blob: 6107a0cd6325f9afe219007e1e1e446fda899b78 [file] [log] [blame]
/*
* kernel/sched.c
*
* Kernel scheduler and related syscalls
*
* Copyright (C) 1991-2002 Linus Torvalds
*
* 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
* make semaphores SMP safe
* 1998-11-19 Implemented schedule_timeout() and related stuff
* by Andrea Arcangeli
* 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
* hybrid priority-list and round-robin design with
* an array-switch method of distributing timeslices
* and per-CPU runqueues. Cleanups and useful suggestions
* by Davide Libenzi, preemptible kernel bits by Robert Love.
* 2003-09-03 Interactivity tuning by Con Kolivas.
* 2004-04-02 Scheduler domains code by Nick Piggin
* 2007-04-15 Work begun on replacing all interactivity tuning with a
* fair scheduling design by Con Kolivas.
* 2007-05-05 Load balancing (smp-nice) and other improvements
* by Peter Williams
* 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
*/
#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 <linux/smp_lock.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/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/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/kthread.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/reciprocal_div.h>
#include <linux/unistd.h>
#include <asm/tlb.h>
/*
* Scheduler clock - returns current time in nanosec units.
* This is default implementation.
* Architectures and sub-architectures can override this.
*/
unsigned long long __attribute__((weak)) sched_clock(void)
{
return (unsigned long long)jiffies * (1000000000 / HZ);
}
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
* and back.
*/
#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20)
#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20)
#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio)
/*
* 'User priority' is the nice value converted to something we
* can work with better when scaling various scheduler parameters,
* it's a [ 0 ... 39 ] range.
*/
#define USER_PRIO(p) ((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
/*
* Some helpers for converting nanosecond timing to jiffy resolution
*/
#define NS_TO_JIFFIES(TIME) ((TIME) / (1000000000 / HZ))
#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ))
#define NICE_0_LOAD SCHED_LOAD_SCALE
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
* These are the 'tuning knobs' of the scheduler:
*
* Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
* default timeslice is 100 msecs, maximum timeslice is 800 msecs.
* Timeslices get refilled after they expire.
*/
#define MIN_TIMESLICE max(5 * HZ / 1000, 1)
#define DEF_TIMESLICE (100 * HZ / 1000)
#ifdef CONFIG_SMP
/*
* Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
* Since cpu_power is a 'constant', we can use a reciprocal divide.
*/
static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
{
return reciprocal_divide(load, sg->reciprocal_cpu_power);
}
/*
* Each time a sched group cpu_power is changed,
* we must compute its reciprocal value
*/
static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
{
sg->__cpu_power += val;
sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
}
#endif
#define SCALE_PRIO(x, prio) \
max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)
/*
* static_prio_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
* to time slice values: [800ms ... 100ms ... 5ms]
*/
static unsigned int static_prio_timeslice(int static_prio)
{
if (static_prio == NICE_TO_PRIO(19))
return 1;
if (static_prio < NICE_TO_PRIO(0))
return SCALE_PRIO(DEF_TIMESLICE * 4, static_prio);
else
return SCALE_PRIO(DEF_TIMESLICE, static_prio);
}
static inline int rt_policy(int policy)
{
if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR))
return 1;
return 0;
}
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
}
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
struct rt_prio_array {
DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
struct list_head queue[MAX_RT_PRIO];
};
struct load_stat {
struct load_weight load;
u64 load_update_start, load_update_last;
unsigned long delta_fair, delta_exec, delta_stat;
};
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
unsigned long nr_running;
s64 fair_clock;
u64 exec_clock;
s64 wait_runtime;
u64 sleeper_bonus;
unsigned long wait_runtime_overruns, wait_runtime_underruns;
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
struct rb_node *rb_load_balance_curr;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
struct sched_entity *curr;
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
/* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
* a hierarchy). Non-leaf lrqs hold other higher schedulable entities
* (like users, containers etc.)
*
* leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
* list is used during load balance.
*/
struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
#endif
};
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
struct rt_prio_array active;
int rt_load_balance_idx;
struct list_head *rt_load_balance_head, *rt_load_balance_curr;
};
/*
* This is the main, per-CPU runqueue data structure.
*
* Locking rule: those places that want to lock multiple runqueues
* (such as the load balancing or the thread migration code), lock
* acquire operations must be ordered by ascending &runqueue.
*/
struct rq {
spinlock_t lock; /* runqueue lock */
/*
* nr_running and cpu_load should be in the same cacheline because
* remote CPUs use both these fields when doing load calculation.
*/
unsigned long nr_running;
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
unsigned char idle_at_tick;
#ifdef CONFIG_NO_HZ
unsigned char in_nohz_recently;
#endif
struct load_stat ls; /* capture load from *all* tasks on this cpu */
unsigned long nr_load_updates;
u64 nr_switches;
struct cfs_rq cfs;
#ifdef CONFIG_FAIR_GROUP_SCHED
struct list_head leaf_cfs_rq_list; /* list of leaf cfs_rq on this cpu */
#endif
struct rt_rq rt;
/*
* This is part of a global counter where only the total sum
* over all CPUs matters. A task can increase this counter on
* one CPU and if it got migrated afterwards it may decrease
* it on another CPU. Always updated under the runqueue lock:
*/
unsigned long nr_uninterruptible;
struct task_struct *curr, *idle;
unsigned long next_balance;
struct mm_struct *prev_mm;
u64 clock, prev_clock_raw;
s64 clock_max_delta;
unsigned int clock_warps, clock_overflows;
u64 idle_clock;
unsigned int clock_deep_idle_events;
u64 tick_timestamp;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
struct sched_domain *sd;
/* For active balancing */
int active_balance;
int push_cpu;
int cpu; /* cpu of this runqueue */
struct task_struct *migration_thread;
struct list_head migration_queue;
#endif
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
/* sys_sched_yield() stats */
unsigned long yld_exp_empty;
unsigned long yld_act_empty;
unsigned long yld_both_empty;
unsigned long yld_cnt;
/* schedule() stats */
unsigned long sched_switch;
unsigned long sched_cnt;
unsigned long sched_goidle;
/* try_to_wake_up() stats */
unsigned long ttwu_cnt;
unsigned long ttwu_local;
#endif
struct lock_class_key rq_lock_key;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
static DEFINE_MUTEX(sched_hotcpu_mutex);
static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
{
rq->curr->sched_class->check_preempt_curr(rq, p);
}
static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
return rq->cpu;
#else
return 0;
#endif
}
/*
* Update the per-runqueue clock, as finegrained as the platform can give
* us, but without assuming monotonicity, etc.:
*/
static void __update_rq_clock(struct rq *rq)
{
u64 prev_raw = rq->prev_clock_raw;
u64 now = sched_clock();
s64 delta = now - prev_raw;
u64 clock = rq->clock;
#ifdef CONFIG_SCHED_DEBUG
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
#endif
/*
* Protect against sched_clock() occasionally going backwards:
*/
if (unlikely(delta < 0)) {
clock++;
rq->clock_warps++;
} else {
/*
* Catch too large forward jumps too:
*/
if (unlikely(clock + delta > rq->tick_timestamp + TICK_NSEC)) {
if (clock < rq->tick_timestamp + TICK_NSEC)
clock = rq->tick_timestamp + TICK_NSEC;
else
clock++;
rq->clock_overflows++;
} else {
if (unlikely(delta > rq->clock_max_delta))
rq->clock_max_delta = delta;
clock += delta;
}
}
rq->prev_clock_raw = now;
rq->clock = clock;
}
static void update_rq_clock(struct rq *rq)
{
if (likely(smp_processor_id() == cpu_of(rq)))
__update_rq_clock(rq);
}
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* See detach_destroy_domains: synchronize_sched for details.
*
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.
*/
#define for_each_domain(cpu, __sd) \
for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
*/
unsigned long long cpu_clock(int cpu)
{
unsigned long long now;
unsigned long flags;
struct rq *rq;
local_irq_save(flags);
rq = cpu_rq(cpu);
update_rq_clock(rq);
now = rq->clock;
local_irq_restore(flags);
return now;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/* Change a task's ->cfs_rq if it moves across CPUs */
static inline void set_task_cfs_rq(struct task_struct *p)
{
p->se.cfs_rq = &task_rq(p)->cfs;
}
#else
static inline void set_task_cfs_rq(struct task_struct *p)
{
}
#endif
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev) do { } while (0)
#endif
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
}
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
rq->lock.owner = current;
#endif
/*
* If we are tracking spinlock dependencies then we have to
* fix up the runqueue lock - which gets 'carried over' from
* prev into current:
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->oncpu;
#else
return rq->curr == p;
#endif
}
static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* We can optimise this out completely for !SMP, because the
* SMP rebalancing from interrupt is the only thing that cares
* here.
*/
next->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
spin_unlock_irq(&rq->lock);
#else
spin_unlock(&rq->lock);
#endif
}
static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* After ->oncpu is cleared, the task can be moved to a different CPU.
* We must ensure this doesn't happen until the switch is completely
* finished.
*/
smp_wmb();
prev->oncpu = 0;
#endif
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
local_irq_enable();
#endif
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
/*
* __task_rq_lock - lock the runqueue a given task resides on.
* Must be called interrupts disabled.
*/
static inline struct rq *__task_rq_lock(struct task_struct *p)
__acquires(rq->lock)
{
struct rq *rq;
repeat_lock_task:
rq = task_rq(p);
spin_lock(&rq->lock);
if (unlikely(rq != task_rq(p))) {
spin_unlock(&rq->lock);
goto repeat_lock_task;
}
return rq;
}
/*
* task_rq_lock - lock the runqueue a given task resides on and disable
* interrupts. Note the ordering: we can safely lookup the task_rq without
* explicitly disabling preemption.
*/
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
__acquires(rq->lock)
{
struct rq *rq;
repeat_lock_task:
local_irq_save(*flags);
rq = task_rq(p);
spin_lock(&rq->lock);
if (unlikely(rq != task_rq(p))) {
spin_unlock_irqrestore(&rq->lock, *flags);
goto repeat_lock_task;
}
return rq;
}
static inline void __task_rq_unlock(struct rq *rq)
__releases(rq->lock)
{
spin_unlock(&rq->lock);
}
static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
__releases(rq->lock)
{
spin_unlock_irqrestore(&rq->lock, *flags);
}
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
static inline struct rq *this_rq_lock(void)
__acquires(rq->lock)
{
struct rq *rq;
local_irq_disable();
rq = this_rq();
spin_lock(&rq->lock);
return rq;
}
/*
* We are going deep-idle (irqs are disabled):
*/
void sched_clock_idle_sleep_event(void)
{
struct rq *rq = cpu_rq(smp_processor_id());
spin_lock(&rq->lock);
__update_rq_clock(rq);
spin_unlock(&rq->lock);
rq->clock_deep_idle_events++;
}
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
/*
* We just idled delta nanoseconds (called with irqs disabled):
*/
void sched_clock_idle_wakeup_event(u64 delta_ns)
{
struct rq *rq = cpu_rq(smp_processor_id());
u64 now = sched_clock();
rq->idle_clock += delta_ns;
/*
* Override the previous timestamp and ignore all
* sched_clock() deltas that occured while we idled,
* and use the PM-provided delta_ns to advance the
* rq clock:
*/
spin_lock(&rq->lock);
rq->prev_clock_raw = now;
rq->clock += delta_ns;
spin_unlock(&rq->lock);
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
/*
* resched_task - mark a task 'to be rescheduled now'.
*
* On UP this means the setting of the need_resched flag, on SMP it
* might also involve a cross-CPU call to trigger the scheduler on
* the target CPU.
*/
#ifdef CONFIG_SMP
#ifndef tsk_is_polling
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif
static void resched_task(struct task_struct *p)
{
int cpu;
assert_spin_locked(&task_rq(p)->lock);
if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
return;
set_tsk_thread_flag(p, TIF_NEED_RESCHED);
cpu = task_cpu(p);
if (cpu == smp_processor_id())
return;
/* NEED_RESCHED must be visible before we test polling */
smp_mb();
if (!tsk_is_polling(p))
smp_send_reschedule(cpu);
}
static void resched_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
if (!spin_trylock_irqsave(&rq->lock, flags))
return;
resched_task(cpu_curr(cpu));
spin_unlock_irqrestore(&rq->lock, flags);
}
#else
static inline void resched_task(struct task_struct *p)
{
assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
}
#endif
static u64 div64_likely32(u64 divident, unsigned long divisor)
{
#if BITS_PER_LONG == 32
if (likely(divident <= 0xffffffffULL))
return (u32)divident / divisor;
do_div(divident, divisor);
return divident;
#else
return divident / divisor;
#endif
}
#if BITS_PER_LONG == 32
# define WMULT_CONST (~0UL)
#else
# define WMULT_CONST (1UL << 32)
#endif
#define WMULT_SHIFT 32
/*
* Shift right and round:
*/
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
struct load_weight *lw)
{
u64 tmp;
if (unlikely(!lw->inv_weight))
lw->inv_weight = (WMULT_CONST - lw->weight/2) / lw->weight + 1;
tmp = (u64)delta_exec * weight;
/*
* Check whether we'd overflow the 64-bit multiplication:
*/
if (unlikely(tmp > WMULT_CONST))
tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
WMULT_SHIFT/2);
else
tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}
static inline unsigned long
calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
{
return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
}
static void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
lw->inv_weight = 0;
}
static void update_load_sub(struct load_weight *lw, unsigned long dec)
{
lw->weight -= dec;
lw->inv_weight = 0;
}
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
* of tasks with abnormal "nice" values across CPUs the contribution that
* each task makes to its run queue's load is weighted according to its
* scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
* scaled version of the new time slice allocation that they receive on time
* slice expiry etc.
*/
#define WEIGHT_IDLEPRIO 2
#define WMULT_IDLEPRIO (1 << 31)
/*
* Nice levels are multiplicative, with a gentle 10% change for every
* nice level changed. I.e. when a CPU-bound task goes from nice 0 to
* nice 1, it will get ~10% less CPU time than another CPU-bound task
* that remained on nice 0.
*
* The "10% effect" is relative and cumulative: from _any_ nice level,
* if you go up 1 level, it's -10% CPU usage, if you go down 1 level
* it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
* If a task goes up by ~10% and another task goes down by ~10% then
* the relative distance between them is ~25%.)
*/
static const int prio_to_weight[40] = {
/* -20 */ 88761, 71755, 56483, 46273, 36291,
/* -15 */ 29154, 23254, 18705, 14949, 11916,
/* -10 */ 9548, 7620, 6100, 4904, 3906,
/* -5 */ 3121, 2501, 1991, 1586, 1277,
/* 0 */ 1024, 820, 655, 526, 423,
/* 5 */ 335, 272, 215, 172, 137,
/* 10 */ 110, 87, 70, 56, 45,
/* 15 */ 36, 29, 23, 18, 15,
};
/*
* Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
*
* In cases where the weight does not change often, we can use the
* precalculated inverse to speed up arithmetics by turning divisions
* into multiplications:
*/
static const u32 prio_to_wmult[40] = {
/* -20 */ 48388, 59856, 76040, 92818, 118348,
/* -15 */ 147320, 184698, 229616, 287308, 360437,
/* -10 */ 449829, 563644, 704093, 875809, 1099582,
/* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326,
/* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587,
/* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126,
/* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717,
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
/*
* runqueue iterator, to support SMP load-balancing between different
* scheduling classes, without having to expose their internal data
* structures to the load-balancing proper:
*/
struct rq_iterator {
void *arg;
struct task_struct *(*start)(void *);
struct task_struct *(*next)(void *);
};
static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, unsigned long *load_moved,
int *this_best_prio, struct rq_iterator *iterator);
#include "sched_stats.h"
#include "sched_rt.c"
#include "sched_fair.c"
#include "sched_idletask.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif
#define sched_class_highest (&rt_sched_class)
static void __update_curr_load(struct rq *rq, struct load_stat *ls)
{
if (rq->curr != rq->idle && ls->load.weight) {
ls->delta_exec += ls->delta_stat;
ls->delta_fair += calc_delta_fair(ls->delta_stat, &ls->load);
ls->delta_stat = 0;
}
}
/*
* Update delta_exec, delta_fair fields for rq.
*
* delta_fair clock advances at a rate inversely proportional to
* total load (rq->ls.load.weight) on the runqueue, while
* delta_exec advances at the same rate as wall-clock (provided
* cpu is not idle).
*
* delta_exec / delta_fair is a measure of the (smoothened) load on this
* runqueue over any given interval. This (smoothened) load is used
* during load balance.
*
* This function is called /before/ updating rq->ls.load
* and when switching tasks.
*/
static void update_curr_load(struct rq *rq)
{
struct load_stat *ls = &rq->ls;
u64 start;
start = ls->load_update_start;
ls->load_update_start = rq->clock;
ls->delta_stat += rq->clock - start;
/*
* Stagger updates to ls->delta_fair. Very frequent updates
* can be expensive.
*/
if (ls->delta_stat >= sysctl_sched_stat_granularity)
__update_curr_load(rq, ls);
}
static inline void inc_load(struct rq *rq, const struct task_struct *p)
{
update_curr_load(rq);
update_load_add(&rq->ls.load, p->se.load.weight);
}
static inline void dec_load(struct rq *rq, const struct task_struct *p)
{
update_curr_load(rq);
update_load_sub(&rq->ls.load, p->se.load.weight);
}
static void inc_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running++;
inc_load(rq, p);
}
static void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
dec_load(rq, p);
}
static void set_load_weight(struct task_struct *p)
{
p->se.wait_runtime = 0;
if (task_has_rt_policy(p)) {
p->se.load.weight = prio_to_weight[0] * 2;
p->se.load.inv_weight = prio_to_wmult[0] >> 1;
return;
}
/*
* SCHED_IDLE tasks get minimal weight:
*/
if (p->policy == SCHED_IDLE) {
p->se.load.weight = WEIGHT_IDLEPRIO;
p->se.load.inv_weight = WMULT_IDLEPRIO;
return;
}
p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
}
static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
sched_info_queued(p);
p->sched_class->enqueue_task(rq, p, wakeup);
p->se.on_rq = 1;
}
static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
p->sched_class->dequeue_task(rq, p, sleep);
p->se.on_rq = 0;
}
/*
* __normal_prio - return the priority that is based on the static prio
*/
static inline int __normal_prio(struct task_struct *p)
{
return p->static_prio;
}
/*
* Calculate the expected normal priority: i.e. priority
* without taking RT-inheritance into account. Might be
* boosted by interactivity modifiers. Changes upon fork,
* setprio syscalls, and whenever the interactivity
* estimator recalculates.
*/
static inline int normal_prio(struct task_struct *p)
{
int prio;
if (task_has_rt_policy(p))
prio = MAX_RT_PRIO-1 - p->rt_priority;
else
prio = __normal_prio(p);
return prio;
}
/*
* Calculate the current priority, i.e. the priority
* taken into account by the scheduler. This value might
* be boosted by RT tasks, or might be boosted by
* interactivity modifiers. Will be RT if the task got
* RT-boosted. If not then it returns p->normal_prio.
*/
static int effective_prio(struct task_struct *p)
{
p->normal_prio = normal_prio(p);
/*
* If we are RT tasks or we were boosted to RT priority,
* keep the priority unchanged. Otherwise, update priority
* to the normal priority:
*/
if (!rt_prio(p->prio))
return p->normal_prio;
return p->prio;
}
/*
* activate_task - move a task to the runqueue.
*/
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible--;
enqueue_task(rq, p, wakeup);
inc_nr_running(p, rq);
}
/*
* activate_idle_task - move idle task to the _front_ of runqueue.
*/
static inline void activate_idle_task(struct task_struct *p, struct rq *rq)
{
update_rq_clock(rq);
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible--;
enqueue_task(rq, p, 0);
inc_nr_running(p, rq);
}
/*
* deactivate_task - remove a task from the runqueue.
*/
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
{
if (p->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible++;
dequeue_task(rq, p, sleep);
dec_nr_running(p, rq);
}
/**
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
*/
inline int task_curr(const struct task_struct *p)
{
return cpu_curr(task_cpu(p)) == p;
}
/* Used instead of source_load when we know the type == 0 */
unsigned long weighted_cpuload(const int cpu)
{
return cpu_rq(cpu)->ls.load.weight;
}
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
#ifdef CONFIG_SMP
task_thread_info(p)->cpu = cpu;
set_task_cfs_rq(p);
#endif
}
#ifdef CONFIG_SMP
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
int old_cpu = task_cpu(p);
struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
u64 clock_offset, fair_clock_offset;
clock_offset = old_rq->clock - new_rq->clock;
fair_clock_offset = old_rq->cfs.fair_clock - new_rq->cfs.fair_clock;
if (p->se.wait_start_fair)
p->se.wait_start_fair -= fair_clock_offset;
if (p->se.sleep_start_fair)
p->se.sleep_start_fair -= fair_clock_offset;
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
p->se.wait_start -= clock_offset;
if (p->se.sleep_start)
p->se.sleep_start -= clock_offset;
if (p->se.block_start)
p->se.block_start -= clock_offset;
#endif
__set_task_cpu(p, new_cpu);
}
struct migration_req {
struct list_head list;
struct task_struct *task;
int dest_cpu;
struct completion done;
};
/*
* The task's runqueue lock must be held.
* Returns true if you have to wait for migration thread.
*/
static int
migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
{
struct rq *rq = task_rq(p);
/*
* If the task is not on a runqueue (and not running), then
* it is sufficient to simply update the task's cpu field.
*/
if (!p->se.on_rq && !task_running(rq, p)) {
set_task_cpu(p, dest_cpu);
return 0;
}
init_completion(&req->done);
req->task = p;
req->dest_cpu = dest_cpu;
list_add(&req->list, &rq->migration_queue);
return 1;
}
/*
* wait_task_inactive - wait for a thread to unschedule.
*
* 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.
*/
void wait_task_inactive(struct task_struct *p)
{
unsigned long flags;
int running, on_rq;
struct rq *rq;
repeat:
/*
* 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))
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);
running = task_running(rq, p);
on_rq = p->se.on_rq;
task_rq_unlock(rq, &flags);
/*
* 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();
goto repeat;
}
/*
* It's not enough that it's not actively running,
* it must be off the runqueue _entirely_, and not
* preempted!
*
* So if it wa 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)) {
yield();
goto repeat;
}
/*
* 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!
*/
}
/***
* 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 doesnt 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();
}
/*
* Return a low guess at the load of a migration-source cpu weighted
* according to the scheduling class and "nice" value.
*
* We want to under-estimate the load of migration sources, to
* balance conservatively.
*/
static inline unsigned long source_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
if (type == 0)
return total;
return min(rq->cpu_load[type-1], total);
}
/*
* Return a high guess at the load of a migration-target cpu weighted
* according to the scheduling class and "nice" value.
*/
static inline unsigned long target_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
if (type == 0)
return total;
return max(rq->cpu_load[type-1], total);
}
/*
* Return the average load per task on the cpu's run queue
*/
static inline unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
unsigned long n = rq->nr_running;
return n ? total / n : SCHED_LOAD_SCALE;
}
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
{
struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
do {
unsigned long load, avg_load;
int local_group;
int i;
/* Skip over this group if it has no CPUs allowed */
if (!cpus_intersects(group->cpumask, p->cpus_allowed))
goto nextgroup;
local_group = cpu_isset(this_cpu, group->cpumask);
/* Tally up the load of all CPUs in the group */
avg_load = 0;
for_each_cpu_mask(i, group->cpumask) {
/* Bias balancing toward cpus of our domain */
if (local_group)
load = source_load(i, load_idx);
else
load = target_load(i, load_idx);
avg_load += load;
}
/* Adjust by relative CPU power of the group */
avg_load = sg_div_cpu_power(group,
avg_load * SCHED_LOAD_SCALE);
if (local_group) {
this_load = avg_load;
this = group;
} else if (avg_load < min_load) {
min_load = avg_load;
idlest = group;
}
nextgroup:
group = group->next;
} while (group != sd->groups);
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
}
/*
* find_idlest_cpu - find the idlest cpu among the cpus in group.
*/
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
cpumask_t tmp;
unsigned long load, min_load = ULONG_MAX;
int idlest = -1;
int i;
/* Traverse only the allowed CPUs */
cpus_and(tmp, group->cpumask, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
min_load = load;
idlest = i;
}
}
return idlest;
}
/*
* sched_balance_self: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
* SD_BALANCE_EXEC.
*
* Balance, ie. select the least loaded group.
*
* Returns the target CPU number, or the same CPU if no balancing is needed.
*
* preempt must be disabled.
*/
static int sched_balance_self(int cpu, int flag)
{
struct task_struct *t = current;
struct sched_domain *tmp, *sd = NULL;
for_each_domain(cpu, tmp) {
/*
* If power savings logic is enabled for a domain, stop there.
*/
if (tmp->flags & SD_POWERSAVINGS_BALANCE)
break;
if (tmp->flags & flag)
sd = tmp;
}
while (sd) {
cpumask_t span;
struct sched_group *group;
int new_cpu, weight;
if (!(sd->flags & flag)) {
sd = sd->child;
continue;
}
span = sd->span;
group = find_idlest_group(sd, t, cpu);
if (!group) {
sd = sd->child;
continue;
}
new_cpu = find_idlest_cpu(group, t, cpu);
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
continue;
}
/* Now try balancing at a lower domain level of new_cpu */
cpu = new_cpu;
sd = NULL;
weight = cpus_weight(span);
for_each_domain(cpu, tmp) {
if (weight <= cpus_weight(tmp->span))
break;
if (tmp->flags & flag)
sd = tmp;
}
/* while loop will break here if sd == NULL */
}
return cpu;
}
#endif /* CONFIG_SMP */
/*
* wake_idle() will wake a task on an idle cpu if task->cpu is
* not idle and an idle cpu is available. The span of cpus to
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
*
* Returns the CPU we should wake onto.
*/
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, struct task_struct *p)
{
cpumask_t tmp;
struct sched_domain *sd;
int i;
/*
* If it is idle, then it is the best cpu to run this task.
*
* This cpu is also the best, if it has more than one task already.
* Siblings must be also busy(in most cases) as they didn't already
* pickup the extra load from this cpu and hence we need not check
* sibling runqueue info. This will avoid the checks and cache miss
* penalities associated with that.
*/
if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
return cpu;
for_each_domain(cpu, sd) {
if (sd->flags & SD_WAKE_IDLE) {
cpus_and(tmp, sd->span, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
if (idle_cpu(i))
return i;
}
} else {
break;
}
}
return cpu;
}
#else
static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
}
#endif
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
* @state: the mask of task states that can be woken
* @sync: do a synchronous wakeup?
*
* 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.
*
* returns failure only if the task is already active.
*/
static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
int cpu, this_cpu, success = 0;
unsigned long flags;
long old_state;
struct rq *rq;
#ifdef CONFIG_SMP
struct sched_domain *sd, *this_sd = NULL;
unsigned long load, this_load;
int new_cpu;
#endif
rq = task_rq_lock(p, &flags);
old_state = p->state;
if (!(old_state & state))
goto out;
if (p->se.on_rq)
goto out_running;
cpu = task_cpu(p);
this_cpu = smp_processor_id();
#ifdef CONFIG_SMP
if (unlikely(task_running(rq, p)))
goto out_activate;
new_cpu = cpu;
schedstat_inc(rq, ttwu_cnt);
if (cpu == this_cpu) {
schedstat_inc(rq, ttwu_local);
goto out_set_cpu;
}
for_each_domain(this_cpu, sd) {
if (cpu_isset(cpu, sd->span)) {
schedstat_inc(sd, ttwu_wake_remote);
this_sd = sd;
break;
}
}
if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
goto out_set_cpu;
/*
* Check for affine wakeup and passive balancing possibilities.
*/
if (this_sd) {
int idx = this_sd->wake_idx;
unsigned int imbalance;
imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
load = source_load(cpu, idx);
this_load = target_load(this_cpu, idx);
new_cpu = this_cpu; /* Wake to this CPU if we can */
if (this_sd->flags & SD_WAKE_AFFINE) {
unsigned long tl = this_load;
unsigned long tl_per_task;
tl_per_task = cpu_avg_load_per_task(this_cpu);
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
if (sync)
tl -= current->se.load.weight;
if ((tl <= load &&
tl + target_load(cpu, idx) <= tl_per_task) ||
100*(tl + p->se.load.weight) <= imbalance*load) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
* there is no bad imbalance.
*/
schedstat_inc(this_sd, ttwu_move_affine);
goto out_set_cpu;
}
}
/*
* Start passive balancing when half the imbalance_pct
* limit is reached.
*/
if (this_sd->flags & SD_WAKE_BALANCE) {
if (imbalance*this_load <= 100*load) {
schedstat_inc(this_sd, ttwu_move_balance);
goto out_set_cpu;
}
}
}
new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
new_cpu = wake_idle(new_cpu, p);
if (new_cpu != cpu) {
set_task_cpu(p, new_cpu);
task_rq_unlock(rq, &flags);
/* might preempt at this point */
rq = task_rq_lock(p, &flags);
old_state = p->state;
if (!(old_state & state))
goto out;
if (p->se.on_rq)
goto out_running;
this_cpu = smp_processor_id();
cpu = task_cpu(p);
}
out_activate:
#endif /* CONFIG_SMP */
update_rq_clock(rq);
activate_task(rq, p, 1);
/*
* Sync wakeups (i.e. those types of wakeups where the waker
* has indicated that it will leave the CPU in short order)
* don't trigger a preemption, if the woken up task will run on
* this cpu. (in this case the 'I will reschedule' promise of
* the waker guarantees that the freshly woken up task is going
* to be considered on this CPU.)
*/
if (!sync || cpu != this_cpu)
check_preempt_curr(rq, p);
success = 1;
out_running:
p->state = TASK_RUNNING;
out:
task_rq_unlock(rq, &flags);
return success;
}
int fastcall wake_up_process(struct task_struct *p)
{
return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}
EXPORT_SYMBOL(wake_up_process);
int fastcall 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(struct task_struct *p)
{
p->se.wait_start_fair = 0;
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.delta_exec = 0;
p->se.delta_fair_run = 0;
p->se.delta_fair_sleep = 0;
p->se.wait_runtime = 0;
p->se.sleep_start_fair = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
p->se.sum_wait_runtime = 0;
p->se.sum_sleep_runtime = 0;
p->se.sleep_start = 0;
p->se.block_start = 0;
p->se.sleep_max = 0;
p->se.block_max = 0;
p->se.exec_max = 0;
p->se.wait_max = 0;
p->se.wait_runtime_overruns = 0;
p->se.wait_runtime_underruns = 0;
#endif
INIT_LIST_HEAD(&p->run_list);
p->se.on_rq = 0;
#ifdef CONFIG_PREEMPT_NOTIFIERS
INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif
/*
* We mark the process as running here, but have not actually
* inserted it onto the runqueue yet. 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;
}
/*
* fork()/clone()-time setup:
*/
void sched_fork(struct task_struct *p, int clone_flags)
{
int cpu = get_cpu();
__sched_fork(p);
#ifdef CONFIG_SMP
cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
__set_task_cpu(p, cpu);
/*
* Make sure we do not leak PI boosting priority to the child:
*/
p->prio = current->normal_prio;
#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) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
p->oncpu = 0;
#endif
#ifdef CONFIG_PREEMPT
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
put_cpu();
}
/*
* After fork, child runs first. (default) If set to 0 then
* parent will (try to) run first.
*/
unsigned int __read_mostly sysctl_sched_child_runs_first = 1;
/*
* 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 fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
unsigned long flags;
struct rq *rq;
int this_cpu;
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
this_cpu = smp_processor_id(); /* parent's CPU */
update_rq_clock(rq);
p->prio = effective_prio(p);
if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
if (!p->sched_class->task_new || !sysctl_sched_child_runs_first ||
(clone_flags & CLONE_VM) || task_cpu(p) != this_cpu ||
!current->se.on_rq) {
activate_task(rq, p, 0);
} else {
/*
* Let the scheduling class do new task startup
* management (if any):
*/
p->sched_class->task_new(rq, p);
inc_nr_running(p, rq);
}
check_preempt_curr(rq, p);
task_rq_unlock(rq, &flags);
}
#ifdef CONFIG_PREEMPT_NOTIFIERS
/**
* preempt_notifier_register - tell me when current is being being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
hlist_add_head(&notifier->link, &current->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(&notifier->link);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
struct hlist_node *node;
hlist_for_each_entry(notifier, node, &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;
struct hlist_node *node;
hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
notifier->ops->sched_out(notifier, next);
}
#else
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
/**
* 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)
{
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 inline 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;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
fire_sched_in_preempt_notifiers(current);
if (mm)
mmdrop(mm);
if (unlikely(prev_state == TASK_DEAD)) {
/*
* 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);
}
}
/**
* 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);
#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(current->pid, 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_enter_lazy_cpu_mode();
if (unlikely(!mm)) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
if (unlikely(!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
/* 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, nr_uninterruptible and nr_context_switches:
*
* externally visible scheduler statistics: current number of runnable
* threads, current number of uninterruptible-sleeping 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 nr_uninterruptible(void)
{
unsigned long i, sum = 0;
for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_uninterruptible;
/*
* Since we read the counters lockless, it might be slightly
* inaccurate. Do not allow it to go below zero though:
*/
if (unlikely((long)sum < 0))
sum = 0;
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_active(void)
{
unsigned long i, running = 0, uninterruptible = 0;
for_each_online_cpu(i) {
running += cpu_rq(i)->nr_running;
uninterruptible += cpu_rq(i)->nr_uninterruptible;
}
if (unlikely((long)uninterruptible < 0))
uninterruptible = 0;
return running + uninterruptible;
}
/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC).
*/
static void update_cpu_load(struct rq *this_rq)
{
u64 fair_delta64, exec_delta64, idle_delta64, sample_interval64, tmp64;
unsigned long total_load = this_rq->ls.load.weight;
unsigned long this_load = total_load;
struct load_stat *ls = &this_rq->ls;
int i, scale;
this_rq->nr_load_updates++;
if (unlikely(!(sysctl_sched_features & SCHED_FEAT_PRECISE_CPU_LOAD)))
goto do_avg;
/* Update delta_fair/delta_exec fields first */
update_curr_load(this_rq);
fair_delta64 = ls->delta_fair + 1;
ls->delta_fair = 0;
exec_delta64 = ls->delta_exec + 1;
ls->delta_exec = 0;
sample_interval64 = this_rq->clock - ls->load_update_last;
ls->load_update_last = this_rq->clock;
if ((s64)sample_interval64 < (s64)TICK_NSEC)
sample_interval64 = TICK_NSEC;
if (exec_delta64 > sample_interval64)
exec_delta64 = sample_interval64;
idle_delta64 = sample_interval64 - exec_delta64;
tmp64 = div64_64(SCHED_LOAD_SCALE * exec_delta64, fair_delta64);
tmp64 = div64_64(tmp64 * exec_delta64, sample_interval64);
this_load = (unsigned long)tmp64;
do_avg:
/* Update our load: */
for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
unsigned long old_load, new_load;
/* scale is effectively 1 << i now, and >> i divides by scale */
old_load = this_rq->cpu_load[i];
new_load = this_load;
this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
}
}
#ifdef CONFIG_SMP
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
static void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
BUG_ON(!irqs_disabled());
if (rq1 == rq2) {
spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
} else {
if (rq1 < rq2) {
spin_lock(&rq1->lock);
spin_lock(&rq2->lock);
} else {
spin_lock(&rq2->lock);
spin_lock(&rq1->lock);
}
}
update_rq_clock(rq1);
update_rq_clock(rq2);
}
/*
* double_rq_unlock - safely unlock two runqueues
*
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
spin_unlock(&rq1->lock);
if (rq1 != rq2)
spin_unlock(&rq2->lock);
else
__release(rq2->lock);
}
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
static void double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
spin_unlock(&this_rq->lock);
BUG_ON(1);
}
if (unlikely(!spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
spin_unlock(&this_rq->lock);
spin_lock(&busiest->lock);
spin_lock(&this_rq->lock);
} else
spin_lock(&busiest->lock);
}
}
/*
* If dest_cpu is allowed for this process, migrate the task to it.
* This is accomplished by forcing the cpu_allowed mask to only
* allow dest_cpu, which will force the cpu onto dest_cpu. Then
* the cpu_allowed mask is restored.
*/
static void sched_migrate_task(struct task_struct *p, int dest_cpu)
{
struct migration_req req;
unsigned long flags;
struct rq *rq;
rq = task_rq_lock(p, &flags);
if (!cpu_isset(dest_cpu, p->cpus_allowed)
|| unlikely(cpu_is_offline(dest_cpu)))
goto out;
/* force the process onto the specified CPU */
if (migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
struct task_struct *mt = rq->migration_thread;
get_task_struct(mt);
task_rq_unlock(rq, &flags);
wake_up_process(mt);
put_task_struct(mt);
wait_for_completion(&req.done);
return;
}
out:
task_rq_unlock(rq, &flags);
}
/*
* 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)
{
int new_cpu, this_cpu = get_cpu();
new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
put_cpu();
if (new_cpu != this_cpu)
sched_migrate_task(current, new_cpu);
}
/*
* pull_task - move a task from a remote runqueue to the local runqueue.
* Both runqueues must be locked.
*/
static void pull_task(struct rq *src_rq, struct task_struct *p,
struct rq *this_rq, int this_cpu)
{
deactivate_task(src_rq, p, 0);
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
/*
* Note that idle threads have a prio of MAX_PRIO, for this test
* to be always true for them.
*/
check_preempt_curr(this_rq, p);
}
/*
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
static
int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
/*
* We do not migrate tasks that are:
* 1) running (obviously), or
* 2) cannot be migrated to this CPU due to cpus_allowed, or
* 3) are cache-hot on their current CPU.
*/
if (!cpu_isset(this_cpu, p->cpus_allowed))
return 0;
*all_pinned = 0;
if (task_running(rq, p))
return 0;
return 1;
}
static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, unsigned long *load_moved,
int *this_best_prio, struct rq_iterator *iterator)
{
int pulled = 0, pinned = 0, skip_for_load;
struct task_struct *p;
long rem_load_move = max_load_move;
if (max_nr_move == 0 || max_load_move == 0)
goto out;
pinned = 1;
/*
* Start the load-balancing iterator:
*/
p = iterator->start(iterator->arg);
next:
if (!p)
goto out;
/*
* To help distribute high priority tasks accross CPUs we don't
* skip a task if it will be the highest priority task (i.e. smallest
* prio value) on its new queue regardless of its load weight
*/
skip_for_load = (p->se.load.weight >> 1) > rem_load_move +
SCHED_LOAD_SCALE_FUZZ;
if ((skip_for_load && p->prio >= *this_best_prio) ||
!can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
p = iterator->next(iterator->arg);
goto next;
}
pull_task(busiest, p, this_rq, this_cpu);
pulled++;
rem_load_move -= p->se.load.weight;
/*
* We only want to steal up to the prescribed number of tasks
* and the prescribed amount of weighted load.
*/
if (pulled < max_nr_move && rem_load_move > 0) {
if (p->prio < *this_best_prio)
*this_best_prio = p->prio;
p = iterator->next(iterator->arg);
goto next;
}
out:
/*
* Right now, this is the only place pull_task() is called,
* so we can safely collect pull_task() stats here rather than
* inside pull_task().
*/
schedstat_add(sd, lb_gained[idle], pulled);
if (all_pinned)
*all_pinned = pinned;
*load_moved = max_load_move - rem_load_move;
return pulled;
}
/*
* move_tasks tries to move up to max_load_move weighted load from busiest to
* this_rq, as part of a balancing operation within domain "sd".
* Returns 1 if successful and 0 otherwise.
*
* Called with both runqueues locked.
*/
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
struct sched_class *class = sched_class_highest;
unsigned long total_load_moved = 0;
int this_best_prio = this_rq->curr->prio;
do {
total_load_moved +=
class->load_balance(this_rq, this_cpu, busiest,
ULONG_MAX, max_load_move - total_load_moved,
sd, idle, all_pinned, &this_best_prio);
class = class->next;
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
}
/*
* move_one_task tries to move exactly one task from busiest to this_rq, as
* part of active balancing operations within "domain".
* Returns 1 if successful and 0 otherwise.
*
* Called with both runqueues locked.
*/
static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
struct sched_domain *sd, enum cpu_idle_type idle)
{
struct sched_class *class;
int this_best_prio = MAX_PRIO;
for (class = sched_class_highest; class; class = class->next)
if (class->load_balance(this_rq, this_cpu, busiest,
1, ULONG_MAX, sd, idle, NULL,
&this_best_prio))
return 1;
return 0;
}
/*
* find_busiest_group finds and returns the busiest CPU group within the
* domain. It calculates and returns the amount of weighted load which
* should be moved to restore balance via the imbalance parameter.
*/
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
int *sd_idle, cpumask_t *cpus, int *balance)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
unsigned long max_pull;
unsigned long busiest_load_per_task, busiest_nr_running;
unsigned long this_load_per_task, this_nr_running;
int load_idx;
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
int power_savings_balance = 1;
unsigned long leader_nr_running = 0, min_load_per_task = 0;
unsigned long min_nr_running = ULONG_MAX;
struct sched_group *group_min = NULL, *group_leader = NULL;
#endif
max_load = this_load = total_load = total_pwr = 0;
busiest_load_per_task = busiest_nr_running = 0;
this_load_per_task = this_nr_running = 0;
if (idle == CPU_NOT_IDLE)
load_idx = sd->busy_idx;
else if (idle == CPU_NEWLY_IDLE)
load_idx = sd->newidle_idx;
else
load_idx = sd->idle_idx;
do {
unsigned long load, group_capacity;
int local_group;
int i;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long sum_nr_running, sum_weighted_load;
local_group = cpu_isset(this_cpu, group->cpumask);
if (local_group)
balance_cpu = first_cpu(group->cpumask);
/* Tally up the load of all CPUs in the group */
sum_weighted_load = sum_nr_running = avg_load = 0;
for_each_cpu_mask(i, group->cpumask) {
struct rq *rq;
if (!cpu_isset(i, *cpus))
continue;
rq = cpu_rq(i);
if (*sd_idle && rq->nr_running)
*sd_idle = 0;
/* Bias balancing toward cpus of our domain */
if (local_group) {
if (idle_cpu(i) && !first_idle_cpu) {
first_idle_cpu = 1;
balance_cpu = i;
}
load = target_load(i, load_idx);
} else
load = source_load(i, load_idx);
avg_load += load;
sum_nr_running += rq->nr_running;
sum_weighted_load += weighted_cpuload(i);
}
/*
* First idle cpu or the first cpu(busiest) in this sched group
* is eligible for doing load balancing at this and above
* domains. In the newly idle case, we will allow all the cpu's
* to do the newly idle load balance.
*/
if (idle != CPU_NEWLY_IDLE && local_group &&
balance_cpu != this_cpu && balance) {
*balance = 0;
goto ret;
}
total_load += avg_load;
total_pwr += group->__cpu_power;
/* Adjust by relative CPU power of the group */
avg_load = sg_div_cpu_power(group,
avg_load * SCHED_LOAD_SCALE);
group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
if (local_group) {
this_load = avg_load;
this = group;
this_nr_running = sum_nr_running;
this_load_per_task = sum_weighted_load;
} else if (avg_load > max_load &&
sum_nr_running > group_capacity) {
max_load = avg_load;
busiest = group;
busiest_nr_running = sum_nr_running;
busiest_load_per_task = sum_weighted_load;
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/*
* Busy processors will not participate in power savings
* balance.
*/
if (idle == CPU_NOT_IDLE ||
!(sd->flags & SD_POWERSAVINGS_BALANCE))
goto group_next;
/*
* If the local group is idle or completely loaded
* no need to do power savings balance at this domain
*/
if (local_group && (this_nr_running >= group_capacity ||
!this_nr_running))
power_savings_balance = 0;
/*
* If a group is already running at full capacity or idle,
* don't include that group in power savings calculations
*/
if (!power_savings_balance || sum_nr_running >= group_capacity
|| !sum_nr_running)
goto group_next;
/*
* Calculate the group which has the least non-idle load.
* This is the group from where we need to pick up the load
* for saving power
*/
if ((sum_nr_running < min_nr_running) ||
(sum_nr_running == min_nr_running &&
first_cpu(group->cpumask) <
first_cpu(group_min->cpumask))) {
group_min = group;
min_nr_running = sum_nr_running;
min_load_per_task = sum_weighted_load /
sum_nr_running;
}
/*
* Calculate the group which is almost near its
* capacity but still has some space to pick up some load
* from other group and save more power
*/
if (sum_nr_running <= group_capacity - 1) {
if (sum_nr_running > leader_nr_running ||
(sum_nr_running == leader_nr_running &&
first_cpu(group->cpumask) >
first_cpu(group_leader->cpumask))) {
group_leader = group;
leader_nr_running = sum_nr_running;
}
}
group_next:
#endif
group = group->next;
} while (group != sd->groups);
if (!busiest || this_load >= max_load || busiest_nr_running == 0)
goto out_balanced;
avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
if (this_load >= avg_load ||
100*max_load <= sd->imbalance_pct*this_load)
goto out_balanced;
busiest_load_per_task /= busiest_nr_running;
/*
* We're trying to get all the cpus to the average_load, so we don't
* want to push ourselves above the average load, nor do we wish to
* reduce the max loaded cpu below the average load, as either of these
* actions would just result in more rebalancing later, and ping-pong
* tasks around. Thus we look for the minimum possible imbalance.
* Negative imbalances (*we* are more loaded than anyone else) will
* be counted as no imbalance for these purposes -- we can't fix that
* by pulling tasks to us. Be careful of negative numbers as they'll
* appear as very large values with unsigned longs.
*/
if (max_load <= busiest_load_per_task)
goto out_balanced;
/*
* In the presence of smp nice balancing, certain scenarios can have
* max load less than avg load(as we skip the groups at or below
* its cpu_power, while calculating max_load..)
*/
if (max_load < avg_load) {
*imbalance = 0;
goto small_imbalance;
}
/* Don't want to pull so many tasks that a group would go idle */
max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
/* How much load to actually move to equalise the imbalance */
*imbalance = min(max_pull * busiest->__cpu_power,
(avg_load - this_load) * this->__cpu_power)
/ SCHED_LOAD_SCALE;
/*
* if *imbalance is less than the average load per runnable task
* there is no gaurantee that any tasks will be moved so we'll have
* a think about bumping its value to force at least one task to be
* moved
*/
if (*imbalance < busiest_load_per_task) {
unsigned long tmp, pwr_now, pwr_move;
unsigned int imbn;
small_imbalance:
pwr_move = pwr_now = 0;
imbn = 2;
if (this_nr_running) {
this_load_per_task /= this_nr_running;
if (busiest_load_per_task > this_load_per_task)
imbn = 1;
} else
this_load_per_task = SCHED_LOAD_SCALE;
if (max_load - this_load + SCHED_LOAD_SCALE_FUZZ >=
busiest_load_per_task * imbn) {
*imbalance = busiest_load_per_task;
return busiest;
}
/*
* OK, we don't have enough imbalance to justify moving tasks,
* however we may be able to increase total CPU power used by
* moving them.
*/
pwr_now += busiest->__cpu_power *
min(busiest_load_per_task, max_load);
pwr_now += this->__cpu_power *
min(this_load_per_task, this_load);
pwr_now /= SCHED_LOAD_SCALE;
/* Amount of load we'd subtract */
tmp = sg_div_cpu_power(busiest,
busiest_load_per_task * SCHED_LOAD_SCALE);
if (max_load > tmp)
pwr_move += busiest->__cpu_power *
min(busiest_load_per_task, max_load - tmp);
/* Amount of load we'd add */
if (max_load * busiest->__cpu_power <
busiest_load_per_task * SCHED_LOAD_SCALE)
tmp = sg_div_cpu_power(this,
max_load * busiest->__cpu_power);
else
tmp = sg_div_cpu_power(this,
busiest_load_per_task * SCHED_LOAD_SCALE);
pwr_move += this->__cpu_power *
min(this_load_per_task, this_load + tmp);
pwr_move /= SCHED_LOAD_SCALE;
/* Move if we gain throughput */
if (pwr_move > pwr_now)
*imbalance = busiest_load_per_task;
}
return busiest;
out_balanced:
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
goto ret;
if (this == group_leader && group_leader != group_min) {
*imbalance = min_load_per_task;
return group_min;
}
#endif
ret:
*imbalance = 0;
return NULL;
}
/*
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
static struct rq *
find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
unsigned long imbalance, cpumask_t *cpus)
{
struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
int i;
for_each_cpu_mask(i, group->cpumask) {
unsigned long wl;
if (!cpu_isset(i, *cpus))
continue;
rq = cpu_rq(i);
wl = weighted_cpuload(i);
if (rq->nr_running == 1 && wl > imbalance)
continue;
if (wl > max_load) {
max_load = wl;
busiest = rq;
}
}
return busiest;
}
/*
* Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
* so long as it is large enough.
*/
#define MAX_PINNED_INTERVAL 512
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*/
static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
cpumask_t cpus = CPU_MASK_ALL;
unsigned long flags;
/*
* When power savings policy is enabled for the parent domain, idle
* sibling can pick up load irrespective of busy siblings. In this case,
* let the state of idle sibling percolate up as CPU_IDLE, instead of
* portraying it as CPU_NOT_IDLE.
*/
if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
schedstat_inc(sd, lb_cnt[idle]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
&cpus, balance);
if (*balance == 0)
goto out_balanced;
if (!group) {
schedstat_inc(sd, lb_nobusyg[idle]);
goto out_balanced;
}
busiest = find_busiest_queue(group, idle, imbalance, &cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
}
BUG_ON(busiest == this_rq);
schedstat_add(sd, lb_imbalance[idle], imbalance);
ld_moved = 0;
if (busiest->nr_running > 1) {
/*
* Attempt to move tasks. If find_busiest_group has found
* an imbalance but busiest->nr_running <= 1, the group is
* still unbalanced. ld_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
ld_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, idle, &all_pinned);
double_rq_unlock(this_rq, busiest);
local_irq_restore(flags);
/*
* some other cpu did the load balance for us.
*/
if (ld_moved && this_cpu != smp_processor_id())
resched_cpu(this_cpu);
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(all_pinned)) {
cpu_clear(cpu_of(busiest), cpus);
if (!cpus_empty(cpus))
goto redo;
goto out_balanced;
}
}
if (!ld_moved) {
schedstat_inc(sd, lb_failed[idle]);
sd->nr_balance_failed++;
if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
spin_unlock_irqrestore(&busiest->lock, flags);
all_pinned = 1;
goto out_one_pinned;
}
if (!busiest->active_balance) {
busiest->active_balance = 1;
busiest->push_cpu = this_cpu;
active_balance = 1;
}
spin_unlock_irqrestore(&busiest->lock, flags);
if (active_balance)
wake_up_process(busiest->migration_thread);
/*
* We've kicked active balancing, reset the failure
* counter.
*/
sd->nr_balance_failed = sd->cache_nice_tries+1;
}
} else
sd->nr_balance_failed = 0;
if (likely(!active_balance)) {
/* We were unbalanced, so reset the balancing interval */
sd->balance_interval = sd->min_interval;
} else {
/*
* If we've begun active balancing, start to back off. This
* case may not be covered by the all_pinned logic if there
* is only 1 task on the busy runqueue (because we don't call
* move_tasks).
*/
if (sd->balance_interval < sd->max_interval)
sd->balance_interval *= 2;
}
if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
return ld_moved;
out_balanced:
schedstat_inc(sd, lb_balanced[idle]);
sd->nr_balance_failed = 0;
out_one_pinned:
/* tune up the balancing interval */
if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
return 0;
}
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*
* Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
* this_rq is locked.
*/
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
struct sched_group *group;
struct rq *busiest = NULL;
unsigned long imbalance;
int ld_moved = 0;
int sd_idle = 0;
int all_pinned = 0;
cpumask_t cpus = CPU_MASK_ALL;
/*
* When power savings policy is enabled for the parent domain, idle
* sibling can pick up load irrespective of busy siblings. In this case,
* let the state of idle sibling percolate up as IDLE, instead of
* portraying it as CPU_NOT_IDLE.
*/
if (sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
schedstat_inc(sd, lb_cnt[CPU_NEWLY_IDLE]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
&sd_idle, &cpus, NULL);
if (!group) {
schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
goto out_balanced;
}
busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance,
&cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
goto out_balanced;
}
BUG_ON(busiest == this_rq);
schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
ld_moved = 0;
if (busiest->nr_running > 1) {
/* Attempt to move tasks */
double_lock_balance(this_rq, busiest);
/* this_rq->clock is already updated */
update_rq_clock(busiest);
ld_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, CPU_NEWLY_IDLE,
&all_pinned);
spin_unlock(&busiest->lock);
if (unlikely(all_pinned)) {
cpu_clear(cpu_of(busiest), cpus);
if (!cpus_empty(cpus))
goto redo;
}
}
if (!ld_moved) {
schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
} else
sd->nr_balance_failed = 0;
return ld_moved;
out_balanced:
schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
sd->nr_balance_failed = 0;
return 0;
}
/*
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
static void idle_balance(int this_cpu, struct rq *this_rq)
{
struct sched_domain *sd;
int pulled_task = -1;
unsigned long next_balance = jiffies + HZ;
for_each_domain(this_cpu, sd) {
unsigned long interval;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
if (sd->flags & SD_BALANCE_NEWIDLE)
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu,
this_rq, sd);
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
if (pulled_task)
break;
}
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
* We are going idle. next_balance may be set based on
* a busy processor. So reset next_balance.
*/
this_rq->next_balance = next_balance;
}
}
/*
* active_load_balance is run by migration threads. It pushes running tasks
* off the busiest CPU onto idle CPUs. It requires at least 1 task to be
* running on each physical CPU where possible, and avoids physical /
* logical imbalances.
*
* Called with busiest_rq locked.
*/
static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
{
int target_cpu = busiest_rq->push_cpu;
struct sched_domain *sd;
struct rq *target_rq;
/* Is there any task to move? */
if (busiest_rq->nr_running <= 1)
return;
target_rq = cpu_rq(target_cpu);
/*
* This condition is "impossible", if it occurs
* we need to fix it. Originally reported by
* Bjorn Helgaas on a 128-cpu setup.
*/
BUG_ON(busiest_rq == target_rq);
/* move a task from busiest_rq to target_rq */
double_lock_balance(busiest_rq, target_rq);
update_rq_clock(busiest_rq);
update_rq_clock(target_rq);
/* Search for an sd spanning us and the target CPU. */
for_each_domain(target_cpu, sd) {
if ((sd->flags & SD_LOAD_BALANCE) &&
cpu_isset(busiest_cpu, sd->span))
break;
}
if (likely(sd)) {
schedstat_inc(sd, alb_cnt);
if (move_one_task(target_rq, target_cpu, busiest_rq,
sd, CPU_IDLE))