drm/amdgpu: put gtt at 0 in the internal address space

There still seem to be some blocks that make accesses
in the lower part of the address space.  This works around
this.

Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2016-11-17 15:40:22 -05:00
parent dc3abc16a7
commit 9dc5a91e4d
1 changed files with 1 additions and 1 deletions

View File

@ -602,7 +602,7 @@ void amdgpu_gtt_location(struct amdgpu_device *adev, struct amdgpu_mc *mc)
dev_warn(adev->dev, "limiting GTT\n");
mc->gtt_size = size_bf;
}
mc->gtt_start = (mc->vram_start & ~mc->gtt_base_align) - mc->gtt_size;
mc->gtt_start = 0;
} else {
if (mc->gtt_size > size_af) {
dev_warn(adev->dev, "limiting GTT\n");