On Mon, 3 Sep 2018 16:28:00 +0200
Juri Lelli <juri.lelli@xxxxxxxxxx> wrote:
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 5b43f482fa0f..8dc26005bb1e 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -2410,6 +2410,24 @@ void __init cpuset_init_smp(void)
> BUG_ON(!cpuset_migrate_mm_wq);
> }
>
> +/**
> + * cpuset_read_only_lock - Grab the callback_lock from another subsysytem
> + *
> + * Description: Gives the holder read-only access to cpusets.
> + */
> +void cpuset_read_only_lock(void)
> +{
> + raw_spin_lock(&callback_lock);
This was confusing to figure out why grabbing a spinlock gives read
only access. So I read the long comment above the definition of
callback_lock. A couple of notes.
1) The above description needs to go into more detail as to why
grabbing a spinlock is "read only".
2) The comment above the callback_lock needs to incorporate this, as
reading that comment alone will not give anyone an idea that this
exists.
Other than that, I don't see any issue with this patch.
-- Steve
> +}
> +
> +/**
> + * cpuset_read_only_unlock - Release the callback_lock from another subsysytem
> + */
> +void cpuset_read_only_unlock(void)
> +{
> + raw_spin_unlock(&callback_lock);
> +}
> +
> /**
> * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
> * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 22f5622cba69..ac11ee599968 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -4228,6 +4228,13 @@ static int __sched_setscheduler(struct task_struct *p,
> rq = task_rq_lock(p, &rf);
> update_rq_clock(rq);
>
> + /*
> + * Make sure we don't race with the cpuset subsystem where root
> + * domains can be rebuilt or modified while operations like DL
> + * admission checks are carried out.
> + */
> + cpuset_read_only_lock();
> +
> /*
> * Changing the policy of the stop threads its a very bad idea:
> */
> @@ -4289,6 +4296,7 @@ static int __sched_setscheduler(struct task_struct *p,
> /* Re-check policy now with rq lock held: */
> if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
> policy = oldpolicy = -1;
> + cpuset_read_only_unlock();
> task_rq_unlock(rq, p, &rf);
> goto recheck;
> }
> @@ -4346,6 +4354,7 @@ static int __sched_setscheduler(struct task_struct *p,
>
> /* Avoid rq from going away on us: */
> preempt_disable();
> + cpuset_read_only_unlock();
> task_rq_unlock(rq, p, &rf);
>
> if (pi)
> @@ -4358,6 +4367,7 @@ static int __sched_setscheduler(struct task_struct *p,
> return 0;
>
> unlock:
> + cpuset_read_only_unlock();
> task_rq_unlock(rq, p, &rf);
> return retval;
> }
