ip6_tables.c

linux-2.6.15.6

/*
 * Packet matching code.
 *
 * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
 * Copyright (C) 2000-2005 Netfilter Core Team <[e-mail]>
 *
 * 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.
 *
 * 19 Jan 2002 Harald Welte <[e-mail]>
 * 	- increase module usage count as soon as we have rules inside
 * 	  a table
 * 06 Jun 2002 Andras Kis-Szabo <[e-mail]>
 *      - new extension header parser code
 */
#include <linux/config.h>
#include <linux/skbuff.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
#include <linux/netdevice.h>
#include <linux/module.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmpv6.h>
#include <net/ipv6.h>
#include <asm/uaccess.h>
#include <asm/semaphore.h>
#include <linux/proc_fs.h>
#include <linux/cpumask.h>

#include <linux/netfilter_ipv6/ip6_tables.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <[e-mail]>");
MODULE_DESCRIPTION("IPv6 packet filter");

#define IPV6_HDR_LEN	(sizeof(struct ipv6hdr))
#define IPV6_OPTHDR_LEN	(sizeof(struct ipv6_opt_hdr))

/*#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
#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))

static DECLARE_MUTEX(ip6t_mutex);

/* Must have mutex */
#define ASSERT_READ_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0)
#define ASSERT_WRITE_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0)
#include <linux/netfilter_ipv4/listhelp.h>

#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.

   To be cache friendly on SMP, we arrange them like so:
   [ n-entries ]
   ... cache-align padding ...
   [ n-entries ]

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

/* The table itself */
struct ip6t_table_info
{
	/* Size per table */
	unsigned int size;
	/* Number of entries: FIXME. --RR */
	unsigned int number;
	/* Initial number of entries. Needed for module usage count */
	unsigned int initial_entries;

	/* Entry points and underflows */
	unsigned int hook_entry[NF_IP6_NUMHOOKS];
	unsigned int underflow[NF_IP6_NUMHOOKS];

	/* ip6t_entry tables: one per CPU */
	char entries[0] ____cacheline_aligned;
};

static LIST_HEAD(ip6t_target);
static LIST_HEAD(ip6t_match);
static LIST_HEAD(ip6t_tables);
#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0)

#ifdef CONFIG_SMP
#define TABLE_OFFSET(t,p) (SMP_ALIGN((t)->size)*(p))
#else
#define TABLE_OFFSET(t,p) 0
#endif

#if 0
#define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0)
#define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; })
#define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0)
#endif

static int ip6_masked_addrcmp(struct in6_addr addr1, struct in6_addr mask,
			      struct in6_addr addr2)
{
	int i;
	for( i = 0; i < 16; i++){
		if((addr1.s6_addr[i] & mask.s6_addr[i]) != 
		   (addr2.s6_addr[i] & mask.s6_addr[i]))
			return 1;
	}
	return 0;
}

/* 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 int
ip6_packet_match(const struct sk_buff *skb,
		 const char *indev,
		 const char *outdev,
		 const struct ip6t_ip6 *ip6info,
		 unsigned int *protoff,
		 int *fragoff)
{
	size_t i;
	unsigned long ret;
	const struct ipv6hdr *ipv6 = skb->nh.ipv6h;

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

	if (FWINV(ip6_masked_addrcmp(ipv6->saddr,ip6info->smsk,ip6info->src),
		  IP6T_INV_SRCIP)
	    || FWINV(ip6_masked_addrcmp(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 0;
	}

	/* 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 0;
	}

	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 0;
	}

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

	/* look for the desired protocol header */
	if((ip6info->flags & IP6T_F_PROTO)) {
		u_int8_t currenthdr = ipv6->nexthdr;
		struct ipv6_opt_hdr _hdr, *hp;
		u_int16_t ptr;		/* Header offset in skb */
		u_int16_t hdrlen;	/* Header */
		u_int16_t _fragoff = 0, *fp = NULL;

		ptr = IPV6_HDR_LEN;

		while (ip6t_ext_hdr(currenthdr)) {
	                /* Is there enough space for the next ext header? */
	                if (skb->len - ptr < IPV6_OPTHDR_LEN)
	                        return 0;

			/* NONE or ESP: there isn't protocol part */
			/* If we want to count these packets in '-p all',
			 * we will change the return 0 to 1*/
			if ((currenthdr == IPPROTO_NONE) || 
				(currenthdr == IPPROTO_ESP))
				break;

			hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
			BUG_ON(hp == NULL);

			/* Size calculation */
	                if (currenthdr == IPPROTO_FRAGMENT) {
				fp = skb_header_pointer(skb,
						   ptr+offsetof(struct frag_hdr,
								frag_off),
						   sizeof(_fragoff),
						   &_fragoff);
				if (fp == NULL)
					return 0;

				_fragoff = ntohs(*fp) & ~0x7;
	                        hdrlen = 8;
	                } else if (currenthdr == IPPROTO_AH)
	                        hdrlen = (hp->hdrlen+2)<<2;
	                else
	                        hdrlen = ipv6_optlen(hp);

			currenthdr = hp->nexthdr;
	                ptr += hdrlen;
			/* ptr is too large */
	                if ( ptr > skb->len ) 
				return 0;
			if (_fragoff) {
				if (ip6t_ext_hdr(currenthdr))
					return 0;
				break;
			}
		}

		*protoff = ptr;
		*fragoff = _fragoff;

		/* currenthdr contains the protocol header */

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

		if (ip6info->proto == currenthdr) {
			if(ip6info->invflags & IP6T_INV_PROTO) {
				return 0;
			}
			return 1;
		}

		/* We need match for the '-p all', too! */
		if ((ip6info->proto != 0) &&
			!(ip6info->invflags & IP6T_INV_PROTO))
			return 0;
	}
	return 1;
}

/* should be ip6 safe */
static inline int 
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 0;
	}
	if (ipv6->invflags & ~IP6T_INV_MASK) {
		duprintf("Unknown invflag bits set: %08X\n",
			 ipv6->invflags & ~IP6T_INV_MASK);
		return 0;
	}
	return 1;
}

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

	return NF_DROP;
}

static inline
int 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,
	     int *hotdrop)
{
	/* Stop iteration if it doesn't match */
	if (!m->u.kernel.match->match(skb, in, out, m->data,
				      offset, protoff, hotdrop))
		return 1;
	else
		return 0;
}

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

/* Returns one of the generic firewall policies, like NF_ACCEPT. */
unsigned int
ip6t_do_table(struct sk_buff **pskb,
	      unsigned int hook,
	      const struct net_device *in,
	      const struct net_device *out,
	      struct ip6t_table *table,
	      void *userdata)
{
	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
	int offset = 0;
	unsigned int protoff = 0;
	int hotdrop = 0;
	/* 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;

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

#ifdef CONFIG_NETFILTER_DEBUG
	/* Check noone else using our table */
	if (((struct ip6t_entry *)table_base)->comefrom != 0xdead57ac
	    && ((struct ip6t_entry *)table_base)->comefrom != 0xeeeeeeec) {
		printk("ASSERT: CPU #%u, %s comefrom(%p) = %X\n",
		       smp_processor_id(),
		       table->name,
		       &((struct ip6t_entry *)table_base)->comefrom,
		       ((struct ip6t_entry *)table_base)->comefrom);
	}
	((struct ip6t_entry *)table_base)->comefrom = 0x57acc001;
#endif

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

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

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

			ADD_COUNTER(e->counters,
				    ntohs((*pskb)->nh.ipv6h->payload_len)
				    + IPV6_HDR_LEN,
				    1);

			t = ip6t_get_target(e);
			IP_NF_ASSERT(t->u.kernel.target);
			/* 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(pskb,
								     in, out,
								     hook,
								     t->data,
								     userdata);

#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 = 0xdead57ac;
#endif
	read_unlock_bh(&table->lock);

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

/*
 * These are weird, but module loading must not be done with mutex
 * held (since they will register), and we have to have a single
 * function to use try_then_request_module().
 */

/* Find table by name, grabs mutex & ref.  Returns ERR_PTR() on error. */
static inline struct ip6t_table *find_table_lock(const char *name)
{
	struct ip6t_table *t;

	if (down_interruptible(&ip6t_mutex) != 0)
		return ERR_PTR(-EINTR);

	list_for_each_entry(t, &ip6t_tables, list)
		if (strcmp(t->name, name) == 0 && try_module_get(t->me))
			return t;
	up(&ip6t_mutex);
	return NULL;
}

/* Find match, grabs ref.  Returns ERR_PTR() on error. */
static inline struct ip6t_match *find_match(const char *name, u8 revision)
{
	struct ip6t_match *m;
	int err = 0;

	if (down_interruptible(&ip6t_mutex) != 0)
		return ERR_PTR(-EINTR);