[PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread Daniel Vetter
On Mon, Jul 01, 2013 at 09:54:17PM +0200, David Herrmann wrote: > On Mon, Jul 1, 2013 at 9:42 PM, Daniel Vetter wrote: > > On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: > >> +/** drm_vma_offset_manager_destroy() > >> + * > >> + * Destroy an object manager which was previously

[PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread David Herrmann
Hi On Mon, Jul 1, 2013 at 9:42 PM, Daniel Vetter wrote: > On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: >> If we want to map GPU memory into user-space, we need to linearize the >> addresses to not confuse mm-core. Currently, GEM and TTM both implement >> their own

[PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread Daniel Vetter
On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: > If we want to map GPU memory into user-space, we need to linearize the > addresses to not confuse mm-core. Currently, GEM and TTM both implement > their own offset-managers to assign a pgoff to each object for user-space > CPU

[PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread David Herrmann
If we want to map GPU memory into user-space, we need to linearize the addresses to not confuse mm-core. Currently, GEM and TTM both implement their own offset-managers to assign a pgoff to each object for user-space CPU access. GEM uses a hash-table, TTM uses an rbtree. This patch provides a

[PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread David Herrmann
If we want to map GPU memory into user-space, we need to linearize the addresses to not confuse mm-core. Currently, GEM and TTM both implement their own offset-managers to assign a pgoff to each object for user-space CPU access. GEM uses a hash-table, TTM uses an rbtree. This patch provides a

Re: [PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread Daniel Vetter
On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: If we want to map GPU memory into user-space, we need to linearize the addresses to not confuse mm-core. Currently, GEM and TTM both implement their own offset-managers to assign a pgoff to each object for user-space CPU access.

Re: [PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread David Herrmann
Hi On Mon, Jul 1, 2013 at 9:42 PM, Daniel Vetter dan...@ffwll.ch wrote: On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: If we want to map GPU memory into user-space, we need to linearize the addresses to not confuse mm-core. Currently, GEM and TTM both implement their own

Re: [PATCH 3/6] drm: add unified vma offset manager

2013-07-01 Thread Daniel Vetter
On Mon, Jul 01, 2013 at 09:54:17PM +0200, David Herrmann wrote: On Mon, Jul 1, 2013 at 9:42 PM, Daniel Vetter dan...@ffwll.ch wrote: On Mon, Jul 01, 2013 at 08:33:00PM +0200, David Herrmann wrote: +/** drm_vma_offset_manager_destroy() + * + * Destroy an object manager which was previously