ip_input.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 1,282 行 · 第 1/3 页

/*
 * 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
 */

#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 <vm/vm.h>
#include <sys/sysctl.h>

#include <net/if.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 <netinet/ip_fw.h>

#include <sys/socketvar.h>
int rsvp_on = 0;
int ip_rsvp_on;
struct socket *ip_rsvpd;

#ifndef	IPFORWARDING
#ifdef GATEWAY
#define	IPFORWARDING	1	/* forward IP packets not for us */
#else /* GATEWAY */
#define	IPFORWARDING	0	/* don't forward IP packets not for us */
#endif /* GATEWAY */
#endif /* IPFORWARDING */
#ifndef	IPSENDREDIRECTS
#define	IPSENDREDIRECTS	1
#endif
int	ipforwarding = IPFORWARDING;
int	ipsendredirects = IPSENDREDIRECTS;
int	ip_defttl = IPDEFTTL;
int	ip_dosourceroute = 0;
#ifdef DIAGNOSTIC
int	ipprintfs = 0;
#endif

extern	struct domain inetdomain;
extern	struct protosw inetsw[];
u_char	ip_protox[IPPROTO_MAX];
int	ipqmaxlen = IFQ_MAXLEN;
struct	in_ifaddr *in_ifaddr;			/* first inet address */
struct	ifqueue ipintrq;

struct ipstat ipstat;
struct ipq ipq;


/*
 * The dummy IP-firewall function, and the pointer we access it through
 */
static int 
dummy_ip_fw_chk(m, ip, rif, dir)
	struct mbuf *m;
	struct ip *ip;
	struct ifnet *rif;
	int dir;
{
	return 1;
}

int (*ip_fw_chk_ptr)(struct mbuf *, struct ip *, struct ifnet *, int dir) = 
	dummy_ip_fw_chk;

int (*ip_fw_ctl_ptr)(int, struct mbuf **);

/*
 * 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.
 */
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;

static void save_rte __P((u_char *, struct in_addr));
/*
 * 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;
	ipq.next = ipq.prev = &ipq;
	ip_id = time.tv_sec & 0xffff;
	ipintrq.ifq_maxlen = ipqmaxlen;
#if defined(IPFIREWALL)
	ip_fw_init();
#endif /* IPFIREWALL */
}

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

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

next:
	/*
	 * Get next datagram off input queue and get IP header
	 * in first mbuf.
	 */
	s = splimp();
	IF_DEQUEUE(&ipintrq, m);
	splx(s);
	if (m == 0)
		return;
#ifdef	DIAGNOSTIC
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("ipintr 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_len < sizeof (struct ip) &&
	    (m = m_pullup(m, sizeof (struct ip))) == 0) {
		ipstat.ips_toosmall++;
		goto next;
	}
	ip = mtod(m, struct ip *);
	if (ip->ip_v != IPVERSION) {
		ipstat.ips_badvers++;
		goto bad;
	}
	hlen = ip->ip_hl << 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++;
			goto next;
		}
		ip = mtod(m, struct ip *);
	}
	ip->ip_sum = in_cksum(m, hlen);
	if (ip->ip_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) {
		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
	 * - Wrap: fake packet's addr/port <unimpl.>
	 * - Encapsulate: put it in another IP and send out. <unimp.>
 	 */

	if (!(*ip_fw_chk_ptr)(m,ip,m->m_pkthdr.rcvif,0) ) {
	       goto next;
	}

	/*
	 * 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))
		goto next;

        /* 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;
		if (ia->ia_ifp &&
#ifdef	DIRECTED_BROADCAST
		    ia->ia_ifp == m->m_pkthdr.rcvif &&
#endif
		    (ia->ia_ifp->if_flags & IFF_BROADCAST)) {
			u_long t;

			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;
			/*
			 * Look for all-0's host part (old broadcast addr),
			 * either for subnet or net.
			 */
			t = ntohl(ip->ip_dst.s_addr);
			if (t == ia->ia_subnet)
				goto ours;
			if (t == ia->ia_net)
				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);
				goto next;
			}
			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);
			goto next;
		}
		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);
	goto next;

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) {
		if (m->m_flags & M_EXT) {		/* XXX */
			if ((m = m_pullup(m, sizeof (struct ip))) == 0) {
				ipstat.ips_toosmall++;
				goto next;
			}
			ip = mtod(m, struct ip *);
		}
		/*
		 * Look for queue of fragments
		 * of this datagram.
		 */
		for (fp = ipq.next; fp != &ipq; 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;
found:

		/*
		 * Adjust ip_len to not reflect header,
		 * set ip_mff if more fragments are expected,
		 * convert offset of this to bytes.
		 */
		ip->ip_len -= hlen;
		((struct ipasfrag *)ip)->ipf_mff &= ~1;
		if (ip->ip_off & IP_MF)
			((struct ipasfrag *)ip)->ipf_mff |= 1;
		ip->ip_off <<= 3;

		/*
		 * If datagram marked as having more fragments
		 * or if this is not the first fragment,
		 * attempt reassembly; if it succeeds, proceed.
		 */
		if (((struct ipasfrag *)ip)->ipf_mff & 1 || ip->ip_off) {
			ipstat.ips_fragments++;
			ip = ip_reass((struct ipasfrag *)ip, fp);
			if (ip == 0)
				goto next;
			ipstat.ips_reassembled++;