深入理解TCP协议及其源代码
1.TCP协议栈的访问接口函数
结构体变量struct proto tcp_prot指定了TCP协议栈的访问接口函数，它几乎包含了所有要用到的东西。
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
.close = tcp_close,
.pre_connect = tcp_v4_pre_connect,
.connect = tcp_v4_connect,
.disconnect = tcp_disconnect,
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v4_init_sock,
.destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
.keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v4_do_rcv,
.release_cb = tcp_release_cb,
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.leave_memory_pressure = tcp_leave_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.no_autobind = true,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
.diag_destroy = tcp_abort,
};
前面介绍了inet_init函数是TCP/IP协议栈初始化的入口函数，通过fs_initcall(inet_init)函数将inet_init函数注册进initcalls的table，可以注册内置的几种协议（TCP，UDP，RAW，PING）。
static int __init inet_init(void)
{
...
rc = proto_register(&tcp_prot, 1);//注册TCP
if (rc)
goto out_free_reserved_ports;
rc = proto_register(&udp_prot, 1);//注册UDP
if (rc)
goto out_unregister_tcp_proto;
rc = proto_register(&raw_prot, 1);//注册RAW
if (rc)
goto out_unregister_udp_proto;
rc = proto_register(&ping_prot, 1);//注册PING
if (rc)
goto out_unregister_raw_proto;
...
}
注册函数proto_register调用kmem_cache_create函数完成TCP协议的slab缓存建立。
int proto_register(struct proto *prot, int alloc_slab)
{
if (alloc_slab) {//注册协议时必须已经分配slab缓存
prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
SLAB_HWCACHE_ALIGN | prot->slab_flags,
NULL);
if (prot->slab == NULL) {
pr_crit("%s: Can't create sock SLAB cache!\n",
prot->name);
goto out;
}
...
}
2.TCP协议的初始化工作
从用户程序的角度看，TCP的三次握手就是客户端发起connect请求，然后由服务端用accept接收请求这一过程中完成的工作。而客户端的connect在tcp_prot中对应的则是tcp_v4_connect函数，服务端的accept对应的则是inet_csk_accept函数。
（1）tcp_v4_connect函数
调用IP层提供的一些服务；调用tcp_connect来构造SYN并发送出去。
/* This will initiate an outgoing connection. */
//主要作用就是发起一个TCP连接
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
···
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
orig_sport, orig_dport, sk);
···
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
···
//以上调用一些IP层提供的一些服务
···
if (!tp->write_seq && likely(!tp->repair))
//计算初始序号
tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
usin->sin_port);
inet->inet_id = tp->write_seq ^ jiffies;
//调用tcp_connect来构造SYN，并将它发送出去。
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->inet_dport = 0;
return err;
}
tcp_connect函数
构造携带SYN标志位的TCP头并发送出去；设置计时器超时重发。
/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
···
/* Send off SYN; include data in Fast Open. */
err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
//tcp_transmit_skb将tcp数据发送出去
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. */
//启动重传定时器
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
return 0;
}
（2）inet_csk_accept函数
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{...
if (sk->sk_state != TCP_LISTEN)//判断是否是LISTEN状态
goto out_err;
/* Find already established connection */
if (reqsk_queue_empty(queue)) {//判断请求队列是否为空
long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
/* If this is a non blocking socket don't sleep */
error = -EAGAIN;
if (!timeo)
goto out_err;
error = inet_csk_wait_for_connect(sk, timeo)；//为空则阻塞，执行此函数等待连接
if (error)
goto out_err;
}
EXPORT_SYMBOL(inet_csk_accept);
（3）负责接收处理数据的入口tcp_v4_rcv
TCP/IP协议栈的初始化入口函数inet_init中涉及了tcp_protocol结构体变量。
static int __init inet_init(void)
{
...
if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
pr_crit("%s: Cannot add TCP protocol\n", __func__);
···
}
而在tcp_protocol中的handler被赋值为tcp_v4_rev。
static struct net_protocol tcp_protocol = {
.early_demux = tcp_v4_early_demux,
.early_demux_handler = tcp_v4_early_demux,
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
.no_policy = 1,
.netns_ok = 1,
.icmp_strict_tag_validation = 1,
};
int tcp_v4_rcv(struct sk_buff *skb)
{
...
if (sk->sk_state == TCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
struct sock *nsk;
sk = req->rsk_listener;
if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
sk_drops_add(sk, skb);
reqsk_put(req);
goto discard_it;
}
if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
/* We own a reference on the listener, increase it again
* as we might lose it too soon.
*/
sock_hold(sk);
refcounted = true;
//创建新的sock进入TCP_SYN_RECV state
nsk = tcp_check_req(sk, skb, req, false);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
//调用 tcp_rcv_state_process
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v4_send_reset(nsk, skb);
goto discard_and_relse;
} else {//成功后直接返回
sock_put(sk);
return 0;
}
}
}
参考链接：
https://github.com/mengning/net/blob/master/np2019.md
https://blog.csdn.net/u010039418/article/details/79350421
浙公网安备 33010602011771号