diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 38d4b682af0b60125f51a11e42ba47a369949924..68718ccdd17820cfb38b4daab837b321874a096f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -51,6 +51,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --duration:
 	Show only events that had a duration greater than N.M ms.
 
+--sched:
+	Accrue thread runtime and provide a summary at the end of the session.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ba055103b52507a0f204f69e6bb6a8179f31a37d..7932ffa298894a00694b82c6f26c058acd3760f9 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -67,7 +67,9 @@ struct thread_trace {
 	u64		  entry_time;
 	u64		  exit_time;
 	bool		  entry_pending;
+	unsigned long	  nr_events;
 	char		  *entry_str;
+	double		  runtime_ms;
 };
 
 static struct thread_trace *thread_trace__new(void)
@@ -77,16 +79,21 @@ static struct thread_trace *thread_trace__new(void)
 
 static struct thread_trace *thread__trace(struct thread *thread)
 {
+	struct thread_trace *ttrace;
+
 	if (thread == NULL)
 		goto fail;
 
 	if (thread->priv == NULL)
 		thread->priv = thread_trace__new();
-
+		
 	if (thread->priv == NULL)
 		goto fail;
 
-	return thread->priv;
+	ttrace = thread->priv;
+	++ttrace->nr_events;
+
+	return ttrace;
 fail:
 	color_fprintf(stdout, PERF_COLOR_RED,
 		      "WARNING: not enough memory, dropping samples!\n");
@@ -102,8 +109,11 @@ struct trace {
 	struct perf_record_opts opts;
 	struct machine		host;
 	u64			base_time;
+	unsigned long		nr_events;
+	bool			sched;
 	bool			multiple_threads;
 	double			duration_filter;
+	double			runtime_ms;
 };
 
 static bool trace__filter_duration(struct trace *trace, double t)
@@ -382,11 +392,37 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	return 0;
 }
 
+static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
+				     struct perf_sample *sample)
+{
+        u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
+	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
+	struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+	struct thread_trace *ttrace = thread__trace(thread);
+
+	if (ttrace == NULL)
+		goto out_dump;
+
+	ttrace->runtime_ms += runtime_ms;
+	trace->runtime_ms += runtime_ms;
+	return 0;
+
+out_dump:
+	printf("%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
+	       evsel->name,
+	       perf_evsel__strval(evsel, sample, "comm"),
+	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
+	       runtime,
+	       perf_evsel__intval(evsel, sample, "vruntime"));
+	return 0;
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
 	struct perf_evsel *evsel;
-	int err = -1, i, nr_events = 0, before;
+	int err = -1, i;
+	unsigned long before;
 	const bool forks = argc > 0;
 
 	if (evlist == NULL) {
@@ -400,6 +436,13 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+	if (trace->sched &&
+	    perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
+				   trace__sched_stat_runtime)) {
+		printf("Couldn't read the sched_stat_runtime tracepoint information!\n");
+		goto out_delete_evlist;
+	}
+
 	err = perf_evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		printf("Problems parsing the target to trace, check your options!\n");
@@ -444,7 +487,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
 again:
-	before = nr_events;
+	before = trace->nr_events;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
@@ -454,7 +497,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 			tracepoint_handler handler;
 			struct perf_sample sample;
 
-			++nr_events;
+			++trace->nr_events;
 
 			err = perf_evlist__parse_sample(evlist, event, &sample);
 			if (err) {
@@ -495,7 +538,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		}
 	}
 
-	if (nr_events == before) {
+	if (trace->nr_events == before) {
 		if (done)
 			goto out_delete_evlist;
 
@@ -513,6 +556,51 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	return err;
 }
 
+static size_t trace__fprintf_threads_header(FILE *fp)
+{
+	size_t printed;
+
+	printed  = fprintf(fp, "\n _____________________________________________________________________\n");
+	printed += fprintf(fp," __)    Summary of events    (__\n\n");
+	printed += fprintf(fp,"              [ task - pid ]     [ events ] [ ratio ]  [ runtime ]\n");
+	printed += fprintf(fp," _____________________________________________________________________\n\n");
+
+	return printed;
+}
+
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
+{
+	size_t printed = trace__fprintf_threads_header(fp);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) {
+		struct thread *thread = rb_entry(nd, struct thread, rb_node);
+		struct thread_trace *ttrace = thread->priv;
+		const char *color;
+		double ratio;
+
+		if (ttrace == NULL)
+			continue;
+
+		ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
+
+		color = PERF_COLOR_NORMAL;
+		if (ratio > 50.0)
+			color = PERF_COLOR_RED;
+		else if (ratio > 25.0)
+			color = PERF_COLOR_GREEN;
+		else if (ratio > 5.0)
+			color = PERF_COLOR_YELLOW;
+
+		printed += color_fprintf(fp, color, "%20s", thread->comm);
+		printed += fprintf(fp, " - %-5d :%11lu   [", thread->pid, ttrace->nr_events);
+		printed += color_fprintf(fp, color, "%5.1f%%", ratio);
+		printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
+	}
+
+	return printed;
+}
+
 static int trace__set_duration(const struct option *opt, const char *str,
 			       int unset __maybe_unused)
 {
@@ -563,6 +651,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK(0, "duration", &trace, "float",
 		     "show only events with duration > N.M ms",
 		     trace__set_duration),
+	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
 	OPT_END()
 	};
 	int err;
@@ -587,5 +676,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!argc && perf_target__none(&trace.opts.target))
 		trace.opts.target.system_wide = true;
 
-	return trace__run(&trace, argc, argv);
+	err = trace__run(&trace, argc, argv);
+
+	if (trace.sched && !err)
+		trace__fprintf_thread_summary(&trace, stdout);
+
+	return err;
 }
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0ae444ef1429939e5fbc7891ac65485eb5bb4c50..ca9ca285406a8651a5027edf55bd5c21efa67944 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -405,16 +405,15 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
-
-		if (__event__synthesize_thread(comm_event, mmap_event, pid, 1,
-					   process, tool, machine) != 0) {
-			err = -1;
-			goto out_closedir;
-		}
+		/*
+ 		 * We may race with exiting thread, so don't stop just because
+ 		 * one thread couldn't be synthesized.
+ 		 */
+		__event__synthesize_thread(comm_event, mmap_event, pid, 1,
+					   process, tool, machine);
 	}
 
 	err = 0;
-out_closedir:
 	closedir(proc);
 out_free_mmap:
 	free(mmap_event);