This series: 1. removes live lockable retry loop in sem_lock(). 2. reverts the current -rt wakeup scheme 3. replaces it with a new completion scheme Removing the retry loop alone fixes the livelock problem, but the current -rt wakeup scheme then ensures that wakees see the array lock in a locked state, which split lock semantics require they react to by taking the array lock themselves, defeating the whole purpose of splitting the lock into simple/complex operation locks. -Mike -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
