diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fcb834dd75c2..90c782749b05 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1016,7 +1016,13 @@ struct perf_output_handle {
 	struct perf_buffer		*rb;
 	unsigned long			wakeup;
 	unsigned long			size;
-	u64				aux_flags;
+	union {
+		u64			flags;		/* perf_output*() */
+		u64			aux_flags;	/* perf_aux_output*() */
+		struct {
+			u64		skip_read : 1;
+		};
+	};
 	union {
 		void			*addr;
 		unsigned long		head;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 987807b1040a..5dd6424e62fa 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1163,6 +1163,12 @@ static void perf_assert_pmu_disabled(struct pmu *pmu)
 	WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0);
 }
 
+static inline void perf_pmu_read(struct perf_event *event)
+{
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
+}
+
 static void get_ctx(struct perf_event_context *ctx)
 {
 	refcount_inc(&ctx->refcount);
@@ -3397,8 +3403,7 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	 * we know the event must be on the current CPU, therefore we
 	 * don't need to use it.
 	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		event->pmu->read(event);
+	perf_pmu_read(event);
 
 	perf_event_update_time(event);
 
@@ -4524,15 +4529,8 @@ static void __perf_event_read(void *info)
 
 	pmu->read(event);
 
-	for_each_sibling_event(sub, event) {
-		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
-			/*
-			 * Use sibling's PMU rather than @event's since
-			 * sibling could be on different (eg: software) PMU.
-			 */
-			sub->pmu->read(sub);
-		}
-	}
+	for_each_sibling_event(sub, event)
+		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
 
@@ -7297,9 +7295,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		values[n++] = running;
 
-	if ((leader != event) &&
-	    (leader->state == PERF_EVENT_STATE_ACTIVE))
-		leader->pmu->read(leader);
+	if ((leader != event) && !handle->skip_read)
+		perf_pmu_read(leader);
 
 	values[n++] = perf_event_count(leader);
 	if (read_format & PERF_FORMAT_ID)
@@ -7312,9 +7309,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	for_each_sibling_event(sub, leader) {
 		n = 0;
 
-		if ((sub != event) &&
-		    (sub->state == PERF_EVENT_STATE_ACTIVE))
-			sub->pmu->read(sub);
+		if ((sub != event) && !handle->skip_read)
+			perf_pmu_read(sub);
 
 		values[n++] = perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
@@ -7369,6 +7365,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 {
 	u64 sample_type = data->type;
 
+	if (data->sample_flags & PERF_SAMPLE_READ)
+		handle->skip_read = 1;
+
 	perf_output_put(handle, *header);
 
 	if (sample_type & PERF_SAMPLE_IDENTIFIER)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 52de76ef8723..dc1193b779c0 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -181,6 +181,7 @@ __perf_output_begin(struct perf_output_handle *handle,
 
 	handle->rb    = rb;
 	handle->event = event;
+	handle->flags = 0;
 
 	have_lost = local_read(&rb->lost);
 	if (unlikely(have_lost)) {