This patch ensures the MES is properly resumed after detecting and recovering from a user queue hang condition.
Key changes: 1. Track when a hung user queue is detected using found_hung_queue flag 2. Call amdgpu_mes_resume() to restart MES scheduling after completing the hang recovery process 3. This complements the existing recovery steps (fence force completion and device wedging) by ensuring the scheduler can process new work Without this resume call, the MES scheduler may remain in a paused state even after the hung queue has been handled, preventing newly submitted work from being processed and leading to system stalls. Signed-off-by: Jesse Zhang <[email protected]> --- drivers/gpu/drm/amd/amdgpu/mes_userqueue.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index b1ee9473d628..6d1af72916a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -208,6 +208,7 @@ static int mes_userq_detect_and_reset(struct amdgpu_device *adev, unsigned int hung_db_num = 0; unsigned long queue_id; u32 db_array[8]; + bool found_hung_queue =false; int r, i; if (db_array_size > 8) { @@ -232,6 +233,7 @@ static int mes_userq_detect_and_reset(struct amdgpu_device *adev, for (i = 0; i < hung_db_num; i++) { if (queue->doorbell_index == db_array[i]) { queue->state = AMDGPU_USERQ_STATE_HUNG; + found_hung_queue = true; atomic_inc(&adev->gpu_reset_counter); amdgpu_userq_fence_driver_force_completion(queue); drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL); @@ -241,6 +243,11 @@ static int mes_userq_detect_and_reset(struct amdgpu_device *adev, } } + if (found_hung_queue) { + /* Resume scheduling after hang recovery */ + r = amdgpu_mes_resume(adev); + } + return r; } -- 2.49.0
