ip_input.c

很好的一个嵌入式linux平台下的bootloader

/* $Id: ip_input.c,v 1.3 2000/04/15 00:50:24 chris Exp $ */
/*
 * Copyright (c) 1982, 1986, 1988 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	7.19 (Berkeley) 5/25/91
 */

#include "param.h"
#include "systm.h"
#include "malloc.h"
#include "mbuf.h"
#include "domain.h"
#include "protosw.h"
#include "socket.h"
#include "errno.h"
#include "time.h"
#include "kernel.h"

#include "../net/if.h"
#include "../net/route.h"

#include "in.h"
#include "in_systm.h"
#include "ip.h"
#include "in_pcb.h"
#include "in_var.h"
#include "ip_var.h"
#include "ip_icmp.h"

#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
#ifdef PROM
const int ipforwarding = IPFORWARDING;
const int ipsendredirects = IPSENDREDIRECTS;
#else
int	ipforwarding = IPFORWARDING;
int	ipsendredirects = IPSENDREDIRECTS;
#endif
#ifdef DIAGNOSTIC
int	ipprintfs = 0;
#endif

extern	struct domain inetdomain;
extern	struct protosw inetsw[];
u_char	ip_protox[IPPROTO_MAX];
#ifdef PROM
const int ipqmaxlen = IFQ_MAXLEN;
#else
int	ipqmaxlen = IFQ_MAXLEN;
#endif
struct	in_ifaddr *in_ifaddr;			/* first inet address */

/*
 * 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;
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 GATEWAY
extern	int if_index;
u_long	*ip_ifmatrix;
#endif

struct	ip *ip_reass();
#ifdef NO_DATA
struct	sockaddr_in ipaddr;
#else
struct	sockaddr_in ipaddr = { sizeof(ipaddr), AF_INET };
#endif
struct	route ipforward_rt;

/*
 * IP initialization: fill in IP protocol switch table.
 * All protocols not implemented in kernel go to raw IP protocol handler.
 */
ip_init()
{
	register const struct protosw *pr;
	register int i;

#ifdef NO_DATA
	ipaddr.sin_len = sizeof(ipaddr);
	ipaddr.sin_family = AF_INET;
#endif
	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;
#ifdef GATEWAY
	i = (if_index + 1) * (if_index + 1) * sizeof (u_long);
	if ((ip_ifmatrix = (u_long *) malloc(i, M_RTABLE, M_WAITOK)) == 0)
		panic("no memory for ip_ifmatrix");
#endif
}

/*
 * Ip input routine.  Checksum and byte swap header.  If fragmented
 * try to reassemble.  Process options.  Pass to next level.
 */
ipintr()
{
	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	DEBUG
	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 *);
	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 *);
	}
	if (ip->ip_sum = in_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_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);
	}

	/*
	 * 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;

	/*
	 * 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 (
#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 (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 = 0;
		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 || ip->ip_off) {
			ipstat.ips_fragments++;
			ip = ip_reass((struct ipasfrag *)ip, fp);
			if (ip == 0)
				goto next;
			else
				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++;
	(*inetsw[ip_protox[ip->ip_p]].pr_input)(m, hlen);
	goto next;
bad:
	m_freem(m);
	goto next;
}

/*
 * 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;
	struct mbuf *t;
	int hlen = ip->ip_hl << 2;
	int i, next;

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

	/*
	 * If first fragment to arrive, create a reassembly queue.
	 */
	if (fp == 0) {
		if ((t = m_get(M_DONTWAIT, MT_FTABLE)) == NULL)
			goto dropfrag;
		fp = mtod(t, struct ipq *);
		insque(fp, &ipq);
		fp->ipq_ttl = IPFRAGTTL;
		fp->ipq_p = ip->ip_p;
		fp->ipq_id = ip->ip_id;
		fp->ipq_next = fp->ipq_prev = (struct ipasfrag *)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 = fp->ipq_next; q != (struct ipasfrag *)fp; q = 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 != (struct ipasfrag *)fp) {
		i = q->ipf_prev->ip_off + 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 = q->ipf_next;
		m_freem(dtom(q->ipf_prev));
		ip_deq(q->ipf_prev);
	}

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

	/*
	 * Reassembly is complete; concatenate fragments.
	 */
	q = fp->ipq_next;
	m = dtom(q);
	t = m->m_next;
	m->m_next = 0;
	m_cat(m, t);
	q = q->ipf_next;
	while (q != (struct ipasfrag *)fp) {
		t = dtom(q);
		q = q->ipf_next;
		m_cat(m, t);
	}

	/*
	 * Create header for new ip packet by
	 * modifying header of first packet;
	 * dequeue and discard fragment reassembly header.
	 * Make header visible.
	 */
	ip = fp->ipq_next;
	ip->ip_len = next;
	((struct ip *)ip)->ip_src = fp->ipq_src;
	((struct ip *)ip)->ip_dst = fp->ipq_dst;
	remque(fp);
	(void) m_free(dtom(fp));
	m = dtom(ip);
	m->m_len += (ip->ip_hl << 2);
	m->m_data -= (ip->ip_hl << 2);
	/* some debugging cruft by sklower, below, will go away soon */
	if (m->m_flags & M_PKTHDR) { /* XXX this should be done elsewhere */
		register int plen = 0;
		for (t = m; m; m = m->m_next)
			plen += m->m_len;
		t->m_pkthdr.len = plen;
	}
	return ((struct ip *)ip);

dropfrag:
	ipstat.ips_fragdropped++;
	m_freem(m);
	return (0);
}

/*
 * Free a fragment reassembly header and all
 * associated datagrams.
 */
ip_freef(fp)
	struct ipq *fp;
{
	register struct ipasfrag *q, *p;

	for (q = fp->ipq_next; q != (struct ipasfrag *)fp; q = p) {
		p = q->ipf_next;
		ip_deq(q);
		m_freem(dtom(q));
	}
	remque(fp);
	(void) m_free(dtom(fp));
}

/*
 * Put an ip fragment on a reassembly chain.
 * Like insque, but pointers in middle of structure.
 */
ip_enq(p, prev)
	register struct ipasfrag *p, *prev;
{

	p->ipf_prev = prev;
	p->ipf_next = prev->ipf_next;
	prev->ipf_next->ipf_prev = p;
	prev->ipf_next = p;
}

/*
 * To ip_enq as remque is to insque.
 */
ip_deq(p)
	register struct ipasfrag *p;
{

	p->ipf_prev->ipf_next = p->ipf_next;
	p->ipf_next->ipf_prev = p->ipf_prev;