Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Two fixes:

   - a SCHED_DEADLINE task selection fix
   - a sched/numa related lockdep splat fix"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Check for stop task appearance when balancing happens
  sched/numa: Fix task_numa_free() lockdep splat

4 files changed, 32 insertions, 11 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 27ef40925525..b08095786cb8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1021,8 +1021,17 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 
         dl_rq = &rq->dl;
 
-        if (need_pull_dl_task(rq, prev))
+        if (need_pull_dl_task(rq, prev)) {
                 pull_dl_task(rq);
+                /*
+                 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+                 * means a stop task can slip in, in which case we need to
+                 * re-start task selection.
+                 */
+                if (rq->stop && rq->stop->on_rq)
+                        return RETRY_TASK;
+        }
+
         /*
          * When prev is DL, we may throttle it in put_prev_task().
          * So, we update time before we check for dl_nr_running.
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7e9bd0b1fa9e..7570dd969c28 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1497,7 +1497,7 @@ static void task_numa_placement(struct task_struct *p)
         /* If the task is part of a group prevent parallel updates to group stats */
         if (p->numa_group) {
                 group_lock = &p->numa_group->lock;
-                spin_lock(group_lock);
+                spin_lock_irq(group_lock);
         }
 
         /* Find the node with the highest number of faults */
@@ -1572,7 +1572,7 @@ static void task_numa_placement(struct task_struct *p)
                         }
                 }
 
-                spin_unlock(group_lock);
+                spin_unlock_irq(group_lock);
         }
 
         /* Preferred node as the node with the most faults */
@@ -1677,7 +1677,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
         if (!join)
                 return;
 
-        double_lock(&my_grp->lock, &grp->lock);
+        BUG_ON(irqs_disabled());
+        double_lock_irq(&my_grp->lock, &grp->lock);
 
         for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
                 my_grp->faults[i] -= p->numa_faults_memory[i];
@@ -1691,7 +1692,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
         grp->nr_tasks++;
 
         spin_unlock(&my_grp->lock);
-        spin_unlock(&grp->lock);
+        spin_unlock_irq(&grp->lock);
 
         rcu_assign_pointer(p->numa_group, grp);
 
@@ -1710,14 +1711,14 @@ void task_numa_free(struct task_struct *p)
         void *numa_faults = p->numa_faults_memory;
 
         if (grp) {
-                spin_lock(&grp->lock);
+                spin_lock_irq(&grp->lock);
                 for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
                         grp->faults[i] -= p->numa_faults_memory[i];
                 grp->total_faults -= p->total_numa_faults;
 
                 list_del(&p->numa_entry);
                 grp->nr_tasks--;
-                spin_unlock(&grp->lock);
+                spin_unlock_irq(&grp->lock);
                 rcu_assign_pointer(p->numa_group, NULL);
                 put_numa_group(grp);
         }
@@ -6727,7 +6728,8 @@ static int idle_balance(struct rq *this_rq)
 out:
         /* Is there a task of a high priority class? */
         if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
-            (this_rq->dl.dl_nr_running ||
+            ((this_rq->stop && this_rq->stop->on_rq) ||
+             this_rq->dl.dl_nr_running ||
              (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
                 pulled_task = -1;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d8cdf1618551..bd2267ad404f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1362,10 +1362,11 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
                 pull_rt_task(rq);
                 /*
                  * pull_rt_task() can drop (and re-acquire) rq->lock; this
-                 * means a dl task can slip in, in which case we need to
-                 * re-start task selection.
+                 * means a dl or stop task can slip in, in which case we need
+                 * to re-start task selection.
                  */
-                if (unlikely(rq->dl.dl_nr_running))
+                if (unlikely((rq->stop && rq->stop->on_rq) ||
+                             rq->dl.dl_nr_running))
                         return RETRY_TASK;
         }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c9007f28d3a2..456e492a3dca 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1385,6 +1385,15 @@ static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
         spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
 }
 
+static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
+{
+        if (l1 > l2)
+                swap(l1, l2);
+
+        spin_lock_irq(l1);
+        spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
 static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
 {
         if (l1 > l2)