Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-12-01 Thread Goel, Akash
On 11/30/2015 1:45 PM, Daniel Vetter wrote: On Mon, Nov 30, 2015 at 11:54:14AM +0530, Goel, Akash wrote: On 11/25/2015 3:30 PM, Daniel Vetter wrote: On Wed, Nov 25, 2015 at 02:57:47PM +0530, Goel, Akash wrote: On 11/25/2015 2:51 PM, Daniel Vetter wrote: On Tue, Nov 24, 2015 at 10:39:38P

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-30 Thread Daniel Vetter
On Mon, Nov 30, 2015 at 11:54:14AM +0530, Goel, Akash wrote: > > > On 11/25/2015 3:30 PM, Daniel Vetter wrote: > >On Wed, Nov 25, 2015 at 02:57:47PM +0530, Goel, Akash wrote: > >> > >> > >>On 11/25/2015 2:51 PM, Daniel Vetter wrote: > >>>On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrot

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-29 Thread Goel, Akash
On 11/25/2015 3:30 PM, Daniel Vetter wrote: On Wed, Nov 25, 2015 at 02:57:47PM +0530, Goel, Akash wrote: On 11/25/2015 2:51 PM, Daniel Vetter wrote: On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: On Tue, Nov 24,

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-26 Thread Chris Wilson
On Thu, Nov 26, 2015 at 09:09:37AM +0530, Goel, Akash wrote: > > > On 11/25/2015 10:58 PM, Chris Wilson wrote: > >On Wed, Nov 25, 2015 at 01:02:20PM +0200, Ville Syrjälä wrote: > >>On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: > >>>On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Goel, Akash
On 11/25/2015 10:58 PM, Chris Wilson wrote: On Wed, Nov 25, 2015 at 01:02:20PM +0200, Ville Syrjälä wrote: On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrot

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Chris Wilson
On Wed, Nov 25, 2015 at 01:02:20PM +0200, Ville Syrjälä wrote: > On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: > > On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: > > > On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: > > > > On Tue, Nov 24, 2015 at 03:3

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Ville Syrjälä
On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: > On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: > > On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: > > > On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > > > > From: Akash Goel > >

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Daniel Vetter
On Wed, Nov 25, 2015 at 02:57:47PM +0530, Goel, Akash wrote: > > > On 11/25/2015 2:51 PM, Daniel Vetter wrote: > >On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: > >>On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: > >>>On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville S

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Goel, Akash
On 11/25/2015 2:51 PM, Daniel Vetter wrote: On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.c

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-25 Thread Daniel Vetter
On Tue, Nov 24, 2015 at 10:39:38PM +, Chris Wilson wrote: > On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: > > On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: > > > On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > > > > From: Akash Goel > >

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-24 Thread Chris Wilson
On Tue, Nov 24, 2015 at 07:14:31PM +0100, Daniel Vetter wrote: > On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: > > On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > > > From: Akash Goel > > > > > > When the object is moved out of CPU read domain, the cacheli

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-24 Thread Daniel Vetter
On Tue, Nov 24, 2015 at 12:04:06PM +0200, Ville Syrjälä wrote: > On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > > From: Akash Goel > > > > When the object is moved out of CPU read domain, the cachelines > > are not invalidated immediately. The invalidation is deferred til

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-24 Thread Chris Wilson
On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > From: Akash Goel > > When the object is moved out of CPU read domain, the cachelines > are not invalidated immediately. The invalidation is deferred till > next time the object is brought back into CPU read domain. > But the

Re: [Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-24 Thread Ville Syrjälä
On Tue, Nov 24, 2015 at 03:35:24PM +0530, akash.g...@intel.com wrote: > From: Akash Goel > > When the object is moved out of CPU read domain, the cachelines > are not invalidated immediately. The invalidation is deferred till > next time the object is brought back into CPU read domain. > But the

[Intel-gfx] [PATCH] drm/i915 : Avoid superfluous invalidation of CPU cache lines

2015-11-24 Thread akash . goel
From: Akash Goel When the object is moved out of CPU read domain, the cachelines are not invalidated immediately. The invalidation is deferred till next time the object is brought back into CPU read domain. But the invalidation is done unconditionally, i.e. even for the case where the cachelines