void tcp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
int data_was_unread = 0;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
/* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
* reader process may not have drained the data yet!
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
len--;
data_was_unread = len;
__kfree_skb(skb);
}
sk_mem_reclaim(sk);
/* If socket has been already reset (e.g. in tcp_reset()) - kill it. */
if (sk->sk_state == TCP_CLOSE)
goto adjudge_to_death;
/* As outlined in RFC 2525, section 2.17, we send a RST here because
* data was lost. To witness the awful effects of the old behavior of
* always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk
* GET in an FTP client, suspend the process, wait for the client to
* advertise a zero window, then kill -9 the FTP client, wheee...
* Note: timeout is always zero in such a case.
*/
if (unlikely(tcp_sk(sk)->repair)) {
sk->sk_prot->disconnect(sk, 0);
} else if (data_was_unread) {
/* Unread data was tossed, zap the connection. */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, sk->sk_allocation);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
} else if (tcp_close_state(sk)) {
/* We FIN if the application ate all the data before
* zapping the connection.
*/
/* RED-PEN. Formally speaking, we have broken TCP state
* machine. State transitions:
*
* TCP_ESTABLISHED -> TCP_FIN_WAIT1
* TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible)
* TCP_CLOSE_WAIT -> TCP_LAST_ACK
*
* are legal only when FIN has been sent (i.e. in window),
* rather than queued out of window. Purists blame.
*
* F.e. "RFC state" is ESTABLISHED,
* if Linux state is FIN-WAIT-1, but FIN is still not sent.
*
* The visible declinations are that sometimes
* we enter time-wait state, when it is not required really
* (harmless), do not send active resets, when they are
* required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when
* they look as CLOSING or LAST_ACK for Linux)
* Probably, I missed some more holelets.
* --ANK
* XXX (TFO) - To start off we don't support SYN ACK FIN
* in a single packet! (May consider it later but will
* probably need API support or TCP_CORK SYN-ACK until
* data is written and socket is closed.)
*/
tcp_send_fin(sk);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
local_bh_disable();
bh_lock_sock(sk);
/* remove backlog if any, without releasing ownership. */
__release_sock(sk);
percpu_counter_inc(sk->sk_prot->orphan_count);
/* Have we already been destroyed by a softirq or backlog? */
if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
goto out;
/* This is a (useful) BSD violating of the RFC. There is a
* problem with TCP as specified in that the other end could
* keep a socket open forever with no application left this end.
* We use a 1 minute timeout (about the same as BSD) then kill
* our end. If they send after that then tough - BUT: long enough
* that we won't make the old 4*rto = almost no time - whoops
* reset mistake.
*
* Nope, it was not mistake. It is really desired behaviour
* f.e. on http Servers, when such sockets are useless, but
* consume significant resources. Let's do it with special
* linger2 option. --ANK
*/
if (sk->sk_state == TCP_FIN_WAIT2) {
struct tcp_sock *tp = tcp_sk(sk);
if (tp->linger2 < 0) {
tcp_set_state(sk, TCP_close);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONLINGER);
} else {
const int tmo = tcp_fin_time(sk);
if (tmo > sock_net(sk)->ipv4.sysctl_tcp_tw_timeout) {
inet_csk_reset_keepalive_timer(sk,
tmo - sock_net(sk)->ipv4.sysctl_tcp_tw_timeout);
} else {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto out;
}
}
}
if (sk->sk_state != TCP_CLOSE) {
sk_mem_reclaim(sk);
if (tcp_check_oom(sk, 0)) {
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONMEMORY);
} else if (!check_net(sock_net(sk))) {
/* Not possible to send reset; just close */
tcp_set_state(sk, TCP_CLOSE);
}
}
if (sk->sk_state == TCP_CLOSE) {
struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
/* We could get here with a non-NULL req if the socket is
* aborted (e.g., closed with unread data) before 3WHS
* finishes.
*/
if (req)
reqsk_fastopen_remove(sk, req, false);
inet_csk_destroy_sock(sk);
}
/* Otherwise, socket is reprieved until protocol close. */
out:
bh_unlock_sock(sk);
local_bh_enable();
release_sock(sk);
sock_put(sk);
}
EXPORT_SYMBOL(tcp_close);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
作为Server的母socket关闭，逻辑很简单：1）先设置为TCP_CLOSE状态，正常来说已经在服务的socket关闭都需要先设置为TCP_CLOSE状态；2）清除icsk_accept_queue队列中的socket，同时也会清除FASTOPEN的socket；3）adjudge_to_death 应用层调用了close设置为孤儿套接字。
/* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
* reader process may not have drained the data yet!
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
len--;
data_was_unread = len;
__kfree_skb(skb);
}
非TCP_LISTEN状态的socket调用close，清除接收队列中的未读取数据，调用close表示不在从内核接收数据了。
sk_mem_reclaim(sk);
上面可能已经释放了部分sk的部分内存资源，这里是回收重新利用。
/* If socket has been already reset (e.g. in tcp_reset()) - kill it. */
if (sk->sk_state == TCP_CLOSE)
goto adjudge_to_death;
如果socket已经是 处于TCP_CLOSE状态了，那么表示这个socket已经是存在最后被释放的边缘了。在adjudge_to_death流程中调用 inet_csk_destroy_sock销毁socket。
/* As outlined in RFC 2525, section 2.17, we send a RST here because
* data was lost. To witness the awful effects of the old behavior of
* always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk
* GET in an FTP client, suspend the process, wait for the client to
* advertise a zero window, then kill -9 the FTP client, wheee...
* Note: timeout is always zero in such a case.
*/
if (unlikely(tcp_sk(sk)->repair)) {
sk->sk_prot->disconnect(sk, 0);
} else if (data_was_unread) {
/* Unread data was tossed, zap the connection. */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, sk->sk_allocation);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
} else if (tcp_close_state(sk)) {
/* We FIN if the application ate all the data before
* zapping the connection.
*/
/* RED-PEN. Formally speaking, we have broken TCP state
* machine. State transitions:
*
* TCP_ESTABLISHED -> TCP_FIN_WAIT1
* TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible)
* TCP_CLOSE_WAIT -> TCP_LAST_ACK
*
* are legal only when FIN has been sent (i.e. in window),
* rather than queued out of window. Purists blame.
*
* F.e. "RFC state" is ESTABLISHED,
* if Linux state is FIN-WAIT-1, but FIN is still not sent.
*
* The visible declinations are that sometimes
* we enter time-wait state, when it is not required really
* (harmless), do not send active resets, when they are
* required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when
* they look as CLOSING or LAST_ACK for Linux)
* Probably, I missed some more holelets.
* --ANK
* XXX (TFO) - To start off we don't support SYN ACK FIN
* in a single packet! (May consider it later but will
* probably need API support or TCP_CORK SYN-ACK until
* data is written and socket is closed.)
*/
tcp_send_fin(sk);
}
前面已经处理了处在TCP_LISTEN和TCP_CLOSE状态的socket了。上面这段代码是处理非这两种状态的TCP连接。
else if (data_was_unread) ，如果前面的socket还有数据为读取，设置为socket为TCP_CLOSE后主动发送reset，关闭TCP连接（进入adjudge_to_death流程中调用 inet_csk_destroy_sock销毁socket）
else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)，设置了SOCK_LINGER但是未设置合理的时间，直接disconnect后进入进入adjudge_to_death流程中调用 inet_csk_destroy_sock销毁socket
else if (tcp_close_state(sk)) 发送fin报文，发起关闭流程，经过关闭流程后最终进入adjudge_to_death流程中调用 inet_csk_destroy_sock销毁socket
sk_stream_wait_close(sk, timeout);
等待socket超时关闭它。
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
local_bh_disable();
bh_lock_sock(sk);
/* remove backlog if any, without releasing ownership. */
__release_sock(sk);
sock_orphan(sk)，应用层已经主动关闭socket了，这时候socket与进程失联，变成了孤儿socket
Copyright © 2024 妖气游戏网 www.17u1u.com All Rights Reserved
