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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  llist: Add back llist_add_batch() and llist_del_first() prototypes
  sched: Don't use tasklist_lock for debug prints
  sched: Warn on rt throttling
  sched: Unify the ->cpus_allowed mask copy
  sched: Wrap scheduler p->cpus_allowed access
  sched: Request for idle balance during nohz idle load balance
  sched: Use resched IPI to kick off the nohz idle balance
  sched: Fix idle_cpu()
  llist: Remove cpu_relax() usage in cmpxchg loops
  sched: Convert to struct llist
  llist: Add llist_next()
  irq_work: Use llist in the struct irq_work logic
  llist: Return whether list is empty before adding in llist_add()
  llist: Move cpu_relax() to after the cmpxchg()
  llist: Remove the platform-dependent NMI checks
  llist: Make some llist functions inline
  sched, tracing: Show PREEMPT_ACTIVE state in trace_sched_switch
  sched: Remove redundant test in check_preempt_tick()
  sched: Add documentation for bandwidth control
  sched: Return unused runtime on group dequeue
  ...

1 files changed, 39 insertions, 60 deletions

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index af1177858be3..056cbd2e2a27 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -124,21 +124,33 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	update_rt_migration(rt_rq);
 }
 
+static inline int has_pushable_tasks(struct rq *rq)
+{
+	return !plist_head_empty(&rq->rt.pushable_tasks);
+}
+
 static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
 	plist_node_init(&p->pushable_tasks, p->prio);
 	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
+
+	/* Update the highest prio pushable task */
+	if (p->prio < rq->rt.highest_prio.next)
+		rq->rt.highest_prio.next = p->prio;
 }
 
 static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
-}
 
-static inline int has_pushable_tasks(struct rq *rq)
-{
-	return !plist_head_empty(&rq->rt.pushable_tasks);
+	/* Update the new highest prio pushable task */
+	if (has_pushable_tasks(rq)) {
+		p = plist_first_entry(&rq->rt.pushable_tasks,
+				      struct task_struct, pushable_tasks);
+		rq->rt.highest_prio.next = p->prio;
+	} else
+		rq->rt.highest_prio.next = MAX_RT_PRIO;
 }
 
 #else
@@ -643,6 +655,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 
 	if (rt_rq->rt_time > runtime) {
 		rt_rq->rt_throttled = 1;
+		printk_once(KERN_WARNING "sched: RT throttling activated\n");
 		if (rt_rq_throttled(rt_rq)) {
 			sched_rt_rq_dequeue(rt_rq);
 			return 1;
@@ -698,47 +711,13 @@ static void update_curr_rt(struct rq *rq)
 
 #if defined CONFIG_SMP
 
-static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu);
-
-static inline int next_prio(struct rq *rq)
-{
-	struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu);
-
-	if (next && rt_prio(next->prio))
-		return next->prio;
-	else
-		return MAX_RT_PRIO;
-}
-
 static void
 inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-	if (prio < prev_prio) {
-
-		/*
-		 * If the new task is higher in priority than anything on the
-		 * run-queue, we know that the previous high becomes our
-		 * next-highest.
-		 */
-		rt_rq->highest_prio.next = prev_prio;
-
-		if (rq->online)
-			cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
-
-	} else if (prio == rt_rq->highest_prio.curr)
-		/*
-		 * If the next task is equal in priority to the highest on
-		 * the run-queue, then we implicitly know that the next highest
-		 * task cannot be any lower than current
-		 */
-		rt_rq->highest_prio.next = prio;
-	else if (prio < rt_rq->highest_prio.next)
-		/*
-		 * Otherwise, we need to recompute next-highest
-		 */
-		rt_rq->highest_prio.next = next_prio(rq);
+	if (rq->online && prio < prev_prio)
+		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
 
 static void
@@ -746,9 +725,6 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-	if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next))
-		rt_rq->highest_prio.next = next_prio(rq);
-
 	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
@@ -961,6 +937,8 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!task_current(rq, p) && p->rt.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)
@@ -971,6 +949,8 @@ 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);
 }
 
 /*
@@ -1017,10 +997,12 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	struct rq *rq;
 	int cpu;
 
-	if (sd_flag != SD_BALANCE_WAKE)
-		return smp_processor_id();
-
 	cpu = task_cpu(p);
+
+	/* For anything but wake ups, just return the task_cpu */
+	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+		goto out;
+
 	rq = cpu_rq(cpu);
 
 	rcu_read_lock();
@@ -1059,6 +1041,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	}
 	rcu_read_unlock();
 
+out:
 	return cpu;
 }
 
@@ -1178,7 +1161,6 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
-	p->se.exec_start = 0;
 
 	/*
 	 * The previous task needs to be made eligible for pushing
@@ -1198,7 +1180,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+	    (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
 	    (p->rt.nr_cpus_allowed > 1))
 		return 1;
 	return 0;
@@ -1343,7 +1325,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 */
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(lowest_rq->cpu,
-						       &task->cpus_allowed) ||
+						       tsk_cpus_allowed(task)) ||
 				     task_running(rq, task) ||
 				     !task->on_rq)) {
 
@@ -1394,6 +1376,7 @@ static int push_rt_task(struct rq *rq)
 {
 	struct task_struct *next_task;
 	struct rq *lowest_rq;
+	int ret = 0;
 
 	if (!rq->rt.overloaded)
 		return 0;
@@ -1426,7 +1409,7 @@ retry:
 	if (!lowest_rq) {
 		struct task_struct *task;
 		/*
-		 * find lock_lowest_rq releases rq->lock
+		 * find_lock_lowest_rq releases rq->lock
 		 * so it is possible that next_task has migrated.
 		 *
 		 * We need to make sure that the task is still on the same
@@ -1436,12 +1419,11 @@ retry:
 		task = pick_next_pushable_task(rq);
 		if (task_cpu(next_task) == rq->cpu && task == next_task) {
 			/*
-			 * If we get here, the task hasn't moved at all, but
-			 * it has failed to push.  We will not try again,
-			 * since the other cpus will pull from us when they
-			 * are ready.
+			 * The task hasn't migrated, and is still the next
+			 * eligible task, but we failed to find a run-queue
+			 * to push it to.  Do not retry in this case, since
+			 * other cpus will pull from us when ready.
 			 */
-			dequeue_pushable_task(rq, next_task);
 			goto out;
 		}
 
@@ -1460,6 +1442,7 @@ retry:
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, lowest_rq->cpu);
 	activate_task(lowest_rq, next_task, 0);
+	ret = 1;
 
 	resched_task(lowest_rq->curr);
 
@@ -1468,7 +1451,7 @@ retry:
 out:
 	put_task_struct(next_task);
 
-	return 1;
+	return ret;
 }
 
 static void push_rt_tasks(struct rq *rq)
@@ -1626,9 +1609,6 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 
 		update_rt_migration(&rq->rt);
 	}
-
-	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->rt.nr_cpus_allowed = weight;
 }
 
 /* Assumes rq->lock is held */
@@ -1863,4 +1843,3 @@ static void print_rt_stats(struct seq_file *m, int cpu)
 	rcu_read_unlock();
 }
 #endif /* CONFIG_SCHED_DEBUG */
-