]> git.proxmox.com Git - mirror_ubuntu-eoan-kernel.git/commit
drm/amdgpu: Fix silent amdgpu_bo_move failures
authorFelix Kuehling <Felix.Kuehling@amd.com>
Sat, 13 Jul 2019 06:27:34 +0000 (02:27 -0400)
committerAlex Deucher <alexander.deucher@amd.com>
Wed, 17 Jul 2019 18:34:30 +0000 (13:34 -0500)
commit67adb569ddf4aee12de999e02c67c1a168dd1a15
treebd8b1c798ac090176d2c479c6cd74fbbf4a51e4c
parent6ea624f60393edc114feb33fa738d6f2f47e9032
drm/amdgpu: Fix silent amdgpu_bo_move failures

Under memory pressure, buffer moves between RAM to VRAM  can
fail when there is no GTT space available. In those cases
amdgpu_bo_move falls back to ttm_bo_move_memcpy, which seems to
succeed, although it doesn't really support non-contiguous or
invisible VRAM. This manifests as VM faults with corrupted page
table entries in KFD eviction stress tests.

Print some helpful messages when lack of GTT space is causing buffer
moves to fail. Check that source and destination memory regions are
supported by ttm_bo_move_memcpy before taking that fallback.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c