Commit 0a6d4e1d authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge branch 'sched/latest' of...

Merge branch 'sched/latest' of git://git.kernel.org/pub/scm/linux/kernel/git/ghaskins/linux-2.6-hacks into sched/rt
parents c5976504 1563513d
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -142,6 +142,7 @@ extern struct cred init_cred;
		.nr_cpus_allowed = NR_CPUS,				\
	},								\
	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
	.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \
	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\
	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\
	.real_parent	= &tsk,						\
+6 −3
Original line number Diff line number Diff line
@@ -96,6 +96,10 @@ struct plist_node {
# define PLIST_HEAD_LOCK_INIT(_lock)
#endif

#define _PLIST_HEAD_INIT(head)				\
	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
	.node_list = LIST_HEAD_INIT((head).node_list)

/**
 * PLIST_HEAD_INIT - static struct plist_head initializer
 * @head:	struct plist_head variable name
@@ -103,8 +107,7 @@ struct plist_node {
 */
#define PLIST_HEAD_INIT(head, _lock)			\
{							\
	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
	.node_list = LIST_HEAD_INIT((head).node_list),	\
        _PLIST_HEAD_INIT(head),                         \
	PLIST_HEAD_LOCK_INIT(&(_lock))			\
}

@@ -116,7 +119,7 @@ struct plist_node {
#define PLIST_NODE_INIT(node, __prio)			\
{							\
	.prio  = (__prio),				\
	.plist = PLIST_HEAD_INIT((node).plist, NULL),	\
	.plist = { _PLIST_HEAD_INIT((node).plist) }, 	\
}

/**
+2 −0
Original line number Diff line number Diff line
@@ -977,6 +977,7 @@ struct sched_class {
			      struct rq *busiest, struct sched_domain *sd,
			      enum cpu_idle_type idle);
	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
	int (*needs_post_schedule) (struct rq *this_rq);
	void (*post_schedule) (struct rq *this_rq);
	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);

@@ -1143,6 +1144,7 @@ struct task_struct {
#endif

	struct list_head tasks;
	struct plist_node pushable_tasks;

	struct mm_struct *mm, *active_mm;

+78 −11
Original line number Diff line number Diff line
@@ -464,11 +464,15 @@ struct rt_rq {
	struct rt_prio_array active;
	unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	int highest_prio; /* highest queued rt task prio */
	struct {
		int curr; /* highest queued rt task prio */
		int next; /* next highest */
	} highest_prio;
#endif
#ifdef CONFIG_SMP
	unsigned long rt_nr_migratory;
	int overloaded;
	struct plist_head pushable_tasks;
#endif
	int rt_throttled;
	u64 rt_time;
@@ -1607,21 +1611,42 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)

#endif

#ifdef CONFIG_PREEMPT

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 * fair double_lock_balance: Safely acquires both rq->locks in a fair
 * way at the expense of forcing extra atomic operations in all
 * invocations.  This assures that the double_lock is acquired using the
 * same underlying policy as the spinlock_t on this architecture, which
 * reduces latency compared to the unfair variant below.  However, it
 * also adds more overhead and therefore may reduce throughput.
 */
static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	int ret = 0;

	if (unlikely(!irqs_disabled())) {
		/* printk() doesn't work good under rq->lock */
	spin_unlock(&this_rq->lock);
		BUG_ON(1);
	double_rq_lock(this_rq, busiest);

	return 1;
}

#else
/*
 * Unfair double_lock_balance: Optimizes throughput at the expense of
 * latency by eliminating extra atomic operations when the locks are
 * already in proper order on entry.  This favors lower cpu-ids and will
 * grant the double lock to lower cpus over higher ids under contention,
 * regardless of entry order into the function.
 */
static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	int ret = 0;

	if (unlikely(!spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			spin_unlock(&this_rq->lock);
@@ -1634,6 +1659,22 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
	return ret;
}

#endif /* CONFIG_PREEMPT */

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
	if (unlikely(!irqs_disabled())) {
		/* printk() doesn't work good under rq->lock */
		spin_unlock(&this_rq->lock);
		BUG_ON(1);
	}

	return _double_lock_balance(this_rq, busiest);
}

static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(busiest->lock)
{
@@ -2445,6 +2486,8 @@ void sched_fork(struct task_struct *p, int clone_flags)
	/* Want to start with kernel preemption disabled. */
	task_thread_info(p)->preempt_count = 1;
#endif
	plist_node_init(&p->pushable_tasks, MAX_PRIO);

	put_cpu();
}

@@ -2585,6 +2628,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
{
	struct mm_struct *mm = rq->prev_mm;
	long prev_state;
#ifdef CONFIG_SMP
	int post_schedule = 0;

	if (current->sched_class->needs_post_schedule)
		post_schedule = current->sched_class->needs_post_schedule(rq);
#endif

	rq->prev_mm = NULL;

@@ -2603,7 +2652,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
	finish_arch_switch(prev);
	finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
	if (current->sched_class->post_schedule)
	if (post_schedule)
		current->sched_class->post_schedule(rq);
#endif

@@ -2984,6 +3033,16 @@ next:
	pulled++;
	rem_load_move -= p->se.load.weight;

#ifdef CONFIG_PREEMPT
	/*
	 * NEWIDLE balancing is a source of latency, so preemptible kernels
	 * will stop after the first task is pulled to minimize the critical
	 * section.
	 */
	if (idle == CPU_NEWLY_IDLE)
		goto out;
#endif

	/*
	 * We only want to steal up to the prescribed amount of weighted load.
	 */
@@ -3030,9 +3089,15 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
				sd, idle, all_pinned, &this_best_prio);
		class = class->next;

#ifdef CONFIG_PREEMPT
		/*
		 * NEWIDLE balancing is a source of latency, so preemptible
		 * kernels will stop after the first task is pulled to minimize
		 * the critical section.
		 */
		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
			break;

#endif
	} while (class && max_load_move > total_load_moved);

	return total_load_moved > 0;
@@ -8201,11 +8266,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
	__set_bit(MAX_RT_PRIO, array->bitmap);

#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	rt_rq->highest_prio = MAX_RT_PRIO;
	rt_rq->highest_prio.curr = MAX_RT_PRIO;
	rt_rq->highest_prio.next = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
	rt_rq->rt_nr_migratory = 0;
	rt_rq->overloaded = 0;
	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
#endif

	rt_rq->rt_time = 0;
+224 −100
Original line number Diff line number Diff line
@@ -49,6 +49,24 @@ static void update_rt_migration(struct rq *rq)
		rq->rt.overloaded = 0;
	}
}

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);
}

static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
}

#else

#define enqueue_pushable_task(rq, p) do { } while (0)
#define dequeue_pushable_task(rq, p) do { } while (0)

#endif /* CONFIG_SMP */

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
@@ -108,7 +126,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
	if (rt_rq->rt_nr_running) {
		if (rt_se && !on_rt_rq(rt_se))
			enqueue_rt_entity(rt_se);
		if (rt_rq->highest_prio < curr->prio)
		if (rt_rq->highest_prio.curr < curr->prio)
			resched_task(curr);
	}
}
@@ -473,7 +491,7 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se)
	struct rt_rq *rt_rq = group_rt_rq(rt_se);

	if (rt_rq)
		return rt_rq->highest_prio;
		return rt_rq->highest_prio.curr;
#endif

	return rt_task_of(rt_se)->prio;
@@ -547,33 +565,64 @@ static void update_curr_rt(struct rq *rq)
	}
}

#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED

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;
}
#endif

static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
	rt_rq->rt_nr_running++;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
	int prio = rt_se_prio(rt_se);
#ifdef CONFIG_SMP
	struct rq *rq = rq_of_rt_rq(rt_rq);
#endif

		rt_rq->highest_prio = rt_se_prio(rt_se);
	WARN_ON(!rt_prio(prio));
	rt_rq->rt_nr_running++;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	if (prio < rt_rq->highest_prio.curr) {

		/*
		 * If the new task is higher in priority than anything on the
		 * run-queue, we have a new high that must be published to
		 * the world.  We also know that the previous high becomes
		 * our next-highest.
		 */
		rt_rq->highest_prio.next = rt_rq->highest_prio.curr;
		rt_rq->highest_prio.curr = prio;
#ifdef CONFIG_SMP
		if (rq->online)
			cpupri_set(&rq->rd->cpupri, rq->cpu,
				   rt_se_prio(rt_se));
			cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
#endif
	}
	} 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);
#endif
#ifdef CONFIG_SMP
	if (rt_se->nr_cpus_allowed > 1) {
		struct rq *rq = rq_of_rt_rq(rt_rq);

	if (rt_se->nr_cpus_allowed > 1)
		rq->rt.rt_nr_migratory++;
	}

	update_rt_migration(rq_of_rt_rq(rt_rq));
	update_rt_migration(rq);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	if (rt_se_boosted(rt_se))
@@ -590,7 +639,8 @@ static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
#ifdef CONFIG_SMP
	int highest_prio = rt_rq->highest_prio;
	struct rq *rq = rq_of_rt_rq(rt_rq);
	int highest_prio = rt_rq->highest_prio.curr;
#endif

	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
@@ -598,33 +648,34 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
	rt_rq->rt_nr_running--;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	if (rt_rq->rt_nr_running) {
		struct rt_prio_array *array;
		int prio = rt_se_prio(rt_se);

		WARN_ON(rt_se_prio(rt_se) < rt_rq->highest_prio);
		if (rt_se_prio(rt_se) == rt_rq->highest_prio) {
			/* recalculate */
			array = &rt_rq->active;
			rt_rq->highest_prio =
		WARN_ON(prio < rt_rq->highest_prio.curr);

		/*
		 * This may have been our highest or next-highest priority
		 * task and therefore we may have some recomputation to do
		 */
		if (prio == rt_rq->highest_prio.curr) {
			struct rt_prio_array *array = &rt_rq->active;

			rt_rq->highest_prio.curr =
				sched_find_first_bit(array->bitmap);
		} /* otherwise leave rq->highest prio alone */
		}

		if (prio <= rt_rq->highest_prio.next)
			rt_rq->highest_prio.next = next_prio(rq);
	} else
		rt_rq->highest_prio = MAX_RT_PRIO;
		rt_rq->highest_prio.curr = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
	if (rt_se->nr_cpus_allowed > 1) {
		struct rq *rq = rq_of_rt_rq(rt_rq);
	if (rt_se->nr_cpus_allowed > 1)
		rq->rt.rt_nr_migratory--;
	}

	if (rt_rq->highest_prio != highest_prio) {
		struct rq *rq = rq_of_rt_rq(rt_rq);

		if (rq->online)
			cpupri_set(&rq->rd->cpupri, rq->cpu,
				   rt_rq->highest_prio);
	}
	if (rq->online && rt_rq->highest_prio.curr != highest_prio)
		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);

	update_rt_migration(rq_of_rt_rq(rt_rq));
	update_rt_migration(rq);
#endif /* CONFIG_SMP */
#ifdef CONFIG_RT_GROUP_SCHED
	if (rt_se_boosted(rt_se))
@@ -718,6 +769,9 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)

	enqueue_rt_entity(rt_se);

	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);

	inc_cpu_load(rq, p->se.load.weight);
}

@@ -728,6 +782,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
	update_curr_rt(rq);
	dequeue_rt_entity(rt_se);

	dequeue_pushable_task(rq, p);

	dec_cpu_load(rq, p->se.load.weight);
}

@@ -878,7 +934,7 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
	return next;
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
	struct sched_rt_entity *rt_se;
	struct task_struct *p;
@@ -900,6 +956,18 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)

	p = rt_task_of(rt_se);
	p->se.exec_start = rq->clock;

	return p;
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
{
	struct task_struct *p = _pick_next_task_rt(rq);

	/* The running task is never eligible for pushing */
	if (p)
		dequeue_pushable_task(rq, p);

	return p;
}

@@ -907,6 +975,13 @@ 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
	 * if it is still active
	 */
	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

#ifdef CONFIG_SMP
@@ -1072,7 +1147,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
		}

		/* If this rq is still suitable use it. */
		if (lowest_rq->rt.highest_prio > task->prio)
		if (lowest_rq->rt.highest_prio.curr > task->prio)
			break;

		/* try again */
@@ -1083,6 +1158,31 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
	return lowest_rq;
}

static inline int has_pushable_tasks(struct rq *rq)
{
	return !plist_head_empty(&rq->rt.pushable_tasks);
}

static struct task_struct *pick_next_pushable_task(struct rq *rq)
{
	struct task_struct *p;

	if (!has_pushable_tasks(rq))
		return NULL;

	p = plist_first_entry(&rq->rt.pushable_tasks,
			      struct task_struct, pushable_tasks);

	BUG_ON(rq->cpu != task_cpu(p));
	BUG_ON(task_current(rq, p));
	BUG_ON(p->rt.nr_cpus_allowed <= 1);

	BUG_ON(!p->se.on_rq);
	BUG_ON(!rt_task(p));

	return p;
}

/*
 * If the current CPU has more than one RT task, see if the non
 * running task can migrate over to a CPU that is running a task
@@ -1092,13 +1192,11 @@ static int push_rt_task(struct rq *rq)
{
	struct task_struct *next_task;
	struct rq *lowest_rq;
	int ret = 0;
	int paranoid = RT_MAX_TRIES;

	if (!rq->rt.overloaded)
		return 0;

	next_task = pick_next_highest_task_rt(rq, -1);
	next_task = pick_next_pushable_task(rq);
	if (!next_task)
		return 0;

@@ -1127,17 +1225,35 @@ static int push_rt_task(struct rq *rq)
		struct task_struct *task;
		/*
		 * find lock_lowest_rq releases rq->lock
		 * so it is possible that next_task has changed.
		 * If it has, then try again.
		 * so it is possible that next_task has migrated.
		 *
		 * We need to make sure that the task is still on the same
		 * run-queue and is also still the next task eligible for
		 * pushing.
		 */
		task = pick_next_pushable_task(rq);
		if (task_cpu(next_task) == rq->cpu && task == next_task) {
			/*
			 * If we get here, the task hasnt 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.
			 */
			dequeue_pushable_task(rq, next_task);
			goto out;
		}

		if (!task)
			/* No more tasks, just exit */
			goto out;

		/*
		 * Something has shifted, try again.
		 */
		task = pick_next_highest_task_rt(rq, -1);
		if (unlikely(task != next_task) && task && paranoid--) {
		put_task_struct(next_task);
		next_task = task;
		goto retry;
	}
		goto out;
	}

	deactivate_task(rq, next_task, 0);
	set_task_cpu(next_task, lowest_rq->cpu);
@@ -1147,23 +1263,12 @@ static int push_rt_task(struct rq *rq)

	double_unlock_balance(rq, lowest_rq);

	ret = 1;
out:
	put_task_struct(next_task);

	return ret;
	return 1;
}

/*
 * TODO: Currently we just use the second highest prio task on
 *       the queue, and stop when it can't migrate (or there's
 *       no more RT tasks).  There may be a case where a lower
 *       priority RT task has a different affinity than the
 *       higher RT task. In this case the lower RT task could
 *       possibly be able to migrate where as the higher priority
 *       RT task could not.  We currently ignore this issue.
 *       Enhancements are welcome!
 */
static void push_rt_tasks(struct rq *rq)
{
	/* push_rt_task will return true if it moved an RT */
@@ -1174,33 +1279,35 @@ static void push_rt_tasks(struct rq *rq)
static int pull_rt_task(struct rq *this_rq)
{
	int this_cpu = this_rq->cpu, ret = 0, cpu;
	struct task_struct *p, *next;
	struct task_struct *p;
	struct rq *src_rq;

	if (likely(!rt_overloaded(this_rq)))
		return 0;

	next = pick_next_task_rt(this_rq);

	for_each_cpu(cpu, this_rq->rd->rto_mask) {
		if (this_cpu == cpu)
			continue;

		src_rq = cpu_rq(cpu);

		/*
		 * Don't bother taking the src_rq->lock if the next highest
		 * task is known to be lower-priority than our current task.
		 * This may look racy, but if this value is about to go
		 * logically higher, the src_rq will push this task away.
		 * And if its going logically lower, we do not care
		 */
		if (src_rq->rt.highest_prio.next >=
		    this_rq->rt.highest_prio.curr)
			continue;

		/*
		 * We can potentially drop this_rq's lock in
		 * double_lock_balance, and another CPU could
		 * steal our next task - hence we must cause
		 * the caller to recalculate the next task
		 * in that case:
		 * alter this_rq
		 */
		if (double_lock_balance(this_rq, src_rq)) {
			struct task_struct *old_next = next;

			next = pick_next_task_rt(this_rq);
			if (next != old_next)
				ret = 1;
		}
		double_lock_balance(this_rq, src_rq);

		/*
		 * Are there still pullable RT tasks?
@@ -1214,7 +1321,7 @@ static int pull_rt_task(struct rq *this_rq)
		 * Do we have an RT task that preempts
		 * the to-be-scheduled task?
		 */
		if (p && (!next || (p->prio < next->prio))) {
		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
			WARN_ON(p == src_rq->curr);
			WARN_ON(!p->se.on_rq);

@@ -1224,12 +1331,9 @@ static int pull_rt_task(struct rq *this_rq)
			 * This is just that p is wakeing up and hasn't
			 * had a chance to schedule. We only pull
			 * p if it is lower in priority than the
			 * current task on the run queue or
			 * this_rq next task is lower in prio than
			 * the current task on that rq.
			 * current task on the run queue
			 */
			if (p->prio < src_rq->curr->prio ||
			    (next && next->prio < src_rq->curr->prio))
			if (p->prio < src_rq->curr->prio)
				goto skip;

			ret = 1;
@@ -1242,13 +1346,7 @@ static int pull_rt_task(struct rq *this_rq)
			 * case there's an even higher prio task
			 * in another runqueue. (low likelyhood
			 * but possible)
			 *
			 * Update next so that we won't pick a task
			 * on another cpu with a priority lower (or equal)
			 * than the one we just picked.
			 */
			next = p;

		}
 skip:
		double_unlock_balance(this_rq, src_rq);
@@ -1260,25 +1358,28 @@ static int pull_rt_task(struct rq *this_rq)
static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
{
	/* Try to pull RT tasks here if we lower this rq's prio */
	if (unlikely(rt_task(prev)) && rq->rt.highest_prio > prev->prio)
	if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio)
		pull_rt_task(rq);
}

/*
 * assumes rq->lock is held
 */
static int needs_post_schedule_rt(struct rq *rq)
{
	return has_pushable_tasks(rq);
}

static void post_schedule_rt(struct rq *rq)
{
	/*
	 * If we have more than one rt_task queued, then
	 * see if we can push the other rt_tasks off to other CPUS.
	 * Note we may release the rq lock, and since
	 * the lock was owned by prev, we need to release it
	 * first via finish_lock_switch and then reaquire it here.
	 * This is only called if needs_post_schedule_rt() indicates that
	 * we need to push tasks away
	 */
	if (unlikely(rq->rt.overloaded)) {
	spin_lock_irq(&rq->lock);
	push_rt_tasks(rq);
	spin_unlock_irq(&rq->lock);
}
}

/*
 * If we are not running and we are not going to reschedule soon, we should
@@ -1288,7 +1389,8 @@ static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
{
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    rq->rt.overloaded)
	    has_pushable_tasks(rq) &&
	    p->rt.nr_cpus_allowed > 1)
		push_rt_tasks(rq);
}

@@ -1324,6 +1426,24 @@ static void set_cpus_allowed_rt(struct task_struct *p,
	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
		struct rq *rq = task_rq(p);

		if (!task_current(rq, p)) {
			/*
			 * Make sure we dequeue this task from the pushable list
			 * before going further.  It will either remain off of
			 * the list because we are no longer pushable, or it
			 * will be requeued.
			 */
			if (p->rt.nr_cpus_allowed > 1)
				dequeue_pushable_task(rq, p);

			/*
			 * Requeue if our weight is changing and still > 1
			 */
			if (weight > 1)
				enqueue_pushable_task(rq, p);

		}

		if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
			rq->rt.rt_nr_migratory++;
		} else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
@@ -1346,7 +1466,7 @@ static void rq_online_rt(struct rq *rq)

	__enable_runtime(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
}

/* Assumes rq->lock is held */
@@ -1438,7 +1558,7 @@ static void prio_changed_rt(struct rq *rq, struct task_struct *p,
		 * can release the rq lock and p could migrate.
		 * Only reschedule if p is still on the same runqueue.
		 */
		if (p->prio > rq->rt.highest_prio && rq->curr == p)
		if (p->prio > rq->rt.highest_prio.curr && rq->curr == p)
			resched_task(p);
#else
		/* For UP simply resched on drop of prio */
@@ -1509,6 +1629,9 @@ static void set_curr_task_rt(struct rq *rq)
	struct task_struct *p = rq->curr;

	p->se.exec_start = rq->clock;

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);
}

static const struct sched_class rt_sched_class = {
@@ -1531,6 +1654,7 @@ static const struct sched_class rt_sched_class = {
	.rq_online              = rq_online_rt,
	.rq_offline             = rq_offline_rt,
	.pre_schedule		= pre_schedule_rt,
	.needs_post_schedule	= needs_post_schedule_rt,
	.post_schedule		= post_schedule_rt,
	.task_wake_up		= task_wake_up_rt,
	.switched_from		= switched_from_rt,