perf bench uprobe empty: Add entry attaching an empty BPF program

Using libbpf and a BPF skel:

  # perf bench uprobe all
  # Running uprobe/baseline benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,055,618 usecs

   1,055.618 usecs/op
  # Running uprobe/empty benchmark...
  # Executed 1,000 usleep(1000) calls
       Total time: 1,057,146 usecs +1,528 to baseline

   1,057.146 usecs/op
  #

Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andre Fredette <anfredet@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Dave Tucker <datucker@redhat.com>
Cc: Derek Barbosa <debarbos@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719204910.539044-5-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Makefile.perf

@@ -1057,6 +1057,7 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
 SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
+SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
 
 $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT):
 	$(Q)$(MKDIR) -p $@

tools/perf/bench/bench.h

@@ -43,6 +43,7 @@ int bench_evlist_open_close(int argc, const char **argv);
 int bench_breakpoint_thread(int argc, const char **argv);
 int bench_breakpoint_enable(int argc, const char **argv);
 int bench_uprobe_baseline(int argc, const char **argv);
+int bench_uprobe_empty(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"

tools/perf/bench/uprobe.c

@@ -24,6 +24,11 @@
 #define LOOPS_DEFAULT 1000
 static int loops = LOOPS_DEFAULT;
 
+enum bench_uprobe {
+        BENCH_UPROBE__BASELINE,
+        BENCH_UPROBE__EMPTY,
+};
+
 static const struct option options[] = {
 	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_END()
@@ -34,6 +39,59 @@ static const char * const bench_uprobe_usage[] = {
 	NULL
 };
 
+#ifdef HAVE_BPF_SKEL
+#include "bpf_skel/bench_uprobe.skel.h"
+
+struct bench_uprobe_bpf *skel;
+
+static int bench_uprobe__setup_bpf_skel(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	int err;
+
+	/* Load and verify BPF application */
+	skel = bench_uprobe_bpf__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load uprobes bench BPF skeleton\n");
+		return -1;
+	}
+
+	err = bench_uprobe_bpf__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	uprobe_opts.func_name = "usleep";
+	skel->links.empty = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.empty,
+							    /*pid=*/-1,
+							    /*binary_path=*/"/lib64/libc.so.6",
+							    /*func_offset=*/0,
+							    /*opts=*/&uprobe_opts);
+	if (!skel->links.empty) {
+		err = -errno;
+		fprintf(stderr, "Failed to attach bench uprobe: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	return err;
+cleanup:
+	bench_uprobe_bpf__destroy(skel);
+	return err;
+}
+
+static void bench_uprobe__teardown_bpf_skel(void)
+{
+	if (skel) {
+		bench_uprobe_bpf__destroy(skel);
+		skel = NULL;
+	}
+}
+#else
+static int bench_uprobe__setup_bpf_skel(void) { return 0; }
+static void bench_uprobe__teardown_bpf_skel(void) {};
+#endif
+
 static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
 {
 	static u64 baseline, previous;
@@ -68,7 +126,7 @@ static int bench_uprobe_format__default_fprintf(const char *name, const char *un
 	return printed + 1;
 }
 
-static int bench_uprobe(int argc, const char **argv)
+static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench)
 {
 	const char *name = "usleep(1000)", *unit = "usec";
 	struct timespec start, end;
@@ -77,7 +135,10 @@ static int bench_uprobe(int argc, const char **argv)
 
 	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
 
-	clock_gettime(CLOCK_REALTIME, &start);
+	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel() < 0)
+		return 0;
+
+        clock_gettime(CLOCK_REALTIME, &start);
 
 	for (i = 0; i < loops; i++) {
 		usleep(USEC_PER_MSEC);
@@ -103,10 +164,18 @@ static int bench_uprobe(int argc, const char **argv)
 		exit(1);
 	}
 
+	if (bench != BENCH_UPROBE__BASELINE)
+		bench_uprobe__teardown_bpf_skel();
+
 	return 0;
 }
 
 int bench_uprobe_baseline(int argc, const char **argv)
 {
-	return bench_uprobe(argc, argv);
+	return bench_uprobe(argc, argv, BENCH_UPROBE__BASELINE);
+}
+
+int bench_uprobe_empty(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY);
 }

tools/perf/builtin-bench.c

@@ -105,7 +105,8 @@ static struct bench breakpoint_benchmarks[] = {
 };
 
 static struct bench uprobe_benchmarks[] = {
-	{ "baseline",	"Baseline libc usleep(1000) call",	bench_uprobe_baseline,	},
+	{ "baseline",	"Baseline libc usleep(1000) call",				bench_uprobe_baseline,	},
+	{ "empty",	"Attach empty BPF prog to uprobe on usleep, system wide",	bench_uprobe_empty,	},
 	{ NULL,	NULL, NULL },
 };
 

tools/perf/util/bpf_skel/bench_uprobe.bpf.c

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2023 Red Hat
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+SEC("uprobe")
+int BPF_UPROBE(empty)
+{
+       return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";