int iptunnel_xmit(struct net *net, struct rtable *rt,
		  struct sk_buff *skb,
		  __be32 src, __be32 dst, __u8 proto,
		  __u8 tos, __u8 ttl, __be16 df)
{
	int pkt_len = skb->len;
	struct iphdr *iph;
	int err;

	nf_reset(skb);
	secpath_reset(skb);
	skb_clear_rxhash(skb);
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt_dst(rt));
#if 0
	/* Do not clear ovs_skb_cb.  It will be done in gso code. */
	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif

	/* Push down and install the IP header. */
	__skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);

	iph = ip_hdr(skb);

	iph->version	=	4;
	iph->ihl	=	sizeof(struct iphdr) >> 2;
	iph->frag_off	=	df;
	iph->protocol	=	proto;
	iph->tos	=	tos;
	iph->daddr	=	dst;
	iph->saddr	=	src;
	iph->ttl	=	ttl;
	__ip_select_ident(iph, &rt_dst(rt), (skb_shinfo(skb)->gso_segs ?: 1) - 1);

	err = ip_local_out(skb);
	if (unlikely(net_xmit_eval(err)))
		pkt_len = 0;
	return pkt_len;
}

static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4,
			    struct net_device *vrf_dev)
{
	struct rtable *rt;
	int err = 1;

	rt = ip_route_output_flow(dev_net(vrf_dev), fl4, NULL);
	if (IS_ERR(rt))
		goto out;

	/* TO-DO: what about broadcast ? */
	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
		ip_rt_put(rt);
		goto out;
	}

	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);
	err = 0;
out:
	return err;
}

static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
			     struct in6_addr *saddr, struct in6_addr *daddr,
			     __u8 proto, __u8 prio, __u8 ttl)
{
	struct ipv6hdr *ip6h;

	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
			    | IPSKB_REROUTED);
	skb_dst_set(skb, dst_clone(dst));

	__skb_push(skb, sizeof(*ip6h));
	skb_reset_network_header(skb);
	ip6h		  = ipv6_hdr(skb);
	ip6_flow_hdr(ip6h, prio, htonl(0));
	ip6h->payload_len = htons(skb->len);
	ip6h->nexthdr     = proto;
	ip6h->hop_limit   = ttl;
	ip6h->daddr	  = *daddr;
	ip6h->saddr	  = *saddr;
	ip6h->payload_len = htons(skb->len - sizeof(*ip6h));
}

int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
                         struct sk_buff *skb,
                         struct net_device *dev, struct in6_addr *saddr,
                         struct in6_addr *daddr,
                         __u8 prio, __u8 ttl, __be16 src_port,
                         __be16 dst_port, bool nocheck)
{
    struct udphdr *uh;
    struct ipv6hdr *ip6h;

    __skb_push(skb, sizeof(*uh));
    skb_reset_transport_header(skb);
    uh = udp_hdr(skb);

    uh->dest = dst_port;
    uh->source = src_port;

    uh->len = htons(skb->len);

    memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
    IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
                          | IPSKB_REROUTED);
    skb_dst_set(skb, dst);

    udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);

    __skb_push(skb, sizeof(*ip6h));
    skb_reset_network_header(skb);
    ip6h		  = ipv6_hdr(skb);
    ip6_flow_hdr(ip6h, prio, htonl(0));
    ip6h->payload_len = htons(skb->len);
    ip6h->nexthdr     = IPPROTO_UDP;
    ip6h->hop_limit   = ttl;
    ip6h->daddr	  = *daddr;
    ip6h->saddr	  = *saddr;

    ip6tunnel_xmit(sk, skb, dev);
    return 0;
}

void ndisc_send_skb(struct sk_buff *skb,
		    struct net_device *dev,
		    struct neighbour *neigh,
		    const struct in6_addr *daddr,
		    const struct in6_addr *saddr,
		    struct icmp6hdr *icmp6h)
{
	struct flowi6 fl6;
	struct dst_entry *dst;
	struct net *net = dev_net(dev);
	struct sock *sk = net->ipv6.ndisc_sk;
	struct inet6_dev *idev;
	int err;
	u8 type;

	type = icmp6h->icmp6_type;

	icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
	dst = icmp6_dst_alloc(dev, neigh, &fl6);
	if (IS_ERR(dst)) {
		kfree_skb(skb);
		return;
	}

	skb_dst_set(skb, dst);

	rcu_read_lock();
	idev = __in6_dev_get(dst->dev);
	IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);

	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
		      dst_output);
	if (!err) {
		ICMP6MSGOUT_INC_STATS(net, idev, type);
		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
	}

	rcu_read_unlock();
}

/* Local traffic destined to local address. Reinsert the packet to rx
 * path, similar to loopback handling.
 */
static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
			  struct dst_entry *dst)
{
	int len = skb->len;

	skb_orphan(skb);

	skb_dst_set(skb, dst);

	/* set pkt_type to avoid skb hitting packet taps twice -
	 * once on Tx and again in Rx processing
	 */
	skb->pkt_type = PACKET_LOOPBACK;

	skb->protocol = eth_type_trans(skb, dev);

	if (likely(netif_rx(skb) == NET_RX_SUCCESS))
		vrf_rx_stats(dev, len);
	else
		this_cpu_inc(dev->dstats->rx_drps);

	return NETDEV_TX_OK;
}

int nat64_send_packet_ipv6(struct sk_buff *skb) 
{
	// Function based on Ecdysis's nat64_output_ipv4
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct flowi fl;
	struct dst_entry *dst;

	skb->protocol = htons(ETH_P_IPV6);

	memset(&fl, 0, sizeof(fl));
	
	if(!&(fl.fl6_src)) {
		return -EINVAL;
	}
	fl.fl6_src = iph->saddr;
	fl.fl6_dst = iph->daddr;
	fl.fl6_flowlabel = 0;
	fl.proto = skb->protocol;

	dst = ip6_route_output(&init_net, NULL, &fl);

	if (!dst) {
		pr_warning("error: ip6_route_output failed");
		return -EINVAL;
	}

	skb->dev = dst->dev;

	skb_dst_set(skb, dst);

	if(ip6_local_out(skb)) {
		pr_warning("nf_NAT64: ip6_local_out failed.");
		return -EINVAL;
	}

	return 0;	
}

// this method will send the message to the destination machine using ipv4
static int cse536_sendmsg(char *data, size_t len)
{
	struct sk_buff *skb;
	struct iphdr *iph;
	struct rtable *rt;
	struct net *net = &init_net;
	unsigned char *skbdata;

	// create and setup an sk_buff	
	skb = alloc_skb(sizeof(struct iphdr) + 4096, GFP_ATOMIC);
	skb_reserve(skb, sizeof(struct iphdr) + 1500);
	skbdata = skb_put(skb, len);
//	skb->csum = csum_and_copy_from_user(data, skbdata, len, 0, &err);
	memcpy(skbdata, data, len);

	// setup and add the ip header
	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	iph->version  = 4;
	iph->ihl      = 5;
	iph->tos      = 0;
	iph->frag_off = 0;
	iph->ttl      = 64;
	iph->daddr    = cse536_daddr;
	iph->saddr    = cse536_saddr;
	iph->protocol = IPPROTO_CSE536;	// my protocol number
	iph->id       = htons(1);
	iph->tot_len  = htons(skb->len);

	// get the route. this seems to be necessary, does not work without
	rt = ip_route_output(net, cse536_daddr, cse536_saddr, 0,0);	
	skb_dst_set(skb, &rt->dst);
	
	//printk("skb data: %s", skbdata);
	return ip_local_out(skb);
}

void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
		   __be32 src, __be32 dst, __u8 proto,
		   __u8 tos, __u8 ttl, __be16 df, bool xnet)
{
	int pkt_len = skb->len - skb_inner_network_offset(skb);
	struct net *net = dev_net(rt->dst.dev);
	struct net_device *dev = skb->dev;
	struct iphdr *iph;
	int err;

	skb_scrub_packet(skb, xnet);

	skb_clear_hash(skb);
	skb_dst_set(skb, &rt->dst);
	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));

	/* Push down and install the IP header. */
	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);

	iph = ip_hdr(skb);

	iph->version	=	4;
	iph->ihl	=	sizeof(struct iphdr) >> 2;
	iph->frag_off	=	df;
	iph->protocol	=	proto;
	iph->tos	=	tos;
	iph->daddr	=	dst;
	iph->saddr	=	src;
	iph->ttl	=	ttl;
	__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);

	err = ip_local_out(net, sk, skb);
	if (unlikely(net_xmit_eval(err)))
		pkt_len = 0;
	iptunnel_xmit_stats(dev, pkt_len);
}

int skb_route(struct sk_buff *skb, void *pkt)
{
	struct dst_entry *dst;

	switch (get_l3_proto(pkt)) {
	case 6:
		dst = route_ipv6(pkt);
		break;
	case 4:
		dst = route_ipv4(pkt);
		break;
	default:
		log_err("Invalid mode: %u", get_l3_proto(pkt));
		return -EINVAL;
	}

	if (!dst)
		return -EINVAL;

	(skb)->dev = dst->dev;
	skb_dst_set(skb, dst);

	return 0;
}

int ip6_push_pending_frames(struct sock *sk)
{
	struct sk_buff *skb, *tmp_skb;
	struct sk_buff **tail_skb;
	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct net *net = sock_net(sk);
	struct ipv6hdr *hdr;
	struct ipv6_txoptions *opt = np->cork.opt;
	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
	unsigned char proto = fl6->flowi6_proto;
	int err = 0;

	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
		goto out;
	tail_skb = &(skb_shinfo(skb)->frag_list);

	/* move skb->data to ip header from ext header */
	if (skb->data < skb_network_header(skb))
		__skb_pull(skb, skb_network_offset(skb));
	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
		__skb_pull(tmp_skb, skb_network_header_len(skb));
		*tail_skb = tmp_skb;
		tail_skb = &(tmp_skb->next);
		skb->len += tmp_skb->len;
		skb->data_len += tmp_skb->len;
		skb->truesize += tmp_skb->truesize;
		tmp_skb->destructor = NULL;
		tmp_skb->sk = NULL;
	}

	/* Allow local fragmentation. */
	if (np->pmtudisc < IPV6_PMTUDISC_DO)
		skb->local_df = 1;

	ipv6_addr_copy(final_dst, &fl6->daddr);
	__skb_pull(skb, skb_network_header_len(skb));
	if (opt && opt->opt_flen)
		ipv6_push_frag_opts(skb, opt, &proto);
	if (opt && opt->opt_nflen)
		ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);

	skb_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	hdr = ipv6_hdr(skb);

	*(__be32*)hdr = fl6->flowlabel |
		     htonl(0x60000000 | ((int)np->cork.tclass << 20));

	hdr->hop_limit = np->cork.hop_limit;
	hdr->nexthdr = proto;
	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
	ipv6_addr_copy(&hdr->daddr, final_dst);

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;

	skb_dst_set(skb, dst_clone(&rt->dst));
	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
	if (proto == IPPROTO_ICMPV6) {
		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));

		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
	}

	err = ip6_local_out(skb);
	if (err) {
		if (err > 0)
			err = net_xmit_errno(err);
		if (err)
			goto error;
	}

out:
	ip6_cork_release(inet, np);
	return err;
error:
	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
	goto out;
}

static int xfrm_output_one(struct sk_buff *skb, int err)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;
	struct net *net = xs_net(x);

	if (err <= 0)
		goto resume;

	do {
		err = xfrm_state_check_space(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			goto error_nolock;
		}

		err = x->outer_mode->output(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
			goto error_nolock;
		}

		spin_lock_bh(&x->lock);
		err = xfrm_state_check_expire(x);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
			goto error;
		}

		if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
			XFRM_SKB_CB(skb)->seq.output = ++x->replay.oseq;
			if (unlikely(x->replay.oseq == 0)) {
				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
				x->replay.oseq--;
				xfrm_audit_state_replay_overflow(x, skb);
				err = -EOVERFLOW;
				goto error;
			}
			if (xfrm_aevent_is_on(net))
				xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
		}

		x->curlft.bytes += skb->len;
		x->curlft.packets++;

		spin_unlock_bh(&x->lock);

		err = x->type->output(x, skb);
		if (err == -EINPROGRESS)
			goto out_exit;

resume:
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			goto error_nolock;
		}

		dst = dst_pop(dst);
		if (!dst) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			err = -EHOSTUNREACH;
			goto error_nolock;
		}
		skb_dst_set(skb, dst);
		x = dst->xfrm;
	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));

	err = 0;

out_exit:
	return err;
error:
	spin_unlock_bh(&x->lock);
error_nolock:
	kfree_skb(skb);
	goto out_exit;
}

/* Send RST reply */
static void send_reset(struct net *net, struct sk_buff *oldskb)
{
	struct sk_buff *nskb;
	struct tcphdr otcph, *tcph;
	unsigned int otcplen, hh_len;
	int tcphoff, needs_ack;
	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
	struct ipv6hdr *ip6h;
#define DEFAULT_TOS_VALUE	0x0U
	const __u8 tclass = DEFAULT_TOS_VALUE;
	struct dst_entry *dst = NULL;
	u8 proto;
	struct flowi fl;

	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
		pr_debug("addr is not unicast.\n");
		return;
	}

	proto = oip6h->nexthdr;
	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);

	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
		pr_debug("Cannot get TCP header.\n");
		return;
	}

	otcplen = oldskb->len - tcphoff;

	/* IP header checks: fragment, too short. */
	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
		pr_debug("proto(%d) != IPPROTO_TCP, "
			 "or too short. otcplen = %d\n",
			 proto, otcplen);
		return;
	}

	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
		BUG();

	/* No RST for RST. */
	if (otcph.rst) {
		pr_debug("RST is set\n");
		return;
	}

	/* Check checksum. */
	if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
			    skb_checksum(oldskb, tcphoff, otcplen, 0))) {
		pr_debug("TCP checksum is invalid\n");
		return;
	}

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr);
	ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
	fl.fl_ip_sport = otcph.dest;
	fl.fl_ip_dport = otcph.source;
	security_skb_classify_flow(oldskb, &fl);
	dst = ip6_route_output(net, NULL, &fl);
	if (dst == NULL || dst->error) {
		dst_release(dst);
		return;
	}
	if (xfrm_lookup(net, &dst, &fl, NULL, 0))
		return;

	hh_len = (dst->dev->hard_header_len + 15)&~15;
	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
			 + sizeof(struct tcphdr) + dst->trailer_len,
			 GFP_ATOMIC);

	if (!nskb) {
		if (net_ratelimit())
			pr_debug("cannot alloc skb\n");
		dst_release(dst);
		return;
	}

	skb_dst_set(nskb, dst);

	skb_reserve(nskb, hh_len + dst->header_len);

	skb_put(nskb, sizeof(struct ipv6hdr));
	skb_reset_network_header(nskb);
	ip6h = ipv6_hdr(nskb);
	*(__be32 *)ip6h =  htonl(0x60000000 | (tclass << 20));
	ip6h->hop_limit = dst_metric(dst, RTAX_HOPLIMIT);
	ip6h->nexthdr = IPPROTO_TCP;
	ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr);
	ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr);

	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
	/* Truncate to length (no data) */
	tcph->doff = sizeof(struct tcphdr)/4;
	tcph->source = otcph.dest;
	tcph->dest = otcph.source;
//.........这里部分代码省略.........

static int xfrm_output_one(struct sk_buff *skb, int err)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;
	struct net *net = xs_net(x);

	if (err <= 0)
		goto resume;

	do {
		err = xfrm_skb_check_space(skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			goto error_nolock;
		}

		err = x->outer_mode->output(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
			goto error_nolock;
		}

		spin_lock_bh(&x->lock);

		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
			err = -EINVAL;
			goto error;
		}

		err = xfrm_state_check_expire(x);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
			goto error;
		}

		err = x->repl->overflow(x, skb);
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
			goto error;
		}

		x->curlft.bytes += skb->len;
		x->curlft.packets++;

		spin_unlock_bh(&x->lock);

		skb_dst_force(skb);

		err = x->type->output(x, skb);
		if (err == -EINPROGRESS)
			goto out;

resume:
		if (err) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			goto error_nolock;
		}

		dst = skb_dst_pop(skb);
		if (!dst) {
			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
			err = -EHOSTUNREACH;
			goto error_nolock;
		}
		skb_dst_set(skb, dst);
		x = dst->xfrm;
	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));

	return 0;

error:
	spin_unlock_bh(&x->lock);
error_nolock:
	kfree_skb(skb);
out:
	return err;
}

/* This requires some explaining. If DNAT has taken place,
 * we will need to fix up the destination Ethernet address.
 * This is also true when SNAT takes place (for the reply direction).
 *
 * 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 net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct iphdr *iph = ip_hdr(skb);
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
	struct rtable *rt;
	int err;

	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;

	if (nf_bridge->pkt_otherhost) {
		skb->pkt_type = PACKET_OTHERHOST;
		nf_bridge->pkt_otherhost = false;
	}
	nf_bridge->in_prerouting = 0;
	if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
		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(net, 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);
				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
						  net, sk, skb, skb->dev,
						  NULL,
						  br_nf_pre_routing_finish_bridge);
				return 0;
			}
			ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
			skb->pkt_type = PACKET_HOST;
		}
	} else {
		rt = bridge_parent_rtable(nf_bridge->physindev);
		if (!rt) {
//.........这里部分代码省略.........

static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
			   void *from, size_t length,
			   struct rtable **rtp,
			   unsigned int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	struct net *net = sock_net(sk);
	struct iphdr *iph;
	struct sk_buff *skb;
	unsigned int iphlen;
	int err;
	struct rtable *rt = *rtp;
	int hlen, tlen;

	if (length > rt->dst.dev->mtu) {
		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
			       rt->dst.dev->mtu);
		return -EMSGSIZE;
	}
	if (flags&MSG_PROBE)
		goto out;

	hlen = LL_RESERVED_SPACE(rt->dst.dev);
	tlen = rt->dst.dev->needed_tailroom;
	skb = sock_alloc_send_skb(sk,
				  length + hlen + tlen + 15,
				  flags & MSG_DONTWAIT, &err);
	if (skb == NULL)
		goto error;
	skb_reserve(skb, hlen);

	skb->priority = sk->sk_priority;
	skb->mark = sk->sk_mark;
	skb_dst_set(skb, &rt->dst);
	*rtp = NULL;

	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	skb_put(skb,sizeof(*iph));

	skb->ip_summed = CHECKSUM_NONE;

	skb->transport_header = skb->network_header;
	err = -EFAULT;
	if (!memcpy_fromiovecend2((void *)iph, from, 0, length))
		goto error_free;

	iphlen = iph->ihl * 4;

	/*
	 * We don't want to modify the ip header, but we do need to
	 * be sure that it won't cause problems later along the network
	 * stack.  Specifically we want to make sure that iph->ihl is a
	 * sane value.  If ihl points beyond the length of the buffer passed
	 * in, reject the frame as invalid
	 */
	err = -EINVAL;
	if (iphlen > length)
		goto error_free;

	if (iphlen >= sizeof(*iph)) {
		if (!iph->saddr)
			iph->saddr = fl4->saddr;
		iph->check   = 0;
		iph->tot_len = htons(length);
		if (!iph->id)
			ip_select_ident(skb, &rt->dst, NULL);

		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
	}
	if (iph->protocol == IPPROTO_ICMP)
		icmp_out_count(net, ((struct icmphdr *)
			skb_transport_header(skb))->type);

	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
		      rt->dst.dev, dst_output);
	if (err > 0)
		err = net_xmit_errno(err);
	if (err)
		goto error;
out:
	return 0;

error_free:
	kfree_skb(skb);
error:
	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
	if (err == -ENOBUFS && !inet->recverr)
		err = 0;
	return err;
}

int ip6_route_me_harder(struct sk_buff *skb)
{
    struct net *net = dev_net(skb_dst(skb)->dev);
    struct ipv6hdr *iph = ipv6_hdr(skb);
    struct dst_entry *dst;
    struct flowi fl = {
        .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
        .mark = skb->mark,
        .fl6_dst = iph->daddr,
        .fl6_src = iph->saddr,
    };

    dst = ip6_route_output(net, skb->sk, &fl);
    if (dst->error) {
        IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
        LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
        dst_release(dst);
        return -EINVAL;
    }

    /* Drop old route. */
    skb_dst_drop(skb);

    skb_dst_set(skb, dst);

#ifdef CONFIG_XFRM
    if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
            xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
        skb_dst_set(skb, NULL);
        if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
            return -1;
        skb_dst_set(skb, dst);
    }
#endif

    return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);

/*
 * Extra routing may needed on local out, as the QUEUE target never
 * returns control to the table.
 */

struct ip6_rt_info {
    struct in6_addr daddr;
    struct in6_addr saddr;
    u_int32_t mark;
};

static void nf_ip6_saveroute(const struct sk_buff *skb,
                             struct nf_queue_entry *entry)
{
    struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);

    if (entry->hook == NF_INET_LOCAL_OUT) {
        struct ipv6hdr *iph = ipv6_hdr(skb);

        rt_info->daddr = iph->daddr;
        rt_info->saddr = iph->saddr;
        rt_info->mark = skb->mark;
    }
}

static int nf_ip6_reroute(struct sk_buff *skb,
                          const struct nf_queue_entry *entry)
{
    struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);

    if (entry->hook == NF_INET_LOCAL_OUT) {
        struct ipv6hdr *iph = ipv6_hdr(skb);
        if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
                !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
                skb->mark != rt_info->mark)
            return ip6_route_me_harder(skb);
    }
    return 0;
}

static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
{
    *dst = ip6_route_output(&init_net, NULL, fl);
    return (*dst)->error;
}

//-----------------------------------------------------------------------------
static bool _gtpurh_route_packet(struct sk_buff *skb_pP, const struct xt_gtpurh_target_info *info_pP)
//-----------------------------------------------------------------------------
{
    int            err   = 0;
    struct rtable *rt    = NULL;
    struct iphdr  *iph_p = ip_hdr(skb_pP);
    int            daddr = iph_p->daddr;
    struct flowi   fl    = {
        .u = {
            .ip4 = {
                .daddr        = daddr,
                .flowi4_tos   = RT_TOS(iph_p->tos),
                .flowi4_scope = RT_SCOPE_UNIVERSE,
            } 
        } 
    }; 
    //skb_pP->pkt_type = PACKET_OTHERHOST;
    skb_pP->pkt_type = PACKET_OUTGOING;
#if 0
    pr_info("GTPURH(%d): Routing packet: %d.%d.%d.%d --> %d.%d.%d.%d Proto: %d, Len: %d Mark: %u Packet type: %u\n",
            info_pP->action,
            iph_p->saddr  & 0xFF,
            (iph_p->saddr & 0x0000FF00) >> 8,
            (iph_p->saddr & 0x00FF0000) >> 16,
            iph_p->saddr >> 24,
            iph_p->daddr  & 0xFF,
            (iph_p->daddr & 0x0000FF00) >> 8,
            (iph_p->daddr & 0x00FF0000) >> 16,
            iph_p->daddr >> 24,
            iph_p->protocol,
            ntohs(iph_p->tot_len),
            skb_pP->mark,
            skb_pP->pkt_type);
#endif
    rt = ip_route_output_key(&init_net, &fl.u.ip4);
    if (rt == null) {
        pr_info("GTPURH: Failed to route packet to dst 0x%x. Error: (%d)\n", fl.u.ip4.daddr, err);
        return GTPURH_FAILURE;
    } 

#if 0
    if (rt->dst.dev) {
        pr_info("GTPURH: dst dev name %s\n", rt->dst.dev->name);
    } else {
        pr_info("GTPURH: dst dev NULL\n");
    }
#endif

    skb_pP->priority = rt_tos2priority(iph_p->tos);
    skb_dst_drop(skb_pP);
    skb_dst_set(skb_pP, &rt->dst);
    skb_pP->dev      = skb_dst(skb_pP)->dev;

    // Send the GTPu message out
    ip_local_out(skb_pP);

    if (err == 0) {
        return GTPURH_SUCCESS;
    } else {
        return GTPURH_FAILURE;
    }
}

int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
		  bool log_ecn_error)
{
	struct pcpu_sw_netstats *tstats;
	const struct iphdr *iph = ip_hdr(skb);
	int err;

#ifdef CONFIG_NET_IPGRE_BROADCAST
	if (ipv4_is_multicast(iph->daddr)) {
		tunnel->dev->stats.multicast++;
		skb->pkt_type = PACKET_BROADCAST;
	}
#endif

	if ((!(tpi->flags&TUNNEL_CSUM) &&  (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
	     ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
		tunnel->dev->stats.rx_crc_errors++;
		tunnel->dev->stats.rx_errors++;
		goto drop;
	}

	if (tunnel->parms.i_flags&TUNNEL_SEQ) {
		if (!(tpi->flags&TUNNEL_SEQ) ||
		    (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
			tunnel->dev->stats.rx_fifo_errors++;
			tunnel->dev->stats.rx_errors++;
			goto drop;
		}
		tunnel->i_seqno = ntohl(tpi->seq) + 1;
	}

	skb_reset_network_header(skb);

	err = IP_ECN_decapsulate(iph, skb);
	if (unlikely(err)) {
		if (log_ecn_error)
			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
					&iph->saddr, iph->tos);
		if (err > 1) {
			++tunnel->dev->stats.rx_frame_errors;
			++tunnel->dev->stats.rx_errors;
			goto drop;
		}
	}

	tstats = this_cpu_ptr(tunnel->dev->tstats);
	u64_stats_update_begin(&tstats->syncp);
	tstats->rx_packets++;
	tstats->rx_bytes += skb->len;
	u64_stats_update_end(&tstats->syncp);

	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));

	if (tunnel->dev->type == ARPHRD_ETHER) {
		skb->protocol = eth_type_trans(skb, tunnel->dev);
		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
	} else {
		skb->dev = tunnel->dev;
	}

	if (tun_dst)
		skb_dst_set(skb, (struct dst_entry *)tun_dst);

	gro_cells_receive(&tunnel->gro_cells, skb);
	return 0;

drop:
	kfree_skb(skb);
	return 0;
}

/* 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.........