epoll之ep_insert()源码分析

原文链接： ordeder http://blog.csdn.net/ordeder/article/details/25514043

参考：http://www.cnblogs.com/apprentice89/p/3234677.html

ep_insert()过程中涉及的数据结构及回调函数如下图所示：

其中，红色部分回调函数构造了红色部分的结构体，该部分回调由ep_item_poll函数使用（貌似就是回调了ep_ptable_queue_proc）不知道为何要这么绕？。而黄色部分结构体主要由init_poll_funcptr和主函数ep_insert构造，该部分数据结构主要由目标fd的wait queue相关。

具体源码表在下面，重点环节已标出，以后有空再完善吧~

struct epoll_event {
	__u32 events;
	__u64 data;
} EPOLL_PACKED;

struct epitem {
	union {
		/* RB tree node links this structure to the eventpoll RB tree */
		struct rb_node rbn;
		/* Used to free the struct epitem */
		struct rcu_head rcu;
	};

	/* List header used to link this structure to the eventpoll ready list */
	struct list_head rdllink;

	/*
	 * Works together "struct eventpoll"->ovflist in keeping the
	 * single linked chain of items.
	 */
	struct epitem *next;

	/* The file descriptor information this item refers to */
	struct epoll_filefd ffd;

	/* Number of active wait queue attached to poll operations */
	int nwait;

	/* List containing poll wait queues */
	struct list_head pwqlist;

	/* The "container" of this item */
	struct eventpoll *ep;

	/* List header used to link this item to the "struct file" items list */
	struct list_head fllink;

	/* wakeup_source used when EPOLLWAKEUP is set */
	struct wakeup_source __rcu *ws;

	/* The structure that describe the interested events and the source fd */
	struct epoll_event event;
};

struct eventpoll {
	/* Protect the access to this structure */
	spinlock_t lock;

	/*
	 * This mutex is used to ensure that files are not removed
	 * while epoll is using them. This is held during the event
	 * collection loop, the file cleanup path, the epoll file exit
	 * code and the ctl operations.
	 */
	struct mutex mtx;

	/* Wait queue used by sys_epoll_wait() */
	wait_queue_head_t wq;

	/* Wait queue used by file->poll() */
	wait_queue_head_t poll_wait;

	/* List of ready file descriptors */
	struct list_head rdllist;

	/* RB tree root used to store monitored fd structs */
	struct rb_root rbr;

	/*
	 * This is a single linked list that chains all the "struct epitem" that
	 * happened while transferring ready events to userspace w/out
	 * holding ->lock.
	 */
	struct epitem *ovflist;

	/* wakeup_source used when ep_scan_ready_list is running */
	struct wakeup_source *ws;

	/* The user that created the eventpoll descriptor */
	struct user_struct *user;

	struct file *file;

	/* used to optimize loop detection check */
	int visited;
	struct list_head visited_list_link;
};



struct ep_pqueue {
	poll_table pt;        //
	struct epitem *epi;   //主epitem
};

typedef struct poll_table_struct {
	poll_queue_proc _qproc; //事件回调函数
	unsigned long _key;	    //事件位标志(由epi->event.events确定)
} poll_table;

static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
{
	pt->_qproc = qproc;
	pt->_key   = ~0UL; /* all events enabled */
}


/* 等待队列的poll回调的hook*/
struct eppoll_entry {
	struct list_head llink;//链接epitem
	struct epitem *base;    //主epitem
	wait_queue_t wait;      //wait队列的元素
	wait_queue_head_t *whead;//wait队列的对头元素指针
};

struct __wait_queue {
	unsigned int		flags;
#define WQ_FLAG_EXCLUSIVE	0x01
	void			*private;
	wait_queue_func_t	func;
	struct list_head	task_list;
};

=============================================================

static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
		     struct file *tfile, int fd, int full_check)
{
	int error, revents, pwake = 0;
	unsigned long flags;
	long user_watches;
	struct epitem *epi;
	struct ep_pqueue epq;//封装epi和它对应的事件回调函数

	user_watches = atomic_long_read(&ep->user->epoll_watches);
	if (unlikely(user_watches >= max_user_watches))
		return -ENOSPC;
	//为tfd新建一个epitem
	if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
		return -ENOMEM;

	/* Item initialization follow here ... */
	INIT_LIST_HEAD(&epi->rdllink);
	INIT_LIST_HEAD(&epi->fllink);
	INIT_LIST_HEAD(&epi->pwqlist);
	epi->ep = ep;
	ep_set_ffd(&epi->ffd, tfile, fd);
	epi->event = *event;
	epi->nwait = 0;
	epi->next = EP_UNACTIVE_PTR;
	if (epi->event.events & EPOLLWAKEUP) {
		error = ep_create_wakeup_source(epi);
		if (error)
			goto error_create_wakeup_source;
	} else {
		RCU_INIT_POINTER(epi->ws, NULL);
	}

	/* Initialize the poll table using the queue callback */
	epq.epi = epi;
	//【1】
	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);

	/*
	 * Attach the item to the poll hooks and get current event bits.
	 * We can safely use the file* here because its usage count has
	 * been increased by the caller of this function. Note that after
	 * this operation completes, the poll callback can start hitting
	 * the new item.
	 */
	//【2】
	revents = ep_item_poll(epi, &epq.pt);

	/*
	 * We have to check if something went wrong during the poll wait queue
	 * install process. Namely an allocation for a wait queue failed due
	 * high memory pressure.
	 */
	error = -ENOMEM;
	if (epi->nwait < 0)
		goto error_unregister;

	/* Add the current item to the list of active epoll hook for this file */
	spin_lock(&tfile->f_lock);
	list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
	spin_unlock(&tfile->f_lock);

	/*
	 * Add the current item to the RB tree. All RB tree operations are
	 * protected by "mtx", and ep_insert() is called with "mtx" held.
	 */
	ep_rbtree_insert(ep, epi);

	/* now check if we've created too many backpaths */
	error = -EINVAL;
	if (full_check && reverse_path_check())
		goto error_remove_epi;

	/* We have to drop the new item inside our item list to keep track of it */
	spin_lock_irqsave(&ep->lock, flags);

	/* If the file is already "ready" we drop it inside the ready list */
	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
		list_add_tail(&epi->rdllink, &ep->rdllist);
		ep_pm_stay_awake(epi);

		/* Notify waiting tasks that events are available */
		if (waitqueue_active(&ep->wq))
			wake_up_locked(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}

	spin_unlock_irqrestore(&ep->lock, flags);

	atomic_long_inc(&ep->user->epoll_watches);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&ep->poll_wait);

	return 0;

error_remove_epi:
	spin_lock(&tfile->f_lock);
	list_del_rcu(&epi->fllink);
	spin_unlock(&tfile->f_lock);

	rb_erase(&epi->rbn, &ep->rbr);

error_unregister:
	ep_unregister_pollwait(ep, epi);

	/*
	 * We need to do this because an event could have been arrived on some
	 * allocated wait queue. Note that we don't care about the ep->ovflist
	 * list, since that is used/cleaned only inside a section bound by "mtx".
	 * And ep_insert() is called with "mtx" held.
	 */
	spin_lock_irqsave(&ep->lock, flags);
	if (ep_is_linked(&epi->rdllink))
		list_del_init(&epi->rdllink);
	spin_unlock_irqrestore(&ep->lock, flags);

	wakeup_source_unregister(ep_wakeup_source(epi));

error_create_wakeup_source:
	kmem_cache_free(epi_cache, epi);

	return error;
}

=============================================================
[回调函数 ep_ptable_queue_proc]
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
				 poll_table *pt)
{
	struct epitem *epi = ep_item_from_epqueue(pt);  //pt在所属ep_pqueue中的epitem指针
	struct eppoll_entry *pwq;
  //构造eppoll_entry并将其挂到目标文件的wait队列中
	if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
    【1】
    //ep_poll_callback：将该eppoll_entry hook 所描述的epitem挂入eventpoll的就绪队列中
		init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);  
		pwq->whead = whead;
		pwq->base = epi;
		【2】
		//正式将该eppoll_entry挂到目标文件的等待队列中，当文件出发事件后，
		//会依次出发该队列中的每一项(eppoll_entry)的ep_poll_callback
		add_wait_queue(whead, &pwq->wait);
		list_add_tail(&pwq->llink, &epi->pwqlist);
		epi->nwait++;
	} else {
		/* We have to signal that an error occurred */
		epi->nwait = -1;
	}
}

=======================================================================

/*
 * This is the callback that is passed to the wait queue wakeup
 * mechanism. It is called by the stored file descriptors when they
 * have events to report.
 */
 [回调函数 ep_poll_callback]
//该函数由目标文件发生读写时候，依次出发等待队列的回调函数，即该函数。
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	int pwake = 0;
	unsigned long flags;
	struct epitem *epi = ep_item_from_wait(wait);
	struct eventpoll *ep = epi->ep;

	if ((unsigned long)key & POLLFREE) {
		ep_pwq_from_wait(wait)->whead = NULL;
		/*
		 * whead = NULL above can race with ep_remove_wait_queue()
		 * which can do another remove_wait_queue() after us, so we
		 * can't use __remove_wait_queue(). whead->lock is held by
		 * the caller.
		 */
		list_del_init(&wait->task_list);
	}

	spin_lock_irqsave(&ep->lock, flags);

	/*
	 * If the event mask does not contain any poll(2) event, we consider the
	 * descriptor to be disabled. This condition is likely the effect of the
	 * EPOLLONESHOT bit that disables the descriptor when an event is received,
	 * until the next EPOLL_CTL_MOD will be issued.
	 */
	if (!(epi->event.events & ~EP_PRIVATE_BITS))
		goto out_unlock;

	/*
	 * Check the events coming with the callback. At this stage, not
	 * every device reports the events in the "key" parameter of the
	 * callback. We need to be able to handle both cases here, hence the
	 * test for "key" != NULL before the event match test.
	 */
	if (key && !((unsigned long) key & epi->event.events))
		goto out_unlock;

	/*
	 * If we are transferring events to userspace, we can hold no locks
	 * (because we're accessing user memory, and because of linux f_op->poll()
	 * semantics). All the events that happen during that period of time are
	 * chained in ep->ovflist and requeued later on.
	 */
	if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
		if (epi->next == EP_UNACTIVE_PTR) {
      【1】
      //目标文件发生的事件符合 epi要监听的 ，故而将epi加入到eventpoll的ovflist(epitem就绪队列)中
			epi->next = ep->ovflist;
			ep->ovflist = epi;
			if (epi->ws) {
				/*
				 * Activate ep->ws since epi->ws may get
				 * deactivated at any time.
				 */
				__pm_stay_awake(ep->ws);
			}

		}
		goto out_unlock;
	}

	/* If this file is already in the ready list we exit soon */
	if (!ep_is_linked(&epi->rdllink)) {
		list_add_tail(&epi->rdllink, &ep->rdllist);
		ep_pm_stay_awake_rcu(epi);
	}

	/*
	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
	 * wait list.
	 */
	if (waitqueue_active(&ep->wq))
		wake_up_locked(&ep->wq);
	if (waitqueue_active(&ep->poll_wait))
		pwake++;

out_unlock:
	spin_unlock_irqrestore(&ep->lock, flags);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&ep->poll_wait);

	return 1;
}