ip_input.c

RTEMS (Real-Time Executive for Multiprocessor Systems) is a free open source real-time operating sys

/*
 * 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
 * $Id: ip_input.c,v 1.4 2002/10/04 14:47:11 joel Exp $
 *	$ANA: ip_input.c,v 1.5 1996/09/18 14:34:59 wollman Exp $
 */

#define	_IP_VHL

#include "opt_ipfw.h"

#include <stddef.h>

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/errno.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/syslog.h>
#include <sys/sysctl.h>

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

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

#include <sys/socketvar.h>

#ifdef IPFIREWALL
#include <netinet/ip_fw.h>
#endif

int rsvp_on = 0;
static int ip_rsvp_on;
struct socket *ip_rsvpd;

int	ipforwarding = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_FORWARDING, forwarding, CTLFLAG_RW,
	&ipforwarding, 0, "");

static int	ipsendredirects = 1; /* XXX */
SYSCTL_INT(_net_inet_ip, IPCTL_SENDREDIRECTS, redirect, CTLFLAG_RW,
	&ipsendredirects, 0, "");

int	ip_defttl = IPDEFTTL;
SYSCTL_INT(_net_inet_ip, IPCTL_DEFTTL, ttl, CTLFLAG_RW,
	&ip_defttl, 0, "");

static int	ip_dosourceroute = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_SOURCEROUTE, sourceroute, CTLFLAG_RW,
	&ip_dosourceroute, 0, "");

static int	ip_acceptsourceroute = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_ACCEPTSOURCEROUTE, accept_sourceroute,
	CTLFLAG_RW, &ip_acceptsourceroute, 0, "");
#ifdef DIAGNOSTIC
static int	ipprintfs = 0;
#endif

extern	struct domain inetdomain;
extern	struct protosw inetsw[];
u_char	ip_protox[IPPROTO_MAX];
static int	ipqmaxlen = IFQ_MAXLEN;
struct	in_ifaddr *in_ifaddr;			/* first inet address */
struct	ifqueue ipintrq;
SYSCTL_INT(_net_inet_ip, IPCTL_INTRQMAXLEN, intr_queue_maxlen, CTLFLAG_RD,
	&ipintrq.ifq_maxlen, 0, "");
SYSCTL_INT(_net_inet_ip, IPCTL_INTRQDROPS, intr_queue_drops, CTLFLAG_RD,
	&ipintrq.ifq_drops, 0, "");

struct ipstat ipstat;

/* Packet reassembly stuff */
#define IPREASS_NHASH_LOG2      6
#define IPREASS_NHASH           (1 << IPREASS_NHASH_LOG2)
#define IPREASS_HMASK           (IPREASS_NHASH - 1)
#define IPREASS_HASH(x,y) \
	(((((x) & 0xF) | ((((x) >> 8) & 0xF) << 4)) ^ (y)) & IPREASS_HMASK)

static struct ipq ipq[IPREASS_NHASH];
static int    nipq = 0;         /* total # of reass queues */
static int    maxnipq;

#ifdef IPCTL_DEFMTU
SYSCTL_INT(_net_inet_ip, IPCTL_DEFMTU, mtu, CTLFLAG_RW,
	&ip_mtu, 0, "");
#endif

#if !defined(COMPAT_IPFW) || COMPAT_IPFW == 1
#undef COMPAT_IPFW
#define COMPAT_IPFW 1
#else
#undef COMPAT_IPFW
#endif

#ifdef COMPAT_IPFW
/* Firewall hooks */
ip_fw_chk_t *ip_fw_chk_ptr;
ip_fw_ctl_t *ip_fw_ctl_ptr;

/* IP Network Address Translation (NAT) hooks */ 
ip_nat_t *ip_nat_ptr;
ip_nat_ctl_t *ip_nat_ctl_ptr;
#endif

/*
 * We need to save the IP options in case a protocol wants to respond
 * to an incoming packet over the same route if the packet got here
 * using IP source routing.  This allows connection establishment and
 * maintenance when the remote end is on a network that is not known
 * to us.
 */
static int	ip_nhops = 0;
static	struct ip_srcrt {
	struct	in_addr dst;			/* final destination */
	char	nop;				/* one NOP to align */
	char	srcopt[IPOPT_OFFSET + 1];	/* OPTVAL, OLEN and OFFSET */
	struct	in_addr route[MAX_IPOPTLEN/sizeof(struct in_addr)];
} ip_srcrt;

#ifdef IPDIVERT
/*
 * Shared variable between ip_input() and ip_reass() to communicate
 * about which packets, once assembled from fragments, get diverted,
 * and to which port.
 */
static u_short	frag_divert_port;
#endif

static void save_rte __P((u_char *, struct in_addr));
static void	 ip_deq __P((struct ipasfrag *));
static int	 ip_dooptions __P((struct mbuf *));
static void	 ip_enq __P((struct ipasfrag *, struct ipasfrag *));
static void	 ip_forward __P((struct mbuf *, int));
static void	 ip_freef __P((struct ipq *));
static struct ip *
	 ip_reass __P((struct ipasfrag *, struct ipq *, struct ipq *));
static struct in_ifaddr *
	 ip_rtaddr __P((struct in_addr));
void	ipintr __P((void));
/*
 * IP initialization: fill in IP protocol switch table.
 * All protocols not implemented in kernel go to raw IP protocol handler.
 */
void
ip_init()
{
	register struct protosw *pr;
	register int i;

	pr = pffindproto(PF_INET, IPPROTO_RAW, SOCK_RAW);
	if (pr == 0)
		panic("ip_init");
	for (i = 0; i < IPPROTO_MAX; i++)
		ip_protox[i] = pr - inetsw;
	for (pr = inetdomain.dom_protosw;
	    pr < inetdomain.dom_protoswNPROTOSW; pr++)
		if (pr->pr_domain->dom_family == PF_INET &&
		    pr->pr_protocol && pr->pr_protocol != IPPROTO_RAW)
			ip_protox[pr->pr_protocol] = pr - inetsw;

	for (i = 0; i < IPREASS_NHASH; i++)
	    ipq[i].next = ipq[i].prev = &ipq[i];

	maxnipq = nmbclusters/4;

	ip_id = rtems_bsdnet_seconds_since_boot() & 0xffff;
	ipintrq.ifq_maxlen = ipqmaxlen;
#ifdef IPFIREWALL
	ip_fw_init();
#endif
#ifdef IPNAT
        ip_nat_init(); 
#endif

}

static struct	sockaddr_in ipaddr = { sizeof(ipaddr), AF_INET };
static struct	route ipforward_rt;

/*
 * Ip input routine.  Checksum and byte swap header.  If fragmented
 * try to reassemble.  Process options.  Pass to next level.
 */
void
ip_input(struct mbuf *m)
{
	struct ip *ip;
	struct ipq *fp;
	struct in_ifaddr *ia;
	int    i, hlen;
	u_short sum;

#ifdef	DIAGNOSTIC
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("ip_input no HDR");
#endif
	/*
	 * If no IP addresses have been set yet but the interfaces
	 * are receiving, can't do anything with incoming packets yet.
	 */
	if (in_ifaddr == NULL)
		goto bad;
	ipstat.ips_total++;

	if (m->m_pkthdr.len < sizeof(struct ip))
		goto tooshort;

#if defined(DIAGNOSTIC) && defined(ORIGINAL_FREEBSD_CODE)
	if (m->m_len < sizeof(struct ip))
		panic("ipintr mbuf too short");
#endif

	if (m->m_len < sizeof (struct ip) &&
	    (m = m_pullup(m, sizeof (struct ip))) == 0) {
		ipstat.ips_toosmall++;
		return;
	}
	ip = mtod(m, struct ip *);

	if (IP_VHL_V(ip->ip_vhl) != IPVERSION) {
		ipstat.ips_badvers++;
		goto bad;
	}

	hlen = IP_VHL_HL(ip->ip_vhl) << 2;
	if (hlen < sizeof(struct ip)) {	/* minimum header length */
		ipstat.ips_badhlen++;
		goto bad;
	}
	if (hlen > m->m_len) {
		if ((m = m_pullup(m, hlen)) == 0) {
			ipstat.ips_badhlen++;
			return;
		}
		ip = mtod(m, struct ip *);
	}
	if (hlen == sizeof(struct ip)) {
		sum = in_cksum_hdr(ip);
	} else {
		sum = in_cksum(m, hlen);
	}
	if (sum) {
		ipstat.ips_badsum++;
		goto bad;
	}

	/*
	 * Convert fields to host representation.
	 */
	NTOHS(ip->ip_len);
	if (ip->ip_len < hlen) {
		ipstat.ips_badlen++;
		goto bad;
	}
	NTOHS(ip->ip_id);
	NTOHS(ip->ip_off);

	/*
	 * 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.
	 * Drop packet if shorter than we expect.
	 */
	if (m->m_pkthdr.len < ip->ip_len) {
tooshort:
		ipstat.ips_tooshort++;
		goto bad;
	}
	if (m->m_pkthdr.len > ip->ip_len) {
		if (m->m_len == m->m_pkthdr.len) {
			m->m_len = ip->ip_len;
			m->m_pkthdr.len = ip->ip_len;
		} else
			m_adj(m, ip->ip_len - m->m_pkthdr.len);
	}
	/*
	 * IpHack's section.
	 * Right now when no processing on packet has done
	 * and it is still fresh out of network we do our black
	 * deals with it.
	 * - Firewall: deny/allow/divert
	 * - Xlate: translate packet's addr/port (NAT).
	 * - Wrap: fake packet's addr/port <unimpl.>
	 * - Encapsulate: put it in another IP and send out. <unimp.>
 	 */

#ifdef COMPAT_IPFW
	if (ip_fw_chk_ptr) {
#ifdef IPDIVERT
		u_short port;

		port = (*ip_fw_chk_ptr)(&ip, hlen, NULL, ip_divert_ignore, &m);
		ip_divert_ignore = 0;
		if (port) {			/* Divert packet */
			frag_divert_port = port;
			goto ours;
		}
#else
		/* If ipfw says divert, we have to just drop packet */
		if ((*ip_fw_chk_ptr)(&ip, hlen, NULL, 0, &m)) {
			m_freem(m);
			m = NULL;
		}
#endif
		if (!m)
			return;
	}

        if (ip_nat_ptr && !(*ip_nat_ptr)(&ip, &m, m->m_pkthdr.rcvif, IP_NAT_IN))
		return;
#endif

	/*
	 * Process options and, if not destined for us,
	 * ship it on.  ip_dooptions returns 1 when an
	 * error was detected (causing an icmp message
	 * to be sent and the original packet to be freed).
	 */
	ip_nhops = 0;		/* for source routed packets */
	if (hlen > sizeof (struct ip) && ip_dooptions(m))
		return;

        /* greedy RSVP, snatches any PATH packet of the RSVP protocol and no
         * matter if it is destined to another node, or whether it is 
         * a multicast one, RSVP wants it! and prevents it from being forwarded
         * anywhere else. Also checks if the rsvp daemon is running before
	 * grabbing the packet.
         */
	if (rsvp_on && ip->ip_p==IPPROTO_RSVP) 
		goto ours;

	/*
	 * Check our list of addresses, to see if the packet is for us.
	 */
	for (ia = in_ifaddr; ia; ia = ia->ia_next) {
#define	satosin(sa)	((struct sockaddr_in *)(sa))

		if (IA_SIN(ia)->sin_addr.s_addr == ip->ip_dst.s_addr)
			goto ours;
#ifdef BOOTP_COMPAT
		if (IA_SIN(ia)->sin_addr.s_addr == INADDR_ANY)
			goto ours;
#endif
		if (ia->ia_ifp && ia->ia_ifp->if_flags & IFF_BROADCAST) {
			if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
			    ip->ip_dst.s_addr)
				goto ours;
			if (ip->ip_dst.s_addr == ia->ia_netbroadcast.s_addr)
				goto ours;
		}
	}
	if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
		struct in_multi *inm;
		if (ip_mrouter) {
			/*
			 * If we are acting as a multicast router, all
			 * incoming multicast packets are passed to the
			 * kernel-level multicast forwarding function.
			 * The packet is returned (relatively) intact; if
			 * ip_mforward() returns a non-zero value, the packet
			 * must be discarded, else it may be accepted below.
			 *
			 * (The IP ident field is put in the same byte order
			 * as expected when ip_mforward() is called from
			 * ip_output().)
			 */
			ip->ip_id = htons(ip->ip_id);
			if (ip_mforward(ip, m->m_pkthdr.rcvif, m, 0) != 0) {
				ipstat.ips_cantforward++;
				m_freem(m);
				return;
			}
			ip->ip_id = ntohs(ip->ip_id);

			/*
			 * The process-level routing demon needs to receive
			 * all multicast IGMP packets, whether or not this
			 * host belongs to their destination groups.
			 */
			if (ip->ip_p == IPPROTO_IGMP)
				goto ours;
			ipstat.ips_forward++;
		}
		/*
		 * See if we belong to the destination multicast group on the
		 * arrival interface.
		 */
		IN_LOOKUP_MULTI(ip->ip_dst, m->m_pkthdr.rcvif, inm);
		if (inm == NULL) {
			ipstat.ips_cantforward++;
			m_freem(m);
			return;
		}
		goto ours;
	}
	if (ip->ip_dst.s_addr == (u_long)INADDR_BROADCAST)
		goto ours;
	if (ip->ip_dst.s_addr == INADDR_ANY)
		goto ours;

	/*
	 * Not for us; forward if possible and desirable.
	 */
	if (ipforwarding == 0) {
		ipstat.ips_cantforward++;
		m_freem(m);
	} else
		ip_forward(m, 0);
	return;

ours:

	/*
	 * If offset or IP_MF are set, must reassemble.
	 * Otherwise, nothing need be done.
	 * (We could look in the reassembly queue to see
	 * if the packet was previously fragmented,
	 * but it's not worth the time; just let them time out.)
	 */
	if (ip->ip_off &~ (IP_DF | IP_RF)) {
		if (m->m_flags & M_EXT) {		/* XXX */
			if ((m = m_pullup(m, sizeof (struct ip))) == 0) {
				ipstat.ips_toosmall++;
#ifdef IPDIVERT
				frag_divert_port = 0;
#endif
				return;
			}
			ip = mtod(m, struct ip *);
		}
		sum = IPREASS_HASH(ip->ip_src.s_addr, ip->ip_id);
		/*
		 * Look for queue of fragments
		 * of this datagram.
		 */
		for (fp = ipq[sum].next; fp != &ipq[sum]; fp = fp->next)
			if (ip->ip_id == fp->ipq_id &&
			    ip->ip_src.s_addr == fp->ipq_src.s_addr &&
			    ip->ip_dst.s_addr == fp->ipq_dst.s_addr &&
			    ip->ip_p == fp->ipq_p)
				goto found;

		fp = 0;

		/* check if there's a place for the new queue */
		if (nipq > maxnipq) {
		    /*
		     * drop something from the tail of the current queue
		     * before proceeding further
		     */
		    if (ipq[sum].prev == &ipq[sum]) {   /* gak */