tcpsyn发生在哪层_深入理解TCP协议及其源代码——TCP三次握客户端tcp层SYN包的发送...

1、TCP基本概念

传输控制协议TCP是一种面向连接的、可靠的、基于字节流的运输层通信协议。TCP层是位于IP层之上，应用层之下的传输层。

2、TCP连接时三次握手示意

3. TCP协议栈从上到下提供的接口

创建socket

创建TCP socket调用接口

在创建socket套接字描述符, sys_socket内核函数会根据指定的协议(例如socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP))挂载对应的协议处理函数

250 static int inet_create(struct net *net, struct socket *sock, int protocol,int kern)

251{

...

262 /* Look for the requested type/protocol pair. */

263 lookup_protocol:

264 err = -ESOCKTNOSUPPORT;

265 rcu_read_lock();

// TCP套接字、UDP套接字、原始套接字的inet_protosw实 例都在inetsw_array数组中定义，

//这些实例会调inet_register_protosw()注册到inetsw中

//根据protocol查找要创建的套接字对应的四层传输协议。

266 list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {

268 ...

283 }

284

//如果没有找到，则调用request_module()来尝试加载协议所属的模块，正常情况下不会发生。

285 if (unlikely(err)) {

286 if (try_loading_module < 2) {

287 rcu_read_unlock();

...

}

三次握手

结构体变量struct proto tcp_prot指定了TCP协议栈的访问接口函数

首先客户端发送SYN报文

调用tcp_v4_connect函数建立与服务器联系并发送SYN段:

tcp_v4_connect函数

140/*This will initiate an outgoing connection.*/141int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, intaddr_len)142{

...171 rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,172 RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,173IPPROTO_TCP,174orig_sport, orig_dport, sk);

...214215 /*Socket identity is still unknown (sport may be zero).

216 * However we set state to SYN-SENT and not releasing socket

217 * lock select source port, enter ourselves into the hash tables and

218 * complete initialization after this.

219*/

220tcp_set_state(sk, TCP_SYN_SENT);

...227 rt =ip_route_newports(fl4, rt, orig_sport, orig_dport,228 inet->inet_sport, inet->inet_dport, sk);

...246 err =tcp_connect(sk);

...

}

265EXPORT_SYMBOL(tcp_v4_connect);

此函数前面部分是确定socket的源端口,目的ip及端口。目的IP和目的端口是由connect系统调用的入参指定。tcp_connect函数用于构建并发送一个SYN请求。

tcp_connect函数

构造一个携带SYN标志位的TCP头，tcp_init_nondata_skb函数实现

发送带有SYN的TCP报文，tcp_transmit_skb函数实现

设置计时器超时重发，net_csk_reset_xmit_timer函数实现

3090/*Build a SYN and send it off.*/3091int tcp_connect(struct sock *sk)3092{

...3108 /*Reserve space for headers.*/

3109skb_reserve(buff, MAX_TCP_HEADER);3110

3111 tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);3112 tp->retrans_stamp =tcp_time_stamp;3113tcp_connect_queue_skb(sk, buff);3114tcp_ecn_send_syn(sk, buff);3115

3116 /*Send off SYN; include data in Fast Open.*/

3117 err = tp->fastopen_req ?tcp_send_syn_data(sk, buff) :3118 tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);

...3129 /*Timer for repeating the SYN until an answer.*/

3130inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,3131 inet_csk(sk)->icsk_rto, TCP_RTO_MAX);

...

}

3134EXPORT_SYMBOL(tcp_connect);

tcp_transmit_sbk函数

__tcp_transmit_skb函数的主要任务是向ip层发送数据包，其中包括

初始化TCP协议头等数据结构

查看clone_it是否要克隆Socket Buffer，应用Socket Buffer可能正被其他进程使用，就要克隆一个份

构建TCP协议选项

阻塞控制，确定网络上有多少数据包最好

构建TCP协议头主要的数据域：源端口、目的端口、数据段初始序列号，计算窗口大小，如果是SYN请求包就不需要计算窗口大小

发送数据包到ip层，发送过程状态机切换，发送SYN包之后切换为SYN_SENT

//net/ipv4/tcp_output.c

static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, intclone_it,

gfp_t gfp_mask)

{return__tcp_transmit_skb(sk, skb, clone_it, gfp_mask,

tcp_sk(sk)->rcv_nxt);

}

tcp_transmit_skb是对__tcp_transmit_skb的封装，继续调用，进入__tcp_transmit_skb发送SYN报文

__tcp_transmit_skb函数

//net/ipv4/tcp_output.c

static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,intclone_it, gfp_t gfp_mask, u32 rcv_nxt)

{const struct inet_connection_sock *icsk =inet_csk(sk);

struct inet_sock*inet;

struct tcp_sock*tp;

struct tcp_skb_cb*tcb;

struct tcp_out_options opts;

unsignedinttcp_options_size, tcp_header_size;

struct sk_buff*oskb =NULL;

struct tcp_md5sig_key*md5;

struct tcphdr*th;

u64 prior_wstamp;interr;

BUG_ON(!skb || !tcp_skb_pcount(skb));

tp=tcp_sk(sk);if(clone_it) {

Socket Buffer

TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq- tp->snd_una;

oskb=skb;

tcp_skb_tsorted_save(oskb) {if(unlikely(skb_cloned(oskb)))

skb=pskb_copy(oskb, gfp_mask);elseskb=skb_clone(oskb, gfp_mask);

} tcp_skb_tsorted_restore(oskb);if (unlikely(!skb))return -ENOBUFS;

}

prior_wstamp= tp->tcp_wstamp_ns;

tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);

skb->skb_mstamp_ns = tp->tcp_wstamp_ns;

inet=inet_sk(sk);

tcb=TCP_SKB_CB(skb);

memset(&opts, 0, sizeof(opts));if (unlikely(tcb->tcp_flags &TCPHDR_SYN))

tcp_options_size= tcp_syn_options(sk, skb, &opts, &md5);elsetcp_options_size= tcp_established_options(sk, skb, &opts,&md5);

tcp_header_size= tcp_options_size +sizeof(struct tcphdr);/*if no packet is in qdisc/device queue, then allow XPS to select

* another queue. We can be called from tcp_tsq_handler()

* which holds one reference to sk.

*

* TODO: Ideally, in-flight pure ACK packets should not matter here.

* One way to get this would be to set skb->truesize = 2 on them.*/skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1);/*If we had to use memory reserve to allocate this skb,

* this might cause drops if packet is looped back :

* Other socket might not have SOCK_MEMALLOC.

* Packets not looped back do not care about pfmemalloc.*/skb->pfmemalloc = 0;

skb_push(skb, tcp_header_size);

skb_reset_transport_header(skb);

skb_orphan(skb);

skb->sk =sk;

skb->destructor = skb_is_tcp_pure_ack(skb) ?__sock_wfree : tcp_wfree;

skb_set_hash_from_sk(skb, sk);

refcount_add(skb->truesize, &sk->sk_wmem_alloc);

skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm);/*Build TCP header and checksum it.*/th= (struct tcphdr *)skb->data;

th->source = inet->inet_sport;

th->dest = inet->inet_dport;

th->seq = htonl(tcb->seq);

th->ack_seq =htonl(rcv_nxt);*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |tcb->tcp_flags);

th->check = 0;

th->urg_ptr = 0;/*The urg_mode check is necessary during a below snd_una win probe*/

if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) {if (before(tp->snd_up, tcb->seq + 0x10000)) {

th->urg_ptr = htons(tp->snd_up - tcb->seq);

th->urg = 1;

}else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {

th->urg_ptr = htons(0xFFFF);

th->urg = 1;

}

}

tcp_options_write((__be32*)(th + 1), tp, &opts);

skb_shinfo(skb)->gso_type = sk->sk_gso_type;if (likely(!(tcb->tcp_flags &TCPHDR_SYN))) {

th->window =htons(tcp_select_window(sk));

tcp_ecn_send(sk, skb, th, tcp_header_size);

}else{/*RFC1323: The window in SYN & SYN/ACK segments

* is never scaled.*/th->window = htons(min(tp->rcv_wnd, 65535U));

}

#ifdef CONFIG_TCP_MD5SIG/*Calculate the MD5 hash, as we have all we need now*/

if(md5) {

sk_nocaps_add(sk, NETIF_F_GSO_MASK);

tp->af_specific->calc_md5_hash(opts.hash_location,

md5, sk, skb);

}

#endif

icsk->icsk_af_ops->send_check(sk, skb);if (likely(tcb->tcp_flags &TCPHDR_ACK))

tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);if (skb->len !=tcp_header_size) {

tcp_event_data_sent(tp, sk);

tp->data_segs_out +=tcp_skb_pcount(skb);

tp->bytes_sent += skb->len -tcp_header_size;

}if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)

TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,

tcp_skb_pcount(skb));

tp->segs_out +=tcp_skb_pcount(skb);/*OK, its time to fill skb_shinfo(skb)->gso_{segs|size}*/skb_shinfo(skb)->gso_segs =tcp_skb_pcount(skb);

skb_shinfo(skb)->gso_size =tcp_skb_mss(skb);/*Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns)*/

/*Cleanup our debris for IP stacks*/memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),

sizeof(struct inet6_skb_parm)));

err= icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);if (unlikely(err > 0)) {

tcp_enter_cwr(sk);

err=net_xmit_eval(err);

}if (!err &&oskb) {

tcp_update_skb_after_send(sk, oskb, prior_wstamp);

tcp_rate_skb_sent(sk, oskb);

}returnerr;

}

客户端tcp层是完成SYN包的发送了，经过下层传输到网卡。之后服务端接收客户端发来的tcp报文，并发送回SYN+ACK。