diff options
| author | Christian König <christian.koenig@amd.com> | 2017-12-22 17:13:03 +0100 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2017-12-27 11:34:31 -0500 |
| commit | 727ffdf2ac6d165f611b1accdf7f6ca770595aea (patch) | |
| tree | bbc4600f81b5ca147fbd6e5186e726863343565f /drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | |
| parent | 6a83a553033d6c3d8fb4683a9c87833ace44121b (diff) | |
drm/amdgpu: fix VM faults with per VM BOs
There was a small window between unreserve and second reserve where the
freshly allocated BO could have been evicted without the VM noticing it.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 22 |
1 files changed, 20 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index af7dceb7131e..e623109be202 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1745,8 +1745,26 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, INIT_LIST_HEAD(&bo_va->valids); INIT_LIST_HEAD(&bo_va->invalids); - if (bo) - list_add_tail(&bo_va->base.bo_list, &bo->va); + if (!bo) + return bo_va; + + list_add_tail(&bo_va->base.bo_list, &bo->va); + + if (bo->tbo.resv != vm->root.base.bo->tbo.resv) + return bo_va; + + if (bo->preferred_domains & + amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type)) + return bo_va; + + /* + * We checked all the prerequisites, but it looks like this per VM BO + * is currently evicted. add the BO to the evicted list to make sure it + * is validated on next VM use to avoid fault. + * */ + spin_lock(&vm->status_lock); + list_move_tail(&bo_va->base.vm_status, &vm->evicted); + spin_unlock(&vm->status_lock); return bo_va; } |