Re: [Intel-gfx] [PATCH 09/18] drm/i915: possibly invalidate TLB before context switch

2012-03-30 Thread Daniel Vetter
On Fri, Mar 30, 2012 at 11:39:53AM -0700, Ben Widawsky wrote: > On Thu, 29 Mar 2012 21:25:49 +0200 > Daniel Vetter wrote: > > > On Sun, Mar 18, 2012 at 01:39:49PM -0700, Ben Widawsky wrote: > > > From http://intellinuxgraphics.org/documentation/SNB/IHD_OS_Vol1_Part3.pdf > > > > > > [DevSNB] If F

Re: [Intel-gfx] [PATCH 09/18] drm/i915: possibly invalidate TLB before context switch

2012-03-30 Thread Ben Widawsky
On Thu, 29 Mar 2012 21:25:49 +0200 Daniel Vetter wrote: > On Sun, Mar 18, 2012 at 01:39:49PM -0700, Ben Widawsky wrote: > > From http://intellinuxgraphics.org/documentation/SNB/IHD_OS_Vol1_Part3.pdf > > > > [DevSNB] If Flush TLB invalidation Mode is enabled it’s the driver’s > > responsibility t

Re: [Intel-gfx] [PATCH 09/18] drm/i915: possibly invalidate TLB before context switch

2012-03-29 Thread Daniel Vetter
On Sun, Mar 18, 2012 at 01:39:49PM -0700, Ben Widawsky wrote: > From http://intellinuxgraphics.org/documentation/SNB/IHD_OS_Vol1_Part3.pdf > > [DevSNB] If Flush TLB invalidation Mode is enabled it’s the driver’s > responsibility to invalidate the TLBs at least once after the previous > context swi

[Intel-gfx] [PATCH 09/18] drm/i915: possibly invalidate TLB before context switch

2012-03-18 Thread Ben Widawsky
From http://intellinuxgraphics.org/documentation/SNB/IHD_OS_Vol1_Part3.pdf [DevSNB] If Flush TLB invalidation Mode is enabled it’s the driver’s responsibility to invalidate the TLBs at least once after the previous context switch after any GTT mappings changed (including new GTT entries). This ca