drm/amdkfd: Avoid queue reset if disabled

If ring reset is disabled, skip resetting queues. Instead, fall back to
device based reset.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: Lijo Lazar

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -2339,9 +2339,18 @@ static int reset_hung_queues_sdma(struct device_queue_manager *dqm)
 
 static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma)
 {
+	struct amdgpu_device *adev = dqm->dev->adev;
+
 	while (halt_if_hws_hang)
 		schedule();
 
+	if (adev->debug_disable_gpu_ring_reset) {
+		dev_info_once(adev->dev,
+			      "%s queue hung, but ring reset disabled",
+			      is_sdma ? "sdma" : "compute");
+
+		return -EPERM;
+	}
 	if (!amdgpu_gpu_recovery)
 		return -ENOTRECOVERABLE;