[PATCH] sched: Fix data-race in wakeup

[Will Deacon]

On Tue, Nov 17, 2020 at 10:46:21AM +0100, Peter Zijlstra wrote:
> On Tue, Nov 17, 2020 at 10:29:36AM +0100, Peter Zijlstra wrote:
> > On Tue, Nov 17, 2020 at 09:15:46AM +0000, Will Deacon wrote:
> > > On Tue, Nov 17, 2020 at 09:30:16AM +0100, Peter Zijlstra wrote:
> > > >  	/* Unserialized, strictly 'current' */
> > > >  
> > > > +	/*
> > > > +	 * p->in_iowait = 1;		ttwu()
> > > > +	 * schedule()			  if (p->on_rq && ..) // false
> > > > +	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
> > > > +	 *   deactivate_task()		      ttwu_queue_wakelist())
> > > > +	 *     p->on_rq = 0;			p->sched_remote_wakeup = X;
> > > > +	 *
> > > > +	 * Guarantees all stores of 'current' are visible before
> > > > +	 * ->sched_remote_wakeup gets used.
> > > 
> > > I'm still not sure this is particularly clear -- don't we want to highlight
> > > that the store of p->on_rq is unordered wrt the update to
> > > p->sched_contributes_to_load() in deactivate_task()?
> 
> How's this then? It still doesn't explicitly call out the specific race,
> but does mention the more fundamental issue that wakelist queueing
> doesn't respect the regular rules anymore.
> 
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -775,7 +775,6 @@ struct task_struct {
>  	unsigned			sched_reset_on_fork:1;
>  	unsigned			sched_contributes_to_load:1;
>  	unsigned			sched_migrated:1;
> -	unsigned			sched_remote_wakeup:1;
>  #ifdef CONFIG_PSI
>  	unsigned			sched_psi_wake_requeue:1;
>  #endif
> @@ -785,6 +784,21 @@ struct task_struct {
>  
>  	/* Unserialized, strictly 'current' */
>  
> +	/*
> +	 * This field must not be in the scheduler word above due to wakelist
> +	 * queueing no longer being serialized by p->on_cpu. However:
> +	 *
> +	 * p->XXX = X;			ttwu()
> +	 * schedule()			  if (p->on_rq && ..) // false
> +	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
> +	 *   deactivate_task()		      ttwu_queue_wakelist())
> +	 *     p->on_rq = 0;			p->sched_remote_wakeup = Y;
> +	 *
> +	 * guarantees all stores of 'current' are visible before
> +	 * ->sched_remote_wakeup gets used, so it can be in this word.
> +	 */
> +	unsigned			sched_remote_wakeup:1;

Much better, thanks!

Will