selftests/bpf: Add BPF batch-timing library

Add a reusable timing library for BPF benchmarks that need to measure
BPF program execution time.

The BPF side (progs/bench_bpf_timing.bpf.h) provides per-CPU sample
arrays and BENCH_BPF_LOOP(), a macro that brackets batch_iters
iterations with bpf_ktime_get_ns() reads and records the elapsed time.
One extra untimed iteration runs afterward for output validation.

The userspace side (benchs/bench_bpf_timing.c) collects samples from
the skeleton BSS, computes percentile statistics, and auto-calibrates
batch_iters to target ~10 ms per batch.

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Link: https://lore.kernel.org/r/20260427232313.1582588-3-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/Makefile

@@ -906,6 +906,7 @@ $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
 $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h
 $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h
 $(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h
+$(OUTPUT)/bench_bpf_timing.o: bench_bpf_timing.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -928,6 +929,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_bpf_crypto.o \
 		 $(OUTPUT)/bench_sockmap.o \
 		 $(OUTPUT)/bench_lpm_trie_map.o \
+		 $(OUTPUT)/bench_bpf_timing.o \
 		 $(OUTPUT)/usdt_1.o \
 		 $(OUTPUT)/usdt_2.o \
 		 #

tools/testing/selftests/bpf/bench_bpf_timing.h

@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#ifndef __BENCH_BPF_TIMING_H__
+#define __BENCH_BPF_TIMING_H__
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include "bench.h"
+
+#ifndef BENCH_NR_SAMPLES
+#define BENCH_NR_SAMPLES	4096
+#endif
+#ifndef BENCH_NR_CPUS
+#define BENCH_NR_CPUS		256
+#endif
+
+typedef void (*bpf_bench_run_fn)(void *ctx);
+
+struct bpf_bench_timing {
+	__u64 (*samples)[BENCH_NR_SAMPLES];	/* skel->bss->timing_samples */
+	__u32 *idx;				/* skel->bss->timing_idx */
+	volatile __u32 *timing_enabled;		/* &skel->bss->timing_enabled */
+	volatile __u32 *batch_iters_bss;	/* &skel->bss->batch_iters */
+	__u32 batch_iters;
+	__u32 target_samples;
+	__u32 nr_cpus;
+	int warmup_ticks;
+	bool done;
+	bool machine_readable;
+};
+
+#define BENCH_TIMING_INIT(t, skel, iters) do {				\
+	(t)->samples = (skel)->bss->timing_samples;			\
+	(t)->idx = (skel)->bss->timing_idx;				\
+	(t)->timing_enabled = &(skel)->bss->timing_enabled;		\
+	(t)->batch_iters_bss = &(skel)->bss->batch_iters;		\
+	(t)->batch_iters = (iters);					\
+	(t)->target_samples = 200;					\
+	(t)->nr_cpus = env.nr_cpus;					\
+	(t)->warmup_ticks = 0;						\
+	(t)->done = false;						\
+	(t)->machine_readable = false;					\
+} while (0)
+
+void bpf_bench_timing_measure(struct bpf_bench_timing *t, struct bench_res *res);
+void bpf_bench_timing_report(struct bpf_bench_timing *t, const char *name, const char *desc);
+void bpf_bench_calibrate(struct bpf_bench_timing *t, bpf_bench_run_fn run_fn, void *ctx);
+
+#endif /* __BENCH_BPF_TIMING_H__ */

tools/testing/selftests/bpf/benchs/bench_bpf_timing.c

@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include "bench_bpf_timing.h"
+#include "bpf_util.h"
+
+struct timing_stats {
+	double min, max;
+	double median, p99;
+	double mean, stddev;
+	int count;
+};
+
+static int cmp_double(const void *a, const void *b)
+{
+	double da = *(const double *)a;
+	double db = *(const double *)b;
+
+	if (da < db)
+		return -1;
+	if (da > db)
+		return 1;
+	return 0;
+}
+
+static double percentile(const double *sorted, int n, double pct)
+{
+	int idx = (int)(n * pct / 100.0);
+
+	if (idx >= n)
+		idx = n - 1;
+	return sorted[idx];
+}
+
+static int collect_samples(struct bpf_bench_timing *t,
+			   double *out, int max_out)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	__u32 timed_iters = t->batch_iters;
+	int total = 0;
+
+	if (nr_cpus > BENCH_NR_CPUS)
+		nr_cpus = BENCH_NR_CPUS;
+
+	for (unsigned int cpu = 0; cpu < nr_cpus; cpu++) {
+		__u32 count = t->idx[cpu];
+
+		if (count > BENCH_NR_SAMPLES)
+			count = BENCH_NR_SAMPLES;
+
+		for (__u32 i = 0; i < count && total < max_out; i++) {
+			__u64 sample = t->samples[cpu][i];
+
+			if (sample == 0)
+				continue;
+			out[total++] = (double)sample / timed_iters;
+		}
+	}
+
+	qsort(out, total, sizeof(double), cmp_double);
+	return total;
+}
+
+static void compute_stats(const double *sorted, int n,
+			  struct timing_stats *s)
+{
+	double sum = 0, var_sum = 0;
+
+	memset(s, 0, sizeof(*s));
+	s->count = n;
+
+	if (n == 0)
+		return;
+
+	s->min    = sorted[0];
+	s->max    = sorted[n - 1];
+	s->median = sorted[n / 2];
+	s->p99    = percentile(sorted, n, 99);
+
+	for (int i = 0; i < n; i++)
+		sum += sorted[i];
+	s->mean = sum / n;
+
+	for (int i = 0; i < n; i++) {
+		double d = sorted[i] - s->mean;
+
+		var_sum += d * d;
+	}
+	s->stddev = n > 1 ? sqrt(var_sum / (n - 1)) : 0;
+}
+
+void bpf_bench_timing_measure(struct bpf_bench_timing *t, struct bench_res *res)
+{
+	unsigned int nr_cpus;
+	__u32 total_samples;
+	int i;
+
+	t->warmup_ticks++;
+
+	if (t->warmup_ticks < env.warmup_sec)
+		return;
+
+	if (t->warmup_ticks == env.warmup_sec) {
+		*t->timing_enabled = 1;
+		return;
+	}
+
+	nr_cpus = bpf_num_possible_cpus();
+	if (nr_cpus > BENCH_NR_CPUS)
+		nr_cpus = BENCH_NR_CPUS;
+
+	total_samples = 0;
+	for (i = 0; i < (int)nr_cpus; i++) {
+		__u32 cnt = t->idx[i];
+
+		if (cnt > BENCH_NR_SAMPLES)
+			cnt = BENCH_NR_SAMPLES;
+		total_samples += cnt;
+	}
+
+	if (total_samples >= (__u32)env.producer_cnt * t->target_samples && !t->done) {
+		t->done = true;
+		*t->timing_enabled = 0;
+		bench_force_done();
+	}
+}
+
+void bpf_bench_timing_report(struct bpf_bench_timing *t, const char *name, const char *description)
+{
+	int max_out = BENCH_NR_CPUS * BENCH_NR_SAMPLES;
+	struct timing_stats s;
+	double *all;
+	int total;
+
+	all = calloc(max_out, sizeof(*all));
+	if (!all) {
+		fprintf(stderr, "failed to allocate timing buffer\n");
+		return;
+	}
+
+	total = collect_samples(t, all, max_out);
+
+	if (total == 0) {
+		printf("No timing samples collected.\n");
+		free(all);
+		return;
+	}
+
+	compute_stats(all, total, &s);
+
+	if (t->machine_readable) {
+		printf("RESULT scenario=%s samples=%d median=%.2f stddev=%.2f cv=%.2f min=%.2f "
+		       "p99=%.2f max=%.2f\n", name, total, s.median, s.stddev,
+		       s.mean > 0 ? s.stddev / s.mean * 100.0 : 0.0, s.min, s.p99, s.max);
+	} else {
+		printf("%s: median %.2f ns/op, stddev %.2f, p99 %.2f (%d samples)\n", name,
+		       s.median, s.stddev, s.p99, total);
+	}
+
+	free(all);
+}
+
+#define CALIBRATE_SEED_BATCH	100
+#define CALIBRATE_MIN_BATCH	100
+#define CALIBRATE_MAX_BATCH	10000000
+#define CALIBRATE_TARGET_MS	10
+#define CALIBRATE_RUNS		5
+#define PROPORTIONALITY_TOL	0.05	/* 5% */
+
+static void reset_timing(struct bpf_bench_timing *t)
+{
+	*t->timing_enabled = 0;
+	memset(t->samples, 0, sizeof(__u64) * BENCH_NR_CPUS * BENCH_NR_SAMPLES);
+	memset(t->idx, 0, sizeof(__u32) * BENCH_NR_CPUS);
+}
+
+static __u64 measure_elapsed(struct bpf_bench_timing *t, bpf_bench_run_fn run_fn, void *run_ctx,
+			     __u32 iters, int runs)
+{
+	__u64 buf[CALIBRATE_RUNS];
+	int n = 0, i, j;
+
+	reset_timing(t);
+	*t->batch_iters_bss = iters;
+	*t->timing_enabled = 1;
+
+	for (i = 0; i < runs; i++)
+		run_fn(run_ctx);
+
+	*t->timing_enabled = 0;
+
+	for (i = 0; i < BENCH_NR_CPUS && n < runs; i++) {
+		__u32 cnt = t->idx[i];
+
+		for (j = 0; j < (int)cnt && n < runs; j++)
+			buf[n++] = t->samples[i][j];
+	}
+
+	if (n == 0)
+		return 0;
+
+	for (i = 1; i < n; i++) {
+		__u64 key = buf[i];
+
+		j = i - 1;
+		while (j >= 0 && buf[j] > key) {
+			buf[j + 1] = buf[j];
+			j--;
+		}
+		buf[j + 1] = key;
+	}
+
+	return buf[n / 2];
+}
+
+static __u32 compute_batch_iters(__u64 per_op_ns)
+{
+	__u64 target_ns = (__u64)CALIBRATE_TARGET_MS * 1000000ULL;
+	__u32 iters;
+
+	if (per_op_ns == 0)
+		return CALIBRATE_MIN_BATCH;
+
+	iters = target_ns / per_op_ns;
+
+	if (iters < CALIBRATE_MIN_BATCH)
+		iters = CALIBRATE_MIN_BATCH;
+	if (iters > CALIBRATE_MAX_BATCH)
+		iters = CALIBRATE_MAX_BATCH;
+
+	return iters;
+}
+
+void bpf_bench_calibrate(struct bpf_bench_timing *t, bpf_bench_run_fn run_fn, void *run_ctx)
+{
+	__u64 elapsed, per_op_ns;
+	__u64 time_n, time_2n;
+	double ratio;
+
+	elapsed = measure_elapsed(t, run_fn, run_ctx, CALIBRATE_SEED_BATCH, CALIBRATE_RUNS);
+	if (elapsed == 0) {
+		fprintf(stderr, "calibration: no timing samples, using default\n");
+		t->batch_iters = 10000;
+		*t->batch_iters_bss = t->batch_iters;
+		reset_timing(t);
+		return;
+	}
+
+	per_op_ns = elapsed / CALIBRATE_SEED_BATCH;
+	t->batch_iters = compute_batch_iters(per_op_ns);
+
+	time_n = measure_elapsed(t, run_fn, run_ctx, t->batch_iters, CALIBRATE_RUNS);
+	time_2n = measure_elapsed(t, run_fn, run_ctx, t->batch_iters * 2, CALIBRATE_RUNS);
+
+	if (time_n > 0 && time_2n > 0) {
+		ratio = (double)time_2n / (double)time_n;
+
+		if (fabs(ratio - 2.0) / 2.0 > PROPORTIONALITY_TOL)
+			fprintf(stderr,
+				"WARNING: proportionality check failed (2N/N ratio=%.3f, "
+				"expected=2.000, error=%.1f%%)\n  System noise may be affecting "
+				"results.\n",
+				ratio, fabs(ratio - 2.0) / 2.0 * 100.0);
+	}
+
+	*t->batch_iters_bss = t->batch_iters;
+	reset_timing(t);
+}

tools/testing/selftests/bpf/progs/bench_bpf_timing.bpf.h

@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#ifndef __BENCH_BPF_TIMING_BPF_H__
+#define __BENCH_BPF_TIMING_BPF_H__
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf_may_goto.h>
+
+#ifndef BENCH_NR_SAMPLES
+#define BENCH_NR_SAMPLES	4096
+#endif
+#ifndef BENCH_NR_CPUS
+#define BENCH_NR_CPUS		256
+#endif
+#define BENCH_CPU_MASK		(BENCH_NR_CPUS - 1)
+
+__u64 timing_samples[BENCH_NR_CPUS][BENCH_NR_SAMPLES];
+__u32 timing_idx[BENCH_NR_CPUS];
+
+volatile __u32 batch_iters;
+volatile __u32 timing_enabled;
+
+static __always_inline void bench_record_sample(__u64 elapsed_ns)
+{
+	__u32 cpu, idx;
+
+	if (!timing_enabled)
+		return;
+
+	cpu = bpf_get_smp_processor_id() & BENCH_CPU_MASK;
+	idx = timing_idx[cpu];
+
+	if (idx >= BENCH_NR_SAMPLES)
+		return;
+
+	timing_samples[cpu][idx] = elapsed_ns;
+	timing_idx[cpu] = idx + 1;
+}
+
+/*
+ * @body:  expression to time; return value (int) stored in __bench_result.
+ * @reset: undo body's side-effects so each iteration starts identically.
+ *         May reference __bench_result.  Use ({}) for empty reset.
+ *
+ * Runs batch_iters timed iterations, then one untimed iteration whose
+ * return value the macro evaluates to (for validation).
+ */
+#define BENCH_BPF_LOOP(body, reset) ({					\
+	__u64 __bench_start = bpf_ktime_get_ns();			\
+	__u32 __bench_i;						\
+	int __bench_result;						\
+									\
+	for (__bench_i = 0;						\
+	     __bench_i < batch_iters && can_loop;			\
+	     __bench_i++) {						\
+		__bench_result = (body);				\
+		reset;							\
+	}								\
+									\
+	bench_record_sample(bpf_ktime_get_ns() - __bench_start);	\
+									\
+	__bench_result = (body);					\
+	__bench_result;							\
+})
+
+#endif /* __BENCH_BPF_TIMING_BPF_H__ */