Without a PMU perf matches an event against any PMU with the
event. Unfortunately some PMU drivers advertise a "cycles" event which
is typically just a core event. To make perf's behavior consistent,
just look up default events with their designated PMU types.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/builtin-stat.c | 133 +++++++++++++++++++++++++++-----------
 1 file changed, 94 insertions(+), 39 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 303628189004..4615aa3f2b7f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1824,6 +1824,38 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 	return 0;
 }
 
+/* Add given software event to evlist without wildcarding. */
+static int parse_software_event(struct evlist *evlist, const char *event,
+				struct parse_events_error *err)
+{
+	char buf[256];
+
+	snprintf(buf, sizeof(buf), "software/%s,name=%s/", event, event);
+	return parse_events(evlist, buf, err);
+}
+
+/* Add legacy hardware/hardware-cache event to evlist for all core PMUs without wildcarding. */
+static int parse_hardware_event(struct evlist *evlist, const char *event,
+				struct parse_events_error *err)
+{
+	char buf[256];
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+		int ret;
+
+		if (perf_pmus__num_core_pmus() == 1)
+			snprintf(buf, sizeof(buf), "%s/%s,name=%s/", pmu->name, event, event);
+		else
+			snprintf(buf, sizeof(buf), "%s/%s/", pmu->name, event);
+
+		ret = parse_events(evlist, buf, err);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 /*
  * Add default events, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1947,26 +1979,31 @@ static int add_default_events(void)
 
 	if (!evlist->core.nr_entries && !evsel_list->core.nr_entries) {
 		/* No events so add defaults. */
-		if (target__has_cpu(&target))
-			ret = parse_events(evlist, "cpu-clock", &err);
-		else
-			ret = parse_events(evlist, "task-clock", &err);
-		if (ret)
-			goto out;
-
-		ret = parse_events(evlist,
-				"context-switches,"
-				"cpu-migrations,"
-				"page-faults,"
-				"instructions,"
-				"cycles,"
-				"stalled-cycles-frontend,"
-				"stalled-cycles-backend,"
-				"branches,"
-				"branch-misses",
-				&err);
-		if (ret)
-			goto out;
+		const char *sw_events[] = {
+			target__has_cpu(&target) ? "cpu-clock" : "task-clock",
+			"context-switches",
+			"cpu-migrations",
+			"page-faults",
+		};
+		const char *hw_events[] = {
+			"instructions",
+			"cycles",
+			"stalled-cycles-frontend",
+			"stalled-cycles-backend",
+			"branches",
+			"branch-misses",
+		};
+
+		for (size_t i = 0; i < ARRAY_SIZE(sw_events); i++) {
+			ret = parse_software_event(evlist, sw_events[i], &err);
+			if (ret)
+				goto out;
+		}
+		for (size_t i = 0; i < ARRAY_SIZE(hw_events); i++) {
+			ret = parse_hardware_event(evlist, hw_events[i], &err);
+			if (ret)
+				goto out;
+		}
 
 		/*
 		 * Add TopdownL1 metrics if they exist. To minimize
@@ -2008,35 +2045,53 @@ static int add_default_events(void)
 		 * Detailed stats (-d), covering the L1 and last level data
 		 * caches:
 		 */
-		ret = parse_events(evlist,
-				"L1-dcache-loads,"
-				"L1-dcache-load-misses,"
-				"LLC-loads,"
-				"LLC-load-misses",
-				&err);
+		const char *hw_events[] = {
+			"L1-dcache-loads",
+			"L1-dcache-load-misses",
+			"LLC-loads",
+			"LLC-load-misses",
+		};
+
+		for (size_t i = 0; i < ARRAY_SIZE(hw_events); i++) {
+			ret = parse_hardware_event(evlist, hw_events[i], &err);
+			if (ret)
+				goto out;
+		}
 	}
 	if (!ret && detailed_run >=  2) {
 		/*
 		 * Very detailed stats (-d -d), covering the instruction cache
 		 * and the TLB caches:
 		 */
-		ret = parse_events(evlist,
-				"L1-icache-loads,"
-				"L1-icache-load-misses,"
-				"dTLB-loads,"
-				"dTLB-load-misses,"
-				"iTLB-loads,"
-				"iTLB-load-misses",
-				&err);
+		const char *hw_events[] = {
+			"L1-icache-loads",
+			"L1-icache-load-misses",
+			"dTLB-loads",
+			"dTLB-load-misses",
+			"iTLB-loads",
+			"iTLB-load-misses",
+		};
+
+		for (size_t i = 0; i < ARRAY_SIZE(hw_events); i++) {
+			ret = parse_hardware_event(evlist, hw_events[i], &err);
+			if (ret)
+				goto out;
+		}
 	}
 	if (!ret && detailed_run >=  3) {
 		/*
 		 * Very, very detailed stats (-d -d -d), adding prefetch events:
 		 */
-		ret = parse_events(evlist,
-				"L1-dcache-prefetches,"
-				"L1-dcache-prefetch-misses",
-				&err);
+		const char *hw_events[] = {
+			"L1-dcache-prefetches",
+			"L1-dcache-prefetch-misses",
+		};
+
+		for (size_t i = 0; i < ARRAY_SIZE(hw_events); i++) {
+			ret = parse_hardware_event(evlist, hw_events[i], &err);
+			if (ret)
+				goto out;
+		}
 	}
 out:
 	if (!ret) {
@@ -2045,7 +2100,7 @@ static int add_default_events(void)
 			 * Make at least one event non-skippable so fatal errors are visible.
 			 * 'cycles' always used to be default and non-skippable, so use that.
 			 */
-			if (strcmp("cycles", evsel__name(evsel)))
+			if (!evsel__match(evsel, HARDWARE, HW_CPU_CYCLES))
 				evsel->skippable = true;
 		}
 	}
-- 
2.51.0.534.gc79095c0ca-goog