[Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-23 Thread Chris Wilson
In the idle worker we drop the prolonged GT wakeref used to cover such essentials as interrupt delivery. (When a CS interrupt arrives, we also assert that the GT is awake.) However, it turns out that 10ms is not long enough to be assured that the last CS interrupt has been delivered, so bump that t

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-23 Thread Chris Wilson
Quoting Mika Kuoppala (2017-10-23 12:52:11) > Chris Wilson writes: > > > In the idle worker we drop the prolonged GT wakeref used to cover such > > essentials as interrupt delivery. (When a CS interrupt arrives, we also > > assert that the GT is awake.) However, it turns out that 10ms is not > >

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-23 Thread Mika Kuoppala
Chris Wilson writes: > In the idle worker we drop the prolonged GT wakeref used to cover such > essentials as interrupt delivery. (When a CS interrupt arrives, we also > assert that the GT is awake.) However, it turns out that 10ms is not > long enough to be assured that the last CS interrupt has

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-20 Thread Chris Wilson
Quoting Mika Kuoppala (2017-10-20 14:23:02) > Chris Wilson writes: > > > Quoting Mika Kuoppala (2017-10-20 14:11:53) > >> Chris Wilson writes: > >> > >> > In the idle worker we drop the prolonged GT wakeref used to cover such > >> > essentials as interrupt delivery. (When a CS interrupt arrives

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-20 Thread Mika Kuoppala
Chris Wilson writes: > Quoting Mika Kuoppala (2017-10-20 14:11:53) >> Chris Wilson writes: >> >> > In the idle worker we drop the prolonged GT wakeref used to cover such >> > essentials as interrupt delivery. (When a CS interrupt arrives, we also >> > assert that the GT is awake.) However, it t

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-20 Thread Chris Wilson
Quoting Mika Kuoppala (2017-10-20 14:11:53) > Chris Wilson writes: > > > In the idle worker we drop the prolonged GT wakeref used to cover such > > essentials as interrupt delivery. (When a CS interrupt arrives, we also > > assert that the GT is awake.) However, it turns out that 10ms is not > >

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-20 Thread Mika Kuoppala
Chris Wilson writes: > In the idle worker we drop the prolonged GT wakeref used to cover such > essentials as interrupt delivery. (When a CS interrupt arrives, we also > assert that the GT is awake.) However, it turns out that 10ms is not > long enough to be assured that the last CS interrupt has

[Intel-gfx] [PATCH 1/2] drm/i915: Bump wait-times for the final CS interrupt before parking

2017-10-20 Thread Chris Wilson
In the idle worker we drop the prolonged GT wakeref used to cover such essentials as interrupt delivery. (When a CS interrupt arrives, we also assert that the GT is awake.) However, it turns out that 10ms is not long enough to be assured that the last CS interrupt has been delivered, so bump that t