ip_icmp.c

eCos/RedBoot for勤研ARM AnywhereII(4510) 含全部源代码

//==========================================================================
//
//      src/sys/netinet/ip_icmp.c
//
//==========================================================================
//####BSDCOPYRIGHTBEGIN####
//
// -------------------------------------------
//
// Portions of this software may have been derived from OpenBSD, 
// FreeBSD or other sources, and are covered by the appropriate
// copyright disclaimers included herein.
//
// Portions created by Red Hat are
// Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
//
// -------------------------------------------
//
//####BSDCOPYRIGHTEND####
//==========================================================================

/*
 * 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_icmp.c	8.2 (Berkeley) 1/4/94
 * $FreeBSD: src/sys/netinet/ip_icmp.c,v 1.39.2.9 2001/07/03 11:01:46 ume Exp $
 */

#include <sys/param.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/sysctl.h>

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

#define _IP_VHL
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#include <netinet/ip_var.h>
#include <netinet/icmp_var.h>

#ifdef IPSEC
#include <netinet6/ipsec.h>
#include <netkey/key.h>
#endif

/*
 * ICMP routines: error generation, receive packet processing, and
 * routines to turnaround packets back to the originator, and
 * host table maintenance routines.
 */

struct	icmpstat icmpstat;
SYSCTL_STRUCT(_net_inet_icmp, ICMPCTL_STATS, stats, CTLFLAG_RD,
	&icmpstat, icmpstat, "");

static int	icmpmaskrepl = 0;
SYSCTL_INT(_net_inet_icmp, ICMPCTL_MASKREPL, maskrepl, CTLFLAG_RW,
	&icmpmaskrepl, 0, "");

static int	drop_redirect = 0;
SYSCTL_INT(_net_inet_icmp, OID_AUTO, drop_redirect, CTLFLAG_RW, 
	&drop_redirect, 0, "");

static int	log_redirect = 0;
SYSCTL_INT(_net_inet_icmp, OID_AUTO, log_redirect, CTLFLAG_RW, 
	&log_redirect, 0, "");

#ifdef ICMP_BANDLIM 
 
/*    
 * ICMP error-response bandwidth limiting sysctl.  If not enabled, sysctl
 *      variable content is -1 and read-only.
 */     
    
static int      icmplim = 200;
SYSCTL_INT(_net_inet_icmp, ICMPCTL_ICMPLIM, icmplim, CTLFLAG_RW,
	&icmplim, 0, "");
#else

#ifdef CYGPKG_NET_FREEBSD_SYSCTL
static int      icmplim = -1;
SYSCTL_INT(_net_inet_icmp, ICMPCTL_ICMPLIM, icmplim, CTLFLAG_RD,
	&icmplim, 0, "");
#endif	
#endif
/*
 * ICMP broadcast echo sysctl
 */

static int	icmpbmcastecho = 0;
SYSCTL_INT(_net_inet_icmp, OID_AUTO, bmcastecho, CTLFLAG_RW,
	&icmpbmcastecho, 0, "");


#ifdef ICMPPRINTFS
int	icmpprintfs = 0;
#endif

static void	icmp_reflect __P((struct mbuf *));
static void	icmp_send __P((struct mbuf *, struct mbuf *));
static int	ip_next_mtu __P((int, int));

extern	struct protosw inetsw[];

/*
 * Generate an error packet of type error
 * in response to bad packet ip.
 */
void
icmp_error(n, type, code, dest, destifp)
	struct mbuf *n;
	int type, code;
	n_long dest;
	struct ifnet *destifp;
{
	register struct ip *oip = mtod(n, struct ip *), *nip;
	register unsigned oiplen = IP_VHL_HL(oip->ip_vhl) << 2;
	register struct icmp *icp;
	register struct mbuf *m;
	unsigned icmplen;

#ifdef ICMPPRINTFS
	if (icmpprintfs)
		printf("icmp_error(%p, %x, %d)\n", oip, type, code);
#endif
	if (type != ICMP_REDIRECT)
		icmpstat.icps_error++;
	/*
	 * Don't send error if not the first fragment of message.
	 * Don't error if the old packet protocol was ICMP
	 * error message, only known informational types.
	 */
	if (oip->ip_off &~ (IP_MF|IP_DF))
		goto freeit;
	if (oip->ip_p == IPPROTO_ICMP && type != ICMP_REDIRECT &&
	  n->m_len >= oiplen + ICMP_MINLEN &&
	  !ICMP_INFOTYPE(((struct icmp *)((caddr_t)oip + oiplen))->icmp_type)) {
		icmpstat.icps_oldicmp++;
		goto freeit;
	}
	/* Don't send error in response to a multicast or broadcast packet */
	if (n->m_flags & (M_BCAST|M_MCAST))
		goto freeit;
	/*
	 * First, formulate icmp message
	 */
	m = m_gethdr(M_DONTWAIT, MT_HEADER);
	if (m == NULL)
		goto freeit;
	icmplen = min(oiplen + 8, oip->ip_len);
	if (icmplen < sizeof(struct ip)) {
		printf("icmp_error: bad length\n");
		m_free(m);
		goto freeit;
	}
	m->m_len = icmplen + ICMP_MINLEN;
	MH_ALIGN(m, m->m_len);
	icp = mtod(m, struct icmp *);
	if ((u_int)type > ICMP_MAXTYPE)
		panic("icmp_error");
	icmpstat.icps_outhist[type]++;
	icp->icmp_type = type;
	if (type == ICMP_REDIRECT)
		icp->icmp_gwaddr.s_addr = dest;
	else {
		icp->icmp_void = 0;
		/*
		 * The following assignments assume an overlay with the
		 * zeroed icmp_void field.
		 */
		if (type == ICMP_PARAMPROB) {
			icp->icmp_pptr = code;
			code = 0;
		} else if (type == ICMP_UNREACH &&
			code == ICMP_UNREACH_NEEDFRAG && destifp) {
			icp->icmp_nextmtu = htons(destifp->if_mtu);
		}
	}

	icp->icmp_code = code;
	m_copydata(n, 0, icmplen, (caddr_t)&icp->icmp_ip);
	nip = &icp->icmp_ip;

	/*
	 * Convert fields to network representation.
	 */
	HTONS(nip->ip_len);
	HTONS(nip->ip_off);

	/*
	 * Now, copy old ip header (without options)
	 * in front of icmp message.
	 */
	if (m->m_data - sizeof(struct ip) < m->m_pktdat)
		panic("icmp len");
	m->m_data -= sizeof(struct ip);
	m->m_len += sizeof(struct ip);
	m->m_pkthdr.len = m->m_len;
	m->m_pkthdr.rcvif = n->m_pkthdr.rcvif;
	nip = mtod(m, struct ip *);
	bcopy((caddr_t)oip, (caddr_t)nip, sizeof(struct ip));
	nip->ip_len = m->m_len;
	nip->ip_vhl = IP_VHL_BORING;
	nip->ip_p = IPPROTO_ICMP;
	nip->ip_tos = 0;
	icmp_reflect(m);

freeit:
	m_freem(n);
}

static struct sockaddr_in icmpsrc = { sizeof (struct sockaddr_in), AF_INET };
static struct sockaddr_in icmpdst = { sizeof (struct sockaddr_in), AF_INET };
static struct sockaddr_in icmpgw = { sizeof (struct sockaddr_in), AF_INET };

/*
 * Process a received ICMP message.
 */
void
icmp_input(m, off)
	register struct mbuf *m;
	int off;
{
	int hlen = off;
	register struct icmp *icp;
	register struct ip *ip = mtod(m, struct ip *);
	int icmplen = ip->ip_len;
	register int i;
	struct in_ifaddr *ia;
	void (*ctlfunc) __P((int, struct sockaddr *, void *));
	int code;

	/*
	 * Locate icmp structure in mbuf, and check
	 * that not corrupted and of at least minimum length.
	 */
#ifdef ICMPPRINTFS
	if (icmpprintfs) {
		char buf[4 * sizeof "123"];
		strcpy(buf, inet_ntoa(ip->ip_src));
		printf("icmp_input from %s to %s, len %d\n",
		       buf, inet_ntoa(ip->ip_dst), icmplen);
	}
#endif
	if (icmplen < ICMP_MINLEN) {
		icmpstat.icps_tooshort++;
		goto freeit;
	}
	i = hlen + min(icmplen, ICMP_ADVLENMIN);
	if (m->m_len < i && (m = m_pullup(m, i)) == 0)  {
		icmpstat.icps_tooshort++;
		return;
	}
	ip = mtod(m, struct ip *);
	m->m_len -= hlen;
	m->m_data += hlen;
	icp = mtod(m, struct icmp *);
	if (in_cksum(m, icmplen)) {
		icmpstat.icps_checksum++;
		goto freeit;
	}
	m->m_len += hlen;
	m->m_data -= hlen;

#if defined(NFAITH) && 0 < NFAITH
	if (m->m_pkthdr.rcvif && m->m_pkthdr.rcvif->if_type == IFT_FAITH) {
		/*
		 * Deliver very specific ICMP type only.
		 */
		switch (icp->icmp_type) {
		case ICMP_UNREACH:
		case ICMP_TIMXCEED:
			break;
		default:
			goto freeit;
		}
	}
#endif

#ifdef ICMPPRINTFS
	if (icmpprintfs)
		printf("icmp_input, type %d code %d\n", icp->icmp_type,
		    icp->icmp_code);
#endif

	/*
	 * Message type specific processing.
	 */
	if (icp->icmp_type > ICMP_MAXTYPE)
		goto raw;
	icmpstat.icps_inhist[icp->icmp_type]++;
	code = icp->icmp_code;
	switch (icp->icmp_type) {

	case ICMP_UNREACH:
		switch (code) {
			case ICMP_UNREACH_NET:
			case ICMP_UNREACH_HOST:
			case ICMP_UNREACH_SRCFAIL:
			case ICMP_UNREACH_NET_UNKNOWN:
			case ICMP_UNREACH_HOST_UNKNOWN:
			case ICMP_UNREACH_ISOLATED:
			case ICMP_UNREACH_TOSNET:
			case ICMP_UNREACH_TOSHOST:
			case ICMP_UNREACH_HOST_PRECEDENCE:
			case ICMP_UNREACH_PRECEDENCE_CUTOFF:
				code = PRC_UNREACH_NET;
				break;

			case ICMP_UNREACH_NEEDFRAG:
				code = PRC_MSGSIZE;
				break;

			/*
			 * RFC 1122, Sections 3.2.2.1 and 4.2.3.9.
			 * Treat subcodes 2,3 as immediate RST
			 */
			case ICMP_UNREACH_PROTOCOL:
			case ICMP_UNREACH_PORT:
				code = PRC_UNREACH_PORT;
				break;

			case ICMP_UNREACH_NET_PROHIB:
			case ICMP_UNREACH_HOST_PROHIB:
			case ICMP_UNREACH_FILTER_PROHIB:
				code = PRC_UNREACH_ADMIN_PROHIB;
				break;

			default:
				goto badcode;
		}
		goto deliver;

	case ICMP_TIMXCEED:
		if (code > 1)
			goto badcode;
		code += PRC_TIMXCEED_INTRANS;
		goto deliver;

	case ICMP_PARAMPROB:
		if (code > 1)
			goto badcode;
		code = PRC_PARAMPROB;
		goto deliver;

	case ICMP_SOURCEQUENCH:
		if (code)
			goto badcode;
		code = PRC_QUENCH;
	deliver:
		/*
		 * Problem with datagram; advise higher level routines.
		 */
		if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
		    IP_VHL_HL(icp->icmp_ip.ip_vhl) < (sizeof(struct ip) >> 2)) {
			icmpstat.icps_badlen++;
			goto freeit;
		}
		NTOHS(icp->icmp_ip.ip_len);
		/* Discard ICMP's in response to multicast packets */
		if (IN_MULTICAST(ntohl(icp->icmp_ip.ip_dst.s_addr)))
			goto badcode;
#ifdef ICMPPRINTFS
		if (icmpprintfs)
			printf("deliver to protocol %d\n", icp->icmp_ip.ip_p);
#endif
		icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
#if 1
		/*
		 * MTU discovery:
		 * If we got a needfrag and there is a host route to the
		 * original destination, and the MTU is not locked, then
		 * set the MTU in the route to the suggested new value
		 * (if given) and then notify as usual.  The ULPs will
		 * notice that the MTU has changed and adapt accordingly.
		 * If no new MTU was suggested, then we guess a new one
		 * less than the current value.  If the new MTU is 
		 * unreasonably small (arbitrarily set at 296), then
		 * we reset the MTU to the interface value and enable the
		 * lock bit, indicating that we are no longer doing MTU
		 * discovery.
		 */
		if (code == PRC_MSGSIZE) {
			struct rtentry *rt;
			int mtu;

			rt = rtalloc1((struct sockaddr *)&icmpsrc, 0,
				      RTF_CLONING | RTF_PRCLONING);
			if (rt && (rt->rt_flags & RTF_HOST)
			    && !(rt->rt_rmx.rmx_locks & RTV_MTU)) {
				mtu = ntohs(icp->icmp_nextmtu);
				if (!mtu)
					mtu = ip_next_mtu(rt->rt_rmx.rmx_mtu,
							  1);
#ifdef DEBUG_MTUDISC
				printf("MTU for %s reduced to %d\n",
					inet_ntoa(icmpsrc.sin_addr), mtu);
#endif
				if (mtu < 296) {
					/* rt->rt_rmx.rmx_mtu =
						rt->rt_ifp->if_mtu; */
					rt->rt_rmx.rmx_locks |= RTV_MTU;
				} else if (rt->rt_rmx.rmx_mtu > mtu) {
					rt->rt_rmx.rmx_mtu = mtu;
				}
			}
			if (rt)
				RTFREE(rt);
		}

#endif
		/*
		 * XXX if the packet contains [IPv4 AH TCP], we can't make a
		 * notification to TCP layer.
		 */