perf test: Improve pmu event metric testing

Break pmu-events test into 2 and add a test to verify that all pmu
metric expressions simply parse. Try to parse all metric ids/events,
skip/warn if metrics for the current architecture fail to parse. To
support warning for a skip, and an ability for a subtest to describe why
it skips.

Tested on power9, skylakex, haswell, broadwell, westmere, sandybridge and
ivybridge.

May skip/warn on other architectures if metrics are invalid. In
particular s390 is untested, but its expressions are trivial. The
untested architectures with expressions are power8, cascadelakex,
tremontx, skylake, jaketown, ivytown and variants of haswell and
broadwell.

v3. addresses review comments from John Garry <john.garry@huawei.com>,
Jiri Olsa <jolsa@redhat.com> and Arnaldo Carvalho de Melo
<acme@kernel.org>.
v2. changes the commit message as event parsing errors no longer cause
the test to fail.

Committer notes:

Check the return value of strtod() to fix the build in systems where
that function is declared with attribute warn_unused_result.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200513212933.41273-1-irogers@google.com
[ split from a larger patch ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/tests/builtin-test.c

@@ -75,6 +75,13 @@ static struct test generic_tests[] = {
 	{
 		.desc = "PMU events",
 		.func = test__pmu_events,
+		.subtest = {
+			.skip_if_fail	= false,
+			.get_nr		= test__pmu_events_subtest_get_nr,
+			.get_desc	= test__pmu_events_subtest_get_desc,
+			.skip_reason	= test__pmu_events_subtest_skip_reason,
+		},
+
 	},
 	{
 		.desc = "DSO data read",

tools/perf/tests/pmu-events.c

 // SPDX-License-Identifier: GPL-2.0
+#include "math.h"
 #include "parse-events.h"
 #include "pmu.h"
 #include "tests.h"
@@ -8,6 +9,9 @@
 #include <linux/zalloc.h>
 #include "debug.h"
 #include "../pmu-events/pmu-events.h"
+#include "util/evlist.h"
+#include "util/expr.h"
+#include "util/parse-events.h"
 
 struct perf_pmu_test_event {
 	struct pmu_event event;
@@ -144,7 +148,7 @@ static struct pmu_events_map *__test_pmu_get_events_map(void)
 }
 
 /* Verify generated events from pmu-events.c is as expected */
-static int __test_pmu_event_table(void)
+static int test_pmu_event_table(void)
 {
 	struct pmu_events_map *map = __test_pmu_get_events_map();
 	struct pmu_event *table;
@@ -347,14 +351,11 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 	return res;
 }
 
-int test__pmu_events(struct test *test __maybe_unused,
-		     int subtest __maybe_unused)
+
+static int test_aliases(void)
 {
 	struct perf_pmu *pmu = NULL;
 
-	if (__test_pmu_event_table())
-		return -1;
-
 	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		int count = 0;
 
@@ -377,3 +378,162 @@ int test__pmu_events(struct test *test __maybe_unused,
 
 	return 0;
 }
+
+static bool is_number(const char *str)
+{
+	char *end_ptr;
+	double v;
+
+	errno = 0;
+	v = strtod(str, &end_ptr);
+	(void)v; // We're not interested in this value, only if it is valid
+	return errno == 0 && end_ptr != str;
+}
+
+static int check_parse_id(const char *id, bool same_cpu, struct pmu_event *pe)
+{
+	struct parse_events_error error;
+	struct evlist *evlist;
+	int ret;
+
+	/* Numbers are always valid. */
+	if (is_number(id))
+		return 0;
+
+	evlist = evlist__new();
+	memset(&error, 0, sizeof(error));
+	ret = parse_events(evlist, id, &error);
+	if (ret && same_cpu) {
+		pr_warning("Parse event failed metric '%s' id '%s' expr '%s'\n",
+			pe->metric_name, id, pe->metric_expr);
+		pr_warning("Error string '%s' help '%s'\n", error.str,
+			error.help);
+	} else if (ret) {
+		pr_debug3("Parse event failed, but for an event that may not be supported by this CPU.\nid '%s' metric '%s' expr '%s'\n",
+			  id, pe->metric_name, pe->metric_expr);
+		ret = 0;
+	}
+	evlist__delete(evlist);
+	free(error.str);
+	free(error.help);
+	free(error.first_str);
+	free(error.first_help);
+	return ret;
+}
+
+static void expr_failure(const char *msg,
+			 const struct pmu_events_map *map,
+			 const struct pmu_event *pe)
+{
+	pr_debug("%s for map %s %s %s\n",
+		msg, map->cpuid, map->version, map->type);
+	pr_debug("On metric %s\n", pe->metric_name);
+	pr_debug("On expression %s\n", pe->metric_expr);
+}
+
+static int test_parsing(void)
+{
+	struct pmu_events_map *cpus_map = perf_pmu__find_map(NULL);
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+	int i, j, k;
+	const char **ids;
+	int idnum;
+	int ret = 0;
+	struct expr_parse_ctx ctx;
+	double result;
+
+	i = 0;
+	for (;;) {
+		map = &pmu_events_map[i++];
+		if (!map->table)
+			break;
+		j = 0;
+		for (;;) {
+			pe = &map->table[j++];
+			if (!pe->name && !pe->metric_group && !pe->metric_name)
+				break;
+			if (!pe->metric_expr)
+				continue;
+			if (expr__find_other(pe->metric_expr, NULL,
+						&ids, &idnum, 0) < 0) {
+				expr_failure("Parse other failed", map, pe);
+				ret++;
+				continue;
+			}
+			expr__ctx_init(&ctx);
+
+			/*
+			 * Add all ids with a made up value. The value may
+			 * trigger divide by zero when subtracted and so try to
+			 * make them unique.
+			 */
+			for (k = 0; k < idnum; k++)
+				expr__add_id(&ctx, ids[k], k + 1);
+
+			for (k = 0; k < idnum; k++) {
+				if (check_parse_id(ids[k], map == cpus_map, pe))
+					ret++;
+			}
+
+			if (expr__parse(&result, &ctx, pe->metric_expr, 0)) {
+				expr_failure("Parse failed", map, pe);
+				ret++;
+			}
+			for (k = 0; k < idnum; k++)
+				zfree(&ids[k]);
+			free(ids);
+		}
+	}
+	/* TODO: fail when not ok */
+	return ret == 0 ? TEST_OK : TEST_SKIP;
+}
+
+static const struct {
+	int (*func)(void);
+	const char *desc;
+} pmu_events_testcase_table[] = {
+	{
+		.func = test_pmu_event_table,
+		.desc = "PMU event table sanity",
+	},
+	{
+		.func = test_aliases,
+		.desc = "PMU event map aliases",
+	},
+	{
+		.func = test_parsing,
+		.desc = "Parsing of PMU event table metrics",
+	},
+};
+
+const char *test__pmu_events_subtest_get_desc(int subtest)
+{
+	if (subtest < 0 ||
+	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
+		return NULL;
+	return pmu_events_testcase_table[subtest].desc;
+}
+
+const char *test__pmu_events_subtest_skip_reason(int subtest)
+{
+	if (subtest < 0 ||
+	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
+		return NULL;
+	if (pmu_events_testcase_table[subtest].func != test_parsing)
+		return NULL;
+	return "some metrics failed";
+}
+
+int test__pmu_events_subtest_get_nr(void)
+{
+	return (int)ARRAY_SIZE(pmu_events_testcase_table);
+}
+
+int test__pmu_events(struct test *test __maybe_unused, int subtest)
+{
+	if (subtest < 0 ||
+	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
+		return TEST_FAIL;
+	return pmu_events_testcase_table[subtest].func();
+}

tools/perf/tests/tests.h

@@ -51,6 +51,9 @@ int test__perf_evsel__tp_sched_test(struct test *test, int subtest);
 int test__syscall_openat_tp_fields(struct test *test, int subtest);
 int test__pmu(struct test *test, int subtest);
 int test__pmu_events(struct test *test, int subtest);
+const char *test__pmu_events_subtest_get_desc(int subtest);
+const char *test__pmu_events_subtest_skip_reason(int subtest);
+int test__pmu_events_subtest_get_nr(void);
 int test__attr(struct test *test, int subtest);
 int test__dso_data(struct test *test, int subtest);
 int test__dso_data_cache(struct test *test, int subtest);