Re: [Intel-gfx] [PATCH] drm/i915: Move tasklet kicking to __i915_request_queue caller

2019-08-15 Thread Mika Kuoppala
Chris Wilson writes: > Quoting Mika Kuoppala (2019-08-15 12:35:37) >> Chris Wilson writes: >> >> > Since __i915_request_queue() may be called from hardirq (timer) context, >> > we cannot use local_bh_disable/enable at the lower level. As we do want >> > to kick the tasklet to speed up initial

Re: [Intel-gfx] [PATCH] drm/i915: Move tasklet kicking to __i915_request_queue caller

2019-08-15 Thread Chris Wilson
Quoting Mika Kuoppala (2019-08-15 12:35:37) > Chris Wilson writes: > > > Since __i915_request_queue() may be called from hardirq (timer) context, > > we cannot use local_bh_disable/enable at the lower level. As we do want > > to kick the tasklet to speed up initial submission or preemption for >

Re: [Intel-gfx] [PATCH] drm/i915: Move tasklet kicking to __i915_request_queue caller

2019-08-15 Thread Mika Kuoppala
Chris Wilson writes: > Since __i915_request_queue() may be called from hardirq (timer) context, > we cannot use local_bh_disable/enable at the lower level. As we do want > to kick the tasklet to speed up initial submission or preemption for > normal client submission, lift it to the normal

[Intel-gfx] [PATCH] drm/i915: Move tasklet kicking to __i915_request_queue caller

2019-08-14 Thread Chris Wilson
Since __i915_request_queue() may be called from hardirq (timer) context, we cannot use local_bh_disable/enable at the lower level. As we do want to kick the tasklet to speed up initial submission or preemption for normal client submission, lift it to the normal process context callpath.