sched: Allow balance callbacks for check_class_changed()
In order to remove dropping rq->lock from the
switched_{to,from}()/prio_changed() sched_class methods, run the
balance callbacks after it.
We need to remove dropping rq->lock because its buggy,
suppose using sched_setattr()/sched_setscheduler() to change a running
task from FIFO to OTHER.
By the time we get to switched_from_rt() the task is already enqueued
on the cfs runqueues. If switched_from_rt() does pull_rt_task() and
drops rq->lock, load-balancing can come in and move our task @p to
another rq.
The subsequent switched_to_fair() still assumes @p is on @rq and bad
things will happen.
By using balance callbacks we delay the load-balancing operations
{rt,dl}x{push,pull} until we've done all the important work and the
task is fully set up.
Furthermore, the balance callbacks do not know about @p, therefore
they cannot get confused like this.
Reported-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: ktkhai@parallels.com
Cc: rostedt@goodmis.org
Cc: juri.lelli@gmail.com
Cc: pang.xunlei@linaro.org
Cc: oleg@redhat.com
Cc: wanpeng.li@linux.intel.com
Link: http://lkml.kernel.org/r/20150611124742.615343911@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b610ef9..ef546e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1001,7 +1001,11 @@
}
/*
- * Can drop rq->lock because from sched_class::switched_from() methods drop it.
+ * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
+ * use the balance_callback list if you want balancing.
+ *
+ * this means any call to check_class_changed() must be followed by a call to
+ * balance_callback().
*/
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
@@ -1010,7 +1014,7 @@
if (prev_class != p->sched_class) {
if (prev_class->switched_from)
prev_class->switched_from(rq, p);
- /* Possble rq->lock 'hole'. */
+
p->sched_class->switched_to(rq, p);
} else if (oldprio != p->prio || dl_task(p))
p->sched_class->prio_changed(rq, p, oldprio);
@@ -1491,8 +1495,12 @@
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
- if (p->sched_class->task_woken)
+ if (p->sched_class->task_woken) {
+ /*
+ * XXX can drop rq->lock; most likely ok.
+ */
p->sched_class->task_woken(rq, p);
+ }
if (rq->idle_stamp) {
u64 delta = rq_clock(rq) - rq->idle_stamp;
@@ -3100,7 +3108,11 @@
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
+ preempt_disable(); /* avoid rq from going away on us */
__task_rq_unlock(rq);
+
+ balance_callback(rq);
+ preempt_enable();
}
#endif
@@ -3661,11 +3673,18 @@
}
check_class_changed(rq, p, prev_class, oldprio);
+ preempt_disable(); /* avoid rq from going away on us */
task_rq_unlock(rq, p, &flags);
if (pi)
rt_mutex_adjust_pi(p);
+ /*
+ * Run balance callbacks after we've adjusted the PI chain.
+ */
+ balance_callback(rq);
+ preempt_enable();
+
return 0;
}