ndisc.c

/*
 *	Neighbour Discovery for IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Mike Shaver		<shaver@ingenia.com>
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

/*
 *	Changes:
 *
 *	Alexey I. Froloff		:	RFC6106 (DNSSL) support
 *	Pierre Ynard			:	export userland ND options
 *						through netlink (RDNSS support)
 *	Lars Fenneberg			:	fixed MTU setting on receipt
 *						of an RA.
 *	Janos Farkas			:	kmalloc failure checks
 *	Alexey Kuznetsov		:	state machine reworked
 *						and moved to net/core.
 *	Pekka Savola			:	RFC2461 validation
 *	YOSHIFUJI Hideaki @USAGI	:	Verify ND options properly
 */

#define pr_fmt(fmt) "ICMPv6: " fmt

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/route.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/jhash.h>

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

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>

#include <net/netlink.h>
#include <linux/rtnetlink.h>

#include <net/flow.h>
#include <net/ip6_checksum.h>
#include <net/inet_common.h>
#include <linux/proc_fs.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

/* Set to 3 to get tracing... */
#define ND_DEBUG 1

#define ND_PRINTK(val, level, fmt, ...)				\
do {								\
	if (val <= ND_DEBUG)					\
		net_##level##_ratelimited(fmt, ##__VA_ARGS__);	\
} while (0)

static u32 ndisc_hash(const void *pkey,
		      const struct net_device *dev,
		      __u32 *hash_rnd);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);

static const struct neigh_ops ndisc_generic_ops = {
	.family =		AF_INET6,
	.solicit =		ndisc_solicit,
	.error_report =		ndisc_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_connected_output,
};

static const struct neigh_ops ndisc_hh_ops = {
	.family =		AF_INET6,
	.solicit =		ndisc_solicit,
	.error_report =		ndisc_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_resolve_output,
};


static const struct neigh_ops ndisc_direct_ops = {
	.family =		AF_INET6,
	.output =		neigh_direct_output,
	.connected_output =	neigh_direct_output,
};

struct neigh_table nd_tbl = {
	.family =	AF_INET6,
	.key_len =	sizeof(struct in6_addr),
	.hash =		ndisc_hash,
	.constructor =	ndisc_constructor,
	.pconstructor =	pndisc_constructor,
	.pdestructor =	pndisc_destructor,
	.proxy_redo =	pndisc_redo,
	.id =		"ndisc_cache",
	.parms = {
		.tbl			= &nd_tbl,
		.base_reachable_time	= ND_REACHABLE_TIME,
		.retrans_time		= ND_RETRANS_TIMER,
		.gc_staletime		= 60 * HZ,
		.reachable_time		= ND_REACHABLE_TIME,
		.delay_probe_time	= 5 * HZ,
		.queue_len_bytes	= 64*1024,
		.ucast_probes		= 3,
		.mcast_probes		= 3,
		.anycast_delay		= 1 * HZ,
		.proxy_delay		= (8 * HZ) / 10,
		.proxy_qlen		= 64,
	},
	.gc_interval =	  30 * HZ,
	.gc_thresh1 =	 128,
	.gc_thresh2 =	 512,
	.gc_thresh3 =	1024,
};

static inline int ndisc_opt_addr_space(struct net_device *dev)
{
	return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type));
}

static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len,
				  unsigned short addr_type)
{
	int pad   = ndisc_addr_option_pad(addr_type);
	int space = NDISC_OPT_SPACE(data_len + pad);

	opt[0] = type;
	opt[1] = space>>3;

	memset(opt + 2, 0, pad);
	opt   += pad;
	space -= pad;

	memcpy(opt+2, data, data_len);
	data_len += 2;
	opt += data_len;
	if ((space -= data_len) > 0)
		memset(opt, 0, space);
	return opt + space;
}

static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
					    struct nd_opt_hdr *end)
{
	int type;
	if (!cur || !end || cur >= end)
		return NULL;
	type = cur->nd_opt_type;
	do {
		cur = ((void *)cur) + (cur->nd_opt_len << 3);
	} while(cur < end && cur->nd_opt_type != type);
	return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}

static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
{
	return opt->nd_opt_type == ND_OPT_RDNSS ||
		opt->nd_opt_type == ND_OPT_DNSSL;
}

static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
					     struct nd_opt_hdr *end)
{
	if (!cur || !end || cur >= end)
		return NULL;
	do {
		cur = ((void *)cur) + (cur->nd_opt_len << 3);
	} while(cur < end && !ndisc_is_useropt(cur));
	return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
}

struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
					  struct ndisc_options *ndopts)
{
	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;

	if (!nd_opt || opt_len < 0 || !ndopts)
		return NULL;
	memset(ndopts, 0, sizeof(*ndopts));
	while (opt_len) {
		int l;
		if (opt_len < sizeof(struct nd_opt_hdr))
			return NULL;
		l = nd_opt->nd_opt_len << 3;
		if (opt_len < l || l == 0)
			return NULL;
		switch (nd_opt->nd_opt_type) {
		case ND_OPT_SOURCE_LL_ADDR:
		case ND_OPT_TARGET_LL_ADDR:
		case ND_OPT_MTU:
		case ND_OPT_REDIRECT_HDR:
			if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
				ND_PRINTK(2, warn,
					  "%s: duplicated ND6 option found: type=%d\n",
					  __func__, nd_opt->nd_opt_type);
			} else {
				ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
			}
			break;
		case ND_OPT_PREFIX_INFO:
			ndopts->nd_opts_pi_end = nd_opt;
			if (!ndopts->nd_opt_array[nd_opt->nd_opt_type])
				ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
			break;
#ifdef CONFIG_IPV6_ROUTE_INFO
		case ND_OPT_ROUTE_INFO:
			ndopts->nd_opts_ri_end = nd_opt;
			if (!ndopts->nd_opts_ri)
				ndopts->nd_opts_ri = nd_opt;
			break;
#endif
		default:
			if (ndisc_is_useropt(nd_opt)) {
				ndopts->nd_useropts_end = nd_opt;
				if (!ndopts->nd_useropts)
					ndopts->nd_useropts = nd_opt;
			} else {
				/*
				 * Unknown options must be silently ignored,
				 * to accommodate future extension to the
				 * protocol.
				 */
				ND_PRINTK(2, notice,
					  "%s: ignored unsupported option; type=%d, len=%d\n",
					  __func__,
					  nd_opt->nd_opt_type,
					  nd_opt->nd_opt_len);
			}
		}
		opt_len -= l;
		nd_opt = ((void *)nd_opt) + l;
	}
	return ndopts;
}

int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
{
	switch (dev->type) {
	case ARPHRD_ETHER:
	case ARPHRD_IEEE802:	/* Not sure. Check it later. --ANK */
	case ARPHRD_FDDI:
		ipv6_eth_mc_map(addr, buf);
		return 0;
	case ARPHRD_ARCNET:
		ipv6_arcnet_mc_map(addr, buf);
		return 0;
	case ARPHRD_INFINIBAND:
		ipv6_ib_mc_map(addr, dev->broadcast, buf);
		return 0;
	case ARPHRD_IPGRE:
		return ipv6_ipgre_mc_map(addr, dev->broadcast, buf);
	default:
		if (dir) {
			memcpy(buf, dev->broadcast, dev->addr_len);
			return 0;
		}
	}
	return -EINVAL;
}

EXPORT_SYMBOL(ndisc_mc_map);

static u32 ndisc_hash(const void *pkey,
		      const struct net_device *dev,
		      __u32 *hash_rnd)
{
	return ndisc_hashfn(pkey, dev, hash_rnd);
}

static int ndisc_constructor(struct neighbour *neigh)
{
	struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key;
	struct net_device *dev = neigh->dev;
	struct inet6_dev *in6_dev;
	struct neigh_parms *parms;
	bool is_multicast = ipv6_addr_is_multicast(addr);

	in6_dev = in6_dev_get(dev);
	if (in6_dev == NULL) {
		return -EINVAL;
	}

	parms = in6_dev->nd_parms;
	__neigh_parms_put(neigh->parms);
	neigh->parms = neigh_parms_clone(parms);

	neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST;
	if (!dev->header_ops) {
		neigh->nud_state = NUD_NOARP;
		neigh->ops = &ndisc_direct_ops;
		neigh->output = neigh_direct_output;
	} else {
		if (is_multicast) {
			neigh->nud_state = NUD_NOARP;
			ndisc_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);
			if (dev->flags&IFF_LOOPBACK)
				neigh->type = RTN_LOCAL;
		} else if (dev->flags&IFF_POINTOPOINT) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->broadcast, dev->addr_len);
		}
		if (dev->header_ops->cache)
			neigh->ops = &ndisc_hh_ops;
		else
			neigh->ops = &ndisc_generic_ops;
		if (neigh->nud_state&NUD_VALID)
			neigh->output = neigh->ops->connected_output;
		else
			neigh->output = neigh->ops->output;
	}
	in6_dev_put(in6_dev);
	return 0;
}

static int pndisc_constructor(struct pneigh_entry *n)
{
	struct in6_addr *addr = (struct in6_addr*)&n->key;
	struct in6_addr maddr;
	struct net_device *dev = n->dev;

	if (dev == NULL || __in6_dev_get(dev) == NULL)
		return -EINVAL;
	addrconf_addr_solict_mult(addr, &maddr);
	ipv6_dev_mc_inc(dev, &maddr);
	return 0;
}

static void pndisc_destructor(struct pneigh_entry *n)
{
	struct in6_addr *addr = (struct in6_addr*)&n->key;
	struct in6_addr maddr;
	struct net_device *dev = n->dev;

	if (dev == NULL || __in6_dev_get(dev) == NULL)
		return;
	addrconf_addr_solict_mult(addr, &maddr);
	ipv6_dev_mc_dec(dev, &maddr);
}

static 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;
	int err;
	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 = sock_alloc_send_skb(sk,
				  (MAX_HEADER + sizeof(struct ipv6hdr) +
				   len + hlen + tlen),
				  1, &err);
	if (!skb) {
		ND_PRINTK(0, err, "ND: %s failed to allocate an skb, err=%d\n",
			  __func__, err);
		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));

	return skb;
}

static 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();
}

/*
 *	Send a Neighbour Discover packet
 */
static void __ndisc_send(struct net_device *dev,
			 struct neighbour *neigh,
			 const struct in6_addr *daddr,
			 const struct in6_addr *saddr,
			 struct icmp6hdr *icmp6h, const struct in6_addr *target,
			 int llinfo)
{
	struct sk_buff *skb;

	skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo);
	if (!skb)
		return;

	ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h);
}

static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
			  const struct in6_addr *daddr,
			  const struct in6_addr *solicited_addr,
			  int router, int solicited, int override, int inc_opt)
{
	struct in6_addr tmpaddr;
	struct inet6_ifaddr *ifp;
	const struct in6_addr *src_addr;
	struct icmp6hdr icmp6h = {
		.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
	};

	/* for anycast or proxy, solicited_addr != src_addr */
	ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1);
	if (ifp) {
		src_addr = solicited_addr;
		if (ifp->flags & IFA_F_OPTIMISTIC)
			override = 0;
		inc_opt |= ifp->idev->cnf.force_tllao;
		in6_ifa_put(ifp);
	} else {
		if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
				       inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs,
				       &tmpaddr))
			return;
		src_addr = &tmpaddr;
	}

	icmp6h.icmp6_router = router;
	icmp6h.icmp6_solicited = solicited;
	icmp6h.icmp6_override = override;

	__ndisc_send(dev, neigh, daddr, src_addr,
		     &icmp6h, solicited_addr,
		     inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
}

static void ndisc_send_unsol_na(struct net_device *dev)
{
	struct inet6_dev *idev;
	struct inet6_ifaddr *ifa;

	idev = in6_dev_get(dev);
	if (!idev)
		return;

	read_lock_bh(&idev->lock);
	list_for_each_entry(ifa, &idev->addr_list, if_list) {
		ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr,
			      /*router=*/ !!idev->cnf.forwarding,
			      /*solicited=*/ false, /*override=*/ true,
			      /*inc_opt=*/ true);
	}
	read_unlock_bh(&idev->lock);

	in6_dev_put(idev);
}

void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
		   const struct in6_addr *solicit,
		   const struct in6_addr *daddr, const struct in6_addr *saddr)
{
	struct in6_addr addr_buf;
	struct icmp6hdr icmp6h = {
		.icmp6_type = NDISC_NEIGHBOUR_SOLICITATION,
	};

	if (saddr == NULL) {
		if (ipv6_get_lladdr(dev, &addr_buf,
				   (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
			return;
		saddr = &addr_buf;
	}

	__ndisc_send(dev, neigh, daddr, saddr,
		     &icmp6h, solicit,
		     !ipv6_addr_any(saddr) ? ND_OPT_SOURCE_LL_ADDR : 0);
}

void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
		   const struct in6_addr *daddr)
{
	struct icmp6hdr icmp6h = {
		.icmp6_type = NDISC_ROUTER_SOLICITATION,
	};
	int send_sllao = dev->addr_len;

#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
	/*
	 * According to section 2.2 of RFC 4429, we must not
	 * send router solicitations with a sllao from
	 * optimistic addresses, but we may send the solicitation
	 * if we don't include the sllao.  So here we check
	 * if our address is optimistic, and if so, we
	 * suppress the inclusion of the sllao.
	 */
	if (send_sllao) {
		struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr,
							   dev, 1);
		if (ifp) {
			if (ifp->flags & IFA_F_OPTIMISTIC)  {
				send_sllao = 0;
			}
			in6_ifa_put(ifp);
		} else {
			send_sllao = 0;
		}
	}
#endif
	__ndisc_send(dev, NULL, daddr, saddr,
		     &icmp6h, NULL,
		     send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0);
}


static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb)
{
	/*
	 *	"The sender MUST return an ICMP
	 *	 destination unreachable"
	 */
	dst_link_failure(skb);
	kfree_skb(skb);
}

/* Called with locked neigh: either read or both */

static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
	struct in6_addr *saddr = NULL;
	struct in6_addr mcaddr;
	struct net_device *dev = neigh->dev;
	struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
	int probes = atomic_read(&neigh->probes);

	if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1))
		saddr = &ipv6_hdr(skb)->saddr;

	if ((probes -= neigh->parms->ucast_probes) < 0) {
		if (!(neigh->nud_state & NUD_VALID)) {
			ND_PRINTK(1, dbg,
				  "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
				  __func__, target);
		}
		ndisc_send_ns(dev, neigh, target, target, saddr);
	} else if ((probes -= neigh->parms->app_probes) < 0) {
#ifdef CONFIG_ARPD
		neigh_app_ns(neigh);
#endif
	} else {
		addrconf_addr_solict_mult(target, &mcaddr);
		ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
	}
}

static int pndisc_is_router(const void *pkey,
			    struct net_device *dev)
{
	struct pneigh_entry *n;
	int ret = -1;

	read_lock_bh(&nd_tbl.lock);
	n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
	if (n)
		ret = !!(n->flags & NTF_ROUTER);
	read_unlock_bh(&nd_tbl.lock);

	return ret;
}

static void ndisc_recv_ns(struct sk_buff *skb)
{
	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
	u8 *lladdr = NULL;
	u32 ndoptlen = skb->tail - (skb->transport_header +
				    offsetof(struct nd_msg, opt));
	struct ndisc_options ndopts;
	struct net_device *dev = skb->dev;
	struct inet6_ifaddr *ifp;
	struct inet6_dev *idev = NULL;
	struct neighbour *neigh;
	int dad = ipv6_addr_any(saddr);
	bool inc;
	int is_router = -1;

	if (ipv6_addr_is_multicast(&msg->target)) {
		ND_PRINTK(2, warn, "NS: multicast target address\n");
		return;
	}

	/*
	 * RFC2461 7.1.1:
	 * DAD has to be destined for solicited node multicast address.
	 */
	if (dad &&
	    !(daddr->s6_addr32[0] == htonl(0xff020000) &&
	      daddr->s6_addr32[1] == htonl(0x00000000) &&
	      daddr->s6_addr32[2] == htonl(0x00000001) &&
	      daddr->s6_addr [12] == 0xff )) {
		ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n");
		return;
	}

	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
		ND_PRINTK(2, warn, "NS: invalid ND options\n");
		return;
	}

	if (ndopts.nd_opts_src_lladdr) {
		lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
		if (!lladdr) {
			ND_PRINTK(2, warn,
				  "NS: invalid link-layer address length\n");
			return;
		}

		/* RFC2461 7.1.1:
		 *	If the IP source address is the unspecified address,
		 *	there MUST NOT be source link-layer address option
		 *	in the message.
		 */
		if (dad) {
			ND_PRINTK(2, warn,
				  "NS: bad DAD packet (link-layer address option)\n");
			return;
		}
	}

	inc = ipv6_addr_is_multicast(daddr);

	ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
	if (ifp) {

		if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
			if (dad) {
				/*
				 * We are colliding with another node
				 * who is doing DAD
				 * so fail our DAD process
				 */
				addrconf_dad_failure(ifp);
				return;
			} else {
				/*
				 * This is not a dad solicitation.
				 * If we are an optimistic node,
				 * we should respond.
				 * Otherwise, we should ignore it.
				 */
				if (!(ifp->flags & IFA_F_OPTIMISTIC))
					goto out;
			}
		}

		idev = ifp->idev;
	} else {
		struct net *net = dev_net(dev);

		idev = in6_dev_get(dev);
		if (!idev) {
			/* XXX: count this drop? */
			return;
		}

		if (ipv6_chk_acast_addr(net, dev, &msg->target) ||
		    (idev->cnf.forwarding &&
		     (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) &&
		     (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
			if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
			    skb->pkt_type != PACKET_HOST &&
			    inc != 0 &&
			    idev->nd_parms->proxy_delay != 0) {
				/*
				 * for anycast or proxy,
				 * sender should delay its response
				 * by a random time between 0 and
				 * MAX_ANYCAST_DELAY_TIME seconds.
				 * (RFC2461) -- yoshfuji
				 */
				struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
				if (n)
					pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
				goto out;
			}
		} else
			goto out;
	}

	if (is_router < 0)
		is_router = !!idev->cnf.forwarding;

	if (dad) {
		ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target,
			      is_router, 0, (ifp != NULL), 1);
		goto out;
	}

	if (inc)
		NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast);
	else
		NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast);

	/*
	 *	update / create cache entry
	 *	for the source address
	 */
	neigh = __neigh_lookup(&nd_tbl, saddr, dev,
			       !inc || lladdr || !dev->addr_len);
	if (neigh)
		neigh_update(neigh, lladdr, NUD_STALE,
			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
			     NEIGH_UPDATE_F_OVERRIDE);
	if (neigh || !dev->header_ops) {
		ndisc_send_na(dev, neigh, saddr, &msg->target,
			      is_router,
			      1, (ifp != NULL && inc), inc);
		if (neigh)
			neigh_release(neigh);
	}

out:
	if (ifp)
		in6_ifa_put(ifp);
	else
		in6_dev_put(idev);
}

static void ndisc_recv_na(struct sk_buff *skb)
{
	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
	u8 *lladdr = NULL;
	u32 ndoptlen = skb->tail - (skb->transport_header +
				    offsetof(struct nd_msg, opt));
	struct ndisc_options ndopts;
	struct net_device *dev = skb->dev;
	struct inet6_ifaddr *ifp;
	struct neighbour *neigh;

	if (skb->len < sizeof(struct nd_msg)) {
		ND_PRINTK(2, warn, "NA: packet too short\n");
		return;
	}

	if (ipv6_addr_is_multicast(&msg->target)) {
		ND_PRINTK(2, warn, "NA: target address is multicast\n");
		return;
	}

	if (ipv6_addr_is_multicast(daddr) &&
	    msg->icmph.icmp6_solicited) {
		ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n");
		return;
	}

	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
		ND_PRINTK(2, warn, "NS: invalid ND option\n");
		return;
	}
	if (ndopts.nd_opts_tgt_lladdr) {
		lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev);
		if (!lladdr) {
			ND_PRINTK(2, warn,
				  "NA: invalid link-layer address length\n");
			return;
		}
	}
	ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
	if (ifp) {
		if (skb->pkt_type != PACKET_LOOPBACK
		    && (ifp->flags & IFA_F_TENTATIVE)) {
				addrconf_dad_failure(ifp);
				return;
		}
		/* What should we make now? The advertisement
		   is invalid, but ndisc specs say nothing
		   about it. It could be misconfiguration, or
		   an smart proxy agent tries to help us :-)

		   We should not print the error if NA has been
		   received from loopback - it is just our own
		   unsolicited advertisement.
		 */
		if (skb->pkt_type != PACKET_LOOPBACK)
			ND_PRINTK(1, warn,
				  "NA: someone advertises our address %pI6 on %s!\n",
				  &ifp->addr, ifp->idev->dev->name);
		in6_ifa_put(ifp);
		return;
	}
	neigh = neigh_lookup(&nd_tbl, &msg->target, dev);

	if (neigh) {
		u8 old_flags = neigh->flags;
		struct net *net = dev_net(dev);

		if (neigh->nud_state & NUD_FAILED)
			goto out;

		/*
		 * Don't update the neighbor cache entry on a proxy NA from
		 * ourselves because either the proxied node is off link or it
		 * has already sent a NA to us.
		 */
		if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) &&
		    net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp &&
		    pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) {
			/* XXX: idev->cnf.proxy_ndp */
			goto out;
		}

		neigh_update(neigh, lladdr,
			     msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
			     (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
			     (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));

		if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
			/*
			 * Change: router to host
			 */
			struct rt6_info *rt;
			rt = rt6_get_dflt_router(saddr, dev);
			if (rt)
				ip6_del_rt(rt);
		}

out:
		neigh_release(neigh);
	}
}

static void ndisc_recv_rs(struct sk_buff *skb)
{
	struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb);
	unsigned long ndoptlen = skb->len - sizeof(*rs_msg);
	struct neighbour *neigh;
	struct inet6_dev *idev;
	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
	struct ndisc_options ndopts;
	u8 *lladdr = NULL;

	if (skb->len < sizeof(*rs_msg))
		return;

	idev = __in6_dev_get(skb->dev);
	if (!idev) {
		ND_PRINTK(1, err, "RS: can't find in6 device\n");
		return;
	}

	/* Don't accept RS if we're not in router mode */
	if (!idev->cnf.forwarding)
		goto out;

	/*
	 * Don't update NCE if src = ::;
	 * this implies that the source node has no ip address assigned yet.
	 */
	if (ipv6_addr_any(saddr))
		goto out;

	/* Parse ND options */
	if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
		ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
		goto out;
	}

	if (ndopts.nd_opts_src_lladdr) {
		lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
					     skb->dev);
		if (!lladdr)
			goto out;
	}

	neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
	if (neigh) {
		neigh_update(neigh, lladdr, NUD_STALE,
			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
			     NEIGH_UPDATE_F_OVERRIDE|
			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
		neigh_release(neigh);
	}
out:
	return;
}

static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
{
	struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra);
	struct sk_buff *skb;
	struct nlmsghdr *nlh;
	struct nduseroptmsg *ndmsg;
	struct net *net = dev_net(ra->dev);
	int err;
	int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg)
				    + (opt->nd_opt_len << 3));
	size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr));

	skb = nlmsg_new(msg_size, GFP_ATOMIC);
	if (skb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}