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/raw_ip.c,v rcsdiff: /ftp/cvs/cvsroot/src/sys/netinet/raw_ip.c,v: warning: Unknown phrases like `commitid ...;' are present. retrieving revision 1.56.2.1 retrieving revision 1.80 diff -u -p -r1.56.2.1 -r1.80 --- src/sys/netinet/raw_ip.c 2001/08/03 04:13:55 1.56.2.1 +++ src/sys/netinet/raw_ip.c 2004/05/07 00:55:15 1.80 @@ -1,9 +1,9 @@ -/* $NetBSD: raw_ip.c,v 1.56.2.1 2001/08/03 04:13:55 lukem Exp $ */ +/* $NetBSD: raw_ip.c,v 1.80 2004/05/07 00:55:15 jonathan Exp $ */ /* * 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: @@ -15,7 +15,7 @@ * 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 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 @@ -41,11 +41,7 @@ * 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 University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * @@ -64,6 +60,10 @@ * @(#)raw_ip.c 8.7 (Berkeley) 5/15/95 */ +#include +__KERNEL_RCSID(0, "$NetBSD: raw_ip.c,v 1.80 2004/05/07 00:55:15 jonathan Exp $"); + +#include "opt_inet.h" #include "opt_ipsec.h" #include "opt_mrouting.h" @@ -95,8 +95,15 @@ #include #endif /*IPSEC*/ +#ifdef FAST_IPSEC +#include +#include /* XXX ipsecstat namespace */ +#endif /* FAST_IPSEC*/ + struct inpcbtable rawcbtable; +int rip_pcbnotify __P((struct inpcbtable *, struct in_addr, + struct in_addr, int, int, void (*) __P((struct inpcb *, int)))); int rip_bind __P((struct inpcb *, struct mbuf *)); int rip_connect __P((struct inpcb *, struct mbuf *)); void rip_disconnect __P((struct inpcb *)); @@ -121,24 +128,17 @@ rip_init() in_pcbinit(&rawcbtable, 1, 1); } -static struct sockaddr_in ripsrc = { sizeof(ripsrc), AF_INET }; - /* * Setup generic address and protocol structures * for raw_input routine, then pass them along with * mbuf chain. */ void -#if __STDC__ rip_input(struct mbuf *m, ...) -#else -rip_input(m, va_alist) - struct mbuf *m; - va_dcl -#endif { - int off, proto; + int proto; struct ip *ip = mtod(m, struct ip *); + struct inpcb_hdr *inph; struct inpcb *inp; struct inpcb *last = 0; struct mbuf *opts = 0; @@ -146,7 +146,7 @@ rip_input(m, va_alist) va_list ap; va_start(ap, m); - off = va_arg(ap, int); + (void)va_arg(ap, int); /* ignore value, advance ap */ proto = va_arg(ap, int); va_end(ap); @@ -158,13 +158,16 @@ rip_input(m, va_alist) /* * XXX Compatibility: programs using raw IP expect ip_len - * XXX to have the header length subtracted. + * XXX to have the header length subtracted, and in host order. + * XXX ip_off is also expected to be host order. */ - ip->ip_len -= ip->ip_hl << 2; + ip->ip_len = ntohs(ip->ip_len) - (ip->ip_hl << 2); + NTOHS(ip->ip_off); - for (inp = rawcbtable.inpt_queue.cqh_first; - inp != (struct inpcb *)&rawcbtable.inpt_queue; - inp = inp->inp_queue.cqe_next) { + CIRCLEQ_FOREACH(inph, &rawcbtable.inpt_queue, inph_queue) { + inp = (struct inpcb *)inph; + if (inp->inp_af != AF_INET) + continue; if (inp->inp_ip.ip_p && inp->inp_ip.ip_p != proto) continue; if (!in_nullhost(inp->inp_laddr) && @@ -176,7 +179,7 @@ rip_input(m, va_alist) if (last) { struct mbuf *n; -#ifdef IPSEC +#if defined(IPSEC) || defined(FAST_IPSEC) /* check AH/ESP integrity. */ if (ipsec4_in_reject_so(m, last->inp_socket)) { ipsecstat.in_polvio++; @@ -200,7 +203,7 @@ rip_input(m, va_alist) } last = inp; } -#ifdef IPSEC +#if defined(IPSEC) || defined(FAST_IPSEC) /* check AH/ESP integrity. */ if (last && ipsec4_in_reject_so(m, last->inp_socket)) { m_freem(m); @@ -232,18 +235,75 @@ rip_input(m, va_alist) return; } +int +rip_pcbnotify(table, faddr, laddr, proto, errno, notify) + struct inpcbtable *table; + struct in_addr faddr, laddr; + int proto; + int errno; + void (*notify) __P((struct inpcb *, int)); +{ + struct inpcb *inp, *ninp; + int nmatch; + + nmatch = 0; + for (inp = (struct inpcb *)CIRCLEQ_FIRST(&table->inpt_queue); + inp != (struct inpcb *)&table->inpt_queue; + inp = ninp) { + ninp = (struct inpcb *)inp->inp_queue.cqe_next; + if (inp->inp_af != AF_INET) + continue; + if (inp->inp_ip.ip_p && inp->inp_ip.ip_p != proto) + continue; + if (in_hosteq(inp->inp_faddr, faddr) && + in_hosteq(inp->inp_laddr, laddr)) { + (*notify)(inp, errno); + nmatch++; + } + } + + return nmatch; +} + +void * +rip_ctlinput(cmd, sa, v) + int cmd; + struct sockaddr *sa; + void *v; +{ + struct ip *ip = v; + void (*notify) __P((struct inpcb *, int)) = in_rtchange; + int errno; + + if (sa->sa_family != AF_INET || + sa->sa_len != sizeof(struct sockaddr_in)) + return NULL; + if ((unsigned)cmd >= PRC_NCMDS) + return NULL; + errno = inetctlerrmap[cmd]; + if (PRC_IS_REDIRECT(cmd)) + notify = in_rtchange, ip = 0; + else if (cmd == PRC_HOSTDEAD) + ip = 0; + else if (errno == 0) + return NULL; + if (ip) { + rip_pcbnotify(&rawcbtable, satosin(sa)->sin_addr, + ip->ip_src, ip->ip_p, errno, notify); + + /* XXX mapped address case */ + } else + in_pcbnotifyall(&rawcbtable, satosin(sa)->sin_addr, errno, + notify); + return NULL; +} + /* * Generate IP header and pass packet to ip_output. * Tack on options user may have setup with control call. */ int -#if __STDC__ rip_output(struct mbuf *m, ...) -#else -rip_output(m, va_alist) - struct mbuf *m; - va_dcl -#endif { struct inpcb *inp; struct ip *ip; @@ -268,12 +328,14 @@ rip_output(m, va_alist) m_freem(m); return (EMSGSIZE); } - M_PREPEND(m, sizeof(struct ip), M_WAIT); + M_PREPEND(m, sizeof(struct ip), M_DONTWAIT); + if (!m) + return (ENOBUFS); ip = mtod(m, struct ip *); ip->ip_tos = 0; - ip->ip_off = 0; + ip->ip_off = htons(0); ip->ip_p = inp->inp_ip.ip_p; - ip->ip_len = m->m_pkthdr.len; + ip->ip_len = htons(m->m_pkthdr.len); ip->ip_src = inp->inp_laddr; ip->ip_dst = inp->inp_faddr; ip->ip_ttl = MAXTTL; @@ -284,24 +346,37 @@ rip_output(m, va_alist) return (EMSGSIZE); } ip = mtod(m, struct ip *); + + /* + * If the mbuf is read-only, we need to allocate + * a new mbuf for the header, since we need to + * modify the header. + */ + if (M_READONLY(m)) { + int hlen = ip->ip_hl << 2; + + m = m_copyup(m, hlen, (max_linkhdr + 3) & ~3); + if (m == NULL) + return (ENOMEM); /* XXX */ + ip = mtod(m, struct ip *); + } + + /* XXX userland passes ip_len and ip_off in host order */ if (m->m_pkthdr.len != ip->ip_len) { m_freem(m); return (EINVAL); } + HTONS(ip->ip_len); + HTONS(ip->ip_off); if (ip->ip_id == 0) - ip->ip_id = htons(ip_id++); + ip->ip_id = ip_newid(); opts = NULL; /* XXX prevent ip_output from overwriting header fields */ flags |= IP_RAWOUTPUT; ipstat.ips_rawout++; } -#ifdef IPSEC - if (ipsec_setsocket(m, inp->inp_socket) != 0) { - m_freem(m); - return ENOBUFS; - } -#endif /*IPSEC*/ - return (ip_output(m, opts, &inp->inp_route, flags, inp->inp_moptions, &inp->inp_errormtu)); + return (ip_output(m, opts, &inp->inp_route, flags, inp->inp_moptions, + inp->inp_socket, &inp->inp_errormtu)); } /* @@ -359,7 +434,8 @@ rip_ctloutput(op, so, level, optname, m) case PRCO_GETOPT: switch (optname) { case IP_HDRINCL: - *m = m_get(M_WAIT, M_SOOPTS); + *m = m_get(M_WAIT, MT_SOOPTS); + MCLAIM((*m), so->so_mowner); (*m)->m_len = sizeof (int); *mtod(*m, int *) = inp->inp_flags & INP_HDRINCL ? 1 : 0; break; @@ -389,7 +465,7 @@ rip_bind(inp, nam) if (nam->m_len != sizeof(*addr)) return (EINVAL); - if (ifnet.tqh_first == 0) + if (TAILQ_FIRST(&ifnet) == 0) return (EADDRNOTAVAIL); if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) @@ -410,7 +486,7 @@ rip_connect(inp, nam) if (nam->m_len != sizeof(*addr)) return (EINVAL); - if (ifnet.tqh_first == 0) + if (TAILQ_FIRST(&ifnet) == 0) return (EADDRNOTAVAIL); if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK)