diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 668 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 101 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 278 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 88 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 972 | ||||
| -rw-r--r-- | kernel/sched/features.h | 18 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 124 | ||||
| -rw-r--r-- | kernel/sched/idle_task.c | 1 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 126 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 81 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 4 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 1 |
12 files changed, 1198 insertions, 1264 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c86935a7f1f8..8b864ecee0e1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1000,7 +1000,11 @@ inline int task_curr(const struct task_struct *p) } /* - * Can drop rq->lock because from sched_class::switched_from() methods drop it. + * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock, + * use the balance_callback list if you want balancing. + * + * this means any call to check_class_changed() must be followed by a call to + * balance_callback(). */ static inline void check_class_changed(struct rq *rq, struct task_struct *p, const struct sched_class *prev_class, @@ -1009,7 +1013,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, if (prev_class != p->sched_class) { if (prev_class->switched_from) prev_class->switched_from(rq, p); - /* Possble rq->lock 'hole'. */ + p->sched_class->switched_to(rq, p); } else if (oldprio != p->prio || dl_task(p)) p->sched_class->prio_changed(rq, p, oldprio); @@ -1041,6 +1045,222 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) } #ifdef CONFIG_SMP +/* + * This is how migration works: + * + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes + * it and puts it into the right queue. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. + */ + +/* + * move_queued_task - move a queued task to new rq. + * + * Returns (locked) new rq. Old rq's lock is released. + */ +static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu) +{ + lockdep_assert_held(&rq->lock); + + dequeue_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, new_cpu); + raw_spin_unlock(&rq->lock); + + rq = cpu_rq(new_cpu); + + raw_spin_lock(&rq->lock); + BUG_ON(task_cpu(p) != new_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; + enqueue_task(rq, p, 0); + check_preempt_curr(rq, p, 0); + + return rq; +} + +struct migration_arg { + struct task_struct *task; + int dest_cpu; +}; + +/* + * Move (not current) task off this cpu, onto dest cpu. We're doing + * this because either it can't run here any more (set_cpus_allowed() + * away from this CPU, or CPU going down), or because we're + * attempting to rebalance this task on exec (sched_exec). + * + * So we race with normal scheduler movements, but that's OK, as long + * as the task is no longer on this CPU. + */ +static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu) +{ + if (unlikely(!cpu_active(dest_cpu))) + return rq; + + /* Affinity changed (again). */ + if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return rq; + + rq = move_queued_task(rq, p, dest_cpu); + + return rq; +} + +/* + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. + */ +static int migration_cpu_stop(void *data) +{ + struct migration_arg *arg = data; + struct task_struct *p = arg->task; + struct rq *rq = this_rq(); + + /* + * The original target cpu might have gone down and we might + * be on another cpu but it doesn't matter. + */ + local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running + * __migrate_task() such that we will not miss enforcing cpus_allowed + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); + + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + /* + * If task_rq(p) != rq, it cannot be migrated here, because we're + * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because + * we're holding p->pi_lock. + */ + if (task_rq(p) == rq && task_on_rq_queued(p)) + rq = __migrate_task(rq, p, arg->dest_cpu); + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + + local_irq_enable(); + return 0; +} + +/* + * sched_class::set_cpus_allowed must do the below, but is not required to + * actually call this function. + */ +void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) +{ + cpumask_copy(&p->cpus_allowed, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + struct rq *rq = task_rq(p); + bool queued, running; + + lockdep_assert_held(&p->pi_lock); + + queued = task_on_rq_queued(p); + running = task_current(rq, p); + + if (queued) { + /* + * Because __kthread_bind() calls this on blocked tasks without + * holding rq->lock. + */ + lockdep_assert_held(&rq->lock); + dequeue_task(rq, p, 0); + } + if (running) + put_prev_task(rq, p); + + p->sched_class->set_cpus_allowed(p, new_mask); + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, p, 0); +} + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + unsigned long flags; + struct rq *rq; + unsigned int dest_cpu; + int ret = 0; + + rq = task_rq_lock(p, &flags); + + /* + * Must re-check here, to close a race against __kthread_bind(), + * sched_setaffinity() is not guaranteed to observe the flag. + */ + if (check && (p->flags & PF_NO_SETAFFINITY)) { + ret = -EINVAL; + goto out; + } + + if (cpumask_equal(&p->cpus_allowed, new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { + ret = -EINVAL; + goto out; + } + + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + /* Need help from migration thread: drop lock and wait. */ + task_rq_unlock(rq, p, &flags); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + return 0; + } else if (task_on_rq_queued(p)) { + /* + * OK, since we're going to drop the lock immediately + * afterwards anyway. + */ + lockdep_unpin_lock(&rq->lock); + rq = move_queued_task(rq, p, dest_cpu); + lockdep_pin_lock(&rq->lock); + } +out: + task_rq_unlock(rq, p, &flags); + + return ret; +} + +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + return __set_cpus_allowed_ptr(p, new_mask, false); +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { #ifdef CONFIG_SCHED_DEBUG @@ -1181,13 +1401,6 @@ out: return ret; } -struct migration_arg { - struct task_struct *task; - int dest_cpu; -}; - -static int migration_cpu_stop(void *data); - /* * wait_task_inactive - wait for a thread to unschedule. * @@ -1320,9 +1533,7 @@ void kick_process(struct task_struct *p) preempt_enable(); } EXPORT_SYMBOL_GPL(kick_process); -#endif /* CONFIG_SMP */ -#ifdef CONFIG_SMP /* * ->cpus_allowed is protected by both rq->lock and p->pi_lock */ @@ -1402,6 +1613,8 @@ out: static inline int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) { + lockdep_assert_held(&p->pi_lock); + if (p->nr_cpus_allowed > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); @@ -1427,7 +1640,16 @@ static void update_avg(u64 *avg, u64 sample) s64 diff = sample - *avg; *avg += diff >> 3; } -#endif + +#else + +static inline int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + return set_cpus_allowed_ptr(p, new_mask); +} + +#endif /* CONFIG_SMP */ static void ttwu_stat(struct task_struct *p, int cpu, int wake_flags) @@ -1486,12 +1708,19 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { check_preempt_curr(rq, p, wake_flags); - trace_sched_wakeup(p, true); - p->state = TASK_RUNNING; + trace_sched_wakeup(p); + #ifdef CONFIG_SMP - if (p->sched_class->task_woken) + if (p->sched_class->task_woken) { + /* + * Our task @p is fully woken up and running; so its safe to + * drop the rq->lock, hereafter rq is only used for statistics. + */ + lockdep_unpin_lock(&rq->lock); p->sched_class->task_woken(rq, p); + lockdep_pin_lock(&rq->lock); + } if (rq->idle_stamp) { u64 delta = rq_clock(rq) - rq->idle_stamp; @@ -1510,6 +1739,8 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) static void ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) { + lockdep_assert_held(&rq->lock); + #ifdef CONFIG_SMP if (p->sched_contributes_to_load) rq->nr_uninterruptible--; @@ -1554,6 +1785,7 @@ void sched_ttwu_pending(void) return; raw_spin_lock_irqsave(&rq->lock, flags); + lockdep_pin_lock(&rq->lock); while (llist) { p = llist_entry(llist, struct task_struct, wake_entry); @@ -1561,6 +1793,7 @@ void sched_ttwu_pending(void) ttwu_do_activate(rq, p, 0); } + lockdep_unpin_lock(&rq->lock); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1657,7 +1890,9 @@ static void ttwu_queue(struct task_struct *p, int cpu) #endif raw_spin_lock(&rq->lock); + lockdep_pin_lock(&rq->lock); ttwu_do_activate(rq, p, 0); + lockdep_unpin_lock(&rq->lock); raw_spin_unlock(&rq->lock); } @@ -1693,6 +1928,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (!(p->state & state)) goto out; + trace_sched_waking(p); + success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -1752,14 +1989,24 @@ static void try_to_wake_up_local(struct task_struct *p) lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet picked a replacement task. + */ + lockdep_unpin_lock(&rq->lock); raw_spin_unlock(&rq->lock); raw_spin_lock(&p->pi_lock); raw_spin_lock(&rq->lock); + lockdep_pin_lock(&rq->lock); } if (!(p->state & TASK_NORMAL)) goto out; + trace_sched_waking(p); + if (!task_on_rq_queued(p)) ttwu_activate(rq, p, ENQUEUE_WAKEUP); @@ -1827,9 +2074,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; -#ifdef CONFIG_SMP - p->se.avg.decay_count = 0; -#endif INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS @@ -1975,7 +2219,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) set_task_cpu(p, cpu); raw_spin_unlock_irqrestore(&p->pi_lock, flags); -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif @@ -2011,8 +2255,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { - rcu_lockdep_assert(rcu_read_lock_sched_held(), - "sched RCU must be held"); + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -2021,8 +2265,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; - rcu_lockdep_assert(rcu_read_lock_sched_held(), - "sched RCU must be held"); + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; @@ -2114,11 +2358,11 @@ void wake_up_new_task(struct task_struct *p) #endif /* Initialize new task's runnable average */ - init_task_runnable_average(p); + init_entity_runnable_average(&p->se); rq = __task_rq_lock(p); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; - trace_sched_wakeup_new(p, true); + trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) @@ -2131,13 +2375,27 @@ void wake_up_new_task(struct task_struct *p) static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE; +void preempt_notifier_inc(void) +{ + static_key_slow_inc(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_inc); + +void preempt_notifier_dec(void) +{ + static_key_slow_dec(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_dec); + /** * preempt_notifier_register - tell me when current is being preempted & rescheduled * @notifier: notifier struct to register */ void preempt_notifier_register(struct preempt_notifier *notifier) { - static_key_slow_inc(&preempt_notifier_key); + if (!static_key_false(&preempt_notifier_key)) + WARN(1, "registering preempt_notifier while notifiers disabled\n"); + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); } EXPORT_SYMBOL_GPL(preempt_notifier_register); @@ -2151,7 +2409,6 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register); void preempt_notifier_unregister(struct preempt_notifier *notifier) { hlist_del(¬ifier->link); - static_key_slow_dec(&preempt_notifier_key); } EXPORT_SYMBOL_GPL(preempt_notifier_unregister); @@ -2267,7 +2524,6 @@ static struct rq *finish_task_switch(struct task_struct *prev) */ prev_state = prev->state; vtime_task_switch(prev); - finish_arch_switch(prev); perf_event_task_sched_in(prev, current); finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -2287,30 +2543,42 @@ static struct rq *finish_task_switch(struct task_struct *prev) put_task_struct(prev); } - tick_nohz_task_switch(current); + tick_nohz_task_switch(); return rq; } #ifdef CONFIG_SMP /* rq->lock is NOT held, but preemption is disabled */ -static inline void post_schedule(struct rq *rq) +static void __balance_callback(struct rq *rq) { - if (rq->post_schedule) { - unsigned long flags; + struct callback_head *head, *next; + void (*func)(struct rq *rq); + unsigned long flags; - raw_spin_lock_irqsave(&rq->lock, flags); - if (rq->curr->sched_class->post_schedule) - rq->curr->sched_class->post_schedule(rq); - raw_spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); + head = rq->balance_callback; + rq->balance_callback = NULL; + while (head) { + func = (void (*)(struct rq *))head->func; + next = head->next; + head->next = NULL; + head = next; - rq->post_schedule = 0; + func(rq); } + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +static inline void balance_callback(struct rq *rq) +{ + if (unlikely(rq->balance_callback)) + __balance_callback(rq); } #else -static inline void post_schedule(struct rq *rq) +static inline void balance_callback(struct rq *rq) { } @@ -2328,7 +2596,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) /* finish_task_switch() drops rq->lock and enables preemtion */ preempt_disable(); rq = finish_task_switch(prev); - post_schedule(rq); + balance_callback(rq); preempt_enable(); if (current->set_child_tid) @@ -2372,6 +2640,7 @@ context_switch(struct rq *rq, struct task_struct *prev, * of the scheduler it's an obvious special-case), so we * do an early lockdep release here: */ + lockdep_unpin_lock(&rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ @@ -2794,6 +3063,7 @@ static void __sched __schedule(void) */ smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); + lockdep_pin_lock(&rq->lock); rq->clock_skip_update <<= 1; /* promote REQ to ACT */ @@ -2836,10 +3106,12 @@ static void __sched __schedule(void) rq = context_switch(rq, prev, next); /* unlocks the rq */ cpu = cpu_of(rq); - } else + } else { + lockdep_unpin_lock(&rq->lock); raw_spin_unlock_irq(&rq->lock); + } - post_schedule(rq); + balance_callback(rq); } static inline void sched_submit_work(struct task_struct *tsk) @@ -3103,7 +3375,11 @@ void rt_mutex_setprio(struct task_struct *p, int prio) check_class_changed(rq, p, prev_class, oldprio); out_unlock: + preempt_disable(); /* avoid rq from going away on us */ __task_rq_unlock(rq); + + balance_callback(rq); + preempt_enable(); } #endif @@ -3441,7 +3717,7 @@ static bool dl_param_changed(struct task_struct *p, static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, - bool user) + bool user, bool pi) { int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : MAX_RT_PRIO - 1 - attr->sched_priority; @@ -3627,18 +3903,20 @@ change: p->sched_reset_on_fork = reset_on_fork; oldprio = p->prio; - /* - * Take priority boosted tasks into account. If the new - * effective priority is unchanged, we just store the new - * normal parameters and do not touch the scheduler class and - * the runqueue. This will be done when the task deboost - * itself. - */ - new_effective_prio = rt_mutex_get_effective_prio(p, newprio); - if (new_effective_prio == oldprio) { - __setscheduler_params(p, attr); - task_rq_unlock(rq, p, &flags); - return 0; + if (pi) { + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + new_effective_prio = rt_mutex_get_effective_prio(p, newprio); + if (new_effective_prio == oldprio) { + __setscheduler_params(p, attr); + task_rq_unlock(rq, p, &flags); + return 0; + } } queued = task_on_rq_queued(p); @@ -3649,7 +3927,7 @@ change: put_prev_task(rq, p); prev_class = p->sched_class; - __setscheduler(rq, p, attr, true); + __setscheduler(rq, p, attr, pi); if (running) p->sched_class->set_curr_task(rq); @@ -3662,9 +3940,17 @@ change: } check_class_changed(rq, p, prev_class, oldprio); + preempt_disable(); /* avoid rq from going away on us */ task_rq_unlock(rq, p, &flags); - rt_mutex_adjust_pi(p); + if (pi) + rt_mutex_adjust_pi(p); + + /* + * Run balance callbacks after we've adjusted the PI chain. + */ + balance_callback(rq); + preempt_enable(); return 0; } @@ -3685,7 +3971,7 @@ static int _sched_setscheduler(struct task_struct *p, int policy, attr.sched_policy = policy; } - return __sched_setscheduler(p, &attr, check); + return __sched_setscheduler(p, &attr, check, true); } /** * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. @@ -3706,7 +3992,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); int sched_setattr(struct task_struct *p, const struct sched_attr *attr) { - return __sched_setscheduler(p, attr, true); + return __sched_setscheduler(p, attr, true, true); } EXPORT_SYMBOL_GPL(sched_setattr); @@ -4108,7 +4394,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) } #endif again: - retval = set_cpus_allowed_ptr(p, new_mask); + retval = __set_cpus_allowed_ptr(p, new_mask, true); if (!retval) { cpuset_cpus_allowed(p, cpus_allowed); @@ -4260,7 +4546,7 @@ SYSCALL_DEFINE0(sched_yield) int __sched _cond_resched(void) { - if (should_resched()) { + if (should_resched(0)) { preempt_schedule_common(); return 1; } @@ -4278,7 +4564,7 @@ EXPORT_SYMBOL(_cond_resched); */ int __cond_resched_lock(spinlock_t *lock) { - int resched = should_resched(); + int resched = should_resched(PREEMPT_LOCK_OFFSET); int ret = 0; lockdep_assert_held(lock); @@ -4300,7 +4586,7 @@ int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); - if (should_resched()) { + if (should_resched(SOFTIRQ_DISABLE_OFFSET)) { local_bh_enable(); preempt_schedule_common(); local_bh_disable(); @@ -4633,7 +4919,8 @@ void init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - raw_spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&idle->pi_lock, flags); + raw_spin_lock(&rq->lock); __sched_fork(0, idle); idle->state = TASK_RUNNING; @@ -4659,7 +4946,8 @@ void init_idle(struct task_struct *idle, int cpu) #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif - raw_spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&idle->pi_lock, flags); /* Set the preempt count _outside_ the spinlocks! */ init_idle_preempt_count(idle, cpu); @@ -4754,149 +5042,6 @@ out: } #ifdef CONFIG_SMP -/* - * move_queued_task - move a queued task to new rq. - * - * Returns (locked) new rq. Old rq's lock is released. - */ -static struct rq *move_queued_task(struct task_struct *p, int new_cpu) -{ - struct rq *rq = task_rq(p); - - lockdep_assert_held(&rq->lock); - - dequeue_task(rq, p, 0); - p->on_rq = TASK_ON_RQ_MIGRATING; - set_task_cpu(p, new_cpu); - raw_spin_unlock(&rq->lock); - - rq = cpu_rq(new_cpu); - - raw_spin_lock(&rq->lock); - BUG_ON(task_cpu(p) != new_cpu); - p->on_rq = TASK_ON_RQ_QUEUED; - enqueue_task(rq, p, 0); - check_preempt_curr(rq, p, 0); - - return rq; -} - -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) -{ - if (p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - - cpumask_copy(&p->cpus_allowed, new_mask); - p->nr_cpus_allowed = cpumask_weight(new_mask); -} - -/* - * This is how migration works: - * - * 1) we invoke migration_cpu_stop() on the target CPU using - * stop_one_cpu(). - * 2) stopper starts to run (implicitly forcing the migrated thread - * off the CPU) - * 3) it checks whether the migrated task is still in the wrong runqueue. - * 4) if it's in the wrong runqueue then the migration thread removes - * it and puts it into the right queue. - * 5) stopper completes and stop_one_cpu() returns and the migration - * is done. - */ - -/* - * Change a given task's CPU affinity. Migrate the thread to a - * proper CPU and schedule it away if the CPU it's executing on - * is removed from the allowed bitmask. - * - * NOTE: the caller must have a valid reference to the task, the - * task must not exit() & deallocate itself prematurely. The - * call is not atomic; no spinlocks may be held. - */ -int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) -{ - unsigned long flags; - struct rq *rq; - unsigned int dest_cpu; - int ret = 0; - - rq = task_rq_lock(p, &flags); - - if (cpumask_equal(&p->cpus_allowed, new_mask)) - goto out; - - if (!cpumask_intersects(new_mask, cpu_active_mask)) { - ret = -EINVAL; - goto out; - } - - do_set_cpus_allowed(p, new_mask); - - /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) - goto out; - - dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (task_running(rq, p) || p->state == TASK_WAKING) { - struct migration_arg arg = { p, dest_cpu }; - /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, p, &flags); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); - tlb_migrate_finish(p->mm); - return 0; - } else if (task_on_rq_queued(p)) - rq = move_queued_task(p, dest_cpu); -out: - task_rq_unlock(rq, p, &flags); - - return ret; -} -EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); - -/* - * Move (not current) task off this cpu, onto dest cpu. We're doing - * this because either it can't run here any more (set_cpus_allowed() - * away from this CPU, or CPU going down), or because we're - * attempting to rebalance this task on exec (sched_exec). - * - * So we race with normal scheduler movements, but that's OK, as long - * as the task is no longer on this CPU. - * - * Returns non-zero if task was successfully migrated. - */ -static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) -{ - struct rq *rq; - int ret = 0; - - if (unlikely(!cpu_active(dest_cpu))) - return ret; - - rq = cpu_rq(src_cpu); - - raw_spin_lock(&p->pi_lock); - raw_spin_lock(&rq->lock); - /* Already moved. */ - if (task_cpu(p) != src_cpu) - goto done; - - /* Affinity changed (again). */ - if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) - goto fail; - - /* - * If we're not on a rq, the next wake-up will ensure we're - * placed properly. - */ - if (task_on_rq_queued(p)) - rq = move_queued_task(p, dest_cpu); -done: - ret = 1; -fail: - raw_spin_unlock(&rq->lock); - raw_spin_unlock(&p->pi_lock); - return ret; -} #ifdef CONFIG_NUMA_BALANCING /* Migrate current task p to target_cpu */ @@ -4944,35 +5089,9 @@ void sched_setnuma(struct task_struct *p, int nid) enqueue_task(rq, p, 0); task_rq_unlock(rq, p, &flags); } -#endif - -/* - * migration_cpu_stop - this will be executed by a highprio stopper thread - * and performs thread migration by bumping thread off CPU then - * 'pushing' onto another runqueue. - */ -static int migration_cpu_stop(void *data) -{ - struct migration_arg *arg = data; - - /* - * The original target cpu might have gone down and we might - * be on another cpu but it doesn't matter. - */ - local_irq_disable(); - /* - * We need to explicitly wake pending tasks before running - * __migrate_task() such that we will not miss enforcing cpus_allowed - * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. - */ - sched_ttwu_pending(); - __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); - local_irq_enable(); - return 0; -} +#endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_HOTPLUG_CPU - /* * Ensures that the idle task is using init_mm right before its cpu goes * offline. @@ -5028,9 +5147,9 @@ static struct task_struct fake_task = { * there's no concurrency possible, we hold the required locks anyway * because of lock validation efforts. */ -static void migrate_tasks(unsigned int dead_cpu) +static void migrate_tasks(struct rq *dead_rq) { - struct rq *rq = cpu_rq(dead_cpu); + struct rq *rq = dead_rq; struct task_struct *next, *stop = rq->stop; int dest_cpu; @@ -5052,7 +5171,7 @@ static void migrate_tasks(unsigned int dead_cpu) */ update_rq_clock(rq); - for ( ; ; ) { + for (;;) { /* * There's this thread running, bail when that's the only * remaining thread. @@ -5060,22 +5179,29 @@ static void migrate_tasks(unsigned int dead_cpu) if (rq->nr_running == 1) break; + /* + * Ensure rq->lock covers the entire task selection + * until the migration. + */ + lockdep_pin_lock(&rq->lock); next = pick_next_task(rq, &fake_task); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); /* Find suitable destination for @next, with force if needed. */ - dest_cpu = select_fallback_rq(dead_cpu, next); - raw_spin_unlock(&rq->lock); - - __migrate_task(next, dead_cpu, dest_cpu); - - raw_spin_lock(&rq->lock); + dest_cpu = select_fallback_rq(dead_rq->cpu, next); + + lockdep_unpin_lock(&rq->lock); + rq = __migrate_task(rq, next, dest_cpu); + if (rq != dead_rq) { + raw_spin_unlock(&rq->lock); + rq = dead_rq; + raw_spin_lock(&rq->lock); + } } rq->stop = stop; } - #endif /* CONFIG_HOTPLUG_CPU */ #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) @@ -5241,8 +5367,7 @@ static void register_sched_domain_sysctl(void) /* may be called multiple times per register */ static void unregister_sched_domain_sysctl(void) { - if (sd_sysctl_header) - unregister_sysctl_table(sd_sysctl_header); + unregister_sysctl_table(sd_sysctl_header); sd_sysctl_header = NULL; if (sd_ctl_dir[0].child) sd_free_ctl_entry(&sd_ctl_dir[0].child); @@ -5254,7 +5379,7 @@ static void register_sched_domain_sysctl(void) static void unregister_sched_domain_sysctl(void) { } -#endif +#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */ static void set_rq_online(struct rq *rq) { @@ -5323,7 +5448,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } - migrate_tasks(cpu); + migrate_tasks(rq); BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); break; @@ -5363,6 +5488,14 @@ static int sched_cpu_active(struct notifier_block *nfb, case CPU_STARTING: set_cpu_rq_start_time(); return NOTIFY_OK; + case CPU_ONLINE: + /* + * At this point a starting CPU has marked itself as online via + * set_cpu_online(). But it might not yet have marked itself + * as active, which is essential from here on. + * + * Thus, fall-through and help the starting CPU along. + */ case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5401,9 +5534,6 @@ static int __init migration_init(void) return 0; } early_initcall(migration_init); -#endif - -#ifdef CONFIG_SMP static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ @@ -6378,8 +6508,10 @@ static void init_numa_topology_type(void) n = sched_max_numa_distance; - if (n <= 1) + if (sched_domains_numa_levels <= 1) { sched_numa_topology_type = NUMA_DIRECT; + return; + } for_each_online_node(a) { for_each_online_node(b) { @@ -6629,7 +6761,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map) struct sched_group *sg; struct sched_group_capacity *sgc; - sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); if (!sd) return -ENOMEM; @@ -7235,7 +7367,7 @@ void __init sched_init(void) rq->sd = NULL; rq->rd = NULL; rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; - rq->post_schedule = 0; + rq->balance_callback = NULL; rq->active_balance = 0; rq->next_balance = jiffies; rq->push_cpu = 0; @@ -7365,32 +7497,12 @@ EXPORT_SYMBOL(___might_sleep); #endif #ifdef CONFIG_MAGIC_SYSRQ -static void normalize_task(struct rq *rq, struct task_struct *p) +void normalize_rt_tasks(void) { - const struct sched_class *prev_class = p->sched_class; + struct task_struct *g, *p; struct sched_attr attr = { .sched_policy = SCHED_NORMAL, }; - int old_prio = p->prio; - int queued; - - queued = task_on_rq_queued(p); - if (queued) - dequeue_task(rq, p, 0); - __setscheduler(rq, p, &attr, false); - if (queued) { - enqueue_task(rq, p, 0); - resched_curr(rq); - } - - check_class_changed(rq, p, prev_class, old_prio); -} - -void normalize_rt_tasks(void) -{ - struct task_struct *g, *p; - unsigned long flags; - struct rq *rq; read_lock(&tasklist_lock); for_each_process_thread(g, p) { @@ -7417,9 +7529,7 @@ void normalize_rt_tasks(void) continue; } - rq = task_rq_lock(p, &flags); - normalize_task(rq, p); - task_rq_unlock(rq, p, &flags); + __sched_setscheduler(p, &attr, false, false); } read_unlock(&tasklist_lock); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index f5a64ffad176..8cbc3db671df 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -555,48 +555,43 @@ drop_precision: } /* - * Atomically advance counter to the new value. Interrupts, vcpu - * scheduling, and scaling inaccuracies can cause cputime_advance - * to be occasionally called with a new value smaller than counter. - * Let's enforce atomicity. + * Adjust tick based cputime random precision against scheduler runtime + * accounting. * - * Normally a caller will only go through this loop once, or not - * at all in case a previous caller updated counter the same jiffy. - */ -static void cputime_advance(cputime_t *counter, cputime_t new) -{ - cputime_t old; - - while (new > (old = READ_ONCE(*counter))) - cmpxchg_cputime(counter, old, new); -} - -/* - * Adjust tick based cputime random precision against scheduler - * runtime accounting. + * Tick based cputime accounting depend on random scheduling timeslices of a + * task to be interrupted or not by the timer. Depending on these + * circumstances, the number of these interrupts may be over or + * under-optimistic, matching the real user and system cputime with a variable + * precision. + * + * Fix this by scaling these tick based values against the total runtime + * accounted by the CFS scheduler. + * + * This code provides the following guarantees: + * + * stime + utime == rtime + * stime_i+1 >= stime_i, utime_i+1 >= utime_i + * + * Assuming that rtime_i+1 >= rtime_i. */ static void cputime_adjust(struct task_cputime *curr, - struct cputime *prev, + struct prev_cputime *prev, cputime_t *ut, cputime_t *st) { cputime_t rtime, stime, utime; + unsigned long flags; - /* - * Tick based cputime accounting depend on random scheduling - * timeslices of a task to be interrupted or not by the timer. - * Depending on these circumstances, the number of these interrupts - * may be over or under-optimistic, matching the real user and system - * cputime with a variable precision. - * - * Fix this by scaling these tick based values against the total - * runtime accounted by the CFS scheduler. - */ + /* Serialize concurrent callers such that we can honour our guarantees */ + raw_spin_lock_irqsave(&prev->lock, flags); rtime = nsecs_to_cputime(curr->sum_exec_runtime); /* - * Update userspace visible utime/stime values only if actual execution - * time is bigger than already exported. Note that can happen, that we - * provided bigger values due to scaling inaccuracy on big numbers. + * This is possible under two circumstances: + * - rtime isn't monotonic after all (a bug); + * - we got reordered by the lock. + * + * In both cases this acts as a filter such that the rest of the code + * can assume it is monotonic regardless of anything else. */ if (prev->stime + prev->utime >= rtime) goto out; @@ -606,22 +601,46 @@ static void cputime_adjust(struct task_cputime *curr, if (utime == 0) { stime = rtime; - } else if (stime == 0) { - utime = rtime; - } else { - cputime_t total = stime + utime; + goto update; + } - stime = scale_stime((__force u64)stime, - (__force u64)rtime, (__force u64)total); - utime = rtime - stime; + if (stime == 0) { + utime = rtime; + goto update; } - cputime_advance(&prev->stime, stime); - cputime_advance(&prev->utime, utime); + stime = scale_stime((__force u64)stime, (__force u64)rtime, + (__force u64)(stime + utime)); + + /* + * Make sure stime doesn't go backwards; this preserves monotonicity + * for utime because rtime is monotonic. + * + * utime_i+1 = rtime_i+1 - stime_i + * = rtime_i+1 - (rtime_i - utime_i) + * = (rtime_i+1 - rtime_i) + utime_i + * >= utime_i + */ + if (stime < prev->stime) + stime = prev->stime; + utime = rtime - stime; + + /* + * Make sure utime doesn't go backwards; this still preserves + * monotonicity for stime, analogous argument to above. + */ + if (utime < prev->utime) { + utime = prev->utime; + stime = rtime - utime; + } +update: + prev->stime = stime; + prev->utime = utime; out: *ut = prev->utime; *st = prev->stime; + raw_spin_unlock_irqrestore(&prev->lock, flags); } void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index eac20c557a55..fc8f01083527 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -213,14 +213,28 @@ static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) return dl_task(prev); } -static inline void set_post_schedule(struct rq *rq) +static DEFINE_PER_CPU(struct callback_head, dl_push_head); +static DEFINE_PER_CPU(struct callback_head, dl_pull_head); + +static void push_dl_tasks(struct rq *); +static void pull_dl_task(struct rq *); + +static inline void queue_push_tasks(struct rq *rq) { - rq->post_schedule = has_pushable_dl_tasks(rq); + if (!has_pushable_dl_tasks(rq)) + return; + + queue_balance_callback(rq, &per_cpu(dl_push_head, rq->cpu), push_dl_tasks); +} + +static inline void queue_pull_task(struct rq *rq) +{ + queue_balance_callback(rq, &per_cpu(dl_pull_head, rq->cpu), pull_dl_task); } static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); -static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) +static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p) { struct rq *later_rq = NULL; bool fallback = false; @@ -254,14 +268,19 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) double_lock_balance(rq, later_rq); } + /* + * By now the task is replenished and enqueued; migrate it. + */ deactivate_task(rq, p, 0); set_task_cpu(p, later_rq->cpu); - activate_task(later_rq, p, ENQUEUE_REPLENISH); + activate_task(later_rq, p, 0); if (!fallback) resched_curr(later_rq); - double_unlock_balance(rq, later_rq); + double_unlock_balance(later_rq, rq); + + return later_rq; } #else @@ -291,12 +310,15 @@ static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) return false; } -static inline int pull_dl_task(struct rq *rq) +static inline void pull_dl_task(struct rq *rq) +{ +} + +static inline void queue_push_tasks(struct rq *rq) { - return 0; } -static inline void set_post_schedule(struct rq *rq) +static inline void queue_pull_task(struct rq *rq) { } #endif /* CONFIG_SMP */ @@ -498,22 +520,23 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, * actually started or not (i.e., the replenishment instant is in * the future or in the past). */ -static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) +static int start_dl_timer(struct task_struct *p) { - struct dl_rq *dl_rq = dl_rq_of_se(dl_se); - struct rq *rq = rq_of_dl_rq(dl_rq); + struct sched_dl_entity *dl_se = &p->dl; + struct hrtimer *timer = &dl_se->dl_timer; + struct rq *rq = task_rq(p); ktime_t now, act; s64 delta; - if (boosted) - return 0; + lockdep_assert_held(&rq->lock); + /* * We want the timer to fire at the deadline, but considering * that it is actually coming from rq->clock and not from * hrtimer's time base reading. */ act = ns_to_ktime(dl_se->deadline); - now = hrtimer_cb_get_time(&dl_se->dl_timer); + now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta); @@ -525,7 +548,19 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) if (ktime_us_delta(act, now) < 0) return 0; - hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS); + /* + * !enqueued will guarantee another callback; even if one is already in + * progress. This ensures a balanced {get,put}_task_struct(). + * + * The race against __run_timer() clearing the enqueued state is + * harmless because we're holding task_rq()->lock, therefore the timer + * expiring after we've done the check will wait on its task_rq_lock() + * and observe our state. + */ + if (!hrtimer_is_queued(timer)) { + get_task_struct(p); + hrtimer_start(timer, act, HRTIMER_MODE_ABS); + } return 1; } @@ -555,35 +590,40 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) rq = task_rq_lock(p, &flags); /* - * We need to take care of several possible races here: - * - * - the task might have changed its scheduling policy - * to something different than SCHED_DEADLINE - * - the task might have changed its reservation parameters - * (through sched_setattr()) - * - the task might have been boosted by someone else and - * might be in the boosting/deboosting path + * The task might have changed its scheduling policy to something + * different than SCHED_DEADLINE (through switched_fromd_dl()). + */ + if (!dl_task(p)) { + __dl_clear_params(p); + goto unlock; + } + + /* + * This is possible if switched_from_dl() raced against a running + * callback that took the above !dl_task() path and we've since then + * switched back into SCHED_DEADLINE. * - * In all this cases we bail out, as the task is already - * in the runqueue or is going to be enqueued back anyway. + * There's nothing to do except drop our task reference. */ - if (!dl_task(p) || dl_se->dl_new || - dl_se->dl_boosted || !dl_se->dl_throttled) + if (dl_se->dl_new) goto unlock; - sched_clock_tick(); - update_rq_clock(rq); + /* + * The task might have been boosted by someone else and might be in the + * boosting/deboosting path, its not throttled. + */ + if (dl_se->dl_boosted) + goto unlock; -#ifdef CONFIG_SMP /* - * If we find that the rq the task was on is no longer - * available, we need to select a new rq. + * Spurious timer due to start_dl_timer() race; or we already received + * a replenishment from rt_mutex_setprio(). */ - if (unlikely(!rq->online)) { - dl_task_offline_migration(rq, p); + if (!dl_se->dl_throttled) goto unlock; - } -#endif + + sched_clock_tick(); + update_rq_clock(rq); /* * If the throttle happened during sched-out; like: @@ -609,17 +649,38 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) check_preempt_curr_dl(rq, p, 0); else resched_curr(rq); + #ifdef CONFIG_SMP /* - * Queueing this task back might have overloaded rq, - * check if we need to kick someone away. + * Perform balancing operations here; after the replenishments. We + * cannot drop rq->lock before this, otherwise the assertion in + * start_dl_timer() about not missing updates is not true. + * + * If we find that the rq the task was on is no longer available, we + * need to select a new rq. + * + * XXX figure out if select_task_rq_dl() deals with offline cpus. + */ + if (unlikely(!rq->online)) + rq = dl_task_offline_migration(rq, p); + + /* + * Queueing this task back might have overloaded rq, check if we need + * to kick someone away. */ if (has_pushable_dl_tasks(rq)) push_dl_task(rq); #endif + unlock: task_rq_unlock(rq, p, &flags); + /* + * This can free the task_struct, including this hrtimer, do not touch + * anything related to that after this. + */ + put_task_struct(p); + return HRTIMER_NORESTART; } @@ -679,7 +740,7 @@ static void update_curr_dl(struct rq *rq) if (dl_runtime_exceeded(dl_se)) { dl_se->dl_throttled = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted))) + if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -892,7 +953,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) /* * Use the scheduling parameters of the top pi-waiter - * task if we have one and its (relative) deadline is + * task if we have one and its (absolute) deadline is * smaller than our one... OTW we keep our runtime and * deadline. */ @@ -1036,8 +1097,6 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) resched_curr(rq); } -static int pull_dl_task(struct rq *this_rq); - #endif /* CONFIG_SMP */ /* @@ -1094,7 +1153,15 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) dl_rq = &rq->dl; if (need_pull_dl_task(rq, prev)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we're + * being very careful to re-start the picking loop. + */ + lockdep_unpin_lock(&rq->lock); pull_dl_task(rq); + lockdep_pin_lock(&rq->lock); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a stop task can slip in, in which case we need to @@ -1128,7 +1195,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) if (hrtick_enabled(rq)) start_hrtick_dl(rq, p); - set_post_schedule(rq); + queue_push_tasks(rq); return p; } @@ -1165,7 +1232,6 @@ static void task_fork_dl(struct task_struct *p) static void task_dead_dl(struct task_struct *p) { - struct hrtimer *timer = &p->dl.dl_timer; struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); /* @@ -1175,8 +1241,6 @@ static void task_dead_dl(struct task_struct *p) /* XXX we should retain the bw until 0-lag */ dl_b->total_bw -= p->dl.dl_bw; raw_spin_unlock_irq(&dl_b->lock); - - hrtimer_cancel(timer); } static void set_curr_task_dl(struct rq *rq) @@ -1499,20 +1563,21 @@ out: static void push_dl_tasks(struct rq *rq) { - /* Terminates as it moves a -deadline task */ + /* push_dl_task() will return true if it moved a -deadline task */ while (push_dl_task(rq)) ; } -static int pull_dl_task(struct rq *this_rq) +static void pull_dl_task(struct rq *this_rq) { - int this_cpu = this_rq->cpu, ret = 0, cpu; + int this_cpu = this_rq->cpu, cpu; struct task_struct *p; + bool resched = false; struct rq *src_rq; u64 dmin = LONG_MAX; if (likely(!dl_overloaded(this_rq))) - return 0; + return; /* * Match the barrier from dl_set_overloaded; this guarantees that if we @@ -1567,7 +1632,7 @@ static int pull_dl_task(struct rq *this_rq) src_rq->curr->dl.deadline)) goto skip; - ret = 1; + resched = true; deactivate_task(src_rq, p, 0); set_task_cpu(p, this_cpu); @@ -1580,12 +1645,8 @@ skip: double_unlock_balance(this_rq, src_rq); } - return ret; -} - -static void post_schedule_dl(struct rq *rq) -{ - push_dl_tasks(rq); + if (resched) + resched_curr(this_rq); } /* @@ -1596,7 +1657,6 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - has_pushable_dl_tasks(rq) && p->nr_cpus_allowed > 1 && dl_task(rq->curr) && (rq->curr->nr_cpus_allowed < 2 || @@ -1608,9 +1668,8 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) static void set_cpus_allowed_dl(struct task_struct *p, const struct cpumask *new_mask) { - struct rq *rq; struct root_domain *src_rd; - int weight; + struct rq *rq; BUG_ON(!dl_task(p)); @@ -1636,37 +1695,7 @@ static void set_cpus_allowed_dl(struct task_struct *p, raw_spin_unlock(&src_dl_b->lock); } - /* - * Update only if the task is actually running (i.e., - * it is on the rq AND it is not throttled). - */ - if (!on_dl_rq(&p->dl)) - return; - - weight = cpumask_weight(new_mask); - - /* - * Only update if the process changes its state from whether it - * can migrate or not. - */ - if ((p->nr_cpus_allowed > 1) == (weight > 1)) - return; - - /* - * The process used to be able to migrate OR it can now migrate - */ - if (weight <= 1) { - if (!task_current(rq, p)) - dequeue_pushable_dl_task(rq, p); - BUG_ON(!rq->dl.dl_nr_migratory); - rq->dl.dl_nr_migratory--; - } else { - if (!task_current(rq, p)) - enqueue_pushable_dl_task(rq, p); - rq->dl.dl_nr_migratory++; - } - - update_dl_migration(&rq->dl); + set_cpus_allowed_common(p, new_mask); } /* Assumes rq->lock is held */ @@ -1701,37 +1730,16 @@ void __init init_sched_dl_class(void) #endif /* CONFIG_SMP */ -/* - * Ensure p's dl_timer is cancelled. May drop rq->lock for a while. - */ -static void cancel_dl_timer(struct rq *rq, struct task_struct *p) -{ - struct hrtimer *dl_timer = &p->dl.dl_timer; - - /* Nobody will change task's class if pi_lock is held */ - lockdep_assert_held(&p->pi_lock); - - if (hrtimer_active(dl_timer)) { - int ret = hrtimer_try_to_cancel(dl_timer); - - if (unlikely(ret == -1)) { - /* - * Note, p may migrate OR new deadline tasks - * may appear in rq when we are unlocking it. - * A caller of us must be fine with that. - */ - raw_spin_unlock(&rq->lock); - hrtimer_cancel(dl_timer); - raw_spin_lock(&rq->lock); - } - } -} - static void switched_from_dl(struct rq *rq, struct task_struct *p) { - /* XXX we should retain the bw until 0-lag */ - cancel_dl_timer(rq, p); - __dl_clear_params(p); + /* + * Start the deadline timer; if we switch back to dl before this we'll + * continue consuming our current CBS slice. If we stay outside of + * SCHED_DEADLINE until the deadline passes, the timer will reset the + * task. + */ + if (!start_dl_timer(p)) + __dl_clear_params(p); /* * Since this might be the only -deadline task on the rq, @@ -1741,8 +1749,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (!task_on_rq_queued(p) || rq->dl.dl_nr_running) return; - if (pull_dl_task(rq)) - resched_curr(rq); + queue_pull_task(rq); } /* @@ -1751,21 +1758,16 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { - int check_resched = 1; - if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (p->nr_cpus_allowed > 1 && rq->dl.overloaded && - push_dl_task(rq) && rq != task_rq(p)) - /* Only reschedule if pushing failed */ - check_resched = 0; -#endif /* CONFIG_SMP */ - if (check_resched) { - if (dl_task(rq->curr)) - check_preempt_curr_dl(rq, p, 0); - else - resched_curr(rq); - } + if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) + queue_push_tasks(rq); +#else + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); +#endif } } @@ -1785,15 +1787,14 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, * or lowering its prio, so... */ if (!rq->dl.overloaded) - pull_dl_task(rq); + queue_pull_task(rq); /* * If we now have a earlier deadline task than p, * then reschedule, provided p is still on this * runqueue. */ - if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && - rq->curr == p) + if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline)) resched_curr(rq); #else /* @@ -1823,7 +1824,6 @@ const struct sched_class dl_sched_class = { .set_cpus_allowed = set_cpus_allowed_dl, .rq_online = rq_online_dl, .rq_offline = rq_offline_dl, - .post_schedule = post_schedule_dl, .task_woken = task_woken_dl, #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 315c68e015d9..641511771ae6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -68,13 +68,8 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group #define PN(F) \ SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) - if (!se) { - struct sched_avg *avg = &cpu_rq(cpu)->avg; - P(avg->runnable_avg_sum); - P(avg->avg_period); + if (!se) return; - } - PN(se->exec_start); PN(se->vruntime); @@ -93,12 +88,8 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group #endif P(se->load.weight); #ifdef CONFIG_SMP - P(se->avg.runnable_avg_sum); - P(se->avg.running_avg_sum); - P(se->avg.avg_period); - P(se->avg.load_avg_contrib); - P(se->avg.utilization_avg_contrib); - P(se->avg.decay_count); + P(se->avg.load_avg); + P(se->avg.util_avg); #endif #undef PN #undef P @@ -142,7 +133,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) 0LL, 0L); #endif #ifdef CONFIG_NUMA_BALANCING - SEQ_printf(m, " %d", task_node(p)); + SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); #endif #ifdef CONFIG_CGROUP_SCHED SEQ_printf(m, " %s", task_group_path(task_group(p))); @@ -214,21 +205,21 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %ld\n", "runnable_load_avg", + SEQ_printf(m, " .%-30s: %lu\n", "load_avg", + cfs_rq->avg.load_avg); + SEQ_printf(m, " .%-30s: %lu\n", "runnable_load_avg", cfs_rq->runnable_load_avg); - SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", - cfs_rq->blocked_load_avg); - SEQ_printf(m, " .%-30s: %ld\n", "utilization_load_avg", - cfs_rq->utilization_load_avg); + SEQ_printf(m, " .%-30s: %lu\n", "util_avg", + cfs_rq->avg.util_avg); + SEQ_printf(m, " .%-30s: %ld\n", "removed_load_avg", + atomic_long_read(&cfs_rq->removed_load_avg)); + SEQ_printf(m, " .%-30s: %ld\n", "removed_util_avg", + atomic_long_read(&cfs_rq->removed_util_avg)); #ifdef CONFIG_FAIR_GROUP_SCHED - SEQ_printf(m, " .%-30s: %ld\n", "tg_load_contrib", - cfs_rq->tg_load_contrib); - SEQ_printf(m, " .%-30s: %d\n", "tg_runnable_contrib", - cfs_rq->tg_runnable_contrib); + SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib", + cfs_rq->tg_load_avg_contrib); SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg", atomic_long_read(&cfs_rq->tg->load_avg)); - SEQ_printf(m, " .%-30s: %d\n", "tg->runnable_avg", - atomic_read(&cfs_rq->tg->runnable_avg)); #endif #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -517,11 +508,21 @@ __initcall(init_sched_debug_procfs); SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) +#ifdef CONFIG_NUMA_BALANCING +void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, + unsigned long tpf, unsigned long gsf, unsigned long gpf) +{ + SEQ_printf(m, "numa_faults node=%d ", node); + SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf); + SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf); +} +#endif + + static void sched_show_numa(struct task_struct *p, struct seq_file *m) { #ifdef CONFIG_NUMA_BALANCING struct mempolicy *pol; - int node, i; if (p->mm) P(mm->numa_scan_seq); @@ -533,26 +534,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m) mpol_get(pol); task_unlock(p); - SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0)); - - for_each_online_node(node) { - for (i = 0; i < 2; i++) { - unsigned long nr_faults = -1; - int cpu_current, home_node; - - if (p->numa_faults) - nr_faults = p->numa_faults[2*node + i]; - - cpu_current = !i ? (task_node(p) == node) : - (pol && node_isset(node, pol->v.nodes)); - - home_node = (p->numa_preferred_nid == node); - - SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", - i, node, cpu_current, home_node, nr_faults); - } - } - + P(numa_pages_migrated); + P(numa_preferred_nid); + P(total_numa_faults); + SEQ_printf(m, "current_node=%d, numa_group_id=%d\n", + task_node(p), task_numa_group_id(p)); + show_numa_stats(p, m); mpol_put(pol); #endif } @@ -640,12 +627,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.load.weight); #ifdef CONFIG_SMP - P(se.avg.runnable_avg_sum); - P(se.avg.running_avg_sum); - P(se.avg.avg_period); - P(se.avg.load_avg_contrib); - P(se.avg.utilization_avg_contrib); - P(se.avg.decay_count); + P(se.avg.load_sum); + P(se.avg.util_sum); + P(se.avg.load_avg); + P(se.avg.util_avg); + P(se.avg.last_update_time); #endif P(policy); P(prio); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40a7fcbf491e..6e2e3483b1ec 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -283,9 +283,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return grp->my_q; } -static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, - int force_update); - static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { if (!cfs_rq->on_list) { @@ -305,8 +302,6 @@ static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) } cfs_rq->on_list = 1; - /* We should have no load, but we need to update last_decay. */ - update_cfs_rq_blocked_load(cfs_rq, 0); } } @@ -616,15 +611,10 @@ static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) */ static u64 __sched_period(unsigned long nr_running) { - u64 period = sysctl_sched_latency; - unsigned long nr_latency = sched_nr_latency; - - if (unlikely(nr_running > nr_latency)) { - period = sysctl_sched_min_granularity; - period *= nr_running; - } - - return period; + if (unlikely(nr_running > sched_nr_latency)) + return nr_running * sysctl_sched_min_granularity; + else + return sysctl_sched_latency; } /* @@ -669,22 +659,37 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) static int select_idle_sibling(struct task_struct *p, int cpu); static unsigned long task_h_load(struct task_struct *p); -static inline void __update_task_entity_contrib(struct sched_entity *se); -static inline void __update_task_entity_utilization(struct sched_entity *se); +/* + * We choose a half-life close to 1 scheduling period. + * Note: The tables below are dependent on this value. + */ +#define LOAD_AVG_PERIOD 32 +#define LOAD_AVG_MAX 47742 /* maximum possible load avg */ +#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */ -/* Give new task start runnable values to heavy its load in infant time */ -void init_task_runnable_average(struct task_struct *p) +/* Give new sched_entity start runnable values to heavy its load in infant time */ +void init_entity_runnable_average(struct sched_entity *se) { - u32 slice; + struct sched_avg *sa = &se->avg; - slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; - p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice; - p->se.avg.avg_period = slice; - __update_task_entity_contrib(&p->se); - __update_task_entity_utilization(&p->se); + sa->last_update_time = 0; + /* + * sched_avg's period_contrib should be strictly less then 1024, so + * we give it 1023 to make sure it is almost a period (1024us), and + * will definitely be update (after enqueue). + */ + sa->period_contrib = 1023; + sa->load_avg = scale_load_down(se->load.weight); + sa->load_sum = sa->load_avg * LOAD_AVG_MAX; + sa->util_avg = scale_load_down(SCHED_LOAD_SCALE); + sa->util_sum = LOAD_AVG_MAX; + /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } + +static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); +static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else -void init_task_runnable_average(struct task_struct *p) +void init_entity_runnable_average(struct sched_entity *se) { } #endif @@ -1415,8 +1420,9 @@ static bool numa_has_capacity(struct task_numa_env *env) * --------------------- vs --------------------- * src->compute_capacity dst->compute_capacity */ - if (src->load * dst->compute_capacity > - dst->load * src->compute_capacity) + if (src->load * dst->compute_capacity * env->imbalance_pct > + + dst->load * src->compute_capacity * 100) return true; return false; @@ -1702,8 +1708,8 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) delta = runtime - p->last_sum_exec_runtime; *period = now - p->last_task_numa_placement; } else { - delta = p->se.avg.runnable_avg_sum; - *period = p->se.avg.avg_period; + delta = p->se.avg.load_sum / p->se.load.weight; + *period = LOAD_AVG_MAX; } p->last_sum_exec_runtime = runtime; @@ -2351,13 +2357,13 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) long tg_weight; /* - * Use this CPU's actual weight instead of the last load_contribution - * to gain a more accurate current total weight. See - * update_cfs_rq_load_contribution(). + * Use this CPU's real-time load instead of the last load contribution + * as the updating of the contribution is delayed, and we will use the + * the real-time load to calc the share. See update_tg_load_avg(). */ tg_weight = atomic_long_read(&tg->load_avg); - tg_weight -= cfs_rq->tg_load_contrib; - tg_weight += cfs_rq->load.weight; + tg_weight -= cfs_rq->tg_load_avg_contrib; + tg_weight += cfs_rq_load_avg(cfs_rq); return tg_weight; } @@ -2367,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) long tg_weight, load, shares; tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq->load.weight; + load = cfs_rq_load_avg(cfs_rq); shares = (tg->shares * load); if (tg_weight) @@ -2429,14 +2435,6 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq) #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_SMP -/* - * We choose a half-life close to 1 scheduling period. - * Note: The tables below are dependent on this value. - */ -#define LOAD_AVG_PERIOD 32 -#define LOAD_AVG_MAX 47742 /* maximum possible load avg */ -#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */ - /* Precomputed fixed inverse multiplies for multiplication by y^n */ static const u32 runnable_avg_yN_inv[] = { 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, @@ -2485,9 +2483,8 @@ static __always_inline u64 decay_load(u64 val, u64 n) local_n %= LOAD_AVG_PERIOD; } - val *= runnable_avg_yN_inv[local_n]; - /* We don't use SRR here since we always want to round down. */ - return val >> 32; + val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); + return val; } /* @@ -2546,23 +2543,22 @@ static u32 __compute_runnable_contrib(u64 n) * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] */ -static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, - struct sched_avg *sa, - int runnable, - int running) +static __always_inline int +__update_load_avg(u64 now, int cpu, struct sched_avg *sa, + unsigned long weight, int running, struct cfs_rq *cfs_rq) { u64 delta, periods; - u32 runnable_contrib; + u32 contrib; int delta_w, decayed = 0; unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); - delta = now - sa->last_runnable_update; + delta = now - sa->last_update_time; /* * This should only happen when time goes backwards, which it * unfortunately does during sched clock init when we swap over to TSC. */ if ((s64)delta < 0) { - sa->last_runnable_update = now; + sa->last_update_time = now; return 0; } @@ -2573,26 +2569,29 @@ static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, delta >>= 10; if (!delta) return 0; - sa->last_runnable_update = now; + sa->last_update_time = now; /* delta_w is the amount already accumulated against our next period */ - delta_w = sa->avg_period % 1024; + delta_w = sa->period_contrib; if (delta + delta_w >= 1024) { - /* period roll-over */ decayed = 1; + /* how much left for next period will start over, we don't know yet */ + sa->period_contrib = 0; + /* * Now that we know we're crossing a period boundary, figure * out how much from delta we need to complete the current * period and accrue it. */ delta_w = 1024 - delta_w; - if (runnable) - sa->runnable_avg_sum += delta_w; + if (weight) { + sa->load_sum += weight * delta_w; + if (cfs_rq) + cfs_rq->runnable_load_sum += weight * delta_w; + } if (running) - sa->running_avg_sum += delta_w * scale_freq - >> SCHED_CAPACITY_SHIFT; - sa->avg_period += delta_w; + sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT; delta -= delta_w; @@ -2600,341 +2599,186 @@ static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, periods = delta / 1024; delta %= 1024; - sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, - periods + 1); - sa->running_avg_sum = decay_load(sa->running_avg_sum, - periods + 1); - sa->avg_period = decay_load(sa->avg_period, - periods + 1); + sa->load_sum = decay_load(sa->load_sum, periods + 1); + if (cfs_rq) { + cfs_rq->runnable_load_sum = + decay_load(cfs_rq->runnable_load_sum, periods + 1); + } + sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1); /* Efficiently calculate \sum (1..n_period) 1024*y^i */ - runnable_contrib = __compute_runnable_contrib(periods); - if (runnable) - sa->runnable_avg_sum += runnable_contrib; + contrib = __compute_runnable_contrib(periods); + if (weight) { + sa->load_sum += weight * contrib; + if (cfs_rq) + cfs_rq->runnable_load_sum += weight * contrib; + } if (running) - sa->running_avg_sum += runnable_contrib * scale_freq - >> SCHED_CAPACITY_SHIFT; - sa->avg_period += runnable_contrib; + sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT; } /* Remainder of delta accrued against u_0` */ - if (runnable) - sa->runnable_avg_sum += delta; + if (weight) { + sa->load_sum += weight * delta; + if (cfs_rq) + cfs_rq->runnable_load_sum += weight * delta; + } if (running) - sa->running_avg_sum += delta * scale_freq - >> SCHED_CAPACITY_SHIFT; - sa->avg_period += delta; + sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT; - return decayed; -} - -/* Synchronize an entity's decay with its parenting cfs_rq.*/ -static inline u64 __synchronize_entity_decay(struct sched_entity *se) -{ - struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 decays = atomic64_read(&cfs_rq->decay_counter); + sa->period_contrib += delta; - decays -= se->avg.decay_count; - se->avg.decay_count = 0; - if (!decays) - return 0; - - se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); - se->avg.utilization_avg_contrib = - decay_load(se->avg.utilization_avg_contrib, decays); + if (decayed) { + sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX); + if (cfs_rq) { + cfs_rq->runnable_load_avg = + div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX); + } + sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX; + } - return decays; + return decayed; } #ifdef CONFIG_FAIR_GROUP_SCHED -static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, - int force_update) -{ - struct task_group *tg = cfs_rq->tg; - long tg_contrib; - - tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; - tg_contrib -= cfs_rq->tg_load_contrib; - - if (!tg_contrib) - return; - - if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) { - atomic_long_add(tg_contrib, &tg->load_avg); - cfs_rq->tg_load_contrib += tg_contrib; - } -} - /* - * Aggregate cfs_rq runnable averages into an equivalent task_group - * representation for computing load contributions. + * Updating tg's load_avg is necessary before update_cfs_share (which is done) + * and effective_load (which is not done because it is too costly). */ -static inline void __update_tg_runnable_avg(struct sched_avg *sa, - struct cfs_rq *cfs_rq) +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) { - struct task_group *tg = cfs_rq->tg; - long contrib; - - /* The fraction of a cpu used by this cfs_rq */ - contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, - sa->avg_period + 1); - contrib -= cfs_rq->tg_runnable_contrib; + long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib; - if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { - atomic_add(contrib, &tg->runnable_avg); - cfs_rq->tg_runnable_contrib += contrib; + if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { + atomic_long_add(delta, &cfs_rq->tg->load_avg); + cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg; } } -static inline void __update_group_entity_contrib(struct sched_entity *se) -{ - struct cfs_rq *cfs_rq = group_cfs_rq(se); - struct task_group *tg = cfs_rq->tg; - int runnable_avg; - - u64 contrib; - - contrib = cfs_rq->tg_load_contrib * tg->shares; - se->avg.load_avg_contrib = div_u64(contrib, - atomic_long_read(&tg->load_avg) + 1); - - /* - * For group entities we need to compute a correction term in the case - * that they are consuming <1 cpu so that we would contribute the same - * load as a task of equal weight. - * - * Explicitly co-ordinating this measurement would be expensive, but - * fortunately the sum of each cpus contribution forms a usable - * lower-bound on the true value. - * - * Consider the aggregate of 2 contributions. Either they are disjoint - * (and the sum represents true value) or they are disjoint and we are - * understating by the aggregate of their overlap. - * - * Extending this to N cpus, for a given overlap, the maximum amount we - * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of - * cpus that overlap for this interval and w_i is the interval width. - * - * On a small machine; the first term is well-bounded which bounds the - * total error since w_i is a subset of the period. Whereas on a - * larger machine, while this first term can be larger, if w_i is the - * of consequential size guaranteed to see n_i*w_i quickly converge to - * our upper bound of 1-cpu. - */ - runnable_avg = atomic_read(&tg->runnable_avg); - if (runnable_avg < NICE_0_LOAD) { - se->avg.load_avg_contrib *= runnable_avg; - se->avg.load_avg_contrib >>= NICE_0_SHIFT; - } -} - -static inline void update_rq_runnable_avg(struct rq *rq, int runnable) -{ - __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg, - runnable, runnable); - __update_tg_runnable_avg(&rq->avg, &rq->cfs); -} #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, - int force_update) {} -static inline void __update_tg_runnable_avg(struct sched_avg *sa, - struct cfs_rq *cfs_rq) {} -static inline void __update_group_entity_contrib(struct sched_entity *se) {} -static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} #endif /* CONFIG_FAIR_GROUP_SCHED */ -static inline void __update_task_entity_contrib(struct sched_entity *se) -{ - u32 contrib; - - /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ - contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); - contrib /= (se->avg.avg_period + 1); - se->avg.load_avg_contrib = scale_load(contrib); -} +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); -/* Compute the current contribution to load_avg by se, return any delta */ -static long __update_entity_load_avg_contrib(struct sched_entity *se) +/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ +static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { - long old_contrib = se->avg.load_avg_contrib; + int decayed; + struct sched_avg *sa = &cfs_rq->avg; - if (entity_is_task(se)) { - __update_task_entity_contrib(se); - } else { - __update_tg_runnable_avg(&se->avg, group_cfs_rq(se)); - __update_group_entity_contrib(se); + if (atomic_long_read(&cfs_rq->removed_load_avg)) { + long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); + sa->load_avg = max_t(long, sa->load_avg - r, 0); + sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); } - return se->avg.load_avg_contrib - old_contrib; -} - - -static inline void __update_task_entity_utilization(struct sched_entity *se) -{ - u32 contrib; - - /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ - contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE); - contrib /= (se->avg.avg_period + 1); - se->avg.utilization_avg_contrib = scale_load(contrib); -} - -static long __update_entity_utilization_avg_contrib(struct sched_entity *se) -{ - long old_contrib = se->avg.utilization_avg_contrib; + if (atomic_long_read(&cfs_rq->removed_util_avg)) { + long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0); + sa->util_avg = max_t(long, sa->util_avg - r, 0); + sa->util_sum = max_t(s32, sa->util_sum - + ((r * LOAD_AVG_MAX) >> SCHED_LOAD_SHIFT), 0); + } - if (entity_is_task(se)) - __update_task_entity_utilization(se); - else - se->avg.utilization_avg_contrib = - group_cfs_rq(se)->utilization_load_avg; + decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, + scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq); - return se->avg.utilization_avg_contrib - old_contrib; -} +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->load_last_update_time_copy = sa->last_update_time; +#endif -static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq, - long load_contrib) -{ - if (likely(load_contrib < cfs_rq->blocked_load_avg)) - cfs_rq->blocked_load_avg -= load_contrib; - else - cfs_rq->blocked_load_avg = 0; + return decayed; } -static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); - -/* Update a sched_entity's runnable average */ -static inline void update_entity_load_avg(struct sched_entity *se, - int update_cfs_rq) +/* Update task and its cfs_rq load average */ +static inline void update_load_avg(struct sched_entity *se, int update_tg) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - long contrib_delta, utilization_delta; int cpu = cpu_of(rq_of(cfs_rq)); - u64 now; + u64 now = cfs_rq_clock_task(cfs_rq); /* - * For a group entity we need to use their owned cfs_rq_clock_task() in - * case they are the parent of a throttled hierarchy. + * Track task load average for carrying it to new CPU after migrated, and + * track group sched_entity load average for task_h_load calc in migration */ - if (entity_is_task(se)) - now = cfs_rq_clock_task(cfs_rq); - else - now = cfs_rq_clock_task(group_cfs_rq(se)); + __update_load_avg(now, cpu, &se->avg, + se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); - if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq, - cfs_rq->curr == se)) - return; - - contrib_delta = __update_entity_load_avg_contrib(se); - utilization_delta = __update_entity_utilization_avg_contrib(se); - - if (!update_cfs_rq) - return; - - if (se->on_rq) { - cfs_rq->runnable_load_avg += contrib_delta; - cfs_rq->utilization_load_avg += utilization_delta; - } else { - subtract_blocked_load_contrib(cfs_rq, -contrib_delta); - } + if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg) + update_tg_load_avg(cfs_rq, 0); } -/* - * Decay the load contributed by all blocked children and account this so that - * their contribution may appropriately discounted when they wake up. - */ -static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) +/* Add the load generated by se into cfs_rq's load average */ +static inline void +enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u64 now = cfs_rq_clock_task(cfs_rq) >> 20; - u64 decays; - - decays = now - cfs_rq->last_decay; - if (!decays && !force_update) - return; + struct sched_avg *sa = &se->avg; + u64 now = cfs_rq_clock_task(cfs_rq); + int migrated = 0, decayed; - if (atomic_long_read(&cfs_rq->removed_load)) { - unsigned long removed_load; - removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0); - subtract_blocked_load_contrib(cfs_rq, removed_load); + if (sa->last_update_time == 0) { + sa->last_update_time = now; + migrated = 1; + } + else { + __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, + se->on_rq * scale_load_down(se->load.weight), + cfs_rq->curr == se, NULL); } - if (decays) { - cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg, - decays); - atomic64_add(decays, &cfs_rq->decay_counter); - cfs_rq->last_decay = now; + decayed = update_cfs_rq_load_avg(now, cfs_rq); + + cfs_rq->runnable_load_avg += sa->load_avg; + cfs_rq->runnable_load_sum += sa->load_sum; + + if (migrated) { + cfs_rq->avg.load_avg += sa->load_avg; + cfs_rq->avg.load_sum += sa->load_sum; + cfs_rq->avg.util_avg += sa->util_avg; + cfs_rq->avg.util_sum += sa->util_sum; } - __update_cfs_rq_tg_load_contrib(cfs_rq, force_update); + if (decayed || migrated) + update_tg_load_avg(cfs_rq, 0); } -/* Add the load generated by se into cfs_rq's child load-average */ -static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, - struct sched_entity *se, - int wakeup) +/* Remove the runnable load generated by se from cfs_rq's runnable load average */ +static inline void +dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - /* - * We track migrations using entity decay_count <= 0, on a wake-up - * migration we use a negative decay count to track the remote decays - * accumulated while sleeping. - * - * Newly forked tasks are enqueued with se->avg.decay_count == 0, they - * are seen by enqueue_entity_load_avg() as a migration with an already - * constructed load_avg_contrib. - */ - if (unlikely(se->avg.decay_count <= 0)) { - se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq)); - if (se->avg.decay_count) { - /* - * In a wake-up migration we have to approximate the - * time sleeping. This is because we can't synchronize - * clock_task between the two cpus, and it is not - * guaranteed to be read-safe. Instead, we can - * approximate this using our carried decays, which are - * explicitly atomically readable. - */ - se->avg.last_runnable_update -= (-se->avg.decay_count) - << 20; - update_entity_load_avg(se, 0); - /* Indicate that we're now synchronized and on-rq */ - se->avg.decay_count = 0; - } - wakeup = 0; - } else { - __synchronize_entity_decay(se); - } + update_load_avg(se, 1); - /* migrated tasks did not contribute to our blocked load */ - if (wakeup) { - subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); - update_entity_load_avg(se, 0); - } - - cfs_rq->runnable_load_avg += se->avg.load_avg_contrib; - cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib; - /* we force update consideration on load-balancer moves */ - update_cfs_rq_blocked_load(cfs_rq, !wakeup); + cfs_rq->runnable_load_avg = + max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0); + cfs_rq->runnable_load_sum = + max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0); } /* - * Remove se's load from this cfs_rq child load-average, if the entity is - * transitioning to a blocked state we track its projected decay using - * blocked_load_avg. + * Task first catches up with cfs_rq, and then subtract + * itself from the cfs_rq (task must be off the queue now). */ -static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, - struct sched_entity *se, - int sleep) +void remove_entity_load_avg(struct sched_entity *se) { - update_entity_load_avg(se, 1); - /* we force update consideration on load-balancer moves */ - update_cfs_rq_blocked_load(cfs_rq, !sleep); + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 last_update_time; - cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib; - cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib; - if (sleep) { - cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; - se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); - } /* migrations, e.g. sleep=0 leave decay_count == 0 */ +#ifndef CONFIG_64BIT + u64 last_update_time_copy; + + do { + last_update_time_copy = cfs_rq->load_last_update_time_copy; + smp_rmb(); + last_update_time = cfs_rq->avg.last_update_time; + } while (last_update_time != last_update_time_copy); +#else + last_update_time = cfs_rq->avg.last_update_time; +#endif + + __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL); + atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg); + atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg); } /* @@ -2944,7 +2788,6 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, */ void idle_enter_fair(struct rq *this_rq) { - update_rq_runnable_avg(this_rq, 1); } /* @@ -2954,24 +2797,28 @@ void idle_enter_fair(struct rq *this_rq) */ void idle_exit_fair(struct rq *this_rq) { - update_rq_runnable_avg(this_rq, 0); +} + +static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq) +{ + return cfs_rq->runnable_load_avg; +} + +static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) +{ + return cfs_rq->avg.load_avg; } static int idle_balance(struct rq *this_rq); #else /* CONFIG_SMP */ -static inline void update_entity_load_avg(struct sched_entity *se, - int update_cfs_rq) {} -static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} -static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, - struct sched_entity *se, - int wakeup) {} -static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, - struct sched_entity *se, - int sleep) {} -static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, - int force_update) {} +static inline void update_load_avg(struct sched_entity *se, int update_tg) {} +static inline void +enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} +static inline void +dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} +static inline void remove_entity_load_avg(struct sched_entity *se) {} static inline int idle_balance(struct rq *rq) { @@ -3103,7 +2950,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); - enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP); + enqueue_entity_load_avg(cfs_rq, se); account_entity_enqueue(cfs_rq, se); update_cfs_shares(cfs_rq); @@ -3178,7 +3025,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); - dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP); + dequeue_entity_load_avg(cfs_rq, se); update_stats_dequeue(cfs_rq, se); if (flags & DEQUEUE_SLEEP) { @@ -3268,7 +3115,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); - update_entity_load_avg(se, 1); + update_load_avg(se, 1); } update_stats_curr_start(cfs_rq, se); @@ -3368,7 +3215,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ - update_entity_load_avg(prev, 1); + update_load_avg(prev, 0); } cfs_rq->curr = NULL; } @@ -3384,8 +3231,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) /* * Ensure that runnable average is periodically updated. */ - update_entity_load_avg(curr, 1); - update_cfs_rq_blocked_load(cfs_rq, 1); + update_load_avg(curr, 1); update_cfs_shares(cfs_rq); #ifdef CONFIG_SCHED_HRTICK @@ -3683,7 +3529,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); - empty = list_empty(&cfs_rq->throttled_list); + empty = list_empty(&cfs_b->throttled_cfs_rq); /* * Add to the _head_ of the list, so that an already-started @@ -4258,14 +4104,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; + update_load_avg(se, 1); update_cfs_shares(cfs_rq); - update_entity_load_avg(se, 1); } - if (!se) { - update_rq_runnable_avg(rq, rq->nr_running); + if (!se) add_nr_running(rq, 1); - } + hrtick_update(rq); } @@ -4319,14 +4164,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; + update_load_avg(se, 1); update_cfs_shares(cfs_rq); - update_entity_load_avg(se, 1); } - if (!se) { + if (!se) sub_nr_running(rq, 1); - update_rq_runnable_avg(rq, 1); - } + hrtick_update(rq); } @@ -4439,6 +4283,12 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, sched_avg_update(this_rq); } +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cfs_rq_runnable_load_avg(&cpu_rq(cpu)->cfs); +} + #ifdef CONFIG_NO_HZ_COMMON /* * There is no sane way to deal with nohz on smp when using jiffies because the @@ -4460,7 +4310,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, static void update_idle_cpu_load(struct rq *this_rq) { unsigned long curr_jiffies = READ_ONCE(jiffies); - unsigned long load = this_rq->cfs.runnable_load_avg; + unsigned long load = weighted_cpuload(cpu_of(this_rq)); unsigned long pending_updates; /* @@ -4506,7 +4356,7 @@ void update_cpu_load_nohz(void) */ void update_cpu_load_active(struct rq *this_rq) { - unsigned long load = this_rq->cfs.runnable_load_avg; + unsigned long load = weighted_cpuload(cpu_of(this_rq)); /* * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). */ @@ -4514,12 +4364,6 @@ void update_cpu_load_active(struct rq *this_rq) __update_cpu_load(this_rq, load, 1); } -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(const int cpu) -{ - return cpu_rq(cpu)->cfs.runnable_load_avg; -} - /* * Return a low guess at the load of a migration-source cpu weighted * according to the scheduling class and "nice" value. @@ -4567,7 +4411,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running); - unsigned long load_avg = rq->cfs.runnable_load_avg; + unsigned long load_avg = weighted_cpuload(cpu); if (nr_running) return load_avg / nr_running; @@ -4686,7 +4530,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) /* * w = rw_i + @wl */ - w = se->my_q->load.weight + wl; + w = cfs_rq_load_avg(se->my_q) + wl; /* * wl = S * s'_i; see (2) @@ -4707,7 +4551,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) /* * wl = dw_i = S * (s'_i - s_i); see (3) */ - wl -= se->load.weight; + wl -= se->avg.load_avg; /* * Recursively apply this logic to all parent groups to compute @@ -4730,26 +4574,29 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) #endif +/* + * Detect M:N waker/wakee relationships via a switching-frequency heuristic. + * A waker of many should wake a different task than the one last awakened + * at a frequency roughly N times higher than one of its wakees. In order + * to determine whether we should let the load spread vs consolodating to + * shared cache, we look for a minimum 'flip' frequency of llc_size in one + * partner, and a factor of lls_size higher frequency in the other. With + * both conditions met, we can be relatively sure that the relationship is + * non-monogamous, with partner count exceeding socket size. Waker/wakee + * being client/server, worker/dispatcher, interrupt source or whatever is + * irrelevant, spread criteria is apparent partner count exceeds socket size. + */ static int wake_wide(struct task_struct *p) { + unsigned int master = current->wakee_flips; + unsigned int slave = p->wakee_flips; int factor = this_cpu_read(sd_llc_size); - /* - * Yeah, it's the switching-frequency, could means many wakee or - * rapidly switch, use factor here will just help to automatically - * adjust the loose-degree, so bigger node will lead to more pull. - */ - if (p->wakee_flips > factor) { - /* - * wakee is somewhat hot, it needs certain amount of cpu - * resource, so if waker is far more hot, prefer to leave - * it alone. - */ - if (current->wakee_flips > (factor * p->wakee_flips)) - return 1; - } - - return 0; + if (master < slave) + swap(master, slave); + if (slave < factor || master < slave * factor) + return 0; + return 1; } static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) @@ -4761,13 +4608,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) unsigned long weight; int balanced; - /* - * If we wake multiple tasks be careful to not bounce - * ourselves around too much. - */ - if (wake_wide(p)) - return 0; - idx = sd->wake_idx; this_cpu = smp_processor_id(); prev_cpu = task_cpu(p); @@ -4781,14 +4621,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) */ if (sync) { tg = task_group(current); - weight = current->se.load.weight; + weight = current->se.avg.load_avg; this_load += effective_load(tg, this_cpu, -weight, -weight); load += effective_load(tg, prev_cpu, 0, -weight); } tg = task_group(p); - weight = p->se.load.weight; + weight = p->se.avg.load_avg; /* * In low-load situations, where prev_cpu is idle and this_cpu is idle @@ -4981,12 +4821,12 @@ done: * tasks. The unit of the return value must be the one of capacity so we can * compare the usage with the capacity of the CPU that is available for CFS * task (ie cpu_capacity). - * cfs.utilization_load_avg is the sum of running time of runnable tasks on a + * cfs.avg.util_avg is the sum of running time of runnable tasks on a * CPU. It represents the amount of utilization of a CPU in the range * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full * capacity of the CPU because it's about the running time on this CPU. - * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE - * because of unfortunate rounding in avg_period and running_load_avg or just + * Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE + * because of unfortunate rounding in util_avg or just * after migrating tasks until the average stabilizes with the new running * time. So we need to check that the usage stays into the range * [0..cpu_capacity_orig] and cap if necessary. @@ -4995,7 +4835,7 @@ done: */ static int get_cpu_usage(int cpu) { - unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg; + unsigned long usage = cpu_rq(cpu)->cfs.avg.util_avg; unsigned long capacity = capacity_orig_of(cpu); if (usage >= SCHED_LOAD_SCALE) @@ -5021,17 +4861,17 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); - int new_cpu = cpu; + int new_cpu = prev_cpu; int want_affine = 0; int sync = wake_flags & WF_SYNC; if (sd_flag & SD_BALANCE_WAKE) - want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); rcu_read_lock(); for_each_domain(cpu, tmp) { if (!(tmp->flags & SD_LOAD_BALANCE)) - continue; + break; /* * If both cpu and prev_cpu are part of this domain, @@ -5045,17 +4885,21 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (tmp->flags & sd_flag) sd = tmp; + else if (!want_affine) + break; } - if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) - prev_cpu = cpu; - - if (sd_flag & SD_BALANCE_WAKE) { - new_cpu = select_idle_sibling(p, prev_cpu); - goto unlock; + if (affine_sd) { + sd = NULL; /* Prefer wake_affine over balance flags */ + if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + new_cpu = cpu; } - while (sd) { + if (!sd) { + if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ + new_cpu = select_idle_sibling(p, new_cpu); + + } else while (sd) { struct sched_group *group; int weight; @@ -5089,7 +4933,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } /* while loop will break here if sd == NULL */ } -unlock: rcu_read_unlock(); return new_cpu; @@ -5101,26 +4944,27 @@ unlock: * previous cpu. However, the caller only guarantees p->pi_lock is held; no * other assumptions, including the state of rq->lock, should be made. */ -static void -migrate_task_rq_fair(struct task_struct *p, int next_cpu) +static void migrate_task_rq_fair(struct task_struct *p, int next_cpu) { - struct sched_entity *se = &p->se; - struct cfs_rq *cfs_rq = cfs_rq_of(se); - /* - * Load tracking: accumulate removed load so that it can be processed - * when we next update owning cfs_rq under rq->lock. Tasks contribute - * to blocked load iff they have a positive decay-count. It can never - * be negative here since on-rq tasks have decay-count == 0. + * We are supposed to update the task to "current" time, then its up to date + * and ready to go to new CPU/cfs_rq. But we have difficulty in getting + * what current time is, so simply throw away the out-of-date time. This + * will result in the wakee task is less decayed, but giving the wakee more + * load sounds not bad. */ - if (se->avg.decay_count) { - se->avg.decay_count = -__synchronize_entity_decay(se); - atomic_long_add(se->avg.load_avg_contrib, - &cfs_rq->removed_load); - } + remove_entity_load_avg(&p->se); + + /* Tell new CPU we are migrated */ + p->se.avg.last_update_time = 0; /* We have migrated, no longer consider this task hot */ - se->exec_start = 0; + p->se.exec_start = 0; +} + +static void task_dead_fair(struct task_struct *p) +{ + remove_entity_load_avg(&p->se); } #endif /* CONFIG_SMP */ @@ -5392,7 +5236,15 @@ simple: return p; idle: + /* + * This is OK, because current is on_cpu, which avoids it being picked + * for load-balance and preemption/IRQs are still disabled avoiding + * further scheduler activity on it and we're being very careful to + * re-start the picking loop. + */ + lockdep_unpin_lock(&rq->lock); new_tasks = idle_balance(rq); + lockdep_pin_lock(&rq->lock); /* * Because idle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we @@ -5662,72 +5514,39 @@ static int task_hot(struct task_struct *p, struct lb_env *env) #ifdef CONFIG_NUMA_BALANCING /* - * Returns true if the destination node is the preferred node. - * Needs to match fbq_classify_rq(): if there is a runnable task - * that is not on its preferred node, we should identify it. + * Returns 1, if task migration degrades locality + * Returns 0, if task migration improves locality i.e migration preferred. + * Returns -1, if task migration is not affected by locality. */ -static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) +static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); unsigned long src_faults, dst_faults; int src_nid, dst_nid; - if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || - !(env->sd->flags & SD_NUMA)) { - return false; - } - - src_nid = cpu_to_node(env->src_cpu); - dst_nid = cpu_to_node(env->dst_cpu); - - if (src_nid == dst_nid) - return false; - - /* Encourage migration to the preferred node. */ - if (dst_nid == p->numa_preferred_nid) - return true; - - /* Migrating away from the preferred node is bad. */ - if (src_nid == p->numa_preferred_nid) - return false; - - if (numa_group) { - src_faults = group_faults(p, src_nid); - dst_faults = group_faults(p, dst_nid); - } else { - src_faults = task_faults(p, src_nid); - dst_faults = task_faults(p, dst_nid); - } - - return dst_faults > src_faults; -} - - -static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) -{ - struct numa_group *numa_group = rcu_dereference(p->numa_group); - unsigned long src_faults, dst_faults; - int src_nid, dst_nid; - - if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) - return false; - if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) - return false; + return -1; + + if (!sched_feat(NUMA)) + return -1; src_nid = cpu_to_node(env->src_cpu); dst_nid = cpu_to_node(env->dst_cpu); if (src_nid == dst_nid) - return false; + return -1; - /* Migrating away from the preferred node is bad. */ - if (src_nid == p->numa_preferred_nid) - return true; + /* Migrating away from the preferred node is always bad. */ + if (src_nid == p->numa_preferred_nid) { + if (env->src_rq->nr_running > env->src_rq->nr_preferred_running) + return 1; + else + return -1; + } /* Encourage migration to the preferred node. */ if (dst_nid == p->numa_preferred_nid) - return false; + return 0; if (numa_group) { src_faults = group_faults(p, src_nid); @@ -5741,16 +5560,10 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) } #else -static inline bool migrate_improves_locality(struct task_struct *p, - struct lb_env *env) -{ - return false; -} - -static inline bool migrate_degrades_locality(struct task_struct *p, +static inline int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { - return false; + return -1; } #endif @@ -5760,7 +5573,7 @@ static inline bool migrate_degrades_locality(struct task_struct *p, static int can_migrate_task(struct task_struct *p, struct lb_env *env) { - int tsk_cache_hot = 0; + int tsk_cache_hot; lockdep_assert_held(&env->src_rq->lock); @@ -5818,13 +5631,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 2) task is cache cold, or * 3) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, env); - if (!tsk_cache_hot) - tsk_cache_hot = migrate_degrades_locality(p, env); + tsk_cache_hot = migrate_degrades_locality(p, env); + if (tsk_cache_hot == -1) + tsk_cache_hot = task_hot(p, env); - if (migrate_improves_locality(p, env) || !tsk_cache_hot || + if (tsk_cache_hot <= 0 || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { - if (tsk_cache_hot) { + if (tsk_cache_hot == 1) { schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } @@ -5898,6 +5711,13 @@ static int detach_tasks(struct lb_env *env) return 0; while (!list_empty(tasks)) { + /* + * We don't want to steal all, otherwise we may be treated likewise, + * which could at worst lead to a livelock crash. + */ + if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) + break; + p = list_first_entry(tasks, struct task_struct, se.group_node); env->loop++; @@ -6007,39 +5827,6 @@ static void attach_tasks(struct lb_env *env) } #ifdef CONFIG_FAIR_GROUP_SCHED -/* - * update tg->load_weight by folding this cpu's load_avg - */ -static void __update_blocked_averages_cpu(struct task_group *tg, int cpu) -{ - struct sched_entity *se = tg->se[cpu]; - struct cfs_rq *cfs_rq = tg->cfs_rq[cpu]; - - /* throttled entities do not contribute to load */ - if (throttled_hierarchy(cfs_rq)) - return; - - update_cfs_rq_blocked_load(cfs_rq, 1); - - if (se) { - update_entity_load_avg(se, 1); - /* - * We pivot on our runnable average having decayed to zero for - * list removal. This generally implies that all our children - * have also been removed (modulo rounding error or bandwidth - * control); however, such cases are rare and we can fix these - * at enqueue. - * - * TODO: fix up out-of-order children on enqueue. - */ - if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running) - list_del_leaf_cfs_rq(cfs_rq); - } else { - struct rq *rq = rq_of(cfs_rq); - update_rq_runnable_avg(rq, rq->nr_running); - } -} - static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -6048,19 +5835,19 @@ static void update_blocked_averages(int cpu) raw_spin_lock_irqsave(&rq->lock, flags); update_rq_clock(rq); + /* * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ for_each_leaf_cfs_rq(rq, cfs_rq) { - /* - * Note: We may want to consider periodically releasing - * rq->lock about these updates so that creating many task - * groups does not result in continually extending hold time. - */ - __update_blocked_averages_cpu(cfs_rq->tg, rq->cpu); - } + /* throttled entities do not contribute to load */ + if (throttled_hierarchy(cfs_rq)) + continue; + if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq)) + update_tg_load_avg(cfs_rq, 0); + } raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -6088,14 +5875,14 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) } if (!se) { - cfs_rq->h_load = cfs_rq->runnable_load_avg; + cfs_rq->h_load = cfs_rq_load_avg(cfs_rq); cfs_rq->last_h_load_update = now; } while ((se = cfs_rq->h_load_next) != NULL) { load = cfs_rq->h_load; - load = div64_ul(load * se->avg.load_avg_contrib, - cfs_rq->runnable_load_avg + 1); + load = div64_ul(load * se->avg.load_avg, + cfs_rq_load_avg(cfs_rq) + 1); cfs_rq = group_cfs_rq(se); cfs_rq->h_load = load; cfs_rq->last_h_load_update = now; @@ -6107,17 +5894,25 @@ static unsigned long task_h_load(struct task_struct *p) struct cfs_rq *cfs_rq = task_cfs_rq(p); update_cfs_rq_h_load(cfs_rq); - return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load, - cfs_rq->runnable_load_avg + 1); + return div64_ul(p->se.avg.load_avg * cfs_rq->h_load, + cfs_rq_load_avg(cfs_rq) + 1); } #else static inline void update_blocked_averages(int cpu) { + struct rq *rq = cpu_rq(cpu); + struct cfs_rq *cfs_rq = &rq->cfs; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); + update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); } static unsigned long task_h_load(struct task_struct *p) { - return p->se.avg.load_avg_contrib; + return p->se.avg.load_avg; } #endif @@ -7426,9 +7221,6 @@ static int idle_balance(struct rq *this_rq) goto out; } - /* - * Drop the rq->lock, but keep IRQ/preempt disabled. - */ raw_spin_unlock(&this_rq->lock); update_blocked_averages(this_cpu); @@ -8020,8 +7812,6 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (numabalancing_enabled) task_tick_numa(rq, curr); - - update_rq_runnable_avg(rq, 1); } /* @@ -8120,15 +7910,18 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) } #ifdef CONFIG_SMP - /* - * Remove our load from contribution when we leave sched_fair - * and ensure we don't carry in an old decay_count if we - * switch back. - */ - if (se->avg.decay_count) { - __synchronize_entity_decay(se); - subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); - } + /* Catch up with the cfs_rq and remove our load when we leave */ + __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq), &se->avg, + se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); + + cfs_rq->avg.load_avg = + max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0); + cfs_rq->avg.load_sum = + max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0); + cfs_rq->avg.util_avg = + max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0); + cfs_rq->avg.util_sum = + max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0); #endif } @@ -8137,16 +7930,31 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) */ static void switched_to_fair(struct rq *rq, struct task_struct *p) { -#ifdef CONFIG_FAIR_GROUP_SCHED struct sched_entity *se = &p->se; + +#ifdef CONFIG_FAIR_GROUP_SCHED /* * Since the real-depth could have been changed (only FAIR * class maintain depth value), reset depth properly. */ se->depth = se->parent ? se->parent->depth + 1 : 0; #endif - if (!task_on_rq_queued(p)) + + if (!task_on_rq_queued(p)) { + + /* + * Ensure the task has a non-normalized vruntime when it is switched + * back to the fair class with !queued, so that enqueue_entity() at + * wake-up time will do the right thing. + * + * If it's queued, then the enqueue_entity(.flags=0) makes the task + * has non-normalized vruntime, if it's !queued, then it still has + * normalized vruntime. + */ + if (p->state != TASK_RUNNING) + se->vruntime += cfs_rq_of(se)->min_vruntime; return; + } /* * We were most likely switched from sched_rt, so @@ -8185,8 +7993,8 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; #endif #ifdef CONFIG_SMP - atomic64_set(&cfs_rq->decay_counter, 1); - atomic_long_set(&cfs_rq->removed_load, 0); + atomic_long_set(&cfs_rq->removed_load_avg, 0); + atomic_long_set(&cfs_rq->removed_util_avg, 0); #endif } @@ -8231,14 +8039,14 @@ static void task_move_group_fair(struct task_struct *p, int queued) if (!queued) { cfs_rq = cfs_rq_of(se); se->vruntime += cfs_rq->min_vruntime; + #ifdef CONFIG_SMP - /* - * migrate_task_rq_fair() will have removed our previous - * contribution, but we must synchronize for ongoing future - * decay. - */ - se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); - cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; + /* Virtually synchronize task with its new cfs_rq */ + p->se.avg.last_update_time = cfs_rq->avg.last_update_time; + cfs_rq->avg.load_avg += p->se.avg.load_avg; + cfs_rq->avg.load_sum += p->se.avg.load_sum; + cfs_rq->avg.util_avg += p->se.avg.util_avg; + cfs_rq->avg.util_sum += p->se.avg.util_sum; #endif } } @@ -8252,8 +8060,11 @@ void free_fair_sched_group(struct task_group *tg) for_each_possible_cpu(i) { if (tg->cfs_rq) kfree(tg->cfs_rq[i]); - if (tg->se) + if (tg->se) { + if (tg->se[i]) + remove_entity_load_avg(tg->se[i]); kfree(tg->se[i]); + } } kfree(tg->cfs_rq); @@ -8290,6 +8101,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); + init_entity_runnable_average(se); } return 1; @@ -8439,6 +8251,8 @@ const struct sched_class fair_sched_class = { .rq_offline = rq_offline_fair, .task_waking = task_waking_fair, + .task_dead = task_dead_fair, + .set_cpus_allowed = set_cpus_allowed_common, #endif .set_curr_task = set_curr_task_fair, @@ -8468,7 +8282,27 @@ void print_cfs_stats(struct seq_file *m, int cpu) print_cfs_rq(m, cpu, cfs_rq); rcu_read_unlock(); } -#endif + +#ifdef CONFIG_NUMA_BALANCING +void show_numa_stats(struct task_struct *p, struct seq_file *m) +{ + int node; + unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + + for_each_online_node(node) { + if (p->numa_faults) { + tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; + tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + if (p->numa_group) { + gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + print_numa_stats(m, node, tsf, tpf, gsf, gpf); + } +} +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ __init void init_sched_fair_class(void) { diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 91e33cd485f6..83a50e7ca533 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -79,20 +79,12 @@ SCHED_FEAT(LB_MIN, false) * numa_balancing= */ #ifdef CONFIG_NUMA_BALANCING -SCHED_FEAT(NUMA, false) /* - * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a - * higher number of hinting faults are recorded during active load - * balancing. + * NUMA will favor moving tasks towards nodes where a higher number of + * hinting faults are recorded during active load balancing. It will + * resist moving tasks towards nodes where a lower number of hinting + * faults have been recorded. */ -SCHED_FEAT(NUMA_FAVOUR_HIGHER, true) - -/* - * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a - * lower number of hinting faults have been recorded. As this has - * the potential to prevent a task ever migrating to a new node - * due to CPU overload it is disabled by default. - */ -SCHED_FEAT(NUMA_RESIST_LOWER, false) +SCHED_FEAT(NUMA, true) #endif diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index fefcb1fa5160..8f177c73ae19 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -15,6 +15,15 @@ #include "sched.h" +/** + * sched_idle_set_state - Record idle state for the current CPU. + * @idle_state: State to record. + */ +void sched_idle_set_state(struct cpuidle_state *idle_state) +{ + idle_set_state(this_rq(), idle_state); +} + static int __read_mostly cpu_idle_force_poll; void cpu_idle_poll_ctrl(bool enable) @@ -68,6 +77,49 @@ void __weak arch_cpu_idle(void) } /** + * default_idle_call - Default CPU idle routine. + * + * To use when the cpuidle framework cannot be used. + */ +void default_idle_call(void) +{ + if (current_clr_polling_and_test()) { + local_irq_enable(); + } else { + stop_critical_timings(); + arch_cpu_idle(); + start_critical_timings(); + } +} + +static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, + int next_state) +{ + /* Fall back to the default arch idle method on errors. */ + if (next_state < 0) { + default_idle_call(); + return next_state; + } + + /* + * The idle task must be scheduled, it is pointless to go to idle, just + * update no idle residency and return. + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + local_irq_enable(); + return -EBUSY; + } + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + return cpuidle_enter(drv, dev, next_state); +} + +/** * cpuidle_idle_call - the main idle function * * NOTE: no locks or semaphores should be used here @@ -81,7 +133,6 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - bool reflect; /* * Check if the idle task must be rescheduled. If it is the @@ -93,20 +144,16 @@ static void cpuidle_idle_call(void) } /* - * During the idle period, stop measuring the disabled irqs - * critical sections latencies - */ - stop_critical_timings(); - - /* * Tell the RCU framework we are entering an idle section, * so no more rcu read side critical sections and one more * step to the grace period */ rcu_idle_enter(); - if (cpuidle_not_available(drv, dev)) - goto use_default; + if (cpuidle_not_available(drv, dev)) { + default_idle_call(); + goto exit_idle; + } /* * Suspend-to-idle ("freeze") is a system state in which all user space @@ -124,52 +171,19 @@ static void cpuidle_idle_call(void) goto exit_idle; } - reflect = false; next_state = cpuidle_find_deepest_state(drv, dev); + call_cpuidle(drv, dev, next_state); } else { - reflect = true; /* * Ask the cpuidle framework to choose a convenient idle state. */ next_state = cpuidle_select(drv, dev); - } - /* Fall back to the default arch idle method on errors. */ - if (next_state < 0) - goto use_default; - - /* - * The idle task must be scheduled, it is pointless to - * go to idle, just update no idle residency and get - * out of this function - */ - if (current_clr_polling_and_test()) { - dev->last_residency = 0; - entered_state = next_state; - local_irq_enable(); - goto exit_idle; - } - - /* Take note of the planned idle state. */ - idle_set_state(this_rq(), &drv->states[next_state]); - - /* - * Enter the idle state previously returned by the governor decision. - * This function will block until an interrupt occurs and will take - * care of re-enabling the local interrupts - */ - entered_state = cpuidle_enter(drv, dev, next_state); - - /* The cpu is no longer idle or about to enter idle. */ - idle_set_state(this_rq(), NULL); - - if (entered_state == -EBUSY) - goto use_default; - - /* - * Give the governor an opportunity to reflect on the outcome - */ - if (reflect) + entered_state = call_cpuidle(drv, dev, next_state); + /* + * Give the governor an opportunity to reflect on the outcome + */ cpuidle_reflect(dev, entered_state); + } exit_idle: __current_set_polling(); @@ -181,20 +195,6 @@ exit_idle: local_irq_enable(); rcu_idle_exit(); - start_critical_timings(); - return; - -use_default: - /* - * We can't use the cpuidle framework, let's use the default - * idle routine. - */ - if (current_clr_polling_and_test()) - local_irq_enable(); - else - arch_cpu_idle(); - - goto exit_idle; } DEFINE_PER_CPU(bool, cpu_dead_idle); diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index c65dac8c97cd..c4ae0f1fdf9b 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -96,6 +96,7 @@ const struct sched_class idle_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, + .set_cpus_allowed = set_cpus_allowed_common, #endif .set_curr_task = set_curr_task_idle, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7d7093c51f8d..d2ea59364a1c 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -260,7 +260,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) #ifdef CONFIG_SMP -static int pull_rt_task(struct rq *this_rq); +static void pull_rt_task(struct rq *this_rq); static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) { @@ -354,13 +354,23 @@ static inline int has_pushable_tasks(struct rq *rq) return !plist_head_empty(&rq->rt.pushable_tasks); } -static inline void set_post_schedule(struct rq *rq) +static DEFINE_PER_CPU(struct callback_head, rt_push_head); +static DEFINE_PER_CPU(struct callback_head, rt_pull_head); + +static void push_rt_tasks(struct rq *); +static void pull_rt_task(struct rq *); + +static inline void queue_push_tasks(struct rq *rq) { - /* - * We detect this state here so that we can avoid taking the RQ - * lock again later if there is no need to push - */ - rq->post_schedule = has_pushable_tasks(rq); + if (!has_pushable_tasks(rq)) + return; + + queue_balance_callback(rq, &per_cpu(rt_push_head, rq->cpu), push_rt_tasks); +} + +static inline void queue_pull_task(struct rq *rq) +{ + queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task); } static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) @@ -412,12 +422,11 @@ static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) return false; } -static inline int pull_rt_task(struct rq *this_rq) +static inline void pull_rt_task(struct rq *this_rq) { - return 0; } -static inline void set_post_schedule(struct rq *rq) +static inline void queue_push_tasks(struct rq *rq) { } #endif /* CONFIG_SMP */ @@ -1469,7 +1478,15 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) struct rt_rq *rt_rq = &rq->rt; if (need_pull_rt_task(rq, prev)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we're + * being very careful to re-start the picking loop. + */ + lockdep_unpin_lock(&rq->lock); pull_rt_task(rq); + lockdep_pin_lock(&rq->lock); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a dl or stop task can slip in, in which case we need @@ -1497,7 +1514,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); - set_post_schedule(rq); + queue_push_tasks(rq); return p; } @@ -1952,14 +1969,15 @@ static void push_irq_work_func(struct irq_work *work) } #endif /* HAVE_RT_PUSH_IPI */ -static int pull_rt_task(struct rq *this_rq) +static void pull_rt_task(struct rq *this_rq) { - int this_cpu = this_rq->cpu, ret = 0, cpu; + int this_cpu = this_rq->cpu, cpu; + bool resched = false; struct task_struct *p; struct rq *src_rq; if (likely(!rt_overloaded(this_rq))) - return 0; + return; /* * Match the barrier from rt_set_overloaded; this guarantees that if we @@ -1970,7 +1988,7 @@ static int pull_rt_task(struct rq *this_rq) #ifdef HAVE_RT_PUSH_IPI if (sched_feat(RT_PUSH_IPI)) { tell_cpu_to_push(this_rq); - return 0; + return; } #endif @@ -2023,7 +2041,7 @@ static int pull_rt_task(struct rq *this_rq) if (p->prio < src_rq->curr->prio) goto skip; - ret = 1; + resched = true; deactivate_task(src_rq, p, 0); set_task_cpu(p, this_cpu); @@ -2039,12 +2057,8 @@ skip: double_unlock_balance(this_rq, src_rq); } - return ret; -} - -static void post_schedule_rt(struct rq *rq) -{ - push_rt_tasks(rq); + if (resched) + resched_curr(this_rq); } /* @@ -2055,7 +2069,6 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - has_pushable_tasks(rq) && p->nr_cpus_allowed > 1 && (dl_task(rq->curr) || rt_task(rq->curr)) && (rq->curr->nr_cpus_allowed < 2 || @@ -2063,45 +2076,6 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) push_rt_tasks(rq); } -static void set_cpus_allowed_rt(struct task_struct *p, - const struct cpumask *new_mask) -{ - struct rq *rq; - int weight; - - BUG_ON(!rt_task(p)); - - if (!task_on_rq_queued(p)) - return; - - weight = cpumask_weight(new_mask); - - /* - * Only update if the process changes its state from whether it - * can migrate or not. - */ - if ((p->nr_cpus_allowed > 1) == (weight > 1)) - return; - - rq = task_rq(p); - - /* - * The process used to be able to migrate OR it can now migrate - */ - if (weight <= 1) { - if (!task_current(rq, p)) - dequeue_pushable_task(rq, p); - BUG_ON(!rq->rt.rt_nr_migratory); - rq->rt.rt_nr_migratory--; - } else { - if (!task_current(rq, p)) - enqueue_pushable_task(rq, p); - rq->rt.rt_nr_migratory++; - } - - update_rt_migration(&rq->rt); -} - /* Assumes rq->lock is held */ static void rq_online_rt(struct rq *rq) { @@ -2140,8 +2114,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) if (!task_on_rq_queued(p) || rq->rt.rt_nr_running) return; - if (pull_rt_task(rq)) - resched_curr(rq); + queue_pull_task(rq); } void __init init_sched_rt_class(void) @@ -2162,8 +2135,6 @@ void __init init_sched_rt_class(void) */ static void switched_to_rt(struct rq *rq, struct task_struct *p) { - int check_resched = 1; - /* * If we are already running, then there's nothing * that needs to be done. But if we are not running @@ -2173,13 +2144,12 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && - /* Don't resched if we changed runqueues */ - push_rt_task(rq) && rq != task_rq(p)) - check_resched = 0; -#endif /* CONFIG_SMP */ - if (check_resched && p->prio < rq->curr->prio) + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) + queue_push_tasks(rq); +#else + if (p->prio < rq->curr->prio) resched_curr(rq); +#endif /* CONFIG_SMP */ } } @@ -2200,14 +2170,13 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) * may need to pull tasks to this runqueue. */ if (oldprio < p->prio) - pull_rt_task(rq); + queue_pull_task(rq); + /* * If there's a higher priority task waiting to run - * then reschedule. Note, the above pull_rt_task - * can release the rq lock and p could migrate. - * Only reschedule if p is still on the same runqueue. + * then reschedule. */ - if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) + if (p->prio > rq->rt.highest_prio.curr) resched_curr(rq); #else /* For UP simply resched on drop of prio */ @@ -2315,10 +2284,9 @@ const struct sched_class rt_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_rt, - .set_cpus_allowed = set_cpus_allowed_rt, + .set_cpus_allowed = set_cpus_allowed_common, .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, - .post_schedule = post_schedule_rt, .task_woken = task_woken_rt, .switched_from = switched_from_rt, #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index aea7c1f393cb..68cda117574c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -245,7 +245,6 @@ struct task_group { #ifdef CONFIG_SMP atomic_long_t load_avg; - atomic_t runnable_avg; #endif #endif @@ -366,27 +365,20 @@ struct cfs_rq { #ifdef CONFIG_SMP /* - * CFS Load tracking - * Under CFS, load is tracked on a per-entity basis and aggregated up. - * This allows for the description of both thread and group usage (in - * the FAIR_GROUP_SCHED case). - * runnable_load_avg is the sum of the load_avg_contrib of the - * sched_entities on the rq. - * blocked_load_avg is similar to runnable_load_avg except that its - * the blocked sched_entities on the rq. - * utilization_load_avg is the sum of the average running time of the - * sched_entities on the rq. + * CFS load tracking */ - unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg; - atomic64_t decay_counter; - u64 last_decay; - atomic_long_t removed_load; - + struct sched_avg avg; + u64 runnable_load_sum; + unsigned long runnable_load_avg; #ifdef CONFIG_FAIR_GROUP_SCHED - /* Required to track per-cpu representation of a task_group */ - u32 tg_runnable_contrib; - unsigned long tg_load_contrib; + unsigned long tg_load_avg_contrib; +#endif + atomic_long_t removed_load_avg, removed_util_avg; +#ifndef CONFIG_64BIT + u64 load_last_update_time_copy; +#endif +#ifdef CONFIG_FAIR_GROUP_SCHED /* * h_load = weight * f(tg) * @@ -595,8 +587,6 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; - - struct sched_avg avg; #endif /* CONFIG_FAIR_GROUP_SCHED */ /* @@ -624,9 +614,10 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; + struct callback_head *balance_callback; + unsigned char idle_balance; /* For active balancing */ - int post_schedule; int active_balance; int push_cpu; struct cpu_stop_work active_balance_work; @@ -767,6 +758,21 @@ extern int migrate_swap(struct task_struct *, struct task_struct *); #ifdef CONFIG_SMP +static inline void +queue_balance_callback(struct rq *rq, + struct callback_head *head, + void (*func)(struct rq *rq)) +{ + lockdep_assert_held(&rq->lock); + + if (unlikely(head->next)) + return; + + head->func = (void (*)(struct callback_head *))func; + head->next = rq->balance_callback; + rq->balance_callback = head; +} + extern void sched_ttwu_pending(void); #define rcu_dereference_check_sched_domain(p) \ @@ -1049,9 +1055,6 @@ static inline int task_on_rq_migrating(struct task_struct *p) #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 finish_arch_post_lock_switch # define finish_arch_post_lock_switch() do { } while (0) #endif @@ -1192,7 +1195,6 @@ struct sched_class { int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - void (*post_schedule) (struct rq *this_rq); void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); @@ -1253,6 +1255,8 @@ extern void trigger_load_balance(struct rq *rq); extern void idle_enter_fair(struct rq *this_rq); extern void idle_exit_fair(struct rq *this_rq); +extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask); + #else static inline void idle_enter_fair(struct rq *rq) { } @@ -1304,7 +1308,7 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se); unsigned long to_ratio(u64 period, u64 runtime); -extern void init_task_runnable_average(struct task_struct *p); +extern void init_entity_runnable_average(struct sched_entity *se); static inline void add_nr_running(struct rq *rq, unsigned count) { @@ -1423,8 +1427,10 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) for (;;) { rq = task_rq(p); raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + lockdep_pin_lock(&rq->lock); return rq; + } raw_spin_unlock(&rq->lock); while (unlikely(task_on_rq_migrating(p))) @@ -1461,8 +1467,10 @@ static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flag * If we observe the new cpu in task_rq_lock, the acquire will * pair with the WMB to ensure we must then also see migrating. */ - if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + lockdep_pin_lock(&rq->lock); return rq; + } raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, *flags); @@ -1474,6 +1482,7 @@ static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flag static inline void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { + lockdep_unpin_lock(&rq->lock); raw_spin_unlock(&rq->lock); } @@ -1482,6 +1491,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) __releases(rq->lock) __releases(p->pi_lock) { + lockdep_unpin_lock(&rq->lock); raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } @@ -1668,9 +1678,22 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); + +#ifdef CONFIG_SCHED_DEBUG extern void print_cfs_stats(struct seq_file *m, int cpu); extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); +extern void +print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); + +#ifdef CONFIG_NUMA_BALANCING +extern void +show_numa_stats(struct task_struct *p, struct seq_file *m); +extern void +print_numa_stats(struct seq_file *m, int node, unsigned long tsf, + unsigned long tpf, unsigned long gsf, unsigned long gpf); +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 077ebbd5e10f..b0fbc7632de5 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -47,7 +47,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) # define schedstat_set(var, val) do { } while (0) #endif -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { t->sched_info.last_queued = 0; @@ -156,7 +156,7 @@ sched_info_switch(struct rq *rq, #define sched_info_depart(rq, t) do { } while (0) #define sched_info_arrive(rq, next) do { } while (0) #define sched_info_switch(rq, t, next) do { } while (0) -#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +#endif /* CONFIG_SCHED_INFO */ /* * The following are functions that support scheduler-internal time accounting. diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 79ffec45a6ac..cbc67da10954 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -123,6 +123,7 @@ const struct sched_class stop_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_stop, + .set_cpus_allowed = set_cpus_allowed_common, #endif .set_curr_task = set_curr_task_stop, |