selftests/bpf: add batched tp/raw_tp/fmodret tests

Utilize bpf_modify_return_test_tp() kfunc to have a fast way to trigger
tp/raw_tp/fmodret programs from another BPF program, which gives us
comparable batched benchmarks to (batched) kprobe/fentry benchmarks.

We don't switch kprobe/fentry batched benchmarks to this kfunc to make
bench tool usable on older kernels as well.

Signed-off-by: Andrii Nakryiko <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

tools/testing/selftests/bpf/bench.c

···
 extern const struct bench bench_trig_kretprobe_multi;
 extern const struct bench bench_trig_fentry;
 extern const struct bench bench_trig_fexit;
+extern const struct bench bench_trig_fmodret;
+extern const struct bench bench_trig_tp;
+extern const struct bench bench_trig_rawtp;
 
 /* uprobe/uretprobe benchmarks */
 extern const struct bench bench_trig_uprobe_nop;
···
 	&bench_trig_kretprobe_multi,
 	&bench_trig_fentry,
 	&bench_trig_fexit,
+	&bench_trig_fmodret,
+	&bench_trig_tp,
+	&bench_trig_rawtp,
 	/* uprobes */
 	&bench_trig_uprobe_nop,
 	&bench_trig_uretprobe_nop,

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

···
 	attach_bpf(ctx.skel->progs.bench_trigger_fexit);
 }
 
+static void trigger_fmodret_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fmodret, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
+	attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
+}
+
+static void trigger_tp_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_tp, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
+	attach_bpf(ctx.skel->progs.bench_trigger_tp);
+}
+
+static void trigger_rawtp_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_rawtp, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
+	attach_bpf(ctx.skel->progs.bench_trigger_rawtp);
+}
+
 /* make sure call is not inlined and not avoided by compiler, so __weak and
  * inline asm volatile in the body of the function
  *
···
 BENCH_TRIG_KERNEL(kretprobe_multi, "kretprobe-multi");
 BENCH_TRIG_KERNEL(fentry, "fentry");
 BENCH_TRIG_KERNEL(fexit, "fexit");
+BENCH_TRIG_KERNEL(fmodret, "fmodret");
+BENCH_TRIG_KERNEL(tp, "tp");
+BENCH_TRIG_KERNEL(rawtp, "rawtp");
 
 /* uprobe benchmarks */
 #define BENCH_TRIG_USERMODE(KIND, PRODUCER, NAME)			\

tools/testing/selftests/bpf/benchs/run_bench_trigger.sh

···
 
 def_tests=( \
 	usermode-count kernel-count syscall-count \
-	fentry fexit \
+	fentry fexit fmodret \
+	rawtp tp \
 	kprobe kprobe-multi \
 	kretprobe kretprobe-multi \
 )

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

···
 	return 0;
 }
 
+extern int bpf_modify_return_test_tp(int nonce) __ksym __weak;
+
+SEC("?raw_tp")
+int trigger_driver_kfunc(void *ctx)
+{
+	int i;
+
+	for (i = 0; i < batch_iters; i++)
+		(void)bpf_modify_return_test_tp(0); /* attach point for benchmarking */
+
+	return 0;
+}
+
 SEC("?kprobe/bpf_get_numa_node_id")
 int bench_trigger_kprobe(void *ctx)
 {
···
 
 SEC("?fexit/bpf_get_numa_node_id")
 int bench_trigger_fexit(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?fmod_ret/bpf_modify_return_test_tp")
+int bench_trigger_fmodret(void *ctx)
+{
+	inc_counter();
+	return -22;
+}
+
+SEC("?tp/bpf_test_run/bpf_trigger_tp")
+int bench_trigger_tp(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?raw_tp/bpf_trigger_tp")
+int bench_trigger_rawtp(void *ctx)
 {
 	inc_counter();
 	return 0;