Release 4.15 kernel/sched/core.c

/*
 *  kernel/sched/core.c
 *
 *  Core kernel scheduler code and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 */
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <uapi/linux/sched/types.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/hotplug.h>
#include <linux/wait_bit.h>
#include <linux/cpuset.h>
#include <linux/delayacct.h>
#include <linux/init_task.h>
#include <linux/context_tracking.h>
#include <linux/rcupdate_wait.h>
#include <linux/compat.h>

#include <linux/blkdev.h>
#include <linux/kprobes.h>
#include <linux/mmu_context.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/prefetch.h>
#include <linux/profile.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/sched/isolation.h>

#include <asm/switch_to.h>
#include <asm/tlb.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif

#include "sched.h"
#include "../workqueue_internal.h"
#include "../smpboot.h"


#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>

DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
/*
 * Debugging: various feature bits
 *
 * If SCHED_DEBUG is disabled, each compilation unit has its own copy of
 * sysctl_sched_features, defined in sched.h, to allow constants propagation
 * at compile time and compiler optimization based on features default.
 */

#define SCHED_FEAT(name, enabled)	\
	(1UL << __SCHED_FEAT_##name) * enabled |

const_debug unsigned int sysctl_sched_features =
#include "features.h"
	0;

#undef SCHED_FEAT
#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.
 */

struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
	__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) && !task_on_rq_migrating(p))) {
			rq_pin_lock(rq, rf);
			return rq;
		}
		raw_spin_unlock(&rq->lock);

		while (unlikely(task_on_rq_migrating(p)))
			cpu_relax();
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
106
97.25%
2
66.67%
Matt Fleming
3
2.75%
1
33.33%
Total
109
100.00%
3
100.00%

/*
 * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
 */

struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
	__acquires(p->pi_lock)
	__acquires(rq->lock)
{
	struct rq *rq;

	for (;;) {
		raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
		rq = task_rq(p);
		raw_spin_lock(&rq->lock);
		/*
                 *      move_queued_task()              task_rq_lock()
                 *
                 *      ACQUIRE (rq->lock)
                 *      [S] ->on_rq = MIGRATING         [L] rq = task_rq()
                 *      WMB (__set_task_cpu())          ACQUIRE (rq->lock);
                 *      [S] ->cpu = new_cpu             [L] task_rq()
                 *                                      [L] ->on_rq
                 *      RELEASE (rq->lock)
                 *
                 * If we observe the old cpu in task_rq_lock, the acquire of
                 * the old rq->lock will fully serialize against the stores.
                 *
                 * If we observe the new CPU in task_rq_lock, the acquire will
                 * pair with the WMB to ensure we must then also see migrating.
                 */
		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
			rq_pin_lock(rq, rf);
			return rq;
		}
		raw_spin_unlock(&rq->lock);
		raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);

		while (unlikely(task_on_rq_migrating(p)))
			cpu_relax();
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
87
65.91%
2
40.00%
Ingo Molnar
44
33.33%
2
40.00%
Matt Fleming
1
0.76%
1
20.00%
Total
132
100.00%
5
100.00%

/*
 * RQ-clock updating methods:
 */



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_key_false((&paravirt_steal_rq_enabled))) {
		steal = paravirt_steal_clock(cpu_of(rq));
		steal -= rq->prev_steal_time_rq;

		if (unlikely(steal > delta))
			steal = delta;

		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_CAPACITY))
		sched_rt_avg_update(rq, irq_delta + steal);
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ingo Molnar
174
100.00%
1
100.00%
Total
174
100.00%
1
100.00%



void update_rq_clock(struct rq *rq)
{
	s64 delta;

	lockdep_assert_held(&rq->lock);

	if (rq->clock_update_flags & RQCF_ACT_SKIP)
		return;

#ifdef CONFIG_SCHED_DEBUG
	if (sched_feat(WARN_DOUBLE_CLOCK))
		SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
	rq->clock_update_flags |= RQCF_UPDATED;
#endif

	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
	if (delta < 0)
		return;
	rq->clock += delta;
	update_rq_clock_task(rq, delta);
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
Ingo Molnar
57
62.64%
1
25.00%
Peter Zijlstra
34
37.36%
3
75.00%
Total
91
100.00%
4
100.00%

#ifdef CONFIG_SCHED_HRTICK
/*
 * Use HR-timers to deliver accurate preemption points.
 */



static void hrtick_clear(struct rq *rq)
{
	if (hrtimer_active(&rq->hrtick_timer))
		hrtimer_cancel(&rq->hrtick_timer);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
89.66%
3
50.00%
Gregory Haskins
1
3.45%
1
16.67%
Linus Torvalds
1
3.45%
1
16.67%
Steven Rostedt
1
3.45%
1
16.67%
Total
29
100.00%
6
100.00%

/*
 * 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);
	struct rq_flags rf;

	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());

	rq_lock(rq, &rf);
	update_rq_clock(rq);
	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
	rq_unlock(rq, &rf);

	return HRTIMER_NORESTART;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
65
78.31%
7
50.00%
Paul Turner
9
10.84%
1
7.14%
Mel Gorman
3
3.61%
1
7.14%
Peter Williams
2
2.41%
1
7.14%
Mike Galbraith
1
1.20%
1
7.14%
Ingo Molnar
1
1.20%
1
7.14%
Nikhil P Rao
1
1.20%
1
7.14%
Rik Van Riel
1
1.20%
1
7.14%
Total
83
100.00%
14
100.00%

#ifdef CONFIG_SMP



static void __hrtick_restart(struct rq *rq)
{
	struct hrtimer *timer = &rq->hrtick_timer;

	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
12
42.86%
1
20.00%
Mel Gorman
8
28.57%
1
20.00%
Jason Baron
5
17.86%
1
20.00%
Thomas Gleixner
2
7.14%
1
20.00%
Paul Turner
1
3.57%
1
20.00%
Total
28
100.00%
5
100.00%

/*
 * called from hardirq (IPI) context
 */


static void __hrtick_start(void *arg)
{
	struct rq *rq = arg;
	struct rq_flags rf;

	rq_lock(rq, &rf);
	__hrtick_restart(rq);
	rq->hrtick_csd_pending = 0;
	rq_unlock(rq, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
36
75.00%
6
54.55%
Paul Turner
10
20.83%
3
27.27%
Ingo Molnar
2
4.17%
2
18.18%
Total
48
100.00%
11
100.00%

/*
 * 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;
	s64 delta;

	/*
         * Don't schedule slices shorter than 10000ns, that just
         * doesn't make sense and can cause timer DoS.
         */
	delta = max_t(s64, delay, 10000LL);
	time = ktime_add_ns(timer->base->get_time(), delta);

	hrtimer_set_expires(timer, time);

	if (rq == this_rq()) {
		__hrtick_restart(rq);
	} else if (!rq->hrtick_csd_pending) {
		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
		rq->hrtick_csd_pending = 1;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
68
64.76%
9
42.86%
xiaofeng.yan
20
19.05%
1
4.76%
Ingo Molnar
7
6.67%
3
14.29%
Steven Rostedt
3
2.86%
1
4.76%
Andrew Morton
1
0.95%
1
4.76%
Paul Turner
1
0.95%
1
4.76%
Gregory Haskins
1
0.95%
1
4.76%
Frédéric Weisbecker
1
0.95%
1
4.76%
Tejun Heo
1
0.95%
1
4.76%
Paul Mackerras
1
0.95%
1
4.76%
Linus Torvalds
1
0.95%
1
4.76%
Total
105
100.00%
21
100.00%

#else
/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */


void hrtick_start(struct rq *rq, u64 delay)
{
	/*
         * Don't schedule slices shorter than 10000ns, that just
         * doesn't make sense. Rely on vruntime for fairness.
         */
	delay = max_t(u64, delay, 10000LL);
	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
		      HRTIMER_MODE_REL_PINNED);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Wanpeng Li
12
30.00%
1
10.00%
Peter Zijlstra
11
27.50%
2
20.00%
Tejun Heo
8
20.00%
1
10.00%
Alexey Dobriyan
3
7.50%
1
10.00%
Ingo Molnar
2
5.00%
1
10.00%
Mathieu Desnoyers
1
2.50%
1
10.00%
Thomas Gleixner
1
2.50%
1
10.00%
Rusty Russell
1
2.50%
1
10.00%
Linus Torvalds
1
2.50%
1
10.00%
Total
40
100.00%
10
100.00%

#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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
31
46.97%
2
28.57%
Tejun Heo
21
31.82%
1
14.29%
Gregory Haskins
8
12.12%
1
14.29%
Linus Torvalds
3
4.55%
1
14.29%
Alexey Dobriyan
2
3.03%
1
14.29%
Rusty Russell
1
1.52%
1
14.29%
Total
66
100.00%
7
100.00%

#else	/* CONFIG_SCHED_HRTICK */


static inline void hrtick_clear(struct rq *rq)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
100.00%
2
100.00%
Total
11
100.00%
2
100.00%



static inline void init_rq_hrtick(struct rq *rq)
{
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
100.00%
2
100.00%
Total
11
100.00%
2
100.00%

#endif	/* CONFIG_SCHED_HRTICK */

/*
 * cmpxchg based fetch_or, macro so it works for different integer types
 */

#define fetch_or(ptr, mask)						\
	({                                                              \
                typeof(ptr) _ptr = (ptr);                               \
                typeof(mask) _mask = (mask);                            \
                typeof(*_ptr) _old, _val = *_ptr;                       \
                                                                        \
                for (;;) {                                              \
                        _old = cmpxchg(_ptr, _val, _val | _mask);       \
                        if (_old == _val)                               \
                                break;                                  \
                        _val = _old;                                    \
                }                                                       \
        _old;                                                           \
})

#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
/*
 * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
 * this avoids any races wrt polling state changes and thereby avoids
 * spurious IPIs.
 */


static bool set_nr_and_not_polling(struct task_struct *p)
{
	struct thread_info *ti = task_thread_info(p);
	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
37
100.00%
1
100.00%
Total
37
100.00%
1
100.00%

/*
 * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
 *
 * If this returns true, then the idle task promises to call
 * sched_ttwu_pending() and reschedule soon.
 */


static bool set_nr_if_polling(struct task_struct *p)
{
	struct thread_info *ti = task_thread_info(p);
	typeof(ti->flags) old, val = READ_ONCE(ti->flags);

	for (;;) {
		if (!(val & _TIF_POLLING_NRFLAG))
			return false;
		if (val & _TIF_NEED_RESCHED)
			return true;
		old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
		if (old == val)
			break;
		val = old;
	}
	return true;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
93
98.94%
1
50.00%
Jason Low
1
1.06%
1
50.00%
Total
94
100.00%
2
100.00%

#else


static bool set_nr_and_not_polling(struct task_struct *p)
{
	set_tsk_need_resched(p);
	return true;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

#ifdef CONFIG_SMP


static bool set_nr_if_polling(struct task_struct *p)
{
	return false;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
14
100.00%
1
100.00%
Total
14
100.00%
1
100.00%

#endif
#endif



void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
	struct wake_q_node *node = &task->wake_q;

	/*
         * Atomically grab the task, if ->wake_q is !nil already it means
         * its already queued (either by us or someone else) and will get the
         * wakeup due to that.
         *
         * This cmpxchg() implies a full barrier, which pairs with the write
         * barrier implied by the wakeup in wake_up_q().
         */
	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
		return;

	get_task_struct(task);

	/*
         * The head is context local, there can be no concurrency.
         */
	*head->lastp = node;
	head->lastp = &node->next;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
62
98.41%
1
50.00%
Davidlohr Bueso A
1
1.59%
1
50.00%
Total
63
100.00%
2
100.00%



void wake_up_q(struct wake_q_head *head)
{
	struct wake_q_node *node = head->first;

	while (node != WAKE_Q_TAIL) {
		struct task_struct *task;

		task = container_of(node, struct task_struct, wake_q);
		BUG_ON(!task);
		/* Task can safely be re-inserted now: */
		node = node->next;
		task->wake_q.next = NULL;

		/*
                 * wake_up_process() implies a wmb() to pair with the queueing
                 * in wake_q_add() so as not to miss wakeups.
                 */
		wake_up_process(task);
		put_task_struct(task);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
75
98.68%
1
50.00%
Ingo Molnar
1
1.32%
1
50.00%
Total
76
100.00%
2
100.00%

/*
 * resched_curr - mark rq's current 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.
 */


void resched_curr(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	int cpu;

	lockdep_assert_held(&rq->lock);

	if (test_tsk_need_resched(curr))
		return;

	cpu = cpu_of(rq);

	if (cpu == smp_processor_id()) {
		set_tsk_need_resched(curr);
		set_preempt_need_resched();
		return;
	}

	if (set_nr_and_not_polling(curr))
		smp_send_reschedule(cpu);
	else
		trace_sched_wake_idle_without_ipi(cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
37
45.68%
5
45.45%
Kirill V Tkhai
18
22.22%
1
9.09%
Ingo Molnar
12
14.81%
2
18.18%
Andrew Lutomirski
6
7.41%
1
9.09%
Gregory Haskins
5
6.17%
1
9.09%
Rusty Russell
3
3.70%
1
9.09%
Total
81
100.00%
11
100.00%



void resched_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);
	resched_curr(rq);
	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
42
89.36%
4
57.14%
Kirill V Tkhai
2
4.26%
1
14.29%
Paul E. McKenney
2
4.26%
1
14.29%
Alexey Dobriyan
1
2.13%
1
14.29%
Total
47
100.00%
7
100.00%

#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
 * 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 i, cpu = smp_processor_id();
	struct sched_domain *sd;

	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
		return cpu;

	rcu_read_lock();
	for_each_domain(cpu, sd) {
		for_each_cpu(i, sched_domain_span(sd)) {
			if (cpu == i)
				continue;

			if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
				cpu = i;
				goto unlock;
			}
		}
	}

	if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
unlock:
	rcu_read_unlock();
	return cpu;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
56
49.56%
7
46.67%
Vatika Harlalka
18
15.93%
1
6.67%
Frédéric Weisbecker
12
10.62%
2
13.33%
Viresh Kumar
11
9.73%
1
6.67%
Wanpeng Li
8
7.08%
1
6.67%
Suresh B. Siddha
5
4.42%
2
13.33%
Thomas Gleixner
3
2.65%
1
6.67%
Total
113
100.00%
15
100.00%

/*
 * 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.
 */


static void wake_up_idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (cpu == smp_processor_id())
		return;

	if (set_nr_and_not_polling(rq->idle))
		smp_send_reschedule(cpu);
	else
		trace_sched_wake_idle_without_ipi(cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
34
72.34%
5
55.56%
Andrew Lutomirski
7
14.89%
2
22.22%
Alexey Dobriyan
5
10.64%
1
11.11%
Frédéric Weisbecker
1
2.13%
1
11.11%
Total
47
100.00%
9
100.00%



static bool wake_up_full_nohz_cpu(int cpu)
{
	/*
         * We just need the target to call irq_exit() and re-evaluate
         * the next tick. The nohz full kick at least implies that.
         * If needed we can still optimize that later with an
         * empty IRQ.
         */
	if (cpu_is_offline(cpu))
		return true;  /* Don't try to wake offline CPUs. */
	if (tick_nohz_full_cpu(cpu)) {
		if (cpu != smp_processor_id() ||
		    tick_nohz_tick_stopped())
			tick_nohz_full_kick_cpu(cpu);
		return true;
	}

	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
40
78.43%
3
75.00%
Paul E. McKenney
11
21.57%
1
25.00%
Total
51
100.00%
4
100.00%

/*
 * Wake up the specified CPU.  If the CPU is going offline, it is the
 * caller's responsibility to deal with the lost wakeup, for example,
 * by hooking into the CPU_DEAD notifier like timers and hrtimers do.
 */


void wake_up_nohz_cpu(int cpu)
{
	if (!wake_up_full_nohz_cpu(cpu))
		wake_up_idle_cpu(cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
21
100.00%
2
100.00%
Total
21
100.00%
2
100.00%



static inline bool got_nohz_idle_kick(void)
{
	int cpu = smp_processor_id();

	if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)))
		return false;

	if (idle_cpu(cpu) && !need_resched())
		return true;

	/*
         * We can't run Idle Load Balance on this CPU for this time so we
         * cancel it and clear NOHZ_BALANCE_KICK
         */
	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vincent Guittot
29
49.15%
1
16.67%
Peter Zijlstra
23
38.98%
4
66.67%
Suresh B. Siddha
7
11.86%
1
16.67%
Total
59
100.00%
6
100.00%

#else /* CONFIG_NO_HZ_COMMON */



static inline bool got_nohz_idle_kick(void)
{
	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
12
100.00%
1
100.00%
Total
12
100.00%
1
100.00%

#endif /* CONFIG_NO_HZ_COMMON */

#ifdef CONFIG_NO_HZ_FULL


bool sched_can_stop_tick(struct rq *rq)
{
	int fifo_nr_running;

	/* Deadline tasks, even if single, need the tick */
	if (rq->dl.dl_nr_running)
		return false;

	/*
         * If there are more than one RR tasks, we need the tick to effect the
         * actual RR behaviour.
         */
	if (rq->rt.rr_nr_running) {
		if (rq->rt.rr_nr_running == 1)
			return true;
		else
			return false;
	}

	/*
         * If there's no RR tasks, but FIFO tasks, we can skip the tick, no
         * forced preemption between FIFO tasks.
         */
	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
	if (fifo_nr_running)
		return true;

	/*
         * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
         * if there's more than one we need the tick for involuntary
         * preemption.
         */
	if (rq->nr_running > 1)
		return false;

	return true;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
53
58.89%
2
50.00%
Peter Zijlstra
24
26.67%
1
25.00%
Rik Van Riel
13
14.44%
1
25.00%
Total
90
100.00%
4
100.00%

#endif /* CONFIG_NO_HZ_FULL */



void sched_avg_update(struct rq *rq)
{
	s64 period = sched_avg_period();

	while ((s64)(rq_clock(rq) - 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;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
32
64.00%
2
20.00%
Andrew Morton
5
10.00%
1
10.00%
Frédéric Weisbecker
3
6.00%
1
10.00%
Mike Galbraith
3
6.00%
1
10.00%
Gregory Haskins
2
4.00%
1
10.00%
Ingo Molnar
2
4.00%
2
20.00%
Alexey Dobriyan
2
4.00%
1
10.00%
Tejun Heo
1
2.00%
1
10.00%
Total
50
100.00%
10
100.00%

#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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
89
73.55%
5
62.50%
Tejun Heo
16
13.22%
1
12.50%
Andrew Morton
13
10.74%
1
12.50%
Gregory Haskins
3
2.48%
1
12.50%
Total
121
100.00%
8
100.00%



int tg_nop(struct task_group *tg, void *data)
{
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
64.71%
1
33.33%
Peter Williams
4
23.53%
1
33.33%
Gregory Haskins
2
11.76%
1
33.33%
Total
17
100.00%
3
100.00%

#endif



static void set_load_weight(struct task_struct *p, bool update_load)
{
	int prio = p->static_prio - MAX_RT_PRIO;
	struct load_weight *load = &p->se.load;

	/*
         * SCHED_IDLE tasks get minimal weight:
         */
	if (idle_policy(p->policy)) {
		load->weight = scale_load(WEIGHT_IDLEPRIO);
		load->inv_weight = WMULT_IDLEPRIO;
		return;
	}

	/*
         * SCHED_OTHER tasks have to update their load when changing their
         * weight
         */
	if (update_load && p->sched_class == &fair_sched_class) {
		reweight_task(p, prio);
	} else {
		load->weight = scale_load(sched_prio_to_weight[prio]);
		load->inv_weight = sched_prio_to_wmult[prio];
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vincent Guittot
27
25.00%
1
7.69%
Ingo Molnar
25
23.15%
2
15.38%
Nikhil P Rao
22
20.37%
2
15.38%
Peter Zijlstra
21
19.44%
3
23.08%
Gregory Haskins
4
3.70%
1
7.69%
Henrik Austad
3
2.78%
1
7.69%
Steven Rostedt
3
2.78%
1
7.69%
Andi Kleen
2
1.85%
1
7.69%
Tejun Heo
1
0.93%
1
7.69%
Total
108
100.00%
13
100.00%



static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
	if (!(flags & ENQUEUE_NOCLOCK))
		update_rq_clock(rq);

	if (!(flags & ENQUEUE_RESTORE))
		sched_info_queued(rq, p);

	p->sched_class->enqueue_task(rq, p, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
30
47.62%
5
38.46%
Alexey Dobriyan
13
20.63%
1
7.69%
Ingo Molnar
10
15.87%
1
7.69%
Steven Rostedt
4
6.35%
2
15.38%
Mike Galbraith
3
4.76%
2
15.38%
Michael S. Tsirkin
2
3.17%
1
7.69%
Tejun Heo
1
1.59%
1
7.69%
Total
63
100.00%
13
100.00%



static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
	if (!(flags & DEQUEUE_NOCLOCK))
		update_rq_clock(rq);

	if (!(flags & DEQUEUE_SAVE))
		sched_info_dequeued(rq, p);

	p->sched_class->dequeue_task(rq, p, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
46
73.02%
8
53.33%
Ingo Molnar
9
14.29%
2
13.33%
Michael S. Tsirkin
2
3.17%
1
6.67%
Tejun Heo
2
3.17%
1
6.67%
Mike Galbraith
2
3.17%
1
6.67%
Ankita Garg
1
1.59%
1
6.67%
Andrew Morton
1
1.59%
1
6.67%
Total
63
100.00%
15
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
39
100.00%
3
100.00%
Total
39
100.00%
3
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
28
71.79%
3
60.00%
Mike Galbraith
10
25.64%
1
20.00%
Andrew Morton
1
2.56%
1
20.00%
Total
39
100.00%
5
100.00%

/*
 * __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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
9
52.94%
1
25.00%
Peter Williams
4
23.53%
1
25.00%
Venkatesh Pallipadi
3
17.65%
1
25.00%
Peter Zijlstra
1
5.88%
1
25.00%
Total
17
100.00%
4
100.00%

/*
 * 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_dl_policy(p))
		prio = MAX_DL_PRIO-1;
	else if (task_has_rt_policy(p))
		prio = MAX_RT_PRIO-1 - p->rt_priority;
	else
		prio = __normal_prio(p);
	return prio;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
25
43.86%
1
9.09%
Dario Faggioli
14
24.56%
1
9.09%
Mike Galbraith
7
12.28%
3
27.27%
Andrew Morton
5
8.77%
1
9.09%
Ingo Molnar
3
5.26%
2
18.18%
Lennart Poettering
1
1.75%
1
9.09%
Nicholas Piggin
1
1.75%
1
9.09%
Peter Williams
1
1.75%
1
9.09%
Total
57
100.00%
11
100.00%

/*
 * 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
32
78.05%
1
16.67%
Peter Zijlstra
3
7.32%
1
16.67%
Mike Galbraith
2
4.88%
1
16.67%
Hiroshi Shimamoto
2
4.88%
1
16.67%
Ingo Molnar
1
2.44%
1
16.67%
Gregory Haskins
1
2.44%
1
16.67%
Total
41
100.00%
6
100.00%

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 *
 * Return: 1 if the task is currently executing. 0 otherwise.
 */


inline int task_curr(const struct task_struct *p)
{
	return cpu_curr(task_cpu(p)) == p;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
13
56.52%
1
25.00%
Ingo Molnar
5
21.74%
1
25.00%
Glauber de Oliveira Costa
3
13.04%
1
25.00%
Gregory Haskins
2
8.70%
1
25.00%
Total
23
100.00%
4
100.00%

/*
 * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
 * use the balance_callback list if you want balancing.
 *
 * this means any call to check_class_changed() must be followed by a call to
 * balance_callback().
 */


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 || dl_task(p))
		p->sched_class->prio_changed(rq, p, oldprio);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
56
62.92%
1
10.00%
Peter Zijlstra
11
12.36%
3
30.00%
Glauber de Oliveira Costa
8
8.99%
1
10.00%
Dario Faggioli
5
5.62%
1
10.00%
Ingo Molnar
4
4.49%
1
10.00%
Steven Rostedt
2
2.25%
1
10.00%
Tejun Heo
2
2.25%
1
10.00%
Venkatesh Pallipadi
1
1.12%
1
10.00%
Total
89
100.00%
10
100.00%



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_curr(rq);
				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 (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
		rq_clock_skip_update(rq, true);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Frédéric Weisbecker
86
76.11%
1
8.33%
Peter Zijlstra
17
15.04%
4
33.33%
Kirill Tkhai
3
2.65%
1
8.33%
Steven Rostedt
2
1.77%
2
16.67%
Mike Galbraith
2
1.77%
1
8.33%
Glauber de Oliveira Costa
1
0.88%
1
8.33%
Ingo Molnar
1
0.88%
1
8.33%
Kirill V Tkhai
1
0.88%
1
8.33%
Total
113
100.00%
12
100.00%

#ifdef CONFIG_SMP
/*
 * This is how migration works:
 *
 * 1) we invoke migration_cpu_stop() on the target CPU using
 *    stop_one_cpu().
 * 2) stopper starts to run (implicitly forcing the migrated thread
 *    off the CPU)
 * 3) it checks whether the migrated task is still in the wrong runqueue.
 * 4) if it's in the wrong runqueue then the migration thread removes
 *    it and puts it into the right queue.
 * 5) stopper completes and stop_one_cpu() returns and the migration
 *    is done.
 */

/*
 * move_queued_task - move a queued task to new rq.
 *
 * Returns (locked) new rq. Old rq's lock is released.
 */


static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
				   struct task_struct *p, int new_cpu)
{
	lockdep_assert_held(&rq->lock);

	p->on_rq = TASK_ON_RQ_MIGRATING;
	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
	set_task_cpu(p, new_cpu);
	rq_unlock(rq, rf);

	rq = cpu_rq(new_cpu);

	rq_lock(rq, rf);
	BUG_ON(task_cpu(p) != new_cpu);
	enqueue_task(rq, p, 0);
	p->on_rq = TASK_ON_RQ_QUEUED;
	check_preempt_curr(rq, p, 0);

	return rq;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
68
59.65%
5
41.67%
Frédéric Weisbecker
20
17.54%
1
8.33%
Joonwoo Park
12
10.53%
1
8.33%
Avi Kivity
4
3.51%
1
8.33%
Paul Turner
4
3.51%
1
8.33%
Andrew Morton
3
2.63%
1
8.33%
Venkatesh Pallipadi
2
1.75%
1
8.33%
Kirill Tkhai
1
0.88%
1
8.33%
Total
114
100.00%
12
100.00%


struct migration_arg {
	
struct task_struct *task;
	
int dest_cpu;
};

/*
 * Move (not current) task off this CPU, onto the destination CPU. We're doing
 * this because either it can't run here any more (set_cpus_allowed()
 * away from this CPU, or CPU going down), or because we're
 * attempting to rebalance this task on exec (sched_exec).
 *
 * So we race with normal scheduler movements, but that's OK, as long
 * as the task is no longer on this CPU.
 */


static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
				 struct task_struct *p, int dest_cpu)
{
	if (p->flags & PF_KTHREAD) {
		if (unlikely(!cpu_online(dest_cpu)))
			return rq;
	} else {
		if (unlikely(!cpu_active(dest_cpu)))
			return rq;
	}

	/* Affinity changed (again). */
	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
		return rq;

	update_rq_clock(rq);
	rq = move_queued_task(rq, rf, p, dest_cpu);

	return rq;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
75
71.43%
5
71.43%
Tejun Heo
27
25.71%
1
14.29%
Ingo Molnar
3
2.86%
1
14.29%
Total
105
100.00%
7
100.00%

/*
 * migration_cpu_stop - this will be executed by a highprio stopper thread
 * and performs thread migration by bumping thread off CPU then
 * 'pushing' onto another runqueue.
 */


static int migration_cpu_stop(void *data)
{
	struct migration_arg *arg = data;
	struct task_struct *p = arg->task;
	struct rq *rq = this_rq();
	struct rq_flags rf;

	/*
         * The original target CPU might have gone down and we might
         * be on another CPU but it doesn't matter.
         */
	local_irq_disable();
	/*
         * We need to explicitly wake pending tasks before running
         * __migrate_task() such that we will not miss enforcing cpus_allowed
         * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
         */
	sched_ttwu_pending();

	raw_spin_lock(&p->pi_lock);
	rq_lock(rq, &rf);
	/*
         * If task_rq(p) != rq, it cannot be migrated here, because we're
         * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
         * we're holding p->pi_lock.
         */
	if (task_rq(p) == rq) {
		if (task_on_rq_queued(p))
			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
		else
			p->wake_cpu = arg->dest_cpu;
	}
	rq_unlock(rq, &rf);
	raw_spin_unlock(&p->pi_lock);

	local_irq_enable();
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
113
88.28%
5
71.43%
Cheng Chao
14
10.94%
1
14.29%
Ingo Molnar
1
0.78%
1
14.29%
Total
128
100.00%
7
100.00%

/*
 * sched_class::set_cpus_allowed must do the below, but is not required to
 * actually call this function.
 */


void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
{
	cpumask_copy(&p->cpus_allowed, new_mask);
	p->nr_cpus_allowed = cpumask_weight(new_mask);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
35
100.00%
3
100.00%
Total
35
100.00%
3
100.00%



void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
	struct rq *rq = task_rq(p);
	bool queued, running;

	lockdep_assert_held(&p->pi_lock);

	queued = task_on_rq_queued(p);
	running = task_current(rq, p);

	if (queued) {
		/*
                 * Because __kthread_bind() calls this on blocked tasks without
                 * holding rq->lock.
                 */
		lockdep_assert_held(&rq->lock);
		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
	}
	if (running)
		put_prev_task(rq, p);

	p->sched_class->set_cpus_allowed(p, new_mask);

	if (queued)
		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
	if (running)
		set_curr_task(rq, p);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
121
93.80%
6
85.71%
Vincent Guittot
8
6.20%
1
14.29%
Total
129
100.00%
7
100.00%

/*
 * Change a given task's CPU affinity. Migrate the thread to a
 * proper CPU and schedule it away if the CPU it's executing on
 * is removed from the allowed bitmask.
 *
 * NOTE: the caller must have a valid reference to the task, the
 * task must not exit() & deallocate itself prematurely. The
 * call is not atomic; no spinlocks may be held.
 */


static int __set_cpus_allowed_ptr(struct task_struct *p,
				  const struct cpumask *new_mask, bool check)
{
	const struct cpumask *cpu_valid_mask = cpu_active_mask;
	unsigned int dest_cpu;
	struct rq_flags rf;
	struct rq *rq;
	int ret = 0;

	rq = task_rq_lock(p, &rf);
	update_rq_clock(rq);

	if (p->flags & PF_KTHREAD) {
		/*
                 * Kernel threads are allowed on online && !active CPUs
                 */
		cpu_valid_mask = cpu_online_mask;
	}

	/*
         * Must re-check here, to close a race against __kthread_bind(),
         * sched_setaffinity() is not guaranteed to observe the flag.
         */
	if (check && (p->flags & PF_NO_SETAFFINITY)) {
		ret = -EINVAL;
		goto out;
	}

	if (cpumask_equal(&p->cpus_allowed, new_mask))
		goto out;

	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
		ret = -EINVAL;
		goto out;
	}

	do_set_cpus_allowed(p, new_mask);

	if (p->flags & PF_KTHREAD) {
		/*
                 * For kernel threads that do indeed end up on online &&
                 * !active we want to ensure they are strict per-CPU threads.
                 */
		WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
			!cpumask_intersects(new_mask, cpu_active_mask) &&
			p->nr_cpus_allowed != 1);
	}

	/* Can the task run on the task's current CPU? If so, we're done */
	if (cpumask_test_cpu(task_cpu(p), new_mask))
		goto out;

	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
	if (task_running(rq, p) || p->state == TASK_WAKING) {
		struct migration_arg arg = { p, dest_cpu };
		/* Need help from migration thread: drop lock and wait. */
		task_rq_unlock(rq, p, &rf);
		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
		tlb_migrate_finish(p->mm);
		return 0;
	} else if (task_on_rq_queued(p)) {
		/*
                 * OK, since we're going to drop the lock immediately
                 * afterwards anyway.
                 */
		rq = move_queued_task(rq, &rf, p, dest_cpu);
	}
out:
	task_rq_unlock(rq, p, &rf);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
254
84.11%
9
56.25%
Frédéric Weisbecker
32
10.60%
1
6.25%
Wanpeng Li
5
1.66%
1
6.25%
Ingo Molnar
5
1.66%
2
12.50%
Mel Gorman
4
1.32%
1
6.25%
Avi Kivity
1
0.33%
1
6.25%
Nicholas Piggin
1
0.33%
1
6.25%
Total
302
100.00%
16
100.00%



int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
	return __set_cpus_allowed_ptr(p, new_mask, false);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
100.00%
1
100.00%
Total
26
100.00%
1
100.00%


EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);



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 &&
			!p->on_rq);

	/*
         * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
         * because schedstat_wait_{start,end} rebase migrating task's wait_start
         * time relying on p->on_rq.
         */
	WARN_ON_ONCE(p->state == TASK_RUNNING &&
		     p->sched_class == &fair_sched_class &&
		     (p->on_rq && !task_on_rq_migrating(p)));

#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 task_group().
         *
         * 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
	/*
         * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
         */
	WARN_ON_ONCE(!cpu_online(new_cpu));
#endif

	trace_sched_migrate_task(p, new_cpu);

	if (task_cpu(p) != new_cpu) {
		if (p->sched_class->migrate_task_rq)
			p->sched_class->migrate_task_rq(p);
		p->se.nr_migrations++;
		perf_event_task_migrate(p);
	}

	__set_task_cpu(p, new_cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
94
56.63%
3
23.08%
Joonwoo Park
29
17.47%
1
7.69%
Frédéric Weisbecker
19
11.45%
1
7.69%
Ingo Molnar
15
9.04%
4
30.77%
Andrew Morton
5
3.01%
1
7.69%
Linus Torvalds
2
1.20%
1
7.69%
Venkatesh Pallipadi
1
0.60%
1
7.69%
Lucas De Marchi
1
0.60%
1
7.69%
Total
166
100.00%
13
100.00%



static void __migrate_swap_task(struct task_struct *p, int cpu)
{
	if (task_on_rq_queued(p)) {
		struct rq *src_rq, *dst_rq;
		struct rq_flags srf, drf;

		src_rq = task_rq(p);
		dst_rq = cpu_rq(cpu);

		rq_pin_lock(src_rq, &srf);
		rq_pin_lock(dst_rq, &drf);

		p->on_rq = TASK_ON_RQ_MIGRATING;
		deactivate_task(src_rq, p, 0);
		set_task_cpu(p, cpu);
		activate_task(dst_rq, p, 0);
		p->on_rq = TASK_ON_RQ_QUEUED;
		check_preempt_curr(dst_rq, p, 0);

		rq_unpin_lock(dst_rq, &drf);
		rq_unpin_lock(src_rq, &srf);

	} else {
		/*
                 * Task isn't running anymore; make it appear like we migrated
                 * it before it went to sleep. This means on wakeup we make the
                 * previous CPU our target instead of where it really is.
                 */
		p->wake_cpu = cpu;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
79
56.83%
3
18.75%
Frédéric Weisbecker
22
15.83%
1
6.25%
Joonwoo Park
12
8.63%
1
6.25%
Tang Chen
10
7.19%
1
6.25%
Ingo Molnar
7
5.04%
4
25.00%
Steven Rostedt
4
2.88%
1
6.25%
Glauber de Oliveira Costa
2
1.44%
2
12.50%
Peter Williams
1
0.72%
1
6.25%
Lennart Poettering
1
0.72%
1
6.25%
Gregory Haskins
1
0.72%
1
6.25%
Total
139
100.00%
16
100.00%


struct migration_swap_arg {
	

struct task_struct *src_task, *dst_task;
	

int src_cpu, dst_cpu;
};



static int migrate_swap_stop(void *data)
{
	struct migration_swap_arg *arg = data;
	struct rq *src_rq, *dst_rq;
	int ret = -EAGAIN;

	if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
		return -EAGAIN;

	src_rq = cpu_rq(arg->src_cpu);
	dst_rq = cpu_rq(arg->dst_cpu);

	double_raw_lock(&arg->src_task->pi_lock,
			&arg->dst_task->pi_lock);
	double_rq_lock(src_rq, dst_rq);

	if (task_cpu(arg->dst_task) != arg->dst_cpu)
		goto unlock;

	if (task_cpu(arg->src_task) != arg->src_cpu)
		goto unlock;

	if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
		goto unlock;

	if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
		goto unlock;

	__migrate_swap_task(arg->src_task, arg->dst_cpu);
	__migrate_swap_task(arg->dst_task, arg->src_cpu);

	ret = 0;

unlock:
	double_rq_unlock(src_rq, dst_rq);
	raw_spin_unlock(&arg->dst_task->pi_lock);
	raw_spin_unlock(&arg->src_task->pi_lock);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
164
72.89%
8
53.33%
Frédéric Weisbecker
38
16.89%
1
6.67%
Ingo Molnar
6
2.67%
1
6.67%
Gregory Haskins
5
2.22%
1
6.67%
Steven Rostedt
4
1.78%
1
6.67%
Tang Chen
4
1.78%
1
6.67%
Glauber de Oliveira Costa
2
0.89%
1
6.67%
Hiroshi Shimamoto
2
0.89%
1
6.67%
Total
225
100.00%
15
100.00%

/*
 * Cross migrate two tasks
 */


int migrate_swap(struct task_struct *cur, struct task_struct *p)
{
	struct migration_swap_arg arg;
	int ret = -EINVAL;

	arg = (struct migration_swap_arg){
		.src_task = cur,
		.src_cpu = task_cpu(cur),
		.dst_task = p,
		.dst_cpu = task_cpu(p),
        };

	if (arg.src_cpu == arg.dst_cpu)
		goto out;

	/*
         * These three tests are all lockless; this is OK since all of them
         * will be re-checked with proper locks held further down the line.
         */
	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
		goto out;

	if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
		goto out;

	if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
		goto out;

	trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
	ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);

out:
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
108
62.79%
6
35.29%
Frédéric Weisbecker
30
17.44%
1
5.88%
Ingo Molnar
15
8.72%
3
17.65%
Andrew Morton
7
4.07%
1
5.88%
Gregory Haskins
4
2.33%
1
5.88%
Hiroshi Shimamoto
2
1.16%
1
5.88%
Linus Torvalds
2
1.16%
2
11.76%
Nicholas Piggin
2
1.16%
1
5.88%
Pavel Emelyanov
2
1.16%
1
5.88%
Total
172
100.00%
17
100.00%

/*
 * 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)
{
	int running, queued;
	struct rq_flags rf;
	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, &rf);
		trace_sched_wait_task(p);
		running = task_running(rq, p);
		queued = task_on_rq_queued(p);
		ncsw = 0;
		if (!match_state || p->state == match_state)
			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
		task_rq_unlock(rq, p, &rf);

		/*
                 * 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(queued)) {
			ktime_t to = 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
116
56.86%
5
22.73%
Frédéric Weisbecker
45
22.06%
2
9.09%
Andrew Morton
9
4.41%
1
4.55%
Ingo Molnar
8
3.92%
4
18.18%
Steven Rostedt
6
2.94%
2
9.09%
Nicholas Piggin
5
2.45%
2
9.09%
Jason Low
5
2.45%
1
4.55%
Linus Torvalds
4
1.96%
2
9.09%
Thomas Gleixner
3
1.47%
1
4.55%
Avi Kivity
2
0.98%
1
4.55%
Roland McGrath
1
0.49%
1
4.55%
Total
204
100.00%
22
100.00%

/***
 * 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);
	if ((cpu != smp_processor_id()) && task_curr(p))
		smp_send_reschedule(cpu);
	preempt_enable();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
57.78%
2
33.33%
Steven Rostedt
11
24.44%
1
16.67%
Avi Kivity
4
8.89%
1
16.67%
Andrew Morton
3
6.67%
1
16.67%
Ingo Molnar
1
2.22%
1
16.67%
Total
45
100.00%
6
100.00%


EXPORT_SYMBOL_GPL(kick_process);

/*
 * ->cpus_allowed is protected by both rq->lock and p->pi_lock
 *
 * A few notes on cpu_active vs cpu_online:
 *
 *  - cpu_active must be a subset of cpu_online
 *
 *  - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
 *    see __set_cpus_allowed_ptr(). At this point the newly online
 *    CPU isn't yet part of the sched domains, and balancing will not
 *    see it.
 *
 *  - on CPU-down we clear cpu_active() to mask the sched domains and
 *    avoid the load balancer to place new tasks on the to be removed
 *    CPU. Existing tasks will remain running there and will be taken
 *    off.
 *
 * This means that fallback selection must not select !active CPUs.
 * And can assume that any active CPU must be online. Conversely
 * select_task_rq() below may allow selection of !active CPUs in order
 * to satisfy the above rules.
 */


static int select_fallback_rq(int cpu, struct task_struct *p)
{
	int nid = cpu_to_node(cpu);
	const struct cpumask *nodemask = NULL;
	enum { cpuset, possible, fail } state = cpuset;
	int dest_cpu;

	/*
         * If the node that the CPU is on has been offlined, cpu_to_node()
         * will return -1. There is no CPU on the node, and we should
         * select the CPU on the other node.
         */
	if (nid != -1) {
		nodemask = cpumask_of_node(nid);

		/* Look for allowed, online CPU in same node. */
		for_each_cpu(dest_cpu, nodemask) {
			if (!cpu_active(dest_cpu))
				continue;
			if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
				return dest_cpu;
		}
	}

	for (;;) {
		/* Any allowed, online CPU? */
		for_each_cpu(dest_cpu, &p->cpus_allowed) {
			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
				continue;
			if (!cpu_online(dest_cpu))
				continue;
			goto out;
		}

		/* No more Mr. Nice Guy. */
		switch (state) {
		case cpuset:
			if (IS_ENABLED(CONFIG_CPUSETS)) {
				cpuset_cpus_allowed_fallback(p);
				state = possible;
				break;
			}
			/* Fall-through */
		case possible:
			do_set_cpus_allowed(p, cpu_possible_mask);
			state = fail;
			break;

		case fail:
			BUG();
			break;
		}
	}

out:
	if (state != cpuset) {
		/*
                 * Don't tell them about moving exiting tasks or
                 * kernel threads (both mm NULL), since they never
                 * leave kernel.
                 */
		if (p->mm && printk_ratelimit()) {
			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
					task_pid_nr(p), p->comm, cpu);
		}
	}

	return dest_cpu;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
180
76.92%
6
42.86%
Tejun Heo
18
7.69%
1
7.14%
Oleg Nesterov
10
4.27%
1
7.14%
Frédéric Weisbecker
10
4.27%
2
14.29%
Avi Kivity
9
3.85%
1
7.14%
Ingo Molnar
6
2.56%
2
14.29%
Rick Lindsley
1
0.43%
1
7.14%
Total
234
100.00%
14
100.00%

/*
 * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
 */

static inline

int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
{
	lockdep_assert_held(&p->pi_lock);

	if (p->nr_cpus_allowed > 1)
		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
	else
		cpu = cpumask_any(&p->cpus_allowed);

	/*
         * In order not to call set_task_cpu() on a blocking task we need
         * to rely on ttwu() to place the task on a valid ->cpus_allowed
         * CPU.
         *
         * Since this is common to all placement strategies, this lives here.
         *
         * [ this allows ->select_task() to simply return task_cpu(p) and
         *   not worry about this generic constraint ]
         */
	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
		     !cpu_online(cpu)))
		cpu = select_fallback_rq(task_cpu(p), p);

	return cpu;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
74
71.84%
9
50.00%
Ingo Molnar
18
17.48%
5
27.78%
Frédéric Weisbecker
7
6.80%
1
5.56%
Arjan van de Ven
2
1.94%
1
5.56%
Rick Lindsley
1
0.97%
1
5.56%
Avi Kivity
1
0.97%
1
5.56%
Total
103
100.00%
18
100.00%



static void update_avg(u64 *avg, u64 sample)
{
	s64 diff = sample - *avg;
	*avg += diff >> 3;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
92.86%
1
33.33%
Frédéric Weisbecker
1
3.57%
1
33.33%
Arjan van de Ven
1
3.57%
1
33.33%
Total
28
100.00%
3
100.00%



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;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Nico Pitre
85
100.00%
1
100.00%
Total
85
100.00%
1
100.00%

#else



static inline int __set_cpus_allowed_ptr(struct task_struct *p,
					 const struct cpumask *new_mask, bool check)
{
	return set_cpus_allowed_ptr(p, new_mask);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
29
100.00%
1
100.00%
Total
29
100.00%
1
100.00%

#endif /* CONFIG_SMP */


static void

ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
{
	struct rq *rq;

	if (!schedstat_enabled())
		return;

	rq = this_rq();

#ifdef CONFIG_SMP
	if (cpu == rq->cpu) {
		schedstat_inc(rq->ttwu_local);
		schedstat_inc(p->se.statistics.nr_wakeups_local);
	} else {
		struct sched_domain *sd;

		schedstat_inc(p->se.statistics.nr_wakeups_remote);
		rcu_read_lock();
		for_each_domain(rq->cpu, sd) {
			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
				schedstat_inc(sd->ttwu_wake_remote);
				break;
			}
		}
		rcu_read_unlock();
	}

	if (wake_flags & WF_MIGRATED)
		schedstat_inc(p->se.statistics.nr_wakeups_migrate);
#endif /* CONFIG_SMP */

	schedstat_inc(rq->ttwu_count);
	schedstat_inc(p->se.statistics.nr_wakeups);

	if (wake_flags & WF_SYNC)
		schedstat_inc(p->se.statistics.nr_wakeups_sync);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
82
46.86%
3
30.00%
Chuansheng Liu
46
26.29%
1
10.00%
Josh Poimboeuf
23
13.14%
2
20.00%
Andrew Lutomirski
8
4.57%
1
10.00%
Ingo Molnar
8
4.57%
2
20.00%
Frédéric Weisbecker
8
4.57%
1
10.00%
Total
175
100.00%
10
100.00%



static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
{
	activate_task(rq, p, en_flags);
	p->on_rq = TASK_ON_RQ_QUEUED;

	/* If a worker is waking up, notify the workqueue: */
	if (p->flags & PF_WQ_WORKER)
		wq_worker_waking_up(p, cpu_of(rq));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
33
61.11%
7
43.75%
Ingo Molnar
8
14.81%
3
18.75%
Andrew Morton
6
11.11%
2
12.50%
Frédéric Weisbecker
4
7.41%
1
6.25%
Nicholas Piggin
1
1.85%
1
6.25%
Linus Torvalds
1
1.85%
1
6.25%
Tejun Heo
1
1.85%
1
6.25%
Total
54
100.00%
16
100.00%

/*
 * Mark the task runnable and perform wakeup-preemption.
 */


static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
			   struct rq_flags *rf)
{
	check_preempt_curr(rq, p, wake_flags);
	p->state = TASK_RUNNING;
	trace_sched_wakeup(p);

#ifdef CONFIG_SMP
	if (p->sched_class->task_woken) {
		/*
                 * Our task @p is fully woken up and running; so its safe to
                 * drop the rq->lock, hereafter rq is only used for statistics.
                 */
		rq_unpin_lock(rq, rf);
		p->sched_class->task_woken(rq, p);
		rq_repin_lock(rq, rf);
	}

	if (rq->idle_stamp) {
		u64 delta = rq_clock(rq) - rq->idle_stamp;
		u64 max = 2*rq->max_idle_balance_cost;

		update_avg(&rq->avg_idle, delta);

		if (rq->avg_idle > max)
			rq->avg_idle = max;

		rq->idle_stamp = 0;
	}
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
88
61.11%
8
38.10%
Roland McGrath
12
8.33%
1
4.76%
Tejun Heo
10
6.94%
1
4.76%
Gregory Haskins
9
6.25%
1
4.76%
Matt Fleming
7
4.86%
1
4.76%
Frédéric Weisbecker
5
3.47%
1
4.76%
Linus Torvalds
3
2.08%
1
4.76%
Ingo Molnar
3
2.08%
2
9.52%
Mathieu Desnoyers
2
1.39%
1
4.76%
Andrew Morton
2
1.39%
1
4.76%
Gautham R. Shenoy
1
0.69%
1
4.76%
Nicholas Piggin
1
0.69%
1
4.76%
Thomas Gleixner
1
0.69%
1
4.76%
Total
144
100.00%
21
100.00%


static void

ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
		 struct rq_flags *rf)
{
	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;

	lockdep_assert_held(&rq->lock);

#ifdef CONFIG_SMP
	if (p->sched_contributes_to_load)
		rq->nr_uninterruptible--;

	if (wake_flags & WF_MIGRATED)
		en_flags |= ENQUEUE_MIGRATED;
#endif

	ttwu_activate(rq, p, en_flags);
	ttwu_do_wakeup(rq, p, wake_flags, rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
53
62.35%
11
61.11%
Frédéric Weisbecker
10
11.76%
1
5.56%
Ingo Molnar
10
11.76%
2
11.11%
Andrew Morton
5
5.88%
1
5.56%
Matt Fleming
4
4.71%
1
5.56%
Linus Torvalds
2
2.35%
1
5.56%
Zachary Amsden
1
1.18%
1
5.56%
Total
85
100.00%
18
100.00%

/*
 * Called in case the task @p isn't fully descheduled from its runqueue,
 * in this case we must do a remote wakeup. Its a 'light' wakeup though,
 * since all we need to do is flip p->state to TASK_RUNNING, since
 * the task is still ->on_rq.
 */


static int ttwu_remote(struct task_struct *p, int wake_flags)
{
	struct rq_flags rf;
	struct rq *rq;
	int ret = 0;

	rq = __task_rq_lock(p, &rf);
	if (task_on_rq_queued(p)) {
		/* check_preempt_curr() may use rq clock */
		update_rq_clock(rq);
		ttwu_do_wakeup(rq, p, wake_flags, &rf);
		ret = 1;
	}
	__task_rq_unlock(rq, &rf);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
61
76.25%
10
62.50%
Oleg Nesterov
6
7.50%
1
6.25%
Andrew Morton
4
5.00%
1
6.25%
Frédéric Weisbecker
4
5.00%
1
6.25%
Tejun Heo
3
3.75%
1
6.25%
Ingo Molnar
1
1.25%
1
6.25%
Matt Fleming
1
1.25%
1
6.25%
Total
80
100.00%
16
100.00%

#ifdef CONFIG_SMP


void sched_ttwu_pending(void)
{
	struct rq *rq = this_rq();
	struct llist_node *llist = llist_del_all(&rq->wake_list);
	struct task_struct *p, *t;
	struct rq_flags rf;

	if (!llist)
		return;

	rq_lock_irqsave(rq, &rf);
	update_rq_clock(rq);

	llist_for_each_entry_safe(p, t, llist, wake_entry)
		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);

	rq_unlock_irqrestore(rq, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
48
50.53%
9
52.94%
Byungchul Park
16
16.84%
1
5.88%
Juri Lelli
13
13.68%
1
5.88%
Matt Fleming
10
10.53%
1
5.88%
Ingo Molnar
3
3.16%
2
11.76%
Andrew Morton
2
2.11%
1
5.88%
Jeremy Fitzhardinge
2
2.11%
1
5.88%
Frédéric Weisbecker
1
1.05%
1
5.88%
Total
95
100.00%
17
100.00%



void scheduler_ipi(void)
{
	/*
         * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
         * TIF_NEED_RESCHED remotely (for the first time) will also send
         * this IPI.
         */
	preempt_fold_need_resched();

	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
		return;

	/*
         * Not all reschedule IPI handlers call irq_enter/irq_exit, since
         * traditionally all their work was done from the interrupt return
         * path. Now that we actually do some work, we need to make sure
         * we do call them.
         *
         * Some archs already do call them, luckily irq_enter/exit nest
         * properly.
         *
         * Arguably we should visit all archs and update all handlers,
         * however a fair share of IPIs are still resched only so this would
         * somewhat pessimize the simple resched case.
         */
	irq_enter();
	sched_ttwu_pending();

	/*
         * Check if someone kicked us for doing the nohz idle load balance.
         */
	if (unlikely(got_nohz_idle_kick())) {
		this_rq()->idle_balance = 1;
		raise_softirq_irqoff(SCHED_SOFTIRQ);
	}
	irq_exit();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
48
80.00%
3
42.86%
Thomas Gleixner
4
6.67%
1
14.29%
Frédéric Weisbecker
4
6.67%
1
14.29%
Oleg Nesterov
3
5.00%
1
14.29%
Andrew Morton
1
1.67%
1
14.29%
Total
60
100.00%
7
100.00%



static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
{
	struct rq *rq = cpu_rq(cpu);

	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);

	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
		if (!set_nr_if_polling(rq->idle))
			smp_send_reschedule(cpu);
		else
			trace_sched_wake_idle_without_ipi(cpu);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
65
81.25%
7
63.64%
Dario Faggioli
7
8.75%
1
9.09%
Frédéric Weisbecker
5
6.25%
1
9.09%
Juri Lelli
2
2.50%
1
9.09%
Kirill Tkhai
1
1.25%
1
9.09%
Total
80
100.00%
11
100.00%



void wake_up_if_idle(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct rq_flags rf;

	rcu_read_lock();

	if (!is_idle_task(rcu_dereference(rq->curr)))
		goto out;

	if (set_nr_if_polling(rq->idle)) {
		trace_sched_wake_idle_without_ipi(cpu);
	} else {
		rq_lock_irqsave(rq, &rf);
		if (is_idle_task(rq->curr))
			smp_send_reschedule(cpu);
		/* Else CPU is not idle, do nothing here: */
		rq_unlock_irqrestore(rq, &rf);
	}

out:
	rcu_read_unlock();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
76
79.17%
6
40.00%
Juri Lelli
8
8.33%
1
6.67%
Rik Van Riel
4
4.17%
2
13.33%
Mel Gorman
3
3.12%
2
13.33%
Andrew Morton
2
2.08%
2
13.33%
Tejun Heo
2
2.08%
1
6.67%
Ingo Molnar
1
1.04%
1
6.67%
Total
96
100.00%
15
100.00%



bool cpus_share_cache(int this_cpu, int that_cpu)
{
	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
20
76.92%
1
33.33%
Mel Gorman
5
19.23%
1
33.33%
Andrew Morton
1
3.85%
1
33.33%
Total
26
100.00%
3
100.00%

#endif /* CONFIG_SMP */



static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
{
	struct rq *rq = cpu_rq(cpu);
	struct rq_flags rf;

#if defined(CONFIG_SMP)
	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
		ttwu_queue_remote(p, cpu, wake_flags);
		return;
	}
#endif

	rq_lock(rq, &rf);
	update_rq_clock(rq);
	ttwu_do_activate(rq, p, wake_flags, &rf);
	rq_unlock(rq, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
61
57.55%
9
56.25%
Andi Kleen
26
24.53%
1
6.25%
Matt Fleming
9
8.49%
1
6.25%
Kirill Tkhai
5
4.72%
1
6.25%
Ingo Molnar
2
1.89%
2
12.50%
Andrew Morton
2
1.89%
1
6.25%
Thomas Gleixner
1
0.94%
1
6.25%
Total
106
100.00%
16
100.00%

/*
 * Notes on Program-Order guarantees on SMP systems.
 *
 *  MIGRATION
 *
 * The basic program-order guarantee on SMP systems is that when a task [t]
 * migrates, all its activity on its old CPU [c0] happens-before any subsequent
 * execution on its new CPU [c1].
 *
 * For migration (of runnable tasks) this is provided by the following means:
 *
 *  A) UNLOCK of the rq(c0)->lock scheduling out task t
 *  B) migration for t is required to synchronize *both* rq(c0)->lock and
 *     rq(c1)->lock (if not at the same time, then in that order).
 *  C) LOCK of the rq(c1)->lock scheduling in task
 *
 * Transitivity guarantees that B happens after A and C after B.
 * Note: we only require RCpc transitivity.
 * Note: the CPU doing B need not be c0 or c1
 *
 * Example:
 *
 *   CPU0            CPU1            CPU2
 *
 *   LOCK rq(0)->lock
 *   sched-out X
 *   sched-in Y
 *   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(0)->lock // orders against CPU0
 *                                   dequeue X
 *                                   UNLOCK rq(0)->lock
 *
 *                                   LOCK rq(1)->lock
 *                                   enqueue X
 *                                   UNLOCK rq(1)->lock
 *
 *                   LOCK rq(1)->lock // orders against CPU2
 *                   sched-out Z
 *                   sched-in X
 *                   UNLOCK rq(1)->lock
 *
 *
 *  BLOCKING -- aka. SLEEP + WAKEUP
 *
 * For blocking we (obviously) need to provide the same guarantee as for
 * migration. However the means are completely different as there is no lock
 * chain to provide order. Instead we do:
 *
 *   1) smp_store_release(X->on_cpu, 0)
 *   2) smp_cond_load_acquire(!X->on_cpu)
 *
 * Example:
 *
 *   CPU0 (schedule)  CPU1 (try_to_wake_up) CPU2 (schedule)
 *
 *   LOCK rq(0)->lock LOCK X->pi_lock
 *   dequeue X
 *   sched-out X
 *   smp_store_release(X->on_cpu, 0);
 *
 *                    smp_cond_load_acquire(&X->on_cpu, !VAL);
 *                    X->state = WAKING
 *                    set_task_cpu(X,2)
 *
 *                    LOCK rq(2)->lock
 *                    enqueue X
 *                    X->state = RUNNING
 *                    UNLOCK rq(2)->lock
 *
 *                                          LOCK rq(2)->lock // orders against CPU1
 *                                          sched-out Z
 *                                          sched-in X
 *                                          UNLOCK rq(2)->lock
 *
 *                    UNLOCK X->pi_lock
 *   UNLOCK rq(0)->lock
 *
 *
 * However; for wakeups there is a second guarantee we must provide, namely we
 * must observe the state that lead to our wakeup. That is, not only must our
 * task observe its own prior state, it must also observe the stores prior to
 * its wakeup.
 *
 * This means that any means of doing remote wakeups must order the CPU doing
 * the wakeup against the CPU the task is going to end up running on. This,
 * however, is already required for the regular Program-Order guarantee above,
 * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
 *
 */

/**
 * try_to_wake_up - wake up a thread
 * @p: the thread to be awakened
 * @state: the mask of task states that can be woken
 * @wake_flags: wake modifier flags (WF_*)
 *
 * If (@state & @p->state) @p->state = TASK_RUNNING.
 *
 * If the task was not queued/runnable, also place it back on a runqueue.
 *
 * Atomic against schedule() which would dequeue a task, also see
 * set_current_state().
 *
 * Return: %true if @p->state changes (an actual wakeup was done),
 *         %false otherwise.
 */

static int

try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
	unsigned long flags;
	int cpu, success = 0;

	/*
         * If we are going to wake up a thread waiting for CONDITION we
         * need to ensure that CONDITION=1 done by the caller can not be
         * reordered with p->state check below. This pairs with mb() in
         * set_current_state() the waiting thread does.
         */
	raw_spin_lock_irqsave(&p->pi_lock, flags);
	smp_mb__after_spinlock();
	if (!(p->state & state))
		goto out;

	trace_sched_waking(p);

	/* We're going to change ->state: */
	success = 1;
	cpu = task_cpu(p);

	/*
         * Ensure we load p->on_rq _after_ p->state, otherwise it would
         * be possible to, falsely, observe p->on_rq == 0 and get stuck
         * in smp_cond_load_acquire() below.
         *
         * sched_ttwu_pending()                 try_to_wake_up()
         *   [S] p->on_rq = 1;                  [L] P->state
         *       UNLOCK rq->lock  -----.
         *                              \
         *                               +---   RMB
         * schedule()                   /
         *       LOCK rq->lock    -----'
         *       UNLOCK rq->lock
         *
         * [task p]
         *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
         *
         * Pairs with the UNLOCK+LOCK on rq->lock from the
         * last wakeup of our task and the schedule that got our task
         * current.
         */
	smp_rmb();
	if (p->on_rq && ttwu_remote(p, wake_flags))
		goto stat;

#ifdef CONFIG_SMP
	/*
         * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
         * possible to, falsely, observe p->on_cpu == 0.
         *
         * One must be running (->on_cpu == 1) in order to remove oneself
         * from the runqueue.
         *
         *  [S] ->on_cpu = 1;   [L] ->on_rq
         *      UNLOCK rq->lock
         *                      RMB
         *      LOCK   rq->lock
         *  [S] ->on_rq = 0;    [L] ->on_cpu
         *
         * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
         * from the consecutive calls to schedule(); the first switching to our
         * task, the second putting it to sleep.
         */
	smp_rmb();

	/*
         * If the owning (remote) CPU is still in the middle of schedule() with
         * this task as prev, wait until its done referencing the task.
         *
         * Pairs with the smp_store_release() in finish_lock_switch().
         *
         * This ensures that tasks getting woken will be fully ordered against
         * their previous state and preserve Program Order.
         */
	smp_cond_load_acquire(&p->on_cpu, !VAL);

	p->sched_contributes_to_load = !!task_contributes_to_load(p);
	p->state = TASK_WAKING;

	if (p->in_iowait) {
		delayacct_blkio_end(p);
		atomic_dec(&task_rq(p)->nr_iowait);
	}

	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
	if (task_cpu(p) != cpu) {
		wake_flags |= WF_MIGRATED;
		set_task_cpu(p, cpu);
	}

#else /* CONFIG_SMP */

	if (p->in_iowait) {
		delayacct_blkio_end(p);
		atomic_dec(&task_rq(p)->nr_iowait);
	}

#endif /* CONFIG_SMP */

	ttwu_queue(p, cpu, wake_flags);
stat:
	ttwu_stat(p, cpu, wake_flags);
out:
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);

	return success;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
138
53.91%
17
45.95%
Tejun Heo
51
19.92%
2
5.41%
Andrew Morton
18
7.03%
4
10.81%
Thomas Gleixner
10
3.91%
1
2.70%
Dario Faggioli
10
3.91%
1
2.70%
Frédéric Weisbecker
6
2.34%
1
2.70%
Josh Snyder
6
2.34%
1
2.70%
Ingo Molnar
6
2.34%
4
10.81%
Balbir Singh
4
1.56%
1
2.70%
Gregory Haskins
3
1.17%
1
2.70%
Juri Lelli
1
0.39%
1
2.70%
Rik Van Riel
1
0.39%
1
2.70%
Rusty Russell
1
0.39%
1
2.70%
Jack Steiner
1
0.39%
1
2.70%
Total
256
100.00%
37
100.00%

/**
 * try_to_wake_up_local - try to wake up a local task with rq lock held
 * @p: the thread to be awakened
 * @rf: request-queue flags for pinning
 *
 * Put @p on the run-queue if it's not already there. The caller must
 * ensure that this_rq() is locked, @p is bound to this_rq() and not
 * the current task.
 */


static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
{
	struct rq *rq = task_rq(p);

	if (WARN_ON_ONCE(rq != this_rq()) ||
	    WARN_ON_ONCE(p == current))
		return;

	lockdep_assert_held(&rq->lock);

	if (!raw_spin_trylock(&p->pi_lock)) {
		/*
                 * This is OK, because current is on_cpu, which avoids it being
                 * picked for load-balance and preemption/IRQs are still
                 * disabled avoiding further scheduler activity on it and we've
                 * not yet picked a replacement task.
                 */
		rq_unlock(rq, rf);
		raw_spin_lock(&p->pi_lock);
		rq_relock(rq, rf);
	}

	if (!(p->state & TASK_NORMAL))
		goto out;

	trace_sched_waking(p);

	if (!task_on_rq_queued(p)) {
		if (p->in_iowait) {
			delayacct_blkio_end(p);
			atomic_dec(&rq->nr_iowait);
		}
		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
	}

	ttwu_do_wakeup(rq, p, 0, rf);
	ttwu_stat(p, smp_processor_id(), 0);
out:
	raw_spin_unlock(&p->pi_lock);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
104
57.78%
11
44.00%
Tejun Heo
21
11.67%
2
8.00%
Andi Kleen
15
8.33%
1
4.00%
Mel Gorman
8
4.44%
1
4.00%
Frédéric Weisbecker
7
3.89%
1
4.00%
Matt Fleming
6
3.33%
1
4.00%
Dario Faggioli
4
2.22%
1
4.00%
Juri Lelli
3
1.67%
1
4.00%
Josh Snyder
3
1.67%
1
4.00%
Steven Rostedt
2
1.11%
1
4.00%
Ingo Molnar
2
1.11%
1
4.00%
Thomas Gleixner
2
1.11%
1
4.00%
Andrew Morton
2
1.11%
1
4.00%
Rick Lindsley
1
0.56%
1
4.00%
Total
180
100.00%
25
100.00%

/**
 * wake_up_process - Wake up a specific process
 * @p: The process to be woken up.
 *
 * Attempt to wake up the nominated process and move it to the set of runnable
 * processes.
 *
 * Return: 1 if the process was woken up, 0 if it was already running.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */


int wake_up_process(struct task_struct *p)
{
	return try_to_wake_up(p, TASK_NORMAL, 0);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
55.00%
3
33.33%
Dario Faggioli
5
25.00%
2
22.22%
Frédéric Weisbecker
1
5.00%
1
11.11%
Venkatesh Pallipadi
1
5.00%
1
11.11%
Rick Lindsley
1
5.00%
1
11.11%
Jack Steiner
1
5.00%
1
11.11%
Total
20
100.00%
9
100.00%


EXPORT_SYMBOL(wake_up_process);



int wake_up_state(struct task_struct *p, unsigned int state)
{
	return try_to_wake_up(p, state, 0);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
20
83.33%
3
60.00%
Venkatesh Pallipadi
2
8.33%
1
20.00%
Dario Faggioli
2
8.33%
1
20.00%
Total
24
100.00%
5
100.00%

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */


static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
{
	p->on_rq			= 0;

	p->se.on_rq			= 0;
	p->se.exec_start		= 0;
	p->se.sum_exec_runtime		= 0;
	p->se.prev_sum_exec_runtime	= 0;
	p->se.nr_migrations		= 0;
	p->se.vruntime			= 0;
	INIT_LIST_HEAD(&p->se.group_node);

#ifdef CONFIG_FAIR_GROUP_SCHED
	p->se.cfs_rq			= NULL;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* Even if schedstat is disabled, there should not be garbage */
	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif

	RB_CLEAR_NODE(&p->dl.rb_node);
	init_dl_task_timer(&p->dl);
	init_dl_inactive_task_timer(&p->dl);
	__dl_clear_params(p);

	INIT_LIST_HEAD(&p->rt.run_list);
	p->rt.timeout		= 0;
	p->rt.time_slice	= sched_rr_timeslice;
	p->rt.on_rq		= 0;
	p->rt.on_list		= 0;

#ifdef CONFIG_PREEMPT_NOTIFIERS
	INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif

#ifdef CONFIG_NUMA_BALANCING
	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
		p->mm->numa_scan_seq = 0;
	}

	if (clone_flags & CLONE_VM)
		p->numa_preferred_nid = current->numa_preferred_nid;
	else
		p->numa_preferred_nid = -1;

	p->node_stamp = 0ULL;
	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
	p->numa_work.next = &p->numa_work;
	p->numa_faults = NULL;
	p->last_task_numa_placement = 0;
	p->last_sum_exec_runtime = 0;

	p->numa_group = NULL;
#endif /* CONFIG_NUMA_BALANCING */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
212
62.91%
11
37.93%
Dario Faggioli
62
18.40%
3
10.34%
Frédéric Weisbecker
20
5.93%
2
6.90%
Byungchul Park
13
3.86%
1
3.45%
Luca Abeni
8
2.37%
1
3.45%
Thomas Gleixner
5
1.48%
1
3.45%
Mike Galbraith
3
0.89%
1
3.45%
Steven Rostedt
2
0.59%
1
3.45%
Juri Lelli
2
0.59%
1
3.45%
Venkatesh Pallipadi
2
0.59%
1
3.45%
Gregory Haskins
2
0.59%
1
3.45%
Ingo Molnar
2
0.59%
2
6.90%
Andrew Morton
2
0.59%
1
3.45%
Suresh B. Siddha
1
0.30%
1
3.45%
Mel Gorman
1
0.30%
1
3.45%
Total
337
100.00%
29
100.00%


DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);

#ifdef CONFIG_NUMA_BALANCING



void set_numabalancing_state(bool enabled)
{
	if (enabled)
		static_branch_enable(&sched_numa_balancing);
	else
		static_branch_disable(&sched_numa_balancing);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
44.00%
2
40.00%
Srikar Dronamraju
6
24.00%
1
20.00%
Dario Faggioli
5
20.00%
1
20.00%
Avi Kivity
3
12.00%
1
20.00%
Total
25
100.00%
5
100.00%

#ifdef CONFIG_PROC_SYSCTL


int sysctl_numa_balancing(struct ctl_table *table, int write,
			 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
	int err;
	int state = static_branch_likely(&sched_numa_balancing);

	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	t = *table;
	t.data = &state;
	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
	if (err < 0)
		return err;
	if (write)
		set_numabalancing_state(state);
	return err;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
80
76.19%
4
30.77%
Dario Faggioli
13
12.38%
1
7.69%
Srikar Dronamraju
5
4.76%
2
15.38%
Linus Torvalds
2
1.90%
2
15.38%
Frédéric Weisbecker
2
1.90%
1
7.69%
Mike Galbraith
1
0.95%
1
7.69%
Ingo Molnar
1
0.95%
1
7.69%
Tejun Heo
1
0.95%
1
7.69%
Total
105
100.00%
13
100.00%

#endif
#endif

#ifdef CONFIG_SCHEDSTATS


DEFINE_STATIC_KEY_FALSE(sched_schedstats);

static bool __initdata __sched_schedstats = false;



static void set_schedstats(bool enabled)
{
	if (enabled)
		static_branch_enable(&sched_schedstats);
	else
		static_branch_disable(&sched_schedstats);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mel Gorman
16
61.54%
1
14.29%
Peter Zijlstra
5
19.23%
2
28.57%
Linus Torvalds
2
7.69%
1
14.29%
Dario Faggioli
1
3.85%
1
14.29%
Martin Schwidefsky
1
3.85%
1
14.29%
Hidetoshi Seto
1
3.85%
1
14.29%
Total
26
100.00%
7
100.00%



void force_schedstat_enabled(void)
{
	if (!schedstat_enabled()) {
		pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
		static_branch_enable(&sched_schedstats);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mel Gorman
16
61.54%
1
14.29%
Dario Faggioli
4
15.38%
1
14.29%
Peter Zijlstra
2
7.69%
1
14.29%
Hidetoshi Seto
1
3.85%
1
14.29%
Andrew Morton
1
3.85%
1
14.29%
Dmitry Adamushko
1
3.85%
1
14.29%
Frédéric Weisbecker
1
3.85%
1
14.29%
Total
26
100.00%
7
100.00%



static int __init setup_schedstats(char *str)
{
	int ret = 0;
	if (!str)
		goto out;

	/*
         * This code is called before jump labels have been set up, so we can't
         * change the static branch directly just yet.  Instead set a temporary
         * variable so init_schedstats() can do it later.
         */
	if (!strcmp(str, "enable")) {
		__sched_schedstats = true;
		ret = 1;
	} else if (!strcmp(str, "disable")) {
		__sched_schedstats = false;
		ret = 1;
	}
out:
	if (!ret)
		pr_warn("Unable to parse schedstats=\n");

	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Mel Gorman
51
62.96%
1
14.29%
Peter Zijlstra
10
12.35%
3
42.86%
Dario Faggioli
9
11.11%
1
14.29%
Frédéric Weisbecker
6
7.41%
1
14.29%
Josh Poimboeuf
5
6.17%
1
14.29%
Total
81
100.00%
7
100.00%

__setup("schedstats=", setup_schedstats);



static void __init init_schedstats(void)
{
	set_schedstats(__sched_schedstats);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Josh Poimboeuf
14
100.00%
1
100.00%
Total
14
100.00%
1
100.00%

#ifdef CONFIG_PROC_SYSCTL


int sysctl_schedstats(struct ctl_table *table, int write,
			 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
	int err;
	int state = static_branch_likely(&sched_schedstats);

	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	t = *table;
	t.data = &state;
	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
	if (err < 0)
		return err;
	if (write)
		set_schedstats(state);
	return err;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Mel Gorman
77
73.33%
1
9.09%
Peter Zijlstra
13
12.38%
1
9.09%
Dario Faggioli
5
4.76%
1
9.09%
Frédéric Weisbecker
2
1.90%
1
9.09%
Linus Torvalds
2
1.90%
2
18.18%
Gregory Haskins
2
1.90%
1
9.09%
Suresh B. Siddha
1
0.95%
1
9.09%
Andrew Morton
1
0.95%
1
9.09%
Mike Galbraith
1
0.95%
1
9.09%
Robert Love
1
0.95%
1
9.09%
Total
105
100.00%
11
100.00%

#endif /* CONFIG_PROC_SYSCTL */
#else  /* !CONFIG_SCHEDSTATS */


static inline void init_schedstats(void) {}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Josh Poimboeuf
8
100.00%
1
100.00%
Total
8
100.00%
1
100.00%

#endif /* CONFIG_SCHEDSTATS */

/*
 * fork()/clone()-time setup:
 */


int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
	unsigned long flags;
	int cpu = get_cpu();

	__sched_fork(clone_flags, p);
	/*
         * We mark the process as NEW here. This guarantees that
         * nobody will actually run it, and a signal or other external
         * event cannot wake it up and insert it on the runqueue either.
         */
	p->state = TASK_NEW;

	/*
         * Make sure we do not leak PI boosting priority to the child.
         */
	p->prio = current->normal_prio;

	/*
         * Revert to default priority/policy on fork if requested.
         */
	if (unlikely(p->sched_reset_on_fork)) {
		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
			p->policy = SCHED_NORMAL;
			p->static_prio = NICE_TO_PRIO(0);
			p->rt_priority = 0;
		} else if (PRIO_TO_NICE(p->static_prio) < 0)
			p->static_prio = NICE_TO_PRIO(0);

		p->prio = p->normal_prio = __normal_prio(p);
		set_load_weight(p, false);

		/*
                 * We don't need the reset flag anymore after the fork. It has
                 * fulfilled its duty:
                 */
		p->sched_reset_on_fork = 0;
	}

	if (dl_prio(p->prio)) {
		put_cpu();
		return -EAGAIN;
	} else if (rt_prio(p->prio)) {
		p->sched_class = &rt_sched_class;
	} else {
		p->sched_class = &fair_sched_class;
	}

	init_entity_runnable_average(&p->se);

	/*
         * The child is not yet in the pid-hash so no cgroup attach races,
         * and the cgroup is pinned to this child due to cgroup_fork()
         * is ran before sched_fork().
         *
         * Silence PROVE_RCU.
         */
	raw_spin_lock_irqsave(&p->pi_lock, flags);
	/*
         * We're setting the CPU for the first time, we don't migrate,
         * so use __set_task_cpu().
         */
	__set_task_cpu(p, cpu);
	if (p->sched_class->task_fork)
		p->sched_class->task_fork(p);
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);

#ifdef CONFIG_SCHED_INFO
	if (likely(sched_info_on()))
		memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
	p->on_cpu = 0;
#endif
	init_task_preempt_count(p);
#ifdef CONFIG_SMP
	plist_node_init(&p->pushable_tasks, MAX_PRIO);
	RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif

	put_cpu();
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
198
61.68%
9
23.68%
Dario Faggioli
61
19.00%
2
5.26%
Frédéric Weisbecker
17
5.30%
3
7.89%
Mel Gorman
6
1.87%
1
2.63%
Tim Chen
4
1.25%
1
2.63%
Linus Torvalds
4
1.25%
2
5.26%
Ingo Molnar
3
0.93%
2
5.26%
Con Kolivas
2
0.62%
1
2.63%
Andrew Morton
2
0.62%
1
2.63%
Thomas Gleixner
2
0.62%
1
2.63%
Hidetoshi Seto
2
0.62%
1
2.63%
Stanislaw Gruszka
2
0.62%
1
2.63%
Vincent Guittot
2
0.62%
1
2.63%
Dmitry Adamushko
2
0.62%
1
2.63%
Oleg Nesterov
2
0.62%
1
2.63%
Laurent Vivier
2
0.62%
1
2.63%
Avi Kivity
2
0.62%
1
2.63%
Martin Schwidefsky
1
0.31%
1
2.63%
Jack Steiner
1
0.31%
1
2.63%
Martin J. Bligh
1
0.31%
1
2.63%
Robert Love
1
0.31%
1
2.63%
Venkatesh Pallipadi
1
0.31%
1
2.63%
Lucas De Marchi
1
0.31%
1
2.63%
Christoph Lameter
1
0.31%
1
2.63%
Steven Rostedt
1
0.31%
1
2.63%
Total
321
100.00%
38
100.00%



unsigned long to_ratio(u64 period, u64 runtime)
{
	if (runtime == RUNTIME_INF)
		return BW_UNIT;

	/*
         * Doing this here saves a lot of checks in all
         * the calling paths, and returning zero seems
         * safe for them anyway.
         */
	if (period == 0)
		return 0;

	return div64_u64(runtime << BW_SHIFT, period);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
31
75.61%
1
16.67%
Frédéric Weisbecker
3
7.32%
1
16.67%
Dario Faggioli
3
7.32%
1
16.67%
Luca Abeni
2
4.88%
1
16.67%
Morten Rasmussen
1
2.44%
1
16.67%
Andrew Morton
1
2.44%
1
16.67%
Total
41
100.00%
6
100.00%

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */


void wake_up_new_task(struct task_struct *p)
{
	struct rq_flags rf;
	struct rq *rq;

	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
	p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
	/*
         * Fork balancing, do it here and not earlier because:
         *  - cpus_allowed can change in the fork path
         *  - any previously selected CPU might disappear through hotplug
         *
         * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
         * as we're not fully set-up yet.
         */
	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
	rq = __task_rq_lock(p, &rf);
	update_rq_clock(rq);
	post_init_entity_util_avg(&p->se);

	activate_task(rq, p, ENQUEUE_NOCLOCK);
	p->on_rq = TASK_ON_RQ_QUEUED;
	trace_sched_wakeup_new(p);
	check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
	if (p->sched_class->task_woken) {
		/*
                 * Nothing relies on rq->lock after this, so its fine to
                 * drop it.
                 */
		rq_unpin_lock(rq, &rf);
		p->sched_class->task_woken(rq, p);
		rq_repin_lock(rq, &rf);
	}
#endif
	task_rq_unlock(rq, p, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Nico Pitre
130
77.84%
1
7.14%
Peter Zijlstra
14
8.38%
4
28.57%
Dario Faggioli
8
4.79%
1
7.14%
Ingo Molnar
4
2.40%
3
21.43%
Matthew Wilcox
4
2.40%
1
7.14%
Frédéric Weisbecker
4
2.40%
1
7.14%
Con Kolivas
1
0.60%
1
7.14%
Thomas Gleixner
1
0.60%
1
7.14%
Laurent Vivier
1
0.60%
1
7.14%
Total
167
100.00%
14
100.00%

#ifdef CONFIG_PREEMPT_NOTIFIERS


static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;



void preempt_notifier_inc(void)
{
	static_key_slow_inc(&preempt_notifier_key);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
9
69.23%
2
50.00%
Dario Faggioli
2
15.38%
1
25.00%
Linus Torvalds
2
15.38%
1
25.00%
Total
13
100.00%
4
100.00%


EXPORT_SYMBOL_GPL(preempt_notifier_inc);



void preempt_notifier_dec(void)
{
	static_key_slow_dec(&preempt_notifier_key);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
10
76.92%
3
60.00%
Dario Faggioli
2
15.38%
1
20.00%
Alex Shi
1
7.69%
1
20.00%
Total
13
100.00%
5
100.00%


EXPORT_SYMBOL_GPL(preempt_notifier_dec);

/**
 * preempt_notifier_register - tell me when current is being preempted & rescheduled
 * @notifier: notifier struct to register
 */


void preempt_notifier_register(struct preempt_notifier *notifier)
{
	if (!static_key_false(&preempt_notifier_key))
		WARN(1, "registering preempt_notifier while notifiers disabled\n");

	hlist_add_head(&notifier->link, &current->preempt_notifiers);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
24
61.54%
2
25.00%
Dario Faggioli
6
15.38%
1
12.50%
Linus Torvalds
4
10.26%
2
25.00%
Arnaldo Carvalho de Melo
2
5.13%
1
12.50%
Ingo Molnar
2
5.13%
1
12.50%
Linus Torvalds (pre-git)
1
2.56%
1
12.50%
Total
39
100.00%
8
100.00%


EXPORT_SYMBOL_GPL(preempt_notifier_register);

/**
 * preempt_notifier_unregister - no longer interested in preemption notifications
 * @notifier: notifier struct to unregister
 *
 * This is *not* safe to call from within a preemption notifier.
 */


void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
	hlist_del(&notifier->link);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
9
50.00%
1
25.00%
Stanislaw Gruszka
4
22.22%
1
25.00%
Mel Gorman
4
22.22%
1
25.00%
Frédéric Weisbecker
1
5.56%
1
25.00%
Total
18
100.00%
4
100.00%


EXPORT_SYMBOL_GPL(preempt_notifier_unregister);



static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
	struct preempt_notifier *notifier;

	hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
		notifier->ops->sched_in(notifier, raw_smp_processor_id());
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
16
44.44%
1
10.00%
Dario Faggioli
8
22.22%
1
10.00%
Linus Torvalds
3
8.33%
1
10.00%
Frédéric Weisbecker
3
8.33%
1
10.00%
Ingo Molnar
2
5.56%
2
20.00%
Oleg Nesterov
1
2.78%
1
10.00%
Mel Gorman
1
2.78%
1
10.00%
Jack Steiner
1
2.78%
1
10.00%
Thomas Gleixner
1
2.78%
1
10.00%
Total
36
100.00%
10
100.00%



static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
	if (static_key_false(&preempt_notifier_key))
		__fire_sched_in_preempt_notifiers(curr);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds
13
52.00%
1
16.67%
Stanislaw Gruszka
6
24.00%
1
16.67%
Dario Faggioli
2
8.00%
1
16.67%
Peter Zijlstra
2
8.00%
1
16.67%
Ingo Molnar
1
4.00%
1
16.67%
Oleg Nesterov
1
4.00%
1
16.67%
Total
25
100.00%
6
100.00%


static void

__fire_sched_out_preempt_notifiers(struct task_struct *curr,
				   struct task_struct *next)
{
	struct preempt_notifier *notifier;

	hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
		notifier->ops->sched_out(notifier, next);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
27
67.50%
5
41.67%
Ingo Molnar
4
10.00%
2
16.67%
Dario Faggioli
4
10.00%
1
8.33%
Linus Torvalds
3
7.50%
2
16.67%
Davide Libenzi
1
2.50%
1
8.33%
Glauber de Oliveira Costa
1
2.50%
1
8.33%
Total
40
100.00%
12
100.00%


static __always_inline void

fire_sched_out_preempt_notifiers(struct task_struct *curr,
				 struct task_struct *next)
{
	if (static_key_false(&preempt_notifier_key))
		__fire_sched_out_preempt_notifiers(curr, next);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds
20
62.50%
1
14.29%
Peter Zijlstra
6
18.75%
3
42.86%
Dario Faggioli
4
12.50%
1
14.29%
Ingo Molnar
1
3.12%
1
14.29%
Thomas Gleixner
1
3.12%
1
14.29%
Total
32
100.00%
7
100.00%

#else /* !CONFIG_PREEMPT_NOTIFIERS */



static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
7
63.64%
1
33.33%
Dario Faggioli
3
27.27%
1
33.33%
Linus Torvalds
1
9.09%
1
33.33%
Total
11
100.00%
3
100.00%


static inline void

fire_sched_out_preempt_notifiers(struct task_struct *curr,
				 struct task_struct *next)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
12
75.00%
2
40.00%
Oleg Nesterov
2
12.50%
1
20.00%
Dario Faggioli
1
6.25%
1
20.00%
Linus Torvalds
1
6.25%
1
20.00%
Total
16
100.00%
5
100.00%

#endif /* CONFIG_PREEMPT_NOTIFIERS */

/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @prev: the current task that is being switched out
 * @next: the task we are going to switch to.
 *
 * This is called with the rq lock held and interrupts off. It must
 * be paired with a subsequent finish_task_switch after the context
 * switch.
 *
 * prepare_task_switch sets up locking and calls architecture specific
 * hooks.
 */

static inline void

prepare_task_switch(struct rq *rq, struct task_struct *prev,
		    struct task_struct *next)
{
	sched_info_switch(rq, prev, next);
	perf_event_task_sched_out(prev, next);
	fire_sched_out_preempt_notifiers(prev, next);
	prepare_lock_switch(rq, next);
	prepare_arch_switch(next);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
19
33.33%
1
5.88%
Peter Zijlstra
19
33.33%
4
23.53%
Mike Galbraith
4
7.02%
1
5.88%
Masami Hiramatsu
3
5.26%
1
5.88%
Guillaume Chazarain
2
3.51%
1
5.88%
Ingo Molnar
2
3.51%
1
5.88%
Linus Torvalds
2
3.51%
2
11.76%
Thomas Gleixner
1
1.75%
1
5.88%
Martin Schwidefsky
1
1.75%
1
5.88%
Davide Libenzi
1
1.75%
1
5.88%
Bob Miller
1
1.75%
1
5.88%
Benjamin LaHaise
1
1.75%
1
5.88%
Steven Rostedt
1
1.75%
1
5.88%
Total
57
100.00%
17
100.00%

/**
 * finish_task_switch - clean up after a task-switch
 * @prev: the thread we just switched away from.
 *
 * finish_task_switch must be called after the context switch, paired
 * with a prepare_task_switch call before the context switch.
 * finish_task_switch will reconcile locking set up by prepare_task_switch,
 * and do any other architecture-specific cleanup actions.
 *
 * Note that we may have delayed dropping an mm in context_switch(). If
 * so, we finish that here outside of the runqueue lock. (Doing it
 * with the lock held can cause deadlocks; see schedule() for
 * details.)
 *
 * The context switch have flipped the stack from under us and restored the
 * local variables which were saved when this task called schedule() in the
 * past. prev == current is still correct but we need to recalculate this_rq
 * because prev may have moved to another CPU.
 */

static struct rq *finish_task_switch(struct task_struct *prev)
	__releases(rq->lock)
{
	struct rq *rq = this_rq();
	struct mm_struct *mm = rq->prev_mm;
	long prev_state;

	/*
         * The previous task will have left us with a preempt_count of 2
         * because it left us after:
         *
         *      schedule()
         *        preempt_disable();                    // 1
         *        __schedule()
         *          raw_spin_lock_irq(&rq->lock)        // 2
         *
         * Also, see FORK_PREEMPT_COUNT.
         */
	if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
		      "corrupted preempt_count: %s/%d/0x%x\n",
		      current->comm, current->pid, preempt_count()))
		preempt_count_set(FORK_PREEMPT_COUNT);

	rq->prev_mm = NULL;

	/*
         * A task struct has one reference for the use as "current".
         * If a task dies, then it sets TASK_DEAD in tsk->state and calls
         * schedule one last time. The schedule call will never return, and
         * the scheduled task must drop that reference.
         *
         * We must observe prev->state before clearing prev->on_cpu (in
         * finish_lock_switch), otherwise a concurrent wakeup can get prev
         * running on another CPU and we could rave with its RUNNING -> DEAD
         * transition, resulting in a double drop.
         */
	prev_state = prev->state;
	vtime_task_switch(prev);
	perf_event_task_sched_in(prev, current);
	/*
         * The membarrier system call requires a full memory barrier
         * after storing to rq->curr, before going back to user-space.
         *
         * TODO: This smp_mb__after_unlock_lock can go away if PPC end
         * up adding a full barrier to switch_mm(), or we should figure
         * out if a smp_mb__after_unlock_lock is really the proper API
         * to use.
         */
	smp_mb__after_unlock_lock();
	finish_lock_switch(rq, prev);
	finish_arch_post_lock_switch();

	fire_sched_in_preempt_notifiers(current);
	if (mm)
		mmdrop(mm);
	if (unlikely(prev_state == TASK_DEAD)) {
		if (prev->sched_class->task_dead)
			prev->sched_class->task_dead(prev);

		/*
                 * Remove function-return probe instances associated with this
                 * task and put them back on the free list.
                 */
		kprobe_flush_task(prev);

		/* Task is done with its stack. */
		put_task_stack(prev);

		put_task_struct(prev);
	}

	tick_nohz_task_switch();
	return rq;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
95
54.60%
7
25.93%
Dario Faggioli
27
15.52%
1
3.70%
Ingo Molnar
7
4.02%
3
11.11%
Andrew Lutomirski
6
3.45%
1
3.70%
Stanislaw Gruszka
6
3.45%
1
3.70%
Linus Torvalds
6
3.45%
3
11.11%
Venkatesh Pallipadi
5
2.87%
1
3.70%
Mathieu Desnoyers
4
2.30%
1
3.70%
Frédéric Weisbecker
4
2.30%
2
7.41%
Srivatsa Vaddagiri
4
2.30%
1
3.70%
Andrew Morton
2
1.15%
1
3.70%
Thomas Gleixner
2
1.15%
1
3.70%
Peter Williams
2
1.15%
1
3.70%
Mel Gorman
2
1.15%
1
3.70%
Oleg Nesterov
2
1.15%
2
7.41%
Total
174
100.00%
27
100.00%

#ifdef CONFIG_SMP

/* rq->lock is NOT held, but preemption is disabled */


static void __balance_callback(struct rq *rq)
{
	struct callback_head *head, *next;
	void (*func)(struct rq *rq);
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);
	head = rq->balance_callback;
	rq->balance_callback = NULL;
	while (head) {
		func = (void (*)(struct rq *))head->func;
		next = head->next;
		head->next = NULL;
		head = next;

		func(rq);
	}
	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
79
71.17%
1
6.67%
Dario Faggioli
13
11.71%
1
6.67%
Ingo Molnar
5
4.50%
3
20.00%
Linus Torvalds
4
3.60%
3
20.00%
Christoph Lameter
2
1.80%
1
6.67%
Frédéric Weisbecker
2
1.80%
2
13.33%
Martin J. Bligh
2
1.80%
1
6.67%
Thomas Gleixner
2
1.80%
1
6.67%
Laurent Vivier
1
0.90%
1
6.67%
Aaron Tomlin
1
0.90%
1
6.67%
Total
111
100.00%
15
100.00%



static inline void balance_callback(struct rq *rq)
{
	if (unlikely(rq->balance_callback))
		__balance_callback(rq);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
13
50.00%
2
40.00%
Linus Torvalds
8
30.77%
1
20.00%
Dario Faggioli
4
15.38%
1
20.00%
Ingo Molnar
1
3.85%
1
20.00%
Total
26
100.00%
5
100.00%

#else



static inline void balance_callback(struct rq *rq)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
6
54.55%
2
33.33%
Dario Faggioli
2
18.18%
1
16.67%
Mel Gorman
1
9.09%
1
16.67%
Oleg Nesterov
1
9.09%
1
16.67%
Linus Torvalds
1
9.09%
1
16.67%
Total
11
100.00%
6
100.00%

#endif

/**
 * schedule_tail - first thing a freshly forked thread must call.
 * @prev: the thread we just switched away from.
 */

asmlinkage __visible void schedule_tail(struct task_struct *prev)
	__releases(rq->lock)
{
	struct rq *rq;

	/*
         * New tasks start with FORK_PREEMPT_COUNT, see there and
         * finish_task_switch() for details.
         *
         * finish_task_switch() will drop rq->lock() and lower preempt_count
         * and the preempt_enable() will end up enabling preemption (on
         * PREEMPT_COUNT kernels).
         */

	rq = finish_task_switch(prev);
	balance_callback(rq);
	preempt_enable();

	if (current->set_child_tid)
		put_user(task_pid_vnr(current), current->set_child_tid);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
20
35.09%
2
12.50%
Dario Faggioli
11
19.30%
1
6.25%
Thomas Gleixner
9
15.79%
3
18.75%
Ingo Molnar
5
8.77%
3
18.75%
Mike Galbraith
3
5.26%
1
6.25%
Oleg Nesterov
2
3.51%
1
6.25%
Linus Torvalds
2
3.51%
1
6.25%
Guillaume Chazarain
2
3.51%
1
6.25%
Bob Miller
1
1.75%
1
6.25%
Robert Love
1
1.75%
1
6.25%
Davide Libenzi
1
1.75%
1
6.25%
Total
57
100.00%
16
100.00%

/*
 * context_switch - switch to the new MM and the new thread's register state.
 */
static __always_inline struct rq *

context_switch(struct rq *rq, struct task_struct *prev,
	       struct task_struct *next, struct rq_flags *rf)
{
        struct mm_struct *mm, *oldmm;

	prepare_task_switch(rq, prev, next);

	mm = next->mm;
	oldmm = prev->active_mm;
	/*
         * For paravirt, this is coupled with an exit in switch_to to
         * combine the page table reload and the switch backend into
         * one hypercall.
         */
	arch_start_context_switch(prev);

	if (!mm) {
		next->active_mm = oldmm;
		mmgrab(oldmm);
		enter_lazy_tlb(oldmm, next);
	} else
		switch_mm_irqs_off(oldmm, mm, next);

	if (!prev->mm) {
		prev->active_mm = NULL;
		rq->prev_mm = oldmm;
	}

	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);

	/*
         * Since the runqueue lock will be released by the next
         * task (which is an invalid locking op but in the case
         * of the scheduler it's an obvious special-case), so we
         * do an early lockdep release here:
         */
	rq_unpin_lock(rq, rf);
	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);
	barrier();

	return finish_task_switch(prev);
}

/*
 * nr_running and nr_context_switches:
 *
 * externally visible scheduler statistics: current number of runnable
 * threads, total number of context switches performed since bootup.
 */


unsigned long nr_running(void)
{
	unsigned long i, sum = 0;

	for_each_online_cpu(i)
		sum += cpu_rq(i)->nr_running;

	return sum;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
81.25%
1
20.00%
Dario Faggioli
2
6.25%
1
20.00%
Thomas Gleixner
2
6.25%
1
20.00%
Ingo Molnar
1
3.12%
1
20.00%
Josh Poimboeuf
1
3.12%
1
20.00%
Total
32
100.00%
5
100.00%

/*
 * Check if only the current task is running on the CPU.
 *
 * Caution: this function does not check that the caller has disabled
 * preemption, thus the result might have a time-of-check-to-time-of-use
 * race.  The caller is responsible to use it correctly, for example:
 *
 * - from a non-preemptable section (of course)
 *
 * - from a thread that is bound to a single CPU
 *
 * - in a loop with very short iterations (e.g. a polling loop)
 */


bool single_task_running(void)
{
	return raw_rq()->nr_running == 1;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
73.33%
2
50.00%
Dario Faggioli
3
20.00%
1
25.00%
Dominik Dingel
1
6.67%
1
25.00%
Total
15
100.00%
4
100.00%


EXPORT_SYMBOL(single_task_running);



unsigned long long nr_context_switches(void)
{
	int i;
	unsigned long long sum = 0;

	for_each_possible_cpu(i)
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
20
57.14%
1
16.67%
Dario Faggioli
8
22.86%
1
16.67%
Linus Torvalds
3
8.57%
1
16.67%
Andi Kleen
2
5.71%
1
16.67%
Thomas Gleixner
1
2.86%
1
16.67%
Andrew Morton
1
2.86%
1
16.67%
Total
35
100.00%
6
100.00%

/*
 * IO-wait accounting, and how its mostly bollocks (on SMP).
 *
 * The idea behind IO-wait account is to account the idle time that we could
 * have spend running if it were not for IO. That is, if we were to improve the
 * storage performance, we'd have a proportional reduction in IO-wait time.
 *
 * This all works nicely on UP, where, when a task blocks on IO, we account
 * idle time as IO-wait, because if the storage were faster, it could've been
 * running and we'd not be idle.
 *
 * This has been extended to SMP, by doing the same for each CPU. This however
 * is broken.
 *
 * Imagine for instance the case where two tasks block on one CPU, only the one
 * CPU will have IO-wait accounted, while the other has regular idle. Even
 * though, if the storage were faster, both could've ran at the same time,
 * utilising both CPUs.
 *
 * This means, that when looking globally, the current IO-wait accounting on
 * SMP is a lower bound, by reason of under accounting.
 *
 * Worse, since the numbers are provided per CPU, they are sometimes
 * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
 * associated with any one particular CPU, it can wake to another CPU than it
 * blocked on. This means the per CPU IO-wait number is meaningless.
 *
 * Task CPU affinities can make all that even more 'interesting'.
 */



unsigned long nr_iowait(void)
{
	unsigned long i, sum = 0;

	for_each_possible_cpu(i)
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
21
58.33%
1
14.29%
Thomas Gleixner
6
16.67%
1
14.29%
Dario Faggioli
3
8.33%
1
14.29%
Arnaldo Carvalho de Melo
2
5.56%
1
14.29%
Frédéric Weisbecker
2
5.56%
1
14.29%
Dean Nelson
1
2.78%
1
14.29%
Steven Rostedt
1
2.78%
1
14.29%
Total
36
100.00%
7
100.00%

/*
 * Consumers of these two interfaces, like for example the cpufreq menu
 * governor are using nonsensical data. Boosting frequency for a CPU that has
 * IO-wait which might not even end up running the task when it does become
 * runnable.
 */



unsigned long nr_iowait_cpu(int cpu)
{
	struct rq *this = cpu_rq(cpu);
	return atomic_read(&this->nr_iowait);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
22
78.57%
1
25.00%
Andrew Lutomirski
2
7.14%
1
25.00%
Dario Faggioli
2
7.14%
1
25.00%
Josh Poimboeuf
2
7.14%
1
25.00%
Total
28
100.00%
4
100.00%



void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
	struct rq *rq = this_rq();
	*nr_waiters = atomic_read(&rq->nr_iowait);
	*load = rq->load.weight;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
30
69.77%
1
12.50%
Dario Faggioli
3
6.98%
1
12.50%
Linus Torvalds
3
6.98%
1
12.50%
Guillaume Chazarain
2
4.65%
1
12.50%
Ingo Molnar
2
4.65%
1
12.50%
Thomas Gleixner
1
2.33%
1
12.50%
Josh Poimboeuf
1
2.33%
1
12.50%
Frédéric Weisbecker
1
2.33%
1
12.50%
Total
43
100.00%
8
100.00%

#ifdef CONFIG_SMP

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */


void sched_exec(void)
{
	struct task_struct *p = current;
	unsigned long flags;
	int dest_cpu;

	raw_spin_lock_irqsave(&p->pi_lock, flags);
	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
	if (dest_cpu == smp_processor_id())
		goto unlock;

	if (likely(cpu_active(dest_cpu))) {
		struct migration_arg arg = { p, dest_cpu };

		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
		return;
	}
unlock:
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
80
67.23%
1
7.14%
Dario Faggioli
18
15.13%
1
7.14%
Oleg Nesterov
6
5.04%
2
14.29%
Linus Torvalds
3
2.52%
2
14.29%
Ingo Molnar
3
2.52%
2
14.29%
Frédéric Weisbecker
2
1.68%
1
7.14%
Arnaldo Carvalho de Melo
2
1.68%
1
7.14%
Thomas Gleixner
2
1.68%
1
7.14%
Christoph Lameter
1
0.84%
1
7.14%
Laurent Vivier
1
0.84%
1
7.14%
Martin J. Bligh
1
0.84%
1
7.14%
Total
119
100.00%
14
100.00%

#endif

DEFINE_PER_CPU(struct kernel_stat, kstat);
DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);


EXPORT_PER_CPU_SYMBOL(kstat);

EXPORT_PER_CPU_SYMBOL(kernel_cpustat);

/*
 * The function fair_sched_class.update_curr accesses the struct curr
 * and its field curr->exec_start; when called from task_sched_runtime(),
 * we observe a high rate of cache misses in practice.
 * Prefetching this data results in improved performance.
 */


static inline void prefetch_curr_exec_start(struct task_struct *p)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	struct sched_entity *curr = (&p->se)->cfs_rq->curr;
#else
	struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
#endif
	prefetch(curr);
	prefetch(&curr->exec_start);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Giovanni Gherdovich
53
81.54%
1
12.50%
Dario Faggioli
3
4.62%
1
12.50%
Ingo Molnar
2
3.08%
1
12.50%
Masami Hiramatsu
2
3.08%
1
12.50%
Peter Zijlstra
2
3.08%
1
12.50%
Thomas Gleixner
1
1.54%
1
12.50%
Frédéric Weisbecker
1
1.54%
1
12.50%
Dean Nelson
1
1.54%
1
12.50%
Total
65
100.00%
8
100.00%

/*
 * Return accounted runtime for the task.
 * In case the task is currently running, return the runtime plus current's
 * pending runtime that have not been accounted yet.
 */


unsigned long long task_sched_runtime(struct task_struct *p)
{
	struct rq_flags rf;
	struct rq *rq;
	u64 ns;

#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
	/*
         * 64-bit doesn't need locks to atomically read a 64bit value.
         * So we have a optimization chance when the task's delta_exec is 0.
         * Reading ->on_cpu is racy, but this is ok.
         *
         * If we race with it leaving CPU, we'll take a lock. So we're correct.
         * If we race with it entering CPU, unaccounted time is 0. This is
         * indistinguishable from the read occurring a few cycles earlier.
         * If we see ->on_cpu without ->on_rq, the task is leaving, and has
         * been accounted, so we're correct here as well.
         */
	if (!p->on_cpu || !task_on_rq_queued(p))
		return p->se.sum_exec_runtime;
#endif

	rq = task_rq_lock(p, &rf);
	/*
         * Must be ->curr _and_ ->on_rq.  If dequeued, we would
         * project cycles that may never be accounted to this
         * thread, breaking clock_gettime().
         */
	if (task_current(rq, p) && task_on_rq_queued(p)) {
		prefetch_curr_exec_start(p);
		update_rq_clock(rq);
		p->sched_class->update_curr(rq);
	}
	ns = p->se.sum_exec_runtime;
	task_rq_unlock(rq, p, &rf);

	return ns;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
73
58.40%
6
26.09%
Dario Faggioli
25
20.00%
2
8.70%
Oleg Nesterov
9
7.20%
2
8.70%
Linus Torvalds (pre-git)
3
2.40%
2
8.70%
Giovanni Gherdovich
3
2.40%
1
4.35%
Ingo Molnar
2
1.60%
2
8.70%
Matt Mackall
2
1.60%
1
4.35%
Srivatsa Vaddagiri
2
1.60%
1
4.35%
Greg Kroah-Hartman
2
1.60%
2
8.70%
Thomas Gleixner
1
0.80%
1
4.35%
Steven Rostedt
1
0.80%
1
4.35%
Christian Bornträger
1
0.80%
1
4.35%
Frédéric Weisbecker
1
0.80%
1
4.35%
Total
125
100.00%
23
100.00%

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 */


void scheduler_tick(void)
{
	int cpu = smp_processor_id();
	struct rq *rq = cpu_rq(cpu);
	struct task_struct *curr = rq->curr;
	struct rq_flags rf;

	sched_clock_tick();

	rq_lock(rq, &rf);

	update_rq_clock(rq);
	curr->sched_class->task_tick(rq, curr, 0);
	cpu_load_update_active(rq);
	calc_global_load_tick(rq);

	rq_unlock(rq, &rf);

	perf_event_task_tick();

#ifdef CONFIG_SMP
	rq->idle_balance = idle_cpu(cpu);
	trigger_load_balance(rq);
#endif
	rq_last_tick_reset(rq);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
52
47.27%
3
13.04%
Dario Faggioli
31
28.18%
1
4.35%
Ingo Molnar
5
4.55%
4
17.39%
Linus Torvalds
4
3.64%
2
8.70%
Thomas Gleixner
3
2.73%
3
13.04%
Peter Williams
2
1.82%
1
4.35%
Andrew Lutomirski
2
1.82%
1
4.35%
Andrew Morton
2
1.82%
1
4.35%
Frédéric Weisbecker
2
1.82%
2
8.70%
Arnaldo Carvalho de Melo
2
1.82%
1
4.35%
Kirill Tkhai
2
1.82%
1
4.35%
Guillaume Chazarain
1
0.91%
1
4.35%
Bob Miller
1
0.91%
1
4.35%
Oleg Nesterov
1
0.91%
1
4.35%
Total
110
100.00%
23
100.00%

#ifdef CONFIG_NO_HZ_FULL
/**
 * scheduler_tick_max_deferment
 *
 * Keep at least one tick per second when a single
 * active task is running because the scheduler doesn't
 * yet completely support full dynticks environment.
 *
 * This makes sure that uptime, CFS vruntime, load
 * balancing, etc... continue to move forward, even
 * with a very low granularity.
 *
 * Return: Maximum deferment in nanoseconds.
 */


u64 scheduler_tick_max_deferment(void)
{
	struct rq *rq = this_rq();
	unsigned long next, now = READ_ONCE(jiffies);

	next = rq->last_sched_tick + HZ;

	if (time_before_eq(next, now))
		return 0;

	return jiffies_to_nsecs(next - now);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
44
81.48%
2
18.18%
Linus Torvalds
2
3.70%
2
18.18%
Frédéric Weisbecker
2
3.70%
2
18.18%
Dario Faggioli
2
3.70%
1
9.09%
Oleg Nesterov
1
1.85%
1
9.09%
Linus Torvalds (pre-git)
1
1.85%
1
9.09%
Ingo Molnar
1
1.85%
1
9.09%
Heiko Carstens
1
1.85%
1
9.09%
Total
54
100.00%
11
100.00%

#endif

#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
				defined(CONFIG_PREEMPT_TRACER))
/*
 * If the value passed in is equal to the current preempt count
 * then we just disabled preemption. Start timing the latency.
 */


static inline void preempt_latency_start(int val)
{
	if (preempt_count() == val) {
		unsigned long ip = get_lock_parent_ip();
#ifdef CONFIG_DEBUG_PREEMPT
		current->preempt_disable_ip = ip;
#endif
		trace_preempt_off(CALLER_ADDR0, ip);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Steven Rostedt
32
72.73%
1
12.50%
Dario Faggioli
3
6.82%
1
12.50%
Peter Zijlstra
3
6.82%
1
12.50%
Davide Libenzi
2
4.55%
1
12.50%
Thomas Gleixner
1
2.27%
1
12.50%
Matt Mackall
1
2.27%
1
12.50%
Frédéric Weisbecker
1
2.27%
1
12.50%
Oleg Nesterov
1
2.27%
1
12.50%
Total
44
100.00%
8
100.00%



void preempt_count_add(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
	/*
         * Underflow?
         */
	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
		return;
#endif
	__preempt_count_add(val);
#ifdef CONFIG_DEBUG_PREEMPT
	/*
         * Spinlock count overflowing soon?
         */
	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
				PREEMPT_MASK - 10);
#endif
	preempt_latency_start(val);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
31
54.39%
1
8.33%
Dario Faggioli
11
19.30%
1
8.33%
Linus Torvalds
3
5.26%
1
8.33%
Dongsheng Yang
2
3.51%
1
8.33%
Oleg Nesterov
2
3.51%
1
8.33%
Steven Rostedt
2
3.51%
1
8.33%
Linus Torvalds (pre-git)
2
3.51%
2
16.67%
Andi Kleen
1
1.75%
1
8.33%
Dean Nelson
1
1.75%
1
8.33%
Rusty Russell
1
1.75%
1
8.33%
Paul E. McKenney
1
1.75%
1
8.33%
Total
57
100.00%
12
100.00%


EXPORT_SYMBOL(preempt_count_add);

NOKPROBE_SYMBOL(preempt_count_add);

/*
 * If the value passed in equals to the current preempt count
 * then we just enabled preemption. Stop timing the latency.
 */


static inline void preempt_latency_stop(int val)
{
	if (preempt_count() == val)
		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Steven Rostedt
15
60.00%
1
50.00%
Giovanni Gherdovich
10
40.00%
1
50.00%
Total
25
100.00%
2
100.00%



void preempt_count_sub(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
	/*
         * Underflow?
         */
	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
		return;
	/*
         * Is the spinlock portion underflowing?
         */
	if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
			!(preempt_count() & PREEMPT_MASK)))
		return;
#endif

	preempt_latency_stop(val);
	__preempt_count_sub(val);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
32
57.14%
3
27.27%
Dario Faggioli
14
25.00%
2
18.18%
Giovanni Gherdovich
3
5.36%
1
9.09%
Steven Rostedt
3
5.36%
2
18.18%
Linus Torvalds (pre-git)
2
3.57%
1
9.09%
Ingo Molnar
1
1.79%
1
9.09%
Frédéric Weisbecker
1
1.79%
1
9.09%
Total
56
100.00%
11
100.00%


EXPORT_SYMBOL(preempt_count_sub);

NOKPROBE_SYMBOL(preempt_count_sub);

#else


static inline void preempt_latency_start(int val) { }
Contributors
Person
Tokens
Prop
Commits
CommitProp
Steven Rostedt
6
66.67%
1
25.00%
Peter Zijlstra
1
11.11%
1
25.00%
Dario Faggioli
1
11.11%
1
25.00%
Ingo Molnar
1
11.11%
1
25.00%
Total
9
100.00%
4
100.00%



static inline void preempt_latency_stop(int val) { }
Contributors
Person
Tokens
Prop
Commits
CommitProp
Steven Rostedt
8
88.89%
1
50.00%
Dario Faggioli
1
11.11%
1
50.00%
Total
9
100.00%
2
100.00%

#endif



static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
{
#ifdef CONFIG_DEBUG_PREEMPT
	return p->preempt_disable_ip;
#else
	return 0;
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ingo Molnar
26
92.86%
2
50.00%
Peter Zijlstra
1
3.57%
1
25.00%
Dario Faggioli
1
3.57%
1
25.00%
Total
28
100.00%
4
100.00%

/*
 * Print scheduling while atomic bug:
 */


static noinline void __schedule_bug(struct task_struct *prev)
{
	/* Save this before calling printk(), since that will clobber it */
	unsigned long preempt_disable_ip = get_preempt_disable_ip(current);

	if (oops_in_progress)
		return;

	printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
		prev->comm, prev->pid, preempt_count());

	debug_show_held_locks(prev);
	print_modules();
	if (irqs_disabled())
		print_irqtrace_events(prev);
	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
	    && in_atomic_preempt_off()) {
		pr_err("Preemption disabled at:");
		print_ip_sym(preempt_disable_ip);
		pr_cont("\n");
	}
	if (panic_on_warn)
		panic("scheduling while atomic\n");

	dump_stack();
	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
47
43.52%
2
11.11%
Dario Faggioli
15
13.89%
1
5.56%
Vegard Nossum
12
11.11%
1
5.56%
Oleg Nesterov
7
6.48%
1
5.56%
Daniel Bristot de Oliveira
6
5.56%
1
5.56%
Linus Torvalds
3
2.78%
1
5.56%
Brian Silverman
3
2.78%
1
5.56%
Andrew Morton
3
2.78%
1
5.56%
Kirill Tkhai
2
1.85%
1
5.56%
Arnaldo Carvalho de Melo
2
1.85%
1
5.56%
Frédéric Weisbecker
2
1.85%
2
11.11%
Peter Williams
2
1.85%
1
5.56%
Rusty Russell
1
0.93%
1
5.56%
Anton Blanchard
1
0.93%
1
5.56%
Ingo Molnar
1
0.93%
1
5.56%
Guillaume Chazarain
1
0.93%
1
5.56%
Total
108
100.00%
18
100.00%

/*
 * Various schedule()-time debugging checks and statistics:
 */


static inline void schedule_debug(struct task_struct *prev)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
	if (task_stack_end_corrupted(prev))
		panic("corrupted stack end detected inside scheduler\n");
#endif

	if (unlikely(in_atomic_preempt_off())) {
		__schedule_bug(prev);
		preempt_count_set(PREEMPT_DISABLED);
	}
	rcu_sleep_check();

	profile_hit(SCHED_PROFILING, __builtin_return_address(0));

	schedstat_inc(this_rq()->sched_count);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
41
58.57%
3
23.08%
Dario Faggioli
11
15.71%
1
7.69%
Jann Horn
6
8.57%
1
7.69%
Dongsheng Yang
2
2.86%
1
7.69%
Oleg Nesterov
2
2.86%
1
7.69%
Heiko Carstens
2
2.86%
1
7.69%
Thomas Gleixner
2
2.86%
1
7.69%
Ingo Molnar
2
2.86%
2
15.38%
Keith Owens
1
1.43%
1
7.69%
Josh Poimboeuf
1
1.43%
1
7.69%
Total
70
100.00%
13
100.00%

/*
 * Pick up the highest-prio task:
 */

static inline struct task_struct *

pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	const struct sched_class *class;
	struct task_struct *p;

	/*
         * Optimization: we know that if all tasks are in the fair class we can
         * call that function directly, but only if the @prev task wasn't of a
         * higher scheduling class, because otherwise those loose the
         * opportunity to pull in more work from other CPUs.
         */
	if (likely((prev->sched_class == &idle_sched_class ||
		    prev->sched_class == &fair_sched_class) &&
		   rq->nr_running == rq->cfs.h_nr_running)) {

		p = fair_sched_class.pick_next_task(rq, prev, rf);
		if (unlikely(p == RETRY_TASK))
			goto again;

		/* Assumes fair_sched_class->next == idle_sched_class */
		if (unlikely(!p))
			p = idle_sched_class.pick_next_task(rq, prev, rf);

		return p;
	}

again:
	for_each_class(class) {
		p = class->pick_next_task(rq, prev, rf);
		if (p) {
			if (unlikely(p == RETRY_TASK))
				goto again;
			return p;
		}
	}

	/* The idle class should always have a runnable task: */
	BUG();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
81
49.09%
4
14.81%
Dario Faggioli
25
15.15%
2
7.41%
Steven Rostedt
18
10.91%
1
3.70%
Ingo Molnar
15
9.09%
8
29.63%
Matt Fleming
6
3.64%
1
3.70%
Linus Torvalds
6
3.64%
2
7.41%
Thomas Gleixner
4
2.42%
2
7.41%
Rusty Russell
3
1.82%
2
7.41%
Andrew Lutomirski
2
1.21%
1
3.70%
Dongsheng Yang
2
1.21%
1
3.70%
Robert Love
1
0.61%
1
3.70%
Juri Lelli
1
0.61%
1
3.70%
Linus Torvalds (pre-git)
1
0.61%
1
3.70%
Total
165
100.00%
27
100.00%

/*
 * __schedule() is the main scheduler function.
 *
 * The main means of driving the scheduler and thus entering this function are:
 *
 *   1. Explicit blocking: mutex, semaphore, waitqueue, etc.
 *
 *   2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
 *      paths. For example, see arch/x86/entry_64.S.
 *
 *      To drive preemption between tasks, the scheduler sets the flag in timer
 *      interrupt handler scheduler_tick().
 *
 *   3. Wakeups don't really cause entry into schedule(). They add a
 *      task to the run-queue and that's it.
 *
 *      Now, if the new task added to the run-queue preempts the current
 *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
 *      called on the nearest possible occasion:
 *
 *       - If the kernel is preemptible (CONFIG_PREEMPT=y):
 *
 *         - in syscall or exception context, at the next outmost
 *           preempt_enable(). (this might be as soon as the wake_up()'s
 *           spin_unlock()!)
 *
 *         - in IRQ context, return from interrupt-handler to
 *           preemptible context
 *
 *       - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
 *         then at the next:
 *
 *          - cond_resched() call
 *          - explicit schedule() call
 *          - return from syscall or exception to user-space
 *          - return from interrupt-handler to user-space
 *
 * WARNING: must be called with preemption disabled!
 */


static void __sched notrace __schedule(bool preempt)
{
	struct task_struct *prev, *next;
	unsigned long *switch_count;
	struct rq_flags rf;
	struct rq *rq;
	int cpu;

	cpu = smp_processor_id();
	rq = cpu_rq(cpu);
	prev = rq->curr;

	schedule_debug(prev);

	if (sched_feat(HRTICK))
		hrtick_clear(rq);

	local_irq_disable();
	rcu_note_context_switch(preempt);

	/*
         * Make sure that signal_pending_state()->signal_pending() below
         * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
         * done by the caller to avoid the race with signal_wake_up().
         */
	rq_lock(rq, &rf);
	smp_mb__after_spinlock();

	/* Promote REQ to ACT */
	rq->clock_update_flags <<= 1;
	update_rq_clock(rq);

	switch_count = &prev->nivcsw;
	if (!preempt && prev->state) {
		if (unlikely(signal_pending_state(prev->state, prev))) {
			prev->state = TASK_RUNNING;
		} else {
			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
			prev->on_rq = 0;

			if (prev->in_iowait) {
				atomic_inc(&rq->nr_iowait);
				delayacct_blkio_start();
			}

			/*
                         * If a worker went to sleep, notify and ask workqueue
                         * whether it wants to wake up a task to maintain
                         * concurrency.
                         */
			if (prev->flags & PF_WQ_WORKER) {
				struct task_struct *to_wakeup;

				to_wakeup = wq_worker_sleeping(prev);
				if (to_wakeup)
					try_to_wake_up_local(to_wakeup, &rf);
			}
		}
		switch_count = &prev->nvcsw;
	}

	next = pick_next_task(rq, prev, &rf);
	clear_tsk_need_resched(prev);
	clear_preempt_need_resched();

	if (likely(prev != next)) {
		rq->nr_switches++;
		rq->curr = next;
		/*
                 * The membarrier system call requires each architecture
                 * to have a full memory barrier after updating
                 * rq->curr, before returning to user-space. For TSO
                 * (e.g. x86), the architecture must provide its own
                 * barrier in switch_mm(). For weakly ordered machines
                 * for which spin_unlock() acts as a full memory
                 * barrier, finish_lock_switch() in common code takes
                 * care of this barrier. For weakly ordered machines for
                 * which spin_unlock() acts as a RELEASE barrier (only
                 * arm64 and PowerPC), arm64 has a full barrier in
                 * switch_to(), and PowerPC has
                 * smp_mb__after_unlock_lock() before
                 * finish_lock_switch().
                 */
		++*switch_count;

		trace_sched_switch(preempt, prev, next);

		/* Also unlocks the rq: */
		rq = context_switch(rq, prev, next, &rf);
	} else {
		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
		rq_unlock_irq(rq, &rf);
	}

	balance_callback(rq);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
164
50.93%
11
21.57%
Dario Faggioli
55
17.08%
4
7.84%
Matt Fleming
25
7.76%
3
5.88%
Tejun Heo
11
3.42%
1
1.96%
Brian Silverman
7
2.17%
1
1.96%
Ingo Molnar
6
1.86%
4
7.84%
Linus Torvalds (pre-git)
5
1.55%
3
5.88%
Vegard Nossum
5
1.55%
1
1.96%
Thomas Gleixner
5
1.55%
2
3.92%
Dongsheng Yang
4
1.24%
1
1.96%
Steven Rostedt
4
1.24%
1
1.96%
Jann Horn
3
0.93%
1
1.96%
Daniel Bristot de Oliveira
3
0.93%
1
1.96%
Andrew Morton
3
0.93%
1
1.96%
Paul E. McKenney
3
0.93%
2
3.92%
Oleg Nesterov
2
0.62%
1
1.96%
Olivier Croquette
2
0.62%
1
1.96%
Linus Torvalds
2
0.62%
1
1.96%
Rusty Russell
2
0.62%
1
1.96%
Greg Kroah-Hartman
2
0.62%
2
3.92%
Juri Lelli
2
0.62%
1
1.96%
Andi Kleen
1
0.31%
1
1.96%
Matt Mackall
1
0.31%
1
1.96%
Robert Love
1
0.31%
1
1.96%
Josh Poimboeuf
1
0.31%
1
1.96%
Lennart Poettering
1
0.31%
1
1.96%
Harald Gustafsson
1
0.31%
1
1.96%
Mathieu Desnoyers
1
0.31%
1
1.96%
Total
322
100.00%
51
100.00%



void __noreturn do_task_dead(void)
{
	/*
         * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
         * when the following two conditions become true.
         *   - There is race condition of mmap_sem (It is acquired by
         *     exit_mm()), and
         *   - SMI occurs before setting TASK_RUNINNG.
         *     (or hypervisor of virtual machine switches to other guest)
         *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
         *
         * To avoid it, we have to wait for releasing tsk->pi_lock which
         * is held by try_to_wake_up()
         */
	raw_spin_lock_irq(&current->pi_lock);
	raw_spin_unlock_irq(&current->pi_lock);

	/* Causes final put_task_struct in finish_task_switch(): */
	__set_current_state(TASK_DEAD);

	/* Tell freezer to ignore us: */
	current->flags |= PF_NOFREEZE;

	__schedule(false);
	BUG();

	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
	for (;;)
		cpu_relax();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
37
67.27%
3
37.50%
Paul E. McKenney
8
14.55%
1
12.50%
Dario Faggioli
4
7.27%
1
12.50%
Ingo Molnar
3
5.45%
1
12.50%
Dongsheng Yang
2
3.64%
1
12.50%
Peter Williams
1
1.82%
1
12.50%
Total
55
100.00%
8
100.00%



static inline void sched_submit_work(struct task_struct *tsk)
{
	if (!tsk->state || tsk_is_pi_blocked(tsk))
		return;
	/*
         * If we are going to sleep and we have plugged IO queued,
         * make sure to submit it to avoid deadlocks.
         */
	if (blk_needs_flush_plug(tsk))
		blk_schedule_flush_plug(tsk);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
15
39.47%
1
11.11%
Dario Faggioli
13
34.21%
1
11.11%
Paul E. McKenney
3
7.89%
2
22.22%
Linus Torvalds
3
7.89%
1
11.11%
Andrew Morton
1
2.63%
1
11.11%
Rick Lindsley
1
2.63%
1
11.11%
Ingo Molnar
1
2.63%
1
11.11%
Rusty Russell
1
2.63%
1
11.11%
Total
38
100.00%
9
100.00%



asmlinkage __visible void __sched schedule(void)
{
	struct task_struct *tsk = current;

	sched_submit_work(tsk);
	do {
		preempt_disable();
		__schedule(false);
		sched_preempt_enable_no_resched();
	} while (need_resched());
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
33
78.57%
3
42.86%
Thomas Gleixner
5
11.90%
1
14.29%
Dario Faggioli
2
4.76%
1
14.29%
Wanpeng Li
1
2.38%
1
14.29%
Rusty Russell
1
2.38%
1
14.29%
Total
42
100.00%
7
100.00%


EXPORT_SYMBOL(schedule);

/*
 * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
 * state (have scheduled out non-voluntarily) by making sure that all
 * tasks have either left the run queue or have gone into user space.
 * As idle tasks do not do either, they must not ever be preempted
 * (schedule out non-voluntarily).
 *
 * schedule_idle() is similar to schedule_preempt_disable() except that it
 * never enables preemption because it does not call sched_submit_work().
 */


void __sched schedule_idle(void)
{
	/*
         * As this skips calling sched_submit_work(), which the idle task does
         * regardless because that function is a nop when the task is in a
         * TASK_RUNNING state, make sure this isn't used someplace that the
         * current task can be in any other state. Note, idle is always in the
         * TASK_RUNNING state.
         */
	WARN_ON_ONCE(current->state);
	do {
		__schedule(false);
	} while (need_resched());
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Steven Rostedt
21
70.00%
2
33.33%
Dario Faggioli
4
13.33%
2
33.33%
Peter Zijlstra
3
10.00%
1
16.67%
Tejun Heo
2
6.67%
1
16.67%
Total
30
100.00%
6
100.00%

#ifdef CONFIG_CONTEXT_TRACKING


asmlinkage __visible void __sched schedule_user(void)
{
	/*
         * If we come here after a random call to set_need_resched(),
         * or we have been woken up remotely but the IPI has not yet arrived,
         * we haven't yet exited the RCU idle mode. Do it here manually until
         * we find a better solution.
         *
         * NB: There are buggy callers of this function.  Ideally we
         * should warn if prev_state != CONTEXT_USER, but that will trigger
         * too frequently to make sense yet.
         */
	enum ctx_state prev_state = exception_enter();
	schedule();
	exception_exit(prev_state);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
16
61.54%
1
25.00%
Tejun Heo
4
15.38%
1
25.00%
Dario Faggioli
4
15.38%
1
25.00%
Keith Owens
2
7.69%
1
25.00%
Total
26
100.00%
4
100.00%

#endif

/**
 * schedule_preempt_disabled - called with preemption disabled
 *
 * Returns with preemption disabled. Note: preempt_count must be 1
 */


void __sched schedule_preempt_disabled(void)
{
	sched_preempt_enable_no_resched();
	schedule();
	preempt_disable();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
13
76.47%
1
33.33%
Tejun Heo
3
17.65%
1
33.33%
Dario Faggioli
1
5.88%
1
33.33%
Total
17
100.00%
3
100.00%



static void __sched notrace preempt_schedule_common(void)
{
	do {
		/*
                 * Because the function tracer can trace preempt_count_sub()
                 * and it also uses preempt_enable/disable_notrace(), if
                 * NEED_RESCHED is set, the preempt_enable_notrace() called
                 * by the function tracer will call this function again and
                 * cause infinite recursion.
                 *
                 * Preemption must be disabled here before the function
                 * tracer can trace. Break up preempt_disable() into two
                 * calls. One to disable preemption without fear of being
                 * traced. The other to still record the preemption latency,
                 * which can also be traced by the function tracer.
                 */
		preempt_disable_notrace();
		preempt_latency_start(1);
		__schedule(true);
		preempt_latency_stop(1);
		preempt_enable_no_resched_notrace();

		/*
                 * Check again in case we missed a preemption opportunity
                 * between schedule and now.
                 */
	} while (need_resched());
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
22
52.38%
4
40.00%
Dario Faggioli
10
23.81%
1
10.00%
Steven Rostedt
5
11.90%
1
10.00%
Brian Silverman
2
4.76%
1
10.00%
David Chinner
1
2.38%
1
10.00%
Rick Lindsley
1
2.38%
1
10.00%
Lennart Poettering
1
2.38%
1
10.00%
Total
42
100.00%
10
100.00%

#ifdef CONFIG_PREEMPT
/*
 * this is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable. Kernel preemptions off return from interrupt
 * occur there and call schedule directly.
 */


asmlinkage __visible void __sched notrace preempt_schedule(void)
{
	/*
         * If there is a non-zero preempt_count or interrupts are disabled,
         * we do not want to preempt the current task. Just return..
         */
	if (likely(!preemptible()))
		return;

	preempt_schedule_common();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
21
84.00%
2
50.00%
Dario Faggioli
3
12.00%
1
25.00%
Linus Torvalds
1
4.00%
1
25.00%
Total
25
100.00%
4
100.00%


NOKPROBE_SYMBOL(preempt_schedule);

EXPORT_SYMBOL(preempt_schedule);

/**
 * preempt_schedule_notrace - preempt_schedule called by tracing
 *
 * The tracing infrastructure uses preempt_enable_notrace to prevent
 * recursion and tracing preempt enabling caused by the tracing
 * infrastructure itself. But as tracing can happen in areas coming
 * from userspace or just about to enter userspace, a preempt enable
 * can occur before user_exit() is called. This will cause the scheduler
 * to be called when the system is still in usermode.
 *
 * To prevent this, the preempt_enable_notrace will use this function
 * instead of preempt_schedule() to exit user context if needed before
 * calling the scheduler.
 */


asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
{
	enum ctx_state prev_ctx;

	if (likely(!preemptible()))
		return;

	do {
		/*
                 * Because the function tracer can trace preempt_count_sub()
                 * and it also uses preempt_enable/disable_notrace(), if
                 * NEED_RESCHED is set, the preempt_enable_notrace() called
                 * by the function tracer will call this function again and
                 * cause infinite recursion.
                 *
                 * Preemption must be disabled here before the function
                 * tracer can trace. Break up preempt_disable() into two
                 * calls. One to disable preemption without fear of being
                 * traced. The other to still record the preemption latency,
                 * which can also be traced by the function tracer.
                 */
		preempt_disable_notrace();
		preempt_latency_start(1);
		/*
                 * Needs preempt disabled in case user_exit() is traced
                 * and the tracer calls preempt_enable_notrace() causing
                 * an infinite recursion.
                 */
		prev_ctx = exception_enter();
		__schedule(true);
		exception_exit(prev_ctx);

		preempt_latency_stop(1);
		preempt_enable_no_resched_notrace();
	} while (need_resched());
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
39
58.21%
4
50.00%
Steven Rostedt
19
28.36%
2
25.00%
Dario Faggioli
7
10.45%
1
12.50%
Thomas Gleixner
2
2.99%
1
12.50%
Total
67
100.00%
8
100.00%


EXPORT_SYMBOL_GPL(preempt_schedule_notrace);

#endif /* CONFIG_PREEMPT */

/*
 * this is the entry point to schedule() from kernel preemption
 * off of irq context.
 * Note, that this is called and return with irqs disabled. This will
 * protect us against recursive calling from irq.
 */


asmlinkage __visible void __sched preempt_schedule_irq(void)
{
	enum ctx_state prev_state;

	/* Catch callers which need to be fixed */
	BUG_ON(preempt_count() || !irqs_disabled());

	prev_state = exception_enter();

	do {
		preempt_disable();
		local_irq_enable();
		__schedule(true);
		local_irq_disable();
		sched_preempt_enable_no_resched();
	} while (need_resched());

	exception_exit(prev_state);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
48
78.69%
3
37.50%
Dario Faggioli
7
11.48%
1
12.50%
Steven Rostedt
2
3.28%
1
12.50%
Wanpeng Li
2
3.28%
1
12.50%
Rusty Russell
1
1.64%
1
12.50%
Rick Lindsley
1
1.64%
1
12.50%
Total
61
100.00%
8
100.00%



int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
			  void *key)
{
	return try_to_wake_up(curr->private, mode, wake_flags);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
14
45.16%
1
12.50%
Dario Faggioli
12
38.71%
3
37.50%
Linus Torvalds
2
6.45%
1
12.50%
Steven Rostedt
1
3.23%
1
12.50%
Robert Love
1
3.23%
1
12.50%
Ingo Molnar
1
3.23%
1
12.50%
Total
31
100.00%
8
100.00%


EXPORT_SYMBOL(default_wake_function);

#ifdef CONFIG_RT_MUTEXES



static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
{
	if (pi_task)
		prio = min(prio, pi_task->prio);

	return prio;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
32
96.97%
1
50.00%
Dario Faggioli
1
3.03%
1
50.00%
Total
33
100.00%
2
100.00%



static inline int rt_effective_prio(struct task_struct *p, int prio)
{
	struct task_struct *pi_task = rt_mutex_get_top_task(p);

	return __rt_effective_prio(pi_task, prio);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
33
100.00%
1
100.00%
Total
33
100.00%
1
100.00%

/*
 * rt_mutex_setprio - set the current priority of a task
 * @p: task to boost
 * @pi_task: donor task
 *
 * This function changes the 'effective' priority of a task. It does
 * not touch ->normal_prio like __setscheduler().
 *
 * Used by the rt_mutex code to implement priority inheritance
 * logic. Call site only calls if the priority of the task changed.
 */


void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
	int prio, oldprio, queued, running, queue_flag =
		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
	const struct sched_class *prev_class;
	struct rq_flags rf;
	struct rq *rq;

	/* XXX used to be waiter->prio, not waiter->task->prio */
	prio = __rt_effective_prio(pi_task, p->normal_prio);

	/*
         * If nothing changed; bail early.
         */
	if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
		return;

	rq = __task_rq_lock(p, &rf);
	update_rq_clock(rq);
	/*
         * Set under pi_lock && rq->lock, such that the value can be used under
         * either lock.
         *
         * Note that there is loads of tricky to make this pointer cache work
         * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
         * ensure a task is de-boosted (pi_task is set to NULL) before the
         * task is allowed to run again (and can exit). This ensures the pointer
         * points to a blocked task -- which guaratees the task is present.
         */
	p->pi_top_task = pi_task;

	/*
         * For FIFO/RR we only need to set prio, if that matches we're done.
         */
	if (prio == p->prio && !dl_prio(prio))
		goto out_unlock;

	/*
         * Idle task boosting is a nono in general. There is one
         * exception, when PREEMPT_RT and NOHZ is active:
         *
         * The idle task calls get_next_timer_interrupt() and holds
         * the timer wheel base->lock on the CPU and another CPU wants
         * to access the timer (probably to cancel it). We can safely
         * ignore the boosting request, as the idle CPU runs this code
         * with interrupts disabled and will complete the lock
         * protected section without being interrupted. So there is no
         * real need to boost.
         */
	if (unlikely(p == rq->idle)) {
		WARN_ON(p != rq->curr);
		WARN_ON(p->pi_blocked_on);
		goto out_unlock;
	}

	trace_sched_pi_setprio(p, pi_task);
	oldprio = p->prio;

	if (oldprio == prio)
		queue_flag &= ~DEQUEUE_MOVE;

	prev_class = p->sched_class;
	queued = task_on_rq_queued(p);
	running = task_current(rq, p);
	if (queued)
		dequeue_task(rq, p, queue_flag);
	if (running)
		put_prev_task(rq, p);

	/*
         * Boosting condition are:
         * 1. -rt task is running and holds mutex A
         *      --> -dl task blocks on mutex A
         *
         * 2. -dl task is running and holds mutex A
         *      --> -dl task blocks on mutex A and could preempt the
         *          running task
         */
	if (dl_prio(prio)) {
		if (!dl_prio(p->normal_prio) ||
		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
			p->dl.dl_boosted = 1;
			queue_flag |= ENQUEUE_REPLENISH;
		} else
			p->dl.dl_boosted = 0;
		p->sched_class = &dl_sched_class;
	} else if (rt_prio(prio)) {
		if (dl_prio(oldprio))
			p->dl.dl_boosted = 0;
		if (oldprio < prio)
			queue_flag |= ENQUEUE_HEAD;
		p->sched_class = &rt_sched_class;
	} else {
		if (dl_prio(oldprio))
			p->dl.dl_boosted = 0;
		if (rt_prio(oldprio))
			p->rt.timeout = 0;
		p->sched_class = &fair_sched_class;
	}

	p->prio = prio;

	if (queued)
		enqueue_task(rq, p, queue_flag);
	if (running)
		set_curr_task(rq, p);

	check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
	/* Avoid rq from going away on us: */
	preempt_disable();
	__task_rq_unlock(rq, &rf);

	balance_callback(rq);
	preempt_enable();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
267
61.24%
13
34.21%
Dario Faggioli
100
22.94%
2
5.26%
Thomas Gleixner
16
3.67%
2
5.26%
Vincent Guittot
8
1.83%
1
2.63%
Chris Wright
7
1.61%
1
2.63%
Steven Rostedt
6
1.38%
2
5.26%
Linus Torvalds
5
1.15%
1
2.63%
Heiko Carstens
4
0.92%
1
2.63%
Dean Nelson
4
0.92%
1
2.63%
Kirill Tkhai
3
0.69%
1
2.63%
Srivatsa Vaddagiri
3
0.69%
1
2.63%
Ingo Molnar
2
0.46%
2
5.26%
Juri Lelli
2
0.46%
1
2.63%
Linus Torvalds (pre-git)
2
0.46%
2
5.26%
Namhyung Kim
1
0.23%
1
2.63%
Darren Hart
1
0.23%
1
2.63%
Con Kolivas
1
0.23%
1
2.63%
Oleg Nesterov
1
0.23%
1
2.63%
Olivier Croquette
1
0.23%
1
2.63%
Jens Axboe
1
0.23%
1
2.63%
Rusty Russell
1
0.23%
1
2.63%
Total
436
100.00%
38
100.00%

#else


static inline int rt_effective_prio(struct task_struct *p, int prio)
{
	return prio;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
18
100.00%
1
100.00%
Total
18
100.00%
1
100.00%

#endif



void set_user_nice(struct task_struct *p, long nice)
{
	bool queued, running;
	int old_prio, delta;
	struct rq_flags rf;
	struct rq *rq;

	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
		return;
	/*
         * We have to be careful, if called from sys_setpriority(),
         * the task might be in the middle of scheduling on another CPU.
         */
	rq = task_rq_lock(p, &rf);
	update_rq_clock(rq);

	/*
         * The RT priorities are set via sched_setscheduler(), but we still
         * allow the 'normal' nice value to be set - but as expected
         * it wont have any effect on scheduling until the task is
         * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
         */
	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		goto out_unlock;
	}
	queued = task_on_rq_queued(p);
	running = task_current(rq, p);
	if (queued)
		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
	if (running)
		put_prev_task(rq, p);

	p->static_prio = NICE_TO_PRIO(nice);
	set_load_weight(p, true);
	old_prio = p->prio;
	p->prio = effective_prio(p);
	delta = p->prio - old_prio;

	if (queued) {
		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
		/*
                 * If the task increased its priority or is running and
                 * lowered its priority, then reschedule its CPU:
                 */
		if (delta < 0 || (delta > 0 && task_running(rq, p)))
			resched_curr(rq);
	}
	if (running)
		set_curr_task(rq, p);
out_unlock:
	task_rq_unlock(rq, p, &rf);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
167
69.87%
11
50.00%
Dario Faggioli
56
23.43%
2
9.09%
Ingo Molnar
3
1.26%
1
4.55%
Andrew Morton
3
1.26%
1
4.55%
Rusty Russell
3
1.26%
2
9.09%
Chris Wright
2
0.84%
1
4.55%
Linus Torvalds (pre-git)
2
0.84%
2
9.09%
Vincent Guittot
2
0.84%
1
4.55%
Srivatsa Vaddagiri
1
0.42%
1
4.55%
Total
239
100.00%
22
100.00%


EXPORT_SYMBOL(set_user_nice);

/*
 * can_nice - check if a task can reduce its nice value
 * @p: task
 * @nice: nice value
 */


int can_nice(const struct task_struct *p, const int nice)
{
	/* Convert nice value [19,-20] to rlimit style value [1,40]: */
	int nice_rlim = nice_to_rlimit(nice);

	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
		capable(CAP_SYS_NICE));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
25
60.98%
2
40.00%
Dario Faggioli
13
31.71%
1
20.00%
Dean Nelson
2
4.88%
1
20.00%
Ingo Molnar
1
2.44%
1
20.00%
Total
41
100.00%
5
100.00%

#ifdef __ARCH_WANT_SYS_NICE

/*
 * sys_nice - change the priority of the current process.
 * @increment: priority increment
 *
 * sys_setpriority is a more generic, but much slower function that
 * does similar things.
 */

SYSCALL_DEFINE1(nice, int, increment)
{
	long nice, retval;

	/*
         * Setpriority might change our priority at the same moment.
         * We don't have to worry. Conceptually one call occurs first
         * and we have a single winner.
         */
	increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
	nice = task_nice(current) + increment;

	nice = clamp_val(nice, MIN_NICE, MAX_NICE);
	if (increment < 0 && !can_nice(current, nice))
		return -EPERM;

	retval = security_task_setnice(current, nice);
	if (retval)
		return retval;

	set_user_nice(current, nice);
	return 0;
}

#endif

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * Return: The priority value as seen by users in /proc.
 * RT tasks are offset by -200. Normal tasks are centered
 * around 0, value goes from -16 to +15.
 */


int task_prio(const struct task_struct *p)
{
	return p->prio - MAX_RT_PRIO;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
9
50.00%
1
25.00%
Dario Faggioli
5
27.78%
1
25.00%
Thomas Gleixner
3
16.67%
1
25.00%
Linus Torvalds (pre-git)
1
5.56%
1
25.00%
Total
18
100.00%
4
100.00%

/**
 * idle_cpu - is a given CPU idle currently?
 * @cpu: the processor in question.
 *
 * Return: 1 if the CPU is currently idle. 0 otherwise.
 */


int idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (rq->curr != rq->idle)
		return 0;

	if (rq->nr_running)
		return 0;

#ifdef CONFIG_SMP
	if (!llist_empty(&rq->wake_list))
		return 0;
#endif

	return 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
32
51.61%
1
20.00%
Dario Faggioli
21
33.87%
2
40.00%
Thomas Gleixner
8
12.90%
1
20.00%
Dean Nelson
1
1.61%
1
20.00%
Total
62
100.00%
5
100.00%

/**
 * idle_task - return the idle task for a given CPU.
 * @cpu: the processor in question.
 *
 * Return: The idle task for the CPU @cpu.
 */


struct task_struct *idle_task(int cpu)
{
	return cpu_rq(cpu)->idle;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
13
72.22%
1
33.33%
Dario Faggioli
3
16.67%
1
33.33%
Kirill Tkhai
2
11.11%
1
33.33%
Total
18
100.00%
3
100.00%

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 *
 * The task of @pid, if found. %NULL otherwise.
 */


static struct task_struct *find_process_by_pid(pid_t pid)
{
	return pid ? find_task_by_vpid(pid) : current;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
19
90.48%
1
50.00%
Dario Faggioli
2
9.52%
1
50.00%
Total
21
100.00%
2
100.00%

/*
 * sched_setparam() passes in -1 for its policy, to let the functions
 * it calls know not to change it.
 */

#define SETPARAM_POLICY	-1



static void __setscheduler_params(struct task_struct *p,
		const struct sched_attr *attr)
{
	int policy = attr->sched_policy;

	if (policy == SETPARAM_POLICY)
		policy = p->policy;

	p->policy = policy;

	if (dl_policy(policy))
		__setparam_dl(p, attr);
	else if (fair_policy(policy))
		p->static_prio = NICE_TO_PRIO(attr->sched_nice);

	/*
         * __sched_setscheduler() ensures attr->sched_priority == 0 when
         * !rt_policy. Always setting this ensures that things like
         * getparam()/getattr() don't report silly values for !rt tasks.
         */
	p->rt_priority = attr->sched_priority;
	p->normal_prio = normal_prio(p);
	set_load_weight(p, true);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
63
63.00%
1
14.29%
Dario Faggioli
26
26.00%
2
28.57%
Thomas Gleixner
7
7.00%
2
28.57%
Vincent Guittot
2
2.00%
1
14.29%
Henrik Austad
2
2.00%
1
14.29%
Total
100
100.00%
7
100.00%

/* Actually do priority change: must hold pi & rq lock. */


static void __setscheduler(struct rq *rq, struct task_struct *p,
			   const struct sched_attr *attr, bool keep_boost)
{
	__setscheduler_params(p, attr);

	/*
         * Keep a potential priority boosting if called from
         * sched_setscheduler().
         */
	p->prio = normal_prio(p);
	if (keep_boost)
		p->prio = rt_effective_prio(p, p->prio);

	if (dl_prio(p->prio))
		p->sched_class = &dl_sched_class;
	else if (rt_prio(p->prio))
		p->sched_class = &rt_sched_class;
	else
		p->sched_class = &fair_sched_class;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
83
83.00%
4
50.00%
Dario Faggioli
14
14.00%
2
25.00%
Thomas Gleixner
2
2.00%
1
12.50%
Heiko Carstens
1
1.00%
1
12.50%
Total
100
100.00%
8
100.00%

/*
 * Check the target process has a UID that matches the current process's:
 */


static bool check_same_owner(struct task_struct *p)
{
	const struct cred *cred = current_cred(), *pcred;
	bool match;

	rcu_read_lock();
	pcred = __task_cred(p);
	match = (uid_eq(cred->euid, pcred->euid) ||
		 uid_eq(cred->euid, pcred->uid));
	rcu_read_unlock();
	return match;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
57
83.82%
2
50.00%
Dario Faggioli
11
16.18%
2
50.00%
Total
68
100.00%
4
100.00%



static int __sched_setscheduler(struct task_struct *p,
				const struct sched_attr *attr,
				bool user, bool pi)
{
	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
		      MAX_RT_PRIO - 1 - attr->sched_priority;
	int retval, oldprio, oldpolicy = -1, queued, running;
	int new_effective_prio, policy = attr->sched_policy;
	const struct sched_class *prev_class;
	struct rq_flags rf;
	int reset_on_fork;
	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
	struct rq *rq;

	/* The pi code expects interrupts enabled */
	BUG_ON(pi && in_interrupt());
recheck:
	/* Double check policy once rq lock held: */
	if (policy < 0) {
		reset_on_fork = p->sched_reset_on_fork;
		policy = oldpolicy = p->policy;
	} else {
		reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);

		if (!valid_policy(policy))
			return -EINVAL;
	}

	if (attr->sched_flags &
		~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
		return -EINVAL;

	/*
         * Valid priorities for SCHED_FIFO and SCHED_RR are
         * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
         * SCHED_BATCH and SCHED_IDLE is 0.
         */
	if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
		return -EINVAL;
	if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
	    (rt_policy(policy) != (attr->sched_priority != 0)))
		return -EINVAL;

	/*
         * Allow unprivileged RT tasks to decrease priority:
         */
	if (user && !capable(CAP_SYS_NICE)) {
		if (fair_policy(policy)) {
			if (attr->sched_nice < task_nice(p) &&
			    !can_nice(p, attr->sched_nice))
				return -EPERM;
		}

		if (rt_policy(policy)) {
			unsigned long rlim_rtprio =
					task_rlimit(p, RLIMIT_RTPRIO);

			/* Can't set/change the rt policy: */
			if (policy != p->policy && !rlim_rtprio)
				return -EPERM;

			/* Can't increase priority: */
			if (attr->sched_priority > p->rt_priority &&
			    attr->sched_priority > rlim_rtprio)
				return -EPERM;
		}

		 /*
                  * Can't set/change SCHED_DEADLINE policy at all for now
                  * (safest behavior); in the future we would like to allow
                  * unprivileged DL tasks to increase their relative deadline
                  * or reduce their runtime (both ways reducing utilization)
                  */
		if (dl_policy(policy))
			return -EPERM;

		/*
                 * Treat SCHED_IDLE as nice 20. Only allow a switch to
                 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
                 */
		if (idle_policy(p->policy) && !idle_policy(policy)) {
			if (!can_nice(p, task_nice(p)))
				return -EPERM;
		}

		/* Can't change other user's priorities: */
		if (!check_same_owner(p))
			return -EPERM;

		/* Normal users shall not reset the sched_reset_on_fork flag: */
		if (p->sched_reset_on_fork && !reset_on_fork)
			return -EPERM;
	}

	if (user) {
		retval = security_task_setscheduler(p);
		if (retval)
			return retval;
	}

	/*
         * Make sure no PI-waiters arrive (or leave) while we are
         * changing the priority of the task:
         *
         * To be able to change p->policy safely, the appropriate
         * runqueue lock must be held.
         */
	rq = task_rq_lock(p, &rf);
	update_rq_clock(rq);

	/*
         * Changing the policy of the stop threads its a very bad idea:
         */
	if (p == rq->stop) {
		task_rq_unlock(rq, p, &rf);
		return -EINVAL;
	}

	/*
         * If not changing anything there's no need to proceed further,
         * but store a possible modification of reset_on_fork.
         */
	if (unlikely(policy == p->policy)) {
		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
			goto change;
		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
			goto change;
		if (dl_policy(policy) && dl_param_changed(p, attr))
			goto change;

		p->sched_reset_on_fork = reset_on_fork;
		task_rq_unlock(rq, p, &rf);
		return 0;
	}
change:

	if (user) {
#ifdef CONFIG_RT_GROUP_SCHED
		/*
                 * Do not allow realtime tasks into groups that have no runtime
                 * assigned.
                 */
		if (rt_bandwidth_enabled() && rt_policy(policy) &&
				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
				!task_group_is_autogroup(task_group(p))) {
			task_rq_unlock(rq, p, &rf);
			return -EPERM;
		}
#endif
#ifdef CONFIG_SMP
		if (dl_bandwidth_enabled() && dl_policy(policy)) {
			cpumask_t *span = rq->rd->span;

			/*
                         * Don't allow tasks with an affinity mask smaller than
                         * the entire root_domain to become SCHED_DEADLINE. We
                         * will also fail if there's no bandwidth available.
                         */
			if (!cpumask_subset(span, &p->cpus_allowed) ||
			    rq->rd->dl_bw.bw == 0) {
				task_rq_unlock(rq, p, &rf);
				return -EPERM;
			}
		}
#endif
	}

	/* Re-check policy now with rq lock held: */
	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
		policy = oldpolicy = -1;
		task_rq_unlock(rq, p, &rf);
		goto recheck;
	}

	/*
         * If setscheduling to SCHED_DEADLINE (or changing the parameters
         * of a SCHED_DEADLINE task) we need to check if enough bandwidth
         * is available.
         */
	if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
		task_rq_unlock(rq, p, &rf);
		return -EBUSY;
	}

	p->sched_reset_on_fork = reset_on_fork;
	oldprio = p->prio;

	if (pi) {
		/*
                 * Take priority boosted tasks into account. If the new
                 * effective priority is unchanged, we just store the new
                 * normal parameters and do not touch the scheduler class and
                 * the runqueue. This will be done when the task deboost
                 * itself.
                 */
		new_effective_prio = rt_effective_prio(p, newprio);
		if (new_effective_prio == oldprio)
			queue_flags &= ~DEQUEUE_MOVE;
	}

	queued = task_on_rq_queued(p);
	running = task_current(rq, p);
	if (queued)
		dequeue_task(rq, p, queue_flags);
	if (running)
		put_prev_task(rq, p);

	prev_class = p->sched_class;
	__setscheduler(rq, p, attr, pi);

	if (queued) {
		/*
                 * We enqueue to tail when the priority of a task is
                 * increased (user space view).
                 */
		if (oldprio < p->prio)
			queue_flags |= ENQUEUE_HEAD;

		enqueue_task(rq, p, queue_flags);
	}
	if (running)
		set_curr_task(rq, p);

	check_class_changed(rq, p, prev_class, oldprio);

	/* Avoid rq from going away on us: */
	preempt_disable();
	task_rq_unlock(rq, p, &rf);

	if (pi)
		rt_mutex_adjust_pi(p);

	/* Run balance callbacks after we've adjusted the PI chain: */
	balance_callback(rq);
	preempt_enable();

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
634
66.32%
13
21.67%
Dario Faggioli
198
20.71%
4
6.67%
Ingo Molnar
17
1.78%
7
11.67%
Linus Torvalds (pre-git)
14
1.46%
2
3.33%
Henrik Austad
9
0.94%
1
1.67%
Vincent Guittot
9
0.94%
1
1.67%
Linus Torvalds
8
0.84%
2
3.33%
Andrew Morton
6
0.63%
3
5.00%
Anton Blanchard
6
0.63%
1
1.67%
Greg Kroah-Hartman
6
0.63%
2
3.33%
Rick Lindsley
5
0.52%
1
1.67%
Thomas Gleixner
4
0.42%
2
3.33%
Heiko Carstens
4
0.42%
1
1.67%
Robert Love
4
0.42%
1
1.67%
David P. Quigley
4
0.42%
1
1.67%
Paul Jackson
3
0.31%
1
1.67%
Steven Rostedt
3
0.31%
1
1.67%
Rusty Russell
3
0.31%
2
3.33%
Arjan van de Ven
2
0.21%
1
1.67%
Luca Abeni
2
0.21%
1
1.67%
Con Kolivas
2
0.21%
1
1.67%
Motohiro Kosaki
2
0.21%
1
1.67%
Oleg Nesterov
2
0.21%
2
3.33%
Andi Kleen
2
0.21%
1
1.67%
Mike Galbraith
1
0.10%
1
1.67%
David Howells
1
0.10%
1
1.67%
Yong Zhang
1
0.10%
1
1.67%
Nico Pitre
1
0.10%
1
1.67%
Christian Ehrhardt
1
0.10%
1
1.67%
Jens Axboe
1
0.10%
1
1.67%
Olivier Croquette
1
0.10%
1
1.67%
Total
956
100.00%
60
100.00%



static int _sched_setscheduler(struct task_struct *p, int policy,
			       const struct sched_param *param, bool check)
{
	struct sched_attr attr = {
		.sched_policy   = policy,
		.sched_priority = param->sched_priority,
		.sched_nice	= PRIO_TO_NICE(p->static_prio),
        };

	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
		policy &= ~SCHED_RESET_ON_FORK;
		attr.sched_policy = policy;
	}

	return __sched_setscheduler(p, &attr, check, true);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
82
83.67%
2
20.00%
Dario Faggioli
7
7.14%
2
20.00%
Linus Torvalds (pre-git)
6
6.12%
3
30.00%
Richard Weinberger
1
1.02%
1
10.00%
Mike Galbraith
1
1.02%
1
10.00%
Ingo Molnar
1
1.02%
1
10.00%
Total
98
100.00%
10
100.00%

/**
 * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Return: 0 on success. An error code otherwise.
 *
 * NOTE that the task may be already dead.
 */


int sched_setscheduler(struct task_struct *p, int policy,
		       const struct sched_param *param)
{
	return _sched_setscheduler(p, policy, param, true);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
21
67.74%
1
16.67%
Anton Blanchard
3
9.68%
1
16.67%
Dario Faggioli
3
9.68%
1
16.67%
Ingo Molnar
2
6.45%
1
16.67%
Andrew Morton
1
3.23%
1
16.67%
Matt Mackall
1
3.23%
1
16.67%
Total
31
100.00%
6
100.00%


EXPORT_SYMBOL_GPL(sched_setscheduler);



int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
{
	return __sched_setscheduler(p, attr, true, true);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
20
71.43%
2
40.00%
Dario Faggioli
5
17.86%
1
20.00%
Dean Nelson
2
7.14%
1
20.00%
Anton Blanchard
1
3.57%
1
20.00%
Total
28
100.00%
5
100.00%


EXPORT_SYMBOL_GPL(sched_setattr);

/**
 * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Just like sched_setscheduler, only don't bother checking if the
 * current context has permission.  For example, this is needed in
 * stop_machine(): we create temporary high priority worker threads,
 * but our caller might not have that capability.
 *
 * Return: 0 on success. An error code otherwise.
 */


int sched_setscheduler_nocheck(struct task_struct *p, int policy,
			       const struct sched_param *param)
{
	return _sched_setscheduler(p, policy, param, false);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
27
87.10%
2
33.33%
Jens Axboe
1
3.23%
1
16.67%
Greg Kroah-Hartman
1
3.23%
1
16.67%
Andrew Morton
1
3.23%
1
16.67%
Dario Faggioli
1
3.23%
1
16.67%
Total
31
100.00%
6
100.00%


EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);


static int

do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
	struct sched_param lparam;
	struct task_struct *p;
	int retval;

	if (!param || pid < 0)
		return -EINVAL;
	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
		return -EFAULT;

	rcu_read_lock();
	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (p != NULL)
		retval = sched_setscheduler(p, policy, &lparam);
	rcu_read_unlock();

	return retval;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
48
47.06%
1
6.25%
Dario Faggioli
29
28.43%
1
6.25%
Greg Kroah-Hartman
6
5.88%
2
12.50%
Anton Blanchard
4
3.92%
1
6.25%
Andrew Morton
4
3.92%
2
12.50%
Rusty Russell
2
1.96%
1
6.25%
Rick Lindsley
2
1.96%
1
6.25%
Eric Paris
1
0.98%
1
6.25%
Eric W. Biedermann
1
0.98%
1
6.25%
Linus Torvalds (pre-git)
1
0.98%
1
6.25%
Christian Bornträger
1
0.98%
1
6.25%
David Howells
1
0.98%
1
6.25%
Mike Galbraith
1
0.98%
1
6.25%
Thomas Gleixner
1
0.98%
1
6.25%
Total
102
100.00%
16
100.00%

/*
 * Mimics kernel/events/core.c perf_copy_attr().
 */


static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
{
	u32 size;
	int ret;

	if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
		return -EFAULT;

	/* Zero the full structure, so that a short copy will be nice: */
	memset(attr, 0, sizeof(*attr));

	ret = get_user(size, &uattr->size);
	if (ret)
		return ret;

	/* Bail out on silly large: */
	if (size > PAGE_SIZE)
		goto err_size;

	/* ABI compatibility quirk: */
	if (!size)
		size = SCHED_ATTR_SIZE_VER0;

	if (size < SCHED_ATTR_SIZE_VER0)
		goto err_size;

	/*
         * If we're handed a bigger struct than we know of,
         * ensure all the unknown bits are 0 - i.e. new
         * user-space does not rely on any kernel feature
         * extensions we dont know about yet.
         */
	if (size > sizeof(*attr)) {
		unsigned char __user *addr;
		unsigned char __user *end;
		unsigned char val;

		addr = (void __user *)uattr + sizeof(*attr);
		end  = (void __user *)uattr + size;

		for (; addr < end; addr++) {
			ret = get_user(val, addr);
			if (ret)
				return ret;
			if (val)
				goto err_size;
		}
		size = sizeof(*attr);
	}

	ret = copy_from_user(attr, uattr, size);
	if (ret)
		return -EFAULT;

	/*
         * XXX: Do we want to be lenient like existing syscalls; or do we want
         * to be strict and return an error on out-of-bounds values?
         */
	attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);

	return 0;

err_size:
	put_user(sizeof(*attr), &uattr->size);
	return -E2BIG;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
120
46.69%
4
17.39%
Dario Faggioli
89
34.63%
1
4.35%
Ingo Molnar
10
3.89%
3
13.04%
Mike Galbraith
8
3.11%
1
4.35%
Linus Torvalds (pre-git)
7
2.72%
4
17.39%
Andi Kleen
6
2.33%
1
4.35%
Rusty Russell
5
1.95%
2
8.70%
Andrew Morton
4
1.56%
2
8.70%
Michael Kerrisk
3
1.17%
1
4.35%
Anton Blanchard
2
0.78%
1
4.35%
Thomas Gleixner
1
0.39%
1
4.35%
Robert Love
1
0.39%
1
4.35%
Vegard Nossum
1
0.39%
1
4.35%
Total
257
100.00%
23
100.00%

/**
 * sys_sched_setscheduler - set/change the scheduler policy and RT priority
 * @pid: the pid in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Return: 0 on success. An error code otherwise.
 */

SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
{
	if (policy < 0)
		return -EINVAL;

	return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 *
 * Return: 0 on success. An error code otherwise.
 */

SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
	return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
}

/**
 * sys_sched_setattr - same as above, but with extended sched_attr
 * @pid: the pid in question.
 * @uattr: structure containing the extended parameters.
 * @flags: for future extension.
 */

SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
			       unsigned int, flags)
{
	struct sched_attr attr;
	struct task_struct *p;
	int retval;

	if (!uattr || pid < 0 || flags)
		return -EINVAL;

	retval = sched_copy_attr(uattr, &attr);
	if (retval)
		return retval;

	if ((int)attr.sched_policy < 0)
		return -EINVAL;

	rcu_read_lock();
	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (p != NULL)
		retval = sched_setattr(p, &attr);
	rcu_read_unlock();

	return retval;
}

/**
 * sys_sched_getscheduler - get the policy (scheduling class) of a thread
 * @pid: the pid in question.
 *
 * Return: On success, the policy of the thread. Otherwise, a negative error
 * code.
 */

SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
	struct task_struct *p;
	int retval;

	if (pid < 0)
		return -EINVAL;

	retval = -ESRCH;
	rcu_read_lock();
	p = find_process_by_pid(pid);
	if (p) {
		retval = security_task_getscheduler(p);
		if (!retval)
			retval = p->policy
				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
	}
	rcu_read_unlock();
	return retval;
}

/**
 * sys_sched_getparam - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 *
 * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
 * code.
 */

SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
	struct sched_param lp = { .sched_priority = 0 };
	struct task_struct *p;
	int retval;

	if (!param || pid < 0)
		return -EINVAL;

	rcu_read_lock();
	p = find_process_by_pid(pid);
	retval = -ESRCH;
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	if (task_has_rt_policy(p))
		lp.sched_priority = p->rt_priority;
	rcu_read_unlock();

	/*
         * This one might sleep, we cannot do it with a spinlock held ...
         */
	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;

	return retval;

out_unlock:
	rcu_read_unlock();
	return retval;
}



static int sched_read_attr(struct sched_attr __user *uattr,
			   struct sched_attr *attr,
			   unsigned int usize)
{
	int ret;

	if (!access_ok(VERIFY_WRITE, uattr, usize))
		return -EFAULT;

	/*
         * If we're handed a smaller struct than we know of,
         * ensure all the unknown bits are 0 - i.e. old
         * user-space does not get uncomplete information.
         */
	if (usize < sizeof(*attr)) {
		unsigned char *addr;
		unsigned char *end;

		addr = (void *)attr + usize;
		end  = (void *)attr + sizeof(*attr);

		for (; addr < end; addr++) {
			if (*addr)
				return -EFBIG;
		}

		attr->size = usize;
	}

	ret = copy_to_user(uattr, attr, attr->size);
	if (ret)
		return -EFAULT;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
99
71.74%
1
11.11%
Dario Faggioli
26
18.84%
1
11.11%
Christian Ehrhardt
3
2.17%
1
11.11%
Nicholas Piggin
3
2.17%
1
11.11%
Robert Love
3
2.17%
1
11.11%
Linus Torvalds (pre-git)
1
0.72%
1
11.11%
Thomas Gleixner
1
0.72%
1
11.11%
Heiko Carstens
1
0.72%
1
11.11%
Ingo Molnar
1
0.72%
1
11.11%
Total
138
100.00%
9
100.00%

/**
 * sys_sched_getattr - similar to sched_getparam, but with sched_attr
 * @pid: the pid in question.
 * @uattr: structure containing the extended parameters.
 * @size: sizeof(attr) for fwd/bwd comp.
 * @flags: for future extension.
 */

SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
		unsigned int, size, unsigned int, flags)
{
	struct sched_attr attr = {
		.size = sizeof(struct sched_attr),
        };
	struct task_struct *p;
	int retval;

	if (!uattr || pid < 0 || size > PAGE_SIZE ||
	    size < SCHED_ATTR_SIZE_VER0 || flags)
		return -EINVAL;

	rcu_read_lock();
	p = find_process_by_pid(pid);
	retval = -ESRCH;
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	attr.sched_policy = p->policy;
	if (p->sched_reset_on_fork)
		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
	if (task_has_dl_policy(p))
		__getparam_dl(p, &attr);
	else if (task_has_rt_policy(p))
		attr.sched_priority = p->rt_priority;
	else
		attr.sched_nice = task_nice(p);

	rcu_read_unlock();

	retval = sched_read_attr(uattr, &attr, size);
	return retval;

out_unlock:
	rcu_read_unlock();
	return retval;
}



long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
	cpumask_var_t cpus_allowed, new_mask;
	struct task_struct *p;
	int retval;

	rcu_read_lock();

	p = find_process_by_pid(pid);
	if (!p) {
		rcu_read_unlock();
		return -ESRCH;
	}

	/* Prevent p going away */
	get_task_struct(p);
	rcu_read_unlock();

	if (p->flags & PF_NO_SETAFFINITY) {
		retval = -EINVAL;
		goto out_put_task;
	}
	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
		retval = -ENOMEM;
		goto out_put_task;
	}
	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
		retval = -ENOMEM;
		goto out_free_cpus_allowed;
	}
	retval = -EPERM;
	if (!check_same_owner(p)) {
		rcu_read_lock();
		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
			rcu_read_unlock();
			goto out_free_new_mask;
		}
		rcu_read_unlock();
	}

	retval = security_task_setscheduler(p);
	if (retval)
		goto out_free_new_mask;


	cpuset_cpus_allowed(p, cpus_allowed);
	cpumask_and(new_mask, in_mask, cpus_allowed);

	/*
         * Since bandwidth control happens on root_domain basis,
         * if admission test is enabled, we only admit -deadline
         * tasks allowed to run on all the CPUs in the task's
         * root_domain.
         */
#ifdef CONFIG_SMP
	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
		rcu_read_lock();
		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
			retval = -EBUSY;
			rcu_read_unlock();
			goto out_free_new_mask;
		}
		rcu_read_unlock();
	}
#endif
again:
	retval = __set_cpus_allowed_ptr(p, new_mask, true);

	if (!retval) {
		cpuset_cpus_allowed(p, cpus_allowed);
		if (!cpumask_subset(new_mask, cpus_allowed)) {
			/*
                         * We must have raced with a concurrent cpuset
                         * update. Just reset the cpus_allowed to the
                         * cpuset's cpus_allowed
                         */
			cpumask_copy(new_mask, cpus_allowed);
			goto again;
		}
	}
out_free_new_mask:
	free_cpumask_var(new_mask);
out_free_cpus_allowed:
	free_cpumask_var(cpus_allowed);
out_put_task:
	put_task_struct(p);
	return retval;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
197
61.18%
5
13.89%
Dario Faggioli
74
22.98%
1
2.78%
Andrew Morton
10
3.11%
6
16.67%
Mike Galbraith
8
2.48%
2
5.56%
Linus Torvalds
6
1.86%
2
5.56%
Linus Torvalds (pre-git)
5
1.55%
4
11.11%
Dean Nelson
3
0.93%
1
2.78%
Ingo Molnar
3
0.93%
3
8.33%
Anton Blanchard
2
0.62%
1
2.78%
Thomas Gleixner
2
0.62%
2
5.56%
Con Kolivas
2
0.62%
1
2.78%
Rick Lindsley
2
0.62%
1
2.78%
Mel Gorman
2
0.62%
1
2.78%
Jens Axboe
1
0.31%
1
2.78%
Oleg Nesterov
1
0.31%
1
2.78%
David P. Quigley
1
0.31%
1
2.78%
Heiko Carstens
1
0.31%
1
2.78%
Paul E. McKenney
1
0.31%
1
2.78%
Robert Love
1
0.31%
1
2.78%
Total
322
100.00%
36
100.00%



static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
			     struct cpumask *new_mask)
{
	if (len < cpumask_size())
		cpumask_clear(new_mask);
	else if (len > cpumask_size())
		len = cpumask_size();

	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
36
60.00%
1
10.00%
Dario Faggioli
7
11.67%
1
10.00%
Kirill Tkhai
5
8.33%
1
10.00%
Mike Galbraith
4
6.67%
1
10.00%
Juri Lelli
3
5.00%
2
20.00%
Linus Torvalds (pre-git)
3
5.00%
2
20.00%
Oleg Nesterov
1
1.67%
1
10.00%
Andrew Morton
1
1.67%
1
10.00%
Total
60
100.00%
10
100.00%

/**
 * sys_sched_setaffinity - set the CPU affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to the new CPU mask
 *
 * Return: 0 on success. An error code otherwise.
 */

SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
		unsigned long __user *, user_mask_ptr)
{
	cpumask_var_t new_mask;
	int retval;

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
		return -ENOMEM;

	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
	if (retval == 0)
		retval = sched_setaffinity(pid, new_mask);
	free_cpumask_var(new_mask);
	return retval;
}



long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
	struct task_struct *p;
	unsigned long flags;
	int retval;

	rcu_read_lock();

	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	raw_spin_lock_irqsave(&p->pi_lock, flags);
	cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);

out_unlock:
	rcu_read_unlock();

	return retval;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
49
48.04%
1
8.33%
Dario Faggioli
25
24.51%
1
8.33%
Juri Lelli
14
13.73%
3
25.00%
Linus Torvalds (pre-git)
5
4.90%
3
25.00%
Mike Galbraith
5
4.90%
1
8.33%
Ingo Molnar
2
1.96%
1
8.33%
Kirill Tkhai
1
0.98%
1
8.33%
Neil Brown
1
0.98%
1
8.33%
Total
102
100.00%
12
100.00%

/**
 * sys_sched_getaffinity - get the CPU affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to hold the current CPU mask
 *
 * Return: size of CPU mask copied to user_mask_ptr on success. An
 * error code otherwise.
 */

SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
		unsigned long __user *, user_mask_ptr)
{
	int ret;
	cpumask_var_t mask;

	if ((len * BITS_PER_BYTE) < nr_cpu_ids)
		return -EINVAL;
	if (len & (sizeof(unsigned long)-1))
		return -EINVAL;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return -ENOMEM;

	ret = sched_getaffinity(pid, mask);
	if (ret == 0) {
		size_t retlen = min_t(size_t, len, cpumask_size());

		if (copy_to_user(user_mask_ptr, mask, retlen))
			ret = -EFAULT;
		else
			ret = retlen;
	}
	free_cpumask_var(mask);

	return ret;
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * This function yields the current CPU to other tasks. If there are no
 * other threads running on this CPU then this function will return.
 *
 * Return: 0.
 */

SYSCALL_DEFINE0(sched_yield)
{
	struct rq_flags rf;
	struct rq *rq;

	local_irq_disable();
	rq = this_rq();
	rq_lock(rq, &rf);

	schedstat_inc(rq->yld_count);
	current->sched_class->yield_task(rq);

	/*
         * Since we are going to call schedule() anyway, there's
         * no need to preempt or enable interrupts:
         */
	preempt_disable();
	rq_unlock(rq, &rf);
	sched_preempt_enable_no_resched();

	schedule();

	return 0;
}

#ifndef CONFIG_PREEMPT


int __sched _cond_resched(void)
{
	if (should_resched(0)) {
		preempt_schedule_common();
		return 1;
	}
	rcu_all_qs();
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
13
44.83%
1
20.00%
Dario Faggioli
9
31.03%
1
20.00%
Konstantin Khlebnikov
3
10.34%
1
20.00%
Paul E. McKenney
3
10.34%
1
20.00%
Andrew Morton
1
3.45%
1
20.00%
Total
29
100.00%
5
100.00%


EXPORT_SYMBOL(_cond_resched);
#endif

/*
 * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
 * call schedule, and on return reacquire the lock.
 *
 * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
 * operations here to prevent schedule() from being called twice (once via
 * spin_unlock(), once by hand).
 */


int __cond_resched_lock(spinlock_t *lock)
{
	int resched = should_resched(PREEMPT_LOCK_OFFSET);
	int ret = 0;

	lockdep_assert_held(lock);

	if (spin_needbreak(lock) || resched) {
		spin_unlock(lock);
		if (resched)
			preempt_schedule_common();
		else
			cpu_relax();
		ret = 1;
		spin_lock(lock);
	}
	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
40
60.61%
2
28.57%
Dario Faggioli
11
16.67%
1
14.29%
Kirill Tkhai
10
15.15%
1
14.29%
Mark Rutland
3
4.55%
1
14.29%
Konstantin Khlebnikov
1
1.52%
1
14.29%
Rik Van Riel
1
1.52%
1
14.29%
Total
66
100.00%
7
100.00%


EXPORT_SYMBOL(__cond_resched_lock);



int __sched __cond_resched_softirq(void)
{
	BUG_ON(!in_softirq());

	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
		local_bh_enable();
		preempt_schedule_common();
		local_bh_disable();
		return 1;
	}
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
30
76.92%
1
16.67%
Kirill Tkhai
5
12.82%
1
16.67%
Dario Faggioli
1
2.56%
1
16.67%
Andrew Morton
1
2.56%
1
16.67%
Rick Lindsley
1
2.56%
1
16.67%
Konstantin Khlebnikov
1
2.56%
1
16.67%
Total
39
100.00%
6
100.00%


EXPORT_SYMBOL(__cond_resched_softirq);

/**
 * yield - yield the current processor to other threads.
 *
 * Do not ever use this function, there's a 99% chance you're doing it wrong.
 *
 * The scheduler is at all times free to pick the calling task as the most
 * eligible task to run, if removing the yield() call from your code breaks
 * it, its already broken.
 *
 * Typical broken usage is:
 *
 * while (!event)
 *      yield();
 *
 * where one assumes that yield() will let 'the other' process run that will
 * make event true. If the current task is a SCHED_FIFO task that will never
 * happen. Never use yield() as a progress guarantee!!
 *
 * If you want to use yield() to wait for something, use wait_event().
 * If you want to use yield() to be 'nice' for others, use cond_resched().
 * If you still want to use yield(), do not!
 */


void __sched yield(void)
{
	set_current_state(TASK_RUNNING);
	sys_sched_yield();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
10
62.50%
1
33.33%
Dario Faggioli
3
18.75%
1
33.33%
Rick Lindsley
3
18.75%
1
33.33%
Total
16
100.00%
3
100.00%


EXPORT_SYMBOL(yield);

/**
 * yield_to - yield the current processor to another thread in
 * your thread group, or accelerate that thread toward the
 * processor it's on.
 * @p: target task
 * @preempt: whether task preemption is allowed or not
 *
 * It's the caller's job to ensure that the target task struct
 * can't go away on us before we can do any checks.
 *
 * Return:
 *      true (>0) if we indeed boosted the target task.
 *      false (0) if we failed to boost the target.
 *      -ESRCH if there's no task to yield to.
 */


int __sched yield_to(struct task_struct *p, bool preempt)
{
	struct task_struct *curr = current;
	struct rq *rq, *p_rq;
	unsigned long flags;
	int yielded = 0;

	local_irq_save(flags);
	rq = this_rq();

again:
	p_rq = task_rq(p);
	/*
         * If we're the only runnable task on the rq and target rq also
         * has only one task, there's absolutely no point in yielding.
         */
	if (rq->nr_running == 1 && p_rq->nr_running == 1) {
		yielded = -ESRCH;
		goto out_irq;
	}

	double_rq_lock(rq, p_rq);
	if (task_rq(p) != p_rq) {
		double_rq_unlock(rq, p_rq);
		goto again;
	}

	if (!curr->sched_class->yield_to_task)
		goto out_unlock;

	if (curr->sched_class != p->sched_class)
		goto out_unlock;

	if (task_running(p_rq, p) || p->state)
		goto out_unlock;

	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
	if (yielded) {
		schedstat_inc(rq->yld_count);
		/*
                 * Make p's CPU reschedule; pick_next_entity takes care of
                 * fairness.
                 */
		if (preempt && rq != p_rq)
			resched_curr(p_rq);
	}

out_unlock:
	double_rq_unlock(rq, p_rq);
out_irq:
	local_irq_restore(flags);

	if (yielded > 0)
		schedule();

	return yielded;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
153
69.23%
3
11.54%
Dario Faggioli
28
12.67%
1
3.85%
Kirill Tkhai
6
2.71%
2
7.69%
Nicholas Piggin
6
2.71%
2
7.69%
Motohiro Kosaki
3
1.36%
1
3.85%
Milton D. Miller II
3
1.36%
1
3.85%
Andrew Morton
3
1.36%
2
7.69%
Robert Love
3
1.36%
1
3.85%
Gregory Haskins
3
1.36%
1
3.85%
Tetsuo Handa
2
0.90%
1
3.85%
Heiko Carstens
2
0.90%
2
7.69%
Ingo Molnar
2
0.90%
2
7.69%
David Howells
1
0.45%
1
3.85%
Oleg Nesterov
1
0.45%
1
3.85%
Linus Torvalds (pre-git)
1
0.45%
1
3.85%
David P. Quigley
1
0.45%
1
3.85%
Thomas Gleixner
1
0.45%
1
3.85%
Mike Galbraith
1
0.45%
1
3.85%
Josh Poimboeuf
1
0.45%
1
3.85%
Total
221
100.00%
26
100.00%


EXPORT_SYMBOL_GPL(yield_to);



int io_schedule_prepare(void)
{
	int old_iowait = current->in_iowait;

	current->in_iowait = 1;
	blk_schedule_flush_plug(current);

	return old_iowait;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
15
53.57%
1
14.29%
Tejun Heo
7
25.00%
1
14.29%
Nicholas Piggin
2
7.14%
1
14.29%
Gregory Haskins
1
3.57%
1
14.29%
Thomas Gleixner
1
3.57%
1
14.29%
Andrew Morton
1
3.57%
1
14.29%
Dario Faggioli
1
3.57%
1
14.29%
Total
28
100.00%
7
100.00%



void io_schedule_finish(int token)
{
	current->in_iowait = token;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
14
100.00%
1
100.00%
Total
14
100.00%
1
100.00%

/*
 * This task is about to go to sleep on IO. Increment rq->nr_iowait so
 * that process accounting knows that this is a task in IO wait state.
 */


long __sched io_schedule_timeout(long timeout)
{
	int token;
	long ret;

	token = io_schedule_prepare();
	ret = schedule_timeout(timeout);
	io_schedule_finish(token);

	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
23
65.71%
1
20.00%
Peter Zijlstra
8
22.86%
1
20.00%
Dario Faggioli
2
5.71%
1
20.00%
Linus Torvalds (pre-git)
1
2.86%
1
20.00%
Milton D. Miller II
1
2.86%
1
20.00%
Total
35
100.00%
5
100.00%


EXPORT_SYMBOL(io_schedule_timeout);



void io_schedule(void)
{
	int token;

	token = io_schedule_prepare();
	schedule();
	io_schedule_finish(token);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
23
100.00%
1
100.00%
Total
23
100.00%
1
100.00%


EXPORT_SYMBOL(io_schedule);

/**
 * sys_sched_get_priority_max - return maximum RT priority.
 * @policy: scheduling class.
 *
 * Return: On success, this syscall returns the maximum
 * rt_priority that can be used by a given scheduling class.
 * On failure, a negative error code is returned.
 */

SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = MAX_USER_RT_PRIO-1;
		break;
	case SCHED_DEADLINE:
	case SCHED_NORMAL:
	case SCHED_BATCH:
	case SCHED_IDLE:
		ret = 0;
		break;
	}
	return ret;
}

/**
 * sys_sched_get_priority_min - return minimum RT priority.
 * @policy: scheduling class.
 *
 * Return: On success, this syscall returns the minimum
 * rt_priority that can be used by a given scheduling class.
 * On failure, a negative error code is returned.
 */

SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 1;
		break;
	case SCHED_DEADLINE:
	case SCHED_NORMAL:
	case SCHED_BATCH:
	case SCHED_IDLE:
		ret = 0;
	}
	return ret;
}



static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
{
	struct task_struct *p;
	unsigned int time_slice;
	struct rq_flags rf;
	struct rq *rq;
	int retval;

	if (pid < 0)
		return -EINVAL;

	retval = -ESRCH;
	rcu_read_lock();
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	rq = task_rq_lock(p, &rf);
	time_slice = 0;
	if (p->sched_class->get_rr_interval)
		time_slice = p->sched_class->get_rr_interval(rq, p);
	task_rq_unlock(rq, p, &rf);

	rcu_read_unlock();
	jiffies_to_timespec64(time_slice, t);
	return 0;

out_unlock:
	rcu_read_unlock();
	return retval;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
80
54.05%
3
27.27%
Dario Faggioli
30
20.27%
1
9.09%
Al Viro
24
16.22%
1
9.09%
Mel Gorman
7
4.73%
2
18.18%
Nicholas Piggin
3
2.03%
1
9.09%
Thomas Gleixner
2
1.35%
1
9.09%
Heiko Carstens
1
0.68%
1
9.09%
Ingo Molnar
1
0.68%
1
9.09%
Total
148
100.00%
11
100.00%

/**
 * sys_sched_rr_get_interval - return the default timeslice of a process.
 * @pid: pid of the process.
 * @interval: userspace pointer to the timeslice value.
 *
 * this syscall writes the default timeslice value of a given process
 * into the user-space timespec buffer. A value of '0' means infinity.
 *
 * Return: On success, 0 and the timeslice is in @interval. Otherwise,
 * an error code.
 */

SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
		struct timespec __user *, interval)
{
	struct timespec64 t;
	int retval = sched_rr_get_interval(pid, &t);

	if (retval == 0)
		retval = put_timespec64(&t, interval);

	return retval;
}

#ifdef CONFIG_COMPAT

COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
		       compat_pid_t, pid,
		       struct compat_timespec __user *, interval)
{
	struct timespec64 t;
	int retval = sched_rr_get_interval(pid, &t);

	if (retval == 0)
		retval = compat_put_timespec64(&t, interval);
	return retval;
}
#endif



void sched_show_task(struct task_struct *p)
{
	unsigned long free = 0;
	int ppid;

	if (!try_get_task_stack(p))
		return;

	printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));

	if (p->state == TASK_RUNNING)
		printk(KERN_CONT "  running task    ");
#ifdef CONFIG_DEBUG_STACK_USAGE
	free = stack_not_used(p);
#endif
	ppid = 0;
	rcu_read_lock();
	if (pid_alive(p))
		ppid = task_pid_nr(rcu_dereference(p->real_parent));
	rcu_read_unlock();
	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
		task_pid_nr(p), ppid,
		(unsigned long)task_thread_info(p)->flags);

	print_worker_info(KERN_INFO, p);
	show_stack(p, NULL);
	put_task_stack(p);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
52
36.36%
1
5.88%
Juri Lelli
27
18.88%
3
17.65%
Dario Faggioli
26
18.18%
1
5.88%
Tetsuo Handa
12
8.39%
1
5.88%
Nicholas Piggin
7
4.90%
1
5.88%
Xie XiuQi
4
2.80%
1
5.88%
Mike Galbraith
3
2.10%
1
5.88%
Linus Torvalds (pre-git)
3
2.10%
2
11.76%
Greg Kroah-Hartman
3
2.10%
1
5.88%
Rusty Russell
2
1.40%
1
5.88%
Joe Perches
1
0.70%
1
5.88%
Thomas Gleixner
1
0.70%
1
5.88%
Milton D. Miller II
1
0.70%
1
5.88%
Kirill Tkhai
1
0.70%
1
5.88%
Total
143
100.00%
17
100.00%


EXPORT_SYMBOL_GPL(sched_show_task);


static inline bool

state_filter_match(unsigned long state_filter, struct task_struct *p)
{
	/* no filter, everything matches */
	if (!state_filter)
		return true;

	/* filter, but doesn't match */
	if (!(p->state & state_filter))
		return false;

	/*
         * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
         * TASK_KILLABLE).
         */
	if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
		return false;

	return true;
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
59
100.00%
1
100.00%
Total
59
100.00%
1
100.00%



void show_state_filter(unsigned long state_filter)
{
	struct task_struct *g, *p;

#if BITS_PER_LONG == 32
	printk(KERN_INFO
		"  task                PC stack   pid father\n");
#else
	printk(KERN_INFO
		"  task                        PC stack   pid father\n");
#endif
	rcu_read_lock();
	for_each_process_thread(g, p) {
		/*
                 * reset the NMI-timeout, listing all files on a slow
                 * console might take a lot of time:
                 * Also, reset softlockup watchdogs on all CPUs, because
                 * another CPU might be blocked waiting for us to process
                 * an IPI.
                 */
		touch_nmi_watchdog();
		touch_all_softlockup_watchdogs();
		if (state_filter_match(state_filter, p))
			sched_show_task(p);
	}

#ifdef CONFIG_SCHED_DEBUG
	if (!state_filter)
		sysrq_sched_debug_show();
#endif
	rcu_read_unlock();
	/*
         * Only show locks if all tasks are dumped:
         */
	if (!state_filter)
		debug_show_all_locks();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
50
52.63%
2
16.67%
Juri Lelli
12
12.63%
2
16.67%
Dario Faggioli
12
12.63%
1
8.33%
Nicholas Piggin
5
5.26%
1
8.33%
Rabin Vincent
5
5.26%
1
8.33%
Andrey Ryabinin
4
4.21%
1
8.33%
Gregory Haskins
4
4.21%
2
16.67%
Andrew Morton
2
2.11%
1
8.33%
Ingo Molnar
1
1.05%
1
8.33%
Total
95
100.00%
12
100.00%

/**
 * init_idle - set up an idle thread for a given CPU
 * @idle: task in question
 * @cpu: CPU the idle task belongs to
 *
 * NOTE: this function does not set the idle thread's NEED_RESCHED
 * flag, to make booting more robust.
 */


void init_idle(struct task_struct *idle, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	raw_spin_lock_irqsave(&idle->pi_lock, flags);
	raw_spin_lock(&rq->lock);

	__sched_fork(0, idle);
	idle->state = TASK_RUNNING;
	idle->se.exec_start = sched_clock();
	idle->flags |= PF_IDLE;

	kasan_unpoison_task_stack(idle);

#ifdef CONFIG_SMP
	/*
         * Its possible that init_idle() gets called multiple times on a task,
         * in that case do_set_cpus_allowed() will not do the right thing.
         *
         * And since this is boot we can forgo the serialization.
         */
	set_cpus_allowed_common(idle, cpumask_of(cpu));
#endif
	/*
         * We're having a chicken and egg problem, even though we are
         * holding rq->lock, the CPU isn't yet set to this CPU so the
         * lockdep check in task_group() will fail.
         *
         * Similar case to sched_fork(). / Alternatively we could
         * use task_rq_lock() here and obtain the other rq->lock.
         *
         * Silence PROVE_RCU
         */
	rcu_read_lock();
	__set_task_cpu(idle, cpu);
	rcu_read_unlock();

	rq->curr = rq->idle = idle;
	idle->on_rq = TASK_ON_RQ_QUEUED;
#ifdef CONFIG_SMP
	idle->on_cpu = 1;
#endif
	raw_spin_unlock(&rq->lock);
	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);

	/* Set the preempt count _outside_ the spinlocks! */
	init_idle_preempt_count(idle, cpu);

	/*
         * The idle tasks have their own, simple scheduling class:
         */
	idle->sched_class = &idle_sched_class;
	ftrace_graph_init_idle_task(idle, cpu);
	vtime_init_idle(idle, cpu);
#ifdef CONFIG_SMP
	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
99
49.25%
5
27.78%
Dario Faggioli
28
13.93%
1
5.56%
Kirill Tkhai
27
13.43%
1
5.56%
Wanpeng Li
20
9.95%
1
5.56%
Gregory Haskins
12
5.97%
2
11.11%
Nicholas Piggin
5
2.49%
1
5.56%
Ingo Molnar
3
1.49%
2
11.11%
Linus Torvalds
2
1.00%
1
5.56%
Andrew Morton
2
1.00%
1
5.56%
Milton D. Miller II
1
0.50%
1
5.56%
Rick Lindsley
1
0.50%
1
5.56%
Nathan Lynch
1
0.50%
1
5.56%
Total
201
100.00%
18
100.00%

#ifdef CONFIG_SMP



int cpuset_cpumask_can_shrink(const struct cpumask *cur,
			      const struct cpumask *trial)
{
	int ret = 1;

	if (!cpumask_weight(cur))
		return ret;

	ret = dl_cpuset_cpumask_can_shrink(cur, trial);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
19
42.22%
4
36.36%
Dario Faggioli
16
35.56%
1
9.09%
Nico Pitre
3
6.67%
1
9.09%
Milton D. Miller II
2
4.44%
1
9.09%
Gregory Haskins
2
4.44%
1
9.09%
Kirill Tkhai
1
2.22%
1
9.09%
Ingo Molnar
1
2.22%
1
9.09%
Nicholas Piggin
1
2.22%
1
9.09%
Total
45
100.00%
11
100.00%



int task_can_attach(struct task_struct *p,
		    const struct cpumask *cs_cpus_allowed)
{
	int ret = 0;

	/*
         * Kthreads which disallow setaffinity shouldn't be moved
         * to a new cpuset; we don't want to change their CPU
         * affinity and isolating such threads by their set of
         * allowed nodes is unnecessary.  Thus, cpusets are not
         * applicable for such threads.  This prevents checking for
         * success of set_cpus_allowed_ptr() on all attached tasks
         * before cpus_allowed may be changed.
         */
	if (p->flags & PF_NO_SETAFFINITY) {
		ret = -EINVAL;
		goto out;
	}

	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
					      cs_cpus_allowed))
		ret = dl_task_can_attach(p, cs_cpus_allowed);

out:
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
42
55.26%
3
30.00%
Dario Faggioli
23
30.26%
1
10.00%
Milton D. Miller II
5
6.58%
2
20.00%
Ingo Molnar
4
5.26%
3
30.00%
Nico Pitre
2
2.63%
1
10.00%
Total
76
100.00%
10
100.00%


bool sched_smp_initialized __read_mostly;

#ifdef CONFIG_NUMA_BALANCING
/* Migrate current task p to target_cpu */


int migrate_task_to(struct task_struct *p, int target_cpu)
{
	struct migration_arg arg = { p, target_cpu };
	int curr_cpu = task_cpu(p);

	if (curr_cpu == target_cpu)
		return 0;

	if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
		return -EINVAL;

	/* TODO: This is not properly updating schedstats */

	trace_sched_move_numa(p, curr_cpu, target_cpu);
	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
56
71.79%
1
11.11%
Ingo Molnar
5
6.41%
2
22.22%
Mel Gorman
4
5.13%
1
11.11%
Nicholas Piggin
4
5.13%
1
11.11%
Peter Zijlstra
4
5.13%
1
11.11%
Tejun Heo
3
3.85%
1
11.11%
Gregory Haskins
1
1.28%
1
11.11%
Linus Torvalds (pre-git)
1
1.28%
1
11.11%
Total
78
100.00%
9
100.00%

/*
 * Requeue a task on a given node and accurately track the number of NUMA
 * tasks on the runqueues
 */


void sched_setnuma(struct task_struct *p, int nid)
{
	bool queued, running;
	struct rq_flags rf;
	struct rq *rq;

	rq = task_rq_lock(p, &rf);
	queued = task_on_rq_queued(p);
	running = task_current(rq, p);

	if (queued)
		dequeue_task(rq, p, DEQUEUE_SAVE);
	if (running)
		put_prev_task(rq, p);

	p->numa_preferred_nid = nid;

	if (queued)
		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
	if (running)
		set_curr_task(rq, p);
	task_rq_unlock(rq, p, &rf);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
58
48.74%
1
4.76%
Peter Zijlstra
15
12.61%
4
19.05%
Nicholas Piggin
11
9.24%
2
9.52%
Alex Shi
8
6.72%
1
4.76%
Vincent Guittot
8
6.72%
1
4.76%
Kirill Tkhai
4
3.36%
1
4.76%
Linus Torvalds (pre-git)
3
2.52%
2
9.52%
Suresh B. Siddha
3
2.52%
1
4.76%
Ingo Molnar
2
1.68%
2
9.52%
Eduard - Gabriel Munteanu
2
1.68%
1
4.76%
Rusty Russell
2
1.68%
2
9.52%
Joe Perches
1
0.84%
1
4.76%
Milton D. Miller II
1
0.84%
1
4.76%
Greg Kroah-Hartman
1
0.84%
1
4.76%
Total
119
100.00%
21
100.00%

#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_HOTPLUG_CPU
/*
 * Ensure that the idle task is using init_mm right before its CPU goes
 * offline.
 */


void idle_task_exit(void)
{
	struct mm_struct *mm = current->active_mm;

	BUG_ON(cpu_online(smp_processor_id()));

	if (mm != &init_mm) {
		switch_mm(mm, &init_mm, current);
		finish_arch_post_lock_switch();
	}
	mmdrop(mm);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
29
55.77%
1
8.33%
Linus Torvalds (pre-git)
5
9.62%
1
8.33%
Andrew Morton
5
9.62%
3
25.00%
Nicholas Piggin
4
7.69%
2
16.67%
Martin Schwidefsky
4
7.69%
1
8.33%
Ingo Molnar
3
5.77%
2
16.67%
Rusty Russell
1
1.92%
1
8.33%
Andrew Lutomirski
1
1.92%
1
8.33%
Total
52
100.00%
12
100.00%

/*
 * Since this CPU is going 'away' for a while, fold any nr_active delta
 * we might have. Assumes we're called after migrate_tasks() so that the
 * nr_active count is stable. We need to take the teardown thread which
 * is calling this into account, so we hand in adjust = 1 to the load
 * calculation.
 *
 * Also see the comment "Global load-average calculations".
 */


static void calc_load_migrate(struct rq *rq)
{
	long delta = calc_load_fold_active(rq, 1);
	if (delta)
		atomic_long_add(delta, &calc_load_tasks);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
17
51.52%
1
11.11%
Andrew Morton
7
21.21%
2
22.22%
Gregory Haskins
2
6.06%
1
11.11%
Nicholas Piggin
2
6.06%
1
11.11%
Thomas Gleixner
2
6.06%
1
11.11%
Linus Torvalds (pre-git)
1
3.03%
1
11.11%
Milton D. Miller II
1
3.03%
1
11.11%
Ingo Molnar
1
3.03%
1
11.11%
Total
33
100.00%
9
100.00%



static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
12
80.00%
1
50.00%
Dario Faggioli
3
20.00%
1
50.00%
Total
15
100.00%
2
100.00%


static const struct sched_class fake_sched_class = {
	.put_prev_task = put_prev_task_fake,
};


static struct task_struct fake_task = {
	/*
         * Avoid pull_{rt,dl}_task()
         */
	.prio = MAX_PRIO + 1,
	.sched_class = &fake_sched_class,
};

/*
 * Migrate all tasks from the rq, sleeping tasks will be migrated by
 * try_to_wake_up()->select_task_rq().
 *
 * Called with rq->lock held even though we'er in stop_machine() and
 * there's no concurrency possible, we hold the required locks anyway
 * because of lock validation efforts.
 */


static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
{
	struct rq *rq = dead_rq;
	struct task_struct *next, *stop = rq->stop;
	struct rq_flags orf = *rf;
	int dest_cpu;

	/*
         * Fudge the rq selection such that the below task selection loop
         * doesn't get stuck on the currently eligible stop task.
         *
         * We're currently inside stop_machine() and the rq is either stuck
         * in the stop_machine_cpu_stop() loop, or we're executing this code,
         * either way we should never end up calling schedule() until we're
         * done here.
         */
	rq->stop = NULL;

	/*
         * put_prev_task() and pick_next_task() sched
         * class method both need to have an up-to-date
         * value of rq->clock[_task]
         */
	update_rq_clock(rq);

	for (;;) {
		/*
                 * There's this thread running, bail when that's the only
                 * remaining thread:
                 */
		if (rq->nr_running == 1)
			break;

		/*
                 * pick_next_task() assumes pinned rq->lock:
                 */
		next = pick_next_task(rq, &fake_task, rf);
		BUG_ON(!next);
		put_prev_task(rq, next);

		/*
                 * Rules for changing task_struct::cpus_allowed are holding
                 * both pi_lock and rq->lock, such that holding either
                 * stabilizes the mask.
                 *
                 * Drop rq->lock is not quite as disastrous as it usually is
                 * because !cpu_active at this point, which means load-balance
                 * will not interfere. Also, stop-machine.
                 */
		rq_unlock(rq, rf);
		raw_spin_lock(&next->pi_lock);
		rq_relock(rq, rf);

		/*
                 * Since we're inside stop-machine, _nothing_ should have
                 * changed the task, WARN if weird stuff happened, because in
                 * that case the above rq->lock drop is a fail too.
                 */
		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
			raw_spin_unlock(&next->pi_lock);
			continue;
		}

		/* Find suitable destination for @next, with force if needed. */
		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
		rq = __migrate_task(rq, rf, next, dest_cpu);
		if (rq != dead_rq) {
			rq_unlock(rq, rf);
			rq = dead_rq;
			*rf = orf;
			rq_relock(rq, rf);
		}
		raw_spin_unlock(&next->pi_lock);
	}

	rq->stop = stop;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
71
31.70%
1
4.00%
Peter Zijlstra
48
21.43%
5
20.00%
Wanpeng Li
47
20.98%
1
4.00%
Gregory Haskins
25
11.16%
4
16.00%
Andrew Morton
13
5.80%
4
16.00%
Nicholas Piggin
7
3.12%
3
12.00%
Ingo Molnar
6
2.68%
3
12.00%
Matt Fleming
4
1.79%
1
4.00%
Tejun Heo
1
0.45%
1
4.00%
Rusty Russell
1
0.45%
1
4.00%
Linus Torvalds (pre-git)
1
0.45%
1
4.00%
Total
224
100.00%
25
100.00%

#endif /* CONFIG_HOTPLUG_CPU */



void set_rq_online(struct rq *rq)
{
	if (!rq->online) {
		const struct sched_class *class;

		cpumask_set_cpu(rq->cpu, rq->rd->online);
		rq->online = 1;

		for_each_class(class) {
			if (class->rq_online)
				class->rq_online(rq);
		}
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
40
63.49%
1
7.14%
Peter Zijlstra
7
11.11%
3
21.43%
Linus Torvalds (pre-git)
4
6.35%
3
21.43%
Gautham R. Shenoy
4
6.35%
1
7.14%
Andrew Morton
2
3.17%
1
7.14%
Paul E. McKenney
2
3.17%
1
7.14%
Gregory Haskins
1
1.59%
1
7.14%
Ingo Molnar
1
1.59%
1
7.14%
Nicholas Piggin
1
1.59%
1
7.14%
John Hawkes
1
1.59%
1
7.14%
Total
63
100.00%
14
100.00%



void set_rq_offline(struct rq *rq)
{
	if (rq->online) {
		const struct sched_class *class;

		for_each_class(class) {
			if (class->rq_offline)
				class->rq_offline(rq);
		}

		cpumask_clear_cpu(rq->cpu, rq->rd->online);
		rq->online = 0;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
44
70.97%
1
12.50%
Peter Zijlstra
5
8.06%
1
12.50%
Nathan Lynch
5
8.06%
1
12.50%
Nicholas Piggin
4
6.45%
1
12.50%
John Hawkes
1
1.61%
1
12.50%
Rusty Russell
1
1.61%
1
12.50%
Andrew Morton
1
1.61%
1
12.50%
Ingo Molnar
1
1.61%
1
12.50%
Total
62
100.00%
8
100.00%



static void set_cpu_rq_start_time(unsigned int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	rq->age_stamp = sched_clock_cpu(cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
16
55.17%
1
14.29%
Corey Minyard
4
13.79%
1
14.29%
Thomas Gleixner
4
13.79%
2
28.57%
Ingo Molnar
2
6.90%
1
14.29%
Tejun Heo
2
6.90%
1
14.29%
Peter Zijlstra
1
3.45%
1
14.29%
Total
29
100.00%
7
100.00%

/*
 * used to mark begin/end of suspend/resume:
 */

static int num_cpus_frozen;

/*
 * Update cpusets according to cpu_active mask.  If cpusets are
 * disabled, cpuset_update_active_cpus() becomes a simple wrapper
 * around partition_sched_domains().
 *
 * If we come here as part of a suspend/resume, don't touch cpusets because we
 * want to restore it back to its original state upon resume anyway.
 */


static void cpuset_cpu_active(void)
{
	if (cpuhp_tasks_frozen) {
		/*
                 * num_cpus_frozen tracks how many CPUs are involved in suspend
                 * resume sequence. As long as this is not the last online
                 * operation in the resume sequence, just build a single sched
                 * domain, ignoring cpusets.
                 */
		partition_sched_domains(1, NULL, NULL);
		if (--num_cpus_frozen)
			return;
		/*
                 * This is the last CPU online operation. So fall through and
                 * restore the original sched domains by considering the
                 * cpuset configurations.
                 */
		cpuset_force_rebuild();
	}
	cpuset_update_active_cpus();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
12
32.43%
1
10.00%
Peter Zijlstra
9
24.32%
2
20.00%
Rusty Russell
5
13.51%
1
10.00%
Thomas Gleixner
5
13.51%
3
30.00%
Dinakar Guniguntala
4
10.81%
1
10.00%
Srivatsa Vaddagiri
1
2.70%
1
10.00%
Rakib Mullick
1
2.70%
1
10.00%
Total
37
100.00%
10
100.00%



static int cpuset_cpu_inactive(unsigned int cpu)
{
	if (!cpuhp_tasks_frozen) {
		if (dl_cpu_busy(cpu))
			return -EBUSY;
		cpuset_update_active_cpus();
	} else {
		num_cpus_frozen++;
		partition_sched_domains(1, NULL, NULL);
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
14
28.57%
3
20.00%
Dario Faggioli
12
24.49%
1
6.67%
Juri Lelli
10
20.41%
1
6.67%
Peter Zijlstra
4
8.16%
4
26.67%
Nicholas Piggin
3
6.12%
1
6.67%
Suresh B. Siddha
2
4.08%
1
6.67%
Rusty Russell
1
2.04%
1
6.67%
Nico Pitre
1
2.04%
1
6.67%
Hidetoshi Seto
1
2.04%
1
6.67%
Rakib Mullick
1
2.04%
1
6.67%
Total
49
100.00%
15
100.00%



int sched_cpu_activate(unsigned int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct rq_flags rf;

	set_cpu_active(cpu, true);

	if (sched_smp_initialized) {
		sched_domains_numa_masks_set(cpu);
		cpuset_cpu_active();
	}

	/*
         * Put the rq online, if not already. This happens:
         *
         * 1) In the early boot process, because we build the real domains
         *    after all CPUs have been brought up.
         *
         * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
         *    domains.
         */
	rq_lock_irqsave(rq, &rf);
	if (rq->rd) {
		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
		set_rq_online(rq);
	}
	rq_unlock_irqrestore(rq, &rf);

	update_max_interval();

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
83
87.37%
3
50.00%
Peter Zijlstra
9
9.47%
1
16.67%
Dario Faggioli
2
2.11%
1
16.67%
Ingo Molnar
1
1.05%
1
16.67%
Total
95
100.00%
6
100.00%



int sched_cpu_deactivate(unsigned int cpu)
{
	int ret;

	set_cpu_active(cpu, false);
	/*
         * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
         * users of this state to go away such that all new such users will
         * observe it.
         *
         * Do sync before park smpboot threads to take care the rcu boost case.
         */
	synchronize_rcu_mult(call_rcu, call_rcu_sched);

	if (!sched_smp_initialized)
		return 0;

	ret = cpuset_cpu_inactive(cpu);
	if (ret) {
		set_cpu_active(cpu, true);
		return ret;
	}
	sched_domains_numa_masks_clear(cpu);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
58
87.88%
2
50.00%
Peter Zijlstra
7
10.61%
1
25.00%
Paul E. McKenney
1
1.52%
1
25.00%
Total
66
100.00%
4
100.00%



static void sched_rq_cpu_starting(unsigned int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	rq->calc_load_update = calc_load_update;
	update_max_interval();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
29
100.00%
1
100.00%
Total
29
100.00%
1
100.00%



int sched_cpu_starting(unsigned int cpu)
{
	set_cpu_rq_start_time(cpu);
	sched_rq_cpu_starting(cpu);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
12
54.55%
2
40.00%
Dario Faggioli
5
22.73%
1
20.00%
Rusty Russell
4
18.18%
1
20.00%
Srivatsa Vaddagiri
1
4.55%
1
20.00%
Total
22
100.00%
5
100.00%

#ifdef CONFIG_HOTPLUG_CPU


int sched_cpu_dying(unsigned int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct rq_flags rf;

	/* Handle pending wakeups and then migrate everything off */
	sched_ttwu_pending();

	rq_lock_irqsave(rq, &rf);
	if (rq->rd) {
		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
		set_rq_offline(rq);
	}
	migrate_tasks(rq, &rf);
	BUG_ON(rq->nr_running != 1);
	rq_unlock_irqrestore(rq, &rf);

	calc_load_migrate(rq);
	update_max_interval();
	nohz_balance_exit_idle(cpu);
	hrtick_clear(rq);
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
60
55.05%
3
27.27%
Juri Lelli
23
21.10%
1
9.09%
Peter Zijlstra
13
11.93%
2
18.18%
Dario Faggioli
5
4.59%
1
9.09%
Suresh B. Siddha
4
3.67%
2
18.18%
Nicholas Piggin
3
2.75%
1
9.09%
Rusty Russell
1
0.92%
1
9.09%
Total
109
100.00%
11
100.00%

#endif

#ifdef CONFIG_SCHED_SMT

DEFINE_STATIC_KEY_FALSE(sched_smt_present);



static void sched_init_smt(void)
{
	/*
         * We've enumerated all CPUs and will assume that if any CPU
         * has SMT siblings, CPU0 will too.
         */
	if (cpumask_weight(cpu_smt_mask(0)) > 1)
		static_branch_enable(&sched_smt_present);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
27
100.00%
1
100.00%
Total
27
100.00%
1
100.00%

#else


static inline void sched_init_smt(void) { }
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
8
100.00%
1
100.00%
Total
8
100.00%
1
100.00%

#endif



void __init sched_init_smp(void)
{
	sched_init_numa();

	/*
         * There's no userspace yet to cause hotplug operations; hence all the
         * CPU masks are stable and all blatant races in the below code cannot
         * happen.
         */
	mutex_lock(&sched_domains_mutex);
	sched_init_domains(cpu_active_mask);
	mutex_unlock(&sched_domains_mutex);

	/* Move init over to a non-isolated CPU */
	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
		BUG();
	sched_init_granularity();

	init_sched_rt_class();
	init_sched_dl_class();

	sched_init_smt();

	sched_smp_initialized = true;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
42
66.67%
1
9.09%
Thomas Gleixner
4
6.35%
1
9.09%
Peter Zijlstra
4
6.35%
2
18.18%
Frédéric Weisbecker
4
6.35%
1
9.09%
Paul Jackson
3
4.76%
1
9.09%
Rusty Russell
2
3.17%
1
9.09%
Ingo Molnar
1
1.59%
1
9.09%
Heiko Carstens
1
1.59%
1
9.09%
Christoph Lameter
1
1.59%
1
9.09%
Suresh B. Siddha
1
1.59%
1
9.09%
Total
63
100.00%
11
100.00%



static int __init migration_init(void)
{
	sched_rq_cpu_starting(smp_processor_id());
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
17
94.44%
2
66.67%
Dario Faggioli
1
5.56%
1
33.33%
Total
18
100.00%
3
100.00%


early_initcall(migration_init);

#else


void __init sched_init_smp(void)
{
	sched_init_granularity();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
11
100.00%
1
100.00%
Total
11
100.00%
1
100.00%

#endif /* CONFIG_SMP */



int in_sched_functions(unsigned long addr)
{
	return in_lock_functions(addr) ||
		(addr >= (unsigned long)__sched_text_start
		&& addr < (unsigned long)__sched_text_end);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
31
93.94%
1
33.33%
Peter Zijlstra
1
3.03%
1
33.33%
Paul Jackson
1
3.03%
1
33.33%
Total
33
100.00%
3
100.00%

#ifdef CONFIG_CGROUP_SCHED
/*
 * Default task group.
 * Every task in system belongs to this group at bootup.
 */

struct task_group root_task_group;

LIST_HEAD(task_groups);

/* Cacheline aligned slab cache for task_group */

static struct kmem_cache *task_group_cache __read_mostly;
#endif

DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);



void __init sched_init(void)
{
	int i, j;
	unsigned long alloc_size = 0, ptr;

	sched_clock_init();
	wait_bit_init();

#ifdef CONFIG_FAIR_GROUP_SCHED
	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
	if (alloc_size) {
		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);

#ifdef CONFIG_FAIR_GROUP_SCHED
		root_task_group.se = (struct sched_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		root_task_group.rt_rq = (struct rt_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

#endif /* CONFIG_RT_GROUP_SCHED */
	}
#ifdef CONFIG_CPUMASK_OFFSTACK
	for_each_possible_cpu(i) {
		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
		per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
	}
#endif /* CONFIG_CPUMASK_OFFSTACK */

	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
	init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());

#ifdef CONFIG_SMP
	init_defrootdomain();
#endif

#ifdef CONFIG_RT_GROUP_SCHED
	init_rt_bandwidth(&root_task_group.rt_bandwidth,
			global_rt_period(), global_rt_runtime());
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_CGROUP_SCHED
	task_group_cache = KMEM_CACHE(task_group, 0);

	list_add(&root_task_group.list, &task_groups);
	INIT_LIST_HEAD(&root_task_group.children);
	INIT_LIST_HEAD(&root_task_group.siblings);
	autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */

	for_each_possible_cpu(i) {
		struct rq *rq;

		rq = cpu_rq(i);
		raw_spin_lock_init(&rq->lock);
		rq->nr_running = 0;
		rq->calc_load_active = 0;
		rq->calc_load_update = jiffies + LOAD_FREQ;
		init_cfs_rq(&rq->cfs);
		init_rt_rq(&rq->rt);
		init_dl_rq(&rq->dl);
#ifdef CONFIG_FAIR_GROUP_SCHED
		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
		/*
                 * How much CPU bandwidth does root_task_group get?
                 *
                 * In case of task-groups formed thr' the cgroup filesystem, it
                 * gets 100% of the CPU resources in the system. This overall
                 * system CPU resource is divided among the tasks of
                 * root_task_group and its child task-groups in a fair manner,
                 * based on each entity's (task or task-group's) weight
                 * (se->load.weight).
                 *
                 * In other words, if root_task_group has 10 tasks of weight
                 * 1024) and two child groups A0 and A1 (of weight 1024 each),
                 * then A0's share of the CPU resource is:
                 *
                 *      A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
                 *
                 * We achieve this by letting root_task_group's tasks sit
                 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
                 */
		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */

		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif

		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
			rq->cpu_load[j] = 0;

#ifdef CONFIG_SMP
		rq->sd = NULL;
		rq->rd = NULL;
		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
		rq->balance_callback = NULL;
		rq->active_balance = 0;
		rq->next_balance = jiffies;
		rq->push_cpu = 0;
		rq->cpu = i;
		rq->online = 0;
		rq->idle_stamp = 0;
		rq->avg_idle = 2*sysctl_sched_migration_cost;
		rq->max_idle_balance_cost = sysctl_sched_migration_cost;

		INIT_LIST_HEAD(&rq->cfs_tasks);

		rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
		rq->last_load_update_tick = jiffies;
		rq->nohz_flags = 0;
#endif
#ifdef CONFIG_NO_HZ_FULL
		rq->last_sched_tick = 0;
#endif
#endif /* CONFIG_SMP */
		init_rq_hrtick(rq);
		atomic_set(&rq->nr_iowait, 0);
	}

	set_load_weight(&init_task, false);

	/*
         * The boot idle thread does lazy MMU switching as well:
         */
	mmgrab(&init_mm);
	enter_lazy_tlb(&init_mm, current);

	/*
         * Make us the idle thread. Technically, schedule() should not be
         * called from this thread, however somewhere below it might be,
         * but because we are the idle thread, we just pick up running again
         * when this runqueue becomes "idle".
         */
	init_idle(current, smp_processor_id());

	calc_load_update = jiffies + LOAD_FREQ;

#ifdef CONFIG_SMP
	idle_thread_set_boot_cpu();
	set_cpu_rq_start_time(smp_processor_id());
#endif
	init_sched_fair_class();

	init_schedstats();

	scheduler_running = 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
502
68.96%
1
1.54%
Peter Zijlstra
54
7.42%
15
23.08%
Mike Travis
17
2.34%
1
1.54%
Vincent Guittot
15
2.06%
3
4.62%
Alex Thorlton
12
1.65%
1
1.54%
Ingo Molnar
11
1.51%
5
7.69%
Suresh B. Siddha
11
1.51%
1
1.54%
Srivatsa S. Bhat
10
1.37%
2
3.08%
Waiman Long
9
1.24%
1
1.54%
Andrew Morton
7
0.96%
3
4.62%
Maksim Krasnyanskiy
7
0.96%
3
4.62%
Rusty Russell
7
0.96%
3
4.62%
Adrian Bunk
7
0.96%
1
1.54%
Frédéric Weisbecker
6
0.82%
1
1.54%
Venkatesh Pallipadi
6
0.82%
1
1.54%
Paul Jackson
4
0.55%
1
1.54%
Gautham R. Shenoy
4
0.55%
2
3.08%
Dhaval Giani
4
0.55%
1
1.54%
Li Zefan
4
0.55%
2
3.08%
Srivatsa Vaddagiri
3
0.41%
1
1.54%
Mike Galbraith
3
0.41%
1
1.54%
Josh Poimboeuf
3
0.41%
1
1.54%
Heiko Carstens
3
0.41%
1
1.54%
Milton D. Miller II
3
0.41%
1
1.54%
William Lee Irwin III
2
0.27%
1
1.54%
Nicholas Piggin
2
0.27%
1
1.54%
Tang Chen
2
0.27%
1
1.54%
Corey Minyard
2
0.27%
1
1.54%
Nico Pitre
2
0.27%
2
3.08%
Thomas Gleixner
1
0.14%
1
1.54%
Vegard Nossum
1
0.14%
1
1.54%
Paul Turner
1
0.14%
1
1.54%
Avi Kivity
1
0.14%
1
1.54%
Linus Torvalds
1
0.14%
1
1.54%
John Hawkes
1
0.14%
1
1.54%
Total
728
100.00%
65
100.00%

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP


static inline int preempt_count_equals(int preempt_offset)
{
	int nested = preempt_count() + rcu_preempt_depth();

	return (nested == preempt_offset);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
24
92.31%
1
50.00%
Mike Travis
2
7.69%
1
50.00%
Total
26
100.00%
2
100.00%



void __might_sleep(const char *file, int line, int preempt_offset)
{
	/*
         * Blocking primitives will set (and therefore destroy) current->state,
         * since we will exit with TASK_RUNNING make sure we enter with it,
         * otherwise we will destroy state.
         */
	WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
			"do not call blocking ops when !TASK_RUNNING; "
			"state=%lx set at [<%p>] %pS\n",
			current->state,
			(void *)current->task_state_change,
			(void *)current->task_state_change);

	___might_sleep(file, line, preempt_offset);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
40
64.52%
5
45.45%
Dario Faggioli
13
20.97%
1
9.09%
Linus Torvalds
4
6.45%
1
9.09%
Srivatsa Vaddagiri
2
3.23%
2
18.18%
Li Zefan
2
3.23%
1
9.09%
Ingo Molnar
1
1.61%
1
9.09%
Total
62
100.00%
11
100.00%


EXPORT_SYMBOL(__might_sleep);



void ___might_sleep(const char *file, int line, int preempt_offset)
{
	/* Ratelimiting timestamp: */
	static unsigned long prev_jiffy;

	unsigned long preempt_disable_ip;

	/* WARN_ON_ONCE() by default, no rate limit required: */
	rcu_sleep_check();

	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
	     !is_idle_task(current)) ||
	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
	    oops_in_progress)
		return;

	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
		return;
	prev_jiffy = jiffies;

	/* Save this before calling printk(), since that will clobber it: */
	preempt_disable_ip = get_preempt_disable_ip(current);

	printk(KERN_ERR
		"BUG: sleeping function called from invalid context at %s:%d\n",
			file, line);
	printk(KERN_ERR
		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
			in_atomic(), irqs_disabled(),
			current->pid, current->comm);

	if (task_stack_end_corrupted(current))
		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");

	debug_show_held_locks(current);
	if (irqs_disabled())
		print_irqtrace_events(current);
	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
	    && !preempt_count_equals(preempt_offset)) {
		pr_err("Preemption disabled at:");
		print_ip_sym(preempt_disable_ip);
		pr_cont("\n");
	}
	dump_stack();
	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
70
38.04%
1
5.00%
Peter Zijlstra
32
17.39%
6
30.00%
Thomas Gleixner
26
14.13%
3
15.00%
Vegard Nossum
21
11.41%
2
10.00%
Andi Kleen
15
8.15%
1
5.00%
Eric Sandeen
7
3.80%
1
5.00%
Srivatsa Vaddagiri
5
2.72%
2
10.00%
Rusty Russell
3
1.63%
1
5.00%
Ingo Molnar
3
1.63%
1
5.00%
Arnaldo Carvalho de Melo
1
0.54%
1
5.00%
Suresh B. Siddha
1
0.54%
1
5.00%
Total
184
100.00%
20
100.00%


EXPORT_SYMBOL(___might_sleep);
#endif

#ifdef CONFIG_MAGIC_SYSRQ


void normalize_rt_tasks(void)
{
	struct task_struct *g, *p;
	struct sched_attr attr = {
		.sched_policy = SCHED_NORMAL,
        };

	read_lock(&tasklist_lock);
	for_each_process_thread(g, p) {
		/*
                 * Only normalize user tasks:
                 */
		if (p->flags & PF_KTHREAD)
			continue;

		p->se.exec_start = 0;
		schedstat_set(p->se.statistics.wait_start,  0);
		schedstat_set(p->se.statistics.sleep_start, 0);
		schedstat_set(p->se.statistics.block_start, 0);

		if (!dl_task(p) && !rt_task(p)) {
			/*
                         * Renice negative nice level userspace
                         * tasks back to 0:
                         */
			if (task_nice(p) < 0)
				set_user_nice(p, 0);
			continue;
		}

		__sched_setscheduler(p, &attr, false, false);
	}
	read_unlock(&tasklist_lock);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
99
66.44%
1
5.56%
Peter Zijlstra
19
12.75%
7
38.89%
Oleg Nesterov
8
5.37%
2
11.11%
Josh Poimboeuf
6
4.03%
1
5.56%
Srivatsa Vaddagiri
5
3.36%
2
11.11%
Jason Wessel
4
2.68%
1
5.56%
Ingo Molnar
3
2.01%
1
5.56%
Dmitry Adamushko
2
1.34%
1
5.56%
Linus Torvalds
2
1.34%
1
5.56%
Dongsheng Yang
1
0.67%
1
5.56%
Total
149
100.00%
18
100.00%

#endif /* CONFIG_MAGIC_SYSRQ */

#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
/*
 * These functions are only useful for the IA64 MCA handling, or kdb.
 *
 * They can only be called when the whole system has been
 * stopped - every CPU needs to be quiescent, and no scheduling
 * activity can take place. Using them for anything else would
 * be a serious bug, and as a result, they aren't even visible
 * under any other configuration.
 */

/**
 * curr_task - return the current task for a given CPU.
 * @cpu: the processor in question.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 *
 * Return: The current task for @cpu.
 */


struct task_struct *curr_task(int cpu)
{
	return cpu_curr(cpu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
8
50.00%
1
16.67%
Peter Zijlstra
7
43.75%
4
66.67%
Srivatsa Vaddagiri
1
6.25%
1
16.67%
Total
16
100.00%
6
100.00%

#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */

#ifdef CONFIG_IA64
/**
 * set_curr_task - set the current task for a given CPU.
 * @cpu: the processor in question.
 * @p: the task pointer to set.
 *
 * Description: This function must only be used when non-maskable interrupts
 * are serviced on a separate stack. It allows the architecture to switch the
 * notion of the current task on a CPU in a non-blocking manner. This function
 * must be called with all CPU's synchronized, and interrupts disabled, the
 * and caller must save the original value of the current task (see
 * curr_task() above) and restore that value before reenabling interrupts and
 * re-starting the system.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */


void ia64_set_curr_task(int cpu, struct task_struct *p)
{
	cpu_curr(cpu) = p;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
13
65.00%
1
20.00%
Peter Zijlstra
6
30.00%
3
60.00%
Frédéric Weisbecker
1
5.00%
1
20.00%
Total
20
100.00%
5
100.00%

#endif

#ifdef CONFIG_CGROUP_SCHED
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);



static void sched_free_group(struct task_group *tg)
{
	free_fair_sched_group(tg);
	free_rt_sched_group(tg);
	autogroup_free(tg);
	kmem_cache_free(task_group_cache, tg);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
14
42.42%
3
42.86%
Dario Faggioli
13
39.39%
1
14.29%
Waiman Long
3
9.09%
1
14.29%
Dhaval Giani
2
6.06%
1
14.29%
Srivatsa Vaddagiri
1
3.03%
1
14.29%
Total
33
100.00%
7
100.00%

/* allocate runqueue etc for a new task group */


struct task_group *sched_create_group(struct task_group *parent)
{
	struct task_group *tg;

	tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
	if (!tg)
		return ERR_PTR(-ENOMEM);

	if (!alloc_fair_sched_group(tg, parent))
		goto err;

	if (!alloc_rt_sched_group(tg, parent))
		goto err;

	return tg;

err:
	sched_free_group(tg);
	return ERR_PTR(-ENOMEM);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
49
59.04%
1
10.00%
Peter Zijlstra
25
30.12%
7
70.00%
Srivatsa Vaddagiri
5
6.02%
1
10.00%
Waiman Long
4
4.82%
1
10.00%
Total
83
100.00%
10
100.00%



void sched_online_group(struct task_group *tg, struct task_group *parent)
{
	unsigned long flags;

	spin_lock_irqsave(&task_group_lock, flags);
	list_add_rcu(&tg->list, &task_groups);

	/* Root should already exist: */
	WARN_ON(!parent);

	tg->parent = parent;
	INIT_LIST_HEAD(&tg->children);
	list_add_rcu(&tg->siblings, &parent->children);
	spin_unlock_irqrestore(&task_group_lock, flags);

	online_fair_sched_group(tg);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
60
70.59%
1
9.09%
Peter Zijlstra
19
22.35%
6
54.55%
Mike Galbraith
3
3.53%
1
9.09%
Ingo Molnar
2
2.35%
2
18.18%
Srivatsa Vaddagiri
1
1.18%
1
9.09%
Total
85
100.00%
11
100.00%

/* rcu callback to free various structures associated with a task group */


static void sched_free_group_rcu(struct rcu_head *rhp)
{
	/* Now it should be safe to free those cfs_rqs: */
	sched_free_group(container_of(rhp, struct task_group, rcu));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
17
68.00%
1
16.67%
Peter Zijlstra
7
28.00%
4
66.67%
Ingo Molnar
1
4.00%
1
16.67%
Total
25
100.00%
6
100.00%



void sched_destroy_group(struct task_group *tg)
{
	/* Wait for possible concurrent references to cfs_rqs complete: */
	call_rcu(&tg->rcu, sched_free_group_rcu);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
11
52.38%
5
71.43%
Dario Faggioli
9
42.86%
1
14.29%
Ingo Molnar
1
4.76%
1
14.29%
Total
21
100.00%
7
100.00%



void sched_offline_group(struct task_group *tg)
{
	unsigned long flags;

	/* End participation in shares distribution: */
	unregister_fair_sched_group(tg);

	spin_lock_irqsave(&task_group_lock, flags);
	list_del_rcu(&tg->list);
	list_del_rcu(&tg->siblings);
	spin_unlock_irqrestore(&task_group_lock, flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
27
51.92%
2
20.00%
Peter Zijlstra
10
19.23%
4
40.00%
Juri Lelli
6
11.54%
1
10.00%
Srivatsa Vaddagiri
4
7.69%
1
10.00%
Kirill Tkhai
4
7.69%
1
10.00%
Ingo Molnar
1
1.92%
1
10.00%
Total
52
100.00%
10
100.00%



static void sched_change_group(struct task_struct *tsk, int type)
{
	struct task_group *tg;

	/*
         * All callers are synchronized by task_rq_lock(); we do not use RCU
         * which is pointless here. Thus, we pass "true" to task_css_check()
         * to prevent lockdep warnings.
         */
	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
			  struct task_group, css);
	tg = autogroup_task_group(tsk, tg);
	tsk->sched_task_group = tg;

#ifdef CONFIG_FAIR_GROUP_SCHED
	if (tsk->sched_class->task_change_group)
		tsk->sched_class->task_change_group(tsk, type);
	else
#endif
		set_task_rq(tsk, task_cpu(tsk));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vincent Guittot
53
59.55%
1
7.69%
Peter Zijlstra
12
13.48%
5
38.46%
Dario Faggioli
7
7.87%
1
7.69%
Clark Williams
6
6.74%
1
7.69%
Kirill Tkhai
5
5.62%
2
15.38%
Srivatsa Vaddagiri
4
4.49%
2
15.38%
Juri Lelli
2
2.25%
1
7.69%
Total
89
100.00%
13
100.00%

/*
 * Change task's runqueue when it moves between groups.
 *
 * The caller of this function should have put the task in its new group by
 * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
 * its new group.
 */


void sched_move_task(struct task_struct *tsk)
{
	int queued, running, queue_flags =
		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
	struct rq_flags rf;
	struct rq *rq;

	rq = task_rq_lock(tsk, &rf);
	update_rq_clock(rq);

	running = task_current(rq, tsk);
	queued = task_on_rq_queued(tsk);

	if (queued)
		dequeue_task(rq, tsk, queue_flags);
	if (running)
		put_prev_task(rq, tsk);

	sched_change_group(tsk, TASK_MOVE_GROUP);

	if (queued)
		enqueue_task(rq, tsk, queue_flags);
	if (running)
		set_curr_task(rq, tsk);

	task_rq_unlock(rq, tsk, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dario Faggioli
56
43.75%
1
7.14%
Peter Zijlstra
51
39.84%
9
64.29%
Vincent Guittot
9
7.03%
2
14.29%
Srivatsa Vaddagiri
6
4.69%
1
7.14%
Kirill Tkhai
6
4.69%
1
7.14%
Total
128
100.00%
14
100.00%



static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
{
	return css ? container_of(css, struct task_group, css) : NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
19
65.52%
1
33.33%
Tejun Heo
8
27.59%
1
33.33%
Peter Zijlstra
2
6.90%
1
33.33%
Total
29
100.00%
3
100.00%


static struct cgroup_subsys_state *

cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct task_group *parent = css_tg(parent_css);
	struct task_group *tg;

	if (!parent) {
		/* This is early initialization for the top cgroup */
		return &root_task_group.css;
	}

	tg = sched_create_group(parent);
	if (IS_ERR(tg))
		return ERR_PTR(-ENOMEM);

	return &tg->css;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
36
52.17%
3
30.00%
Tejun Heo
13
18.84%
2
20.00%
Dhaval Giani
9
13.04%
2
20.00%
Konstantin Khlebnikov
7
10.14%
1
10.00%
Peter Zijlstra
3
4.35%
1
10.00%
Yong Zhang
1
1.45%
1
10.00%
Total
69
100.00%
10
100.00%

/* Expose task group only after completing cgroup initialization */


static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{
	struct task_group *tg = css_tg(css);
	struct task_group *parent = css_tg(css->parent);

	if (parent)
		sched_online_group(tg, parent);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Konstantin Khlebnikov
37
78.72%
1
50.00%
Li Zefan
10
21.28%
1
50.00%
Total
47
100.00%
2
100.00%



static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
	struct task_group *tg = css_tg(css);

	sched_offline_group(tg);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
10
38.46%
1
16.67%
Peter Zijlstra
8
30.77%
3
50.00%
Paul Turner
4
15.38%
1
16.67%
Tejun Heo
4
15.38%
1
16.67%
Total
26
100.00%
6
100.00%



static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{
	struct task_group *tg = css_tg(css);

	/*
         * Relies on the RCU grace period between css_released() and this.
         */
	sched_free_group(tg);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Li Zefan
20
74.07%
1
33.33%
Tejun Heo
4
14.81%
1
33.33%
Peter Zijlstra
3
11.11%
1
33.33%
Total
27
100.00%
3
100.00%

/*
 * This is called before wake_up_new_task(), therefore we really only
 * have to set its group bits, all the other stuff does not apply.
 */


static void cpu_cgroup_fork(struct task_struct *task)
{
	struct rq_flags rf;
	struct rq *rq;

	rq = task_rq_lock(task, &rf);

	update_rq_clock(rq);
	sched_change_group(task, TASK_SET_GROUP);

	task_rq_unlock(rq, task, &rf);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vincent Guittot
30
57.69%
1
33.33%
Kirill Tkhai
17
32.69%
1
33.33%
Peter Zijlstra
5
9.62%
1
33.33%
Total
52
100.00%
3
100.00%



static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *css;
	int ret = 0;

	cgroup_taskset_for_each(task, css, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
		if (!sched_rt_can_attach(css_tg(css), task))
			return -EINVAL;
#else
		/* We don't support RT-tasks being in separate groups */
		if (task->sched_class != &fair_sched_class)
			return -EINVAL;
#endif
		/*
                 * Serialize against wake_up_new_task() such that if its
                 * running, we're sure to observe its full state.
                 */
		raw_spin_lock_irq(&task->pi_lock);
		/*
                 * Avoid calling sched_move_task() before wake_up_new_task()
                 * has happened. This would lead to problems with PELT, due to
                 * move wanting to detach+attach while we're not attached yet.
                 */
		if (task->state == TASK_NEW)
			ret = -EINVAL;
		raw_spin_unlock_irq(&task->pi_lock);

		if (ret)
			break;
	}
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
61
53.98%
4
36.36%
Tejun Heo
27
23.89%
3
27.27%
Srivatsa Vaddagiri
23
20.35%
3
27.27%
Dhaval Giani
2
1.77%
1
9.09%
Total
113
100.00%
11
100.00%



static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *css;

	cgroup_taskset_for_each(task, css, tset)
		sched_move_task(task);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
22
64.71%
2
50.00%
Srivatsa Vaddagiri
7
20.59%
1
25.00%
Dhaval Giani
5
14.71%
1
25.00%
Total
34
100.00%
4
100.00%

#ifdef CONFIG_FAIR_GROUP_SCHED


static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
				struct cftype *cftype, u64 shareval)
{
	return sched_group_set_shares(css_tg(css), scale_load(shareval));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
12
36.36%
2
28.57%
Srivatsa Vaddagiri
11
33.33%
1
14.29%
Paul Menage
4
12.12%
2
28.57%
Tejun Heo
4
12.12%
1
14.29%
Nikhil P Rao
2
6.06%
1
14.29%
Total
33
100.00%
7
100.00%



static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct task_group *tg = css_tg(css);

	return (u64) scale_load_down(tg->shares);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
16
43.24%
1
16.67%
Peter Zijlstra
15
40.54%
2
33.33%
Tejun Heo
4
10.81%
1
16.67%
Paul Menage
1
2.70%
1
16.67%
Nikhil P Rao
1
2.70%
1
16.67%
Total
37
100.00%
6
100.00%

#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);


const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; 
/* 1s */

const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; 
/* 1ms */

static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);



static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
{
	int i, ret = 0, runtime_enabled, runtime_was_enabled;
	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;

	if (tg == &root_task_group)
		return -EINVAL;

	/*
         * Ensure we have at some amount of bandwidth every period.  This is
         * to prevent reaching a state of large arrears when throttled via
         * entity_tick() resulting in prolonged exit starvation.
         */
	if (quota < min_cfs_quota_period || period < min_cfs_quota_period)
		return -EINVAL;

	/*
         * Likewise, bound things on the otherside by preventing insane quota
         * periods.  This also allows us to normalize in computing quota
         * feasibility.
         */
	if (period > max_cfs_quota_period)
		return -EINVAL;

	/*
         * Prevent race between setting of cfs_rq->runtime_enabled and
         * unthrottle_offline_cfs_rqs().
         */
	get_online_cpus();
	mutex_lock(&cfs_constraints_mutex);
	ret = __cfs_schedulable(tg, period, quota);
	if (ret)
		goto out_unlock;

	runtime_enabled = quota != RUNTIME_INF;
	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
	/*
         * If we need to toggle cfs_bandwidth_used, off->on must occur
         * before making related changes, and on->off must occur afterwards
         */
	if (runtime_enabled && !runtime_was_enabled)
		cfs_bandwidth_usage_inc();
	raw_spin_lock_irq(&cfs_b->lock);
	cfs_b->period = ns_to_ktime(period);
	cfs_b->quota = quota;

	__refill_cfs_bandwidth_runtime(cfs_b);

	/* Restart the period timer (if active) to handle new period expiry: */
	if (runtime_enabled)
		start_cfs_bandwidth(cfs_b);

	raw_spin_unlock_irq(&cfs_b->lock);

	for_each_online_cpu(i) {
		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
		struct rq *rq = cfs_rq->rq;
		struct rq_flags rf;

		rq_lock_irq(rq, &rf);
		cfs_rq->runtime_enabled = runtime_enabled;
		cfs_rq->runtime_remaining = 0;

		if (cfs_rq->throttled)
			unthrottle_cfs_rq(cfs_rq);
		rq_unlock_irq(rq, &rf);
	}
	if (runtime_was_enabled && !runtime_enabled)
		cfs_bandwidth_usage_dec();
out_unlock:
	mutex_unlock(&cfs_constraints_mutex);
	put_online_cpus();

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
124
46.27%
9
42.86%
Paul Turner
113
42.16%
7
33.33%
Ben Segall
18
6.72%
1
4.76%
Kirill Tkhai
8
2.99%
1
4.76%
Dhaval Giani
3
1.12%
1
4.76%
Ingo Molnar
1
0.37%
1
4.76%
Thomas Gleixner
1
0.37%
1
4.76%
Total
268
100.00%
21
100.00%



int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
	u64 quota, period;

	period = ktime_to_ns(tg->cfs_bandwidth.period);
	if (cfs_quota_us < 0)
		quota = RUNTIME_INF;
	else
		quota = (u64)cfs_quota_us * NSEC_PER_USEC;

	return tg_set_cfs_bandwidth(tg, period, quota);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
38
64.41%
2
66.67%
Paul Turner
21
35.59%
1
33.33%
Total
59
100.00%
3
100.00%



long tg_get_cfs_quota(struct task_group *tg)
{
	u64 quota_us;

	if (tg->cfs_bandwidth.quota == RUNTIME_INF)
		return -1;

	quota_us = tg->cfs_bandwidth.quota;
	do_div(quota_us, NSEC_PER_USEC);

	return quota_us;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
38
84.44%
3
75.00%
Paul Turner
7
15.56%
1
25.00%
Total
45
100.00%
4
100.00%



int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
	u64 quota, period;

	period = (u64)cfs_period_us * NSEC_PER_USEC;
	quota = tg->cfs_bandwidth.quota;

	return tg_set_cfs_bandwidth(tg, period, quota);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
34
75.56%
2
66.67%
Paul Turner
11
24.44%
1
33.33%
Total
45
100.00%
3
100.00%



long tg_get_cfs_period(struct task_group *tg)
{
	u64 cfs_period_us;

	cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period);
	do_div(cfs_period_us, NSEC_PER_USEC);

	return cfs_period_us;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
76.47%
2
50.00%
Paul Turner
6
17.65%
1
25.00%
Dhaval Giani
2
5.88%
1
25.00%
Total
34
100.00%
4
100.00%



static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
				  struct cftype *cft)
{
	return tg_get_cfs_quota(css_tg(css));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
11
44.00%
1
25.00%
Paul Turner
5
20.00%
1
25.00%
Peter Zijlstra
5
20.00%
1
25.00%
Tejun Heo
4
16.00%
1
25.00%
Total
25
100.00%
4
100.00%



static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
				   struct cftype *cftype, s64 cfs_quota_us)
{
	return tg_set_cfs_quota(css_tg(css), cfs_quota_us);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Turner
13
43.33%
1
25.00%
Srivatsa Vaddagiri
11
36.67%
1
25.00%
Tejun Heo
4
13.33%
1
25.00%
Dhaval Giani
2
6.67%
1
25.00%
Total
30
100.00%
4
100.00%



static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
				   struct cftype *cft)
{
	return tg_get_cfs_period(css_tg(css));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
13
52.00%
1
33.33%
Paul Turner
8
32.00%
1
33.33%
Tejun Heo
4
16.00%
1
33.33%
Total
25
100.00%
3
100.00%



static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
				    struct cftype *cftype, u64 cfs_period_us)
{
	return tg_set_cfs_period(css_tg(css), cfs_period_us);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Srivatsa Vaddagiri
12
40.00%
1
20.00%
Paul Turner
9
30.00%
1
20.00%
Tejun Heo
4
13.33%
1
20.00%
Peter Zijlstra
3
10.00%
1
20.00%
Dhaval Giani
2
6.67%
1
20.00%
Total
30
100.00%
5
100.00%


struct cfs_schedulable_data {
	
struct task_group *tg;
	

u64 period, quota;
};

/*
 * normalize group quota/period to be quota/max_period
 * note: units are usecs
 */


static u64 normalize_cfs_quota(struct task_group *tg,
			       struct cfs_schedulable_data *d)
{
	u64 quota, period;

	if (tg == d->tg) {
		period = d->period;
		quota = d->quota;
	} else {
		period = tg_get_cfs_period(tg);
		quota = tg_get_cfs_quota(tg);
	}

	/* note: these should typically be equivalent */
	if (quota == RUNTIME_INF || quota == -1)
		return RUNTIME_INF;

	return to_ratio(period, quota);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Turner
70
84.34%
1
50.00%
Srivatsa Vaddagiri
13
15.66%
1
50.00%
Total
83
100.00%
2
100.00%



static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
{
	struct cfs_schedulable_data *d = data;
	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
	s64 quota = 0, parent_quota = -1;

	if (!tg->parent) {
		quota = RUNTIME_INF;
	} else {
		struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth;

		quota = normalize_cfs_quota(tg, d);
		parent_quota = parent_b->hierarchical_quota;

		/*
                 * Ensure max(child_quota) <= parent_quota, inherit when no
                 * limit is set:
                 */
		if (quota == RUNTIME_INF)
			quota = parent_quota;
		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
			return -EINVAL;
	}
	cfs_b->hierarchical_quota = quota;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Turner
94
78.33%
1
16.67%
Peter Zijlstra
23
19.17%
3
50.00%
Zhihui Zhang
2
1.67%
1
16.67%
Ingo Molnar
1
0.83%
1
16.67%
Total
120
100.00%
6
100.00%



static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{
	int ret;
	struct cfs_schedulable_data data = {
		.tg = tg,
		.period = period,
		.quota = quota,
        };

	if (quota != RUNTIME_INF) {
		do_div(data.period, NSEC_PER_USEC);
		do_div(data.quota, NSEC_PER_USEC);
	}

	rcu_read_lock();
	ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
	rcu_read_unlock();

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Turner
71
80.68%
2
40.00%
Srivatsa Vaddagiri
13
14.77%
1
20.00%
Nikhil P Rao
2
2.27%
1
20.00%
Paul Menage
2
2.27%
1
20.00%
Total
88
100.00%
5
100.00%



static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
{
	struct task_group *tg = css_tg(seq_css(sf));
	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;

	seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);

	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Nikhil P Rao
35
47.30%
2
25.00%
Tejun Heo
19
25.68%
4
50.00%
Srivatsa Vaddagiri
17
22.97%
1
12.50%
Peter Zijlstra
3
4.05%
1
12.50%
Total
74
100.00%
8
100.00%

#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED


static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
				struct cftype *cft, s64 val)
{
	return sched_group_set_rt_runtime(css_tg(css), val);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
23
76.67%
2
40.00%
Tejun Heo
4
13.33%
1
20.00%
Paul Menage
2
6.67%
1
20.00%
Mirco Tischler
1
3.33%
1
20.00%
Total
30
100.00%
5
100.00%



static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	return sched_group_rt_runtime(css_tg(css));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
19
76.00%
2
50.00%
Tejun Heo
4
16.00%
1
25.00%
Paul Menage
2
8.00%
1
25.00%
Total
25
100.00%
4
100.00%



static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
				    struct cftype *cftype, u64 rt_period_us)
{
	return sched_group_set_rt_period(css_tg(css), rt_period_us);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
26
86.67%
1
50.00%
Tejun Heo
4
13.33%
1
50.00%
Total
30
100.00%
2
100.00%



static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
				   struct cftype *cft)
{
	return sched_group_rt_period(css_tg(css));
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
21
84.00%
1
50.00%
Tejun Heo
4
16.00%
1
50.00%
Total
25
100.00%
2
100.00%

#endif /* CONFIG_RT_GROUP_SCHED */


static struct cftype cpu_legacy_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
	{
		.name = "shares",
		.read_u64 = cpu_shares_read_u64,
		.write_u64 = cpu_shares_write_u64,
        },
#endif
#ifdef CONFIG_CFS_BANDWIDTH
	{
		.name = "cfs_quota_us",
		.read_s64 = cpu_cfs_quota_read_s64,
		.write_s64 = cpu_cfs_quota_write_s64,
        },
	{
		.name = "cfs_period_us",
		.read_u64 = cpu_cfs_period_read_u64,
		.write_u64 = cpu_cfs_period_write_u64,
        },
	{
		.name = "stat",
		.seq_show = cpu_cfs_stat_show,
        },
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	{
		.name = "rt_runtime_us",
		.read_s64 = cpu_rt_runtime_read,
		.write_s64 = cpu_rt_runtime_write,
        },
	{
		.name = "rt_period_us",
		.read_u64 = cpu_rt_period_read_uint,
		.write_u64 = cpu_rt_period_write_uint,
        },
#endif
	{ }	/* Terminate */
};



static int cpu_extra_stat_show(struct seq_file *sf,
			       struct cgroup_subsys_state *css)
{
#ifdef CONFIG_CFS_BANDWIDTH
	{
		struct task_group *tg = css_tg(css);
		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
		u64 throttled_usec;

		throttled_usec = cfs_b->throttled_time;
		do_div(throttled_usec, NSEC_PER_USEC);

		seq_printf(sf, "nr_periods %d\n"
			   "nr_throttled %d\n"
			   "throttled_usec %llu\n",
			   cfs_b->nr_periods, cfs_b->nr_throttled,
			   throttled_usec);
	}
#endif
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
78
96.30%
2
66.67%
Srivatsa Vaddagiri
3
3.70%
1
33.33%
Total
81
100.00%
3
100.00%

#ifdef CONFIG_FAIR_GROUP_SCHED


static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct task_group *tg = css_tg(css);
	u64 weight = scale_load_down(tg->shares);

	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
46
100.00%
1
100.00%
Total
46
100.00%
1
100.00%



static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
				struct cftype *cft, u64 weight)
{
	/*
         * cgroup weight knobs should use the common MIN, DFL and MAX
         * values which are 1, 100 and 10000 respectively.  While it loses
         * a bit of range on both ends, it maps pretty well onto the shares
         * value used by scheduler and the round-trip conversions preserve
         * the original value over the entire range.
         */
	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
		return -ERANGE;

	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);

	return sched_group_set_shares(css_tg(css), scale_load(weight));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
58
98.31%
1
50.00%
Konstantin Khlebnikov
1
1.69%
1
50.00%
Total
59
100.00%
2
100.00%



static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
				    struct cftype *cft)
{
	unsigned long weight = scale_load_down(css_tg(css)->shares);
	int last_delta = INT_MAX;
	int prio, delta;

	/* find the closest nice value to the current weight */
	for (prio = 0; prio < ARRAY_SIZE(sched_prio_to_weight); prio++) {
		delta = abs(sched_prio_to_weight[prio] - weight);
		if (delta >= last_delta)
			break;
		last_delta = delta;
	}

	return PRIO_TO_NICE(prio - 1 + MAX_RT_PRIO);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
90
97.83%
1
50.00%
Li Zefan
2
2.17%
1
50.00%
Total
92
100.00%
2
100.00%



static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
				     struct cftype *cft, s64 nice)
{
	unsigned long weight;

	if (nice < MIN_NICE || nice > MAX_NICE)
		return -ERANGE;

	weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
	return sched_group_set_shares(css_tg(css), scale_load(weight));
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
63
100.00%
1
100.00%
Total
63
100.00%
1
100.00%

#endif



static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
						  long period, long quota)
{
	if (quota < 0)
		seq_puts(sf, "max");
	else
		seq_printf(sf, "%ld", quota);

	seq_printf(sf, " %ld\n", period);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
50
100.00%
1
100.00%
Total
50
100.00%
1
100.00%

/* caller should put the current value in *@periodp before calling */


static int __maybe_unused cpu_period_quota_parse(char *buf,
						 u64 *periodp, u64 *quotap)
{
	char tok[21];	/* U64_MAX */

	if (!sscanf(buf, "%s %llu", tok, periodp))
		return -EINVAL;

	*periodp *= NSEC_PER_USEC;

	if (sscanf(tok, "%llu", quotap))
		*quotap *= NSEC_PER_USEC;
	else if (!strcmp(tok, "max"))
		*quotap = RUNTIME_INF;
	else
		return -EINVAL;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
89
100.00%
1
100.00%
Total
89
100.00%
1
100.00%

#ifdef CONFIG_CFS_BANDWIDTH


static int cpu_max_show(struct seq_file *sf, void *v)
{
	struct task_group *tg = css_tg(seq_css(sf));

	cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg));
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
46
100.00%
1
100.00%
Total
46
100.00%
1
100.00%



static ssize_t cpu_max_write(struct kernfs_open_file *of,
			     char *buf, size_t nbytes, loff_t off)
{
	struct task_group *tg = css_tg(of_css(of));
	u64 period = tg_get_cfs_period(tg);
	u64 quota;
	int ret;

	ret = cpu_period_quota_parse(buf, &period, &quota);
	if (!ret)
		ret = tg_set_cfs_bandwidth(tg, period, quota);
	return ret ?: nbytes;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
83
100.00%
1
100.00%
Total
83
100.00%
1
100.00%

#endif


static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
	{
		.name = "weight",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = cpu_weight_read_u64,
		.write_u64 = cpu_weight_write_u64,
        },
	{
		.name = "weight.nice",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_s64 = cpu_weight_nice_read_s64,
		.write_s64 = cpu_weight_nice_write_s64,
        },
#endif
#ifdef CONFIG_CFS_BANDWIDTH
	{
		.name = "max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = cpu_max_show,
		.write = cpu_max_write,
        },
#endif
	{ }	/* terminate */
};


struct cgroup_subsys cpu_cgrp_subsys = {
	.css_alloc	= cpu_cgroup_css_alloc,
	.css_online	= cpu_cgroup_css_online,
	.css_released	= cpu_cgroup_css_released,
	.css_free	= cpu_cgroup_css_free,
	.css_extra_stat_show = cpu_extra_stat_show,
	.fork		= cpu_cgroup_fork,
	.can_attach	= cpu_cgroup_can_attach,
	.attach		= cpu_cgroup_attach,
	.legacy_cftypes	= cpu_legacy_files,
	.dfl_cftypes	= cpu_files,
	.early_init	= true,
	.threaded	= true,
};

#endif	/* CONFIG_CGROUP_SCHED */



void dump_cpu_task(int cpu)
{
	pr_info("Task dump for CPU %d:\n", cpu);
	sched_show_task(cpu_curr(cpu));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul E. McKenney
23
100.00%
1
100.00%
Total
23
100.00%
1
100.00%

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */

const int sched_prio_to_weight[40] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
 *
 * In cases where the weight does not change often, we can use the
 * precalculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */

const u32 sched_prio_to_wmult[40] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Peter Zijlstra
10878
47.97%
203
26.30%
Dario Faggioli
3314
14.62%
6
0.78%
Tejun Heo
1157
5.10%
25
3.24%
Ingo Molnar
776
3.42%
51
6.61%
Frédéric Weisbecker
757
3.34%
26
3.37%
Paul Turner
548
2.42%
11
1.42%
Thomas Gleixner
489
2.16%
35
4.53%
Srivatsa Vaddagiri
313
1.38%
5
0.65%
Andi Kleen
271
1.20%
5
0.65%
Mel Gorman
233
1.03%
8
1.04%
Nico Pitre
228
1.01%
5
0.65%
Andrew Morton
214
0.94%
19
2.46%
Vincent Guittot
204
0.90%
6
0.78%
Steven Rostedt
202
0.89%
13
1.68%
Linus Torvalds
187
0.82%
19
2.46%
Juri Lelli
167
0.74%
8
1.04%
Kirill Tkhai
137
0.60%
8
1.04%
Gregory Haskins
113
0.50%
9
1.17%
Al Viro
112
0.49%
1
0.13%
Josh Poimboeuf
101
0.45%
4
0.52%
Linus Torvalds (pre-git)
101
0.45%
18
2.33%
Nicholas Piggin
100
0.44%
10
1.30%
Wanpeng Li
95
0.42%
5
0.65%
Mike Galbraith
94
0.41%
13
1.68%
Matt Fleming
90
0.40%
3
0.39%
Oleg Nesterov
86
0.38%
12
1.55%
Rusty Russell
76
0.34%
17
2.20%
Nikhil P Rao
73
0.32%
3
0.39%
Giovanni Gherdovich
70
0.31%
1
0.13%
Paul E. McKenney
66
0.29%
10
1.30%
Konstantin Khlebnikov
56
0.25%
2
0.26%
Joonwoo Park
53
0.23%
1
0.13%
Chuansheng Liu
46
0.20%
1
0.13%
Li Zefan
44
0.19%
2
0.26%
Vegard Nossum
41
0.18%
4
0.52%
Andrew Lutomirski
41
0.18%
7
0.91%
Suresh B. Siddha
38
0.17%
8
1.04%
Dhaval Giani
33
0.15%
6
0.78%
Byungchul Park
29
0.13%
2
0.26%
Avi Kivity
29
0.13%
1
0.13%
Heiko Carstens
29
0.13%
4
0.52%
Greg Kroah-Hartman
28
0.12%
2
0.26%
Venkatesh Pallipadi
28
0.12%
7
0.91%
Alexey Dobriyan
26
0.11%
1
0.13%
Anton Blanchard
24
0.11%
1
0.13%
Rick Lindsley
24
0.11%
1
0.13%
Robert Love
24
0.11%
2
0.26%
Waiman Long
24
0.11%
1
0.13%
Paul Menage
22
0.10%
4
0.52%
Kirill V Tkhai
22
0.10%
1
0.13%
Dean Nelson
20
0.09%
1
0.13%
xiaofeng.yan
20
0.09%
1
0.13%
Rik Van Riel
20
0.09%
4
0.52%
Stanislaw Gruszka
20
0.09%
2
0.26%
Peter Williams
19
0.08%
2
0.26%
Milton D. Miller II
19
0.08%
4
0.52%
Mike Travis
19
0.08%
1
0.13%
Vatika Harlalka
18
0.08%
1
0.13%
Ben Segall
18
0.08%
1
0.13%
Glauber de Oliveira Costa
17
0.07%
2
0.26%
Paul Jackson
16
0.07%
2
0.26%
Tang Chen
16
0.07%
2
0.26%
Srikar Dronamraju
16
0.07%
2
0.26%
Tetsuo Handa
15
0.07%
2
0.26%
Cheng Chao
14
0.06%
1
0.13%
Patrick Bellasi
14
0.06%
1
0.13%
Henrik Austad
14
0.06%
1
0.13%
Arnaldo Carvalho de Melo
14
0.06%
2
0.26%
Dongsheng Yang
14
0.06%
3
0.39%
Roland McGrath
13
0.06%
1
0.13%
Alex Thorlton
12
0.05%
1
0.13%
Brian Silverman
12
0.05%
1
0.13%
Luca Abeni
12
0.05%
3
0.39%
Dmitry Adamushko
11
0.05%
3
0.39%
Viresh Kumar
11
0.05%
1
0.13%
Srivatsa S. Bhat
10
0.04%
2
0.26%
Mathieu Desnoyers
10
0.04%
2
0.26%
Guillaume Chazarain
9
0.04%
1
0.13%
Josh Snyder
9
0.04%
1
0.13%
Chris Wright
9
0.04%
1
0.13%
Jann Horn
9
0.04%
1
0.13%
Con Kolivas
9
0.04%
3
0.39%
Alex Shi
9
0.04%
2
0.26%
Gautham R. Shenoy
9
0.04%
4
0.52%
Daniel Bristot de Oliveira
9
0.04%
1
0.13%
Jens Axboe
8
0.04%
1
0.13%
Mark Brown
8
0.04%
1
0.13%
Adrian Bunk
8
0.04%
1
0.13%
Maksim Krasnyanskiy
7
0.03%
3
0.39%
Eric Sandeen
7
0.03%
1
0.13%
David P. Quigley
7
0.03%
1
0.13%
Martin Schwidefsky
7
0.03%
3
0.39%
Nathan Lynch
6
0.03%
1
0.13%
Clark Williams
6
0.03%
1
0.13%
Laurent Vivier
6
0.03%
1
0.13%
Matt Mackall
6
0.03%
1
0.13%
Lennart Poettering
6
0.03%
1
0.13%
Corey Minyard
6
0.03%
1
0.13%
Jason Low
6
0.03%
2
0.26%
Hiroshi Shimamoto
6
0.03%
1
0.13%
Hidetoshi Seto
6
0.03%
2
0.26%
Motohiro Kosaki
5
0.02%
2
0.26%
Jack Steiner
5
0.02%
1
0.13%
Christian Ehrhardt
5
0.02%
1
0.13%
Jason Baron
5
0.02%
1
0.13%
Christoph Lameter
5
0.02%
3
0.39%
William Lee Irwin III
5
0.02%
2
0.26%
Christian Bornträger
5
0.02%
1
0.13%
Rabin Vincent
5
0.02%
1
0.13%
Mark Rutland
5
0.02%
1
0.13%
Yong Zhang
5
0.02%
3
0.39%
Bob Miller
5
0.02%
1
0.13%
Masami Hiramatsu
5
0.02%
2
0.26%
Arjan van de Ven
5
0.02%
2
0.26%
Davide Libenzi
5
0.02%
1
0.13%
Olivier Croquette
4
0.02%
1
0.13%
Xie XiuQi
4
0.02%
1
0.13%
Tim Chen
4
0.02%
1
0.13%
Balbir Singh
4
0.02%
1
0.13%
Jason Wessel
4
0.02%
1
0.13%
Dinakar Guniguntala
4
0.02%
1
0.13%
Matthew Wilcox
4
0.02%
1
0.13%
David Howells
4
0.02%
2
0.26%
Andrey Ryabinin
4
0.02%
1
0.13%
Martin J. Bligh
4
0.02%
1
0.13%
Michael S. Tsirkin
4
0.02%
1
0.13%
Keith Owens
3
0.01%
1
0.13%
Davidlohr Bueso A
3
0.01%
2
0.26%
John Hawkes
3
0.01%
1
0.13%
Michael Kerrisk
3
0.01%
1
0.13%
Arnd Bergmann
3
0.01%
1
0.13%
Rakib Mullick
2
0.01%
1
0.13%
Eduard - Gabriel Munteanu
2
0.01%
1
0.13%
Pavel Emelyanov
2
0.01%
1
0.13%
Dave Jones
2
0.01%
1
0.13%
Zhihui Zhang
2
0.01%
1
0.13%
Joe Perches
2
0.01%
1
0.13%
Aaron Tomlin
2
0.01%
1
0.13%
Jeremy Fitzhardinge
2
0.01%
1
0.13%
Lucas De Marchi
2
0.01%
1
0.13%
Gerald Schaefer
2
0.01%
1
0.13%
Benjamin LaHaise
2
0.01%
1
0.13%
Namhyung Kim
2
0.01%
2
0.26%
Dominik Dingel
1
0.00%
1
0.13%
Randy Dunlap
1
0.00%
1
0.13%
Eric Paris
1
0.00%
1
0.13%
David Chinner
1
0.00%
1
0.13%
Paul Mackerras
1
0.00%
1
0.13%
Ankita Garg
1
0.00%
1
0.13%
Neil Brown
1
0.00%
1
0.13%
Zachary Amsden
1
0.00%
1
0.13%
Yacine Belkadi
1
0.00%
1
0.13%
Darren Hart
1
0.00%
1
0.13%
Morten Rasmussen
1
0.00%
1
0.13%
Harald Gustafsson
1
0.00%
1
0.13%
Eric W. Biedermann
1
0.00%
1
0.13%
Carsten Emde
1
0.00%
1
0.13%
Mirco Tischler
1
0.00%
1
0.13%
Jonathan Corbet
1
0.00%
1
0.13%
Richard Weinberger
1
0.00%
1
0.13%
Total
22675
100.00%
772
100.00%
Directory: kernel/sched

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.