ip6_tables.c

/*
 * Packet matching code.
 *
 * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
 * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/capability.h>
#include <linux/in.h>
#include <linux/skbuff.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
#include <linux/netdevice.h>
#include <linux/module.h>
#include <linux/poison.h>
#include <linux/icmpv6.h>
#include <net/ipv6.h>
#include <asm/uaccess.h>
#include <linux/mutex.h>
#include <linux/proc_fs.h>
#include <linux/cpumask.h>

#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/netfilter/x_tables.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("IPv6 packet filter");

/*#define DEBUG_IP_FIREWALL*/
/*#define DEBUG_ALLOW_ALL*/ /* Useful for remote debugging */
/*#define DEBUG_IP_FIREWALL_USER*/

#ifdef DEBUG_IP_FIREWALL
#define dprintf(format, args...)  printk(format , ## args)
#else
#define dprintf(format, args...)
#endif

#ifdef DEBUG_IP_FIREWALL_USER
#define duprintf(format, args...) printk(format , ## args)
#else
#define duprintf(format, args...)
#endif

#ifdef CONFIG_NETFILTER_DEBUG
#define IP_NF_ASSERT(x)						\
do {								\
	if (!(x))						\
		printk("IP_NF_ASSERT: %s:%s:%u\n",		\
		       __FUNCTION__, __FILE__, __LINE__);	\
} while(0)
#else
#define IP_NF_ASSERT(x)
#endif

#if 0
/* All the better to debug you with... */
#define static
#define inline
#endif

/*
   We keep a set of rules for each CPU, so we can avoid write-locking
   them in the softirq when updating the counters and therefore
   only need to read-lock in the softirq; doing a write_lock_bh() in user
   context stops packets coming through and allows user context to read
   the counters or update the rules.

   Hence the start of any table is given by get_table() below.  */

/* Check for an extension */
int
ip6t_ext_hdr(u8 nexthdr)
{
	return ( (nexthdr == IPPROTO_HOPOPTS)   ||
		 (nexthdr == IPPROTO_ROUTING)   ||
		 (nexthdr == IPPROTO_FRAGMENT)  ||
		 (nexthdr == IPPROTO_ESP)       ||
		 (nexthdr == IPPROTO_AH)        ||
		 (nexthdr == IPPROTO_NONE)      ||
		 (nexthdr == IPPROTO_DSTOPTS) );
}

/* Returns whether matches rule or not. */
static inline bool
ip6_packet_match(const struct sk_buff *skb,
		 const char *indev,
		 const char *outdev,
		 const struct ip6t_ip6 *ip6info,
		 unsigned int *protoff,
		 int *fragoff, bool *hotdrop)
{
	size_t i;
	unsigned long ret;
	const struct ipv6hdr *ipv6 = ipv6_hdr(skb);

#define FWINV(bool,invflg) ((bool) ^ !!(ip6info->invflags & invflg))

	if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk,
				       &ip6info->src), IP6T_INV_SRCIP)
	    || FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk,
					  &ip6info->dst), IP6T_INV_DSTIP)) {
		dprintf("Source or dest mismatch.\n");
/*
		dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr,
			ipinfo->smsk.s_addr, ipinfo->src.s_addr,
			ipinfo->invflags & IP6T_INV_SRCIP ? " (INV)" : "");
		dprintf("DST: %u. Mask: %u. Target: %u.%s\n", ip->daddr,
			ipinfo->dmsk.s_addr, ipinfo->dst.s_addr,
			ipinfo->invflags & IP6T_INV_DSTIP ? " (INV)" : "");*/
		return false;
	}

	/* Look for ifname matches; this should unroll nicely. */
	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
		ret |= (((const unsigned long *)indev)[i]
			^ ((const unsigned long *)ip6info->iniface)[i])
			& ((const unsigned long *)ip6info->iniface_mask)[i];
	}

	if (FWINV(ret != 0, IP6T_INV_VIA_IN)) {
		dprintf("VIA in mismatch (%s vs %s).%s\n",
			indev, ip6info->iniface,
			ip6info->invflags&IP6T_INV_VIA_IN ?" (INV)":"");
		return false;
	}

	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
		ret |= (((const unsigned long *)outdev)[i]
			^ ((const unsigned long *)ip6info->outiface)[i])
			& ((const unsigned long *)ip6info->outiface_mask)[i];
	}

	if (FWINV(ret != 0, IP6T_INV_VIA_OUT)) {
		dprintf("VIA out mismatch (%s vs %s).%s\n",
			outdev, ip6info->outiface,
			ip6info->invflags&IP6T_INV_VIA_OUT ?" (INV)":"");
		return false;
	}

/* ... might want to do something with class and flowlabel here ... */

	/* look for the desired protocol header */
	if((ip6info->flags & IP6T_F_PROTO)) {
		int protohdr;
		unsigned short _frag_off;

		protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off);
		if (protohdr < 0) {
			if (_frag_off == 0)
				*hotdrop = true;
			return false;
		}
		*fragoff = _frag_off;

		dprintf("Packet protocol %hi ?= %s%hi.\n",
				protohdr,
				ip6info->invflags & IP6T_INV_PROTO ? "!":"",
				ip6info->proto);

		if (ip6info->proto == protohdr) {
			if(ip6info->invflags & IP6T_INV_PROTO) {
				return false;
			}
			return true;
		}

		/* We need match for the '-p all', too! */
		if ((ip6info->proto != 0) &&
			!(ip6info->invflags & IP6T_INV_PROTO))
			return false;
	}
	return true;
}

/* should be ip6 safe */
static inline bool
ip6_checkentry(const struct ip6t_ip6 *ipv6)
{
	if (ipv6->flags & ~IP6T_F_MASK) {
		duprintf("Unknown flag bits set: %08X\n",
			 ipv6->flags & ~IP6T_F_MASK);
		return false;
	}
	if (ipv6->invflags & ~IP6T_INV_MASK) {
		duprintf("Unknown invflag bits set: %08X\n",
			 ipv6->invflags & ~IP6T_INV_MASK);
		return false;
	}
	return true;
}

static unsigned int
ip6t_error(struct sk_buff *skb,
	  const struct net_device *in,
	  const struct net_device *out,
	  unsigned int hooknum,
	  const struct xt_target *target,
	  const void *targinfo)
{
	if (net_ratelimit())
		printk("ip6_tables: error: `%s'\n", (char *)targinfo);

	return NF_DROP;
}

static inline
bool do_match(struct ip6t_entry_match *m,
	      const struct sk_buff *skb,
	      const struct net_device *in,
	      const struct net_device *out,
	      int offset,
	      unsigned int protoff,
	      bool *hotdrop)
{
	/* Stop iteration if it doesn't match */
	if (!m->u.kernel.match->match(skb, in, out, m->u.kernel.match, m->data,
				      offset, protoff, hotdrop))
		return true;
	else
		return false;
}

static inline struct ip6t_entry *
get_entry(void *base, unsigned int offset)
{
	return (struct ip6t_entry *)(base + offset);
}

/* All zeroes == unconditional rule. */
static inline int
unconditional(const struct ip6t_ip6 *ipv6)
{
	unsigned int i;

	for (i = 0; i < sizeof(*ipv6); i++)
		if (((char *)ipv6)[i])
			break;

	return (i == sizeof(*ipv6));
}

#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
/* This cries for unification! */
static const char *hooknames[] = {
	[NF_INET_PRE_ROUTING]		= "PREROUTING",
	[NF_INET_LOCAL_IN]		= "INPUT",
	[NF_INET_FORWARD]		= "FORWARD",
	[NF_INET_LOCAL_OUT]		= "OUTPUT",
	[NF_INET_POST_ROUTING]		= "POSTROUTING",
};

enum nf_ip_trace_comments {
	NF_IP6_TRACE_COMMENT_RULE,
	NF_IP6_TRACE_COMMENT_RETURN,
	NF_IP6_TRACE_COMMENT_POLICY,
};

static const char *comments[] = {
	[NF_IP6_TRACE_COMMENT_RULE]	= "rule",
	[NF_IP6_TRACE_COMMENT_RETURN]	= "return",
	[NF_IP6_TRACE_COMMENT_POLICY]	= "policy",
};

static struct nf_loginfo trace_loginfo = {
	.type = NF_LOG_TYPE_LOG,
	.u = {
		.log = {
			.level = 4,
			.logflags = NF_LOG_MASK,
		},
	},
};

static inline int
get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e,
		      char *hookname, char **chainname,
		      char **comment, unsigned int *rulenum)
{
	struct ip6t_standard_target *t = (void *)ip6t_get_target(s);

	if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) {
		/* Head of user chain: ERROR target with chainname */
		*chainname = t->target.data;
		(*rulenum) = 0;
	} else if (s == e) {
		(*rulenum)++;

		if (s->target_offset == sizeof(struct ip6t_entry)
		   && strcmp(t->target.u.kernel.target->name,
			     IP6T_STANDARD_TARGET) == 0
		   && t->verdict < 0
		   && unconditional(&s->ipv6)) {
			/* Tail of chains: STANDARD target (return/policy) */
			*comment = *chainname == hookname
				? (char *)comments[NF_IP6_TRACE_COMMENT_POLICY]
				: (char *)comments[NF_IP6_TRACE_COMMENT_RETURN];
		}
		return 1;
	} else
		(*rulenum)++;

	return 0;
}

static void trace_packet(struct sk_buff *skb,
			 unsigned int hook,
			 const struct net_device *in,
			 const struct net_device *out,
			 char *tablename,
			 struct xt_table_info *private,
			 struct ip6t_entry *e)
{
	void *table_base;
	struct ip6t_entry *root;
	char *hookname, *chainname, *comment;
	unsigned int rulenum = 0;

	table_base = (void *)private->entries[smp_processor_id()];
	root = get_entry(table_base, private->hook_entry[hook]);

	hookname = chainname = (char *)hooknames[hook];
	comment = (char *)comments[NF_IP6_TRACE_COMMENT_RULE];

	IP6T_ENTRY_ITERATE(root,
			   private->size - private->hook_entry[hook],
			   get_chainname_rulenum,
			   e, hookname, &chainname, &comment, &rulenum);

	nf_log_packet(AF_INET6, hook, skb, in, out, &trace_loginfo,
		      "TRACE: %s:%s:%s:%u ",
		      tablename, chainname, comment, rulenum);
}
#endif

/* Returns one of the generic firewall policies, like NF_ACCEPT. */
unsigned int
ip6t_do_table(struct sk_buff *skb,
	      unsigned int hook,
	      const struct net_device *in,
	      const struct net_device *out,
	      struct xt_table *table)
{
	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
	int offset = 0;
	unsigned int protoff = 0;
	bool hotdrop = false;
	/* Initializing verdict to NF_DROP keeps gcc happy. */
	unsigned int verdict = NF_DROP;
	const char *indev, *outdev;
	void *table_base;
	struct ip6t_entry *e, *back;
	struct xt_table_info *private;

	/* Initialization */
	indev = in ? in->name : nulldevname;
	outdev = out ? out->name : nulldevname;
	/* We handle fragments by dealing with the first fragment as
	 * if it was a normal packet.  All other fragments are treated
	 * normally, except that they will NEVER match rules that ask
	 * things we don't know, ie. tcp syn flag or ports).  If the
	 * rule is also a fragment-specific rule, non-fragments won't
	 * match it. */

	read_lock_bh(&table->lock);
	private = table->private;
	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
	table_base = (void *)private->entries[smp_processor_id()];
	e = get_entry(table_base, private->hook_entry[hook]);

	/* For return from builtin chain */
	back = get_entry(table_base, private->underflow[hook]);

	do {
		IP_NF_ASSERT(e);
		IP_NF_ASSERT(back);
		if (ip6_packet_match(skb, indev, outdev, &e->ipv6,
			&protoff, &offset, &hotdrop)) {
			struct ip6t_entry_target *t;

			if (IP6T_MATCH_ITERATE(e, do_match,
					       skb, in, out,
					       offset, protoff, &hotdrop) != 0)
				goto no_match;

			ADD_COUNTER(e->counters,
				    ntohs(ipv6_hdr(skb)->payload_len) +
				    sizeof(struct ipv6hdr), 1);

			t = ip6t_get_target(e);
			IP_NF_ASSERT(t->u.kernel.target);

#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
			/* The packet is traced: log it */
			if (unlikely(skb->nf_trace))
				trace_packet(skb, hook, in, out,
					     table->name, private, e);
#endif
			/* Standard target? */
			if (!t->u.kernel.target->target) {
				int v;

				v = ((struct ip6t_standard_target *)t)->verdict;
				if (v < 0) {
					/* Pop from stack? */
					if (v != IP6T_RETURN) {
						verdict = (unsigned)(-v) - 1;
						break;
					}
					e = back;
					back = get_entry(table_base,
							 back->comefrom);
					continue;
				}
				if (table_base + v != (void *)e + e->next_offset
				    && !(e->ipv6.flags & IP6T_F_GOTO)) {
					/* Save old back ptr in next entry */
					struct ip6t_entry *next
						= (void *)e + e->next_offset;
					next->comefrom
						= (void *)back - table_base;
					/* set back pointer to next entry */
					back = next;
				}

				e = get_entry(table_base, v);
			} else {
				/* Targets which reenter must return
				   abs. verdicts */
#ifdef CONFIG_NETFILTER_DEBUG
				((struct ip6t_entry *)table_base)->comefrom
					= 0xeeeeeeec;
#endif
				verdict = t->u.kernel.target->target(skb,
								     in, out,
								     hook,
								     t->u.kernel.target,
								     t->data);

#ifdef CONFIG_NETFILTER_DEBUG
				if (((struct ip6t_entry *)table_base)->comefrom
				    != 0xeeeeeeec
				    && verdict == IP6T_CONTINUE) {
					printk("Target %s reentered!\n",
					       t->u.kernel.target->name);
					verdict = NF_DROP;
				}
				((struct ip6t_entry *)table_base)->comefrom
					= 0x57acc001;
#endif
				if (verdict == IP6T_CONTINUE)
					e = (void *)e + e->next_offset;
				else
					/* Verdict */
					break;
			}
		} else {

		no_match:
			e = (void *)e + e->next_offset;
		}
	} while (!hotdrop);

#ifdef CONFIG_NETFILTER_DEBUG
	((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON;
#endif
	read_unlock_bh(&table->lock);

#ifdef DEBUG_ALLOW_ALL
	return NF_ACCEPT;
#else
	if (hotdrop)
		return NF_DROP;
	else return verdict;
#endif
}

/* Figures out from what hook each rule can be called: returns 0 if
   there are loops.  Puts hook bitmask in comefrom. */
static int
mark_source_chains(struct xt_table_info *newinfo,
		   unsigned int valid_hooks, void *entry0)
{
	unsigned int hook;

	/* No recursion; use packet counter to save back ptrs (reset
	   to 0 as we leave), and comefrom to save source hook bitmask */
	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
		unsigned int pos = newinfo->hook_entry[hook];
		struct ip6t_entry *e
			= (struct ip6t_entry *)(entry0 + pos);
		int visited = e->comefrom & (1 << hook);

		if (!(valid_hooks & (1 << hook)))
			continue;

		/* Set initial back pointer. */
		e->counters.pcnt = pos;

		for (;;) {
			struct ip6t_standard_target *t
				= (void *)ip6t_get_target(e);

			if (e->comefrom & (1 << NF_INET_NUMHOOKS)) {
				printk("iptables: loop hook %u pos %u %08X.\n",
				       hook, pos, e->comefrom);
				return 0;
			}
			e->comefrom
				|= ((1 << hook) | (1 << NF_INET_NUMHOOKS));

			/* Unconditional return/END. */
			if ((e->target_offset == sizeof(struct ip6t_entry)
			    && (strcmp(t->target.u.user.name,
				       IP6T_STANDARD_TARGET) == 0)
			    && t->verdict < 0
			    && unconditional(&e->ipv6)) || visited) {
				unsigned int oldpos, size;

				if (t->verdict < -NF_MAX_VERDICT - 1) {
					duprintf("mark_source_chains: bad "
						"negative verdict (%i)\n",
								t->verdict);
					return 0;
				}

				/* Return: backtrack through the last
				   big jump. */
				do {
					e->comefrom ^= (1<<NF_INET_NUMHOOKS);
#ifdef DEBUG_IP_FIREWALL_USER
					if (e->comefrom
					    & (1 << NF_INET_NUMHOOKS)) {
						duprintf("Back unset "
							 "on hook %u "
							 "rule %u\n",
							 hook, pos);
					}
#endif
					oldpos = pos;
					pos = e->counters.pcnt;
					e->counters.pcnt = 0;

					/* We're at the start. */
					if (pos == oldpos)
						goto next;

					e = (struct ip6t_entry *)
						(entry0 + pos);
				} while (oldpos == pos + e->next_offset);

				/* Move along one */
				size = e->next_offset;
				e = (struct ip6t_entry *)
					(entry0 + pos + size);
				e->counters.pcnt = pos;
				pos += size;
			} else {
				int newpos = t->verdict;

				if (strcmp(t->target.u.user.name,
					   IP6T_STANDARD_TARGET) == 0
				    && newpos >= 0) {
					if (newpos > newinfo->size -
						sizeof(struct ip6t_entry)) {
						duprintf("mark_source_chains: "
							"bad verdict (%i)\n",
								newpos);
						return 0;
					}
					/* This a jump; chase it. */
					duprintf("Jump rule %u -> %u\n",
						 pos, newpos);
				} else {
					/* ... this is a fallthru */
					newpos = pos + e->next_offset;
				}
				e = (struct ip6t_entry *)
					(entry0 + newpos);
				e->counters.pcnt = pos;
				pos = newpos;
			}
		}
		next:
		duprintf("Finished chain %u\n", hook);
	}
	return 1;
}

static inline int
cleanup_match(struct ip6t_entry_match *m, unsigned int *i)
{
	if (i && (*i)-- == 0)
		return 1;

	if (m->u.kernel.match->destroy)
		m->u.kernel.match->destroy(m->u.kernel.match, m->data);
	module_put(m->u.kernel.match->me);
	return 0;
}

static inline int
check_entry(struct ip6t_entry *e, const char *name)
{
	struct ip6t_entry_target *t;

	if (!ip6_checkentry(&e->ipv6)) {
		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
		return -EINVAL;
	}

	if (e->target_offset + sizeof(struct ip6t_entry_target) >
	    e->next_offset)
		return -EINVAL;

	t = ip6t_get_target(e);
	if (e->target_offset + t->u.target_size > e->next_offset)
		return -EINVAL;

	return 0;
}

static inline int check_match(struct ip6t_entry_match *m, const char *name,
			      const struct ip6t_ip6 *ipv6,
			      unsigned int hookmask, unsigned int *i)
{
	struct xt_match *match;
	int ret;

	match = m->u.kernel.match;
	ret = xt_check_match(match, AF_INET6, m->u.match_size - sizeof(*m),
			     name, hookmask, ipv6->proto,
			     ipv6->invflags & IP6T_INV_PROTO);
	if (!ret && m->u.kernel.match->checkentry
	    && !m->u.kernel.match->checkentry(name, ipv6, match, m->data,
					      hookmask)) {
		duprintf("ip_tables: check failed for `%s'.\n",
			 m->u.kernel.match->name);
		ret = -EINVAL;
	}
	if (!ret)
		(*i)++;
	return ret;
}

static inline int
find_check_match(struct ip6t_entry_match *m,
		 const char *name,
		 const struct ip6t_ip6 *ipv6,
		 unsigned int hookmask,
		 unsigned int *i)
{
	struct xt_match *match;
	int ret;

	match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name,
					m->u.user.revision),
					"ip6t_%s", m->u.user.name);
	if (IS_ERR(match) || !match) {
		duprintf("find_check_match: `%s' not found\n", m->u.user.name);
		return match ? PTR_ERR(match) : -ENOENT;
	}
	m->u.kernel.match = match;

	ret = check_match(m, name, ipv6, hookmask, i);
	if (ret)
		goto err;

	return 0;
err:
	module_put(m->u.kernel.match->me);
	return ret;
}

static inline int check_target(struct ip6t_entry *e, const char *name)
{
	struct ip6t_entry_target *t;
	struct xt_target *target;
	int ret;

	t = ip6t_get_target(e);
	target = t->u.kernel.target;
	ret = xt_check_target(target, AF_INET6, t->u.target_size - sizeof(*t),
			      name, e->comefrom, e->ipv6.proto,
			      e->ipv6.invflags & IP6T_INV_PROTO);
	if (!ret && t->u.kernel.target->checkentry
	    && !t->u.kernel.target->checkentry(name, e, target, t->data,
					       e->comefrom)) {
		duprintf("ip_tables: check failed for `%s'.\n",
			 t->u.kernel.target->name);
		ret = -EINVAL;
	}
	return ret;
}

static inline int
find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size,
		 unsigned int *i)
{
	struct ip6t_entry_target *t;
	struct xt_target *target;
	int ret;
	unsigned int j;

	ret = check_entry(e, name);
	if (ret)
		return ret;

	j = 0;
	ret = IP6T_MATCH_ITERATE(e, find_check_match, name, &e->ipv6,
				 e->comefrom, &j);
	if (ret != 0)
		goto cleanup_matches;

	t = ip6t_get_target(e);
	target = try_then_request_module(xt_find_target(AF_INET6,
							t->u.user.name,
							t->u.user.revision),
					 "ip6t_%s", t->u.user.name);
	if (IS_ERR(target) || !target) {
		duprintf("find_check_entry: `%s' not found\n", t->u.user.name);
		ret = target ? PTR_ERR(target) : -ENOENT;
		goto cleanup_matches;
	}
	t->u.kernel.target = target;

	ret = check_target(e, name);
	if (ret)
		goto err;

	(*i)++;
	return 0;
 err:
	module_put(t->u.kernel.target->me);
 cleanup_matches:
	IP6T_MATCH_ITERATE(e, cleanup_match, &j);
	return ret;
}

static inline int
check_entry_size_and_hooks(struct ip6t_entry *e,
			   struct xt_table_info *newinfo,
			   unsigned char *base,
			   unsigned char *limit,
			   const unsigned int *hook_entries,
			   const unsigned int *underflows,
			   unsigned int *i)
{
	unsigned int h;

	if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0
	    || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
		duprintf("Bad offset %p\n", e);
		return -EINVAL;
	}

	if (e->next_offset
	    < sizeof(struct ip6t_entry) + sizeof(struct ip6t_entry_target)) {
		duprintf("checking: element %p size %u\n",
			 e, e->next_offset);
		return -EINVAL;
	}

	/* Check hooks & underflows */
	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
		if ((unsigned char *)e - base == hook_entries[h])
			newinfo->hook_entry[h] = hook_entries[h];
		if ((unsigned char *)e - base == underflows[h])
			newinfo->underflow[h] = underflows[h];
	}

	/* FIXME: underflows must be unconditional, standard verdicts
	   < 0 (not IP6T_RETURN). --RR */

	/* Clear counters and comefrom */
	e->counters = ((struct xt_counters) { 0, 0 });
	e->comefrom = 0;

	(*i)++;
	return 0;
}

static inline int
cleanup_entry(struct ip6t_entry *e, unsigned int *i)
{
	struct ip6t_entry_target *t;

	if (i && (*i)-- == 0)
		return 1;

	/* Cleanup all matches */
	IP6T_MATCH_ITERATE(e, cleanup_match, NULL);
	t = ip6t_get_target(e);
	if (t->u.kernel.target->destroy)
		t->u.kernel.target->destroy(t->u.kernel.target, t->data);
	module_put(t->u.kernel.target->me);
	return 0;
}

/* Checks and translates the user-supplied table segment (held in
   newinfo) */
static int
translate_table(const char *name,
		unsigned int valid_hooks,
		struct xt_table_info *newinfo,
		void *entry0,
		unsigned int size,
		unsigned int number,
		const unsigned int *hook_entries,
		const unsigned int *underflows)
{
	unsigned int i;
	int ret;

	newinfo->size = size;
	newinfo->number = number;

	/* Init all hooks to impossible value. */
	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
		newinfo->hook_entry[i] = 0xFFFFFFFF;
		newinfo->underflow[i] = 0xFFFFFFFF;
	}

	duprintf("translate_table: size %u\n", newinfo->size);
	i = 0;
	/* Walk through entries, checking offsets. */
	ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size,
				check_entry_size_and_hooks,
				newinfo,
				entry0,
				entry0 + size,
				hook_entries, underflows, &i);
	if (ret != 0)
		return ret;

	if (i != number) {
		duprintf("translate_table: %u not %u entries\n",
			 i, number);
		return -EINVAL;
	}

	/* Check hooks all assigned */
	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
		/* Only hooks which are valid */
		if (!(valid_hooks & (1 << i)))
			continue;
		if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
			duprintf("Invalid hook entry %u %u\n",
				 i, hook_entries[i]);
			return -EINVAL;
		}
		if (newinfo->underflow[i] == 0xFFFFFFFF) {
			duprintf("Invalid underflow %u %u\n",
				 i, underflows[i]);
			return -EINVAL;
		}
	}

	if (!mark_source_chains(newinfo, valid_hooks, entry0))
		return -ELOOP;

	/* Finally, each sanity check must pass */
	i = 0;
	ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size,
				find_check_entry, name, size, &i);

	if (ret != 0) {
		IP6T_ENTRY_ITERATE(entry0, newinfo->size,
				   cleanup_entry, &i);
		return ret;
	}

	/* And one copy for every other CPU */
	for_each_possible_cpu(i) {
		if (newinfo->entries[i] && newinfo->entries[i] != entry0)
			memcpy(newinfo->entries[i], entry0, newinfo->size);
	}

	return 0;
}

/* Gets counters. */
static inline int
add_entry_to_counter(const struct ip6t_entry *e,
		     struct xt_counters total[],
		     unsigned int *i)
{
	ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);

	(*i)++;
	return 0;
}

static inline int
set_entry_to_counter(const struct ip6t_entry *e,
		     struct ip6t_counters total[],
		     unsigned int *i)
{
	SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);

	(*i)++;
	return 0;
}

static void
get_counters(const struct xt_table_info *t,
	     struct xt_counters counters[])
{
	unsigned int cpu;
	unsigned int i;
	unsigned int curcpu;

	/* Instead of clearing (by a previous call to memset())
	 * the counters and using adds, we set the counters
	 * with data used by 'current' CPU
	 * We dont care about preemption here.
	 */
	curcpu = raw_smp_processor_id();

	i = 0;
	IP6T_ENTRY_ITERATE(t->entries[curcpu],
			   t->size,
			   set_entry_to_counter,
			   counters,
			   &i);

	for_each_possible_cpu(cpu) {
		if (cpu == curcpu)
			continue;
		i = 0;
		IP6T_ENTRY_ITERATE(t->entries[cpu],
				  t->size,
				  add_entry_to_counter,
				  counters,
				  &i);
	}
}

static inline struct xt_counters *alloc_counters(struct xt_table *table)
{
	unsigned int countersize;
	struct xt_counters *counters;
	struct xt_table_info *private = table->private;

	/* We need atomic snapshot of counters: rest doesn't change
	   (other than comefrom, which userspace doesn't care
	   about). */
	countersize = sizeof(struct xt_counters) * private->number;
	counters = vmalloc_node(countersize, numa_node_id());

	if (counters == NULL)
		return ERR_PTR(-ENOMEM);

	/* First, sum counters... */
	write_lock_bh(&table->lock);
	get_counters(private, counters);
	write_unlock_bh(&table->lock);

	return counters;
}

static int
copy_entries_to_user(unsigned int total_size,
		     struct xt_table *table,
		     void __user *userptr)
{
	unsigned int off, num;
	struct ip6t_entry *e;
	struct xt_counters *counters;
	struct xt_table_info *private = table->private;
	int ret = 0;
	void *loc_cpu_entry;

	counters = alloc_counters(table);
	if (IS_ERR(counters))
		return PTR_ERR(counters);

	/* choose the copy that is on ourc node/cpu */
	loc_cpu_entry = private->entries[raw_smp_processor_id()];
	if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
		ret = -EFAULT;
		goto free_counters;
	}

	/* FIXME: use iterator macros --RR */
	/* ... then go back and fix counters and names */
	for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){
		unsigned int i;
		struct ip6t_entry_match *m;
		struct ip6t_entry_target *t;

		e = (struct ip6t_entry *)(loc_cpu_entry + off);
		if (copy_to_user(userptr + off
				 + offsetof(struct ip6t_entry, counters),
				 &counters[num],
				 sizeof(counters[num])) != 0) {
			ret = -EFAULT;
			goto free_counters;
		}

		for (i = sizeof(struct ip6t_entry);
		     i < e->target_offset;
		     i += m->u.match_size) {
			m = (void *)e + i;

			if (copy_to_user(userptr + off + i
					 + offsetof(struct ip6t_entry_match,
						    u.user.name),
					 m->u.kernel.match->name,
					 strlen(m->u.kernel.match->name)+1)
			    != 0) {
				ret = -EFAULT;
				goto free_counters;
			}
		}

		t = ip6t_get_target(e);
		if (copy_to_user(userptr + off + e->target_offset
				 + offsetof(struct ip6t_entry_target,
					    u.user.name),
				 t->u.kernel.target->name,
				 strlen(t->u.kernel.target->name)+1) != 0) {
			ret = -EFAULT;
			goto free_counters;
		}
	}

 free_counters:
	vfree(counters);
	return ret;
}

static int get_info(void __user *user, int *len)
{
	char name[IP6T_TABLE_MAXNAMELEN];
	struct xt_table *t;
	int ret;

	if (*len != sizeof(struct ip6t_getinfo)) {
		duprintf("length %u != %u\n", *len,
			 sizeof(struct ip6t_getinfo));
		return -EINVAL;
	}

	if (copy_from_user(name, user, sizeof(name)) != 0)
		return -EFAULT;

	name[IP6T_TABLE_MAXNAMELEN-1] = '\0';

	t = try_then_request_module(xt_find_table_lock(AF_INET6, name),
				    "ip6table_%s", name);
	if (t && !IS_ERR(t)) {
		struct ip6t_getinfo info;
		struct xt_table_info *private = t->private;

		info.valid_hooks = t->valid_hooks;
		memcpy(info.hook_entry, private->hook_entry,
		       sizeof(info.hook_entry));
		memcpy(info.underflow, private->underflow,
		       sizeof(info.underflow));
		info.num_entries = private->number;
		info.size = private->size;
		memcpy(info.name, name, sizeof(info.name));

		if (copy_to_user(user, &info, *len) != 0)
			ret = -EFAULT;
		else
			ret = 0;

		xt_table_unlock(t);
		module_put(t->me);
	} else
		ret = t ? PTR_ERR(t) : -ENOENT;
	return ret;
}

static int
get_entries(struct ip6t_get_entries __user *uptr, int *len)
{
	int ret;
	struct ip6t_get_entries get;
	struct xt_table *t;

	if (*len < sizeof(get)) {
		duprintf("get_entries: %u < %u\n", *len, sizeof(get));
		return -EINVAL;
	}
	if (copy_from_user(&get, uptr, sizeof(get)) != 0)
		return -EFAULT;
	if (*len != sizeof(struct ip6t_get_entries) + get.size) {
		duprintf("get_entries: %u != %u\n", *len,
			 sizeof(struct ip6t_get_entries) + get.size);
		return -EINVAL;
	}

	t = xt_find_table_lock(AF_INET6, get.name);
	if (t && !IS_ERR(t)) {
		struct xt_table_info *private = t->private;
		duprintf("t->private->number = %u\n", private->number);
		if (get.size == private->size)
			ret = copy_entries_to_user(private->size,
						   t, uptr->entrytable);
		else {
			duprintf("get_entries: I've got %u not %u!\n",
				 private->size, entries->size);
			ret = -EINVAL;
		}
		module_put(t->me);
		xt_table_unlock(t);
	} else
		ret = t ? PTR_ERR(t) : -ENOENT;

	return ret;
}

static int
do_replace(void __user *user, unsigned int len)
{
	int ret;
	struct ip6t_replace tmp;
	struct xt_table *t;
	struct xt_table_info *newinfo, *oldinfo;
	struct xt_counters *counters;
	void *loc_cpu_entry, *loc_cpu_old_entry;

	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
		return -EFAULT;

	/* overflow check */
	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
		return -ENOMEM;

	newinfo = xt_alloc_table_info(tmp.size);
	if (!newinfo)
		return -ENOMEM;

	/* choose the copy that is on our node/cpu */
	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
			   tmp.size) != 0) {
		ret = -EFAULT;
		goto free_newinfo;
	}

	counters = vmalloc_node(tmp.num_counters * sizeof(struct xt_counters),
				numa_node_id());
	if (!counters) {
		ret = -ENOMEM;
		goto free_newinfo;
	}

	ret = translate_table(tmp.name, tmp.valid_hooks,
			      newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
			      tmp.hook_entry, tmp.underflow);
	if (ret != 0)
		goto free_newinfo_counters;

	duprintf("ip_tables: Translated table\n");

	t = try_then_request_module(xt_find_table_lock(AF_INET6, tmp.name),
				    "ip6table_%s", tmp.name);
	if (!t || IS_ERR(t)) {
		ret = t ? PTR_ERR(t) : -ENOENT;
		goto free_newinfo_counters_untrans;
	}

	/* You lied! */
	if (tmp.valid_hooks != t->valid_hooks) {
		duprintf("Valid hook crap: %08X vs %08X\n",
			 tmp.valid_hooks, t->valid_hooks);
		ret = -EINVAL;
		goto put_module;
	}

	oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret);
	if (!oldinfo)
		goto put_module;

	/* Update module usage count based on number of rules */
	duprintf("do_replace: oldnum=%u, initnum=%u, newnum=%u\n",
		oldinfo->number, oldinfo->initial_entries, newinfo->number);
	if ((oldinfo->number > oldinfo->initial_entries) ||
	    (newinfo->number <= oldinfo->initial_entries))
		module_put(t->me);
	if ((oldinfo->number > oldinfo->initial_entries) &&
	    (newinfo->number <= oldinfo->initial_entries))
		module_put(t->me);

	/* Get the old counters. */
	get_counters(oldinfo, counters);
	/* Decrease module usage counts and free resource */
	loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
	IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL);
	xt_free_table_info(oldinfo);
	if (copy_to_user(tmp.counters, counters,
			 sizeof(struct xt_counters) * tmp.num_counters) != 0)
		ret = -EFAULT;
	vfree(counters);
	xt_table_unlock(t);
	return ret;

 put_module:
	module_put(t->me);
	xt_table_unlock(t);
 free_newinfo_counters_untrans:
	IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL);
 free_newinfo_counters:
	vfree(counters);
 free_newinfo:
	xt_free_table_info(newinfo);
	return ret;
}

/* We're lazy, and add to the first CPU; overflow works its fey magic
 * and everything is OK. */
static inline int
add_counter_to_entry(struct ip6t_entry *e,
		     const struct xt_counters addme[],
		     unsigned int *i)
{
#if 0
	duprintf("add_counter: Entry %u %lu/%lu + %lu/%lu\n",
		 *i,
		 (long unsigned int)e->counters.pcnt,
		 (long unsigned int)e->counters.bcnt,
		 (long unsigned int)addme[*i].pcnt,
		 (long unsigned int)addme[*i].bcnt);
#endif

	ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);

	(*i)++;
	return 0;
}

static int
do_add_counters(void __user *user, unsigned int len)
{
	unsigned int i;
	struct xt_counters_info tmp, *paddc;
	struct xt_table_info *private;
	struct xt_table *t;
	int ret = 0;
	void *loc_cpu_entry;

	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
		return -EFAULT;

	if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters))
		return -EINVAL;

	paddc = vmalloc_node(len, numa_node_id());
	if (!paddc)
		return -ENOMEM;

	if (copy_from_user(paddc, user, len) != 0) {
		ret = -EFAULT;
		goto free;
	}

	t = xt_find_table_lock(AF_INET6, tmp.name);
	if (!t || IS_ERR(t)) {
		ret = t ? PTR_ERR(t) : -ENOENT;
		goto free;
	}

	write_lock_bh(&t->lock);
	private = t->private;
	if (private->number != tmp.num_counters) {
		ret = -EINVAL;
		goto unlock_up_free;
	}

	i = 0;
	/* Choose the copy that is on our node */
	loc_cpu_entry = private->entries[smp_processor_id()];
	IP6T_ENTRY_ITERATE(loc_cpu_entry,
			  private->size,
			  add_counter_to_entry,
			  paddc->counters,
			  &i);
 unlock_up_free:
	write_unlock_bh(&t->lock);
	xt_table_unlock(t);
	module_put(t->me);
 free:
	vfree(paddc);

	return ret;
}

static int
do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
{
	int ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	switch (cmd) {
	case IP6T_SO_SET_REPLACE:
		ret = do_replace(user, len);
		break;

	case IP6T_SO_SET_ADD_COUNTERS:
		ret = do_add_counters(user, len);
		break;

	default:
		duprintf("do_ip6t_set_ctl:  unknown request %i\n", cmd);
		ret = -EINVAL;
	}

	return ret;
}

static int
do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
	int ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	switch (cmd) {
	case IP6T_SO_GET_INFO:
		ret = get_info(user, len);
		break;

	case IP6T_SO_GET_ENTRIES:
		ret = get_entries(user, len);
		break;

	case IP6T_SO_GET_REVISION_MATCH:
	case IP6T_SO_GET_REVISION_TARGET: {
		struct ip6t_get_revision rev;
		int target;

		if (*len != sizeof(rev)) {
			ret = -EINVAL;
			break;
		}
		if (copy_from_user(&rev, user, sizeof(rev)) != 0) {
			ret = -EFAULT;
			break;
		}

		if (cmd == IP6T_SO_GET_REVISION_TARGET)
			target = 1;
		else
			target = 0;

		try_then_request_module(xt_find_revision(AF_INET6, rev.name,
							 rev.revision,
							 target, &ret),
					"ip6t_%s", rev.name);
		break;
	}

	default:
		duprintf("do_ip6t_get_ctl: unknown request %i\n", cmd);
		ret = -EINVAL;
	}

	return ret;
}

int ip6t_register_table(struct xt_table *table,
			const struct ip6t_replace *repl)
{
	int ret;
	struct xt_table_info *newinfo;
	struct xt_table_info bootstrap
		= { 0, 0, 0, { 0 }, { 0 }, { } };
	void *loc_cpu_entry;

	newinfo = xt_alloc_table_info(repl->size);
	if (!newinfo)
		return -ENOMEM;

	/* choose the copy on our node/cpu */
	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
	memcpy(loc_cpu_entry, repl->entries, repl->size);

	ret = translate_table(table->name, table->valid_hooks,
			      newinfo, loc_cpu_entry, repl->size,
			      repl->num_entries,
			      repl->hook_entry,
			      repl->underflow);
	if (ret != 0) {
		xt_free_table_info(newinfo);
		return ret;
	}

	ret = xt_register_table(table, &bootstrap, newinfo);
	if (ret != 0) {
		xt_free_table_info(newinfo);
		return ret;
	}

	return 0;
}

void ip6t_unregister_table(struct xt_table *table)
{
	struct xt_table_info *private;
	void *loc_cpu_entry;

	private = xt_unregister_table(table);

	/* Decrease module usage counts and free resources */
	loc_cpu_entry = private->entries[raw_smp_processor_id()];
	IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL);
	xt_free_table_info(private);
}

/* Returns 1 if the type and code is matched by the range, 0 otherwise */
static inline bool
icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,
		     u_int8_t type, u_int8_t code,
		     bool invert)
{
	return (type == test_type && code >= min_code && code <= max_code)
		^ invert;
}

static bool
icmp6_match(const struct sk_buff *skb,
	   const struct net_device *in,
	   const struct net_device *out,
	   const struct xt_match *match,
	   const void *matchinfo,
	   int offset,
	   unsigned int protoff,
	   bool *hotdrop)
{
	struct icmp6hdr _icmp, *ic;
	const struct ip6t_icmp *icmpinfo = matchinfo;

	/* Must not be a fragment. */
	if (offset)
		return false;

	ic = skb_header_pointer(skb, protoff, sizeof(_icmp), &_icmp);
	if (ic == NULL) {
		/* We've been asked to examine this packet, and we
		   can't.  Hence, no choice but to drop. */
		duprintf("Dropping evil ICMP tinygram.\n");
		*hotdrop = true;
		return false;
	}

	return icmp6_type_code_match(icmpinfo->type,
				     icmpinfo->code[0],
				     icmpinfo->code[1],
				     ic->icmp6_type, ic->icmp6_code,
				     !!(icmpinfo->invflags&IP6T_ICMP_INV));
}

/* Called when user tries to insert an entry of this type. */
static bool
icmp6_checkentry(const char *tablename,
	   const void *entry,
	   const struct xt_match *match,
	   void *matchinfo,
	   unsigned int hook_mask)
{
	const struct ip6t_icmp *icmpinfo = matchinfo;

	/* Must specify no unknown invflags */
	return !(icmpinfo->invflags & ~IP6T_ICMP_INV);
}

/* The built-in targets: standard (NULL) and error. */
static struct xt_target ip6t_standard_target __read_mostly = {
	.name		= IP6T_STANDARD_TARGET,
	.targetsize	= sizeof(int),
	.family		= AF_INET6,
};

static struct xt_target ip6t_error_target __read_mostly = {
	.name		= IP6T_ERROR_TARGET,
	.target		= ip6t_error,
	.targetsize	= IP6T_FUNCTION_MAXNAMELEN,
	.family		= AF_INET6,
};

static struct nf_sockopt_ops ip6t_sockopts = {
	.pf		= PF_INET6,
	.set_optmin	= IP6T_BASE_CTL,
	.set_optmax	= IP6T_SO_SET_MAX+1,
	.set		= do_ip6t_set_ctl,
	.get_optmin	= IP6T_BASE_CTL,
	.get_optmax	= IP6T_SO_GET_MAX+1,
	.get		= do_ip6t_get_ctl,
	.owner		= THIS_MODULE,
};

static struct xt_match icmp6_matchstruct __read_mostly = {
	.name		= "icmp6",
	.match		= &icmp6_match,
	.matchsize	= sizeof(struct ip6t_icmp),
	.checkentry	= icmp6_checkentry,
	.proto		= IPPROTO_ICMPV6,
	.family		= AF_INET6,
};

static int __init ip6_tables_init(void)
{
	int ret;

	ret = xt_proto_init(AF_INET6);
	if (ret < 0)
		goto err1;

	/* Noone else will be downing sem now, so we won't sleep */
	ret = xt_register_target(&ip6t_standard_target);
	if (ret < 0)
		goto err2;
	ret = xt_register_target(&ip6t_error_target);
	if (ret < 0)
		goto err3;
	ret = xt_register_match(&icmp6_matchstruct);
	if (ret < 0)
		goto err4;

	/* Register setsockopt */
	ret = nf_register_sockopt(&ip6t_sockopts);
	if (ret < 0)
		goto err5;

	printk(KERN_INFO "ip6_tables: (C) 2000-2006 Netfilter Core Team\n");
	return 0;

err5:
	xt_unregister_match(&icmp6_matchstruct);
err4:
	xt_unregister_target(&ip6t_error_target);
err3:
	xt_unregister_target(&ip6t_standard_target);
err2:
	xt_proto_fini(AF_INET6);
err1:
	return ret;
}

static void __exit ip6_tables_fini(void)
{
	nf_unregister_sockopt(&ip6t_sockopts);
	xt_unregister_match(&icmp6_matchstruct);
	xt_unregister_target(&ip6t_error_target);
	xt_unregister_target(&ip6t_standard_target);
	xt_proto_fini(AF_INET6);
}

/*
 * find the offset to specified header or the protocol number of last header
 * if target < 0. "last header" is transport protocol header, ESP, or
 * "No next header".
 *
 * If target header is found, its offset is set in *offset and return protocol
 * number. Otherwise, return -1.
 *
 * If the first fragment doesn't contain the final protocol header or
 * NEXTHDR_NONE it is considered invalid.
 *
 * Note that non-1st fragment is special case that "the protocol number
 * of last header" is "next header" field in Fragment header. In this case,
 * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
 * isn't NULL.
 *
 */
int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
		  int target, unsigned short *fragoff)
{
	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
	unsigned int len = skb->len - start;

	if (fragoff)
		*fragoff = 0;

	while (nexthdr != target) {
		struct ipv6_opt_hdr _hdr, *hp;
		unsigned int hdrlen;

		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
			if (target < 0)
				break;
			return -ENOENT;
		}

		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
		if (hp == NULL)
			return -EBADMSG;
		if (nexthdr == NEXTHDR_FRAGMENT) {
			unsigned short _frag_off;
			__be16 *fp;
			fp = skb_header_pointer(skb,
						start+offsetof(struct frag_hdr,
							       frag_off),
						sizeof(_frag_off),
						&_frag_off);
			if (fp == NULL)
				return -EBADMSG;

			_frag_off = ntohs(*fp) & ~0x7;
			if (_frag_off) {
				if (target < 0 &&
				    ((!ipv6_ext_hdr(hp->nexthdr)) ||
				     hp->nexthdr == NEXTHDR_NONE)) {
					if (fragoff)
						*fragoff = _frag_off;
					return hp->nexthdr;
				}
				return -ENOENT;
			}
			hdrlen = 8;
		} else if (nexthdr == NEXTHDR_AUTH)
			hdrlen = (hp->hdrlen + 2) << 2;
		else
			hdrlen = ipv6_optlen(hp);

		nexthdr = hp->nexthdr;
		len -= hdrlen;
		start += hdrlen;
	}

	*offset = start;
	return nexthdr;
}

EXPORT_SYMBOL(ip6t_register_table);
EXPORT_SYMBOL(ip6t_unregister_table);
EXPORT_SYMBOL(ip6t_do_table);
EXPORT_SYMBOL(ip6t_ext_hdr);
EXPORT_SYMBOL(ipv6_find_hdr);

module_init(ip6_tables_init);
module_exit(ip6_tables_fini);