I've long ago stopped trying to fully understand all the locking in
amdkfd, so maybe this is safe for a contrived reason. It's definitely
not how this should be done. Considers this more a request for a
proper patch.
Cc: Felix Kuehling <felix.kuehl...@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Simona Vetter <simona.vet...@intel.com>
Signed-off-by: Simona Vetter <simona.vet...@ffwll.ch>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 260165bbe373..aa51930a012b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1774,6 +1774,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
ret = drm_gem_handle_create(adev->kfd.client.file, gobj,
&(*mem)->gem_handle);
if (ret)
goto err_gem_handle_create;
+ /* FIXME: Thou shall completely initialize the bo before calling
+ * drm_gem_handle_create. Or explain why this is safe. */
bo = gem_to_amdgpu_bo(gobj);
if (bo_type == ttm_bo_type_sg) {
bo->tbo.sg = sg;
--
2.49.0
