perf: Remove the perf_output_begin(.sample) argument

Since only samples call perf_output_sample() its much saner (and more
correct) to put the sample logic in there than in the
perf_output_begin()/perf_output_end() pair.

Saves a useless argument, reduces conditionals and shrinks
struct perf_output_handle, win!

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-2crpvsx3cqu67q3zqjbnlpsc@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -340,7 +340,7 @@ static int intel_pmu_drain_bts_buffer(void)
 	 */
 	perf_prepare_sample(&header, &data, event, &regs);
 
-	if (perf_output_begin(&handle, event, header.size * (top - at), 1))
+	if (perf_output_begin(&handle, event, header.size * (top - at)))
 		return 1;
 
 	for (; at < top; at++) {

include/linux/perf_event.h

@@ -925,7 +925,6 @@ struct perf_output_handle {
 	unsigned long			size;
 	void				*addr;
 	int				page;
-	int				sample;
 };
 
 #ifdef CONFIG_PERF_EVENTS
@@ -1117,8 +1116,7 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 #endif
 
 extern int perf_output_begin(struct perf_output_handle *handle,
-			     struct perf_event *event, unsigned int size,
-			     int sample);
+			     struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);
 extern void perf_output_copy(struct perf_output_handle *handle,
 			     const void *buf, unsigned int len);

kernel/events/core.c

@@ -3928,6 +3928,20 @@ void perf_output_sample(struct perf_output_handle *handle,
 			perf_output_put(handle, raw);
 		}
 	}
+
+	if (!event->attr.watermark) {
+		int wakeup_events = event->attr.wakeup_events;
+
+		if (wakeup_events) {
+			struct ring_buffer *rb = handle->rb;
+			int events = local_inc_return(&rb->events);
+
+			if (events >= wakeup_events) {
+				local_sub(wakeup_events, &rb->events);
+				local_inc(&rb->wakeup);
+			}
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -3984,7 +3998,7 @@ static void perf_event_output(struct perf_event *event,
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	if (perf_output_begin(&handle, event, header.size, 1))
+	if (perf_output_begin(&handle, event, header.size))
 		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
@@ -4024,7 +4038,7 @@ perf_event_read_event(struct perf_event *event,
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size, 0);
+	ret = perf_output_begin(&handle, event, read_event.header.size);
 	if (ret)
 		return;
 
@@ -4067,7 +4081,7 @@ static void perf_event_task_output(struct perf_event *event,
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
 	ret = perf_output_begin(&handle, event,
-				task_event->event_id.header.size, 0);
+				task_event->event_id.header.size);
 	if (ret)
 		goto out;
 
@@ -4204,7 +4218,7 @@ static void perf_event_comm_output(struct perf_event *event,
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
 	ret = perf_output_begin(&handle, event,
-				comm_event->event_id.header.size, 0);
+				comm_event->event_id.header.size);
 
 	if (ret)
 		goto out;
@@ -4351,7 +4365,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
 	ret = perf_output_begin(&handle, event,
-				mmap_event->event_id.header.size, 0);
+				mmap_event->event_id.header.size);
 	if (ret)
 		goto out;
 
@@ -4546,7 +4560,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
 	ret = perf_output_begin(&handle, event,
-				throttle_event.header.size, 0);
+				throttle_event.header.size);
 	if (ret)
 		return;
 

kernel/events/ring_buffer.c

@@ -98,8 +98,7 @@ out:
 }
 
 int perf_output_begin(struct perf_output_handle *handle,
-		      struct perf_event *event, unsigned int size,
-		      int sample)
+		      struct perf_event *event, unsigned int size)
 {
 	struct ring_buffer *rb;
 	unsigned long tail, offset, head;
@@ -124,7 +123,6 @@ int perf_output_begin(struct perf_output_handle *handle,
 
 	handle->rb	= rb;
 	handle->event	= event;
-	handle->sample	= sample;
 
 	if (!rb->nr_pages)
 		goto out;
@@ -192,21 +190,6 @@ void perf_output_copy(struct perf_output_handle *handle,
 
 void perf_output_end(struct perf_output_handle *handle)
 {
-	struct perf_event *event = handle->event;
-	struct ring_buffer *rb = handle->rb;
-
-	if (handle->sample && !event->attr.watermark) {
-		int wakeup_events = event->attr.wakeup_events;
-
-		if (wakeup_events) {
-			int events = local_inc_return(&rb->events);
-			if (events >= wakeup_events) {
-				local_sub(wakeup_events, &rb->events);
-				local_inc(&rb->wakeup);
-			}
-		}
-	}
-
 	perf_output_put_handle(handle);
 	rcu_read_unlock();
 }