Re: [Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-04 Thread Ville Syrjälä
On Thu, Apr 03, 2014 at 05:28:54PM +0200, Daniel Vetter wrote: > On Thu, Apr 03, 2014 at 01:21:38PM +0300, Ville Syrjälä wrote: > > On Thu, Apr 03, 2014 at 08:05:35AM +0100, Chris Wilson wrote: > > > On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > > > > We have been setting the bit

Re: [Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-03 Thread Daniel Vetter
On Thu, Apr 03, 2014 at 01:21:38PM +0300, Ville Syrjälä wrote: > On Thu, Apr 03, 2014 at 08:05:35AM +0100, Chris Wilson wrote: > > On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > > > We have been setting the bit which was originally BIOS dependent since: > > > commit f05bb0c7b624252

Re: [Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-03 Thread Ville Syrjälä
On Thu, Apr 03, 2014 at 08:05:35AM +0100, Chris Wilson wrote: > On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > > We have been setting the bit which was originally BIOS dependent since: > > commit f05bb0c7b624252a5e768287e340e8e45df96e42 > > Author: Chris Wilson > > Date: Sun Jan

Re: [Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-03 Thread Daniel Vetter
On Thu, Apr 03, 2014 at 08:05:35AM +0100, Chris Wilson wrote: > On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > > We have been setting the bit which was originally BIOS dependent since: > > commit f05bb0c7b624252a5e768287e340e8e45df96e42 > > Author: Chris Wilson > > Date: Sun Jan

Re: [Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-03 Thread Chris Wilson
On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > We have been setting the bit which was originally BIOS dependent since: > commit f05bb0c7b624252a5e768287e340e8e45df96e42 > Author: Chris Wilson > Date: Sun Jan 20 16:33:32 2013 + > > drm/i915: GFX_MODE Flush TLB Invalidate

[Intel-gfx] [PATCH] drm/i915: Invariably invalidate before ctx switch

2014-04-02 Thread Ben Widawsky
We have been setting the bit which was originally BIOS dependent since: commit f05bb0c7b624252a5e768287e340e8e45df96e42 Author: Chris Wilson Date: Sun Jan 20 16:33:32 2013 + drm/i915: GFX_MODE Flush TLB Invalidate Mode must be '1' for scanline waits Therefore, we do not need to try to