ip_nat_core.c

linux-2.6.15.6

/* NAT for netfilter; shared with compatibility layer. */

/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2004 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.
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/netfilter_ipv4.h>
#include <linux/vmalloc.h>
#include <net/checksum.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/tcp.h>  /* For tcp_prot in getorigdst */
#include <linux/icmp.h>
#include <linux/udp.h>
#include <linux/jhash.h>

#define ASSERT_READ_LOCK(x)
#define ASSERT_WRITE_LOCK(x)

#include <linux/netfilter_ipv4/ip_conntrack.h>
#include <linux/netfilter_ipv4/ip_conntrack_core.h>
#include <linux/netfilter_ipv4/ip_conntrack_protocol.h>
#include <linux/netfilter_ipv4/ip_nat.h>
#include <linux/netfilter_ipv4/ip_nat_protocol.h>
#include <linux/netfilter_ipv4/ip_nat_core.h>
#include <linux/netfilter_ipv4/ip_nat_helper.h>
#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
#include <linux/netfilter_ipv4/listhelp.h>

#if 0
#define DEBUGP printk
#else
#define DEBUGP(format, args...)
#endif

DEFINE_RWLOCK(ip_nat_lock);

/* Calculated at init based on memory size */
static unsigned int ip_nat_htable_size;

static struct list_head *bysource;

#define MAX_IP_NAT_PROTO 256
static struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO];

static inline struct ip_nat_protocol *
__ip_nat_proto_find(u_int8_t protonum)
{
	return ip_nat_protos[protonum];
}

struct ip_nat_protocol *
ip_nat_proto_find_get(u_int8_t protonum)
{
	struct ip_nat_protocol *p;

	/* we need to disable preemption to make sure 'p' doesn't get
	 * removed until we've grabbed the reference */
	preempt_disable();
	p = __ip_nat_proto_find(protonum);
	if (!try_module_get(p->me))
		p = &ip_nat_unknown_protocol;
	preempt_enable();

	return p;
}
EXPORT_SYMBOL_GPL(ip_nat_proto_find_get);

void
ip_nat_proto_put(struct ip_nat_protocol *p)
{
	module_put(p->me);
}
EXPORT_SYMBOL_GPL(ip_nat_proto_put);

/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
hash_by_src(const struct ip_conntrack_tuple *tuple)
{
	/* Original src, to ensure we map it consistently if poss. */
	return jhash_3words(tuple->src.ip, tuple->src.u.all,
			    tuple->dst.protonum, 0) % ip_nat_htable_size;
}

/* Noone using conntrack by the time this called. */
static void ip_nat_cleanup_conntrack(struct ip_conntrack *conn)
{
	if (!(conn->status & IPS_NAT_DONE_MASK))
		return;

	write_lock_bh(&ip_nat_lock);
	list_del(&conn->nat.info.bysource);
	write_unlock_bh(&ip_nat_lock);
}

/* We do checksum mangling, so if they were wrong before they're still
 * wrong.  Also works for incomplete packets (eg. ICMP dest
 * unreachables.) */
u_int16_t
ip_nat_cheat_check(u_int32_t oldvalinv, u_int32_t newval, u_int16_t oldcheck)
{
	u_int32_t diffs[] = { oldvalinv, newval };
	return csum_fold(csum_partial((char *)diffs, sizeof(diffs),
				      oldcheck^0xFFFF));
}
EXPORT_SYMBOL(ip_nat_cheat_check);

/* Is this tuple already taken? (not by us) */
int
ip_nat_used_tuple(const struct ip_conntrack_tuple *tuple,
		  const struct ip_conntrack *ignored_conntrack)
{
	/* Conntrack tracking doesn't keep track of outgoing tuples; only
	   incoming ones.  NAT means they don't have a fixed mapping,
	   so we invert the tuple and look for the incoming reply.

	   We could keep a separate hash if this proves too slow. */
	struct ip_conntrack_tuple reply;

	invert_tuplepr(&reply, tuple);
	return ip_conntrack_tuple_taken(&reply, ignored_conntrack);
}
EXPORT_SYMBOL(ip_nat_used_tuple);

/* If we source map this tuple so reply looks like reply_tuple, will
 * that meet the constraints of range. */
static int
in_range(const struct ip_conntrack_tuple *tuple,
	 const struct ip_nat_range *range)
{
	struct ip_nat_protocol *proto = 
				__ip_nat_proto_find(tuple->dst.protonum);

	/* If we are supposed to map IPs, then we must be in the
	   range specified, otherwise let this drag us onto a new src IP. */
	if (range->flags & IP_NAT_RANGE_MAP_IPS) {
		if (ntohl(tuple->src.ip) < ntohl(range->min_ip)
		    || ntohl(tuple->src.ip) > ntohl(range->max_ip))
			return 0;
	}

	if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)
	    || proto->in_range(tuple, IP_NAT_MANIP_SRC,
			       &range->min, &range->max))
		return 1;

	return 0;
}

static inline int
same_src(const struct ip_conntrack *ct,
	 const struct ip_conntrack_tuple *tuple)
{
	return (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum
		== tuple->dst.protonum
		&& ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip
		== tuple->src.ip
		&& ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all
		== tuple->src.u.all);
}

/* Only called for SRC manip */
static int
find_appropriate_src(const struct ip_conntrack_tuple *tuple,
		     struct ip_conntrack_tuple *result,
		     const struct ip_nat_range *range)
{
	unsigned int h = hash_by_src(tuple);
	struct ip_conntrack *ct;

	read_lock_bh(&ip_nat_lock);
	list_for_each_entry(ct, &bysource[h], nat.info.bysource) {
		if (same_src(ct, tuple)) {
			/* Copy source part from reply tuple. */
			invert_tuplepr(result,
				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
			result->dst = tuple->dst;

			if (in_range(result, range)) {
				read_unlock_bh(&ip_nat_lock);
				return 1;
			}
		}
	}
	read_unlock_bh(&ip_nat_lock);
	return 0;
}

/* For [FUTURE] fragmentation handling, we want the least-used
   src-ip/dst-ip/proto triple.  Fairness doesn't come into it.  Thus
   if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports
   1-65535, we don't do pro-rata allocation based on ports; we choose
   the ip with the lowest src-ip/dst-ip/proto usage.
*/
static void
find_best_ips_proto(struct ip_conntrack_tuple *tuple,
		    const struct ip_nat_range *range,
		    const struct ip_conntrack *conntrack,
		    enum ip_nat_manip_type maniptype)
{
	u_int32_t *var_ipp;
	/* Host order */
	u_int32_t minip, maxip, j;

	/* No IP mapping?  Do nothing. */
	if (!(range->flags & IP_NAT_RANGE_MAP_IPS))
		return;

	if (maniptype == IP_NAT_MANIP_SRC)
		var_ipp = &tuple->src.ip;
	else
		var_ipp = &tuple->dst.ip;

	/* Fast path: only one choice. */
	if (range->min_ip == range->max_ip) {
		*var_ipp = range->min_ip;
		return;
	}

	/* Hashing source and destination IPs gives a fairly even
	 * spread in practice (if there are a small number of IPs
	 * involved, there usually aren't that many connections
	 * anyway).  The consistency means that servers see the same
	 * client coming from the same IP (some Internet Banking sites
	 * like this), even across reboots. */
	minip = ntohl(range->min_ip);
	maxip = ntohl(range->max_ip);
	j = jhash_2words(tuple->src.ip, tuple->dst.ip, 0);
	*var_ipp = htonl(minip + j % (maxip - minip + 1));
}

/* Manipulate the tuple into the range given.  For NF_IP_POST_ROUTING,
 * we change the source to map into the range.  For NF_IP_PRE_ROUTING
 * and NF_IP_LOCAL_OUT, we change the destination to map into the
 * range.  It might not be possible to get a unique tuple, but we try.
 * At worst (or if we race), we will end up with a final duplicate in
 * __ip_conntrack_confirm and drop the packet. */
static void
get_unique_tuple(struct ip_conntrack_tuple *tuple,
		 const struct ip_conntrack_tuple *orig_tuple,
		 const struct ip_nat_range *range,
		 struct ip_conntrack *conntrack,
		 enum ip_nat_manip_type maniptype)
{
	struct ip_nat_protocol *proto;

	/* 1) If this srcip/proto/src-proto-part is currently mapped,
	   and that same mapping gives a unique tuple within the given
	   range, use that.

	   This is only required for source (ie. NAT/masq) mappings.
	   So far, we don't do local source mappings, so multiple
	   manips not an issue.  */
	if (maniptype == IP_NAT_MANIP_SRC) {
		if (find_appropriate_src(orig_tuple, tuple, range)) {
			DEBUGP("get_unique_tuple: Found current src map\n");
			if (!ip_nat_used_tuple(tuple, conntrack))
				return;
		}
	}

	/* 2) Select the least-used IP/proto combination in the given
	   range. */
	*tuple = *orig_tuple;
	find_best_ips_proto(tuple, range, conntrack, maniptype);

	/* 3) The per-protocol part of the manip is made to map into
	   the range to make a unique tuple. */

	proto = ip_nat_proto_find_get(orig_tuple->dst.protonum);

	/* Only bother mapping if it's not already in range and unique */
	if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)
	     || proto->in_range(tuple, maniptype, &range->min, &range->max))
	    && !ip_nat_used_tuple(tuple, conntrack)) {
		ip_nat_proto_put(proto);
		return;
	}

	/* Last change: get protocol to try to obtain unique tuple. */
	proto->unique_tuple(tuple, range, maniptype, conntrack);

	ip_nat_proto_put(proto);
}

unsigned int
ip_nat_setup_info(struct ip_conntrack *conntrack,
		  const struct ip_nat_range *range,
		  unsigned int hooknum)
{
	struct ip_conntrack_tuple curr_tuple, new_tuple;
	struct ip_nat_info *info = &conntrack->nat.info;
	int have_to_hash = !(conntrack->status & IPS_NAT_DONE_MASK);
	enum ip_nat_manip_type maniptype = HOOK2MANIP(hooknum);

	IP_NF_ASSERT(hooknum == NF_IP_PRE_ROUTING
		     || hooknum == NF_IP_POST_ROUTING
		     || hooknum == NF_IP_LOCAL_IN
		     || hooknum == NF_IP_LOCAL_OUT);
	BUG_ON(ip_nat_initialized(conntrack, maniptype));

	/* What we've got will look like inverse of reply. Normally
	   this is what is in the conntrack, except for prior
	   manipulations (future optimization: if num_manips == 0,
	   orig_tp =
	   conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */
	invert_tuplepr(&curr_tuple,
		       &conntrack->tuplehash[IP_CT_DIR_REPLY].tuple);

	get_unique_tuple(&new_tuple, &curr_tuple, range, conntrack, maniptype);

	if (!ip_ct_tuple_equal(&new_tuple, &curr_tuple)) {
		struct ip_conntrack_tuple reply;

		/* Alter conntrack table so will recognize replies. */