ip6_output.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	IPv6 output functions
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on linux/net/ipv4/ip_output.c
 *
 *	Changes:
 *	A.N.Kuznetsov	:	airthmetics in fragmentation.
 *				extension headers are implemented.
 *				route changes now work.
 *				ip6_forward does not confuse sniffers.
 *				etc.
 *
 *      H. von Brand    :       Added missing #include <linux/string.h>
 *	Imran Patel	:	frag id should be in NBO
 *      Kazunori MIYAZAWA @USAGI
 *			:       add ip6_append_data and related functions
 *				for datagram xmit
 */

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/in6.h>
#include <linux/tcp.h>
#include <linux/route.h>
#include <linux/module.h>
#include <linux/slab.h>

#include <linux/bpf-cgroup.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/rawv6.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/checksum.h>
#include <linux/mroute6.h>
#include <net/l3mdev.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>

static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct net_device *dev = dst->dev;
	unsigned int hh_len = LL_RESERVED_SPACE(dev);
	int delta = hh_len - skb_headroom(skb);
	const struct in6_addr *nexthop;
	struct neighbour *neigh;
	int ret;

	/* Be paranoid, rather than too clever. */
	if (unlikely(delta > 0) && dev->header_ops) {
		/* pskb_expand_head() might crash, if skb is shared */
		if (skb_shared(skb)) {
			struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);

			if (likely(nskb)) {
				if (skb->sk)
					skb_set_owner_w(nskb, skb->sk);
				consume_skb(skb);
			} else {
				kfree_skb(skb);
			}
			skb = nskb;
		}
		if (skb &&
		    pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
			kfree_skb(skb);
			skb = NULL;
		}
		if (!skb) {
			IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
			return -ENOMEM;
		}
	}

	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));

		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
		    ((mroute6_is_socket(net, skb) &&
		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
					 &ipv6_hdr(skb)->saddr))) {
			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);

			/* Do not check for IFF_ALLMULTI; multicast routing
			   is not supported in any case.
			 */
			if (newskb)
				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
					net, sk, newskb, NULL, newskb->dev,
					dev_loopback_xmit);

			if (ipv6_hdr(skb)->hop_limit == 0) {
				IP6_INC_STATS(net, idev,
					      IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return 0;
			}
		}

		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len);

		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
		    IPV6_ADDR_SCOPE_NODELOCAL &&
		    !(dev->flags & IFF_LOOPBACK)) {
			kfree_skb(skb);
			return 0;
		}
	}

	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
		int res = lwtunnel_xmit(skb);

		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
			return res;
	}

	rcu_read_lock_bh();
	nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
	if (unlikely(!neigh))
		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
	if (!IS_ERR(neigh)) {
		sock_confirm_neigh(skb, neigh);
		ret = neigh_output(neigh, skb, false);
		rcu_read_unlock_bh();
		return ret;
	}
	rcu_read_unlock_bh();

	IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EINVAL;
}

static int
ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
				    struct sk_buff *skb, unsigned int mtu)
{
	struct sk_buff *segs, *nskb;
	netdev_features_t features;
	int ret = 0;

	/* Please see corresponding comment in ip_finish_output_gso
	 * describing the cases where GSO segment length exceeds the
	 * egress MTU.
	 */
	features = netif_skb_features(skb);
	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
	if (IS_ERR_OR_NULL(segs)) {
		kfree_skb(skb);
		return -ENOMEM;
	}

	consume_skb(skb);

	skb_list_walk_safe(segs, segs, nskb) {
		int err;

		skb_mark_not_on_list(segs);
		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
		if (err && ret == 0)
			ret = err;
	}

	return ret;
}

static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	unsigned int mtu;

#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
	/* Policy lookup after SNAT yielded a new policy */
	if (skb_dst(skb)->xfrm) {
		IP6CB(skb)->flags |= IP6SKB_REROUTED;
		return dst_output(net, sk, skb);
	}
#endif

	mtu = ip6_skb_dst_mtu(skb);
	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);

	if ((skb->len > mtu && !skb_is_gso(skb)) ||
	    dst_allfrag(skb_dst(skb)) ||
	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
		return ip6_fragment(net, sk, skb, ip6_finish_output2);
	else
		return ip6_finish_output2(net, sk, skb);
}

static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	int ret;

	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
	switch (ret) {
	case NET_XMIT_SUCCESS:
		return __ip6_finish_output(net, sk, skb);
	case NET_XMIT_CN:
		return __ip6_finish_output(net, sk, skb) ? : ret;
	default:
		kfree_skb(skb);
		return ret;
	}
}

int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));

	skb->protocol = htons(ETH_P_IPV6);
	skb->dev = dev;

	if (unlikely(idev->cnf.disable_ipv6)) {
		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
		kfree_skb(skb);
		return 0;
	}

	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
			    net, sk, skb, indev, dev,
			    ip6_finish_output,
			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
}

bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
{
	if (!np->autoflowlabel_set)
		return ip6_default_np_autolabel(net);
	else
		return np->autoflowlabel;
}

/*
 * xmit an sk_buff (used by TCP, SCTP and DCCP)
 * Note : socket lock is not held for SYNACK packets, but might be modified
 * by calls to skb_set_owner_w() and ipv6_local_error(),
 * which are using proper atomic operations or spinlocks.
 */
int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
	     __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority)
{
	struct net *net = sock_net(sk);
	const struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *first_hop = &fl6->daddr;
	struct dst_entry *dst = skb_dst(skb);
	unsigned int head_room;
	struct ipv6hdr *hdr;
	u8  proto = fl6->flowi6_proto;
	int seg_len = skb->len;
	int hlimit = -1;
	u32 mtu;

	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
	if (opt)
		head_room += opt->opt_nflen + opt->opt_flen;

	if (unlikely(skb_headroom(skb) < head_room)) {
		struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
		if (!skb2) {
			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
				      IPSTATS_MIB_OUTDISCARDS);
			kfree_skb(skb);
			return -ENOBUFS;
		}
		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);
		consume_skb(skb);
		skb = skb2;
	}

	if (opt) {
		seg_len += opt->opt_nflen + opt->opt_flen;

		if (opt->opt_flen)
			ipv6_push_frag_opts(skb, opt, &proto);

		if (opt->opt_nflen)
			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
					     &fl6->saddr);
	}

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

	/*
	 *	Fill in the IPv6 header
	 */
	if (np)
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = ip6_dst_hoplimit(dst);

	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
				ip6_autoflowlabel(net, np), fl6));

	hdr->payload_len = htons(seg_len);
	hdr->nexthdr = proto;
	hdr->hop_limit = hlimit;

	hdr->saddr = fl6->saddr;
	hdr->daddr = *first_hop;

	skb->protocol = htons(ETH_P_IPV6);
	skb->priority = priority;
	skb->mark = mark;

	mtu = dst_mtu(dst);
	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
			      IPSTATS_MIB_OUT, skb->len);

		/* if egress device is enslaved to an L3 master device pass the
		 * skb to its handler for processing
		 */
		skb = l3mdev_ip6_out((struct sock *)sk, skb);
		if (unlikely(!skb))
			return 0;

		/* hooks should never assume socket lock is held.
		 * we promote our socket to non const
		 */
		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
			       net, (struct sock *)sk, skb, NULL, dst->dev,
			       dst_output);
	}

	skb->dev = dst->dev;
	/* ipv6_local_error() does not require socket lock,
	 * we promote our socket to non const
	 */
	ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);

	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
	kfree_skb(skb);
	return -EMSGSIZE;
}
EXPORT_SYMBOL(ip6_xmit);

static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
{
	struct ip6_ra_chain *ra;
	struct sock *last = NULL;

	read_lock(&ip6_ra_lock);
	for (ra = ip6_ra_chain; ra; ra = ra->next) {
		struct sock *sk = ra->sk;
		if (sk && ra->sel == sel &&
		    (!sk->sk_bound_dev_if ||
		     sk->sk_bound_dev_if == skb->dev->ifindex)) {
			struct ipv6_pinfo *np = inet6_sk(sk);

			if (np && np->rtalert_isolate &&
			    !net_eq(sock_net(sk), dev_net(skb->dev))) {
				continue;
			}
			if (last) {
				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
				if (skb2)
					rawv6_rcv(last, skb2);
			}
			last = sk;
		}
	}

	if (last) {
		rawv6_rcv(last, skb);
		read_unlock(&ip6_ra_lock);
		return 1;
	}
	read_unlock(&ip6_ra_lock);
	return 0;
}

static int ip6_forward_proxy_check(struct sk_buff *skb)
{
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	u8 nexthdr = hdr->nexthdr;
	__be16 frag_off;
	int offset;

	if (ipv6_ext_hdr(nexthdr)) {
		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off);
		if (offset < 0)
			return 0;
	} else
		offset = sizeof(struct ipv6hdr);

	if (nexthdr == IPPROTO_ICMPV6) {
		struct icmp6hdr *icmp6;

		if (!pskb_may_pull(skb, (skb_network_header(skb) +
					 offset + 1 - skb->data)))
			return 0;

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

		switch (icmp6->icmp6_type) {
		case NDISC_ROUTER_SOLICITATION:
		case NDISC_ROUTER_ADVERTISEMENT:
		case NDISC_NEIGHBOUR_SOLICITATION:
		case NDISC_NEIGHBOUR_ADVERTISEMENT:
		case NDISC_REDIRECT:
			/* For reaction involving unicast neighbor discovery
			 * message destined to the proxied address, pass it to
			 * input function.
			 */
			return 1;
		default:
			break;
		}
	}

	/*
	 * The proxying router can't forward traffic sent to a link-local
	 * address, so signal the sender and discard the packet. This
	 * behavior is clarified by the MIPv6 specification.
	 */
	if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) {
		dst_link_failure(skb);
		return -1;
	}

	return 0;
}

static inline int ip6_forward_finish(struct net *net, struct sock *sk,
				     struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);

	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);

#ifdef CONFIG_NET_SWITCHDEV
	if (skb->offload_l3_fwd_mark) {
		consume_skb(skb);
		return 0;
	}
#endif

	skb->tstamp = 0;
	return dst_output(net, sk, skb);
}

static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
	if (skb->len <= mtu)
		return false;

	/* ipv6 conntrack defrag sets max_frag_size + ignore_df */
	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
		return true;

	if (skb->ignore_df)
		return false;

	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
		return false;

	return true;
}

int ip6_forward(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct net *net = dev_net(dst->dev);
	struct inet6_dev *idev;
	u32 mtu;

	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
	if (net->ipv6.devconf_all->forwarding == 0)
		goto error;

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

	if (unlikely(skb->sk))
		goto drop;

	if (skb_warn_if_lro(skb))
		goto drop;

	if (!net->ipv6.devconf_all->disable_policy &&
	    !idev->cnf.disable_policy &&
	    !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	skb_forward_csum(skb);

	/*
	 *	We DO NOT make any processing on
	 *	RA packets, pushing them to user level AS IS
	 *	without ane WARRANTY that application will be able
	 *	to interpret them. The reason is that we
	 *	cannot make anything clever here.
	 *
	 *	We are not end-node, so that if packet contains
	 *	AH/ESP, we cannot make anything.
	 *	Defragmentation also would be mistake, RA packets
	 *	cannot be fragmented, because there is no warranty
	 *	that different fragments will go along one path. --ANK
	 */
	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
		if (ip6_call_ra_chain(skb, ntohs(opt->ra)))
			return 0;
	}

	/*
	 *	check and decrement ttl
	 */
	if (hdr->hop_limit <= 1) {
		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);

		kfree_skb(skb);
		return -ETIMEDOUT;
	}

	/* XXX: idev->cnf.proxy_ndp? */
	if (net->ipv6.devconf_all->proxy_ndp &&
	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
		int proxied = ip6_forward_proxy_check(skb);
		if (proxied > 0)
			return ip6_input(skb);
		else if (proxied < 0) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
			goto drop;
		}
	}

	if (!xfrm6_route_forward(skb)) {
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}
	dst = skb_dst(skb);

	/* IPv6 specs say nothing about it, but it is clear that we cannot
	   send redirects to source routed frames.
	   We don't send redirects to frames decapsulated from IPsec.
	 */
	if (IP6CB(skb)->iif == dst->dev->ifindex &&
	    opt->srcrt == 0 && !skb_sec_path(skb)) {
		struct in6_addr *target = NULL;
		struct inet_peer *peer;
		struct rt6_info *rt;

		/*
		 *	incoming and outgoing devices are the same
		 *	send a redirect.
		 */

		rt = (struct rt6_info *) dst;
		if (rt->rt6i_flags & RTF_GATEWAY)
			target = &rt->rt6i_gateway;
		else
			target = &hdr->daddr;

		peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);

		/* Limit redirects both by destination (here)
		   and by source (inside ndisc_send_redirect)
		 */
		if (inet_peer_xrlim_allow(peer, 1*HZ))
			ndisc_send_redirect(skb, target);
		if (peer)
			inet_putpeer(peer);
	} else {
		int addrtype = ipv6_addr_type(&hdr->saddr);

		/* This check is security critical. */
		if (addrtype == IPV6_ADDR_ANY ||
		    addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
			goto error;
		if (addrtype & IPV6_ADDR_LINKLOCAL) {
			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
				    ICMPV6_NOT_NEIGHBOUR, 0);
			goto error;
		}
	}

	mtu = ip6_dst_mtu_forward(dst);
	if (mtu < IPV6_MIN_MTU)
		mtu = IPV6_MIN_MTU;

	if (ip6_pkt_too_big(skb, mtu)) {
		/* Again, force OUTPUT device used as source address */
		skb->dev = dst->dev;
		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS);
		__IP6_INC_STATS(net, ip6_dst_idev(dst),
				IPSTATS_MIB_FRAGFAILS);
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	if (skb_cow(skb, dst->dev->hard_header_len)) {
		__IP6_INC_STATS(net, ip6_dst_idev(dst),
				IPSTATS_MIB_OUTDISCARDS);
		goto drop;
	}

	hdr = ipv6_hdr(skb);

	/* Mangling hops number delayed to point after skb COW */

	hdr->hop_limit--;

	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
		       net, NULL, skb, skb->dev, dst->dev,
		       ip6_forward_finish);

error:
	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
drop:
	kfree_skb(skb);
	return -EINVAL;
}

static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
	to->pkt_type = from->pkt_type;
	to->priority = from->priority;
	to->protocol = from->protocol;
	skb_dst_drop(to);
	skb_dst_set(to, dst_clone(skb_dst(from)));
	to->dev = from->dev;
	to->mark = from->mark;

	skb_copy_hash(to, from);

#ifdef CONFIG_NET_SCHED
	to->tc_index = from->tc_index;
#endif
	nf_copy(to, from);
	skb_ext_copy(to, from);
	skb_copy_secmark(to, from);
}

int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr,
		      u8 nexthdr, __be32 frag_id,
		      struct ip6_fraglist_iter *iter)
{
	unsigned int first_len;
	struct frag_hdr *fh;

	/* BUILD HEADER */
	*prevhdr = NEXTHDR_FRAGMENT;
	iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
	if (!iter->tmp_hdr)
		return -ENOMEM;

	iter->frag = skb_shinfo(skb)->frag_list;
	skb_frag_list_init(skb);

	iter->offset = 0;
	iter->hlen = hlen;
	iter->frag_id = frag_id;
	iter->nexthdr = nexthdr;

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

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

	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));

	return 0;
}
EXPORT_SYMBOL(ip6_fraglist_init);

void ip6_fraglist_prepare(struct sk_buff *skb,
			  struct ip6_fraglist_iter *iter)
{
	struct sk_buff *frag = iter->frag;
	unsigned int hlen = iter->hlen;
	struct frag_hdr *fh;

	frag->ip_summed = CHECKSUM_NONE;
	skb_reset_transport_header(frag);
	fh = __skb_push(frag, sizeof(struct frag_hdr));
	__skb_push(frag, hlen);
	skb_reset_network_header(frag);
	memcpy(skb_network_header(frag), iter->tmp_hdr, hlen);
	iter->offset += skb->len - hlen - sizeof(struct frag_hdr);
	fh->nexthdr = iter->nexthdr;
	fh->reserved = 0;
	fh->frag_off = htons(iter->offset);
	if (frag->next)
		fh->frag_off |= htons(IP6_MF);
	fh->identification = iter->frag_id;
	ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr));
	ip6_copy_metadata(frag, skb);
}
EXPORT_SYMBOL(ip6_fraglist_prepare);

void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu,
		   unsigned short needed_tailroom, int hdr_room, u8 *prevhdr,
		   u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state)
{
	state->prevhdr = prevhdr;
	state->nexthdr = nexthdr;
	state->frag_id = frag_id;

	state->hlen = hlen;
	state->mtu = mtu;

	state->left = skb->len - hlen;	/* Space per frame */
	state->ptr = hlen;		/* Where to start from */

	state->hroom = hdr_room;
	state->troom = needed_tailroom;

	state->offset = 0;
}
EXPORT_SYMBOL(ip6_frag_init);

struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state)
{
	u8 *prevhdr = state->prevhdr, *fragnexthdr_offset;
	struct sk_buff *frag;
	struct frag_hdr *fh;
	unsigned int len;

	len = state->left;
	/* IF: it doesn't fit, use 'mtu' - the data space left */
	if (len > state->mtu)
		len = state->mtu;
	/* IF: we are not sending up to and including the packet end
	   then align the next start on an eight byte boundary */
	if (len < state->left)
		len &= ~7;

	/* Allocate buffer */
	frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) +
			 state->hroom + state->troom, GFP_ATOMIC);
	if (!frag)
		return ERR_PTR(-ENOMEM);

	/*
	 *	Set up data on packet
	 */

	ip6_copy_metadata(frag, skb);
	skb_reserve(frag, state->hroom);
	skb_put(frag, len + state->hlen + sizeof(struct frag_hdr));
	skb_reset_network_header(frag);
	fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen);
	frag->transport_header = (frag->network_header + state->hlen +
				  sizeof(struct frag_hdr));

	/*
	 *	Charge the memory for the fragment to any owner
	 *	it might possess
	 */
	if (skb->sk)
		skb_set_owner_w(frag, skb->sk);

	/*
	 *	Copy the packet header into the new buffer.
	 */
	skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen);

	fragnexthdr_offset = skb_network_header(frag);
	fragnexthdr_offset += prevhdr - skb_network_header(skb);
	*fragnexthdr_offset = NEXTHDR_FRAGMENT;

	/*
	 *	Build fragment header.
	 */
	fh->nexthdr = state->nexthdr;
	fh->reserved = 0;
	fh->identification = state->frag_id;

	/*
	 *	Copy a block of the IP datagram.
	 */
	BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag),
			     len));
	state->left -= len;

	fh->frag_off = htons(state->offset);
	if (state->left > 0)
		fh->frag_off |= htons(IP6_MF);
	ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr));

	state->ptr += len;
	state->offset += len;

	return frag;
}
EXPORT_SYMBOL(ip6_frag_next);

int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
		 int (*output)(struct net *, struct sock *, struct sk_buff *))
{
	struct sk_buff *frag;
	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
				inet6_sk(skb->sk) : NULL;
	struct ip6_frag_state state;
	unsigned int mtu, hlen, nexthdr_offset;
	ktime_t tstamp = skb->tstamp;
	int hroom, err = 0;
	__be32 frag_id;
	u8 *prevhdr, nexthdr = 0;

	err = ip6_find_1stfragopt(skb, &prevhdr);
	if (err < 0)
		goto fail;
	hlen = err;
	nexthdr = *prevhdr;
	nexthdr_offset = prevhdr - skb_network_header(skb);

	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 (unlikely(!skb->ignore_df && skb->len > mtu))
		goto fail_toobig;

	if (IP6CB(skb)->frag_max_size) {
		if (IP6CB(skb)->frag_max_size > mtu)
			goto fail_toobig;

		/* don't send fragments larger than what we received */
		mtu = IP6CB(skb)->frag_max_size;
		if (mtu < IPV6_MIN_MTU)
			mtu = IPV6_MIN_MTU;
	}

	if (np && np->frag_size < mtu) {
		if (np->frag_size)
			mtu = np->frag_size;
	}
	if (mtu < hlen + sizeof(struct frag_hdr) + 8)
		goto fail_toobig;
	mtu -= hlen + sizeof(struct frag_hdr);

	frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
				    &ipv6_hdr(skb)->saddr);

	if (skb->ip_summed == CHECKSUM_PARTIAL &&
	    (err = skb_checksum_help(skb)))
		goto fail;

	prevhdr = skb_network_header(skb) + nexthdr_offset;
	hroom = LL_RESERVED_SPACE(rt->dst.dev);
	if (skb_has_frag_list(skb)) {
		unsigned int first_len = skb_pagelen(skb);
		struct ip6_fraglist_iter iter;
		struct sk_buff *frag2;

		if (first_len - hlen > mtu ||
		    ((first_len - hlen) & 7) ||
		    skb_cloned(skb) ||
		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
			goto slow_path;

		skb_walk_frags(skb, frag) {
			/* Correct geometry. */
			if (frag->len > mtu ||
			    ((frag->len & 7) && frag->next) ||
			    skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr)))
				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 = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id,
					&iter);
		if (err < 0)
			goto fail;

		for (;;) {
			/* Prepare header of the next frame,
			 * before previous one went down. */
			if (iter.frag)
				ip6_fraglist_prepare(skb, &iter);

			skb->tstamp = tstamp;
			err = output(net, sk, skb);
			if (!err)
				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
					      IPSTATS_MIB_FRAGCREATES);

			if (err || !iter.frag)
				break;

			skb = ip6_fraglist_next(&iter);
		}

		kfree(iter.tmp_hdr);

		if (err == 0) {
			IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
				      IPSTATS_MIB_FRAGOKS);
			return 0;
		}

		kfree_skb_list(iter.frag);

		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
			      IPSTATS_MIB_FRAGFAILS);
		return err;

slow_path_clean:
		skb_walk_frags(skb, frag2) {
			if (frag2 == frag)
				break;
			frag2->sk = NULL;
			frag2->destructor = NULL;
			skb->truesize += frag2->truesize;
		}
	}

slow_path:
	/*
	 *	Fragment the datagram.
	 */

	ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom,
		      LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id,
		      &state);

	/*
	 *	Keep copying data until we run out.
	 */

	while (state.left > 0) {
		frag = ip6_frag_next(skb, &state);
		if (IS_ERR(frag)) {
			err = PTR_ERR(frag);
			goto fail;
		}

		/*
		 *	Put this fragment into the sending queue.
		 */
		frag->tstamp = tstamp;
		err = output(net, sk, frag);
		if (err)
			goto fail;

		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
			      IPSTATS_MIB_FRAGCREATES);
	}
	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
		      IPSTATS_MIB_FRAGOKS);
	consume_skb(skb);
	return err;

fail_toobig: