diff options
Diffstat (limited to 'kernel/sched/wait.c')
| -rw-r--r-- | kernel/sched/wait.c | 223 |
1 files changed, 148 insertions, 75 deletions
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 17f11c6b0a9f..20f27e2cf7ae 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -1,16 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Generic waiting primitives. * * (C) 2004 Nadia Yvette Chambers, Oracle */ -#include <linux/init.h> -#include <linux/export.h> -#include <linux/sched/signal.h> -#include <linux/sched/debug.h> -#include <linux/mm.h> -#include <linux/wait.h> -#include <linux/hash.h> -#include <linux/kthread.h> +#include "sched.h" void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key) { @@ -27,7 +21,7 @@ void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - __add_wait_queue_entry_tail(wq_head, wq_entry); + __add_wait_queue(wq_head, wq_entry); spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue); @@ -43,6 +37,35 @@ void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue } EXPORT_SYMBOL(add_wait_queue_exclusive); +void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) +{ + unsigned long flags; + + wq_entry->flags |= WQ_FLAG_PRIORITY; + spin_lock_irqsave(&wq_head->lock, flags); + __add_wait_queue(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); +} +EXPORT_SYMBOL_GPL(add_wait_queue_priority); + +int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head, + struct wait_queue_entry *wq_entry) +{ + struct list_head *head = &wq_head->head; + + wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY; + + guard(spinlock_irqsave)(&wq_head->lock); + + if (!list_empty(head) && + (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY)) + return -EBUSY; + + list_add(&wq_entry->entry, head); + return 0; +} +EXPORT_SYMBOL_GPL(add_wait_queue_priority_exclusive); + void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; @@ -53,28 +76,57 @@ void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry } EXPORT_SYMBOL(remove_wait_queue); - /* * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve - * number) then we wake all the non-exclusive tasks and one exclusive task. + * number) then we wake that number of exclusive tasks, and potentially all + * the non-exclusive tasks. Normally, exclusive tasks will be at the end of + * the list and any non-exclusive tasks will be woken first. A priority task + * may be at the head of the list, and can consume the event without any other + * tasks being woken if it's also an exclusive task. * * There are circumstances in which we can try to wake a task which has already * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, +static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, int wake_flags, void *key) { wait_queue_entry_t *curr, *next; - list_for_each_entry_safe(curr, next, &wq_head->head, entry) { + lockdep_assert_held(&wq_head->lock); + + curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry); + + if (&curr->entry == &wq_head->head) + return nr_exclusive; + + list_for_each_entry_safe_from(curr, next, &wq_head->head, entry) { unsigned flags = curr->flags; + int ret; - if (curr->func(curr, mode, wake_flags, key) && - (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + ret = curr->func(curr, mode, wake_flags, key); + if (ret < 0) + break; + if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } + + return nr_exclusive; +} + +static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode, + int nr_exclusive, int wake_flags, void *key) +{ + unsigned long flags; + int remaining; + + spin_lock_irqsave(&wq_head->lock, flags); + remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, + key); + spin_unlock_irqrestore(&wq_head->lock, flags); + + return nr_exclusive - remaining; } /** @@ -84,20 +136,22 @@ static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier + * before accessing the task state. Returns the number of exclusive + * tasks that were awaken. */ -void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, - int nr_exclusive, void *key) +int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, + int nr_exclusive, void *key) { - unsigned long flags; - - spin_lock_irqsave(&wq_head->lock, flags); - __wake_up_common(wq_head, mode, nr_exclusive, 0, key); - spin_unlock_irqrestore(&wq_head->lock, flags); + return __wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key); } EXPORT_SYMBOL(__wake_up); +void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key) +{ + __wake_up_common_lock(wq_head, mode, 1, WF_CURRENT_CPU, key); +} + /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ @@ -117,7 +171,6 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key); * __wake_up_sync_key - wake up threads blocked on a waitqueue. * @wq_head: the waitqueue * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: opaque value to be passed to wakeup targets * * The sync wakeup differs that the waker knows that it will schedule @@ -127,36 +180,58 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key); * * On UP it can prevent extra preemption. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, - int nr_exclusive, void *key) + void *key) { - unsigned long flags; - int wake_flags = 1; /* XXX WF_SYNC */ - if (unlikely(!wq_head)) return; - if (unlikely(nr_exclusive != 1)) - wake_flags = 0; - - spin_lock_irqsave(&wq_head->lock, flags); - __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key); - spin_unlock_irqrestore(&wq_head->lock, flags); + __wake_up_common_lock(wq_head, mode, 1, WF_SYNC, key); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); +/** + * __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue. + * @wq_head: the waitqueue + * @mode: which threads + * @key: opaque value to be passed to wakeup targets + * + * The sync wakeup differs in that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + * + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. + */ +void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, + unsigned int mode, void *key) +{ + __wake_up_common(wq_head, mode, 1, WF_SYNC, key); +} +EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key); + /* * __wake_up_sync - see __wake_up_sync_key() */ -void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive) +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) { - __wake_up_sync_key(wq_head, mode, nr_exclusive, NULL); + __wake_up_sync_key(wq_head, mode, NULL); } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any @@ -183,17 +258,22 @@ prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_ent } EXPORT_SYMBOL(prepare_to_wait); -void +/* Returns true if we are the first waiter in the queue, false otherwise. */ +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; + bool was_empty = false; wq_entry->flags |= WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - if (list_empty(&wq_entry->entry)) + if (list_empty(&wq_entry->entry)) { + was_empty = list_empty(&wq_head->head); __add_wait_queue_entry_tail(wq_head, wq_entry); + } set_current_state(state); spin_unlock_irqrestore(&wq_head->lock, flags); + return was_empty; } EXPORT_SYMBOL(prepare_to_wait_exclusive); @@ -212,7 +292,7 @@ long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_en long ret = 0; spin_lock_irqsave(&wq_head->lock, flags); - if (unlikely(signal_pending_state(state, current))) { + if (signal_pending_state(state, current)) { /* * Exclusive waiter must not fail if it was selected by wakeup, * it should "consume" the condition we were waiting for. @@ -261,6 +341,7 @@ int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait) spin_unlock(&wq->lock); schedule(); spin_lock(&wq->lock); + return 0; } EXPORT_SYMBOL(do_wait_intr); @@ -277,6 +358,7 @@ int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait) spin_unlock_irq(&wq->lock); schedule(); spin_lock_irq(&wq->lock); + return 0; } EXPORT_SYMBOL(do_wait_intr_irq); @@ -321,16 +403,12 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i int ret = default_wake_function(wq_entry, mode, sync, key); if (ret) - list_del_init(&wq_entry->entry); + list_del_init_careful(&wq_entry->entry); + return ret; } EXPORT_SYMBOL(autoremove_wake_function); -static inline bool is_kthread_should_stop(void) -{ - return (current->flags & PF_KTHREAD) && kthread_should_stop(); -} - /* * DEFINE_WAIT_FUNC(wait, woken_wake_func); * @@ -339,35 +417,36 @@ static inline bool is_kthread_should_stop(void) * if (condition) * break; * - * p->state = mode; condition = true; - * smp_mb(); // A smp_wmb(); // C - * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; - * schedule() try_to_wake_up(); - * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; - * smp_mb() // B smp_wmb(); // C - * wq_entry->flags |= WQ_FLAG_WOKEN; - * } - * remove_wait_queue(&wq_head, &wait); + * // in wait_woken() // in woken_wake_function() * + * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN; + * smp_mb(); // A try_to_wake_up(): + * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier> + * schedule() if (p->state & mode) + * p->state = TASK_RUNNING; p->state = TASK_RUNNING; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~ + * smp_mb(); // B condition = true; + * } smp_mb(); // C + * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN; */ long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { - set_current_state(mode); /* A */ /* - * The above implies an smp_mb(), which matches with the smp_wmb() from - * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must - * also observe all state before the wakeup. + * The below executes an smp_mb(), which matches with the full barrier + * executed by the try_to_wake_up() in woken_wake_function() such that + * either we see the store to wq_entry->flags in woken_wake_function() + * or woken_wake_function() sees our store to current->state. */ - if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) + set_current_state(mode); /* A */ + if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !kthread_should_stop_or_park()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); /* - * The below implies an smp_mb(), it too pairs with the smp_wmb() from - * woken_wake_function() such that we must either observe the wait - * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss - * an event. + * The below executes an smp_mb(), which matches with the smp_mb() (C) + * in woken_wake_function() such that either we see the wait condition + * being true or the store to wq_entry->flags in woken_wake_function() + * follows ours in the coherence order. */ smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ @@ -377,14 +456,8 @@ EXPORT_SYMBOL(wait_woken); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - /* - * Although this function is called under waitqueue lock, LOCK - * doesn't imply write barrier and the users expects write - * barrier semantics on wakeup functions. The following - * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() - * and is paired with smp_store_mb() in wait_woken(). - */ - smp_wmb(); /* C */ + /* Pairs with the smp_store_mb() in wait_woken(). */ + smp_mb(); /* C */ wq_entry->flags |= WQ_FLAG_WOKEN; return default_wake_function(wq_entry, mode, sync, key); |