ttm_device_delayed_workqueue would reschedule itself if there is pending BO to be destroyed. So just one flush + cancel_sync is not enough. We still see lru_list not empty warnging.
Fix it by waiting all BO to be destroyed. Signed-off-by: xinhui pan <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6f47726f1765..e249923eb9a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3957,11 +3957,17 @@ static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev) */ void amdgpu_device_fini_hw(struct amdgpu_device *adev) { + int pending = 1; + dev_info(adev->dev, "amdgpu: finishing device.\n"); flush_delayed_work(&adev->delayed_init_work); - if (adev->mman.initialized) { + while (adev->mman.initialized && pending) { flush_delayed_work(&adev->mman.bdev.wq); - ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); + pending = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); + if (pending) { + ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, true); + msleep((HZ / 100) < 1) ? 1 : HZ / 100); + } } adev->shutdown = true; -- 2.25.1
