/* * kernel/sched.c * * Kernel scheduler and related syscalls * * Copyright (C) 1991-2002 Linus Torvalds * * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and * make semaphores SMP safe * 1998-11-19 Implemented schedule_timeout() and related stuff * by Andrea Arcangeli * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: * hybrid priority-list and round-robin design with * an array-switch method of distributing timeslices * and per-CPU runqueues. Cleanups and useful suggestions * by Davide Libenzi, preemptible kernel bits by Robert Love. * 2003-09-03 Interactivity tuning by Con Kolivas. * 2004-04-02 Scheduler domains code by Nick Piggin */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], * and back. */ #define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) #define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) #define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) /* * 'User priority' is the nice value converted to something we * can work with better when scaling various scheduler parameters, * it's a [ 0 ... 39 ] range. */ #define USER_PRIO(p) ((p)-MAX_RT_PRIO) #define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) #define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) /* * Some helpers for converting nanosecond timing to jiffy resolution */ #define NS_TO_JIFFIES(TIME) ((TIME) / (1000000000 / HZ)) #define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) /* * These are the 'tuning knobs' of the scheduler: * * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger), * default timeslice is 100 msecs, maximum timeslice is 800 msecs. * Timeslices get refilled after they expire. */ #define MIN_TIMESLICE max(5 * HZ / 1000, 1) #define DEF_TIMESLICE (100 * HZ / 1000) #define ON_RUNQUEUE_WEIGHT 30 #define CHILD_PENALTY 95 #define PARENT_PENALTY 100 #define EXIT_WEIGHT 3 #define PRIO_BONUS_RATIO 25 #define MAX_BONUS (MAX_USER_PRIO * PRIO_BONUS_RATIO / 100) #define INTERACTIVE_DELTA 2 #define MAX_SLEEP_AVG (DEF_TIMESLICE * MAX_BONUS) #define STARVATION_LIMIT (MAX_SLEEP_AVG) #define NS_MAX_SLEEP_AVG (JIFFIES_TO_NS(MAX_SLEEP_AVG)) /* * If a task is 'interactive' then we reinsert it in the active * array after it has expired its current timeslice. (it will not * continue to run immediately, it will still roundrobin with * other interactive tasks.) * * This part scales the interactivity limit depending on niceness. * * We scale it linearly, offset by the INTERACTIVE_DELTA delta. * Here are a few examples of different nice levels: * * TASK_INTERACTIVE(-20): [1,1,1,1,1,1,1,1,1,0,0] * TASK_INTERACTIVE(-10): [1,1,1,1,1,1,1,0,0,0,0] * TASK_INTERACTIVE( 0): [1,1,1,1,0,0,0,0,0,0,0] * TASK_INTERACTIVE( 10): [1,1,0,0,0,0,0,0,0,0,0] * TASK_INTERACTIVE( 19): [0,0,0,0,0,0,0,0,0,0,0] * * (the X axis represents the possible -5 ... 0 ... +5 dynamic * priority range a task can explore, a value of '1' means the * task is rated interactive.) * * Ie. nice +19 tasks can never get 'interactive' enough to be * reinserted into the active array. And only heavily CPU-hog nice -20 * tasks will be expired. Default nice 0 tasks are somewhere between, * it takes some effort for them to get interactive, but it's not * too hard. */ #define CURRENT_BONUS(p) \ (NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \ MAX_SLEEP_AVG) #define GRANULARITY (10 * HZ / 1000 ? : 1) #ifdef CONFIG_SMP #define TIMESLICE_GRANULARITY(p) (GRANULARITY * \ (1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \ num_online_cpus()) #else #define TIMESLICE_GRANULARITY(p) (GRANULARITY * \ (1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1))) #endif #define SCALE(v1,v1_max,v2_max) \ (v1) * (v2_max) / (v1_max) #define DELTA(p) \ (SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA) #define TASK_INTERACTIVE(p) \ ((p)->prio <= (p)->static_prio - DELTA(p)) #define INTERACTIVE_SLEEP(p) \ (JIFFIES_TO_NS(MAX_SLEEP_AVG * \ (MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1)) #define TASK_PREEMPTS_CURR(p, rq) \ ((p)->prio < (rq)->curr->prio) /* * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ] * to time slice values: [800ms ... 100ms ... 5ms] * * The higher a thread's priority, the bigger timeslices * it gets during one round of execution. But even the lowest * priority thread gets MIN_TIMESLICE worth of execution time. */ #define SCALE_PRIO(x, prio) \ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE) static unsigned int task_timeslice(task_t *p) { if (p->static_prio < NICE_TO_PRIO(0)) return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio); else return SCALE_PRIO(DEF_TIMESLICE, p->static_prio); } #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \ < (long long) (sd)->cache_hot_time) /* * These are the runqueue data structures: */ #define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long)) typedef struct runqueue runqueue_t; struct prio_array { unsigned int nr_active; unsigned long bitmap[BITMAP_SIZE]; struct list_head queue[MAX_PRIO]; }; /* * This is the main, per-CPU runqueue data structure. * * Locking rule: those places that want to lock multiple runqueues * (such as the load balancing or the thread migration code), lock * acquire operations must be ordered by ascending &runqueue. */ struct runqueue { spinlock_t lock; /* * nr_running and cpu_load should be in the same cacheline because * remote CPUs use both these fields when doing load calculation. */ unsigned long nr_running; #ifdef CONFIG_SMP unsigned long cpu_load[3]; #endif unsigned long long nr_switches; /* * This is part of a global counter where only the total sum * over all CPUs matters. A task can increase this counter on * one CPU and if it got migrated afterwards it may decrease * it on another CPU. Always updated under the runqueue lock: */ unsigned long nr_uninterruptible; unsigned long expired_timestamp; unsigned long long timestamp_last_tick; task_t *curr, *idle; struct mm_struct *prev_mm; prio_array_t *active, *expired, arrays[2]; int best_expired_prio; atomic_t nr_iowait; #ifdef CONFIG_SMP struct sched_domain *sd; /* For active balancing */ int active_balance; int push_cpu; task_t *migration_thread; struct list_head migration_queue; int cpu; #endif #ifdef CONFIG_SCHEDSTATS /* latency stats */ struct sched_info rq_sched_info; /* sys_sched_yield() stats */ unsigned long yld_exp_empty; unsigned long yld_act_empty; unsigned long yld_both_empty; unsigned long yld_cnt; /* schedule() stats */ unsigned long sched_switch; unsigned long sched_cnt; unsigned long sched_goidle; /* try_to_wake_up() stats */ unsigned long ttwu_cnt; unsigned long ttwu_local; #endif }; static DEFINE_PER_CPU(struct runqueue, runqueues); /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. * See detach_destroy_domains: synchronize_sched for details. * * The domain tree of any CPU may only be accessed from within * preempt-disabled sections. */ #define for_each_domain(cpu, domain) \ for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent) #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() (&__get_cpu_var(runqueues)) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif #ifndef finish_arch_switch # define finish_arch_switch(prev) do { } while (0) #endif #ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(runqueue_t *rq, task_t *p) { return rq->curr == p; } static inline void prepare_lock_switch(runqueue_t *rq, task_t *next) { } static inline void finish_lock_switch(runqueue_t *rq, task_t *prev) { #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; #endif spin_unlock_irq(&rq->lock); } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ static inline int task_running(runqueue_t *rq, task_t *p) { #ifdef CONFIG_SMP return p->oncpu; #else return rq->curr == p; #endif } static inline void prepare_lock_switch(runqueue_t *rq, task_t *next) { #ifdef CONFIG_SMP /* * We can optimise this out completely for !SMP, because the * SMP rebalancing from interrupt is the only thing that cares * here. */ next->oncpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW spin_unlock_irq(&rq->lock); #else spin_unlock(&rq->lock); #endif } static inline void finish_lock_switch(runqueue_t *rq, task_t *prev) { #ifdef CONFIG_SMP /* * After ->oncpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); prev->oncpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); #endif } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* * task_rq_lock - lock the runqueue a given task resides on and disable * interrupts. Note the ordering: we can safely lookup the task_rq without * explicitly disabling preemption. */ static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags) __acquires(rq->lock) { struct runqueue *rq; repeat_lock_task: local_irq_save(*flags); rq = task_rq(p); spin_lock(&rq->lock); if (unlikely(rq != task_rq(p))) { spin_unlock_irqrestore(&rq->lock, *flags); goto repeat_lock_task; } return rq; } static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags) __releases(rq->lock) { spin_unlock_irqrestore(&rq->lock, *flags); } #ifdef CONFIG_SCHEDSTATS /* * bump this up when changing the output format or the meaning of an existing * format, so that tools can adapt (or abort) */ #define SCHEDSTAT_VERSION 12 static int show_schedstat(struct seq_file *seq, void *v) { int cpu; seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); seq_printf(seq, "timestamp %lu\n", jiffies); for_each_online_cpu(cpu) { runqueue_t *rq = cpu_rq(cpu); #ifdef CONFIG_SMP struct sched_domain *sd; int dcnt = 0; #endif /* runqueue-specific stats */ seq_printf(seq, "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu", cpu, rq->yld_both_empty, rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt, rq->sched_switch, rq->sched_cnt, rq->sched_goidle, rq->ttwu_cnt, rq->ttwu_local, rq->rq_sched_info.cpu_time, rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt); seq_printf(seq, "\n"); #ifdef CONFIG_SMP /* domain-specific stats */ preempt_disable(); for_each_domain(cpu, sd) { enum idle_type itype; char mask_str[NR_CPUS]; cpumask_scnprintf(mask_str, NR_CPUS, sd->span); seq_printf(seq, "domain%d %s", dcnt++, mask_str); for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES; itype++) { seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu", sd->lb_cnt[itype], sd->lb_balanced[itype], sd->lb_failed[itype], sd->lb_imbalance[itype], sd->lb_gained[itype], sd->lb_hot_gained[itype], sd->lb_nobusyq[itype], sd->lb_nobusyg[itype]); } seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n", sd->alb_cnt, sd->alb_failed, sd->alb_pushed, sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed, sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed, sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance); } preempt_enable(); #endif } return 0; } static int schedstat_open(struct inode *inode, struct file *file) { unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32); char *buf = kmalloc(size, GFP_KERNEL); struct seq_file *m; int res; if (!buf) return -ENOMEM; res = single_open(file, show_schedstat, NULL); if (!res) { m = file->private_data; m->buf = buf; m->size = size; } else kfree(buf); return res; } struct file_operations proc_schedstat_operations = { .open = schedstat_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; # define schedstat_inc(rq, field) do { (rq)->field++; } while (0) # define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) #else /* !CONFIG_SCHEDSTATS */ # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) #endif /* * rq_lock - lock a given runqueue and disable interrupts. */ static inline runqueue_t *this_rq_lock(void) __acquires(rq->lock) { runqueue_t *rq; local_irq_disable(); rq = this_rq(); spin_lock(&rq->lock); return rq; } #ifdef CONFIG_SCHEDSTATS /* * Called when a process is dequeued from the active array and given * the cpu. We should note that with the exception of interactive * tasks, the expired queue will become the active queue after the active * queue is empty, without explicitly dequeuing and requeuing tasks in the * expired queue. (Interactive tasks may be requeued directly to the * active queue, thus delaying tasks in the expired queue from running; * see scheduler_tick()). * * This function is only called from sched_info_arrive(), rather than * dequeue_task(). Even though a task may be queued and dequeued multiple * times as it is shuffled about, we're really interested in knowing how * long it was from the *first* time it was queued to the time that it * finally hit a cpu. */ static inline void sched_info_dequeued(task_t *t) { t->sched_info.last_queued = 0; } /* * Called when a task finally hits the cpu. We can now calculate how * long it was waiting to run. We also note when it began so that we * can keep stats on how long its timeslice is. */ static void sched_info_arrive(task_t *t) { unsigned long now = jiffies, diff = 0; struct runqueue *rq = task_rq(t); if (t->sched_info.last_queued) diff = now - t->sched_info.last_queued; sched_info_dequeued(t); t->sched_info.run_delay += diff; t->sched_info.last_arrival = now; t->sched_info.pcnt++; if (!rq) return; rq->rq_sched_info.run_delay += diff; rq->rq_sched_info.pcnt++; } /* * Called when a process is queued into either the active or expired * array. The time is noted and later used to determine how long we * had to wait for us to reach the cpu. Since the expired queue will * become the active queue after active queue is empty, without dequeuing * and requeuing any tasks, we are interested in queuing to either. It * is unusual but not impossible for tasks to be dequeued and immediately * requeued in the same or another array: this can happen in sched_yield(), * set_user_nice(), and even load_balance() as it moves tasks from runqueue * to runqueue. * * This function is only called from enqueue_task(), but also only updates * the timestamp if it is already not set. It's assumed that * sched_info_dequeued() will clear that stamp when appropriate. */ static inline void sched_info_queued(task_t *t) { if (!t->sched_info.last_queued) t->sched_info.last_queued = jiffies; } /* * Called when a process ceases being the active-running process, either * voluntarily or involuntarily. Now we can calculate how long we ran. */ static inline void sched_info_depart(task_t *t) { struct runqueue *rq = task_rq(t); unsigned long diff = jiffies - t->sched_info.last_arrival; t->sched_info.cpu_time += diff; if (rq) rq->rq_sched_info.cpu_time += diff; } /* * Called when tasks are switched involuntarily due, typically, to expiring * their time slice. (This may also be called when switching to or from * the idle task.) We are only called when prev != next. */ static inline void sched_info_switch(task_t *prev, task_t *next) { struct runqueue *rq = task_rq(prev); /* * prev now departs the cpu. It's not interesting to record * stats about how efficient we were at scheduling the idle * process, however. */ if (prev != rq->idle) sched_info_depart(prev); if (next != rq->idle) sched_info_arrive(next); } #else #define sched_info_queued(t) do { } while (0) #define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS */ /* * Adding/removing a task to/from a priority array: */ static void dequeue_task(struct task_struct *p, prio_array_t *array) { array->nr_active--; list_del(&p->run_list); if (list_empty(array->queue + p->prio)) __clear_bit(p->prio, array->bitmap); } static void enqueue_task(struct task_struct *p, prio_array_t *array) { sched_info_queued(p); list_add_tail(&p->run_list, array->queue + p->prio); __set_bit(p->prio, array->bitmap); array->nr_active++; p->array = array; } /* * Put task to the end of the run list without the overhead of dequeue * followed by enqueue. */ static void requeue_task(struct task_struct *p, prio_array_t *array) { list_move_tail(&p->run_list, array->queue + p->prio); } static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array) { list_add(&p->run_list, array->queue + p->prio); __set_bit(p->prio, array->bitmap); array->nr_active++; p->array = array; } /* * effective_prio - return the priority that is based on the static * priority but is modified by bonuses/penalties. * * We scale the actual sleep average [0 .... MAX_SLEEP_AVG] * into the -5 ... 0 ... +5 bonus/penalty range. * * We use 25% of the full 0...39 priority range so that: * * 1) nice +19 interactive tasks do not preempt nice 0 CPU hogs. * 2) nice -20 CPU hogs do not get preempted by nice 0 tasks. * * Both properties are important to certain workloads. */ static int effective_prio(task_t *p) { int bonus, prio; if (rt_task(p)) return p->prio; bonus = CURRENT_BONUS(p) - MAX_BONUS / 2; prio = p->static_prio - bonus; if (prio < MAX_RT_PRIO) prio = MAX_RT_PRIO; if (prio > MAX_PRIO-1) prio = MAX_PRIO-1; return prio; } /* * __activate_task - move a task to the runqueue. */ static inline void __activate_task(task_t *p, runqueue_t *rq) { enqueue_task(p, rq->active); rq->nr_running++; } /* * __activate_idle_task - move idle task to the _front_ of runqueue. */ static inline void __activate_idle_task(task_t *p, runqueue_t *rq) { enqueue_task_head(p, rq->active); rq->nr_running++; } static int recalc_task_prio(task_t *p, unsigned long long now) { /* Caller must always ensure 'now >= p->timestamp' */ unsigned long long __sleep_time = now - p->timestamp; unsigned long sleep_time; if (unlikely(p->policy == SCHED_BATCH)) sleep_time = 0; else { if (__sleep_time > NS_MAX_SLEEP_AVG) sleep_time = NS_MAX_SLEEP_AVG; else sleep_time = (unsigned long)__sleep_time; } if (likely(sleep_time > 0)) { /* * User tasks that sleep a long time are categorised as * idle and will get just interactive status to stay active & * prevent them suddenly becoming cpu hogs and starving * other processes. */ if (p->mm && p->activated != -1 && sleep_time > INTERACTIVE_SLEEP(p)) { p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG - DEF_TIMESLICE); } else { /* * Tasks waking from uninterruptible sleep are * limited in their sleep_avg rise as they * are likely to be waiting on I/O */ if (p->activated == -1 && p->mm) { if (p->sleep_avg >= INTERACTIVE_SLEEP(p)) sleep_time = 0; else if (p->sleep_avg + sleep_time >= INTERACTIVE_SLEEP(p)) { p->sleep_avg = INTERACTIVE_SLEEP(p); sleep_time = 0; } } /* * This code gives a bonus to interactive tasks. * * The boost works by updating the 'average sleep time' * value here, based on ->timestamp. The more time a * task spends sleeping, the higher the average gets - * and the higher the priority boost gets as well. */ p->sleep_avg += sleep_time; if (p->sleep_avg > NS_MAX_SLEEP_AVG) p->sleep_avg = NS_MAX_SLEEP_AVG; } } return effective_prio(p); } /* * activate_task - move a task to the runqueue and do priority recalculation * * Update all the scheduling statistics stuff. (sleep average * calculation, priority modifiers, etc.) */ static void activate_task(task_t *p, runqueue_t *rq, int local) { unsigned long long now; now = sched_clock(); #ifdef CONFIG_SMP if (!local) { /* Compensate for drifting sched_clock */ runqueue_t *this_rq = this_rq(); now = (now - this_rq->timestamp_last_tick) + rq->timestamp_last_tick; } #endif if (!rt_task(p)) p->prio = recalc_task_prio(p, now); /* * This checks to make sure it's not an uninterruptible task * that is now waking up. */ if (!p->activated) { /* * Tasks which were woken up by interrupts (ie. hw events) * are most likely of interactive nature. So we give them * the credit of extending their sleep time to the period * of time they spend on the runqueue, waiting for execution * on a CPU, first time around: */ if (in_interrupt()) p->activated = 2; else { /* * Normal first-time wakeups get a credit too for * on-runqueue time, but it will be weighted down: */ p->activated = 1; } } p->timestamp = now; __activate_task(p, rq); } /* * deactivate_task - remove a task from the runqueue. */ static void deactivate_task(struct task_struct *p, runqueue_t *rq) { rq->nr_running--; dequeue_task(p, p->array); p->array = NULL; } /* * resched_task - mark a task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ #ifdef CONFIG_SMP static void resched_task(task_t *p) { int cpu; assert_spin_locked(&task_rq(p)->lock); if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) return; set_tsk_thread_flag(p, TIF_NEED_RESCHED); cpu = task_cpu(p); if (cpu == smp_processor_id()) return; /* NEED_RESCHED must be visible before we test POLLING_NRFLAG */ smp_mb(); if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG)) smp_send_reschedule(cpu); } #else static inline void resched_task(task_t *p) { assert_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } #endif /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. */ inline int task_curr(const task_t *p) { return cpu_curr(task_cpu(p)) == p; } #ifdef CONFIG_SMP typedef struct { struct list_head list; task_t *task; int dest_cpu; struct completion done; } migration_req_t; /* * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req) { runqueue_t *rq = task_rq(p); /* * If the task is not on a runqueue (and not running), then * it is sufficient to simply update the task's cpu field. */ if (!p->array && !task_running(rq, p)) { set_task_cpu(p, dest_cpu); return 0; } init_completion(&req->done); req->task = p; req->dest_cpu = dest_cpu; list_add(&req->list, &rq->migration_queue); return 1; } /* * wait_task_inactive - wait for a thread to unschedule. * * The caller must ensure that the task *will* unschedule sometime soon, * else this function might spin for a *long* time. This function can't * be called with interrupts off, or it may introduce deadlock with * smp_call_function() if an IPI is sent by the same process we are * waiting to become inactive. */ void wait_task_inactive(task_t *p) { unsigned long flags; runqueue_t *rq; int preempted; repeat: rq = task_rq_lock(p, &flags); /* Must be off runqueue entirely, not preempted. */ if (unlikely(p->array || task_running(rq, p))) { /* If it's preempted, we yield. It could be a while. */ preempted = !task_running(rq, p); task_rq_unlock(rq, &flags); cpu_relax(); if (preempted) yield(); goto repeat; } task_rq_unlock(rq, &flags); } /*** * kick_process - kick a running thread to enter/exit the kernel * @p: the to-be-kicked thread * * Cause a process which is running on another CPU to enter * kernel-mode, without any delay. (to get signals handled.) * * NOTE: this function doesnt have to take the runqueue lock, * because all it wants to ensure is that the remote task enters * the kernel. If the IPI races and the task has been migrated * to another CPU then no harm is done and the purpose has been * achieved as well. */ void kick_process(task_t *p) { int cpu; preempt_disable(); cpu = task_cpu(p); if ((cpu != smp_processor_id()) && task_curr(p)) smp_send_reschedule(cpu); preempt_enable(); } /* * Return a low guess at the load of a migration-source cpu. * * We want to under-estimate the load of migration sources, to * balance conservatively. */ static inline unsigned long source_load(int cpu, int type) { runqueue_t *rq = cpu_rq(cpu); unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE; if (type == 0) return load_now; return min(rq->cpu_load[type-1], load_now); } /* * Return a high guess at the load of a migration-target cpu */ static inline unsigned long target_load(int cpu, int type) { runqueue_t *rq = cpu_rq(cpu); unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE; if (type == 0) return load_now; return max(rq->cpu_load[type-1], load_now); } /* * find_idlest_group finds and returns the least busy CPU group within the * domain. */ static struct sched_group * find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) { struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; unsigned long min_load = ULONG_MAX, this_load = 0; int load_idx = sd->forkexec_idx; int imbalance = 100 + (sd->imbalance_pct-100)/2; do { unsigned long load, avg_load; int local_group; int i; /* Skip over this group if it has no CPUs allowed */ if (!cpus_intersects(group->cpumask, p->cpus_allowed)) goto nextgroup; local_group = cpu_isset(this_cpu, group->cpumask); /* Tally up the load of all CPUs in the group */ avg_load = 0; for_each_cpu_mask(i, group->cpumask) { /* Bias balancing toward cpus of our domain */ if (local_group) load = source_load(i, load_idx); else load = target_load(i, load_idx); avg_load += load; } /* Adjust by relative CPU power of the group */ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; if (local_group) { this_load = avg_load; this = group; } else if (avg_load < min_load) { min_load = avg_load; idlest = group; } nextgroup: group = group->next; } while (group != sd->groups); if (!idlest || 100*this_load < imbalance*min_load) return NULL; return idlest; } /* * find_idlest_queue - find the idlest runqueue among the cpus in group. */ static int find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { cpumask_t tmp; unsigned long load, min_load = ULONG_MAX; int idlest = -1; int i; /* Traverse only the allowed CPUs */ cpus_and(tmp, group->cpumask, p->cpus_allowed); for_each_cpu_mask(i, tmp) { load = source_load(i, 0); if (load < min_load || (load == min_load && i == this_cpu)) { min_load = load; idlest = i; } } return idlest; } /* * sched_balance_self: balance the current task (running on cpu) in domains * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and * SD_BALANCE_EXEC. * * Balance, ie. select the least loaded group. * * Returns the target CPU number, or the same CPU if no balancing is needed. * * preempt must be disabled. */ static int sched_balance_self(int cpu, int flag) { struct task_struct *t = current; struct sched_domain *tmp, *sd = NULL; for_each_domain(cpu, tmp) if (tmp->flags & flag) sd = tmp; while (sd) { cpumask_t span; struct sched_group *group; int new_cpu; int weight; span = sd->span; group = find_idlest_group(sd, t, cpu); if (!group) goto nextlevel; new_cpu = find_idlest_cpu(group, t, cpu); if (new_cpu == -1 || new_cpu == cpu) goto nextlevel; /* Now try balancing at a lower domain level */ cpu = new_cpu; nextlevel: sd = NULL; weight = cpus_weight(span); for_each_domain(cpu, tmp) { if (weight <= cpus_weight(tmp->span)) break; if (tmp->flags & flag) sd = tmp; } /* while loop will break here if sd == NULL */ } return cpu; } #endif /* CONFIG_SMP */ /* * wake_idle() will wake a task on an idle cpu if task->cpu is * not idle and an idle cpu is available. The span of cpus to * search starts with cpus closest then further out as needed, * so we always favor a closer, idle cpu. * * Returns the CPU we should wake onto. */ #if defined(ARCH_HAS_SCHED_WAKE_IDLE) static int wake_idle(int cpu, task_t *p) { cpumask_t tmp; struct sched_domain *sd; int i; if (idle_cpu(cpu)) return cpu; for_each_domain(cpu, sd) { if (sd->flags & SD_WAKE_IDLE) { cpus_and(tmp, sd->span, p->cpus_allowed); for_each_cpu_mask(i, tmp) { if (idle_cpu(i)) return i; } } else break; } return cpu; } #else static inline int wake_idle(int cpu, task_t *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(task_t *p, unsigned int state, int sync) { int cpu, this_cpu, success = 0; unsigned long flags; long old_state; runqueue_t *rq; #ifdef CONFIG_SMP unsigned long load, this_load; struct sched_domain *sd, *this_sd = NULL; int new_cpu; #endif rq = task_rq_lock(p, &flags); old_state = p->state; if (!(old_state & state)) goto out; if (p->array) goto out_running; cpu = task_cpu(p); this_cpu = smp_processor_id(); #ifdef CONFIG_SMP if (unlikely(task_running(rq, p))) goto out_activate; new_cpu = cpu; schedstat_inc(rq, ttwu_cnt); if (cpu == this_cpu) { schedstat_inc(rq, ttwu_local); goto out_set_cpu; } for_each_domain(this_cpu, sd) { if (cpu_isset(cpu, sd->span)) { schedstat_inc(sd, ttwu_wake_remote); this_sd = sd; break; } } if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) goto out_set_cpu; /* * Check for affine wakeup and passive balancing possibilities. */ if (this_sd) { int idx = this_sd->wake_idx; unsigned int imbalance; imbalance = 100 + (this_sd->imbalance_pct - 100) / 2; load = source_load(cpu, idx); this_load = target_load(this_cpu, idx); new_cpu = this_cpu; /* Wake to this CPU if we can */ if (this_sd->flags & SD_WAKE_AFFINE) { unsigned long tl = this_load; /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load * of the current CPU: */ if (sync) tl -= SCHED_LOAD_SCALE; if ((tl <= load && tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) || 100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) { /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and * there is no bad imbalance. */ schedstat_inc(this_sd, ttwu_move_affine); goto out_set_cpu; } } /* * Start passive balancing when half the imbalance_pct * limit is reached. */ if (this_sd->flags & SD_WAKE_BALANCE) { if (imbalance*this_load <= 100*load) { schedstat_inc(this_sd, ttwu_move_balance); goto out_set_cpu; } } } new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */ out_set_cpu: new_cpu = wake_idle(new_cpu, p); if (new_cpu != cpu) { set_task_cpu(p, new_cpu); task_rq_unlock(rq, &flags); /* might preempt at this point */ rq = task_rq_lock(p, &flags); old_state = p->state; if (!(old_state & state)) goto out; if (p->array) goto out_running; this_cpu = smp_processor_id(); cpu = task_cpu(p); } out_activate: #endif /* CONFIG_SMP */ if (old_state == TASK_UNINTERRUPTIBLE) { rq->nr_uninterruptible--; /* * Tasks on involuntary sleep don't earn * sleep_avg beyond just interactive state. */ p->activated = -1; } /* * Tasks that have marked their sleep as noninteractive get * woken up without updating their sleep average. (i.e. their * sleep is handled in a priority-neutral manner, no priority * boost and no penalty.) */ if (old_state & TASK_NONINTERACTIVE) __activate_task(p, rq); else activate_task(p, rq, cpu == this_cpu); /* * Sync wakeups (i.e. those types of wakeups where the waker * has indicated that it will leave the CPU in short order) * don't trigger a preemption, if the woken up task will run on * this cpu. (in this case the 'I will reschedule' promise of * the waker guarantees that the freshly woken up task is going * to be considered on this CPU.) */ if (!sync || cpu != this_cpu) { if (TASK_PREEMPTS_CURR(p, rq)) resched_task(rq->curr); } success = 1; out_running: p->state = TASK_RUNNING; out: task_rq_unlock(rq, &flags); return success; } int fastcall wake_up_process(task_t *p) { return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED | TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0); } EXPORT_SYMBOL(wake_up_process); int fastcall wake_up_state(task_t *p, unsigned int state) { return try_to_wake_up(p, state, 0); } /* * Perform scheduler related setup for a newly forked process p. * p is forked by current. */ void fastcall sched_fork(task_t *p, int clone_flags) { int cpu = get_cpu(); #ifdef CONFIG_SMP cpu = sched_balance_self(cpu, SD_BALANCE_FORK); #endif set_task_cpu(p, cpu); /* * 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; INIT_LIST_HEAD(&p->run_list); p->array = NULL; #ifdef CONFIG_SCHEDSTATS memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) p->oncpu = 0; #endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif /* * Share the timeslice between parent and child, thus the * total amount of pending timeslices in the system doesn't change, * resulting in more scheduling fairness. */ local_irq_disable(); p->time_slice = (current->time_slice + 1) >> 1; /* * The remainder of the first timeslice might be recovered by * the parent if the child exits early enough. */ p->first_time_slice = 1; current->time_slice >>= 1; p->timestamp = sched_clock(); if (unlikely(!current->time_slice)) { /* * This case is rare, it happens when the parent has only * a single jiffy left from its timeslice. Taking the * runqueue lock is not a problem. */ current->time_slice = 1; scheduler_tick(); } local_irq_enable(); put_cpu(); } /* * wake_up_new_task - wake up a newly created task for the first time. * * This function will do some initial scheduler statistics housekeeping * that must be done for every newly created context, then puts the task * on the runqueue and wakes it. */ void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags) { unsigned long flags; int this_cpu, cpu; runqueue_t *rq, *this_rq; rq = task_rq_lock(p, &flags); BUG_ON(p->state != TASK_RUNNING); this_cpu = smp_processor_id(); cpu = task_cpu(p); /* * We decrease the sleep average of forking parents * and children as well, to keep max-interactive tasks * from forking tasks that are max-interactive. The parent * (current) is done further down, under its lock. */ p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) * CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS); p->prio = effective_prio(p); if (likely(cpu == this_cpu)) { if (!(clone_flags & CLONE_VM)) { /* * The VM isn't cloned, so we're in a good position to * do child-runs-first in anticipation of an exec. This * usually avoids a lot of COW overhead. */ if (unlikely(!current->array)) __activate_task(p, rq); else { p->prio = current->prio; list_add_tail(&p->run_list, ¤t->run_list); p->array = current->array; p->array->nr_active++; rq->nr_running++; } set_need_resched(); } else /* Run child last */ __activate_task(p, rq); /* * We skip the following code due to cpu == this_cpu * * task_rq_unlock(rq, &flags); * this_rq = task_rq_lock(current, &flags); */ this_rq = rq; } else { this_rq = cpu_rq(this_cpu); /* * Not the local CPU - must adjust timestamp. This should * get optimised away in the !CONFIG_SMP case. */ p->timestamp = (p->timestamp - this_rq->timestamp_last_tick) + rq->timestamp_last_tick; __activate_task(p, rq); if (TASK_PREEMPTS_CURR(p, rq)) resched_task(rq->curr); /* * Parent and child are on different CPUs, now get the * parent runqueue to update the parent's ->sleep_avg: */ task_rq_unlock(rq, &flags); this_rq = task_rq_lock(current, &flags); } current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) * PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS); task_rq_unlock(this_rq, &flags); } /* * Potentially available exiting-child timeslices are * retrieved here - this way the parent does not get * penalized for creating too many threads. * * (this cannot be used to 'generate' timeslices * artificially, because any timeslice recovered here * was given away by the parent in the first place.) */ void fastcall sched_exit(task_t *p) { unsigned long flags; runqueue_t *rq; /* * If the child was a (relative-) CPU hog then decrease * the sleep_avg of the parent as well. */ rq = task_rq_lock(p->parent, &flags); if (p->first_time_slice && task_cpu(p) == task_cpu(p->parent)) { p->parent->time_slice += p->time_slice; if (unlikely(p->parent->time_slice > task_timeslice(p))) p->parent->time_slice = task_timeslice(p); } if (p->sleep_avg < p->parent->sleep_avg) p->parent->sleep_avg = p->parent->sleep_avg / (EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg / (EXIT_WEIGHT + 1); task_rq_unlock(rq, &flags); } /** * prepare_task_switch - prepare to switch tasks * @rq: the runqueue preparing to switch * @next: the task we are going to switch to. * * This is called with the rq lock held and interrupts off. It must * be paired with a subsequent finish_task_switch after the context * switch. * * prepare_task_switch sets up locking and calls architecture specific * hooks. */ static inline void prepare_task_switch(runqueue_t *rq, task_t *next) { prepare_lock_switch(rq, next); prepare_arch_switch(next); } /** * finish_task_switch - clean up after a task-switch * @rq: runqueue associated with task-switch * @prev: the thread we just switched away from. * * finish_task_switch must be called after the context switch, paired * with a prepare_task_switch call before the context switch. * finish_task_switch will reconcile locking set up by prepare_task_switch, * and do any other architecture-specific cleanup actions. * * Note that we may have delayed dropping an mm in context_switch(). If * so, we finish that here outside of the runqueue lock. (Doing it * with the lock held can cause deadlocks; see schedule() for * details.) */ static inline void finish_task_switch(runqueue_t *rq, task_t *prev) __releases(rq->lock) { struct mm_struct *mm = rq->prev_mm; unsigned long prev_task_flags; rq->prev_mm = NULL; /* * A task struct has one reference for the use as "current". * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and * calls schedule one last time. The schedule call will never return, * and the scheduled task must drop that reference. * The test for EXIT_ZOMBIE must occur while the runqueue locks are * still held, otherwise prev could be scheduled on another cpu, die * there before we look at prev->state, and then the reference would * be dropped twice. * Manfred Spraul */ prev_task_flags = prev->flags; finish_arch_switch(prev); finish_lock_switch(rq, prev); if (mm) mmdrop(mm); if (unlikely(prev_task_flags & PF_DEAD)) put_task_struct(prev); } /** * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. */ asmlinkage void schedule_tail(task_t *prev) __releases(rq->lock) { runqueue_t *rq = this_rq(); finish_task_switch(rq, prev); #ifdef __ARCH_WANT_UNLOCKED_CTXSW /* In this case, finish_task_switch does not reenable preemption */ preempt_enable(); #endif if (current->set_child_tid) put_user(current->pid, current->set_child_tid); } /* * context_switch - switch to the new MM and the new * thread's register state. */ static inline task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next) { struct mm_struct *mm = next->mm; struct mm_struct *oldmm = prev->active_mm; if (unlikely(!mm)) { next->active_mm = oldmm; atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else switch_mm(oldmm, mm, next); if (unlikely(!prev->mm)) { prev->active_mm = NULL; WARN_ON(rq->prev_mm); rq->prev_mm = oldmm; } /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); return prev; } /* * nr_running, nr_uninterruptible and nr_context_switches: * * externally visible scheduler statistics: current number of runnable * threads, current number of uninterruptible-sleeping threads, total * number of context switches performed since bootup. */ unsigned long nr_running(void) { unsigned long i, sum = 0; for_each_online_cpu(i) sum += cpu_rq(i)->nr_running; return sum; } unsigned long nr_uninterruptible(void) { unsigned long i, sum = 0; for_each_cpu(i) sum += cpu_rq(i)->nr_uninterruptible; /* * Since we read the counters lockless, it might be slightly * inaccurate. Do not allow it to go below zero though: */ if (unlikely((long)sum < 0)) sum = 0; return sum; } unsigned long long nr_context_switches(void) { unsigned long long i, sum = 0; for_each_cpu(i) sum += cpu_rq(i)->nr_switches; return sum; } unsigned long nr_iowait(void) { unsigned long i, sum = 0; for_each_cpu(i) sum += atomic_read(&cpu_rq(i)->nr_iowait); return sum; } #ifdef CONFIG_SMP /* * double_rq_lock - safely lock two runqueues * * We must take them in cpu order to match code in * dependent_sleeper and wake_dependent_sleeper. * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) __acquires(rq1->lock) __acquires(rq2->lock) { if (rq1 == rq2) { spin_lock(&rq1->lock); __acquire(rq2->lock); /* Fake it out ;) */ } else { if (rq1->cpu < rq2->cpu) { spin_lock(&rq1->lock); spin_lock(&rq2->lock); } else { spin_lock(&rq2->lock); spin_lock(&rq1->lock); } } } /* * 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(runqueue_t *rq1, runqueue_t *rq2) __releases(rq1->lock) __releases(rq2->lock) { spin_unlock(&rq1->lock); if (rq1 != rq2) spin_unlock(&rq2->lock); else __release(rq2->lock); } /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. */ static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest) __releases(this_rq->lock) __acquires(busiest->lock) __acquires(this_rq->lock) { if (unlikely(!spin_trylock(&busiest->lock))) { if (busiest->cpu < this_rq->cpu) { spin_unlock(&this_rq->lock); spin_lock(&busiest->lock); spin_lock(&this_rq->lock); } else spin_lock(&busiest->lock); } } /* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only * allow dest_cpu, which will force the cpu onto dest_cpu. Then * the cpu_allowed mask is restored. */ static void sched_migrate_task(task_t *p, int dest_cpu) { migration_req_t req; runqueue_t *rq; unsigned long flags; rq = task_rq_lock(p, &flags); if (!cpu_isset(dest_cpu, p->cpus_allowed) || unlikely(cpu_is_offline(dest_cpu))) goto out; /* force the process onto the specified CPU */ if (migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ struct task_struct *mt = rq->migration_thread; get_task_struct(mt); task_rq_unlock(rq, &flags); wake_up_process(mt); put_task_struct(mt); wait_for_completion(&req.done); return; } out: task_rq_unlock(rq, &flags); } /* * sched_exec - execve() is a valuable balancing opportunity, because at * this point the task has the smallest effective memory and cache footprint. */ void sched_exec(void) { int new_cpu, this_cpu = get_cpu(); new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC); put_cpu(); if (new_cpu != this_cpu) sched_migrate_task(current, new_cpu); } /* * pull_task - move a task from a remote runqueue to the local runqueue. * Both runqueues must be locked. */ static void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p, runqueue_t *this_rq, prio_array_t *this_array, int this_cpu) { dequeue_task(p, src_array); src_rq->nr_running--; set_task_cpu(p, this_cpu); this_rq->nr_running++; enqueue_task(p, this_array); p->timestamp = (p->timestamp - src_rq->timestamp_last_tick) + this_rq->timestamp_last_tick; /* * Note that idle threads have a prio of MAX_PRIO, for this test * to be always true for them. */ if (TASK_PREEMPTS_CURR(p, this_rq)) resched_task(this_rq->curr); } /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ static int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu, struct sched_domain *sd, enum idle_type idle, int *all_pinned) { /* * We do not migrate tasks that are: * 1) running (obviously), or * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ if (!cpu_isset(this_cpu, p->cpus_allowed)) return 0; *all_pinned = 0; if (task_running(rq, p)) return 0; /* * Aggressive migration if: * 1) task is cache cold, or * 2) too many balance attempts have failed. */ if (sd->nr_balance_failed > sd->cache_nice_tries) return 1; if (task_hot(p, rq->timestamp_last_tick, sd)) return 0; return 1; } /* * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq, * as part of a balancing operation within "domain". Returns the number of * tasks moved. * * Called with both runqueues locked. */ static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest, unsigned long max_nr_move, struct sched_domain *sd, enum idle_type idle, int *all_pinned) { prio_array_t *array, *dst_array; struct list_head *head, *curr; int idx, pulled = 0, pinned = 0; task_t *tmp; if (max_nr_move == 0) goto out; pinned = 1; /* * We first consider expired tasks. Those will likely not be * executed in the near future, and they are most likely to * be cache-cold, thus switching CPUs has the least effect * on them. */ if (busiest->expired->nr_active) { array = busiest->expired; dst_array = this_rq->expired; } else { array = busiest->active; dst_array = this_rq->active; } new_array: /* Start searching at priority 0: */ idx = 0; skip_bitmap: if (!idx) idx = sched_find_first_bit(array->bitmap); else idx = find_next_bit(array->bitmap, MAX_PRIO, idx); if (idx >= MAX_PRIO) { if (array == busiest->expired && busiest->active->nr_active) { array = busiest->active; dst_array = this_rq->active; goto new_array; } goto out; } head = array->queue + idx; curr = head->prev; skip_queue: tmp = list_entry(curr, task_t, run_list); curr = curr->prev; if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) { if (curr != head) goto skip_queue; idx++; goto skip_bitmap; } #ifdef CONFIG_SCHEDSTATS if (task_hot(tmp, busiest->timestamp_last_tick, sd)) schedstat_inc(sd, lb_hot_gained[idle]); #endif pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu); pulled++; /* We only want to steal up to the prescribed number of tasks. */ if (pulled < max_nr_move) { if (curr != head) goto skip_queue; idx++; goto skip_bitmap; } out: /* * Right now, this is the only place pull_task() is called, * so we can safely collect pull_task() stats here rather than * inside pull_task(). */ schedstat_add(sd, lb_gained[idle], pulled); if (all_pinned) *all_pinned = pinned; return pulled; } /* * find_busiest_group finds and returns the busiest CPU group within the * domain. It calculates and returns the number of tasks which should be * moved to restore balance via the imbalance parameter. */ static struct sched_group * find_busiest_group(struct sched_domain *sd, int this_cpu, unsigned long *imbalance, enum idle_type idle, int *sd_idle) { struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; unsigned long max_load, avg_load, total_load, this_load, total_pwr; unsigned long max_pull; int load_idx; max_load = this_load = total_load = total_pwr = 0; if (idle == NOT_IDLE) load_idx = sd->busy_idx; else if (idle == NEWLY_IDLE) load_idx = sd->newidle_idx; else load_idx = sd->idle_idx; do { unsigned long load; int local_group; int i; local_group = cpu_isset(this_cpu, group->cpumask); /* Tally up the load of all CPUs in the group */ avg_load = 0; for_each_cpu_mask(i, group->cpumask) { if (*sd_idle && !idle_cpu(i)) *sd_idle = 0; /* Bias balancing toward cpus of our domain */ if (local_group) load = target_load(i, load_idx); else load = source_load(i, load_idx); avg_load += load; } total_load += avg_load; total_pwr += group->cpu_power; /* Adjust by relative CPU power of the group */ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; if (local_group) { this_load = avg_load; this = group; } else if (avg_load > max_load) { max_load = avg_load; busiest = group; } group = group->next; } while (group != sd->groups); if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE) goto out_balanced; avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr; if (this_load >= avg_load || 100*max_load <= sd->imbalance_pct*this_load) goto out_balanced; /* * 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. */ /* Don't want to pull so many tasks that a group would go idle */ max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE); /* How much load to actually move to equalise the imbalance */ *imbalance = min(max_pull * busiest->cpu_power, (avg_load - this_load) * this->cpu_power) / SCHED_LOAD_SCALE; if (*imbalance < SCHED_LOAD_SCALE) { unsigned long pwr_now = 0, pwr_move = 0; unsigned long tmp; if (max_load - this_load >= SCHED_LOAD_SCALE*2) { *imbalance = 1; return busiest; } /* * OK, we don't have enough imbalance to justify moving tasks, * however we may be able to increase total CPU power used by * moving them. */ pwr_now += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load); pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load); pwr_now /= SCHED_LOAD_SCALE; /* Amount of load we'd subtract */ tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power; if (max_load > tmp) pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load - tmp); /* Amount of load we'd add */ if (max_load*busiest->cpu_power < SCHED_LOAD_SCALE*SCHED_LOAD_SCALE) tmp = max_load*busiest->cpu_power/this->cpu_power; else tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power; pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp); pwr_move /= SCHED_LOAD_SCALE; /* Move if we gain throughput */ if (pwr_move <= pwr_now) goto out_balanced; *imbalance = 1; return busiest; } /* Get rid of the scaling factor, rounding down as we divide */ *imbalance = *imbalance / SCHED_LOAD_SCALE; return busiest; out_balanced: *imbalance = 0; return NULL; } /* * find_busiest_queue - find the busiest runqueue among the cpus in group. */ static runqueue_t *find_busiest_queue(struct sched_group *group, enum idle_type idle) { unsigned long load, max_load = 0; runqueue_t *busiest = NULL; int i; for_each_cpu_mask(i, group->cpumask) { load = source_load(i, 0); if (load > max_load) { max_load = load; busiest = cpu_rq(i); } } return busiest; } /* * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but * so long as it is large enough. */ #define MAX_PINNED_INTERVAL 512 /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. * * Called with this_rq unlocked. */ static int load_balance(int this_cpu, runqueue_t *this_rq, struct sched_domain *sd, enum idle_type idle) { struct sched_group *group; runqueue_t *busiest; unsigned long imbalance; int nr_moved, all_pinned = 0; int active_balance = 0; int sd_idle = 0; if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER) sd_idle = 1; schedstat_inc(sd, lb_cnt[idle]); group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle); if (!group) { schedstat_inc(sd, lb_nobusyg[idle]); goto out_balanced; } busiest = find_busiest_queue(group, idle); if (!busiest) { schedstat_inc(sd, lb_nobusyq[idle]); goto out_balanced; } BUG_ON(busiest == this_rq); schedstat_add(sd, lb_imbalance[idle], imbalance); nr_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. nr_moved simply stays zero, so it is * correctly treated as an imbalance. */ double_rq_lock(this_rq, busiest); nr_moved = move_tasks(this_rq, this_cpu, busiest, imbalance, sd, idle, &all_pinned); double_rq_unlock(this_rq, busiest); /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(all_pinned)) goto out_balanced; } if (!nr_moved) { schedstat_inc(sd, lb_failed[idle]); sd->nr_balance_failed++; if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) { spin_lock(&busiest->lock); /* don't kick the migration_thread, if the curr * task on busiest cpu can't be moved to this_cpu */ if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) { spin_unlock(&busiest->lock); 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(&busiest->lock); 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 (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER) return -1; return nr_moved; out_balanced: schedstat_inc(sd, lb_balanced[idle]); sd->nr_balance_failed = 0; out_one_pinned: /* tune up the balancing interval */ if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) || (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER) return -1; return 0; } /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. * * Called from schedule when this_rq is about to become idle (NEWLY_IDLE). * this_rq is locked. */ static int load_balance_newidle(int this_cpu, runqueue_t *this_rq, struct sched_domain *sd) { struct sched_group *group; runqueue_t *busiest = NULL; unsigned long imbalance; int nr_moved = 0; int sd_idle = 0; if (sd->flags & SD_SHARE_CPUPOWER) sd_idle = 1; schedstat_inc(sd, lb_cnt[NEWLY_IDLE]); group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle); if (!group) { schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]); goto out_balanced; } busiest = find_busiest_queue(group, NEWLY_IDLE); if (!busiest) { schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]); goto out_balanced; } BUG_ON(busiest == this_rq); schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance); nr_moved = 0; if (busiest->nr_running > 1) { /* Attempt to move tasks */ double_lock_balance(this_rq, busiest); nr_moved = move_tasks(this_rq, this_cpu, busiest, imbalance, sd, NEWLY_IDLE, NULL); spin_unlock(&busiest->lock); } if (!nr_moved) { schedstat_inc(sd, lb_failed[NEWLY_IDLE]); if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER) return -1; } else sd->nr_balance_failed = 0; return nr_moved; out_balanced: schedstat_inc(sd, lb_balanced[NEWLY_IDLE]); if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER) 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, runqueue_t *this_rq) { struct sched_domain *sd; for_each_domain(this_cpu, sd) { if (sd->flags & SD_BALANCE_NEWIDLE) { if (load_balance_newidle(this_cpu, this_rq, sd)) { /* We've pulled tasks over so stop searching */ break; } } } } /* * 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(runqueue_t *busiest_rq, int busiest_cpu) { struct sched_domain *sd; runqueue_t *target_rq; int target_cpu = busiest_rq->push_cpu; if (busiest_rq->nr_running <= 1) /* no task to move */ 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); /* Search for an sd spanning us and the target CPU. */ for_each_domain(target_cpu, sd) if ((sd->flags & SD_LOAD_BALANCE) && cpu_isset(busiest_cpu, sd->span)) break; if (unlikely(sd == NULL)) goto out; schedstat_inc(sd, alb_cnt); if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL)) schedstat_inc(sd, alb_pushed); else schedstat_inc(sd, alb_failed); out: spin_unlock(&target_rq->lock); } /* * rebalance_tick will get called every timer tick, on every CPU. * * 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. */ /* Don't have all balancing operations going off at once */ #define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS) static void rebalance_tick(int this_cpu, runqueue_t *this_rq, enum idle_type idle) { unsigned long old_load, this_load; unsigned long j = jiffies + CPU_OFFSET(this_cpu); struct sched_domain *sd; int i; this_load = this_rq->nr_running * SCHED_LOAD_SCALE; /* Update our load */ for (i = 0; i < 3; i++) { unsigned long new_load = this_load; int scale = 1 << i; old_load = this_rq->cpu_load[i]; /* * 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) / scale; } for_each_domain(this_cpu, sd) { unsigned long interval; if (!(sd->flags & SD_LOAD_BALANCE)) continue; interval = sd->balance_interval; if (idle != SCHED_IDLE) interval *= sd->busy_factor; /* scale ms to jiffies */ interval = msecs_to_jiffies(interval); if (unlikely(!interval)) interval = 1; if (j - sd->last_balance >= interval) { if (load_balance(this_cpu, this_rq, sd, idle)) { /* * We've pulled tasks over so either we're no * longer idle, or one of our SMT siblings is * not idle. */ idle = NOT_IDLE; } sd->last_balance += interval; } } } #else /* * on UP we do not need to balance between CPUs: */ static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle) { } static inline void idle_balance(int cpu, runqueue_t *rq) { } #endif static inline int wake_priority_sleeper(runqueue_t *rq) { int ret = 0; #ifdef CONFIG_SCHED_SMT spin_lock(&rq->lock); /* * If an SMT sibling task has been put to sleep for priority * reasons reschedule the idle task to see if it can now run. */ if (rq->nr_running) { resched_task(rq->idle); ret = 1; } spin_unlock(&rq->lock); #endif return ret; } DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); /* * This is called on clock ticks and on context switches. * Bank in p->sched_time the ns elapsed since the last tick or switch. */ static inline void update_cpu_clock(task_t *p, runqueue_t *rq, unsigned long long now) { unsigned long long last = max(p->timestamp, rq->timestamp_last_tick); p->sched_time += now - last; } /* * Return current->sched_time plus any more ns on the sched_clock * that have not yet been banked. */ unsigned long long current_sched_time(const task_t *tsk) { unsigned long long ns; unsigned long flags; local_irq_save(flags); ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick); ns = tsk->sched_time + (sched_clock() - ns); local_irq_restore(flags); return ns; } /* * We place interactive tasks back into the active array, if possible. * * To guarantee that this does not starve expired tasks we ignore the * interactivity of a task if the first expired task had to wait more * than a 'reasonable' amount of time. This deadline timeout is * load-dependent, as the frequency of array switched decreases with * increasing number of running tasks. We also ignore the interactivity * if a better static_prio task has expired: */ #define EXPIRED_STARVING(rq) \ ((STARVATION_LIMIT && ((rq)->expired_timestamp && \ (jiffies - (rq)->expired_timestamp >= \ STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \ ((rq)->curr->static_prio > (rq)->best_expired_prio)) /* * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in user space since the last update */ void account_user_time(struct task_struct *p, cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; cputime64_t tmp; p->utime = cputime_add(p->utime, cputime); /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); if (TASK_NICE(p) > 0) cpustat->nice = cputime64_add(cpustat->nice, tmp); else cpustat->user = cputime64_add(cpustat->user, tmp); } /* * Account system cpu time to a process. * @p: the