Commit | Line | Data |
---|---|---|
8bb0daff RC |
1 | TODO |
2 | . Where should we do eviction (detatch_pages())? We aren't necessarily | |
3 | accessing the pages via a GART, so maybe we need some other threshold | |
4 | to put a cap on the # of pages that can be pin'd. | |
5 | . Use mm_shrinker to trigger unpinning pages. | |
6 | . This is mainly theoretical since most of these devices don't actually | |
7 | have swap or harddrive. | |
8 | . GEM/shmem backed pages can have existing mappings (kernel linear map, | |
9 | etc..), which isn't really ideal. | |
10 | . Revisit GEM sync object infrastructure.. TTM has some framework for this | |
11 | already. Possibly this could be refactored out and made more common? | |
12 | There should be some way to do this with less wheel-reinvention. | |
13 | . This can be handled by the dma-buf fence/reservation stuff when it | |
14 | lands | |
15 | ||
16 | Userspace: | |
17 | . git://anongit.freedesktop.org/xorg/driver/xf86-video-omap | |
18 | ||
19 | Currently tested on | |
20 | . OMAP3530 beagleboard | |
21 | . OMAP4430 pandaboard | |
22 | . OMAP4460 pandaboard | |
23 | . OMAP5432 uEVM |