Re: [patch-rt v2] rtmutex: Fix lock stealing logic

[Mike Galbraith <efault@gmx.de>]

On Fri, 2017-06-23 at 09:33 -0400, Steven Rostedt wrote:
>  				  struct task_struct *task,
> > @@ -886,20 +901,16 @@ static int __try_to_take_rt_mutex(struct
> >  	 */
> >  	if (waiter) {
> >  		/*
> > -		 * If waiter is not the highest priority waiter of
> > -		 * @lock, give up.
> > +		 * If waiter is not the highest priority waiter of @lock,
> > +		 * or its peer when lateral steal is allowed, give up.
> >  		 */
> > -		if (waiter != rt_mutex_top_waiter(lock)) {
> > -			/* XXX rt_mutex_waiter_less() ? */
> > +		if (!rt_mutex_steal(lock, waiter, mode))
> >  			return 0;
> > -		}
> > -
> >  		/*
> >  		 * We can acquire the lock. Remove the waiter from the
> >  		 * lock waiters tree.
> >  		 */
> >  		rt_mutex_dequeue(lock, waiter);
> > -
> 
> I liked that space.

I like minus signs in diffstat, that one was a freebee.  Maintainers
can revive it if they like, or I can post a V3 with it revived as well
as s/rt_mutex_steal/rt_mutex_claim.

	-Mike