connect的内核实现/非阻塞connect

c库/内核一路看下来，关键代码：

int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	int err;
	long timeo;

	if (addr_len < sizeof(uaddr->sa_family))
		return -EINVAL;

	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->sk_prot->disconnect(sk, flags);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		goto out;
	}

	switch (sock->state) {
	default:
		err = -EINVAL;
		goto out;
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_CONNECTING:
		err = -EALREADY;
		/* Fall out of switch with err, set for this state */
		break;
	case SS_UNCONNECTED:
		err = -EISCONN;
		if (sk->sk_state != TCP_CLOSE)
			goto out;

		err = sk->sk_prot->connect(sk, uaddr, addr_len);//tcp调用tcp_connect

		if (err < 0)
			goto out;

		sock->state = SS_CONNECTING;

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		err = -EINPROGRESS;
		break;
	}

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);//非阻塞socket，timeo等于0


	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		/* Error code is set above */
		if (!timeo || !inet_wait_for_connect(sk, timeo))
			goto out; //非阻塞socket，马上返回。阻塞的则等待连接完成/失败（信号唤醒）或者超时返回

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
	}

	/* Connection was closed by RST, timeout, ICMP error
	 * or another process disconnected us.
	 */
	if (sk->sk_state == TCP_CLOSE)
		goto sock_error;

	/* sk->sk_err may be not zero now, if RECVERR was ordered by user
	 * and error was received after socket entered established state.
	 * Hence, it is handled normally after connect() return successfully.
	 */

	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;

sock_error:
	err = sock_error(sk) ? : -ECONNABORTED;
	sock->state = SS_UNCONNECTED;
	if (sk->sk_prot->disconnect(sk, flags))
		sock->state = SS_DISCONNECTING;
	goto out;
}

static inline long sock_sndtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_sndtimeo;
}

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

	/* Basic assumption: if someone sets sk->sk_err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);//设超时定时器，然后调schedule()切出去，重新调度执行后回到schedule_timeout中继续执行

		lock_sock(sk);
		if (signal_pending(current) || !timeo) //超时了或者被信号唤醒（比如内核协议栈完成连接/或者连接失败发送信号）
			break;
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
	}
	finish_wait(sk_sleep(sk), &wait);
	return timeo;
}


signed long __sched schedule_timeout(signed long timeout)
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT://不设置socket的超时时间的话，默认是这种情况，一直阻塞直到内核协议栈发来信号（成功或者失败）
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default:
		/*
		 * Another bit of PARANOID. Note that the retval will be
		 * 0 since no piece of kernel is supposed to do a check
		 * for a negative retval of schedule_timeout() (since it
		 * should never happens anyway). You just have the printk()
		 * that will tell you if something is gone wrong and where.
		 */
		if (timeout < 0) {
			printk(KERN_ERR "schedule_timeout: wrong timeout "
				"value %lx\n", timeout);
			dump_stack();
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	expire = timeout + jiffies;
//设超时定时器，然后调schedule()切出去，重新调度执行后del_singleshot_timer_sync继续执行
        setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
        __mod_timer(&timer, expire, false, TIMER_NOT_PINNED);
        schedule();
        del_singleshot_timer_sync(&timer);

        /* Remove the timer from the object tracker */
        destroy_timer_on_stack(&timer);

        timeout = expire - jiffies; 
out:
        return timeout < 0 ? 0 : timeout;

/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *buff;
	int err;

	tcp_connect_init(sk);

	buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
	if (unlikely(buff == NULL))
		return -ENOBUFS;

	/* Reserve space for headers. */
	skb_reserve(buff, MAX_TCP_HEADER);

	tp->snd_nxt = tp->write_seq;
	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
	TCP_ECN_send_syn(sk, buff);

	/* Send it off. */
	TCP_SKB_CB(buff)->when = tcp_time_stamp;
	tp->retrans_stamp = TCP_SKB_CB(buff)->when;
	skb_header_release(buff);
	__tcp_add_write_queue_tail(sk, buff);
	sk->sk_wmem_queued += buff->truesize;
	sk_mem_charge(sk, buff->truesize);
	tp->packets_out += tcp_skb_pcount(buff);
	err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
	if (err == -ECONNREFUSED)
		return err;

	/* We change tp->snd_nxt after the tcp_transmit_skb() call
	 * in order to make this packet get counted in tcpOutSegs.
	 */
	tp->snd_nxt = tp->write_seq;
	tp->pushed_seq = tp->write_seq;
	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);

	/* Timer for repeating the SYN until an answer. */
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
				  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
	return 0;
}

1.调用connect的任务嵌入内核后，最后调用tcp_connect 发送SYN，并为内核协议栈起一个重发SYN的定时器，该定时器超时时间是一个RTO，之后的连接工作就完全交给内核协议栈，比如超时重发SYN、三次握手后续流程等。如果连接一直超时，最长折腾75s后就不再尝试重发SYN。
connect 发送SYN后，与内核协议栈是异步关系。


2.对于非阻塞socket，connect马上返回。对于阻塞socket则调用connect的任务等待连接完成或者连接失败（内核协议栈发来信号唤醒该任务）或者超时返回。


3.如果我们想设置connect的超时时间，有两种方法：


1）阻塞socket，设置发送超时时间，用setsockopt设置socket的sk_sndtimeo字段

int sock_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, unsigned int optlen)
{
......
        case SO_RCVTIMEO:
		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
		break;


	case SO_SNDTIMEO:
		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
		break;
......
}

2）非阻塞socket，connect马上返回后用select检测来控制超时时间。