tcp_input.c revision 046676780b2d3108b4ce6868fd158aa2f28dfa16
/* $Id$ */
/** @file
* NAT - TCP input.
*/
/*
* Copyright (C) 2006-2010 Oracle Corporation
*
* This file is part of VirtualBox Open Source Edition (OSE), as
* available from http://www.virtualbox.org. This file is free software;
* General Public License (GPL) as published by the Free Software
* Foundation, in version 2 as it comes in the "COPYING" file of the
* VirtualBox OSE distribution. VirtualBox OSE is distributed in the
* hope that it will be useful, but WITHOUT ANY WARRANTY of any kind.
*/
/*
* This code is based on:
*
* Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* 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
* 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_input.c 8.5 (Berkeley) 4/10/94
* tcp_input.c,v 1.10 1994/10/13 18:36:32 wollman Exp
*/
/*
* Changes and additions relating to SLiRP
* Copyright (c) 1995 Danny Gasparovski.
*
* Please read the file COPYRIGHT for the
* terms and conditions of the copyright.
*/
#include <slirp.h>
#include "ip_icmp.h"
/* for modulo comparisons of timestamps */
#define TSTMP_LT(a, b) ((int)((a)-(b)) < 0)
#define TSTMP_GEQ(a, b) ((int)((a)-(b)) >= 0)
#ifndef TCP_ACK_HACK
else \
#else /* !TCP_ACK_HACK */
#endif /* TCP_ACK_HACK */
/*
* deps: netinet/tcp_reass.c
* tcp_reass_maxqlen = 48 (deafault)
* tcp_reass_maxseg = nmbclusters/16 (nmbclusters = 1024 + maxusers * 64 from kern/kern_mbuf.c let's say 256)
*/
int
{
struct tseg_qent *q;
int flags;
/*
* XXX: tcp_reass() is rather inefficient with its data structures
* and should be rewritten (see NetBSD for optimizations). While
* doing that it should move to its own file tcp_reass.c.
*/
/*
* Call with th==NULL after become established to
* force pre-ESTABLISHED data up to user socket.
*/
{
goto present;
}
/*
* Limit the number of segments in the reassembly queue to prevent
* holding on to too many segments (and thus running out of mbufs).
* Make sure to let the missing segment through which caused this
* queue. Always keep one global queue entry spare to be able to
* process the missing segment.
*/
{
*tlenp = 0;
return (0);
}
/*
* Allocate a new queue entry. If we can't, or hit the zone limit
* just drop the pkt.
*/
{
*tlenp = 0;
return (0);
}
/*
* Find a segment which begins after this one does.
*/
{
break;
p = q;
}
/*
* If there is a preceding segment, it may provide some of
* our data already. If so, drop the data from the incoming
* segment. If it provides all of our data, drop us.
*/
if (p != NULL)
{
int i;
/* conversion to int (in i) handles seq wraparound */
if (i > 0)
{
if (i >= *tlenp)
{
/*
* Try to present any queued data
* at the left window edge to the user.
* This is needed after the 3-WHS
* completes.
*/
goto present; /* ??? */
}
m_adj(m, i);
*tlenp -= i;
}
}
/*
* While we overlap succeeding segments trim them or,
* if they are completely covered, dequeue them.
*/
while (q)
{
if (i <= 0)
break;
if (i < q->tqe_len)
{
q->tqe_len -= i;
break;
}
LIST_REMOVE(q, tqe_q);
RTMemFree(q);
q = nq;
}
/* Insert the new segment queue entry into place. */
if (p == NULL)
{
}
else
{
}
/*
* Present data to user, advancing rcv_nxt through
* completed sequence space.
*/
{
return (0);
}
{
return (0);
}
do
{
LIST_REMOVE(q, tqe_q);
/* XXX: This place should be checked for the same code in
* original BSD code for Slirp and current BSD used SS_FCANTRCVMORE
*/
else
RTMemFree(q);
q = nq;
}
return flags;
}
/*
* TCP input routine, follows pages 65-76 of the
* protocol specification dated September, 1981 very closely.
*/
void
{
int optlen = 0;
register int tiflags;
/* int dropsocket = 0; */
int iss = 0;
/* int ts_present = 0; */
LogFlow(("tcp_input: m = %8lx, iphlen = %2d, inso = %lx\n",
{
}
/*
* If called with m == 0, then we're continuing the connect
*/
if (m == NULL)
{
/* Re-set a few variables */
/** @todo (vvl) clarify why it might happens */
{
LogRel(("NAT: ti is null. can't do any reseting connection actions\n"));
/* mbuf should be cleared in sofree called from tcp_close */
return;
}
goto cont_conn;
}
/*
* Get IP and TCP header together in first mbuf.
* Note: IP leaves IP header in first mbuf.
*/
{
ip_stripoptions(m, (struct mbuf *)0);
}
/* XXX Check if too short */
/*
* Save a copy of the IP header in case we want restore it
* for sending an ICMP error message in response.
*/
/*
* (vvl) ip_input substracts IP header length from ip->ip_len value.
* here we do the test the same as input method of UDP protocol.
*/
/*
* Checksum extended TCP header and data.
*/
/* keep checksum for ICMP reply
* ti->ti_sum = cksum(m, len);
* if (ti->ti_sum) { */
{
goto drop;
}
/*
* Check that TCP offset makes sense,
* pull out TCP options and adjust length. XXX
*/
{
goto drop;
}
{
/*
* Do quick retrieval of timestamp options ("options
* prediction?"). If timestamp is the only option and it's
* formatted as recommended in RFC 1323 appendix A, we
* quickly get the values now and not bother calling
* tcp_dooptions(), etc.
*/
#if 0
if (( optlen == TCPOLEN_TSTAMP_APPA
|| ( optlen > TCPOLEN_TSTAMP_APPA
{
ts_present = 1;
}
#endif
}
/*
* Convert TCP protocol specific fields to host format.
*/
/*
* Drop TCP, IP headers and TCP options.
*/
/*
* Locate pcb for segment.
*/
so = tcp_last_so;
{
#ifdef VBOX_WITH_SLIRP_MT
#endif
/* @todo fix SOLOOKUP macrodefinition to be usable here */
#ifndef VBOX_WITH_SLIRP_MT
#else
/* { */
{
break; /* so is locked here */
}
}
}
#endif
if (so)
{
tcp_last_so = so;
}
}
else
{
}
/*
* If the state is CLOSED (i.e., TCB does not exist) then
* all data in the incoming segment is discarded.
* If the TCB exists but is in CLOSED state, it is embryonic,
* but should either do a listen or a connect soon.
*
* state == CLOSED means we've done socreate() but haven't
* attached it to a protocol yet...
*
* XXX If a TCB does not exist, and the TH_SYN flag is
* the only flag set, then create a session, mark it
* as if it was LISTENING, and continue...
*/
if (so == 0)
{
{
goto dropwithreset;
}
{
goto dropwithreset;
}
{
goto dropwithreset;
}
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
#else
#endif
/* tcp_last_so = so; */ /* XXX ? */
/* tp = sototcpcb(so); */
}
/*
* If this is a still-connecting socket, this probably
* a retransmit of the SYN. Whether it's a retransmit SYN
* or something else, we nuke it.
*/
{
goto drop;
}
/* XXX Should never fail */
if (tp == 0)
{
goto dropwithreset;
}
{
goto drop;
}
/* Unscale the window into a 32-bit value. */
/* if ((tiflags & TH_SYN) == 0)
* tiwin = ti->ti_win << tp->snd_scale;
* else
*/
/*
* Segment received on connection.
* Reset idle time and keep-alive timer.
*/
if (so_options)
else
/*
* Process options if not in LISTEN state,
* else do it below (after getting remote address).
*/
/* , */
/* &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.
*
* XXX Some of these tests are not needed
* eg: the tiwin == tp->snd_wnd prevents many more
* predictions.. with no *real* advantage..
*/
/* && (!ts_present || TSTMP_GEQ(ts_val, tp->ts_recent)) */
{
/*
* If last ACK falls within this segment's sequence numbers,
* record the timestamp.
*/
#if 0
{
}
#endif
{
{
/*
* this is a pure ack for outstanding data.
*/
#if 0
if (ts_present)
else
#endif
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
#else
/* drop all what sbuf have */
else
#endif
/*
* If all outstanding data are acked, stop
* retransmit timer, otherwise restart timer
* using current (possibly backed-off) value.
* If process is waiting for space,
* are ready to send, let tcp_output
* decide between more output or persist.
*/
/*
* There's room in so_snd, sowwakup will read()
* from the socket if we can
*/
#if 0
#endif
/*
* This is called because sowwakeup might have
* put data into so_snd. Since we don't so sowwakeup,
* we don't need this.. XXX???
*/
return;
}
}
{
/*
* this is a pure, in-sequence data packet
* with nothing on the reassembly queue and
* we have enough buffer space to take it.
*/
/*
* Add data to socket buffer.
*/
/*
* XXX This is called when data arrives. Later, check
* if we can actually write() to the socket
* XXX Need to check? It's be NON_BLOCKING
*/
/* sorwakeup(so); */
/*
* If this is a short packet, then ACK now - with Nagel
* congestion avoidance sender won't send more until
* he gets an ACK.
*
* It is better to not delay acks at all to maximize
* TCP throughput. See RFC 2581.
*/
return;
}
} /* header prediction */
/*
* 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;
if (win < 0)
win = 0;
}
{
/*
* If the state is LISTEN then ignore segment if it contains an RST.
* If the segment contains an ACK then it is bad and send a RST.
* If it does not contain a SYN then it is not interesting; drop it.
* Don't bother responding if the destination was a broadcast.
* Otherwise initialize tp->rcv_nxt, and tp->irs, select an initial
* tp->iss, and send a segment:
* <SEQ=ISS><ACK=RCV_NXT><CTL=SYN,ACK>
* Also initialize tp->snd_nxt to tp->iss+1 and tp->snd_una to tp->iss.
* Fill in remote peer address fields if not previously specified.
* Enter SYN_RECEIVED state, and process any other fields of this
* segment in this state.
*/
case TCPS_LISTEN:
{
{
goto drop;
}
{
goto dropwithreset;
}
{
goto drop;
}
/*
* This has way too many gotos...
* But a bit of spaghetti code never hurt anybody :)
*/
&& errno != EINPROGRESS
&& errno != EWOULDBLOCK)
{
if (errno == ECONNREFUSED)
{
/* ACK the SYN, send RST to refuse the connection */
}
else
{
if (errno == EHOSTUNREACH)
}
}
else
{
/*
* Haven't connected yet, save the current mbuf
* and ti, and return
* XXX Some OS's don't tell us whether the connect()
* succeeded or not. So we must time it out.
*/
}
return;
/* m==NULL
* Check if the connect succeeded
*/
LogFlowFunc(("cont_conn:\n"));
{
goto dropwithreset;
}
LogFlowFunc(("cont_input:\n"));
if (optp)
if (iss)
else
goto trimthenstep6;
} /* case TCPS_LISTEN */
/*
* If the state is SYN_SENT:
* if seg contains an ACK, but not for our SYN, drop the input.
* if seg contains a RST, then drop the connection.
* if seg does not contain SYN, then drop it.
* Otherwise this is an acceptable SYN segment
* initialize tp->rcv_nxt and tp->irs
* if seg contains ack then advance tp->snd_una
* if SYN has been acked change to ESTABLISHED else SYN_RCVD state
* arrange for segment to be acked (eventually)
*/
case TCPS_SYN_SENT:
{
goto dropwithreset;
}
{
goto drop;
}
{
goto drop;
}
{
}
{
/* Do window scaling on this connection? */
#if 0
== (TF_RCVD_SCALE|TF_REQ_SCALE))
{
}
#endif
/*
* if we didn't have to retransmit the SYN,
* use its rtt as our initial srtt & rtt var.
*/
}
else
LogFlowFunc(("trimthenstep6:\n"));
/*
* Advance ti->ti_seq to correspond to first data byte.
* If data, trim to stay within window,
* dropping FIN if necessary.
*/
{
}
goto step6;
} /* switch tp->t_state */
/*
* States other than LISTEN or SYN_SENT.
* First check timestamp, if present.
* Then check that at least some bytes of segment are within
* receive window. If segment begins before rcv_nxt,
* drop leading data (and SYN); if nothing left, just ack.
*
* RFC 1323 PAWS: If we have a timestamp reply on this segment
* and it's less than ts_recent, drop it.
*/
#if 0
if ( ts_present
{
/* Check to see if ts_recent is over 24 days old. */
{
/*
* 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.
*/
}
else
{
goto dropafterack;
}
}
#endif
if (todrop > 0)
{
{
else
todrop--;
}
/*
* Following if statement from Stevens, vol. 2, p. 960.
*/
{
/*
* Any valid FIN must be to the left of the window.
* At this point the FIN must be a duplicate or out
* of sequence; drop it.
*/
/*
* Send an ACK to resynchronize and drop any data.
* But keep on processing for RST or ACK.
*/
}
else
{
}
else
{
}
}
/*
* If new data are received on a connection after the
* user processes are gone, then RST the other end.
*/
{
goto dropwithreset;
}
/*
* If segment ends after window, drop trailing data
* (and PUSH and FIN); if nothing left, just ACK.
*/
if (todrop > 0)
{
{
/*
* 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.
*/
{
goto findso;
}
/*
* 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.
*/
{
}
else
{
goto dropafterack;
}
}
else
}
/*
* If last ACK falls within this segment's sequence numbers,
* record its timestamp.
*/
#if 0
if ( ts_present
{
}
#endif
/*
* 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.
*/
{
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; */
LogFlowFunc(("close:\n"));
goto drop;
case TCPS_CLOSING:
case TCPS_LAST_ACK:
case TCPS_TIME_WAIT:
goto drop;
}
/*
* If a SYN is in the window, then this is an
* error and we send an RST and drop the connection.
*/
{
goto dropwithreset;
}
/*
* If the ACK bit is off we drop the segment and return.
*/
{
goto drop;
}
/*
* Ack processing.
*/
{
/*
* In SYN_RECEIVED state if the ack ACKs our SYN then enter
* ESTABLISHED state and continue processing, otherwise
* send an RST. una<=ack<=max
*/
case TCPS_SYN_RECEIVED:
goto dropwithreset;
/*
* The sent SYN is ack'ed with our sequence number +1
* The first data byte already in the buffer will get
* lost if no correction is made. This is only needed for
* SS_CTL since the buffer is empty otherwise.
* tp->snd_una++; or:
*/
/* Do window scaling? */
#if 0
== (TF_RCVD_SCALE|TF_REQ_SCALE))
{
}
#endif
/* Avoid ack processing; snd_una==ti_ack => dup ack */
goto synrx_to_est;
/* 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 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
* threshold 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 (win < 2)
win = 2;
goto drop;
}
{
goto drop;
}
}
else
break;
}
LogFlowFunc(("%d -> synrx_to_est:\n"));
/*
* If the congestion window was inflated to account
* for the other side's cached packets, retract it.
*/
{
goto dropafterack;
}
/*
* 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 0
if (ts_present)
else
#endif
/*
* 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.
*/
{
needoutput = 1;
}
/*
* 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).
*/
{
}
{
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
#else
#endif
ourfinisacked = 1;
}
else
{
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
#else
#endif
ourfinisacked = 0;
}
/*
* XXX sowwakup is called when data is acked and there's room for
* for more data... it should read() the socket
*/
#if 0
#endif
{
/*
* 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.
*/
{
}
}
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)
{
}
break;
/*
* In LAST_ACK, we may still be waiting for data to drain
* If our FIN is now acknowledged, delete the TCB,
* enter the closed state and return.
*/
case TCPS_LAST_ACK:
if (ourfinisacked)
{
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:
goto dropafterack;
}
} /* switch(tp->t_state) */
LogFlowFunc(("step6:\n"));
/*
* Update window information.
* Don't look at window if no ACK: TAC's send garbage on first SYN.
*/
{
/* keep track of pure window updates */
needoutput = 1;
}
/*
* Process segments with URG.
*/
{
/* BSD's sbufs are auto extent so we shouldn't worry here */
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
/*
* 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.
*/
{
goto dodata;
}
#endif
/*
* 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).
*/
{
}
}
else
/*
* If no out of band data is expected,
* pull receive urgent pointer along
* with the receive window.
*/
LogFlowFunc(("dodata:\n"));
/*
* If this is a small packet, then ACK now - with Nagel
* congestion avoidance sender won't send more until
* he gets an ACK.
*
* See above.
*/
{
}
/*
* 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.
*/
{
{
else
}
else
{
}
/*
* Note the amount of data that peer has sent into
* our window, in order to estimate the sender's
* buffer size.
*/
}
else
{
}
/*
* If FIN is received ACK the FIN and let the user know
* that the connection is closing.
*/
{
{
/*
* If we receive a FIN we can't send more data,
* set it SS_FDRAIN
* Shutdown the socket if there is no rx data in the
* buffer.
* soread() is called on completion of shutdown() and
* will got to TCPS_LAST_ACK, and use tcp_output()
* to send the FIN.
*/
/* sofcantrcvmore(so); */
}
{
/*
* In SYN_RECEIVED and ESTABLISHED STATES
* enter the CLOSE_WAIT state.
*/
case TCPS_SYN_RECEIVED:
case TCPS_ESTABLISHED:
break;
/*
* If still in FIN_WAIT_1 STATE FIN has not been acked so
* enter the CLOSING state.
*/
case TCPS_FIN_WAIT_1:
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:
break;
/*
* In TIME_WAIT state restart the 2 MSL time_wait timer.
*/
case TCPS_TIME_WAIT:
break;
}
}
/*
* Return any desired output.
*/
return;
LogFlowFunc(("dropafterack:\n"));
/*
* Generate an ACK dropping incoming segment if it occupies
* sequence space, where the ACK reflects our state.
*/
{
goto drop;
}
return;
LogFlowFunc(("dropwithreset:\n"));
/* reuses m if m!=NULL, m_free() unnecessary */
else
{
}
return;
drop:
LogFlowFunc(("drop:\n"));
/*
* Drop space held by incoming segment and return.
*/
#ifdef VBOX_WITH_SLIRP_MT
{
}
#endif
return;
}
void
{
{
if (opt == TCPOPT_EOL)
break;
if (opt == TCPOPT_NOP)
optlen = 1;
else
{
if (optlen <= 0)
break;
}
switch (opt)
{
default:
continue;
case TCPOPT_MAXSEG:
if (optlen != TCPOLEN_MAXSEG)
continue;
continue;
break;
#if 0
case TCPOPT_WINDOW:
if (optlen != TCPOLEN_WINDOW)
continue;
continue;
break;
case TCPOPT_TIMESTAMP:
if (optlen != TCPOLEN_TIMESTAMP)
continue;
*ts_present = 1;
/*
* A timestamp received in a SYN makes
* it ok to send timestamp requests and replies.
*/
{
}
break;
#endif
}
}
}
/*
* Pull out of band byte out of a segment so
* it doesn't appear in the user's data queue.
* It is still reflected in the segment length for
* sequencing purposes.
*/
#if 0
void
{
while (cnt >= 0)
{
{
m->m_len--;
return;
}
m = m->m_next; /* XXX WRONG! Fix it! */
if (m == 0)
break;
}
panic("tcp_pulloutofband");
}
#endif
/*
* Collect new round-trip time estimate
* and update averages and current timeout.
*/
void
{
register short delta;
{
/*
* srtt is stored as fixed point with 3 bits after the
* binary point (i.e., scaled by 8). The following magic
* is equivalent to the smoothing algorithm in rfc793 with
* an alpha of .875 (srtt = rtt/8 + srtt*7/8 in fixed
* point). Adjust rtt to origin 0.
*/
/*
* We accumulate a smoothed rtt variance (actually, a
* smoothed mean difference), then set the retransmit
* timer to smoothed rtt + 4 times the smoothed variance.
* rttvar is stored as fixed point with 2 bits after the
* binary point (scaled by 4). The following is
* equivalent to rfc793 smoothing with an alpha of .75
* (rttvar = rttvar*3/4 + |delta| / 4). This replaces
* rfc793's wired-in beta.
*/
if (delta < 0)
}
else
{
/*
* No rtt measurement yet - use the unsmoothed rtt.
* Set the variance to half the rtt (so our first
* retransmit happens at 3*rtt).
*/
}
tp->t_rxtshift = 0;
/*
* the retransmit should happen at rtt + 4 * rttvar.
* Because of the way we do the smoothing, srtt and rttvar
* will each average +1/2 tick of bias. When we compute
* the retransmit timer, we want 1/2 tick of rounding and
* 1 extra tick because of +-1/2 tick uncertainty in the
* firing of the timer. The bias will give us exactly the
* 1.5 tick we need. But, because the bias is
* statistical, we have to test that we don't drop below
* the minimum feasible timer (which is 2 ticks).
*/
/*
* We received an ack for a packet that wasn't retransmitted;
* it is probably safe to discard any error indications we've
* received recently. This isn't quite right, but close enough
* for now (a route might have failed after we sent a segment,
* and the return path might not be symmetrical).
*/
tp->t_softerror = 0;
}
/*
* Determine a reasonable value for maxseg size.
* If the route is known, check route for mtu.
* If none, use an mss that can be handled on the outgoing
* interface without forcing IP to fragment; if bigger than
* an mbuf cluster (MCLBYTES), round down to nearest multiple of MCLBYTES
* to utilize large mbufs. If no route is found, route has no mtu,
* or the destination isn't local, use a default, hopefully conservative
* size (usually 512 or the default IP max size, but no more than the mtu
* of the interface), as we can't discover anything about intervening
* gateways or networks. We also initialize the congestion/slow start
* window to be a single segment if the destination isn't local.
* While looking at the routing entry, we also initialize other path-dependent
* parameters from pre-set or cached values in the routing entry.
*/
int
{
int mss;
if (offer)
#ifndef VBOX_WITH_SLIRP_BSD_SBUF
#else
sbuf_new(&so->so_snd, NULL, tcp_sndspace+((tcp_sndspace%mss)?(mss-(tcp_sndspace%mss)):0), SBUF_AUTOEXTEND);
sbuf_new(&so->so_rcv, NULL, tcp_rcvspace+((tcp_rcvspace%mss)?(mss-(tcp_rcvspace%mss)):0), SBUF_AUTOEXTEND);
#endif
return mss;
}