Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-05-06 Thread Dave Gordon
On 06/05/16 09:55, Tvrtko Ursulin wrote: On 05/05/16 19:38, Dave Gordon wrote: On 29/04/2016 16:44, Tvrtko Ursulin wrote: On 27/04/16 19:03, Dave Gordon wrote: Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" conditio

Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-05-06 Thread Tvrtko Ursulin
On 05/05/16 19:38, Dave Gordon wrote: On 29/04/2016 16:44, Tvrtko Ursulin wrote: On 27/04/16 19:03, Dave Gordon wrote: Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" condition is impossible, so the previous runtime W

Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-05-05 Thread Dave Gordon
On 29/04/2016 16:44, Tvrtko Ursulin wrote: On 27/04/16 19:03, Dave Gordon wrote: Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" condition is impossible, so the previous runtime WARN_ON() is promoted to a GEM_BUG_ON() f

Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-05-03 Thread Tvrtko Ursulin
On 29/04/16 17:10, Chris Wilson wrote: On Fri, Apr 29, 2016 at 04:44:24PM +0100, Tvrtko Ursulin wrote: On 27/04/16 19:03, Dave Gordon wrote: Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" condition is impossible, so

Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-04-29 Thread Chris Wilson
On Fri, Apr 29, 2016 at 04:44:24PM +0100, Tvrtko Ursulin wrote: > > On 27/04/16 19:03, Dave Gordon wrote: > >Mostly little optimisations; for instance, if the driver is correctly > >following the submission protocol, the "out of space" condition is > >impossible, so the previous runtime WARN_ON()

Re: [Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-04-29 Thread Tvrtko Ursulin
On 27/04/16 19:03, Dave Gordon wrote: Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" condition is impossible, so the previous runtime WARN_ON() is promoted to a GEM_BUG_ON() for a more dramatic effect in development and

[Intel-gfx] [PATCH v2 4/5] drm/i915/guc: rework guc_add_workqueue_item()

2016-04-27 Thread Dave Gordon
Mostly little optimisations; for instance, if the driver is correctly following the submission protocol, the "out of space" condition is impossible, so the previous runtime WARN_ON() is promoted to a GEM_BUG_ON() for a more dramatic effect in development and less impact in end-user systems. Simila