3.16.36-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <pet...@infradead.org>

commit 4c9a4bc89a9cca8128bce67d6bc8870d6b7ee0b2 upstream.

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 <umgwanakikb...@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
Cc: ktk...@parallels.com
Cc: rost...@goodmis.org
Cc: juri.le...@gmail.com
Cc: pang.xun...@linaro.org
Cc: o...@redhat.com
Cc: wanpeng...@linux.intel.com
Link: http://lkml.kernel.org/r/20150611124742.615343...@infradead.org
Signed-off-by: Thomas Gleixner <t...@linutronix.de>
[Conflicts: kernel/sched/core.c]
Signed-off-by: Byungchul Park <byungchul.p...@lge.com>
Signed-off-by: Ben Hutchings <b...@decadent.org.uk>
---
 kernel/sched/core.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -999,6 +999,13 @@ inline int task_curr(const struct task_s
        return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * 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,
                                       int oldprio)
@@ -1500,8 +1507,12 @@ ttwu_do_wakeup(struct rq *rq, struct tas
 
        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;
@@ -3052,7 +3063,11 @@ void rt_mutex_setprio(struct task_struct
 
        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
 
@@ -3575,10 +3590,17 @@ change:
        }
 
        check_class_changed(rq, p, prev_class, oldprio);
+       preempt_disable(); /* avoid rq from going away on us */
        task_rq_unlock(rq, p, &flags);
 
        rt_mutex_adjust_pi(p);
 
+       /*
+        * Run balance callbacks after we've adjusted the PI chain.
+        */
+       balance_callback(rq);
+       preempt_enable();
+
        return 0;
 }
 

Reply via email to