Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-23 Thread Chris Wilson
On Mon, Feb 22, 2016 at 12:42:48PM -0800, Jesse Barnes wrote: > On 02/20/2016 01:22 AM, Chris Wilson wrote: > > On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: > >> On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: > >>> From: John Harrison > >>> >

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-22 Thread Jesse Barnes
On 02/20/2016 01:22 AM, Chris Wilson wrote: > On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: >> On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: >>> From: John Harrison >>> >>> MMIO flips are the preferred mechanism now > > Because introducing

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-22 Thread John Harrison
So is the summary that currently MMIO flips do not work on some platforms? That could be a problem because the scheduler is intended to be enabled for everything and thus will be forcing MMIO flips on everything. So should I reverse the logic here - only enable the scheduler if MMIO flips are

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-22 Thread Lankhorst, Maarten
Hey, Jesse Barnes schreef op vr 19-02-2016 om 12:01 [-0800]: > On 02/19/2016 11:53 AM, Ville Syrjälä wrote: > > On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: > >> On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: > >>> From: John Harrison > >>>

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-20 Thread Chris Wilson
On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: > On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: > > From: John Harrison > > > > MMIO flips are the preferred mechanism now Because introducing variable latency in waking up a big core is a good

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-19 Thread Jesse Barnes
On 02/19/2016 11:53 AM, Ville Syrjälä wrote: > On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: >> On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: >>> From: John Harrison >>> >>> MMIO flips are the preferred mechanism now but more importantly, pipe

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-19 Thread Ville Syrjälä
On Fri, Feb 19, 2016 at 11:28:05AM -0800, Jesse Barnes wrote: > On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: > > From: John Harrison > > > > MMIO flips are the preferred mechanism now but more importantly, pipe > > based flips cause issues for the

Re: [Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-19 Thread Jesse Barnes
On 02/18/2016 06:26 AM, john.c.harri...@intel.com wrote: > From: John Harrison > > MMIO flips are the preferred mechanism now but more importantly, pipe > based flips cause issues for the scheduler. Specifically, submitting > work to the rings around the side of the

[Intel-gfx] [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled

2016-02-18 Thread John . C . Harrison
From: John Harrison MMIO flips are the preferred mechanism now but more importantly, pipe based flips cause issues for the scheduler. Specifically, submitting work to the rings around the side of the scheduler could cause that work to be lost if the scheduler generates