socket 源码阅读 - bind

[junnplus]

// net/socket.c
/*
 *	Bind a name to a socket. Nothing much to do here since it's
 *	the protocol's responsibility to handle the local address.
 *
 *	We move the socket address to kernel space before we call
 *	the protocol layer (having also checked the address is ok).
 */

int __sys_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, &address);
		if (!err) {
			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;
}

__sys_bind 先将参数 fd 转换为 socket 指针，然后调用 socket 指针对应类型的 sock->bind 函数。

对于流套接字的 INET 协议族，sock->ops->bind 指向 inet_bind 函数。

// net/ipv4/af_inet.c
const struct proto_ops inet_stream_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
...
}

[junnplus]

sockfd_lookup_light

// net/socket.c
static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
	struct fd f = fdget(fd);
	struct socket *sock;

	*err = -EBADF;
	if (f.file) {
		sock = sock_from_file(f.file, err);
		if (likely(sock)) {
			*fput_needed = f.flags;
			return sock;
		}
		fdput(f);
	}
	return NULL;
}

• fdget 函数获取 fd 对应的文件指针。
• sock_from_file 获取文件指针绑定的 socket 指针。

// net/socket.c
/**
 *	sock_from_file - Return the &socket bounded to @file.
 *	@file: file
 *	@err: pointer to an error code return
 *
 *	On failure returns %NULL and assigns -ENOTSOCK to @err.
 */

struct socket *sock_from_file(struct file *file, int *err)
{
	if (file->f_op == &socket_file_ops)
		return file->private_data;	/* set in sock_map_fd */

	*err = -ENOTSOCK;
	return NULL;
}

在前面 socket 系统调用的时候，会为新创建的 socket 关联一个文件指针。

// net/socket.c - sock_alloc_file
	sock->file = file;
	file->private_data = sock;

[junnplus]

inet_bind

// net/ipv4/af_inet.c

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sock *sk = sock->sk;
	int err;

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

...
	return __inet_bind(sk, uaddr, addr_len, false, true);
}

int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
		bool force_bind_address_no_port, bool with_lock)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	unsigned short snum;
	int chk_addr_ret;
	u32 tb_id = RT_TABLE_LOCAL;
	int err;

	if (addr->sin_family != AF_INET) {
		/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
		 * only if s_addr is INADDR_ANY.
		 */
		err = -EAFNOSUPPORT;
		if (addr->sin_family != AF_UNSPEC ||
		    addr->sin_addr.s_addr != htonl(INADDR_ANY))
			goto out;
	}

	tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
	chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);

	/* 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 (!inet_can_nonlocal_bind(net, inet) &&
	    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 && inet_port_requires_bind_service(net, snum) &&
	    !ns_capable(net->user_ns, 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.
	 */
	if (with_lock)
		lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->inet_num)
		goto out_release_sock;

	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
	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 (snum || !(inet->bind_address_no_port ||
		      force_bind_address_no_port)) {
		if (sk->sk_prot->get_port(sk, snum)) {
			inet->inet_saddr = inet->inet_rcv_saddr = 0;
			err = -EADDRINUSE;
			goto out_release_sock;
		}
		err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
		if (err) {
			inet->inet_saddr = inet->inet_rcv_saddr = 0;
			goto out_release_sock;
		}
	}

	if (inet->inet_rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->inet_sport = htons(inet->inet_num);
	inet->inet_daddr = 0;
	inet->inet_dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	if (with_lock)
		release_sock(sk);
out:
	return err;
}