Re: [PATCH] perf: Cure task_oncpu_function_call() races

[Peter Zijlstra <peterz@infradead.org>]

On Tue, 2011-02-01 at 19:08 +0100, Peter Zijlstra wrote:
> > > +static void perf_remove_from_context(struct perf_event *event)
> > >  {
> > > ...
> > >     raw_spin_lock_irq(&ctx->lock);
> > >     /*
> > > +    * If we failed to find a running task, but find it running now that
> > > +    * we've acquired the ctx->lock, retry.
> > >      */
> > > +   if (task_curr(task)) {
> > >             raw_spin_unlock_irq(&ctx->lock);
> > >             goto retry;
> > >     }
> > >
> > >     /*
> > > +    * Since the task isn't running, its safe to remove the event, us
> > > +    * holding the ctx->lock ensures the task won't get scheduled in.
> > >      */
> > > +   list_del_event(event, ctx);
> > 
> > this looks suspicious (the same for perf_install_in_context).
> > 
> > Unlike the IPI handler, this can see schedule-in-progress in any state.
> > In particular, we can see rq->curr == next (so that task_curr() == F),
> > but before "prev" has already called perf_event_task_sched_out().
> > 
> > So we have to check ctx->is_active, or schedule() should change rq->curr
> > after perf_event_task_sched_out().
> 
> I only considered current == next in that case, not current == prev, let
> me undo some of those sched.c bits and put a comment. 

On second thought, your proposed ->is_active check seems to result in
much nicer code in sched.c. Let me think through that.