[L0] fix a deadlock on a recursive event rwlock

L0, when creating a list of events to wait on, in some cases
was first grabbing a lock on a potentially completed event,
and then tried to get a command list, which sometimes needs to
cleanup all completed events. This caused a deadlock.

This patch moves getting a command list to before the event lock.
But because the lock is required to decide whether this command
list actually needed, we might be wasting time here.

Author: pbalcer

source/adapters/level_zero/event.cpp

@@ -1307,6 +1307,15 @@ ur_result_t _ur_ze_event_list_t::createAndRetainUrZeEventList(
           }
         }
 
+        ur_command_list_ptr_t CommandList;
+        if (Queue && Queue->Device != CurQueue->Device) {
+          // Get a command list prior to acquiring an event lock.
+          // This prevents a potential deadlock with recursive
+          // event locks.
+          UR_CALL(Queue->Context->getAvailableCommandList(Queue, CommandList,
+                                                          false, true));
+        }
+
         std::shared_lock<ur_shared_mutex> Lock(EventList[I]->Mutex);
 
         if (Queue && Queue->Device != CurQueue->Device &&
@@ -1316,10 +1325,6 @@ ur_result_t _ur_ze_event_list_t::createAndRetainUrZeEventList(
           bool IsInternal = true;
           bool IsMultiDevice = true;
 
-          ur_command_list_ptr_t CommandList{};
-          UR_CALL(Queue->Context->getAvailableCommandList(Queue, CommandList,
-                                                          false, true));
-
           UR_CALL(createEventAndAssociateQueue(
               Queue, &MultiDeviceEvent, EventList[I]->CommandType, CommandList,
               IsInternal, IsMultiDevice));