Linux Kernel 2.6.9源码分析 -- bind

Linux Kernel 2.6.9源码分析 – bind

先来看下bind API的原型:
int bind(int sockfd, const struct sockaddr *addr, socklen_t addrlen);
参数说明:
sockfd：即socket描述字，它是通过socket()函数创建了，唯一标识一个socket。bind()函数就是将给这个描述字绑定一个名字。
addr：一个const struct sockaddr 指针，指向要绑定给sockfd的协议地址。这个地址结构根据地址创建socket时的地址协议族的不同而不同，如ipv4对应的是：
struct sockaddr_in {
sa_family_t sin_family; / address family: AF_INET /
in_port_t sin_port; / port in network byte order /
struct in_addr sin_addr; / internet address /
};
/ Internet address. /
struct in_addr {
uint32_t s_addr; / address in network byte order */
};
addrlen：对应的是地址的长度。
下面来看下其对应的系统调用如何来bind 地址的.

asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
	int err;

	if((sock = sockfd_lookup(fd,&err))!=NULL)
	{
		if((err=move_addr_to_kernel(umyaddr,addrlen,address))>=0) {
			err = security_socket_bind(sock, (struct sockaddr *)address, addrlen);
			if (err) {
				sockfd_put(sock);
				return err;
			}
			err = sock->ops->bind(sock, (struct sockaddr *)address, addrlen);
		}
		sockfd_put(sock);
	}			
	return err;
}

其中sockfd_lookup函数是通过用户传入的文件描述符fd，找到对应的struct socket结构.通过前一章socket 可知查找步骤如下：
1.在当前进程的描述符中通过fd 找到struct file结构
2.通过file->f_dentry->d_inode inode的地址转换得到struct socket的地址.
接下来再来调用sock->ops->bind，我们来看下AF_INET协议族的TCP的bind如何实现的.
net/ipv4/af_inet.c

struct proto_ops inet_stream_ops = {
	.family =	PF_INET,
	.owner =	THIS_MODULE,
	.release =	inet_release,
	.bind =		inet_bind,
	.connect =	inet_stream_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	inet_accept,
	.getname =	inet_getname,
	.poll =		tcp_poll,
	.ioctl =	inet_ioctl,
	.listen =	inet_listen,
	.shutdown =	inet_shutdown,
	.setsockopt =	sock_common_setsockopt,
	.getsockopt =	sock_common_getsockopt,
	.sendmsg =	inet_sendmsg,
	.recvmsg =	sock_common_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	tcp_sendpage
};

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_opt *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	chk_addr_ret = inet_addr_type(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 &&
	    addr->sin_addr.s_addr != 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->num)
		goto out_release_sock;

	inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->saddr = 0;  /* Use device */

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

	if (inet->rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->sport = htons(inet->num);
	inet->daddr = 0;
	inet->dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}

从tcp_prot结构中来看，并没有定义bind接口，所以sk->sk_prot->bind应该为NULL，所以TCP的bind就是在inet_bind中完成的.

struct proto tcp_prot = {
	.name			= "TCP",
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= tcp_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v4_init_sock,
	.destroy		= tcp_v4_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.sendmsg		= tcp_sendmsg,
	.recvmsg		= tcp_recvmsg,
	.backlog_rcv		= tcp_v4_do_rcv,
	.hash			= tcp_v4_hash,
	.unhash			= tcp_unhash,
	.get_port		= tcp_v4_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.memory_allocated	= &tcp_memory_allocated,
	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_mem		= sysctl_tcp_mem,
	.sysctl_wmem		= sysctl_tcp_wmem,
	.sysctl_rmem		= sysctl_tcp_rmem,
	.max_header		= MAX_TCP_HEADER,
	.slab_obj_size		= sizeof(struct tcp_sock),
};

从这个函数来看，将struct sockaddr_in中的sin_port 通过tcp_v4_get_port函数做一些检查和转换再赋值给inet->sport
而struct sockaddr_in中的sin_addr赋值给inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;