Re: [PATCH v2] events/core: fix acoount failure for event's total_enable_time

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Dec 20, 2024 at 04:14:14PM +0100, Peter Zijlstra wrote:
> On Fri, Dec 20, 2024 at 02:05:39PM +0000, Yeoreum Yun wrote:

> > the answer is in the perf_event_exit_event()'s
> > perf_remove_from_context(). in here
> > event_sched_out() is called via __perf_remove_from_context()
> > So above case, the enable time is fixed in here.
> 
> OK, how's this then?

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 065f9188b44a..96a00034b26f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2406,7 +2406,8 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event)
 
 #define DETACH_GROUP	0x01UL
 #define DETACH_CHILD	0x02UL
-#define DETACH_DEAD	0x04UL
+#define DETACH_EXIT	0x04UL
+#define DETACH_DEAD	0x048L
 
 /*
  * Cross CPU call to remove a performance event
@@ -2421,6 +2422,7 @@ __perf_remove_from_context(struct perf_event *event,
 			   void *info)
 {
 	struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx;
+	enum perf_event_state state = PERF_EVENT_STATE_OFF;
 	unsigned long flags = (unsigned long)info;
 
 	ctx_time_update(cpuctx, ctx);
@@ -2429,16 +2431,20 @@ __perf_remove_from_context(struct perf_event *event,
 	 * Ensure event_sched_out() switches to OFF, at the very least
 	 * this avoids raising perf_pending_task() at this time.
 	 */
-	if (flags & DETACH_DEAD)
+	if (flags & DETACH_EXIT)
+		state = PERF_EVENT_STATE_EXIT;
+	if (flags & DETACH_DEAD) {
 		event->pending_disable = 1;
+		state = PERF_EVENT_STATE_DEAD;
+	}
 	event_sched_out(event, ctx);
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	if (flags & DETACH_CHILD)
 		perf_child_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_DEAD)
-		event->state = PERF_EVENT_STATE_DEAD;
+
+	perf_event_set_state(event, min(event->state, state));
 
 	if (!pmu_ctx->nr_events) {
 		pmu_ctx->rotate_necessary = 0;
@@ -13371,12 +13377,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		mutex_lock(&parent_event->child_mutex);
 	}
 
-	perf_remove_from_context(event, detach_flags);
-
-	raw_spin_lock_irq(&ctx->lock);
-	if (event->state > PERF_EVENT_STATE_EXIT)
-		perf_event_set_state(event, PERF_EVENT_STATE_EXIT);
-	raw_spin_unlock_irq(&ctx->lock);
+	perf_remove_from_context(event, detach_flags | DETACH_EXIT);
 
 	/*
 	 * Child events can be freed.