perf bench: Add pmu-scan benchmark

The pmu-scan benchmark will repeatedly scan the sysfs to get the
available PMU information.

  $ ./perf bench internals pmu-scan
  # Running 'internals/pmu-scan' benchmark:
  Computing performance of sysfs PMU event scan for 100 times
    Average PMU scanning took: 6850.990 usec (+- 48.445 usec)

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/bench/Build

@@ -15,6 +15,7 @@ perf-y += find-bit-bench.o
 perf-y += inject-buildid.o
 perf-y += evlist-open-close.o
 perf-y += breakpoint.o
+perf-y += pmu-scan.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_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0

tools/perf/bench/pmu-scan.c

@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Benchmark scanning sysfs files for PMU information.
+ *
+ * Copyright 2023 Google LLC.
+ */
+#include <stdio.h>
+#include "bench.h"
+#include "util/debug.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
+#include "util/stat.h"
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/time64.h>
+#include <subcmd/parse-options.h>
+
+static unsigned int iterations = 100;
+
+struct pmu_scan_result {
+	char *name;
+	int nr_aliases;
+	int nr_formats;
+	int nr_caps;
+};
+
+static const struct option options[] = {
+	OPT_UINTEGER('i', "iterations", &iterations,
+		"Number of iterations used to compute average"),
+	OPT_END()
+};
+
+static const char *const bench_usage[] = {
+	"perf bench internals pmu-scan <options>",
+	NULL
+};
+
+static int nr_pmus;
+static struct pmu_scan_result *results;
+
+static int save_result(void)
+{
+	struct perf_pmu *pmu;
+	struct list_head *list;
+	struct pmu_scan_result *r;
+
+	perf_pmu__scan(NULL);
+
+	perf_pmus__for_each_pmu(pmu) {
+		r = realloc(results, (nr_pmus + 1) * sizeof(*r));
+		if (r == NULL)
+			return -ENOMEM;
+
+		results = r;
+		r = results + nr_pmus;
+
+		r->name = strdup(pmu->name);
+		r->nr_caps = pmu->nr_caps;
+
+		r->nr_aliases = 0;
+		list_for_each(list, &pmu->aliases)
+			r->nr_aliases++;
+
+		r->nr_formats = 0;
+		list_for_each(list, &pmu->format)
+			r->nr_formats++;
+
+		pr_debug("pmu[%d] name=%s, nr_caps=%d, nr_aliases=%d, nr_formats=%d\n",
+			nr_pmus, r->name, r->nr_caps, r->nr_aliases, r->nr_formats);
+		nr_pmus++;
+	}
+
+	perf_pmu__destroy();
+	return 0;
+}
+
+static int check_result(void)
+{
+	struct pmu_scan_result *r;
+	struct perf_pmu *pmu;
+	struct list_head *list;
+	int nr;
+
+	for (int i = 0; i < nr_pmus; i++) {
+		r = &results[i];
+		pmu = perf_pmu__find(r->name);
+		if (pmu == NULL) {
+			pr_err("Cannot find PMU %s\n", r->name);
+			return -1;
+		}
+
+		if (pmu->nr_caps != (u32)r->nr_caps) {
+			pr_err("Unmatched number of event caps in %s: expect %d vs got %d\n",
+				pmu->name, r->nr_caps, pmu->nr_caps);
+			return -1;
+		}
+
+		nr = 0;
+		list_for_each(list, &pmu->aliases)
+			nr++;
+		if (nr != r->nr_aliases) {
+			pr_err("Unmatched number of event aliases in %s: expect %d vs got %d\n",
+				pmu->name, r->nr_aliases, nr);
+			return -1;
+		}
+
+		nr = 0;
+		list_for_each(list, &pmu->format)
+			nr++;
+		if (nr != r->nr_formats) {
+			pr_err("Unmatched number of event formats in %s: expect %d vs got %d\n",
+				pmu->name, r->nr_formats, nr);
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static void delete_result(void)
+{
+	for (int i = 0; i < nr_pmus; i++)
+		free(results[i].name);
+	free(results);
+
+	results = NULL;
+	nr_pmus = 0;
+}
+
+static int run_pmu_scan(void)
+{
+	struct stats stats;
+	struct timeval start, end, diff;
+	double time_average, time_stddev;
+	u64 runtime_us;
+	unsigned int i;
+	int ret;
+
+	init_stats(&stats);
+	pr_info("Computing performance of sysfs PMU event scan for %u times\n",
+		iterations);
+
+	if (save_result() < 0) {
+		pr_err("Failed to initialize PMU scan result\n");
+		return -1;
+	}
+
+	for (i = 0; i < iterations; i++) {
+		gettimeofday(&start, NULL);
+		perf_pmu__scan(NULL);
+		gettimeofday(&end, NULL);
+
+		timersub(&end, &start, &diff);
+		runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+		update_stats(&stats, runtime_us);
+
+		ret = check_result();
+		perf_pmu__destroy();
+		if (ret < 0)
+			break;
+	}
+
+	time_average = avg_stats(&stats);
+	time_stddev = stddev_stats(&stats);
+	pr_info("  Average PMU scanning took: %.3f usec (+- %.3f usec)\n",
+		time_average, time_stddev);
+
+	delete_result();
+	return 0;
+}
+
+int bench_pmu_scan(int argc, const char **argv)
+{
+	int err = 0;
+
+	argc = parse_options(argc, argv, options, bench_usage, 0);
+	if (argc) {
+		usage_with_options(bench_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	err = run_pmu_scan();
+
+	return err;
+}

tools/perf/builtin-bench.c

@@ -92,6 +92,7 @@ static struct bench internals_benchmarks[] = {
 	{ "kallsyms-parse", "Benchmark kallsyms parsing",	bench_kallsyms_parse	},
 	{ "inject-build-id", "Benchmark build-id injection",	bench_inject_build_id	},
 	{ "evlist-open-close", "Benchmark evlist open and close",	bench_evlist_open_close	},
+	{ "pmu-scan", "Benchmark sysfs PMU info scanning",	bench_pmu_scan		},
 	{ NULL,		NULL,					NULL			}
 };