On Thu, Jan 06 2005, Nick Piggin wrote:
This memory barrier is not needed because the waitqueue will only get
waiters on it in the following situations:
rq->count has exceeded the threshold - however all manipulations of ->count
are performed under the runqueue lock, and so we will correctly pick up any
waiter.
Memory allocation for the request fails. In this case, there is no additional
help provided by the memory barrier. We are guaranteed to eventually wake
up waiters because the request allocation mempool guarantees that if the mem
allocation for a request fails, there must be some requests in flight. They
will wake up waiters when they are retired.
Not sure I agree completely. Yes it will work, but only because it tests
<= q->nr_requests and I don't think that 'eventually' is good enough :-)
The actual waitqueue manipulation doesn't happen under the queue lock,
so the memory barrier is needed to pickup the change on SMP. So I'd like
to keep the barrier.
I'd prefer to add smp_mb() to waitqueue_active() actually!