kernel_optimize_test/include/linux/wait.h
Linus Torvalds 5ef64cc898 mm: allow a controlled amount of unfairness in the page lock
Commit 2a9127fcf2 ("mm: rewrite wait_on_page_bit_common() logic") made
the page locking entirely fair, in that if a waiter came in while the
lock was held, the lock would be transferred to the lockers strictly in
order.

That was intended to finally get rid of the long-reported watchdog
failures that involved the page lock under extreme load, where a process
could end up waiting essentially forever, as other page lockers stole
the lock from under it.

It also improved some benchmarks, but it ended up causing huge
performance regressions on others, simply because fair lock behavior
doesn't end up giving out the lock as aggressively, causing better
worst-case latency, but potentially much worse average latencies and
throughput.

Instead of reverting that change entirely, this introduces a controlled
amount of unfairness, with a sysctl knob to tune it if somebody needs
to.  But the default value should hopefully be good for any normal load,
allowing a few rounds of lock stealing, but enforcing the strict
ordering before the lock has been stolen too many times.

There is also a hint from Matthieu Baerts that the fair page coloring
may end up exposing an ABBA deadlock that is hidden by the usual
optimistic lock stealing, and while the unfairness doesn't fix the
fundamental issue (and I'm still looking at that), it avoids it in
practice.

The amount of unfairness can be modified by writing a new value to the
'sysctl_page_lock_unfairness' variable (default value of 5, exposed
through /proc/sys/vm/page_lock_unfairness), but that is hopefully
something we'd use mainly for debugging rather than being necessary for
any deep system tuning.

This whole issue has exposed just how critical the page lock can be, and
how contended it gets under certain locks.  And the main contention
doesn't really seem to be anything related to IO (which was the origin
of this lock), but for things like just verifying that the page file
mapping is stable while faulting in the page into a page table.

Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/
Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1
Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/
Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com>
Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Chris Mason <clm@fb.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-17 10:26:41 -07:00

1156 lines
40 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
/*
* Linux wait queue related types and methods
*/
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/current.h>
#include <uapi/linux/wait.h>
typedef struct wait_queue_entry wait_queue_entry_t;
typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
/* wait_queue_entry::flags */
#define WQ_FLAG_EXCLUSIVE 0x01
#define WQ_FLAG_WOKEN 0x02
#define WQ_FLAG_BOOKMARK 0x04
#define WQ_FLAG_CUSTOM 0x08
#define WQ_FLAG_DONE 0x10
/*
* A single wait-queue entry structure:
*/
struct wait_queue_entry {
unsigned int flags;
void *private;
wait_queue_func_t func;
struct list_head entry;
};
struct wait_queue_head {
spinlock_t lock;
struct list_head head;
};
typedef struct wait_queue_head wait_queue_head_t;
struct task_struct;
/*
* Macros for declaration and initialisaton of the datatypes
*/
#define __WAITQUEUE_INITIALIZER(name, tsk) { \
.private = tsk, \
.func = default_wake_function, \
.entry = { NULL, NULL } }
#define DECLARE_WAITQUEUE(name, tsk) \
struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk)
#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.head = { &(name).head, &(name).head } }
#define DECLARE_WAIT_QUEUE_HEAD(name) \
struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *);
#define init_waitqueue_head(wq_head) \
do { \
static struct lock_class_key __key; \
\
__init_waitqueue_head((wq_head), #wq_head, &__key); \
} while (0)
#ifdef CONFIG_LOCKDEP
# define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
({ init_waitqueue_head(&name); name; })
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
#else
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name)
#endif
static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p)
{
wq_entry->flags = 0;
wq_entry->private = p;
wq_entry->func = default_wake_function;
}
static inline void
init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func)
{
wq_entry->flags = 0;
wq_entry->private = NULL;
wq_entry->func = func;
}
/**
* waitqueue_active -- locklessly test for waiters on the queue
* @wq_head: the waitqueue to test for waiters
*
* returns true if the wait list is not empty
*
* NOTE: this function is lockless and requires care, incorrect usage _will_
* lead to sporadic and non-obvious failure.
*
* Use either while holding wait_queue_head::lock or when used for wakeups
* with an extra smp_mb() like::
*
* CPU0 - waker CPU1 - waiter
*
* for (;;) {
* @cond = true; prepare_to_wait(&wq_head, &wait, state);
* smp_mb(); // smp_mb() from set_current_state()
* if (waitqueue_active(wq_head)) if (@cond)
* wake_up(wq_head); break;
* schedule();
* }
* finish_wait(&wq_head, &wait);
*
* Because without the explicit smp_mb() it's possible for the
* waitqueue_active() load to get hoisted over the @cond store such that we'll
* observe an empty wait list while the waiter might not observe @cond.
*
* Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
* which (when the lock is uncontended) are of roughly equal cost.
*/
static inline int waitqueue_active(struct wait_queue_head *wq_head)
{
return !list_empty(&wq_head->head);
}
/**
* wq_has_single_sleeper - check if there is only one sleeper
* @wq_head: wait queue head
*
* Returns true of wq_head has only one sleeper on the list.
*
* Please refer to the comment for waitqueue_active.
*/
static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head)
{
return list_is_singular(&wq_head->head);
}
/**
* wq_has_sleeper - check if there are any waiting processes
* @wq_head: wait queue head
*
* Returns true if wq_head has waiting processes
*
* Please refer to the comment for waitqueue_active.
*/
static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
{
/*
* We need to be sure we are in sync with the
* add_wait_queue modifications to the wait queue.
*
* This memory barrier should be paired with one on the
* waiting side.
*/
smp_mb();
return waitqueue_active(wq_head);
}
extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
list_add(&wq_entry->entry, &wq_head->head);
}
/*
* Used for wake-one threads:
*/
static inline void
__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq_head, wq_entry);
}
static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
list_add_tail(&wq_entry->entry, &wq_head->head);
}
static inline void
__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_entry_tail(wq_head, wq_entry);
}
static inline void
__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
list_del(&wq_entry->entry);
}
void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
unsigned int mode, void *key, wait_queue_entry_t *bookmark);
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
#define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL)
#define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL)
#define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL)
#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1)
#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0)
#define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
#define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL)
#define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE)
/*
* Wakeup macros to be used to report events to the targets.
*/
#define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m))
#define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m))
#define wake_up_poll(x, m) \
__wake_up(x, TASK_NORMAL, 1, poll_to_key(m))
#define wake_up_locked_poll(x, m) \
__wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m))
#define wake_up_interruptible_poll(x, m) \
__wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m))
#define wake_up_interruptible_sync_poll(x, m) \
__wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
#define wake_up_interruptible_sync_poll_locked(x, m) \
__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
#define ___wait_cond_timeout(condition) \
({ \
bool __cond = (condition); \
if (__cond && !__ret) \
__ret = 1; \
__cond || !__ret; \
})
#define ___wait_is_interruptible(state) \
(!__builtin_constant_p(state) || \
state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \
extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags);
/*
* The below macro ___wait_event() has an explicit shadow of the __ret
* variable when used from the wait_event_*() macros.
*
* This is so that both can use the ___wait_cond_timeout() construct
* to wrap the condition.
*
* The type inconsistency of the wait_event_*() __ret variable is also
* on purpose; we use long where we can return timeout values and int
* otherwise.
*/
#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \
({ \
__label__ __out; \
struct wait_queue_entry __wq_entry; \
long __ret = ret; /* explicit shadow */ \
\
init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \
for (;;) { \
long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\
\
if (condition) \
break; \
\
if (___wait_is_interruptible(state) && __int) { \
__ret = __int; \
goto __out; \
} \
\
cmd; \
} \
finish_wait(&wq_head, &__wq_entry); \
__out: __ret; \
})
#define __wait_event(wq_head, condition) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
schedule())
/**
* wait_event - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event(wq_head, condition) \
do { \
might_sleep(); \
if (condition) \
break; \
__wait_event(wq_head, condition); \
} while (0)
#define __io_wait_event(wq_head, condition) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
io_schedule())
/*
* io_wait_event() -- like wait_event() but with io_schedule()
*/
#define io_wait_event(wq_head, condition) \
do { \
might_sleep(); \
if (condition) \
break; \
__io_wait_event(wq_head, condition); \
} while (0)
#define __wait_event_freezable(wq_head, condition) \
___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \
freezable_schedule())
/**
* wait_event_freezable - sleep (or freeze) until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
* to system load) until the @condition evaluates to true. The
* @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event_freezable(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_freezable(wq_head, condition); \
__ret; \
})
#define __wait_event_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_UNINTERRUPTIBLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_freezable_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_INTERRUPTIBLE, 0, timeout, \
__ret = freezable_schedule_timeout(__ret))
/*
* like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
* increasing load and is freezable.
*/
#define wait_event_freezable_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \
cmd1; schedule(); cmd2)
/*
* Just like wait_event_cmd(), except it sets exclusive flag
*/
#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \
do { \
if (condition) \
break; \
__wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \
} while (0)
#define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
cmd1; schedule(); cmd2)
/**
* wait_event_cmd - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @cmd1: the command will be executed before sleep
* @cmd2: the command will be executed after sleep
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event_cmd(wq_head, condition, cmd1, cmd2) \
do { \
if (condition) \
break; \
__wait_event_cmd(wq_head, condition, cmd1, cmd2); \
} while (0)
#define __wait_event_interruptible(wq_head, condition) \
___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \
schedule())
/**
* wait_event_interruptible - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_interruptible(wq_head, condition); \
__ret; \
})
#define __wait_event_interruptible_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_INTERRUPTIBLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
* interrupted by a signal.
*/
#define wait_event_interruptible_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_interruptible_timeout(wq_head, \
condition, timeout); \
__ret; \
})
#define __wait_event_hrtimeout(wq_head, condition, timeout, state) \
({ \
int __ret = 0; \
struct hrtimer_sleeper __t; \
\
hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \
HRTIMER_MODE_REL); \
if ((timeout) != KTIME_MAX) \
hrtimer_start_range_ns(&__t.timer, timeout, \
current->timer_slack_ns, \
HRTIMER_MODE_REL); \
\
__ret = ___wait_event(wq_head, condition, state, 0, 0, \
if (!__t.task) { \
__ret = -ETIME; \
break; \
} \
schedule()); \
\
hrtimer_cancel(&__t.timer); \
destroy_hrtimer_on_stack(&__t.timer); \
__ret; \
})
/**
* wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, as a ktime_t
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function returns 0 if @condition became true, or -ETIME if the timeout
* elapsed.
*/
#define wait_event_hrtimeout(wq_head, condition, timeout) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_hrtimeout(wq_head, condition, timeout, \
TASK_UNINTERRUPTIBLE); \
__ret; \
})
/**
* wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, as a ktime_t
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function returns 0 if @condition became true, -ERESTARTSYS if it was
* interrupted by a signal, or -ETIME if the timeout elapsed.
*/
#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \
({ \
long __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_hrtimeout(wq, condition, timeout, \
TASK_INTERRUPTIBLE); \
__ret; \
})
#define __wait_event_interruptible_exclusive(wq, condition) \
___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \
schedule())
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_interruptible_exclusive(wq, condition); \
__ret; \
})
#define __wait_event_killable_exclusive(wq, condition) \
___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \
schedule())
#define wait_event_killable_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_killable_exclusive(wq, condition); \
__ret; \
})
#define __wait_event_freezable_exclusive(wq, condition) \
___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \
freezable_schedule())
#define wait_event_freezable_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_freezable_exclusive(wq, condition); \
__ret; \
})
/**
* wait_event_idle - wait for a condition without contributing to system load
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
*/
#define wait_event_idle(wq_head, condition) \
do { \
might_sleep(); \
if (!(condition)) \
___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \
} while (0)
/**
* wait_event_idle_exclusive - wait for a condition with contributing to system load
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus if other processes wait on the same list, when this
* process is woken further processes are not considered.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
*/
#define wait_event_idle_exclusive(wq_head, condition) \
do { \
might_sleep(); \
if (!(condition)) \
___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \
} while (0)
#define __wait_event_idle_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_IDLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_idle_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_idle_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_IDLE, 1, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus if other processes wait on the same list, when this
* process is woken further processes are not considered.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\
__ret; \
})
extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *);
extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
({ \
int __ret; \
DEFINE_WAIT(__wait); \
if (exclusive) \
__wait.flags |= WQ_FLAG_EXCLUSIVE; \
do { \
__ret = fn(&(wq), &__wait); \
if (__ret) \
break; \
} while (!(condition)); \
__remove_wait_queue(&(wq), &__wait); \
__set_current_state(TASK_RUNNING); \
__ret; \
})
/**
* wait_event_interruptible_locked - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock()/spin_unlock()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_locked(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
/**
* wait_event_interruptible_locked_irq - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_locked_irq(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
/**
* wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock()/spin_unlock()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus when other process waits process on the list if this
* process is awaken further processes are not considered.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_exclusive_locked(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
/**
* wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus when other process waits process on the list if this
* process is awaken further processes are not considered.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
#define __wait_event_killable(wq, condition) \
___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
/**
* wait_event_killable - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_KILLABLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_killable(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_killable(wq_head, condition); \
__ret; \
})
#define __wait_event_killable_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_KILLABLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_KILLABLE) until the
* @condition evaluates to true or a kill signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
* interrupted by a kill signal.
*
* Only kill signals interrupt this process.
*/
#define wait_event_killable_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_killable_timeout(wq_head, \
condition, timeout); \
__ret; \
})
#define __wait_event_lock_irq(wq_head, condition, lock, cmd) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
spin_unlock_irq(&lock); \
cmd; \
schedule(); \
spin_lock_irq(&lock))
/**
* wait_event_lock_irq_cmd - sleep until a condition gets true. The
* condition is checked under the lock. This
* is expected to be called with the lock
* taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before cmd
* and schedule() and reacquired afterwards.
* @cmd: a command which is invoked outside the critical section before
* sleep
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before invoking the cmd and going to sleep and is reacquired
* afterwards.
*/
#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \
do { \
if (condition) \
break; \
__wait_event_lock_irq(wq_head, condition, lock, cmd); \
} while (0)
/**
* wait_event_lock_irq - sleep until a condition gets true. The
* condition is checked under the lock. This
* is expected to be called with the lock
* taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*/
#define wait_event_lock_irq(wq_head, condition, lock) \
do { \
if (condition) \
break; \
__wait_event_lock_irq(wq_head, condition, lock, ); \
} while (0)
#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \
___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \
spin_unlock_irq(&lock); \
cmd; \
schedule(); \
spin_lock_irq(&lock))
/**
* wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
* The condition is checked under the lock. This is expected to
* be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before cmd and
* schedule() and reacquired afterwards.
* @cmd: a command which is invoked outside the critical section before
* sleep
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before invoking the cmd and going to sleep and is reacquired
* afterwards.
*
* The macro will return -ERESTARTSYS if it was interrupted by a signal
* and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \
({ \
int __ret = 0; \
if (!(condition)) \
__ret = __wait_event_interruptible_lock_irq(wq_head, \
condition, lock, cmd); \
__ret; \
})
/**
* wait_event_interruptible_lock_irq - sleep until a condition gets true.
* The condition is checked under the lock. This is expected
* to be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*
* The macro will return -ERESTARTSYS if it was interrupted by a signal
* and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_lock_irq(wq_head, condition, lock) \
({ \
int __ret = 0; \
if (!(condition)) \
__ret = __wait_event_interruptible_lock_irq(wq_head, \
condition, lock,); \
__ret; \
})
#define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
state, 0, timeout, \
spin_unlock_irq(&lock); \
__ret = schedule_timeout(__ret); \
spin_lock_irq(&lock));
/**
* wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
* true or a timeout elapses. The condition is checked under
* the lock. This is expected to be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*
* The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it
* was interrupted by a signal, and the remaining jiffies otherwise
* if the condition evaluated to true before the timeout elapsed.
*/
#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \
timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_lock_irq_timeout( \
wq_head, condition, lock, timeout, \
TASK_INTERRUPTIBLE); \
__ret; \
})
#define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_lock_irq_timeout( \
wq_head, condition, lock, timeout, \
TASK_UNINTERRUPTIBLE); \
__ret; \
})
/*
* Waitqueues which are removed from the waitqueue_head at wakeup time
*/
void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
#define DEFINE_WAIT_FUNC(name, function) \
struct wait_queue_entry name = { \
.private = current, \
.func = function, \
.entry = LIST_HEAD_INIT((name).entry), \
}
#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)
#define init_wait(wait) \
do { \
(wait)->private = current; \
(wait)->func = autoremove_wake_function; \
INIT_LIST_HEAD(&(wait)->entry); \
(wait)->flags = 0; \
} while (0)
bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg);
#endif /* _LINUX_WAIT_H */