网络篇之bind

网络篇之socket

bind函数用来设置套接字监听的ip和端口，内核代码如下：

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, &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;
}

sockfd_lookup_light根据fd搜索current->files->fdt，找到对应的struct file，再找到struct socket。这里就不继续分析了。

move_addr_to_kernel是将用户空间的数据，拷贝到内核空间。

sock->ops->bind执行绑定动作。

ops最终指向全局数据static struct inet_protosw inetsw_array[]中的ops，本文主要分析tcp的创建过程，因此ops指向的是inet_stream_ops。

const 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,

... ...

};

由上面可知，sock->ops->bind指向的是inet_bind。下面看下inet_bind的代码：

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);
	struct net *net = sock_net(sk);
	unsigned short snum;
	int chk_addr_ret;
	u32 tb_id = RT_TABLE_LOCAL;
	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;
	// 地址长度不合法
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	// 协议簇不合法
	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 (!net->ipv4.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;

	// 如果指定端口，且端口小于1024,调用ns_capable进行权限检查
	if (snum && snum < inet_prot_sock(net) &&
	    !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.
	 */
	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) &&
	    sk->sk_prot->get_port(sk, snum)) { // 指向地址端口的绑定，实际执行的是inet_csk_get_port
		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)
		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:
	release_sock(sk);
out:
	return err;
}

函数进行的一系列的检查后，调用sk->sk_prot->get_port(指向inet_csk_get_port) 执行绑定操作。

int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
	int ret = 1, port = snum;
	struct inet_bind_hashbucket *head;
	struct net *net = sock_net(sk);
	struct inet_bind_bucket *tb = NULL;
	kuid_t uid = sock_i_uid(sk);

	// 如果端口为0,则随机选择一个端口
	if (!port) {
		head = inet_csk_find_open_port(sk, &tb, &port);
		if (!head)
			return ret;
		if (!tb)
			goto tb_not_found;
		goto success;
	}
	head = &hinfo->bhash[inet_bhashfn(net, port,
					  hinfo->bhash_size)];
	spin_lock_bh(&head->lock);
	inet_bind_bucket_for_each(tb, &head->chain)
		if (net_eq(ib_net(tb), net) && tb->port == port)
			goto tb_found;
tb_not_found:
	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
				     net, head, port);
	if (!tb)
		goto fail_unlock;
tb_found:
	if (!hlist_empty(&tb->owners)) {
		if (sk->sk_reuse == SK_FORCE_REUSE)
			goto success;

		if ((tb->fastreuse > 0 && reuse) ||
		    sk_reuseport_match(tb, sk))
			goto success;
		if (inet_csk_bind_conflict(sk, tb, true, true))
			goto fail_unlock;
	}
success:
	if (hlist_empty(&tb->owners)) {
		tb->fastreuse = reuse;
		if (sk->sk_reuseport) {
			tb->fastreuseport = FASTREUSEPORT_ANY;
			tb->fastuid = uid;
			tb->fast_rcv_saddr = sk->sk_rcv_saddr; // 本地Ipv4地址
			tb->fast_ipv6_only = ipv6_only_sock(sk);
			tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
		} else {
			tb->fastreuseport = 0;
		}
	} else {
		if (!reuse)
			tb->fastreuse = 0;
		if (sk->sk_reuseport) {

			// 检查是否可重用
			if (!sk_reuseport_match(tb, sk)) {
				tb->fastreuseport = FASTREUSEPORT_STRICT;
				tb->fastuid = uid;
				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
				tb->fast_ipv6_only = ipv6_only_sock(sk);
				tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
			}
		} else {
			tb->fastreuseport = 0;
		}
	}
	if (!inet_csk(sk)->icsk_bind_hash)
		inet_bind_hash(sk, tb, port);
	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
	ret = 0;

fail_unlock:
	spin_unlock_bh(&head->lock);
	return ret;
}

如果传入端口为 0,则随机选择一个端口，否则绑定指定的端口。

下面的变量head需要重点关注:

struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;

struct inet_bind_hashbucket *head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)];

首先变量head，检查指定端口是否已经创建，没有创建，则调用inet_bind_bucket_create创建。

端口已经绑定时，tb->owners不为空，需要检查端口是否可以重用。

新创建的绑定信息，struct inet_connection_sock->icsk_bind_hash为空，调用inet_bind_hash保存绑定信息。

void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
		    const unsigned short snum)
{
	inet_sk(sk)->inet_num = snum; // 端口
	sk_add_bind_node(sk, &tb->owners); // hlist_add_head(&sk->sk_bind_node, list);
	inet_csk(sk)->icsk_bind_hash = tb;
}

tb被添加到sk->sk_bind_node列表中，同时赋给了struct inet_connection_sock->icsk_bind_hash。

在inet_bind最后，调用sk_dst_reset删除sk缓存的路由信息，至此bind分析结束。