作者最近还在研究waitqueue，本文可能还有点问题，没搞全。这里先简单的笔记下吧，占个坑~
CONTENTS
wait.h
#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/config.h>
#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);
/*默认的唤醒回调函数*/
int default_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
/* 等待队列中的单个元素 */
struct __wait_queue {
unsigned int flags;
#define WQ_FLAG_EXCLUSIVE 0x01
struct task_struct * task; /* 等待的任务 */
wait_queue_func_t func; /* 唤醒后的回调函数 */
struct list_head task_list;/* 元素在链表中 */
};
/* 等待某一位时使用的等待子元素 */
struct wait_bit_key {
void *flags; /*该位所在的地址*/
int bit_nr; /* 该位的偏移量 */
};
/* 等待队列中的单个元素 */
struct wait_bit_queue {
struct wait_bit_key key;
wait_queue_t wait;
};
/* 等待队列头 */
struct __wait_queue_head {
spinlock_t lock; /* 等待队列是一个链表，该锁用来锁定链表操作 */
struct list_head task_list; /* 链表头 */
};
typedef struct __wait_queue_head wait_queue_head_t;
/*
* Macros for declaration and initialisaton of the datatypes
*/
/* 初始化一个等待队列元素 */
#define __WAITQUEUE_INITIALIZER(name, tsk) { \
.task = tsk, \
.func = default_wake_function, \ /* 默认唤醒回调函数 */
.task_list = { NULL, NULL } } /* 元素不在任何一个链表中 */
#define DECLARE_WAITQUEUE(name, tsk) \
wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk)
/* 使用一个等待队列元素初始化一个等待队列，其实是初始化一个链表头 */
#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \
.lock = SPIN_LOCK_UNLOCKED, \
.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, }
/* 初始化一个等待队列 */
static inline void init_waitqueue_head(wait_queue_head_t *q)
{
q->lock = SPIN_LOCK_UNLOCKED;
INIT_LIST_HEAD(&q->task_list);
}
/* 初始化一个等待队列元素指针 */
static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
{
q->flags = 0;
q->task = p;
q->func = default_wake_function;/* 使用默认回调函数 */
}
/* 使用自定义回调函数初始化一个等待队列元素 */
static inline void init_waitqueue_func_entry(wait_queue_t *q,
wait_queue_func_t func)
{
q->flags = 0;
q->task = NULL;
q->func = func;
}
/* 判断一个等待队列是否有效，通过判断里面是否还有等待元素 */
static inline int waitqueue_active(wait_queue_head_t *q)
{
return !list_empty(&q->task_list);
}
/*
* Used to distinguish between sync and async io wait context:
* sync i/o typically specifies a NULL wait queue entry or a wait
* queue entry bound to a task (current task) to wake up.
* aio specifies a wait queue entry with an async notification
* callback routine, not associated with any task.
*/
#define is_sync_wait(wait) (!(wait) || ((wait)->task))
extern void FASTCALL(add_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
extern void FASTCALL(add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t * wait));
extern void FASTCALL(remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
/* 将一个元素新加入到等待队列中 */
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:
*/
/* 将一个元素新加入到等待队列中,加入队尾 */
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);
}
/*将一个等待队列元素从队列中移除*/
static inline void __remove_wait_queue(wait_queue_head_t *head,
wait_queue_t *old)
{
list_del(&old->task_list);
}
void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key));
extern void FASTCALL(__wake_up_locked(wait_queue_head_t *q, unsigned int mode));
extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr));
void FASTCALL(__wake_up_bit(wait_queue_head_t *, void *, int));
int FASTCALL(__wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned));
int FASTCALL(__wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned));
void FASTCALL(wake_up_bit(void *, int));
int FASTCALL(out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned));
int FASTCALL(out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned));
wait_queue_head_t *FASTCALL(bit_waitqueue(void *, int));
#define wake_up(x) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_nr(x, nr) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, nr, NULL)
#define wake_up_all(x) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 0, NULL)
#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_locked(x) __wake_up_locked((x), TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE)
#define wake_up_interruptible_sync(x) __wake_up_sync((x),TASK_INTERRUPTIBLE, 1)
/* 等待某一事件响应 */
#define __wait_event(wq, condition) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \ /* 这里的实现没有超时 */
/* 等待时不可被中断打断 */
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \ /* 条件满足才会跳出 */
break; \
schedule(); \ /* 这里就开始休眠了，如果条件不满足，而且被意外唤醒（？？），那么继续循环 */
} \
finish_wait(&wq, &__wait); \ /* 完成等待 */
} while (0)
#define wait_event(wq, condition) \
do { \
if (condition) \ /* 在进入等待前先判断下，如果条件满足就不用等了 */
break; \
__wait_event(wq, condition); \
} while (0)
/* 加入超时后的等待事件响应 */
#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); \ /* 让出CPU */
if (!ret) \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
#define wait_event_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_timeout(wq, condition, __ret); \
__ret; \
})
/* 可被中断打断的等待事件响应 */
#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)
#define wait_event_interruptible(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible(wq, condition, __ret); \
__ret; \
})
/* 加入超时后的等待事件响应，也可被中断打断 */
#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)
#define wait_event_interruptible_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_interruptible_timeout(wq, condition, __ret); \
__ret; \
})
/* 加入互斥唤醒的等待，如果有多个任务在等待，这里就唤醒一个 */
#define __wait_event_interruptible_exclusive(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait_exclusive(&wq, &__wait, \
TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible_exclusive(wq, condition, __ret);\
__ret; \
})
/*
* Must be called with the spinlock in the wait_queue_head_t held.
*/
/*
将任务加入等待队列，注意这里是互斥加入
*/
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 during 2.7.
*/
extern void FASTCALL(sleep_on(wait_queue_head_t *q));
extern long FASTCALL(sleep_on_timeout(wait_queue_head_t *q,
signed long timeout));
extern void FASTCALL(interruptible_sleep_on(wait_queue_head_t *q));
extern long FASTCALL(interruptible_sleep_on_timeout(wait_queue_head_t *q,
signed long timeout));
/*
* Waitqueues which are removed from the waitqueue_head at wakeup time
*/
void FASTCALL(prepare_to_wait(wait_queue_head_t *q,
wait_queue_t *wait, int state));
void FASTCALL(prepare_to_wait_exclusive(wait_queue_head_t *q,
wait_queue_t *wait, int state));
void FASTCALL(finish_wait(wait_queue_head_t *q, wait_queue_t *wait));
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);
/*
* 定义一个等待队列元素，这里可以看到task为current，函数为默认的自动移除唤醒函数，
* 唤醒后该元素即被移除出队列。
*/
#define DEFINE_WAIT(name) \
wait_queue_t name = { \
.task = current, \
.func = autoremove_wake_function, \
.task_list = { .next = &(name).task_list, \
.prev = &(name).task_list, \
}, \
}
#define DEFINE_WAIT_BIT(name, word, bit) \
struct wait_bit_queue name = { \
.key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \
.wait = { \
.task = current, \
.func = wake_bit_function, \
.task_list = \
LIST_HEAD_INIT((name).wait.task_list), \
}, \
}
#define init_wait(wait) \
do { \
(wait)->task = 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
wait.c
/*
* Generic waiting primitives.
*
* (C) 2004 William Irwin, Oracle
*/
#include <linux/config.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/wait.h>
#include <linux/hash.h>
/* 将一个等待队列元素添加到等待队列中 */
void fastcall 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);/* 关中断 加锁 */
__add_wait_queue(q, wait); /* 调用内部实现函数 */
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(add_wait_queue);
/* 用互斥方式将一个等待队列元素加入到等待队列中 */
void fastcall 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);
/* 从队列中移除某一个等待元素 */
void fastcall remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
{
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);/* 关中断 加锁 */
__remove_wait_queue(q, wait);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(remove_wait_queue);
/*
* 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 the critical region).
*/
/* 当前进程准备进入等待状态 */
void fastcall
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);
/*
* don't alter the task state if this is just going to
* queue an async wait queue callback
*/
if (is_sync_wait(wait))
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait);
void fastcall
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);
/*
* don't alter the task state if this is just going to
* queue an async wait queue callback
*/
if (is_sync_wait(wait))
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
/* 当前进程结束等待 */
void fastcall 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);
/* 删除自己的回调函数 */
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
/* 首先调用默认的回调函数 */
int ret = default_wake_function(wait, mode, sync, key);
if (ret)
list_del_init(&wait->task_list);/* 然后将该等待队列元素从队列中删除 */
return ret;
}
EXPORT_SYMBOL(autoremove_wake_function);
/* 使用bit校验的唤醒回调函数 */
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);
/* 如果指定的位校验不通过，就直接返回 */
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.
*/
/* 等待某一位为真时进行回调函数响应 */
int __sched fastcall
__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
int (*action)(void *), 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.flags);
} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);/* 不停的循环检测 */
finish_wait(wq, &q->wait);
return ret;
}
EXPORT_SYMBOL(__wait_on_bit);
int __sched fastcall out_of_line_wait_on_bit(void *word, int bit,
int (*action)(void *), 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 fastcall
__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
int (*action)(void *), unsigned mode)
{
int ret = 0;
do {
prepare_to_wait_exclusive(wq, &q->wait, mode);
if (test_bit(q->key.bit_nr, q->key.flags)) {
if ((ret = (*action)(q->key.flags)))
break;
}
} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
finish_wait(wq, &q->wait);
return ret;
}
EXPORT_SYMBOL(__wait_on_bit_lock);
int __sched fastcall out_of_line_wait_on_bit_lock(void *word, int bit,
int (*action)(void *), 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 fastcall __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_INTERRUPTIBLE|TASK_UNINTERRUPTIBLE, 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_clear_bit(), 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 fastcall wake_up_bit(void *word, int bit)
{
__wake_up_bit(bit_waitqueue(word, bit), word, bit);
}
EXPORT_SYMBOL(wake_up_bit);
fastcall 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);
发表评论