Re: [RFC PATCH v15 7/7] sched: Start blocked_on chain processing in find_proxy_task()

[Peter Zijlstra]

On Mon, Mar 17, 2025 at 05:43:56PM +0100, Peter Zijlstra wrote:
> On Wed, Mar 12, 2025 at 03:11:37PM -0700, John Stultz wrote:
> > @@ -6668,47 +6676,138 @@ static bool proxy_deactivate(struct rq *rq, struct task_struct *donor)
> >  }
> >  
> >  /*
> > + * Find runnable lock owner to proxy for mutex blocked donor
> > + *
> > + * Follow the blocked-on relation:
> > + *   task->blocked_on -> mutex->owner -> task...
> > + *
> > + * Lock order:
> > + *
> > + *   p->pi_lock
> > + *     rq->lock
> > + *       mutex->wait_lock
> > + *
> > + * Returns the task that is going to be used as execution context (the one
> > + * that is actually going to be run on cpu_of(rq)).
> >   */
> >  static struct task_struct *
> >  find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
> >  {
> > +	struct task_struct *owner = NULL;
> > +	struct task_struct *ret = NULL;
> > +	int this_cpu = cpu_of(rq);
> > +	struct task_struct *p;
> >  	struct mutex *mutex;
> >  
> > +	/* Follow blocked_on chain. */
> > +	for (p = donor; task_is_blocked(p); p = owner) {
> > +		mutex = p->blocked_on;
> > +		/* Something changed in the chain, so pick again */
> > +		if (!mutex)
> > +			return NULL;
> >  		/*
> > +		 * By taking mutex->wait_lock we hold off concurrent mutex_unlock()
> > +		 * and ensure @owner sticks around.
> >  		 */
> > +		raw_spin_lock(&mutex->wait_lock);
> 
> This comment -- that is only true if you kill __mutex_unlock_fast(),
> which I don't think you did in the previous patches.

Ignore this; I got myself confused again. :-)