Messages in this thread | | | Subject | Re: softlockups in multi_cpu_stop | From | Davidlohr Bueso <> | Date | Fri, 06 Mar 2015 20:44:30 -0800 |
| |
On Fri, 2015-03-06 at 20:31 -0800, Jason Low wrote: > On Fri, 2015-03-06 at 13:12 -0800, Jason Low wrote: > > Just in case, here's the updated patch which addresses Linus's comments > and with a changelog. > > Note: The changelog says that it fixes (locking/rwsem: Avoid deceiving > lock spinners), though I still haven't seen full confirmation that it > addresses all of the lockup reports. > > ------ > Subject: [PATCH] rwsem: Avoid spinning when owner is not running > > Fixes tip commmit b3fd4f03ca0b (locking/rwsem: Avoid deceiving lock spinners). > > When doing optimistic spinning in rwsem, threads should stop spinning when > the lock owner is not running. While a thread is spinning on owner, if > the owner reschedules, owner->on_cpu returns false and we stop spinning. > > However, commit b3fd4f03ca0b essentially caused the check to get ignored > because when we break out of the spin loop due to !on_cpu, we continue > spinning if sem->owner != NULL.
I would mention the actual effects of the bug, either just a "lockup" and/or a fragment of the trace. But ultimately this comes down to missing a need_resched() condition.
> > This patch fixes this by making sure we stop spinning if the owner is not > running. Furthermore, just like with mutexes, refactor the code such that > we don't have separate checks for owner_running(). This makes it more > straightforward in terms of why we exit the spin on owner loop and we > would also avoid needing to "guess" why we broke out of the loop to make > this more readable. > > Cc: Ming Lei <ming.lei@canonical.com> > Cc: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
| |