On Tue, May 25, 2010 at 6:18 PM, Peter Zijlstra <peterz@infradead.org> wrote:
quoted text
> On Tue, 2010-05-25 at 18:10 +0200, Stephane Eranian wrote:
>> > Index: linux-2.6/kernel/perf_event.c
>> > ===================================================================
>> > --- linux-2.6.orig/kernel/perf_event.c
>> > +++ linux-2.6/kernel/perf_event.c
>> > @@ -668,15 +668,9 @@ group_sched_in(struct perf_event *group_
>> >                }
>> >        }
>> >
>> > -       if (!txn)
>> > +       if (!txn || !pmu->commit_txn(pmu))
>> >                return 0;
>> >
>> > -       ret = pmu->commit_txn(pmu);
>> > -       if (!ret) {
>> > -               pmu->cancel_txn(pmu);
>> > -               return 0;
>> > -       }
>> > -
>> >  group_error:
>> >        /*
>> >         * Groups can be scheduled in as one unit only, so undo any
>> >
>> Looks okay.
>>
>> I believe you can also drop the txn test in group_sched_in() after group_error:,
>> given you have the if !(txn) return 0.
>
> Can't we still get in the group_error: branch with either scenario?
>
You're right. We must keep it because of failure in the siblings' loop.
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/