On Wed, Jun 11, 2014 at 07:59:34PM +0200, Oleg Nesterov wrote:
> On 06/11, Paul E. McKenney wrote:
> >
> > On Wed, Jun 11, 2014 at 07:17:34PM +0200, Oleg Nesterov wrote:
> > > On 06/11, Oleg Nesterov wrote:
> > > >
> > > > On 06/11, Paul E. McKenney wrote:
> > > >
> > > > > raw_spin_unlock_irqrestore(&rnp->lock, flags);
> > > > > rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority.
> > > > > */
> > > > > rt_mutex_unlock(&mtx); /* Keep lockdep happy. */
> > > > >
> > > > > + /* Wait until boostee is done accessing mtx before
> > > > > reinitializing. */
> > > > > + wait_for_completion(&rnp->boost_completion);
> > > > > +
> > > >
> > > > I must have missed something, I dont understand why we need
> > > > ->boost_completion.
> > > >
> > > > What if you simply move that rt_mutex into rcu_node ?
> > > >
> > > > Or. Given that rcu_boost_kthread() never exits, it can declare this
> > > > mutex
> > > > on stack and pass the pointer to rcu_boost() ?
> > >
> > > Ah, please ignore, I forgot about init_proxy_locked(). Although perhaps
> > > this
> > > can be solved easily.
> >
> > You beat me to it. ;-)
> >
> > I was thinking of ->boost_completion as the way to solve it easily, but
> > what did you have in mind?
>
> I meant, rcu_boost() could probably just do "mtx->owner = t", we know that
> it was unlocked by us and nobody else can use it until we set
> t->rcu_boost_mutex.
My concern with this is that rcu_read_unlock_special() could hypothetically
get preempted (either by kernel or hypervisor), so that it might be a long
time until it makes its reference. But maybe that reference would be
harmless in this case.
> And if we move it into rcu_node, then we can probably kill ->rcu_boost_mutex,
> rcu_read_unlock_special() could check rnp->boost_mutex->owner == current.
If this was anywhere near a hot code path, I would be sorely tempted.
> But you know, I also think that the dentist removed the rest of my brains
> along my tooth, so I am not sure if I actually have something in mind.
Ouch!!! When that happens to me, most of my brains return some time
after the anesthetic wears off, but I know the feeling!
Thanx, Paul
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
