X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsched.c;h=82975b5b42f71441eb148e3eeaac4c29a5316e4c;hb=c890692bf37671b5b78a1870d55d6d87e1c8a509;hp=3c91f110fc625a7a79304ad28165481b1a0be54b;hpb=047106adcc85e3023da210143a6ab8a55df9e0fc;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sched.c b/kernel/sched.c index 3c91f11..82975b5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -141,7 +141,7 @@ struct rt_prio_array { struct rt_bandwidth { /* nests inside the rq lock: */ - spinlock_t rt_runtime_lock; + raw_spinlock_t rt_runtime_lock; ktime_t rt_period; u64 rt_runtime; struct hrtimer rt_period_timer; @@ -178,7 +178,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period = ns_to_ktime(period); rt_b->rt_runtime = runtime; - spin_lock_init(&rt_b->rt_runtime_lock); + raw_spin_lock_init(&rt_b->rt_runtime_lock); hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); @@ -200,7 +200,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) if (hrtimer_active(&rt_b->rt_period_timer)) return; - spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_b->rt_runtime_lock); for (;;) { unsigned long delta; ktime_t soft, hard; @@ -217,7 +217,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, HRTIMER_MODE_ABS_PINNED, 0); } - spin_unlock(&rt_b->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); } #ifdef CONFIG_RT_GROUP_SCHED @@ -233,7 +233,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) */ static DEFINE_MUTEX(sched_domains_mutex); -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED #include @@ -243,13 +243,7 @@ static LIST_HEAD(task_groups); /* task group related information */ struct task_group { -#ifdef CONFIG_CGROUP_SCHED struct cgroup_subsys_state css; -#endif - -#ifdef CONFIG_USER_SCHED - uid_t uid; -#endif #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each cpu */ @@ -274,35 +268,7 @@ struct task_group { struct list_head children; }; -#ifdef CONFIG_USER_SCHED - -/* Helper function to pass uid information to create_sched_user() */ -void set_tg_uid(struct user_struct *user) -{ - user->tg->uid = user->uid; -} - -/* - * Root task group. - * Every UID task group (including init_task_group aka UID-0) will - * be a child to this group. - */ -struct task_group root_task_group; - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* Default task group's sched entity on each cpu */ -static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); -/* Default task group's cfs_rq on each cpu */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq); -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq); -#endif /* CONFIG_RT_GROUP_SCHED */ -#else /* !CONFIG_USER_SCHED */ #define root_task_group init_task_group -#endif /* CONFIG_USER_SCHED */ /* task_group_lock serializes add/remove of task groups and also changes to * a task group's cpu shares. @@ -318,11 +284,7 @@ static int root_task_group_empty(void) } #endif -#ifdef CONFIG_USER_SCHED -# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else /* !CONFIG_USER_SCHED */ # define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif /* CONFIG_USER_SCHED */ /* * A weight of 0 or 1 can cause arithmetics problems. @@ -348,11 +310,7 @@ static inline struct task_group *task_group(struct task_struct *p) { struct task_group *tg; -#ifdef CONFIG_USER_SCHED - rcu_read_lock(); - tg = __task_cred(p)->user->tg; - rcu_read_unlock(); -#elif defined(CONFIG_CGROUP_SCHED) +#ifdef CONFIG_CGROUP_SCHED tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), struct task_group, css); #else @@ -383,7 +341,7 @@ static inline struct task_group *task_group(struct task_struct *p) return NULL; } -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ /* CFS-related fields in a runqueue */ struct cfs_rq { @@ -470,7 +428,7 @@ struct rt_rq { u64 rt_time; u64 rt_runtime; /* Nests inside the rq lock: */ - spinlock_t rt_runtime_lock; + raw_spinlock_t rt_runtime_lock; #ifdef CONFIG_RT_GROUP_SCHED unsigned long rt_nr_boosted; @@ -478,7 +436,6 @@ struct rt_rq { struct rq *rq; struct list_head leaf_rt_rq_list; struct task_group *tg; - struct sched_rt_entity *rt_se; #endif }; @@ -525,7 +482,7 @@ static struct root_domain def_root_domain; */ struct rq { /* runqueue lock: */ - spinlock_t lock; + raw_spinlock_t lock; /* * nr_running and cpu_load should be in the same cacheline because @@ -535,14 +492,12 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ - unsigned long last_tick_seen; unsigned char in_nohz_recently; #endif /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; - u64 nr_migrations_in; struct cfs_rq cfs; struct rt_rq rt; @@ -591,6 +546,8 @@ struct rq { u64 rt_avg; u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; #endif /* calc_load related fields */ @@ -645,6 +602,11 @@ static inline int cpu_of(struct rq *rq) #endif } +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + rcu_read_lock_sched_held() || \ + lockdep_is_held(&sched_domains_mutex)) + /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. * See detach_destroy_domains: synchronize_sched for details. @@ -653,7 +615,7 @@ static inline int cpu_of(struct rq *rq) * preempt-disabled sections. */ #define for_each_domain(cpu, __sd) \ - for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() (&__get_cpu_var(runqueues)) @@ -685,7 +647,7 @@ inline void update_rq_clock(struct rq *rq) */ int runqueue_is_locked(int cpu) { - return spin_is_locked(&cpu_rq(cpu)->lock); + return raw_spin_is_locked(&cpu_rq(cpu)->lock); } /* @@ -772,7 +734,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, if (!sched_feat_names[i]) return -EINVAL; - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -814,6 +776,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; * default: 0.25ms */ unsigned int sysctl_sched_shares_ratelimit = 250000; +unsigned int normalized_sysctl_sched_shares_ratelimit = 250000; /* * Inject some fuzzyness into changing the per-cpu group shares @@ -892,7 +855,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ @@ -916,9 +879,9 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) next->oncpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); #else - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); #endif } @@ -940,18 +903,35 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* + * Check whether the task is waking, we use this to synchronize against + * ttwu() so that task_cpu() reports a stable number. + * + * We need to make an exception for PF_STARTING tasks because the fork + * path might require task_rq_lock() to work, eg. it can call + * set_cpus_allowed_ptr() from the cpuset clone_ns code. + */ +static inline int task_is_waking(struct task_struct *p) +{ + return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING)); +} + +/* * __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; + for (;;) { - struct rq *rq = task_rq(p); - spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) + while (task_is_waking(p)) + cpu_relax(); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_is_waking(p))) return rq; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } } @@ -966,12 +946,14 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) struct rq *rq; for (;;) { + while (task_is_waking(p)) + cpu_relax(); local_irq_save(*flags); rq = task_rq(p); - spin_lock(&rq->lock); - if (likely(rq == task_rq(p))) + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_is_waking(p))) return rq; - spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock_irqrestore(&rq->lock, *flags); } } @@ -980,19 +962,19 @@ void task_rq_unlock_wait(struct task_struct *p) struct rq *rq = task_rq(p); smp_mb(); /* spin-unlock-wait is not a full memory barrier */ - spin_unlock_wait(&rq->lock); + raw_spin_unlock_wait(&rq->lock); } static void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { - spin_unlock(&rq->lock); + raw_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); + raw_spin_unlock_irqrestore(&rq->lock, *flags); } /* @@ -1005,7 +987,7 @@ static struct rq *this_rq_lock(void) local_irq_disable(); rq = this_rq(); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); return rq; } @@ -1052,10 +1034,10 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); update_rq_clock(rq); rq->curr->sched_class->task_tick(rq, rq->curr, 1); - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); return HRTIMER_NORESTART; } @@ -1068,10 +1050,10 @@ static void __hrtick_start(void *arg) { struct rq *rq = arg; - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); hrtimer_restart(&rq->hrtick_timer); rq->hrtick_csd_pending = 0; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } /* @@ -1178,7 +1160,7 @@ static void resched_task(struct task_struct *p) { int cpu; - assert_spin_locked(&task_rq(p)->lock); + assert_raw_spin_locked(&task_rq(p)->lock); if (test_tsk_need_resched(p)) return; @@ -1200,10 +1182,10 @@ static void resched_cpu(int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - if (!spin_trylock_irqsave(&rq->lock, flags)) + if (!raw_spin_trylock_irqsave(&rq->lock, flags)) return; resched_task(cpu_curr(cpu)); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } #ifdef CONFIG_NO_HZ @@ -1272,7 +1254,7 @@ static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) #else /* !CONFIG_SMP */ static void resched_task(struct task_struct *p) { - assert_spin_locked(&task_rq(p)->lock); + assert_raw_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } @@ -1389,32 +1371,6 @@ static const u32 prio_to_wmult[40] = { /* 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 *); -}; - -#ifdef CONFIG_SMP -static unsigned long -balance_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, - int *this_best_prio, struct rq_iterator *iterator); - -static int -iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle, - struct rq_iterator *iterator); -#endif - /* Time spent by the tasks of the cpu accounting group executing in ... */ enum cpuacct_stat_index { CPUACCT_STAT_USER, /* ... user mode */ @@ -1530,7 +1486,7 @@ static unsigned long target_load(int cpu, int type) static struct sched_group *group_of(int cpu) { - struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd); + struct sched_domain *sd = rcu_dereference_sched(cpu_rq(cpu)->sd); if (!sd) return NULL; @@ -1565,7 +1521,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static __read_mostly unsigned long *update_shares_data; +static __read_mostly unsigned long __percpu *update_shares_data; static void __set_se_shares(struct sched_entity *se, unsigned long shares); @@ -1599,11 +1555,11 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu, struct rq *rq = cpu_rq(cpu); unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight; tg->cfs_rq[cpu]->shares = boost ? 0 : shares; __set_se_shares(tg->se[cpu], shares); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } } @@ -1614,7 +1570,7 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu, */ static int tg_shares_up(struct task_group *tg, void *data) { - unsigned long weight, rq_weight = 0, shares = 0; + unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0; unsigned long *usd_rq_weight; struct sched_domain *sd = data; unsigned long flags; @@ -1630,6 +1586,7 @@ static int tg_shares_up(struct task_group *tg, void *data) weight = tg->cfs_rq[i]->load.weight; usd_rq_weight[i] = weight; + rq_weight += weight; /* * If there are currently no tasks on the cpu pretend there * is one of average load so that when a new task gets to @@ -1638,10 +1595,13 @@ static int tg_shares_up(struct task_group *tg, void *data) if (!weight) weight = NICE_0_LOAD; - rq_weight += weight; + sum_weight += weight; shares += tg->cfs_rq[i]->shares; } + if (!rq_weight) + rq_weight = sum_weight; + if ((!shares && rq_weight) || shares > tg->shares) shares = tg->shares; @@ -1696,16 +1656,6 @@ static void update_shares(struct sched_domain *sd) } } -static void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ - if (root_task_group_empty()) - return; - - spin_unlock(&rq->lock); - update_shares(sd); - spin_lock(&rq->lock); -} - static void update_h_load(long cpu) { if (root_task_group_empty()) @@ -1720,10 +1670,6 @@ static inline void update_shares(struct sched_domain *sd) { } -static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ -} - #endif #ifdef CONFIG_PREEMPT @@ -1743,7 +1689,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __acquires(busiest->lock) __acquires(this_rq->lock) { - spin_unlock(&this_rq->lock); + raw_spin_unlock(&this_rq->lock); double_rq_lock(this_rq, busiest); return 1; @@ -1764,14 +1710,16 @@ static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) { int ret = 0; - if (unlikely(!spin_trylock(&busiest->lock))) { + if (unlikely(!raw_spin_trylock(&busiest->lock))) { if (busiest < this_rq) { - spin_unlock(&this_rq->lock); - spin_lock(&busiest->lock); - spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); + raw_spin_unlock(&this_rq->lock); + raw_spin_lock(&busiest->lock); + raw_spin_lock_nested(&this_rq->lock, + SINGLE_DEPTH_NESTING); ret = 1; } else - spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock_nested(&busiest->lock, + SINGLE_DEPTH_NESTING); } return ret; } @@ -1785,7 +1733,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) { if (unlikely(!irqs_disabled())) { /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); + raw_spin_unlock(&this_rq->lock); BUG_ON(1); } @@ -1795,9 +1743,54 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) __releases(busiest->lock) { - spin_unlock(&busiest->lock); + raw_spin_unlock(&busiest->lock); lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); } + +/* + * 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) { + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ + } else { + if (rq1 < rq2) { + raw_spin_lock(&rq1->lock); + raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); + } else { + raw_spin_lock(&rq2->lock); + raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); + } + } + 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) +{ + raw_spin_unlock(&rq1->lock); + if (rq1 != rq2) + raw_spin_unlock(&rq2->lock); + else + __release(rq2->lock); +} + #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1810,19 +1803,31 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #endif static void calc_load_account_active(struct rq *this_rq); +static void update_sysctl(void); +static int get_update_sysctl_factor(void); -#include "sched_stats.h" -#include "sched_idletask.c" -#include "sched_fair.c" -#include "sched_rt.c" -#ifdef CONFIG_SCHED_DEBUG -# include "sched_debug.c" +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + set_task_rq(p, cpu); +#ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + task_thread_info(p)->cpu = cpu; #endif +} + +static const struct sched_class rt_sched_class; #define sched_class_highest (&rt_sched_class) #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) +#include "sched_stats.h" + static void inc_nr_running(struct rq *rq) { rq->nr_running++; @@ -1860,13 +1865,14 @@ static void update_avg(u64 *avg, u64 sample) *avg += diff >> 3; } -static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) +static void +enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) { if (wakeup) p->se.start_runtime = p->se.sum_exec_runtime; sched_info_queued(p); - p->sched_class->enqueue_task(rq, p, wakeup); + p->sched_class->enqueue_task(rq, p, wakeup, head); p->se.on_rq = 1; } @@ -1889,6 +1895,37 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) } /* + * activate_task - move a task to the runqueue. + */ +static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + + enqueue_task(rq, p, wakeup, false); + inc_nr_running(rq); +} + +/* + * deactivate_task - remove a task from the runqueue. + */ +static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + + dequeue_task(rq, p, sleep); + dec_nr_running(rq); +} + +#include "sched_idletask.c" +#include "sched_fair.c" +#include "sched_rt.c" +#ifdef CONFIG_SCHED_DEBUG +# include "sched_debug.c" +#endif + +/* * __normal_prio - return the priority that is based on the static prio */ static inline int __normal_prio(struct task_struct *p) @@ -1934,30 +1971,6 @@ static int effective_prio(struct task_struct *p) 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 (task_contributes_to_load(p)) - rq->nr_uninterruptible--; - - enqueue_task(rq, p, wakeup); - inc_nr_running(rq); -} - -/* - * deactivate_task - remove a task from the runqueue. - */ -static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) -{ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible++; - - dequeue_task(rq, p, sleep); - dec_nr_running(rq); -} - /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. @@ -1967,20 +1980,6 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } -static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) -{ - set_task_rq(p, cpu); -#ifdef CONFIG_SMP - /* - * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be - * successfuly executed on another CPU. We must ensure that updates of - * per-task data have been completed by this moment. - */ - smp_wmb(); - task_thread_info(p)->cpu = cpu; -#endif -} - static inline void check_class_changed(struct rq *rq, struct task_struct *p, const struct sched_class *prev_class, int oldprio, int running) @@ -1993,39 +1992,6 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, p->sched_class->prio_changed(rq, p, oldprio, running); } -/** - * kthread_bind - bind a just-created kthread to a cpu. - * @p: thread created by kthread_create(). - * @cpu: cpu (might not be online, must be possible) for @k to run on. - * - * Description: This function is equivalent to set_cpus_allowed(), - * except that @cpu doesn't need to be online, and the thread must be - * stopped (i.e., just returned from kthread_create()). - * - * Function lives here instead of kthread.c because it messes with - * scheduler internals which require locking. - */ -void kthread_bind(struct task_struct *p, unsigned int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - /* Must have done schedule() in kthread() before we set_task_cpu */ - if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) { - WARN_ON(1); - return; - } - - spin_lock_irqsave(&rq->lock, flags); - update_rq_clock(rq); - set_task_cpu(p, cpu); - p->cpus_allowed = cpumask_of_cpu(cpu); - p->rt.nr_cpus_allowed = 1; - p->flags |= PF_THREAD_BOUND; - spin_unlock_irqrestore(&rq->lock, flags); -} -EXPORT_SYMBOL(kthread_bind); - #ifdef CONFIG_SMP /* * Is this task likely cache-hot: @@ -2035,6 +2001,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) { s64 delta; + if (p->sched_class != &fair_sched_class) + return 0; + /* * Buddy candidates are cache hot: */ @@ -2043,9 +2012,6 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) &p->se == cfs_rq_of(&p->se)->last)) return 1; - if (p->sched_class != &fair_sched_class) - return 0; - if (sysctl_sched_migration_cost == -1) return 1; if (sysctl_sched_migration_cost == 0) @@ -2056,39 +2022,23 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } - 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); - struct cfs_rq *old_cfsrq = task_cfs_rq(p), - *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu); - u64 clock_offset; - - clock_offset = old_rq->clock - new_rq->clock; +#ifdef CONFIG_SCHED_DEBUG + /* + * We should never call set_task_cpu() on a blocked task, + * ttwu() will sort out the placement. + */ + WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && + !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); +#endif trace_sched_migrate_task(p, new_cpu); -#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 - if (old_cpu != new_cpu) { + if (task_cpu(p) != new_cpu) { p->se.nr_migrations++; - new_rq->nr_migrations_in++; -#ifdef CONFIG_SCHEDSTATS - if (task_hot(p, old_rq->clock, NULL)) - schedstat_inc(p, se.nr_forced2_migrations); -#endif - perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, - 1, 1, NULL, 0); + perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); } - p->se.vruntime -= old_cfsrq->min_vruntime - - new_cfsrq->min_vruntime; __set_task_cpu(p, new_cpu); } @@ -2113,13 +2063,10 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) /* * If the task is not on a runqueue (and not running), then - * it is sufficient to simply update the task's cpu field. + * the next wake-up will properly place the task. */ - if (!p->se.on_rq && !task_running(rq, p)) { - update_rq_clock(rq); - set_task_cpu(p, dest_cpu); + if (!p->se.on_rq && !task_running(rq, p)) return 0; - } init_completion(&req->done); req->task = p; @@ -2324,40 +2271,109 @@ void task_oncpu_function_call(struct task_struct *p, preempt_enable(); } -/*** - * 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 wake_flags) +#ifdef CONFIG_SMP +static int select_fallback_rq(int cpu, struct task_struct *p) { - int cpu, orig_cpu, this_cpu, success = 0; - unsigned long flags; - struct rq *rq, *orig_rq; - - if (!sched_feat(SYNC_WAKEUPS)) - wake_flags &= ~WF_SYNC; + int dest_cpu; + const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); - this_cpu = get_cpu(); + /* Look for allowed, online CPU in same node. */ + for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + return dest_cpu; - smp_wmb(); - rq = orig_rq = task_rq_lock(p, &flags); - update_rq_clock(rq); - if (!(p->state & state)) - goto out; + /* Any allowed, online CPU? */ + dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); + if (dest_cpu < nr_cpu_ids) + return dest_cpu; - if (p->se.on_rq) - goto out_running; + /* No more Mr. Nice Guy. */ + if (dest_cpu >= nr_cpu_ids) { + rcu_read_lock(); + cpuset_cpus_allowed_locked(p, &p->cpus_allowed); + rcu_read_unlock(); + dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); + + /* + * 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(KERN_INFO "process %d (%s) no " + "longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } + } + + return dest_cpu; +} + +/* + * Gets called from 3 sites (exec, fork, wakeup), since it is called without + * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done + * by: + * + * exec: is unstable, retry loop + * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING + */ +static inline +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) +{ + int cpu = p->sched_class->select_task_rq(p, 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, &p->cpus_allowed) || + !cpu_online(cpu))) + cpu = select_fallback_rq(task_cpu(p), 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 wake_flags) +{ + int cpu, orig_cpu, this_cpu, success = 0; + unsigned long flags; + struct rq *rq; + + if (!sched_feat(SYNC_WAKEUPS)) + wake_flags &= ~WF_SYNC; + + this_cpu = get_cpu(); + + smp_wmb(); + rq = task_rq_lock(p, &flags); + update_rq_clock(rq); + if (!(p->state & state)) + goto out; + + if (p->se.on_rq) + goto out_running; cpu = task_cpu(p); orig_cpu = cpu; @@ -2375,20 +2391,34 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (task_contributes_to_load(p)) rq->nr_uninterruptible--; p->state = TASK_WAKING; - task_rq_unlock(rq, &flags); - cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags); + if (p->sched_class->task_waking) + p->sched_class->task_waking(rq, p); + + __task_rq_unlock(rq); + + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) { - local_irq_save(flags); - rq = cpu_rq(cpu); - update_rq_clock(rq); + /* + * Since we migrate the task without holding any rq->lock, + * we need to be careful with task_rq_lock(), since that + * might end up locking an invalid rq. + */ set_task_cpu(p, cpu); - local_irq_restore(flags); } - rq = task_rq_lock(p, &flags); + rq = cpu_rq(cpu); + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + + /* + * We migrated the task without holding either rq->lock, however + * since the task is not on the task list itself, nobody else + * will try and migrate the task, hence the rq should match the + * cpu we just moved it to. + */ + WARN_ON(task_cpu(p) != cpu); WARN_ON(p->state != TASK_WAKING); - cpu = task_cpu(p); #ifdef CONFIG_SCHEDSTATS schedstat_inc(rq, ttwu_count); @@ -2441,8 +2471,19 @@ out_running: p->state = TASK_RUNNING; #ifdef CONFIG_SMP - if (p->sched_class->task_wake_up) - p->sched_class->task_wake_up(rq, p); + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } #endif out: task_rq_unlock(rq, &flags); @@ -2489,7 +2530,6 @@ static void __sched_fork(struct task_struct *p) p->se.avg_overlap = 0; p->se.start_runtime = 0; p->se.avg_wakeup = sysctl_sched_wakeup_granularity; - p->se.avg_running = 0; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; @@ -2511,7 +2551,6 @@ static void __sched_fork(struct task_struct *p) p->se.nr_failed_migrations_running = 0; p->se.nr_failed_migrations_hot = 0; p->se.nr_forced_migrations = 0; - p->se.nr_forced2_migrations = 0; p->se.nr_wakeups = 0; p->se.nr_wakeups_sync = 0; @@ -2532,14 +2571,6 @@ static void __sched_fork(struct task_struct *p) #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; } /* @@ -2548,9 +2579,14 @@ static void __sched_fork(struct task_struct *p) void sched_fork(struct task_struct *p, int clone_flags) { int cpu = get_cpu(); - unsigned long flags; __sched_fork(p); + /* + * We mark the process as waking 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_WAKING; /* * Revert to default priority/policy on fork if requested. @@ -2582,13 +2618,10 @@ void sched_fork(struct task_struct *p, int clone_flags) if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; -#ifdef CONFIG_SMP - cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0); -#endif - local_irq_save(flags); - update_rq_clock(cpu_rq(cpu)); + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + set_task_cpu(p, cpu); - local_irq_restore(flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -2617,28 +2650,41 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; + int cpu __maybe_unused = get_cpu(); - rq = task_rq_lock(p, &flags); - BUG_ON(p->state != TASK_RUNNING); - update_rq_clock(rq); +#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 + * + * We still have TASK_WAKING but PF_STARTING is gone now, meaning + * ->cpus_allowed is stable, we have preemption disabled, meaning + * cpu_online_mask is stable. + */ + cpu = select_task_rq(p, SD_BALANCE_FORK, 0); + set_task_cpu(p, cpu); +#endif - if (!p->sched_class->task_new || !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(rq); - } + /* + * Since the task is not on the rq and we still have TASK_WAKING set + * nobody else will migrate this task. + */ + rq = cpu_rq(cpu); + raw_spin_lock_irqsave(&rq->lock, flags); + + BUG_ON(p->state != TASK_WAKING); + p->state = TASK_RUNNING; + update_rq_clock(rq); + activate_task(rq, p, 0); trace_sched_wakeup_new(rq, p, 1); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP - if (p->sched_class->task_wake_up) - p->sched_class->task_wake_up(rq, p); + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); #endif task_rq_unlock(rq, &flags); + put_cpu(); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -2757,10 +2803,16 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) */ prev_state = prev->state; finish_arch_switch(prev); - perf_event_task_sched_in(current, cpu_of(rq)); - fire_sched_in_preempt_notifiers(current); +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_disable(); +#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ + perf_event_task_sched_in(current); +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_enable(); +#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); + fire_sched_in_preempt_notifiers(current); if (mm) mmdrop(mm); if (unlikely(prev_state == TASK_DEAD)) { @@ -2788,10 +2840,10 @@ static inline void post_schedule(struct rq *rq) if (rq->post_schedule) { unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->curr->sched_class->post_schedule) rq->curr->sched_class->post_schedule(rq); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); rq->post_schedule = 0; } @@ -2855,14 +2907,14 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); - if (unlikely(!mm)) { + if (likely(!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)) { + if (likely(!prev->mm)) { prev->active_mm = NULL; rq->prev_mm = oldmm; } @@ -3025,15 +3077,6 @@ static void calc_load_account_active(struct rq *this_rq) } /* - * Externally visible per-cpu scheduler statistics: - * cpu_nr_migrations(cpu) - number of migrations into that cpu - */ -u64 cpu_nr_migrations(int cpu) -{ - return cpu_rq(cpu)->nr_migrations_in; -} - -/* * Update rq->cpu_load[] statistics. This function is usually called every * scheduler tick (TICK_NSEC). */ @@ -3046,1880 +3089,76 @@ static void update_cpu_load(struct rq *this_rq) /* 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; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale-1; - this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; - } - - if (time_after_eq(jiffies, this_rq->calc_load_update)) { - this_rq->calc_load_update += LOAD_FREQ; - calc_load_account_active(this_rq); - } -} - -#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_nested(&rq2->lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&rq2->lock); - spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); - } - } - 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); -} - -/* - * 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 (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) - || unlikely(!cpu_active(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 = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0); - 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, 0); -} - -/* - * 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) -{ - int tsk_cache_hot = 0; - /* - * 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 (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { - schedstat_inc(p, se.nr_failed_migrations_affine); - return 0; - } - *all_pinned = 0; - - if (task_running(rq, p)) { - schedstat_inc(p, se.nr_failed_migrations_running); - return 0; - } - - /* - * Aggressive migration if: - * 1) task is cache cold, or - * 2) too many balance attempts have failed. - */ - - tsk_cache_hot = task_hot(p, rq->clock, sd); - if (!tsk_cache_hot || - sd->nr_balance_failed > sd->cache_nice_tries) { -#ifdef CONFIG_SCHEDSTATS - if (tsk_cache_hot) { - schedstat_inc(sd, lb_hot_gained[idle]); - schedstat_inc(p, se.nr_forced_migrations); - } -#endif - return 1; - } - - if (tsk_cache_hot) { - schedstat_inc(p, se.nr_failed_migrations_hot); - return 0; - } - return 1; -} - -static unsigned long -balance_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, - int *this_best_prio, struct rq_iterator *iterator) -{ - int loops = 0, pulled = 0, pinned = 0; - struct task_struct *p; - long rem_load_move = max_load_move; - - if (max_load_move == 0) - goto out; - - pinned = 1; - - /* - * Start the load-balancing iterator: - */ - p = iterator->start(iterator->arg); -next: - if (!p || loops++ > sysctl_sched_nr_migrate) - goto out; - - if ((p->se.load.weight >> 1) > rem_load_move || - !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; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible kernels - * will stop after the first task is pulled to minimize the critical - * section. - */ - if (idle == CPU_NEWLY_IDLE) - goto out; -#endif - - /* - * We only want to steal up to the prescribed amount of weighted load. - */ - if (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 one of only two places 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; - - return max_load_move - rem_load_move; -} - -/* - * 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) -{ - const 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, - max_load_move - total_load_moved, - sd, idle, all_pinned, &this_best_prio); - class = class->next; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize - * the critical section. - */ - if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) - break; -#endif - } while (class && max_load_move > total_load_moved); - - return total_load_moved > 0; -} - -static int -iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle, - struct rq_iterator *iterator) -{ - struct task_struct *p = iterator->start(iterator->arg); - int pinned = 0; - - while (p) { - if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { - pull_task(busiest, p, this_rq, this_cpu); - /* - * Right now, this is only the second place pull_task() - * is called, so we can safely collect pull_task() - * stats here rather than inside pull_task(). - */ - schedstat_inc(sd, lb_gained[idle]); - - return 1; - } - p = iterator->next(iterator->arg); - } - - return 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) -{ - const struct sched_class *class; - - for_each_class(class) { - if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) - return 1; - } - - return 0; -} -/********** Helpers for find_busiest_group ************************/ -/* - * sd_lb_stats - Structure to store the statistics of a sched_domain - * during load balancing. - */ -struct sd_lb_stats { - struct sched_group *busiest; /* Busiest group in this sd */ - struct sched_group *this; /* Local group in this sd */ - unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ - unsigned long avg_load; /* Average load across all groups in sd */ - - /** Statistics of this group */ - unsigned long this_load; - unsigned long this_load_per_task; - unsigned long this_nr_running; - - /* Statistics of the busiest group */ - unsigned long max_load; - unsigned long busiest_load_per_task; - unsigned long busiest_nr_running; - - int group_imb; /* Is there imbalance in this sd */ -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance; /* Is powersave balance needed for this sd */ - struct sched_group *group_min; /* Least loaded group in sd */ - struct sched_group *group_leader; /* Group which relieves group_min */ - unsigned long min_load_per_task; /* load_per_task in group_min */ - unsigned long leader_nr_running; /* Nr running of group_leader */ - unsigned long min_nr_running; /* Nr running of group_min */ -#endif -}; - -/* - * sg_lb_stats - stats of a sched_group required for load_balancing - */ -struct sg_lb_stats { - unsigned long avg_load; /*Avg load across the CPUs of the group */ - unsigned long group_load; /* Total load over the CPUs of the group */ - unsigned long sum_nr_running; /* Nr tasks running in the group */ - unsigned long sum_weighted_load; /* Weighted load of group's tasks */ - unsigned long group_capacity; - int group_imb; /* Is there an imbalance in the group ? */ -}; - -/** - * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. - * @group: The group whose first cpu is to be returned. - */ -static inline unsigned int group_first_cpu(struct sched_group *group) -{ - return cpumask_first(sched_group_cpus(group)); -} - -/** - * get_sd_load_idx - Obtain the load index for a given sched domain. - * @sd: The sched_domain whose load_idx is to be obtained. - * @idle: The Idle status of the CPU for whose sd load_icx is obtained. - */ -static inline int get_sd_load_idx(struct sched_domain *sd, - enum cpu_idle_type idle) -{ - int load_idx; - - switch (idle) { - case CPU_NOT_IDLE: - load_idx = sd->busy_idx; - break; - - case CPU_NEWLY_IDLE: - load_idx = sd->newidle_idx; - break; - default: - load_idx = sd->idle_idx; - break; - } - - return load_idx; -} - - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * init_sd_power_savings_stats - Initialize power savings statistics for - * the given sched_domain, during load balancing. - * - * @sd: Sched domain whose power-savings statistics are to be initialized. - * @sds: Variable containing the statistics for sd. - * @idle: Idle status of the CPU at which we're performing load-balancing. - */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - sds->power_savings_balance = 0; - else { - sds->power_savings_balance = 1; - sds->min_nr_running = ULONG_MAX; - sds->leader_nr_running = 0; - } -} - -/** - * update_sd_power_savings_stats - Update the power saving stats for a - * sched_domain while performing load balancing. - * - * @group: sched_group belonging to the sched_domain under consideration. - * @sds: Variable containing the statistics of the sched_domain - * @local_group: Does group contain the CPU for which we're performing - * load balancing ? - * @sgs: Variable containing the statistics of the group. - */ -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - - if (!sds->power_savings_balance) - return; - - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (sds->this_nr_running >= sgs->group_capacity || - !sds->this_nr_running)) - sds->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 (!sds->power_savings_balance || - sgs->sum_nr_running >= sgs->group_capacity || - !sgs->sum_nr_running) - return; - - /* - * 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 ((sgs->sum_nr_running < sds->min_nr_running) || - (sgs->sum_nr_running == sds->min_nr_running && - group_first_cpu(group) > group_first_cpu(sds->group_min))) { - sds->group_min = group; - sds->min_nr_running = sgs->sum_nr_running; - sds->min_load_per_task = sgs->sum_weighted_load / - sgs->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 (sgs->sum_nr_running + 1 > sgs->group_capacity) - return; - - if (sgs->sum_nr_running > sds->leader_nr_running || - (sgs->sum_nr_running == sds->leader_nr_running && - group_first_cpu(group) < group_first_cpu(sds->group_leader))) { - sds->group_leader = group; - sds->leader_nr_running = sgs->sum_nr_running; - } -} - -/** - * check_power_save_busiest_group - see if there is potential for some power-savings balance - * @sds: Variable containing the statistics of the sched_domain - * under consideration. - * @this_cpu: Cpu at which we're currently performing load-balancing. - * @imbalance: Variable to store the imbalance. - * - * Description: - * Check if we have potential to perform some power-savings balance. - * If yes, set the busiest group to be the least loaded group in the - * sched_domain, so that it's CPUs can be put to idle. - * - * Returns 1 if there is potential to perform power-savings balance. - * Else returns 0. - */ -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - if (!sds->power_savings_balance) - return 0; - - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - *imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - return 1; - -} -#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - return; -} - -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - return; -} - -static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - return 0; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - - -unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) -{ - return SCHED_LOAD_SCALE; -} - -unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) -{ - return default_scale_freq_power(sd, cpu); -} - -unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) -{ - unsigned long weight = cpumask_weight(sched_domain_span(sd)); - unsigned long smt_gain = sd->smt_gain; - - smt_gain /= weight; - - return smt_gain; -} - -unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) -{ - return default_scale_smt_power(sd, cpu); -} - -unsigned long scale_rt_power(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - u64 total, available; - - sched_avg_update(rq); - - total = sched_avg_period() + (rq->clock - rq->age_stamp); - available = total - rq->rt_avg; - - if (unlikely((s64)total < SCHED_LOAD_SCALE)) - total = SCHED_LOAD_SCALE; - - total >>= SCHED_LOAD_SHIFT; - - return div_u64(available, total); -} - -static void update_cpu_power(struct sched_domain *sd, int cpu) -{ - unsigned long weight = cpumask_weight(sched_domain_span(sd)); - unsigned long power = SCHED_LOAD_SCALE; - struct sched_group *sdg = sd->groups; - - if (sched_feat(ARCH_POWER)) - power *= arch_scale_freq_power(sd, cpu); - else - power *= default_scale_freq_power(sd, cpu); - - power >>= SCHED_LOAD_SHIFT; - - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - if (sched_feat(ARCH_POWER)) - power *= arch_scale_smt_power(sd, cpu); - else - power *= default_scale_smt_power(sd, cpu); - - power >>= SCHED_LOAD_SHIFT; - } - - power *= scale_rt_power(cpu); - power >>= SCHED_LOAD_SHIFT; - - if (!power) - power = 1; - - sdg->cpu_power = power; -} - -static void update_group_power(struct sched_domain *sd, int cpu) -{ - struct sched_domain *child = sd->child; - struct sched_group *group, *sdg = sd->groups; - unsigned long power; - - if (!child) { - update_cpu_power(sd, cpu); - return; - } - - power = 0; - - group = child->groups; - do { - power += group->cpu_power; - group = group->next; - } while (group != child->groups); - - sdg->cpu_power = power; -} - -/** - * update_sg_lb_stats - Update sched_group's statistics for load balancing. - * @sd: The sched_domain whose statistics are to be updated. - * @group: sched_group whose statistics are to be updated. - * @this_cpu: Cpu for which load balance is currently performed. - * @idle: Idle status of this_cpu - * @load_idx: Load index of sched_domain of this_cpu for load calc. - * @sd_idle: Idle status of the sched_domain containing group. - * @local_group: Does group contain this_cpu. - * @cpus: Set of cpus considered for load balancing. - * @balance: Should we balance. - * @sgs: variable to hold the statistics for this group. - */ -static inline void update_sg_lb_stats(struct sched_domain *sd, - struct sched_group *group, int this_cpu, - enum cpu_idle_type idle, int load_idx, int *sd_idle, - int local_group, const struct cpumask *cpus, - int *balance, struct sg_lb_stats *sgs) -{ - unsigned long load, max_cpu_load, min_cpu_load; - int i; - unsigned int balance_cpu = -1, first_idle_cpu = 0; - unsigned long sum_avg_load_per_task; - unsigned long avg_load_per_task; - - if (local_group) { - balance_cpu = group_first_cpu(group); - if (balance_cpu == this_cpu) - update_group_power(sd, this_cpu); - } - - /* Tally up the load of all CPUs in the group */ - sum_avg_load_per_task = avg_load_per_task = 0; - max_cpu_load = 0; - min_cpu_load = ~0UL; - - for_each_cpu_and(i, sched_group_cpus(group), cpus) { - struct rq *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); - if (load > max_cpu_load) - max_cpu_load = load; - if (min_cpu_load > load) - min_cpu_load = load; - } - - sgs->group_load += load; - sgs->sum_nr_running += rq->nr_running; - sgs->sum_weighted_load += weighted_cpuload(i); - - sum_avg_load_per_task += cpu_avg_load_per_task(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; - return; - } - - /* Adjust by relative CPU power of the group */ - sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; - - - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of two tasks. - * - * APZ: with cgroup the avg task weight can vary wildly and - * might not be a suitable number - should we keep a - * normalized nr_running number somewhere that negates - * the hierarchy? - */ - avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) / - group->cpu_power; - - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) - sgs->group_imb = 1; - - sgs->group_capacity = - DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); -} - -/** - * update_sd_lb_stats - Update sched_group's statistics for load balancing. - * @sd: sched_domain whose statistics are to be updated. - * @this_cpu: Cpu for which load balance is currently performed. - * @idle: Idle status of this_cpu - * @sd_idle: Idle status of the sched_domain containing group. - * @cpus: Set of cpus considered for load balancing. - * @balance: Should we balance. - * @sds: variable to hold the statistics for this sched_domain. - */ -static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, - enum cpu_idle_type idle, int *sd_idle, - const struct cpumask *cpus, int *balance, - struct sd_lb_stats *sds) -{ - struct sched_domain *child = sd->child; - struct sched_group *group = sd->groups; - struct sg_lb_stats sgs; - int load_idx, prefer_sibling = 0; - - if (child && child->flags & SD_PREFER_SIBLING) - prefer_sibling = 1; - - init_sd_power_savings_stats(sd, sds, idle); - load_idx = get_sd_load_idx(sd, idle); - - do { - int local_group; - - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle, - local_group, cpus, balance, &sgs); - - if (local_group && balance && !(*balance)) - return; - - sds->total_load += sgs.group_load; - sds->total_pwr += group->cpu_power; - - /* - * In case the child domain prefers tasks go to siblings - * first, lower the group capacity to one so that we'll try - * and move all the excess tasks away. - */ - if (prefer_sibling) - sgs.group_capacity = min(sgs.group_capacity, 1UL); - - if (local_group) { - sds->this_load = sgs.avg_load; - sds->this = group; - sds->this_nr_running = sgs.sum_nr_running; - sds->this_load_per_task = sgs.sum_weighted_load; - } else if (sgs.avg_load > sds->max_load && - (sgs.sum_nr_running > sgs.group_capacity || - sgs.group_imb)) { - sds->max_load = sgs.avg_load; - sds->busiest = group; - sds->busiest_nr_running = sgs.sum_nr_running; - sds->busiest_load_per_task = sgs.sum_weighted_load; - sds->group_imb = sgs.group_imb; - } - - update_sd_power_savings_stats(group, sds, local_group, &sgs); - group = group->next; - } while (group != sd->groups); -} - -/** - * fix_small_imbalance - Calculate the minor imbalance that exists - * amongst the groups of a sched_domain, during - * load balancing. - * @sds: Statistics of the sched_domain whose imbalance is to be calculated. - * @this_cpu: The cpu at whose sched_domain we're performing load-balance. - * @imbalance: Variable to store the imbalance. - */ -static inline void fix_small_imbalance(struct sd_lb_stats *sds, - int this_cpu, unsigned long *imbalance) -{ - unsigned long tmp, pwr_now = 0, pwr_move = 0; - unsigned int imbn = 2; - - if (sds->this_nr_running) { - sds->this_load_per_task /= sds->this_nr_running; - if (sds->busiest_load_per_task > - sds->this_load_per_task) - imbn = 1; - } else - sds->this_load_per_task = - cpu_avg_load_per_task(this_cpu); - - if (sds->max_load - sds->this_load + sds->busiest_load_per_task >= - sds->busiest_load_per_task * imbn) { - *imbalance = sds->busiest_load_per_task; - return; - } - - /* - * 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 += sds->busiest->cpu_power * - min(sds->busiest_load_per_task, sds->max_load); - pwr_now += sds->this->cpu_power * - min(sds->this_load_per_task, sds->this_load); - pwr_now /= SCHED_LOAD_SCALE; - - /* Amount of load we'd subtract */ - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / - sds->busiest->cpu_power; - if (sds->max_load > tmp) - pwr_move += sds->busiest->cpu_power * - min(sds->busiest_load_per_task, sds->max_load - tmp); - - /* Amount of load we'd add */ - if (sds->max_load * sds->busiest->cpu_power < - sds->busiest_load_per_task * SCHED_LOAD_SCALE) - tmp = (sds->max_load * sds->busiest->cpu_power) / - sds->this->cpu_power; - else - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / - sds->this->cpu_power; - pwr_move += sds->this->cpu_power * - min(sds->this_load_per_task, sds->this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; - - /* Move if we gain throughput */ - if (pwr_move > pwr_now) - *imbalance = sds->busiest_load_per_task; -} - -/** - * calculate_imbalance - Calculate the amount of imbalance present within the - * groups of a given sched_domain during load balance. - * @sds: statistics of the sched_domain whose imbalance is to be calculated. - * @this_cpu: Cpu for which currently load balance is being performed. - * @imbalance: The variable to store the imbalance. - */ -static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, - unsigned long *imbalance) -{ - unsigned long max_pull; - /* - * 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 (sds->max_load < sds->avg_load) { - *imbalance = 0; - return fix_small_imbalance(sds, this_cpu, imbalance); - } - - /* Don't want to pull so many tasks that a group would go idle */ - max_pull = min(sds->max_load - sds->avg_load, - sds->max_load - sds->busiest_load_per_task); - - /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * sds->busiest->cpu_power, - (sds->avg_load - sds->this_load) * sds->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 < sds->busiest_load_per_task) - return fix_small_imbalance(sds, this_cpu, imbalance); - -} -/******* find_busiest_group() helpers end here *********************/ - -/** - * find_busiest_group - Returns the busiest group within the sched_domain - * if there is an imbalance. If there isn't an imbalance, and - * the user has opted for power-savings, it returns a group whose - * CPUs can be put to idle by rebalancing those tasks elsewhere, if - * such a group exists. - * - * Also calculates the amount of weighted load which should be moved - * to restore balance. - * - * @sd: The sched_domain whose busiest group is to be returned. - * @this_cpu: The cpu for which load balancing is currently being performed. - * @imbalance: Variable which stores amount of weighted load which should - * be moved to restore balance/put a group to idle. - * @idle: The idle status of this_cpu. - * @sd_idle: The idleness of sd - * @cpus: The set of CPUs under consideration for load-balancing. - * @balance: Pointer to a variable indicating if this_cpu - * is the appropriate cpu to perform load balancing at this_level. - * - * Returns: - the busiest group if imbalance exists. - * - If no imbalance and user has opted for power-savings balance, - * return the least loaded group whose CPUs can be - * put to idle by rebalancing its tasks onto our group. - */ -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, const struct cpumask *cpus, int *balance) -{ - struct sd_lb_stats sds; - - memset(&sds, 0, sizeof(sds)); - - /* - * Compute the various statistics relavent for load balancing at - * this level. - */ - update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, - balance, &sds); - - /* Cases where imbalance does not exist from POV of this_cpu */ - /* 1) this_cpu is not the appropriate cpu to perform load balancing - * at this level. - * 2) There is no busy sibling group to pull from. - * 3) This group is the busiest group. - * 4) This group is more busy than the avg busieness at this - * sched_domain. - * 5) The imbalance is within the specified limit. - * 6) Any rebalance would lead to ping-pong - */ - if (balance && !(*balance)) - goto ret; - - if (!sds.busiest || sds.busiest_nr_running == 0) - goto out_balanced; - - if (sds.this_load >= sds.max_load) - goto out_balanced; - - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; - - if (sds.this_load >= sds.avg_load) - goto out_balanced; - - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) - goto out_balanced; - - sds.busiest_load_per_task /= sds.busiest_nr_running; - if (sds.group_imb) - sds.busiest_load_per_task = - min(sds.busiest_load_per_task, sds.avg_load); - - /* - * 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 (sds.max_load <= sds.busiest_load_per_task) - goto out_balanced; - - /* Looks like there is an imbalance. Compute it */ - calculate_imbalance(&sds, this_cpu, imbalance); - return sds.busiest; - -out_balanced: - /* - * There is no obvious imbalance. But check if we can do some balancing - * to save power. - */ - if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) - return sds.busiest; -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, const struct cpumask *cpus) -{ - struct rq *busiest = NULL, *rq; - unsigned long max_load = 0; - int i; - - for_each_cpu(i, sched_group_cpus(group)) { - unsigned long power = power_of(i); - unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); - unsigned long wl; - - if (!cpumask_test_cpu(i, cpus)) - continue; - - rq = cpu_rq(i); - wl = weighted_cpuload(i) * SCHED_LOAD_SCALE; - wl /= power; - - if (capacity && 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 - -/* Working cpumask for load_balance and load_balance_newidle. */ -static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); - -/* - * 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; - unsigned long flags; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - - cpumask_setall(cpus); - - /* - * 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_count[idle]); - -redo: - update_shares(sd); - 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)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_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 (!cpumask_test_cpu(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)) - ld_moved = -1; - - goto out; - -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)) - ld_moved = -1; - else - ld_moved = 0; -out: - if (ld_moved) - update_shares(sd); - return ld_moved; -} - -/* - * 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; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - - cpumask_setall(cpus); - - /* - * 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_count[CPU_NEWLY_IDLE]); -redo: - update_shares_locked(this_rq, sd); - 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); - double_unlock_balance(this_rq, busiest); - - if (unlikely(all_pinned)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) - goto redo; - } - } - - if (!ld_moved) { - int active_balance = 0; - - 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; - - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return -1; - - if (sd->nr_balance_failed++ < 2) - return -1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. The same method used to move task in load_balance() - * have been extended for load_balance_newidle() to speedup - * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2) - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - - /* Lock busiest in correct order while this_rq is held */ - double_lock_balance(this_rq, busiest); - - /* - * don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu - */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { - double_unlock_balance(this_rq, busiest); - all_pinned = 1; - return ld_moved; - } - - if (!busiest->active_balance) { - busiest->active_balance = 1; - busiest->push_cpu = this_cpu; - active_balance = 1; - } - - double_unlock_balance(this_rq, busiest); - /* - * Should not call ttwu while holding a rq->lock - */ - spin_unlock(&this_rq->lock); - if (active_balance) - wake_up_process(busiest->migration_thread); - spin_lock(&this_rq->lock); - - } else - sd->nr_balance_failed = 0; - - update_shares_locked(this_rq, sd); - 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 = 0; - 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) && - cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) - break; - } - - if (likely(sd)) { - schedstat_inc(sd, alb_count); - - if (move_one_task(target_rq, target_cpu, busiest_rq, - sd, CPU_IDLE)) - schedstat_inc(sd, alb_pushed); - else - schedstat_inc(sd, alb_failed); - } - double_unlock_balance(busiest_rq, target_rq); -} - -#ifdef CONFIG_NO_HZ -static struct { - atomic_t load_balancer; - cpumask_var_t cpu_mask; - cpumask_var_t ilb_grp_nohz_mask; -} nohz ____cacheline_aligned = { - .load_balancer = ATOMIC_INIT(-1), -}; - -int get_nohz_load_balancer(void) -{ - return atomic_read(&nohz.load_balancer); -} - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * lowest_flag_domain - Return lowest sched_domain containing flag. - * @cpu: The cpu whose lowest level of sched domain is to - * be returned. - * @flag: The flag to check for the lowest sched_domain - * for the given cpu. - * - * Returns the lowest sched_domain of a cpu which contains the given flag. - */ -static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) -{ - struct sched_domain *sd; - - for_each_domain(cpu, sd) - if (sd && (sd->flags & flag)) - break; - - return sd; -} - -/** - * for_each_flag_domain - Iterates over sched_domains containing the flag. - * @cpu: The cpu whose domains we're iterating over. - * @sd: variable holding the value of the power_savings_sd - * for cpu. - * @flag: The flag to filter the sched_domains to be iterated. - * - * Iterates over all the scheduler domains for a given cpu that has the 'flag' - * set, starting from the lowest sched_domain to the highest. - */ -#define for_each_flag_domain(cpu, sd, flag) \ - for (sd = lowest_flag_domain(cpu, flag); \ - (sd && (sd->flags & flag)); sd = sd->parent) - -/** - * is_semi_idle_group - Checks if the given sched_group is semi-idle. - * @ilb_group: group to be checked for semi-idleness - * - * Returns: 1 if the group is semi-idle. 0 otherwise. - * - * We define a sched_group to be semi idle if it has atleast one idle-CPU - * and atleast one non-idle CPU. This helper function checks if the given - * sched_group is semi-idle or not. - */ -static inline int is_semi_idle_group(struct sched_group *ilb_group) -{ - cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask, - sched_group_cpus(ilb_group)); - - /* - * A sched_group is semi-idle when it has atleast one busy cpu - * and atleast one idle cpu. - */ - if (cpumask_empty(nohz.ilb_grp_nohz_mask)) - return 0; - - if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group))) - return 0; - - return 1; -} -/** - * find_new_ilb - Finds the optimum idle load balancer for nomination. - * @cpu: The cpu which is nominating a new idle_load_balancer. - * - * Returns: Returns the id of the idle load balancer if it exists, - * Else, returns >= nr_cpu_ids. - * - * This algorithm picks the idle load balancer such that it belongs to a - * semi-idle powersavings sched_domain. The idea is to try and avoid - * completely idle packages/cores just for the purpose of idle load balancing - * when there are other idle cpu's which are better suited for that job. - */ -static int find_new_ilb(int cpu) -{ - struct sched_domain *sd; - struct sched_group *ilb_group; - - /* - * Have idle load balancer selection from semi-idle packages only - * when power-aware load balancing is enabled - */ - if (!(sched_smt_power_savings || sched_mc_power_savings)) - goto out_done; - - /* - * Optimize for the case when we have no idle CPUs or only one - * idle CPU. Don't walk the sched_domain hierarchy in such cases - */ - if (cpumask_weight(nohz.cpu_mask) < 2) - goto out_done; - - for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { - ilb_group = sd->groups; - - do { - if (is_semi_idle_group(ilb_group)) - return cpumask_first(nohz.ilb_grp_nohz_mask); - - ilb_group = ilb_group->next; - - } while (ilb_group != sd->groups); - } - -out_done: - return cpumask_first(nohz.cpu_mask); -} -#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ -static inline int find_new_ilb(int call_cpu) -{ - return cpumask_first(nohz.cpu_mask); -} -#endif - -/* - * This routine will try to nominate the ilb (idle load balancing) - * owner among the cpus whose ticks are stopped. ilb owner will do the idle - * load balancing on behalf of all those cpus. If all the cpus in the system - * go into this tickless mode, then there will be no ilb owner (as there is - * no need for one) and all the cpus will sleep till the next wakeup event - * arrives... - * - * For the ilb owner, tick is not stopped. And this tick will be used - * for idle load balancing. ilb owner will still be part of - * nohz.cpu_mask.. - * - * While stopping the tick, this cpu will become the ilb owner if there - * is no other owner. And will be the owner till that cpu becomes busy - * or if all cpus in the system stop their ticks at which point - * there is no need for ilb owner. - * - * When the ilb owner becomes busy, it nominates another owner, during the - * next busy scheduler_tick() - */ -int select_nohz_load_balancer(int stop_tick) -{ - int cpu = smp_processor_id(); - - if (stop_tick) { - cpu_rq(cpu)->in_nohz_recently = 1; - - if (!cpu_active(cpu)) { - if (atomic_read(&nohz.load_balancer) != cpu) - return 0; - - /* - * If we are going offline and still the leader, - * give up! - */ - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); - - return 0; - } - - cpumask_set_cpu(cpu, nohz.cpu_mask); - - /* time for ilb owner also to sleep */ - if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - if (atomic_read(&nohz.load_balancer) == cpu) - atomic_set(&nohz.load_balancer, -1); - return 0; - } - - if (atomic_read(&nohz.load_balancer) == -1) { - /* make me the ilb owner */ - if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) - return 1; - } else if (atomic_read(&nohz.load_balancer) == cpu) { - int new_ilb; - - if (!(sched_smt_power_savings || - sched_mc_power_savings)) - return 1; - /* - * Check to see if there is a more power-efficient - * ilb. - */ - new_ilb = find_new_ilb(cpu); - if (new_ilb < nr_cpu_ids && new_ilb != cpu) { - atomic_set(&nohz.load_balancer, -1); - resched_cpu(new_ilb); - return 0; - } - return 1; - } - } else { - if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) - return 0; - - cpumask_clear_cpu(cpu, nohz.cpu_mask); - - if (atomic_read(&nohz.load_balancer) == cpu) - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); - } - return 0; -} -#endif - -static DEFINE_SPINLOCK(balancing); - -/* - * It checks each scheduling domain to see if it is due to be balanced, - * and initiates a balancing operation if so. - * - * Balancing parameters are set up in arch_init_sched_domains. - */ -static void rebalance_domains(int cpu, enum cpu_idle_type idle) -{ - int balance = 1; - struct rq *rq = cpu_rq(cpu); - unsigned long interval; - struct sched_domain *sd; - /* Earliest time when we have to do rebalance again */ - unsigned long next_balance = jiffies + 60*HZ; - int update_next_balance = 0; - int need_serialize; - - for_each_domain(cpu, sd) { - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; - - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; - - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - if (unlikely(!interval)) - interval = 1; - if (interval > HZ*NR_CPUS/10) - interval = HZ*NR_CPUS/10; - - need_serialize = sd->flags & SD_SERIALIZE; - - if (need_serialize) { - if (!spin_trylock(&balancing)) - goto out; - } - - if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance)) { - /* - * We've pulled tasks over so either we're no - * longer idle, or one of our SMT siblings is - * not idle. - */ - idle = CPU_NOT_IDLE; - } - sd->last_balance = jiffies; - } - if (need_serialize) - spin_unlock(&balancing); -out: - if (time_after(next_balance, sd->last_balance + interval)) { - next_balance = sd->last_balance + interval; - update_next_balance = 1; - } - - /* - * Stop the load balance at this level. There is another - * CPU in our sched group which is doing load balancing more - * actively. - */ - if (!balance) - break; - } - - /* - * next_balance will be updated only when there is a need. - * When the cpu is attached to null domain for ex, it will not be - * updated. - */ - if (likely(update_next_balance)) - rq->next_balance = next_balance; -} - -/* - * run_rebalance_domains is triggered when needed from the scheduler tick. - * In CONFIG_NO_HZ case, the idle load balance owner will do the - * rebalancing for all the cpus for whom scheduler ticks are stopped. - */ -static void run_rebalance_domains(struct softirq_action *h) -{ - int this_cpu = smp_processor_id(); - struct rq *this_rq = cpu_rq(this_cpu); - enum cpu_idle_type idle = this_rq->idle_at_tick ? - CPU_IDLE : CPU_NOT_IDLE; - - rebalance_domains(this_cpu, idle); - -#ifdef CONFIG_NO_HZ - /* - * If this cpu is the owner for idle load balancing, then do the - * balancing on behalf of the other idle cpus whose ticks are - * stopped. - */ - if (this_rq->idle_at_tick && - atomic_read(&nohz.load_balancer) == this_cpu) { - struct rq *rq; - int balance_cpu; - - for_each_cpu(balance_cpu, nohz.cpu_mask) { - if (balance_cpu == this_cpu) - continue; + unsigned long old_load, new_load; - /* - * If this cpu gets work to do, stop the load balancing - * work being done for other cpus. Next load - * balancing owner will pick it up. - */ - if (need_resched()) - break; + /* scale is effectively 1 << i now, and >> i divides by scale */ - rebalance_domains(balance_cpu, CPU_IDLE); + old_load = this_rq->cpu_load[i]; + new_load = this_load; + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale-1; + this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; + } - rq = cpu_rq(balance_cpu); - if (time_after(this_rq->next_balance, rq->next_balance)) - this_rq->next_balance = rq->next_balance; - } + if (time_after_eq(jiffies, this_rq->calc_load_update)) { + this_rq->calc_load_update += LOAD_FREQ; + calc_load_account_active(this_rq); } -#endif } -static inline int on_null_domain(int cpu) -{ - return !rcu_dereference(cpu_rq(cpu)->sd); -} +#ifdef CONFIG_SMP /* - * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. - * - * In case of CONFIG_NO_HZ, this is the place where we nominate a new - * idle load balancing owner or decide to stop the periodic load balancing, - * if the whole system is idle. + * sched_exec - execve() is a valuable balancing opportunity, because at + * this point the task has the smallest effective memory and cache footprint. */ -static inline void trigger_load_balance(struct rq *rq, int cpu) +void sched_exec(void) { -#ifdef CONFIG_NO_HZ - /* - * If we were in the nohz mode recently and busy at the current - * scheduler tick, then check if we need to nominate new idle - * load balancer. - */ - if (rq->in_nohz_recently && !rq->idle_at_tick) { - rq->in_nohz_recently = 0; - - if (atomic_read(&nohz.load_balancer) == cpu) { - cpumask_clear_cpu(cpu, nohz.cpu_mask); - atomic_set(&nohz.load_balancer, -1); - } - - if (atomic_read(&nohz.load_balancer) == -1) { - int ilb = find_new_ilb(cpu); + struct task_struct *p = current; + struct migration_req req; + int dest_cpu, this_cpu; + unsigned long flags; + struct rq *rq; - if (ilb < nr_cpu_ids) - resched_cpu(ilb); - } +again: + this_cpu = get_cpu(); + dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0); + if (dest_cpu == this_cpu) { + put_cpu(); + return; } + rq = task_rq_lock(p, &flags); + put_cpu(); + /* - * If this cpu is idle and doing idle load balancing for all the - * cpus with ticks stopped, is it time for that to stop? + * select_task_rq() can race against ->cpus_allowed */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - resched_cpu(cpu); - return; + if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) + || unlikely(!cpu_active(dest_cpu))) { + task_rq_unlock(rq, &flags); + goto again; } - /* - * If this cpu is idle and the idle load balancing is done by - * someone else, then no need raise the SCHED_SOFTIRQ - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpumask_test_cpu(cpu, nohz.cpu_mask)) - return; -#endif - /* Don't need to rebalance while attached to NULL domain */ - if (time_after_eq(jiffies, rq->next_balance) && - likely(!on_null_domain(cpu))) - raise_softirq(SCHED_SOFTIRQ); -} + /* 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; -#else /* CONFIG_SMP */ + get_task_struct(mt); + task_rq_unlock(rq, &flags); + wake_up_process(mt); + put_task_struct(mt); + wait_for_completion(&req.done); -/* - * on UP we do not need to balance between CPUs: - */ -static inline void idle_balance(int cpu, struct rq *rq) -{ + return; + } + task_rq_unlock(rq, &flags); } #endif @@ -5053,8 +3292,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime = cputime_add(p->gtime, cputime); /* Add guest time to cpustat. */ - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); + if (TASK_NICE(p) > 0) { + cpustat->nice = cputime64_add(cpustat->nice, tmp); + cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); + } else { + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); + } } /* @@ -5169,60 +3413,86 @@ void account_idle_ticks(unsigned long ticks) * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -cputime_t task_utime(struct task_struct *p) +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->utime; + *ut = p->utime; + *st = p->stime; } -cputime_t task_stime(struct task_struct *p) +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->stime; + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; } #else -cputime_t task_utime(struct task_struct *p) + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t utime = cputime_to_clock_t(p->utime), - total = utime + cputime_to_clock_t(p->stime); - u64 temp; + cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); /* * Use CFS's precise accounting: */ - temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - temp *= utime; + u64 temp; + + temp = (u64)(rtime * utime); do_div(temp, total); - } - utime = (clock_t)temp; + utime = (cputime_t)temp; + } else + utime = rtime; - p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); - return p->prev_utime; + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); + + *ut = p->prev_utime; + *st = p->prev_stime; } -cputime_t task_stime(struct task_struct *p) +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t stime; + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; - /* - * Use CFS's precise accounting. (we subtract utime from - * the total, to make sure the total observed by userspace - * grows monotonically - apps rely on that): - */ - stime = nsec_to_clock_t(p->se.sum_exec_runtime) - - cputime_to_clock_t(task_utime(p)); + thread_group_cputime(p, &cputime); - if (stime >= 0) - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + total = cputime_add(cputime.utime, cputime.stime); + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - return p->prev_stime; -} -#endif + if (total) { + u64 temp; -inline cputime_t task_gtime(struct task_struct *p) -{ - return p->gtime; + temp = (u64)(rtime * cputime.utime); + do_div(temp, total); + utime = (cputime_t)temp; + } else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, + cputime_sub(rtime, sig->prev_utime)); + + *ut = sig->prev_utime; + *st = sig->prev_stime; } +#endif /* * This function gets called by the timer code, with HZ frequency. @@ -5239,13 +3509,13 @@ void scheduler_tick(void) sched_clock_tick(); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); update_rq_clock(rq); update_cpu_load(rq); curr->sched_class->task_tick(rq, curr, 0); - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); - perf_event_task_tick(curr, cpu); + perf_event_task_tick(curr); #ifdef CONFIG_SMP rq->idle_at_tick = idle_cpu(cpu); @@ -5357,13 +3627,14 @@ static inline void schedule_debug(struct task_struct *prev) #endif } -static void put_prev_task(struct rq *rq, struct task_struct *p) +static void put_prev_task(struct rq *rq, struct task_struct *prev) { - u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime; + if (prev->state == TASK_RUNNING) { + u64 runtime = prev->se.sum_exec_runtime; - update_avg(&p->se.avg_running, runtime); + runtime -= prev->se.prev_sum_exec_runtime; + runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - if (p->state == TASK_RUNNING) { /* * In order to avoid avg_overlap growing stale when we are * indeed overlapping and hence not getting put to sleep, grow @@ -5373,12 +3644,9 @@ static void put_prev_task(struct rq *rq, struct task_struct *p) * correlates to the amount of cache footprint a task can * build up. */ - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - update_avg(&p->se.avg_overlap, runtime); - } else { - update_avg(&p->se.avg_running, 0); + update_avg(&prev->se.avg_overlap, runtime); } - p->sched_class->put_prev_task(rq, p); + prev->sched_class->put_prev_task(rq, prev); } /* @@ -5439,7 +3707,7 @@ need_resched_nonpreemptible: if (sched_feat(HRTICK)) hrtick_clear(rq); - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); clear_tsk_need_resched(prev); @@ -5461,7 +3729,7 @@ need_resched_nonpreemptible: if (likely(prev != next)) { sched_info_switch(prev, next); - perf_event_task_sched_out(prev, next, cpu); + perf_event_task_sched_out(prev, next); rq->nr_switches++; rq->curr = next; @@ -5475,12 +3743,15 @@ need_resched_nonpreemptible: cpu = smp_processor_id(); rq = cpu_rq(cpu); } else - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); post_schedule(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) + if (unlikely(reacquire_kernel_lock(current) < 0)) { + prev = rq->curr; + switch_count = &prev->nivcsw; goto need_resched_nonpreemptible; + } preempt_enable_no_resched(); if (need_resched()) @@ -5488,7 +3759,7 @@ need_resched_nonpreemptible: } EXPORT_SYMBOL(schedule); -#ifdef CONFIG_SMP +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. @@ -5892,14 +4163,15 @@ EXPORT_SYMBOL(wait_for_completion_killable); */ bool try_wait_for_completion(struct completion *x) { + unsigned long flags; int ret = 1; - spin_lock_irq(&x->wait.lock); + spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; else x->done--; - spin_unlock_irq(&x->wait.lock); + spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(try_wait_for_completion); @@ -5914,12 +4186,13 @@ EXPORT_SYMBOL(try_wait_for_completion); */ bool completion_done(struct completion *x) { + unsigned long flags; int ret = 1; - spin_lock_irq(&x->wait.lock); + spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - spin_unlock_irq(&x->wait.lock); + spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(completion_done); @@ -5987,7 +4260,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) unsigned long flags; int oldprio, on_rq, running; struct rq *rq; - const struct sched_class *prev_class = p->sched_class; + const struct sched_class *prev_class; BUG_ON(prio < 0 || prio > MAX_PRIO); @@ -5995,6 +4268,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) update_rq_clock(rq); oldprio = p->prio; + prev_class = p->sched_class; on_rq = p->se.on_rq; running = task_current(rq, p); if (on_rq) @@ -6012,7 +4286,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (on_rq) { - enqueue_task(rq, p, 0); + enqueue_task(rq, p, 0, oldprio < prio); check_class_changed(rq, p, prev_class, oldprio, running); } @@ -6056,7 +4330,7 @@ void set_user_nice(struct task_struct *p, long nice) delta = p->prio - old_prio; if (on_rq) { - enqueue_task(rq, p, 0); + enqueue_task(rq, p, 0, false); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -6079,7 +4353,7 @@ 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 <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); } @@ -6182,22 +4456,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) BUG_ON(p->se.on_rq); p->policy = policy; - switch (p->policy) { - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - p->sched_class = &fair_sched_class; - break; - case SCHED_FIFO: - case SCHED_RR: - p->sched_class = &rt_sched_class; - break; - } - p->rt_priority = prio; p->normal_prio = normal_prio(p); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); + if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; set_load_weight(p); } @@ -6222,7 +4488,7 @@ static int __sched_setscheduler(struct task_struct *p, int policy, { int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; - const struct sched_class *prev_class = p->sched_class; + const struct sched_class *prev_class; struct rq *rq; int reset_on_fork; @@ -6264,7 +4530,7 @@ recheck: if (!lock_task_sighand(p, &flags)) return -ESRCH; - rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; + rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); unlock_task_sighand(p, &flags); /* can't set/change the rt policy */ @@ -6312,7 +4578,7 @@ recheck: * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: */ - spin_lock_irqsave(&p->pi_lock, flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); /* * To be able to change p->policy safely, the apropriate * runqueue lock must be held. @@ -6322,7 +4588,7 @@ recheck: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } update_rq_clock(rq); @@ -6336,6 +4602,7 @@ recheck: p->sched_reset_on_fork = reset_on_fork; oldprio = p->prio; + prev_class = p->sched_class; __setscheduler(rq, p, policy, param->sched_priority); if (running) @@ -6346,7 +4613,7 @@ recheck: check_class_changed(rq, p, prev_class, oldprio, running); } __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); rt_mutex_adjust_pi(p); @@ -6446,7 +4713,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) return -EINVAL; retval = -ESRCH; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (p) { retval = security_task_getscheduler(p); @@ -6454,7 +4721,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) retval = p->policy | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); } - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } @@ -6472,7 +4739,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) if (!param || pid < 0) return -EINVAL; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); retval = -ESRCH; if (!p) @@ -6483,7 +4750,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) goto out_unlock; lp.sched_priority = p->rt_priority; - read_unlock(&tasklist_lock); + rcu_read_unlock(); /* * This one might sleep, we cannot do it with a spinlock held ... @@ -6493,7 +4760,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) return retval; out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } @@ -6504,22 +4771,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) int retval; get_online_cpus(); - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (!p) { - read_unlock(&tasklist_lock); + rcu_read_unlock(); put_online_cpus(); return -ESRCH; } - /* - * It is not safe to call set_cpus_allowed with the - * tasklist_lock held. We will bump the task_struct's - * usage count and then drop tasklist_lock. - */ + /* Prevent p going away */ get_task_struct(p); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { retval = -ENOMEM; @@ -6600,10 +4863,12 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; + unsigned long flags; + struct rq *rq; int retval; get_online_cpus(); - read_lock(&tasklist_lock); + rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); @@ -6614,10 +4879,12 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) if (retval) goto out_unlock; + rq = task_rq_lock(p, &flags); cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); + task_rq_unlock(rq, &flags); out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); put_online_cpus(); return retval; @@ -6635,7 +4902,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, int ret; cpumask_var_t mask; - if (len < cpumask_size()) + if (len < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) return -EINVAL; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) @@ -6643,10 +4912,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - if (copy_to_user(user_mask_ptr, mask, cpumask_size())) + int retlen = min(len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; else - ret = cpumask_size(); + ret = retlen; } free_cpumask_var(mask); @@ -6672,7 +4943,7 @@ SYSCALL_DEFINE0(sched_yield) */ __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); - _raw_spin_unlock(&rq->lock); + do_raw_spin_unlock(&rq->lock); preempt_enable_no_resched(); schedule(); @@ -6852,6 +5123,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, { struct task_struct *p; unsigned int time_slice; + unsigned long flags; + struct rq *rq; int retval; struct timespec t; @@ -6859,7 +5132,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, return -EINVAL; retval = -ESRCH; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (!p) goto out_unlock; @@ -6868,15 +5141,17 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, if (retval) goto out_unlock; - time_slice = p->sched_class->get_rr_interval(p); + rq = task_rq_lock(p, &flags); + time_slice = p->sched_class->get_rr_interval(rq, p); + task_rq_unlock(rq, &flags); - read_unlock(&tasklist_lock); + rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; return retval; out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } @@ -6942,7 +5217,7 @@ void show_state_filter(unsigned long state_filter) /* * Only show locks if all tasks are dumped: */ - if (state_filter == -1) + if (!state_filter) debug_show_all_locks(); } @@ -6964,12 +5239,12 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); __sched_fork(idle); + idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - idle->prio = idle->normal_prio = MAX_PRIO; cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); __set_task_cpu(idle, cpu); @@ -6977,7 +5252,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) idle->oncpu = 1; #endif - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ #if defined(CONFIG_PREEMPT) @@ -7010,22 +5285,43 @@ cpumask_var_t nohz_cpu_mask; * * This idea comes from the SD scheduler of Con Kolivas: */ -static inline void sched_init_granularity(void) +static int get_update_sysctl_factor(void) { - unsigned int factor = 1 + ilog2(num_online_cpus()); - const unsigned long limit = 200000000; + unsigned int cpus = min_t(int, num_online_cpus(), 8); + unsigned int factor; + + switch (sysctl_sched_tunable_scaling) { + case SCHED_TUNABLESCALING_NONE: + factor = 1; + break; + case SCHED_TUNABLESCALING_LINEAR: + factor = cpus; + break; + case SCHED_TUNABLESCALING_LOG: + default: + factor = 1 + ilog2(cpus); + break; + } - sysctl_sched_min_granularity *= factor; - if (sysctl_sched_min_granularity > limit) - sysctl_sched_min_granularity = limit; + return factor; +} - sysctl_sched_latency *= factor; - if (sysctl_sched_latency > limit) - sysctl_sched_latency = limit; +static void update_sysctl(void) +{ + unsigned int factor = get_update_sysctl_factor(); - sysctl_sched_wakeup_granularity *= factor; +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); + SET_SYSCTL(sched_shares_ratelimit); +#undef SET_SYSCTL +} - sysctl_sched_shares_ratelimit *= factor; +static inline void sched_init_granularity(void) +{ + update_sysctl(); } #ifdef CONFIG_SMP @@ -7062,7 +5358,8 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) int ret = 0; rq = task_rq_lock(p, &flags); - if (!cpumask_intersects(new_mask, cpu_online_mask)) { + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; goto out; } @@ -7084,7 +5381,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) { + if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) { /* Need help from migration thread: drop lock and wait. */ struct task_struct *mt = rq->migration_thread; @@ -7117,7 +5414,7 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) { struct rq *rq_dest, *rq_src; - int ret = 0, on_rq; + int ret = 0; if (unlikely(!cpu_active(dest_cpu))) return ret; @@ -7133,12 +5430,13 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) goto fail; - on_rq = p->se.on_rq; - if (on_rq) + /* + * If we're not on a rq, the next wake-up will ensure we're + * placed properly. + */ + if (p->se.on_rq) { deactivate_task(rq_src, p, 0); - - set_task_cpu(p, dest_cpu); - if (on_rq) { + set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); check_preempt_curr(rq_dest, p, 0); } @@ -7173,10 +5471,10 @@ static int migration_thread(void *data) struct migration_req *req; struct list_head *head; - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); if (cpu_is_offline(cpu)) { - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); break; } @@ -7188,7 +5486,7 @@ static int migration_thread(void *data) head = &rq->migration_queue; if (list_empty(head)) { - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); schedule(); set_current_state(TASK_INTERRUPTIBLE); continue; @@ -7197,14 +5495,14 @@ static int migration_thread(void *data) list_del_init(head->next); if (req->task != NULL) { - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); __migrate_task(req->task, cpu, req->dest_cpu); } else if (likely(cpu == (badcpu = smp_processor_id()))) { req->dest_cpu = RCU_MIGRATION_GOT_QS; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } else { req->dest_cpu = RCU_MIGRATION_MUST_SYNC; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu); } local_irq_enable(); @@ -7234,37 +5532,10 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) { int dest_cpu; - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu)); again: - /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask) - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) - goto move; - - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask); - if (dest_cpu < nr_cpu_ids) - goto move; - - /* No more Mr. Nice Guy. */ - if (dest_cpu >= nr_cpu_ids) { - cpuset_cpus_allowed_locked(p, &p->cpus_allowed); - dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed); - - /* - * 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(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, dead_cpu); - } - } + dest_cpu = select_fallback_rq(dead_cpu, p); -move: /* It can have affinity changed while we were choosing. */ if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu))) goto again; @@ -7279,7 +5550,7 @@ move: */ static void migrate_nr_uninterruptible(struct rq *rq_src) { - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask)); + struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); unsigned long flags; local_irq_save(flags); @@ -7327,14 +5598,14 @@ void sched_idle_next(void) * Strictly not necessary since rest of the CPUs are stopped by now * and interrupts disabled on the current cpu. */ - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); update_rq_clock(rq); activate_task(rq, p, 0); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } /* @@ -7370,9 +5641,9 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) * that's OK. No task can be added to this CPU, so iteration is * fine. */ - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); move_task_off_dead_cpu(dead_cpu, p); - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); put_task_struct(p); } @@ -7413,17 +5684,16 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0, }, + {} }; static struct ctl_table sd_ctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = sd_ctl_dir, }, - {0, }, + {} }; static struct ctl_table *sd_alloc_ctl_entry(int n) @@ -7533,7 +5803,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu) static struct ctl_table_header *sd_sysctl_header; static void register_sched_domain_sysctl(void) { - int i, cpu_num = num_online_cpus(); + int i, cpu_num = num_possible_cpus(); struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); char buf[32]; @@ -7543,7 +5813,7 @@ static void register_sched_domain_sysctl(void) if (entry == NULL) return; - for_each_online_cpu(i) { + for_each_possible_cpu(i) { snprintf(buf, 32, "cpu%d", i); entry->procname = kstrdup(buf, GFP_KERNEL); entry->mode = 0555; @@ -7639,13 +5909,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) /* Update our root-domain */ rq = cpu_rq(cpu); - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_online(rq); } - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); break; #ifdef CONFIG_HOTPLUG_CPU @@ -7670,14 +5940,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) put_task_struct(rq->migration_thread); rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); deactivate_task(rq, rq->idle, 0); - rq->idle->static_prio = MAX_PRIO; __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); rq->idle->sched_class = &idle_sched_class; migrate_dead_tasks(cpu); - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); cpuset_unlock(); migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); @@ -7687,30 +5956,30 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) * they didn't take sched_hotcpu_mutex. Just wake up * the requestors. */ - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); while (!list_empty(&rq->migration_queue)) { struct migration_req *req; req = list_entry(rq->migration_queue.next, struct migration_req, list); list_del_init(&req->list); - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); complete(&req->done); - spin_lock_irq(&rq->lock); + raw_spin_lock_irq(&rq->lock); } - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); break; case CPU_DYING: case CPU_DYING_FROZEN: /* Update our root-domain */ rq = cpu_rq(cpu); - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); break; #endif } @@ -7747,6 +6016,16 @@ early_initcall(migration_init); #ifdef CONFIG_SCHED_DEBUG +static __read_mostly int sched_domain_debug_enabled; + +static int __init sched_domain_debug_setup(char *str) +{ + sched_domain_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_domain_debug_setup); + static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { @@ -7833,6 +6112,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) cpumask_var_t groupmask; int level = 0; + if (!sched_domain_debug_enabled) + return; + if (!sd) { printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); return; @@ -7927,7 +6209,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) struct root_domain *old_rd = NULL; unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { old_rd = rq->rd; @@ -7953,7 +6235,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) set_rq_online(rq); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) free_rootdomain(old_rd); @@ -8054,6 +6336,7 @@ 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; } @@ -8238,14 +6521,14 @@ enum s_alloc { */ #ifdef CONFIG_SCHED_SMT static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); +static DEFINE_PER_CPU(struct static_sched_group, sched_groups); static int cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, struct sched_group **sg, struct cpumask *unused) { if (sg) - *sg = &per_cpu(sched_group_cpus, cpu).sg; + *sg = &per_cpu(sched_groups, cpu).sg; return cpu; } #endif /* CONFIG_SCHED_SMT */ @@ -8890,7 +7173,7 @@ static int build_sched_domains(const struct cpumask *cpu_map) return __build_sched_domains(cpu_map, NULL); } -static struct cpumask *doms_cur; /* current sched domains */ +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' */ @@ -8912,6 +7195,31 @@ 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 @@ -8923,12 +7231,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map) arch_update_cpu_topology(); ndoms_cur = 1; - doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); + doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) - doms_cur = fallback_doms; - cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur); + err = build_sched_domains(doms_cur[0]); register_sched_domain_sysctl(); return err; @@ -8978,19 +7286,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * 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's of length 'ndoms_new'. + * '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 kmalloc'd. This routine takes - * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc 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. + * 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, @@ -8998,8 +7306,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * Call with hotplug lock held */ -/* FIXME: Change to struct cpumask *doms_new[] */ -void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { int i, j, n; @@ -9018,40 +7325,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, /* 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]) + 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); + detach_destroy_domains(doms_cur[i]); match1: ; } if (doms_new == NULL) { ndoms_cur = 0; - doms_new = fallback_doms; - cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + 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 < ndoms_cur && !new_topology; j++) { - if (cpumask_equal(&doms_new[i], &doms_cur[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, + __build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } /* Remember the new sched domains */ - if (doms_cur != fallback_doms) - kfree(doms_cur); + 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; @@ -9103,11 +7410,13 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) #ifdef CONFIG_SCHED_MC static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_mc_power_savings); } static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); @@ -9119,11 +7428,13 @@ static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, #ifdef CONFIG_SCHED_SMT static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_smt_power_savings); } static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); @@ -9162,8 +7473,10 @@ static int update_sched_domains(struct notifier_block *nfb, switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: partition_sched_domains(1, NULL, NULL); return NOTIFY_OK; @@ -9210,7 +7523,7 @@ void __init sched_init_smp(void) #endif get_online_cpus(); mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(cpu_online_mask); + arch_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); @@ -9283,13 +7596,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) #ifdef CONFIG_SMP rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; - plist_head_init(&rt_rq->pushable_tasks, &rq->lock); + plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); #endif rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; rt_rq->rt_runtime = 0; - spin_lock_init(&rt_rq->rt_runtime_lock); + raw_spin_lock_init(&rt_rq->rt_runtime_lock); #ifdef CONFIG_RT_GROUP_SCHED rt_rq->rt_nr_boosted = 0; @@ -9336,7 +7649,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, tg->rt_rq[cpu] = rt_rq; init_rt_rq(rt_rq, rq); rt_rq->tg = tg; - rt_rq->rt_se = rt_se; rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; if (add) list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list); @@ -9367,16 +7679,9 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); #endif -#ifdef CONFIG_USER_SCHED - alloc_size *= 2; -#endif #ifdef CONFIG_CPUMASK_OFFSTACK alloc_size += num_possible_cpus() * cpumask_size(); #endif - /* - * As sched_init() is called before page_alloc is setup, - * we use alloc_bootmem(). - */ if (alloc_size) { ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); @@ -9387,13 +7692,6 @@ void __init sched_init(void) init_task_group.cfs_rq = (struct cfs_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#ifdef CONFIG_USER_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_USER_SCHED */ #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED init_task_group.rt_se = (struct sched_rt_entity **)ptr; @@ -9402,13 +7700,6 @@ void __init sched_init(void) init_task_group.rt_rq = (struct rt_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#ifdef CONFIG_USER_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_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { @@ -9428,22 +7719,13 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED init_rt_bandwidth(&init_task_group.rt_bandwidth, global_rt_period(), global_rt_runtime()); -#ifdef CONFIG_USER_SCHED - init_rt_bandwidth(&root_task_group.rt_bandwidth, - global_rt_period(), RUNTIME_INF); -#endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED list_add(&init_task_group.list, &task_groups); INIT_LIST_HEAD(&init_task_group.children); -#ifdef CONFIG_USER_SCHED - INIT_LIST_HEAD(&root_task_group.children); - init_task_group.parent = &root_task_group; - list_add(&init_task_group.siblings, &root_task_group.children); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long), @@ -9453,7 +7735,7 @@ void __init sched_init(void) struct rq *rq; rq = cpu_rq(i); - spin_lock_init(&rq->lock); + raw_spin_lock_init(&rq->lock); rq->nr_running = 0; rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; @@ -9483,25 +7765,6 @@ void __init sched_init(void) * directly in rq->cfs (i.e init_task_group->se[] = NULL). */ init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - root_task_group.shares = NICE_0_LOAD; - init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL); - /* - * In case of task-groups formed thr' the user id of tasks, - * init_task_group represents tasks belonging to root user. - * Hence it forms a sibling of all subsequent groups formed. - * In this case, init_task_group gets only a fraction of overall - * system cpu resource, based on the weight assigned to root - * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished - * by letting tasks of init_task_group sit in a separate cfs_rq - * (init_tg_cfs_rq) and having one entity represent this group of - * tasks in rq->cfs (i.e init_task_group->se[] != NULL). - */ - init_tg_cfs_entry(&init_task_group, - &per_cpu(init_tg_cfs_rq, i), - &per_cpu(init_sched_entity, i), i, 1, - root_task_group.se[i]); - #endif #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -9510,12 +7773,6 @@ void __init sched_init(void) INIT_LIST_HEAD(&rq->leaf_rt_rq_list); #ifdef CONFIG_CGROUP_SCHED init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL); - init_tg_rt_entry(&init_task_group, - &per_cpu(init_rt_rq, i), - &per_cpu(init_sched_rt_entity, i), i, 1, - root_task_group.rt_se[i]); #endif #endif @@ -9531,6 +7788,8 @@ void __init sched_init(void) rq->cpu = i; rq->online = 0; rq->migration_thread = NULL; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); #endif @@ -9549,7 +7808,7 @@ void __init sched_init(void) #endif #ifdef CONFIG_RT_MUTEXES - plist_head_init(&init_task.pi_waiters, &init_task.pi_lock); + plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); #endif /* @@ -9580,7 +7839,9 @@ void __init sched_init(void) zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ perf_event_init(); @@ -9591,12 +7852,12 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP static inline int preempt_count_equals(int preempt_offset) { - int nested = preempt_count() & ~PREEMPT_ACTIVE; + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); return (nested == PREEMPT_INATOMIC_BASE + preempt_offset); } -void __might_sleep(char *file, int line, int preempt_offset) +void __might_sleep(const char *file, int line, int preempt_offset) { #ifdef in_atomic static unsigned long prev_jiffy; /* ratelimiting */ @@ -9672,13 +7933,13 @@ void normalize_rt_tasks(void) continue; } - spin_lock(&p->pi_lock); + raw_spin_lock(&p->pi_lock); rq = __task_rq_lock(p); normalize_task(rq, p); __task_rq_unlock(rq); - spin_unlock(&p->pi_lock); + raw_spin_unlock(&p->pi_lock); } while_each_thread(g, p); read_unlock_irqrestore(&tasklist_lock, flags); @@ -9774,13 +8035,15 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) se = kzalloc_node(sizeof(struct sched_entity), GFP_KERNEL, cpu_to_node(i)); if (!se) - goto err; + goto err_free_rq; init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]); } return 1; + err_free_rq: + kfree(cfs_rq); err: return 0; } @@ -9862,13 +8125,15 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) rt_se = kzalloc_node(sizeof(struct sched_rt_entity), GFP_KERNEL, cpu_to_node(i)); if (!rt_se) - goto err; + goto err_free_rq; init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]); } return 1; + err_free_rq: + kfree(rt_rq); err: return 0; } @@ -9903,7 +8168,7 @@ static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) } #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED static void free_sched_group(struct task_group *tg) { free_fair_sched_group(tg); @@ -10002,17 +8267,17 @@ void sched_move_task(struct task_struct *tsk) #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->moved_group) - tsk->sched_class->moved_group(tsk); + tsk->sched_class->moved_group(tsk, on_rq); #endif if (unlikely(running)) tsk->sched_class->set_curr_task(rq); if (on_rq) - enqueue_task(rq, tsk, 0); + enqueue_task(rq, tsk, 0, false); task_rq_unlock(rq, &flags); } -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED static void __set_se_shares(struct sched_entity *se, unsigned long shares) @@ -10037,9 +8302,9 @@ static void set_se_shares(struct sched_entity *se, unsigned long shares) struct rq *rq = cfs_rq->rq; unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); __set_se_shares(se, shares); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } static DEFINE_MUTEX(shares_mutex); @@ -10154,13 +8419,6 @@ static int tg_schedulable(struct task_group *tg, void *data) runtime = d->rt_runtime; } -#ifdef CONFIG_USER_SCHED - if (tg == &root_task_group) { - period = global_rt_period(); - runtime = global_rt_runtime(); - } -#endif - /* * Cannot have more runtime than the period. */ @@ -10224,18 +8482,18 @@ static int tg_set_bandwidth(struct task_group *tg, if (err) goto unlock; - spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + 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]; - spin_lock(&rt_rq->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_runtime = rt_runtime; - spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_rq->rt_runtime_lock); } - spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); unlock: read_unlock(&tasklist_lock); mutex_unlock(&rt_constraints_mutex); @@ -10340,15 +8598,15 @@ static int sched_rt_global_constraints(void) if (sysctl_sched_rt_runtime == 0) return -EBUSY; - spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + 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; - spin_lock(&rt_rq->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_runtime = global_rt_runtime(); - spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_rq->rt_runtime_lock); } - spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); return 0; } @@ -10563,7 +8821,7 @@ struct cgroup_subsys cpu_cgroup_subsys = { struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 *cpuusage; + u64 __percpu *cpuusage; struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; }; @@ -10639,9 +8897,9 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) /* * Take rq->lock to make 64-bit read safe on 32-bit platforms. */ - spin_lock_irq(&cpu_rq(cpu)->lock); + raw_spin_lock_irq(&cpu_rq(cpu)->lock); data = *cpuusage; - spin_unlock_irq(&cpu_rq(cpu)->lock); + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); #else data = *cpuusage; #endif @@ -10657,9 +8915,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) /* * Take rq->lock to make 64-bit write safe on 32-bit platforms. */ - spin_lock_irq(&cpu_rq(cpu)->lock); + raw_spin_lock_irq(&cpu_rq(cpu)->lock); *cpuusage = val; - spin_unlock_irq(&cpu_rq(cpu)->lock); + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); #else *cpuusage = val; #endif @@ -10780,12 +9038,30 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) } /* + * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large + * in cputime_t units. As a result, cpuacct_update_stats calls + * percpu_counter_add with values large enough to always overflow the + * per cpu batch limit causing bad SMP scalability. + * + * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we + * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled + * and enabled. We cap it at INT_MAX which is the largest allowed batch value. + */ +#ifdef CONFIG_SMP +#define CPUACCT_BATCH \ + min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX) +#else +#define CPUACCT_BATCH 0 +#endif + +/* * Charge the system/user time to the task's accounting group. */ static void cpuacct_update_stats(struct task_struct *tsk, enum cpuacct_stat_index idx, cputime_t val) { struct cpuacct *ca; + int batch = CPUACCT_BATCH; if (unlikely(!cpuacct_subsys.active)) return; @@ -10794,7 +9070,7 @@ static void cpuacct_update_stats(struct task_struct *tsk, ca = task_ca(tsk); do { - percpu_counter_add(&ca->cpustat[idx], val); + __percpu_counter_add(&ca->cpustat[idx], val, batch); ca = ca->parent; } while (ca); rcu_read_unlock(); @@ -10893,9 +9169,9 @@ void synchronize_sched_expedited(void) init_completion(&req->done); req->task = NULL; req->dest_cpu = RCU_MIGRATION_NEED_QS; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); list_add(&req->list, &rq->migration_queue); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); wake_up_process(rq->migration_thread); } for_each_online_cpu(cpu) { @@ -10903,13 +9179,14 @@ void synchronize_sched_expedited(void) req = &per_cpu(rcu_migration_req, cpu); rq = cpu_rq(cpu); wait_for_completion(&req->done); - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC)) need_full_sync = 1; req->dest_cpu = RCU_MIGRATION_IDLE; - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE; + synchronize_sched_expedited_count++; mutex_unlock(&rcu_sched_expedited_mutex); put_online_cpus(); if (need_full_sync)