Messages in this thread | | | Date | Fri, 13 Feb 2015 13:09:14 -0800 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH] sched/completion: completion_done() should serialize with complete() |
| |
On Thu, Feb 12, 2015 at 08:59:13PM +0100, Oleg Nesterov wrote: > Commit de30ec47302c "Remove unnecessary ->wait.lock serialization when > reading completion state" was not correct, without lock/unlock the code > like stop_machine_from_inactive_cpu() > > while (!completion_done()) > cpu_relax(); > > can return before complete() finishes its spin_unlock() which writes to > this memory. And spin_unlock_wait(). > > While at it, change try_wait_for_completion() to use READ_ONCE(). > > Reported-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> > Reported-by: Davidlohr Bueso <dave@stgolabs.net> > Signed-off-by: Oleg Nesterov <oleg@redhat.com>
So I am having some difficulty reproducing the original problem, but the patch passes rcutorture testing. So...
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> --- x/kernel/sched/completion.c > +++ x/kernel/sched/completion.c > @@ -274,7 +274,7 @@ bool try_wait_for_completion(struct comp > * first without taking the lock so we can > * return early in the blocking case. > */ > - if (!ACCESS_ONCE(x->done)) > + if (!READ_ONCE(x->done)) > return 0; > > spin_lock_irqsave(&x->wait.lock, flags); > @@ -297,6 +297,11 @@ EXPORT_SYMBOL(try_wait_for_completion); > */ > bool completion_done(struct completion *x) > { > - return !!ACCESS_ONCE(x->done); > + if (!READ_ONCE(x->done)) > + return false; > + > + smp_rmb(); > + spin_unlock_wait(&x->wait.lock); > + return true; > } > EXPORT_SYMBOL(completion_done); >
| |