Linux 内核网络之 Shutdown 的实现

asmlinkage long sys_shutdown(int fd, int how)
{
int err, fput_needed;
struct socket *sock;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock != NULL) {
err = security_socket_shutdown(sock, how);
if (!err)
err = sock->ops->shutdown(sock, how); // inet_shutdown
fput_light(sock->file, fput_needed);
}
return err;
}
int inet_shutdown(struct socket *sock, int how)
{
struct sock sk = sock->sk;
int err = 0;
/ This should really check to make sure
• the socket is a TCP socket. (WHY AC...)
/
//how 增1 是为了利用how变量进行为操作
how++; / maps 0->1 has the advantage of making bit 1 rcvs and
1->2 bit 2 snds.
2->3 /
if ((how & ~SHUTDOWN_MASK) || !how) / MAXINT->0 /
return -EINVAL;
lock_sock(sk);
//根据传输控制块的状态重新设置套接口状态，使套接口状态在完成关闭前只有2种
if (sock->state == SS_CONNECTING) {
if ((1 << sk->sk_state) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
sock->state = SS_DISCONNECTING;
else
sock->state = SS_CONNECTED;
}
//若传输控制块处于其他状态，则设置shutdown关闭方式后，调用传输层接口shutdown，进行具体传输层关闭
switch (sk->sk_state) {
case TCP_CLOSE:
err = -ENOTCONN;
/ Hack to wake up other listeners, who can poll for
POLLHUP, even on eg. unconnected UDP sockets -- RR /
default:
sk->sk_shutdown |= how; // 把关闭信息设置到sk_shutdown 中
if (sk->sk_prot->shutdown)
sk->sk_prot->shutdown(sk, how); // tcp_shutdown
break;
/ Remaining two branches are temporary solution for missing
• close() in multithreaded environment. It is not a good idea,
• but we have no choice until close() is repaired at VFS level.
/
//若处于TCP_LISTEN，则需要判断关闭方式，若有接收方向的关闭操作，则和TCP_SYN_SENT处理一样
case TCP_LISTEN:
if (!(how & RCV_SHUTDOWN))
break;
/ Fall through /
//若处于连接状态过程中(LISTEN或者SYN_SENT状态)，则不允许在继续连接，调用disconnect断开连接操作
case TCP_SYN_SENT:
err = sk->sk_prot->disconnect(sk, O_NONBLOCK); // tcp_disconnect
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
break;
}
/ Wake up anyone sleeping in poll. */
// 调用sk_state_change，唤醒在传输控制块的等待队列上的进程。sk_state_change 在 sock_init_data 中被初始化
sk->sk_state_change(sk);
release_sock(sk);
return err;
}

若处于正在连接过程中，则调用 tcp_disconnect 断开连接。
void tcp_shutdown(struct sock sk, int how)
{
/ We need to grab some memory, and put together a FIN,
• and then put it into the queue to be sent.
• Tim MacKenzie(​​tym@dibbler.cs.monash.edu.au​​) 4 Dec '92.
/
/ 不含有SEND_SHUTDOWN，返回，接收方关闭，不发fin */
if (!(how & SEND_SHUTDOWN))
return;
/* If we've already sent a FIN, or it's a closed state, skip this. /
/ 以下这几个状态发fin /
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_SYN_SENT |
TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
/ Clear out any half completed packets. FIN if needed. /
if (tcp_close_state(sk)) / 设置新状态，发送fin */
tcp_send_fin(sk);
}
}
对于关闭读通道，不需要发送 FIN 报文，直接返回。

int tcp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int err = 0;
int old_state = sk->sk_state;
/* 不是close状态则设置为close，从hash中删除控制块 */
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
/* ABORT function of RFC793 /
/ LISTEN状态，停止监听 /
if (old_state == TCP_LISTEN) {
//删除keepalive定时器，对全连接上的每个socket调用tcp_disconnect
inet_csk_listen_stop(sk);
/ 根据状态确定是否需要发送rst
|| 下一个发送序号并不是最后一个队列数据段序号
&& 是被动关闭的结束状态 /
} else if (tcp_need_reset(old_state) ||
(tp->snd_nxt != tp->write_seq &&
(1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
/ The last check adjusts for discrepancy of Linux wrt. RFC
• states
/
/ 发送rst */
tcp_send_active_reset(sk, gfp_any());
sk->sk_err = ECONNRESET;
} else if (old_state == TCP_SYN_SENT)
sk->sk_err = ECONNRESET;
/* 清除定时器 /
tcp_clear_xmit_timers(sk);
/ 释放接收队列中的skb /
__skb_queue_purge(&sk->sk_receive_queue);
/ 释放发送队列中的skb */
sk_stream_writequeue_purge(sk);
/*释放未按顺序达到的skb */
__skb_queue_purge(&tp->out_of_order_queue);
#ifdef CONFIG_NET_DMA
__skb_queue_purge(&sk->sk_async_wait_queue);
#endif
/* 其他各种清理工作 */
inet->dport = 0;
...
return err;
}

int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
...
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
...
}