1 files changed, 106 insertions, 28 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d8cdf1618551..b3512f1afce9 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -79,6 +79,8 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
         rt_rq->overloaded = 0;
         plist_head_init(&rt_rq->pushable_tasks);
 #endif
+        /* We start is dequeued state, because no RT tasks are queued */
+        rt_rq->rt_queued = 0;
 
         rt_rq->rt_time = 0;
         rt_rq->rt_throttled = 0;
@@ -112,6 +114,13 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
         return rt_se->rt_rq;
 }
 
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
+{
+        struct rt_rq *rt_rq = rt_se->rt_rq;
+
+        return rt_rq->rq;
+}
+
 void free_rt_sched_group(struct task_group *tg)
 {
         int i;
@@ -211,10 +220,16 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
         return container_of(rt_rq, struct rq, rt);
 }
 
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
 {
         struct task_struct *p = rt_task_of(rt_se);
-        struct rq *rq = task_rq(p);
+
+        return task_rq(p);
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+        struct rq *rq = rq_of_rt_se(rt_se);
 
         return &rq->rt;
 }
@@ -391,6 +406,9 @@ static inline void set_post_schedule(struct rq *rq)
 }
 #endif /* CONFIG_SMP */
 
+static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
+static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
+
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
         return !list_empty(&rt_se->run_list);
@@ -452,8 +470,11 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
         rt_se = rt_rq->tg->rt_se[cpu];
 
         if (rt_rq->rt_nr_running) {
-                if (rt_se && !on_rt_rq(rt_se))
+                if (!rt_se)
+                        enqueue_top_rt_rq(rt_rq);
+                else if (!on_rt_rq(rt_se))
                         enqueue_rt_entity(rt_se, false);
+
                 if (rt_rq->highest_prio.curr < curr->prio)
                         resched_task(curr);
         }
@@ -466,10 +487,17 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 
         rt_se = rt_rq->tg->rt_se[cpu];
 
-        if (rt_se && on_rt_rq(rt_se))
+        if (!rt_se)
+                dequeue_top_rt_rq(rt_rq);
+        else if (on_rt_rq(rt_se))
                 dequeue_rt_entity(rt_se);
 }
 
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+        return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+
 static int rt_se_boosted(struct sched_rt_entity *rt_se)
 {
         struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -532,12 +560,23 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 
 static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
-        if (rt_rq->rt_nr_running)
-                resched_task(rq_of_rt_rq(rt_rq)->curr);
+        struct rq *rq = rq_of_rt_rq(rt_rq);
+
+        if (!rt_rq->rt_nr_running)
+                return;
+
+        enqueue_top_rt_rq(rt_rq);
+        resched_task(rq->curr);
 }
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
+        dequeue_top_rt_rq(rt_rq);
+}
+
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+        return rt_rq->rt_throttled;
 }
 
 static inline const struct cpumask *sched_rt_period_mask(void)
@@ -851,14 +890,8 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
                  * but accrue some time due to boosting.
                  */
                 if (likely(rt_b->rt_runtime)) {
-                        static bool once = false;
-
                         rt_rq->rt_throttled = 1;
-
-                        if (!once) {
-                                once = true;
-                                printk_sched("sched: RT throttling activated\n");
-                        }
+                        printk_deferred_once("sched: RT throttling activated\n");
                 } else {
                         /*
                          * In case we did anyway, make it go away,
@@ -922,6 +955,38 @@ static void update_curr_rt(struct rq *rq)
         }
 }
 
+static void
+dequeue_top_rt_rq(struct rt_rq *rt_rq)
+{
+        struct rq *rq = rq_of_rt_rq(rt_rq);
+
+        BUG_ON(&rq->rt != rt_rq);
+
+        if (!rt_rq->rt_queued)
+                return;
+
+        BUG_ON(!rq->nr_running);
+
+        sub_nr_running(rq, rt_rq->rt_nr_running);
+        rt_rq->rt_queued = 0;
+}
+
+static void
+enqueue_top_rt_rq(struct rt_rq *rt_rq)
+{
+        struct rq *rq = rq_of_rt_rq(rt_rq);
+
+        BUG_ON(&rq->rt != rt_rq);
+
+        if (rt_rq->rt_queued)
+                return;
+        if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+                return;
+
+        add_nr_running(rq, rt_rq->rt_nr_running);
+        rt_rq->rt_queued = 1;
+}
+
 #if defined CONFIG_SMP
 
 static void
@@ -1045,12 +1110,23 @@ void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 static inline
+unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se)
+{
+        struct rt_rq *group_rq = group_rt_rq(rt_se);
+
+        if (group_rq)
+                return group_rq->rt_nr_running;
+        else
+                return 1;
+}
+
+static inline
 void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
         int prio = rt_se_prio(rt_se);
 
         WARN_ON(!rt_prio(prio));
-        rt_rq->rt_nr_running++;
+        rt_rq->rt_nr_running += rt_se_nr_running(rt_se);
 
         inc_rt_prio(rt_rq, prio);
         inc_rt_migration(rt_se, rt_rq);
@@ -1062,7 +1138,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
         WARN_ON(!rt_prio(rt_se_prio(rt_se)));
         WARN_ON(!rt_rq->rt_nr_running);
-        rt_rq->rt_nr_running--;
+        rt_rq->rt_nr_running -= rt_se_nr_running(rt_se);
 
         dec_rt_prio(rt_rq, rt_se_prio(rt_se));
         dec_rt_migration(rt_se, rt_rq);
@@ -1119,6 +1195,8 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
                 back = rt_se;
         }
 
+        dequeue_top_rt_rq(rt_rq_of_se(back));
+
         for (rt_se = back; rt_se; rt_se = rt_se->back) {
                 if (on_rt_rq(rt_se))
                         __dequeue_rt_entity(rt_se);
@@ -1127,13 +1205,18 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 
 static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
+        struct rq *rq = rq_of_rt_se(rt_se);
+
         dequeue_rt_stack(rt_se);
         for_each_sched_rt_entity(rt_se)
                 __enqueue_rt_entity(rt_se, head);
+        enqueue_top_rt_rq(&rq->rt);
 }
 
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 {
+        struct rq *rq = rq_of_rt_se(rt_se);
+
         dequeue_rt_stack(rt_se);
 
         for_each_sched_rt_entity(rt_se) {
@@ -1142,6 +1225,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
                 if (rt_rq && rt_rq->rt_nr_running)
                         __enqueue_rt_entity(rt_se, false);
         }
+        enqueue_top_rt_rq(&rq->rt);
 }
 
 /*
@@ -1159,8 +1243,6 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
         if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
                 enqueue_pushable_task(rq, p);
-
-        inc_nr_running(rq);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1171,8 +1253,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
         dequeue_rt_entity(rt_se);
 
         dequeue_pushable_task(rq, p);
-
-        dec_nr_running(rq);
 }
 
 /*
@@ -1362,10 +1442,11 @@ 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;
         }
 
@@ -1376,10 +1457,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
         if (prev->sched_class == &rt_sched_class)
                 update_curr_rt(rq);
 
-        if (!rt_rq->rt_nr_running)
-                return NULL;
-
-        if (rt_rq_throttled(rt_rq))
+        if (!rt_rq->rt_queued)
                 return NULL;
 
         put_prev_task(rq, prev);
@@ -1891,9 +1969,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
          */
         if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
-                if (rq->rt.overloaded && push_rt_task(rq) &&
+                if (p->nr_cpus_allowed > 1 && rq->rt.overloaded &&
                     /* Don't resched if we changed runqueues */
-                    rq != task_rq(p))
+                    push_rt_task(rq) && rq != task_rq(p))
                         check_resched = 0;
 #endif /* CONFIG_SMP */
                 if (check_resched && p->prio < rq->curr->prio)