[PATCH 4/5] drm/omap: use __GFP_DMA32 for shmem-backed gem

Hi, On 02/06/14 16:03, David Herrmann wrote: > Hi Tomi > > Any chance you could give this a spin on an omap device? It shouldn't > affect any 32bit devices, so this is mostly a cosmetic change. > However, I'd really like to get rid of that 'TODO' item. So a > "Tested-by:" would be really nice. I

[PATCH 4/5] drm/omap: use __GFP_DMA32 for shmem-backed gem

Hi On Thu, Jun 5, 2014 at 4:04 PM, Rob Clark wrote: > On Thu, Jun 5, 2014 at 9:52 AM, Tomi Valkeinen > wrote: >> Hi, >> >> On 02/06/14 16:03, David Herrmann wrote: >>> Hi Tomi >>> >>> Any chance you could give this a spin on an omap device? It shouldn't >>> affect any 32bit devices, so this is

[PATCH 4/5] drm/omap: use __GFP_DMA32 for shmem-backed gem

On Thu, Jun 5, 2014 at 9:52 AM, Tomi Valkeinen wrote: > Hi, > > On 02/06/14 16:03, David Herrmann wrote: >> Hi Tomi >> >> Any chance you could give this a spin on an omap device? It shouldn't >> affect any 32bit devices, so this is mostly a cosmetic change. >> However, I'd really like to get rid o

[PATCH 4/5] drm/omap: use __GFP_DMA32 for shmem-backed gem

Hi Tomi Any chance you could give this a spin on an omap device? It shouldn't affect any 32bit devices, so this is mostly a cosmetic change. However, I'd really like to get rid of that 'TODO' item. So a "Tested-by:" would be really nice. Thanks David On Sun, May 25, 2014 at 2:34 PM, David Herrma

[PATCH 4/5] drm/omap: use __GFP_DMA32 for shmem-backed gem

OMAP requires bo-pages to be in the DMA32 zone. Explicitly request this by setting __GFP_DMA32 as mapping-gfp-mask during shmem initialization. This drops HIGHMEM from the gfp-mask and uses DMA32 instead. shmem-core takes care to relocate pages during swap-in in case they have been loaded into the