Messages in this thread | | | From | Andy Lutomirski <> | Date | Fri, 8 Apr 2016 08:57:53 -0700 | Subject | Re: [RFC PATCH 0/3] restartable sequences v2: fast user-space percpu critical sections |
| |
On Apr 8, 2016 4:04 AM, "Peter Zijlstra" <peterz@infradead.org> 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
| |