* terms and conditions of the copyright.
*/
-#include <slirp.h>
+#include "qemu/osdep.h"
+#include "slirp.h"
#include "ip_icmp.h"
-struct socket tcb;
-
#define TCPREXMTTHRESH 3
-struct socket *tcp_last_so = &tcb;
-
-tcp_seq tcp_iss; /* tcp initial send seq # */
#define TCP_PAWS_IDLE (24 * 24 * 60 * 60 * PR_SLOWHZ)
tp->t_flags |= TF_DELACK; \
(tp)->rcv_nxt += (ti)->ti_len; \
flags = (ti)->ti_flags & TH_FIN; \
- STAT(tcpstat.tcps_rcvpack++); \
- STAT(tcpstat.tcps_rcvbyte += (ti)->ti_len); \
if (so->so_emu) { \
if (tcp_emu((so),(m))) sbappend((so), (m)); \
} else \
sbappend((so), (m)); \
-/* sorwakeup(so); */ \
} else {\
(flags) = tcp_reass((tp), (ti), (m)); \
tp->t_flags |= TF_ACKNOW; \
tp->t_flags |= TF_DELACK; \
(tp)->rcv_nxt += (ti)->ti_len; \
flags = (ti)->ti_flags & TH_FIN; \
- STAT(tcpstat.tcps_rcvpack++); \
- STAT(tcpstat.tcps_rcvbyte += (ti)->ti_len); \
if (so->so_emu) { \
if (tcp_emu((so),(m))) sbappend(so, (m)); \
} else \
sbappend((so), (m)); \
-/* sorwakeup(so); */ \
} else { \
(flags) = tcp_reass((tp), (ti), (m)); \
tp->t_flags |= TF_ACKNOW; \
i = q->ti_seq + q->ti_len - ti->ti_seq;
if (i > 0) {
if (i >= ti->ti_len) {
- STAT(tcpstat.tcps_rcvduppack++);
- STAT(tcpstat.tcps_rcvdupbyte += ti->ti_len);
- m_freem(m);
+ m_free(m);
/*
* Try to present any queued data
* at the left window edge to the user.
}
q = tcpiphdr_next(q);
}
- STAT(tcpstat.tcps_rcvoopack++);
- STAT(tcpstat.tcps_rcvoobyte += ti->ti_len);
ti->ti_mbuf = m;
/*
q = tcpiphdr_next(q);
m = tcpiphdr_prev(q)->ti_mbuf;
remque(tcpiphdr2qlink(tcpiphdr_prev(q)));
- m_freem(m);
+ m_free(m);
}
/*
remque(tcpiphdr2qlink(ti));
m = ti->ti_mbuf;
ti = tcpiphdr_next(ti);
-/* if (so->so_state & SS_FCANTRCVMORE) */
if (so->so_state & SS_FCANTSENDMORE)
- m_freem(m);
+ m_free(m);
else {
if (so->so_emu) {
if (tcp_emu(so,m)) sbappend(so, m);
sbappend(so, m);
}
} while (ti != (struct tcpiphdr *)tp && ti->ti_seq == tp->rcv_nxt);
-/* sorwakeup(so); */
return (flags);
}
* protocol specification dated September, 1981 very closely.
*/
void
-tcp_input(struct mbuf *m, int iphlen, struct socket *inso)
+tcp_input(struct mbuf *m, int iphlen, struct socket *inso, unsigned short af)
{
- struct ip save_ip, *ip;
+ struct ip save_ip, *ip;
+ struct ip6 save_ip6, *ip6;
register struct tcpiphdr *ti;
caddr_t optp = NULL;
int optlen = 0;
register int tiflags;
struct socket *so = NULL;
int todrop, acked, ourfinisacked, needoutput = 0;
-/* int dropsocket = 0; */
int iss = 0;
u_long tiwin;
int ret;
-/* int ts_present = 0; */
+ struct sockaddr_storage lhost, fhost;
+ struct sockaddr_in *lhost4, *fhost4;
+ struct sockaddr_in6 *lhost6, *fhost6;
struct ex_list *ex_ptr;
+ Slirp *slirp;
DEBUG_CALL("tcp_input");
- DEBUG_ARGS((dfd," m = %8lx iphlen = %2d inso = %lx\n",
- (long )m, iphlen, (long )inso ));
+ DEBUG_ARGS((dfd, " m = %p iphlen = %2d inso = %p\n",
+ m, iphlen, inso));
/*
* If called with m == 0, then we're continuing the connect
*/
if (m == NULL) {
so = inso;
+ slirp = so->slirp;
/* Re-set a few variables */
tp = sototcpcb(so);
goto cont_conn;
}
+ slirp = m->slirp;
+ ip = mtod(m, struct ip *);
+ ip6 = mtod(m, struct ip6 *);
- STAT(tcpstat.tcps_rcvtotal++);
- /*
- * 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);
- iphlen=sizeof(struct ip );
- }
- /* XXX Check if too short */
+ switch (af) {
+ case AF_INET:
+ if (iphlen > sizeof(struct ip)) {
+ ip_stripoptions(m, (struct mbuf *)0);
+ iphlen = sizeof(struct ip);
+ }
+ /* 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.
- */
- ip=mtod(m, struct ip *);
- save_ip = *ip;
- save_ip.ip_len+= iphlen;
+ /*
+ * Save a copy of the IP header in case we want restore it
+ * for sending an ICMP error message in response.
+ */
+ save_ip = *ip;
+ save_ip.ip_len += iphlen;
- /*
- * Checksum extended TCP header and data.
- */
- tlen = ((struct ip *)ti)->ip_len;
- tcpiphdr2qlink(ti)->next = tcpiphdr2qlink(ti)->prev = NULL;
- memset(&ti->ti_i.ih_mbuf, 0 , sizeof(struct mbuf_ptr));
- ti->ti_x1 = 0;
- ti->ti_len = htons((u_int16_t)tlen);
- len = sizeof(struct ip ) + tlen;
- /* keep checksum for ICMP reply
- * ti->ti_sum = cksum(m, len);
- * if (ti->ti_sum) { */
- if(cksum(m, len)) {
- STAT(tcpstat.tcps_rcvbadsum++);
- goto drop;
+ /*
+ * Get IP and TCP header together in first mbuf.
+ * Note: IP leaves IP header in first mbuf.
+ */
+ m->m_data -= sizeof(struct tcpiphdr) - sizeof(struct ip)
+ - sizeof(struct tcphdr);
+ m->m_len += sizeof(struct tcpiphdr) - sizeof(struct ip)
+ - sizeof(struct tcphdr);
+ ti = mtod(m, struct tcpiphdr *);
+
+ /*
+ * Checksum extended TCP header and data.
+ */
+ tlen = ip->ip_len;
+ tcpiphdr2qlink(ti)->next = tcpiphdr2qlink(ti)->prev = NULL;
+ memset(&ti->ih_mbuf, 0 , sizeof(struct mbuf_ptr));
+ memset(&ti->ti, 0, sizeof(ti->ti));
+ ti->ti_x0 = 0;
+ ti->ti_src = save_ip.ip_src;
+ ti->ti_dst = save_ip.ip_dst;
+ ti->ti_pr = save_ip.ip_p;
+ ti->ti_len = htons((uint16_t)tlen);
+ break;
+
+ case AF_INET6:
+ /*
+ * Save a copy of the IP header in case we want restore it
+ * for sending an ICMP error message in response.
+ */
+ save_ip6 = *ip6;
+ /*
+ * Get IP and TCP header together in first mbuf.
+ * Note: IP leaves IP header in first mbuf.
+ */
+ m->m_data -= sizeof(struct tcpiphdr) - (sizeof(struct ip6)
+ + sizeof(struct tcphdr));
+ m->m_len += sizeof(struct tcpiphdr) - (sizeof(struct ip6)
+ + sizeof(struct tcphdr));
+ ti = mtod(m, struct tcpiphdr *);
+
+ tlen = ip6->ip_pl;
+ tcpiphdr2qlink(ti)->next = tcpiphdr2qlink(ti)->prev = NULL;
+ memset(&ti->ih_mbuf, 0 , sizeof(struct mbuf_ptr));
+ memset(&ti->ti, 0, sizeof(ti->ti));
+ ti->ti_x0 = 0;
+ ti->ti_src6 = save_ip6.ip_src;
+ ti->ti_dst6 = save_ip6.ip_dst;
+ ti->ti_nh6 = save_ip6.ip_nh;
+ ti->ti_len = htons((uint16_t)tlen);
+ break;
+
+ default:
+ g_assert_not_reached();
+ }
+
+ len = ((sizeof(struct tcpiphdr) - sizeof(struct tcphdr)) + tlen);
+ if (cksum(m, len)) {
+ goto drop;
}
/*
*/
off = ti->ti_off << 2;
if (off < sizeof (struct tcphdr) || off > tlen) {
- STAT(tcpstat.tcps_rcvbadoff++);
goto drop;
}
tlen -= off;
if (off > sizeof (struct tcphdr)) {
optlen = off - sizeof (struct tcphdr);
optp = mtod(m, caddr_t) + sizeof (struct tcpiphdr);
-
- /*
- * 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 ((optlen == TCPOLEN_TSTAMP_APPA ||
- * (optlen > TCPOLEN_TSTAMP_APPA &&
- * optp[TCPOLEN_TSTAMP_APPA] == TCPOPT_EOL)) &&
- * *(u_int32_t *)optp == htonl(TCPOPT_TSTAMP_HDR) &&
- * (ti->ti_flags & TH_SYN) == 0) {
- * ts_present = 1;
- * ts_val = ntohl(*(u_int32_t *)(optp + 4));
- * ts_ecr = ntohl(*(u_int32_t *)(optp + 8));
- * optp = NULL; / * we've parsed the options * /
- * }
- */
}
tiflags = ti->ti_flags;
m->m_data += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
m->m_len -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
- if (slirp_restrict) {
- for (ex_ptr = exec_list; ex_ptr; ex_ptr = ex_ptr->ex_next) {
- if (ex_ptr->ex_fport == ti->ti_dport &&
- ti->ti_dst.s_addr == ex_ptr->ex_addr.s_addr) {
- break;
- }
- }
- if (!ex_ptr)
- goto drop;
- }
/*
* Locate pcb for segment.
*/
findso:
- so = tcp_last_so;
- if (so->so_fport != ti->ti_dport ||
- so->so_lport != ti->ti_sport ||
- so->so_laddr.s_addr != ti->ti_src.s_addr ||
- so->so_faddr.s_addr != ti->ti_dst.s_addr) {
- so = solookup(&tcb, ti->ti_src, ti->ti_sport,
- ti->ti_dst, ti->ti_dport);
- if (so)
- tcp_last_so = so;
- STAT(tcpstat.tcps_socachemiss++);
+ lhost.ss_family = af;
+ fhost.ss_family = af;
+ switch (af) {
+ case AF_INET:
+ lhost4 = (struct sockaddr_in *) &lhost;
+ lhost4->sin_addr = ti->ti_src;
+ lhost4->sin_port = ti->ti_sport;
+ fhost4 = (struct sockaddr_in *) &fhost;
+ fhost4->sin_addr = ti->ti_dst;
+ fhost4->sin_port = ti->ti_dport;
+ break;
+ case AF_INET6:
+ lhost6 = (struct sockaddr_in6 *) &lhost;
+ lhost6->sin6_addr = ti->ti_src6;
+ lhost6->sin6_port = ti->ti_sport;
+ fhost6 = (struct sockaddr_in6 *) &fhost;
+ fhost6->sin6_addr = ti->ti_dst6;
+ fhost6->sin6_port = ti->ti_dport;
+ break;
+ default:
+ g_assert_not_reached();
}
+ so = solookup(&slirp->tcp_last_so, &slirp->tcb, &lhost, &fhost);
+
/*
* If the state is CLOSED (i.e., TCB does not exist) then
* all data in the incoming segment is discarded.
* as if it was LISTENING, and continue...
*/
if (so == NULL) {
+ if (slirp->restricted) {
+ /* Any hostfwds will have an existing socket, so we only get here
+ * for non-hostfwd connections. These should be dropped, unless it
+ * happens to be a guestfwd.
+ */
+ for (ex_ptr = slirp->exec_list; ex_ptr; ex_ptr = ex_ptr->ex_next) {
+ if (ex_ptr->ex_fport == ti->ti_dport &&
+ ti->ti_dst.s_addr == ex_ptr->ex_addr.s_addr) {
+ break;
+ }
+ }
+ if (!ex_ptr) {
+ goto dropwithreset;
+ }
+ }
+
if ((tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) != TH_SYN)
goto dropwithreset;
- if ((so = socreate()) == NULL)
+ if ((so = socreate(slirp)) == NULL)
goto dropwithreset;
if (tcp_attach(so) < 0) {
free(so); /* Not sofree (if it failed, it's not insqued) */
sbreserve(&so->so_snd, TCP_SNDSPACE);
sbreserve(&so->so_rcv, TCP_RCVSPACE);
- /* tcp_last_so = so; */ /* XXX ? */
- /* tp = sototcpcb(so); */
-
- so->so_laddr = ti->ti_src;
- so->so_lport = ti->ti_sport;
- so->so_faddr = ti->ti_dst;
- so->so_fport = ti->ti_dport;
-
- if ((so->so_iptos = tcp_tos(so)) == 0)
- so->so_iptos = ((struct ip *)ti)->ip_tos;
+ so->lhost.ss = lhost;
+ so->fhost.ss = fhost;
+
+ so->so_iptos = tcp_tos(so);
+ if (so->so_iptos == 0) {
+ switch (af) {
+ case AF_INET:
+ so->so_iptos = ((struct ip *)ti)->ip_tos;
+ break;
+ case AF_INET6:
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ }
tp = sototcpcb(so);
tp->t_state = TCPS_LISTEN;
if (tp->t_state == TCPS_CLOSED)
goto drop;
- /* Unscale the window into a 32-bit value. */
-/* if ((tiflags & TH_SYN) == 0)
- * tiwin = ti->ti_win << tp->snd_scale;
- * else
- */
- tiwin = ti->ti_win;
+ tiwin = ti->ti_win;
/*
* Segment received on connection.
*/
if (optp && tp->t_state != TCPS_LISTEN)
tcp_dooptions(tp, (u_char *)optp, optlen, ti);
-/* , */
-/* &ts_present, &ts_val, &ts_ecr); */
/*
* Header prediction: check for the two common cases
*/
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) &&
/*
* this is a pure ack for outstanding data.
*/
- STAT(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))
+ 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;
- STAT(tcpstat.tcps_rcvackpack++);
- STAT(tcpstat.tcps_rcvackbyte += acked);
sbdrop(&so->so_snd, acked);
tp->snd_una = ti->ti_ack;
- m_freem(m);
+ m_free(m);
/*
* If all outstanding data are acked, stop
else if (tp->t_timer[TCPT_PERSIST] == 0)
tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
- /*
- * There's room in so_snd, sowwakup will read()
- * from the socket if we can
- */
-/* if (so->so_snd.sb_flags & SB_NOTIFY)
- * sowwakeup(so);
- */
/*
* This is called because sowwakeup might have
* put data into so_snd. Since we don't so sowwakeup,
* with nothing on the reassembly queue and
* we have enough buffer space to take it.
*/
- STAT(tcpstat.tcps_preddat++);
tp->rcv_nxt += ti->ti_len;
- STAT(tcpstat.tcps_rcvpack++);
- STAT(tcpstat.tcps_rcvbyte += ti->ti_len);
/*
* Add data to socket buffer.
*/
} else
sbappend(so, m);
- /*
- * 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
* If this is destined for the control address, then flag to
* tcp_ctl once connected, otherwise connect
*/
- if ((so->so_faddr.s_addr & vnetwork_mask.s_addr) ==
- vnetwork_addr.s_addr) {
- if (so->so_faddr.s_addr != vhost_addr.s_addr &&
- so->so_faddr.s_addr != vnameserver_addr.s_addr) {
-#if 0
- if(lastbyte==CTL_CMD || lastbyte==CTL_EXEC) {
- /* Command or exec adress */
- so->so_state |= SS_CTL;
- } else
-#endif
- {
+ if (af == AF_INET &&
+ (so->so_faddr.s_addr & slirp->vnetwork_mask.s_addr) ==
+ slirp->vnetwork_addr.s_addr) {
+ if (so->so_faddr.s_addr != slirp->vhost_addr.s_addr &&
+ so->so_faddr.s_addr != slirp->vnameserver_addr.s_addr) {
/* May be an add exec */
- for(ex_ptr = exec_list; ex_ptr; ex_ptr = ex_ptr->ex_next) {
+ for (ex_ptr = slirp->exec_list; ex_ptr;
+ ex_ptr = ex_ptr->ex_next) {
if(ex_ptr->ex_fport == so->so_fport &&
so->so_faddr.s_addr == ex_ptr->ex_addr.s_addr) {
so->so_state |= SS_CTL;
break;
}
}
- }
- if(so->so_state & SS_CTL) goto cont_input;
+ if (so->so_state & SS_CTL) {
+ goto cont_input;
+ }
}
/* CTL_ALIAS: Do nothing, tcp_fconnect will be called on it */
}
goto cont_input;
}
- if((tcp_fconnect(so) == -1) && (errno != EINPROGRESS) && (errno != EWOULDBLOCK)) {
- u_char code=ICMP_UNREACH_NET;
- DEBUG_MISC((dfd," tcp fconnect errno = %d-%s\n",
+ if ((tcp_fconnect(so, so->so_ffamily) == -1) &&
+ (errno != EAGAIN) &&
+ (errno != EINPROGRESS) && (errno != EWOULDBLOCK)
+ ) {
+ uint8_t code;
+ DEBUG_MISC((dfd, " tcp fconnect errno = %d-%s\n",
errno,strerror(errno)));
if(errno == ECONNREFUSED) {
/* ACK the SYN, send RST to refuse the connection */
- tcp_respond(tp, ti, m, ti->ti_seq+1, (tcp_seq)0,
- TH_RST|TH_ACK);
+ tcp_respond(tp, ti, m, ti->ti_seq + 1, (tcp_seq) 0,
+ TH_RST | TH_ACK, af);
} else {
- if(errno == EHOSTUNREACH) code=ICMP_UNREACH_HOST;
+ switch (af) {
+ case AF_INET:
+ code = ICMP_UNREACH_NET;
+ if (errno == EHOSTUNREACH) {
+ code = ICMP_UNREACH_HOST;
+ }
+ break;
+ case AF_INET6:
+ code = ICMP6_UNREACH_NO_ROUTE;
+ if (errno == EHOSTUNREACH) {
+ code = ICMP6_UNREACH_ADDRESS;
+ }
+ break;
+ default:
+ g_assert_not_reached();
+ }
HTONL(ti->ti_seq); /* restore tcp header */
HTONL(ti->ti_ack);
HTONS(ti->ti_win);
HTONS(ti->ti_urp);
m->m_data -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
m->m_len += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);
- *ip=save_ip;
- icmp_error(m, ICMP_UNREACH,code, 0,strerror(errno));
+ switch (af) {
+ case AF_INET:
+ m->m_data += sizeof(struct tcpiphdr) - sizeof(struct ip)
+ - sizeof(struct tcphdr);
+ m->m_len -= sizeof(struct tcpiphdr) - sizeof(struct ip)
+ - sizeof(struct tcphdr);
+ *ip = save_ip;
+ icmp_send_error(m, ICMP_UNREACH, code, 0, strerror(errno));
+ break;
+ case AF_INET6:
+ m->m_data += sizeof(struct tcpiphdr) - (sizeof(struct ip6)
+ + sizeof(struct tcphdr));
+ m->m_len -= sizeof(struct tcpiphdr) - (sizeof(struct ip6)
+ + sizeof(struct tcphdr));
+ *ip6 = save_ip6;
+ icmp6_send_error(m, ICMP6_UNREACH, code);
+ break;
+ default:
+ g_assert_not_reached();
+ }
}
- tp = tcp_close(tp);
+ tcp_close(tp);
m_free(m);
} else {
/*
so->so_ti = ti;
tp->t_timer[TCPT_KEEP] = TCPTV_KEEP_INIT;
tp->t_state = TCPS_SYN_RECEIVED;
+ /*
+ * Initialize receive sequence numbers now so that we can send a
+ * valid RST if the remote end rejects our connection.
+ */
+ tp->irs = ti->ti_seq;
+ tcp_rcvseqinit(tp);
+ tcp_template(tp);
}
return;
if (optp)
tcp_dooptions(tp, (u_char *)optp, optlen, ti);
- /* , */
- /* &ts_present, &ts_val, &ts_ecr); */
if (iss)
tp->iss = iss;
else
- tp->iss = tcp_iss;
- tcp_iss += TCP_ISSINCR/2;
+ tp->iss = slirp->tcp_iss;
+ slirp->tcp_iss += TCP_ISSINCR/2;
tp->irs = ti->ti_seq;
tcp_sendseqinit(tp);
tcp_rcvseqinit(tp);
tp->t_flags |= TF_ACKNOW;
tp->t_state = TCPS_SYN_RECEIVED;
tp->t_timer[TCPT_KEEP] = TCPTV_KEEP_INIT;
- STAT(tcpstat.tcps_accepts++);
goto trimthenstep6;
} /* case TCPS_LISTEN */
goto dropwithreset;
if (tiflags & TH_RST) {
- if (tiflags & TH_ACK)
- tp = tcp_drop(tp,0); /* XXX Check t_softerror! */
+ if (tiflags & TH_ACK) {
+ tcp_drop(tp, 0); /* XXX Check t_softerror! */
+ }
goto drop;
}
tcp_rcvseqinit(tp);
tp->t_flags |= TF_ACKNOW;
if (tiflags & TH_ACK && SEQ_GT(tp->snd_una, tp->iss)) {
- STAT(tcpstat.tcps_connects++);
soisfconnected(so);
tp->t_state = TCPS_ESTABLISHED;
- /* Do window scaling on this connection? */
-/* 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);
/*
m_adj(m, -todrop);
ti->ti_len = tp->rcv_wnd;
tiflags &= ~TH_FIN;
- STAT(tcpstat.tcps_rcvpackafterwin++);
- STAT(tcpstat.tcps_rcvbyteafterwin += todrop);
}
tp->snd_wl1 = ti->ti_seq - 1;
tp->rcv_up = ti->ti_seq;
} /* 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
+ * 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 (ts_present && (tiflags & TH_RST) == 0 && tp->ts_recent &&
- * TSTMP_LT(ts_val, tp->ts_recent)) {
- *
- */ /* 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;
- * }
- * }
- */
-
todrop = tp->rcv_nxt - ti->ti_seq;
if (todrop > 0) {
if (tiflags & TH_SYN) {
*/
tp->t_flags |= TF_ACKNOW;
todrop = ti->ti_len;
- STAT(tcpstat.tcps_rcvduppack++);
- STAT(tcpstat.tcps_rcvdupbyte += todrop);
- } else {
- STAT(tcpstat.tcps_rcvpartduppack++);
- STAT(tcpstat.tcps_rcvpartdupbyte += todrop);
}
m_adj(m, todrop);
ti->ti_seq += todrop;
if ((so->so_state & SS_NOFDREF) &&
tp->t_state > TCPS_CLOSE_WAIT && ti->ti_len) {
tp = tcp_close(tp);
- STAT(tcpstat.tcps_rcvafterclose++);
goto dropwithreset;
}
*/
todrop = (ti->ti_seq+ti->ti_len) - (tp->rcv_nxt+tp->rcv_wnd);
if (todrop > 0) {
- STAT(tcpstat.tcps_rcvpackafterwin++);
if (todrop >= ti->ti_len) {
- STAT(tcpstat.tcps_rcvbyteafterwin += ti->ti_len);
/*
* If a new connection request is received
* while in TIME_WAIT, drop the old connection
*/
if (tp->rcv_wnd == 0 && ti->ti_seq == tp->rcv_nxt) {
tp->t_flags |= TF_ACKNOW;
- STAT(tcpstat.tcps_rcvwinprobe++);
- } else
+ } else {
goto dropafterack;
- } else
- STAT(tcpstat.tcps_rcvbyteafterwin += todrop);
+ }
+ }
m_adj(m, -todrop);
ti->ti_len -= todrop;
tiflags &= ~(TH_PUSH|TH_FIN);
}
- /*
- * 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;
- * }
- */
-
/*
* If the RST bit is set examine the state:
* SYN_RECEIVED STATE:
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;
- STAT(tcpstat.tcps_drops++);
- tp = tcp_close(tp);
+ tcp_close(tp);
goto drop;
case TCPS_CLOSING:
case TCPS_LAST_ACK:
case TCPS_TIME_WAIT:
- tp = tcp_close(tp);
+ tcp_close(tp);
goto drop;
}
if (SEQ_GT(tp->snd_una, ti->ti_ack) ||
SEQ_GT(ti->ti_ack, tp->snd_max))
goto dropwithreset;
- STAT(tcpstat.tcps_connects++);
tp->t_state = TCPS_ESTABLISHED;
/*
* The sent SYN is ack'ed with our sequence number +1
soisfconnected(so);
so->so_state &= ~SS_CTL; /* success XXX */
} else if (ret == 2) {
- so->so_state = SS_NOFDREF; /* CTL_CMD */
+ so->so_state &= SS_PERSISTENT_MASK;
+ so->so_state |= SS_NOFDREF; /* CTL_CMD */
} else {
needoutput = 1;
tp->t_state = TCPS_FIN_WAIT_1;
soisfconnected(so);
}
- /* 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;
/* Avoid ack processing; snd_una==ti_ack => dup ack */
if (SEQ_LEQ(ti->ti_ack, tp->snd_una)) {
if (ti->ti_len == 0 && tiwin == tp->snd_wnd) {
- STAT(tcpstat.tcps_rcvdupack++);
- DEBUG_MISC((dfd," dup ack m = %lx so = %lx \n",
- (long )m, (long )so));
+ DEBUG_MISC((dfd, " dup ack m = %p so = %p\n",
+ m, so));
/*
* If we have outstanding data (other than
* a window probe), this is a completely
tp->snd_cwnd = tp->snd_ssthresh;
tp->t_dupacks = 0;
if (SEQ_GT(ti->ti_ack, tp->snd_max)) {
- STAT(tcpstat.tcps_rcvacktoomuch++);
goto dropafterack;
}
acked = ti->ti_ack - tp->snd_una;
- STAT(tcpstat.tcps_rcvackpack++);
- STAT(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
+ * If 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))
+ if (tp->t_rtt && SEQ_GT(ti->ti_ack, tp->t_rtseq))
tcp_xmit_timer(tp,tp->t_rtt);
/*
tp->snd_wnd -= acked;
ourfinisacked = 0;
}
- /*
- * XXX sowwakup is called when data is acked and there's room for
- * for more data... it should read() the socket
- */
-/* if (so->so_snd.sb_flags & SB_NOTIFY)
- * sowwakeup(so);
- */
tp->snd_una = ti->ti_ack;
if (SEQ_LT(tp->snd_nxt, tp->snd_una))
tp->snd_nxt = tp->snd_una;
* we'll hang forever.
*/
if (so->so_state & SS_FCANTRCVMORE) {
- soisfdisconnected(so);
tp->t_timer[TCPT_2MSL] = TCP_MAXIDLE;
}
tp->t_state = TCPS_FIN_WAIT_2;
tp->t_state = TCPS_TIME_WAIT;
tcp_canceltimers(tp);
tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
- soisfdisconnected(so);
}
break;
*/
case TCPS_LAST_ACK:
if (ourfinisacked) {
- tp = tcp_close(tp);
+ tcp_close(tp);
goto drop;
}
break;
(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)
- STAT(tcpstat.tcps_rcvwinupd++);
tp->snd_wnd = tiwin;
tp->snd_wl1 = ti->ti_seq;
tp->snd_wl2 = ti->ti_ack;
tp->rcv_up = tp->rcv_nxt;
dodata:
+ /*
+ * If this is a small packet, then ACK now - with Nagel
+ * congestion avoidance sender won't send more until
+ * he gets an ACK.
+ */
+ if (ti->ti_len && (unsigned)ti->ti_len <= 5 &&
+ ((struct tcpiphdr_2 *)ti)->first_char == (char)27) {
+ tp->t_flags |= TF_ACKNOW;
+ }
+
/*
* Process the segment text, merging it into the TCP sequencing queue,
* and arranging for acknowledgment of receipt if necessary.
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_datalen - (tp->rcv_adv - tp->rcv_nxt);
} else {
m_free(m);
tiflags &= ~TH_FIN;
* will got to TCPS_LAST_ACK, and use tcp_output()
* to send the FIN.
*/
-/* sofcantrcvmore(so); */
sofwdrain(so);
tp->t_flags |= TF_ACKNOW;
tp->t_state = TCPS_TIME_WAIT;
tcp_canceltimers(tp);
tp->t_timer[TCPT_2MSL] = 2 * TCPTV_MSL;
- soisfdisconnected(so);
break;
/*
}
}
- /*
- * 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.
- */
-/* if (ti->ti_len && (unsigned)ti->ti_len < tp->t_maxseg) {
- */
-/* if ((ti->ti_len && (unsigned)ti->ti_len < tp->t_maxseg &&
- * (so->so_iptos & IPTOS_LOWDELAY) == 0) ||
- * ((so->so_iptos & IPTOS_LOWDELAY) &&
- * ((struct tcpiphdr_2 *)ti)->first_char == (char)27)) {
- */
- if (ti->ti_len && (unsigned)ti->ti_len <= 5 &&
- ((struct tcpiphdr_2 *)ti)->first_char == (char)27) {
- tp->t_flags |= TF_ACKNOW;
- }
-
/*
* Return any desired output.
*/
*/
if (tiflags & TH_RST)
goto drop;
- m_freem(m);
+ m_free(m);
tp->t_flags |= TF_ACKNOW;
(void) tcp_output(tp);
return;
dropwithreset:
/* reuses m if m!=NULL, m_free() unnecessary */
if (tiflags & TH_ACK)
- tcp_respond(tp, ti, m, (tcp_seq)0, ti->ti_ack, TH_RST);
+ tcp_respond(tp, ti, m, (tcp_seq)0, ti->ti_ack, TH_RST, af);
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);
+ tcp_respond(tp, ti, m, ti->ti_seq + ti->ti_len, (tcp_seq) 0,
+ TH_RST | TH_ACK, af);
}
return;
* Drop space held by incoming segment and return.
*/
m_free(m);
-
- return;
}
- /* , ts_present, ts_val, ts_ecr) */
-/* int *ts_present;
- * u_int32_t *ts_val, *ts_ecr;
- */
static void
tcp_dooptions(struct tcpcb *tp, u_char *cp, int cnt, struct tcpiphdr *ti)
{
- u_int16_t mss;
+ uint16_t mss;
int opt, optlen;
DEBUG_CALL("tcp_dooptions");
- DEBUG_ARGS((dfd," tp = %lx cnt=%i \n", (long )tp, cnt));
+ DEBUG_ARGS((dfd, " tp = %p cnt=%i\n", tp, cnt));
for (; cnt > 0; cnt -= optlen, cp += optlen) {
opt = cp[0];
NTOHS(mss);
(void) tcp_mss(tp, mss); /* sets t_maxseg */
break;
-
-/* case TCPOPT_WINDOW:
- * if (optlen != TCPOLEN_WINDOW)
- * continue;
- * if (!(ti->ti_flags & TH_SYN))
- * continue;
- * tp->t_flags |= TF_RCVD_SCALE;
- * tp->requested_s_scale = min(cp[2], TCP_MAX_WINSHIFT);
- * break;
- */
-/* case TCPOPT_TIMESTAMP:
- * if (optlen != TCPOLEN_TIMESTAMP)
- * continue;
- * *ts_present = 1;
- * memcpy((char *) ts_val, (char *)cp + 2, sizeof(*ts_val));
- * NTOHL(*ts_val);
- * memcpy((char *) ts_ecr, (char *)cp + 6, sizeof(*ts_ecr));
- * NTOHL(*ts_ecr);
- *
- */ /*
- * * A timestamp received in a SYN makes
- * * it ok to send timestamp requests and replies.
- * */
-/* if (ti->ti_flags & TH_SYN) {
- * tp->t_flags |= TF_RCVD_TSTMP;
- * tp->ts_recent = *ts_val;
- * tp->ts_recent_age = tcp_now;
- * }
- */ break;
}
}
}
register short delta;
DEBUG_CALL("tcp_xmit_timer");
- DEBUG_ARG("tp = %lx", (long)tp);
+ DEBUG_ARG("tp = %p", tp);
DEBUG_ARG("rtt = %d", rtt);
- STAT(tcpstat.tcps_rttupdated++);
if (tp->t_srtt != 0) {
/*
* srtt is stored as fixed point with 3 bits after the
int mss;
DEBUG_CALL("tcp_mss");
- DEBUG_ARG("tp = %lx", (long)tp);
+ DEBUG_ARG("tp = %p", tp);
DEBUG_ARG("offer = %d", offer);
- mss = min(IF_MTU, IF_MRU) - sizeof(struct tcpiphdr);
+ switch (so->so_ffamily) {
+ case AF_INET:
+ mss = min(IF_MTU, IF_MRU) - sizeof(struct tcphdr)
+ + sizeof(struct ip);
+ break;
+ case AF_INET6:
+ mss = min(IF_MTU, IF_MRU) - sizeof(struct tcphdr)
+ + sizeof(struct ip6);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
if (offer)
mss = min(mss, offer);
mss = max(mss, 32);
projects / qemu.git / blobdiff