selftests/bpf: Allow to benchmark trigger with stacktrace

Adding support to call bpf_get_stackid helper from trigger programs,
so far added for kprobe multi.

Adding the --stacktrace/-g option to enable it.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20260126211837.472802-7-jolsa@kernel.org

Author: olsajiri

tools/testing/selftests/bpf/bench.c

@@ -265,6 +265,7 @@ static const struct argp_option opts[] = {
 	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
 	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
 	{ "quiet", 'q', NULL, 0, "Be more quiet"},
+	{ "stacktrace", 's', NULL, 0, "Get stack trace"},
 	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
 	  "Set of CPUs for producer threads; implies --affinity"},
 	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
@@ -350,6 +351,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 'q':
 		env.quiet = true;
 		break;
+	case 's':
+		env.stacktrace = true;
+		break;
 	case ARG_PROD_AFFINITY_SET:
 		env.affinity = true;
 		if (parse_num_list(arg, &env.prod_cpus.cpus,

tools/testing/selftests/bpf/bench.h

@@ -26,6 +26,7 @@ struct env {
 	bool list;
 	bool affinity;
 	bool quiet;
+	bool stacktrace;
 	int consumer_cnt;
 	int producer_cnt;
 	int nr_cpus;

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

@@ -146,6 +146,7 @@ static void setup_ctx(void)
 	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, true);
 
 	ctx.skel->rodata->batch_iters = args.batch_iters;
+	ctx.skel->rodata->stacktrace = env.stacktrace;
 }
 
 static void load_ctx(void)

tools/testing/selftests/bpf/progs/trigger_bench.c

@@ -25,6 +25,34 @@ static __always_inline void inc_counter(void)
 	__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
 }
 
+volatile const int stacktrace;
+
+typedef __u64 stack_trace_t[128];
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	 __uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, stack_trace_t);
+} stack_heap SEC(".maps");
+
+static __always_inline void do_stacktrace(void *ctx)
+{
+	if (!stacktrace)
+		return;
+
+	__u64 *ptr = bpf_map_lookup_elem(&stack_heap, &(__u32){0});
+
+	if (ptr)
+		bpf_get_stack(ctx, ptr, sizeof(stack_trace_t), 0);
+}
+
+static __always_inline void handle(void *ctx)
+{
+	inc_counter();
+	do_stacktrace(ctx);
+}
+
 SEC("?uprobe")
 int bench_trigger_uprobe(void *ctx)
 {
@@ -81,21 +109,21 @@ int trigger_driver_kfunc(void *ctx)
 SEC("?kprobe/bpf_get_numa_node_id")
 int bench_trigger_kprobe(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?kretprobe/bpf_get_numa_node_id")
 int bench_trigger_kretprobe(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?kprobe.multi/bpf_get_numa_node_id")
 int bench_trigger_kprobe_multi(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
@@ -108,7 +136,7 @@ int bench_kprobe_multi_empty(void *ctx)
 SEC("?kretprobe.multi/bpf_get_numa_node_id")
 int bench_trigger_kretprobe_multi(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
@@ -121,34 +149,34 @@ int bench_kretprobe_multi_empty(void *ctx)
 SEC("?fentry/bpf_get_numa_node_id")
 int bench_trigger_fentry(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?fexit/bpf_get_numa_node_id")
 int bench_trigger_fexit(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?fmod_ret/bpf_modify_return_test_tp")
 int bench_trigger_fmodret(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return -22;
 }
 
 SEC("?tp/bpf_test_run/bpf_trigger_tp")
 int bench_trigger_tp(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }
 
 SEC("?raw_tp/bpf_trigger_tp")
 int bench_trigger_rawtp(void *ctx)
 {
-	inc_counter();
+	handle(ctx);
 	return 0;
 }