perf bench uprobe: Add benchmark to test uprobe overhead

This just adds the initial "workload", a call to libc's usleep(1000us)
function:

  $ perf stat --null perf bench uprobe all
  # Running uprobe/baseline benchmark...
  # Executed 1000 usleep(1000) calls
       Total time: 1053533 usecs

   1053.533 usecs/op

   Performance counter stats for 'perf bench uprobe all':

         1.061042896 seconds time elapsed

         0.001079000 seconds user
         0.006499000 seconds sys

  $

More entries will be added using a BPF skel to add various uprobes to
the usleep() function.

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/20230719204910.539044-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-bench.txt

@@ -67,6 +67,9 @@ SUBSYSTEM
 'internals'::
 	Benchmark internal perf functionality.
 
+'uprobe'::
+	Benchmark overhead of uprobe + BPF.
+
 'all'::
 	All benchmark subsystems.
 

tools/perf/bench/Build

@@ -16,6 +16,7 @@ perf-y += inject-buildid.o
 perf-y += evlist-open-close.o
 perf-y += breakpoint.o
 perf-y += pmu-scan.o
+perf-y += uprobe.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o

tools/perf/bench/bench.h

@@ -42,6 +42,7 @@ int bench_inject_build_id(int argc, const char **argv);
 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_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"

tools/perf/bench/uprobe.c

@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * uprobe.c
+ *
+ * uprobe benchmarks
+ *
+ *  Copyright (C) 2023, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+#include <linux/time64.h>
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+
+#define LOOPS_DEFAULT 1000
+static int loops = LOOPS_DEFAULT;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_uprobe_usage[] = {
+	"perf bench uprobe <options>",
+	NULL
+};
+
+static int bench_uprobe(int argc, const char **argv)
+{
+	const char *name = "usleep(1000)", *unit = "usec";
+	struct timespec start, end;
+	u64 diff;
+	int i;
+
+	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
+
+	clock_gettime(CLOCK_REALTIME, &start);
+
+	for (i = 0; i < loops; i++) {
+		usleep(USEC_PER_MSEC);
+	}
+
+	clock_gettime(CLOCK_REALTIME, &end);
+
+	diff = end.tv_sec * NSEC_PER_SEC + end.tv_nsec - (start.tv_sec * NSEC_PER_SEC + start.tv_nsec);
+	diff /= NSEC_PER_USEC;
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Executed %'d %s calls\n", loops, name);
+		printf(" %14s: %'" PRIu64 " %ss\n\n", "Total time", diff, unit);
+		printf(" %'.3f %ss/op\n", (double)diff / (double)loops, unit);
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%" PRIu64 "\n", diff);
+		break;
+
+	default:
+		/* reaching here is something of a disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+	}
+
+	return 0;
+}
+
+int bench_uprobe_baseline(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv);
+}

tools/perf/builtin-bench.c

@@ -104,6 +104,11 @@ static struct bench breakpoint_benchmarks[] = {
 	{ NULL,	NULL, NULL },
 };
 
+static struct bench uprobe_benchmarks[] = {
+	{ "baseline",	"Baseline libc usleep(1000) call",	bench_uprobe_baseline,	},
+	{ NULL,	NULL, NULL },
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -123,6 +128,7 @@ static struct collection collections[] = {
 #endif
 	{ "internals",	"Perf-internals benchmarks",			internals_benchmarks	},
 	{ "breakpoint",	"Breakpoint benchmarks",			breakpoint_benchmarks	},
+	{ "uprobe",	"uprobe benchmarks",				uprobe_benchmarks	},
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };