系统调用accept的实现

linux版本：4.9.51

在APP中，

connfd = accept(listenfd, (struct sockaddr*)&cli_addr, &clilen);

SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
        int __user *, upeer_addrlen, int, flags)
 

/*
 *	For accept, we attempt to create a new socket, set up the link
 *	with the client, wake up the client, then return the new
 *	connected fd. We collect the address of the connector in kernel
 *	space and move it to user at the very end. This is unclean because
 *	we open the socket then return an error.
 *
 *	1003.1g adds the ability to recvmsg() to query connection pending
 *	status to recvmsg. We need to add that support in a way thats
 *	clean when we restucture accept also.
 */

SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen, int, flags)
{
	struct socket *sock, *newsock;
	struct file *newfile;
	int err, len, newfd, fput_needed;
	struct sockaddr_storage address;

	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = -ENFILE;
	// 为client socket分配一个对象，并做一些初始化
	newsock = sock_alloc();
	if (!newsock)
		goto out_put;

	newsock->type = sock->type;
	newsock->ops = sock->ops;

	/*
	 * We don't need try_module_get here, as the listening socket (sock)
	 * has the protocol module (sock->ops->owner) held.
	 */
	__module_get(newsock->ops->owner);

	// 新的file描述符
	newfd = get_unused_fd_flags(flags);
	if (unlikely(newfd < 0)) {
		err = newfd;
		sock_release(newsock);
		goto out_put;
	}
	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
	if (IS_ERR(newfile)) {
		err = PTR_ERR(newfile);
		put_unused_fd(newfd);
		sock_release(newsock);
		goto out_put;
	}

	err = security_socket_accept(sock, newsock);
	if (err)
		goto out_fd;

	// inet_accept
	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
	if (err < 0)
		goto out_fd;

	// 把新的地址返回user space
	if (upeer_sockaddr) {
		if (newsock->ops->getname(newsock, (struct sockaddr *)&address,
					  &len, 2) < 0) {
			err = -ECONNABORTED;
			goto out_fd;
		}
		err = move_addr_to_user(&address,
					len, upeer_sockaddr, upeer_addrlen);
		if (err < 0)
			goto out_fd;
	}

	/* File flags are not inherited via accept() unlike another OSes. */

	// 安装file描述符
	fd_install(newfd, newfile);
	err = newfd;

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
out_fd:
	fput(newfile);
	put_unused_fd(newfd);
	goto out_put;
}

inet_accept

/*
 *	Accept a pending connection. The TCP layer now gives BSD semantics.
 */

int inet_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk1 = sock->sk;
	int err = -EINVAL;

	// sk_prot = tcp_prot
	// accept  = inet_csk_accept
	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);

	if (!sk2)
		goto do_err;

	lock_sock(sk2);

	sock_rps_record_flow(sk2);
	WARN_ON(!((1 << sk2->sk_state) &
		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
		  TCPF_CLOSE_WAIT | TCPF_CLOSE)));

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	err = 0;
	release_sock(sk2);
do_err:
	return err;
}

 

/*
 * Wait for an incoming connection, avoid race conditions. This must be called
 * with the socket locked.
 */
static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	DEFINE_WAIT(wait);
	int err;

	/*
	 * True wake-one mechanism for incoming connections: only
	 * one process gets woken up, not the 'whole herd'.
	 * Since we do not 'race & poll' for established sockets
	 * anymore, the common case will execute the loop only once.
	 *
	 * Subtle issue: "add_wait_queue_exclusive()" will be added
	 * after any current non-exclusive waiters, and we know that
	 * it will always _stay_ after any new non-exclusive waiters
	 * because all non-exclusive waiters are added at the
	 * beginning of the wait-queue. As such, it's ok to "drop"
	 * our exclusiveness temporarily when we get woken up without
	 * having to remove and re-insert us on the wait queue.
	 */
	for (;;) {
		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
					  TASK_INTERRUPTIBLE);
		release_sock(sk);

		// 如果accept队列为空，则把CPU交出去，休眠一会儿
		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
			timeo = schedule_timeout(timeo);

		sched_annotate_sleep();
		lock_sock(sk);
		err = 0;

		// icsk_accept_queue 队列存储接收到的client socket，有了，就可以走了
		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
			break;

		err = -EINVAL;
		if (sk->sk_state != TCP_LISTEN)
			break;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
	}
	finish_wait(sk_sleep(sk), &wait);
	return err;
}

 

获得地址

/*
 *	This does both peername and sockname.
 */
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
			int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct inet_sock *inet	= inet_sk(sk);
	DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);

	sin->sin_family = AF_INET;
	if (peer) {
		if (!inet->inet_dport ||
		    (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		     peer == 1))
			return -ENOTCONN;
		sin->sin_port = inet->inet_dport;
		sin->sin_addr.s_addr = inet->inet_daddr;
	} else {
		__be32 addr = inet->inet_rcv_saddr;
		if (!addr)
			addr = inet->inet_saddr;
		sin->sin_port = inet->inet_sport;
		sin->sin_addr.s_addr = addr;
	}
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
	*uaddr_len = sizeof(*sin);
	return 0;
}