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 1,665 行 · 第 1/3 页

		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);
#ifdef IPFIREWALL_FORWARD
	ip_fw_fwd_addr = NULL;
#endif
	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_MF | IP_OFFMASK | IP_RF)) {
		if (m->m_flags & M_EXT) {		/* XXX */
			if ((m = m_pullup(m, hlen)) == 0) {
				ipstat.ips_toosmall++;
#ifdef IPDIVERT
				frag_divert_port = 0;
				ip_divert_cookie = 0;
#endif
#ifdef IPFIREWALL_FORWARD
				ip_fw_fwd_addr = NULL;
#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 */
			for (i = 0; i < IPREASS_NHASH; i++) {
			    if (ipq[i].prev != &ipq[i]) {
				ip_freef(ipq[i].prev);
				break;
			    }
			}
		    } else
			ip_freef(ipq[sum].prev);
		}
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;
		mff = (ip->ip_off & IP_MF) != 0;
		if (mff) {
		        /*
		         * Make sure that fragments have a data length
			 * that's a non-zero multiple of 8 bytes.
		         */
			if (ip->ip_len == 0 || (ip->ip_len & 0x7) != 0) {
				ipstat.ips_toosmall++; /* XXX */
				goto bad;
			}
			m->m_flags |= M_FRAG;
		}
		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 (mff || ip->ip_off) {
			ipstat.ips_fragments++;
			m->m_pkthdr.header = ip;
			ip = ip_reass(m, fp, &ipq[sum]);
			if (ip == 0) {
#ifdef	IPFIREWALL_FORWARD
				ip_fw_fwd_addr = NULL;
#endif
				return;
			}
			/* Get the length of the reassembled packets header */
			hlen = IP_VHL_HL(ip->ip_vhl) << 2;
			ipstat.ips_reassembled++;
			m = dtom(ip);
#ifdef IPDIVERT
			if (frag_divert_port) {
				ip->ip_len += hlen;
				HTONS(ip->ip_len);
				HTONS(ip->ip_off);
				HTONS(ip->ip_id);
				ip->ip_sum = 0;
				ip->ip_sum = in_cksum_hdr(ip);
				NTOHS(ip->ip_id);
				NTOHS(ip->ip_off);
				NTOHS(ip->ip_len);
				ip->ip_len -= hlen;
			}
#endif
		} else
			if (fp)
				ip_freef(fp);
	} else
		ip->ip_len -= hlen;

#ifdef IPDIVERT
	/*
	 * Divert reassembled packets to the divert protocol if required
	 *  If divert port is null then cookie should be too,
	 * so we shouldn't need to clear them here. Assume ip_divert does so.
	 */
	if (frag_divert_port) {
		ipstat.ips_delivered++;
		ip_divert_port = frag_divert_port;
		frag_divert_port = 0;
		(*inetsw[ip_protox[IPPROTO_DIVERT]].pr_input)(m, hlen);
		return;
	}

	/* Don't let packets divert themselves */
	if (ip->ip_p == IPPROTO_DIVERT) {
		ipstat.ips_noproto++;
		goto bad;
	}

#endif

	/*
	 * Switch out to protocol's input routine.
	 */
	ipstat.ips_delivered++;
	(*inetsw[ip_protox[ip->ip_p]].pr_input)(m, hlen);
#ifdef	IPFIREWALL_FORWARD
	ip_fw_fwd_addr = NULL;	/* tcp needed it */
#endif
	return;
bad:
#ifdef	IPFIREWALL_FORWARD
	ip_fw_fwd_addr = NULL;
#endif
	m_freem(m);
}

/*
 * IP software interrupt routine - to go away sometime soon
 */
#ifdef OSKIT
void 
#else /* !OSKIT */
static void
#endif /* !OSKIT */
ipintr(void)
{
	int s;
	struct mbuf *m;

	while(1) {
		s = splimp();
		IF_DEQUEUE(&ipintrq, m);
		splx(s);
		if (m == 0)
			return;
		ip_input(m);
	}
}

NETISR_SET(NETISR_IP, ipintr);
  
/*
 * 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.
 */
static struct ip *
ip_reass(m, fp, where)
	register struct mbuf *m;
	register struct ipq *fp;
	struct   ipq    *where;
{
	struct ip *ip = mtod(m, struct ip *);
	register struct mbuf *p = 0, *q, *nq;
	struct mbuf *t;
	int hlen = IP_VHL_HL(ip->ip_vhl) << 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, where);
		nipq++;
		fp->ipq_ttl = IPFRAGTTL;
		fp->ipq_p = ip->ip_p;
		fp->ipq_id = ip->ip_id;
		fp->ipq_src = ip->ip_src;
		fp->ipq_dst = ip->ip_dst;
		fp->ipq_frags = m;
		m->m_nextpkt = NULL;
#ifdef IPDIVERT
		fp->ipq_divert = 0;
		fp->ipq_div_cookie = 0;
#endif
		goto inserted;
	}

#define GETIP(m)	((struct ip*)((m)->m_pkthdr.header))

	/*
	 * Find a segment which begins after this one does.
	 */
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt)
		if (GETIP(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, otherwise
	 * stick new segment in the proper place.
	 */
	if (p) {
		i = GETIP(p)->ip_off + GETIP(p)->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;
		}
		m->m_nextpkt = p->m_nextpkt;
		p->m_nextpkt = m;
	} else {
		m->m_nextpkt = fp->ipq_frags;
		fp->ipq_frags = m;
	}

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	for (; q != NULL && ip->ip_off + ip->ip_len > GETIP(q)->ip_off;
	     q = nq) {
		i = (ip->ip_off + ip->ip_len) -
		    GETIP(q)->ip_off;
		if (i < GETIP(q)->ip_len) {
			GETIP(q)->ip_len -= i;
			GETIP(q)->ip_off += i;
			m_adj(q, i);
			break;
		}
		nq = q->m_nextpkt;
		m->m_nextpkt = nq;
		m_freem(q);
	}

inserted:

#ifdef IPDIVERT
	/*
	 * Any fragment diverting causes the whole packet to divert
	 */
	if (frag_divert_port) {
		fp->ipq_divert = frag_divert_port;
		fp->ipq_div_cookie = ip_divert_cookie;
	}
	frag_divert_port = 0;
	ip_divert_cookie = 0;
#endif

	/*
	 * Check for complete reassembly.
	 */
	next = 0;
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt) {
		if (GETIP(q)->ip_off != next)
			return (0);
		next += GETIP(q)->ip_len;
	}
	/* Make sure the last packet didn't have the IP_MF flag */
	if (p->m_flags & M_FRAG)
		return (0);

	/*
	 * Reassembly is complete.  Make sure the packet is a sane size.
	 */
	q = fp->ipq_frags;
	ip = GETIP(q);
	if (next + (IP_VHL_HL(ip->ip_vhl) << 2) > IP_MAXPACKET) {
		ipstat.ips_toolong++;
		ip_freef(fp);
		return (0);
	}

	/*
	 * Concatenate fragments.
	 */
	m = q;
	t = m->m_next;
	m->m_next = 0;
	m_cat(m, t);
	nq = q->m_nextpkt;
	q->m_nextpkt = 0;
	for (q = nq; q != NULL; q = nq) {
		nq = q->m_nextpkt;
		q->m_nextpkt = NULL;
		m_cat(m, q);
	}

#ifdef IPDIVERT
	/*
	 * extract divert port for packet, if any
	 */
	frag_divert_port = fp->ipq_divert;
	ip_divert_cookie = fp->ipq_div_cookie;
#endif

	/*
	 * Create header for new ip packet by
	 * modifying header of first packet;
	 * dequeue and discard fragment reassembly header.
	 * Make header visible.
	 */
	ip->ip_len = next;
	ip->ip_src = fp->ipq_src;
	ip->ip_dst = fp->ipq_dst;
	remque(fp);
	nipq--;
	(void) m_free(dtom(fp));
	m->m_len += (IP_VHL_HL(ip->ip_vhl) << 2);
	m->m_data -= (IP_VHL_HL(ip->ip_vhl) << 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 (ip);

dropfrag:
#ifdef IPDIVERT
	frag_divert_port = 0;
	ip_divert_cookie = 0;
#endif
	ipstat.ips_fragdropped++;
	m_freem(m);
	return (0);

#undef GETIP
}

/*
 * Free a fragment reassembly header and all
 * associated datagrams.
 */
static void
ip_freef(fp)
	struct ipq *fp;
{
	register struct mbuf *q;

	while (fp->ipq_frags) {
		q = fp->ipq_frags;
		fp->ipq_frags = q->m_nextpkt;
		m_freem(q);
	}
	remque(fp);
	(void) m_free(dtom(fp));
	nipq--;
}

/*
 * IP timer processing;
 * if a timer expires on a reassembly
 * queue, discard it.
 */
void
ip_slowtimo()
{
	register struct ipq *fp;
	int s = splnet();
	int i;

	for (i = 0; i < IPREASS_NHASH; i++) {
		fp = ipq[i].next;
		if (fp == 0)
			continue;
		while (fp != &ipq[i]) {
			--fp->ipq_ttl;
			fp = fp->next;
			if (fp->prev->ipq_ttl == 0) {
				ipstat.ips_fragtimeout++;
				ip_freef(fp->prev);
			}
		}
	}
	ipflow_slowtimo();
	splx(s);
}

/*
 * Drain off all datagram fragments.
 */
void
ip_drain()
{
	int     i;

	for (i = 0; i < IPREASS_NHASH; i++) {
		while (ipq[i].next != &ipq[i]) {
			ipstat.ips_fragdropped++;
			ip_freef(ipq[i].next);
		}
	}
	in_rtqdrain();
}

/*
 * Do option processing on a datagram,
 * possibly discarding it if bad options are encountered,
 * or forwarding it if source-routed.
 * Returns 1 if packet has been forwarded/freed,
 * 0 if the packet should be processed further.
 */
static int
ip_dooptions(m)
	struct mbuf *m;
{
	register struct ip *ip = mtod(m, struct ip *);
	register u_char *cp;
	register struct ip_timestamp *ipt;
	register struct in_ifaddr *ia;
	int opt, optlen, cnt, off, code, type = ICMP_PARAMPROB, forward = 0;
	struct in_addr *sin, dst;
	n_time ntime;

	dst = ip->ip_dst;
	cp = (u_char *)(ip + 1);
	cnt = (IP_VHL_HL(ip->ip_vhl) << 2) - sizeof (struct ip);
	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[IPOPT_OPTVAL];
		if (opt == IPOPT_EOL)
			break;
		if (opt == IPOPT_NOP)
			optlen = 1;
		else {
			optlen = cp[IPOPT_OLEN];
			if (optlen <= 0 || optlen > cnt) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
		}
		switch (opt) {

		default:
			break;

		/*
		 * Source routing with record.
		 * Find interface with current destination address.
		 * If none on this machine then drop if strictly routed,
		 * or do nothing if loosely routed.
		 * Record interface address and bring up next address
		 * component.  If strictly routed make sure next
		 * address is on directly accessible net.
		 */
		case IPOPT_LSRR:
		case IPOPT_SSRR:
			if ((off = cp[IPOPT_OFFSET]) < IPOPT_MINOFF) {
				code = &cp[IPOPT_OFFSET] - (u_char *)ip;
				goto bad;
			}
			ipaddr.sin_addr = ip->ip_dst;
			ia = (struct in_ifaddr *)
				ifa_ifwithaddr((struct sockaddr *)&ipaddr);
			if (ia == 0) {
				if (opt == IPOPT_SSRR) {
					type = ICMP_UNREACH;
					code = ICMP_UNREACH_SRCFAIL;
					goto bad;
				}
				if (!ip_dosourceroute)
					goto nosourcerouting;
				/*
				 * Loose routing, and not at next destination
				 * yet; nothing to do except forward.
				 */
				break;
			}
			off--;			/* 0 origin */
			if (off > optlen - sizeof(struct in_addr)) {
				/*
				 * End of source route.  Should be for us.
				 */
				if (!ip_acceptsourceroute)
					goto nosourcerouting;
				save_rte(cp, ip->ip_src);
				break;
			}

			if (!ip_dosourceroute) {
				if (ipforwarding) {
					char buf[16]; /* aaa.bbb.ccc.ddd\0 */
					/*
					 * Acting as a router, so generate ICMP
					 */
nosourcerouting:
					strcpy(buf, inet_ntoa(ip->ip_dst));
					log(LOG_WARNING, 
					    "attempted source route from %s to %s\n",
					    inet_ntoa(ip->ip_src), buf);
					type = ICMP_UNREACH;
					code = ICMP_UNREACH_SRCFAIL;
					goto bad;
				} else {