Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-11-12 Thread Francisco Jerez
Chris Wilson writes: > Quoting Francisco Jerez (2019-07-24 21:37:24) >> Chris Wilson writes: >> >> > Since userspace has the ability to bypass the CPU cache from within its >> > unprivileged command stream, we have to flush the CPU cache to memory >> > in order to overwrite the previous

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-11-12 Thread Chris Wilson
Quoting Francisco Jerez (2019-07-24 21:37:24) > Chris Wilson writes: > > > Since userspace has the ability to bypass the CPU cache from within its > > unprivileged command stream, we have to flush the CPU cache to memory > > in order to overwrite the previous contents on creation. > > > >

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-24 Thread Francisco Jerez
Chris Wilson writes: > Since userspace has the ability to bypass the CPU cache from within its > unprivileged command stream, we have to flush the CPU cache to memory > in order to overwrite the previous contents on creation. > > Signed-off-by: Chris Wilson > Cc: Joonas Lahtinen > Cc:

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-20 Thread Chris Wilson
Quoting Jason Ekstrand (2019-07-19 23:55:03) > Just to be clear, is this just adding a CLFLUSH or is it actually changing the > default caching state of buffers from CACHED to NONE?  If it's actually > changing the default state, that's going to break userspace badly. What userspace is actually

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-19 Thread Jason Ekstrand
Just to be clear, is this just adding a CLFLUSH or is it actually changing the default caching state of buffers from CACHED to NONE? If it's actually changing the default state, that's going to break userspace badly. --Jason On Fri, Jul 19, 2019 at 5:21 AM Chris Wilson wrote: > Quoting Lionel

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-19 Thread Chris Wilson
Quoting Lionel Landwerlin (2019-07-19 11:18:42) > On 18/07/2019 17:54, Chris Wilson wrote: > > Since userspace has the ability to bypass the CPU cache from within its > > unprivileged command stream, we have to flush the CPU cache to memory > > in order to overwrite the previous contents on

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-19 Thread Lionel Landwerlin
On 18/07/2019 17:54, Chris Wilson wrote: Since userspace has the ability to bypass the CPU cache from within its unprivileged command stream, we have to flush the CPU cache to memory in order to overwrite the previous contents on creation. Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc:

Re: [Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-19 Thread Joonas Lahtinen
Quoting Chris Wilson (2019-07-18 17:54:06) > Since userspace has the ability to bypass the CPU cache from within its > unprivileged command stream, we have to flush the CPU cache to memory > in order to overwrite the previous contents on creation. > > Signed-off-by: Chris Wilson > Cc: Joonas

[Intel-gfx] [PATCH 3/4] drm/i915: Flush all user surfaces prior to first use

2019-07-18 Thread Chris Wilson
Since userspace has the ability to bypass the CPU cache from within its unprivileged command stream, we have to flush the CPU cache to memory in order to overwrite the previous contents on creation. Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: stablevger.kernel.org ---