BSD 4_4_Lite1 release

[unix-history] / usr / src / sys / netinet / tcp_output.c

diff --git a/usr/src/sys/netinet/tcp_output.c b/usr/src/sys/netinet/tcp_output.c
index 241fbd8..667579f 100644 (file)
--- a/usr/src/sys/netinet/tcp_output.c
+++ b/usr/src/sys/netinet/tcp_output.c
@@ -1,54 +1,84 @@
 /*
 /*

- * Copyright (c) 1982, 1986 Regents of the University of California.
- * All rights reserved.  The Berkeley software License Agreement
- * specifies the terms and conditions for redistribution.
+ * Copyright (c) 1982, 1986, 1988, 1990, 1993
+ *     The Regents of the University of California.  All rights reserved.

  *
  *

- *     @(#)tcp_output.c        7.6 (Berkeley) %G%
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *     This product includes software developed by the University of
+ *     California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *     @(#)tcp_output.c        8.3 (Berkeley) 12/30/93

  */
 
  */
 

-#include "param.h"
-#include "systm.h"
-#include "mbuf.h"
-#include "protosw.h"
-#include "socket.h"
-#include "socketvar.h"
-#include "errno.h"
-
-#include "../net/route.h"
-
-#include "in.h"
-#include "in_pcb.h"
-#include "in_systm.h"
-#include "ip.h"
-#include "ip_var.h"
-#include "tcp.h"
+#include <sys/param.h>
+#include <sys/systm.h>
+#include <sys/malloc.h>
+#include <sys/mbuf.h>
+#include <sys/protosw.h>
+#include <sys/socket.h>
+#include <sys/socketvar.h>
+#include <sys/errno.h>
+
+#include <net/route.h>
+
+#include <netinet/in.h>
+#include <netinet/in_systm.h>
+#include <netinet/ip.h>
+#include <netinet/in_pcb.h>
+#include <netinet/ip_var.h>
+#include <netinet/tcp.h>

 #define        TCPOUTFLAGS
 #define        TCPOUTFLAGS

-#include "tcp_fsm.h"
-#include "tcp_seq.h"
-#include "tcp_timer.h"
-#include "tcp_var.h"
-#include "tcpip.h"
-#include "tcp_debug.h"
+#include <netinet/tcp_fsm.h>
+#include <netinet/tcp_seq.h>
+#include <netinet/tcp_timer.h>
+#include <netinet/tcp_var.h>
+#include <netinet/tcpip.h>
+#include <netinet/tcp_debug.h>
+
+#ifdef notyet
+extern struct mbuf *m_copypack();
+#endif

 
 

-/*
- * Initial options.
- */
-u_char tcp_initopt[4] = { TCPOPT_MAXSEG, 4, 0x0, 0x0, };
+
+#define MAX_TCPOPTLEN  32      /* max # bytes that go in options */

 
 /*
  * Tcp output routine: figure out what should be sent and send it.
  */
 
 /*
  * Tcp output routine: figure out what should be sent and send it.
  */

+int

 tcp_output(tp)
        register struct tcpcb *tp;
 {
        register struct socket *so = tp->t_inpcb->inp_socket;
 tcp_output(tp)
        register struct tcpcb *tp;
 {
        register struct socket *so = tp->t_inpcb->inp_socket;

-       register int len, win;
-       struct mbuf *m0;
+       register long len, win;

        int off, flags, error;
        register struct mbuf *m;
        register struct tcpiphdr *ti;
        int off, flags, error;
        register struct mbuf *m;
        register struct tcpiphdr *ti;

-       u_char *opt;
-       unsigned optlen = 0;
+       u_char opt[MAX_TCPOPTLEN];
+       unsigned optlen, hdrlen;

        int idle, sendalot;
 
        /*
        int idle, sendalot;
 
        /*


@@ -58,11 +88,19 @@ tcp_output(tp)
         * to send, then transmit; otherwise, investigate further.
         */
        idle = (tp->snd_max == tp->snd_una);
         * to send, then transmit; otherwise, investigate further.
         */
        idle = (tp->snd_max == tp->snd_una);

+       if (idle && tp->t_idle >= tp->t_rxtcur)
+               /*
+                * We have been idle for "a while" and no acks are
+                * expected to clock out any data we send --
+                * slow start to get ack "clock" running again.
+                */
+               tp->snd_cwnd = tp->t_maxseg;

 again:
        sendalot = 0;
        off = tp->snd_nxt - tp->snd_una;
 again:
        sendalot = 0;
        off = tp->snd_nxt - tp->snd_una;

-       win = MIN(tp->snd_wnd, tp->snd_cwnd);
+       win = min(tp->snd_wnd, tp->snd_cwnd);

 
 

+       flags = tcp_outflags[tp->t_state];

        /*
         * If in persist timeout with window of 0, send 1 byte.
         * Otherwise, if window is small but nonzero
        /*
         * If in persist timeout with window of 0, send 1 byte.
         * Otherwise, if window is small but nonzero


@@ -70,40 +108,50 @@ again:
         * and go to transmit state.
         */
        if (tp->t_force) {
         * and go to transmit state.
         */
        if (tp->t_force) {

-               if (win == 0)
+               if (win == 0) {
+                       /*
+                        * If we still have some data to send, then
+                        * clear the FIN bit.  Usually this would
+                        * happen below when it realizes that we
+                        * aren't sending all the data.  However,
+                        * if we have exactly 1 byte of unset data,
+                        * then it won't clear the FIN bit below,
+                        * and if we are in persist state, we wind
+                        * up sending the packet without recording
+                        * that we sent the FIN bit.
+                        *
+                        * We can't just blindly clear the FIN bit,
+                        * because if we don't have any more data
+                        * to send then the probe will be the FIN
+                        * itself.
+                        */
+                       if (off < so->so_snd.sb_cc)
+                               flags &= ~TH_FIN;

                        win = 1;
                        win = 1;

-               else {
+               } else {

                        tp->t_timer[TCPT_PERSIST] = 0;
                        tp->t_rxtshift = 0;
                }
        }
 
                        tp->t_timer[TCPT_PERSIST] = 0;
                        tp->t_rxtshift = 0;
                }
        }
 

-       len = MIN(so->so_snd.sb_cc, win) - off;
-       flags = tcp_outflags[tp->t_state];
+       len = min(so->so_snd.sb_cc, win) - off;

 
        if (len < 0) {
                /*
                 * If FIN has been sent but not acked,
                 * but we haven't been called to retransmit,
 
        if (len < 0) {
                /*
                 * If FIN has been sent but not acked,
                 * but we haven't been called to retransmit,

-                * len will be -1; transmit if acking, otherwise no need.
-                * Otherwise, window shrank after we sent into it.
-                * If window shrank to 0, cancel pending retransmit
-                * and pull snd_nxt back to (closed) window.
-                * We will enter persist state below.
-                * If the window didn't close completely,
+                * len will be -1.  Otherwise, window shrank
+                * after we sent into it.  If window shrank to 0,
+                * cancel pending retransmit and pull snd_nxt
+                * back to (closed) window.  We will enter persist
+                * state below.  If the window didn't close completely,

                 * just wait for an ACK.
                 */
                 * just wait for an ACK.
                 */

-               if (flags & TH_FIN) {
-                       if (tp->t_flags & TF_ACKNOW)
-                               len = 0;
-                       else
-                               return (0);
-               } else if (win == 0) {
+               len = 0;
+               if (win == 0) {

                        tp->t_timer[TCPT_REXMT] = 0;
                        tp->snd_nxt = tp->snd_una;
                        tp->t_timer[TCPT_REXMT] = 0;
                        tp->snd_nxt = tp->snd_una;

-                       len = 0;
-               } else
-                       return (0);
+               }

        }
        if (len > tp->t_maxseg) {
                len = tp->t_maxseg;
        }
        if (len > tp->t_maxseg) {
                len = tp->t_maxseg;


@@ -111,26 +159,8 @@ again:
        }
        if (SEQ_LT(tp->snd_nxt + len, tp->snd_una + so->so_snd.sb_cc))
                flags &= ~TH_FIN;
        }
        if (SEQ_LT(tp->snd_nxt + len, tp->snd_una + so->so_snd.sb_cc))
                flags &= ~TH_FIN;

-       win = sbspace(&so->so_rcv);
-

 
 

-       /*
-        * If our state indicates that FIN should be sent
-        * and we have not yet done so, or we're retransmitting the FIN,
-        * then we need to send.
-        */
-       if (flags & TH_FIN &&
-           ((tp->t_flags & TF_SENTFIN) == 0 || tp->snd_nxt == tp->snd_una))
-               goto send;
-       /*
-        * Send if we owe peer an ACK.
-        */
-       if (tp->t_flags & TF_ACKNOW)
-               goto send;
-       if (flags & (TH_SYN|TH_RST))
-               goto send;
-       if (SEQ_GT(tp->snd_up, tp->snd_una))
-               goto send;
+       win = sbspace(&so->so_rcv);

 
        /*
         * Sender silly window avoidance.  If connection is idle
 
        /*
         * Sender silly window avoidance.  If connection is idle


@@ -159,11 +189,41 @@ again:
        /*
         * Compare available window to amount of window
         * known to peer (as advertised window less
        /*
         * Compare available window to amount of window
         * known to peer (as advertised window less

-        * next expected input.)  If the difference is 35% or more of the
-        * maximum possible window, then want to send a window update to peer.
+        * next expected input).  If the difference is at least two
+        * max size segments, or at least 50% of the maximum possible
+        * window, then want to send a window update to peer.
+        */
+       if (win > 0) {
+               /* 
+                * "adv" is the amount we can increase the window,
+                * taking into account that we are limited by
+                * TCP_MAXWIN << tp->rcv_scale.
+                */
+               long adv = min(win, (long)TCP_MAXWIN << tp->rcv_scale) -
+                       (tp->rcv_adv - tp->rcv_nxt);
+
+               if (adv >= (long) (2 * tp->t_maxseg))
+                       goto send;
+               if (2 * adv >= (long) so->so_rcv.sb_hiwat)
+                       goto send;
+       }
+
+       /*
+        * Send if we owe peer an ACK.

         */
         */

-       if (win > 0 &&
-           ((100*(win-(tp->rcv_adv-tp->rcv_nxt))/so->so_rcv.sb_hiwat) >= 35))
+       if (tp->t_flags & TF_ACKNOW)
+               goto send;
+       if (flags & (TH_SYN|TH_RST))
+               goto send;
+       if (SEQ_GT(tp->snd_up, tp->snd_una))
+               goto send;
+       /*
+        * If our state indicates that FIN should be sent
+        * and we have not yet done so, or we're retransmitting the FIN,
+        * then we need to send.
+        */
+       if (flags & TH_FIN &&
+           ((tp->t_flags & TF_SENTFIN) == 0 || tp->snd_nxt == tp->snd_una))

                goto send;
 
        /*
                goto send;
 
        /*


@@ -200,16 +260,80 @@ again:
        return (0);
 
 send:
        return (0);
 
 send:

+       /*
+        * Before ESTABLISHED, force sending of initial options
+        * unless TCP set not to do any options.
+        * NOTE: we assume that the IP/TCP header plus TCP options
+        * always fit in a single mbuf, leaving room for a maximum
+        * link header, i.e.
+        *      max_linkhdr + sizeof (struct tcpiphdr) + optlen <= MHLEN
+        */
+       optlen = 0;
+       hdrlen = sizeof (struct tcpiphdr);
+       if (flags & TH_SYN) {
+               tp->snd_nxt = tp->iss;
+               if ((tp->t_flags & TF_NOOPT) == 0) {
+                       u_short mss;
+
+                       opt[0] = TCPOPT_MAXSEG;
+                       opt[1] = 4;
+                       mss = htons((u_short) tcp_mss(tp, 0));
+                       bcopy((caddr_t)&mss, (caddr_t)(opt + 2), sizeof(mss));
+                       optlen = 4;
+        
+                       if ((tp->t_flags & TF_REQ_SCALE) &&
+                           ((flags & TH_ACK) == 0 ||
+                           (tp->t_flags & TF_RCVD_SCALE))) {
+                               *((u_long *) (opt + optlen)) = htonl(
+                                       TCPOPT_NOP << 24 |
+                                       TCPOPT_WINDOW << 16 |
+                                       TCPOLEN_WINDOW << 8 |
+                                       tp->request_r_scale);
+                               optlen += 4;
+                       }
+               }
+       }
+ 
+       /*
+        * Send a timestamp and echo-reply if this is a SYN and our side 
+        * wants to use timestamps (TF_REQ_TSTMP is set) or both our side
+        * and our peer have sent timestamps in our SYN's.
+        */
+       if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP &&
+            (flags & TH_RST) == 0 &&
+           ((flags & (TH_SYN|TH_ACK)) == TH_SYN ||
+            (tp->t_flags & TF_RCVD_TSTMP))) {
+               u_long *lp = (u_long *)(opt + optlen);
+ 
+               /* Form timestamp option as shown in appendix A of RFC 1323. */
+               *lp++ = htonl(TCPOPT_TSTAMP_HDR);
+               *lp++ = htonl(tcp_now);
+               *lp   = htonl(tp->ts_recent);
+               optlen += TCPOLEN_TSTAMP_APPA;
+       }
+
+       hdrlen += optlen;
+ 
+       /*
+        * Adjust data length if insertion of options will
+        * bump the packet length beyond the t_maxseg length.
+        */
+        if (len > tp->t_maxseg - optlen) {
+               len = tp->t_maxseg - optlen;
+               sendalot = 1;
+        }
+
+
+#ifdef DIAGNOSTIC
+       if (max_linkhdr + hdrlen > MHLEN)
+               panic("tcphdr too big");
+#endif
+

        /*
         * Grab a header mbuf, attaching a copy of data to
         * be transmitted, and initialize the header from
         * the template for sends on this connection.
         */
        /*
         * Grab a header mbuf, attaching a copy of data to
         * be transmitted, and initialize the header from
         * the template for sends on this connection.
         */

-       MGET(m, M_DONTWAIT, MT_HEADER);
-       if (m == NULL)
-               return (ENOBUFS);
-       m->m_off = MMAXOFF - sizeof (struct tcpiphdr);
-       m->m_len = sizeof (struct tcpiphdr);

        if (len) {
                if (tp->t_force && len == 1)
                        tcpstat.tcps_sndprobe++;
        if (len) {
                if (tp->t_force && len == 1)
                        tcpstat.tcps_sndprobe++;


@@ -220,18 +344,62 @@ send:
                        tcpstat.tcps_sndpack++;
                        tcpstat.tcps_sndbyte += len;
                }
                        tcpstat.tcps_sndpack++;
                        tcpstat.tcps_sndbyte += len;
                }

-               m->m_next = m_copy(so->so_snd.sb_mb, off, len);
-               if (m->m_next == 0)
-                       len = 0;
-       } else if (tp->t_flags & TF_ACKNOW)
-               tcpstat.tcps_sndacks++;
-       else if (flags & (TH_SYN|TH_FIN|TH_RST))
-               tcpstat.tcps_sndctrl++;
-       else if (SEQ_GT(tp->snd_up, tp->snd_una))
-               tcpstat.tcps_sndurg++;
-       else
-               tcpstat.tcps_sndwinup++;
+#ifdef notyet
+               if ((m = m_copypack(so->so_snd.sb_mb, off,
+                   (int)len, max_linkhdr + hdrlen)) == 0) {
+                       error = ENOBUFS;
+                       goto out;
+               }
+               /*
+                * m_copypack left space for our hdr; use it.
+                */
+               m->m_len += hdrlen;
+               m->m_data -= hdrlen;
+#else
+               MGETHDR(m, M_DONTWAIT, MT_HEADER);
+               if (m == NULL) {
+                       error = ENOBUFS;
+                       goto out;
+               }
+               m->m_data += max_linkhdr;
+               m->m_len = hdrlen;
+               if (len <= MHLEN - hdrlen - max_linkhdr) {
+                       m_copydata(so->so_snd.sb_mb, off, (int) len,
+                           mtod(m, caddr_t) + hdrlen);
+                       m->m_len += len;
+               } else {
+                       m->m_next = m_copy(so->so_snd.sb_mb, off, (int) len);
+                       if (m->m_next == 0)
+                               len = 0;
+               }
+#endif
+               /*
+                * If we're sending everything we've got, set PUSH.
+                * (This will keep happy those implementations which only
+                * give data to the user when a buffer fills or
+                * a PUSH comes in.)
+                */
+               if (off + len == so->so_snd.sb_cc)
+                       flags |= TH_PUSH;
+       } else {
+               if (tp->t_flags & TF_ACKNOW)
+                       tcpstat.tcps_sndacks++;
+               else if (flags & (TH_SYN|TH_FIN|TH_RST))
+                       tcpstat.tcps_sndctrl++;
+               else if (SEQ_GT(tp->snd_up, tp->snd_una))
+                       tcpstat.tcps_sndurg++;
+               else
+                       tcpstat.tcps_sndwinup++;

 
 

+               MGETHDR(m, M_DONTWAIT, MT_HEADER);
+               if (m == NULL) {
+                       error = ENOBUFS;
+                       goto out;
+               }
+               m->m_data += max_linkhdr;
+               m->m_len = hdrlen;
+       }
+       m->m_pkthdr.rcvif = (struct ifnet *)0;

        ti = mtod(m, struct tcpiphdr *);
        if (tp->t_template == 0)
                panic("tcp_output");
        ti = mtod(m, struct tcpiphdr *);
        if (tp->t_template == 0)
                panic("tcp_output");


@@ -245,44 +413,26 @@ send:
        if (flags & TH_FIN && tp->t_flags & TF_SENTFIN && 
            tp->snd_nxt == tp->snd_max)
                tp->snd_nxt--;
        if (flags & TH_FIN && tp->t_flags & TF_SENTFIN && 
            tp->snd_nxt == tp->snd_max)
                tp->snd_nxt--;

-       ti->ti_seq = htonl(tp->snd_nxt);
-       ti->ti_ack = htonl(tp->rcv_nxt);

        /*
        /*

-        * Before ESTABLISHED, force sending of initial options
-        * unless TCP set to not do any options.
+        * If we are doing retransmissions, then snd_nxt will
+        * not reflect the first unsent octet.  For ACK only
+        * packets, we do not want the sequence number of the
+        * retransmitted packet, we want the sequence number
+        * of the next unsent octet.  So, if there is no data
+        * (and no SYN or FIN), use snd_max instead of snd_nxt
+        * when filling in ti_seq.  But if we are in persist
+        * state, snd_max might reflect one byte beyond the
+        * right edge of the window, so use snd_nxt in that
+        * case, since we know we aren't doing a retransmission.
+        * (retransmit and persist are mutually exclusive...)

         */
         */

-       opt = NULL;
-       if (tp->t_state < TCPS_ESTABLISHED && (tp->t_flags & TF_NOOPT) == 0) {
-               u_short mss;
-
-               mss = MIN(so->so_rcv.sb_hiwat / 2, tcp_mss(tp));
-               if (mss > IP_MSS - sizeof(struct tcpiphdr)) {
-                       opt = tcp_initopt;
-                       optlen = sizeof (tcp_initopt);
-                       *(u_short *)(opt + 2) = htons(mss);
-               }
-       } else if (tp->t_tcpopt) {
-               opt = mtod(tp->t_tcpopt, u_char *);
-               optlen = tp->t_tcpopt->m_len;
-       }
-       if (opt) {
-               m0 = m->m_next;
-               m->m_next = m_get(M_DONTWAIT, MT_DATA);
-               if (m->m_next == 0) {
-                       (void) m_free(m);
-                       m_freem(m0);
-                       return (ENOBUFS);
-               }
-               m->m_next->m_next = m0;
-               m0 = m->m_next;
-               m0->m_len = optlen;
-               bcopy((caddr_t)opt, mtod(m0, caddr_t), optlen);
-               opt = (u_char *)(mtod(m0, caddr_t) + optlen);
-               while (m0->m_len & 0x3) {
-                       *opt++ = TCPOPT_EOL;
-                       m0->m_len++;
-               }
-               optlen = m0->m_len;
+       if (len || (flags & (TH_SYN|TH_FIN)) || tp->t_timer[TCPT_PERSIST])
+               ti->ti_seq = htonl(tp->snd_nxt);
+       else
+               ti->ti_seq = htonl(tp->snd_max);
+       ti->ti_ack = htonl(tp->rcv_nxt);
+       if (optlen) {
+               bcopy((caddr_t)opt, (caddr_t)(ti + 1), optlen);

                ti->ti_off = (sizeof (struct tcphdr) + optlen) >> 2;
        }
        ti->ti_flags = flags;
                ti->ti_off = (sizeof (struct tcphdr) + optlen) >> 2;
        }
        ti->ti_flags = flags;


@@ -290,11 +440,13 @@ send:
         * Calculate receive window.  Don't shrink window,
         * but avoid silly window syndrome.
         */
         * Calculate receive window.  Don't shrink window,
         * but avoid silly window syndrome.
         */

-       if (win < so->so_rcv.sb_hiwat / 4 && win < tp->t_maxseg)
+       if (win < (long)(so->so_rcv.sb_hiwat / 4) && win < (long)tp->t_maxseg)

                win = 0;
                win = 0;

-       if (win < (int)(tp->rcv_adv - tp->rcv_nxt))
-               win = (int)(tp->rcv_adv - tp->rcv_nxt);
-       ti->ti_win = htons((u_short)win);
+       if (win > (long)TCP_MAXWIN << tp->rcv_scale)
+               win = (long)TCP_MAXWIN << tp->rcv_scale;
+       if (win < (long)(tp->rcv_adv - tp->rcv_nxt))
+               win = (long)(tp->rcv_adv - tp->rcv_nxt);
+       ti->ti_win = htons((u_short) (win>>tp->rcv_scale));

        if (SEQ_GT(tp->snd_up, tp->snd_nxt)) {
                ti->ti_urp = htons((u_short)(tp->snd_up - tp->snd_nxt));
                ti->ti_flags |= TH_URG;
        if (SEQ_GT(tp->snd_up, tp->snd_nxt)) {
                ti->ti_urp = htons((u_short)(tp->snd_up - tp->snd_nxt));
                ti->ti_flags |= TH_URG;


@@ -306,64 +458,63 @@ send:
                 * number wraparound.
                 */
                tp->snd_up = tp->snd_una;               /* drag it along */
                 * number wraparound.
                 */
                tp->snd_up = tp->snd_una;               /* drag it along */

-       /*
-        * If anything to send and we can send it all, set PUSH.
-        * (This will keep happy those implementations which only
-        * give data to the user when a buffer fills or a PUSH comes in.)
-        */
-       if (len && off+len == so->so_snd.sb_cc)
-               ti->ti_flags |= TH_PUSH;

 
        /*
         * Put TCP length in extended header, and then
         * checksum extended header and data.
         */
        if (len + optlen)
 
        /*
         * Put TCP length in extended header, and then
         * checksum extended header and data.
         */
        if (len + optlen)

-               ti->ti_len = htons((u_short)(sizeof(struct tcphdr) +
+               ti->ti_len = htons((u_short)(sizeof (struct tcphdr) +

                    optlen + len));
                    optlen + len));

-       ti->ti_sum = in_cksum(m, sizeof (struct tcpiphdr) + (int)optlen + len);
+       ti->ti_sum = in_cksum(m, (int)(hdrlen + len));

 
        /*
         * In transmit state, time the transmission and arrange for
         * the retransmit.  In persist state, just set snd_max.
         */
        if (tp->t_force == 0 || tp->t_timer[TCPT_PERSIST] == 0) {
 
        /*
         * In transmit state, time the transmission and arrange for
         * the retransmit.  In persist state, just set snd_max.
         */
        if (tp->t_force == 0 || tp->t_timer[TCPT_PERSIST] == 0) {

-               /*
-                * Time this transmission if not a retransmission and
-                * not currently timing anything.
-                */
-               if (tp->t_rtt == 0 && tp->snd_nxt == tp->snd_max) {
-                       tp->t_rtt = 1;
-                       tp->t_rtseq = tp->snd_nxt;
-                       tcpstat.tcps_segstimed++;
-               }
+               tcp_seq startseq = tp->snd_nxt;
+

                /*
                 * Advance snd_nxt over sequence space of this segment.
                 */
                /*
                 * Advance snd_nxt over sequence space of this segment.
                 */

-               if (flags & TH_SYN)
-                       tp->snd_nxt++;
-               if (flags & TH_FIN) {
-                       tp->snd_nxt++;
-                       tp->t_flags |= TF_SENTFIN;
+               if (flags & (TH_SYN|TH_FIN)) {
+                       if (flags & TH_SYN)
+                               tp->snd_nxt++;
+                       if (flags & TH_FIN) {
+                               tp->snd_nxt++;
+                               tp->t_flags |= TF_SENTFIN;
+                       }

                }
                tp->snd_nxt += len;
                }
                tp->snd_nxt += len;

-               if (SEQ_GT(tp->snd_nxt, tp->snd_max))
+               if (SEQ_GT(tp->snd_nxt, tp->snd_max)) {

                        tp->snd_max = tp->snd_nxt;
                        tp->snd_max = tp->snd_nxt;

+                       /*
+                        * Time this transmission if not a retransmission and
+                        * not currently timing anything.
+                        */
+                       if (tp->t_rtt == 0) {
+                               tp->t_rtt = 1;
+                               tp->t_rtseq = startseq;
+                               tcpstat.tcps_segstimed++;
+                       }
+               }

 
                /*
                 * Set retransmit timer if not currently set,
                 * and not doing an ack or a keep-alive probe.
 
                /*
                 * Set retransmit timer if not currently set,
                 * and not doing an ack or a keep-alive probe.

-                * Initial value for retransmit timer is tcp_beta*tp->t_srtt.
+                * Initial value for retransmit timer is smoothed
+                * round-trip time + 2 * round-trip time variance.

                 * Initialize shift counter which is used for backoff
                 * of retransmit time.
                 */
                if (tp->t_timer[TCPT_REXMT] == 0 &&
                    tp->snd_nxt != tp->snd_una) {
                 * Initialize shift counter which is used for backoff
                 * of retransmit time.
                 */
                if (tp->t_timer[TCPT_REXMT] == 0 &&
                    tp->snd_nxt != tp->snd_una) {

-                       TCPT_RANGESET(tp->t_timer[TCPT_REXMT],
-                         tcp_beta * (tp->t_srtt ? tp->t_srtt : TCPTV_SRTTDFLT),
-                         TCPTV_MIN, TCPTV_MAX);
-                       tp->t_rxtshift = 0;
-                       tp->t_timer[TCPT_PERSIST] = 0;
+                       tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
+                       if (tp->t_timer[TCPT_PERSIST]) {
+                               tp->t_timer[TCPT_PERSIST] = 0;
+                               tp->t_rxtshift = 0;
+                       }

                }
        } else
                if (SEQ_GT(tp->snd_nxt + len, tp->snd_max))
                }
        } else
                if (SEQ_GT(tp->snd_nxt + len, tp->snd_max))


@@ -377,14 +528,41 @@ send:
 
        /*
         * Fill in IP length and desired time to live and
 
        /*
         * Fill in IP length and desired time to live and

-        * send to IP level.
+        * send to IP level.  There should be a better way
+        * to handle ttl and tos; we could keep them in
+        * the template, but need a way to checksum without them.

         */
         */

-       ((struct ip *)ti)->ip_len = sizeof (struct tcpiphdr) + optlen + len;
-       ((struct ip *)ti)->ip_ttl = TCP_TTL;
+       m->m_pkthdr.len = hdrlen + len;
+#ifdef TUBA
+       if (tp->t_tuba_pcb)
+               error = tuba_output(m, tp);
+       else
+#endif
+    {
+       ((struct ip *)ti)->ip_len = m->m_pkthdr.len;
+       ((struct ip *)ti)->ip_ttl = tp->t_inpcb->inp_ip.ip_ttl; /* XXX */
+       ((struct ip *)ti)->ip_tos = tp->t_inpcb->inp_ip.ip_tos; /* XXX */
+#if BSD >= 43

        error = ip_output(m, tp->t_inpcb->inp_options, &tp->t_inpcb->inp_route,
        error = ip_output(m, tp->t_inpcb->inp_options, &tp->t_inpcb->inp_route,

+           so->so_options & SO_DONTROUTE, 0);
+#else
+       error = ip_output(m, (struct mbuf *)0, &tp->t_inpcb->inp_route, 

            so->so_options & SO_DONTROUTE);
            so->so_options & SO_DONTROUTE);

-       if (error)
+#endif
+    }
+       if (error) {
+out:
+               if (error == ENOBUFS) {
+                       tcp_quench(tp->t_inpcb, 0);
+                       return (0);
+               }
+               if ((error == EHOSTUNREACH || error == ENETDOWN)
+                   && TCPS_HAVERCVDSYN(tp->t_state)) {
+                       tp->t_softerror = error;
+                       return (0);
+               }

                return (error);
                return (error);

+       }

        tcpstat.tcps_sndtotal++;
 
        /*
        tcpstat.tcps_sndtotal++;
 
        /*


@@ -395,15 +573,18 @@ send:
         */
        if (win > 0 && SEQ_GT(tp->rcv_nxt+win, tp->rcv_adv))
                tp->rcv_adv = tp->rcv_nxt + win;
         */
        if (win > 0 && SEQ_GT(tp->rcv_nxt+win, tp->rcv_adv))
                tp->rcv_adv = tp->rcv_nxt + win;

+       tp->last_ack_sent = tp->rcv_nxt;

        tp->t_flags &= ~(TF_ACKNOW|TF_DELACK);
        if (sendalot)
                goto again;
        return (0);
 }
 
        tp->t_flags &= ~(TF_ACKNOW|TF_DELACK);
        if (sendalot)
                goto again;
        return (0);
 }
 

+void

 tcp_setpersist(tp)
        register struct tcpcb *tp;
 {
 tcp_setpersist(tp)
        register struct tcpcb *tp;
 {

+       register t = ((tp->t_srtt >> 2) + tp->t_rttvar) >> 1;

 
        if (tp->t_timer[TCPT_REXMT])
                panic("tcp_output REXMT");
 
        if (tp->t_timer[TCPT_REXMT])
                panic("tcp_output REXMT");


@@ -411,7 +592,7 @@ tcp_setpersist(tp)
         * Start/restart persistance timer.
         */
        TCPT_RANGESET(tp->t_timer[TCPT_PERSIST],
         * Start/restart persistance timer.
         */
        TCPT_RANGESET(tp->t_timer[TCPT_PERSIST],

-           ((int)(tcp_beta * tp->t_srtt)) << tp->t_rxtshift,
+           t * tcp_backoff[tp->t_rxtshift],

            TCPTV_PERSMIN, TCPTV_PERSMAX);
        if (tp->t_rxtshift < TCP_MAXRXTSHIFT)
                tp->t_rxtshift++;
            TCPTV_PERSMIN, TCPTV_PERSMAX);
        if (tp->t_rxtshift < TCP_MAXRXTSHIFT)
                tp->t_rxtshift++;