On 02/15, Raghavendra K T wrote:
>
> * Raghavendra K T <[email protected]> [2015-02-15 11:25:44]:
>
> Resending the V5 with smp_mb__after_atomic() change without bumping up
> revision

Reviewed-by: Oleg Nesterov <[email protected]>


Of course, this needs the acks from maintainers. And I agree that SLOWPATH
in .head makes xadd() in unlock() unavoidable. However I do not see how we
can avoid the locked inc if we want to eliminate read-after-unlock.

_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Reply via email to