On 03/02/2014 08:31 AM, Oleg Nesterov wrote:
Forgot to ask...
On 02/26, Waiman Long wrote:
+notify_next:
+ /*
+ * Wait, if needed, until the next one in queue set up the next field
+ */
+ while (!(next = ACCESS_ONCE(node->next)))
+ arch_mutex_cpu_relax();
+ /*
+ * The next one in queue is now at the head
+ */
+ smp_store_release(&next->wait, false);
Do we really need smp_store_release()? It seems that we can rely on the
control dependency here. And afaics there is no need to serialise this
store with other changes in *lock, plus they all have mb's anyway.
Oleg.
I am just following the current logic in the mcs_spin_unlock function.
It is probably true that we don't need the release semantic in this
particular case.
-Longman
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
