Messages in this thread | | | From | Roman Penyaev <> | Date | Mon, 25 Apr 2016 18:40:59 +0200 | Subject | Re: [PATCH 1/1] [RFC] workqueue: fix ghost PENDING flag while doing MQ IO |
| |
On Mon, Apr 25, 2016 at 6:00 PM, Tejun Heo <tj@kernel.org> wrote: > On Mon, Apr 25, 2016 at 11:48:47AM -0400, Tejun Heo wrote: >> Heh, excellent debugging. I wonder how old this bug is. cc'ing David > > I just went through the history. So, we used to have clear_bit() > instead of atomic_long_set() but clear_bit() doesn't imply any barrier > either, so kudos to you. You just debugged an issue which is most > likely has been there for over a decade! :)
That's nice, that we can finally fix it. But as I was saying I was just lucky enough to have very easy reproduction. I could check all crazy ideas I had :)
-- Roman
| |