On Mon, 26 Sep 2016 14:32:14 +0200
Peter Zijlstra <[email protected]> wrote:
>
> --- a/kernel/futex.c
> +++ b/kernel/futex.c
> @@ -1374,9 +1374,8 @@ static int wake_futex_pi(u32 __user *uad
> * scheduled away before the wake up can take place.
> */
> spin_unlock(&hb->lock);
> - wake_up_q(&wake_q);
> - if (deboost)
> - rt_mutex_adjust_prio(current);
> +
> + rt_mutex_postunlock(&wake_q, deboost);
Hmm...
>
> return 0;
> }
> --- a/kernel/locking/rtmutex.c
> +++ b/kernel/locking/rtmutex.c
> @@ -1325,6 +1308,16 @@ static bool __sched rt_mutex_slowunlock(
> */
> mark_wakeup_next_waiter(wake_q, lock);
>
> + /*
> + * We should deboost before waking the top waiter task such that
> + * we don't run two tasks with the 'same' priority. This however
> + * can lead to prio-inversion if we would get preempted after
> + * the deboost but before waking our high-prio task, hence the
> + * preempt_disable before unlock. Pairs with preempt_enable() in
> + * rt_mutex_postunlock();
There's a preempt_enable() in rt_mutex_postunlock()? Does
wake_futex_pi() know that?
-- Steve
> + */
> + preempt_disable();
> +
> raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
>
> /* check PI boosting */
> @@ -1390,14 +1383,23 @@ rt_mutex_fastunlock(struct rt_mutex *loc
> } else {
> bool deboost = slowfn(lock, &wake_q);
>
> - wake_up_q(&wake_q);
> -
> - /* Undo pi boosting if necessary: */
> - if (deboost)
> - rt_mutex_adjust_prio(current);
> + rt_mutex_postunlock(&wake_q, deboost);
> }
> }
>
> +
> +/*
> + * Undo pi boosting (if necessary) and wake top waiter.
> + */
> +void rt_mutex_postunlock(struct wake_q_head *wake_q, bool deboost)
> +{
> + wake_up_q(wake_q);
> +
> + /* Pairs with preempt_disable() in rt_mutex_slowunlock() */
> + if (deboost)
> + preempt_enable();
> +}
> +
> /**
> * rt_mutex_lock - lock a rt_mutex
> *
> --- a/kernel/locking/rtmutex_common.h
> +++ b/kernel/locking/rtmutex_common.h
> @@ -111,6 +111,7 @@ extern int rt_mutex_finish_proxy_lock(st
> extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct
> hrtimer_sleeper *to);
> extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
> struct wake_q_head *wqh);
> +extern void rt_mutex_postunlock(struct wake_q_head *wake_q, bool deboost);
> extern void rt_mutex_adjust_prio(struct task_struct *task);
>
> #ifdef CONFIG_DEBUG_RT_MUTEXES
>
