Re: [Intel-gfx] [PATCH 14/41] drm/i915: Use a radixtree for random access to the object's backing storage

2016-10-17 Thread Chris Wilson
On Mon, Oct 17, 2016 at 10:56:27AM +0100, Tvrtko Ursulin wrote: > > On 14/10/2016 15:07, Chris Wilson wrote: > >On Fri, Oct 14, 2016 at 02:32:03PM +0100, Tvrtko Ursulin wrote: > >>On 14/10/2016 13:18, Chris Wilson wrote: > >>>A while ago we switched from a contiguous array of pages into an sglist,

Re: [Intel-gfx] [PATCH 14/41] drm/i915: Use a radixtree for random access to the object's backing storage

2016-10-17 Thread Tvrtko Ursulin
On 14/10/2016 15:07, Chris Wilson wrote: On Fri, Oct 14, 2016 at 02:32:03PM +0100, Tvrtko Ursulin wrote: On 14/10/2016 13:18, Chris Wilson wrote: A while ago we switched from a contiguous array of pages into an sglist, for that was both more convenient for mapping to hardware and avoided the r

Re: [Intel-gfx] [PATCH 14/41] drm/i915: Use a radixtree for random access to the object's backing storage

2016-10-14 Thread Chris Wilson
On Fri, Oct 14, 2016 at 02:32:03PM +0100, Tvrtko Ursulin wrote: > > On 14/10/2016 13:18, Chris Wilson wrote: > >A while ago we switched from a contiguous array of pages into an sglist, > >for that was both more convenient for mapping to hardware and avoided > >the requirement for a vmalloc array o

Re: [Intel-gfx] [PATCH 14/41] drm/i915: Use a radixtree for random access to the object's backing storage

2016-10-14 Thread Tvrtko Ursulin
On 14/10/2016 13:18, Chris Wilson wrote: A while ago we switched from a contiguous array of pages into an sglist, for that was both more convenient for mapping to hardware and avoided the requirement for a vmalloc array of pages on every object. However, certain GEM API calls (like pwrite, pread