Re: WARN_ON_ONCE() hit at kernel/events/core.c:330

[Peter Zijlstra]

On Thu, Apr 04, 2019 at 01:09:09PM +0200, Peter Zijlstra wrote:

> That is not entirely the scenario I talked about, but *groan*.
> 
> So what I meant was:
> 
> 	CPU-0							CPU-n
> 
> 	__schedule()
> 	  local_irq_disable()
> 
> 	  ...
> 	    deactivate_task(prev);
> 
> 								try_to_wake_up(@p)
> 								  ...
> 								  smp_cond_load_acquire(&p->on_cpu, !VAL);
> 
> 	  <PMI>
> 	    ..
> 	    perf_event_disable_inatomic()
> 	      event->pending_disable = 1;
> 	      irq_work_queue() /* self-IPI */
> 	  </PMI>
> 
> 	  context_switch()
> 	    prepare_task_switch()
> 	      perf_event_task_sched_out()
> 	        // the above chain that clears pending_disable
> 
> 	    finish_task_switch()
> 	      finish_task()
> 	        smp_store_release(prev->on_cpu, 0);
> 								  /* finally.... */
> 								// take woken
> 								// context_switch to @p
> 	      finish_lock_switch()
> 	        raw_spin_unlock_irq()
> 		/* w00t, IRQs enabled, self-IPI time */
> 	        <self-IPI>
> 		  perf_pending_event()
> 		    // event->pending_disable == 0
> 		</self-IPI>
> 
> 
> What you're suggesting, is that the time between:
> 
>   smp_store_release(prev->on_cpu, 0);
> 
> and
> 
>   <self-IPI>
> 
> on CPU-0 is sufficient for CPU-n to context switch to the task, enable
> the event there, trigger a PMI that calls perf_event_disable_inatomic()
> _again_ (this would mean irq_work_queue() failing, which we don't check)
> (and schedule out again, although that's not required).
> 
> This being virt that might actually be possible if (v)CPU-0 takes a nap
> I suppose.
> 
> Let me think about this a little more...

Does the below cure things? It's not exactly pretty, but it could just
do the trick.

---
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dfc4bab0b02b..d496e6911442 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (event->pending_disable == smp_processor_id()) {
+		event->pending_disable = -1;
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2198,7 +2198,7 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	event->pending_disable = 1;
+	event->pending_disable = smp_processor_id();
 	irq_work_queue(&event->pending);
 }
 
@@ -5822,8 +5822,8 @@ static void perf_pending_event(struct irq_work *entry)
 	 * and we won't recurse 'further'.
 	 */
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (event->pending_disable == smp_processor_id()) {
+		event->pending_disable = -1;
 		perf_event_disable_local(event);
 	}
 
@@ -10236,6 +10236,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
+	event->pending_disable = -1;
 	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);