Re: [Intel-gfx] [PATCH 3/3] drm/i915: add fences to the request struct

2014-12-04 Thread Chris Wilson
On Wed, Dec 03, 2014 at 11:49:07AM -0800, Jesse Barnes wrote: This simplifies the sync code quite a bit. I don't think we'll be able to get away with using the core fence code's seqno support, since we'll be moving away from simple seqno comparisions with the scheduler and preemption, but the

Re: [Intel-gfx] [PATCH 3/3] drm/i915: add fences to the request struct

2014-12-04 Thread Daniel Vetter
On Thu, Dec 04, 2014 at 09:13:21AM +, Chris Wilson wrote: On Wed, Dec 03, 2014 at 11:49:07AM -0800, Jesse Barnes wrote: This simplifies the sync code quite a bit. I don't think we'll be able to get away with using the core fence code's seqno support, since we'll be moving away from

Re: [Intel-gfx] [PATCH 3/3] drm/i915: add fences to the request struct

2014-12-04 Thread Chris Wilson
On Thu, Dec 04, 2014 at 12:05:34PM +0100, Daniel Vetter wrote: On Thu, Dec 04, 2014 at 09:13:21AM +, Chris Wilson wrote: On Wed, Dec 03, 2014 at 11:49:07AM -0800, Jesse Barnes wrote: This simplifies the sync code quite a bit. I don't think we'll be able to get away with using the

Re: [Intel-gfx] [PATCH 3/3] drm/i915: add fences to the request struct

2014-12-04 Thread Daniel Vetter
On Thu, Dec 4, 2014 at 12:29 PM, Chris Wilson ch...@chris-wilson.co.uk wrote: It uses locked atomic operations, which are unnecessary for the very frequent is-complete checks (due to the nice ordering constraints of x86). So let's look at the fastpaths: - fence already signaled: Just a test_bit

[Intel-gfx] [PATCH 3/3] drm/i915: add fences to the request struct

2014-12-03 Thread Jesse Barnes
This simplifies the sync code quite a bit. I don't think we'll be able to get away with using the core fence code's seqno support, since we'll be moving away from simple seqno comparisions with the scheduler and preemption, but the additional code is pretty minimal anyway, and lets us add