Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-07-20 Thread Chris Wilson
On Tue, Jul 15, 2014 at 08:30:33PM -0700, Ben Widawsky wrote: On Tue, Jul 15, 2014 at 04:15:08PM +0200, Daniel Vetter wrote: On Thu, Apr 24, 2014 at 02:47:48PM -0700, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-07-20 Thread Ben Widawsky
On Sun, Jul 20, 2014 at 09:29:55AM +0100, Chris Wilson wrote: On Tue, Jul 15, 2014 at 08:30:33PM -0700, Ben Widawsky wrote: On Tue, Jul 15, 2014 at 04:15:08PM +0200, Daniel Vetter wrote: On Thu, Apr 24, 2014 at 02:47:48PM -0700, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-07-15 Thread Daniel Vetter
On Thu, Apr 24, 2014 at 02:47:48PM -0700, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten to access them directly on many architectures, we have to read them through the GTT aperture. If they are not accessible through

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-07-15 Thread Ben Widawsky
On Tue, Jul 15, 2014 at 04:15:08PM +0200, Daniel Vetter wrote: On Thu, Apr 24, 2014 at 02:47:48PM -0700, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten to access them directly on many architectures, we have to read

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-04-24 Thread Ben Widawsky
On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten to access them directly on many architectures, we have to read them through the GTT aperture. If they are not accessible through the aperture, then we have to abort. This was complicated by

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-03-05 Thread Chris Wilson
On Tue, Mar 04, 2014 at 10:01:56PM +, Chris Wilson wrote: On Tue, Mar 04, 2014 at 01:27:05PM -0800, Ben Widawsky wrote: On Tue, Mar 04, 2014 at 03:45:56PM +0100, Daniel Vetter wrote: On Tue, Feb 18, 2014 at 11:18:04AM -0800, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-03-04 Thread Daniel Vetter
On Tue, Feb 18, 2014 at 11:18:04AM -0800, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten to access them directly on many architectures, we have to read them through the GTT aperture. If they are not accessible through

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-03-04 Thread Ben Widawsky
On Tue, Mar 04, 2014 at 03:45:56PM +0100, Daniel Vetter wrote: On Tue, Feb 18, 2014 at 11:18:04AM -0800, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten to access them directly on many architectures, we have to read

Re: [Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-03-04 Thread Chris Wilson
On Tue, Mar 04, 2014 at 01:27:05PM -0800, Ben Widawsky wrote: On Tue, Mar 04, 2014 at 03:45:56PM +0100, Daniel Vetter wrote: On Tue, Feb 18, 2014 at 11:18:04AM -0800, Ben Widawsky wrote: On Wed, Feb 12, 2014 at 07:18:40PM +, Chris Wilson wrote: For stolen pages, since it is verboten

[Intel-gfx] [PATCH] drm/i915: Do not access stolen memory directly by the CPU, even for error capture

2014-02-12 Thread Chris Wilson
For stolen pages, since it is verboten to access them directly on many architectures, we have to read them through the GTT aperture. If they are not accessible through the aperture, then we have to abort. This was complicated by commit 8b6124a633d8095b0c8364f585edff9c59568a96 Author: Chris