On 17/11/20 09:46, Peter Zijlstra wrote:
> 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.
> + */
Isn't the control dep between that ttwu() p->on_rq read and
p->sched_remote_wakeup write "sufficient"? That should be giving the right
ordering for the rest of ttwu() wrt. those 'current' bits, considering they
are written before that smp_mb__after_spinlock().
In any case, consider me convinced:
Reviewed-by: Valentin Schneider <[email protected]>
> + unsigned sched_remote_wakeup:1;
> +
> /* Bit to tell LSMs we're in execve(): */
> unsigned in_execve:1;
> unsigned in_iowait:1;
