WSL2-Linux-Kernel/kernel/sched/wait.c

625 строки
18 KiB
C
Исходник Обычный вид История

/*
* Generic waiting primitives.
*
* (C) 2004 Nadia Yvette Chambers, Oracle
*/
#include <linux/init.h>
#include <linux/export.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)
{
spin_lock_init(&q->lock);
lockdep_set_class_and_name(&q->lock, key, name);
INIT_LIST_HEAD(&q->task_list);
}
EXPORT_SYMBOL(__init_waitqueue_head);
void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
{
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);
}
EXPORT_SYMBOL(add_wait_queue);
void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
{
unsigned long flags;
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)
{
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__remove_wait_queue(q, wait);
spin_unlock_irqrestore(&q->lock, flags);
}
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)
{
wait_queue_t *curr, *next;
list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
unsigned flags = curr->flags;
if (curr->func(curr, mode, wake_flags, key) &&
(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
}
}
/**
* __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)
{
unsigned long flags;
spin_lock_irqsave(&q->lock, 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)
{
__wake_up_common(q, mode, nr, 0, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
{
__wake_up_common(q, mode, 1, 0, key);
}
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)
{
__wake_up_sync_key(q, mode, nr_exclusive, 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)
{
unsigned long flags;
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&q->lock, flags);
if (list_empty(&wait->task_list))
__add_wait_queue(q, wait);
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait);
void
prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
unsigned long flags;
wait->flags |= WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&q->lock, flags);
if (list_empty(&wait->task_list))
__add_wait_queue_tail(q, wait);
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;
if (signal_pending_state(state, current))
return -ERESTARTSYS;
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);
/**
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
* 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;
__set_current_state(TASK_RUNNING);
/*
* We can check for list emptiness outside the lock
* IFF:
* - we use the "careful" check that verifies both
* the next and prev pointers, so that there cannot
* be any half-pending updates in progress on other
* CPU's that we haven't seen yet (and that might
* still change the stack area.
* and
* - all other users take the lock (ie we can only
* have _one_ other CPU that looks at or modifies
* the list).
*/
if (!list_empty_careful(&wait->task_list)) {
spin_lock_irqsave(&q->lock, flags);
list_del_init(&wait->task_list);
spin_unlock_irqrestore(&q->lock, flags);
}
}
EXPORT_SYMBOL(finish_wait);
/**
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
* abort_exclusive_wait - abort exclusive waiting in a queue
* @q: waitqueue waited on
* @wait: wait descriptor
* @mode: runstate of the waiter to be woken
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
* @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
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
* 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);
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(abort_exclusive_wait);
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
int ret = default_wake_function(wait, mode, sync, key);
if (ret)
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 */
return timeout;
}
EXPORT_SYMBOL(wait_woken);
int woken_wake_function(wait_queue_t *wait, 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 */
wait->flags |= WQ_FLAG_WOKEN;
return default_wake_function(wait, mode, sync, key);
}
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);
/*
* 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,
sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: David Howells <dhowells@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
wait_bit_action_f *action, unsigned mode)
{
int ret = 0;
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);
int __sched out_of_line_wait_on_bit(void *word, int bit,
sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: David Howells <dhowells@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
wait_bit_action_f *action, unsigned mode)
{
wait_queue_head_t *wq = bit_waitqueue(word, bit);
DEFINE_WAIT_BIT(wait, word, bit);
return __wait_on_bit(wq, &wait, action, mode);
}
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)
{
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,
sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: David Howells <dhowells@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
wait_bit_action_f *action, unsigned mode)
{
do {
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
int ret;
prepare_to_wait_exclusive(wq, &q->wait, mode);
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
if (!test_bit(q->key.bit_nr, q->key.flags))
continue;
ret = action(&q->key, mode);
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
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);
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 02:12:14 +03:00
return 0;
}
EXPORT_SYMBOL(__wait_on_bit_lock);
int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: David Howells <dhowells@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
wait_bit_action_f *action, 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);
wait_queue_head_t *bit_waitqueue(void *word, int bit)
{
const int shift = BITS_PER_LONG == 32 ? 5 : 6;
const struct zone *zone = page_zone(virt_to_page(word));
unsigned long val = (unsigned long)word << shift | bit;
return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
}
EXPORT_SYMBOL(bit_waitqueue);
Add wait_on_atomic_t() and wake_up_atomic_t() Add wait_on_atomic_t() and wake_up_atomic_t() to indicate became-zero events on atomic_t types. This uses the bit-wake waitqueue table. The key is set to a value outside of the number of bits in a long so that wait_on_bit() won't be woken up accidentally. What I'm using this for is: in a following patch I add a counter to struct fscache_cookie to count the number of outstanding operations that need access to netfs data. The way this works is: (1) When a cookie is allocated, the counter is initialised to 1. (2) When an operation wants to access netfs data, it calls atomic_inc_unless() to increment the counter before it does so. If it was 0, then the counter isn't incremented, the operation isn't permitted to access the netfs data (which might by this point no longer exist) and the operation aborts in some appropriate manner. (3) When an operation finishes with the netfs data, it decrements the counter and if it reaches 0, calls wake_up_atomic_t() on it - the assumption being that it was the last blocker. (4) When a cookie is released, the counter is decremented and the releaser uses wait_on_atomic_t() to wait for the counter to become 0 - which should indicate no one is using the netfs data any longer. The netfs data can then be destroyed. There are some alternatives that I have thought of and that have been suggested by Tejun Heo: (A) Using wait_on_bit() to wait on a bit in the counter. This doesn't work because if that bit happens to be 0 then the wait won't happen - even if the counter is non-zero. (B) Using wait_on_bit() to wait on a flag elsewhere which is cleared when the counter reaches 0. Such a flag would be redundant and would add complexity. (C) Adding a waitqueue to fscache_cookie - this would expand that struct by several words for an event that happens just once in each cookie's lifetime. Further, cookies are generally per-file so there are likely to be a lot of them. (D) Similar to (C), but add a pointer to a waitqueue in the cookie instead of a waitqueue. This would add single word per cookie and so would be less of an expansion - but still an expansion. (E) Adding a static waitqueue to the fscache module. Generally this would be fine, but under certain circumstances many cookies will all get added at the same time (eg. NFS umount, cache withdrawal) thereby presenting scaling issues. Note that the wait may be significant as disk I/O may be in progress. So, I think reusing the wait_on_bit() waitqueue set is reasonable. I don't make much use of the waitqueue I need on a per-cookie basis, but sometimes I have a huge flood of the cookies to deal with. I also don't want to add a whole new set of global waitqueue tables specifically for the dec-to-0 event if I can reuse the bit tables. Signed-off-by: David Howells <dhowells@redhat.com> Tested-By: Milosz Tanski <milosz@adfin.com> Acked-by: Jeff Layton <jlayton@redhat.com>
2013-05-10 22:50:26 +04:00
/*
* 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);
Add wait_on_atomic_t() and wake_up_atomic_t() Add wait_on_atomic_t() and wake_up_atomic_t() to indicate became-zero events on atomic_t types. This uses the bit-wake waitqueue table. The key is set to a value outside of the number of bits in a long so that wait_on_bit() won't be woken up accidentally. What I'm using this for is: in a following patch I add a counter to struct fscache_cookie to count the number of outstanding operations that need access to netfs data. The way this works is: (1) When a cookie is allocated, the counter is initialised to 1. (2) When an operation wants to access netfs data, it calls atomic_inc_unless() to increment the counter before it does so. If it was 0, then the counter isn't incremented, the operation isn't permitted to access the netfs data (which might by this point no longer exist) and the operation aborts in some appropriate manner. (3) When an operation finishes with the netfs data, it decrements the counter and if it reaches 0, calls wake_up_atomic_t() on it - the assumption being that it was the last blocker. (4) When a cookie is released, the counter is decremented and the releaser uses wait_on_atomic_t() to wait for the counter to become 0 - which should indicate no one is using the netfs data any longer. The netfs data can then be destroyed. There are some alternatives that I have thought of and that have been suggested by Tejun Heo: (A) Using wait_on_bit() to wait on a bit in the counter. This doesn't work because if that bit happens to be 0 then the wait won't happen - even if the counter is non-zero. (B) Using wait_on_bit() to wait on a flag elsewhere which is cleared when the counter reaches 0. Such a flag would be redundant and would add complexity. (C) Adding a waitqueue to fscache_cookie - this would expand that struct by several words for an event that happens just once in each cookie's lifetime. Further, cookies are generally per-file so there are likely to be a lot of them. (D) Similar to (C), but add a pointer to a waitqueue in the cookie instead of a waitqueue. This would add single word per cookie and so would be less of an expansion - but still an expansion. (E) Adding a static waitqueue to the fscache module. Generally this would be fine, but under certain circumstances many cookies will all get added at the same time (eg. NFS umount, cache withdrawal) thereby presenting scaling issues. Note that the wait may be significant as disk I/O may be in progress. So, I think reusing the wait_on_bit() waitqueue set is reasonable. I don't make much use of the waitqueue I need on a per-cookie basis, but sometimes I have a huge flood of the cookies to deal with. I also don't want to add a whole new set of global waitqueue tables specifically for the dec-to-0 event if I can reuse the bit tables. Signed-off-by: David Howells <dhowells@redhat.com> Tested-By: Milosz Tanski <milosz@adfin.com> Acked-by: Jeff Layton <jlayton@redhat.com>
2013-05-10 22:50:26 +04:00
} while (!ret && atomic_read(val) != 0);
finish_wait(wq, &q->wait);
return ret;
}
#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)
{
wait_queue_head_t *wq = atomic_t_waitqueue(p);
DEFINE_WAIT_ATOMIC_T(wait, p);
return __wait_on_atomic_t(wq, &wait, action, mode);
}
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
Add wait_on_atomic_t() and wake_up_atomic_t() Add wait_on_atomic_t() and wake_up_atomic_t() to indicate became-zero events on atomic_t types. This uses the bit-wake waitqueue table. The key is set to a value outside of the number of bits in a long so that wait_on_bit() won't be woken up accidentally. What I'm using this for is: in a following patch I add a counter to struct fscache_cookie to count the number of outstanding operations that need access to netfs data. The way this works is: (1) When a cookie is allocated, the counter is initialised to 1. (2) When an operation wants to access netfs data, it calls atomic_inc_unless() to increment the counter before it does so. If it was 0, then the counter isn't incremented, the operation isn't permitted to access the netfs data (which might by this point no longer exist) and the operation aborts in some appropriate manner. (3) When an operation finishes with the netfs data, it decrements the counter and if it reaches 0, calls wake_up_atomic_t() on it - the assumption being that it was the last blocker. (4) When a cookie is released, the counter is decremented and the releaser uses wait_on_atomic_t() to wait for the counter to become 0 - which should indicate no one is using the netfs data any longer. The netfs data can then be destroyed. There are some alternatives that I have thought of and that have been suggested by Tejun Heo: (A) Using wait_on_bit() to wait on a bit in the counter. This doesn't work because if that bit happens to be 0 then the wait won't happen - even if the counter is non-zero. (B) Using wait_on_bit() to wait on a flag elsewhere which is cleared when the counter reaches 0. Such a flag would be redundant and would add complexity. (C) Adding a waitqueue to fscache_cookie - this would expand that struct by several words for an event that happens just once in each cookie's lifetime. Further, cookies are generally per-file so there are likely to be a lot of them. (D) Similar to (C), but add a pointer to a waitqueue in the cookie instead of a waitqueue. This would add single word per cookie and so would be less of an expansion - but still an expansion. (E) Adding a static waitqueue to the fscache module. Generally this would be fine, but under certain circumstances many cookies will all get added at the same time (eg. NFS umount, cache withdrawal) thereby presenting scaling issues. Note that the wait may be significant as disk I/O may be in progress. So, I think reusing the wait_on_bit() waitqueue set is reasonable. I don't make much use of the waitqueue I need on a per-cookie basis, but sometimes I have a huge flood of the cookies to deal with. I also don't want to add a whole new set of global waitqueue tables specifically for the dec-to-0 event if I can reuse the bit tables. Signed-off-by: David Howells <dhowells@redhat.com> Tested-By: Milosz Tanski <milosz@adfin.com> Acked-by: Jeff Layton <jlayton@redhat.com>
2013-05-10 22:50:26 +04:00
*
* 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)
{
__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
}
EXPORT_SYMBOL(wake_up_atomic_t);
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
__sched int bit_wait(struct wait_bit_key *word, int mode)
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
{
schedule();
if (signal_pending_state(mode, current))
return -EINTR;
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
return 0;
}
EXPORT_SYMBOL(bit_wait);
__sched int bit_wait_io(struct wait_bit_key *word, int mode)
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
{
io_schedule();
if (signal_pending_state(mode, current))
return -EINTR;
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
return 0;
}
EXPORT_SYMBOL(bit_wait_io);
__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
{
unsigned long now = READ_ONCE(jiffies);
if (time_after_eq(now, word->timeout))
return -EAGAIN;
schedule_timeout(word->timeout - now);
if (signal_pending_state(mode, current))
return -EINTR;
return 0;
}
EXPORT_SYMBOL_GPL(bit_wait_timeout);
__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
{
unsigned long now = READ_ONCE(jiffies);
if (time_after_eq(now, word->timeout))
return -EAGAIN;
io_schedule_timeout(word->timeout - now);
if (signal_pending_state(mode, current))
return -EINTR;
return 0;
}
EXPORT_SYMBOL_GPL(bit_wait_io_timeout);