Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

Peter Zijlstra writes: > On Wed, Aug 24, 2016 at 05:15:54PM +0300, Alexander Shishkin wrote: >> @@ -221,10 +245,13 @@ static void __bts_event_start(struct perf_event *event) >> >> /* >> * local barrier to make sure that ds configuration made it >> - * before we enable BTS >> +

Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

On Wed, Aug 24, 2016 at 05:15:54PM +0300, Alexander Shishkin wrote: > @@ -221,10 +245,13 @@ static void __bts_event_start(struct perf_event *event) > > /* >* local barrier to make sure that ds configuration made it > - * before we enable BTS > + * before we enable BTS and

Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

Yes, Will's patch notwithstanding, these patches fix the warnings/oopses that you observed. On 26 August 2016 at 23:49, Vince Weaver wrote: > On Wed, 24 Aug 2016, Alexander Shishkin wrote: > >> Alexander Shishkin writes: >> >> > Alexander Shishkin writes: >> > >> >> Signed-off-by: Alexander Shi

Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

On Wed, 24 Aug 2016, Alexander Shishkin wrote: > Alexander Shishkin writes: > > > Alexander Shishkin writes: > > > >> Signed-off-by: Alexander Shishkin > > > > Ok, this one is broken, please disregard. > > Vince, can you try the following (with the other two in this series)? > Sorry for the

Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

Alexander Shishkin writes: > Alexander Shishkin writes: > >> Signed-off-by: Alexander Shishkin > > Ok, this one is broken, please disregard. Vince, can you try the following (with the other two in this series)? --- >From 68713194b3df8e565c4d319a80e9e7338fa1ec13 Mon Sep 17 00:00:00 2001 From:

Re: [PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

Alexander Shishkin writes: > The intel_bts driver is using a cpu-local 'started' variable to order > callbacks and PMIs and make sure that AUX transactions don't get messed > up. However, the ordering rules in regard to this variable is a complete > mess, which recently resulted in perf_fuzzer-tr

[PATCH 1/3] perf/x86/intel/bts: Fix confused ordering of PMU callbacks

The intel_bts driver is using a cpu-local 'started' variable to order callbacks and PMIs and make sure that AUX transactions don't get messed up. However, the ordering rules in regard to this variable is a complete mess, which recently resulted in perf_fuzzer-triggered warnings and panics. The gen