C++ icmp_send函数代码示例

static void ip_expire(unsigned long arg)
{
	struct ipq *qp;

	qp = (struct ipq *)arg;

	/*
	 *	Send an ICMP "Fragment Reassembly Timeout" message.
	 */

	ip_statistics.IpReasmTimeout++;
	ip_statistics.IpReasmFails++;   
	/* This if is always true... shrug */
	if(qp->fragments!=NULL)
		icmp_send(qp->fragments->skb,ICMP_TIME_EXCEEDED,
				ICMP_EXC_FRAGTIME, 0, qp->dev);

	/*
	 *	Nuke the fragment queue.
	 */
	ip_free(qp);
}

static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct iphdr  *iph = ip_hdr(skb);
	int encap_limit = -1;
	struct flowi fl;
	__u8 dsfield;
	__u32 mtu;
	int err;

	if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) ||
	    !ip6_tnl_xmit_ctl(t))
		return -1;

	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
		encap_limit = t->parms.encap_limit;

	memcpy(&fl, &t->fl, sizeof (fl));
	fl.proto = IPPROTO_IPIP;

	dsfield = ipv4_get_dsfield(iph);

	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
		fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
					  & IPV6_TCLASS_MASK;

	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
	if (err != 0) {
		/* XXX: send ICMP error even if DF is not set. */
		if (err == -EMSGSIZE)
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));
		return -1;
	}

	return 0;
}

static bool ipv6_validate_packet_len(struct sk_buff *skb_in, struct sk_buff *skb_out)
{
	struct ipv6hdr *ip6_hdr = ipv6_hdr(skb_out);
	struct hdr_iterator iterator = HDR_ITERATOR_INIT(ip6_hdr);
	unsigned int ipv6_mtu;
	unsigned int ipv4_mtu;

	if (skb_out->len <= skb_out->dev->mtu)
		return true;

	hdr_iterator_last(&iterator);
	if (iterator.hdr_type == IPPROTO_ICMPV6) {
		struct icmp6hdr *icmpv6_hdr = icmp6_hdr(skb_out);
		if (is_icmp6_error(icmpv6_hdr->icmp6_type)) {
			int new_packet_len = skb_out->dev->mtu;
			int l3_payload_len = new_packet_len - (iterator.data - (void *) ip6_hdr);

			skb_trim(skb_out, new_packet_len);

			ip6_hdr->payload_len = cpu_to_be16(l3_payload_len);

			icmpv6_hdr->icmp6_cksum = 0;
			icmpv6_hdr->icmp6_cksum = csum_ipv6_magic(&ip6_hdr->saddr, &ip6_hdr->daddr,
					l3_payload_len, IPPROTO_ICMPV6, csum_partial(icmpv6_hdr, l3_payload_len, 0));

			return true;
		}
	}

	ipv6_mtu = skb_out->dev->mtu;
	ipv4_mtu = skb_in->dev->mtu;

	log_debug("Packet is too large for the outgoing MTU and IPv6 routers don't do fragmentation. "
			"Dropping...");
	icmp_send(skb_in, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			cpu_to_be32(min_uint(ipv6_mtu, ipv4_mtu + 20)));
	return false;
}

/**
 * \ingroup tcpcmd
 * \b PING-Befehl Sende "Ping" an angegebene Adresse
 */
int16_t command_ping (char *outbuffer)
{
	uint32_t var = 0;

	if (getLong(&var))
	{
		unsigned long dest_ip=0;

		for (uint8_t i=0; i<4; ++i) {
			dest_ip += (var<<(8*i));
			if (!getLong(&var))
				break;
		}

		//ARP Request senden
		arp_request (dest_ip);
		
		//ICMP-Nachricht Type=8 Code=0: Echo-Anfrage
		//TODO: Sequenznummer, Identifier 
		icmp_send(dest_ip,0x08,0x00,1,1);
	}
	return 0;
}

static int icmp_hnd_echo_request(const struct icmphdr *icmph,
		const struct icmpbody_echo *echo_req,
		struct sk_buff *skb) {
	size_t len;
	struct icmpbody_echo *echo_rep;

	if (icmph->code != 0) {
		skb_free(skb);
		return 0; /* error: bad code */
	}

	len = ip_data_length(ip_hdr(skb));
	if (sizeof *icmph + sizeof *echo_req > len) {
		skb_free(skb);
		return 0; /* error: invalid length */
	}
	len -= sizeof *icmph + sizeof *echo_req;

	echo_rep = &icmp_hdr(skb)->body[0].echo;

	return icmp_send(ICMP_ECHO_REPLY, 0, echo_rep,
			sizeof *echo_rep + len, skb);
}

static int ipip6_rcv(struct sk_buff *skb)
{
	struct iphdr *iph;
	struct ip_tunnel *tunnel;

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		goto out;

	iph = skb->nh.iph;

	read_lock(&ipip6_lock);
	if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
		secpath_reset(skb);
		skb->mac.raw = skb->nh.raw;
		skb->nh.raw = skb->data;
		memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
		IPCB(skb)->flags = 0;
		skb->protocol = htons(ETH_P_IPV6);
		skb->pkt_type = PACKET_HOST;
		tunnel->stat.rx_packets++;
		tunnel->stat.rx_bytes += skb->len;
		skb->dev = tunnel->dev;
		dst_release(skb->dst);
		skb->dst = NULL;
		nf_reset(skb);
		ipip6_ecn_decapsulate(iph, skb);
		netif_rx(skb);
		read_unlock(&ipip6_lock);
		return 0;
	}

	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0);
	kfree_skb(skb);
	read_unlock(&ipip6_lock);
out:
	return 0;
}

static int gre_rcv(struct sk_buff *skb)
{
	struct tnl_ptk_info tpi;
	bool csum_err = false;

#ifdef CONFIG_NET_IPGRE_BROADCAST
	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
		/* Looped back packet, drop it! */
		if (rt_is_output_route(skb_rtable(skb)))
			goto drop;
	}
#endif

	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
		goto drop;

	if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
		return 0;

	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
	kfree_skb(skb);
	return 0;
}

int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
		    int encap_type)
{
	int ret;
	struct xfrm4_protocol *handler;
	struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);

	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);

	if (!head)
		goto out;

	for_each_protocol_rcu(*head, handler)
		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
			return ret;

out:
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

	kfree_skb(skb);
	return 0;
}

/*
 *  Pass or drop the packet.
 *  Called by ip_vs_in, when the virtual service is available but
 *  no destination is available for a new connection.
 */
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
		struct ip_vs_protocol *pp)
{
	__be16 _ports[2], *pptr;
	struct iphdr *iph = ip_hdr(skb);

	pptr = skb_header_pointer(skb, iph->ihl*4,
				  sizeof(_ports), _ports);
	if (pptr == NULL) {
		ip_vs_service_put(svc);
		return NF_DROP;
	}

	/* if it is fwmark-based service, the cache_bypass sysctl is up
	   and the destination is RTN_UNICAST (and not local), then create
	   a cache_bypass connection entry */
	if (sysctl_ip_vs_cache_bypass && svc->fwmark
	    && (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
		int ret, cs;
		struct ip_vs_conn *cp;

		ip_vs_service_put(svc);

		/* create a new connection entry */
		IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
		cp = ip_vs_conn_new(iph->protocol,
				    iph->saddr, pptr[0],
				    iph->daddr, pptr[1],
				    0, 0,
				    IP_VS_CONN_F_BYPASS,
				    NULL);
		if (cp == NULL)
			return NF_DROP;

		/* statistics */
		ip_vs_in_stats(cp, skb);

		/* set state */
		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);

		/* transmit the first SYN packet */
		ret = cp->packet_xmit(skb, cp, pp);
		/* do not touch skb anymore */

		atomic_inc(&cp->in_pkts);
		ip_vs_conn_put(cp);
		return ret;
	}

	/*
	 * When the virtual ftp service is presented, packets destined
	 * for other services on the VIP may get here (except services
	 * listed in the ipvs table), pass the packets, because it is
	 * not ipvs job to decide to drop the packets.
	 */
	if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
		ip_vs_service_put(svc);
		return NF_ACCEPT;
	}

	ip_vs_service_put(svc);

	/*
	 * Notify the client that the destination is unreachable, and
	 * release the socket buffer.
	 * Since it is in IP layer, the TCP socket is not actually
	 * created, the TCP RST packet cannot be sent, instead that
	 * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
	 */
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
	return NF_DROP;
}

static unsigned int
fw_in(unsigned int hooknum,
      struct sk_buff **pskb,
      const struct net_device *in,
      const struct net_device *out,
      int (*okfn)(struct sk_buff *))
{
	int ret = FW_BLOCK;
	u_int16_t redirpt;

	/* Assume worse case: any hook could change packet */
	(*pskb)->nfcache |= NFC_UNKNOWN | NFC_ALTERED;
	if ((*pskb)->ip_summed == CHECKSUM_HW)
		if (skb_checksum_help(*pskb, (out == NULL)))
			return NF_DROP;

	switch (hooknum) {
	case NF_IP_PRE_ROUTING:
		if (fwops->fw_acct_in)
			fwops->fw_acct_in(fwops, PF_INET,
					  (struct net_device *)in,
					  &redirpt, pskb);

		if ((*pskb)->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) {
			*pskb = ip_ct_gather_frags(*pskb);

			if (!*pskb)
				return NF_STOLEN;
		}

		ret = fwops->fw_input(fwops, PF_INET, (struct net_device *)in,
				      &redirpt, pskb);
		break;

	case NF_IP_FORWARD:
		/* Connection will only be set if it was
                   demasqueraded: if so, skip forward chain. */
		if ((*pskb)->nfct)
			ret = FW_ACCEPT;
		else ret = fwops->fw_forward(fwops, PF_INET,
					     (struct net_device *)out,
					     &redirpt, pskb);
		break;

	case NF_IP_POST_ROUTING:
		ret = fwops->fw_output(fwops, PF_INET,
				       (struct net_device *)out,
				       &redirpt, pskb);
		if (ret == FW_ACCEPT || ret == FW_SKIP) {
			if (fwops->fw_acct_out)
				fwops->fw_acct_out(fwops, PF_INET,
						   (struct net_device *)out,
						   &redirpt,
						   pskb);

			/* ip_conntrack_confirm return NF_DROP or NF_ACCEPT */
			if (ip_conntrack_confirm(*pskb) == NF_DROP)
				ret = FW_BLOCK;
		}
		break;
	}

	switch (ret) {
	case FW_REJECT: {
		/* Alexey says:
		 *
		 * Generally, routing is THE FIRST thing to make, when
		 * packet enters IP stack. Before packet is routed you
		 * cannot call any service routines from IP stack.  */
		struct iphdr *iph = (*pskb)->nh.iph;

		if ((*pskb)->dst != NULL
		    || ip_route_input(*pskb, iph->daddr, iph->saddr, iph->tos,
				      (struct net_device *)in) == 0)
			icmp_send(*pskb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH,
				  0);
		return NF_DROP;
	}

	case FW_ACCEPT:
	case FW_SKIP:
		if (hooknum == NF_IP_PRE_ROUTING) {
			check_for_demasq(pskb);
			check_for_redirect(*pskb);
		} else if (hooknum == NF_IP_POST_ROUTING) {
			check_for_unredirect(*pskb);
			/* Handle ICMP errors from client here */
			if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP
			    && (*pskb)->nfct)
				check_for_masq_error(pskb);
		}
		return NF_ACCEPT;

	case FW_MASQUERADE:
		if (hooknum == NF_IP_FORWARD) {
#ifdef CONFIG_IP_VS
			/* check if it is for ip_vs */
			if (check_for_ip_vs_out(pskb, okfn) == NF_STOLEN)
				return NF_STOLEN;
#endif
//.........这里部分代码省略.........

int icmp_error(struct iphdr * __ip, int __type, 
			   int __code, struct ifnet * __if) 
{
//	uint8_t icmp_buf[sizeof(struct icmp) + IP_MAXOPTLEN + 8];
	struct icmp * icp;
	int len;

	/* TODO: 
	if (type != ICMP_REDIRECT)
		icmpstat.icps_error++; */

	/* Don't send error if not the first fragment 
	   Ref.: TCP/IP Illustrated Volume 2, pg. 325 */
	icp = (struct icmp *)__ip->opt;

	if (__ip->ip_off & ~(IP_MF | IP_DF)) {
		DCC_LOG1(LOG_WARNING, "not first fragment!; ip_off = %04x", 
				 __ip->ip_off);
		return -1;
	}

	len = MIN((__ip->hlen << 2) + 8 , ntohs(__ip->tot_len));
	memcpy((void *)&(icp->icmp_ip), __ip, len);

	/*
	if ((ip->proto == IPPROTO_ICMP) && (type != ICMP_REDIRECT) &&
	    (totlen >= iplen + ICMP_MINLEN) ) {
	 TODO: 
		icmpstat.icps_oldicmp++; 
		return -1;
	} */

	/* Don't send error in response to a multicast or broadcast packet */
	if (in_broadcast(__ip->daddr, __if) || IN_MULTICAST(__ip->daddr)) {
		DCC_LOG(LOG_INFO, "broadcast/multicast!");
		return -1;
	}

	if ((unsigned int)__type > ICMP_MAXTYPE) {
		DCC_LOG(LOG_PANIC, "icmp_error");
		return -1;
	}

	/* TODO: 
		icmpstat.icps_outhist[type]++; */

	icp->icmp_type = __type;
	icp->icmp_void = 0;
	if (__type == ICMP_PARAMETERPROB)  {
		icp->icmp_pptr = __code;
		__code = 0;
	} else {
		if ((__type == ICMP_DEST_UNREACH) && 
		    (__code == ICMP_FRAG_NEEDED) && (__if)) {
			icp->icmp_nextmtu = htons(__if->if_mtu);
		}
	}
	icp->icmp_code = __code;

	return icmp_send(__ip, icp, len);
}

/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(struct timer_list *t)
{
	struct inet_frag_queue *frag = from_timer(frag, t, timer);
	struct ipq *qp;
	struct net *net;

	qp = container_of(frag, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	rcu_read_lock();
	spin_lock(&qp->q.lock);

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);

	if (!inet_frag_evicting(&qp->q)) {
		struct sk_buff *clone, *head = qp->q.fragments;
		const struct iphdr *iph;
		int err;

		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);

		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
			goto out;

		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out;


		/* skb has no dst, perform route lookup again */
		iph = ip_hdr(head);
		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
					   iph->tos, head->dev);
		if (err)
			goto out;

		/* Only an end host needs to send an ICMP
		 * "Fragment Reassembly Timeout" message, per RFC792.
		 */
		if (frag_expire_skip_icmp(qp->user) &&
		    (skb_rtable(head)->rt_type != RTN_LOCAL))
			goto out;

		clone = skb_clone(head, GFP_ATOMIC);

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		if (clone) {
			spin_unlock(&qp->q.lock);
			icmp_send(clone, ICMP_TIME_EXCEEDED,
				  ICMP_EXC_FRAGTIME, 0);
			consume_skb(clone);
			goto out_rcu_unlock;
		}
	}
out:
	spin_unlock(&qp->q.lock);
out_rcu_unlock:
	rcu_read_unlock();
	ipq_put(qp);
}

//.........这里部分代码省略.........
		return;
	case ICMP_PARAMETERPROB:
		if (skb->h.icmph->un.gateway < hlen)
			return;

		/* So... This guy found something strange INSIDE encapsulated
		   packet. Well, he is fool, but what can we do ?
		 */
		rel_type = ICMP_PARAMETERPROB;
		rel_info = skb->h.icmph->un.gateway - hlen;
		break;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return;
		case ICMP_FRAG_NEEDED:
			/* And it is the only really necessary thing :-) */
			rel_info = ntohs(skb->h.icmph->un.frag.mtu);
			if (rel_info < hlen+68)
				return;
			rel_info -= hlen;
			/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
			if (rel_info > ntohs(eiph->tot_len))
				return;
			break;
		default:
			/* All others are translated to HOST_UNREACH.
			   rfc2003 contains "deep thoughts" about NET_UNREACH,
			   I believe, it is just ether pollution. --ANK
			 */
			rel_type = ICMP_DEST_UNREACH;
			rel_code = ICMP_HOST_UNREACH;
			break;
		}
		break;
	case ICMP_TIME_EXCEEDED:
		if (code != ICMP_EXC_TTL)
			return;
		break;
	}

	/* Prepare fake skb to feed it to icmp_send */
	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (skb2 == NULL)
		return;
	dst_release(skb2->dst);
	skb2->dst = NULL;
	skb_pull(skb2, skb->data - (u8*)eiph);
	skb2->nh.raw = skb2->data;

	/* Try to guess incoming interface */
	if (ip_route_output(&rt, eiph->saddr, 0, RT_TOS(eiph->tos), 0)) {
		kfree_skb(skb2);
		return;
	}
	skb2->dev = rt->u.dst.dev;

	/* route "incoming" packet */
	if (rt->rt_flags&RTCF_LOCAL) {
		ip_rt_put(rt);
		rt = NULL;
		if (ip_route_output(&rt, eiph->daddr, eiph->saddr, eiph->tos, 0) ||
		    rt->u.dst.dev->type != ARPHRD_IPGRE) {
			ip_rt_put(rt);
			kfree_skb(skb2);
			return;
		}
	} else {
		ip_rt_put(rt);
		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
		    skb2->dst->dev->type != ARPHRD_IPGRE) {
			kfree_skb(skb2);
			return;
		}
	}

	/* change mtu on this route */
	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
		if (rel_info > skb2->dst->pmtu) {
			kfree_skb(skb2);
			return;
		}
		skb2->dst->pmtu = rel_info;
		rel_info = htonl(rel_info);
	} else if (type == ICMP_TIME_EXCEEDED) {
		struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv;
		if (t->parms.iph.ttl) {
			rel_type = ICMP_DEST_UNREACH;
			rel_code = ICMP_HOST_UNREACH;
		}
	}

	icmp_send(skb2, rel_type, rel_code, rel_info);
	kfree_skb(skb2);
	return;
#endif
}

//.........这里部分代码省略.........
			}
			offset += 4;
		}
		if (flags&GRE_KEY) {
			key = *(__be32*)(h + offset);
			offset += 4;
		}
		if (flags&GRE_SEQ) {
			seqno = ntohl(*(__be32*)(h + offset));
			offset += 4;
		}
	}

	gre_proto = *(__be16 *)(h + 2);

	read_lock(&ipgre_lock);
	if ((tunnel = ipgre_tunnel_lookup(skb->dev,
					  iph->saddr, iph->daddr, key,
					  gre_proto))) {
		struct net_device_stats *stats = &tunnel->dev->stats;

		secpath_reset(skb);

		skb->protocol = gre_proto;
		/* WCCP version 1 and 2 protocol decoding.
		 * - Change protocol to IP
		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
		 */
		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
			skb->protocol = htons(ETH_P_IP);
			if ((*(h + offset) & 0xF0) != 0x40)
				offset += 4;
		}

		skb->mac_header = skb->network_header;
		__pskb_pull(skb, offset);
		skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
		skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
		if (ipv4_is_multicast(iph->daddr)) {
			/* Looped back packet, drop it! */
			if (skb_rtable(skb)->fl.iif == 0)
				goto drop;
			stats->multicast++;
			skb->pkt_type = PACKET_BROADCAST;
		}
#endif

		if (((flags&GRE_CSUM) && csum) ||
		    (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
			stats->rx_crc_errors++;
			stats->rx_errors++;
			goto drop;
		}
		if (tunnel->parms.i_flags&GRE_SEQ) {
			if (!(flags&GRE_SEQ) ||
			    (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
				stats->rx_fifo_errors++;
				stats->rx_errors++;
				goto drop;
			}
			tunnel->i_seqno = seqno + 1;
		}

		len = skb->len;

		/* Warning: All skb pointers will be invalidated! */
		if (tunnel->dev->type == ARPHRD_ETHER) {
			if (!pskb_may_pull(skb, ETH_HLEN)) {
				stats->rx_length_errors++;
				stats->rx_errors++;
				goto drop;
			}

			iph = ip_hdr(skb);
			skb->protocol = eth_type_trans(skb, tunnel->dev);
			skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
		}

		stats->rx_packets++;
		stats->rx_bytes += len;
		skb->dev = tunnel->dev;
		skb_dst_drop(skb);
		nf_reset(skb);

		skb_reset_network_header(skb);
		ipgre_ecn_decapsulate(iph, skb);

		netif_rx(skb);
		read_unlock(&ipgre_lock);
		return(0);
	}
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

drop:
	read_unlock(&ipgre_lock);
drop_nolock:
	kfree_skb(skb);
	return(0);
}

int ip_forward(struct sk_buff *skb)
{
	struct net_device *dev2;	/* Output device */
	struct iphdr *iph;	/* Our header */
	struct rtable *rt;	/* Route we use */
	struct ip_options * opt	= &(IPCB(skb)->opt);
	unsigned short mtu;

	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
		return NET_RX_SUCCESS;

	if (skb->pkt_type != PACKET_HOST)
		goto drop;

	skb->ip_summed = CHECKSUM_NONE;
	
	/*
	 *	According to the RFC, we must first decrease the TTL field. If
	 *	that reaches zero, we must reply an ICMP control message telling
	 *	that the packet's lifetime expired.
	 */

	iph = skb->nh.iph;
	rt = (struct rtable*)skb->dst;

	if (iph->ttl <= 1)
                goto too_many_hops;

	if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
                goto sr_failed;

	/*
	 *	Having picked a route we can now send the frame out
	 *	after asking the firewall permission to do so.
	 */

	skb->priority = rt_tos2priority(iph->tos);
	dev2 = rt->u.dst.dev;
	mtu = rt->u.dst.pmtu;

	/*
	 *	We now generate an ICMP HOST REDIRECT giving the route
	 *	we calculated.
	 */
	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr)
		ip_rt_send_redirect(skb);

	/* We are about to mangle packet. Copy it! */
	if (skb_cow(skb, dev2->hard_header_len))
		goto drop;
	iph = skb->nh.iph;

	/* Decrease ttl after skb cow done */
	ip_decrease_ttl(iph);

	/*
	 * We now may allocate a new buffer, and copy the datagram into it.
	 * If the indicated interface is up and running, kick it.
	 */

	if (skb->len > mtu && (ntohs(iph->frag_off) & IP_DF))
		goto frag_needed;

#ifdef CONFIG_IP_ROUTE_NAT
	if (rt->rt_flags & RTCF_NAT) {
		if (ip_do_nat(skb)) {
			kfree_skb(skb);
			return NET_RX_BAD;
		}
	}
#endif

	return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, dev2,
		       ip_forward_finish);

frag_needed:
	IP_INC_STATS_BH(IpFragFails);
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
        goto drop;

sr_failed:
        /*
	 *	Strict routing permits no gatewaying
	 */
         icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
         goto drop;

too_many_hops:
        /* Tell the sender its packet died... */
        icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}