Re: [PATCH v3 2/3] sched: Provide copy_user_cpus_mask() to copy out user mask

From: Peter Zijlstra
Date: Mon Aug 15 2022 - 04:59:08 EST


On Fri, Aug 12, 2022 at 04:39:28PM -0400, Waiman Long wrote:
> Since accessing the content of the user_cpus_ptr requires lock protection
> to ensure its validity, provide a helper function copy_user_cpus_mask()
> to facilitate its reading.

Sure, but this is atrocious.

> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2619,6 +2619,24 @@ void release_user_cpus_ptr(struct task_struct *p)
> kfree(clear_user_cpus_ptr(p));
> }
>
> +/*
> + * Return the copied mask pointer or NULL if user mask not available.
> + */
> +struct cpumask *copy_user_cpus_mask(struct task_struct *p,
> + struct cpumask *user_mask)
> +{
> + struct rq_flags rf;
> + struct rq *rq = task_rq_lock(p, &rf);
> + struct cpumask *mask = NULL;
> +
> + if (p->user_cpus_ptr) {
> + cpumask_copy(user_mask, p->user_cpus_ptr);
> + mask = user_mask;
> + }
> + task_rq_unlock(rq, p, &rf);
> + return mask;
> +}

For reading the mask you only need one of those locks, and I would
suggest p->pi_lock is much less contended than rq->lock.