+/*
+ * to lockup a list of amdgpu devices in a hive safely, if not a hive
+ * with multiple nodes, it will be similar as amdgpu_device_lock_adev.
+ *
+ * unlock won't require roll back.
+ */
+static int amdgpu_device_lock_hive_adev(struct amdgpu_device *adev, struct amdgpu_hive_info *hive)
+{
+ struct amdgpu_device *tmp_adev = NULL;
+
+ if (adev->gmc.xgmi.num_physical_nodes > 1) {
+ if (!hive) {
+ dev_err(adev->dev, "Hive is NULL while device has multiple xgmi nodes");
+ return -ENODEV;
+ }
+ list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+ if (!amdgpu_device_lock_adev(tmp_adev, hive))
+ goto roll_back;
+ }
+ } else if (!amdgpu_device_lock_adev(adev, hive))
+ return -EAGAIN;
+
+ return 0;
+roll_back:
+ if (!list_is_first(&tmp_adev->gmc.xgmi.head, &hive->device_list)) {
+ /*
+ * if the lockup iteration break in the middle of a hive,
+ * it may means there may has a race issue,
+ * or a hive device locked up independently.
+ * we may be in trouble and may not, so will try to roll back
+ * the lock and give out a warnning.
+ */
+ dev_warn(tmp_adev->dev, "Hive lock iteration broke in the middle. Rolling back to unlock");
+ list_for_each_entry_continue_reverse(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+ amdgpu_device_unlock_adev(tmp_adev);
+ }
+ }
+ return -EAGAIN;
+}
+