drm/amdgpu: fix VM faults with per VM BOs (727ffdf2) · Commits · 戴 / test

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>

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

+20 −2

Original line number	Diff line number	Diff line
		@@ -1745,9 +1745,27 @@ 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)
		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;
		}

Admin message