diff options
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 799 |
1 files changed, 455 insertions, 344 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d1f7149f8704..97ee9ac7e97c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -33,7 +33,7 @@ #include <linux/init.h> #include <linux/uaccess.h> #include <linux/highmem.h> -#include <asm/mmu_context.h> +#include <linux/mmu_context.h> #include <linux/interrupt.h> #include <linux/capability.h> #include <linux/completion.h> @@ -170,6 +170,71 @@ static struct rq *this_rq_lock(void) return rq; } +/* + * __task_rq_lock - lock the rq @p resides on. + */ +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + rf->cookie = lockdep_pin_lock(&rq->lock); + return rq; + } + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, rf->flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old cpu in task_rq_lock, the acquire of + * the old rq->lock will fully serialize against the stores. + * + * 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))) { + rf->cookie = lockdep_pin_lock(&rq->lock); + return rq; + } + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -249,29 +314,6 @@ void hrtick_start(struct rq *rq, u64 delay) } } -static int -hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int cpu = (int)(long)hcpu; - - switch (action) { - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - hrtick_clear(cpu_rq(cpu)); - return NOTIFY_OK; - } - - return NOTIFY_DONE; -} - -static __init void init_hrtick(void) -{ - hotcpu_notifier(hotplug_hrtick, 0); -} #else /* * Called to set the hrtick timer state. @@ -288,10 +330,6 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL_PINNED); } - -static inline void init_hrtick(void) -{ -} #endif /* CONFIG_SMP */ static void init_rq_hrtick(struct rq *rq) @@ -315,10 +353,6 @@ static inline void hrtick_clear(struct rq *rq) static inline void init_rq_hrtick(struct rq *rq) { } - -static inline void init_hrtick(void) -{ -} #endif /* CONFIG_SCHED_HRTICK */ /* @@ -400,7 +434,7 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * wakeup due to that. * * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_list(). + * barrier implied by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -499,7 +533,10 @@ int get_nohz_timer_target(void) rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { - if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) { + if (cpu == i) + continue; + + if (!idle_cpu(i) && is_housekeeping_cpu(i)) { cpu = i; goto unlock; } @@ -1085,12 +1122,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) static int __set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask, bool check) { - unsigned long flags; - struct rq *rq; + const struct cpumask *cpu_valid_mask = cpu_active_mask; unsigned int dest_cpu; + struct rq_flags rf; + struct rq *rq; int ret = 0; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); + + if (p->flags & PF_KTHREAD) { + /* + * Kernel threads are allowed on online && !active CPUs + */ + cpu_valid_mask = cpu_online_mask; + } /* * Must re-check here, to close a race against __kthread_bind(), @@ -1104,22 +1149,32 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (cpumask_equal(&p->cpus_allowed, new_mask)) goto out; - if (!cpumask_intersects(new_mask, cpu_active_mask)) { + if (!cpumask_intersects(new_mask, cpu_valid_mask)) { ret = -EINVAL; goto out; } do_set_cpus_allowed(p, new_mask); + if (p->flags & PF_KTHREAD) { + /* + * For kernel threads that do indeed end up on online && + * !active we want to ensure they are strict per-cpu threads. + */ + WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && + !cpumask_intersects(new_mask, cpu_active_mask) && + p->nr_cpus_allowed != 1); + } + /* 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); + dest_cpu = cpumask_any_and(cpu_valid_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); + task_rq_unlock(rq, p, &rf); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; @@ -1128,12 +1183,12 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, * OK, since we're going to drop the lock immediately * afterwards anyway. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf.cookie); rq = move_queued_task(rq, p, dest_cpu); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, rf.cookie); } out: - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return ret; } @@ -1317,8 +1372,8 @@ out: */ unsigned long wait_task_inactive(struct task_struct *p, long match_state) { - unsigned long flags; int running, queued; + struct rq_flags rf; unsigned long ncsw; struct rq *rq; @@ -1353,14 +1408,14 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * lock now, to be *sure*. If we're wrong, we'll * just go back and repeat. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); trace_sched_wait_task(p); running = task_running(rq, p); queued = task_on_rq_queued(p); ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); /* * If it changed from the expected state, bail out now. @@ -1434,6 +1489,25 @@ EXPORT_SYMBOL_GPL(kick_process); /* * ->cpus_allowed is protected by both rq->lock and p->pi_lock + * + * A few notes on cpu_active vs cpu_online: + * + * - cpu_active must be a subset of cpu_online + * + * - on cpu-up we allow per-cpu kthreads on the online && !active cpu, + * see __set_cpus_allowed_ptr(). At this point the newly online + * cpu isn't yet part of the sched domains, and balancing will not + * see it. + * + * - on cpu-down we clear cpu_active() to mask the sched domains and + * avoid the load balancer to place new tasks on the to be removed + * cpu. Existing tasks will remain running there and will be taken + * off. + * + * This means that fallback selection must not select !active CPUs. + * And can assume that any active CPU must be online. Conversely + * select_task_rq() below may allow selection of !active CPUs in order + * to satisfy the above rules. */ static int select_fallback_rq(int cpu, struct task_struct *p) { @@ -1452,8 +1526,6 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* Look for allowed, online CPU in same node. */ for_each_cpu(dest_cpu, nodemask) { - if (!cpu_online(dest_cpu)) - continue; if (!cpu_active(dest_cpu)) continue; if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) @@ -1464,9 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for (;;) { /* Any allowed, online CPU? */ for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { - if (!cpu_online(dest_cpu)) + if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu)) continue; - if (!cpu_active(dest_cpu)) + if (!cpu_online(dest_cpu)) continue; goto out; } @@ -1515,8 +1587,10 @@ 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) + if (tsk_nr_cpus_allowed(p) > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + else + cpu = cpumask_any(tsk_cpus_allowed(p)); /* * In order not to call set_task_cpu() on a blocking task we need @@ -1604,8 +1678,8 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl /* * Mark the task runnable and perform wakeup-preemption. */ -static void -ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, + struct pin_cookie cookie) { check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -1617,9 +1691,9 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) * 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); + lockdep_unpin_lock(&rq->lock, cookie); p->sched_class->task_woken(rq, p); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); } if (rq->idle_stamp) { @@ -1637,17 +1711,23 @@ 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) +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, + struct pin_cookie cookie) { + int en_flags = ENQUEUE_WAKEUP; + lockdep_assert_held(&rq->lock); #ifdef CONFIG_SMP if (p->sched_contributes_to_load) rq->nr_uninterruptible--; + + if (wake_flags & WF_MIGRATED) + en_flags |= ENQUEUE_MIGRATED; #endif - ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); - ttwu_do_wakeup(rq, p, wake_flags); + ttwu_activate(rq, p, en_flags); + ttwu_do_wakeup(rq, p, wake_flags, cookie); } /* @@ -1658,17 +1738,18 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) */ static int ttwu_remote(struct task_struct *p, int wake_flags) { + struct rq_flags rf; struct rq *rq; int ret = 0; - rq = __task_rq_lock(p); + rq = __task_rq_lock(p, &rf); if (task_on_rq_queued(p)) { /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags); + ttwu_do_wakeup(rq, p, wake_flags, rf.cookie); ret = 1; } - __task_rq_unlock(rq); + __task_rq_unlock(rq, &rf); return ret; } @@ -1678,6 +1759,7 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); + struct pin_cookie cookie; struct task_struct *p; unsigned long flags; @@ -1685,15 +1767,21 @@ void sched_ttwu_pending(void) return; raw_spin_lock_irqsave(&rq->lock, flags); - lockdep_pin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); while (llist) { + int wake_flags = 0; + p = llist_entry(llist, struct task_struct, wake_entry); llist = llist_next(llist); - ttwu_do_activate(rq, p, 0); + + if (p->sched_remote_wakeup) + wake_flags = WF_MIGRATED; + + ttwu_do_activate(rq, p, wake_flags, cookie); } - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1735,10 +1823,12 @@ void scheduler_ipi(void) irq_exit(); } -static void ttwu_queue_remote(struct task_struct *p, int cpu) +static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); + p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { if (!set_nr_if_polling(rq->idle)) smp_send_reschedule(cpu); @@ -1777,22 +1867,23 @@ bool cpus_share_cache(int this_cpu, int that_cpu) } #endif /* CONFIG_SMP */ -static void ttwu_queue(struct task_struct *p, int cpu) +static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); + struct pin_cookie cookie; #if defined(CONFIG_SMP) if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { sched_clock_cpu(cpu); /* sync clocks x-cpu */ - ttwu_queue_remote(p, cpu); + ttwu_queue_remote(p, cpu, wake_flags); return; } #endif raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); - ttwu_do_activate(rq, p, 0); - lockdep_unpin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); + ttwu_do_activate(rq, p, wake_flags, cookie); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); } @@ -1961,9 +2052,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; - if (p->sched_class->task_waking) - p->sched_class->task_waking(p); - cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; @@ -1971,7 +2059,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) } #endif /* CONFIG_SMP */ - ttwu_queue(p, cpu); + ttwu_queue(p, cpu, wake_flags); stat: if (schedstat_enabled()) ttwu_stat(p, cpu, wake_flags); @@ -1989,7 +2077,7 @@ out: * ensure that this_rq() is locked, @p is bound to this_rq() and not * the current task. */ -static void try_to_wake_up_local(struct task_struct *p) +static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie) { struct rq *rq = task_rq(p); @@ -2006,11 +2094,11 @@ static void try_to_wake_up_local(struct task_struct *p) * disabled avoiding further scheduler activity on it and we've * not yet picked a replacement task. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); raw_spin_lock(&p->pi_lock); raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, cookie); } if (!(p->state & TASK_NORMAL)) @@ -2021,7 +2109,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!task_on_rq_queued(p)) ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_do_wakeup(rq, p, 0); + ttwu_do_wakeup(rq, p, 0, cookie); if (schedstat_enabled()) ttwu_stat(p, smp_processor_id(), 0); out: @@ -2167,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +#ifdef CONFIG_SCHEDSTATS + DEFINE_STATIC_KEY_FALSE(sched_schedstats); +static bool __initdata __sched_schedstats = false; -#ifdef CONFIG_SCHEDSTATS static void set_schedstats(bool enabled) { if (enabled) @@ -2192,11 +2282,16 @@ static int __init setup_schedstats(char *str) if (!str) goto out; + /* + * This code is called before jump labels have been set up, so we can't + * change the static branch directly just yet. Instead set a temporary + * variable so init_schedstats() can do it later. + */ if (!strcmp(str, "enable")) { - set_schedstats(true); + __sched_schedstats = true; ret = 1; } else if (!strcmp(str, "disable")) { - set_schedstats(false); + __sched_schedstats = false; ret = 1; } out: @@ -2207,6 +2302,11 @@ out: } __setup("schedstats=", setup_schedstats); +static void __init init_schedstats(void) +{ + set_schedstats(__sched_schedstats); +} + #ifdef CONFIG_PROC_SYSCTL int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -2227,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write, set_schedstats(state); return err; } -#endif -#endif +#endif /* CONFIG_PROC_SYSCTL */ +#else /* !CONFIG_SCHEDSTATS */ +static inline void init_schedstats(void) {} +#endif /* CONFIG_SCHEDSTATS */ /* * fork()/clone()-time setup: @@ -2381,7 +2483,8 @@ static int dl_overflow(struct task_struct *p, int policy, u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; int cpus, err = -1; - if (new_bw == p->dl.dl_bw) + /* !deadline task may carry old deadline bandwidth */ + if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) return 0; /* @@ -2420,12 +2523,12 @@ extern void init_dl_bw(struct dl_bw *dl_b); */ void wake_up_new_task(struct task_struct *p) { - unsigned long flags; + struct rq_flags rf; struct rq *rq; - raw_spin_lock_irqsave(&p->pi_lock, flags); /* Initialize new task's runnable average */ init_entity_runnable_average(&p->se); + raw_spin_lock_irqsave(&p->pi_lock, rf.flags); #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: @@ -2434,8 +2537,9 @@ void wake_up_new_task(struct task_struct *p) */ set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif + rq = __task_rq_lock(p, &rf); + post_init_entity_util_avg(&p->se); - rq = __task_rq_lock(p); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); @@ -2446,12 +2550,12 @@ void wake_up_new_task(struct task_struct *p) * Nothing relies on rq->lock after this, so its fine to * drop it. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, rf.cookie); p->sched_class->task_woken(rq, p); - lockdep_pin_lock(&rq->lock); + lockdep_repin_lock(&rq->lock, rf.cookie); } #endif - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -2713,7 +2817,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, struct pin_cookie cookie) { struct mm_struct *mm, *oldmm; @@ -2733,7 +2837,7 @@ context_switch(struct rq *rq, struct task_struct *prev, atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else - switch_mm(oldmm, mm, next); + switch_mm_irqs_off(oldmm, mm, next); if (!prev->mm) { prev->active_mm = NULL; @@ -2745,7 +2849,7 @@ 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); + lockdep_unpin_lock(&rq->lock, cookie); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ @@ -2867,7 +2971,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_cpustat); */ unsigned long long task_sched_runtime(struct task_struct *p) { - unsigned long flags; + struct rq_flags rf; struct rq *rq; u64 ns; @@ -2887,7 +2991,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) return p->se.sum_exec_runtime; #endif - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * Must be ->curr _and_ ->on_rq. If dequeued, we would * project cycles that may never be accounted to this @@ -2898,7 +3002,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) p->sched_class->update_curr(rq); } ns = p->se.sum_exec_runtime; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return ns; } @@ -2918,7 +3022,7 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); - update_cpu_load_active(rq); + cpu_load_update_active(rq); calc_global_load_tick(rq); raw_spin_unlock(&rq->lock); @@ -2961,6 +3065,20 @@ u64 scheduler_tick_max_deferment(void) #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) +/* + * If the value passed in is equal to the current preempt count + * then we just disabled preemption. Start timing the latency. + */ +static inline void preempt_latency_start(int val) +{ + if (preempt_count() == val) { + unsigned long ip = get_lock_parent_ip(); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} void preempt_count_add(int val) { @@ -2979,17 +3097,21 @@ void preempt_count_add(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) { - unsigned long ip = get_lock_parent_ip(); -#ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = ip; -#endif - trace_preempt_off(CALLER_ADDR0, ip); - } + preempt_latency_start(val); } EXPORT_SYMBOL(preempt_count_add); NOKPROBE_SYMBOL(preempt_count_add); +/* + * If the value passed in equals to the current preempt count + * then we just enabled preemption. Stop timing the latency. + */ +static inline void preempt_latency_stop(int val) +{ + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); +} + void preempt_count_sub(int val) { #ifdef CONFIG_DEBUG_PREEMPT @@ -3006,13 +3128,15 @@ void preempt_count_sub(int val) return; #endif - if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + preempt_latency_stop(val); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); NOKPROBE_SYMBOL(preempt_count_sub); +#else +static inline void preempt_latency_start(int val) { } +static inline void preempt_latency_stop(int val) { } #endif /* @@ -3047,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev) static inline void schedule_debug(struct task_struct *prev) { #ifdef CONFIG_SCHED_STACK_END_CHECK - BUG_ON(task_stack_end_corrupted(prev)); + if (task_stack_end_corrupted(prev)) + panic("corrupted stack end detected inside scheduler\n"); #endif if (unlikely(in_atomic_preempt_off())) { @@ -3065,7 +3190,7 @@ static inline void schedule_debug(struct task_struct *prev) * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev) +pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) { const struct sched_class *class = &fair_sched_class; struct task_struct *p; @@ -3076,20 +3201,20 @@ pick_next_task(struct rq *rq, struct task_struct *prev) */ if (likely(prev->sched_class == class && rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq, prev); + p = fair_sched_class.pick_next_task(rq, prev, cookie); if (unlikely(p == RETRY_TASK)) goto again; /* assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) - p = idle_sched_class.pick_next_task(rq, prev); + p = idle_sched_class.pick_next_task(rq, prev, cookie); return p; } again: for_each_class(class) { - p = class->pick_next_task(rq, prev); + p = class->pick_next_task(rq, prev, cookie); if (p) { if (unlikely(p == RETRY_TASK)) goto again; @@ -3143,6 +3268,7 @@ static void __sched notrace __schedule(bool preempt) { struct task_struct *prev, *next; unsigned long *switch_count; + struct pin_cookie cookie; struct rq *rq; int cpu; @@ -3176,7 +3302,7 @@ static void __sched notrace __schedule(bool preempt) */ smp_mb__before_spinlock(); raw_spin_lock(&rq->lock); - lockdep_pin_lock(&rq->lock); + cookie = lockdep_pin_lock(&rq->lock); rq->clock_skip_update <<= 1; /* promote REQ to ACT */ @@ -3198,7 +3324,7 @@ static void __sched notrace __schedule(bool preempt) to_wakeup = wq_worker_sleeping(prev); if (to_wakeup) - try_to_wake_up_local(to_wakeup); + try_to_wake_up_local(to_wakeup, cookie); } } switch_count = &prev->nvcsw; @@ -3207,7 +3333,7 @@ static void __sched notrace __schedule(bool preempt) if (task_on_rq_queued(prev)) update_rq_clock(rq); - next = pick_next_task(rq, prev); + next = pick_next_task(rq, prev, cookie); clear_tsk_need_resched(prev); clear_preempt_need_resched(); rq->clock_skip_update = 0; @@ -3218,9 +3344,9 @@ static void __sched notrace __schedule(bool preempt) ++*switch_count; trace_sched_switch(preempt, prev, next); - rq = context_switch(rq, prev, next); /* unlocks the rq */ + rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */ } else { - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock_irq(&rq->lock); } @@ -3287,8 +3413,23 @@ void __sched schedule_preempt_disabled(void) static void __sched notrace preempt_schedule_common(void) { do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ preempt_disable_notrace(); + preempt_latency_start(1); __schedule(true); + preempt_latency_stop(1); preempt_enable_no_resched_notrace(); /* @@ -3340,7 +3481,21 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) return; do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ preempt_disable_notrace(); + preempt_latency_start(1); /* * Needs preempt disabled in case user_exit() is traced * and the tracer calls preempt_enable_notrace() causing @@ -3350,6 +3505,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) __schedule(true); exception_exit(prev_ctx); + preempt_latency_stop(1); preempt_enable_no_resched_notrace(); } while (need_resched()); } @@ -3406,12 +3562,13 @@ EXPORT_SYMBOL(default_wake_function); void rt_mutex_setprio(struct task_struct *p, int prio) { int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE; - struct rq *rq; const struct sched_class *prev_class; + struct rq_flags rf; + struct rq *rq; BUG_ON(prio > MAX_PRIO); - rq = __task_rq_lock(p); + rq = __task_rq_lock(p, &rf); /* * Idle task boosting is a nono in general. There is one @@ -3487,7 +3644,7 @@ 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); + __task_rq_unlock(rq, &rf); balance_callback(rq); preempt_enable(); @@ -3497,7 +3654,7 @@ out_unlock: void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, queued; - unsigned long flags; + struct rq_flags rf; struct rq *rq; if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) @@ -3506,7 +3663,7 @@ void set_user_nice(struct task_struct *p, long nice) * We have to be careful, if called from sys_setpriority(), * the task might be in the middle of scheduling on another CPU. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -3537,7 +3694,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_curr(rq); } out_unlock: - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } EXPORT_SYMBOL(set_user_nice); @@ -3834,11 +3991,11 @@ static int __sched_setscheduler(struct task_struct *p, MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, queued, running; int new_effective_prio, policy = attr->sched_policy; - unsigned long flags; const struct sched_class *prev_class; - struct rq *rq; + struct rq_flags rf; int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; + struct rq *rq; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -3933,13 +4090,13 @@ recheck: * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); /* * Changing the policy of the stop threads its a very bad idea */ if (p == rq->stop) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EINVAL; } @@ -3956,7 +4113,7 @@ recheck: goto change; p->sched_reset_on_fork = reset_on_fork; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return 0; } change: @@ -3970,7 +4127,7 @@ change: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EPERM; } #endif @@ -3985,7 +4142,7 @@ change: */ if (!cpumask_subset(span, &p->cpus_allowed) || rq->rd->dl_bw.bw == 0) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EPERM; } } @@ -3995,7 +4152,7 @@ change: /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); goto recheck; } @@ -4005,7 +4162,7 @@ change: * is available. */ if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); return -EBUSY; } @@ -4050,7 +4207,7 @@ change: check_class_changed(rq, p, prev_class, oldprio); preempt_disable(); /* avoid rq from going away on us */ - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); if (pi) rt_mutex_adjust_pi(p); @@ -4903,10 +5060,10 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, { struct task_struct *p; unsigned int time_slice; - unsigned long flags; + struct rq_flags rf; + struct timespec t; struct rq *rq; int retval; - struct timespec t; if (pid < 0) return -EINVAL; @@ -4921,11 +5078,11 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, if (retval) goto out_unlock; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); time_slice = 0; if (p->sched_class->get_rr_interval) time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); @@ -4992,16 +5149,19 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG - sysrq_sched_debug_show(); + if (!state_filter) + sysrq_sched_debug_show(); #endif rcu_read_unlock(); /* @@ -5163,6 +5323,8 @@ out: #ifdef CONFIG_SMP +static bool sched_smp_initialized __read_mostly; + #ifdef CONFIG_NUMA_BALANCING /* Migrate current task p to target_cpu */ int migrate_task_to(struct task_struct *p, int target_cpu) @@ -5188,11 +5350,11 @@ int migrate_task_to(struct task_struct *p, int target_cpu) */ void sched_setnuma(struct task_struct *p, int nid) { - struct rq *rq; - unsigned long flags; bool queued, running; + struct rq_flags rf; + struct rq *rq; - rq = task_rq_lock(p, &flags); + rq = task_rq_lock(p, &rf); queued = task_on_rq_queued(p); running = task_current(rq, p); @@ -5207,7 +5369,7 @@ void sched_setnuma(struct task_struct *p, int nid) p->sched_class->set_curr_task(rq); if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE); - task_rq_unlock(rq, p, &flags); + task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_NUMA_BALANCING */ @@ -5223,7 +5385,7 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); if (mm != &init_mm) { - switch_mm(mm, &init_mm, current); + switch_mm_irqs_off(mm, &init_mm, current); finish_arch_post_lock_switch(); } mmdrop(mm); @@ -5232,13 +5394,15 @@ void idle_task_exit(void) /* * Since this CPU is going 'away' for a while, fold any nr_active delta * we might have. Assumes we're called after migrate_tasks() so that the - * nr_active count is stable. + * nr_active count is stable. We need to take the teardown thread which + * is calling this into account, so we hand in adjust = 1 to the load + * calculation. * * Also see the comment "Global load-average calculations". */ static void calc_load_migrate(struct rq *rq) { - long delta = calc_load_fold_active(rq); + long delta = calc_load_fold_active(rq, 1); if (delta) atomic_long_add(delta, &calc_load_tasks); } @@ -5271,6 +5435,7 @@ static void migrate_tasks(struct rq *dead_rq) { struct rq *rq = dead_rq; struct task_struct *next, *stop = rq->stop; + struct pin_cookie cookie; int dest_cpu; /* @@ -5302,8 +5467,8 @@ static void migrate_tasks(struct rq *dead_rq) /* * pick_next_task assumes pinned rq->lock. */ - lockdep_pin_lock(&rq->lock); - next = pick_next_task(rq, &fake_task); + cookie = lockdep_pin_lock(&rq->lock); + next = pick_next_task(rq, &fake_task, cookie); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -5316,7 +5481,7 @@ static void migrate_tasks(struct rq *dead_rq) * because !cpu_active at this point, which means load-balance * will not interfere. Also, stop-machine. */ - lockdep_unpin_lock(&rq->lock); + lockdep_unpin_lock(&rq->lock, cookie); raw_spin_unlock(&rq->lock); raw_spin_lock(&next->pi_lock); raw_spin_lock(&rq->lock); @@ -5377,127 +5542,13 @@ static void set_rq_offline(struct rq *rq) } } -/* - * migration_call - callback that gets triggered when a CPU is added. - * Here we can start up the necessary migration thread for the new CPU. - */ -static int -migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +static void set_cpu_rq_start_time(unsigned int cpu) { - int cpu = (long)hcpu; - unsigned long flags; struct rq *rq = cpu_rq(cpu); - switch (action & ~CPU_TASKS_FROZEN) { - - case CPU_UP_PREPARE: - rq->calc_load_update = calc_load_update; - account_reset_rq(rq); - break; - - case CPU_ONLINE: - /* Update our root-domain */ - raw_spin_lock_irqsave(&rq->lock, flags); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - - set_rq_online(rq); - } - raw_spin_unlock_irqrestore(&rq->lock, flags); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_DYING: - sched_ttwu_pending(); - /* Update our root-domain */ - raw_spin_lock_irqsave(&rq->lock, flags); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); - } - migrate_tasks(rq); - BUG_ON(rq->nr_running != 1); /* the migration thread */ - raw_spin_unlock_irqrestore(&rq->lock, flags); - break; - - case CPU_DEAD: - calc_load_migrate(rq); - break; -#endif - } - - update_max_interval(); - - return NOTIFY_OK; -} - -/* - * Register at high priority so that task migration (migrate_all_tasks) - * happens before everything else. This has to be lower priority than - * the notifier in the perf_event subsystem, though. - */ -static struct notifier_block migration_notifier = { - .notifier_call = migration_call, - .priority = CPU_PRI_MIGRATION, -}; - -static void set_cpu_rq_start_time(void) -{ - int cpu = smp_processor_id(); - struct rq *rq = cpu_rq(cpu); rq->age_stamp = sched_clock_cpu(cpu); } -static int sched_cpu_active(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_STARTING: - set_cpu_rq_start_time(); - return NOTIFY_OK; - - case CPU_DOWN_FAILED: - set_cpu_active(cpu, true); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} - -static int sched_cpu_inactive(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_PREPARE: - set_cpu_active((long)hcpu, false); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } -} - -static int __init migration_init(void) -{ - void *cpu = (void *)(long)smp_processor_id(); - int err; - - /* Initialize migration for the boot CPU */ - err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); - BUG_ON(err == NOTIFY_BAD); - migration_call(&migration_notifier, CPU_ONLINE, cpu); - register_cpu_notifier(&migration_notifier); - - /* Register cpu active notifiers */ - cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); - cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); - - return 0; -} -early_initcall(migration_init); - static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ #ifdef CONFIG_SCHED_DEBUG @@ -6645,10 +6696,10 @@ static void sched_init_numa(void) init_numa_topology_type(); } -static void sched_domains_numa_masks_set(int cpu) +static void sched_domains_numa_masks_set(unsigned int cpu) { - int i, j; int node = cpu_to_node(cpu); + int i, j; for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) { @@ -6658,51 +6709,20 @@ static void sched_domains_numa_masks_set(int cpu) } } -static void sched_domains_numa_masks_clear(int cpu) +static void sched_domains_numa_masks_clear(unsigned int cpu) { int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); } } -/* - * Update sched_domains_numa_masks[level][node] array when new cpus - * are onlined. - */ -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - sched_domains_numa_masks_set(cpu); - break; - - case CPU_DEAD: - sched_domains_numa_masks_clear(cpu); - break; - - default: - return NOTIFY_DONE; - } - - return NOTIFY_OK; -} #else -static inline void sched_init_numa(void) -{ -} - -static int sched_domains_numa_masks_update(struct notifier_block *nfb, - unsigned long action, - void *hcpu) -{ - return 0; -} +static inline void sched_init_numa(void) { } +static void sched_domains_numa_masks_set(unsigned int cpu) { } +static void sched_domains_numa_masks_clear(unsigned int cpu) { } #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -7092,13 +7112,9 @@ static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ * If we come here as part of a suspend/resume, don't touch cpusets because we * want to restore it back to its original state upon resume anyway. */ -static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static void cpuset_cpu_active(void) { - switch (action) { - case CPU_ONLINE_FROZEN: - case CPU_DOWN_FAILED_FROZEN: - + if (cpuhp_tasks_frozen) { /* * num_cpus_frozen tracks how many CPUs are involved in suspend * resume sequence. As long as this is not the last online @@ -7108,35 +7124,25 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, num_cpus_frozen--; if (likely(num_cpus_frozen)) { partition_sched_domains(1, NULL, NULL); - break; + return; } - /* * This is the last CPU online operation. So fall through and * restore the original sched domains by considering the * cpuset configurations. */ - - case CPU_ONLINE: - cpuset_update_active_cpus(true); - break; - default: - return NOTIFY_DONE; } - return NOTIFY_OK; + cpuset_update_active_cpus(true); } -static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, - void *hcpu) +static int cpuset_cpu_inactive(unsigned int cpu) { unsigned long flags; - long cpu = (long)hcpu; struct dl_bw *dl_b; bool overflow; int cpus; - switch (action) { - case CPU_DOWN_PREPARE: + if (!cpuhp_tasks_frozen) { rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); @@ -7148,19 +7154,120 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, rcu_read_unlock_sched(); if (overflow) - return notifier_from_errno(-EBUSY); + return -EBUSY; cpuset_update_active_cpus(false); - break; - case CPU_DOWN_PREPARE_FROZEN: + } else { num_cpus_frozen++; partition_sched_domains(1, NULL, NULL); - break; - default: - return NOTIFY_DONE; } - return NOTIFY_OK; + return 0; +} + +int sched_cpu_activate(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + set_cpu_active(cpu, true); + + if (sched_smp_initialized) { + sched_domains_numa_masks_set(cpu); + cpuset_cpu_active(); + } + + /* + * Put the rq online, if not already. This happens: + * + * 1) In the early boot process, because we build the real domains + * after all cpus have been brought up. + * + * 2) At runtime, if cpuset_cpu_active() fails to rebuild the + * domains. + */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_online(rq); + } + raw_spin_unlock_irqrestore(&rq->lock, flags); + + update_max_interval(); + + return 0; } +int sched_cpu_deactivate(unsigned int cpu) +{ + int ret; + + set_cpu_active(cpu, false); + /* + * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU + * users of this state to go away such that all new such users will + * observe it. + * + * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might + * not imply sync_sched(), so wait for both. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + synchronize_rcu_mult(call_rcu, call_rcu_sched); + else + synchronize_rcu(); + + if (!sched_smp_initialized) + return 0; + + ret = cpuset_cpu_inactive(cpu); + if (ret) { + set_cpu_active(cpu, true); + return ret; + } + sched_domains_numa_masks_clear(cpu); + return 0; +} + +static void sched_rq_cpu_starting(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + rq->calc_load_update = calc_load_update; + account_reset_rq(rq); + update_max_interval(); +} + +int sched_cpu_starting(unsigned int cpu) +{ + set_cpu_rq_start_time(cpu); + sched_rq_cpu_starting(cpu); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +int sched_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* Handle pending wakeups and then migrate everything off */ + sched_ttwu_pending(); + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + migrate_tasks(rq); + BUG_ON(rq->nr_running != 1); + raw_spin_unlock_irqrestore(&rq->lock, flags); + calc_load_migrate(rq); + update_max_interval(); + nohz_balance_exit_idle(cpu); + hrtick_clear(rq); + return 0; +} +#endif + void __init sched_init_smp(void) { cpumask_var_t non_isolated_cpus; @@ -7182,12 +7289,6 @@ void __init sched_init_smp(void) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); - hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); - hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); - hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); - - init_hrtick(); - /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) BUG(); @@ -7196,7 +7297,16 @@ void __init sched_init_smp(void) init_sched_rt_class(); init_sched_dl_class(); + sched_smp_initialized = true; +} + +static int __init migration_init(void) +{ + sched_rq_cpu_starting(smp_processor_id()); + return 0; } +early_initcall(migration_init); + #else void __init sched_init_smp(void) { @@ -7331,8 +7441,6 @@ void __init sched_init(void) for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; - rq->last_load_update_tick = jiffies; - #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; @@ -7351,12 +7459,13 @@ void __init sched_init(void) rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ_COMMON + rq->last_load_update_tick = jiffies; rq->nohz_flags = 0; #endif #ifdef CONFIG_NO_HZ_FULL rq->last_sched_tick = 0; #endif -#endif +#endif /* CONFIG_SMP */ init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); } @@ -7394,10 +7503,12 @@ void __init sched_init(void) if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); - set_cpu_rq_start_time(); + set_cpu_rq_start_time(smp_processor_id()); #endif init_sched_fair_class(); + init_schedstats(); + scheduler_running = 1; } @@ -7639,10 +7750,10 @@ void sched_move_task(struct task_struct *tsk) { struct task_group *tg; int queued, running; - unsigned long flags; + struct rq_flags rf; struct rq *rq; - rq = task_rq_lock(tsk, &flags); + rq = task_rq_lock(tsk, &rf); running = task_current(rq, tsk); queued = task_on_rq_queued(tsk); @@ -7674,7 +7785,7 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); - task_rq_unlock(rq, tsk, &flags); + task_rq_unlock(rq, tsk, &rf); } #endif /* CONFIG_CGROUP_SCHED */ @@ -7894,7 +8005,7 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) static int sched_rt_global_constraints(void) { unsigned long flags; - int i, ret = 0; + int i; raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); for_each_possible_cpu(i) { @@ -7906,7 +8017,7 @@ static int sched_rt_global_constraints(void) } raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - return ret; + return 0; } #endif /* CONFIG_RT_GROUP_SCHED */ |