C++ dev_net函数代码示例

/* 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 flowi fl = {};
	unsigned long orefdst;
	unsigned int hh_len;
	unsigned int type;

	type = inet_addr_type(net, iph->saddr);
	if (skb->sk && inet_sk(skb->sk)->transparent)
		type = RTN_LOCAL;
	if (addr_type == RTN_UNSPEC)
		addr_type = type;

	/* 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.
	 */
	if (addr_type == RTN_LOCAL) {
		fl.nl_u.ip4_u.daddr = iph->daddr;
		if (type == RTN_LOCAL)
			fl.nl_u.ip4_u.saddr = iph->saddr;
		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
		fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
		fl.mark = skb->mark;
		fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
		if (ip_route_output_key(net, &rt, &fl) != 0)
			return -1;

		/* Drop old route. */
		skb_dst_drop(skb);
		skb_dst_set(skb, &rt->dst);
	} else {
		/* non-local src, find valid iif to satisfy
		 * rp-filter when calling ip_route_input. */
		fl.nl_u.ip4_u.daddr = iph->saddr;
		if (ip_route_output_key(net, &rt, &fl) != 0)
			return -1;

		orefdst = skb->_skb_refdst;
		if (ip_route_input(skb, iph->daddr, iph->saddr,
				   RT_TOS(iph->tos), rt->dst.dev) != 0) {
			dst_release(&rt->dst);
			return -1;
		}
		dst_release(&rt->dst);
		refdst_drop(orefdst);
	}

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

#ifdef CONFIG_XFRM
	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
	    xfrm_decode_session(skb, &fl, AF_INET) == 0) {
		struct dst_entry *dst = skb_dst(skb);
		skb_dst_set(skb, NULL);
		if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
			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_len - skb_headroom(skb), 0, GFP_ATOMIC))
		return -1;

	return 0;
}

int ip6_mc_input(struct sk_buff *skb)
{
	struct ipv6hdr *hdr;
	int deliver;

	IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCASTPKTS);

	hdr = ipv6_hdr(skb);
	deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);

#ifdef CONFIG_IPV6_MROUTE
	/*
	 *      IPv6 multicast router mode is now supported ;)
	 */
	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
		/*
		 * Okay, we try to forward - split and duplicate
		 * packets.
		 */
		struct sk_buff *skb2;
		struct inet6_skb_parm *opt = IP6CB(skb);

		/* Check for MLD */
		if (unlikely(opt->ra)) {
			/* Check if this is a mld message */
			u8 *ptr = skb_network_header(skb) + opt->ra;
			struct icmp6hdr *icmp6;
			u8 nexthdr = hdr->nexthdr;
			int offset;

			/* Check if the value of Router Alert
			 * is for MLD (0x0000).
			 */
			if ((ptr[2] | ptr[3]) == 0) {
				deliver = 0;

				if (!ipv6_ext_hdr(nexthdr)) {
					/* BUG */
					goto out;
				}
				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
							  &nexthdr);
				if (offset < 0)
					goto out;

				if (nexthdr != IPPROTO_ICMPV6)
					goto out;

				if (!pskb_may_pull(skb, (skb_network_header(skb) +
						   offset + 1 - skb->data)))
					goto out;

				icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset);

				switch (icmp6->icmp6_type) {
				case ICMPV6_MGM_QUERY:
				case ICMPV6_MGM_REPORT:
				case ICMPV6_MGM_REDUCTION:
				case ICMPV6_MLD2_REPORT:
					deliver = 1;
					break;
				}
				goto out;
			}
			/* unknown RA - process it normally */
		}

		if (deliver)
			skb2 = skb_clone(skb, GFP_ATOMIC);
		else {
			skb2 = skb;
			skb = NULL;
		}

		if (skb2) {
			skb2->dev = skb2->dst->dev;
			ip6_mr_input(skb2);
		}
	}
out:
#endif
	if (likely(deliver))
		ip6_input(skb);
	else {
		/* discard */
		kfree_skb(skb);
	}

	return 0;
}

struct sk_buff *ndisc_build_skb(struct net_device *dev,
				const struct in6_addr *daddr,
				const struct in6_addr *saddr,
				struct icmp6hdr *icmp6h,
				const struct in6_addr *target,
				int llinfo)
{
	struct net *net = dev_net(dev);
	struct sock *sk = net->ipv6.ndisc_sk;
	struct sk_buff *skb;
	struct icmp6hdr *hdr;
	int hlen = LL_RESERVED_SPACE(dev);
	int tlen = dev->needed_tailroom;
	int len;
	u8 *opt;

	if (!dev->addr_len)
		llinfo = 0;

	len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0);
	if (llinfo)
		len += ndisc_opt_addr_space(dev);

	skb = alloc_skb((MAX_HEADER + sizeof(struct ipv6hdr) +
			 len + hlen + tlen), GFP_ATOMIC);
	if (!skb) {
		ND_PRINTK0(KERN_ERR
			   "ICMPv6 ND: %s() failed to allocate an skb.\n",
			   __func__);
		return NULL;
	}

	skb_reserve(skb, hlen);
	ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);

	skb->transport_header = skb->tail;
	skb_put(skb, len);

	hdr = (struct icmp6hdr *)skb_transport_header(skb);
	memcpy(hdr, icmp6h, sizeof(*hdr));

	opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
	if (target) {
		*(struct in6_addr *)opt = *target;
		opt += sizeof(*target);
	}

	if (llinfo)
		ndisc_fill_addr_option(opt, llinfo, dev->dev_addr,
				       dev->addr_len, dev->type);

	hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len,
					   IPPROTO_ICMPV6,
					   csum_partial(hdr,
							len, 0));

	/* Manually assign socket ownership as we avoid calling
	 * sock_alloc_send_pskb() to bypass wmem buffer limits
	 */
	skb_set_owner_w(skb, sk);

	return skb;
}

static bool
socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct udphdr _hdr, *hp = NULL;
	struct sock *sk;
	struct in6_addr *daddr, *saddr;
	__be16 dport, sport;
	int thoff, tproto;
	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;

	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
	if (tproto < 0) {
		pr_debug("unable to find transport header in IPv6 packet, dropping\n");
		return NF_DROP;
	}

	if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
		hp = skb_header_pointer(skb, thoff,
					sizeof(_hdr), &_hdr);
		if (hp == NULL)
			return false;

		saddr = &iph->saddr;
		sport = hp->source;
		daddr = &iph->daddr;
		dport = hp->dest;

	} else if (tproto == IPPROTO_ICMPV6) {
		if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
					 &sport, &dport))
			return false;
	} else {
		return false;
	}

	sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
				   saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
	if (sk != NULL) {
		bool wildcard;
		bool transparent = true;

		/* Ignore sockets listening on INADDR_ANY */
		wildcard = (sk->sk_state != TCP_TIME_WAIT &&
			    ipv6_addr_any(&inet6_sk(sk)->rcv_saddr));

		/* Ignore non-transparent sockets,
		   if XT_SOCKET_TRANSPARENT is used */
		if (info && info->flags & XT_SOCKET_TRANSPARENT)
			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
					inet_sk(sk)->transparent) ||
				       (sk->sk_state == TCP_TIME_WAIT &&
					inet_twsk(sk)->tw_transparent));

		xt_socket_put_sk(sk);

		if (wildcard || !transparent)
			sk = NULL;
	}

	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
		 "(orig %pI6:%hu) sock %p\n",
		 tproto, saddr, ntohs(sport),
		 daddr, ntohs(dport),
		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);

	return (sk != NULL);
}

void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	u32 headroom = sizeof(struct iphdr);
	struct ip_tunnel_info *tun_info;
	const struct ip_tunnel_key *key;
	const struct iphdr *inner_iph;
	struct rtable *rt;
	struct flowi4 fl4;
	__be16 df = 0;
	u8 tos, ttl;

	tun_info = skb_tunnel_info(skb);
	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
		     ip_tunnel_info_af(tun_info) != AF_INET))
		goto tx_error;
	key = &tun_info->key;
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
	tos = key->tos;
	if (tos == 1) {
		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);
	}
	init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
			 RT_TOS(tos), tunnel->parms.link);
	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
		goto tx_error;
	rt = ip_route_output_key(tunnel->net, &fl4);
	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;
	}
	tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
	ttl = key->ttl;
	if (ttl == 0) {
		if (skb->protocol == htons(ETH_P_IP))
			ttl = inner_iph->ttl;
		else if (skb->protocol == htons(ETH_P_IPV6))
			ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
		else
			ttl = ip4_dst_hoplimit(&rt->dst);
	}
	if (key->tun_flags & TUNNEL_DONT_FRAGMENT)
		df = htons(IP_DF);
	else if (skb->protocol == htons(ETH_P_IP))
		df = inner_iph->frag_off & htons(IP_DF);
	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
	if (headroom > dev->needed_headroom)
		dev->needed_headroom = headroom;

	if (skb_cow_head(skb, dev->needed_headroom)) {
		ip_rt_put(rt);
		goto tx_dropped;
	}
	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
	return;
tx_error:
	dev->stats.tx_errors++;
	goto kfree;
tx_dropped:
	dev->stats.tx_dropped++;
kfree:
	kfree_skb(skb);
}

static int ip6_input_finish(struct sk_buff *skb)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	const struct inet6_protocol *ipprot;
	struct inet6_dev *idev;
	unsigned int nhoff;
	int nexthdr;
	bool raw;

	/*
	 *	Parse extension headers
	 */

	rcu_read_lock();
resubmit:
	idev = ip6_dst_idev(skb_dst(skb));
	if (!pskb_pull(skb, skb_transport_offset(skb)))
		goto discard;
	nhoff = IP6CB(skb)->nhoff;
	nexthdr = skb_network_header(skb)[nhoff];

	raw = raw6_local_deliver(skb, nexthdr);
	if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) {
		int ret;

		if (ipprot->flags & INET6_PROTO_FINAL) {
			const struct ipv6hdr *hdr;

			/* Free reference early: we don't need it any more,
			   and it may hold ip_conntrack module loaded
			   indefinitely. */
			nf_reset(skb);

			skb_postpull_rcsum(skb, skb_network_header(skb),
					   skb_network_header_len(skb));
			hdr = ipv6_hdr(skb);
			if (ipv6_addr_is_multicast(&hdr->daddr) &&
			    !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
			    &hdr->saddr) &&
			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
				goto discard;
		}
		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

		ret = ipprot->handler(skb);
		if (ret > 0)
			goto resubmit;
		else if (ret == 0)
			IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
	} else {
		if (!raw) {
			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				IP6_INC_STATS_BH(net, idev,
						 IPSTATS_MIB_INUNKNOWNPROTOS);
				icmpv6_send(skb, ICMPV6_PARAMPROB,
					    ICMPV6_UNK_NEXTHDR, nhoff);
			}
		} else
			IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
		kfree_skb(skb);
	}
	rcu_read_unlock();
	return 0;

discard:
	IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
	rcu_read_unlock();
	kfree_skb(skb);
	return 0;
}

int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
	const struct ipv6hdr *hdr;
	u32 		pkt_len;
	struct inet6_dev *idev;
	struct net *net = dev_net(skb->dev);

	if (skb->pkt_type == PACKET_OTHERHOST) {
		kfree_skb(skb);
		return NET_RX_DROP;
	}

	rcu_read_lock();

	idev = __in6_dev_get(skb->dev);

	IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_IN, skb->len);

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
	    !idev || unlikely(idev->cnf.disable_ipv6)) {
		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));

	/*
	 * Store incoming device index. When the packet will
	 * be queued, we cannot refer to skb->dev anymore.
	 *
	 * BTW, when we send a packet for our own local address on a
	 * non-loopback interface (e.g. ethX), it is being delivered
	 * via the loopback interface (lo) here; skb->dev = loopback_dev.
	 * It, however, should be considered as if it is being
	 * arrived via the sending interface (ethX), because of the
	 * nature of scoping architecture. --yoshfuji
	 */
	IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;

	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
		goto err;

	hdr = ipv6_hdr(skb);

	if (hdr->version != 6)
		goto err;

	/*
	 * RFC4291 2.5.3
	 * A packet received on an interface with a destination address
	 * of loopback must be dropped.
	 */
	if (!(dev->flags & IFF_LOOPBACK) &&
	    ipv6_addr_loopback(&hdr->daddr))
		goto err;

	/* RFC4291 2.7
	 * Nodes must not originate a packet to a multicast address whose scope
	 * field contains the reserved value 0; if such a packet is received, it
	 * must be silently dropped.
	 */
	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
		goto err;

	/*
	 * RFC4291 2.7
	 * Multicast addresses must not be used as source addresses in IPv6
	 * packets or appear in any Routing header.
	 */
	if (ipv6_addr_is_multicast(&hdr->saddr))
		goto err;

	skb->transport_header = skb->network_header + sizeof(*hdr);
	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);

	pkt_len = ntohs(hdr->payload_len);

	/* pkt_len may be zero if Jumbo payload option is present */
	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
		if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
			IP6_INC_STATS_BH(net,
					 idev, IPSTATS_MIB_INTRUNCATEDPKTS);
			goto drop;
		}
		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
			IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
			goto drop;
		}
		hdr = ipv6_hdr(skb);
	}

	if (hdr->nexthdr == NEXTHDR_HOP) {
		if (ipv6_parse_hopopts(skb) < 0) {
			IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
			rcu_read_unlock();
			return NET_RX_DROP;
		}
	}

//.........这里部分代码省略.........

static int arp_process(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct in_device *in_dev = __in_dev_get_rcu(dev);
	struct arphdr *arp;
	unsigned char *arp_ptr;
	struct rtable *rt;
	unsigned char *sha;
	__be32 sip, tip;
	u16 dev_type = dev->type;
	int addr_type;
	struct neighbour *n;
	struct net *net = dev_net(dev);
	bool is_garp = false;

	/* arp_rcv below verifies the ARP header and verifies the device
	 * is ARP'able.
	 */

	if (in_dev == NULL)
		goto out;

	arp = arp_hdr(skb);

	switch (dev_type) {
	default:
		if (arp->ar_pro != htons(ETH_P_IP) ||
		    htons(dev_type) != arp->ar_hrd)
			goto out;
		break;
	case ARPHRD_ETHER:
	case ARPHRD_IEEE802_TR:
	case ARPHRD_FDDI:
	case ARPHRD_IEEE802:
		/*
		 * ETHERNET, Token Ring and Fibre Channel (which are IEEE 802
		 * devices, according to RFC 2625) devices will accept ARP
		 * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2).
		 * This is the case also of FDDI, where the RFC 1390 says that
		 * FDDI devices should accept ARP hardware of (1) Ethernet,
		 * however, to be more robust, we'll accept both 1 (Ethernet)
		 * or 6 (IEEE 802.2)
		 */
		if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
		     arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
		    arp->ar_pro != htons(ETH_P_IP))
			goto out;
		break;
	case ARPHRD_AX25:
		if (arp->ar_pro != htons(AX25_P_IP) ||
		    arp->ar_hrd != htons(ARPHRD_AX25))
			goto out;
		break;
	case ARPHRD_NETROM:
		if (arp->ar_pro != htons(AX25_P_IP) ||
		    arp->ar_hrd != htons(ARPHRD_NETROM))
			goto out;
		break;
	}

	/* Understand only these message types */

	if (arp->ar_op != htons(ARPOP_REPLY) &&
	    arp->ar_op != htons(ARPOP_REQUEST))
		goto out;

/*
 *	Extract fields
 */
	arp_ptr = (unsigned char *)(arp + 1);
	sha	= arp_ptr;
	arp_ptr += dev->addr_len;
	memcpy(&sip, arp_ptr, 4);
	arp_ptr += 4;
	arp_ptr += dev->addr_len;
	memcpy(&tip, arp_ptr, 4);
/*
 *	Check for bad requests for 127.x.x.x and requests for multicast
 *	addresses.  If this is one such, delete it.
 */
	if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
		goto out;

/*
 *     Special case: We must set Frame Relay source Q.922 address
 */
	if (dev_type == ARPHRD_DLCI)
		sha = dev->broadcast;

/*
 *  Process entry.  The idea here is we want to send a reply if it is a
 *  request for us or if it is a request for someone else that we hold
 *  a proxy for.  We want to add an entry to our cache if it is a reply
 *  to us or if it is a request for our address.
 *  (The assumption for this last is that if someone is requesting our
 *  address, they are probably intending to talk to us, so it saves time
 *  if we cache their address.  Their address is also probably not in
 *  our cache, since ours is not in their cache.)
 *
 *  Putting this another way, we only care about replies if they are to
//.........这里部分代码省略.........

static int arp_constructor(struct neighbour *neigh)
{
	__be32 addr = *(__be32 *)neigh->primary_key;
	struct net_device *dev = neigh->dev;
	struct in_device *in_dev;
	struct neigh_parms *parms;

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (in_dev == NULL) {
		rcu_read_unlock();
		return -EINVAL;
	}

	neigh->type = inet_addr_type(dev_net(dev), addr);

	parms = in_dev->arp_parms;
	__neigh_parms_put(neigh->parms);
	neigh->parms = neigh_parms_clone(parms);
	rcu_read_unlock();

	if (!dev->header_ops) {
		neigh->nud_state = NUD_NOARP;
		neigh->ops = &arp_direct_ops;
		neigh->output = neigh_direct_output;
	} else {
		/* Good devices (checked by reading texts, but only Ethernet is
		   tested)

		   ARPHRD_ETHER: (ethernet, apfddi)
		   ARPHRD_FDDI: (fddi)
		   ARPHRD_IEEE802: (tr)
		   ARPHRD_METRICOM: (strip)
		   ARPHRD_ARCNET:
		   etc. etc. etc.

		   ARPHRD_IPDDP will also work, if author repairs it.
		   I did not it, because this driver does not work even
		   in old paradigm.
		 */

#if 1
		/* So... these "amateur" devices are hopeless.
		   The only thing, that I can say now:
		   It is very sad that we need to keep ugly obsolete
		   code to make them happy.

		   They should be moved to more reasonable state, now
		   they use rebuild_header INSTEAD OF hard_start_xmit!!!
		   Besides that, they are sort of out of date
		   (a lot of redundant clones/copies, useless in 2.1),
		   I wonder why people believe that they work.
		 */
		switch (dev->type) {
		default:
			break;
		case ARPHRD_ROSE:
#if IS_ENABLED(CONFIG_AX25)
		case ARPHRD_AX25:
#if IS_ENABLED(CONFIG_NETROM)
		case ARPHRD_NETROM:
#endif
			neigh->ops = &arp_broken_ops;
			neigh->output = neigh->ops->output;
			return 0;
#else
			break;
#endif
		}
#endif
		if (neigh->type == RTN_MULTICAST) {
			neigh->nud_state = NUD_NOARP;
			arp_mc_map(addr, neigh->ha, dev, 1);
		} else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
		} else if (neigh->type == RTN_BROADCAST ||
			   (dev->flags & IFF_POINTOPOINT)) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->broadcast, dev->addr_len);
		}

		if (dev->header_ops->cache)
			neigh->ops = &arp_hh_ops;
		else
			neigh->ops = &arp_generic_ops;

		if (neigh->nud_state & NUD_VALID)
			neigh->output = neigh->ops->connected_output;
		else
			neigh->output = neigh->ops->output;
	}
	return 0;
}

static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
	__be32 saddr = 0;
	u8  *dst_ha = NULL;
	struct net_device *dev = neigh->dev;
	__be32 target = *(__be32 *)neigh->primary_key;
	int probes = atomic_read(&neigh->probes);
	struct in_device *in_dev;

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (!in_dev) {
		rcu_read_unlock();
		return;
	}
	switch (IN_DEV_ARP_ANNOUNCE(in_dev)) {
	default:
	case 0:		/* By default announce any local IP */
		if (skb && inet_addr_type(dev_net(dev),
					  ip_hdr(skb)->saddr) == RTN_LOCAL)
			saddr = ip_hdr(skb)->saddr;
		break;
	case 1:		/* Restrict announcements of saddr in same subnet */
		if (!skb)
			break;
		saddr = ip_hdr(skb)->saddr;
		if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) {
			/* saddr should be known to target */
			if (inet_addr_onlink(in_dev, target, saddr))
				break;
		}
		saddr = 0;
		break;
	case 2:		/* Avoid secondary IPs, get a primary/preferred one */
		break;
	}
	rcu_read_unlock();

	if (!saddr)
		saddr = inet_select_addr(dev, target, RT_SCOPE_LINK);

	probes -= neigh->parms->ucast_probes;
	if (probes < 0) {
		if (!(neigh->nud_state & NUD_VALID))
			printk(KERN_DEBUG
			       "trying to ucast probe in NUD_INVALID\n");
		dst_ha = neigh->ha;
		read_lock_bh(&neigh->lock);
	} else {
		probes -= neigh->parms->app_probes;
		if (probes < 0) {
#ifdef CONFIG_ARPD
			neigh_app_ns(neigh);
#endif
			return;
		}
	}

	arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
		 dst_ha, dev->dev_addr, NULL);
	if (dst_ha)
		read_unlock_bh(&neigh->lock);
}

static int vti4_err(struct sk_buff *skb, u32 info)
{
	__be32 spi;
	__u32 mark;
	struct xfrm_state *x;
	struct ip_tunnel *tunnel;
	struct ip_esp_hdr *esph;
	struct ip_auth_hdr *ah ;
	struct ip_comp_hdr *ipch;
	struct net *net = dev_net(skb->dev);
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	int protocol = iph->protocol;
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);

	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
				  iph->daddr, iph->saddr, 0);
	if (!tunnel)
		return -1;

	mark = be32_to_cpu(tunnel->parms.o_key);

	switch (protocol) {
	case IPPROTO_ESP:
		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
		spi = esph->spi;
		break;
	case IPPROTO_AH:
		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
		spi = ah->spi;
		break;
	case IPPROTO_COMP:
		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
		spi = htonl(ntohs(ipch->cpi));
		break;
	default:
		return 0;
	}

	switch (icmp_hdr(skb)->type) {
	case ICMP_DEST_UNREACH:
		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
			return 0;
	case ICMP_REDIRECT:
		break;
	default:
		return 0;
	}

	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
			      spi, protocol, AF_INET);
	if (!x)
		return 0;

	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
		ipv4_update_pmtu(skb, net, info, 0, protocol);
	else
		ipv4_redirect(skb, net, 0, protocol);
	xfrm_state_put(x);

	return 0;
}

static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
			    struct flowi *fl)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct ip_tunnel_parm *parms = &tunnel->parms;
	struct dst_entry *dst = skb_dst(skb);
	struct net_device *tdev;	/* Device to other host */
	int pkt_len = skb->len;
	int err;
	int mtu;

	if (!dst) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}

	dst_hold(dst);
	dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
	if (IS_ERR(dst)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}

	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
		dev->stats.tx_carrier_errors++;
		dst_release(dst);
		goto tx_error_icmp;
	}

	tdev = dst->dev;

	if (tdev == dev) {
		dst_release(dst);
		dev->stats.collisions++;
		goto tx_error;
	}

	mtu = dst_mtu(dst);
	if (skb->len > mtu) {
		skb_dst_update_pmtu(skb, mtu);
		if (skb->protocol == htons(ETH_P_IP)) {
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));
		} else {
			if (mtu < IPV6_MIN_MTU)
				mtu = IPV6_MIN_MTU;

			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		}

		dst_release(dst);
		goto tx_error;
	}

	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
	skb_dst_set(skb, dst);
	skb->dev = skb_dst(skb)->dev;

	err = dst_output(tunnel->net, skb->sk, skb);
	if (net_xmit_eval(err) == 0)
		err = pkt_len;
	iptunnel_xmit_stats(dev, err);
	return NETDEV_TX_OK;

tx_error_icmp:
	dst_link_failure(skb);
tx_error:
	dev->stats.tx_errors++;
	kfree_skb(skb);
	return NETDEV_TX_OK;
}

int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
{
	const struct ip_options *sopt;
	unsigned char *sptr, *dptr;
	int soffset, doffset;
	int	optlen;
	__be32	daddr;

	memset(dopt, 0, sizeof(struct ip_options));

	sopt = &(IPCB(skb)->opt);

	if (sopt->optlen == 0)
		return 0;

	sptr = skb_network_header(skb);
	dptr = dopt->__data;

	daddr = skb_rtable(skb)->rt_spec_dst;

	if (sopt->rr) {
		optlen  = sptr[sopt->rr+1];
		soffset = sptr[sopt->rr+2];
		dopt->rr = dopt->optlen + sizeof(struct iphdr);
		memcpy(dptr, sptr+sopt->rr, optlen);
		if (sopt->rr_needaddr && soffset <= optlen) {
			if (soffset + 3 > optlen)
				return -EINVAL;
			dptr[2] = soffset + 4;
			dopt->rr_needaddr = 1;
		}
		dptr += optlen;
		dopt->optlen += optlen;
	}
	if (sopt->ts) {
		optlen = sptr[sopt->ts+1];
		soffset = sptr[sopt->ts+2];
		dopt->ts = dopt->optlen + sizeof(struct iphdr);
		memcpy(dptr, sptr+sopt->ts, optlen);
		if (soffset <= optlen) {
			if (sopt->ts_needaddr) {
				if (soffset + 3 > optlen)
					return -EINVAL;
				dopt->ts_needaddr = 1;
				soffset += 4;
			}
			if (sopt->ts_needtime) {
				if (soffset + 3 > optlen)
					return -EINVAL;
				if ((dptr[3]&0xF) != IPOPT_TS_PRESPEC) {
					dopt->ts_needtime = 1;
					soffset += 4;
				} else {
					dopt->ts_needtime = 0;

					if (soffset + 7 <= optlen) {
						__be32 addr;

						memcpy(&addr, dptr+soffset-1, 4);
						if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_UNICAST) {
							dopt->ts_needtime = 1;
							soffset += 8;
						}
					}
				}
			}
			dptr[2] = soffset;
		}
		dptr += optlen;
		dopt->optlen += optlen;
	}
	if (sopt->srr) {
		unsigned char *start = sptr+sopt->srr;
		__be32 faddr;

		optlen  = start[1];
		soffset = start[2];
		doffset = 0;
		if (soffset > optlen)
			soffset = optlen + 1;
		soffset -= 4;
		if (soffset > 3) {
			memcpy(&faddr, &start[soffset-1], 4);
			for (soffset-=4, doffset=4; soffset > 3; soffset-=4, doffset+=4)
				memcpy(&dptr[doffset-1], &start[soffset-1], 4);
			/*
			 * RFC1812 requires to fix illegal source routes.
			 */
			if (memcmp(&ip_hdr(skb)->saddr,
				   &start[soffset + 3], 4) == 0)
				doffset -= 4;
		}
		if (doffset > 3) {
			memcpy(&start[doffset-1], &daddr, 4);
			dopt->faddr = faddr;
			dptr[0] = start[0];
			dptr[1] = doffset+3;
			dptr[2] = 4;
			dptr += doffset+3;
			dopt->srr = dopt->optlen + sizeof(struct iphdr);
//.........这里部分代码省略.........

int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
	struct sk_buff *frag;
	struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
	struct ipv6hdr *tmp_hdr;
	struct frag_hdr *fh;
	unsigned int mtu, hlen, left, len;
	int hroom, troom;
	__be32 frag_id = 0;
	int ptr, offset = 0, err=0;
	u8 *prevhdr, nexthdr = 0;
	struct net *net = dev_net(skb_dst(skb)->dev);

	hlen = ip6_find_1stfragopt(skb, &prevhdr);
	nexthdr = *prevhdr;

	mtu = ip6_skb_dst_mtu(skb);

	/* We must not fragment if the socket is set to force MTU discovery
	 * or if the skb it not generated by a local socket.
	 */
	if (!skb->local_df && skb->len > mtu) {
		skb->dev = skb_dst(skb)->dev;
		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
			      IPSTATS_MIB_FRAGFAILS);
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	if (np && np->frag_size < mtu) {
		if (np->frag_size)
			mtu = np->frag_size;
	}
	mtu -= hlen + sizeof(struct frag_hdr);

	if (skb_has_frag_list(skb)) {
		int first_len = skb_pagelen(skb);
		struct sk_buff *frag2;

		if (first_len - hlen > mtu ||
		    ((first_len - hlen) & 7) ||
		    skb_cloned(skb))
			goto slow_path;

		skb_walk_frags(skb, frag) {
			/* Correct geometry. */
			if (frag->len > mtu ||
			    ((frag->len & 7) && frag->next) ||
			    skb_headroom(frag) < hlen)
				goto slow_path_clean;

			/* Partially cloned skb? */
			if (skb_shared(frag))
				goto slow_path_clean;

			BUG_ON(frag->sk);
			if (skb->sk) {
				frag->sk = skb->sk;
				frag->destructor = sock_wfree;
			}
			skb->truesize -= frag->truesize;
		}

		err = 0;
		offset = 0;
		frag = skb_shinfo(skb)->frag_list;
		skb_frag_list_init(skb);
		/* BUILD HEADER */

		*prevhdr = NEXTHDR_FRAGMENT;
		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
		if (!tmp_hdr) {
			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
				      IPSTATS_MIB_FRAGFAILS);
			return -ENOMEM;
		}

		__skb_pull(skb, hlen);
		fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
		__skb_push(skb, hlen);
		skb_reset_network_header(skb);
		memcpy(skb_network_header(skb), tmp_hdr, hlen);

		ipv6_select_ident(fh, rt);
		fh->nexthdr = nexthdr;
		fh->reserved = 0;
		fh->frag_off = htons(IP6_MF);
		frag_id = fh->identification;

		first_len = skb_pagelen(skb);
		skb->data_len = first_len - skb_headlen(skb);
		skb->len = first_len;
		ipv6_hdr(skb)->payload_len = htons(first_len -
						   sizeof(struct ipv6hdr));

		dst_hold(&rt->dst);

		for (;;) {
//.........这里部分代码省略.........

static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
			u8 type, u8 code, int offset, __be32 info)
{
	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
	struct dccp_sock *dp;
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	__u64 seq;
	struct net *net = dev_net(skb->dev);

	if (skb->len < offset + sizeof(*dh) ||
	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
				   ICMP6_MIB_INERRORS);
		return;
	}

	sk = inet6_lookup(net, &dccp_hashinfo,
			&hdr->daddr, dh->dccph_dport,
			&hdr->saddr, dh->dccph_sport, inet6_iif(skb));

	if (sk == NULL) {
		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
				   ICMP6_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == DCCP_TIME_WAIT) {
		inet_twsk_put(inet_twsk(sk));
		return;
	}

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);

	if (sk->sk_state == DCCP_CLOSED)
		goto out;

	dp = dccp_sk(sk);
	seq = dccp_hdr_seq(dh);
	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	np = inet6_sk(sk);

	if (type == NDISC_REDIRECT) {
		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);

		if (dst)
			dst->ops->redirect(dst, sk, skb);
		goto out;
	}

	if (type == ICMPV6_PKT_TOOBIG) {
		struct dst_entry *dst = NULL;

		if (sock_owned_by_user(sk))
			goto out;
		if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
			goto out;

		dst = inet6_csk_update_pmtu(sk, ntohl(info));
		if (!dst)
			goto out;

		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
			dccp_sync_mss(sk, dst_mtu(dst));
		goto out;
	}

	icmpv6_err_convert(type, code, &err);

	/* Might be for an request_sock */
	switch (sk->sk_state) {
		struct request_sock *req, **prev;
	case DCCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
					   &hdr->daddr, &hdr->saddr,
					   inet6_iif(skb));
		if (req == NULL)
			goto out;

		/*
		 * ICMPs are not backlogged, hence we cannot get an established
		 * socket here.
		 */
		WARN_ON(req->sk != NULL);

		if (!between48(seq, dccp_rsk(req)->dreq_iss,
				    dccp_rsk(req)->dreq_gss)) {
			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
//.........这里部分代码省略.........