*
* (C) 2004 Nadia Yvette Chambers, Oracle
*/
-#include <linux/export.h>
+
+#include <linux/completion.h>
#include <linux/sched.h>
-#include <linux/mm.h>
#include <linux/wait.h>
-#include <linux/hash.h>
-#include <linux/kthread.h>
-void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
+static inline int waitqueue_active(wait_queue_head_t *q)
{
- spin_lock_init(&q->lock);
- lockdep_set_class_and_name(&q->lock, key, name);
- INIT_LIST_HEAD(&q->task_list);
+ return !list_empty(&q->task_list);
}
-EXPORT_SYMBOL(__init_waitqueue_head);
-
-void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
{
- unsigned long flags;
-
- wait->flags &= ~WQ_FLAG_EXCLUSIVE;
- spin_lock_irqsave(&q->lock, flags);
- __add_wait_queue(q, wait);
- spin_unlock_irqrestore(&q->lock, flags);
+ list_add(&new->task_list, &head->task_list);
}
-EXPORT_SYMBOL(add_wait_queue);
-void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+static inline void __add_wait_queue_tail(wait_queue_head_t *head,
+ wait_queue_t *new)
{
- unsigned long flags;
+ list_add_tail(&new->task_list, &head->task_list);
+}
+static inline void
+__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+{
wait->flags |= WQ_FLAG_EXCLUSIVE;
- spin_lock_irqsave(&q->lock, flags);
__add_wait_queue_tail(q, wait);
- spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(add_wait_queue_exclusive);
-void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+static inline void
+__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
{
- unsigned long flags;
-
- spin_lock_irqsave(&q->lock, flags);
- __remove_wait_queue(q, wait);
- spin_unlock_irqrestore(&q->lock, flags);
+ list_del(&old->task_list);
}
-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.
- *
- * 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(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int wake_flags, void *key)
+ int nr_exclusive, int wake_flags, void *key)
{
wait_queue_t *curr, *next;
}
}
-/**
- * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @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.
- */
-void __wake_up(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, void *key)
+static void __wake_up(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, void *key)
{
unsigned long flags;
__wake_up_common(q, mode, nr_exclusive, 0, key);
spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(__wake_up);
-/*
- * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
- */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+void wake_up(wait_queue_head_t *q)
{
- __wake_up_common(q, mode, nr, 0, NULL);
+ __wake_up(q, TASK_NORMAL, 1, NULL);
}
-EXPORT_SYMBOL_GPL(__wake_up_locked);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+void wake_up_all(wait_queue_head_t *q)
{
- __wake_up_common(q, mode, 1, 0, key);
+ __wake_up(q, TASK_NORMAL, 0, NULL);
}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key);
-
-/**
- * __wake_up_sync_key - wake up threads blocked on a waitqueue.
- * @q: 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
- * 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.
- *
- * 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.
- */
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, void *key)
-{
- unsigned long flags;
- int wake_flags = 1; /* XXX WF_SYNC */
-
- if (unlikely(!q))
- return;
- if (unlikely(nr_exclusive != 1))
- wake_flags = 0;
-
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_common(q, mode, nr_exclusive, wake_flags, key);
- spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL_GPL(__wake_up_sync_key);
-
-/*
- * __wake_up_sync - see __wake_up_sync_key()
- */
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+static void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
{
- __wake_up_sync_key(q, mode, nr_exclusive, NULL);
+ __wake_up_common(q, mode, nr, 0, NULL);
}
-EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
-/*
- * Note: we use "set_current_state()" _after_ the wait-queue add,
- * because we need a memory barrier there on SMP, so that any
- * wake-function that tests for the wait-queue being active
- * will be guaranteed to see waitqueue addition _or_ subsequent
- * tests in this thread will see the wakeup having taken place.
- *
- * The spin_unlock() itself is semi-permeable and only protects
- * one way (it only protects stuff inside the critical region and
- * stops them from bleeding out - it would still allow subsequent
- * loads to move into the critical region).
- */
void
prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(prepare_to_wait);
-void
+static void
prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
unsigned long flags;
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL(prepare_to_wait_exclusive);
-
-long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
-{
- unsigned long flags;
-
- wait->private = current;
- wait->func = autoremove_wake_function;
-
- spin_lock_irqsave(&q->lock, flags);
- if (list_empty(&wait->task_list)) {
- if (wait->flags & WQ_FLAG_EXCLUSIVE)
- __add_wait_queue_tail(q, wait);
- else
- __add_wait_queue(q, wait);
- }
- set_current_state(state);
- spin_unlock_irqrestore(&q->lock, flags);
- return 0;
-}
-EXPORT_SYMBOL(prepare_to_wait_event);
-
-/**
- * finish_wait - clean up after waiting in a queue
- * @q: waitqueue waited on
- * @wait: wait descriptor
- *
- * Sets current thread back to running state and removes
- * the wait descriptor from the given waitqueue if still
- * queued.
- */
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
{
unsigned long flags;
spin_unlock_irqrestore(&q->lock, flags);
}
}
-EXPORT_SYMBOL(finish_wait);
-
-/**
- * abort_exclusive_wait - abort exclusive waiting in a queue
- * @q: waitqueue waited on
- * @wait: wait descriptor
- * @mode: runstate of the waiter to be woken
- * @key: key to identify a wait bit queue or %NULL
- *
- * Sets current thread back to running state and removes
- * the wait descriptor from the given waitqueue if still
- * queued.
- *
- * Wakes up the next waiter if the caller is concurrently
- * woken up through the queue.
- *
- * This prevents waiter starvation where an exclusive waiter
- * aborts and is woken up concurrently and no one wakes up
- * the next waiter.
- */
-void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
- unsigned int mode, void *key)
-{
- unsigned long flags;
-
- __set_current_state(TASK_RUNNING);
- spin_lock_irqsave(&q->lock, flags);
- if (!list_empty(&wait->task_list))
- list_del_init(&wait->task_list);
- else if (waitqueue_active(q))
- __wake_up_locked_key(q, mode, key);
- spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL(abort_exclusive_wait);
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
void *key)
list_del_init(&wait->task_list);
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);
- *
- * add_wait_queue(&wq, &wait);
- * for (;;) {
- * if (condition)
- * break;
- *
- * p->state = mode; condition = true;
- * smp_mb(); // A smp_wmb(); // C
- * if (!wait->flags & WQ_FLAG_WOKEN) wait->flags |= WQ_FLAG_WOKEN;
- * schedule() try_to_wake_up();
- * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~
- * wait->flags &= ~WQ_FLAG_WOKEN; condition = true;
- * smp_mb() // B smp_wmb(); // C
- * wait->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq, &wait);
- *
- */
-long wait_woken(wait_queue_t *wait, 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.
- */
- if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
- 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.
- */
- smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+struct wait_bit_key {
+ void *flags;
+ int bit_nr;
+ unsigned long timeout;
+};
- return timeout;
-}
-EXPORT_SYMBOL(wait_woken);
+struct wait_bit_queue {
+ struct wait_bit_key key;
+ wait_queue_t wait;
+};
-int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
{
- /*
- * 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 */
- wait->flags |= WQ_FLAG_WOKEN;
+ struct wait_bit_key *key = arg;
+ struct wait_bit_queue *wait_bit =
+ container_of(wait, struct wait_bit_queue, wait);
- return default_wake_function(wait, mode, sync, key);
+ return (wait_bit->key.flags == key->flags &&
+ wait_bit->key.bit_nr == key->bit_nr &&
+ !test_bit(key->bit_nr, key->flags))
+ ? autoremove_wake_function(wait, mode, sync, key) : 0;
}
-EXPORT_SYMBOL(woken_wake_function);
-int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
-{
- struct wait_bit_key *key = arg;
- struct wait_bit_queue *wait_bit
- = container_of(wait, struct wait_bit_queue, wait);
-
- if (wait_bit->key.flags != key->flags ||
- wait_bit->key.bit_nr != key->bit_nr ||
- test_bit(key->bit_nr, key->flags))
- return 0;
- else
- return autoremove_wake_function(wait, mode, sync, key);
-}
-EXPORT_SYMBOL(wake_bit_function);
+static DECLARE_WAIT_QUEUE_HEAD(bit_wq);
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking)
- * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
- * permitted return codes. Nonzero return codes halt waiting and return.
- */
-int __sched
-__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
- wait_bit_action_f *action, unsigned mode)
-{
- int ret = 0;
+#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \
+ { .flags = word, .bit_nr = bit, }
- do {
- prepare_to_wait(wq, &q->wait, mode);
- if (test_bit(q->key.bit_nr, q->key.flags))
- ret = (*action)(&q->key, mode);
- } while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
- finish_wait(wq, &q->wait);
- return ret;
-}
-EXPORT_SYMBOL(__wait_on_bit);
+#define DEFINE_WAIT_BIT(name, word, bit) \
+ struct wait_bit_queue name = { \
+ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \
+ .wait = { \
+ .private = current, \
+ .func = wake_bit_function, \
+ .task_list = \
+ LIST_HEAD_INIT((name).wait.task_list), \
+ }, \
+ }
-int __sched out_of_line_wait_on_bit(void *word, int bit,
- wait_bit_action_f *action, unsigned mode)
+void wake_up_bit(void *word, int bit)
{
- wait_queue_head_t *wq = bit_waitqueue(word, bit);
- DEFINE_WAIT_BIT(wait, word, bit);
+ struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
- return __wait_on_bit(wq, &wait, action, mode);
+ if (waitqueue_active(&bit_wq))
+ __wake_up(&bit_wq, TASK_NORMAL, 1, &key);
}
-EXPORT_SYMBOL(out_of_line_wait_on_bit);
-int __sched out_of_line_wait_on_bit_timeout(
- void *word, int bit, wait_bit_action_f *action,
- unsigned mode, unsigned long timeout)
+void __wait_on_bit(void *word, int bit, unsigned mode)
{
- wait_queue_head_t *wq = bit_waitqueue(word, bit);
DEFINE_WAIT_BIT(wait, word, bit);
- wait.key.timeout = jiffies + timeout;
- return __wait_on_bit(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
-
-int __sched
-__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
- wait_bit_action_f *action, unsigned mode)
-{
do {
- int ret;
+ prepare_to_wait(&bit_wq, &wait.wait, mode);
+ if (test_bit(wait.key.bit_nr, wait.key.flags))
+ schedule();
+ } while (test_bit(wait.key.bit_nr, wait.key.flags));
- prepare_to_wait_exclusive(wq, &q->wait, mode);
- if (!test_bit(q->key.bit_nr, q->key.flags))
- continue;
- ret = action(&q->key, mode);
- if (!ret)
- continue;
- abort_exclusive_wait(wq, &q->wait, mode, &q->key);
- return ret;
- } while (test_and_set_bit(q->key.bit_nr, q->key.flags));
- finish_wait(wq, &q->wait);
- return 0;
+ finish_wait(&bit_wq, &wait.wait);
}
-EXPORT_SYMBOL(__wait_on_bit_lock);
-int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
- wait_bit_action_f *action, unsigned mode)
+void __wait_on_bit_lock(void *word, int bit, unsigned mode)
{
- wait_queue_head_t *wq = bit_waitqueue(word, bit);
DEFINE_WAIT_BIT(wait, word, bit);
- return __wait_on_bit_lock(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
-
-void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit)
-{
- struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
- if (waitqueue_active(wq))
- __wake_up(wq, TASK_NORMAL, 1, &key);
-}
-EXPORT_SYMBOL(__wake_up_bit);
-
-/**
- * wake_up_bit - wake up a waiter on a bit
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that wakes up waiters
- * on a bit. For instance, if one were to have waiters on a bitflag,
- * one would call wake_up_bit() after clearing the bit.
- *
- * In order for this to function properly, as it uses waitqueue_active()
- * internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_atomic(), but in some
- * cases where bitflags are manipulated non-atomically under a lock, one
- * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
- * because spin_unlock() does not guarantee a memory barrier.
- */
-void wake_up_bit(void *word, int bit)
-{
- __wake_up_bit(bit_waitqueue(word, bit), word, bit);
-}
-EXPORT_SYMBOL(wake_up_bit);
-
-static DECLARE_WAIT_QUEUE_HEAD(__bit_waitqueue);
-
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
- return &__bit_waitqueue;
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
-/*
- * Manipulate the atomic_t address to produce a better bit waitqueue table hash
- * index (we're keying off bit -1, but that would produce a horrible hash
- * value).
- */
-static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
-{
- if (BITS_PER_LONG == 64) {
- unsigned long q = (unsigned long)p;
- return bit_waitqueue((void *)(q & ~1), q & 1);
- }
- return bit_waitqueue(p, 0);
-}
-
-static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync,
- void *arg)
-{
- struct wait_bit_key *key = arg;
- struct wait_bit_queue *wait_bit
- = container_of(wait, struct wait_bit_queue, wait);
- atomic_t *val = key->flags;
-
- if (wait_bit->key.flags != key->flags ||
- wait_bit->key.bit_nr != key->bit_nr ||
- atomic_read(val) != 0)
- return 0;
- return autoremove_wake_function(wait, mode, sync, key);
-}
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
- * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero
- * return codes halt waiting and return.
- */
-static __sched
-int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q,
- int (*action)(atomic_t *), unsigned mode)
-{
- atomic_t *val;
- int ret = 0;
-
do {
- prepare_to_wait(wq, &q->wait, mode);
- val = q->key.flags;
- if (atomic_read(val) == 0)
- break;
- ret = (*action)(val);
- } while (!ret && atomic_read(val) != 0);
- finish_wait(wq, &q->wait);
- return ret;
+ prepare_to_wait_exclusive(&bit_wq, &wait.wait, mode);
+ if (!test_bit(wait.key.bit_nr, wait.key.flags))
+ continue;
+ schedule();
+ } while (test_and_set_bit(wait.key.bit_nr, wait.key.flags));
+ finish_wait(&bit_wq, &wait.wait);
}
-#define DEFINE_WAIT_ATOMIC_T(name, p) \
- struct wait_bit_queue name = { \
- .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \
- .wait = { \
- .private = current, \
- .func = wake_atomic_t_function, \
- .task_list = \
- LIST_HEAD_INIT((name).wait.task_list), \
- }, \
- }
-
-__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
- unsigned mode)
+void complete(struct completion *x)
{
- wait_queue_head_t *wq = atomic_t_waitqueue(p);
- DEFINE_WAIT_ATOMIC_T(wait, p);
+ unsigned long flags;
- return __wait_on_atomic_t(wq, &wait, action, mode);
+ spin_lock_irqsave(&x->wait.lock, flags);
+ x->done++;
+ __wake_up_locked(&x->wait, TASK_NORMAL, 1);
+ spin_unlock_irqrestore(&x->wait.lock, flags);
}
-EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
-/**
- * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @p: The atomic_t being waited on, a kernel virtual address
- *
- * Wake up anyone waiting for the atomic_t to go to zero.
- *
- * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
- * check is done by the waiter's wake function, not the by the waker itself).
- */
-void wake_up_atomic_t(atomic_t *p)
+void wait_for_completion(struct completion *x)
{
- __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
-}
-EXPORT_SYMBOL(wake_up_atomic_t);
+ spin_lock_irq(&x->wait.lock);
-__sched int bit_wait(struct wait_bit_key *word, int mode)
-{
- schedule();
- return 0;
-}
-EXPORT_SYMBOL(bit_wait);
-
-__sched int bit_wait_io(struct wait_bit_key *word, int mode)
-{
- io_schedule();
- return 0;
-}
-EXPORT_SYMBOL(bit_wait_io);
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
-__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
-{
- unsigned long now = jiffies;
- if (time_after_eq(now, word->timeout))
- return -EAGAIN;
- schedule_timeout(word->timeout - now);
- return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_timeout);
+ __add_wait_queue_tail_exclusive(&x->wait, &wait);
+ do {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&x->wait.lock);
-__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
-{
- unsigned long now = jiffies;
- if (time_after_eq(now, word->timeout))
- return -EAGAIN;
- io_schedule_timeout(word->timeout - now);
- return 0;
+ schedule();
+ spin_lock_irq(&x->wait.lock);
+ } while (!x->done);
+ __remove_wait_queue(&x->wait, &wait);
+ if (!x->done)
+ goto out;
+ }
+ x->done--;
+out:
+ spin_unlock_irq(&x->wait.lock);
}
-EXPORT_SYMBOL_GPL(bit_wait_io_timeout);