On Apr 8, 2016 4:04 AM, "Peter Zijlstra" <[email protected]> wrote: > > On Thu, Apr 07, 2016 at 03:05:26PM -0700, Andy Lutomirski wrote: > > > It doesn't, which is what I like about my variant. If the thread > > accesses the protected data structure, though, it should bump the > > sequence count, which will cause the first thread to about when it > > gets scheduled in. > > Nope it won't, because that first thread is right at the commit > instruction, nothing will stop it from executing that store and clobbing > what we just wrote. >
I don't think so. I write an event number. You commit because you didn't notice. I haven't loaded yet from the value you wrote when you committed, so nothing goes wrong. --Andy
