Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux

drm/amdgpu: use top down allocation for non-CPU accessible vram

Should help avoid fragmentation of vram due to CPU access
requirements.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

+1 -1
+1 -1
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
··· 127 127 placements[c].fpfn = 128 128 adev->mc.visible_vram_size >> PAGE_SHIFT; 129 129 placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | 130 - TTM_PL_FLAG_VRAM; 130 + TTM_PL_FLAG_VRAM | TTM_PL_FLAG_TOPDOWN; 131 131 } 132 132 placements[c].fpfn = 0; 133 133 placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |