Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. =================================================================== RCS file: /ftp/cvs/cvsroot/src/sys/netinet/ip_input.c,v rcsdiff: /ftp/cvs/cvsroot/src/sys/netinet/ip_input.c,v: warning: Unknown phrases like `commitid ...;' are present. retrieving revision 1.74.2.1 retrieving revision 1.92.2.1 diff -u -p -r1.74.2.1 -r1.92.2.1 --- src/sys/netinet/ip_input.c 1998/12/11 04:53:08 1.74.2.1 +++ src/sys/netinet/ip_input.c 1999/12/27 18:36:16 1.92.2.1 @@ -1,9 +1,9 @@ -/* $NetBSD: ip_input.c,v 1.74.2.1 1998/12/11 04:53:08 kenh Exp $ */ +/* $NetBSD: ip_input.c,v 1.92.2.1 1999/12/27 18:36:16 wrstuden Exp $ */ /* - * Copyright (c) 1982, 1986, 1988, 1993 - * The Regents of the University of California. All rights reserved. - * + * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project. + * All rights reserved. + * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: @@ -12,18 +12,14 @@ * 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 + * 3. Neither the name of the project 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 + * + * THIS SOFTWARE IS PROVIDED BY THE PROJECT 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 + * ARE DISCLAIMED. IN NO EVENT SHALL THE PROJECT 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) @@ -31,8 +27,6 @@ * 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. - * - * @(#)ip_input.c 8.2 (Berkeley) 1/4/94 */ /*- @@ -42,9 +36,9 @@ * This code is derived from software contributed to The NetBSD Foundation * by Public Access Networks Corporation ("Panix"). It was developed under * contract to Panix by Eric Haszlakiewicz and Thor Lancelot Simon. - * + * * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions + * 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. @@ -53,18 +47,18 @@ * 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 NetBSD - * Foundation, Inc. and its contributors. + * This product includes software developed by the NetBSD + * Foundation, Inc. and its contributors. * 4. Neither the name of The NetBSD Foundation 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 NETBSD FOUNDATION, INC. AND CONTRIBUTORS + * + * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. 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 FOUNDATION OR CONTRIBUTORS + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * 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) @@ -72,8 +66,44 @@ * POSSIBILITY OF SUCH DAMAGE. */ +/* + * Copyright (c) 1982, 1986, 1988, 1993 + * 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 + * 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. + * + * @(#)ip_input.c 8.2 (Berkeley) 1/4/94 + */ + #include "opt_gateway.h" #include "opt_pfil_hooks.h" +#include "opt_ipsec.h" #include "opt_mrouting.h" #include @@ -105,6 +135,15 @@ #include #include #include +/* just for gif_ttl */ +#include +#include "gif.h" + +#ifdef IPSEC +#include +#include +#include +#endif #ifndef IPFORWARDING #ifdef GATEWAY @@ -164,7 +203,59 @@ struct ifqueue ipintrq; struct ipstat ipstat; u_int16_t ip_id; int ip_defttl; + struct ipqhead ipq; +int ipq_locked; + +static __inline int ipq_lock_try __P((void)); +static __inline void ipq_unlock __P((void)); + +static __inline int +ipq_lock_try() +{ + int s; + + s = splimp(); + if (ipq_locked) { + splx(s); + return (0); + } + ipq_locked = 1; + splx(s); + return (1); +} + +static __inline void +ipq_unlock() +{ + int s; + + s = splimp(); + ipq_locked = 0; + splx(s); +} + +#ifdef DIAGNOSTIC +#define IPQ_LOCK() \ +do { \ + if (ipq_lock_try() == 0) { \ + printf("%s:%d: ipq already locked\n", __FILE__, __LINE__); \ + panic("ipq_lock"); \ + } \ +} while (0) +#define IPQ_LOCK_CHECK() \ +do { \ + if (ipq_locked == 0) { \ + printf("%s:%d: ipq lock not held\n", __FILE__, __LINE__); \ + panic("ipq lock check"); \ + } \ +} while (0) +#else +#define IPQ_LOCK() (void) ipq_lock_try() +#define IPQ_LOCK_CHECK() /* nothing */ +#endif + +#define IPQ_UNLOCK() ipq_unlock() struct pool ipqent_pool; @@ -226,39 +317,57 @@ struct sockaddr_in ipaddr = { sizeof(ipa struct route ipforward_rt; /* + * IP software interrupt routine + */ +void +ipintr() +{ + int s; + struct mbuf *m; + + while (1) { + s = splimp(); + IF_DEQUEUE(&ipintrq, m); + splx(s); + if (m == 0) + return; + ip_input(m); + } +} + +/* * Ip input routine. Checksum and byte swap header. If fragmented * try to reassemble. Process options. Pass to next level. */ void -ipintr() +ip_input(struct mbuf *m) { register struct ip *ip = NULL; - register struct mbuf *m; register struct ipq *fp; register struct in_ifaddr *ia; register struct ifaddr *ifa; struct ipqent *ipqe; - int hlen = 0, mff, len, s; + int hlen = 0, mff, len; #ifdef PFIL_HOOKS struct packet_filter_hook *pfh; struct mbuf *m0; int rv; #endif /* PFIL_HOOKS */ -next: - /* - * Get next datagram off input queue and get IP header - * in first mbuf. - */ - s = splimp(); - IF_DEQUEUE(&ipintrq, m); - splx(s); - if (m == 0) - return; #ifdef DIAGNOSTIC if ((m->m_flags & M_PKTHDR) == 0) panic("ipintr no HDR"); #endif +#ifdef IPSEC + /* + * should the inner packet be considered authentic? + * see comment in ah4_input(). + */ + if (m) { + m->m_flags &= ~M_AUTHIPHDR; + m->m_flags &= ~M_AUTHIPDGM; + } +#endif /* * If no IP addresses have been set yet but the interfaces * are receiving, can't do anything with incoming packets yet. @@ -269,7 +378,7 @@ next: if (m->m_len < sizeof (struct ip) && (m = m_pullup(m, sizeof (struct ip))) == 0) { ipstat.ips_toosmall++; - goto next; + return; } ip = mtod(m, struct ip *); if (ip->ip_v != IPVERSION) { @@ -284,11 +393,19 @@ next: if (hlen > m->m_len) { if ((m = m_pullup(m, hlen)) == 0) { ipstat.ips_badhlen++; - goto next; + return; } ip = mtod(m, struct ip *); } - if ((ip->ip_sum = in_cksum(m, hlen)) != 0) { + /* + * we drop packets that have a multicast address as source + * as wanted by rfc 1112 + */ + if (IN_MULTICAST(ip->ip_src.s_addr)) { + goto bad; + } + + if (in_cksum(m, hlen) != 0) { ipstat.ips_badsum++; goto bad; } @@ -297,11 +414,18 @@ next: * Convert fields to host representation. */ NTOHS(ip->ip_len); - NTOHS(ip->ip_id); NTOHS(ip->ip_off); len = ip->ip_len; /* + * Check for additional length bogosity + */ + if (len < hlen) { + ipstat.ips_badlen++; + goto bad; + } + + /* * Check that the amount of data in the buffers * is as at least much as the IP header would have us expect. * Trim mbufs if longer than we expect. @@ -319,11 +443,16 @@ next: m_adj(m, len - m->m_pkthdr.len); } +#ifdef IPSEC + /* ipflow (IP fast fowarding) is not compatible with IPsec. */ + m->m_flags &= ~M_CANFASTFWD; +#else /* * Assume that we can create a fast-forward IP flow entry * based on this packet. */ m->m_flags |= M_CANFASTFWD; +#endif #ifdef PFIL_HOOKS /* @@ -338,10 +467,10 @@ next: if (pfh->pfil_func) { rv = pfh->pfil_func(ip, hlen, m->m_pkthdr.rcvif, 0, &m0); if (rv) - goto next; + return; m = m0; if (m == NULL) - goto next; + return; ip = mtod(m, struct ip *); } #endif /* PFIL_HOOKS */ @@ -354,27 +483,19 @@ next: */ ip_nhops = 0; /* for source routed packets */ if (hlen > sizeof (struct ip) && ip_dooptions(m)) - goto next; + return; /* * Check our list of addresses, to see if the packet is for us. */ - s = splimp(); INADDR_TO_IA(ip->ip_dst, ia); - if (ia != NULL) { - ifa_delref(&ia->ia_ifa); - splx(s); + if (ia != NULL) goto ours; - } if (m->m_pkthdr.rcvif->if_flags & IFF_BROADCAST) { for (ifa = m->m_pkthdr.rcvif->if_addrlist.tqh_first; ifa != NULL; ifa = ifa->ifa_list.tqe_next) { if (ifa->ifa_addr->sa_family != AF_INET) continue; ia = ifatoia(ifa); - /* - * Don't ifa_addref ia as we don't use it after - * we splx(s) below - */ if (in_hosteq(ip->ip_dst, ia->ia_broadaddr.sin_addr) || in_hosteq(ip->ip_dst, ia->ia_netbroadcast) || /* @@ -382,21 +503,16 @@ next: * either for subnet or net. */ ip->ip_dst.s_addr == ia->ia_subnet || - ip->ip_dst.s_addr == ia->ia_net) { - splx(s); + ip->ip_dst.s_addr == ia->ia_net) goto ours; - } /* * An interface with IP address zero accepts * all packets that arrive on that interface. */ - if (in_nullhost(ia->ia_addr.sin_addr)) { - splx(s); + if (in_nullhost(ia->ia_addr.sin_addr)) goto ours; - } } } - splx(s); if (IN_MULTICAST(ip->ip_dst.s_addr)) { struct in_multi *inm; #ifdef MROUTING @@ -405,7 +521,7 @@ next: if (m->m_flags & M_EXT) { if ((m = m_pullup(m, hlen)) == 0) { ipstat.ips_toosmall++; - goto next; + return; } ip = mtod(m, struct ip *); } @@ -423,13 +539,11 @@ next: * as expected when ip_mforward() is called from * ip_output().) */ - ip->ip_id = htons(ip->ip_id); if (ip_mforward(m, m->m_pkthdr.rcvif) != 0) { ipstat.ips_cantforward++; m_freem(m); - goto next; + return; } - ip->ip_id = ntohs(ip->ip_id); /* * The process-level routing demon needs to receive @@ -449,7 +563,7 @@ next: if (inm == NULL) { ipstat.ips_cantforward++; m_freem(m); - goto next; + return; } goto ours; } @@ -465,7 +579,7 @@ next: m_freem(m); } else ip_forward(m, 0); - goto next; + return; ours: /* @@ -480,6 +594,7 @@ ours: * Look for queue of fragments * of this datagram. */ + IPQ_LOCK(); for (fp = ipq.lh_first; fp != NULL; fp = fp->ipq_q.le_next) if (ip->ip_id == fp->ipq_id && in_hosteq(ip->ip_src, fp->ipq_src) && @@ -503,6 +618,7 @@ found: */ if (ip->ip_len == 0 || (ip->ip_len & 0x7) != 0) { ipstat.ips_badfrags++; + IPQ_UNLOCK(); goto bad; } } @@ -518,32 +634,42 @@ found: ipqe = pool_get(&ipqent_pool, PR_NOWAIT); if (ipqe == NULL) { ipstat.ips_rcvmemdrop++; + IPQ_UNLOCK(); goto bad; } ipqe->ipqe_mff = mff; ipqe->ipqe_m = m; ipqe->ipqe_ip = ip; m = ip_reass(ipqe, fp); - if (m == 0) - goto next; + if (m == 0) { + IPQ_UNLOCK(); + return; + } ipstat.ips_reassembled++; ip = mtod(m, struct ip *); hlen = ip->ip_hl << 2; + ip->ip_len += hlen; } else if (fp) ip_freef(fp); - } else - ip->ip_len -= hlen; + IPQ_UNLOCK(); + } /* * Switch out to protocol's input routine. */ +#if IFA_STATS + ia->ia_ifa.ifa_data.ifad_inbytes += ip->ip_len; +#endif ipstat.ips_delivered++; - (*inetsw[ip_protox[ip->ip_p]].pr_input)(m, hlen); - goto next; + { + int off = hlen, nh = ip->ip_p; + + (*inetsw[ip_protox[nh]].pr_input)(m, off, nh); + return; + } bad: m_freem(m); - goto next; } /* @@ -564,6 +690,8 @@ ip_reass(ipqe, fp) int hlen = ipqe->ipqe_ip->ip_hl << 2; int i, next; + IPQ_LOCK_CHECK(); + /* * Presence of header sizes in mbufs * would confuse code below. @@ -686,6 +814,8 @@ insert: * Make header visible. */ ip->ip_len = next; + ip->ip_ttl = 0; /* xxx */ + ip->ip_sum = 0; ip->ip_src = fp->ipq_src; ip->ip_dst = fp->ipq_dst; LIST_REMOVE(fp, ipq_q); @@ -718,6 +848,8 @@ ip_freef(fp) { register struct ipqent *q, *p; + IPQ_LOCK_CHECK(); + for (q = fp->ipq_fragq.lh_first; q != NULL; q = p) { p = q->ipqe_q.le_next; m_freem(q->ipqe_m); @@ -739,6 +871,7 @@ ip_slowtimo() register struct ipq *fp, *nfp; int s = splsoftnet(); + IPQ_LOCK(); for (fp = ipq.lh_first; fp != NULL; fp = nfp) { nfp = fp->ipq_q.le_next; if (--fp->ipq_ttl == 0) { @@ -746,6 +879,7 @@ ip_slowtimo() ip_freef(fp); } } + IPQ_UNLOCK(); #ifdef GATEWAY ipflow_slowtimo(); #endif @@ -759,10 +893,19 @@ void ip_drain() { + /* + * We may be called from a device's interrupt context. If + * the ipq is already busy, just bail out now. + */ + if (ipq_lock_try() == 0) + return; + while (ipq.lh_first != NULL) { ipstat.ips_fragdropped++; ip_freef(ipq.lh_first); } + + IPQ_UNLOCK(); } /* @@ -845,7 +988,6 @@ ip_dooptions(m) * End of source route. Should be for us. */ save_rte(cp, ip->ip_src); - ifa_delref(&ia->ia_ifa); break; } /* @@ -853,7 +995,6 @@ ip_dooptions(m) */ bcopy((caddr_t)(cp + off), (caddr_t)&ipaddr.sin_addr, sizeof(ipaddr.sin_addr)); - ifa_delref(&ia->ia_ifa); if (opt == IPOPT_SSRR) { #define INA struct in_ifaddr * #define SA struct sockaddr * @@ -873,7 +1014,6 @@ ip_dooptions(m) * Let ip_intr's mcast routing check handle mcast pkts */ forward = !IN_MULTICAST(ip->ip_dst.s_addr); - ifa_delref(&ia->ia_ifa); break; case IPOPT_RR: @@ -902,7 +1042,6 @@ ip_dooptions(m) bcopy((caddr_t)&ia->ia_addr.sin_addr, (caddr_t)(cp + off), sizeof(struct in_addr)); cp[IPOPT_OFFSET] += sizeof(struct in_addr); - ifa_delref(&ia->ia_ifa); break; case IPOPT_TS: @@ -932,7 +1071,6 @@ ip_dooptions(m) continue; bcopy((caddr_t)&ia->ia_addr.sin_addr, (caddr_t)sin, sizeof(struct in_addr)); - ifa_delref(&ia->ia_ifa); ipt->ipt_ptr += sizeof(struct in_addr); break; @@ -942,10 +1080,8 @@ ip_dooptions(m) goto bad; bcopy((caddr_t)sin, (caddr_t)&ipaddr.sin_addr, sizeof(struct in_addr)); - ia = (INA)ifa_ifwithaddr((SA)&ipaddr); - if (ia == 0) + if (ifa_ifwithaddr((SA)&ipaddr) == 0) continue; - ifa_delref(&ia->ia_ifa); ipt->ipt_ptr += sizeof(struct in_addr); break; @@ -969,7 +1105,6 @@ ip_dooptions(m) } return (0); bad: - ip->ip_len -= ip->ip_hl << 2; /* XXX icmp_error adds in hdr length */ icmp_error(m, type, code, 0, 0); ipstat.ips_badoptions++; return (1); @@ -984,8 +1119,6 @@ ip_rtaddr(dst) struct in_addr dst; { register struct sockaddr_in *sin; - struct in_ifaddr *ia; - int s; sin = satosin(&ipforward_rt.ro_dst); @@ -1002,11 +1135,7 @@ ip_rtaddr(dst) } if (ipforward_rt.ro_rt == 0) return ((struct in_ifaddr *)0); - s = splimp(); - ia = (ifatoia(ipforward_rt.ro_rt->rt_ifa)); - ifa_addref(&ia->ia_ifa); - splx(s); - return ia; + return (ifatoia(ipforward_rt.ro_rt->rt_ifa)); } /* @@ -1024,7 +1153,7 @@ save_rte(option, dst) #ifdef DIAGNOSTIC if (ipprintfs) printf("save_rte: olen %d\n", olen); -#endif +#endif /* 0 */ if (olen > sizeof(ip_srcrt) - (1 + sizeof(dst))) return; bcopy((caddr_t)option, (caddr_t)ip_srcrt.srcopt, olen); @@ -1118,14 +1247,15 @@ ip_stripoptions(m, mopt) register caddr_t opts; int olen; - olen = (ip->ip_hl<<2) - sizeof (struct ip); + olen = (ip->ip_hl << 2) - sizeof (struct ip); opts = (caddr_t)(ip + 1); i = m->m_len - (sizeof (struct ip) + olen); bcopy(opts + olen, opts, (unsigned)i); m->m_len -= olen; if (m->m_flags & M_PKTHDR) m->m_pkthdr.len -= olen; - ip->ip_hl = sizeof(struct ip) >> 2; + ip->ip_len -= olen; + ip->ip_hl = sizeof (struct ip) >> 2; } int inetctlerrmap[PRC_NCMDS] = { @@ -1163,6 +1293,9 @@ ip_forward(m, srcrt) struct mbuf *mcopy; n_long dest; struct ifnet *destifp; +#ifdef IPSEC + struct ifnet dummyifp; +#endif dest = 0; #ifdef DIAGNOSTIC @@ -1171,12 +1304,11 @@ ip_forward(m, srcrt) ntohl(ip->ip_src.s_addr), ntohl(ip->ip_dst.s_addr), ip->ip_ttl); #endif - if (m->m_flags & M_BCAST || in_canforward(ip->ip_dst) == 0) { + if (m->m_flags & (M_BCAST|M_MCAST) || in_canforward(ip->ip_dst) == 0) { ipstat.ips_cantforward++; m_freem(m); return; } - HTONS(ip->ip_id); if (ip->ip_ttl <= IPTTLDEC) { icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS, dest, 0); return; @@ -1223,20 +1355,27 @@ ip_forward(m, srcrt) if (rt->rt_ifa && (ip->ip_src.s_addr & ifatoia(rt->rt_ifa)->ia_subnetmask) == ifatoia(rt->rt_ifa)->ia_subnet) { - if (rt->rt_flags & RTF_GATEWAY) - dest = satosin(rt->rt_gateway)->sin_addr.s_addr; - else - dest = ip->ip_dst.s_addr; - /* Router requirements says to only send host redirects */ - type = ICMP_REDIRECT; - code = ICMP_REDIRECT_HOST; + if (rt->rt_flags & RTF_GATEWAY) + dest = satosin(rt->rt_gateway)->sin_addr.s_addr; + else + dest = ip->ip_dst.s_addr; + /* + * Router requirements says to only send host + * redirects. + */ + type = ICMP_REDIRECT; + code = ICMP_REDIRECT_HOST; #ifdef DIAGNOSTIC - if (ipprintfs) - printf("redirect (%d) to %x\n", code, (u_int32_t)dest); + if (ipprintfs) + printf("redirect (%d) to %x\n", code, + (u_int32_t)dest); #endif } } +#ifdef IPSEC + m->m_pkthdr.rcvif = NULL; +#endif /*IPSEC*/ error = ip_output(m, (struct mbuf *)0, &ipforward_rt, (IP_FORWARDING | (ip_directedbcast ? IP_ALLOWBROADCAST : 0)), 0); if (error) @@ -1278,8 +1417,57 @@ ip_forward(m, srcrt) case EMSGSIZE: type = ICMP_UNREACH; code = ICMP_UNREACH_NEEDFRAG; +#ifndef IPSEC if (ipforward_rt.ro_rt) destifp = ipforward_rt.ro_rt->rt_ifp; +#else + /* + * If the packet is routed over IPsec tunnel, tell the + * originator the tunnel MTU. + * tunnel MTU = if MTU - sizeof(IP) - ESP/AH hdrsiz + * XXX quickhack!!! + */ + if (ipforward_rt.ro_rt) { + struct secpolicy *sp; + int ipsecerror; + int ipsechdr; + struct route *ro; + + sp = ipsec4_getpolicybyaddr(mcopy, + IP_FORWARDING, + &ipsecerror); + + if (sp == NULL) + destifp = ipforward_rt.ro_rt->rt_ifp; + else { + /* count IPsec header size */ + ipsechdr = ipsec4_hdrsiz(mcopy, NULL); + + /* + * find the correct route for outer IPv4 + * header, compute tunnel MTU. + * + * XXX BUG ALERT + * The "dummyifp" code relies upon the fact + * that icmp_error() touches only ifp->if_mtu. + */ + /*XXX*/ + destifp = NULL; + if (sp->req != NULL + && sp->req->sa != NULL) { + ro = &sp->req->sa->saidx->sa_route; + if (ro->ro_rt && ro->ro_rt->rt_ifp) { + dummyifp.if_mtu = + ro->ro_rt->rt_ifp->if_mtu; + dummyifp.if_mtu -= ipsechdr; + destifp = &dummyifp; + } + } + + key_freesp(sp); + } + } +#endif /*IPSEC*/ ipstat.ips_cantfrag++; break; @@ -1360,7 +1548,7 @@ ip_sysctl(name, namelen, oldp, oldlenp, void *newp; size_t newlen; { - extern int subnetsarelocal; + extern int subnetsarelocal, hostzeroisbroadcast; int error, old; @@ -1452,6 +1640,15 @@ ip_sysctl(name, namelen, oldp, oldlenp, return (error); } #endif + case IPCTL_HOSTZEROBROADCAST: + return (sysctl_int(oldp, oldlenp, newp, newlen, + &hostzeroisbroadcast)); +#if NGIF > 0 + case IPCTL_GIF_TTL: + return(sysctl_int(oldp, oldlenp, newp, newlen, + &ip_gif_ttl)); +#endif + default: return (EOPNOTSUPP); }