Re: [Intel-gfx] [PATCH] drm/i915: Kill the tasklet then disable

2017-02-13 Thread Chris Wilson
On Mon, Feb 13, 2017 at 12:00:13PM +0200, Mika Kuoppala wrote: > Chris Wilson writes: > > > Disabling the tasklet leaves it if scheduled on the ready to run list > > until it is re-enabled. This will leave the ksoftird thread spinning > > until satisfied. To prevent this situation on starting the

Re: [Intel-gfx] [PATCH] drm/i915: Kill the tasklet then disable

2017-02-13 Thread Mika Kuoppala
Chris Wilson writes: > Disabling the tasklet leaves it if scheduled on the ready to run list > until it is re-enabled. This will leave the ksoftird thread spinning > until satisfied. To prevent this situation on starting the GPU reset, we > want to kill the tasklet first and then disable. The sam

Re: [Intel-gfx] [PATCH] drm/i915: Kill the tasklet then disable

2017-02-12 Thread Chris Wilson
On Sun, Feb 12, 2017 at 10:31:48AM +, Chris Wilson wrote: > Disabling the tasklet leaves it if scheduled on the ready to run list > until it is re-enabled. This will leave the ksoftird thread spinning > until satisfied. To prevent this situation on starting the GPU reset, we > want to kill the

[Intel-gfx] [PATCH] drm/i915: Kill the tasklet then disable

2017-02-12 Thread Chris Wilson
Disabling the tasklet leaves it if scheduled on the ready to run list until it is re-enabled. This will leave the ksoftird thread spinning until satisfied. To prevent this situation on starting the GPU reset, we want to kill the tasklet first and then disable. The same problem will arise when a tas