On 27/4/07 08:08, "Jeremy Fitzhardinge" <jeremy@xxxxxxxx> wrote: >> Don't you need a rmb() here then? The CPU could speculate reads >> (more occurrences) >> > > Is rmb() sufficient? It will stop a speculative read on the pending > flag, but will it make sure the write has happened by then? Ie, is it a > write-vs-read barrier, or just a read-vs-read? > Documentation/memory-barriers.txt suggests not. The barrier() is sufficient. We are racing against Xen checking evtchn_upcall_mask *on the local cpu*. Which means an interrupt has to occur, which squashes speculative stuff. Yeah, I know, it needs a better comment. :-) -- Keir _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/virtualization
