Peter,

On Wed, Jan 5, 2011 at 2:01 PM, Stephane Eranian <eran...@google.com> wrote:
> On Wed, Jan 5, 2011 at 12:23 PM, Peter Zijlstra <pet...@infradead.org> wrote:
>> On Mon, 2011-01-03 at 18:20 +0200, Stephane Eranian wrote:
>>> +void
>>> +perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
>>> +{
>>> +     struct perf_cgroup *cgrp_out = perf_cgroup_from_task(task);
>>> +     struct perf_cgroup *cgrp_in = perf_cgroup_from_task(next);
>>> +     struct perf_cpu_context *cpuctx;
>>> +     struct pmu *pmu;
>>> +     /*
>>> +      * if task is DEAD, then css_out is irrelevant, it has
>>> +      * been changed to init_cgrp in cgroup_exit() from do_exit().
>>> +      * Furthermore, perf_cgroup_exit_task(), has scheduled out
>>> +      * all css constrained events, only unconstrained events
>>> +      * remain. Therefore we need to reschedule based on css_in.
>>> +      */
>>> +     if (task->state != TASK_DEAD && cgrp_out == cgrp_in)
>>> +             return;
>>
>> I think that check is broken, TASK_DEAD is set way after calling
>> cgroup_exit(), so if we get preempted in between there you'll still go
>> funny.
>>

I looked at this part again.

The original code checking for TASK_DEAD is correct.

The reason is simple, you're looking at perf_cgroup_switch() which is
invoked as part of schedule() and NOT perf_event_task_exit() (called
prior to cgroup_exit()).
Thus, by the time you do the final schedule(), the task state has indeed
been switched to TASK_DEAD.

I remember testing for this condition during the debug phase.

I will resubmit with the other smaller cleanups.

------------------------------------------------------------------------------
Learn how Oracle Real Application Clusters (RAC) One Node allows customers
to consolidate database storage, standardize their database environment, and, 
should the need arise, upgrade to a full multi-node Oracle RAC database 
without downtime or disruption
http://p.sf.net/sfu/oracle-sfdevnl
_______________________________________________
perfmon2-devel mailing list
perfmon2-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/perfmon2-devel

Reply via email to