ip_output.c

嵌入式操作系统ECOS的网络开发包

//==========================================================================
//
//      sys/netinet/ip_output.c
//
//     
//
//==========================================================================
//####BSDCOPYRIGHTBEGIN####
//
// -------------------------------------------
//
// Portions of this software may have been derived from OpenBSD or other sources,
// and are covered by the appropriate copyright disclaimers included herein.
//
// -------------------------------------------
//
//####BSDCOPYRIGHTEND####
//==========================================================================
//#####DESCRIPTIONBEGIN####
//
// Author(s):    gthomas
// Contributors: gthomas
// Date:         2000-01-10
// Purpose:      
// Description:  
//              
//
//####DESCRIPTIONEND####
//
//==========================================================================


/*	$OpenBSD: ip_output.c,v 1.57 1999/12/10 08:55:23 angelos Exp $	*/
/*	$NetBSD: ip_output.c,v 1.28 1996/02/13 23:43:07 christos Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1988, 1990, 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_output.c	8.3 (Berkeley) 1/21/94
 */

#include <sys/param.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/errno.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#ifndef __ECOS
#include <sys/systm.h>
#endif
#include <sys/kernel.h>
#ifndef __ECOS
#include <sys/proc.h>

#include <vm/vm.h>
#include <sys/proc.h>
#endif

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>

#ifdef vax
#include <machine/mtpr.h>
#endif

#include <machine/stdarg.h>

#ifdef IPSEC
#include <netinet/ip_ah.h>
#include <netinet/ip_esp.h>
#include <netinet/udp.h>
#include <netinet/tcp.h>
#include <net/pfkeyv2.h>

#ifdef ENCDEBUG
#define DPRINTF(x)    do { if (encdebug) printf x ; } while (0)
#else
#define DPRINTF(x)
#endif

#ifndef offsetof
#define offsetof(s, e) ((int)&((s *)0)->e)
#endif

extern u_int8_t get_sa_require  __P((struct inpcb *));

#endif /* IPSEC */

static struct mbuf *ip_insertoptions __P((struct mbuf *, struct mbuf *, int *));
static void ip_mloopback
	__P((struct ifnet *, struct mbuf *, struct sockaddr_in *));
#if defined(IPFILTER) || defined(IPFILTER_LKM)
int (*fr_checkp) __P((struct ip *, int, struct ifnet *, int, struct mbuf **));
#endif

#ifdef IPSEC
extern int ipsec_auth_default_level;
extern int ipsec_esp_trans_default_level;
extern int ipsec_esp_network_default_level;

extern int pfkeyv2_acquire(struct tdb *, int);
#endif

#ifndef RAMDOM_IP_ID
u_short ip_id;
#endif

/*
 * IP output.  The packet in mbuf chain m contains a skeletal IP
 * header (with len, off, ttl, proto, tos, src, dst).
 * The mbuf chain containing the packet will be freed.
 * The mbuf opt, if present, will not be freed.
 */
int
#if __STDC__
ip_output(struct mbuf *m0, ...)
#else
ip_output(m0, va_alist)
	struct mbuf *m0;
	va_dcl
#endif
{
	register struct ip *ip, *mhip;
	register struct ifnet *ifp;
	register struct mbuf *m = m0;
	register int hlen = sizeof (struct ip);
	int len, off, error = 0;
	struct route iproute;
	struct sockaddr_in *dst;
	struct in_ifaddr *ia;
	struct mbuf *opt;
	struct route *ro;
	int flags;
	struct ip_moptions *imo;
	va_list ap;
#ifdef IPSEC
	union sockaddr_union sunion;
	struct mbuf *mp;
	struct udphdr *udp;
	struct tcphdr *tcp;
	struct inpcb *inp;

	struct route_enc re0, *re = &re0;
	struct sockaddr_encap *ddst, *gw;
	u_int8_t sa_require, sa_have = 0;
	struct tdb *tdb, *t;
	int s, ip6flag;

#ifdef INET6
	struct ip6_hdr *ip6;
#endif /* INET6 */
#endif /* IPSEC */

	va_start(ap, m0);
	opt = va_arg(ap, struct mbuf *);
	ro = va_arg(ap, struct route *);
	flags = va_arg(ap, int);
	imo = va_arg(ap, struct ip_moptions *);
#ifdef IPSEC
	inp = va_arg(ap, struct inpcb *);
#endif /* IPSEC */
	va_end(ap);

#ifdef	DIAGNOSTIC
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("ip_output no HDR");
#endif
	if (opt) {
		m = ip_insertoptions(m, opt, &len);
		hlen = len;
	}
	ip = mtod(m, struct ip *);
	/*
	 * Fill in IP header.
	 */
	if ((flags & (IP_FORWARDING|IP_RAWOUTPUT)) == 0) {
		ip->ip_v = IPVERSION;
		ip->ip_off &= IP_DF;
#ifdef RANDOM_IP_ID
		ip->ip_id = ip_randomid();
#else
		ip->ip_id = htons(ip_id++);
#endif
		ip->ip_hl = hlen >> 2;
		ipstat.ips_localout++;
	} else {
		hlen = ip->ip_hl << 2;
	}

	/*
	 * Route packet.
	 */
	if (ro == 0) {
		ro = &iproute;
		bzero((caddr_t)ro, sizeof (*ro));
	}
	dst = satosin(&ro->ro_dst);
	/*
	 * If there is a cached route,
	 * check that it is to the same destination
	 * and is still up.  If not, free it and try again.
	 */
	if (ro->ro_rt && ((ro->ro_rt->rt_flags & RTF_UP) == 0 ||
	    dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
		RTFREE(ro->ro_rt);
		ro->ro_rt = (struct rtentry *)0;
	}
	if (ro->ro_rt == 0) {
		dst->sin_family = AF_INET;
		dst->sin_len = sizeof(*dst);
		dst->sin_addr = ip->ip_dst;
	}
	/*
	 * If routing to interface only,
	 * short circuit routing lookup.
	 */
	if (flags & IP_ROUTETOIF) {
		if ((ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst)))) == 0 &&
		    (ia = ifatoia(ifa_ifwithnet(sintosa(dst)))) == 0) {
			ipstat.ips_noroute++;
			error = ENETUNREACH;
			goto bad;
		}
		ifp = ia->ia_ifp;
		ip->ip_ttl = 1;
	} else {
		if (ro->ro_rt == 0)
			rtalloc(ro);
		if (ro->ro_rt == 0) {
			ipstat.ips_noroute++;
			error = EHOSTUNREACH;
			goto bad;
		}
		ia = ifatoia(ro->ro_rt->rt_ifa);
		ifp = ro->ro_rt->rt_ifp;
		ro->ro_rt->rt_use++;
		if (ro->ro_rt->rt_flags & RTF_GATEWAY)
			dst = satosin(ro->ro_rt->rt_gateway);
	}
	if (IN_MULTICAST(ip->ip_dst.s_addr)) {
		struct in_multi *inm;

		m->m_flags |= M_MCAST;
		/*
		 * IP destination address is multicast.  Make sure "dst"
		 * still points to the address in "ro".  (It may have been
		 * changed to point to a gateway address, above.)
		 */
		dst = satosin(&ro->ro_dst);
		/*
		 * See if the caller provided any multicast options
		 */
		if (imo != NULL) {
			ip->ip_ttl = imo->imo_multicast_ttl;
			if (imo->imo_multicast_ifp != NULL)
				ifp = imo->imo_multicast_ifp;
		} else
			ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
		/*
		 * Confirm that the outgoing interface supports multicast.
		 */
		if ((ifp->if_flags & IFF_MULTICAST) == 0) {
			ipstat.ips_noroute++;
			error = ENETUNREACH;
			goto bad;
		}
		/*
		 * If source address not specified yet, use address
		 * of outgoing interface.
		 */
		if (ip->ip_src.s_addr == INADDR_ANY) {
			register struct in_ifaddr *ia;

			for (ia = in_ifaddr.tqh_first; ia; ia = ia->ia_list.tqe_next)
				if (ia->ia_ifp == ifp) {
					ip->ip_src = ia->ia_addr.sin_addr;
					break;
				}
		}

		IN_LOOKUP_MULTI(ip->ip_dst, ifp, inm);
		if (inm != NULL &&
		   (imo == NULL || imo->imo_multicast_loop)) {
			/*
			 * If we belong to the destination multicast group
			 * on the outgoing interface, and the caller did not
			 * forbid loopback, loop back a copy.
			 */
			ip_mloopback(ifp, m, dst);
		}
#ifdef MROUTING
		else {
			/*
			 * If we are acting as a multicast router, perform
			 * multicast forwarding as if the packet had just
			 * arrived on the interface to which we are about
			 * to send.  The multicast forwarding function
			 * recursively calls this function, using the
			 * IP_FORWARDING flag to prevent infinite recursion.
			 *
			 * Multicasts that are looped back by ip_mloopback(),
			 * above, will be forwarded by the ip_input() routine,
			 * if necessary.
			 */
			extern struct socket *ip_mrouter;

			if (ip_mrouter && (flags & IP_FORWARDING) == 0) {
				if (ip_mforward(m, ifp) != 0) {
					m_freem(m);
					goto done;
				}
			}
		}
#endif
		/*
		 * Multicasts with a time-to-live of zero may be looped-
		 * back, above, but must not be transmitted on a network.
		 * Also, multicasts addressed to the loopback interface
		 * are not sent -- the above call to ip_mloopback() will
		 * loop back a copy if this host actually belongs to the
		 * destination group on the loopback interface.
		 */
		if (ip->ip_ttl == 0 || (ifp->if_flags & IFF_LOOPBACK) != 0) {
			m_freem(m);
			goto done;
		}

		goto sendit;
	}
#ifndef notdef
	/*
	 * If source address not specified yet, use address
	 * of outgoing interface.
	 */
	if (ip->ip_src.s_addr == INADDR_ANY)
		ip->ip_src = ia->ia_addr.sin_addr;
#endif
	/*
	 * Look for broadcast address and
	 * and verify user is allowed to send
	 * such a packet.
	 */
	if (in_broadcast(dst->sin_addr, ifp)) {
		if ((ifp->if_flags & IFF_BROADCAST) == 0) {
			error = EADDRNOTAVAIL;
			goto bad;
		}
		if ((flags & IP_ALLOWBROADCAST) == 0) {
			error = EACCES;
			goto bad;
		}
		/* don't allow broadcast messages to be fragmented */
		if ((u_int16_t)ip->ip_len > ifp->if_mtu) {
			error = EMSGSIZE;
			goto bad;
		}
		m->m_flags |= M_BCAST;
	} else
		m->m_flags &= ~M_BCAST;

sendit:
#ifdef IPSEC
	/*
	 * Check if the packet needs encapsulation.
	 */
	if (!(flags & IP_ENCAPSULATED) &&
	    (inp == NULL || 
	     inp->inp_seclevel[SL_AUTH] != IPSEC_LEVEL_BYPASS ||
	     inp->inp_seclevel[SL_ESP_TRANS] != IPSEC_LEVEL_BYPASS ||
	     inp->inp_seclevel[SL_ESP_NETWORK] != IPSEC_LEVEL_BYPASS)) {
		if (inp == NULL)
			sa_require = get_sa_require(inp);
		else
			sa_require = inp->inp_secrequire;

		bzero((caddr_t) re, sizeof(*re));

		/*
		 * splnet is chosen over spltdb because we are not allowed to
		 * lower the level, and udp_output calls us in splnet().
		 */
		s = splnet();

		/*
		 * Check if there was an outgoing SA bound to the flow
		 * from a transport protocol.
		 */
		if (inp && inp->inp_tdb &&
		    (inp->inp_tdb->tdb_dst.sin.sin_addr.s_addr == INADDR_ANY ||
		     !bcmp(&inp->inp_tdb->tdb_dst.sin.sin_addr,
			   &ip->ip_dst, sizeof(ip->ip_dst)))) {
			tdb = inp->inp_tdb;
			goto have_tdb;
		}

		if (!ipsec_in_use) {
			splx(s);
			goto no_encap;
		}

		ddst = (struct sockaddr_encap *) &re->re_dst;
		ddst->sen_family = PF_KEY;
		ddst->sen_len = SENT_IP4_LEN;
		ddst->sen_type = SENT_IP4;
		ddst->sen_ip_src = ip->ip_src;
		ddst->sen_ip_dst = ip->ip_dst;
		ddst->sen_proto = ip->ip_p;

		switch (ip->ip_p) {
		case IPPROTO_UDP:
			if (m->m_len < hlen + 2 * sizeof(u_int16_t)) {
				if ((m = m_pullup(m, hlen + 2 *
				    sizeof(u_int16_t))) == 0)
					return ENOBUFS;
				ip = mtod(m, struct ip *);
			}
			udp = (struct udphdr *) (mtod(m, u_char *) + hlen);
			ddst->sen_sport = ntohs(udp->uh_sport);
			ddst->sen_dport = ntohs(udp->uh_dport);
			break;

		case IPPROTO_TCP:
			if (m->m_len < hlen + 2 * sizeof(u_int16_t)) {
				if ((m = m_pullup(m, hlen + 2 *
				    sizeof(u_int16_t))) == 0)
					return ENOBUFS;
				ip = mtod(m, struct ip *);
			}
			tcp = (struct tcphdr *) (mtod(m, u_char *) + hlen);
			ddst->sen_sport = ntohs(tcp->th_sport);
			ddst->sen_dport = ntohs(tcp->th_dport);
			break;

		default:
			ddst->sen_sport = 0;
			ddst->sen_dport = 0;
		}

		rtalloc((struct route *) re);
		if (re->re_rt == NULL) {
			splx(s);
			goto no_encap;
		}

		gw = (struct sockaddr_encap *) (re->re_rt->rt_gateway);

		/* Sanity check */
		if (gw == NULL || ((gw->sen_type != SENT_IPSP) &&
				   (gw->sen_type != SENT_IPSP6))) {
			splx(s);
		        DPRINTF(("ip_output(): no gw or gw data not IPSP\n"));

			if (re->re_rt)
				RTFREE(re->re_rt);
			error = EHOSTUNREACH;
			m_freem(m);
			goto done;
		}

		/*
		 * There might be a specific route, that tells us to avoid
		 * doing IPsec; this is useful for specific routes that we
		 * don't want to have IPsec applied on, like the key
		 * management ports.
		 */

		if ((gw != NULL) && (gw->sen_ipsp_sproto == 0) &&
		    (gw->sen_ipsp_spi == 0)) {
		    if ((gw->sen_family == AF_INET) &&
			(gw->sen_ipsp_dst.s_addr == 0)) {
			splx(s);
			goto no_encap;
		    }

#ifdef INET6
		    if ((gw->sen_family == AF_INET6) &&
			IN6_IS_ADDR_UNSPECIFIED(&gw->sen_ipsp6_dst)) {
			splx(s);
			goto no_encap;
		    }
#endif /* INET6 */
		}

		/*
		 * At this point we have an IPSP "gateway" (tunnel) spec.
		 * Use the destination of the tunnel and the SPI to
		 * look up the necessary Tunnel Control Block. Look it up,
		 * and then pass it, along with the packet and the gw,
		 * to the appropriate transformation.
		 */
		bzero(&sunion, sizeof(sunion));

		if (gw->sen_type == SENT_IPSP) {
		    sunion.sin.sin_family = AF_INET;
		    sunion.sin.sin_len = sizeof(struct sockaddr_in);
		    sunion.sin.sin_addr = gw->sen_ipsp_dst;
		}
#ifdef INET6
		if (gw->sen_type == SENT_IPSP6) {
		    sunion.sin6.sin6_family = AF_INET6;
		    sunion.sin6.sin6_len = sizeof(struct sockaddr_in6);
		    sunion.sin6.sin6_addr = gw->sen_ipsp6_dst;
		}
#endif /* INET6 */

		tdb = (struct tdb *) gettdb(gw->sen_ipsp_spi, &sunion,
					    gw->sen_ipsp_sproto);

		/* 
		 * For VPNs a route with a reserved SPI is used to
		 * indicate the need for an SA when none is established.
		 */
		if (((ntohl(gw->sen_ipsp_spi) == SPI_LOCAL_USE) &&
		     (gw->sen_type == SENT_IPSP)) ||
		    ((ntohl(gw->sen_ipsp6_spi) == SPI_LOCAL_USE) &&
		     (gw->sen_type == SENT_IPSP6))) {
		    if (tdb == NULL) {
			/*
			 * XXX We should construct a TDB from system
			 * default (which should be tunable via sysctl).
			 * For now, drop packet and ignore SPD entry.
			 */
			splx(s);
			goto no_encap;
		    }
		    else {
			if (tdb->tdb_authalgxform)
			  sa_require = NOTIFY_SATYPE_AUTH;
			if (tdb->tdb_encalgxform)
			  sa_require |= NOTIFY_SATYPE_CONF;
			if (tdb->tdb_flags & TDBF_TUNNELING)
			  sa_require |= NOTIFY_SATYPE_TUNNEL;
		    }

		    /* PF_KEYv2 notification message */
		    if (tdb && tdb->tdb_satype != SADB_X_SATYPE_BYPASS)
		            if ((error = pfkeyv2_acquire(tdb, 0)) != 0)
			            return error;

		    splx(s);

		    /* 
		     * When sa_require is set, the packet will be dropped
		     * at no_encap.
		     */
		    goto no_encap;
		}

	     have_tdb: