perf, x86: Fixup the precise_ip computation

In case we don't have PEBS, the LBR fixup doesn't make sense.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Stephane Eranian <eranian@google.com>
LKML-Reference: <20101019134808.354429461@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Peter Zijlstra 2010-10-19 14:38:11 +02:00 committed by Ingo Molnar
parent 65af94baca
commit 5553be2620

View file

@ -497,12 +497,13 @@ static int x86_pmu_hw_config(struct perf_event *event)
int precise = 0;
/* Support for constant skid */
if (x86_pmu.pebs)
if (x86_pmu.pebs) {
precise++;
/* Support for IP fixup */
if (x86_pmu.lbr_nr)
precise++;
}
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;