diff options
| author | Deepak Nibade <dnibade@nvidia.com> | 2016-08-04 10:26:42 -0400 |
|---|---|---|
| committer | mobile promotions <svcmobile_promotions@nvidia.com> | 2016-09-01 12:10:00 -0400 |
| commit | c845b210129a4a2ebd8a3cd22c53dc30cad3664d (patch) | |
| tree | 41c60205ce8927ef9062aa4a257fd9d8bdf8a4d5 /drivers/gpu/nvgpu/gk20a/mm_gk20a.h | |
| parent | c38cc24e1a752d6eb5b07d771ddbf6ab700f695d (diff) | |
gpu: nvgpu: support GMMU mappings for vidmem page allocator
Switch to use page allocator for vidmem
Support GMMU mappings for page (non-contiguous page allocator)
in update_gmmu_ptes_locked()
If aperture is VIDMEM, traverse each chunk in an allocation
and map it to GPU VA separately
Fix CE page clearing to support page allocator
Fix gk20a_pramin_enter() to get base address from new
allocator
Define API gk20a_mem_get_vidmem_addr() to get base address
of allocation. Note that this API should not be used if we
have more than 1 chunk
Jira DNVGPU-96
Change-Id: I725422f3538aeb477ca4220ba57ef8b3c53db703
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1199177
(cherry picked from commit 1afae6ee6529ab88cedd5bcbe458fbdc0d4b1fd8)
Reviewed-on: http://git-master/r/1197647
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Diffstat (limited to 'drivers/gpu/nvgpu/gk20a/mm_gk20a.h')
0 files changed, 0 insertions, 0 deletions