epoll源码探秘（epoll_create）

epoll源码探秘（epoll_create）

epoll系列的系统函数，很简单，但是很强大。epoll_create(),epoll_ctl() , epoll_wait()，三个就够了。

一些重要的结构：

/*
 * Each file descriptor added to the eventpoll interface will
 * have an entry of this type linked to the "rbr" RB tree.
 * Avoid increasing the size of this struct, there can be many thousands
 * of these on a server and we do not want this to take another cache line.（红黑树单节点）
 */
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 （列表头用于连接结构的eventpoll就绪列表）*/
	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 （关联的文件描述符）*/
	struct epoll_filefd ffd;

	/* Number of active wait queue attached to poll operations (轮询操作)*/
	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 （感兴趣的监控文件描述符的状态）*/
	struct epoll_event event;
};

/*
 * This structure is stored inside the "private_data" member of the file
 * structure and represents（表现）the main data structure for the eventpoll
 * interface.
 */
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() （双链表,epoll文件的等待队列。
	 *调用epoll_wait的进程可能在此队列上睡眠， 等待ep_poll_callback()函数唤醒或超时 
	 */
	wait_queue_head_t wq;

	/* Wait queue used by file->poll() （双链表, poll_wait是eventpoll文件本身的唤醒队列，
	 *该队列上睡眠的进程是等待eventpoll文件本身的某些事件发生
	 */
	wait_queue_head_t poll_wait;

	/* List of ready file descriptors （就绪链表）*/
	struct list_head rdllist;

	/* RB tree root used to store monitored fd structs (存储监听文件描述符结构红黑树根节点)*/
	struct rb_root rbr;

	/*
	 * This is a single linked list（单链表） that chains all the "struct epitem" that
	 * happened while transferring ready events to userspace w/out
	 * holding ->lock.(如果正在向用户空间传递事件，此时状态就绪的文件描述符相关的结构会暂时放在该队列上，
	 * 否则会直接添加到就绪队列rdllist中。)
	 */
	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;
};

epoll_create函数：

         创建一个epoll的句柄。需要注意的是，当创建好epoll句柄后，它就是会占用一个fd值，在linux下如果查看/proc/进程id/fd/，是能够看到这个fd的，所以在使用完epoll后，必须调用close()关闭，否则可能导致fd被耗尽。

int epoll_create(int size);
int epoll_create1(int flags);

第一级：epoll_create()（注意在Linux 2.6.8之后，size参数是被忽略的）

第二级： epoll_create1()

第三级：ep_alloc()创建内部数据(eventpoll)

                 在ep_alloc()中

               1.初始化epoll文件等待队列（双向链表）

               2.初始化eventpoll文件唤醒队列（双向链表）

               3.初始化就绪队列（双向链表）

static inline void INIT_LIST_HEAD(struct list_head *list)
{
	list->next = list;
	list->prev = list;
}

               4.初始化红黑树根节点

#define RB_ROOT	(struct rb_root) { NULL, }
ep->rbr = RB_ROOT;

               5.初始化发生事件红黑树节点链表（单链表）

#define EP_UNACTIVE_PTR ((void *) -1L)
ep->ovflist = EP_UNACTIVE_PTR;

第三级：get_unused_fd_flags()获取一个空闲的文件描述符

第三级：anon_inode_getfile()创建一个匿名文件

第三级：fd_install()将文件与fd建立联系

/*
 * Open an eventpoll file descriptor.
 */
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
	int error, fd;
	struct eventpoll *ep = NULL;
	struct file *file;

	/* Check the EPOLL_* constant for consistency(符合条件EPOLL_CLOEXEC != O_CLOEXEC就报错).  */
	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);

	if (flags & ~EPOLL_CLOEXEC)
		return -EINVAL;
	/*
	 * Create the internal(内部) data structure ("struct eventpoll").
	 */
	error = ep_alloc(&ep);
	if (error < 0)
		return error;
	/*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure and a free file descriptor.
	 *（分配eventpoll实例并初始化,存储在file结构的private_data成员中。 
     * private_data成员用来存储文件描述符真正对应的对象。例如 
     * 如果文件描述符是一个套接字的话，其对应的file实例的private_data 
     * 成员存储的就是一个socket实例。）
	 */
	fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
	if (fd < 0) {
		error = fd;
		goto out_free_ep;
	}
	file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
				 O_RDWR | (flags & O_CLOEXEC));
	if (IS_ERR(file)) {
		error = PTR_ERR(file);
		goto out_free_fd;
	}
	ep->file = file;
	fd_install(fd, file);
	return fd;

out_free_fd:
	put_unused_fd(fd);
out_free_ep:
	ep_free(ep);
	return error;
}

SYSCALL_DEFINE1(epoll_create, int, size)
{
	if (size <= 0)
		return -EINVAL;

	return sys_epoll_create1(0);
}