Messages in this thread Patch in this message | | | Subject | Re: [PATCH] perf_events: fix validate_event bug | From | Peter Zijlstra <> | Date | Wed, 18 Nov 2009 17:46:25 +0100 |
| |
On Thu, 2009-10-22 at 16:51 +0200, Stephane Eranian wrote: > The validate_event() was failing on valid event > combinations. The function was assuming that if > x86_schedule_event() returned 0, it meant error. > But x86_schedule_event() returns the counter index > and 0 is a perfectly valid value. An error is returned > if the function returns a negative value.
Good point.
> Furthermore, validate_event() was also failing for > event groups because the event->pmu was not set until > after hw_perf_pmu_init().
(hw_perf_event_init, right?)
Won't this give very funny results for mixed pmu groups?
How about something like:
if (event->pmu && event->pmu != &pmu) return 0;
That should deal with new events, who do not yet have their pmu set and for those we know they're for us, but exclude events for other PMUs.
> Signed-off-by: Stephane Eranian <eranian@gmail.com> > -- > arch/x86/kernel/cpu/perf_event.c | 5 +---- > 1 file changed, 1 insertion(+), 4 deletions(-) > > diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c > index 2e20bca..d321ff7 100644 > --- a/arch/x86/kernel/cpu/perf_event.c > +++ b/arch/x86/kernel/cpu/perf_event.c > @@ -2229,10 +2229,7 @@ validate_event(struct cpu_hw_events *cpuc, struct perf_event *event) > { > struct hw_perf_event fake_event = event->hw; > > - if (event->pmu != &pmu) > - return 0; > - > - return x86_schedule_event(cpuc, &fake_event); > + return x86_schedule_event(cpuc, &fake_event) >= 0; > } > > static int validate_group(struct perf_event *event)
| |