Messages in this thread | | | Date | Wed, 23 Nov 2011 11:10:15 +0100 | Subject | Re: [PATCH] perf_event: fix loss of notification with multi-event sampling | From | Stephane Eranian <> |
| |
On Wed, Nov 23, 2011 at 11:06 AM, Peter Zijlstra <peterz@infradead.org> wrote: > On Wed, 2011-11-23 at 10:30 +0100, Stephane Eranian wrote: >> >> In the case of perf_event, we are not in a producer-consumer model, so >> it seems like the behavior we have now is correct. The caller of poll() >> gets stuck if the file descriptor is closed. > > But wouldn't out event->waitq still be referenced by that waiting task? > Even though we freed it in our fops->release() callback? > I suspect you don't end up in fops->release() if you have an ongoing poll because you've probably increment the file's refcount along the way.
| |