aafd9d6a46
Pull timer/dynticks updates from Ingo Molnar: "This tree contains misc dynticks updates: a fix and three cleanups" * 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: sched/nohz: Fix overflow error in scheduler_tick_max_deferment() nohz_full: fix code style issue of tick_nohz_full_stop_tick nohz: Get timekeeping max deferment outside jiffies_lock tick: Rename tick_check_idle() to tick_irq_enter()
7980 lines
188 KiB
C
7980 lines
188 KiB
C
/*
|
|
* kernel/sched/core.c
|
|
*
|
|
* Kernel scheduler and related syscalls
|
|
*
|
|
* Copyright (C) 1991-2002 Linus Torvalds
|
|
*
|
|
* 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
|
|
* make semaphores SMP safe
|
|
* 1998-11-19 Implemented schedule_timeout() and related stuff
|
|
* by Andrea Arcangeli
|
|
* 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
|
|
* hybrid priority-list and round-robin design with
|
|
* an array-switch method of distributing timeslices
|
|
* and per-CPU runqueues. Cleanups and useful suggestions
|
|
* by Davide Libenzi, preemptible kernel bits by Robert Love.
|
|
* 2003-09-03 Interactivity tuning by Con Kolivas.
|
|
* 2004-04-02 Scheduler domains code by Nick Piggin
|
|
* 2007-04-15 Work begun on replacing all interactivity tuning with a
|
|
* fair scheduling design by Con Kolivas.
|
|
* 2007-05-05 Load balancing (smp-nice) and other improvements
|
|
* by Peter Williams
|
|
* 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
|
|
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
|
|
* 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
|
|
* Thomas Gleixner, Mike Kravetz
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/init.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/highmem.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/capability.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/debug_locks.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/security.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/freezer.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/times.h>
|
|
#include <linux/tsacct_kern.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/delayacct.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init_task.h>
|
|
#include <linux/binfmts.h>
|
|
#include <linux/context_tracking.h>
|
|
|
|
#include <asm/switch_to.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/irq_regs.h>
|
|
#include <asm/mutex.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>
|
|
|
|
void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
|
|
{
|
|
unsigned long delta;
|
|
ktime_t soft, hard, now;
|
|
|
|
for (;;) {
|
|
if (hrtimer_active(period_timer))
|
|
break;
|
|
|
|
now = hrtimer_cb_get_time(period_timer);
|
|
hrtimer_forward(period_timer, now, period);
|
|
|
|
soft = hrtimer_get_softexpires(period_timer);
|
|
hard = hrtimer_get_expires(period_timer);
|
|
delta = ktime_to_ns(ktime_sub(hard, soft));
|
|
__hrtimer_start_range_ns(period_timer, soft, delta,
|
|
HRTIMER_MODE_ABS_PINNED, 0);
|
|
}
|
|
}
|
|
|
|
DEFINE_MUTEX(sched_domains_mutex);
|
|
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
|
|
|
|
static void update_rq_clock_task(struct rq *rq, s64 delta);
|
|
|
|
void update_rq_clock(struct rq *rq)
|
|
{
|
|
s64 delta;
|
|
|
|
if (rq->skip_clock_update > 0)
|
|
return;
|
|
|
|
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
|
|
rq->clock += delta;
|
|
update_rq_clock_task(rq, delta);
|
|
}
|
|
|
|
/*
|
|
* Debugging: various feature bits
|
|
*/
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
(1UL << __SCHED_FEAT_##name) * enabled |
|
|
|
|
const_debug unsigned int sysctl_sched_features =
|
|
#include "features.h"
|
|
0;
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
#define SCHED_FEAT(name, enabled) \
|
|
#name ,
|
|
|
|
static const char * const sched_feat_names[] = {
|
|
#include "features.h"
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
static int sched_feat_show(struct seq_file *m, void *v)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < __SCHED_FEAT_NR; i++) {
|
|
if (!(sysctl_sched_features & (1UL << i)))
|
|
seq_puts(m, "NO_");
|
|
seq_printf(m, "%s ", sched_feat_names[i]);
|
|
}
|
|
seq_puts(m, "\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
|
|
#define jump_label_key__true STATIC_KEY_INIT_TRUE
|
|
#define jump_label_key__false STATIC_KEY_INIT_FALSE
|
|
|
|
#define SCHED_FEAT(name, enabled) \
|
|
jump_label_key__##enabled ,
|
|
|
|
struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
|
|
#include "features.h"
|
|
};
|
|
|
|
#undef SCHED_FEAT
|
|
|
|
static void sched_feat_disable(int i)
|
|
{
|
|
if (static_key_enabled(&sched_feat_keys[i]))
|
|
static_key_slow_dec(&sched_feat_keys[i]);
|
|
}
|
|
|
|
static void sched_feat_enable(int i)
|
|
{
|
|
if (!static_key_enabled(&sched_feat_keys[i]))
|
|
static_key_slow_inc(&sched_feat_keys[i]);
|
|
}
|
|
#else
|
|
static void sched_feat_disable(int i) { };
|
|
static void sched_feat_enable(int i) { };
|
|
#endif /* HAVE_JUMP_LABEL */
|
|
|
|
static int sched_feat_set(char *cmp)
|
|
{
|
|
int i;
|
|
int neg = 0;
|
|
|
|
if (strncmp(cmp, "NO_", 3) == 0) {
|
|
neg = 1;
|
|
cmp += 3;
|
|
}
|
|
|
|
for (i = 0; i < __SCHED_FEAT_NR; i++) {
|
|
if (strcmp(cmp, sched_feat_names[i]) == 0) {
|
|
if (neg) {
|
|
sysctl_sched_features &= ~(1UL << i);
|
|
sched_feat_disable(i);
|
|
} else {
|
|
sysctl_sched_features |= (1UL << i);
|
|
sched_feat_enable(i);
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
return i;
|
|
}
|
|
|
|
static ssize_t
|
|
sched_feat_write(struct file *filp, const char __user *ubuf,
|
|
size_t cnt, loff_t *ppos)
|
|
{
|
|
char buf[64];
|
|
char *cmp;
|
|
int i;
|
|
|
|
if (cnt > 63)
|
|
cnt = 63;
|
|
|
|
if (copy_from_user(&buf, ubuf, cnt))
|
|
return -EFAULT;
|
|
|
|
buf[cnt] = 0;
|
|
cmp = strstrip(buf);
|
|
|
|
i = sched_feat_set(cmp);
|
|
if (i == __SCHED_FEAT_NR)
|
|
return -EINVAL;
|
|
|
|
*ppos += cnt;
|
|
|
|
return cnt;
|
|
}
|
|
|
|
static int sched_feat_open(struct inode *inode, struct file *filp)
|
|
{
|
|
return single_open(filp, sched_feat_show, NULL);
|
|
}
|
|
|
|
static const struct file_operations sched_feat_fops = {
|
|
.open = sched_feat_open,
|
|
.write = sched_feat_write,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
static __init int sched_init_debug(void)
|
|
{
|
|
debugfs_create_file("sched_features", 0644, NULL, NULL,
|
|
&sched_feat_fops);
|
|
|
|
return 0;
|
|
}
|
|
late_initcall(sched_init_debug);
|
|
#endif /* CONFIG_SCHED_DEBUG */
|
|
|
|
/*
|
|
* Number of tasks to iterate in a single balance run.
|
|
* Limited because this is done with IRQs disabled.
|
|
*/
|
|
const_debug unsigned int sysctl_sched_nr_migrate = 32;
|
|
|
|
/*
|
|
* period over which we average the RT time consumption, measured
|
|
* in ms.
|
|
*
|
|
* default: 1s
|
|
*/
|
|
const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
|
|
|
|
/*
|
|
* period over which we measure -rt task cpu usage in us.
|
|
* default: 1s
|
|
*/
|
|
unsigned int sysctl_sched_rt_period = 1000000;
|
|
|
|
__read_mostly int scheduler_running;
|
|
|
|
/*
|
|
* part of the period that we allow rt tasks to run in us.
|
|
* default: 0.95s
|
|
*/
|
|
int sysctl_sched_rt_runtime = 950000;
|
|
|
|
/*
|
|
* __task_rq_lock - lock the rq @p resides on.
|
|
*/
|
|
static inline struct rq *__task_rq_lock(struct task_struct *p)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
lockdep_assert_held(&p->pi_lock);
|
|
|
|
for (;;) {
|
|
rq = task_rq(p);
|
|
raw_spin_lock(&rq->lock);
|
|
if (likely(rq == task_rq(p)))
|
|
return rq;
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
|
|
*/
|
|
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
|
|
__acquires(p->pi_lock)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
for (;;) {
|
|
raw_spin_lock_irqsave(&p->pi_lock, *flags);
|
|
rq = task_rq(p);
|
|
raw_spin_lock(&rq->lock);
|
|
if (likely(rq == task_rq(p)))
|
|
return rq;
|
|
raw_spin_unlock(&rq->lock);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
|
|
}
|
|
}
|
|
|
|
static void __task_rq_unlock(struct rq *rq)
|
|
__releases(rq->lock)
|
|
{
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
static inline void
|
|
task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
|
|
__releases(rq->lock)
|
|
__releases(p->pi_lock)
|
|
{
|
|
raw_spin_unlock(&rq->lock);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
|
|
}
|
|
|
|
/*
|
|
* this_rq_lock - lock this runqueue and disable interrupts.
|
|
*/
|
|
static struct rq *this_rq_lock(void)
|
|
__acquires(rq->lock)
|
|
{
|
|
struct rq *rq;
|
|
|
|
local_irq_disable();
|
|
rq = this_rq();
|
|
raw_spin_lock(&rq->lock);
|
|
|
|
return rq;
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_HRTICK
|
|
/*
|
|
* Use HR-timers to deliver accurate preemption points.
|
|
*/
|
|
|
|
static void hrtick_clear(struct rq *rq)
|
|
{
|
|
if (hrtimer_active(&rq->hrtick_timer))
|
|
hrtimer_cancel(&rq->hrtick_timer);
|
|
}
|
|
|
|
/*
|
|
* High-resolution timer tick.
|
|
* Runs from hardirq context with interrupts disabled.
|
|
*/
|
|
static enum hrtimer_restart hrtick(struct hrtimer *timer)
|
|
{
|
|
struct rq *rq = container_of(timer, struct rq, hrtick_timer);
|
|
|
|
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
update_rq_clock(rq);
|
|
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
return HRTIMER_NORESTART;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static int __hrtick_restart(struct rq *rq)
|
|
{
|
|
struct hrtimer *timer = &rq->hrtick_timer;
|
|
ktime_t time = hrtimer_get_softexpires(timer);
|
|
|
|
return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
|
|
}
|
|
|
|
/*
|
|
* called from hardirq (IPI) context
|
|
*/
|
|
static void __hrtick_start(void *arg)
|
|
{
|
|
struct rq *rq = arg;
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
__hrtick_restart(rq);
|
|
rq->hrtick_csd_pending = 0;
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
/*
|
|
* Called to set the hrtick timer state.
|
|
*
|
|
* called with rq->lock held and irqs disabled
|
|
*/
|
|
void hrtick_start(struct rq *rq, u64 delay)
|
|
{
|
|
struct hrtimer *timer = &rq->hrtick_timer;
|
|
ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
|
|
|
|
hrtimer_set_expires(timer, time);
|
|
|
|
if (rq == this_rq()) {
|
|
__hrtick_restart(rq);
|
|
} else if (!rq->hrtick_csd_pending) {
|
|
__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
|
|
rq->hrtick_csd_pending = 1;
|
|
}
|
|
}
|
|
|
|
static int
|
|
hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|
{
|
|
int cpu = (int)(long)hcpu;
|
|
|
|
switch (action) {
|
|
case CPU_UP_CANCELED:
|
|
case CPU_UP_CANCELED_FROZEN:
|
|
case CPU_DOWN_PREPARE:
|
|
case CPU_DOWN_PREPARE_FROZEN:
|
|
case CPU_DEAD:
|
|
case CPU_DEAD_FROZEN:
|
|
hrtick_clear(cpu_rq(cpu));
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static __init void init_hrtick(void)
|
|
{
|
|
hotcpu_notifier(hotplug_hrtick, 0);
|
|
}
|
|
#else
|
|
/*
|
|
* Called to set the hrtick timer state.
|
|
*
|
|
* called with rq->lock held and irqs disabled
|
|
*/
|
|
void hrtick_start(struct rq *rq, u64 delay)
|
|
{
|
|
__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
|
|
HRTIMER_MODE_REL_PINNED, 0);
|
|
}
|
|
|
|
static inline void init_hrtick(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static void init_rq_hrtick(struct rq *rq)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
rq->hrtick_csd_pending = 0;
|
|
|
|
rq->hrtick_csd.flags = 0;
|
|
rq->hrtick_csd.func = __hrtick_start;
|
|
rq->hrtick_csd.info = rq;
|
|
#endif
|
|
|
|
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
|
|
rq->hrtick_timer.function = hrtick;
|
|
}
|
|
#else /* CONFIG_SCHED_HRTICK */
|
|
static inline void hrtick_clear(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
static inline void init_rq_hrtick(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
static inline void init_hrtick(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SCHED_HRTICK */
|
|
|
|
/*
|
|
* resched_task - mark a task 'to be rescheduled now'.
|
|
*
|
|
* On UP this means the setting of the need_resched flag, on SMP it
|
|
* might also involve a cross-CPU call to trigger the scheduler on
|
|
* the target CPU.
|
|
*/
|
|
void resched_task(struct task_struct *p)
|
|
{
|
|
int cpu;
|
|
|
|
lockdep_assert_held(&task_rq(p)->lock);
|
|
|
|
if (test_tsk_need_resched(p))
|
|
return;
|
|
|
|
set_tsk_need_resched(p);
|
|
|
|
cpu = task_cpu(p);
|
|
if (cpu == smp_processor_id()) {
|
|
set_preempt_need_resched();
|
|
return;
|
|
}
|
|
|
|
/* NEED_RESCHED must be visible before we test polling */
|
|
smp_mb();
|
|
if (!tsk_is_polling(p))
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
|
|
void resched_cpu(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
unsigned long flags;
|
|
|
|
if (!raw_spin_trylock_irqsave(&rq->lock, flags))
|
|
return;
|
|
resched_task(cpu_curr(cpu));
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
}
|
|
|
|
#ifdef CONFIG_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 cpu = smp_processor_id();
|
|
int i;
|
|
struct sched_domain *sd;
|
|
|
|
rcu_read_lock();
|
|
for_each_domain(cpu, sd) {
|
|
for_each_cpu(i, sched_domain_span(sd)) {
|
|
if (!idle_cpu(i)) {
|
|
cpu = i;
|
|
goto unlock;
|
|
}
|
|
}
|
|
}
|
|
unlock:
|
|
rcu_read_unlock();
|
|
return cpu;
|
|
}
|
|
/*
|
|
* When add_timer_on() enqueues a timer into the timer wheel of an
|
|
* idle CPU then this timer might expire before the next timer event
|
|
* which is scheduled to wake up that CPU. In case of a completely
|
|
* idle system the next event might even be infinite time into the
|
|
* future. wake_up_idle_cpu() ensures that the CPU is woken up and
|
|
* leaves the inner idle loop so the newly added timer is taken into
|
|
* account when the CPU goes back to idle and evaluates the timer
|
|
* wheel for the next timer event.
|
|
*/
|
|
static void wake_up_idle_cpu(int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
if (cpu == smp_processor_id())
|
|
return;
|
|
|
|
/*
|
|
* This is safe, as this function is called with the timer
|
|
* wheel base lock of (cpu) held. When the CPU is on the way
|
|
* to idle and has not yet set rq->curr to idle then it will
|
|
* be serialized on the timer wheel base lock and take the new
|
|
* timer into account automatically.
|
|
*/
|
|
if (rq->curr != rq->idle)
|
|
return;
|
|
|
|
/*
|
|
* We can set TIF_RESCHED on the idle task of the other CPU
|
|
* lockless. The worst case is that the other CPU runs the
|
|
* idle task through an additional NOOP schedule()
|
|
*/
|
|
set_tsk_need_resched(rq->idle);
|
|
|
|
/* NEED_RESCHED must be visible before we test polling */
|
|
smp_mb();
|
|
if (!tsk_is_polling(rq->idle))
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
|
|
static bool wake_up_full_nohz_cpu(int cpu)
|
|
{
|
|
if (tick_nohz_full_cpu(cpu)) {
|
|
if (cpu != smp_processor_id() ||
|
|
tick_nohz_tick_stopped())
|
|
smp_send_reschedule(cpu);
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
void wake_up_nohz_cpu(int cpu)
|
|
{
|
|
if (!wake_up_full_nohz_cpu(cpu))
|
|
wake_up_idle_cpu(cpu);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
#else /* CONFIG_NO_HZ_COMMON */
|
|
|
|
static inline bool got_nohz_idle_kick(void)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_NO_HZ_COMMON */
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
bool sched_can_stop_tick(void)
|
|
{
|
|
struct rq *rq;
|
|
|
|
rq = this_rq();
|
|
|
|
/* Make sure rq->nr_running update is visible after the IPI */
|
|
smp_rmb();
|
|
|
|
/* More than one running task need preemption */
|
|
if (rq->nr_running > 1)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
#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;
|
|
}
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
|
|
(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
|
|
/*
|
|
* Iterate task_group tree rooted at *from, calling @down when first entering a
|
|
* node and @up when leaving it for the final time.
|
|
*
|
|
* Caller must hold rcu_lock or sufficient equivalent.
|
|
*/
|
|
int walk_tg_tree_from(struct task_group *from,
|
|
tg_visitor down, tg_visitor up, void *data)
|
|
{
|
|
struct task_group *parent, *child;
|
|
int ret;
|
|
|
|
parent = from;
|
|
|
|
down:
|
|
ret = (*down)(parent, data);
|
|
if (ret)
|
|
goto out;
|
|
list_for_each_entry_rcu(child, &parent->children, siblings) {
|
|
parent = child;
|
|
goto down;
|
|
|
|
up:
|
|
continue;
|
|
}
|
|
ret = (*up)(parent, data);
|
|
if (ret || parent == from)
|
|
goto out;
|
|
|
|
child = parent;
|
|
parent = parent->parent;
|
|
if (parent)
|
|
goto up;
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int tg_nop(struct task_group *tg, void *data)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
static void set_load_weight(struct task_struct *p)
|
|
{
|
|
int prio = p->static_prio - MAX_RT_PRIO;
|
|
struct load_weight *load = &p->se.load;
|
|
|
|
/*
|
|
* SCHED_IDLE tasks get minimal weight:
|
|
*/
|
|
if (p->policy == SCHED_IDLE) {
|
|
load->weight = scale_load(WEIGHT_IDLEPRIO);
|
|
load->inv_weight = WMULT_IDLEPRIO;
|
|
return;
|
|
}
|
|
|
|
load->weight = scale_load(prio_to_weight[prio]);
|
|
load->inv_weight = prio_to_wmult[prio];
|
|
}
|
|
|
|
static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
update_rq_clock(rq);
|
|
sched_info_queued(rq, p);
|
|
p->sched_class->enqueue_task(rq, p, flags);
|
|
}
|
|
|
|
static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
update_rq_clock(rq);
|
|
sched_info_dequeued(rq, p);
|
|
p->sched_class->dequeue_task(rq, p, flags);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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((¶virt_steal_rq_enabled))) {
|
|
u64 st;
|
|
|
|
steal = paravirt_steal_clock(cpu_of(rq));
|
|
steal -= rq->prev_steal_time_rq;
|
|
|
|
if (unlikely(steal > delta))
|
|
steal = delta;
|
|
|
|
st = steal_ticks(steal);
|
|
steal = st * TICK_NSEC;
|
|
|
|
rq->prev_steal_time_rq += steal;
|
|
|
|
delta -= steal;
|
|
}
|
|
#endif
|
|
|
|
rq->clock_task += delta;
|
|
|
|
#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
|
|
if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
|
|
sched_rt_avg_update(rq, irq_delta + steal);
|
|
#endif
|
|
}
|
|
|
|
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, ¶m);
|
|
|
|
stop->sched_class = &stop_sched_class;
|
|
}
|
|
|
|
cpu_rq(cpu)->stop = stop;
|
|
|
|
if (old_stop) {
|
|
/*
|
|
* Reset it back to a normal scheduling class so that
|
|
* it can die in pieces.
|
|
*/
|
|
old_stop->sched_class = &rt_sched_class;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* __normal_prio - return the priority that is based on the static prio
|
|
*/
|
|
static inline int __normal_prio(struct task_struct *p)
|
|
{
|
|
return p->static_prio;
|
|
}
|
|
|
|
/*
|
|
* Calculate the expected normal priority: i.e. priority
|
|
* without taking RT-inheritance into account. Might be
|
|
* boosted by interactivity modifiers. Changes upon fork,
|
|
* setprio syscalls, and whenever the interactivity
|
|
* estimator recalculates.
|
|
*/
|
|
static inline int normal_prio(struct task_struct *p)
|
|
{
|
|
int prio;
|
|
|
|
if (task_has_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;
|
|
}
|
|
|
|
/*
|
|
* Calculate the current priority, i.e. the priority
|
|
* taken into account by the scheduler. This value might
|
|
* be boosted by RT tasks, or might be boosted by
|
|
* interactivity modifiers. Will be RT if the task got
|
|
* RT-boosted. If not then it returns p->normal_prio.
|
|
*/
|
|
static int effective_prio(struct task_struct *p)
|
|
{
|
|
p->normal_prio = normal_prio(p);
|
|
/*
|
|
* If we are RT tasks or we were boosted to RT priority,
|
|
* keep the priority unchanged. Otherwise, update priority
|
|
* to the normal priority:
|
|
*/
|
|
if (!rt_prio(p->prio))
|
|
return p->normal_prio;
|
|
return p->prio;
|
|
}
|
|
|
|
/**
|
|
* task_curr - is this task currently executing on a CPU?
|
|
* @p: the task in question.
|
|
*
|
|
* 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;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
const struct sched_class *class;
|
|
|
|
if (p->sched_class == rq->curr->sched_class) {
|
|
rq->curr->sched_class->check_preempt_curr(rq, p, flags);
|
|
} else {
|
|
for_each_class(class) {
|
|
if (class == rq->curr->sched_class)
|
|
break;
|
|
if (class == p->sched_class) {
|
|
resched_task(rq->curr);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* A queue event has occurred, and we're going to schedule. In
|
|
* this case, we can save a useless back to back clock update.
|
|
*/
|
|
if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
|
|
rq->skip_clock_update = 1;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
|
|
{
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
/*
|
|
* We should never call set_task_cpu() on a blocked task,
|
|
* ttwu() will sort out the placement.
|
|
*/
|
|
WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
|
|
!(task_preempt_count(p) & PREEMPT_ACTIVE));
|
|
|
|
#ifdef CONFIG_LOCKDEP
|
|
/*
|
|
* The caller should hold either p->pi_lock or rq->lock, when changing
|
|
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
|
|
*
|
|
* sched_move_task() holds both and thus holding either pins the cgroup,
|
|
* see 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
|
|
#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, new_cpu);
|
|
p->se.nr_migrations++;
|
|
perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
|
|
}
|
|
|
|
__set_task_cpu(p, new_cpu);
|
|
}
|
|
|
|
static void __migrate_swap_task(struct task_struct *p, int cpu)
|
|
{
|
|
if (p->on_rq) {
|
|
struct rq *src_rq, *dst_rq;
|
|
|
|
src_rq = task_rq(p);
|
|
dst_rq = cpu_rq(cpu);
|
|
|
|
deactivate_task(src_rq, p, 0);
|
|
set_task_cpu(p, cpu);
|
|
activate_task(dst_rq, p, 0);
|
|
check_preempt_curr(dst_rq, p, 0);
|
|
} 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 targer instead of where it really is.
|
|
*/
|
|
p->wake_cpu = cpu;
|
|
}
|
|
}
|
|
|
|
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;
|
|
|
|
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, tsk_cpus_allowed(arg->src_task)))
|
|
goto unlock;
|
|
|
|
if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* 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, tsk_cpus_allowed(arg.src_task)))
|
|
goto out;
|
|
|
|
if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
|
|
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;
|
|
}
|
|
|
|
struct migration_arg {
|
|
struct task_struct *task;
|
|
int dest_cpu;
|
|
};
|
|
|
|
static int migration_cpu_stop(void *data);
|
|
|
|
/*
|
|
* wait_task_inactive - wait for a thread to unschedule.
|
|
*
|
|
* If @match_state is nonzero, it's the @p->state value just checked and
|
|
* not expected to change. If it changes, i.e. @p might have woken up,
|
|
* then return zero. When we succeed in waiting for @p to be off its CPU,
|
|
* we return a positive number (its total switch count). If a second call
|
|
* a short while later returns the same number, the caller can be sure that
|
|
* @p has remained unscheduled the whole time.
|
|
*
|
|
* The caller must ensure that the task *will* unschedule sometime soon,
|
|
* else this function might spin for a *long* time. This function can't
|
|
* be called with interrupts off, or it may introduce deadlock with
|
|
* smp_call_function() if an IPI is sent by the same process we are
|
|
* waiting to become inactive.
|
|
*/
|
|
unsigned long wait_task_inactive(struct task_struct *p, long match_state)
|
|
{
|
|
unsigned long flags;
|
|
int running, on_rq;
|
|
unsigned long ncsw;
|
|
struct rq *rq;
|
|
|
|
for (;;) {
|
|
/*
|
|
* We do the initial early heuristics without holding
|
|
* any task-queue locks at all. We'll only try to get
|
|
* the runqueue lock when things look like they will
|
|
* work out!
|
|
*/
|
|
rq = task_rq(p);
|
|
|
|
/*
|
|
* If the task is actively running on another CPU
|
|
* still, just relax and busy-wait without holding
|
|
* any locks.
|
|
*
|
|
* NOTE! Since we don't hold any locks, it's not
|
|
* even sure that "rq" stays as the right runqueue!
|
|
* But we don't care, since "task_running()" will
|
|
* return false if the runqueue has changed and p
|
|
* is actually now running somewhere else!
|
|
*/
|
|
while (task_running(rq, p)) {
|
|
if (match_state && unlikely(p->state != match_state))
|
|
return 0;
|
|
cpu_relax();
|
|
}
|
|
|
|
/*
|
|
* Ok, time to look more closely! We need the rq
|
|
* lock now, to be *sure*. If we're wrong, we'll
|
|
* just go back and repeat.
|
|
*/
|
|
rq = task_rq_lock(p, &flags);
|
|
trace_sched_wait_task(p);
|
|
running = task_running(rq, p);
|
|
on_rq = p->on_rq;
|
|
ncsw = 0;
|
|
if (!match_state || p->state == match_state)
|
|
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
|
|
task_rq_unlock(rq, p, &flags);
|
|
|
|
/*
|
|
* If it changed from the expected state, bail out now.
|
|
*/
|
|
if (unlikely(!ncsw))
|
|
break;
|
|
|
|
/*
|
|
* Was it really running after all now that we
|
|
* checked with the proper locks actually held?
|
|
*
|
|
* Oops. Go back and try again..
|
|
*/
|
|
if (unlikely(running)) {
|
|
cpu_relax();
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* It's not enough that it's not actively running,
|
|
* it must be off the runqueue _entirely_, and not
|
|
* preempted!
|
|
*
|
|
* So if it was still runnable (but just not actively
|
|
* running right now), it's preempted, and we should
|
|
* yield - it could be a while.
|
|
*/
|
|
if (unlikely(on_rq)) {
|
|
ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
|
|
|
|
set_current_state(TASK_UNINTERRUPTIBLE);
|
|
schedule_hrtimeout(&to, HRTIMER_MODE_REL);
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Ahh, all good. It wasn't running, and it wasn't
|
|
* runnable, which means that it will never become
|
|
* running in the future either. We're all done!
|
|
*/
|
|
break;
|
|
}
|
|
|
|
return ncsw;
|
|
}
|
|
|
|
/***
|
|
* kick_process - kick a running thread to enter/exit the kernel
|
|
* @p: the to-be-kicked thread
|
|
*
|
|
* Cause a process which is running on another CPU to enter
|
|
* kernel-mode, without any delay. (to get signals handled.)
|
|
*
|
|
* NOTE: this function doesn't have to take the runqueue lock,
|
|
* because all it wants to ensure is that the remote task enters
|
|
* the kernel. If the IPI races and the task has been migrated
|
|
* to another CPU then no harm is done and the purpose has been
|
|
* achieved as well.
|
|
*/
|
|
void kick_process(struct task_struct *p)
|
|
{
|
|
int cpu;
|
|
|
|
preempt_disable();
|
|
cpu = task_cpu(p);
|
|
if ((cpu != smp_processor_id()) && task_curr(p))
|
|
smp_send_reschedule(cpu);
|
|
preempt_enable();
|
|
}
|
|
EXPORT_SYMBOL_GPL(kick_process);
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* ->cpus_allowed is protected by both rq->lock and p->pi_lock
|
|
*/
|
|
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_online(dest_cpu))
|
|
continue;
|
|
if (!cpu_active(dest_cpu))
|
|
continue;
|
|
if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
|
|
return dest_cpu;
|
|
}
|
|
}
|
|
|
|
for (;;) {
|
|
/* Any allowed, online CPU? */
|
|
for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
|
|
if (!cpu_online(dest_cpu))
|
|
continue;
|
|
if (!cpu_active(dest_cpu))
|
|
continue;
|
|
goto out;
|
|
}
|
|
|
|
switch (state) {
|
|
case cpuset:
|
|
/* No more Mr. Nice Guy. */
|
|
cpuset_cpus_allowed_fallback(p);
|
|
state = possible;
|
|
break;
|
|
|
|
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_sched("process %d (%s) no longer affine to cpu%d\n",
|
|
task_pid_nr(p), p->comm, cpu);
|
|
}
|
|
}
|
|
|
|
return dest_cpu;
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
|
|
|
|
/*
|
|
* 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, tsk_cpus_allowed(p)) ||
|
|
!cpu_online(cpu)))
|
|
cpu = select_fallback_rq(task_cpu(p), p);
|
|
|
|
return cpu;
|
|
}
|
|
|
|
static void update_avg(u64 *avg, u64 sample)
|
|
{
|
|
s64 diff = sample - *avg;
|
|
*avg += diff >> 3;
|
|
}
|
|
#endif
|
|
|
|
static void
|
|
ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
|
|
{
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
struct rq *rq = this_rq();
|
|
|
|
#ifdef CONFIG_SMP
|
|
int this_cpu = smp_processor_id();
|
|
|
|
if (cpu == this_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(this_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);
|
|
|
|
#endif /* CONFIG_SCHEDSTATS */
|
|
}
|
|
|
|
static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
|
|
{
|
|
activate_task(rq, p, en_flags);
|
|
p->on_rq = 1;
|
|
|
|
/* if a worker is waking up, notify workqueue */
|
|
if (p->flags & PF_WQ_WORKER)
|
|
wq_worker_waking_up(p, cpu_of(rq));
|
|
}
|
|
|
|
/*
|
|
* Mark the task runnable and perform wakeup-preemption.
|
|
*/
|
|
static void
|
|
ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
|
|
{
|
|
check_preempt_curr(rq, p, wake_flags);
|
|
trace_sched_wakeup(p, true);
|
|
|
|
p->state = TASK_RUNNING;
|
|
#ifdef CONFIG_SMP
|
|
if (p->sched_class->task_woken)
|
|
p->sched_class->task_woken(rq, p);
|
|
|
|
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
|
|
}
|
|
|
|
static void
|
|
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
if (p->sched_contributes_to_load)
|
|
rq->nr_uninterruptible--;
|
|
#endif
|
|
|
|
ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
|
|
ttwu_do_wakeup(rq, p, wake_flags);
|
|
}
|
|
|
|
/*
|
|
* 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 *rq;
|
|
int ret = 0;
|
|
|
|
rq = __task_rq_lock(p);
|
|
if (p->on_rq) {
|
|
/* check_preempt_curr() may use rq clock */
|
|
update_rq_clock(rq);
|
|
ttwu_do_wakeup(rq, p, wake_flags);
|
|
ret = 1;
|
|
}
|
|
__task_rq_unlock(rq);
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static void sched_ttwu_pending(void)
|
|
{
|
|
struct rq *rq = this_rq();
|
|
struct llist_node *llist = llist_del_all(&rq->wake_list);
|
|
struct task_struct *p;
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
|
|
while (llist) {
|
|
p = llist_entry(llist, struct task_struct, wake_entry);
|
|
llist = llist_next(llist);
|
|
ttwu_do_activate(rq, p, 0);
|
|
}
|
|
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
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)
|
|
&& !tick_nohz_full_cpu(smp_processor_id())
|
|
&& !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();
|
|
tick_nohz_full_check();
|
|
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();
|
|
}
|
|
|
|
static void ttwu_queue_remote(struct task_struct *p, int cpu)
|
|
{
|
|
if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list))
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
|
|
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);
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static void ttwu_queue(struct task_struct *p, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
#if defined(CONFIG_SMP)
|
|
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
|
|
sched_clock_cpu(cpu); /* sync clocks x-cpu */
|
|
ttwu_queue_remote(p, cpu);
|
|
return;
|
|
}
|
|
#endif
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
ttwu_do_activate(rq, p, 0);
|
|
raw_spin_unlock(&rq->lock);
|
|
}
|
|
|
|
/**
|
|
* 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_*)
|
|
*
|
|
* Put it on the run-queue if it's not already there. The "current"
|
|
* thread is always on the run-queue (except when the actual
|
|
* re-schedule is in progress), and as such you're allowed to do
|
|
* the simpler "current->state = TASK_RUNNING" to mark yourself
|
|
* runnable without the overhead of this.
|
|
*
|
|
* Return: %true if @p was woken up, %false if it was already running.
|
|
* or @state didn't match @p's state.
|
|
*/
|
|
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.
|
|
*/
|
|
smp_mb__before_spinlock();
|
|
raw_spin_lock_irqsave(&p->pi_lock, flags);
|
|
if (!(p->state & state))
|
|
goto out;
|
|
|
|
success = 1; /* we're going to change ->state */
|
|
cpu = task_cpu(p);
|
|
|
|
if (p->on_rq && ttwu_remote(p, wake_flags))
|
|
goto stat;
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* If the owning (remote) cpu is still in the middle of schedule() with
|
|
* this task as prev, wait until its done referencing the task.
|
|
*/
|
|
while (p->on_cpu)
|
|
cpu_relax();
|
|
/*
|
|
* Pairs with the smp_wmb() in finish_lock_switch().
|
|
*/
|
|
smp_rmb();
|
|
|
|
p->sched_contributes_to_load = !!task_contributes_to_load(p);
|
|
p->state = TASK_WAKING;
|
|
|
|
if (p->sched_class->task_waking)
|
|
p->sched_class->task_waking(p);
|
|
|
|
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);
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
ttwu_queue(p, cpu);
|
|
stat:
|
|
ttwu_stat(p, cpu, wake_flags);
|
|
out:
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
|
|
return success;
|
|
}
|
|
|
|
/**
|
|
* try_to_wake_up_local - try to wake up a local task with rq lock held
|
|
* @p: the thread to be awakened
|
|
*
|
|
* 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 *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)) {
|
|
raw_spin_unlock(&rq->lock);
|
|
raw_spin_lock(&p->pi_lock);
|
|
raw_spin_lock(&rq->lock);
|
|
}
|
|
|
|
if (!(p->state & TASK_NORMAL))
|
|
goto out;
|
|
|
|
if (!p->on_rq)
|
|
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
|
|
|
|
ttwu_do_wakeup(rq, p, 0);
|
|
ttwu_stat(p, smp_processor_id(), 0);
|
|
out:
|
|
raw_spin_unlock(&p->pi_lock);
|
|
}
|
|
|
|
/**
|
|
* 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)
|
|
{
|
|
WARN_ON(task_is_stopped_or_traced(p));
|
|
return try_to_wake_up(p, TASK_NORMAL, 0);
|
|
}
|
|
EXPORT_SYMBOL(wake_up_process);
|
|
|
|
int wake_up_state(struct task_struct *p, unsigned int state)
|
|
{
|
|
return try_to_wake_up(p, state, 0);
|
|
}
|
|
|
|
/*
|
|
* 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_SCHEDSTATS
|
|
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
|
|
#endif
|
|
|
|
RB_CLEAR_NODE(&p->dl.rb_node);
|
|
hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
|
|
p->dl.dl_runtime = p->dl.runtime = 0;
|
|
p->dl.dl_deadline = p->dl.deadline = 0;
|
|
p->dl.dl_period = 0;
|
|
p->dl.flags = 0;
|
|
|
|
INIT_LIST_HEAD(&p->rt.run_list);
|
|
|
|
#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->numa_faults_buffer = NULL;
|
|
|
|
INIT_LIST_HEAD(&p->numa_entry);
|
|
p->numa_group = NULL;
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
void set_numabalancing_state(bool enabled)
|
|
{
|
|
if (enabled)
|
|
sched_feat_set("NUMA");
|
|
else
|
|
sched_feat_set("NO_NUMA");
|
|
}
|
|
#else
|
|
__read_mostly bool numabalancing_enabled;
|
|
|
|
void set_numabalancing_state(bool enabled)
|
|
{
|
|
numabalancing_enabled = enabled;
|
|
}
|
|
#endif /* CONFIG_SCHED_DEBUG */
|
|
|
|
#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 = numabalancing_enabled;
|
|
|
|
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;
|
|
}
|
|
#endif
|
|
#endif
|
|
|
|
/*
|
|
* 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 running 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_RUNNING;
|
|
|
|
/*
|
|
* 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);
|
|
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
if (p->sched_class->task_fork)
|
|
p->sched_class->task_fork(p);
|
|
|
|
/*
|
|
* 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);
|
|
set_task_cpu(p, cpu);
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
|
|
|
|
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
|
|
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;
|
|
}
|
|
|
|
unsigned long to_ratio(u64 period, u64 runtime)
|
|
{
|
|
if (runtime == RUNTIME_INF)
|
|
return 1ULL << 20;
|
|
|
|
/*
|
|
* 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 << 20, period);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
inline struct dl_bw *dl_bw_of(int i)
|
|
{
|
|
return &cpu_rq(i)->rd->dl_bw;
|
|
}
|
|
|
|
static inline int dl_bw_cpus(int i)
|
|
{
|
|
struct root_domain *rd = cpu_rq(i)->rd;
|
|
int cpus = 0;
|
|
|
|
for_each_cpu_and(i, rd->span, cpu_active_mask)
|
|
cpus++;
|
|
|
|
return cpus;
|
|
}
|
|
#else
|
|
inline struct dl_bw *dl_bw_of(int i)
|
|
{
|
|
return &cpu_rq(i)->dl.dl_bw;
|
|
}
|
|
|
|
static inline int dl_bw_cpus(int i)
|
|
{
|
|
return 1;
|
|
}
|
|
#endif
|
|
|
|
static inline
|
|
void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
|
|
{
|
|
dl_b->total_bw -= tsk_bw;
|
|
}
|
|
|
|
static inline
|
|
void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
|
|
{
|
|
dl_b->total_bw += tsk_bw;
|
|
}
|
|
|
|
static inline
|
|
bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
|
|
{
|
|
return dl_b->bw != -1 &&
|
|
dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
|
|
}
|
|
|
|
/*
|
|
* We must be sure that accepting a new task (or allowing changing the
|
|
* parameters of an existing one) is consistent with the bandwidth
|
|
* constraints. If yes, this function also accordingly updates the currently
|
|
* allocated bandwidth to reflect the new situation.
|
|
*
|
|
* This function is called while holding p's rq->lock.
|
|
*/
|
|
static int dl_overflow(struct task_struct *p, int policy,
|
|
const struct sched_attr *attr)
|
|
{
|
|
|
|
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
|
|
u64 period = attr->sched_period;
|
|
u64 runtime = attr->sched_runtime;
|
|
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
|
|
int cpus, err = -1;
|
|
|
|
if (new_bw == p->dl.dl_bw)
|
|
return 0;
|
|
|
|
/*
|
|
* Either if a task, enters, leave, or stays -deadline but changes
|
|
* its parameters, we may need to update accordingly the total
|
|
* allocated bandwidth of the container.
|
|
*/
|
|
raw_spin_lock(&dl_b->lock);
|
|
cpus = dl_bw_cpus(task_cpu(p));
|
|
if (dl_policy(policy) && !task_has_dl_policy(p) &&
|
|
!__dl_overflow(dl_b, cpus, 0, new_bw)) {
|
|
__dl_add(dl_b, new_bw);
|
|
err = 0;
|
|
} else if (dl_policy(policy) && task_has_dl_policy(p) &&
|
|
!__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
|
|
__dl_clear(dl_b, p->dl.dl_bw);
|
|
__dl_add(dl_b, new_bw);
|
|
err = 0;
|
|
} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
|
|
__dl_clear(dl_b, p->dl.dl_bw);
|
|
err = 0;
|
|
}
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
return err;
|
|
}
|
|
|
|
extern void init_dl_bw(struct dl_bw *dl_b);
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
raw_spin_lock_irqsave(&p->pi_lock, flags);
|
|
#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
|
|
*/
|
|
set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
|
|
#endif
|
|
|
|
/* Initialize new task's runnable average */
|
|
init_task_runnable_average(p);
|
|
rq = __task_rq_lock(p);
|
|
activate_task(rq, p, 0);
|
|
p->on_rq = 1;
|
|
trace_sched_wakeup_new(p, true);
|
|
check_preempt_curr(rq, p, WF_FORK);
|
|
#ifdef CONFIG_SMP
|
|
if (p->sched_class->task_woken)
|
|
p->sched_class->task_woken(rq, p);
|
|
#endif
|
|
task_rq_unlock(rq, p, &flags);
|
|
}
|
|
|
|
#ifdef CONFIG_PREEMPT_NOTIFIERS
|
|
|
|
/**
|
|
* preempt_notifier_register - tell me when current is being preempted & rescheduled
|
|
* @notifier: notifier struct to register
|
|
*/
|
|
void preempt_notifier_register(struct preempt_notifier *notifier)
|
|
{
|
|
hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
|
|
}
|
|
EXPORT_SYMBOL_GPL(preempt_notifier_register);
|
|
|
|
/**
|
|
* preempt_notifier_unregister - no longer interested in preemption notifications
|
|
* @notifier: notifier struct to unregister
|
|
*
|
|
* This is safe to call from within a preemption notifier.
|
|
*/
|
|
void preempt_notifier_unregister(struct preempt_notifier *notifier)
|
|
{
|
|
hlist_del(¬ifier->link);
|
|
}
|
|
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());
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
#else /* !CONFIG_PREEMPT_NOTIFIERS */
|
|
|
|
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
|
|
{
|
|
}
|
|
|
|
static void
|
|
fire_sched_out_preempt_notifiers(struct task_struct *curr,
|
|
struct task_struct *next)
|
|
{
|
|
}
|
|
|
|
#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)
|
|
{
|
|
trace_sched_switch(prev, 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);
|
|
}
|
|
|
|
/**
|
|
* finish_task_switch - clean up after a task-switch
|
|
* @rq: runqueue associated with 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.)
|
|
*/
|
|
static void finish_task_switch(struct rq *rq, struct task_struct *prev)
|
|
__releases(rq->lock)
|
|
{
|
|
struct mm_struct *mm = rq->prev_mm;
|
|
long prev_state;
|
|
|
|
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.
|
|
* The test for TASK_DEAD must occur while the runqueue locks are
|
|
* still held, otherwise prev could be scheduled on another cpu, die
|
|
* there before we look at prev->state, and then the reference would
|
|
* be dropped twice.
|
|
* Manfred Spraul <manfred@colorfullife.com>
|
|
*/
|
|
prev_state = prev->state;
|
|
vtime_task_switch(prev);
|
|
finish_arch_switch(prev);
|
|
perf_event_task_sched_in(prev, current);
|
|
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)) {
|
|
task_numa_free(prev);
|
|
|
|
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);
|
|
put_task_struct(prev);
|
|
}
|
|
|
|
tick_nohz_task_switch(current);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/* assumes rq->lock is held */
|
|
static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
if (prev->sched_class->pre_schedule)
|
|
prev->sched_class->pre_schedule(rq, prev);
|
|
}
|
|
|
|
/* rq->lock is NOT held, but preemption is disabled */
|
|
static inline void post_schedule(struct rq *rq)
|
|
{
|
|
if (rq->post_schedule) {
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->curr->sched_class->post_schedule)
|
|
rq->curr->sched_class->post_schedule(rq);
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
rq->post_schedule = 0;
|
|
}
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void pre_schedule(struct rq *rq, struct task_struct *p)
|
|
{
|
|
}
|
|
|
|
static inline void post_schedule(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
#endif
|
|
|
|
/**
|
|
* schedule_tail - first thing a freshly forked thread must call.
|
|
* @prev: the thread we just switched away from.
|
|
*/
|
|
asmlinkage void schedule_tail(struct task_struct *prev)
|
|
__releases(rq->lock)
|
|
{
|
|
struct rq *rq = this_rq();
|
|
|
|
finish_task_switch(rq, prev);
|
|
|
|
/*
|
|
* FIXME: do we need to worry about rq being invalidated by the
|
|
* task_switch?
|
|
*/
|
|
post_schedule(rq);
|
|
|
|
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
|
|
/* In this case, finish_task_switch does not reenable preemption */
|
|
preempt_enable();
|
|
#endif
|
|
if (current->set_child_tid)
|
|
put_user(task_pid_vnr(current), current->set_child_tid);
|
|
}
|
|
|
|
/*
|
|
* context_switch - switch to the new MM and the new
|
|
* thread's register state.
|
|
*/
|
|
static inline void
|
|
context_switch(struct rq *rq, struct task_struct *prev,
|
|
struct task_struct *next)
|
|
{
|
|
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;
|
|
atomic_inc(&oldmm->mm_count);
|
|
enter_lazy_tlb(oldmm, next);
|
|
} else
|
|
switch_mm(oldmm, mm, next);
|
|
|
|
if (!prev->mm) {
|
|
prev->active_mm = NULL;
|
|
rq->prev_mm = oldmm;
|
|
}
|
|
/*
|
|
* 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:
|
|
*/
|
|
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
|
|
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
|
|
#endif
|
|
|
|
context_tracking_task_switch(prev, next);
|
|
/* Here we just switch the register state and the stack. */
|
|
switch_to(prev, next, prev);
|
|
|
|
barrier();
|
|
/*
|
|
* this_rq must be evaluated again because prev may have moved
|
|
* CPUs since it called schedule(), thus the 'rq' on its stack
|
|
* frame will be invalid.
|
|
*/
|
|
finish_task_switch(this_rq(), 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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
unsigned long nr_iowait_cpu(int cpu)
|
|
{
|
|
struct rq *this = cpu_rq(cpu);
|
|
return atomic_read(&this->nr_iowait);
|
|
}
|
|
|
|
#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);
|
|
}
|
|
|
|
#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);
|
|
|
|
/*
|
|
* Return any ns on the sched_clock that have not yet been accounted in
|
|
* @p in case that task is currently running.
|
|
*
|
|
* Called with task_rq_lock() held on @rq.
|
|
*/
|
|
static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
|
|
{
|
|
u64 ns = 0;
|
|
|
|
if (task_current(rq, p)) {
|
|
update_rq_clock(rq);
|
|
ns = rq_clock_task(rq) - p->se.exec_start;
|
|
if ((s64)ns < 0)
|
|
ns = 0;
|
|
}
|
|
|
|
return ns;
|
|
}
|
|
|
|
unsigned long long task_delta_exec(struct task_struct *p)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
u64 ns = 0;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
ns = do_task_delta_exec(p, rq);
|
|
task_rq_unlock(rq, p, &flags);
|
|
|
|
return ns;
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
u64 ns = 0;
|
|
|
|
#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 (!p->on_cpu)
|
|
return p->se.sum_exec_runtime;
|
|
#endif
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
|
|
task_rq_unlock(rq, p, &flags);
|
|
|
|
return ns;
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
|
|
sched_clock_tick();
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
update_rq_clock(rq);
|
|
curr->sched_class->task_tick(rq, curr, 0);
|
|
update_cpu_load_active(rq);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
perf_event_task_tick();
|
|
|
|
#ifdef CONFIG_SMP
|
|
rq->idle_balance = idle_cpu(cpu);
|
|
trigger_load_balance(rq);
|
|
#endif
|
|
rq_last_tick_reset(rq);
|
|
}
|
|
|
|
#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 = ACCESS_ONCE(jiffies);
|
|
|
|
next = rq->last_sched_tick + HZ;
|
|
|
|
if (time_before_eq(next, now))
|
|
return 0;
|
|
|
|
return jiffies_to_nsecs(next - now);
|
|
}
|
|
#endif
|
|
|
|
notrace unsigned long get_parent_ip(unsigned long addr)
|
|
{
|
|
if (in_lock_functions(addr)) {
|
|
addr = CALLER_ADDR2;
|
|
if (in_lock_functions(addr))
|
|
addr = CALLER_ADDR3;
|
|
}
|
|
return addr;
|
|
}
|
|
|
|
#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
|
|
defined(CONFIG_PREEMPT_TRACER))
|
|
|
|
void __kprobes 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
|
|
if (preempt_count() == val)
|
|
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
|
|
}
|
|
EXPORT_SYMBOL(preempt_count_add);
|
|
|
|
void __kprobes 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
|
|
|
|
if (preempt_count() == val)
|
|
trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
|
|
__preempt_count_sub(val);
|
|
}
|
|
EXPORT_SYMBOL(preempt_count_sub);
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Print scheduling while atomic bug:
|
|
*/
|
|
static noinline void __schedule_bug(struct task_struct *prev)
|
|
{
|
|
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);
|
|
dump_stack();
|
|
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
|
|
}
|
|
|
|
/*
|
|
* Various schedule()-time debugging checks and statistics:
|
|
*/
|
|
static inline void schedule_debug(struct task_struct *prev)
|
|
{
|
|
/*
|
|
* Test if we are atomic. Since do_exit() needs to call into
|
|
* schedule() atomically, we ignore that path. Otherwise whine
|
|
* if we are scheduling when we should not.
|
|
*/
|
|
if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
|
|
__schedule_bug(prev);
|
|
rcu_sleep_check();
|
|
|
|
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
|
|
|
|
schedstat_inc(this_rq(), sched_count);
|
|
}
|
|
|
|
static void put_prev_task(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
if (prev->on_rq || rq->skip_clock_update < 0)
|
|
update_rq_clock(rq);
|
|
prev->sched_class->put_prev_task(rq, prev);
|
|
}
|
|
|
|
/*
|
|
* Pick up the highest-prio task:
|
|
*/
|
|
static inline struct task_struct *
|
|
pick_next_task(struct rq *rq)
|
|
{
|
|
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:
|
|
*/
|
|
if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
|
|
p = fair_sched_class.pick_next_task(rq);
|
|
if (likely(p))
|
|
return p;
|
|
}
|
|
|
|
for_each_class(class) {
|
|
p = class->pick_next_task(rq);
|
|
if (p)
|
|
return p;
|
|
}
|
|
|
|
BUG(); /* the idle class will always have a runnable task */
|
|
}
|
|
|
|
/*
|
|
* __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
|
|
*/
|
|
static void __sched __schedule(void)
|
|
{
|
|
struct task_struct *prev, *next;
|
|
unsigned long *switch_count;
|
|
struct rq *rq;
|
|
int cpu;
|
|
|
|
need_resched:
|
|
preempt_disable();
|
|
cpu = smp_processor_id();
|
|
rq = cpu_rq(cpu);
|
|
rcu_note_context_switch(cpu);
|
|
prev = rq->curr;
|
|
|
|
schedule_debug(prev);
|
|
|
|
if (sched_feat(HRTICK))
|
|
hrtick_clear(rq);
|
|
|
|
/*
|
|
* 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().
|
|
*/
|
|
smp_mb__before_spinlock();
|
|
raw_spin_lock_irq(&rq->lock);
|
|
|
|
switch_count = &prev->nivcsw;
|
|
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
|
|
if (unlikely(signal_pending_state(prev->state, prev))) {
|
|
prev->state = TASK_RUNNING;
|
|
} else {
|
|
deactivate_task(rq, prev, DEQUEUE_SLEEP);
|
|
prev->on_rq = 0;
|
|
|
|
/*
|
|
* 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, cpu);
|
|
if (to_wakeup)
|
|
try_to_wake_up_local(to_wakeup);
|
|
}
|
|
}
|
|
switch_count = &prev->nvcsw;
|
|
}
|
|
|
|
pre_schedule(rq, prev);
|
|
|
|
if (unlikely(!rq->nr_running))
|
|
idle_balance(cpu, rq);
|
|
|
|
put_prev_task(rq, prev);
|
|
next = pick_next_task(rq);
|
|
clear_tsk_need_resched(prev);
|
|
clear_preempt_need_resched();
|
|
rq->skip_clock_update = 0;
|
|
|
|
if (likely(prev != next)) {
|
|
rq->nr_switches++;
|
|
rq->curr = next;
|
|
++*switch_count;
|
|
|
|
context_switch(rq, prev, next); /* unlocks the rq */
|
|
/*
|
|
* 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 it can be moved to another cpu/rq.
|
|
*/
|
|
cpu = smp_processor_id();
|
|
rq = cpu_rq(cpu);
|
|
} else
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
|
|
post_schedule(rq);
|
|
|
|
sched_preempt_enable_no_resched();
|
|
if (need_resched())
|
|
goto need_resched;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
asmlinkage void __sched schedule(void)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
|
|
sched_submit_work(tsk);
|
|
__schedule();
|
|
}
|
|
EXPORT_SYMBOL(schedule);
|
|
|
|
#ifdef CONFIG_CONTEXT_TRACKING
|
|
asmlinkage 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.
|
|
*/
|
|
user_exit();
|
|
schedule();
|
|
user_enter();
|
|
}
|
|
#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();
|
|
}
|
|
|
|
#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 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;
|
|
|
|
do {
|
|
__preempt_count_add(PREEMPT_ACTIVE);
|
|
__schedule();
|
|
__preempt_count_sub(PREEMPT_ACTIVE);
|
|
|
|
/*
|
|
* Check again in case we missed a preemption opportunity
|
|
* between schedule and now.
|
|
*/
|
|
barrier();
|
|
} while (need_resched());
|
|
}
|
|
EXPORT_SYMBOL(preempt_schedule);
|
|
#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 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_count_add(PREEMPT_ACTIVE);
|
|
local_irq_enable();
|
|
__schedule();
|
|
local_irq_disable();
|
|
__preempt_count_sub(PREEMPT_ACTIVE);
|
|
|
|
/*
|
|
* Check again in case we missed a preemption opportunity
|
|
* between schedule and now.
|
|
*/
|
|
barrier();
|
|
} while (need_resched());
|
|
|
|
exception_exit(prev_state);
|
|
}
|
|
|
|
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
|
|
void *key)
|
|
{
|
|
return try_to_wake_up(curr->private, mode, wake_flags);
|
|
}
|
|
EXPORT_SYMBOL(default_wake_function);
|
|
|
|
static long __sched
|
|
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
|
|
{
|
|
unsigned long flags;
|
|
wait_queue_t wait;
|
|
|
|
init_waitqueue_entry(&wait, current);
|
|
|
|
__set_current_state(state);
|
|
|
|
spin_lock_irqsave(&q->lock, flags);
|
|
__add_wait_queue(q, &wait);
|
|
spin_unlock(&q->lock);
|
|
timeout = schedule_timeout(timeout);
|
|
spin_lock_irq(&q->lock);
|
|
__remove_wait_queue(q, &wait);
|
|
spin_unlock_irqrestore(&q->lock, flags);
|
|
|
|
return timeout;
|
|
}
|
|
|
|
void __sched interruptible_sleep_on(wait_queue_head_t *q)
|
|
{
|
|
sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
|
|
}
|
|
EXPORT_SYMBOL(interruptible_sleep_on);
|
|
|
|
long __sched
|
|
interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
|
|
{
|
|
return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
|
|
}
|
|
EXPORT_SYMBOL(interruptible_sleep_on_timeout);
|
|
|
|
void __sched sleep_on(wait_queue_head_t *q)
|
|
{
|
|
sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
|
|
}
|
|
EXPORT_SYMBOL(sleep_on);
|
|
|
|
long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
|
|
{
|
|
return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
|
|
}
|
|
EXPORT_SYMBOL(sleep_on_timeout);
|
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
|
|
/*
|
|
* rt_mutex_setprio - set the current priority of a task
|
|
* @p: task
|
|
* @prio: prio value (kernel-internal form)
|
|
*
|
|
* 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.
|
|
*/
|
|
void rt_mutex_setprio(struct task_struct *p, int prio)
|
|
{
|
|
int oldprio, on_rq, running, enqueue_flag = 0;
|
|
struct rq *rq;
|
|
const struct sched_class *prev_class;
|
|
|
|
BUG_ON(prio > MAX_PRIO);
|
|
|
|
rq = __task_rq_lock(p);
|
|
|
|
/*
|
|
* 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, prio);
|
|
p->pi_top_task = rt_mutex_get_top_task(p);
|
|
oldprio = p->prio;
|
|
prev_class = p->sched_class;
|
|
on_rq = p->on_rq;
|
|
running = task_current(rq, p);
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
if (running)
|
|
p->sched_class->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) || (p->pi_top_task &&
|
|
dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
|
|
p->dl.dl_boosted = 1;
|
|
p->dl.dl_throttled = 0;
|
|
enqueue_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)
|
|
enqueue_flag = ENQUEUE_HEAD;
|
|
p->sched_class = &rt_sched_class;
|
|
} else {
|
|
if (dl_prio(oldprio))
|
|
p->dl.dl_boosted = 0;
|
|
p->sched_class = &fair_sched_class;
|
|
}
|
|
|
|
p->prio = prio;
|
|
|
|
if (running)
|
|
p->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, p, enqueue_flag);
|
|
|
|
check_class_changed(rq, p, prev_class, oldprio);
|
|
out_unlock:
|
|
__task_rq_unlock(rq);
|
|
}
|
|
#endif
|
|
|
|
void set_user_nice(struct task_struct *p, long nice)
|
|
{
|
|
int old_prio, delta, on_rq;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
|
|
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, &flags);
|
|
/*
|
|
* 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;
|
|
}
|
|
on_rq = p->on_rq;
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
|
|
p->static_prio = NICE_TO_PRIO(nice);
|
|
set_load_weight(p);
|
|
old_prio = p->prio;
|
|
p->prio = effective_prio(p);
|
|
delta = p->prio - old_prio;
|
|
|
|
if (on_rq) {
|
|
enqueue_task(rq, p, 0);
|
|
/*
|
|
* 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_task(rq->curr);
|
|
}
|
|
out_unlock:
|
|
task_rq_unlock(rq, p, &flags);
|
|
}
|
|
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 = 20 - nice;
|
|
|
|
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
|
|
capable(CAP_SYS_NICE));
|
|
}
|
|
|
|
#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.
|
|
*/
|
|
if (increment < -40)
|
|
increment = -40;
|
|
if (increment > 40)
|
|
increment = 40;
|
|
|
|
nice = TASK_NICE(current) + increment;
|
|
if (nice < -20)
|
|
nice = -20;
|
|
if (nice > 19)
|
|
nice = 19;
|
|
|
|
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;
|
|
}
|
|
|
|
/**
|
|
* task_nice - return the nice value of a given task.
|
|
* @p: the task in question.
|
|
*
|
|
* Return: The nice value [ -20 ... 0 ... 19 ].
|
|
*/
|
|
int task_nice(const struct task_struct *p)
|
|
{
|
|
return TASK_NICE(p);
|
|
}
|
|
EXPORT_SYMBOL(task_nice);
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
/*
|
|
* This function initializes the sched_dl_entity of a newly becoming
|
|
* SCHED_DEADLINE task.
|
|
*
|
|
* Only the static values are considered here, the actual runtime and the
|
|
* absolute deadline will be properly calculated when the task is enqueued
|
|
* for the first time with its new policy.
|
|
*/
|
|
static void
|
|
__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
|
|
{
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
init_dl_task_timer(dl_se);
|
|
dl_se->dl_runtime = attr->sched_runtime;
|
|
dl_se->dl_deadline = attr->sched_deadline;
|
|
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
|
|
dl_se->flags = attr->sched_flags;
|
|
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
|
|
dl_se->dl_throttled = 0;
|
|
dl_se->dl_new = 1;
|
|
}
|
|
|
|
/* Actually do priority change: must hold pi & rq lock. */
|
|
static void __setscheduler(struct rq *rq, struct task_struct *p,
|
|
const struct sched_attr *attr)
|
|
{
|
|
int policy = attr->sched_policy;
|
|
|
|
if (policy == -1) /* setparam */
|
|
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);
|
|
p->prio = rt_mutex_getprio(p);
|
|
|
|
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;
|
|
|
|
set_load_weight(p);
|
|
}
|
|
|
|
static void
|
|
__getparam_dl(struct task_struct *p, struct sched_attr *attr)
|
|
{
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
attr->sched_priority = p->rt_priority;
|
|
attr->sched_runtime = dl_se->dl_runtime;
|
|
attr->sched_deadline = dl_se->dl_deadline;
|
|
attr->sched_period = dl_se->dl_period;
|
|
attr->sched_flags = dl_se->flags;
|
|
}
|
|
|
|
/*
|
|
* This function validates the new parameters of a -deadline task.
|
|
* We ask for the deadline not being zero, and greater or equal
|
|
* than the runtime, as well as the period of being zero or
|
|
* greater than deadline. Furthermore, we have to be sure that
|
|
* user parameters are above the internal resolution (1us); we
|
|
* check sched_runtime only since it is always the smaller one.
|
|
*/
|
|
static bool
|
|
__checkparam_dl(const struct sched_attr *attr)
|
|
{
|
|
return attr && attr->sched_deadline != 0 &&
|
|
(attr->sched_period == 0 ||
|
|
(s64)(attr->sched_period - attr->sched_deadline) >= 0) &&
|
|
(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 &&
|
|
attr->sched_runtime >= (2 << (DL_SCALE - 1));
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
static int __sched_setscheduler(struct task_struct *p,
|
|
const struct sched_attr *attr,
|
|
bool user)
|
|
{
|
|
int retval, oldprio, oldpolicy = -1, on_rq, running;
|
|
int policy = attr->sched_policy;
|
|
unsigned long flags;
|
|
const struct sched_class *prev_class;
|
|
struct rq *rq;
|
|
int reset_on_fork;
|
|
|
|
/* may grab non-irq protected spin_locks */
|
|
BUG_ON(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 (policy != SCHED_DEADLINE &&
|
|
policy != SCHED_FIFO && policy != SCHED_RR &&
|
|
policy != SCHED_NORMAL && policy != SCHED_BATCH &&
|
|
policy != SCHED_IDLE)
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* Treat SCHED_IDLE as nice 20. Only allow a switch to
|
|
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
|
|
*/
|
|
if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
|
|
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, &flags);
|
|
|
|
/*
|
|
* Changing the policy of the stop threads its a very bad idea
|
|
*/
|
|
if (p == rq->stop) {
|
|
task_rq_unlock(rq, p, &flags);
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* If not changing anything there's no need to proceed further:
|
|
*/
|
|
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))
|
|
goto change;
|
|
|
|
task_rq_unlock(rq, p, &flags);
|
|
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, &flags);
|
|
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, &flags);
|
|
return -EPERM;
|
|
}
|
|
}
|
|
#endif
|
|
}
|
|
|
|
/* recheck policy now with rq lock held */
|
|
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
|
|
policy = oldpolicy = -1;
|
|
task_rq_unlock(rq, p, &flags);
|
|
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)) && dl_overflow(p, policy, attr)) {
|
|
task_rq_unlock(rq, p, &flags);
|
|
return -EBUSY;
|
|
}
|
|
|
|
on_rq = p->on_rq;
|
|
running = task_current(rq, p);
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
if (running)
|
|
p->sched_class->put_prev_task(rq, p);
|
|
|
|
p->sched_reset_on_fork = reset_on_fork;
|
|
|
|
oldprio = p->prio;
|
|
prev_class = p->sched_class;
|
|
__setscheduler(rq, p, attr);
|
|
|
|
if (running)
|
|
p->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, p, 0);
|
|
|
|
check_class_changed(rq, p, prev_class, oldprio);
|
|
task_rq_unlock(rq, p, &flags);
|
|
|
|
rt_mutex_adjust_pi(p);
|
|
|
|
return 0;
|
|
}
|
|
|
|
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 & 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);
|
|
}
|
|
/**
|
|
* 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);
|
|
}
|
|
EXPORT_SYMBOL_GPL(sched_setscheduler);
|
|
|
|
int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
|
|
{
|
|
return __sched_setscheduler(p, attr, true);
|
|
}
|
|
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);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
|
|
if (size > PAGE_SIZE) /* silly large */
|
|
goto err_size;
|
|
|
|
if (!size) /* abi compat */
|
|
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, -20, 19);
|
|
|
|
out:
|
|
return ret;
|
|
|
|
err_size:
|
|
put_user(sizeof(*attr), &uattr->size);
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
/**
|
|
* 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)
|
|
{
|
|
/* negative values for policy are not valid */
|
|
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, -1, param);
|
|
}
|
|
|
|
/**
|
|
* sys_sched_setattr - same as above, but with extended sched_attr
|
|
* @pid: the pid in question.
|
|
* @uattr: structure containing the extended parameters.
|
|
*/
|
|
SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
|
|
{
|
|
struct sched_attr attr;
|
|
struct task_struct *p;
|
|
int retval;
|
|
|
|
if (!uattr || pid < 0)
|
|
return -EINVAL;
|
|
|
|
if (sched_copy_attr(uattr, &attr))
|
|
return -EFAULT;
|
|
|
|
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;
|
|
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_dl_policy(p)) {
|
|
retval = -EINVAL;
|
|
goto out_unlock;
|
|
}
|
|
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)
|
|
goto err_size;
|
|
}
|
|
|
|
attr->size = usize;
|
|
}
|
|
|
|
ret = copy_to_user(uattr, attr, usize);
|
|
if (ret)
|
|
return -EFAULT;
|
|
|
|
out:
|
|
return ret;
|
|
|
|
err_size:
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
/**
|
|
* 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.
|
|
*/
|
|
SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
|
|
unsigned int, size)
|
|
{
|
|
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)
|
|
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_unlock;
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
retval = security_task_setscheduler(p);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
|
|
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)) {
|
|
const struct cpumask *span = task_rq(p)->rd->span;
|
|
|
|
if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
|
|
retval = -EBUSY;
|
|
goto out_unlock;
|
|
}
|
|
}
|
|
#endif
|
|
again:
|
|
retval = set_cpus_allowed_ptr(p, new_mask);
|
|
|
|
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_unlock:
|
|
free_cpumask_var(new_mask);
|
|
out_free_cpus_allowed:
|
|
free_cpumask_var(cpus_allowed);
|
|
out_put_task:
|
|
put_task_struct(p);
|
|
return retval;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
/**
|
|
* 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: 0 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 *rq = this_rq_lock();
|
|
|
|
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:
|
|
*/
|
|
__release(rq->lock);
|
|
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
|
|
do_raw_spin_unlock(&rq->lock);
|
|
sched_preempt_enable_no_resched();
|
|
|
|
schedule();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __cond_resched(void)
|
|
{
|
|
__preempt_count_add(PREEMPT_ACTIVE);
|
|
__schedule();
|
|
__preempt_count_sub(PREEMPT_ACTIVE);
|
|
}
|
|
|
|
int __sched _cond_resched(void)
|
|
{
|
|
if (should_resched()) {
|
|
__cond_resched();
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(_cond_resched);
|
|
|
|
/*
|
|
* __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();
|
|
int ret = 0;
|
|
|
|
lockdep_assert_held(lock);
|
|
|
|
if (spin_needbreak(lock) || resched) {
|
|
spin_unlock(lock);
|
|
if (resched)
|
|
__cond_resched();
|
|
else
|
|
cpu_relax();
|
|
ret = 1;
|
|
spin_lock(lock);
|
|
}
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__cond_resched_lock);
|
|
|
|
int __sched __cond_resched_softirq(void)
|
|
{
|
|
BUG_ON(!in_softirq());
|
|
|
|
if (should_resched()) {
|
|
local_bh_enable();
|
|
__cond_resched();
|
|
local_bh_disable();
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
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();
|
|
}
|
|
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.
|
|
*/
|
|
bool __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_task(p_rq->curr);
|
|
}
|
|
|
|
out_unlock:
|
|
double_rq_unlock(rq, p_rq);
|
|
out_irq:
|
|
local_irq_restore(flags);
|
|
|
|
if (yielded > 0)
|
|
schedule();
|
|
|
|
return yielded;
|
|
}
|
|
EXPORT_SYMBOL_GPL(yield_to);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
void __sched io_schedule(void)
|
|
{
|
|
struct rq *rq = raw_rq();
|
|
|
|
delayacct_blkio_start();
|
|
atomic_inc(&rq->nr_iowait);
|
|
blk_flush_plug(current);
|
|
current->in_iowait = 1;
|
|
schedule();
|
|
current->in_iowait = 0;
|
|
atomic_dec(&rq->nr_iowait);
|
|
delayacct_blkio_end();
|
|
}
|
|
EXPORT_SYMBOL(io_schedule);
|
|
|
|
long __sched io_schedule_timeout(long timeout)
|
|
{
|
|
struct rq *rq = raw_rq();
|
|
long ret;
|
|
|
|
delayacct_blkio_start();
|
|
atomic_inc(&rq->nr_iowait);
|
|
blk_flush_plug(current);
|
|
current->in_iowait = 1;
|
|
ret = schedule_timeout(timeout);
|
|
current->in_iowait = 0;
|
|
atomic_dec(&rq->nr_iowait);
|
|
delayacct_blkio_end();
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
/**
|
|
* 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 task_struct *p;
|
|
unsigned int time_slice;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
int retval;
|
|
struct timespec t;
|
|
|
|
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, &flags);
|
|
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, &flags);
|
|
|
|
rcu_read_unlock();
|
|
jiffies_to_timespec(time_slice, &t);
|
|
retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
|
|
return retval;
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
return retval;
|
|
}
|
|
|
|
static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
|
|
|
|
void sched_show_task(struct task_struct *p)
|
|
{
|
|
unsigned long free = 0;
|
|
int ppid;
|
|
unsigned state;
|
|
|
|
state = p->state ? __ffs(p->state) + 1 : 0;
|
|
printk(KERN_INFO "%-15.15s %c", p->comm,
|
|
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
|
|
#if BITS_PER_LONG == 32
|
|
if (state == TASK_RUNNING)
|
|
printk(KERN_CONT " running ");
|
|
else
|
|
printk(KERN_CONT " %08lx ", thread_saved_pc(p));
|
|
#else
|
|
if (state == TASK_RUNNING)
|
|
printk(KERN_CONT " running task ");
|
|
else
|
|
printk(KERN_CONT " %016lx ", thread_saved_pc(p));
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_STACK_USAGE
|
|
free = stack_not_used(p);
|
|
#endif
|
|
rcu_read_lock();
|
|
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);
|
|
}
|
|
|
|
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();
|
|
do_each_thread(g, p) {
|
|
/*
|
|
* reset the NMI-timeout, listing all files on a slow
|
|
* console might take a lot of time:
|
|
*/
|
|
touch_nmi_watchdog();
|
|
if (!state_filter || (p->state & state_filter))
|
|
sched_show_task(p);
|
|
} while_each_thread(g, p);
|
|
|
|
touch_all_softlockup_watchdogs();
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
sysrq_sched_debug_show();
|
|
#endif
|
|
rcu_read_unlock();
|
|
/*
|
|
* Only show locks if all tasks are dumped:
|
|
*/
|
|
if (!state_filter)
|
|
debug_show_all_locks();
|
|
}
|
|
|
|
void init_idle_bootup_task(struct task_struct *idle)
|
|
{
|
|
idle->sched_class = &idle_sched_class;
|
|
}
|
|
|
|
/**
|
|
* 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(&rq->lock, flags);
|
|
|
|
__sched_fork(0, idle);
|
|
idle->state = TASK_RUNNING;
|
|
idle->se.exec_start = sched_clock();
|
|
|
|
do_set_cpus_allowed(idle, cpumask_of(cpu));
|
|
/*
|
|
* 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;
|
|
#if defined(CONFIG_SMP)
|
|
idle->on_cpu = 1;
|
|
#endif
|
|
raw_spin_unlock_irqrestore(&rq->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);
|
|
#if defined(CONFIG_SMP)
|
|
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
|
|
{
|
|
if (p->sched_class && p->sched_class->set_cpus_allowed)
|
|
p->sched_class->set_cpus_allowed(p, new_mask);
|
|
|
|
cpumask_copy(&p->cpus_allowed, new_mask);
|
|
p->nr_cpus_allowed = cpumask_weight(new_mask);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
|
|
{
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
unsigned int dest_cpu;
|
|
int ret = 0;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
|
|
if (cpumask_equal(&p->cpus_allowed, new_mask))
|
|
goto out;
|
|
|
|
if (!cpumask_intersects(new_mask, cpu_active_mask)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
do_set_cpus_allowed(p, new_mask);
|
|
|
|
/* 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_active_mask, new_mask);
|
|
if (p->on_rq) {
|
|
struct migration_arg arg = { p, dest_cpu };
|
|
/* Need help from migration thread: drop lock and wait. */
|
|
task_rq_unlock(rq, p, &flags);
|
|
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
|
|
tlb_migrate_finish(p->mm);
|
|
return 0;
|
|
}
|
|
out:
|
|
task_rq_unlock(rq, p, &flags);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
|
|
|
|
/*
|
|
* Move (not current) task off this cpu, onto dest 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.
|
|
*
|
|
* Returns non-zero if task was successfully migrated.
|
|
*/
|
|
static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
|
|
{
|
|
struct rq *rq_dest, *rq_src;
|
|
int ret = 0;
|
|
|
|
if (unlikely(!cpu_active(dest_cpu)))
|
|
return ret;
|
|
|
|
rq_src = cpu_rq(src_cpu);
|
|
rq_dest = cpu_rq(dest_cpu);
|
|
|
|
raw_spin_lock(&p->pi_lock);
|
|
double_rq_lock(rq_src, rq_dest);
|
|
/* Already moved. */
|
|
if (task_cpu(p) != src_cpu)
|
|
goto done;
|
|
/* Affinity changed (again). */
|
|
if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
|
|
goto fail;
|
|
|
|
/*
|
|
* If we're not on a rq, the next wake-up will ensure we're
|
|
* placed properly.
|
|
*/
|
|
if (p->on_rq) {
|
|
dequeue_task(rq_src, p, 0);
|
|
set_task_cpu(p, dest_cpu);
|
|
enqueue_task(rq_dest, p, 0);
|
|
check_preempt_curr(rq_dest, p, 0);
|
|
}
|
|
done:
|
|
ret = 1;
|
|
fail:
|
|
double_rq_unlock(rq_src, rq_dest);
|
|
raw_spin_unlock(&p->pi_lock);
|
|
return ret;
|
|
}
|
|
|
|
#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, tsk_cpus_allowed(p)))
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
struct rq *rq;
|
|
unsigned long flags;
|
|
bool on_rq, running;
|
|
|
|
rq = task_rq_lock(p, &flags);
|
|
on_rq = p->on_rq;
|
|
running = task_current(rq, p);
|
|
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
if (running)
|
|
p->sched_class->put_prev_task(rq, p);
|
|
|
|
p->numa_preferred_nid = nid;
|
|
|
|
if (running)
|
|
p->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, p, 0);
|
|
task_rq_unlock(rq, p, &flags);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* 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;
|
|
|
|
/*
|
|
* The original target cpu might have gone down and we might
|
|
* be on another cpu but it doesn't matter.
|
|
*/
|
|
local_irq_disable();
|
|
__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
|
|
local_irq_enable();
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
/*
|
|
* Ensures 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);
|
|
mmdrop(mm);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*
|
|
* Also see the comment "Global load-average calculations".
|
|
*/
|
|
static void calc_load_migrate(struct rq *rq)
|
|
{
|
|
long delta = calc_load_fold_active(rq);
|
|
if (delta)
|
|
atomic_long_add(delta, &calc_load_tasks);
|
|
}
|
|
|
|
/*
|
|
* 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(unsigned int dead_cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(dead_cpu);
|
|
struct task_struct *next, *stop = rq->stop;
|
|
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;
|
|
|
|
next = pick_next_task(rq);
|
|
BUG_ON(!next);
|
|
next->sched_class->put_prev_task(rq, next);
|
|
|
|
/* Find suitable destination for @next, with force if needed. */
|
|
dest_cpu = select_fallback_rq(dead_cpu, next);
|
|
raw_spin_unlock(&rq->lock);
|
|
|
|
__migrate_task(next, dead_cpu, dest_cpu);
|
|
|
|
raw_spin_lock(&rq->lock);
|
|
}
|
|
|
|
rq->stop = stop;
|
|
}
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
|
|
|
|
static struct ctl_table sd_ctl_dir[] = {
|
|
{
|
|
.procname = "sched_domain",
|
|
.mode = 0555,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table sd_ctl_root[] = {
|
|
{
|
|
.procname = "kernel",
|
|
.mode = 0555,
|
|
.child = sd_ctl_dir,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table *sd_alloc_ctl_entry(int n)
|
|
{
|
|
struct ctl_table *entry =
|
|
kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
|
|
|
|
return entry;
|
|
}
|
|
|
|
static void sd_free_ctl_entry(struct ctl_table **tablep)
|
|
{
|
|
struct ctl_table *entry;
|
|
|
|
/*
|
|
* In the intermediate directories, both the child directory and
|
|
* procname are dynamically allocated and could fail but the mode
|
|
* will always be set. In the lowest directory the names are
|
|
* static strings and all have proc handlers.
|
|
*/
|
|
for (entry = *tablep; entry->mode; entry++) {
|
|
if (entry->child)
|
|
sd_free_ctl_entry(&entry->child);
|
|
if (entry->proc_handler == NULL)
|
|
kfree(entry->procname);
|
|
}
|
|
|
|
kfree(*tablep);
|
|
*tablep = NULL;
|
|
}
|
|
|
|
static int min_load_idx = 0;
|
|
static int max_load_idx = CPU_LOAD_IDX_MAX-1;
|
|
|
|
static void
|
|
set_table_entry(struct ctl_table *entry,
|
|
const char *procname, void *data, int maxlen,
|
|
umode_t mode, proc_handler *proc_handler,
|
|
bool load_idx)
|
|
{
|
|
entry->procname = procname;
|
|
entry->data = data;
|
|
entry->maxlen = maxlen;
|
|
entry->mode = mode;
|
|
entry->proc_handler = proc_handler;
|
|
|
|
if (load_idx) {
|
|
entry->extra1 = &min_load_idx;
|
|
entry->extra2 = &max_load_idx;
|
|
}
|
|
}
|
|
|
|
static struct ctl_table *
|
|
sd_alloc_ctl_domain_table(struct sched_domain *sd)
|
|
{
|
|
struct ctl_table *table = sd_alloc_ctl_entry(13);
|
|
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
set_table_entry(&table[0], "min_interval", &sd->min_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax, false);
|
|
set_table_entry(&table[1], "max_interval", &sd->max_interval,
|
|
sizeof(long), 0644, proc_doulongvec_minmax, false);
|
|
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
|
|
sizeof(int), 0644, proc_dointvec_minmax, true);
|
|
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[9], "cache_nice_tries",
|
|
&sd->cache_nice_tries,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[10], "flags", &sd->flags,
|
|
sizeof(int), 0644, proc_dointvec_minmax, false);
|
|
set_table_entry(&table[11], "name", sd->name,
|
|
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
|
|
/* &table[12] is terminator */
|
|
|
|
return table;
|
|
}
|
|
|
|
static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
|
|
{
|
|
struct ctl_table *entry, *table;
|
|
struct sched_domain *sd;
|
|
int domain_num = 0, i;
|
|
char buf[32];
|
|
|
|
for_each_domain(cpu, sd)
|
|
domain_num++;
|
|
entry = table = sd_alloc_ctl_entry(domain_num + 1);
|
|
if (table == NULL)
|
|
return NULL;
|
|
|
|
i = 0;
|
|
for_each_domain(cpu, sd) {
|
|
snprintf(buf, 32, "domain%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_domain_table(sd);
|
|
entry++;
|
|
i++;
|
|
}
|
|
return table;
|
|
}
|
|
|
|
static struct ctl_table_header *sd_sysctl_header;
|
|
static void register_sched_domain_sysctl(void)
|
|
{
|
|
int i, cpu_num = num_possible_cpus();
|
|
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
|
|
char buf[32];
|
|
|
|
WARN_ON(sd_ctl_dir[0].child);
|
|
sd_ctl_dir[0].child = entry;
|
|
|
|
if (entry == NULL)
|
|
return;
|
|
|
|
for_each_possible_cpu(i) {
|
|
snprintf(buf, 32, "cpu%d", i);
|
|
entry->procname = kstrdup(buf, GFP_KERNEL);
|
|
entry->mode = 0555;
|
|
entry->child = sd_alloc_ctl_cpu_table(i);
|
|
entry++;
|
|
}
|
|
|
|
WARN_ON(sd_sysctl_header);
|
|
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
|
|
}
|
|
|
|
/* may be called multiple times per register */
|
|
static void unregister_sched_domain_sysctl(void)
|
|
{
|
|
if (sd_sysctl_header)
|
|
unregister_sysctl_table(sd_sysctl_header);
|
|
sd_sysctl_header = NULL;
|
|
if (sd_ctl_dir[0].child)
|
|
sd_free_ctl_entry(&sd_ctl_dir[0].child);
|
|
}
|
|
#else
|
|
static void register_sched_domain_sysctl(void)
|
|
{
|
|
}
|
|
static void unregister_sched_domain_sysctl(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
static 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);
|
|
}
|
|
}
|
|
}
|
|
|
|
static 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;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* migration_call - callback that gets triggered when a CPU is added.
|
|
* Here we can start up the necessary migration thread for the new CPU.
|
|
*/
|
|
static int
|
|
migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
|
|
{
|
|
int cpu = (long)hcpu;
|
|
unsigned long flags;
|
|
struct rq *rq = cpu_rq(cpu);
|
|
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
|
|
case CPU_UP_PREPARE:
|
|
rq->calc_load_update = calc_load_update;
|
|
break;
|
|
|
|
case CPU_ONLINE:
|
|
/* Update our root-domain */
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->rd) {
|
|
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
|
|
|
|
set_rq_online(rq);
|
|
}
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
break;
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
case CPU_DYING:
|
|
sched_ttwu_pending();
|
|
/* Update our root-domain */
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
if (rq->rd) {
|
|
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
|
|
set_rq_offline(rq);
|
|
}
|
|
migrate_tasks(cpu);
|
|
BUG_ON(rq->nr_running != 1); /* the migration thread */
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
break;
|
|
|
|
case CPU_DEAD:
|
|
calc_load_migrate(rq);
|
|
break;
|
|
#endif
|
|
}
|
|
|
|
update_max_interval();
|
|
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
/*
|
|
* Register at high priority so that task migration (migrate_all_tasks)
|
|
* happens before everything else. This has to be lower priority than
|
|
* the notifier in the perf_event subsystem, though.
|
|
*/
|
|
static struct notifier_block migration_notifier = {
|
|
.notifier_call = migration_call,
|
|
.priority = CPU_PRI_MIGRATION,
|
|
};
|
|
|
|
static int sched_cpu_active(struct notifier_block *nfb,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_STARTING:
|
|
case CPU_DOWN_FAILED:
|
|
set_cpu_active((long)hcpu, true);
|
|
return NOTIFY_OK;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static int sched_cpu_inactive(struct notifier_block *nfb,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
unsigned long flags;
|
|
long cpu = (long)hcpu;
|
|
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_DOWN_PREPARE:
|
|
set_cpu_active(cpu, false);
|
|
|
|
/* explicitly allow suspend */
|
|
if (!(action & CPU_TASKS_FROZEN)) {
|
|
struct dl_bw *dl_b = dl_bw_of(cpu);
|
|
bool overflow;
|
|
int cpus;
|
|
|
|
raw_spin_lock_irqsave(&dl_b->lock, flags);
|
|
cpus = dl_bw_cpus(cpu);
|
|
overflow = __dl_overflow(dl_b, cpus, 0, 0);
|
|
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
|
|
|
|
if (overflow)
|
|
return notifier_from_errno(-EBUSY);
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static int __init migration_init(void)
|
|
{
|
|
void *cpu = (void *)(long)smp_processor_id();
|
|
int err;
|
|
|
|
/* Initialize migration for the boot CPU */
|
|
err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
|
|
BUG_ON(err == NOTIFY_BAD);
|
|
migration_call(&migration_notifier, CPU_ONLINE, cpu);
|
|
register_cpu_notifier(&migration_notifier);
|
|
|
|
/* Register cpu active notifiers */
|
|
cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
|
|
cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
|
|
|
|
return 0;
|
|
}
|
|
early_initcall(migration_init);
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
|
|
static __read_mostly int sched_debug_enabled;
|
|
|
|
static int __init sched_debug_setup(char *str)
|
|
{
|
|
sched_debug_enabled = 1;
|
|
|
|
return 0;
|
|
}
|
|
early_param("sched_debug", sched_debug_setup);
|
|
|
|
static inline bool sched_debug(void)
|
|
{
|
|
return sched_debug_enabled;
|
|
}
|
|
|
|
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
|
|
struct cpumask *groupmask)
|
|
{
|
|
struct sched_group *group = sd->groups;
|
|
char str[256];
|
|
|
|
cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
|
|
cpumask_clear(groupmask);
|
|
|
|
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
|
|
|
|
if (!(sd->flags & SD_LOAD_BALANCE)) {
|
|
printk("does not load-balance\n");
|
|
if (sd->parent)
|
|
printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
|
|
" has parent");
|
|
return -1;
|
|
}
|
|
|
|
printk(KERN_CONT "span %s level %s\n", str, sd->name);
|
|
|
|
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
|
|
printk(KERN_ERR "ERROR: domain->span does not contain "
|
|
"CPU%d\n", cpu);
|
|
}
|
|
if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
|
|
printk(KERN_ERR "ERROR: domain->groups does not contain"
|
|
" CPU%d\n", cpu);
|
|
}
|
|
|
|
printk(KERN_DEBUG "%*s groups:", level + 1, "");
|
|
do {
|
|
if (!group) {
|
|
printk("\n");
|
|
printk(KERN_ERR "ERROR: group is NULL\n");
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* Even though we initialize ->power to something semi-sane,
|
|
* we leave power_orig unset. This allows us to detect if
|
|
* domain iteration is still funny without causing /0 traps.
|
|
*/
|
|
if (!group->sgp->power_orig) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: domain->cpu_power not "
|
|
"set\n");
|
|
break;
|
|
}
|
|
|
|
if (!cpumask_weight(sched_group_cpus(group))) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: empty group\n");
|
|
break;
|
|
}
|
|
|
|
if (!(sd->flags & SD_OVERLAP) &&
|
|
cpumask_intersects(groupmask, sched_group_cpus(group))) {
|
|
printk(KERN_CONT "\n");
|
|
printk(KERN_ERR "ERROR: repeated CPUs\n");
|
|
break;
|
|
}
|
|
|
|
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
|
|
|
|
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
|
|
|
|
printk(KERN_CONT " %s", str);
|
|
if (group->sgp->power != SCHED_POWER_SCALE) {
|
|
printk(KERN_CONT " (cpu_power = %d)",
|
|
group->sgp->power);
|
|
}
|
|
|
|
group = group->next;
|
|
} while (group != sd->groups);
|
|
printk(KERN_CONT "\n");
|
|
|
|
if (!cpumask_equal(sched_domain_span(sd), groupmask))
|
|
printk(KERN_ERR "ERROR: groups don't span domain->span\n");
|
|
|
|
if (sd->parent &&
|
|
!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
|
|
printk(KERN_ERR "ERROR: parent span is not a superset "
|
|
"of domain->span\n");
|
|
return 0;
|
|
}
|
|
|
|
static void sched_domain_debug(struct sched_domain *sd, int cpu)
|
|
{
|
|
int level = 0;
|
|
|
|
if (!sched_debug_enabled)
|
|
return;
|
|
|
|
if (!sd) {
|
|
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
|
|
return;
|
|
}
|
|
|
|
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
|
|
|
|
for (;;) {
|
|
if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
|
|
break;
|
|
level++;
|
|
sd = sd->parent;
|
|
if (!sd)
|
|
break;
|
|
}
|
|
}
|
|
#else /* !CONFIG_SCHED_DEBUG */
|
|
# define sched_domain_debug(sd, cpu) do { } while (0)
|
|
static inline bool sched_debug(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* CONFIG_SCHED_DEBUG */
|
|
|
|
static int sd_degenerate(struct sched_domain *sd)
|
|
{
|
|
if (cpumask_weight(sched_domain_span(sd)) == 1)
|
|
return 1;
|
|
|
|
/* Following flags need at least 2 groups */
|
|
if (sd->flags & (SD_LOAD_BALANCE |
|
|
SD_BALANCE_NEWIDLE |
|
|
SD_BALANCE_FORK |
|
|
SD_BALANCE_EXEC |
|
|
SD_SHARE_CPUPOWER |
|
|
SD_SHARE_PKG_RESOURCES)) {
|
|
if (sd->groups != sd->groups->next)
|
|
return 0;
|
|
}
|
|
|
|
/* Following flags don't use groups */
|
|
if (sd->flags & (SD_WAKE_AFFINE))
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
|
|
{
|
|
unsigned long cflags = sd->flags, pflags = parent->flags;
|
|
|
|
if (sd_degenerate(parent))
|
|
return 1;
|
|
|
|
if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
|
|
return 0;
|
|
|
|
/* Flags needing groups don't count if only 1 group in parent */
|
|
if (parent->groups == parent->groups->next) {
|
|
pflags &= ~(SD_LOAD_BALANCE |
|
|
SD_BALANCE_NEWIDLE |
|
|
SD_BALANCE_FORK |
|
|
SD_BALANCE_EXEC |
|
|
SD_SHARE_CPUPOWER |
|
|
SD_SHARE_PKG_RESOURCES |
|
|
SD_PREFER_SIBLING);
|
|
if (nr_node_ids == 1)
|
|
pflags &= ~SD_SERIALIZE;
|
|
}
|
|
if (~cflags & pflags)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void free_rootdomain(struct rcu_head *rcu)
|
|
{
|
|
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
|
|
|
|
cpupri_cleanup(&rd->cpupri);
|
|
cpudl_cleanup(&rd->cpudl);
|
|
free_cpumask_var(rd->dlo_mask);
|
|
free_cpumask_var(rd->rto_mask);
|
|
free_cpumask_var(rd->online);
|
|
free_cpumask_var(rd->span);
|
|
kfree(rd);
|
|
}
|
|
|
|
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
|
|
{
|
|
struct root_domain *old_rd = NULL;
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&rq->lock, flags);
|
|
|
|
if (rq->rd) {
|
|
old_rd = rq->rd;
|
|
|
|
if (cpumask_test_cpu(rq->cpu, old_rd->online))
|
|
set_rq_offline(rq);
|
|
|
|
cpumask_clear_cpu(rq->cpu, old_rd->span);
|
|
|
|
/*
|
|
* If we dont want to free the old_rd yet then
|
|
* set old_rd to NULL to skip the freeing later
|
|
* in this function:
|
|
*/
|
|
if (!atomic_dec_and_test(&old_rd->refcount))
|
|
old_rd = NULL;
|
|
}
|
|
|
|
atomic_inc(&rd->refcount);
|
|
rq->rd = rd;
|
|
|
|
cpumask_set_cpu(rq->cpu, rd->span);
|
|
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
|
|
set_rq_online(rq);
|
|
|
|
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
|
|
|
if (old_rd)
|
|
call_rcu_sched(&old_rd->rcu, free_rootdomain);
|
|
}
|
|
|
|
static int init_rootdomain(struct root_domain *rd)
|
|
{
|
|
memset(rd, 0, sizeof(*rd));
|
|
|
|
if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
|
|
goto out;
|
|
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
|
|
goto free_span;
|
|
if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
|
|
goto free_online;
|
|
if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
|
|
goto free_dlo_mask;
|
|
|
|
init_dl_bw(&rd->dl_bw);
|
|
if (cpudl_init(&rd->cpudl) != 0)
|
|
goto free_dlo_mask;
|
|
|
|
if (cpupri_init(&rd->cpupri) != 0)
|
|
goto free_rto_mask;
|
|
return 0;
|
|
|
|
free_rto_mask:
|
|
free_cpumask_var(rd->rto_mask);
|
|
free_dlo_mask:
|
|
free_cpumask_var(rd->dlo_mask);
|
|
free_online:
|
|
free_cpumask_var(rd->online);
|
|
free_span:
|
|
free_cpumask_var(rd->span);
|
|
out:
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/*
|
|
* By default the system creates a single root-domain with all cpus as
|
|
* members (mimicking the global state we have today).
|
|
*/
|
|
struct root_domain def_root_domain;
|
|
|
|
static void init_defrootdomain(void)
|
|
{
|
|
init_rootdomain(&def_root_domain);
|
|
|
|
atomic_set(&def_root_domain.refcount, 1);
|
|
}
|
|
|
|
static struct root_domain *alloc_rootdomain(void)
|
|
{
|
|
struct root_domain *rd;
|
|
|
|
rd = kmalloc(sizeof(*rd), GFP_KERNEL);
|
|
if (!rd)
|
|
return NULL;
|
|
|
|
if (init_rootdomain(rd) != 0) {
|
|
kfree(rd);
|
|
return NULL;
|
|
}
|
|
|
|
return rd;
|
|
}
|
|
|
|
static void free_sched_groups(struct sched_group *sg, int free_sgp)
|
|
{
|
|
struct sched_group *tmp, *first;
|
|
|
|
if (!sg)
|
|
return;
|
|
|
|
first = sg;
|
|
do {
|
|
tmp = sg->next;
|
|
|
|
if (free_sgp && atomic_dec_and_test(&sg->sgp->ref))
|
|
kfree(sg->sgp);
|
|
|
|
kfree(sg);
|
|
sg = tmp;
|
|
} while (sg != first);
|
|
}
|
|
|
|
static void free_sched_domain(struct rcu_head *rcu)
|
|
{
|
|
struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
|
|
|
|
/*
|
|
* If its an overlapping domain it has private groups, iterate and
|
|
* nuke them all.
|
|
*/
|
|
if (sd->flags & SD_OVERLAP) {
|
|
free_sched_groups(sd->groups, 1);
|
|
} else if (atomic_dec_and_test(&sd->groups->ref)) {
|
|
kfree(sd->groups->sgp);
|
|
kfree(sd->groups);
|
|
}
|
|
kfree(sd);
|
|
}
|
|
|
|
static void destroy_sched_domain(struct sched_domain *sd, int cpu)
|
|
{
|
|
call_rcu(&sd->rcu, free_sched_domain);
|
|
}
|
|
|
|
static void destroy_sched_domains(struct sched_domain *sd, int cpu)
|
|
{
|
|
for (; sd; sd = sd->parent)
|
|
destroy_sched_domain(sd, cpu);
|
|
}
|
|
|
|
/*
|
|
* Keep a special pointer to the highest sched_domain that has
|
|
* SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
|
|
* allows us to avoid some pointer chasing select_idle_sibling().
|
|
*
|
|
* Also keep a unique ID per domain (we use the first cpu number in
|
|
* the cpumask of the domain), this allows us to quickly tell if
|
|
* two cpus are in the same cache domain, see cpus_share_cache().
|
|
*/
|
|
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
|
|
DEFINE_PER_CPU(int, sd_llc_size);
|
|
DEFINE_PER_CPU(int, sd_llc_id);
|
|
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
|
|
DEFINE_PER_CPU(struct sched_domain *, sd_busy);
|
|
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
|
|
|
|
static void update_top_cache_domain(int cpu)
|
|
{
|
|
struct sched_domain *sd;
|
|
struct sched_domain *busy_sd = NULL;
|
|
int id = cpu;
|
|
int size = 1;
|
|
|
|
sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
|
|
if (sd) {
|
|
id = cpumask_first(sched_domain_span(sd));
|
|
size = cpumask_weight(sched_domain_span(sd));
|
|
busy_sd = sd->parent; /* sd_busy */
|
|
}
|
|
rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
|
|
|
|
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
|
|
per_cpu(sd_llc_size, cpu) = size;
|
|
per_cpu(sd_llc_id, cpu) = id;
|
|
|
|
sd = lowest_flag_domain(cpu, SD_NUMA);
|
|
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
|
|
|
|
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
|
|
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
|
|
}
|
|
|
|
/*
|
|
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
|
|
* hold the hotplug lock.
|
|
*/
|
|
static void
|
|
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
|
|
{
|
|
struct rq *rq = cpu_rq(cpu);
|
|
struct sched_domain *tmp;
|
|
|
|
/* Remove the sched domains which do not contribute to scheduling. */
|
|
for (tmp = sd; tmp; ) {
|
|
struct sched_domain *parent = tmp->parent;
|
|
if (!parent)
|
|
break;
|
|
|
|
if (sd_parent_degenerate(tmp, parent)) {
|
|
tmp->parent = parent->parent;
|
|
if (parent->parent)
|
|
parent->parent->child = tmp;
|
|
/*
|
|
* Transfer SD_PREFER_SIBLING down in case of a
|
|
* degenerate parent; the spans match for this
|
|
* so the property transfers.
|
|
*/
|
|
if (parent->flags & SD_PREFER_SIBLING)
|
|
tmp->flags |= SD_PREFER_SIBLING;
|
|
destroy_sched_domain(parent, cpu);
|
|
} else
|
|
tmp = tmp->parent;
|
|
}
|
|
|
|
if (sd && sd_degenerate(sd)) {
|
|
tmp = sd;
|
|
sd = sd->parent;
|
|
destroy_sched_domain(tmp, cpu);
|
|
if (sd)
|
|
sd->child = NULL;
|
|
}
|
|
|
|
sched_domain_debug(sd, cpu);
|
|
|
|
rq_attach_root(rq, rd);
|
|
tmp = rq->sd;
|
|
rcu_assign_pointer(rq->sd, sd);
|
|
destroy_sched_domains(tmp, cpu);
|
|
|
|
update_top_cache_domain(cpu);
|
|
}
|
|
|
|
/* cpus with isolated domains */
|
|
static cpumask_var_t cpu_isolated_map;
|
|
|
|
/* Setup the mask of cpus configured for isolated domains */
|
|
static int __init isolated_cpu_setup(char *str)
|
|
{
|
|
alloc_bootmem_cpumask_var(&cpu_isolated_map);
|
|
cpulist_parse(str, cpu_isolated_map);
|
|
return 1;
|
|
}
|
|
|
|
__setup("isolcpus=", isolated_cpu_setup);
|
|
|
|
static const struct cpumask *cpu_cpu_mask(int cpu)
|
|
{
|
|
return cpumask_of_node(cpu_to_node(cpu));
|
|
}
|
|
|
|
struct sd_data {
|
|
struct sched_domain **__percpu sd;
|
|
struct sched_group **__percpu sg;
|
|
struct sched_group_power **__percpu sgp;
|
|
};
|
|
|
|
struct s_data {
|
|
struct sched_domain ** __percpu sd;
|
|
struct root_domain *rd;
|
|
};
|
|
|
|
enum s_alloc {
|
|
sa_rootdomain,
|
|
sa_sd,
|
|
sa_sd_storage,
|
|
sa_none,
|
|
};
|
|
|
|
struct sched_domain_topology_level;
|
|
|
|
typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
|
|
typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
|
|
|
|
#define SDTL_OVERLAP 0x01
|
|
|
|
struct sched_domain_topology_level {
|
|
sched_domain_init_f init;
|
|
sched_domain_mask_f mask;
|
|
int flags;
|
|
int numa_level;
|
|
struct sd_data data;
|
|
};
|
|
|
|
/*
|
|
* Build an iteration mask that can exclude certain CPUs from the upwards
|
|
* domain traversal.
|
|
*
|
|
* Asymmetric node setups can result in situations where the domain tree is of
|
|
* unequal depth, make sure to skip domains that already cover the entire
|
|
* range.
|
|
*
|
|
* In that case build_sched_domains() will have terminated the iteration early
|
|
* and our sibling sd spans will be empty. Domains should always include the
|
|
* cpu they're built on, so check that.
|
|
*
|
|
*/
|
|
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
|
|
{
|
|
const struct cpumask *span = sched_domain_span(sd);
|
|
struct sd_data *sdd = sd->private;
|
|
struct sched_domain *sibling;
|
|
int i;
|
|
|
|
for_each_cpu(i, span) {
|
|
sibling = *per_cpu_ptr(sdd->sd, i);
|
|
if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
|
|
continue;
|
|
|
|
cpumask_set_cpu(i, sched_group_mask(sg));
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Return the canonical balance cpu for this group, this is the first cpu
|
|
* of this group that's also in the iteration mask.
|
|
*/
|
|
int group_balance_cpu(struct sched_group *sg)
|
|
{
|
|
return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
|
|
}
|
|
|
|
static int
|
|
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
|
|
{
|
|
struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
|
|
const struct cpumask *span = sched_domain_span(sd);
|
|
struct cpumask *covered = sched_domains_tmpmask;
|
|
struct sd_data *sdd = sd->private;
|
|
struct sched_domain *child;
|
|
int i;
|
|
|
|
cpumask_clear(covered);
|
|
|
|
for_each_cpu(i, span) {
|
|
struct cpumask *sg_span;
|
|
|
|
if (cpumask_test_cpu(i, covered))
|
|
continue;
|
|
|
|
child = *per_cpu_ptr(sdd->sd, i);
|
|
|
|
/* See the comment near build_group_mask(). */
|
|
if (!cpumask_test_cpu(i, sched_domain_span(child)))
|
|
continue;
|
|
|
|
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
|
|
GFP_KERNEL, cpu_to_node(cpu));
|
|
|
|
if (!sg)
|
|
goto fail;
|
|
|
|
sg_span = sched_group_cpus(sg);
|
|
if (child->child) {
|
|
child = child->child;
|
|
cpumask_copy(sg_span, sched_domain_span(child));
|
|
} else
|
|
cpumask_set_cpu(i, sg_span);
|
|
|
|
cpumask_or(covered, covered, sg_span);
|
|
|
|
sg->sgp = *per_cpu_ptr(sdd->sgp, i);
|
|
if (atomic_inc_return(&sg->sgp->ref) == 1)
|
|
build_group_mask(sd, sg);
|
|
|
|
/*
|
|
* Initialize sgp->power such that even if we mess up the
|
|
* domains and no possible iteration will get us here, we won't
|
|
* die on a /0 trap.
|
|
*/
|
|
sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
|
|
sg->sgp->power_orig = sg->sgp->power;
|
|
|
|
/*
|
|
* Make sure the first group of this domain contains the
|
|
* canonical balance cpu. Otherwise the sched_domain iteration
|
|
* breaks. See update_sg_lb_stats().
|
|
*/
|
|
if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
|
|
group_balance_cpu(sg) == cpu)
|
|
groups = sg;
|
|
|
|
if (!first)
|
|
first = sg;
|
|
if (last)
|
|
last->next = sg;
|
|
last = sg;
|
|
last->next = first;
|
|
}
|
|
sd->groups = groups;
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
free_sched_groups(first, 0);
|
|
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
|
|
{
|
|
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
|
|
struct sched_domain *child = sd->child;
|
|
|
|
if (child)
|
|
cpu = cpumask_first(sched_domain_span(child));
|
|
|
|
if (sg) {
|
|
*sg = *per_cpu_ptr(sdd->sg, cpu);
|
|
(*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu);
|
|
atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */
|
|
}
|
|
|
|
return cpu;
|
|
}
|
|
|
|
/*
|
|
* build_sched_groups will build a circular linked list of the groups
|
|
* covered by the given span, and will set each group's ->cpumask correctly,
|
|
* and ->cpu_power to 0.
|
|
*
|
|
* Assumes the sched_domain tree is fully constructed
|
|
*/
|
|
static int
|
|
build_sched_groups(struct sched_domain *sd, int cpu)
|
|
{
|
|
struct sched_group *first = NULL, *last = NULL;
|
|
struct sd_data *sdd = sd->private;
|
|
const struct cpumask *span = sched_domain_span(sd);
|
|
struct cpumask *covered;
|
|
int i;
|
|
|
|
get_group(cpu, sdd, &sd->groups);
|
|
atomic_inc(&sd->groups->ref);
|
|
|
|
if (cpu != cpumask_first(span))
|
|
return 0;
|
|
|
|
lockdep_assert_held(&sched_domains_mutex);
|
|
covered = sched_domains_tmpmask;
|
|
|
|
cpumask_clear(covered);
|
|
|
|
for_each_cpu(i, span) {
|
|
struct sched_group *sg;
|
|
int group, j;
|
|
|
|
if (cpumask_test_cpu(i, covered))
|
|
continue;
|
|
|
|
group = get_group(i, sdd, &sg);
|
|
cpumask_clear(sched_group_cpus(sg));
|
|
sg->sgp->power = 0;
|
|
cpumask_setall(sched_group_mask(sg));
|
|
|
|
for_each_cpu(j, span) {
|
|
if (get_group(j, sdd, NULL) != group)
|
|
continue;
|
|
|
|
cpumask_set_cpu(j, covered);
|
|
cpumask_set_cpu(j, sched_group_cpus(sg));
|
|
}
|
|
|
|
if (!first)
|
|
first = sg;
|
|
if (last)
|
|
last->next = sg;
|
|
last = sg;
|
|
}
|
|
last->next = first;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Initialize sched groups cpu_power.
|
|
*
|
|
* cpu_power indicates the capacity of sched group, which is used while
|
|
* distributing the load between different sched groups in a sched domain.
|
|
* Typically cpu_power for all the groups in a sched domain will be same unless
|
|
* there are asymmetries in the topology. If there are asymmetries, group
|
|
* having more cpu_power will pickup more load compared to the group having
|
|
* less cpu_power.
|
|
*/
|
|
static void init_sched_groups_power(int cpu, struct sched_domain *sd)
|
|
{
|
|
struct sched_group *sg = sd->groups;
|
|
|
|
WARN_ON(!sg);
|
|
|
|
do {
|
|
sg->group_weight = cpumask_weight(sched_group_cpus(sg));
|
|
sg = sg->next;
|
|
} while (sg != sd->groups);
|
|
|
|
if (cpu != group_balance_cpu(sg))
|
|
return;
|
|
|
|
update_group_power(sd, cpu);
|
|
atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
|
|
}
|
|
|
|
int __weak arch_sd_sibling_asym_packing(void)
|
|
{
|
|
return 0*SD_ASYM_PACKING;
|
|
}
|
|
|
|
/*
|
|
* Initializers for schedule domains
|
|
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
|
|
*/
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
# define SD_INIT_NAME(sd, type) sd->name = #type
|
|
#else
|
|
# define SD_INIT_NAME(sd, type) do { } while (0)
|
|
#endif
|
|
|
|
#define SD_INIT_FUNC(type) \
|
|
static noinline struct sched_domain * \
|
|
sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \
|
|
{ \
|
|
struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \
|
|
*sd = SD_##type##_INIT; \
|
|
SD_INIT_NAME(sd, type); \
|
|
sd->private = &tl->data; \
|
|
return sd; \
|
|
}
|
|
|
|
SD_INIT_FUNC(CPU)
|
|
#ifdef CONFIG_SCHED_SMT
|
|
SD_INIT_FUNC(SIBLING)
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
SD_INIT_FUNC(MC)
|
|
#endif
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
SD_INIT_FUNC(BOOK)
|
|
#endif
|
|
|
|
static int default_relax_domain_level = -1;
|
|
int sched_domain_level_max;
|
|
|
|
static int __init setup_relax_domain_level(char *str)
|
|
{
|
|
if (kstrtoint(str, 0, &default_relax_domain_level))
|
|
pr_warn("Unable to set relax_domain_level\n");
|
|
|
|
return 1;
|
|
}
|
|
__setup("relax_domain_level=", setup_relax_domain_level);
|
|
|
|
static void set_domain_attribute(struct sched_domain *sd,
|
|
struct sched_domain_attr *attr)
|
|
{
|
|
int request;
|
|
|
|
if (!attr || attr->relax_domain_level < 0) {
|
|
if (default_relax_domain_level < 0)
|
|
return;
|
|
else
|
|
request = default_relax_domain_level;
|
|
} else
|
|
request = attr->relax_domain_level;
|
|
if (request < sd->level) {
|
|
/* turn off idle balance on this domain */
|
|
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
|
|
} else {
|
|
/* turn on idle balance on this domain */
|
|
sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
|
|
}
|
|
}
|
|
|
|
static void __sdt_free(const struct cpumask *cpu_map);
|
|
static int __sdt_alloc(const struct cpumask *cpu_map);
|
|
|
|
static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
|
|
const struct cpumask *cpu_map)
|
|
{
|
|
switch (what) {
|
|
case sa_rootdomain:
|
|
if (!atomic_read(&d->rd->refcount))
|
|
free_rootdomain(&d->rd->rcu); /* fall through */
|
|
case sa_sd:
|
|
free_percpu(d->sd); /* fall through */
|
|
case sa_sd_storage:
|
|
__sdt_free(cpu_map); /* fall through */
|
|
case sa_none:
|
|
break;
|
|
}
|
|
}
|
|
|
|
static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
|
|
const struct cpumask *cpu_map)
|
|
{
|
|
memset(d, 0, sizeof(*d));
|
|
|
|
if (__sdt_alloc(cpu_map))
|
|
return sa_sd_storage;
|
|
d->sd = alloc_percpu(struct sched_domain *);
|
|
if (!d->sd)
|
|
return sa_sd_storage;
|
|
d->rd = alloc_rootdomain();
|
|
if (!d->rd)
|
|
return sa_sd;
|
|
return sa_rootdomain;
|
|
}
|
|
|
|
/*
|
|
* NULL the sd_data elements we've used to build the sched_domain and
|
|
* sched_group structure so that the subsequent __free_domain_allocs()
|
|
* will not free the data we're using.
|
|
*/
|
|
static void claim_allocations(int cpu, struct sched_domain *sd)
|
|
{
|
|
struct sd_data *sdd = sd->private;
|
|
|
|
WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
|
|
*per_cpu_ptr(sdd->sd, cpu) = NULL;
|
|
|
|
if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
|
|
*per_cpu_ptr(sdd->sg, cpu) = NULL;
|
|
|
|
if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref))
|
|
*per_cpu_ptr(sdd->sgp, cpu) = NULL;
|
|
}
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static const struct cpumask *cpu_smt_mask(int cpu)
|
|
{
|
|
return topology_thread_cpumask(cpu);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Topology list, bottom-up.
|
|
*/
|
|
static struct sched_domain_topology_level default_topology[] = {
|
|
#ifdef CONFIG_SCHED_SMT
|
|
{ sd_init_SIBLING, cpu_smt_mask, },
|
|
#endif
|
|
#ifdef CONFIG_SCHED_MC
|
|
{ sd_init_MC, cpu_coregroup_mask, },
|
|
#endif
|
|
#ifdef CONFIG_SCHED_BOOK
|
|
{ sd_init_BOOK, cpu_book_mask, },
|
|
#endif
|
|
{ sd_init_CPU, cpu_cpu_mask, },
|
|
{ NULL, },
|
|
};
|
|
|
|
static struct sched_domain_topology_level *sched_domain_topology = default_topology;
|
|
|
|
#define for_each_sd_topology(tl) \
|
|
for (tl = sched_domain_topology; tl->init; tl++)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
static int sched_domains_numa_levels;
|
|
static int *sched_domains_numa_distance;
|
|
static struct cpumask ***sched_domains_numa_masks;
|
|
static int sched_domains_curr_level;
|
|
|
|
static inline int sd_local_flags(int level)
|
|
{
|
|
if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
|
|
return 0;
|
|
|
|
return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
|
|
}
|
|
|
|
static struct sched_domain *
|
|
sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
|
|
{
|
|
struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
|
|
int level = tl->numa_level;
|
|
int sd_weight = cpumask_weight(
|
|
sched_domains_numa_masks[level][cpu_to_node(cpu)]);
|
|
|
|
*sd = (struct sched_domain){
|
|
.min_interval = sd_weight,
|
|
.max_interval = 2*sd_weight,
|
|
.busy_factor = 32,
|
|
.imbalance_pct = 125,
|
|
.cache_nice_tries = 2,
|
|
.busy_idx = 3,
|
|
.idle_idx = 2,
|
|
.newidle_idx = 0,
|
|
.wake_idx = 0,
|
|
.forkexec_idx = 0,
|
|
|
|
.flags = 1*SD_LOAD_BALANCE
|
|
| 1*SD_BALANCE_NEWIDLE
|
|
| 0*SD_BALANCE_EXEC
|
|
| 0*SD_BALANCE_FORK
|
|
| 0*SD_BALANCE_WAKE
|
|
| 0*SD_WAKE_AFFINE
|
|
| 0*SD_SHARE_CPUPOWER
|
|
| 0*SD_SHARE_PKG_RESOURCES
|
|
| 1*SD_SERIALIZE
|
|
| 0*SD_PREFER_SIBLING
|
|
| 1*SD_NUMA
|
|
| sd_local_flags(level)
|
|
,
|
|
.last_balance = jiffies,
|
|
.balance_interval = sd_weight,
|
|
};
|
|
SD_INIT_NAME(sd, NUMA);
|
|
sd->private = &tl->data;
|
|
|
|
/*
|
|
* Ugly hack to pass state to sd_numa_mask()...
|
|
*/
|
|
sched_domains_curr_level = tl->numa_level;
|
|
|
|
return sd;
|
|
}
|
|
|
|
static const struct cpumask *sd_numa_mask(int cpu)
|
|
{
|
|
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
|
|
}
|
|
|
|
static void sched_numa_warn(const char *str)
|
|
{
|
|
static int done = false;
|
|
int i,j;
|
|
|
|
if (done)
|
|
return;
|
|
|
|
done = true;
|
|
|
|
printk(KERN_WARNING "ERROR: %s\n\n", str);
|
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
printk(KERN_WARNING " ");
|
|
for (j = 0; j < nr_node_ids; j++)
|
|
printk(KERN_CONT "%02d ", node_distance(i,j));
|
|
printk(KERN_CONT "\n");
|
|
}
|
|
printk(KERN_WARNING "\n");
|
|
}
|
|
|
|
static bool find_numa_distance(int distance)
|
|
{
|
|
int i;
|
|
|
|
if (distance == node_distance(0, 0))
|
|
return true;
|
|
|
|
for (i = 0; i < sched_domains_numa_levels; i++) {
|
|
if (sched_domains_numa_distance[i] == distance)
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static void sched_init_numa(void)
|
|
{
|
|
int next_distance, curr_distance = node_distance(0, 0);
|
|
struct sched_domain_topology_level *tl;
|
|
int level = 0;
|
|
int i, j, k;
|
|
|
|
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
|
|
if (!sched_domains_numa_distance)
|
|
return;
|
|
|
|
/*
|
|
* O(nr_nodes^2) deduplicating selection sort -- in order to find the
|
|
* unique distances in the node_distance() table.
|
|
*
|
|
* Assumes node_distance(0,j) includes all distances in
|
|
* node_distance(i,j) in order to avoid cubic time.
|
|
*/
|
|
next_distance = curr_distance;
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
for (j = 0; j < nr_node_ids; j++) {
|
|
for (k = 0; k < nr_node_ids; k++) {
|
|
int distance = node_distance(i, k);
|
|
|
|
if (distance > curr_distance &&
|
|
(distance < next_distance ||
|
|
next_distance == curr_distance))
|
|
next_distance = distance;
|
|
|
|
/*
|
|
* While not a strong assumption it would be nice to know
|
|
* about cases where if node A is connected to B, B is not
|
|
* equally connected to A.
|
|
*/
|
|
if (sched_debug() && node_distance(k, i) != distance)
|
|
sched_numa_warn("Node-distance not symmetric");
|
|
|
|
if (sched_debug() && i && !find_numa_distance(distance))
|
|
sched_numa_warn("Node-0 not representative");
|
|
}
|
|
if (next_distance != curr_distance) {
|
|
sched_domains_numa_distance[level++] = next_distance;
|
|
sched_domains_numa_levels = level;
|
|
curr_distance = next_distance;
|
|
} else break;
|
|
}
|
|
|
|
/*
|
|
* In case of sched_debug() we verify the above assumption.
|
|
*/
|
|
if (!sched_debug())
|
|
break;
|
|
}
|
|
/*
|
|
* 'level' contains the number of unique distances, excluding the
|
|
* identity distance node_distance(i,i).
|
|
*
|
|
* The sched_domains_numa_distance[] array includes the actual distance
|
|
* numbers.
|
|
*/
|
|
|
|
/*
|
|
* Here, we should temporarily reset sched_domains_numa_levels to 0.
|
|
* If it fails to allocate memory for array sched_domains_numa_masks[][],
|
|
* the array will contain less then 'level' members. This could be
|
|
* dangerous when we use it to iterate array sched_domains_numa_masks[][]
|
|
* in other functions.
|
|
*
|
|
* We reset it to 'level' at the end of this function.
|
|
*/
|
|
sched_domains_numa_levels = 0;
|
|
|
|
sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
|
|
if (!sched_domains_numa_masks)
|
|
return;
|
|
|
|
/*
|
|
* Now for each level, construct a mask per node which contains all
|
|
* cpus of nodes that are that many hops away from us.
|
|
*/
|
|
for (i = 0; i < level; i++) {
|
|
sched_domains_numa_masks[i] =
|
|
kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
|
|
if (!sched_domains_numa_masks[i])
|
|
return;
|
|
|
|
for (j = 0; j < nr_node_ids; j++) {
|
|
struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
|
|
if (!mask)
|
|
return;
|
|
|
|
sched_domains_numa_masks[i][j] = mask;
|
|
|
|
for (k = 0; k < nr_node_ids; k++) {
|
|
if (node_distance(j, k) > sched_domains_numa_distance[i])
|
|
continue;
|
|
|
|
cpumask_or(mask, mask, cpumask_of_node(k));
|
|
}
|
|
}
|
|
}
|
|
|
|
tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
|
|
sizeof(struct sched_domain_topology_level), GFP_KERNEL);
|
|
if (!tl)
|
|
return;
|
|
|
|
/*
|
|
* Copy the default topology bits..
|
|
*/
|
|
for (i = 0; default_topology[i].init; i++)
|
|
tl[i] = default_topology[i];
|
|
|
|
/*
|
|
* .. and append 'j' levels of NUMA goodness.
|
|
*/
|
|
for (j = 0; j < level; i++, j++) {
|
|
tl[i] = (struct sched_domain_topology_level){
|
|
.init = sd_numa_init,
|
|
.mask = sd_numa_mask,
|
|
.flags = SDTL_OVERLAP,
|
|
.numa_level = j,
|
|
};
|
|
}
|
|
|
|
sched_domain_topology = tl;
|
|
|
|
sched_domains_numa_levels = level;
|
|
}
|
|
|
|
static void sched_domains_numa_masks_set(int cpu)
|
|
{
|
|
int i, j;
|
|
int node = cpu_to_node(cpu);
|
|
|
|
for (i = 0; i < sched_domains_numa_levels; i++) {
|
|
for (j = 0; j < nr_node_ids; j++) {
|
|
if (node_distance(j, node) <= sched_domains_numa_distance[i])
|
|
cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void sched_domains_numa_masks_clear(int cpu)
|
|
{
|
|
int i, j;
|
|
for (i = 0; i < sched_domains_numa_levels; i++) {
|
|
for (j = 0; j < nr_node_ids; j++)
|
|
cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Update sched_domains_numa_masks[level][node] array when new cpus
|
|
* are onlined.
|
|
*/
|
|
static int sched_domains_numa_masks_update(struct notifier_block *nfb,
|
|
unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
int cpu = (long)hcpu;
|
|
|
|
switch (action & ~CPU_TASKS_FROZEN) {
|
|
case CPU_ONLINE:
|
|
sched_domains_numa_masks_set(cpu);
|
|
break;
|
|
|
|
case CPU_DEAD:
|
|
sched_domains_numa_masks_clear(cpu);
|
|
break;
|
|
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
return NOTIFY_OK;
|
|
}
|
|
#else
|
|
static inline void sched_init_numa(void)
|
|
{
|
|
}
|
|
|
|
static int sched_domains_numa_masks_update(struct notifier_block *nfb,
|
|
unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
static int __sdt_alloc(const struct cpumask *cpu_map)
|
|
{
|
|
struct sched_domain_topology_level *tl;
|
|
int j;
|
|
|
|
for_each_sd_topology(tl) {
|
|
struct sd_data *sdd = &tl->data;
|
|
|
|
sdd->sd = alloc_percpu(struct sched_domain *);
|
|
if (!sdd->sd)
|
|
return -ENOMEM;
|
|
|
|
sdd->sg = alloc_percpu(struct sched_group *);
|
|
if (!sdd->sg)
|
|
return -ENOMEM;
|
|
|
|
sdd->sgp = alloc_percpu(struct sched_group_power *);
|
|
if (!sdd->sgp)
|
|
return -ENOMEM;
|
|
|
|
for_each_cpu(j, cpu_map) {
|
|
struct sched_domain *sd;
|
|
struct sched_group *sg;
|
|
struct sched_group_power *sgp;
|
|
|
|
sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
|
|
GFP_KERNEL, cpu_to_node(j));
|
|
if (!sd)
|
|
return -ENOMEM;
|
|
|
|
*per_cpu_ptr(sdd->sd, j) = sd;
|
|
|
|
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
|
|
GFP_KERNEL, cpu_to_node(j));
|
|
if (!sg)
|
|
return -ENOMEM;
|
|
|
|
sg->next = sg;
|
|
|
|
*per_cpu_ptr(sdd->sg, j) = sg;
|
|
|
|
sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
|
|
GFP_KERNEL, cpu_to_node(j));
|
|
if (!sgp)
|
|
return -ENOMEM;
|
|
|
|
*per_cpu_ptr(sdd->sgp, j) = sgp;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __sdt_free(const struct cpumask *cpu_map)
|
|
{
|
|
struct sched_domain_topology_level *tl;
|
|
int j;
|
|
|
|
for_each_sd_topology(tl) {
|
|
struct sd_data *sdd = &tl->data;
|
|
|
|
for_each_cpu(j, cpu_map) {
|
|
struct sched_domain *sd;
|
|
|
|
if (sdd->sd) {
|
|
sd = *per_cpu_ptr(sdd->sd, j);
|
|
if (sd && (sd->flags & SD_OVERLAP))
|
|
free_sched_groups(sd->groups, 0);
|
|
kfree(*per_cpu_ptr(sdd->sd, j));
|
|
}
|
|
|
|
if (sdd->sg)
|
|
kfree(*per_cpu_ptr(sdd->sg, j));
|
|
if (sdd->sgp)
|
|
kfree(*per_cpu_ptr(sdd->sgp, j));
|
|
}
|
|
free_percpu(sdd->sd);
|
|
sdd->sd = NULL;
|
|
free_percpu(sdd->sg);
|
|
sdd->sg = NULL;
|
|
free_percpu(sdd->sgp);
|
|
sdd->sgp = NULL;
|
|
}
|
|
}
|
|
|
|
struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
|
|
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
|
|
struct sched_domain *child, int cpu)
|
|
{
|
|
struct sched_domain *sd = tl->init(tl, cpu);
|
|
if (!sd)
|
|
return child;
|
|
|
|
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
|
|
if (child) {
|
|
sd->level = child->level + 1;
|
|
sched_domain_level_max = max(sched_domain_level_max, sd->level);
|
|
child->parent = sd;
|
|
sd->child = child;
|
|
}
|
|
set_domain_attribute(sd, attr);
|
|
|
|
return sd;
|
|
}
|
|
|
|
/*
|
|
* Build sched domains for a given set of cpus and attach the sched domains
|
|
* to the individual cpus
|
|
*/
|
|
static int build_sched_domains(const struct cpumask *cpu_map,
|
|
struct sched_domain_attr *attr)
|
|
{
|
|
enum s_alloc alloc_state;
|
|
struct sched_domain *sd;
|
|
struct s_data d;
|
|
int i, ret = -ENOMEM;
|
|
|
|
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
|
|
if (alloc_state != sa_rootdomain)
|
|
goto error;
|
|
|
|
/* Set up domains for cpus specified by the cpu_map. */
|
|
for_each_cpu(i, cpu_map) {
|
|
struct sched_domain_topology_level *tl;
|
|
|
|
sd = NULL;
|
|
for_each_sd_topology(tl) {
|
|
sd = build_sched_domain(tl, cpu_map, attr, sd, i);
|
|
if (tl == sched_domain_topology)
|
|
*per_cpu_ptr(d.sd, i) = sd;
|
|
if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
|
|
sd->flags |= SD_OVERLAP;
|
|
if (cpumask_equal(cpu_map, sched_domain_span(sd)))
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* Build the groups for the domains */
|
|
for_each_cpu(i, cpu_map) {
|
|
for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
|
|
sd->span_weight = cpumask_weight(sched_domain_span(sd));
|
|
if (sd->flags & SD_OVERLAP) {
|
|
if (build_overlap_sched_groups(sd, i))
|
|
goto error;
|
|
} else {
|
|
if (build_sched_groups(sd, i))
|
|
goto error;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* Calculate CPU power for physical packages and nodes */
|
|
for (i = nr_cpumask_bits-1; i >= 0; i--) {
|
|
if (!cpumask_test_cpu(i, cpu_map))
|
|
continue;
|
|
|
|
for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
|
|
claim_allocations(i, sd);
|
|
init_sched_groups_power(i, sd);
|
|
}
|
|
}
|
|
|
|
/* Attach the domains */
|
|
rcu_read_lock();
|
|
for_each_cpu(i, cpu_map) {
|
|
sd = *per_cpu_ptr(d.sd, i);
|
|
cpu_attach_domain(sd, d.rd, i);
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
ret = 0;
|
|
error:
|
|
__free_domain_allocs(&d, alloc_state, cpu_map);
|
|
return ret;
|
|
}
|
|
|
|
static cpumask_var_t *doms_cur; /* current sched domains */
|
|
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
|
|
static struct sched_domain_attr *dattr_cur;
|
|
/* attribues of custom domains in 'doms_cur' */
|
|
|
|
/*
|
|
* Special case: If a kmalloc of a doms_cur partition (array of
|
|
* cpumask) fails, then fallback to a single sched domain,
|
|
* as determined by the single cpumask fallback_doms.
|
|
*/
|
|
static cpumask_var_t fallback_doms;
|
|
|
|
/*
|
|
* arch_update_cpu_topology lets virtualized architectures update the
|
|
* cpu core maps. It is supposed to return 1 if the topology changed
|
|
* or 0 if it stayed the same.
|
|
*/
|
|
int __attribute__((weak)) arch_update_cpu_topology(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
|
|
{
|
|
int i;
|
|
cpumask_var_t *doms;
|
|
|
|
doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
|
|
if (!doms)
|
|
return NULL;
|
|
for (i = 0; i < ndoms; i++) {
|
|
if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
|
|
free_sched_domains(doms, i);
|
|
return NULL;
|
|
}
|
|
}
|
|
return doms;
|
|
}
|
|
|
|
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
|
|
{
|
|
unsigned int i;
|
|
for (i = 0; i < ndoms; i++)
|
|
free_cpumask_var(doms[i]);
|
|
kfree(doms);
|
|
}
|
|
|
|
/*
|
|
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
|
|
* For now this just excludes isolated cpus, but could be used to
|
|
* exclude other special cases in the future.
|
|
*/
|
|
static int init_sched_domains(const struct cpumask *cpu_map)
|
|
{
|
|
int err;
|
|
|
|
arch_update_cpu_topology();
|
|
ndoms_cur = 1;
|
|
doms_cur = alloc_sched_domains(ndoms_cur);
|
|
if (!doms_cur)
|
|
doms_cur = &fallback_doms;
|
|
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
|
|
err = build_sched_domains(doms_cur[0], NULL);
|
|
register_sched_domain_sysctl();
|
|
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Detach sched domains from a group of cpus specified in cpu_map
|
|
* These cpus will now be attached to the NULL domain
|
|
*/
|
|
static void detach_destroy_domains(const struct cpumask *cpu_map)
|
|
{
|
|
int i;
|
|
|
|
rcu_read_lock();
|
|
for_each_cpu(i, cpu_map)
|
|
cpu_attach_domain(NULL, &def_root_domain, i);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* handle null as "default" */
|
|
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
|
|
struct sched_domain_attr *new, int idx_new)
|
|
{
|
|
struct sched_domain_attr tmp;
|
|
|
|
/* fast path */
|
|
if (!new && !cur)
|
|
return 1;
|
|
|
|
tmp = SD_ATTR_INIT;
|
|
return !memcmp(cur ? (cur + idx_cur) : &tmp,
|
|
new ? (new + idx_new) : &tmp,
|
|
sizeof(struct sched_domain_attr));
|
|
}
|
|
|
|
/*
|
|
* Partition sched domains as specified by the 'ndoms_new'
|
|
* cpumasks in the array doms_new[] of cpumasks. This compares
|
|
* doms_new[] to the current sched domain partitioning, doms_cur[].
|
|
* It destroys each deleted domain and builds each new domain.
|
|
*
|
|
* 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
|
|
* The masks don't intersect (don't overlap.) We should setup one
|
|
* sched domain for each mask. CPUs not in any of the cpumasks will
|
|
* not be load balanced. If the same cpumask appears both in the
|
|
* current 'doms_cur' domains and in the new 'doms_new', we can leave
|
|
* it as it is.
|
|
*
|
|
* The passed in 'doms_new' should be allocated using
|
|
* alloc_sched_domains. This routine takes ownership of it and will
|
|
* free_sched_domains it when done with it. If the caller failed the
|
|
* alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
|
|
* and partition_sched_domains() will fallback to the single partition
|
|
* 'fallback_doms', it also forces the domains to be rebuilt.
|
|
*
|
|
* If doms_new == NULL it will be replaced with cpu_online_mask.
|
|
* ndoms_new == 0 is a special case for destroying existing domains,
|
|
* and it will not create the default domain.
|
|
*
|
|
* Call with hotplug lock held
|
|
*/
|
|
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
|
|
struct sched_domain_attr *dattr_new)
|
|
{
|
|
int i, j, n;
|
|
int new_topology;
|
|
|
|
mutex_lock(&sched_domains_mutex);
|
|
|
|
/* always unregister in case we don't destroy any domains */
|
|
unregister_sched_domain_sysctl();
|
|
|
|
/* Let architecture update cpu core mappings. */
|
|
new_topology = arch_update_cpu_topology();
|
|
|
|
n = doms_new ? ndoms_new : 0;
|
|
|
|
/* Destroy deleted domains */
|
|
for (i = 0; i < ndoms_cur; i++) {
|
|
for (j = 0; j < n && !new_topology; j++) {
|
|
if (cpumask_equal(doms_cur[i], doms_new[j])
|
|
&& dattrs_equal(dattr_cur, i, dattr_new, j))
|
|
goto match1;
|
|
}
|
|
/* no match - a current sched domain not in new doms_new[] */
|
|
detach_destroy_domains(doms_cur[i]);
|
|
match1:
|
|
;
|
|
}
|
|
|
|
n = ndoms_cur;
|
|
if (doms_new == NULL) {
|
|
n = 0;
|
|
doms_new = &fallback_doms;
|
|
cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
|
|
WARN_ON_ONCE(dattr_new);
|
|
}
|
|
|
|
/* Build new domains */
|
|
for (i = 0; i < ndoms_new; i++) {
|
|
for (j = 0; j < n && !new_topology; j++) {
|
|
if (cpumask_equal(doms_new[i], doms_cur[j])
|
|
&& dattrs_equal(dattr_new, i, dattr_cur, j))
|
|
goto match2;
|
|
}
|
|
/* no match - add a new doms_new */
|
|
build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
|
|
match2:
|
|
;
|
|
}
|
|
|
|
/* Remember the new sched domains */
|
|
if (doms_cur != &fallback_doms)
|
|
free_sched_domains(doms_cur, ndoms_cur);
|
|
kfree(dattr_cur); /* kfree(NULL) is safe */
|
|
doms_cur = doms_new;
|
|
dattr_cur = dattr_new;
|
|
ndoms_cur = ndoms_new;
|
|
|
|
register_sched_domain_sysctl();
|
|
|
|
mutex_unlock(&sched_domains_mutex);
|
|
}
|
|
|
|
static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
|
|
|
|
/*
|
|
* 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 int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
switch (action) {
|
|
case CPU_ONLINE_FROZEN:
|
|
case CPU_DOWN_FAILED_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.
|
|
*/
|
|
num_cpus_frozen--;
|
|
if (likely(num_cpus_frozen)) {
|
|
partition_sched_domains(1, NULL, NULL);
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* This is the last CPU online operation. So fall through and
|
|
* restore the original sched domains by considering the
|
|
* cpuset configurations.
|
|
*/
|
|
|
|
case CPU_ONLINE:
|
|
case CPU_DOWN_FAILED:
|
|
cpuset_update_active_cpus(true);
|
|
break;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
switch (action) {
|
|
case CPU_DOWN_PREPARE:
|
|
cpuset_update_active_cpus(false);
|
|
break;
|
|
case CPU_DOWN_PREPARE_FROZEN:
|
|
num_cpus_frozen++;
|
|
partition_sched_domains(1, NULL, NULL);
|
|
break;
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
void __init sched_init_smp(void)
|
|
{
|
|
cpumask_var_t non_isolated_cpus;
|
|
|
|
alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
|
|
alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
|
|
|
|
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);
|
|
init_sched_domains(cpu_active_mask);
|
|
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
|
|
if (cpumask_empty(non_isolated_cpus))
|
|
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
|
|
mutex_unlock(&sched_domains_mutex);
|
|
|
|
hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
|
|
hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
|
|
hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
|
|
|
|
init_hrtick();
|
|
|
|
/* Move init over to a non-isolated CPU */
|
|
if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
|
|
BUG();
|
|
sched_init_granularity();
|
|
free_cpumask_var(non_isolated_cpus);
|
|
|
|
init_sched_rt_class();
|
|
init_sched_dl_class();
|
|
}
|
|
#else
|
|
void __init sched_init_smp(void)
|
|
{
|
|
sched_init_granularity();
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
const_debug unsigned int sysctl_timer_migration = 1;
|
|
|
|
int in_sched_functions(unsigned long addr)
|
|
{
|
|
return in_lock_functions(addr) ||
|
|
(addr >= (unsigned long)__sched_text_start
|
|
&& addr < (unsigned long)__sched_text_end);
|
|
}
|
|
|
|
#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);
|
|
#endif
|
|
|
|
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
|
|
|
|
void __init sched_init(void)
|
|
{
|
|
int i, j;
|
|
unsigned long alloc_size = 0, ptr;
|
|
|
|
#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
|
|
#ifdef CONFIG_CPUMASK_OFFSTACK
|
|
alloc_size += num_possible_cpus() * cpumask_size();
|
|
#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) = (void *)ptr;
|
|
ptr += cpumask_size();
|
|
}
|
|
#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
|
|
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, rq);
|
|
init_dl_rq(&rq->dl, rq);
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
|
|
INIT_LIST_HEAD(&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_LIST_HEAD(&rq->leaf_rt_rq_list);
|
|
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;
|
|
|
|
rq->last_load_update_tick = jiffies;
|
|
|
|
#ifdef CONFIG_SMP
|
|
rq->sd = NULL;
|
|
rq->rd = NULL;
|
|
rq->cpu_power = SCHED_POWER_SCALE;
|
|
rq->post_schedule = 0;
|
|
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->nohz_flags = 0;
|
|
#endif
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
rq->last_sched_tick = 0;
|
|
#endif
|
|
#endif
|
|
init_rq_hrtick(rq);
|
|
atomic_set(&rq->nr_iowait, 0);
|
|
}
|
|
|
|
set_load_weight(&init_task);
|
|
|
|
#ifdef CONFIG_PREEMPT_NOTIFIERS
|
|
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
|
|
#endif
|
|
|
|
/*
|
|
* The boot idle thread does lazy MMU switching as well:
|
|
*/
|
|
atomic_inc(&init_mm.mm_count);
|
|
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;
|
|
|
|
/*
|
|
* During early bootup we pretend to be a normal task:
|
|
*/
|
|
current->sched_class = &fair_sched_class;
|
|
|
|
#ifdef CONFIG_SMP
|
|
zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
|
|
/* May be allocated at isolcpus cmdline parse time */
|
|
if (cpu_isolated_map == NULL)
|
|
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
|
|
idle_thread_set_boot_cpu();
|
|
#endif
|
|
init_sched_fair_class();
|
|
|
|
scheduler_running = 1;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
|
|
static inline int preempt_count_equals(int preempt_offset)
|
|
{
|
|
int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
|
|
|
|
return (nested == preempt_offset);
|
|
}
|
|
|
|
void __might_sleep(const char *file, int line, int preempt_offset)
|
|
{
|
|
static unsigned long prev_jiffy; /* ratelimiting */
|
|
|
|
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
|
|
if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
|
|
system_state != SYSTEM_RUNNING || oops_in_progress)
|
|
return;
|
|
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
|
|
return;
|
|
prev_jiffy = jiffies;
|
|
|
|
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);
|
|
|
|
debug_show_held_locks(current);
|
|
if (irqs_disabled())
|
|
print_irqtrace_events(current);
|
|
dump_stack();
|
|
}
|
|
EXPORT_SYMBOL(__might_sleep);
|
|
#endif
|
|
|
|
#ifdef CONFIG_MAGIC_SYSRQ
|
|
static void normalize_task(struct rq *rq, struct task_struct *p)
|
|
{
|
|
const struct sched_class *prev_class = p->sched_class;
|
|
struct sched_attr attr = {
|
|
.sched_policy = SCHED_NORMAL,
|
|
};
|
|
int old_prio = p->prio;
|
|
int on_rq;
|
|
|
|
on_rq = p->on_rq;
|
|
if (on_rq)
|
|
dequeue_task(rq, p, 0);
|
|
__setscheduler(rq, p, &attr);
|
|
if (on_rq) {
|
|
enqueue_task(rq, p, 0);
|
|
resched_task(rq->curr);
|
|
}
|
|
|
|
check_class_changed(rq, p, prev_class, old_prio);
|
|
}
|
|
|
|
void normalize_rt_tasks(void)
|
|
{
|
|
struct task_struct *g, *p;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
read_lock_irqsave(&tasklist_lock, flags);
|
|
do_each_thread(g, p) {
|
|
/*
|
|
* Only normalize user tasks:
|
|
*/
|
|
if (!p->mm)
|
|
continue;
|
|
|
|
p->se.exec_start = 0;
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
p->se.statistics.wait_start = 0;
|
|
p->se.statistics.sleep_start = 0;
|
|
p->se.statistics.block_start = 0;
|
|
#endif
|
|
|
|
if (!dl_task(p) && !rt_task(p)) {
|
|
/*
|
|
* Renice negative nice level userspace
|
|
* tasks back to 0:
|
|
*/
|
|
if (TASK_NICE(p) < 0 && p->mm)
|
|
set_user_nice(p, 0);
|
|
continue;
|
|
}
|
|
|
|
raw_spin_lock(&p->pi_lock);
|
|
rq = __task_rq_lock(p);
|
|
|
|
normalize_task(rq, p);
|
|
|
|
__task_rq_unlock(rq);
|
|
raw_spin_unlock(&p->pi_lock);
|
|
} while_each_thread(g, p);
|
|
|
|
read_unlock_irqrestore(&tasklist_lock, flags);
|
|
}
|
|
|
|
#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);
|
|
}
|
|
|
|
#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 set_curr_task(int cpu, struct task_struct *p)
|
|
{
|
|
cpu_curr(cpu) = p;
|
|
}
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
/* task_group_lock serializes the addition/removal of task groups */
|
|
static DEFINE_SPINLOCK(task_group_lock);
|
|
|
|
static void free_sched_group(struct task_group *tg)
|
|
{
|
|
free_fair_sched_group(tg);
|
|
free_rt_sched_group(tg);
|
|
autogroup_free(tg);
|
|
kfree(tg);
|
|
}
|
|
|
|
/* allocate runqueue etc for a new task group */
|
|
struct task_group *sched_create_group(struct task_group *parent)
|
|
{
|
|
struct task_group *tg;
|
|
|
|
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
|
|
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:
|
|
free_sched_group(tg);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
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);
|
|
|
|
WARN_ON(!parent); /* root should already exist */
|
|
|
|
tg->parent = parent;
|
|
INIT_LIST_HEAD(&tg->children);
|
|
list_add_rcu(&tg->siblings, &parent->children);
|
|
spin_unlock_irqrestore(&task_group_lock, flags);
|
|
}
|
|
|
|
/* rcu callback to free various structures associated with a task group */
|
|
static void free_sched_group_rcu(struct rcu_head *rhp)
|
|
{
|
|
/* now it should be safe to free those cfs_rqs */
|
|
free_sched_group(container_of(rhp, struct task_group, rcu));
|
|
}
|
|
|
|
/* Destroy runqueue etc associated with a task group */
|
|
void sched_destroy_group(struct task_group *tg)
|
|
{
|
|
/* wait for possible concurrent references to cfs_rqs complete */
|
|
call_rcu(&tg->rcu, free_sched_group_rcu);
|
|
}
|
|
|
|
void sched_offline_group(struct task_group *tg)
|
|
{
|
|
unsigned long flags;
|
|
int i;
|
|
|
|
/* end participation in shares distribution */
|
|
for_each_possible_cpu(i)
|
|
unregister_fair_sched_group(tg, i);
|
|
|
|
spin_lock_irqsave(&task_group_lock, flags);
|
|
list_del_rcu(&tg->list);
|
|
list_del_rcu(&tg->siblings);
|
|
spin_unlock_irqrestore(&task_group_lock, flags);
|
|
}
|
|
|
|
/* 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)
|
|
{
|
|
struct task_group *tg;
|
|
int on_rq, running;
|
|
unsigned long flags;
|
|
struct rq *rq;
|
|
|
|
rq = task_rq_lock(tsk, &flags);
|
|
|
|
running = task_current(rq, tsk);
|
|
on_rq = tsk->on_rq;
|
|
|
|
if (on_rq)
|
|
dequeue_task(rq, tsk, 0);
|
|
if (unlikely(running))
|
|
tsk->sched_class->put_prev_task(rq, tsk);
|
|
|
|
tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id,
|
|
lockdep_is_held(&tsk->sighand->siglock)),
|
|
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_move_group)
|
|
tsk->sched_class->task_move_group(tsk, on_rq);
|
|
else
|
|
#endif
|
|
set_task_rq(tsk, task_cpu(tsk));
|
|
|
|
if (unlikely(running))
|
|
tsk->sched_class->set_curr_task(rq);
|
|
if (on_rq)
|
|
enqueue_task(rq, tsk, 0);
|
|
|
|
task_rq_unlock(rq, tsk, &flags);
|
|
}
|
|
#endif /* CONFIG_CGROUP_SCHED */
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
/*
|
|
* Ensure that the real time constraints are schedulable.
|
|
*/
|
|
static DEFINE_MUTEX(rt_constraints_mutex);
|
|
|
|
/* Must be called with tasklist_lock held */
|
|
static inline int tg_has_rt_tasks(struct task_group *tg)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
do_each_thread(g, p) {
|
|
if (rt_task(p) && task_rq(p)->rt.tg == tg)
|
|
return 1;
|
|
} while_each_thread(g, p);
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct rt_schedulable_data {
|
|
struct task_group *tg;
|
|
u64 rt_period;
|
|
u64 rt_runtime;
|
|
};
|
|
|
|
static int tg_rt_schedulable(struct task_group *tg, void *data)
|
|
{
|
|
struct rt_schedulable_data *d = data;
|
|
struct task_group *child;
|
|
unsigned long total, sum = 0;
|
|
u64 period, runtime;
|
|
|
|
period = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
runtime = tg->rt_bandwidth.rt_runtime;
|
|
|
|
if (tg == d->tg) {
|
|
period = d->rt_period;
|
|
runtime = d->rt_runtime;
|
|
}
|
|
|
|
/*
|
|
* Cannot have more runtime than the period.
|
|
*/
|
|
if (runtime > period && runtime != RUNTIME_INF)
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Ensure we don't starve existing RT tasks.
|
|
*/
|
|
if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
|
|
return -EBUSY;
|
|
|
|
total = to_ratio(period, runtime);
|
|
|
|
/*
|
|
* Nobody can have more than the global setting allows.
|
|
*/
|
|
if (total > to_ratio(global_rt_period(), global_rt_runtime()))
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* The sum of our children's runtime should not exceed our own.
|
|
*/
|
|
list_for_each_entry_rcu(child, &tg->children, siblings) {
|
|
period = ktime_to_ns(child->rt_bandwidth.rt_period);
|
|
runtime = child->rt_bandwidth.rt_runtime;
|
|
|
|
if (child == d->tg) {
|
|
period = d->rt_period;
|
|
runtime = d->rt_runtime;
|
|
}
|
|
|
|
sum += to_ratio(period, runtime);
|
|
}
|
|
|
|
if (sum > total)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
|
|
{
|
|
int ret;
|
|
|
|
struct rt_schedulable_data data = {
|
|
.tg = tg,
|
|
.rt_period = period,
|
|
.rt_runtime = runtime,
|
|
};
|
|
|
|
rcu_read_lock();
|
|
ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int tg_set_rt_bandwidth(struct task_group *tg,
|
|
u64 rt_period, u64 rt_runtime)
|
|
{
|
|
int i, err = 0;
|
|
|
|
mutex_lock(&rt_constraints_mutex);
|
|
read_lock(&tasklist_lock);
|
|
err = __rt_schedulable(tg, rt_period, rt_runtime);
|
|
if (err)
|
|
goto unlock;
|
|
|
|
raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
|
|
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
|
|
tg->rt_bandwidth.rt_runtime = rt_runtime;
|
|
|
|
for_each_possible_cpu(i) {
|
|
struct rt_rq *rt_rq = tg->rt_rq[i];
|
|
|
|
raw_spin_lock(&rt_rq->rt_runtime_lock);
|
|
rt_rq->rt_runtime = rt_runtime;
|
|
raw_spin_unlock(&rt_rq->rt_runtime_lock);
|
|
}
|
|
raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
|
|
unlock:
|
|
read_unlock(&tasklist_lock);
|
|
mutex_unlock(&rt_constraints_mutex);
|
|
|
|
return err;
|
|
}
|
|
|
|
static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
|
|
{
|
|
u64 rt_runtime, rt_period;
|
|
|
|
rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
|
|
if (rt_runtime_us < 0)
|
|
rt_runtime = RUNTIME_INF;
|
|
|
|
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
|
|
}
|
|
|
|
static long sched_group_rt_runtime(struct task_group *tg)
|
|
{
|
|
u64 rt_runtime_us;
|
|
|
|
if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
|
|
return -1;
|
|
|
|
rt_runtime_us = tg->rt_bandwidth.rt_runtime;
|
|
do_div(rt_runtime_us, NSEC_PER_USEC);
|
|
return rt_runtime_us;
|
|
}
|
|
|
|
static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
|
|
{
|
|
u64 rt_runtime, rt_period;
|
|
|
|
rt_period = (u64)rt_period_us * NSEC_PER_USEC;
|
|
rt_runtime = tg->rt_bandwidth.rt_runtime;
|
|
|
|
if (rt_period == 0)
|
|
return -EINVAL;
|
|
|
|
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
|
|
}
|
|
|
|
static long sched_group_rt_period(struct task_group *tg)
|
|
{
|
|
u64 rt_period_us;
|
|
|
|
rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
|
|
do_div(rt_period_us, NSEC_PER_USEC);
|
|
return rt_period_us;
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
#ifdef CONFIG_RT_GROUP_SCHED
|
|
static int sched_rt_global_constraints(void)
|
|
{
|
|
int ret = 0;
|
|
|
|
mutex_lock(&rt_constraints_mutex);
|
|
read_lock(&tasklist_lock);
|
|
ret = __rt_schedulable(NULL, 0, 0);
|
|
read_unlock(&tasklist_lock);
|
|
mutex_unlock(&rt_constraints_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
|
|
{
|
|
/* Don't accept realtime tasks when there is no way for them to run */
|
|
if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
#else /* !CONFIG_RT_GROUP_SCHED */
|
|
static int sched_rt_global_constraints(void)
|
|
{
|
|
unsigned long flags;
|
|
int i, ret = 0;
|
|
|
|
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
|
|
for_each_possible_cpu(i) {
|
|
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
|
|
|
|
raw_spin_lock(&rt_rq->rt_runtime_lock);
|
|
rt_rq->rt_runtime = global_rt_runtime();
|
|
raw_spin_unlock(&rt_rq->rt_runtime_lock);
|
|
}
|
|
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
|
|
|
|
return ret;
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
static int sched_dl_global_constraints(void)
|
|
{
|
|
u64 runtime = global_rt_runtime();
|
|
u64 period = global_rt_period();
|
|
u64 new_bw = to_ratio(period, runtime);
|
|
int cpu, ret = 0;
|
|
|
|
/*
|
|
* Here we want to check the bandwidth not being set to some
|
|
* value smaller than the currently allocated bandwidth in
|
|
* any of the root_domains.
|
|
*
|
|
* FIXME: Cycling on all the CPUs is overdoing, but simpler than
|
|
* cycling on root_domains... Discussion on different/better
|
|
* solutions is welcome!
|
|
*/
|
|
for_each_possible_cpu(cpu) {
|
|
struct dl_bw *dl_b = dl_bw_of(cpu);
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
|
if (new_bw < dl_b->total_bw)
|
|
ret = -EBUSY;
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
if (ret)
|
|
break;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void sched_dl_do_global(void)
|
|
{
|
|
u64 new_bw = -1;
|
|
int cpu;
|
|
|
|
def_dl_bandwidth.dl_period = global_rt_period();
|
|
def_dl_bandwidth.dl_runtime = global_rt_runtime();
|
|
|
|
if (global_rt_runtime() != RUNTIME_INF)
|
|
new_bw = to_ratio(global_rt_period(), global_rt_runtime());
|
|
|
|
/*
|
|
* FIXME: As above...
|
|
*/
|
|
for_each_possible_cpu(cpu) {
|
|
struct dl_bw *dl_b = dl_bw_of(cpu);
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
|
dl_b->bw = new_bw;
|
|
raw_spin_unlock(&dl_b->lock);
|
|
}
|
|
}
|
|
|
|
static int sched_rt_global_validate(void)
|
|
{
|
|
if (sysctl_sched_rt_period <= 0)
|
|
return -EINVAL;
|
|
|
|
if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void sched_rt_do_global(void)
|
|
{
|
|
def_rt_bandwidth.rt_runtime = global_rt_runtime();
|
|
def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
|
|
}
|
|
|
|
int sched_rt_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int old_period, old_runtime;
|
|
static DEFINE_MUTEX(mutex);
|
|
int ret;
|
|
|
|
mutex_lock(&mutex);
|
|
old_period = sysctl_sched_rt_period;
|
|
old_runtime = sysctl_sched_rt_runtime;
|
|
|
|
ret = proc_dointvec(table, write, buffer, lenp, ppos);
|
|
|
|
if (!ret && write) {
|
|
ret = sched_rt_global_validate();
|
|
if (ret)
|
|
goto undo;
|
|
|
|
ret = sched_rt_global_constraints();
|
|
if (ret)
|
|
goto undo;
|
|
|
|
ret = sched_dl_global_constraints();
|
|
if (ret)
|
|
goto undo;
|
|
|
|
sched_rt_do_global();
|
|
sched_dl_do_global();
|
|
}
|
|
if (0) {
|
|
undo:
|
|
sysctl_sched_rt_period = old_period;
|
|
sysctl_sched_rt_runtime = old_runtime;
|
|
}
|
|
mutex_unlock(&mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
int sched_rr_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int ret;
|
|
static DEFINE_MUTEX(mutex);
|
|
|
|
mutex_lock(&mutex);
|
|
ret = proc_dointvec(table, write, buffer, lenp, ppos);
|
|
/* make sure that internally we keep jiffies */
|
|
/* also, writing zero resets timeslice to default */
|
|
if (!ret && write) {
|
|
sched_rr_timeslice = sched_rr_timeslice <= 0 ?
|
|
RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
|
|
}
|
|
mutex_unlock(&mutex);
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUP_SCHED
|
|
|
|
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
|
|
{
|
|
return css ? container_of(css, struct task_group, css) : NULL;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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(css));
|
|
|
|
if (parent)
|
|
sched_online_group(tg, parent);
|
|
return 0;
|
|
}
|
|
|
|
static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
|
|
{
|
|
struct task_group *tg = css_tg(css);
|
|
|
|
sched_destroy_group(tg);
|
|
}
|
|
|
|
static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
|
|
{
|
|
struct task_group *tg = css_tg(css);
|
|
|
|
sched_offline_group(tg);
|
|
}
|
|
|
|
static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
|
|
struct cgroup_taskset *tset)
|
|
{
|
|
struct task_struct *task;
|
|
|
|
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
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
|
|
struct cgroup_taskset *tset)
|
|
{
|
|
struct task_struct *task;
|
|
|
|
cgroup_taskset_for_each(task, css, tset)
|
|
sched_move_task(task);
|
|
}
|
|
|
|
static void cpu_cgroup_exit(struct cgroup_subsys_state *css,
|
|
struct cgroup_subsys_state *old_css,
|
|
struct task_struct *task)
|
|
{
|
|
/*
|
|
* cgroup_exit() is called in the copy_process() failure path.
|
|
* Ignore this case since the task hasn't ran yet, this avoids
|
|
* trying to poke a half freed task state from generic code.
|
|
*/
|
|
if (!(task->flags & PF_EXITING))
|
|
return;
|
|
|
|
sched_move_task(task);
|
|
}
|
|
|
|
#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));
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
#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;
|
|
|
|
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 && cfs_b->timer_active) {
|
|
/* force a reprogram */
|
|
cfs_b->timer_active = 0;
|
|
__start_cfs_bandwidth(cfs_b);
|
|
}
|
|
raw_spin_unlock_irq(&cfs_b->lock);
|
|
|
|
for_each_possible_cpu(i) {
|
|
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
|
|
struct rq *rq = cfs_rq->rq;
|
|
|
|
raw_spin_lock_irq(&rq->lock);
|
|
cfs_rq->runtime_enabled = runtime_enabled;
|
|
cfs_rq->runtime_remaining = 0;
|
|
|
|
if (cfs_rq->throttled)
|
|
unthrottle_cfs_rq(cfs_rq);
|
|
raw_spin_unlock_irq(&rq->lock);
|
|
}
|
|
if (runtime_was_enabled && !runtime_enabled)
|
|
cfs_bandwidth_usage_dec();
|
|
out_unlock:
|
|
mutex_unlock(&cfs_constraints_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
|
|
struct cftype *cft)
|
|
{
|
|
return tg_get_cfs_quota(css_tg(css));
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
|
|
struct cftype *cft)
|
|
{
|
|
return tg_get_cfs_period(css_tg(css));
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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->hierarchal_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->hierarchal_quota = quota;
|
|
|
|
return 0;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
static int cpu_stats_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;
|
|
}
|
|
#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);
|
|
}
|
|
|
|
static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
|
|
struct cftype *cft)
|
|
{
|
|
return sched_group_rt_runtime(css_tg(css));
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
|
|
struct cftype *cft)
|
|
{
|
|
return sched_group_rt_period(css_tg(css));
|
|
}
|
|
#endif /* CONFIG_RT_GROUP_SCHED */
|
|
|
|
static struct cftype cpu_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_stats_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 */
|
|
};
|
|
|
|
struct cgroup_subsys cpu_cgroup_subsys = {
|
|
.name = "cpu",
|
|
.css_alloc = cpu_cgroup_css_alloc,
|
|
.css_free = cpu_cgroup_css_free,
|
|
.css_online = cpu_cgroup_css_online,
|
|
.css_offline = cpu_cgroup_css_offline,
|
|
.can_attach = cpu_cgroup_can_attach,
|
|
.attach = cpu_cgroup_attach,
|
|
.exit = cpu_cgroup_exit,
|
|
.subsys_id = cpu_cgroup_subsys_id,
|
|
.base_cftypes = cpu_files,
|
|
.early_init = 1,
|
|
};
|
|
|
|
#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));
|
|
}
|