void
sockstats(PNATState pData)
{
char buff[256];
size_t n;
struct socket *so, *so_next;
lprint("\n");
lprint(
"Proto[state] Sock Local Address, Port Remote Address, Port RecvQ SendQ\n");
QSOCKET_FOREACH(so, so_next, tcp)
/* { */
n = RTStrPrintf(buff, sizeof(buff), "tcp[%s]", so->so_tcpcb?tcpstates[so->so_tcpcb->t_state]:"NONE");
while (n < 17)
buff[n++] = ' ';
buff[17] = 0;
lprint("%s %3d %15s %5d ",
buff, so->s, inet_ntoa(so->so_laddr), RT_N2H_U16(so->so_lport));
lprint("%15s %5d %5d %5d\n",
inet_ntoa(so->so_faddr), RT_N2H_U16(so->so_fport),
SBUF_LEN(&so->so_rcv), SBUF_LEN(&so->so_snd));
LOOP_LABEL(tcp, so, so_next);
}
/*
* Tcp output routine: figure out what should be sent and send it.
*/
int
tcp_output(PNATState pData, register struct tcpcb *tp)
{
register struct socket *so = tp->t_socket;
register long len, win;
int off, flags, error;
register struct mbuf *m = NULL;
register struct tcpiphdr *ti;
u_char opt[MAX_TCPOPTLEN];
unsigned optlen, hdrlen;
int idle, sendalot;
int size = 0;
LogFlowFunc(("ENTER: tcp_output: tp = %R[tcpcb793]\n", tp));
/*
* Determine length of data that should be transmitted,
* and flags that will be used.
* If there is some data or critical controls (SYN, RST)
* 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;
win = min(tp->snd_wnd, tp->snd_cwnd);
flags = tcp_outflags[tp->t_state];
Log2((" --- tcp_output flags = 0x%x\n", flags));
/*
* If in persist timeout with window of 0, send 1 byte.
* Otherwise, if window is small but nonzero
* and timer expired, we will send what we can
* and go to transmit state.
*/
if (tp->t_force)
{
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 < SBUF_LEN(&so->so_snd))
flags &= ~TH_FIN;
win = 1;
}
else
{
tp->t_timer[TCPT_PERSIST] = 0;
tp->t_rxtshift = 0;
}
}
len = min(SBUF_LEN(&so->so_snd), win) - off;
if (len < 0)
{
/*
* If FIN has been sent but not acked,
* but we haven't been called to retransmit,
* 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.
*/
len = 0;
if (win == 0)
{
tp->t_timer[TCPT_REXMT] = 0;
tp->snd_nxt = tp->snd_una;
}
}
if (len > tp->t_maxseg)
{
len = tp->t_maxseg;
sendalot = 1;
}
if (SEQ_LT(tp->snd_nxt + len, tp->snd_una + SBUF_LEN(&so->so_snd)))
flags &= ~TH_FIN;
win = sbspace(&so->so_rcv);
/*
* Sender silly window avoidance. If connection is idle
* and can send all data, a maximum segment,
* at least a maximum default-size segment do it,
* or are forced, do it; otherwise don't bother.
* If peer's buffer is tiny, then send
* when window is at least half open.
* If retransmitting (possibly after persist timer forced us
* to send into a small window), then must resend.
*/
if (len)
{
if (len == tp->t_maxseg)
goto send;
if ((1 || idle || tp->t_flags & TF_NODELAY) &&
len + off >= SBUF_LEN(&so->so_snd))
goto send;
if (tp->t_force)
goto send;
if (len >= tp->max_sndwnd / 2 && tp->max_sndwnd > 0)
goto send;
if (SEQ_LT(tp->snd_nxt, tp->snd_max))
goto send;
}
/*
* Compare available window to amount of window
* known to peer (as advertised window less
* 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);
if (SEQ_GT(tp->rcv_adv, tp->rcv_nxt))
adv -= tp->rcv_adv - tp->rcv_nxt;
if (adv >= (long) (2 * tp->t_maxseg))
goto send;
if (2 * adv >= (long) SBUF_SIZE(&so->so_rcv))
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;
/*
* 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;
/*
* TCP window updates are not reliable, rather a polling protocol
* using ``persist'' packets is used to insure receipt of window
* updates. The three ``states'' for the output side are:
* idle not doing retransmits or persists
* persisting to move a small or zero window
* (re)transmitting and thereby not persisting
*
* tp->t_timer[TCPT_PERSIST]
* is set when we are in persist state.
* tp->t_force
* is set when we are called to send a persist packet.
* tp->t_timer[TCPT_REXMT]
* is set when we are retransmitting
* The output side is idle when both timers are zero.
*
* If send window is too small, there is data to transmit, and no
* retransmit or persist is pending, then go to persist state.
* If nothing happens soon, send when timer expires:
* if window is nonzero, transmit what we can,
* otherwise force out a byte.
*/
if ( SBUF_LEN(&so->so_snd)
&& tp->t_timer[TCPT_REXMT] == 0
&& tp->t_timer[TCPT_PERSIST] == 0)
{
tp->t_rxtshift = 0;
tcp_setpersist(tp);
}
/*
* No reason to send a segment, just return.
*/
tcpstat.tcps_didnuttin++;
LogFlowFuncLeave();
return (0);
send:
LogFlowFunc(("send\n"));
/*
* 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_int16_t mss;
opt[0] = TCPOPT_MAXSEG;
opt[1] = 4;
mss = RT_H2N_U16((u_int16_t) tcp_mss(pData, tp, 0));
memcpy((caddr_t)(opt + 2), (caddr_t)&mss, sizeof(mss));
optlen = 4;
#if 0
if ( (tp->t_flags & TF_REQ_SCALE)
&& ( (flags & TH_ACK) == 0
|| (tp->t_flags & TF_RCVD_SCALE)))
{
*((u_int32_t *) (opt + optlen)) = RT_H2N_U32( TCPOPT_NOP << 24
| TCPOPT_WINDOW << 16
| TCPOLEN_WINDOW << 8
| tp->request_r_scale);
optlen += 4;
}
#endif
}
}
/*
* 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 0
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_int32_t *lp = (u_int32_t *)(opt + optlen);
/* Form timestamp option as shown in appendix A of RFC 1323. */
*lp++ = RT_H2N_U32_C(TCPOPT_TSTAMP_HDR);
*lp++ = RT_H2N_U32(tcp_now);
*lp = RT_H2N_U32(tp->ts_recent);
optlen += TCPOLEN_TSTAMP_APPA;
}
#endif
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;
}
/*
* Grab a header mbuf, attaching a copy of data to
* be transmitted, and initialize the header from
* the template for sends on this connection.
*/
if (len)
{
if (tp->t_force && len == 1)
tcpstat.tcps_sndprobe++;
else if (SEQ_LT(tp->snd_nxt, tp->snd_max))
{
tcpstat.tcps_sndrexmitpack++;
tcpstat.tcps_sndrexmitbyte += len;
}
else
{
tcpstat.tcps_sndpack++;
tcpstat.tcps_sndbyte += len;
}
size = MCLBYTES;
if ((len + hdrlen + ETH_HLEN) < MSIZE)
size = MCLBYTES;
else if ((len + hdrlen + ETH_HLEN) < MCLBYTES)
size = MCLBYTES;
else if((len + hdrlen + ETH_HLEN) < MJUM9BYTES)
size = MJUM9BYTES;
else if ((len + hdrlen + ETH_HLEN) < MJUM16BYTES)
size = MJUM16BYTES;
else
AssertMsgFailed(("Unsupported size"));
m = m_getjcl(pData, M_NOWAIT, MT_HEADER, M_PKTHDR, size);
if (m == NULL)
{
/* error = ENOBUFS; */
error = 1;
goto out;
}
m->m_data += if_maxlinkhdr;
m->m_pkthdr.header = mtod(m, void *);
m->m_len = hdrlen;
/*
* This will always succeed, since we make sure our mbufs
* are big enough to hold one MSS packet + header + ... etc.
*/
#if 0
if (len <= MHLEN - hdrlen - max_linkhdr)
{
#endif
sbcopy(&so->so_snd, off, (int) len, mtod(m, caddr_t) + hdrlen);
m->m_len += len;
#if 0
}
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 == SBUF_LEN(&so->so_snd))
flags |= TH_PUSH;
}
else
{
