TCP连接的建立（二）

被动打开

SYN cookies

TCP协议开辟了一个比較大的内存空间请求连接队列来存储连接请求块，当SYN请求不断添加，请求连接数目到达上限时，会致使系统丢弃SYN连接请求。SYN cookies技术就能够使server在半连接队列已满的情况下仍能处理新的SYN请求。

当半连接队列满时，SYN cookies并不丢弃SYN请求。而是通过加密技术来标识半连接状态。在TCP实现中，当收到client的SYN请求时，server须要回复SYN+ACK包给client，然后client再发送确认包给server。通常，server的初始序列号是由server依照一定的规律计算得到的随机数，而在SYN cookies中，server的初始序列号是由clientIP地址、clientport号、serverIP地址和serverport号、接收到的client初始序列号以及其它一些安全数值进行hash运算，并加密后得到的，称之为cookies。

当server遭受SYN攻击使得请求连接队列满时，server并不拒绝新的SYN请求，而是回复一个初始化序列号为cookies的SYN包给client。假设收到client的ACK段。server将client的ACK序列号减1得到的值。与用上述那些要素hash运算得到的值比較，假设相等。直接完毕三次握手。注意：此时并不比查看此连接是否属于请求连接队列。

启用SYN cookies是通过在启动环境中设置一下命令来完毕：

echo 1 > /proc/sys/net/ipv4/tcp_syncookies

第一次握手：接收SYN段

传输控制块接收处理的段都有tcp_v4_do_rcv()处理，在该函数中再依据不同的状态由不同的函数处理。

/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sock *rsk;
#ifdef CONFIG_TCP_MD5SIG
	/*
	 * We really want to reject the packet as early as possible
	 * if:
	 *  o We're expecting an MD5'd packet and this is no MD5 tcp option
	 *  o There is an MD5 option and we're not expecting one
	 */
	if (tcp_v4_inbound_md5_hash(sk, skb))
		goto discard;
#endif

	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		TCP_CHECK_TIMER(sk);
		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
			rsk = sk;
			goto reset;
		}
		TCP_CHECK_TIMER(sk);
		return 0;
	}

	if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
		goto csum_err;

	if (sk->sk_state == TCP_LISTEN) {
		struct sock *nsk = tcp_v4_hnd_req(sk, skb);
		if (!nsk)
			goto discard;

		if (nsk != sk) {
			if (tcp_child_process(sk, nsk, skb)) {
				rsk = nsk;
				goto reset;
			}
			return 0;
		}
	}

	TCP_CHECK_TIMER(sk);
	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
		rsk = sk;
		goto reset;
	}
	TCP_CHECK_TIMER(sk);
	return 0;

reset:
	tcp_v4_send_reset(rsk, skb);
discard:
	kfree_skb(skb);
	/* Be careful here. If this function gets more complicated and
	 * gcc suffers from register pressure on the x86, sk (in %ebx)
	 * might be destroyed here. This current version compiles correctly,
	 * but you have been warned.
	 */
	return 0;

csum_err:
	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
	goto discard;
}

第二次握手：发送SYN+ACK段

tcp_v4_send_synack()用来为服务端构造回应client连接请求SYN段的SYN+ACK段，并将其封装在IP数据报中发送给client。

/*
 *	Send a SYN-ACK after having received a SYN.
 *	This still operates on a request_sock only, not on a big
 *	socket.
 */
static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
				struct dst_entry *dst)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int err = -1;
	struct sk_buff * skb;

	/* First, grab a route. */
	if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
		return -1;

	skb = tcp_make_synack(sk, dst, req);

	if (skb) {
		struct tcphdr *th = tcp_hdr(skb);

		th->check = tcp_v4_check(skb->len,
					 ireq->loc_addr,
					 ireq->rmt_addr,
					 csum_partial(th, skb->len,
						      skb->csum));

		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
					    ireq->rmt_addr,
					    ireq->opt);
		err = net_xmit_eval(err);
	}

	dst_release(dst);
	return err;
}
static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
{
	return __tcp_v4_send_synack(sk, req, NULL);
}

第三次握手：接收ACK段

服务端接收到SYN段后，会为将建立的连接创建一个连接请求块，同一时候发送SYN+ACK段给client作为回应，然后启动建立连接定时器，等待client最后一次握手的ACK段

connect系统调用的实现

inet_stream_connect()是connect系统调用的套接口层实现，首先校验设置的地址族，然后校验套接口状态，套接口状态为SS_UNCONNECTED时调用传输层接口。TCP中为tcp_v4_connect()。最后，等待连接的完毕或失败。

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	int err;
	long timeo;

	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);
		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);

	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;

		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;
}

调用传输层接口，连接须要三层握手，connect接口仅仅是完毕发送SYN段过程，兴许两次握手由协议栈完毕。

SYN段发送成功后，兴许仅仅需等待第三次握手结束。

主动打开

第一次握手：发送SYN段

初始化client传输控制块并发送SYN段，通过tcp_v4_connect()完毕

/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
	struct rtable *rt;
	__be32 daddr, nexthop;
	int tmp;
	int err;

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	nexthop = daddr = usin->sin_addr.s_addr;
	if (inet->opt && inet->opt->srr) {
		if (!daddr)
			return -EINVAL;
		nexthop = inet->opt->faddr;
	}

	tmp = ip_route_connect(&rt, nexthop, inet->saddr,
			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
			       IPPROTO_TCP,
			       inet->sport, usin->sin_port, sk, 1);
	if (tmp < 0) {
		if (tmp == -ENETUNREACH)
			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
		return tmp;
	}

	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
		ip_rt_put(rt);
		return -ENETUNREACH;
	}

	if (!inet->opt || !inet->opt->srr)
		daddr = rt->rt_dst;

	if (!inet->saddr)
		inet->saddr = rt->rt_src;
	inet->rcv_saddr = inet->saddr;

	if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) {
		/* Reset inherited state */
		tp->rx_opt.ts_recent	   = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		tp->write_seq		   = 0;
	}

	if (tcp_death_row.sysctl_tw_recycle &&
	    !tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
		struct inet_peer *peer = rt_get_peer(rt);
		/*
		 * VJ's idea. We save last timestamp seen from
		 * the destination in peer table, when entering state
		 * TIME-WAIT * and initialize rx_opt.ts_recent from it,
		 * when trying new connection.
		 */
		if (peer != NULL &&
		    peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) {
			tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
			tp->rx_opt.ts_recent = peer->tcp_ts;
		}
	}

	inet->dport = usin->sin_port;
	inet->daddr = daddr;

	inet_csk(sk)->icsk_ext_hdr_len = 0;
	if (inet->opt)
		inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;

	tp->rx_opt.mss_clamp = 536;

	/* Socket identity is still unknown (sport may be zero).
	 * However we set state to SYN-SENT and not releasing socket
	 * lock select source port, enter ourselves into the hash tables and
	 * complete initialization after this.
	 */
	tcp_set_state(sk, TCP_SYN_SENT);
	err = inet_hash_connect(&tcp_death_row, sk);
	if (err)
		goto failure;

	err = ip_route_newports(&rt, IPPROTO_TCP,
				inet->sport, inet->dport, sk);
	if (err)
		goto failure;

	/* OK, now commit destination to socket.  */
	sk->sk_gso_type = SKB_GSO_TCPV4;
	sk_setup_caps(sk, &rt->u.dst);

	if (!tp->write_seq)
		tp->write_seq = secure_tcp_sequence_number(inet->saddr,
							   inet->daddr,
							   inet->sport,
							   usin->sin_port);

	inet->id = tp->write_seq ^ jiffies;

	err = tcp_connect(sk);
	rt = NULL;
	if (err)
		goto failure;

	return 0;

failure:
	/*
	 * This unhashes the socket and releases the local port,
	 * if necessary.
	 */
	tcp_set_state(sk, TCP_CLOSE);
	ip_rt_put(rt);
	sk->sk_route_caps = 0;
	inet->dport = 0;
	return err;
}

第二次握手：接收SYN+ACK段

处于SYN_SENT状态的传输控制块，通过tcp_rcv_state_process()来处理。

/*
 *	This function implements the receiving procedure of RFC 793 for
 *	all states except ESTABLISHED and TIME_WAIT.
 *	It's called from both tcp_v4_rcv and tcp_v6_rcv and should be
 *	address independent.
 */

int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
			  struct tcphdr *th, unsigned len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	int queued = 0;
	int res;

	tp->rx_opt.saw_tstamp = 0;

	switch (sk->sk_state) {
	case TCP_CLOSE:
		goto discard;

	case TCP_LISTEN:
		if (th->ack)
			return 1;

		if (th->rst)
			goto discard;

		if (th->syn) {
			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
				return 1;

			/* Now we have several options: In theory there is
			 * nothing else in the frame. KA9Q has an option to
			 * send data with the syn, BSD accepts data with the
			 * syn up to the [to be] advertised window and
			 * Solaris 2.1 gives you a protocol error. For now
			 * we just ignore it, that fits the spec precisely
			 * and avoids incompatibilities. It would be nice in
			 * future to drop through and process the data.
			 *
			 * Now that TTCP is starting to be used we ought to
			 * queue this data.
			 * But, this leaves one open to an easy denial of
			 * service attack, and SYN cookies can't defend
			 * against this problem. So, we drop the data
			 * in the interest of security over speed unless
			 * it's still in use.
			 */
			kfree_skb(skb);
			return 0;
		}
		goto discard;

	case TCP_SYN_SENT:
		queued = tcp_rcv_synsent_state_process(sk, skb, th, len);
		if (queued >= 0)
			return queued;

		/* Do step6 onward by hand. */
		tcp_urg(sk, skb, th);
		__kfree_skb(skb);
		tcp_data_snd_check(sk);
		return 0;
	}

	res = tcp_validate_incoming(sk, skb, th, 0);
	if (res <= 0)
		return -res;

	/* step 5: check the ACK field */
	if (th->ack) {
		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;

		switch (sk->sk_state) {
		case TCP_SYN_RECV:
			if (acceptable) {
				tp->copied_seq = tp->rcv_nxt;
				smp_mb();
				tcp_set_state(sk, TCP_ESTABLISHED);
				sk->sk_state_change(sk);

				/* Note, that this wakeup is only for marginal
				 * crossed SYN case. Passively open sockets
				 * are not waked up, because sk->sk_sleep ==
				 * NULL and sk->sk_socket == NULL.
				 */
				if (sk->sk_socket)
					sk_wake_async(sk,
						      SOCK_WAKE_IO, POLL_OUT);

				tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
				tp->snd_wnd = ntohs(th->window) <<
					      tp->rx_opt.snd_wscale;
				tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);

				/* tcp_ack considers this ACK as duplicate
				 * and does not calculate rtt.
				 * Force it here.
				 */
				tcp_ack_update_rtt(sk, 0, 0);

				if (tp->rx_opt.tstamp_ok)
					tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;

				/* Make sure socket is routed, for
				 * correct metrics.
				 */
				icsk->icsk_af_ops->rebuild_header(sk);

				tcp_init_metrics(sk);

				tcp_init_congestion_control(sk);

				/* Prevent spurious tcp_cwnd_restart() on
				 * first data packet.
				 */
				tp->lsndtime = tcp_time_stamp;

				tcp_mtup_init(sk);
				tcp_initialize_rcv_mss(sk);
				tcp_init_buffer_space(sk);
				tcp_fast_path_on(tp);
			} else {
				return 1;
			}
			break;

		case TCP_FIN_WAIT1:
			if (tp->snd_una == tp->write_seq) {
				tcp_set_state(sk, TCP_FIN_WAIT2);
				sk->sk_shutdown |= SEND_SHUTDOWN;
				dst_confirm(sk->sk_dst_cache);

				if (!sock_flag(sk, SOCK_DEAD))
					/* Wake up lingering close() */
					sk->sk_state_change(sk);
				else {
					int tmo;

					if (tp->linger2 < 0 ||
					    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
					     after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
						tcp_done(sk);
						NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
						return 1;
					}

					tmo = tcp_fin_time(sk);
					if (tmo > TCP_TIMEWAIT_LEN) {
						inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
					} else if (th->fin || sock_owned_by_user(sk)) {
						/* Bad case. We could lose such FIN otherwise.
						 * It is not a big problem, but it looks confusing
						 * and not so rare event. We still can lose it now,
						 * if it spins in bh_lock_sock(), but it is really
						 * marginal case.
						 */
						inet_csk_reset_keepalive_timer(sk, tmo);
					} else {
						tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
						goto discard;
					}
				}
			}
			break;

		case TCP_CLOSING:
			if (tp->snd_una == tp->write_seq) {
				tcp_time_wait(sk, TCP_TIME_WAIT, 0);
				goto discard;
			}
			break;

		case TCP_LAST_ACK:
			if (tp->snd_una == tp->write_seq) {
				tcp_update_metrics(sk);
				tcp_done(sk);
				goto discard;
			}
			break;
		}
	} else
		goto discard;

	/* step 6: check the URG bit */
	tcp_urg(sk, skb, th);

	/* step 7: process the segment text */
	switch (sk->sk_state) {
	case TCP_CLOSE_WAIT:
	case TCP_CLOSING:
	case TCP_LAST_ACK:
		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
			break;
	case TCP_FIN_WAIT1:
	case TCP_FIN_WAIT2:
		/* RFC 793 says to queue data in these states,
		 * RFC 1122 says we MUST send a reset.
		 * BSD 4.4 also does reset.
		 */
		if (sk->sk_shutdown & RCV_SHUTDOWN) {
			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
				tcp_reset(sk);
				return 1;
			}
		}
		/* Fall through */
	case TCP_ESTABLISHED:
		tcp_data_queue(sk, skb);
		queued = 1;
		break;
	}

	/* tcp_data could move socket to TIME-WAIT */
	if (sk->sk_state != TCP_CLOSE) {
		tcp_data_snd_check(sk);
		tcp_ack_snd_check(sk);
	}

	if (!queued) {
discard:
		__kfree_skb(skb);
	}
	return 0;
}

第三次握手：发送ACK段

tcp_send_ack()用来发送一个ACK段，同一时候更新窗体

/* This routine sends an ack and also updates the window. */
void tcp_send_ack(struct sock *sk)
{
	struct sk_buff *buff;

	/* If we have been reset, we may not send again. */
	if (sk->sk_state == TCP_CLOSE)
		return;

	/* We are not putting this on the write queue, so
	 * tcp_transmit_skb() will set the ownership to this
	 * sock.
	 */
	buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
	if (buff == NULL) {
		inet_csk_schedule_ack(sk);
		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
					  TCP_DELACK_MAX, TCP_RTO_MAX);
		return;
	}

	/* Reserve space for headers and prepare control bits. */
	skb_reserve(buff, MAX_TCP_HEADER);
	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPCB_FLAG_ACK);

	/* Send it off, this clears delayed acks for us. */
	TCP_SKB_CB(buff)->when = tcp_time_stamp;
	tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
}

发送ACK段时，TCP必须不在CLOSE状态。

为ACK段分配一个SKB，假设分配失败则在启动延时定时器后返回。