sched/rt: Prevent idle task boosting

Idle task boosting is a nono in general. There is one
exception, when PREEMPT_RT and NOHZ is active:

The idle task calls get_next_timer_interrupt() and holds
the timer wheel base->lock on the CPU and another CPU wants
to access the timer (probably to cancel it). We can safely
ignore the boosting request, as the idle CPU runs this code
with interrupts disabled and will complete the lock
protected section without being interrupted. So there is no
real need to boost.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-755rvsosz7sdzot12a3gbha6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 820f7453fda93534ef0e4980d63997c27a473915..c2bbdecaa27dae171df8bb00049510871ebdd9e6 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3779,6 +3779,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
        rq = __task_rq_lock(p);
 
+       /*
+        * Idle task boosting is a nono in general. There is one
+        * exception, when PREEMPT_RT and NOHZ is active:
+        *
+        * The idle task calls get_next_timer_interrupt() and holds
+        * the timer wheel base->lock on the CPU and another CPU wants
+        * to access the timer (probably to cancel it). We can safely
+        * ignore the boosting request, as the idle CPU runs this code
+        * with interrupts disabled and will complete the lock
+        * protected section without being interrupted. So there is no
+        * real need to boost.
+        */
+       if (unlikely(p == rq->idle)) {
+               WARN_ON(p != rq->curr);
+               WARN_ON(p->pi_blocked_on);
+               goto out_unlock;
+       }
+
        trace_sched_pi_setprio(p, prio);
        oldprio = p->prio;
        prev_class = p->sched_class;
@@ -3802,11 +3820,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
                enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
        check_class_changed(rq, p, prev_class, oldprio);
+out_unlock:
        __task_rq_unlock(rq);
 }
-
 #endif
-
 void set_user_nice(struct task_struct *p, long nice)
 {
        int old_prio, delta, on_rq;