Re: softlockups in multi_cpu_stop

[Davidlohr Bueso <dave@stgolabs.net>]

On Sat, 2015-03-07 at 10:10 +0800, Ming Lei wrote:
> On Sat, Mar 7, 2015 at 10:07 AM, Davidlohr Bueso <dave@stgolabs.net> wrote:
> > On Sat, 2015-03-07 at 09:55 +0800, Ming Lei wrote:
> >> On Fri, 06 Mar 2015 14:15:37 -0800
> >> Davidlohr Bueso <dave@stgolabs.net> wrote:
> >>
> >> > On Fri, 2015-03-06 at 13:12 -0800, Jason Low wrote:
> >> > > In owner_running() there are 2 conditions that would make it return
> >> > > false: if the owner changed or if the owner is not running. However,
> >> > > that patch continues spinning if there is a "new owner" but it does not
> >> > > take into account that we may want to stop spinning if the owner is not
> >> > > running (due to getting rescheduled).
> >> >
> >> > So you're rationale is that we're missing this need_resched:
> >> >
> >> >     while (owner_running(sem, owner)) {
> >> >             /* abort spinning when need_resched */
> >> >             if (need_resched()) {
> >> >                     rcu_read_unlock();
> >> >                     return false;
> >> >             }
> >> >     }
> >> >
> >> > Because the owner_running() would return false, right? Yeah that makes
> >> > sense, as missing a resched is a bug, as opposed to our heuristics being
> >> > so painfully off.
> >> >
> >> > Sasha, Ming (Cc'ed), does this address the issues you guys are seeing?
> >>
> >> For the xfstest lockup, what matters is that the owner isn't running, since
> >> the following simple change does fix the issue:
> >
> > I much prefer Jason's approach, which should also take care of the
> > issue, as it includes the !owner->on_cpu stop condition to stop
> > spinning.
> 
> But the check on owner->on_cpu should be moved outside the loop
> because new owner can be scheduled out too, right?

That's not what this is about. New lock _owners_ need to worry about
burning cycles trying to acquire the lock ;)

> >>
> >> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> >> index 06e2214..5e08705 100644
> >> --- a/kernel/locking/rwsem-xadd.c
> >> +++ b/kernel/locking/rwsem-xadd.c
> >> @@ -358,8 +358,9 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
> >>       }
> >>       rcu_read_unlock();
> >>
> >> -     if (READ_ONCE(sem->owner))
> >> -             return true; /* new owner, continue spinning */
> >> +     owner = READ_ONCE(sem->owner);
> >> +     if (owner && owner->on_cpu)
> >> +             return true;

So if I'm understanding this right, your patch works because you add
another on_cpu check and at this point we could very well have
sem->owner == owner -- such that owner_running return false for the same
reason in the first place! So Jason's patch takes on the issue directly
by never allowing ups to reach this point.

Thanks,
Davidlohr