ip_input.c

嵌入式操作系统ECOS的网络开发包

#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("save_rte: olen %d\n", olen);
#endif
	if (olen > sizeof(ip_srcrt) - (1 + sizeof(dst)))
		return;
	bcopy(option, ip_srcrt.srcopt, olen);
	ip_nhops = (olen - IPOPT_OFFSET - 1) / sizeof(struct in_addr);
	ip_srcrt.dst = dst;
}

/*
 * Retrieve incoming source route for use in replies,
 * in the same form used by setsockopt.
 * The first hop is placed before the options, will be removed later.
 */
struct mbuf *
ip_srcroute()
{
	register struct in_addr *p, *q;
	register struct mbuf *m;

	if (ip_nhops == 0)
		return ((struct mbuf *)0);
	m = m_get(M_DONTWAIT, MT_HEADER);
	if (m == 0)
		return ((struct mbuf *)0);

#define OPTSIZ	(sizeof(ip_srcrt.nop) + sizeof(ip_srcrt.srcopt))

	/* length is (nhops+1)*sizeof(addr) + sizeof(nop + srcrt header) */
	m->m_len = ip_nhops * sizeof(struct in_addr) + sizeof(struct in_addr) +
	    OPTSIZ;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("ip_srcroute: nhops %d mlen %d", ip_nhops, m->m_len);
#endif

	/*
	 * First save first hop for return route
	 */
	p = &ip_srcrt.route[ip_nhops - 1];
	*(mtod(m, struct in_addr *)) = *p--;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf(" hops %lx", (u_long)ntohl(mtod(m, struct in_addr *)->s_addr));
#endif

	/*
	 * Copy option fields and padding (nop) to mbuf.
	 */
	ip_srcrt.nop = IPOPT_NOP;
	ip_srcrt.srcopt[IPOPT_OFFSET] = IPOPT_MINOFF;
	(void)memcpy(mtod(m, caddr_t) + sizeof(struct in_addr),
	    &ip_srcrt.nop, OPTSIZ);
	q = (struct in_addr *)(mtod(m, caddr_t) +
	    sizeof(struct in_addr) + OPTSIZ);
#undef OPTSIZ
	/*
	 * Record return path as an IP source route,
	 * reversing the path (pointers are now aligned).
	 */
	while (p >= ip_srcrt.route) {
#ifdef DIAGNOSTIC
		if (ipprintfs)
			printf(" %lx", (u_long)ntohl(q->s_addr));
#endif
		*q++ = *p--;
	}
	/*
	 * Last hop goes to final destination.
	 */
	*q = ip_srcrt.dst;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf(" %lx\n", (u_long)ntohl(q->s_addr));
#endif
	return (m);
}

/*
 * Strip out IP options, at higher
 * level protocol in the kernel.
 * Second argument is buffer to which options
 * will be moved, and return value is their length.
 * XXX should be deleted; last arg currently ignored.
 */
void
ip_stripoptions(m, mopt)
	register struct mbuf *m;
	struct mbuf *mopt;
{
	register int i;
	struct ip *ip = mtod(m, struct ip *);
	register caddr_t opts;
	int olen;

	olen = (IP_VHL_HL(ip->ip_vhl) << 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_vhl = IP_MAKE_VHL(IPVERSION, sizeof(struct ip) >> 2);
}

int inetctlerrmap[PRC_NCMDS] = {
	0,		0,		0,		0,
	0,		EMSGSIZE,	EHOSTDOWN,	EHOSTUNREACH,
	EHOSTUNREACH,	EHOSTUNREACH,	ECONNREFUSED,	ECONNREFUSED,
	EMSGSIZE,	EHOSTUNREACH,	0,		0,
	0,		0,		0,		0,
	ENOPROTOOPT,	ECONNREFUSED
};

/*
 * Forward a packet.  If some error occurs return the sender
 * an icmp packet.  Note we can't always generate a meaningful
 * icmp message because icmp doesn't have a large enough repertoire
 * of codes and types.
 *
 * If not forwarding, just drop the packet.  This could be confusing
 * if ipforwarding was zero but some routing protocol was advancing
 * us as a gateway to somewhere.  However, we must let the routing
 * protocol deal with that.
 *
 * The srcrt parameter indicates whether the packet is being forwarded
 * via a source route.
 */
#ifdef NATPT
void
#else
static void
#endif
ip_forward(m, srcrt)
	struct mbuf *m;
	int srcrt;
{
	register struct ip *ip = mtod(m, struct ip *);
	register struct sockaddr_in *sin;
	register struct rtentry *rt;
	int error, type = 0, code = 0;
	struct mbuf *mcopy;
	n_long dest;
	struct ifnet *destifp;
#ifdef IPSEC
	struct ifnet dummyifp;
#endif

	dest = 0;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("forward: src %lx dst %lx ttl %x\n",
		    (u_long)ip->ip_src.s_addr, (u_long)ip->ip_dst.s_addr,
		    ip->ip_ttl);
#endif


	if (m->m_flags & (M_BCAST|M_MCAST) || in_canforward(ip->ip_dst) == 0) {
		ipstat.ips_cantforward++;
		m_freem(m);
		return;
	}
#ifdef IPSTEALTH
	if (!ipstealth) {
#endif
		if (ip->ip_ttl <= IPTTLDEC) {
			icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS,
			    dest, 0);
			return;
		}
#ifdef IPSTEALTH
	}
#endif

	sin = (struct sockaddr_in *)&ipforward_rt.ro_dst;
	if ((rt = ipforward_rt.ro_rt) == 0 ||
	    ip->ip_dst.s_addr != sin->sin_addr.s_addr) {
		if (ipforward_rt.ro_rt) {
			RTFREE(ipforward_rt.ro_rt);
			ipforward_rt.ro_rt = 0;
		}
		sin->sin_family = AF_INET;
		sin->sin_len = sizeof(*sin);
		sin->sin_addr = ip->ip_dst;

		rtalloc_ign(&ipforward_rt, RTF_PRCLONING);
		if (ipforward_rt.ro_rt == 0) {
			icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, dest, 0);
			return;
		}
		rt = ipforward_rt.ro_rt;
	}

	/*
	 * Save the IP header and at most 8 bytes of the payload,
	 * in case we need to generate an ICMP message to the src.
	 *
	 * We don't use m_copy() because it might return a reference
	 * to a shared cluster. Both this function and ip_output()
	 * assume exclusive access to the IP header in `m', so any
	 * data in a cluster may change before we reach icmp_error().
	 */
	MGET(mcopy, M_DONTWAIT, m->m_type);
	if (mcopy != NULL) {
		M_COPY_PKTHDR(mcopy, m);
		mcopy->m_len = imin((IP_VHL_HL(ip->ip_vhl) << 2) + 8,
		    (int)ip->ip_len);
		m_copydata(m, 0, mcopy->m_len, mtod(mcopy, caddr_t));
	}

#ifdef IPSTEALTH
	if (!ipstealth) {
#endif
		ip->ip_ttl -= IPTTLDEC;
#ifdef IPSTEALTH
	}
#endif

	/*
	 * If forwarding packet using same interface that it came in on,
	 * perhaps should send a redirect to sender to shortcut a hop.
	 * Only send redirect if source is sending directly to us,
	 * and if packet was not source routed (or has any options).
	 * Also, don't send redirect if forwarding using a default route
	 * or a route modified by a redirect.
	 */
#define	satosin(sa)	((struct sockaddr_in *)(sa))
	if (rt->rt_ifp == m->m_pkthdr.rcvif &&
	    (rt->rt_flags & (RTF_DYNAMIC|RTF_MODIFIED)) == 0 &&
	    satosin(rt_key(rt))->sin_addr.s_addr != 0 &&
	    ipsendredirects && !srcrt) {
#define	RTA(rt)	((struct in_ifaddr *)(rt->rt_ifa))
		u_long src = ntohl(ip->ip_src.s_addr);

		if (RTA(rt) &&
		    (src & RTA(rt)->ia_subnetmask) == RTA(rt)->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;
#ifdef DIAGNOSTIC
		    if (ipprintfs)
		        printf("redirect (%d) to %lx\n", code, (u_long)dest);
#endif
		}
	}

	error = ip_output(m, (struct mbuf *)0, &ipforward_rt, 
			  IP_FORWARDING, 0);
	if (error)
		ipstat.ips_cantforward++;
	else {
		ipstat.ips_forward++;
		if (type)
			ipstat.ips_redirectsent++;
		else {
			if (mcopy) {
				ipflow_create(&ipforward_rt, mcopy);
				m_freem(mcopy);
			}
			return;
		}
	}
	if (mcopy == NULL)
		return;
	destifp = NULL;

	switch (error) {

	case 0:				/* forwarded, but need redirect */
		/* type, code set above */
		break;

	case ENETUNREACH:		/* shouldn't happen, checked above */
	case EHOSTUNREACH:
	case ENETDOWN:
	case EHOSTDOWN:
	default:
		type = ICMP_UNREACH;
		code = ICMP_UNREACH_HOST;
		break;

	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 = NULL;
			int ipsecerror;
			int ipsechdr;
			struct route *ro;

			sp = ipsec4_getpolicybyaddr(mcopy,
						    IPSEC_DIR_OUTBOUND,
			                            IP_FORWARDING,
			                            &ipsecerror);

			if (sp == NULL)
				destifp = ipforward_rt.ro_rt->rt_ifp;
			else {
				/* count IPsec header size */
				ipsechdr = ipsec4_hdrsiz(mcopy,
							 IPSEC_DIR_OUTBOUND,
							 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->sav != NULL
				 && sp->req->sav->sah != NULL) {
					ro = &sp->req->sav->sah->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;

	case ENOBUFS:
#ifdef ALTQ
		/*
		 * don't generate ICMP_SOURCEQUENCH
		 * (RFC1812 Requirements for IP Version 4 Routers)
		 */
		if (mcopy)
			m_freem(mcopy);
		return;
#else
		type = ICMP_SOURCEQUENCH;
		code = 0;
		break;
#endif

	case EACCES:			/* ipfw denied packet */
		m_freem(mcopy);
		return;
	}
	icmp_error(mcopy, type, code, dest, destifp);
}

void
ip_savecontrol(inp, mp, ip, m)
	register struct inpcb *inp;
	register struct mbuf **mp;
	register struct ip *ip;
	register struct mbuf *m;
{
	if (inp->inp_socket->so_options & SO_TIMESTAMP) {
		struct timeval tv;

		microtime(&tv);
		*mp = sbcreatecontrol((caddr_t) &tv, sizeof(tv),
			SCM_TIMESTAMP, SOL_SOCKET);
		if (*mp)
			mp = &(*mp)->m_next;
	}
	if (inp->inp_flags & INP_RECVDSTADDR) {
		*mp = sbcreatecontrol((caddr_t) &ip->ip_dst,
		    sizeof(struct in_addr), IP_RECVDSTADDR, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
#ifdef notyet
	/* XXX
	 * Moving these out of udp_input() made them even more broken
	 * than they already were.
	 */
	/* options were tossed already */
	if (inp->inp_flags & INP_RECVOPTS) {
		*mp = sbcreatecontrol((caddr_t) opts_deleted_above,
		    sizeof(struct in_addr), IP_RECVOPTS, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
	/* ip_srcroute doesn't do what we want here, need to fix */
	if (inp->inp_flags & INP_RECVRETOPTS) {
		*mp = sbcreatecontrol((caddr_t) ip_srcroute(),
		    sizeof(struct in_addr), IP_RECVRETOPTS, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
#endif
	if (inp->inp_flags & INP_RECVIF) {
		struct ifnet *ifp;
		struct sdlbuf {
			struct sockaddr_dl sdl;
			u_char	pad[32];
		} sdlbuf;
		struct sockaddr_dl *sdp;
		struct sockaddr_dl *sdl2 = &sdlbuf.sdl;

		if (((ifp = m->m_pkthdr.rcvif)) 
		&& ( ifp->if_index && (ifp->if_index <= if_index))) {
			sdp = (struct sockaddr_dl *)(ifnet_addrs
					[ifp->if_index - 1]->ifa_addr);
			/*
			 * Change our mind and don't try copy.
			 */
			if ((sdp->sdl_family != AF_LINK)
			|| (sdp->sdl_len > sizeof(sdlbuf))) {
				goto makedummy;
			}
			bcopy(sdp, sdl2, sdp->sdl_len);
		} else {
makedummy:	
			sdl2->sdl_len
				= offsetof(struct sockaddr_dl, sdl_data[0]);
			sdl2->sdl_family = AF_LINK;
			sdl2->sdl_index = 0;
			sdl2->sdl_nlen = sdl2->sdl_alen = sdl2->sdl_slen = 0;
		}
		*mp = sbcreatecontrol((caddr_t) sdl2, sdl2->sdl_len,
			IP_RECVIF, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
}

int
ip_rsvp_init(struct socket *so)
{
	if (so->so_type != SOCK_RAW ||
	    so->so_proto->pr_protocol != IPPROTO_RSVP)
	  return EOPNOTSUPP;

	if (ip_rsvpd != NULL)
	  return EADDRINUSE;

	ip_rsvpd = so;
	/*
	 * This may seem silly, but we need to be sure we don't over-increment
	 * the RSVP counter, in case something slips up.
	 */
	if (!ip_rsvp_on) {
		ip_rsvp_on = 1;
		rsvp_on++;
	}

	return 0;
}

int
ip_rsvp_done(void)
{
	ip_rsvpd = NULL;
	/*
	 * This may seem silly, but we need to be sure we don't over-decrement
	 * the RSVP counter, in case something slips up.
	 */
	if (ip_rsvp_on) {
		ip_rsvp_on = 0;
		rsvp_on--;
	}
	return 0;
}