/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt;
	struct flowi4 fl4 = {};
	__be32 saddr = iph->saddr;
	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
	unsigned int hh_len;

	if (addr_type == RTN_UNSPEC)
		addr_type = inet_addr_type(net, saddr);
	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
		flags |= FLOWI_FLAG_ANYSRC;
	else
		saddr = 0;

	/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
	 * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
	 */
	fl4.daddr = iph->daddr;
	fl4.saddr = saddr;
	fl4.flowi4_tos = RT_TOS(iph->tos);
	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
	fl4.flowi4_mark = skb->mark;
	fl4.flowi4_flags = flags;
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt))
		return -1;

	/* Drop old route. */
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	if (skb_dst(skb)->error)
		return -1;

#ifdef CONFIG_XFRM
	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
		struct dst_entry *dst = skb_dst(skb);
		skb_dst_set(skb, NULL);
		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
		if (IS_ERR(dst))
			return -1;
		skb_dst_set(skb, dst);
	}
#endif

	/* Change in oif may mean change in hh_len. */
	hh_len = skb_dst(skb)->dev->hard_header_len;
	if (skb_headroom(skb) < hh_len &&
	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
				0, GFP_ATOMIC))
		return -1;

	return 0;
}

/*
 *      Direct Routing transmitter
 *      Used for ANY protocol
 */
int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	      struct ip_vs_protocol *pp)
{
	struct rtable *rt;			/* Route to the other host */
	struct iphdr  *iph = ip_hdr(skb);
	int    mtu;

	EnterFunction(10);

	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
				      RT_TOS(iph->tos), 1|2)))
		goto tx_error_icmp;
	if (rt->rt_flags & RTCF_LOCAL) {
		ip_rt_put(rt);
		IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
	}

	/* MTU checking */
	mtu = dst_mtu(&rt->dst);
	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		ip_rt_put(rt);
		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
		goto tx_error;
	}

	/*
	 * Call ip_send_check because we are not sure it is called
	 * after ip_defrag. Is copy-on-write needed?
	 */
	if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
		ip_rt_put(rt);
		return NF_STOLEN;
	}
	ip_send_check(ip_hdr(skb));

	/* drop old route */
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);

	LeaveFunction(10);
	return NF_STOLEN;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	kfree_skb(skb);
	LeaveFunction(10);
	return NF_STOLEN;
}

/* Try to route the packet according to the routing keys specified in
 * route_info. Keys are :
 *  - ifindex : 
 *      0 if no oif preferred, 
 *      otherwise set to the index of the desired oif
 *  - route_info->gw :
 *      0 if no gateway specified,
 *      otherwise set to the next host to which the pkt must be routed
 * If success, skb->dev is the output device to which the packet must 
 * be sent and skb->dst is not NULL
 *
 * RETURN: -1 if an error occured
 *          1 if the packet was succesfully routed to the 
 *            destination desired
 *          0 if the kernel routing table could not route the packet
 *            according to the keys specified
 */
static int route(struct sk_buff *skb,
		 unsigned int ifindex,
		 const struct ipt_route_target_info *route_info)
{
	int err;
	struct rtable *rt;
	struct iphdr *iph = ip_hdr(skb);
	struct flowi fl = {
		.oif = ifindex,
		.nl_u = {
			.ip4_u = {
				.daddr = iph->daddr,
				.saddr = 0,
				.tos = RT_TOS(iph->tos),
				.scope = RT_SCOPE_UNIVERSE,
			}
		} 
	};
	
	/* The destination address may be overloaded by the target */
	if (route_info->gw)
		fl.fl4_dst = route_info->gw;
	
	/* Trying to route the packet using the standard routing table. */
	if ((err = ip_route_output_key(&init_net,&rt, &fl))) {
		if (net_ratelimit()) 
			pr_debug("ipt_ROUTE: couldn't route pkt (err: %i)",err);
		return -1;
	}
	
	/* Drop old route. */
	skb_dst_drop(skb);

	/* Success if no oif specified or if the oif correspond to the 
	 * one desired */
	if (!ifindex || rt->dst.dev->ifindex == ifindex) {
		skb_dst_set(skb, &rt->dst);
		skb->dev = skb_dst(skb)->dev;
		skb->protocol = htons(ETH_P_IP);
		return 1;
	}
	
	/* The interface selected by the routing table is not the one
	 * specified by the user. This may happen because the dst address
	 * is one of our own addresses.
	 */
	if (net_ratelimit()) 
		pr_debug("ipt_ROUTE: failed to route as desired gw, oif=%i (got oif=%i)\n", 
		//pr_debug("ipt_ROUTE: failed to route as desired gw=%u.%u.%u.%u oif=%i (got oif=%i)\n", 
		       ifindex, rt->dst.dev->ifindex);
		       //NIPQUAD(route_info->gw), ifindex, rt->dst.dev->ifindex);
	
	return 0;
}

static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct net *net = ovs_dp_get_net(vport->dp);
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
	struct ovs_key_ipv4_tunnel *tun_key;
	struct rtable *rt;
	struct flowi4 fl;
	__be16 src_port;
	__be16 df;
	int err;

	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
		err = -EINVAL;
		goto error;
	}

	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_UDP;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		goto error;
	}

	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
		htons(IP_DF) : 0;

	skb->ignore_df = 1;

	src_port = udp_flow_src_port(net, skb, 0, 0, true);

	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
			     fl.saddr, tun_key->ipv4_dst,
			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
			     src_port, dst_port,
			     htonl(be64_to_cpu(tun_key->tun_id) << 8),
			     false);
	if (err < 0)
		ip_rt_put(rt);
	return err;
error:
	kfree_skb(skb);
	return err;
}

static inline struct rtable *route_mirror(struct sk_buff *skb, int local)
{
        struct iphdr *iph = skb->nh.iph;
	struct dst_entry *odst;
	struct rt_key key = {};
	struct rtable *rt;

	if (local) {
		key.dst = iph->saddr;
		key.src = iph->daddr;
		key.tos = RT_TOS(iph->tos);

		if (ip_route_output_key(&rt, &key) != 0)
			return NULL;
	} else {
		/* non-local src, find valid iif to satisfy
		 * rp-filter when calling ip_route_input. */
		key.dst = iph->daddr;
		if (ip_route_output_key(&rt, &key) != 0)
			return NULL;

		odst = skb->dst;
		if (ip_route_input(skb, iph->saddr, iph->daddr,
		                   RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
			dst_release(&rt->u.dst);
			return NULL;
		}
		dst_release(&rt->u.dst);
		rt = (struct rtable *)skb->dst;
		skb->dst = odst;
	}

	if (rt->u.dst.error) {
		dst_release(&rt->u.dst);
		rt = NULL;
	}

	return rt;
}

static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
					   struct net_device *vrf_dev)
{
	struct iphdr *ip4h = ip_hdr(skb);
	int ret = NET_XMIT_DROP;
	struct flowi4 fl4 = {
		/* needed to match OIF rule */
		.flowi4_oif = vrf_dev->ifindex,
		.flowi4_iif = LOOPBACK_IFINDEX,
		.flowi4_tos = RT_TOS(ip4h->tos),
		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
				FLOWI_FLAG_SKIP_NH_OIF,
		.daddr = ip4h->daddr,
	};

	if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
		goto err;

	if (!ip4h->saddr) {
		ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
					       RT_SCOPE_LINK);
	}

	ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
	if (unlikely(net_xmit_eval(ret)))
		vrf_dev->stats.tx_errors++;
	else
		ret = NET_XMIT_SUCCESS;

out:
	return ret;
err:
	vrf_tx_error(vrf_dev, skb);
	goto out;
}

static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
	/* strip the ethernet header added for pass through VRF device */
	__skb_pull(skb, skb_network_offset(skb));

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return vrf_process_v4_outbound(skb, dev);
	case htons(ETH_P_IPV6):
		return vrf_process_v6_outbound(skb, dev);
	default:
		vrf_tx_error(dev, skb);
		return NET_XMIT_DROP;
	}
}

int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
			       struct net *net,
			       const struct ovs_tunnel_info *tun_info,
			       u8 ipproto,
			       u32 skb_mark,
			       __be16 tp_src,
			       __be16 tp_dst)
{
	const struct ovs_key_ipv4_tunnel *tun_key;
	struct rtable *rt;
	struct flowi4 fl;

	if (unlikely(!tun_info))
		return -EINVAL;

	tun_key = &tun_info->tunnel;

	/* Route lookup to get srouce IP address.
	 * The process may need to be changed if the corresponding process
	 * in vports ops changed.
	 */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb_mark;
	fl.flowi4_proto = ipproto;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		return PTR_ERR(rt);

	ip_rt_put(rt);

	/* Generate egress_tun_info based on tun_info,
	 * saddr, tp_src and tp_dst
	 */
	__ovs_flow_tun_info_init(egress_tun_info,
				 fl.saddr, tun_key->ipv4_dst,
				 tun_key->ipv4_tos,
				 tun_key->ipv4_ttl,
				 tp_src, tp_dst,
				 tun_key->tun_id,
				 tun_key->tun_flags,
				 tun_info->options,
				 tun_info->options_len);

	return 0;
}

static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct net *net = ovs_dp_get_net(vport->dp);
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->sport;
	struct rtable *rt;
	struct flowi fl;
	__be16 src_port;
	int port_min;
	int port_max;
	__be16 df;
	int err;

	if (unlikely(!OVS_CB(skb)->tun_key)) {
		err = -EINVAL;
		goto error;
	}

	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.fl4_dst = OVS_CB(skb)->tun_key->ipv4_dst;
	fl.fl4_src = OVS_CB(skb)->tun_key->ipv4_src;
	fl.fl4_tos = RT_TOS(OVS_CB(skb)->tun_key->ipv4_tos);
	fl.mark = skb->mark;
	fl.proto = IPPROTO_UDP;

	err = ip_route_output_key(net, &rt, &fl);
	if (err)
		goto error;

	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
		htons(IP_DF) : 0;

	skb->local_df = 1;

	inet_get_local_port_range(&port_min, &port_max);
	src_port = vxlan_src_port(port_min, port_max, skb);

	err = vxlan_xmit_skb(net, vxlan_port->vs, rt, skb,
			     fl.fl4_src, OVS_CB(skb)->tun_key->ipv4_dst,
			     OVS_CB(skb)->tun_key->ipv4_tos,
			     OVS_CB(skb)->tun_key->ipv4_ttl, df,
			     src_port, dst_port,
			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
	if (err < 0)
		ip_rt_put(rt);
error:
	return err;
}

static struct rtable *gre_get_rt(struct sk_buff *skb,
				 struct net_device *dev,
				 struct flowi4 *fl,
				 const struct ip_tunnel_key *key)
{
	struct net *net = dev_net(dev);

	memset(fl, 0, sizeof(*fl));
	fl->daddr = key->u.ipv4.dst;
	fl->saddr = key->u.ipv4.src;
	fl->flowi4_tos = RT_TOS(key->tos);
	fl->flowi4_mark = skb->mark;
	fl->flowi4_proto = IPPROTO_GRE;

	return ip_route_output_key(net, fl);
}

static int ip_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);

	iph = &tunnel->parms.iph;

	/* Guess output device to choose reasonable mtu and needed_headroom */
	if (iph->daddr) {
		struct flowi4 fl4;
		struct rtable *rt;

		rt = ip_route_output_tunnel(dev_net(dev), &fl4,
					    tunnel->parms.iph.protocol,
					    iph->daddr, iph->saddr,
					    tunnel->parms.o_key,
					    RT_TOS(iph->tos),
					    tunnel->parms.link);
		if (!IS_ERR(rt)) {
			tdev = rt->dst.dev;
			ip_rt_put(rt);
		}
		if (dev->type != ARPHRD_ETHER)
			dev->flags |= IFF_POINTOPOINT;
	}

	if (!tdev && tunnel->parms.link)
		tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);

	if (tdev) {
		hlen = tdev->hard_header_len + tdev->needed_headroom;
		mtu = tdev->mtu;
	}
	dev->iflink = tunnel->parms.link;

	dev->needed_headroom = t_hlen + hlen;
	mtu -= (dev->hard_header_len + t_hlen);

	if (mtu < 68)
		mtu = 68;

	return mtu;
}

static struct rtable *ovs_tunnel_route_lookup(struct net *net,
					      const struct ip_tunnel_key *key,
					      u32 mark,
					      struct flowi4 *fl,
					      u8 protocol)
{
	struct rtable *rt;

	memset(fl, 0, sizeof(*fl));
	fl->daddr = key->u.ipv4.dst;
	fl->saddr = key->u.ipv4.src;
	fl->flowi4_tos = RT_TOS(key->tos);
	fl->flowi4_mark = mark;
	fl->flowi4_proto = protocol;

	rt = ip_route_output_key(net, fl);
	return rt;
}

static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct net *net = ovs_dp_get_net(vport->dp);
	struct ovs_key_ipv4_tunnel *tun_key;
	struct flowi4 fl;
	struct rtable *rt;
	int min_headroom;
	int tunnel_hlen;
	__be16 df;
	int err;

	if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
		err = -EINVAL;
		goto error;
	}

	tun_key = OVS_CB(skb)->egress_tun_key;
	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_GRE;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		return PTR_ERR(rt);

	tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);

	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
			+ tunnel_hlen + sizeof(struct iphdr)
			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
		int head_delta = SKB_DATA_ALIGN(min_headroom -
						skb_headroom(skb) +
						16);
		err = pskb_expand_head(skb, max_t(int, head_delta, 0),
					0, GFP_ATOMIC);
		if (unlikely(err))
			goto err_free_rt;
	}

static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel_info *tun_info;
	struct net *net = dev_net(dev);
	const struct ip_tunnel_key *key;
	struct flowi4 fl;
	struct rtable *rt;
	int min_headroom;
	int tunnel_hlen;
	__be16 df, flags;
	int err;

	tun_info = skb_tunnel_info(skb, AF_INET);
	if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX))
		goto err_free_skb;

	key = &tun_info->key;
	memset(&fl, 0, sizeof(fl));
	fl.daddr = key->ipv4_dst;
	fl.saddr = key->ipv4_src;
	fl.flowi4_tos = RT_TOS(key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_GRE;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		goto err_free_skb;

	tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);

	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
			+ tunnel_hlen + sizeof(struct iphdr);
	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
		int head_delta = SKB_DATA_ALIGN(min_headroom -
						skb_headroom(skb) +
						16);
		err = pskb_expand_head(skb, max_t(int, head_delta, 0),
				       0, GFP_ATOMIC);
		if (unlikely(err))
			goto err_free_rt;
	}

static int route_mirror(struct sk_buff *skb)
{
        struct iphdr *iph = skb->nh.iph;
	struct rtable *rt;

	/* Backwards */
	if (ip_route_output(&rt, iph->saddr, iph->daddr,
			    RT_TOS(iph->tos) | RTO_CONN,
			    0)) {
		return 0;
	}

	/* check if the interface we are leaving by is the same as the
           one we arrived on */
	if (skb->dev == rt->u.dst.dev) {
		/* Drop old route. */
		dst_release(skb->dst);
		skb->dst = &rt->u.dst;
		return 1;
	}
	return 0;
}

/* With a chainsaw... */
static int route_me_harder(struct sk_buff *skb)
{
    struct iphdr *iph = skb->nh.iph;
    struct rtable *rt;

    struct rt_key key = {
	dst:iph->daddr, src:iph->saddr,
	oif:skb->sk ? skb->sk->bound_dev_if : 0,
	tos:RT_TOS(iph->tos) | RTO_CONN,
#ifdef CONFIG_IP_ROUTE_FWMARK
	fwmark:skb->nfmark
#endif
    };

    if (ip_route_output_key(&rt, &key) != 0)
	return -EINVAL;

    /* Drop old route. */
    dst_release(skb->dst);
    skb->dst = &rt->u.dst;
    return 0;
}

static struct rtable *route_packet_ipv4(struct sk_buff *skb)
{
	struct iphdr *ip_header = ip_hdr(skb);
	struct flowi fl;
	struct rtable *table;

	memset(&fl, 0, sizeof(fl));
	fl.u.ip4.daddr = ip_header->daddr;
	fl.flowi_tos = RT_TOS(ip_header->tos);
	fl.flowi_proto = skb->protocol;

	table = ip_route_output_key(&init_net, &fl.u.ip4);
	if (!table) {
		log_err(ERR_ROUTE_FAILED, "ip_route_output_key() returned NULL. Cannot route packet.");
		return NULL;
	}
	if (IS_ERR(table)) {
		log_err(ERR_ROUTE_FAILED, "ip_route_output_key() returned %p. Cannot route packet.", table);
		return NULL;
	}

	return table;
}

void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
		    const struct iphdr *tnl_params, const u8 protocol)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *inner_iph;
	struct flowi4 fl4;
	u8     tos, ttl;
	__be16 df;
	struct rtable *rt;		/* Route to the other host */
	unsigned int max_headroom;	/* The extra header space needed */
	__be32 dst;
	int err;

	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);

	dst = tnl_params->daddr;
	if (dst == 0) {
		/* NBMA tunnel */

		if (skb_dst(skb) == NULL) {
			dev->stats.tx_fifo_errors++;
			goto tx_error;
		}

		if (skb->protocol == htons(ETH_P_IP)) {
			rt = skb_rtable(skb);
			dst = rt_nexthop(rt, inner_iph->daddr);
		}
#if IS_ENABLED(CONFIG_IPV6)
		else if (skb->protocol == htons(ETH_P_IPV6)) {
			const struct in6_addr *addr6;
			struct neighbour *neigh;
			bool do_tx_error_icmp;
			int addr_type;

			neigh = dst_neigh_lookup(skb_dst(skb),
						 &ipv6_hdr(skb)->daddr);
			if (neigh == NULL)
				goto tx_error;

			addr6 = (const struct in6_addr *)&neigh->primary_key;
			addr_type = ipv6_addr_type(addr6);

			if (addr_type == IPV6_ADDR_ANY) {
				addr6 = &ipv6_hdr(skb)->daddr;
				addr_type = ipv6_addr_type(addr6);
			}

			if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
				do_tx_error_icmp = true;
			else {
				do_tx_error_icmp = false;
				dst = addr6->s6_addr32[3];
			}
			neigh_release(neigh);
			if (do_tx_error_icmp)
				goto tx_error_icmp;
		}
#endif
		else
			goto tx_error;
	}

	tos = tnl_params->tos;
	if (tos & 0x1) {
		tos &= ~0x1;
		if (skb->protocol == htons(ETH_P_IP))
			tos = inner_iph->tos;
		else if (skb->protocol == htons(ETH_P_IPV6))
			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
	}

	rt = ip_route_output_tunnel(tunnel->net, &fl4,
				    protocol,
				    dst, tnl_params->saddr,
				    tunnel->parms.o_key,
				    RT_TOS(tos),
				    tunnel->parms.link);
	if (IS_ERR(rt)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error;
	}
	if (rt->dst.dev == dev) {
		ip_rt_put(rt);
		dev->stats.collisions++;
		goto tx_error;
	}

	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
		ip_rt_put(rt);
		goto tx_error;
	}

	if (tunnel->net != dev_net(dev))
		skb_scrub_packet(skb);

	if (tunnel->err_count > 0) {
		if (time_before(jiffies,
				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
			tunnel->err_count--;
//.........这里部分代码省略.........

static int ipip_tunnel_xmit(struct sk_buff *skb, struct device *dev)
{
	struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
	struct net_device_stats *stats = &tunnel->stat;
	struct iphdr  *tiph = &tunnel->parms.iph;
	u8     tos = tunnel->parms.iph.tos;
	u16    df = tiph->frag_off;
	struct rtable *rt;     			/* Route to the other host */
	struct device *tdev;			/* Device to other host */
	struct iphdr  *old_iph = skb->nh.iph;
	struct iphdr  *iph;			/* Our new IP header */
	int    max_headroom;			/* The extra header space needed */
	u32    dst = tiph->daddr;
	int    mtu;

	if (tunnel->recursion++) {
		tunnel->stat.collisions++;
		goto tx_error;
	}

	if (skb->protocol != __constant_htons(ETH_P_IP))
		goto tx_error;

	if (tos&1)
		tos = old_iph->tos;

	if (!dst) {
		/* NBMA tunnel */
		if ((rt = (struct rtable*)skb->dst) == NULL) {
			tunnel->stat.tx_fifo_errors++;
			goto tx_error;
		}
		if ((dst = rt->rt_gateway) == 0)
			goto tx_error_icmp;
	}

	if (ip_route_output(&rt, dst, tiph->saddr, RT_TOS(tos), tunnel->parms.link)) {
		tunnel->stat.tx_carrier_errors++;
		goto tx_error_icmp;
	}
	tdev = rt->u.dst.dev;

	if (tdev == dev) {
		ip_rt_put(rt);
		tunnel->stat.collisions++;
		goto tx_error;
	}

	mtu = rt->u.dst.pmtu - sizeof(struct iphdr);
	if (mtu < 68) {
		tunnel->stat.collisions++;
		ip_rt_put(rt);
		goto tx_error;
	}
	if (skb->dst && mtu < skb->dst->pmtu)
		skb->dst->pmtu = mtu;

	df |= (old_iph->frag_off&__constant_htons(IP_DF));

	if ((old_iph->frag_off&__constant_htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) {
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
		ip_rt_put(rt);
		goto tx_error;
	}

	if (tunnel->err_count > 0) {
		if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
			tunnel->err_count--;
			dst_link_failure(skb);
		} else
			tunnel->err_count = 0;
	}

	skb->h.raw = skb->nh.raw;

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom = (((tdev->hard_header_len+15)&~15)+sizeof(struct iphdr));

	if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
		if (!new_skb) {
			ip_rt_put(rt);
  			stats->tx_dropped++;
			dev_kfree_skb(skb);
			tunnel->recursion--;
			return 0;
		}
		if (skb->sk)
			skb_set_owner_w(new_skb, skb->sk);
		dev_kfree_skb(skb);
		skb = new_skb;
	}

	skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

//.........这里部分代码省略.........

/* This requires some explaining. If DNAT has taken place,
 * we will need to fix up the destination Ethernet address.
 *
 * There are two cases to consider:
 * 1. The packet was DNAT'ed to a device in the same bridge
 *    port group as it was received on. We can still bridge
 *    the packet.
 * 2. The packet was DNAT'ed to a different device, either
 *    a non-bridged device or another bridge port group.
 *    The packet will need to be routed.
 *
 * The correct way of distinguishing between these two cases is to
 * call ip_route_input() and to look at skb->dst->dev, which is
 * changed to the destination device if ip_route_input() succeeds.
 *
 * Let's first consider the case that ip_route_input() succeeds:
 *
 * If the output device equals the logical bridge device the packet
 * came in on, we can consider this bridging. The corresponding MAC
 * address will be obtained in br_nf_pre_routing_finish_bridge.
 * Otherwise, the packet is considered to be routed and we just
 * change the destination MAC address so that the packet will
 * later be passed up to the IP stack to be routed. For a redirected
 * packet, ip_route_input() will give back the localhost as output device,
 * which differs from the bridge device.
 *
 * Let's now consider the case that ip_route_input() fails:
 *
 * This can be because the destination address is martian, in which case
 * the packet will be dropped.
 * If IP forwarding is disabled, ip_route_input() will fail, while
 * ip_route_output_key() can return success. The source
 * address for ip_route_output_key() is set to zero, so ip_route_output_key()
 * thinks we're handling a locally generated packet and won't care
 * if IP forwarding is enabled. If the output device equals the logical bridge
 * device, we proceed as if ip_route_input() succeeded. If it differs from the
 * logical bridge port or if ip_route_output_key() fails we drop the packet.
 */
static int br_nf_pre_routing_finish(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct iphdr *iph = ip_hdr(skb);
	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
	struct rtable *rt;
	int err;

	if (nf_bridge->mask & BRNF_PKT_TYPE) {
		skb->pkt_type = PACKET_OTHERHOST;
		nf_bridge->mask ^= BRNF_PKT_TYPE;
	}
	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
	if (dnat_took_place(skb)) {
		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
			struct in_device *in_dev = __in_dev_get_rcu(dev);

			/* If err equals -EHOSTUNREACH the error is due to a
			 * martian destination or due to the fact that
			 * forwarding is disabled. For most martian packets,
			 * ip_route_output_key() will fail. It won't fail for 2 types of
			 * martian destinations: loopback destinations and destination
			 * 0.0.0.0. In both cases the packet will be dropped because the
			 * destination is the loopback device and not the bridge. */
			if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
				goto free_skb;

			rt = ip_route_output(dev_net(dev), iph->daddr, 0,
					     RT_TOS(iph->tos), 0);
			if (!IS_ERR(rt)) {
				/* - Bridged-and-DNAT'ed traffic doesn't
				 *   require ip_forwarding. */
				if (rt->dst.dev == dev) {
					skb_dst_set(skb, &rt->dst);
					goto bridged_dnat;
				}
				ip_rt_put(rt);
			}
free_skb:
			kfree_skb(skb);
			return 0;
		} else {
			if (skb_dst(skb)->dev == dev) {
bridged_dnat:
				skb->dev = nf_bridge->physindev;
				nf_bridge_update_protocol(skb);
				nf_bridge_push_encap_header(skb);
				NF_HOOK_THRESH(NFPROTO_BRIDGE,
					       NF_BR_PRE_ROUTING,
					       skb, skb->dev, NULL,
					       br_nf_pre_routing_finish_bridge,
					       1);
				return 0;
			}
			memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
			skb->pkt_type = PACKET_HOST;
		}
	} else {
		rt = bridge_parent_rtable(nf_bridge->physindev);
		if (!rt) {
			kfree_skb(skb);
			return 0;
//.........这里部分代码省略.........

//.........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
}