Re: [RFC PATCH 6/6] perf: Disable IRQs in address filter sync path

2016-10-04 Thread Mathieu Poirier
On 26 September 2016 at 10:18, Alexander Shishkin wrote: > Alexander Shishkin writes: > >> If PMU callbacks are executed in hardirq context, the address filter >> sync code needs to disable interrupts when taking its spinlock to be >> consistent with the rest of its users. This may happen if the

Re: [RFC PATCH 6/6] perf: Disable IRQs in address filter sync path

2016-09-26 Thread Alexander Shishkin
Alexander Shishkin writes: > If PMU callbacks are executed in hardirq context, the address filter > sync code needs to disable interrupts when taking its spinlock to be > consistent with the rest of its users. This may happen if the PMU is > used in AUX sampling. Hi Mathieu, I've been meaning t

[RFC PATCH 6/6] perf: Disable IRQs in address filter sync path

2016-09-23 Thread Alexander Shishkin
If PMU callbacks are executed in hardirq context, the address filter sync code needs to disable interrupts when taking its spinlock to be consistent with the rest of its users. This may happen if the PMU is used in AUX sampling. Signed-off-by: Alexander Shishkin --- kernel/events/core.c | 5 +++-