ip_output.c

来自「基于组件方式开发操作系统的OSKIT源代码」· C语言 代码 · 共 1,566 行 · 第 1/3 页

/*
 * 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
 *	$Id: ip_output.c,v 1.85.2.3 1999/05/04 16:24:00 luigi Exp $
 */

#define _IP_VHL

#include "opt_ipfw.h"
#include "opt_ipdn.h"
#include "opt_ipdivert.h"
#include "opt_ipfilter.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>

#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/in_cksum.h>

static MALLOC_DEFINE(M_IPMOPTS, "ip_moptions", "internet multicast options");

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

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

#ifdef DUMMYNET
#include <netinet/ip_dummynet.h>
#endif

#ifdef IPFIREWALL_FORWARD_DEBUG
#define print_ip(a)	 printf("%ld.%ld.%ld.%ld",(ntohl(a.s_addr)>>24)&0xFF,\
				 		  (ntohl(a.s_addr)>>16)&0xFF,\
						  (ntohl(a.s_addr)>>8)&0xFF,\
						  (ntohl(a.s_addr))&0xFF);
#endif

u_short ip_id;

static struct mbuf *ip_insertoptions __P((struct mbuf *, struct mbuf *, int *));
static void	ip_mloopback
	__P((struct ifnet *, struct mbuf *, struct sockaddr_in *, int));
static int	ip_getmoptions
	__P((struct sockopt *, struct ip_moptions *));
static int	ip_pcbopts __P((int, struct mbuf **, struct mbuf *));
static int	ip_setmoptions
	__P((struct sockopt *, struct ip_moptions **));

#if defined(IPFILTER_LKM) || defined(IPFILTER)
int	ip_optcopy __P((struct ip *, struct ip *));
extern int (*fr_checkp) __P((struct ip *, int, struct ifnet *, int, struct mbuf **));
#else
static int	ip_optcopy __P((struct ip *, struct ip *));
#endif


extern	struct protosw inetsw[];

/*
 * 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
ip_output(m0, opt, ro, flags, imo)
	struct mbuf *m0;
	struct mbuf *opt;
	struct route *ro;
	int flags;
	struct ip_moptions *imo;
{
	struct ip *ip, *mhip;
	struct ifnet *ifp;
	struct mbuf *m = m0;
	int hlen = sizeof (struct ip);
	int len, off, error = 0;
	struct sockaddr_in *dst;
	struct in_ifaddr *ia;
	int isbroadcast;
#ifdef IPFIREWALL_FORWARD
	int fwd_rewrite_src = 0;
#endif

#ifndef IPDIVERT /* dummy variable for the firewall code to play with */
        u_short ip_divert_cookie = 0 ;
#endif
#ifdef COMPAT_IPFW
	struct ip_fw_chain *rule = NULL ;
#endif

#if defined(IPFIREWALL) && defined(DUMMYNET)
        /*  
         * dummynet packet are prepended a vestigial mbuf with
         * m_type = MT_DUMMYNET and m_data pointing to the matching
         * rule.
         */ 
        if (m->m_type == MT_DUMMYNET) {
            /*
             * the packet was already tagged, so part of the
             * processing was already done, and we need to go down.
             * opt, flags and imo have already been used, and now
             * they are used to hold ifp, dst and NULL, respectively.
             */
            rule = (struct ip_fw_chain *)(m->m_data) ;
            m0 = m = m->m_next ;
            ip = mtod(m, struct ip *);
            dst = (struct sockaddr_in *)flags;
            ifp = (struct ifnet *)opt;
            hlen = IP_VHL_HL(ip->ip_vhl) << 2 ;
            opt = NULL ;
            flags = 0 ; /* XXX is this correct ? */
            goto sendit;
        } else
            rule = NULL ;
#endif

#ifdef	DIAGNOSTIC
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("ip_output no HDR");
	if (!ro)
		panic("ip_output no route, proto = %d",
		      mtod(m, struct ip *)->ip_p);
#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_vhl = IP_MAKE_VHL(IPVERSION, hlen >> 2);
		ip->ip_off &= IP_DF;
		ip->ip_id = htons(ip_id++);
		ipstat.ips_localout++;
	} else {
		hlen = IP_VHL_HL(ip->ip_vhl) << 2;
	}

	dst = (struct sockaddr_in *)&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.
	 */
#define ifatoia(ifa)	((struct in_ifaddr *)(ifa))
#define sintosa(sin)	((struct sockaddr *)(sin))
	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;
		isbroadcast = in_broadcast(dst->sin_addr, ifp);
	} else {
		/*
		 * If this is the case, we probably don't want to allocate
		 * a protocol-cloned route since we didn't get one from the
		 * ULP.  This lets TCP do its thing, while not burdening
		 * forwarding or ICMP with the overhead of cloning a route.
		 * Of course, we still want to do any cloning requested by
		 * the link layer, as this is probably required in all cases
		 * for correct operation (as it is for ARP).
		 */
		if (ro->ro_rt == 0)
			rtalloc_ign(ro, RTF_PRCLONING);
		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 = (struct sockaddr_in *)ro->ro_rt->rt_gateway;
		if (ro->ro_rt->rt_flags & RTF_HOST)
			isbroadcast = (ro->ro_rt->rt_flags & RTF_BROADCAST);
		else
			isbroadcast = in_broadcast(dst->sin_addr, ifp);
	}
	if (IN_MULTICAST(ntohl(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 = (struct sockaddr_in *)&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;
			if (imo->imo_multicast_vif != -1)
				ip->ip_src.s_addr =
				    ip_mcast_src(imo->imo_multicast_vif);
		} else
			ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
		/*
		 * Confirm that the outgoing interface supports multicast.
		 */
		if ((imo == NULL) || (imo->imo_multicast_vif == -1)) {
			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 *ia1;

			for (ia1 = in_ifaddrhead.tqh_first; ia1;
			     ia1 = ia1->ia_link.tqe_next)
				if (ia1->ia_ifp == ifp) {
					ip->ip_src = IA_SIN(ia1)->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, hlen);
		}
		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.
			 */
			if (ip_mrouter && (flags & IP_FORWARDING) == 0) {
				/*
				 * Check if rsvp daemon is running. If not, don't
				 * set ip_moptions. This ensures that the packet
				 * is multicast and not just sent down one link
				 * as prescribed by rsvpd.
				 */
				if (!rsvp_on)
				  imo = NULL;
				if (ip_mforward(ip, ifp, m, imo) != 0) {
					m_freem(m);
					goto done;
				}
			}
		}

		/*
		 * 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) {
			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_SIN(ia)->sin_addr;
#ifdef IPFIREWALL_FORWARD
		/* Keep note that we did this - if the firewall changes
		 * the next-hop, our interface may change, changing the
		 * default source IP. It's a shame so much effort happens
		 * twice. Oh well. 
		 */
		fwd_rewrite_src++;
#endif /* IPFIREWALL_FORWARD */
	}
#endif /* notdef */
	/*
	 * Verify that we have any chance at all of being able to queue
	 *      the packet or packet fragments
	 */
	if ((ifp->if_snd.ifq_len + ip->ip_len / ifp->if_mtu + 1) >=
		ifp->if_snd.ifq_maxlen) {
			error = ENOBUFS;
			goto bad;
	}

	/*
	 * Look for broadcast address and
	 * and verify user is allowed to send
	 * such a packet.
	 */
	if (isbroadcast) {
		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_short)ip->ip_len > ifp->if_mtu) {
			error = EMSGSIZE;
			goto bad;
		}
		m->m_flags |= M_BCAST;
	} else {
		m->m_flags &= ~M_BCAST;
	}

sendit:
	/*
	 * IpHack's section.
	 * - Xlate: translate packet's addr/port (NAT).
	 * - Firewall: deny/allow/etc.
	 * - Wrap: fake packet's addr/port <unimpl.>
	 * - Encapsulate: put it in another IP and send out. <unimp.>
	 */ 
#if defined(IPFILTER) || defined(IPFILTER_LKM)
	if (fr_checkp) {
		struct  mbuf    *m1 = m;

		if ((error = (*fr_checkp)(ip, hlen, ifp, 1, &m1)) || !m1)
			goto done;
		ip = mtod(m = m1, struct ip *);
	}
#endif

#ifdef COMPAT_IPFW
        if (ip_nat_ptr && !(*ip_nat_ptr)(&ip, &m, ifp, IP_NAT_OUT)) {
		error = EACCES; 
		goto done;
	}

	/*
	 * Check with the firewall...
	 */
	if (ip_fw_chk_ptr) {
		struct sockaddr_in *old = dst;

		off = (*ip_fw_chk_ptr)(&ip,
		    hlen, ifp, &ip_divert_cookie, &m, &rule, &dst);
                /*
                 * On return we must do the following:
                 * m == NULL         -> drop the pkt
                 * 1<=off<= 0xffff   -> DIVERT
                 * (off & 0x10000)   -> send to a DUMMYNET pipe
                 * dst != old        -> IPFIREWALL_FORWARD
                 * off==0, dst==old  -> accept
                 * If some of the above modules is not compiled in, then
                 * we should't have to check the corresponding condition
                 * (because the ipfw control socket should not accept
                 * unsupported rules), but better play safe and drop
                 * packets in case of doubt.
                 */
		if (!m) { /* firewall said to reject */
			error = EACCES;
			goto done;
		}
		if (off == 0 && dst == old) /* common case */
			goto pass ;
#ifdef DUMMYNET
                if (off & 0x10000) {  
                    /*
                     * pass the pkt to dummynet. Need to include
                     * pipe number, m, ifp, ro, dst because these are
                     * not recomputed in the next pass.
                     * All other parameters have been already used and
                     * so they are not needed anymore. 
                     * XXX note: if the ifp or ro entry are deleted
                     * while a pkt is in dummynet, we are in trouble!
                     */ 
                    dummynet_io(off & 0xffff, DN_TO_IP_OUT, m,ifp,ro,dst,rule);
			goto done;
		}
#endif   
#ifdef IPDIVERT
                if (off > 0 && off < 0x10000) {         /* Divert packet */
                       ip_divert_port = off & 0xffff ;
                       (*inetsw[ip_protox[IPPROTO_DIVERT]].pr_input)(m, 0);
			goto done;
		}
#endif

#ifdef IPFIREWALL_FORWARD
		/* Here we check dst to make sure it's directly reachable on the
		 * interface we previously thought it was.
		 * If it isn't (which may be likely in some situations) we have
		 * to re-route it (ie, find a route for the next-hop and the
		 * associated interface) and set them here. This is nested
		 * forwarding which in most cases is undesirable, except where
		 * such control is nigh impossible. So we do it here.
		 * And I'm babbling.
		 */
		if (off == 0 && old != dst) {
			struct in_ifaddr *ia;

			/* It's changed... */
			/* There must be a better way to do this next line... */
			static struct route sro_fwd, *ro_fwd = &sro_fwd;
#ifdef IPFIREWALL_FORWARD_DEBUG
			printf("IPFIREWALL_FORWARD: New dst ip: ");
			print_ip(dst->sin_addr);
			printf("\n");
#endif
			/*
			 * We need to figure out if we have been forwarded
			 * to a local socket. If so then we should somehow 
			 * "loop back" to ip_input, and get directed to the
			 * PCB as if we had received this packet. This is
			 * because it may be dificult to identify the packets
			 * you want to forward until they are being output
			 * and have selected an interface. (e.g. locally
			 * initiated packets) If we used the loopback inteface,
			 * we would not be able to control what happens 
			 * as the packet runs through ip_input() as
			 * it is done through a ISR.
			 */
			for (ia = TAILQ_FIRST(&in_ifaddrhead); ia;
					ia = TAILQ_NEXT(ia, ia_link)) {
				/*
				 * If the addr to forward to is one
				 * of ours, we pretend to
				 * be the destination for this packet.
				 */
				if (IA_SIN(ia)->sin_addr.s_addr ==