73eba1a839
keeps us from stomping on ourselves. Say we're in the middle of re-evaluating a loop (and sleeping) when a command completes, or a timer refires, and this *other* thread decides *it* wants to start re-evaluating the loop. Bad news. We have to be a bit careful- if we can't acquire the MBOX semaphore at interrupt level, we will simulate a host interface error. This is a bit of a temp workaround. There's some work underway driven by a NetBSD commercial user that will try and force most mailbox stuff into a part A/part B interrupt driven model.