diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dc7a694..b94dffc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1133,6 +1133,7 @@
 	u64		  exit_time;
 	bool		  entry_pending;
 	unsigned long	  nr_events;
+	unsigned long	  pfmaj, pfmin;
 	char		  *entry_str;
 	double		  runtime_ms;
 	struct {
@@ -1804,8 +1805,20 @@
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct addr_location al;
 	char map_type = 'd';
+	struct thread_trace *ttrace;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	if (ttrace == NULL)
+		return -1;
+
+	if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
+		ttrace->pfmaj++;
+	else
+		ttrace->pfmin++;
+
+	if (trace->summary_only)
+		return 0;
 
 	thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
@@ -2346,6 +2359,10 @@
 	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
 	printed += fprintf(fp, "%.1f%%", ratio);
+	if (ttrace->pfmaj)
+		printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
+	if (ttrace->pfmin)
+		printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);