Andrew Morton writes: > I still wonder about that barrier. At the least it should be smp_mb(). > But aren't our set_bit() semantics _alone_ sufficient to make this barrier > unneeded?
No, but our wake_up semantics certainly ought to be, if they aren't already. It's the wake_up which implies synchronization with other tasks, not the set_bit. Paul. _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@ozlabs.org https://ozlabs.org/mailman/listinfo/linuxppc-dev
