drm/amdgpu: amdgpu_device_recover_vram got NULL of shadow->parent

amdgpu_bo_destroy had a bug by calling amdgpu_bo_unref outside mutex_lock.
If amdgpu_device_recover_vram executed between amdgpu_bo_unref and list_del_init,
it would get NULL of shadow->parent, then caused Call Trace and GPU reset failed.

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

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ec9e450..93b2c5a 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -88,12 +88,14 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
        if (bo->gem_base.import_attach)
                drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg);
        drm_gem_object_release(&bo->gem_base);
-       amdgpu_bo_unref(&bo->parent);
+       /* in case amdgpu_device_recover_vram got NULL of bo->parent */
        if (!list_empty(&bo->shadow_list)) {
                mutex_lock(&adev->shadow_list_lock);
                list_del_init(&bo->shadow_list);
                mutex_unlock(&adev->shadow_list_lock);
        }
+       amdgpu_bo_unref(&bo->parent);
+
        kfree(bo->metadata);
        kfree(bo);
 }