diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 82c8809d1d9c..9cc71a3a5362 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -540,6 +540,15 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que amdgpu_userq_cleanup(queue); mutex_unlock(&uq_mgr->userq_mutex); + /* + * A failed unmap means MES could not remove the hung queue and is now + * unresponsive. Recover the GPU here so the wedged MES does not fail + * the next, unrelated queue submission and trigger a reset attributed + * to an innocent workload. + */ + if (r) + queue_work(adev->reset_domain->wq, &uq_mgr->reset_work); + cancel_delayed_work_sync(&queue->hang_detect_work); uq_funcs->mqd_destroy(queue); queue->userq_mgr = NULL;