Linux内核--网络协议栈深入分析(五)--套接字的绑定、监听、连接和断开

本文分析基于Linux Kernel 3.2.1

原创作品，转载请标明http://blog.csdn.net/yming0221/article/details/7996528

更多请查看专栏http://blog.csdn.net/column/details/linux-kernel-net.html

作者：闫明

1、套接字的绑定

创建完套接字服务器端会在应用层使用bind函数惊醒套接字的绑定，这时会产生系统调用，sys_bind内核函数进行套接字。

系统调用函数的具体实现

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
		if (err >= 0) {
			err = security_socket_bind(sock,
						   (struct sockaddr *)&address,
						   addrlen);
			if (!err)
				err = sock->ops->bind(sock,
						      (struct sockaddr *)
						      &address, addrlen);
		}
		fput_light(sock->file, fput_needed);
	}
	return err;
}

首先调用函数sockfd_lookup_light()函数通过文件描述符来查找对应的套接字sock。

static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
	struct file *file;
	struct socket *sock;

	*err = -EBADF;
	file = fget_light(fd, fput_needed);
	if (file) {
		sock = sock_from_file(file, err);
		if (sock)
			return sock;
		fput_light(file, *fput_needed);
	}
	return NULL;
}

上面函数中先调用fget_light函数通过文件描述符返回对应的文件结构，然后调用函数sock_from_file函数返回该文件对应的套接字结构体地址，它存储在file->private_data属性中。

再回到sys_bind函数，在返回了对应的套接字结构之后，调用move_addr_to_kernel将用户地址空间的socket拷贝到内核空间。

然后调用INET协议族的操作集中bind函数inet_bind函数将socket地址（内核空间）和socket绑定。

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	//RAW类型套接字若有自己的bind函数，则使用之
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	.....................
        //地址合法性检查
	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
	    !(inet->freebind || inet->transparent) &&
	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	err = -EACCES;
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->inet_num)//如果sk的状态是CLOSE或者本地端口已经被绑定
		goto out_release_sock;

	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;//设置源地址
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->inet_saddr = 0;  /* Use device */

	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
		inet->inet_saddr = inet->inet_rcv_saddr = 0;
		err = -EADDRINUSE;
		goto out_release_sock;
	}

	if (inet->inet_rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)