ip_input.c

qemu虚拟机代码

/*
 * 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
 * ip_input.c,v 1.11 1994/11/16 10:17:08 jkh Exp
 */

/*
 * Changes and additions relating to SLiRP are
 * Copyright (c) 1995 Danny Gasparovski.
 * 
 * Please read the file COPYRIGHT for the
 * terms and conditions of the copyright.
 */

#include <slirp.h>
#include "ip_icmp.h"

int ip_defttl;
struct ipstat ipstat;
struct ipq ipq;

/*
 * IP initialization: fill in IP protocol switch table.
 * All protocols not implemented in kernel go to raw IP protocol handler.
 */
void
ip_init()
{
	ipq.next = ipq.prev = (ipqp_32)&ipq;
	ip_id = tt.tv_sec & 0xffff;
	udp_init();
	tcp_init();
	ip_defttl = IPDEFTTL;
}

/*
 * Ip input routine.  Checksum and byte swap header.  If fragmented
 * try to reassemble.  Process options.  Pass to next level.
 */
void
ip_input(m)
	struct mbuf *m;
{
	register struct ip *ip;
	int hlen;
	
	DEBUG_CALL("ip_input");
	DEBUG_ARG("m = %lx", (long)m);
	DEBUG_ARG("m_len = %d", m->m_len);

	ipstat.ips_total++;
	
	if (m->m_len < sizeof (struct ip)) {
		ipstat.ips_toosmall++;
		return;
	}
	
	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 ) || hlen>m->m_len) {/* min header length */
	  ipstat.ips_badhlen++;                     /* or packet too short */
	  goto bad;
	}

        /* keep ip header intact for ICMP reply
	 * ip->ip_sum = cksum(m, hlen); 
	 * if (ip->ip_sum) { 
	 */
	if(cksum(m,hlen)) {
	  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_len < ip->ip_len) {
		ipstat.ips_tooshort++;
		goto bad;
	}
	/* Should drop packet if mbuf too long? hmmm... */
	if (m->m_len > ip->ip_len)
	   m_adj(m, ip->ip_len - m->m_len);

	/* check ip_ttl for a correct ICMP reply */
	if(ip->ip_ttl==0 || ip->ip_ttl==1) {
	  icmp_error(m, ICMP_TIMXCEED,ICMP_TIMXCEED_INTRANS, 0,"ttl");
	  goto bad;
	}

	/*
	 * 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).
	 */
/* We do no IP options */
/*	if (hlen > sizeof (struct ip) && ip_dooptions(m))
 *		goto next;
 */
	/*
	 * 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.)
	 * 
	 * XXX This should fail, don't fragment yet
	 */
	if (ip->ip_off &~ IP_DF) {
	  register struct ipq *fp;
		/*
		 * Look for queue of fragments
		 * of this datagram.
		 */
		for (fp = (struct ipq *) ipq.next; fp != &ipq;
		     fp = (struct ipq *) 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;
		if (ip->ip_off & IP_MF)
		  ((struct ipasfrag *)ip)->ipf_mff |= 1;
		else 
		  ((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)
				return;
			ipstat.ips_reassembled++;
			m = dtom(ip);
		} else
			if (fp)
		   	   ip_freef(fp);

	} else
		ip->ip_len -= hlen;

	/*
	 * Switch out to protocol's input routine.
	 */
	ipstat.ips_delivered++;
	switch (ip->ip_p) {
	 case IPPROTO_TCP:
		tcp_input(m, hlen, (struct socket *)NULL);
		break;
	 case IPPROTO_UDP:
		udp_input(m, hlen);
		break;
	 case IPPROTO_ICMP:
		icmp_input(m, hlen);
		break;
	 default:
		ipstat.ips_noproto++;
		m_free(m);
	}
	return;
bad:
	m_freem(m);
	return;
}

/*
 * Take incoming datagram fragment and try to
 * reassemble it into whole datagram.  If a chain for
 * reassembly of this datagram already exists, then it
 * is given as fp; otherwise have to make a chain.
 */
struct ip *
ip_reass(ip, fp)
	register struct ipasfrag *ip;
	register struct ipq *fp;
{
	register struct mbuf *m = dtom(ip);
	register struct ipasfrag *q;
	int hlen = ip->ip_hl << 2;
	int i, next;
	
	DEBUG_CALL("ip_reass");
	DEBUG_ARG("ip = %lx", (long)ip);
	DEBUG_ARG("fp = %lx", (long)fp);
	DEBUG_ARG("m = %lx", (long)m);

	/*
	 * Presence of header sizes in mbufs
	 * would confuse code below.
         * Fragment m_data is concatenated.
	 */
	m->m_data += hlen;
	m->m_len -= hlen;

	/*
	 * If first fragment to arrive, create a reassembly queue.
	 */
	if (fp == 0) {
	  struct mbuf *t;
	  if ((t = m_get()) == NULL) goto dropfrag;
	  fp = mtod(t, struct ipq *);
	  insque_32(fp, &ipq);
	  fp->ipq_ttl = IPFRAGTTL;
	  fp->ipq_p = ip->ip_p;
	  fp->ipq_id = ip->ip_id;
	  fp->ipq_next = fp->ipq_prev = (ipasfragp_32)fp;
	  fp->ipq_src = ((struct ip *)ip)->ip_src;
	  fp->ipq_dst = ((struct ip *)ip)->ip_dst;
	  q = (struct ipasfrag *)fp;
	  goto insert;
	}
	
	/*
	 * Find a segment which begins after this one does.
	 */
	for (q = (struct ipasfrag *)fp->ipq_next; q != (struct ipasfrag *)fp;
	    q = (struct ipasfrag *)q->ipf_next)
		if (q->ip_off > ip->ip_off)
			break;

	/*
	 * If there is a preceding segment, it may provide some of
	 * our data already.  If so, drop the data from the incoming
	 * segment.  If it provides all of our data, drop us.
	 */
	if (q->ipf_prev != (ipasfragp_32)fp) {
		i = ((struct ipasfrag *)(q->ipf_prev))->ip_off +
		  ((struct ipasfrag *)(q->ipf_prev))->ip_len - ip->ip_off;
		if (i > 0) {
			if (i >= ip->ip_len)
				goto dropfrag;
			m_adj(dtom(ip), i);
			ip->ip_off += i;
			ip->ip_len -= i;
		}
	}

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	while (q != (struct ipasfrag *)fp && ip->ip_off + ip->ip_len > q->ip_off) {
		i = (ip->ip_off + ip->ip_len) - q->ip_off;
		if (i < q->ip_len) {
			q->ip_len -= i;
			q->ip_off += i;
			m_adj(dtom(q), i);
			break;
		}
		q = (struct ipasfrag *) q->ipf_next;
		m_freem(dtom((struct ipasfrag *) q->ipf_prev));
		ip_deq((struct ipasfrag *) q->ipf_prev);
	}

insert:
	/*
	 * Stick new segment in its place;
	 * check for complete reassembly.
	 */
	ip_enq(ip, (struct ipasfrag *) q->ipf_prev);
	next = 0;
	for (q = (struct ipasfrag *) fp->ipq_next; q != (struct ipasfrag *)fp;
	     q = (struct ipasfrag *) q->ipf_next) {
		if (q->ip_off != next)
			return (0);
		next += q->ip_len;
	}
	if (((struct ipasfrag *)(q->ipf_prev))->ipf_mff & 1)
		return (0);

	/*
	 * Reassembly is complete; concatenate fragments.
	 */
	q = (struct ipasfrag *) fp->ipq_next;
	m = dtom(q);

	q = (struct ipasfrag *) q->ipf_next;
	while (q != (struct ipasfrag *)fp) {
	  struct mbuf *t;
	  t = dtom(q);
	  q = (struct ipasfrag *) q->ipf_next;
	  m_cat(m, t);
	}