24 lines
930 B
Text
24 lines
930 B
Text
|
TODO
|
||
|
|
. Where should we do eviction (detatch_pages())? We aren't necessarily
|
||
|
|
accessing the pages via a GART, so maybe we need some other threshold
|
||
|
|
to put a cap on the # of pages that can be pin'd.
|
||
|
|
. Use mm_shrinker to trigger unpinning pages.
|
||
|
|
. This is mainly theoretical since most of these devices don't actually
|
||
|
|
have swap or harddrive.
|
||
|
|
. GEM/shmem backed pages can have existing mappings (kernel linear map,
|
||
|
|
etc..), which isn't really ideal.
|
||
|
|
. Revisit GEM sync object infrastructure.. TTM has some framework for this
|
||
|
|
already. Possibly this could be refactored out and made more common?
|
||
|
|
There should be some way to do this with less wheel-reinvention.
|
||
|
|
. This can be handled by the dma-buf fence/reservation stuff when it
|
||
|
|
lands
|
||
|
|
|
||
|
|
Userspace:
|
||
|
|
. git://anongit.freedesktop.org/xorg/driver/xf86-video-omap
|
||
|
|
|
||
|
|
Currently tested on
|
||
|
|
. OMAP3530 beagleboard
|
||
|
|
. OMAP4430 pandaboard
|
||
|
|
. OMAP4460 pandaboard
|
||
|
|
. OMAP5432 uEVM
|