perf parse-events: Restrict core PMU bypass to --cputype option

Commit b1c5efbfd92e ("perf parse-events: Remove hard coded legacy hardware
and cache parsing") introduced a bypass to PMU filtering to prevent uncore
PMUs from being filtered out during event parsing, which was required for
resolving `duration_time` and `uncore_freq` when running with `--cputype`.
However, this bypass was active whenever `pmu_filter` was set, which also
incorrectly bypassed filtering for the `--pmu-filter` option.

Introduce a `cputype_filter` boolean flag in `parse_events_state` and
`parse_events_option_args` to distinguish filtering initiated by
`--cputype` from that initiated by `--pmu-filter`. Restrict the core-only
check in `parse_events__filter_pmu()` to when `cputype_filter` is true.

Fixes: b1c5efbfd92e ("perf parse-events: Remove hard coded legacy hardware and cache parsing")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

5 files changed, 53 insertions, 29 deletions

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8c7b299a55db..69bfa2a723b2 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1262,7 +1262,8 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
 		     struct expr_parse_ctx *ids, const char *modifier,
 		     bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
 		     struct evlist **out_evlist,
-		     const char *filter_pmu)
+		     const char *filter_pmu,
+		     bool cputype_filter)
 {
 	struct parse_events_error parse_error;
 	struct evlist *parsed_evlist;
@@ -1317,7 +1318,9 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
 	pr_debug("Parsing metric events '%s'\n", events.buf);
 	parse_events_error__init(&parse_error);
 	ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
-			     &parse_error, fake_pmu, /*warn_if_reordered=*/false,
+			     cputype_filter,
+			     &parse_error, fake_pmu,
+			     /*warn_if_reordered=*/false,
 			     /*fake_tp=*/false);
 	if (ret) {
 		parse_events_error__print(&parse_error, events.buf);
@@ -1382,7 +1385,7 @@ static struct evsel *pick_display_evsel(struct list_head *metric_list,
 }
 
 static int parse_groups(struct evlist *perf_evlist,
-			const char *pmu, const char *str,
+			const char *pmu, bool cputype_filter, const char *str,
 			bool metric_no_group,
 			bool metric_no_merge,
 			bool metric_no_threshold,
@@ -1420,7 +1423,8 @@ static int parse_groups(struct evlist *perf_evlist,
 					/*group_events=*/false,
 					tool_events,
 					&combined_evlist,
-					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
+					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu,
+					cputype_filter);
 		}
 		if (combined)
 			expr__ctx_free(combined);
@@ -1476,7 +1480,8 @@ static int parse_groups(struct evlist *perf_evlist,
 		if (!metric_evlist) {
 			ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
 					m->group_events, tool_events, &m->evlist,
-					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
+					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu,
+					cputype_filter);
 			if (ret)
 				goto out;
 
@@ -1543,6 +1548,7 @@ static int parse_groups(struct evlist *perf_evlist,
 	if (combined_evlist) {
 		evlist__splice_list_tail(perf_evlist, &evlist__core(combined_evlist)->entries);
 		evlist__put(combined_evlist);
+		combined_evlist = NULL;
 	}
 
 	list_for_each_entry(m, &metric_list, nd) {
@@ -1551,12 +1557,15 @@ static int parse_groups(struct evlist *perf_evlist,
 	}
 
 out:
+	if (combined_evlist)
+		evlist__put(combined_evlist);
 	metricgroup__free_metrics(&metric_list);
 	return ret;
 }
 
 int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *pmu,
+			      bool cputype_filter,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,
@@ -1570,16 +1579,17 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 	if (hardware_aware_grouping)
 		pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n");
 
-	return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge,
+	return parse_groups(perf_evlist, pmu, cputype_filter, str, metric_no_group, metric_no_merge,
 			    metric_no_threshold, user_requested_cpu_list, system_wide,
 			    /*fake_pmu=*/false, table);
 }
 
 int metricgroup__parse_groups_test(struct evlist *evlist,
 				   const struct pmu_metrics_table *table,
-				   const char *str)
+				   const char *str,
+				   bool cputype_filter)
 {
-	return parse_groups(evlist, "all", str,
+	return parse_groups(evlist, "all", cputype_filter, str,
 			    /*metric_no_group=*/false,
 			    /*metric_no_merge=*/false,
 			    /*metric_no_threshold=*/false,
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 4be6bfc13c46..6a66f14dd01b 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -71,6 +71,7 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 bool create);
 int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *pmu,
+			      bool cputype_filter,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,
@@ -80,7 +81,8 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      bool hardware_aware_grouping);
 int metricgroup__parse_groups_test(struct evlist *evlist,
 				   const struct pmu_metrics_table *table,
-				   const char *str);
+				   const char *str,
+				   bool cputype_filter);
 
 int metricgroup__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				 void *data);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 194bc94dfc1e..cc7ad331a49f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -429,6 +429,9 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	if (parse_state->pmu_filter == NULL)
 		return false;
 
+	if (parse_state->cputype_filter && !pmu->is_core)
+		return false;
+
 	return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
 }
 
@@ -2288,18 +2291,20 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list)
 	return (idx_changed || num_leaders != orig_num_leaders) ? 1 : 0;
 }
 
-int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
+int __parse_events(struct evlist *evlist, const char *str,
+		   const char *pmu_filter, bool cputype_filter,
 		   struct parse_events_error *err, bool fake_pmu,
 		   bool warn_if_reordered, bool fake_tp)
 {
 	struct parse_events_state parse_state = {
-		.list	  = LIST_HEAD_INIT(parse_state.list),
-		.idx	  = evlist__nr_entries(evlist),
-		.error	  = err,
-		.stoken	  = PE_START_EVENTS,
-		.fake_pmu = fake_pmu,
-		.fake_tp  = fake_tp,
-		.pmu_filter = pmu_filter,
+		.list			= LIST_HEAD_INIT(parse_state.list),
+		.idx			= evlist__nr_entries(evlist),
+		.error			= err,
+		.stoken			= PE_START_EVENTS,
+		.fake_pmu		= fake_pmu,
+		.fake_tp		= fake_tp,
+		.pmu_filter		= pmu_filter,
+		.cputype_filter		= cputype_filter,
 		.match_legacy_cache_terms = true,
 	};
 	int ret, ret2;
@@ -2312,15 +2317,15 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 	}
 
 	ret2 = parse_events__sort_events_and_fix_groups(&parse_state.list);
-	if (ret2 < 0)
-		return ret;
+	if (ret2 < 0 && !ret)
+		ret = ret2;
 
 	/*
 	 * Add list to the evlist even with errors to allow callers to clean up.
 	 */
 	evlist__splice_list_tail(evlist, &parse_state.list);
 
-	if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus) {
+	if (ret2 > 0 && warn_if_reordered && !parse_state.wild_card_pmus) {
 		evlist__uniquify_evsel_names(evlist, &stat_config);
 		pr_warning("WARNING: events were regrouped to match PMUs\n");
 
@@ -2518,8 +2523,9 @@ int parse_events_option(const struct option *opt, const char *str,
 	int ret;
 
 	parse_events_error__init(&err);
-	ret = __parse_events(*args->evlistp, str, args->pmu_filter, &err,
-			     /*fake_pmu=*/false, /*warn_if_reordered=*/true,
+	ret = __parse_events(*args->evlistp, str, args->pmu_filter,
+			     args->cputype_filter, &err, /*fake_pmu=*/false,
+			     /*warn_if_reordered=*/true,
 			     /*fake_tp=*/false);
 
 	if (ret) {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 3577ab213730..b14c832b03a1 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -26,20 +26,23 @@ const char *event_type(size_t type);
 struct parse_events_option_args {
 	struct evlist **evlistp;
 	const char *pmu_filter;
+	bool cputype_filter;
 };
 int parse_events_option(const struct option *opt, const char *str, int unset);
 int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset);
-__attribute__((nonnull(1, 2, 4)))
-int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
-		   struct parse_events_error *error, bool fake_pmu,
-		   bool warn_if_reordered, bool fake_tp);
+__attribute__((nonnull(1, 2, 5))) int
+__parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
+	       bool cputype_filter, struct parse_events_error *error,
+	       bool fake_pmu, bool warn_if_reordered, bool fake_tp);
 
 __attribute__((nonnull(1, 2, 3)))
 static inline int parse_events(struct evlist *evlist, const char *str,
 			       struct parse_events_error *err)
 {
-	return __parse_events(evlist, str, /*pmu_filter=*/NULL, err, /*fake_pmu=*/false,
-			      /*warn_if_reordered=*/true, /*fake_tp=*/false);
+	return __parse_events(evlist, str, /*pmu_filter=*/NULL,
+			      /*cputype_filter=*/false, err, /*fake_pmu=*/false,
+			      /*warn_if_reordered=*/true,
+			      /*fake_tp=*/false);
 }
 
 int parse_event(struct evlist *evlist, const char *str);
@@ -161,6 +164,8 @@ struct parse_events_state {
 	bool			   fake_tp;
 	/* If non-null, when wildcard matching only match the given PMU. */
 	const char		  *pmu_filter;
+	/* If true, the pmu_filter was set by --cputype option. */
+	bool cputype_filter;
 	/* Should PE_LEGACY_NAME tokens be generated for config terms? */
 	bool			   match_legacy_cache_terms;
 	/* Were multiple PMUs scanned to find events? */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 11e1f39c1bea..af85c0771c44 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -3411,7 +3411,8 @@ static PyObject *pyrf__parse_metrics(PyObject *self, PyObject *args)
 			((struct pyrf_cpu_map *)pcpus)->cpus : NULL;
 
 	perf_evlist__set_maps(evlist__core(evlist), cpus, threads);
-	ret = metricgroup__parse_groups(evlist, pmu ?: "all", input,
+	ret = metricgroup__parse_groups(evlist, pmu ?: "all",
+					/*cputype_filter=*/false, input,
 					/*metric_no_group=*/ false,
 					/*metric_no_merge=*/ false,
 					/*metric_no_threshold=*/ true,