| Subject | Re: [PATCH 14/34] perf, x86: Avoid checkpointed counters causing excessive TSX aborts | From | Peter Zijlstra <> | Date | Tue, 23 Oct 2012 15:03:43 +0200 |
| |
On Thu, 2012-10-18 at 16:19 -0700, Andi Kleen wrote: > @@ -1079,6 +1079,17 @@ static void intel_pmu_enable_event(struct perf_event *event) > int intel_pmu_save_and_restart(struct perf_event *event) > { > x86_perf_event_update(event); > + /* > + * For a checkpointed counter always reset back to 0. This > + * avoids a situation where the counter overflows, aborts the > + * transaction and is then set back to shortly before the > + * overflow, and overflows and aborts again. > + */ > + if (event->hw.config & HSW_INTX_CHECKPOINTED) {
Would an unlikely() make sense there? Most events won't have this set.
> + /* No race with NMIs because the counter should not be armed */ > + wrmsrl(event->hw.event_base, 0); > + local64_set(&event->hw.prev_count, 0); > + } > return x86_perf_event_set_period(event); > }
|