2010-01-30 21:34:55
和前面一样,被动连接方也进入tcp_v4_hnd_req函数处理,不过由于前面受到SYN时已经建立了连接请求(假设SYNCOOKIES没启用),
inet_csk_search_req函数返回建立的连接请求结构request_sock。
流程进入tcp_check_req处理
struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev)
{
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
int paws_reject = 0;
struct tcp_options_received tmp_opt;
struct sock *child;
tmp_opt.saw_tstamp = 0;
/* 如果存在TCP选项,解析它 */
if (th->doff > (sizeof(struct tcphdr)>>2)) {
tcp_parse_options(skb, &tmp_opt, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
/* We do not store true stamp, but it is not required,
* it can be estimated (approximately)
* from another data.
*/
tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
paws_reject = tcp_paws_check(&tmp_opt, th->rst);
}
}
/* Check for pure retransmitted SYN. */
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn &&
flg == TCP_FLAG_SYN &&
!paws_reject) {
/*
* RFC793 draws (Incorrectly! It was fixed in RFC1122)
* this case on figure 6 and figure 8, but formal
* protocol description says NOTHING.
* To be more exact, it says that we should send ACK,
* because this segment (at least, if it has no data)
* is out of window.
*
* CONCLUSION: RFC793 (even with RFC1122) DOES NOT
* describe SYN-RECV state. All the description
* is wrong, we cannot believe to it and should
* rely only on common sense and implementation
* experience.
*
* Enforce "SYN-ACK" according to figure 8, figure 6
* of RFC793, fixed by RFC1122.
*/
req->rsk_ops->rtx_syn_ack(sk, req);
return NULL;
}
/* Further reproduces section "SEGMENT ARRIVES"
for state SYN-RECEIVED of RFC793.
It is broken, however, it does not work only
when SYNs are crossed.
You would think that SYN crossing is impossible here, since
we should have a SYN_SENT socket (from connect()) on our end,
but this is not true if the crossed SYNs were sent to both
ends by a malicious third party. We must defend against this,
and to do that we first verify the ACK (as per RFC793, page
36) and reset if it is invalid. Is this a true full defense?
To convince ourselves, let us consider a way in which the ACK
test can still pass in this 'malicious crossed SYNs' case.
Malicious sender sends identical SYNs (and thus identical sequence
numbers) to both A and B:
A: gets SYN, seq=7
B: gets SYN, seq=7
By our good fortune, both A and B select the same initial
send sequence number of seven
A: sends SYN|ACK, seq=7, ack_seq=8
B: sends SYN|ACK, seq=7, ack_seq=8
So we are now A eating this SYN|ACK, ACK test passes. So
does sequence test, SYN is truncated, and thus we consider
it a bare ACK.
If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this
bare ACK. Otherwise, we create an established connection. Both
ends (listening sockets) accept the new incoming connection and try
to talk to each other.
Note: This case is both harmless, and rare. Possibility is about the
same as us discovering intelligent life on another plant tomorrow.
But generally, we should (RFC lies!) to accept ACK
from SYNACK both here and in tcp_rcv_state_process().
tcp_rcv_state_process() does not, hence, we do not too.
Note that the case is absolutely generic:
we cannot optimize anything here without
violating protocol. All the checks must be made
before attempt to create socket.
*/
/* RFC793 page 36: "If the connection is in any non-synchronized state ...
* and the incoming segment acknowledges something not yet
* sent (the segment carries an unacceptable ACK) ...
* a reset is sent."
*
* Invalid ACK: reset will be sent by listening socket
*/
if ((flg & TCP_FLAG_ACK) &&
(TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
* is essentially ACK extension and too early or too late values
* should cause reset in unsynchronized states.
*/
/* RFC793: "first check sequence number". */
if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) {
/* Out of window: send ACK and drop. */
if (!(flg & TCP_FLAG_RST))
req->rsk_ops->send_ack(sk, skb, req);
if (paws_reject)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
return NULL;
}
/* In sequence, PAWS is OK. */
if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1))
req->ts_recent = tmp_opt.rcv_tsval;
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
/* Truncate SYN, it is out of window starting
at tcp_rsk(req)->rcv_isn + 1. */
flg &= ~TCP_FLAG_SYN;
}
/* RFC793: "second check the RST bit" and
* "fourth, check the SYN bit"
*/
if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
goto embryonic_reset;
}
/* ACK sequence verified above, just make sure ACK is
* set. If ACK not set, just silently drop the packet.
*/
if (!(flg & TCP_FLAG_ACK))
return NULL;
/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
inet_rsk(req)->acked = 1;
return NULL;
}
/* OK, ACK is valid, create big socket and
* feed this segment to it. It will repeat all
* the tests. THIS SEGMENT MUST MOVE SOCKET TO
* ESTABLISHED STATE. If it will be dropped after
* socket is created, wait for troubles.
*/
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL)
goto listen_overflow;
#ifdef CONFIG_TCP_MD5SIG
else {
/* Copy over the MD5 key from the original socket */
struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
key = tp->af_specific->md5_lookup(sk, child);
if (key != NULL) {
/*
* We're using one, so create a matching key on the
* newsk structure. If we fail to get memory then we
* end up not copying the key across. Shucks.
*/
char *newkey = kmemdup(key->key, key->keylen,
GFP_ATOMIC);
if (newkey) {
if (!tcp_alloc_md5sig_pool())
BUG();
tp->af_specific->md5_add(child, child, newkey,
key->keylen);
}
}
}
#endif
inet_csk_reqsk_queue_unlink(sk, req, prev);
inet_csk_reqsk_queue_removed(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
return child;
listen_overflow:
if (!sysctl_tcp_abort_on_overflow) {
inet_rsk(req)->acked = 1;
return NULL;
}
embryonic_reset:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
if (!(flg & TCP_FLAG_RST))
req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req, prev);
return NULL;
}
该函数的前面部分进行各种检查,然后通过后调用icsk_af_ops的syn_recv_sock操作符也即tcp_v4_syn_recv_sock函数,它的主要作用是
从request_sock中构造新的sock结构,并赋值相应的成员。
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
goto exit;
/* 创建新的sock结构,并用req和skb来初始化 */
newsk = tcp_create_openreq_child(sk, req, skb);
if (!newsk)
goto exit;
newsk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(newsk, dst);
/* 相关赋值 */
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
newinet->daddr = ireq->rmt_addr;
newinet->rcv_saddr = ireq->loc_addr;
newinet->saddr = ireq->loc_addr;
newinet->opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
newinet->id = newtp->write_seq ^ jiffies;
tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
if (tcp_sk(sk)->rx_opt.user_mss &&
tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
tcp_initialize_rcv_mss(newsk);
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) {
/*
* We're using one, so create a matching key
* on the newsk structure. If we fail to get
* memory, then we end up not copying the key
* across. Shucks.
*/
char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
if (newkey != NULL)
tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr,
newkey, key->keylen);
newsk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
#endif
/* 将该sock加入到nolisten的hash表中,以供查询*/
__inet_hash_nolisten(newsk);
/* 和sk共有端口,直接加入对应的hash桶的owner列表中 */
__inet_inherit_port(sk, newsk);
return newsk;
exit_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
dst_release(dst);
return NULL;
}
再看看tcp_create_openreq_child函数
if (newsk != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct tcp_sock *newtp;
/* Now setup tcp_sock */
newtp = tcp_sk(newsk);
newtp->pred_flags = 0;
/* 更新滑动窗口 */
newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
newtp->snd_up = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn);
newtp->srtt = 0;
newtp->mdev = TCP_TIMEOUT_INIT;
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newtp->packets_out = 0;
newtp->retrans_out = 0;
newtp->sacked_out = 0;
newtp->fackets_out = 0;
newtp->snd_ssthresh = 0x7fffffff;
/* So many TCP implementations out there (incorrectly) count the
* initial SYN frame in their delayed-ACK and congestion control
* algorithms that we must have the following bandaid to talk
* efficiently to them. -DaveM
*/
newtp->snd_cwnd = 2;
newtp->snd_cwnd_cnt = 0;
newtp->bytes_acked = 0;
newtp->frto_counter = 0;
newtp->frto_highmark = 0;
newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
newtp->write_seq = treq->snt_isn + 1;
newtp->pushed_seq = newtp->write_seq;
newtp->rx_opt.saw_tstamp = 0;
newtp->rx_opt.dsack = 0;
newtp->rx_opt.eff_sacks = 0;
newtp->rx_opt.num_sacks = 0;
newtp->urg_data = 0;
if (sock_flag(newsk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(newsk,
keepalive_time_when(newtp));
newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
if (sysctl_tcp_fack)
tcp_enable_fack(newtp);
}
newtp->window_clamp = req->window_clamp;
newtp->rcv_ssthresh = req->rcv_wnd;
newtp->rcv_wnd = req->rcv_wnd;
newtp->rx_opt.wscale_ok = ireq->wscale_ok;
if (newtp->rx_opt.wscale_ok) {
newtp->rx_opt.snd_wscale = ireq->snd_wscale;
newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
} else {
newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
newtp->window_clamp = min(newtp->window_clamp, 65535U);
}
newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) <<
newtp->rx_opt.snd_wscale);
newtp->max_window = newtp->snd_wnd;
if (newtp->rx_opt.tstamp_ok) {
newtp->rx_opt.ts_recent = req->ts_recent;
newtp->rx_opt.ts_recent_stamp = get_seconds();
newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
} else {
newtp->rx_opt.ts_recent_stamp = 0;
newtp->tcp_header_len = sizeof(struct tcphdr);
}
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
if (newtp->af_specific->md5_lookup(sk, newsk))
newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len)
newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
newtp->rx_opt.mss_clamp = req->mss;
TCP_ECN_openreq_child(newtp, req);
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
return newsk;
}
从tcp_check_req返回后,流程进入tcp_child_process
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb)
{
int ret = 0;
int state = child->sk_state;
if (!sock_owned_by_user(child)) {
ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb),
skb->len);
/* Wakeup parent, send SIGIO */
if (state == TCP_SYN_RECV && child->sk_state != state)
parent->sk_data_ready(parent, 0);
} else {
/* Alas, it is possible again, because we do lookup
* in main socket hash table and lock on listening
* socket does not protect us more.
*/
sk_add_backlog(child, skb);
}
bh_unlock_sock(child);
sock_put(child);
return ret;
}
随后再次进入tcp_recv_state_process
/* step 5: check the ACK field */
if (th->ack) {
int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
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)->ack_seq,
TCP_SKB_CB(skb)->seq);
/* tcp_ack considers this ACK as duplicate
* and does not calculate rtt.
* Fix it at least with timestamps.
*/
if (tp->rx_opt.saw_tstamp &&
tp->rx_opt.rcv_tsecr && !tp->srtt)
tcp_ack_saw_tstamp(sk, 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);