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

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes, most of them SCHED_DEADLINE fallout"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Prevent rt_time growth to infinity
  sched/deadline: Switch CPU's presence test order
  sched/deadline: Cleanup RT leftovers from {inc/dec}_dl_migration
  sched: Fix double normalization of vruntime

4 files changed, 20 insertions, 10 deletions

diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b8838b56d1c..5b9bb42b2d47 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-        WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);
+        WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
 
         if (dl_time_before(new_dl, cp->elements[idx].dl)) {
                 cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
         }
 
 out:
-        WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);
+        WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
         return best_cpu;
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 15cbc17fbf84..6e79b3faa4cd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -135,7 +135,6 @@ static void update_dl_migration(struct dl_rq *dl_rq)
 static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
         struct task_struct *p = dl_task_of(dl_se);
-        dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
         if (p->nr_cpus_allowed > 1)
                 dl_rq->dl_nr_migratory++;
@@ -146,7 +145,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
         struct task_struct *p = dl_task_of(dl_se);
-        dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
         if (p->nr_cpus_allowed > 1)
                 dl_rq->dl_nr_migratory--;
@@ -564,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
         return 1;
 }
 
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -627,11 +627,13 @@ static void update_curr_dl(struct rq *rq)
                 struct rt_rq *rt_rq = &rq->rt;
 
                 raw_spin_lock(&rt_rq->rt_runtime_lock);
-                rt_rq->rt_time += delta_exec;
                 /*
                  * We'll let actual RT tasks worry about the overflow here, we
-                 * have our own CBS to keep us inline -- see above.
+                 * have our own CBS to keep us inline; only account when RT
+                 * bandwidth is relevant.
                  */
+                if (sched_rt_bandwidth_account(rt_rq))
+                        rt_rq->rt_time += delta_exec;
                 raw_spin_unlock(&rt_rq->rt_runtime_lock);
         }
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 78157099b167..9b4c4f320130 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7001,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
         struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
         /*
-         * Ensure the task's vruntime is normalized, so that when its
+         * Ensure the task's vruntime is normalized, so that when it's
          * switched back to the fair class the enqueue_entity(.flags=0) will
          * do the right thing.
          *
-         * If it was on_rq, then the dequeue_entity(.flags=0) will already
-         * have normalized the vruntime, if it was !on_rq, then only when
+         * If it's on_rq, then the dequeue_entity(.flags=0) will already
+         * have normalized the vruntime, if it's !on_rq, then only when
          * the task is sleeping will it still have non-normalized vruntime.
          */
-        if (!se->on_rq && p->state != TASK_RUNNING) {
+        if (!p->on_rq && p->state != TASK_RUNNING) {
                 /*
                  * Fix up our vruntime so that the current sleep doesn't
                  * cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b775b45..1999021042c7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+        struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+        return (hrtimer_active(&rt_b->rt_period_timer) ||
+                rt_rq->rt_time < rt_b->rt_runtime);
+}
+
 #ifdef CONFIG_SMP
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.