diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5496546..d0f91fe 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -10,6 +10,7 @@
 #include "util/strlist.h"
 #include "util/intlist.h"
 #include "util/thread_map.h"
+#include "util/stat.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -909,6 +910,8 @@
 		int	  max;
 		char	  **table;
 	} paths;
+
+	struct intlist *syscall_stats;
 };
 
 static struct thread_trace *thread_trace__new(void)
@@ -918,6 +921,8 @@
 	if (ttrace)
 		ttrace->paths.max = -1;
 
+	ttrace->syscall_stats = intlist__new(NULL);
+
 	return ttrace;
 }
 
@@ -964,6 +969,7 @@
 	struct intlist		*pid_list;
 	bool			sched;
 	bool			multiple_threads;
+	bool			summary;
 	bool			show_comm;
 	double			duration_filter;
 	double			runtime_ms;
@@ -1291,10 +1297,8 @@
 				  struct perf_sample *sample);
 
 static struct syscall *trace__syscall_info(struct trace *trace,
-					   struct perf_evsel *evsel,
-					   struct perf_sample *sample)
+					   struct perf_evsel *evsel, int id)
 {
-	int id = perf_evsel__intval(evsel, sample, "id");
 
 	if (id < 0) {
 
@@ -1335,6 +1339,32 @@
 	return NULL;
 }
 
+static void thread__update_stats(struct thread_trace *ttrace,
+				 int id, struct perf_sample *sample)
+{
+	struct int_node *inode;
+	struct stats *stats;
+	u64 duration = 0;
+
+	inode = intlist__findnew(ttrace->syscall_stats, id);
+	if (inode == NULL)
+		return;
+
+	stats = inode->priv;
+	if (stats == NULL) {
+		stats = malloc(sizeof(struct stats));
+		if (stats == NULL)
+			return;
+		init_stats(stats);
+		inode->priv = stats;
+	}
+
+	if (ttrace->entry_time && sample->time > ttrace->entry_time)
+		duration = sample->time - ttrace->entry_time;
+
+	update_stats(stats, duration);
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			    struct perf_sample *sample)
 {
@@ -1342,7 +1372,8 @@
 	void *args;
 	size_t printed = 0;
 	struct thread *thread;
-	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
+	int id = perf_evsel__intval(evsel, sample, "id");
+	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
 	if (sc == NULL)
@@ -1394,7 +1425,8 @@
 	int ret;
 	u64 duration = 0;
 	struct thread *thread;
-	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
+	int id = perf_evsel__intval(evsel, sample, "id");
+	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
 	if (sc == NULL)
@@ -1408,6 +1440,9 @@
 	if (ttrace == NULL)
 		return -1;
 
+	if (trace->summary)
+		thread__update_stats(ttrace, id, sample);
+
 	ret = perf_evsel__intval(evsel, sample, "ret");
 
 	ttrace = thread->priv;
@@ -1574,6 +1609,8 @@
 	return cmd_record(i, rec_argv, NULL);
 }
 
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = perf_evlist__new();
@@ -1703,6 +1740,9 @@
 	goto again;
 
 out_unmap_evlist:
+	if (!err && trace->summary)
+		trace__fprintf_thread_summary(trace, trace->output);
+
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
@@ -1798,6 +1838,9 @@
 	if (err)
 		pr_err("Failed to process events, error %d", err);
 
+	else if (trace->summary)
+		trace__fprintf_thread_summary(trace, trace->output);
+
 out:
 	perf_session__delete(session);
 
@@ -1808,10 +1851,53 @@
 {
 	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");
+	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, "                                  syscall  count    min     max    avg  stddev\n");
+	printed += fprintf(fp, "                                                   msec    msec   msec     %%\n");
+	printed += fprintf(fp, " _____________________________________________________________________________\n\n");
+
+	return printed;
+}
+
+static size_t thread__dump_stats(struct thread_trace *ttrace,
+				 struct trace *trace, FILE *fp)
+{
+	struct stats *stats;
+	size_t printed = 0;
+	struct syscall *sc;
+	struct int_node *inode = intlist__first(ttrace->syscall_stats);
+
+	if (inode == NULL)
+		return 0;
+
+	printed += fprintf(fp, "\n");
+
+	/* each int_node is a syscall */
+	while (inode) {
+		stats = inode->priv;
+		if (stats) {
+			double min = (double)(stats->min) / NSEC_PER_MSEC;
+			double max = (double)(stats->max) / NSEC_PER_MSEC;
+			double avg = avg_stats(stats);
+			double pct;
+			u64 n = (u64) stats->n;
+
+			pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
+			avg /= NSEC_PER_MSEC;
+
+			sc = &trace->syscalls.table[inode->i];
+			printed += fprintf(fp, "%24s  %14s : ", "", sc->name);
+			printed += fprintf(fp, "%5" PRIu64 "  %8.3f  %8.3f",
+					   n, min, max);
+			printed += fprintf(fp, "  %8.3f  %6.2f\n", avg, pct);
+		}
+
+		inode = intlist__next(inode);
+	}
+
+	printed += fprintf(fp, "\n\n");
 
 	return printed;
 }
@@ -1850,6 +1936,7 @@
 	printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
 	printed += color_fprintf(fp, color, "%5.1f%%", ratio);
 	printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
+	printed += thread__dump_stats(ttrace, trace, fp);
 
 	data->printed += printed;
 
@@ -1953,6 +2040,8 @@
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_BOOLEAN('T', "time", &trace.full_time,
 		    "Show full timestamp, not time relative to first start"),
+	OPT_BOOLEAN(0, "summary", &trace.summary,
+		    "Show syscall summary with statistics"),
 	OPT_END()
 	};
 	int err;
@@ -2008,9 +2097,6 @@
 	else
 		err = trace__run(&trace, argc, argv);
 
-	if (trace.sched && !err)
-		trace__fprintf_thread_summary(&trace, trace.output);
-
 out_close:
 	if (output_name != NULL)
 		fclose(trace.output);