From: Kirill Tkhai <ktk...@parallels.com>

hrtimer_try_to_cancel() may bring a suprise, its call may fail.

raw_spin_lock(&rq->lock)
...                            dl_task_timer                 
raw_spin_lock(&rq->lock)
...                               raw_spin_lock(&rq->lock)   ...
   switched_from_dl()             ...                        ...
      hrtimer_try_to_cancel()     ...                        ...
   switched_to_fair()             ...                        ...
...                               ...                        ...
...                               ...                        ...
raw_spin_unlock(&rq->lock)        ...                        (asquired)
...                               ...                        ...
...                               ...                        ...
do_exit()                         ...                        ...
   schedule()                     ...                        ...
      raw_spin_lock(&rq->lock)    ...                        
raw_spin_unlock(&rq->lock)
      ...                         ...                        ...
      raw_spin_unlock(&rq->lock)  ...                        
raw_spin_lock(&rq->lock)
      ...                         ...                        (asquired)
      put_task_struct()           ...                        ...
          free_task_struct()      ...                        ...
      ...                         ...                        
raw_spin_unlock(&rq->lock)
...                               (asquired)                 ...
...                               ...                        ...
...                               Surprise!!!                ...

So, let's implement 100% guaranteed way to cancel the timer and let's
be sure we are safe even in very unlikely situations.

We do not create any problem with rq unlocking, because it already
may happed below in pull_dl_task(). No problem with deadline tasks
balancing too.

Signed-off-by: Kirill Tkhai <ktk...@parallels.com>
---
 kernel/sched/deadline.c |   33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index abfaf3d..63f8b4a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -555,11 +555,6 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
        struct hrtimer *timer = &dl_se->dl_timer;
 
-       if (hrtimer_active(timer)) {
-               hrtimer_try_to_cancel(timer);
-               return;
-       }
-
        hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        timer->function = dl_task_timer;
 }
@@ -1567,10 +1562,34 @@ void init_sched_dl_class(void)
 
 #endif /* CONFIG_SMP */
 
+/*
+ *  Surely cancel task's dl_timer. May drop rq->lock.
+ */
+static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
+{
+       struct hrtimer *dl_timer = &p->dl.dl_timer;
+
+       /* Nobody will change task's class if pi_lock is held */
+       lockdep_assert_held(&p->pi_lock);
+
+       if (hrtimer_active(dl_timer)) {
+               int ret = hrtimer_try_to_cancel(dl_timer);
+
+               if (unlikely(ret == -1)) {
+                       /*
+                        * Note, p may migrate OR new deadline tasks
+                        * may appear in rq when we are unlocking it.
+                        */
+                       raw_spin_unlock(&rq->lock);
+                       hrtimer_cancel(dl_timer);
+                       raw_spin_lock(&rq->lock);
+               }
+       }
+}
+
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
-       if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
-               hrtimer_try_to_cancel(&p->dl.dl_timer);
+       cancel_dl_timer(rq, p);
 
        __dl_clear_params(p);
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to