sched: Move all scheduler bits into kernel/sched/

There's too many sched*.[ch] files in kernel/, give them their own
directory.

(No code changed, other than Makefile glue added.)

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 0 insertions, 8101 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
deleted file mode 100644
index 2ffcceed886..00000000000
--- a/kernel/sched.c
+++ /dev/null
@@ -1,8101 +0,0 @@
-/*
- *  kernel/sched.c
- *
- *  Kernel scheduler and related syscalls
- *
- *  Copyright (C) 1991-2002  Linus Torvalds
- *
- *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
- *		make semaphores SMP safe
- *  1998-11-19	Implemented schedule_timeout() and related stuff
- *		by Andrea Arcangeli
- *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
- *		hybrid priority-list and round-robin design with
- *		an array-switch method of distributing timeslices
- *		and per-CPU runqueues.  Cleanups and useful suggestions
- *		by Davide Libenzi, preemptible kernel bits by Robert Love.
- *  2003-09-03	Interactivity tuning by Con Kolivas.
- *  2004-04-02	Scheduler domains code by Nick Piggin
- *  2007-04-15  Work begun on replacing all interactivity tuning with a
- *              fair scheduling design by Con Kolivas.
- *  2007-05-05  Load balancing (smp-nice) and other improvements
- *              by Peter Williams
- *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
- *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
- *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
- *              Thomas Gleixner, Mike Kravetz
- */
-
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/nmi.h>
-#include <linux/init.h>
-#include <linux/uaccess.h>
-#include <linux/highmem.h>
-#include <asm/mmu_context.h>
-#include <linux/interrupt.h>
-#include <linux/capability.h>
-#include <linux/completion.h>
-#include <linux/kernel_stat.h>
-#include <linux/debug_locks.h>
-#include <linux/perf_event.h>
-#include <linux/security.h>
-#include <linux/notifier.h>
-#include <linux/profile.h>
-#include <linux/freezer.h>
-#include <linux/vmalloc.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/pid_namespace.h>
-#include <linux/smp.h>
-#include <linux/threads.h>
-#include <linux/timer.h>
-#include <linux/rcupdate.h>
-#include <linux/cpu.h>
-#include <linux/cpuset.h>
-#include <linux/percpu.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/sysctl.h>
-#include <linux/syscalls.h>
-#include <linux/times.h>
-#include <linux/tsacct_kern.h>
-#include <linux/kprobes.h>
-#include <linux/delayacct.h>
-#include <linux/unistd.h>
-#include <linux/pagemap.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/debugfs.h>
-#include <linux/ctype.h>
-#include <linux/ftrace.h>
-#include <linux/slab.h>
-#include <linux/init_task.h>
-
-#include <asm/tlb.h>
-#include <asm/irq_regs.h>
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
-
-#include "sched.h"
-#include "workqueue_sched.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
-	unsigned long delta;
-	ktime_t soft, hard, now;
-
-	for (;;) {
-		if (hrtimer_active(period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(period_timer);
-		hrtimer_forward(period_timer, now, period);
-
-		soft = hrtimer_get_softexpires(period_timer);
-		hard = hrtimer_get_expires(period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(period_timer, soft, delta,
-					 HRTIMER_MODE_ABS_PINNED, 0);
-	}
-}
-
-DEFINE_MUTEX(sched_domains_mutex);
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-
-static void update_rq_clock_task(struct rq *rq, s64 delta);
-
-void update_rq_clock(struct rq *rq)
-{
-	s64 delta;
-
-	if (rq->skip_clock_update > 0)
-		return;
-
-	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
-	rq->clock += delta;
-	update_rq_clock_task(rq, delta);
-}
-
-/*
- * Debugging: various feature bits
- */
-
-#define SCHED_FEAT(name, enabled)	\
-	(1UL << __SCHED_FEAT_##name) * enabled |
-
-const_debug unsigned int sysctl_sched_features =
-#include "sched_features.h"
-	0;
-
-#undef SCHED_FEAT
-
-#ifdef CONFIG_SCHED_DEBUG
-#define SCHED_FEAT(name, enabled)	\
-	#name ,
-
-static __read_mostly char *sched_feat_names[] = {
-#include "sched_features.h"
-	NULL
-};
-
-#undef SCHED_FEAT
-
-static int sched_feat_show(struct seq_file *m, void *v)
-{
-	int i;
-
-	for (i = 0; sched_feat_names[i]; i++) {
-		if (!(sysctl_sched_features & (1UL << i)))
-			seq_puts(m, "NO_");
-		seq_printf(m, "%s ", sched_feat_names[i]);
-	}
-	seq_puts(m, "\n");
-
-	return 0;
-}
-
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	char *cmp;
-	int neg = 0;
-	int i;
-
-	if (cnt > 63)
-		cnt = 63;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-	cmp = strstrip(buf);
-
-	if (strncmp(cmp, "NO_", 3) == 0) {
-		neg = 1;
-		cmp += 3;
-	}
-
-	for (i = 0; sched_feat_names[i]; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg)
-				sysctl_sched_features &= ~(1UL << i);
-			else
-				sysctl_sched_features |= (1UL << i);
-			break;
-		}
-	}
-
-	if (!sched_feat_names[i])
-		return -EINVAL;
-
-	*ppos += cnt;
-
-	return cnt;
-}
-
-static int sched_feat_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, sched_feat_show, NULL);
-}
-
-static const struct file_operations sched_feat_fops = {
-	.open		= sched_feat_open,
-	.write		= sched_feat_write,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static __init int sched_init_debug(void)
-{
-	debugfs_create_file("sched_features", 0644, NULL, NULL,
-			&sched_feat_fops);
-
-	return 0;
-}
-late_initcall(sched_init_debug);
-
-#endif
-
-/*
- * Number of tasks to iterate in a single balance run.
- * Limited because this is done with IRQs disabled.
- */
-const_debug unsigned int sysctl_sched_nr_migrate = 32;
-
-/*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
-/*
- * period over which we measure -rt task cpu usage in us.
- * default: 1s
- */
-unsigned int sysctl_sched_rt_period = 1000000;
-
-__read_mostly int scheduler_running;
-
-/*
- * part of the period that we allow rt tasks to run in us.
- * default: 0.95s
- */
-int sysctl_sched_rt_runtime = 950000;
-
-
-
-/*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	lockdep_assert_held(&p->pi_lock);
-
-	for (;;) {
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-	}
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
-	__acquires(p->pi_lock)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	for (;;) {
-		raw_spin_lock_irqsave(&p->pi_lock, *flags);
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-	}
-}
-
-static void __task_rq_unlock(struct rq *rq)
-	__releases(rq->lock)
-{
-	raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
-	__releases(rq->lock)
-	__releases(p->pi_lock)
-{
-	raw_spin_unlock(&rq->lock);
-	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-}
-
-/*
- * this_rq_lock - lock this runqueue and disable interrupts.
- */
-static struct rq *this_rq_lock(void)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	local_irq_disable();
-	rq = this_rq();
-	raw_spin_lock(&rq->lock);
-
-	return rq;
-}
-
-#ifdef CONFIG_SCHED_HRTICK
-/*
- * Use HR-timers to deliver accurate preemption points.
- *
- * Its all a bit involved since we cannot program an hrt while holding the
- * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
- * reschedule event.
- *
- * When we get rescheduled we reprogram the hrtick_timer outside of the
- * rq->lock.
- */
-
-static void hrtick_clear(struct rq *rq)
-{
-	if (hrtimer_active(&rq->hrtick_timer))
-		hrtimer_cancel(&rq->hrtick_timer);
-}
-
-/*
- * High-resolution timer tick.
- * Runs from hardirq context with interrupts disabled.
- */
-static enum hrtimer_restart hrtick(struct hrtimer *timer)
-{
-	struct rq *rq = container_of(timer, struct rq, hrtick_timer);
-
-	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-
-	raw_spin_lock(&rq->lock);
-	update_rq_clock(rq);
-	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
-	raw_spin_unlock(&rq->lock);
-
-	return HRTIMER_NORESTART;
-}
-
-#ifdef CONFIG_SMP
-/*
- * called from hardirq (IPI) context
- */
-static void __hrtick_start(void *arg)
-{
-	struct rq *rq = arg;
-
-	raw_spin_lock(&rq->lock);
-	hrtimer_restart(&rq->hrtick_timer);
-	rq->hrtick_csd_pending = 0;
-	raw_spin_unlock(&rq->lock);
-}
-
-/*
- * Called to set the hrtick timer state.
- *
- * called with rq->lock held and irqs disabled
- */
-void hrtick_start(struct rq *rq, u64 delay)
-{
-	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
-
-	hrtimer_set_expires(timer, time);
-
-	if (rq == this_rq()) {
-		hrtimer_restart(timer);
-	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
-		rq->hrtick_csd_pending = 1;
-	}
-}
-
-static int
-hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-	int cpu = (int)(long)hcpu;
-
-	switch (action) {
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		hrtick_clear(cpu_rq(cpu));
-		return NOTIFY_OK;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static __init void init_hrtick(void)
-{
-	hotcpu_notifier(hotplug_hrtick, 0);
-}
-#else
-/*
- * Called to set the hrtick timer state.
- *
- * called with rq->lock held and irqs disabled
- */
-void hrtick_start(struct rq *rq, u64 delay)
-{
-	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
-}
-
-static inline void init_hrtick(void)
-{
-}
-#endif /* CONFIG_SMP */
-
-static void init_rq_hrtick(struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	rq->hrtick_csd_pending = 0;
-
-	rq->hrtick_csd.flags = 0;
-	rq->hrtick_csd.func = __hrtick_start;
-	rq->hrtick_csd.info = rq;
-#endif
-
-	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	rq->hrtick_timer.function = hrtick;
-}
-#else	/* CONFIG_SCHED_HRTICK */
-static inline void hrtick_clear(struct rq *rq)
-{
-}
-
-static inline void init_rq_hrtick(struct rq *rq)
-{
-}
-
-static inline void init_hrtick(void)
-{
-}
-#endif	/* CONFIG_SCHED_HRTICK */
-
-/*
- * resched_task - mark a task 'to be rescheduled now'.
- *
- * On UP this means the setting of the need_resched flag, on SMP it
- * might also involve a cross-CPU call to trigger the scheduler on
- * the target CPU.
- */
-#ifdef CONFIG_SMP
-
-#ifndef tsk_is_polling
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
-#endif
-
-void resched_task(struct task_struct *p)
-{
-	int cpu;
-
-	assert_raw_spin_locked(&task_rq(p)->lock);
-
-	if (test_tsk_need_resched(p))
-		return;
-
-	set_tsk_need_resched(p);
-
-	cpu = task_cpu(p);
-	if (cpu == smp_processor_id())
-		return;
-
-	/* NEED_RESCHED must be visible before we test polling */
-	smp_mb();
-	if (!tsk_is_polling(p))
-		smp_send_reschedule(cpu);
-}
-
-void resched_cpu(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
-
-	if (!raw_spin_trylock_irqsave(&rq->lock, flags))
-		return;
-	resched_task(cpu_curr(cpu));
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
-#ifdef CONFIG_NO_HZ
-/*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu.  This is good for power-savings.
- *
- * We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
- */
-int get_nohz_timer_target(void)
-{
-	int cpu = smp_processor_id();
-	int i;
-	struct sched_domain *sd;
-
-	rcu_read_lock();
-	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i)) {
-				cpu = i;
-				goto unlock;
-			}
-		}
-	}
-unlock:
-	rcu_read_unlock();
-	return cpu;
-}
-/*
- * When add_timer_on() enqueues a timer into the timer wheel of an
- * idle CPU then this timer might expire before the next timer event
- * which is scheduled to wake up that CPU. In case of a completely
- * idle system the next event might even be infinite time into the
- * future. wake_up_idle_cpu() ensures that the CPU is woken up and
- * leaves the inner idle loop so the newly added timer is taken into
- * account when the CPU goes back to idle and evaluates the timer
- * wheel for the next timer event.
- */
-void wake_up_idle_cpu(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	if (cpu == smp_processor_id())
-		return;
-
-	/*
-	 * This is safe, as this function is called with the timer
-	 * wheel base lock of (cpu) held. When the CPU is on the way
-	 * to idle and has not yet set rq->curr to idle then it will
-	 * be serialized on the timer wheel base lock and take the new
-	 * timer into account automatically.
-	 */
-	if (rq->curr != rq->idle)
-		return;
-
-	/*
-	 * We can set TIF_RESCHED on the idle task of the other CPU
-	 * lockless. The worst case is that the other CPU runs the
-	 * idle task through an additional NOOP schedule()
-	 */
-	set_tsk_need_resched(rq->idle);
-
-	/* NEED_RESCHED must be visible before we test polling */
-	smp_mb();
-	if (!tsk_is_polling(rq->idle))
-		smp_send_reschedule(cpu);
-}
-
-static inline bool got_nohz_idle_kick(void)
-{
-	return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
-}
-
-#else /* CONFIG_NO_HZ */
-
-static inline bool got_nohz_idle_kick(void)
-{
-	return false;
-}
-
-#endif /* CONFIG_NO_HZ */
-
-void sched_avg_update(struct rq *rq)
-{
-	s64 period = sched_avg_period();
-
-	while ((s64)(rq->clock - rq->age_stamp) > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (rq->age_stamp));
-		rq->age_stamp += period;
-		rq->rt_avg /= 2;
-	}
-}
-
-#else /* !CONFIG_SMP */
-void resched_task(struct task_struct *p)
-{
-	assert_raw_spin_locked(&task_rq(p)->lock);
-	set_tsk_need_resched(p);
-}
-#endif /* CONFIG_SMP */
-
-#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
-			(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
-/*
- * Iterate task_group tree rooted at *from, calling @down when first entering a
- * node and @up when leaving it for the final time.
- *
- * Caller must hold rcu_lock or sufficient equivalent.
- */
-int walk_tg_tree_from(struct task_group *from,
-			     tg_visitor down, tg_visitor up, void *data)
-{
-	struct task_group *parent, *child;
-	int ret;
-
-	parent = from;
-
-down:
-	ret = (*down)(parent, data);
-	if (ret)
-		goto out;
-	list_for_each_entry_rcu(child, &parent->children, siblings) {
-		parent = child;
-		goto down;
-
-up:
-		continue;
-	}
-	ret = (*up)(parent, data);
-	if (ret || parent == from)
-		goto out;
-
-	child = parent;
-	parent = parent->parent;
-	if (parent)
-		goto up;
-out:
-	return ret;
-}
-
-int tg_nop(struct task_group *tg, void *data)
-{
-	return 0;
-}
-#endif
-
-void update_cpu_load(struct rq *this_rq);
-
-static void set_load_weight(struct task_struct *p)
-{
-	int prio = p->static_prio - MAX_RT_PRIO;
-	struct load_weight *load = &p->se.load;
-
-	/*
-	 * SCHED_IDLE tasks get minimal weight:
-	 */
-	if (p->policy == SCHED_IDLE) {
-		load->weight = scale_load(WEIGHT_IDLEPRIO);
-		load->inv_weight = WMULT_IDLEPRIO;
-		return;
-	}
-
-	load->weight = scale_load(prio_to_weight[prio]);
-	load->inv_weight = prio_to_wmult[prio];
-}
-
-static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
-{
-	update_rq_clock(rq);
-	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, flags);
-}
-
-static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
-{
-	update_rq_clock(rq);
-	sched_info_dequeued(p);
-	p->sched_class->dequeue_task(rq, p, flags);
-}
-
-/*
- * activate_task - move a task to the runqueue.
- */
-void activate_task(struct rq *rq, struct task_struct *p, int flags)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
-	enqueue_task(rq, p, flags);
-}
-
-/*
- * deactivate_task - remove a task from the runqueue.
- */
-void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
-	dequeue_task(rq, p, flags);
-}
-
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-
-/*
- * There are no locks covering percpu hardirq/softirq time.
- * They are only modified in account_system_vtime, on corresponding CPU
- * with interrupts disabled. So, writes are safe.
- * They are read and saved off onto struct rq in update_rq_clock().
- * This may result in other CPU reading this CPU's irq time and can
- * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value with a side effect of accounting a slice of irq time to wrong
- * task when irq is in progress while we read rq->clock. That is a worthy
- * compromise in place of having locks on each irq in account_system_time.
- */
-static DEFINE_PER_CPU(u64, cpu_hardirq_time);
-static DEFINE_PER_CPU(u64, cpu_softirq_time);
-
-static DEFINE_PER_CPU(u64, irq_start_time);
-static int sched_clock_irqtime;
-
-void enable_sched_clock_irqtime(void)
-{
-	sched_clock_irqtime = 1;
-}
-
-void disable_sched_clock_irqtime(void)
-{
-	sched_clock_irqtime = 0;
-}
-
-#ifndef CONFIG_64BIT
-static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
-
-static inline void irq_time_write_begin(void)
-{
-	__this_cpu_inc(irq_time_seq.sequence);
-	smp_wmb();
-}
-
-static inline void irq_time_write_end(void)
-{
-	smp_wmb();
-	__this_cpu_inc(irq_time_seq.sequence);
-}
-
-static inline u64 irq_time_read(int cpu)
-{
-	u64 irq_time;
-	unsigned seq;
-
-	do {
-		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
-		irq_time = per_cpu(cpu_softirq_time, cpu) +
-			   per_cpu(cpu_hardirq_time, cpu);
-	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
-
-	return irq_time;
-}
-#else /* CONFIG_64BIT */
-static inline void irq_time_write_begin(void)
-{
-}
-
-static inline void irq_time_write_end(void)
-{
-}
-
-static inline u64 irq_time_read(int cpu)
-{
-	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
-}
-#endif /* CONFIG_64BIT */
-
-/*
- * Called before incrementing preempt_count on {soft,}irq_enter
- * and before decrementing preempt_count on {soft,}irq_exit.
- */
-void account_system_vtime(struct task_struct *curr)
-{
-	unsigned long flags;
-	s64 delta;
-	int cpu;
-
-	if (!sched_clock_irqtime)
-		return;
-
-	local_irq_save(flags);
-
-	cpu = smp_processor_id();
-	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
-	__this_cpu_add(irq_start_time, delta);
-
-	irq_time_write_begin();
-	/*
-	 * We do not account for softirq time from ksoftirqd here.
-	 * We want to continue accounting softirq time to ksoftirqd thread
-	 * in that case, so as not to confuse scheduler with a special task
-	 * that do not consume any time, but still wants to run.
-	 */
-	if (hardirq_count())
-		__this_cpu_add(cpu_hardirq_time, delta);
-	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
-		__this_cpu_add(cpu_softirq_time, delta);
-
-	irq_time_write_end();
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(account_system_vtime);
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
-	if (unlikely(steal > NSEC_PER_SEC))
-		return div_u64(steal, TICK_NSEC);
-
-	return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
-
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-/*
- * In theory, the compile should just see 0 here, and optimize out the call
- * to sched_rt_avg_update. But I don't trust it...
- */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-
-	/*
-	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
-	 * this case when a previous update_rq_clock() happened inside a
-	 * {soft,}irq region.
-	 *
-	 * When this happens, we stop ->clock_task and only update the
-	 * prev_irq_time stamp to account for the part that fit, so that a next
-	 * update will consume the rest. This ensures ->clock_task is
-	 * monotonic.
-	 *
-	 * It does however cause some slight miss-attribution of {soft,}irq
-	 * time, a more accurate solution would be to update the irq_time using
-	 * the current rq->clock timestamp, except that would require using
-	 * atomic ops.
-	 */
-	if (irq_delta > delta)
-		irq_delta = delta;
-
-	rq->prev_irq_time += irq_delta;
-	delta -= irq_delta;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	if (static_branch((&paravirt_steal_rq_enabled))) {
-		u64 st;
-
-		steal = paravirt_steal_clock(cpu_of(rq));
-		steal -= rq->prev_steal_time_rq;
-
-		if (unlikely(steal > delta))
-			steal = delta;
-
-		st = steal_ticks(steal);
-		steal = st * TICK_NSEC;
-
-		rq->prev_steal_time_rq += steal;
-
-		delta -= steal;
-	}
-#endif
-
-	rq->clock_task += delta;
-
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
-		sched_rt_avg_update(rq, irq_delta + steal);
-#endif
-}
-
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-static int irqtime_account_hi_update(void)
-{
-	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	unsigned long flags;
-	u64 latest_ns;
-	int ret = 0;
-
-	local_irq_save(flags);
-	latest_ns = this_cpu_read(cpu_hardirq_time);
-	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
-		ret = 1;
-	local_irq_restore(flags);
-	return ret;
-}
-
-static int irqtime_account_si_update(void)
-{
-	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	unsigned long flags;
-	u64 latest_ns;
-	int ret = 0;
-
-	local_irq_save(flags);
-	latest_ns = this_cpu_read(cpu_softirq_time);
-	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
-		ret = 1;
-	local_irq_restore(flags);
-	return ret;
-}
-
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#define sched_clock_irqtime	(0)
-
-#endif
-
-void sched_set_stop_task(int cpu, struct task_struct *stop)
-{
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
-	struct task_struct *old_stop = cpu_rq(cpu)->stop;
-
-	if (stop) {
-		/*
-		 * Make it appear like a SCHED_FIFO task, its something
-		 * userspace knows about and won't get confused about.
-		 *
-		 * Also, it will make PI more or less work without too
-		 * much confusion -- but then, stop work should not
-		 * rely on PI working anyway.
-		 */
-		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
-
-		stop->sched_class = &stop_sched_class;
-	}
-
-	cpu_rq(cpu)->stop = stop;
-
-	if (old_stop) {
-		/*
-		 * Reset it back to a normal scheduling class so that
-		 * it can die in pieces.
-		 */
-		old_stop->sched_class = &rt_sched_class;
-	}
-}
-
-/*
- * __normal_prio - return the priority that is based on the static prio
- */
-static inline int __normal_prio(struct task_struct *p)
-{
-	return p->static_prio;
-}
-
-/*
- * Calculate the expected normal priority: i.e. priority
- * without taking RT-inheritance into account. Might be
- * boosted by interactivity modifiers. Changes upon fork,
- * setprio syscalls, and whenever the interactivity
- * estimator recalculates.
- */
-static inline int normal_prio(struct task_struct *p)
-{
-	int prio;
-
-	if (task_has_rt_policy(p))
-		prio = MAX_RT_PRIO-1 - p->rt_priority;
-	else
-		prio = __normal_prio(p);
-	return prio;
-}
-
-/*
- * Calculate the current priority, i.e. the priority
- * taken into account by the scheduler. This value might
- * be boosted by RT tasks, or might be boosted by
- * interactivity modifiers. Will be RT if the task got
- * RT-boosted. If not then it returns p->normal_prio.
- */
-static int effective_prio(struct task_struct *p)
-{
-	p->normal_prio = normal_prio(p);
-	/*
-	 * If we are RT tasks or we were boosted to RT priority,
-	 * keep the priority unchanged. Otherwise, update priority
-	 * to the normal priority:
-	 */
-	if (!rt_prio(p->prio))
-		return p->normal_prio;
-	return p->prio;
-}
-
-/**
- * task_curr - is this task currently executing on a CPU?
- * @p: the task in question.
- */
-inline int task_curr(const struct task_struct *p)
-{
-	return cpu_curr(task_cpu(p)) == p;
-}
-
-static inline void check_class_changed(struct rq *rq, struct task_struct *p,
-				       const struct sched_class *prev_class,
-				       int oldprio)
-{
-	if (prev_class != p->sched_class) {
-		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p);
-		p->sched_class->switched_to(rq, p);
-	} else if (oldprio != p->prio)
-		p->sched_class->prio_changed(rq, p, oldprio);
-}
-
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-	const struct sched_class *class;
-
-	if (p->sched_class == rq->curr->sched_class) {
-		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	} else {
-		for_each_class(class) {
-			if (class == rq->curr->sched_class)
-				break;
-			if (class == p->sched_class) {
-				resched_task(rq->curr);
-				break;
-			}
-		}
-	}
-
-	/*
-	 * A queue event has occurred, and we're going to schedule.  In
-	 * this case, we can save a useless back to back clock update.
-	 */
-	if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
-		rq->skip_clock_update = 1;
-}
-
-#ifdef CONFIG_SMP
-void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
-{
-#ifdef CONFIG_SCHED_DEBUG
-	/*
-	 * We should never call set_task_cpu() on a blocked task,
-	 * ttwu() will sort out the placement.
-	 */
-	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
-
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * The caller should hold either p->pi_lock or rq->lock, when changing
-	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
-	 *
-	 * sched_move_task() holds both and thus holding either pins the cgroup,
-	 * see set_task_rq().
-	 *
-	 * Furthermore, all task_rq users should acquire both locks, see
-	 * task_rq_lock().
-	 */
-	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-				      lockdep_is_held(&task_rq(p)->lock)));
-#endif
-#endif
-
-	trace_sched_migrate_task(p, new_cpu);
-
-	if (task_cpu(p) != new_cpu) {
-		p->se.nr_migrations++;
-		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
-	}
-
-	__set_task_cpu(p, new_cpu);
-}
-
-struct migration_arg {
-	struct task_struct *task;
-	int dest_cpu;
-};
-
-static int migration_cpu_stop(void *data);
-
-/*
- * wait_task_inactive - wait for a thread to unschedule.
- *
- * If @match_state is nonzero, it's the @p->state value just checked and
- * not expected to change.  If it changes, i.e. @p might have woken up,
- * then return zero.  When we succeed in waiting for @p to be off its CPU,
- * we return a positive number (its total switch count).  If a second call
- * a short while later returns the same number, the caller can be sure that
- * @p has remained unscheduled the whole time.
- *
- * The caller must ensure that the task *will* unschedule sometime soon,
- * else this function might spin for a *long* time. This function can't
- * be called with interrupts off, or it may introduce deadlock with
- * smp_call_function() if an IPI is sent by the same process we are
- * waiting to become inactive.
- */
-unsigned long wait_task_inactive(struct task_struct *p, long match_state)
-{
-	unsigned long flags;
-	int running, on_rq;
-	unsigned long ncsw;
-	struct rq *rq;
-
-	for (;;) {
-		/*
-		 * We do the initial early heuristics without holding
-		 * any task-queue locks at all. We'll only try to get
-		 * the runqueue lock when things look like they will
-		 * work out!
-		 */
-		rq = task_rq(p);
-
-		/*
-		 * If the task is actively running on another CPU
-		 * still, just relax and busy-wait without holding
-		 * any locks.
-		 *
-		 * NOTE! Since we don't hold any locks, it's not
-		 * even sure that "rq" stays as the right runqueue!
-		 * But we don't care, since "task_running()" will
-		 * return false if the runqueue has changed and p
-		 * is actually now running somewhere else!
-		 */
-		while (task_running(rq, p)) {
-			if (match_state && unlikely(p->state != match_state))
-				return 0;
-			cpu_relax();
-		}
-
-		/*
-		 * Ok, time to look more closely! We need the rq
-		 * lock now, to be *sure*. If we're wrong, we'll
-		 * just go back and repeat.
-		 */
-		rq = task_rq_lock(p, &flags);
-		trace_sched_wait_task(p);
-		running = task_running(rq, p);
-		on_rq = p->on_rq;
-		ncsw = 0;
-		if (!match_state || p->state == match_state)
-			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-		task_rq_unlock(rq, p, &flags);
-
-		/*
-		 * If it changed from the expected state, bail out now.
-		 */
-		if (unlikely(!ncsw))
-			break;
-
-		/*
-		 * Was it really running after all now that we
-		 * checked with the proper locks actually held?
-		 *
-		 * Oops. Go back and try again..
-		 */
-		if (unlikely(running)) {
-			cpu_relax();
-			continue;
-		}
-
-		/*
-		 * It's not enough that it's not actively running,
-		 * it must be off the runqueue _entirely_, and not
-		 * preempted!
-		 *
-		 * So if it was still runnable (but just not actively
-		 * running right now), it's preempted, and we should
-		 * yield - it could be a while.
-		 */
-		if (unlikely(on_rq)) {
-			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
-
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
-			continue;
-		}
-
-		/*
-		 * Ahh, all good. It wasn't running, and it wasn't
-		 * runnable, which means that it will never become
-		 * running in the future either. We're all done!
-		 */
-		break;
-	}
-
-	return ncsw;
-}
-
-/***
- * kick_process - kick a running thread to enter/exit the kernel
- * @p: the to-be-kicked thread
- *
- * Cause a process which is running on another CPU to enter
- * kernel-mode, without any delay. (to get signals handled.)
- *
- * NOTE: this function doesn't have to take the runqueue lock,
- * because all it wants to ensure is that the remote task enters
- * the kernel. If the IPI races and the task has been migrated
- * to another CPU then no harm is done and the purpose has been
- * achieved as well.
- */
-void kick_process(struct task_struct *p)
-{
-	int cpu;
-
-	preempt_disable();
-	cpu = task_cpu(p)