1 files changed, 60 insertions, 38 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 68ea7589c143..2c38dd98f6ca 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -108,9 +108,7 @@ static struct parse_events_option_args parse_events_option_args = {
 
 static bool all_counters_use_bpf = true;
 
-static struct target target = {
-	.uid	= UINT_MAX,
-};
+static struct target target;
 
 static volatile sig_atomic_t	child_pid			= -1;
 static int			detailed_run			=  0;
@@ -681,8 +679,6 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	if (child_pid != -1)
 		kill(child_pid, SIGTERM);
 
-	tpebs_delete();
-
 	return COUNTER_FATAL;
 }
 
@@ -1369,7 +1365,7 @@ static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
 	struct aggr_cpu_id id;
 
 	/* per-process mode - should use global aggr mode */
-	if (cpu.cpu == -1)
+	if (cpu.cpu == -1 || cpu.cpu >= config->cpus_aggr_map->nr)
 		return get_id(config, cpu);
 
 	if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu]))
@@ -1517,11 +1513,8 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	if (!perf_cpu_map__is_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
-		nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
-	else
-		nr = 0;
-	stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
+	nr = perf_cpu_map__max(evsel_list->core.all_cpus).cpu + 1;
+	stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr);
 	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
 
@@ -1696,48 +1689,48 @@ static struct aggr_cpu_id perf_env__get_global_aggr_by_cpu(struct perf_cpu cpu _
 static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
 						     struct perf_cpu cpu)
 {
-	return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_socket_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
 						  struct perf_cpu cpu)
 {
-	return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_die_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_cluster_file(struct perf_stat_config *config __maybe_unused,
 						      struct perf_cpu cpu)
 {
-	return perf_env__get_cluster_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_cluster_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_cache_file(struct perf_stat_config *config __maybe_unused,
 						    struct perf_cpu cpu)
 {
-	return perf_env__get_cache_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_cache_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
 						   struct perf_cpu cpu)
 {
-	return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_core_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_cpu_file(struct perf_stat_config *config __maybe_unused,
 						  struct perf_cpu cpu)
 {
-	return perf_env__get_cpu_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_cpu_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
 						   struct perf_cpu cpu)
 {
-	return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_node_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static struct aggr_cpu_id perf_stat__get_global_file(struct perf_stat_config *config __maybe_unused,
 						     struct perf_cpu cpu)
 {
-	return perf_env__get_global_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+	return perf_env__get_global_aggr_by_cpu(cpu, perf_session__env(perf_stat.session));
 }
 
 static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode)
@@ -1796,7 +1789,7 @@ static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode)
 
 static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 {
-	struct perf_env *env = &st->session->header.env;
+	struct perf_env *env = perf_session__env(st->session);
 	aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
 	bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
 
@@ -1856,7 +1849,7 @@ static int add_default_events(void)
 		 * will use this approach. To determine transaction support
 		 * on an architecture test for such a metric name.
 		 */
-		if (!metricgroup__has_metric(pmu, "transaction")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "transaction")) {
 			pr_err("Missing transaction metrics\n");
 			ret = -1;
 			goto out;
@@ -1867,8 +1860,7 @@ static int add_default_events(void)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
-						stat_config.hardware_aware_grouping,
-						&stat_config.metric_events);
+						stat_config.hardware_aware_grouping);
 		goto out;
 	}
 
@@ -1890,7 +1882,7 @@ static int add_default_events(void)
 			smi_reset = true;
 		}
 
-		if (!metricgroup__has_metric(pmu, "smi")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "smi")) {
 			pr_err("Missing smi metrics\n");
 			ret = -1;
 			goto out;
@@ -1905,8 +1897,7 @@ static int add_default_events(void)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
-						stat_config.hardware_aware_grouping,
-						&stat_config.metric_events);
+						stat_config.hardware_aware_grouping);
 		goto out;
 	}
 
@@ -1943,8 +1934,7 @@ static int add_default_events(void)
 						/*metric_no_threshold=*/true,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
-						stat_config.hardware_aware_grouping,
-						&stat_config.metric_events) < 0) {
+						stat_config.hardware_aware_grouping) < 0) {
 			ret = -1;
 			goto out;
 		}
@@ -1980,7 +1970,7 @@ static int add_default_events(void)
 		 * Add TopdownL1 metrics if they exist. To minimize
 		 * multiplexing, don't request threshold computation.
 		 */
-		if (metricgroup__has_metric(pmu, "Default")) {
+		if (metricgroup__has_metric_or_groups(pmu, "Default")) {
 			struct evlist *metric_evlist = evlist__new();
 
 			if (!metric_evlist) {
@@ -1993,8 +1983,7 @@ static int add_default_events(void)
 							/*metric_no_threshold=*/true,
 							stat_config.user_requested_cpu_list,
 							stat_config.system_wide,
-							stat_config.hardware_aware_grouping,
-							&stat_config.metric_events) < 0) {
+							stat_config.hardware_aware_grouping) < 0) {
 				ret = -1;
 				goto out;
 			}
@@ -2003,6 +1992,9 @@ static int add_default_events(void)
 				evsel->default_metricgroup = true;
 
 			evlist__splice_list_tail(evlist, &metric_evlist->core.entries);
+			metricgroup__copy_metric_events(evlist, /*cgrp=*/NULL,
+							&evlist->metric_events,
+							&metric_evlist->metric_events);
 			evlist__delete(metric_evlist);
 		}
 	}
@@ -2057,6 +2049,9 @@ out:
 	}
 	parse_events_error__exit(&err);
 	evlist__splice_list_tail(evsel_list, &evlist->core.entries);
+	metricgroup__copy_metric_events(evsel_list, /*cgrp=*/NULL,
+					&evsel_list->metric_events,
+					&evlist->metric_events);
 	evlist__delete(evlist);
 	return ret;
 }
@@ -2117,8 +2112,9 @@ static int process_stat_round_event(struct perf_session *session,
 {
 	struct perf_record_stat_round *stat_round = &event->stat_round;
 	struct timespec tsh, *ts = NULL;
-	const char **argv = session->header.env.cmdline_argv;
-	int argc = session->header.env.nr_cmdline;
+	struct perf_env *env = perf_session__env(session);
+	const char **argv = env->cmdline_argv;
+	int argc = env->nr_cmdline;
 
 	process_counters();
 
@@ -2329,6 +2325,32 @@ static void setup_system_wide(int forks)
 	}
 }
 
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+static int parse_tpebs_mode(const struct option *opt, const char *str,
+			    int unset __maybe_unused)
+{
+	enum tpebs_mode *mode = opt->value;
+
+	if (!strcasecmp("mean", str)) {
+		*mode = TPEBS_MODE__MEAN;
+		return 0;
+	}
+	if (!strcasecmp("min", str)) {
+		*mode = TPEBS_MODE__MIN;
+		return 0;
+	}
+	if (!strcasecmp("max", str)) {
+		*mode = TPEBS_MODE__MAX;
+		return 0;
+	}
+	if (!strcasecmp("last", str)) {
+		*mode = TPEBS_MODE__LAST;
+		return 0;
+	}
+	return -1;
+}
+#endif // HAVE_ARCH_X86_64_SUPPORT
+
 int cmd_stat(int argc, const char **argv)
 {
 	struct opt_aggr_mode opt_mode = {};
@@ -2433,6 +2455,9 @@ int cmd_stat(int argc, const char **argv)
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 		OPT_BOOLEAN(0, "record-tpebs", &tpebs_recording,
 			"enable recording for tpebs when retire_latency required"),
+		OPT_CALLBACK(0, "tpebs-mode", &tpebs_mode, "tpebs-mode",
+			"Mode of TPEBS recording: mean, min or max",
+			parse_tpebs_mode),
 #endif
 		OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
 			"Set the metrics level for the top-down statistics (0: max level)"),
@@ -2714,8 +2739,7 @@ int cmd_stat(int argc, const char **argv)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
-						stat_config.hardware_aware_grouping,
-						&stat_config.metric_events);
+						stat_config.hardware_aware_grouping);
 
 		zfree(&metrics);
 		if (ret) {
@@ -2735,8 +2759,7 @@ int cmd_stat(int argc, const char **argv)
 			goto out;
 		}
 
-		if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list,
-					  &stat_config.metric_events, true) < 0) {
+		if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list, true) < 0) {
 			parse_options_usage(stat_usage, stat_options,
 					    "for-each-cgroup", 0);
 			goto out;
@@ -2911,7 +2934,6 @@ out:
 
 	evlist__delete(evsel_list);
 
-	metricgroup__rblist_exit(&stat_config.metric_events);
 	evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close);
 
 	return status;