Linux内核通知链(notifier chain)

1、概述

Linux内核中各个子系统相互依赖，当其中某个子系统状态发生改变时，就必须使用一定的机制告知使用其服务的其他子系统，以便其他子系统采取相应的措施。为满足这样的需求，内核实现了事件通知链机制（notification chain）。
通知链只能用在各个子系统之间，而不能在内核和用户空间进行事件的通知。组成内核的核心系统代码均位于kernel目录下，通知链表位于kernel/notifier.c中，对应的头文件为include/linux/notifier.h。
事件通知链表是一个事件处理函数的列表，每个通知链都与某个或某些事件有关，当特定的事件发生时，就调用相应的事件通知链中的回调函数，进行相应的处理。

2、通知链核心代码

通知链的核心结构体为：

// include\linux\notifier.h
struct notifier_block {
	notifier_fn_t notifier_call;
	struct notifier_block __rcu *next;
	int priority;
};

// kernel\notifier.c

/*
 *	Notifier chain core routines.  The exported routines below
 *	are layered on top of these, with appropriate locking added.
 */

static int notifier_chain_register(struct notifier_block **nl,
		struct notifier_block *n)
{
	while ((*nl) != NULL) {
		if (n->priority > (*nl)->priority)
			break;
		nl = &((*nl)->next);
	}
	n->next = *nl;
	rcu_assign_pointer(*nl, n);
	return 0;
}

static int notifier_chain_cond_register(struct notifier_block **nl,
		struct notifier_block *n)
{
	while ((*nl) != NULL) {
		if ((*nl) == n)
			return 0;
		if (n->priority > (*nl)->priority)
			break;
		nl = &((*nl)->next);
	}
	n->next = *nl;
	rcu_assign_pointer(*nl, n);
	return 0;
}

static int notifier_chain_unregister(struct notifier_block **nl,
		struct notifier_block *n)
{
	while ((*nl) != NULL) {
		if ((*nl) == n) {
			rcu_assign_pointer(*nl, n->next);
			return 0;
		}
		nl = &((*nl)->next);
	}
	return -ENOENT;
}

/**
 * notifier_call_chain - Informs the registered notifiers about an event.
 *	@nl:		Pointer to head of the blocking notifier chain
 *	@val:		Value passed unmodified to notifier function
 *	@v:		Pointer passed unmodified to notifier function
 *	@nr_to_call:	Number of notifier functions to be called. Don't care
 *			value of this parameter is -1.
 *	@nr_calls:	Records the number of notifications sent. Don't care
 *			value of this field is NULL.
 *	@returns:	notifier_call_chain returns the value returned by the
 *			last notifier function called.
 */
static int notifier_call_chain(struct notifier_block **nl,
			       unsigned long val, void *v,
			       int nr_to_call, int *nr_calls)
{
	int ret = NOTIFY_DONE;
	struct notifier_block *nb, *next_nb;

	nb = rcu_dereference_raw(*nl);

	while (nb && nr_to_call) {
		next_nb = rcu_dereference_raw(nb->next);

#ifdef CONFIG_DEBUG_NOTIFIERS
		if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
			WARN(1, "Invalid notifier called!");
			nb = next_nb;
			continue;
		}
#endif
		ret = nb->notifier_call(nb, val, v);

		if (nr_calls)
			(*nr_calls)++;

		if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK)
			break;
		nb = next_nb;
		nr_to_call--;
	}
	return ret;
}
NOKPROBE_SYMBOL(notifier_call_chain);

由notifier_chain_register可知，将目标通知块添加到通知链表中。原理是：
首先将目标通知块的next指向链表头中的通知块。然后将目标通知块放入链表头中。
由notifier_chain_cond_register可知，只有目标通知块不在通知链表中时，才会将通知块添加到通知链表中。
由notifier_call_chain可知，当调用notifier_call_chain时，会遍历通知链中的通知块，并依次调用其中的回调函数，发送相应的通知信息。

3、通知链分类

通知链总共分4种：

1）Atomic notifier chains（原子通知链）：

通知链的回调函数（当事件发生时要执行的函数）在中断上下文中运行，不允许阻塞。
相关函数和结构体：

// include\linux\notifier.h
struct atomic_notifier_head {
	spinlock_t lock;
	struct notifier_block __rcu *head;
};

#define ATOMIC_NOTIFIER_INIT(name) {				\
		.lock = __SPIN_LOCK_UNLOCKED(name.lock),	\
		.head = NULL }

#define ATOMIC_NOTIFIER_HEAD(name)				\
	struct atomic_notifier_head name =			\
		ATOMIC_NOTIFIER_INIT(name)

ATOMIC_NOTIFIER_HEAD用于初始化atomic_notifier_head 结构体。

// kernel\notifier.c
/*
 *	Atomic notifier chain routines.  Registration and unregistration
 *	use a spinlock, and call_chain is synchronized by RCU (no locks).
 */

/**
 *	atomic_notifier_chain_register - Add notifier to an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to an atomic notifier chain.
 *
 *	Currently always returns zero.
 */
int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
		struct notifier_block *n)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&nh->lock, flags);
	ret = notifier_chain_register(&nh->head, n);
	spin_unlock_irqrestore(&nh->lock, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);

/**
 *	atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from an atomic notifier chain.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
		struct notifier_block *n)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&nh->lock, flags);
	ret = notifier_chain_unregister(&nh->head, n);
	spin_unlock_irqrestore(&nh->lock, flags);
	synchronize_rcu();
	return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);

/**
 *	__atomic_notifier_call_chain - Call functions in an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *	@nr_to_call: See the comment for notifier_call_chain.
 *	@nr_calls: See the comment for notifier_call_chain.
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in an atomic context, so they must not block.
 *	This routine uses RCU to synchronize with changes to the chain.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then atomic_notifier_call_chain()
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */
int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
				 unsigned long val, void *v,
				 int nr_to_call, int *nr_calls)
{
	int ret;

	rcu_read_lock();
	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain);
NOKPROBE_SYMBOL(__atomic_notifier_call_chain);

int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
			       unsigned long val, void *v)
{
	return __atomic_notifier_call_chain(nh, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
NOKPROBE_SYMBOL(atomic_notifier_call_chain);

@nh： 通知的链表头
@val：传给回调函数的值，可以定义为通知类型值。
@v: 传给回调函数的指针，可以是任何需要传输的数据。

2）Blocking notifier chains（可阻塞通知链）：

通知链中通知块的回调函数在进程上下文中运行，允许阻塞。

// include\linux\notifier.h

struct blocking_notifier_head {
	struct rw_semaphore rwsem;
	struct notifier_block __rcu *head;
};

#define BLOCKING_NOTIFIER_INIT(name) {				\
		.rwsem = __RWSEM_INITIALIZER((name).rwsem),	\
		.head = NULL }

#define BLOCKING_NOTIFIER_HEAD(name)				\
	struct blocking_notifier_head name =			\
		BLOCKING_NOTIFIER_INIT(name)
		

// kernel\notifier.c

/*
 *	Blocking notifier chain routines.  All access to the chain is
 *	synchronized by an rwsem.
 */

/**
 *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a blocking notifier chain.
 *	Must be called in process context.
 *
 *	Currently always returns zero.
 */
int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call down_write().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_register(&nh->head, n);

	down_write(&nh->rwsem);
	ret = notifier_chain_register(&nh->head, n);
	up_write(&nh->rwsem);
	return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);

/**
 *	blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a blocking notifier chain, only if not already
 *	present in the chain.
 *	Must be called in process context.
 *
 *	Currently always returns zero.
 */
int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	down_write(&nh->rwsem);
	ret = notifier_chain_cond_register(&nh->head, n);
	up_write(&nh->rwsem);
	return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register);

/**
 *	blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from a blocking notifier chain.
 *	Must be called from process context.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call down_write().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_unregister(&nh->head, n);

	down_write(&nh->rwsem);
	ret = notifier_chain_unregister(&nh->head, n);
	up_write(&nh->rwsem);
	return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);

/**
 *	__blocking_notifier_call_chain - Call functions in a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *	@nr_to_call: See comment for notifier_call_chain.
 *	@nr_calls: See comment for notifier_call_chain.
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in a process context, so they are allowed to block.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then blocking_notifier_call_chain()
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */
int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
				   unsigned long val, void *v,
				   int nr_to_call, int *nr_calls)
{
	int ret = NOTIFY_DONE;

	/*
	 * We check the head outside the lock, but if this access is
	 * racy then it does not matter what the result of the test
	 * is, we re-check the list after having taken the lock anyway:
	 */
	if (rcu_access_pointer(nh->head)) {
		down_read(&nh->rwsem);
		ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
					nr_calls);
		up_read(&nh->rwsem);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(__blocking_notifier_call_chain);

int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
		unsigned long val, void *v)
{
	return __blocking_notifier_call_chain(nh, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);

3）Raw notifier chains（原始通知链）：

对通知链中的通知块元素的回调函数没有任何限制，所有锁和保护机制都由调用者维护。

// include\linux\notifier.h
struct raw_notifier_head {
	struct notifier_block __rcu *head;
};
#define RAW_INIT_NOTIFIER_HEAD(name) do {	\
		(name)->head = NULL;		\
	} while (0)

#define RAW_NOTIFIER_INIT(name)	{				\
		.head = NULL }

// kernel\notifier.c

/*
 *	Raw notifier chain routines.  There is no protection;
 *	the caller must provide it.  Use at your own risk!
 */

/**
 *	raw_notifier_chain_register - Add notifier to a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a raw notifier chain.
 *	All locking must be provided by the caller.
 *
 *	Currently always returns zero.
 */
int raw_notifier_chain_register(struct raw_notifier_head *nh,
		struct notifier_block *n)
{
	return notifier_chain_register(&nh->head, n);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_register);

/**
 *	raw_notifier_chain_unregister - Remove notifier from a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from a raw notifier chain.
 *	All locking must be provided by the caller.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
		struct notifier_block *n)
{
	return notifier_chain_unregister(&nh->head, n);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);

/**
 *	__raw_notifier_call_chain - Call functions in a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *	@nr_to_call: See comment for notifier_call_chain.
 *	@nr_calls: See comment for notifier_call_chain
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in an undefined context.
 *	All locking must be provided by the caller.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then raw_notifier_call_chain()
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */
int __raw_notifier_call_chain(struct raw_notifier_head *nh,
			      unsigned long val, void *v,
			      int nr_to_call, int *nr_calls)
{
	return notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
}
EXPORT_SYMBOL_GPL(__raw_notifier_call_chain);

int raw_notifier_call_chain(struct raw_notifier_head *nh,
		unsigned long val, void *v)
{
	return __raw_notifier_call_chain(nh, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(raw_notifier_call_chain);

4)SRCU notifier chains

可阻塞通知链的一种变体。拥有相同的约数条件。
srcu_notifier_call_chain（）中的开销非常低：没有缓存反弹，也没有内存屏障。 作为补偿，srcu_notifier_chain_unregister（）相当昂贵。 SRCU用于通知链经常被调用而同时有很少删除notifier_blocks的情况。 同样，SRCU通知链使用起来更加复杂，因为它们需要特殊的运行时初始化。

// include\linux\notifier.h
struct srcu_notifier_head {
	struct mutex mutex;
	struct srcu_struct srcu;
	struct notifier_block __rcu *head;
};
/* srcu_notifier_heads must be initialized and cleaned up dynamically */
/* srcu_notifier_heads cannot be initialized statically */
extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
#define srcu_cleanup_notifier_head(name)	\
		cleanup_srcu_struct(&(name)->srcu);

// kernel\notifier.c
/*
 *	SRCU notifier chain routines.    Registration and unregistration
 *	use a mutex, and call_chain is synchronized by SRCU (no locks).
 */

/**
 *	srcu_notifier_chain_register - Add notifier to an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to an SRCU notifier chain.
 *	Must be called in process context.
 *
 *	Currently always returns zero.
 */
int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call mutex_lock().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_register(&nh->head, n);

	mutex_lock(&nh->mutex);
	ret = notifier_chain_register(&nh->head, n);
	mutex_unlock(&nh->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_register);

/**
 *	srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from an SRCU notifier chain.
 *	Must be called from process context.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call mutex_lock().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_unregister(&nh->head, n);

	mutex_lock(&nh->mutex);
	ret = notifier_chain_unregister(&nh->head, n);
	mutex_unlock(&nh->mutex);
	synchronize_srcu(&nh->srcu);
	return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);

/**
 *	__srcu_notifier_call_chain - Call functions in an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *	@nr_to_call: See comment for notifier_call_chain.
 *	@nr_calls: See comment for notifier_call_chain
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in a process context, so they are allowed to block.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then srcu_notifier_call_chain()
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */
int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
			       unsigned long val, void *v,
			       int nr_to_call, int *nr_calls)
{
	int ret;
	int idx;

	idx = srcu_read_lock(&nh->srcu);
	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
	srcu_read_unlock(&nh->srcu, idx);
	return ret;
}
EXPORT_SYMBOL_GPL(__srcu_notifier_call_chain);

int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
		unsigned long val, void *v)
{
	return __srcu_notifier_call_chain(nh, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);

/**
 *	srcu_init_notifier_head - Initialize an SRCU notifier head
 *	@nh: Pointer to head of the srcu notifier chain
 *
 *	Unlike other sorts of notifier heads, SRCU notifier heads require
 *	dynamic initialization.  Be sure to call this routine before
 *	calling any of the other SRCU notifier routines for this head.
 *
 *	If an SRCU notifier head is deallocated, it must first be cleaned
 *	up by calling srcu_cleanup_notifier_head().  Otherwise the head's
 *	per-cpu data (used by the SRCU mechanism) will leak.
 */
void srcu_init_notifier_head(struct srcu_notifier_head *nh)
{
	mutex_init(&nh->mutex);
	if (init_srcu_struct(&nh->srcu) < 0)
		BUG();
	nh->head = NULL;
}
EXPORT_SYMBOL_GPL(srcu_init_notifier_head);

4、通知链的使用

以原子通知链为例说明。
1）初始化定义通知链，使用如下函数。

#define ATOMIC_NOTIFIER_HEAD(name)				\
	struct atomic_notifier_head name =			\
		ATOMIC_NOTIFIER_INIT(name)

2）注册通知链，这里需要提前初始化一个通知链的通知块，在注册的时候添加到通知链中。

int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
		struct notifier_block *nb);

这里的nb只需要提前初始化好回调函数即可。
例如：

	fault_nb.notifier_call = direct_charge_fault_notifier_call;
	ret = atomic_notifier_chain_register(&direct_charge_sc_fault_notifier_list, &fault_nb);

这里面要提前定义好回调函数。
3）然后在需要的地方发送通知即可。调用

int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
		unsigned long val, void *v);

这里面atomic_notifier_head 是之前定义好的通知链。val是传给回调函数的值。v是传给回调函数的指针，可以是任何类型的数据结构的指针。
注意
如果需要在多个模块中使用通知链，可以在通知链定义模块中添加获取通知链的接口函数，将其声明在头文件中，然后其他模块通过这个接口，获取该通知链，就可以使用该通知链了。