Congestion Control |---snd_cwnd---|||---snd_ssthresh---| * * */
struct tcpcb { struct list_node node; short t_state; /* state of this connection */ short t_timer[TCPT_NTIMERS]; /* tcp timers */ short t_rxtshift; /* log(2) of rexmt exp. backoff */ short t_rxtcur; /* current retransmit value */ short t_dupacks; /* consecutive dup acks recd */ unsigned short t_maxseg; /* maximum segment size */ char t_force; /* 1 if forcing out a byte */ unsigned short t_flags;
struct tcpiphdr *t_template; /* skeletal packet for transmit */ struct inpcb *t_inpcb; /* back pointer to internet pcb */ /* * The following fields are used as in the protocol specification. * See RFC783, Dec. 1981, page 21. */ /* send sequence variables */ tcp_seq snd_una; /* send unacknowledged */ tcp_seq snd_nxt; /* send next */ tcp_seq snd_up; /* send urgent pointer */ tcp_seq snd_wl1; /* window update seg seq number */ tcp_seq snd_wl2; /* window update seg ack number */ tcp_seq iss; /* initial send sequence number */ unsigned int snd_wnd; /* send window */ /* receive sequence variables */ unsigned int rcv_wnd; /* receive window */ tcp_seq rcv_nxt; /* receive next */ tcp_seq rcv_up; /* receive urgent pointer */ tcp_seq irs; /* initial receive sequence number */
/* receive variables */ tcp_seq rcv_adv; /* advertised window */ /* retransmit variables */ tcp_seq snd_max; /* highest sequence number sent * /* congestion control (for slow start, source quench, retransmit after loss) */ unsigned int snd_cwnd; /* congestion-controlled window */ unsigned int snd_ssthresh; /* * transmit timing stuff. See below for scale of srtt and rttvar. * "Variance" is actually smoothed difference. */ short t_idle; /* inactivity time */ short t_rtt; /* round trip time */ tcp_seq t_rtseq; /* sequence number being timed */ short t_srtt; /* smoothed round-trip time */ short t_rttvar; /* variance in round-trip time */ unsigned short t_rttmin; /* minimum rtt allowed */ unsigned long max_sndwnd; /* largest window peer has offered */
/* out-of-band data */ char t_oobflags; /* have some */ char t_iobc; /* input character */ short t_softerror; /* possible error not yet reported */
/* RFC 1323 variables */ unsigned char snd_scale; /* window scaling for send window */ unsigned char rcv_scale; /* window scaling for recv window */ unsigned char request_r_scale; /* pending window scaling */ unsigned char requested_s_scale; unsigned long ts_recent; /* timestamp echo data */ unsigned long ts_recent_age; /* when last updated */ tcp_seq last_ack_sent;
void *t_tuba_pcb; /* next level down pcb for TCP over z */ };
/* * Get IP and TCP header together in first mbuf. * Note: IP leaves IP header in first mbuf. */ ti = mtod(m, struct tcpiphdr *); if (iphlen > sizeof (struct ip)) ip_stripoptions(m, (struct mbuf *)0); if (m->m_len < sizeof (struct tcpiphdr)) { if ((m = m_pullup(m, sizeof (struct tcpiphdr))) == 0) { tcpstat.tcps_rcvshort++; return; } ti = mtod(m, struct tcpiphdr *); }
so = inp->inp_socket; if (so->so_options & (SO_DEBUG|SO_ACCEPTCONN)) { if (so->so_options & SO_DEBUG) { ostate = tp->t_state; tcp_saveti = *ti; } if (so->so_options & SO_ACCEPTCONN) { so = sonewconn(so, 0); if (so == 0) goto drop; /* * This is ugly, but .... * * Mark socket as temporary until we're * committed to keeping it. The code at * ``drop'' and ``dropwithreset'' check the * flag dropsocket to see if the temporary * socket created here should be discarded. * We mark the socket as discardable until * we're committed to it below in TCPS_LISTEN. */ dropsocket++; inp = (struct inpcb *)so->so_pcb; inp->inp_laddr = ti->ti_dst; inp->inp_lport = ti->ti_dport; #if BSD>=43 inp->inp_options = ip_srcroute(); #endif tp = intotcpcb(inp); tp->t_state = TCPS_LISTEN;
/* Compute proper scaling value from buffer space */ while (tp->request_r_scale < TCP_MAX_WINSHIFT && TCP_MAXWIN << tp->request_r_scale < so->so_rcv.sb_hiwat) tp->request_r_scale++; } } /* * Segment received on connection. * Reset idle time and keep-alive timer. */ tp->t_idle = 0; tp->t_timer[TCPT_KEEP] = tcp_keepidle;
/* * Process options if not in LISTEN state, * else do it below (after getting remote address). */ if (optp && tp->t_state != TCPS_LISTEN) tcp_dooptions(tp, optp, optlen, ti, &ts_present, &ts_val, &ts_ecr);
/* * Header prediction: check for the two common cases * of a uni-directional data xfer. If the packet has * no control flags, is in-sequence, the window didn't * change and we're not retransmitting, it's a * candidate. If the length is zero and the ack moved * forward, we're the sender side of the xfer. Just * free the data acked & wake any higher level process * that was blocked waiting for space. If the length * is non-zero and the ack didn't move, we're the * receiver side. If we're getting packets in-order * (the reassembly queue is empty), add the data to * the socket buffer and note that we need a delayed ack. */ if (tp->t_state == TCPS_ESTABLISHED && (tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK && (!ts_present || TSTMP_GEQ(ts_val, tp->ts_recent)) && ti->ti_seq == tp->rcv_nxt && tiwin && tiwin == tp->snd_wnd && tp->snd_nxt == tp->snd_max) {
/* * If last ACK falls within this segment's sequence numbers, * record the timestamp. */ if (ts_present && SEQ_LEQ(ti->ti_seq, tp->last_ack_sent) && SEQ_LT(tp->last_ack_sent, ti->ti_seq + ti->ti_len)) { tp->ts_recent_age = tcp_now; tp->ts_recent = ts_val; }
if (ti->ti_len == 0) { if (SEQ_GT(ti->ti_ack, tp->snd_una) && SEQ_LEQ(ti->ti_ack, tp->snd_max) && tp->snd_cwnd >= tp->snd_wnd) { /* * this is a pure ack for outstanding data. */ ++tcpstat.tcps_predack; if (ts_present) tcp_xmit_timer(tp, tcp_now-ts_ecr+1); else if (tp->t_rtt && SEQ_GT(ti->ti_ack, tp->t_rtseq)) tcp_xmit_timer(tp, tp->t_rtt); acked = ti->ti_ack - tp->snd_una; tcpstat.tcps_rcvackpack++; tcpstat.tcps_rcvackbyte += acked; sbdrop(&so->so_snd, acked); tp->snd_una = ti->ti_ack; m_freem(m);
/* * If all outstanding data are acked, stop * retransmit timer, otherwise restart timer * using current (possibly backed-off) value. * If process is waiting for space, * wakeup/selwakeup/signal. If data * are ready to send, let tcp_output * decide between more output or persist. */ if (tp->snd_una == tp->snd_max) tp->t_timer[TCPT_REXMT] = 0; else if (tp->t_timer[TCPT_PERSIST] == 0) tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
if (so->so_snd.sb_flags & SB_NOTIFY) sowwakeup(so); if (so->so_snd.sb_cc) (void) tcp_output(tp); return; } } else if (ti->ti_ack == tp->snd_una && tp->seg_next == (struct tcpiphdr *)tp && ti->ti_len <= sbspace(&so->so_rcv)) { /* * this is a pure, in-sequence data packet * with nothing on the reassembly queue and * we have enough buffer space to take it. */ ++tcpstat.tcps_preddat; tp->rcv_nxt += ti->ti_len; tcpstat.tcps_rcvpack++; tcpstat.tcps_rcvbyte += ti->ti_len; /* * Drop TCP, IP headers and TCP options then add data * to socket buffer. */ m->m_data += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr); m->m_len -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr); sbappend(&so->so_rcv, m); sorwakeup(so); tp->t_flags |= TF_DELACK; return; } }
/* * Drop TCP, IP headers and TCP options. */ m->m_data += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr); m->m_len -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
/* * Calculate amount of space in receive window, * and then do TCP input processing. * Receive window is amount of space in rcv queue, * but not less than advertised window. */ { int win;
/* * How much space is there in a socket buffer (so->so_snd or so->so_rcv)? * This is problematical if the fields are unsigned, as the space might * still be negative (cc > hiwat or mbcnt > mbmax). Should detect * overflow and return 0. Should use "lmin" but it doesn't exist now. */ #define sbspace(sb) \ ((long) imin((int)((sb)->sb_hiwat - (sb)->sb_cc), \ (int)((sb)->sb_mbmax - (sb)->sb_mbcnt)))
case TCPS_LISTEN: { struct mbuf *am; register struct sockaddr_in *sin;
if (tiflags & TH_RST) goto drop; if (tiflags & TH_ACK) goto dropwithreset; if ((tiflags & TH_SYN) == 0) goto drop; /* * RFC1122 4.2.3.10, p. 104: discard bcast/mcast SYN * in_broadcast() should never return true on a received * packet with M_BCAST not set. */ if (m->m_flags & (M_BCAST|M_MCAST) || IN_MULTICAST(ti->ti_dst.s_addr)) goto drop; am = m_get(M_DONTWAIT, MT_SONAME); /* XXX */ if (am == NULL) goto drop;
/* Check to see if ts_recent is over 24 days old. */ if ((int)(tcp_now - tp->ts_recent_age) > TCP_PAWS_IDLE) { /* * Invalidate ts_recent. If this segment updates * ts_recent, the age will be reset later and ts_recent * will get a valid value. If it does not, setting * ts_recent to zero will at least satisfy the * requirement that zero be placed in the timestamp * echo reply when ts_recent isn't valid. The * age isn't reset until we get a valid ts_recent * because we don't want out-of-order segments to be * dropped when ts_recent is old. */ tp->ts_recent = 0; } else { tcpstat.tcps_rcvduppack++; tcpstat.tcps_rcvdupbyte += ti->ti_len; tcpstat.tcps_pawsdrop++; goto dropafterack; } }
if (todrop >= ti->ti_len) { tcpstat.tcps_rcvduppack++; tcpstat.tcps_rcvdupbyte += ti->ti_len; /* * If segment is just one to the left of the window, * check two special cases: * 1. Don't toss RST in response to 4.2-style keepalive. * 2. If the only thing to drop is a FIN, we can drop * it, but check the ACK or we will get into FIN * wars if our FINs crossed (both CLOSING). * In either case, send ACK to resynchronize, * but keep on processing for RST or ACK. */ if ((tiflags & TH_FIN && todrop == ti->ti_len + 1) #ifdef TCP_COMPAT_42 || (tiflags & TH_RST && ti->ti_seq == tp->rcv_nxt - 1) #endif ) { todrop = ti->ti_len; tiflags &= ~TH_FIN; tp->t_flags |= TF_ACKNOW; } else { /* * Handle the case when a bound socket connects * to itself. Allow packets with a SYN and * an ACK to continue with the processing. */ if (todrop != 0 || (tiflags & TH_ACK) == 0) goto dropafterack; } } else { tcpstat.tcps_rcvpartduppack++; tcpstat.tcps_rcvpartdupbyte += todrop; } m_adj(m, todrop); ti->ti_seq += todrop; ti->ti_len -= todrop; if (ti->ti_urp > todrop) ti->ti_urp -= todrop; else { tiflags &= ~TH_URG; ti->ti_urp = 0; } }
/* * If new data are received on a connection after the * user processes are gone, then RST the other end. */ if ((so->so_state & SS_NOFDREF) && tp->t_state > TCPS_CLOSE_WAIT && ti->ti_len) { tp = tcp_close(tp); tcpstat.tcps_rcvafterclose++; goto dropwithreset; }
/* * If segment ends after window, drop trailing data * (and PUSH and FIN); if nothing left, just ACK. */ todrop = (ti->ti_seq+ti->ti_len) - (tp->rcv_nxt+tp->rcv_wnd); if (todrop > 0) { tcpstat.tcps_rcvpackafterwin++; if (todrop >= ti->ti_len) { tcpstat.tcps_rcvbyteafterwin += ti->ti_len; /* * If a new connection request is received * while in TIME_WAIT, drop the old connection * and start over if the sequence numbers * are above the previous ones. */ if (tiflags & TH_SYN && tp->t_state == TCPS_TIME_WAIT && SEQ_GT(ti->ti_seq, tp->rcv_nxt)) { iss = tp->rcv_nxt + TCP_ISSINCR; tp = tcp_close(tp); goto findpcb; } /* * If window is closed can only take segments at * window edge, and have to drop data and PUSH from * incoming segments. Continue processing, but * remember to ack. Otherwise, drop segment * and ack. */ if (tp->rcv_wnd == 0 && ti->ti_seq == tp->rcv_nxt) { tp->t_flags |= TF_ACKNOW; tcpstat.tcps_rcvwinprobe++; } else goto dropafterack; } else tcpstat.tcps_rcvbyteafterwin += todrop; m_adj(m, -todrop); ti->ti_len -= todrop; tiflags &= ~(TH_PUSH|TH_FIN); }
记录时间戳
1 2 3 4 5 6 7 8 9 10
/* * If last ACK falls within this segment's sequence numbers, * record its timestamp. */ if (ts_present && SEQ_LEQ(ti->ti_seq, tp->last_ack_sent) && SEQ_LT(tp->last_ack_sent, ti->ti_seq + ti->ti_len + ((tiflags & (TH_SYN|TH_FIN)) != 0))) { tp->ts_recent_age = tcp_now; tp->ts_recent = ts_val; }
标志处理
SYN-RECEIVED
收到 RST：
被动打开 → 回到 LISTEN，不通知用户，清空重传队列。
SYN_SENT主动打开 → 通知“连接被拒绝”，清空队列，进入 CLOSED，删除 TCB。
关于主动打开为什么会进入SYN_SENT状态，这里解释一下，只有在同时打开时才会发生。
ESTABLISHED / FIN-WAIT-1 / FIN-WAIT-2 / CLOSE-WAIT
/* * If the RST bit is set examine the state: * SYN_RECEIVED STATE: * If passive open, return to LISTEN state. * If active open, inform user that connection was refused. * ESTABLISHED, FIN_WAIT_1, FIN_WAIT2, CLOSE_WAIT STATES: * Inform user that connection was reset, and close tcb. * CLOSING, LAST_ACK, TIME_WAIT STATES * Close the tcb. */ if (tiflags&TH_RST) switch (tp->t_state) {
case TCPS_SYN_RECEIVED: so->so_error = ECONNREFUSED; goto close;
case TCPS_ESTABLISHED: case TCPS_FIN_WAIT_1: case TCPS_FIN_WAIT_2: case TCPS_CLOSE_WAIT: so->so_error = ECONNRESET; close: tp->t_state = TCPS_CLOSED; tcpstat.tcps_drops++; tp = tcp_close(tp); goto drop;
case TCPS_CLOSING: case TCPS_LAST_ACK: case TCPS_TIME_WAIT: tp = tcp_close(tp); goto drop; }
其他标志处理
1.如果是连接阶段，由于前面经过了控制流判断，所以现在一定是syn_recived状态，带有ack
2.在 TCP 连接一旦建立（ESTABLISHED）之后，所有报文段都必须带 ACK 标志。
所以带SYN和不带ack的，都应该丢弃
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/* * If a SYN is in the window, then this is an * error and we send an RST and drop the connection. */ if (tiflags & TH_SYN) { tp = tcp_drop(tp, ECONNRESET); goto dropwithreset; }
/* * If the ACK bit is off we drop the segment and return. */ if ((tiflags & TH_ACK) == 0) goto drop;
/* * In SYN_RECEIVED state if the ack ACKs our SYN then enter * ESTABLISHED state and continue processing, otherwise * send an RST. */ case TCPS_SYN_RECEIVED: if (SEQ_GT(tp->snd_una, ti->ti_ack) || SEQ_GT(ti->ti_ack, tp->snd_max)) goto dropwithreset; tcpstat.tcps_connects++; soisconnected(so); tp->t_state = TCPS_ESTABLISHED; /* Do window scaling? */ if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) == (TF_RCVD_SCALE|TF_REQ_SCALE)) { tp->snd_scale = tp->requested_s_scale; tp->rcv_scale = tp->request_r_scale; } (void) tcp_reass(tp, (struct tcpiphdr *)0, (struct mbuf *)0); tp->snd_wl1 = ti->ti_seq - 1; /* fall into ... */
/* * In ESTABLISHED state: drop duplicate ACKs; ACK out of range * ACKs. If the ack is in the range * tp->snd_una < ti->ti_ack <= tp->snd_max * then advance tp->snd_una to ti->ti_ack and drop * data from the retransmission queue. If this ACK reflects * more up to date window information we update our window information. */ case TCPS_ESTABLISHED: case TCPS_FIN_WAIT_1: case TCPS_FIN_WAIT_2: case TCPS_CLOSE_WAIT: case TCPS_CLOSING: case TCPS_LAST_ACK: case TCPS_TIME_WAIT:
if (SEQ_LEQ(ti->ti_ack, tp->snd_una)) { if (ti->ti_len == 0 && tiwin == tp->snd_wnd) { tcpstat.tcps_rcvdupack++; /* * If we have outstanding data (other than * a window probe), this is a completely * duplicate ack (ie, window info didn't * change), the ack is the biggest we've * seen and we've seen exactly our rexmt * threshhold of them, assume a packet * has been dropped and retransmit it. * Kludge snd_nxt & the congestion * window so we send only this one * packet. * * We know we're losing at the current * window size so do congestion avoidance * (set ssthresh to half the current window * and pull our congestion window back to * the new ssthresh). * * Dup acks mean that packets have left the * network (they're now cached at the receiver) * so bump cwnd by the amount in the receiver * to keep a constant cwnd packets in the * network. */ if (tp->t_timer[TCPT_REXMT] == 0 || ti->ti_ack != tp->snd_una) tp->t_dupacks = 0; else if (++tp->t_dupacks == tcprexmtthresh) { tcp_seq onxt = tp->snd_nxt; u_int win = min(tp->snd_wnd, tp->snd_cwnd) / 2 / tp->t_maxseg;
if (win < 2) win = 2; tp->snd_ssthresh = win * tp->t_maxseg; tp->t_timer[TCPT_REXMT] = 0; tp->t_rtt = 0; tp->snd_nxt = ti->ti_ack; tp->snd_cwnd = tp->t_maxseg; (void) tcp_output(tp); tp->snd_cwnd = tp->snd_ssthresh + tp->t_maxseg * tp->t_dupacks; if (SEQ_GT(onxt, tp->snd_nxt)) tp->snd_nxt = onxt; goto drop; } else if (tp->t_dupacks > tcprexmtthresh) { tp->snd_cwnd += tp->t_maxseg; (void) tcp_output(tp); goto drop; } } else tp->t_dupacks = 0; break; } /* * If the congestion window was inflated to account * for the other side's cached packets, retract it. */ if (tp->t_dupacks > tcprexmtthresh && tp->snd_cwnd > tp->snd_ssthresh) tp->snd_cwnd = tp->snd_ssthresh; tp->t_dupacks = 0; if (SEQ_GT(ti->ti_ack, tp->snd_max)) { tcpstat.tcps_rcvacktoomuch++; goto dropafterack; } acked = ti->ti_ack - tp->snd_una; tcpstat.tcps_rcvackpack++; tcpstat.tcps_rcvackbyte += acked;
/* * If we have a timestamp reply, update smoothed * round trip time. If no timestamp is present but * transmit timer is running and timed sequence * number was acked, update smoothed round trip time. * Since we now have an rtt measurement, cancel the * timer backoff (cf., Phil Karn's retransmit alg.). * Recompute the initial retransmit timer. */ if (ts_present) tcp_xmit_timer(tp, tcp_now-ts_ecr+1); else if (tp->t_rtt && SEQ_GT(ti->ti_ack, tp->t_rtseq)) tcp_xmit_timer(tp,tp->t_rtt);
/* * If all outstanding data is acked, stop retransmit * timer and remember to restart (more output or persist). * If there is more data to be acked, restart retransmit * timer, using current (possibly backed-off) value. */ if (ti->ti_ack == tp->snd_max) { tp->t_timer[TCPT_REXMT] = 0; needoutput = 1; } else if (tp->t_timer[TCPT_PERSIST] == 0) tp->t_timer[TCPT_REXMT] = tp->t_rxtcur; /* * When new data is acked, open the congestion window. * If the window gives us less than ssthresh packets * in flight, open exponentially (maxseg per packet). * Otherwise open linearly: maxseg per window * (maxseg^2 / cwnd per packet), plus a constant * fraction of a packet (maxseg/8) to help larger windows * open quickly enough. */ { register u_int cw = tp->snd_cwnd; register u_int incr = tp->t_maxseg;
/* * In FIN_WAIT_1 STATE in addition to the processing * for the ESTABLISHED state if our FIN is now acknowledged * then enter FIN_WAIT_2. */ case TCPS_FIN_WAIT_1: if (ourfinisacked) { /* * If we can't receive any more * data, then closing user can proceed. * Starting the timer is contrary to the * specification, but if we don't get a FIN * we'll hang forever. */ if (so->so_state & SS_CANTRCVMORE) { soisdisconnected(so); tp->t_timer[TCPT_2MSL] = tcp_maxidle; } tp->t_state = TCPS_FIN_WAIT_2; } break;
/* * In CLOSING STATE in addition to the processing for * the ESTABLISHED state if the ACK acknowledges our FIN * then enter the TIME-WAIT state, otherwise ignore * the segment. */ case TCPS_CLOSING: if (ourfinisacked) { tp->t_state = TCPS_TIME_WAIT; tcp_canceltimers(tp); tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL; soisdisconnected(so); } break;
/* * In LAST_ACK, we may still be waiting for data to drain * and/or to be acked, as well as for the ack of our FIN. * If our FIN is now acknowledged, delete the TCB, * enter the closed state and return. */ case TCPS_LAST_ACK: if (ourfinisacked) { tp = tcp_close(tp); goto drop; } break;
/* * In TIME_WAIT state the only thing that should arrive * is a retransmission of the remote FIN. Acknowledge * it and restart the finack timer. */ case TCPS_TIME_WAIT: tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL; goto dropafterack; } }
step6: /* * Update window information. * Don't look at window if no ACK: TAC's send garbage on first SYN. */ if ((tiflags & TH_ACK) && (SEQ_LT(tp->snd_wl1, ti->ti_seq) || tp->snd_wl1 == ti->ti_seq && (SEQ_LT(tp->snd_wl2, ti->ti_ack) || tp->snd_wl2 == ti->ti_ack && tiwin > tp->snd_wnd))) { /* keep track of pure window updates */ if (ti->ti_len == 0 && tp->snd_wl2 == ti->ti_ack && tiwin > tp->snd_wnd) tcpstat.tcps_rcvwinupd++; tp->snd_wnd = tiwin; tp->snd_wl1 = ti->ti_seq; tp->snd_wl2 = ti->ti_ack; if (tp->snd_wnd > tp->max_sndwnd) tp->max_sndwnd = tp->snd_wnd; needoutput = 1; }
/* * Process segments with URG. */ if ((tiflags & TH_URG) && ti->ti_urp && TCPS_HAVERCVDFIN(tp->t_state) == 0) { /* * This is a kludge, but if we receive and accept * random urgent pointers, we'll crash in * soreceive. It's hard to imagine someone * actually wanting to send this much urgent data. */ if (ti->ti_urp + so->so_rcv.sb_cc > sb_max) { ti->ti_urp = 0; /* XXX */ tiflags &= ~TH_URG; /* XXX */ goto dodata; /* XXX */ } /* * If this segment advances the known urgent pointer, * then mark the data stream. This should not happen * in CLOSE_WAIT, CLOSING, LAST_ACK or TIME_WAIT STATES since * a FIN has been received from the remote side. * In these states we ignore the URG. * * According to RFC961 (Assigned Protocols), * the urgent pointer points to the last octet * of urgent data. We continue, however, * to consider it to indicate the first octet * of data past the urgent section as the original * spec states (in one of two places). */ if (SEQ_GT(ti->ti_seq+ti->ti_urp, tp->rcv_up)) { tp->rcv_up = ti->ti_seq + ti->ti_urp; so->so_oobmark = so->so_rcv.sb_cc + (tp->rcv_up - tp->rcv_nxt) - 1; if (so->so_oobmark == 0) so->so_state |= SS_RCVATMARK; sohasoutofband(so); tp->t_oobflags &= ~(TCPOOB_HAVEDATA | TCPOOB_HADDATA); } /* * Remove out of band data so doesn't get presented to user. * This can happen independent of advancing the URG pointer, * but if two URG's are pending at once, some out-of-band * data may creep in... ick. */ if (ti->ti_urp <= ti->ti_len #ifdef SO_OOBINLINE && (so->so_options & SO_OOBINLINE) == 0 #endif ) tcp_pulloutofband(so, ti, m); } else /* * If no out of band data is expected, * pull receive urgent pointer along * with the receive window. */ if (SEQ_GT(tp->rcv_nxt, tp->rcv_up)) tp->rcv_up = tp->rcv_nxt; dodata: /* XXX */
/* * Process the segment text, merging it into the TCP sequencing queue, * and arranging for acknowledgment of receipt if necessary. * This process logically involves adjusting tp->rcv_wnd as data * is presented to the user (this happens in tcp_usrreq.c, * case PRU_RCVD). If a FIN has already been received on this * connection then we just ignore the text. */ if ((ti->ti_len || (tiflags&TH_FIN)) && TCPS_HAVERCVDFIN(tp->t_state) == 0) { TCP_REASS(tp, ti, m, so, tiflags); /* * Note the amount of data that peer has sent into * our window, in order to estimate the sender's * buffer size. */ len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt); } else { m_freem(m); tiflags &= ~TH_FIN; }
/* * If FIN is received ACK the FIN and let the user know * that the connection is closing. */ if (tiflags & TH_FIN) { if (TCPS_HAVERCVDFIN(tp->t_state) == 0) { socantrcvmore(so); tp->t_flags |= TF_ACKNOW; tp->rcv_nxt++; } switch (tp->t_state) {
/* * In SYN_RECEIVED and ESTABLISHED STATES * enter the CLOSE_WAIT state. */ case TCPS_SYN_RECEIVED: case TCPS_ESTABLISHED: tp->t_state = TCPS_CLOSE_WAIT; break;
/* * If still in FIN_WAIT_1 STATE FIN has not been acked so * enter the CLOSING state. */ case TCPS_FIN_WAIT_1: tp->t_state = TCPS_CLOSING; break;
/* * In FIN_WAIT_2 state enter the TIME_WAIT state, * starting the time-wait timer, turning off the other * standard timers. */ case TCPS_FIN_WAIT_2: tp->t_state = TCPS_TIME_WAIT; tcp_canceltimers(tp); tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL; soisdisconnected(so); break;
/* * In TIME_WAIT state restart the 2 MSL time_wait timer. */ case TCPS_TIME_WAIT: tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL; break; } } if (so->so_options & SO_DEBUG) tcp_trace(TA_INPUT, ostate, tp, &tcp_saveti, 0);
/* * Return any desired output. */ if (needoutput || (tp->t_flags & TF_ACKNOW)) (void) tcp_output(tp); return;
dropafterack: /* * Generate an ACK dropping incoming segment if it occupies * sequence space, where the ACK reflects our state. */ if (tiflags & TH_RST) goto drop; m_freem(m); tp->t_flags |= TF_ACKNOW; (void) tcp_output(tp); return;
dropwithreset: /* * Generate a RST, dropping incoming segment. * Make ACK acceptable to originator of segment. * Don't bother to respond if destination was broadcast/multicast. */ if ((tiflags & TH_RST) || m->m_flags & (M_BCAST|M_MCAST) || IN_MULTICAST(ti->ti_dst.s_addr)) goto drop; if (tiflags & TH_ACK) tcp_respond(tp, ti, m, (tcp_seq)0, ti->ti_ack, TH_RST); else { if (tiflags & TH_SYN) ti->ti_len++; tcp_respond(tp, ti, m, ti->ti_seq+ti->ti_len, (tcp_seq)0, TH_RST|TH_ACK); } /* destroy temporarily created socket */ if (dropsocket) (void) soabort(so); return;
drop: /* * Drop space held by incoming segment and return. */ if (tp && (tp->t_inpcb->inp_socket->so_options & SO_DEBUG)) tcp_trace(TA_DROP, ostate, tp, &tcp_saveti, 0); m_freem(m); /* destroy temporarily created socket */ if (dropsocket) (void) soabort(so); return; #ifndef TUBA_INCLUDE }
