Messages in this thread |  | | Date | Thu, 16 Apr 2015 12:16:37 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH 2/3 v2] futex: avoid double wake up in futex_wake() on -RT |
| |
On Thu, Apr 16, 2015 at 11:19:41AM +0200, Thomas Gleixner wrote: > So any code which does not handle a spurious wakeup is broken > independent of the futex changes. So really nothing to worry about.
Back when we did this:
http://lkml.iu.edu/hypermail/linux/kernel/1109.1/01941.html http://lkml.iu.edu/hypermail/linux/kernel/1109.1/01943.html
Things came apart -- notably sysvsems.
And yes its true that anything not dealing with spuriuos wakups is borken, but there's still quite a lot of borken out there, although I think we fixed all the really common ones.
But if we decide we want to go do this, I'd propose we reintroduce this delayed wake list thing again.
|  |