diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 86848c57b55ed32bc2feebbf79458c9cd9f1ea66..404315df1e1676398fabc56054db3d34dfbf629b 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -670,9 +670,7 @@ unlock:
 
 static inline void intel_pmu_drain_pebs_buffer(void)
 {
-	struct pt_regs regs;
-
-	x86_pmu.drain_pebs(&regs);
+	x86_pmu.drain_pebs(NULL);
 }
 
 /*
@@ -1737,6 +1735,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	struct x86_perf_regs perf_regs;
 	struct pt_regs *regs = &perf_regs.regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
+	struct pt_regs dummy_iregs;
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		/*
@@ -1749,6 +1748,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	} else if (!intel_pmu_save_and_restart(event))
 		return;
 
+	if (!iregs)
+		iregs = &dummy_iregs;
+
 	while (count > 1) {
 		setup_sample(event, iregs, at, &data, regs);
 		perf_event_output(event, &data, regs);
@@ -1758,16 +1760,22 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	}
 
 	setup_sample(event, iregs, at, &data, regs);
-
-	/*
-	 * All but the last records are processed.
-	 * The last one is left to be able to call the overflow handler.
-	 */
-	if (perf_event_overflow(event, &data, regs)) {
-		x86_pmu_stop(event, 0);
-		return;
+	if (iregs == &dummy_iregs) {
+		/*
+		 * The PEBS records may be drained in the non-overflow context,
+		 * e.g., large PEBS + context switch. Perf should treat the
+		 * last record the same as other PEBS records, and doesn't
+		 * invoke the generic overflow handler.
+		 */
+		perf_event_output(event, &data, regs);
+	} else {
+		/*
+		 * All but the last records are processed.
+		 * The last one is left to be able to call the overflow handler.
+		 */
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
 	}
-
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)