2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-21 11:44:01 +08:00
linux-next/include/linux/wait.h
Johannes Weiner 777c6c5f1f 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 12:56:48 -08:00

518 lines
16 KiB
C

#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
#define WNOHANG 0x00000001
#define WUNTRACED 0x00000002
#define WSTOPPED WUNTRACED
#define WEXITED 0x00000004
#define WCONTINUED 0x00000008
#define WNOWAIT 0x01000000 /* Don't reap, just poll status. */
#define __WNOTHREAD 0x20000000 /* Don't wait on children of other threads in this group */
#define __WALL 0x40000000 /* Wait on all children, regardless of type */
#define __WCLONE 0x80000000 /* Wait only on non-SIGCHLD children */
/* First argument to waitid: */
#define P_ALL 0
#define P_PID 1
#define P_PGID 2
#ifdef __KERNEL__
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/system.h>
#include <asm/current.h>
typedef struct __wait_queue wait_queue_t;
typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int sync, void *key);
int default_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
struct __wait_queue {
unsigned int flags;
#define WQ_FLAG_EXCLUSIVE 0x01
void *private;
wait_queue_func_t func;
struct list_head task_list;
};
struct wait_bit_key {
void *flags;
int bit_nr;
};
struct wait_bit_queue {
struct wait_bit_key key;
wait_queue_t wait;
};
struct __wait_queue_head {
spinlock_t lock;
struct list_head task_list;
};
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, \
.task_list = { NULL, NULL } }
#define DECLARE_WAITQUEUE(name, tsk) \
wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk)
#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.task_list = { &(name).task_list, &(name).task_list } }
#define DECLARE_WAIT_QUEUE_HEAD(name) \
wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \
{ .flags = word, .bit_nr = bit, }
extern void init_waitqueue_head(wait_queue_head_t *q);
#ifdef CONFIG_LOCKDEP
# define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
({ init_waitqueue_head(&name); name; })
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
wait_queue_head_t 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(wait_queue_t *q, struct task_struct *p)
{
q->flags = 0;
q->private = p;
q->func = default_wake_function;
}
static inline void init_waitqueue_func_entry(wait_queue_t *q,
wait_queue_func_t func)
{
q->flags = 0;
q->private = NULL;
q->func = func;
}
static inline int waitqueue_active(wait_queue_head_t *q)
{
return !list_empty(&q->task_list);
}
extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait);
extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
{
list_add(&new->task_list, &head->task_list);
}
/*
* Used for wake-one threads:
*/
static inline void __add_wait_queue_tail(wait_queue_head_t *head,
wait_queue_t *new)
{
list_add_tail(&new->task_list, &head->task_list);
}
static inline void __remove_wait_queue(wait_queue_head_t *head,
wait_queue_t *old)
{
list_del(&old->task_list);
}
void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, int sync, void *key);
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
void __wake_up_bit(wait_queue_head_t *, void *, int);
int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
void wake_up_bit(void *, int);
int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned);
int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned);
wait_queue_head_t *bit_waitqueue(void *, int);
#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)
#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, 1)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* macro to avoid include hell
*/
#define wake_up_nested(x, s) \
do { \
unsigned long flags; \
\
spin_lock_irqsave_nested(&(x)->lock, flags, (s)); \
wake_up_locked(x); \
spin_unlock_irqrestore(&(x)->lock, flags); \
} while (0)
#else
#define wake_up_nested(x, s) wake_up(x)
#endif
#define __wait_event(wq, condition) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
schedule(); \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* wait_event - 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_UNINTERRUPTIBLE) until the
* @condition evaluates to true. 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.
*/
#define wait_event(wq, condition) \
do { \
if (condition) \
break; \
__wait_event(wq, condition); \
} while (0)
#define __wait_event_timeout(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
ret = schedule_timeout(ret); \
if (!ret) \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* wait_event_timeout - 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, 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 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 the @timeout elapsed, and the remaining
* jiffies if the condition evaluated to true before the timeout elapsed.
*/
#define wait_event_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_timeout(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* wait_event_interruptible - 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.
*
* 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, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible_timeout(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
ret = schedule_timeout(ret); \
if (!ret) \
break; \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* wait_event_interruptible_timeout - 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, 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 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 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_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_interruptible_timeout(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible_exclusive(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait_exclusive(&wq, &__wait, \
TASK_INTERRUPTIBLE); \
if (condition) { \
finish_wait(&wq, &__wait); \
break; \
} \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
abort_exclusive_wait(&wq, &__wait, \
TASK_INTERRUPTIBLE, NULL); \
break; \
} \
} while (0)
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible_exclusive(wq, condition, __ret);\
__ret; \
})
#define __wait_event_killable(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_KILLABLE); \
if (condition) \
break; \
if (!fatal_signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* wait_event_killable - 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_KILLABLE) 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 will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_killable(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_killable(wq, condition, __ret); \
__ret; \
})
/*
* Must be called with the spinlock in the wait_queue_head_t held.
*/
static inline void add_wait_queue_exclusive_locked(wait_queue_head_t *q,
wait_queue_t * wait)
{
wait->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_tail(q, wait);
}
/*
* Must be called with the spinlock in the wait_queue_head_t held.
*/
static inline void remove_wait_queue_locked(wait_queue_head_t *q,
wait_queue_t * wait)
{
__remove_wait_queue(q, wait);
}
/*
* These are the old interfaces to sleep waiting for an event.
* They are racy. DO NOT use them, use the wait_event* interfaces above.
* We plan to remove these interfaces.
*/
extern void sleep_on(wait_queue_head_t *q);
extern long sleep_on_timeout(wait_queue_head_t *q,
signed long timeout);
extern void interruptible_sleep_on(wait_queue_head_t *q);
extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
signed long timeout);
/*
* Waitqueues which are removed from the waitqueue_head at wakeup time
*/
void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
unsigned int mode, void *key);
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
#define DEFINE_WAIT(name) \
wait_queue_t name = { \
.private = current, \
.func = autoremove_wake_function, \
.task_list = LIST_HEAD_INIT((name).task_list), \
}
#define DEFINE_WAIT_BIT(name, word, bit) \
struct wait_bit_queue name = { \
.key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \
.wait = { \
.private = current, \
.func = wake_bit_function, \
.task_list = \
LIST_HEAD_INIT((name).wait.task_list), \
}, \
}
#define init_wait(wait) \
do { \
(wait)->private = current; \
(wait)->func = autoremove_wake_function; \
INIT_LIST_HEAD(&(wait)->task_list); \
} while (0)
/**
* wait_on_bit - wait for a bit to be cleared
* @word: the word being waited on, a kernel virtual address
* @bit: the bit of the word being waited on
* @action: the function used to sleep, which may take special actions
* @mode: the task state to sleep in
*
* There is a standard hashed waitqueue table for generic use. This
* is the part of the hashtable's accessor API that waits on a bit.
* For instance, if one were to have waiters on a bitflag, one would
* call wait_on_bit() in threads waiting for the bit to clear.
* One uses wait_on_bit() where one is waiting for the bit to clear,
* but has no intention of setting it.
*/
static inline int wait_on_bit(void *word, int bit,
int (*action)(void *), unsigned mode)
{
if (!test_bit(bit, word))
return 0;
return out_of_line_wait_on_bit(word, bit, action, mode);
}
/**
* wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
* @word: the word being waited on, a kernel virtual address
* @bit: the bit of the word being waited on
* @action: the function used to sleep, which may take special actions
* @mode: the task state to sleep in
*
* There is a standard hashed waitqueue table for generic use. This
* is the part of the hashtable's accessor API that waits on a bit
* when one intends to set it, for instance, trying to lock bitflags.
* For instance, if one were to have waiters trying to set bitflag
* and waiting for it to clear before setting it, one would call
* wait_on_bit() in threads waiting to be able to set the bit.
* One uses wait_on_bit_lock() where one is waiting for the bit to
* clear with the intention of setting it, and when done, clearing it.
*/
static inline int wait_on_bit_lock(void *word, int bit,
int (*action)(void *), unsigned mode)
{
if (!test_and_set_bit(bit, word))
return 0;
return out_of_line_wait_on_bit_lock(word, bit, action, mode);
}
#endif /* __KERNEL__ */
#endif