[NETFILTER]: Add ctnetlink subsystem

Add ctnetlink subsystem for userspace-access to ip_conntrack table.
This allows reading and updating of existing entries, as well as
creating new ones (and new expect's) via nfnetlink.

Please note the 'strange' byte order: nfattr (tag+length) are in host
byte order, while the payload is always guaranteed to be in network
byte order.  This allows a simple userspace process to encapsulate netlink
messages into arch-independent udp packets by just processing/swapping the
headers and not knowing anything about the actual payload.

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

16 files changed, 2067 insertions, 82 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index ff3393eba92..e47ba39eb65 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -702,5 +702,12 @@ config IP_NF_ARP_MANGLE
 	  Allows altering the ARP packet payload: source and destination
 	  hardware and network addresses.
 
+config IP_NF_CONNTRACK_NETLINK
+        tristate 'Connection tracking netlink interface'
+        depends on IP_NF_CONNTRACK && NETFILTER_NETLINK
+        help
+          This option enables support for a netlink-based userspace interface
+
+
 endmenu
 
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 45796d5924d..abf2a7d1a58 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -9,6 +9,10 @@ iptable_nat-objs	:= ip_nat_standalone.o ip_nat_rule.o ip_nat_core.o ip_nat_helpe
 # connection tracking
 obj-$(CONFIG_IP_NF_CONNTRACK) += ip_conntrack.o
 
+# conntrack netlink interface
+obj-$(CONFIG_IP_NF_CONNTRACK_NETLINK) += ip_conntrack_netlink.o
+
+
 # SCTP protocol connection tracking
 obj-$(CONFIG_IP_NF_CT_PROTO_SCTP) += ip_conntrack_proto_sctp.o
 
diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c
index caf89deae11..d9fddae8d78 100644
--- a/net/ipv4/netfilter/ip_conntrack_core.c
+++ b/net/ipv4/netfilter/ip_conntrack_core.c
@@ -50,7 +50,7 @@
 #include <linux/netfilter_ipv4/ip_conntrack_core.h>
 #include <linux/netfilter_ipv4/listhelp.h>
 
-#define IP_CONNTRACK_VERSION	"2.2"
+#define IP_CONNTRACK_VERSION	"2.3"
 
 #if 0
 #define DEBUGP printk
@@ -77,6 +77,8 @@ unsigned int ip_ct_log_invalid;
 static LIST_HEAD(unconfirmed);
 static int ip_conntrack_vmalloc;
 
+static unsigned int ip_conntrack_next_id = 1;
+static unsigned int ip_conntrack_expect_next_id = 1;
 #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
 struct notifier_block *ip_conntrack_chain;
 struct notifier_block *ip_conntrack_expect_chain;
@@ -154,13 +156,6 @@ void ip_conntrack_event_cache_init(const struct sk_buff *skb)
 
 DEFINE_PER_CPU(struct ip_conntrack_stat, ip_conntrack_stat);
 
-void 
-ip_conntrack_put(struct ip_conntrack *ct)
-{
-	IP_NF_ASSERT(ct);
-	nf_conntrack_put(&ct->ct_general);
-}
-
 static int ip_conntrack_hash_rnd_initted;
 static unsigned int ip_conntrack_hash_rnd;
 
@@ -222,6 +217,12 @@ static void unlink_expect(struct ip_conntrack_expect *exp)
 	exp->master->expecting--;
 }
 
+void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp)
+{
+	unlink_expect(exp);
+	ip_conntrack_expect_put(exp);
+}
+
 static void expectation_timed_out(unsigned long ul_expect)
 {
 	struct ip_conntrack_expect *exp = (void *)ul_expect;
@@ -232,6 +233,33 @@ static void expectation_timed_out(unsigned long ul_expect)
 	ip_conntrack_expect_put(exp);
 }
 
+struct ip_conntrack_expect *
+__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple)
+{
+	struct ip_conntrack_expect *i;
+	
+	list_for_each_entry(i, &ip_conntrack_expect_list, list) {
+		if (ip_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) {
+			atomic_inc(&i->use);
+			return i;
+		}
+	}
+	return NULL;
+}
+
+/* Just find a expectation corresponding to a tuple. */
+struct ip_conntrack_expect *
+ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple)
+{
+	struct ip_conntrack_expect *i;
+	
+	read_lock_bh(&ip_conntrack_lock);
+	i = __ip_conntrack_expect_find(tuple);
+	read_unlock_bh(&ip_conntrack_lock);
+
+	return i;
+}
+
 /* If an expectation for this connection is found, it gets delete from
  * global list then returned. */
 static struct ip_conntrack_expect *
@@ -256,7 +284,7 @@ find_expectation(const struct ip_conntrack_tuple *tuple)
 }
 
 /* delete all expectations for this conntrack */
-static void remove_expectations(struct ip_conntrack *ct)
+void ip_ct_remove_expectations(struct ip_conntrack *ct)
 {
 	struct ip_conntrack_expect *i, *tmp;
 
@@ -286,7 +314,7 @@ clean_from_lists(struct ip_conntrack *ct)
 	LIST_DELETE(&ip_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]);
 
 	/* Destroy all pending expectations */
-	remove_expectations(ct);
+	ip_ct_remove_expectations(ct);
 }
 
 static void
@@ -304,7 +332,7 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	/* To make sure we don't get any weird locking issues here:
 	 * destroy_conntrack() MUST NOT be called with a write lock
 	 * to ip_conntrack_lock!!! -HW */
-	proto = ip_ct_find_proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum);
+	proto = __ip_conntrack_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum);
 	if (proto && proto->destroy)
 		proto->destroy(ct);
 
@@ -316,7 +344,7 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	 * except TFTP can create an expectation on the first packet,
 	 * before connection is in the list, so we need to clean here,
 	 * too. */
-	remove_expectations(ct);
+	ip_ct_remove_expectations(ct);
 
 	/* We overload first tuple to link into unconfirmed list. */
 	if (!is_confirmed(ct)) {
@@ -331,8 +359,7 @@ destroy_conntrack(struct nf_conntrack *nfct)
 		ip_conntrack_put(ct->master);
 
 	DEBUGP("destroy_conntrack: returning ct=%p to slab\n", ct);
-	kmem_cache_free(ip_conntrack_cachep, ct);
-	atomic_dec(&ip_conntrack_count);
+	ip_conntrack_free(ct);
 }
 
 static void death_by_timeout(unsigned long ul_conntrack)
@@ -359,7 +386,7 @@ conntrack_tuple_cmp(const struct ip_conntrack_tuple_hash *i,
 		&& ip_ct_tuple_equal(tuple, &i->tuple);
 }
 
-static struct ip_conntrack_tuple_hash *
+struct ip_conntrack_tuple_hash *
 __ip_conntrack_find(const struct ip_conntrack_tuple *tuple,
 		    const struct ip_conntrack *ignored_conntrack)
 {
@@ -394,6 +421,29 @@ ip_conntrack_find_get(const struct ip_conntrack_tuple *tuple,
 	return h;
 }
 
+static void __ip_conntrack_hash_insert(struct ip_conntrack *ct,
+					unsigned int hash,
+					unsigned int repl_hash) 
+{
+	ct->id = ++ip_conntrack_next_id;
+	list_prepend(&ip_conntrack_hash[hash],
+		     &ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
+	list_prepend(&ip_conntrack_hash[repl_hash],
+		     &ct->tuplehash[IP_CT_DIR_REPLY].list);
+}
+
+void ip_conntrack_hash_insert(struct ip_conntrack *ct)
+{
+	unsigned int hash, repl_hash;
+
+	hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+	repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+
+	write_lock_bh(&ip_conntrack_lock);
+	__ip_conntrack_hash_insert(ct, hash, repl_hash);
+	write_unlock_bh(&ip_conntrack_lock);
+}
+
 /* Confirm a connection given skb; places it in hash table */
 int
 __ip_conntrack_confirm(struct sk_buff **pskb)
@@ -440,10 +490,7 @@ __ip_conntrack_confirm(struct sk_buff **pskb)
 		/* Remove from unconfirmed list */
 		list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
 
-		list_prepend(&ip_conntrack_hash[hash],
-			     &ct->tuplehash[IP_CT_DIR_ORIGINAL]);
-		list_prepend(&ip_conntrack_hash[repl_hash],
-			     &ct->tuplehash[IP_CT_DIR_REPLY]);
+		__ip_conntrack_hash_insert(ct, hash, repl_hash);
 		/* Timer relative to confirmation time, not original
 		   setting time, otherwise we'd get timer wrap in
 		   weird delay cases. */
@@ -527,34 +574,84 @@ static inline int helper_cmp(const struct ip_conntrack_helper *i,
 	return ip_ct_tuple_mask_cmp(rtuple, &i->tuple, &i->mask);
 }
 
-static struct ip_conntrack_helper *ip_ct_find_helper(const struct ip_conntrack_tuple *tuple)
+static struct ip_conntrack_helper *
+__ip_conntrack_helper_find( const struct ip_conntrack_tuple *tuple)
 {
 	return LIST_FIND(&helpers, helper_cmp,
 			 struct ip_conntrack_helper *,
 			 tuple);
 }
 
-/* Allocate a new conntrack: we return -ENOMEM if classification
-   failed due to stress.  Otherwise it really is unclassifiable. */
-static struct ip_conntrack_tuple_hash *
-init_conntrack(const struct ip_conntrack_tuple *tuple,
-	       struct ip_conntrack_protocol *protocol,
-	       struct sk_buff *skb)
+struct ip_conntrack_helper *
+ip_conntrack_helper_find_get( const struct ip_conntrack_tuple *tuple)
+{
+	struct ip_conntrack_helper *helper;
+
+	/* need ip_conntrack_lock to assure that helper exists until
+	 * try_module_get() is called */
+	read_lock_bh(&ip_conntrack_lock);
+
+	helper = __ip_conntrack_helper_find(tuple);
+	if (helper) {
+		/* need to increase module usage count to assure helper will
+		 * not go away while the caller is e.g. busy putting a
+		 * conntrack in the hash that uses the helper */
+		if (!try_module_get(helper->me))
+			helper = NULL;
+	}
+
+	read_unlock_bh(&ip_conntrack_lock);
+
+	return helper;
+}
+
+void ip_conntrack_helper_put(struct ip_conntrack_helper *helper)
+{
+	module_put(helper->me);
+}
+
+struct ip_conntrack_protocol *
+__ip_conntrack_proto_find(u_int8_t protocol)
+{
+	return ip_ct_protos[protocol];
+}
+
+/* this is guaranteed to always return a valid protocol helper, since
+ * it falls back to generic_protocol */
+struct ip_conntrack_protocol *
+ip_conntrack_proto_find_get(u_int8_t protocol)
+{
+	struct ip_conntrack_protocol *p;
+
+	preempt_disable();
+	p = __ip_conntrack_proto_find(protocol);
+	if (p) {
+		if (!try_module_get(p->me))
+			p = &ip_conntrack_generic_protocol;
+	}
+	preempt_enable();
+	
+	return p;
+}
+
+void ip_conntrack_proto_put(struct ip_conntrack_protocol *p)
+{
+	module_put(p->me);
+}
+
+struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig,
+					struct ip_conntrack_tuple *repl)
 {
 	struct ip_conntrack *conntrack;
-	struct ip_conntrack_tuple repl_tuple;
-	size_t hash;
-	struct ip_conntrack_expect *exp;
 
 	if (!ip_conntrack_hash_rnd_initted) {
 		get_random_bytes(&ip_conntrack_hash_rnd, 4);
 		ip_conntrack_hash_rnd_initted = 1;
 	}
 
-	hash = hash_conntrack(tuple);
-
 	if (ip_conntrack_max
 	    && atomic_read(&ip_conntrack_count) >= ip_conntrack_max) {
+		unsigned int hash = hash_conntrack(orig);
 		/* Try dropping from this hash chain. */
 		if (!early_drop(&ip_conntrack_hash[hash])) {
 			if (net_ratelimit())
@@ -565,31 +662,58 @@ init_conntrack(const struct ip_conntrack_tuple *tuple,
 		}
 	}
 
-	if (!ip_ct_invert_tuple(&repl_tuple, tuple, protocol)) {
-		DEBUGP("Can't invert tuple.\n");
-		return NULL;
-	}
-
 	conntrack = kmem_cache_alloc(ip_conntrack_cachep, GFP_ATOMIC);
 	if (!conntrack) {
 		DEBUGP("Can't allocate conntrack.\n");
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 	}
 
 	memset(conntrack, 0, sizeof(*conntrack));
 	atomic_set(&conntrack->ct_general.use, 1);
 	conntrack->ct_general.destroy = destroy_conntrack;
-	conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *tuple;
-	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = repl_tuple;
-	if (!protocol->new(conntrack, skb)) {
-		kmem_cache_free(ip_conntrack_cachep, conntrack);
-		return NULL;
-	}
+	conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
 	/* Don't set timer yet: wait for confirmation */
 	init_timer(&conntrack->timeout);
 	conntrack->timeout.data = (unsigned long)conntrack;
 	conntrack->timeout.function = death_by_timeout;
 
+	atomic_inc(&ip_conntrack_count);
+
+	return conntrack;
+}
+
+void
+ip_conntrack_free(struct ip_conntrack *conntrack)
+{
+	atomic_dec(&ip_conntrack_count);
+	kmem_cache_free(ip_conntrack_cachep, conntrack);
+}
+
+/* Allocate a new conntrack: we return -ENOMEM if classification
+ * failed due to stress.   Otherwise it really is unclassifiable */
+static struct ip_conntrack_tuple_hash *
+init_conntrack(struct ip_conntrack_tuple *tuple,
+	       struct ip_conntrack_protocol *protocol,
+	       struct sk_buff *skb)
+{
+	struct ip_conntrack *conntrack;
+	struct ip_conntrack_tuple repl_tuple;
+	struct ip_conntrack_expect *exp;
+
+	if (!ip_ct_invert_tuple(&repl_tuple, tuple, protocol)) {
+		DEBUGP("Can't invert tuple.\n");
+		return NULL;
+	}
+
+	if (!(conntrack = ip_conntrack_alloc(tuple, &repl_tuple)))
+		return NULL;
+
+	if (!protocol->new(conntrack, skb)) {
+		ip_conntrack_free(conntrack);
+		return NULL;
+	}
+
 	write_lock_bh(&ip_conntrack_lock);
 	exp = find_expectation(tuple);
 
@@ -610,7 +734,7 @@ init_conntrack(const struct ip_conntrack_tuple *tuple,
 		nf_conntrack_get(&conntrack->master->ct_general);
 		CONNTRACK_STAT_INC(expect_new);
 	} else {
-		conntrack->helper = ip_ct_find_helper(&repl_tuple);
+		conntrack->helper = __ip_conntrack_helper_find(&repl_tuple);
 
 		CONNTRACK_STAT_INC(new);
 	}
@@ -618,7 +742,6 @@ init_conntrack(const struct ip_conntrack_tuple *tuple,
 	/* Overload tuple linked list to put us in unconfirmed list. */
 	list_add(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL].list, &unconfirmed);
 
-	atomic_inc(&ip_conntrack_count);
 	write_unlock_bh(&ip_conntrack_lock);
 
 	if (exp) {
@@ -729,7 +852,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum,
 	}
 #endif
 
-	proto = ip_ct_find_proto((*pskb)->nh.iph->protocol);
+	proto = __ip_conntrack_proto_find((*pskb)->nh.iph->protocol);
 
 	/* It may be an special packet, error, unclean...
 	 * inverse of the return code tells to the netfilter
@@ -777,7 +900,7 @@ int invert_tuplepr(struct ip_conntrack_tuple *inverse,
 		   const struct ip_conntrack_tuple *orig)
 {
 	return ip_ct_invert_tuple(inverse, orig, 
-				  ip_ct_find_proto(orig->dst.protonum));
+				  __ip_conntrack_proto_find(orig->dst.protonum));
 }
 
 /* Would two expected things clash? */
@@ -857,6 +980,8 @@ static void ip_conntrack_expect_insert(struct ip_conntrack_expect *exp)
 	exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ;
 	add_timer(&exp->timeout);
 
+	exp->id = ++ip_conntrack_expect_next_id;
+	atomic_inc(&exp->use);
 	CONNTRACK_STAT_INC(expect_create);
 }
 
@@ -936,7 +1061,7 @@ void ip_conntrack_alter_reply(struct ip_conntrack *conntrack,
 
 	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
 	if (!conntrack->master && conntrack->expecting == 0)
-		conntrack->helper = ip_ct_find_helper(newreply);
+		conntrack->helper = __ip_conntrack_helper_find(newreply);
 	write_unlock_bh(&ip_conntrack_lock);
 }
 
@@ -950,6 +1075,19 @@ int ip_conntrack_helper_register(struct ip_conntrack_helper *me)
 	return 0;
 }
 
+struct ip_conntrack_helper *
+__ip_conntrack_helper_find_byname(const char *name)
+{
+	struct ip_conntrack_helper *h;
+
+	list_for_each_entry(h, &helpers, list) {
+		if (!strcmp(h->name, name))
+			return h;
+	}
+
+	return NULL;
+}
+
 static inline int unhelp(struct ip_conntrack_tuple_hash *i,
 			 const struct ip_conntrack_helper *me)
 {
@@ -1025,6 +1163,39 @@ void ip_ct_refresh_acct(struct ip_conntrack *ct,
 	}
 }
 
+#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \
+    defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE)
+/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be
+ * in ip_conntrack_core, since we don't want the protocols to autoload
+ * or depend on ctnetlink */
+int ip_ct_port_tuple_to_nfattr(struct sk_buff *skb,
+			       const struct ip_conntrack_tuple *tuple)
+{
+	NFA_PUT(skb, CTA_PROTO_SRC_PORT, sizeof(u_int16_t),
+		&tuple->src.u.tcp.port);
+	NFA_PUT(skb, CTA_PROTO_DST_PORT, sizeof(u_int16_t),
+		&tuple->dst.u.tcp.port);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[],
+			       struct ip_conntrack_tuple *t)
+{
+	if (!tb[CTA_PROTO_SRC_PORT-1] || !tb[CTA_PROTO_DST_PORT-1])
+		return -EINVAL;
+
+	t->src.u.tcp.port =
+		*(u_int16_t *)NFA_DATA(tb[CTA_PROTO_SRC_PORT-1]);
+	t->dst.u.tcp.port =
+		*(u_int16_t *)NFA_DATA(tb[CTA_PROTO_DST_PORT-1]);
+
+	return 0;
+}
+#endif
+
 /* Returns new sk_buff, or NULL */
 struct sk_buff *
 ip_ct_gather_frags(struct sk_buff *skb, u_int32_t user)
@@ -1203,16 +1374,13 @@ static void free_conntrack_hash(void)
 				     * ip_conntrack_htable_size));
 }
 
-/* Mishearing the voices in his head, our hero wonders how he's
-   supposed to kill the mall. */
-void ip_conntrack_cleanup(void)
+void ip_conntrack_flush()
 {
-	ip_ct_attach = NULL;
 	/* This makes sure all current packets have passed through
            netfilter framework.  Roll on, two-stage module
            delete... */
 	synchronize_net();
- 
+
  i_see_dead_people:
 	ip_ct_iterate_cleanup(kill_all, NULL);
 	if (atomic_read(&ip_conntrack_count) != 0) {
@@ -1222,7 +1390,14 @@ void ip_conntrack_cleanup(void)
 	/* wait until all references to ip_conntrack_untracked are dropped */
 	while (atomic_read(&ip_conntrack_untracked.ct_general.use) > 1)
 		schedule();
+}
 
+/* Mishearing the voices in his head, our hero wonders how he's
+   supposed to kill the mall. */
+void ip_conntrack_cleanup(void)
+{
+	ip_ct_attach = NULL;
+	ip_conntrack_flush();
 	kmem_cache_destroy(ip_conntrack_cachep);
 	kmem_cache_destroy(ip_conntrack_expect_cachep);
 	free_conntrack_hash();
diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c
new file mode 100644
index 00000000000..f43ec18c916
--- /dev/null
+++ b/net/ipv4/netfilter/ip_conntrack_netlink.c
@@ -0,0 +1,1588 @@
+/* Connection tracking via netlink socket. Allows for user space
+ * protocol helpers and general trouble making from userspace.
+ *
+ * (C) 2001 by Jay Schulist <jschlst@samba.org>
+ * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2003 by Patrick Mchardy <kaber@trash.net>
+ * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net>
+ *
+ * I've reworked this stuff to use attributes instead of conntrack 
+ * structures. 5.44 am. I need more tea. --pablo 05/07/11.
+ *
+ * Initial connection tracking via netlink development funded and 
+ * generally made possible by Network Robots, Inc. (www.networkrobots.com)
+ *
+ * Further development of this code funded by Astaro AG (http://www.astaro.com)
+ *
+ * This software may be used and distributed according to the terms
+ * of the GNU General Public License, incorporated herein by reference.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/netlink.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <linux/netfilter_ipv4/ip_conntrack_core.h>
+#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
+#include <linux/netfilter_ipv4/ip_conntrack_protocol.h>
+#include <linux/netfilter_ipv4/ip_nat_protocol.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
+MODULE_LICENSE("GPL");
+
+static char __initdata version[] = "0.90";
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+
+static inline int
+ctnetlink_dump_tuples_proto(struct sk_buff *skb, 
+			    const struct ip_conntrack_tuple *tuple)
+{
+	struct ip_conntrack_protocol *proto;
+
+	NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum);
+
+	proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
+	if (proto && proto->tuple_to_nfattr)
+		return proto->tuple_to_nfattr(skb, tuple);
+
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_tuples(struct sk_buff *skb, 
+		      const struct ip_conntrack_tuple *tuple)
+{
+	struct nfattr *nest_parms;
+	
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_IP);
+	NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t), &tuple->src.ip);
+	NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t), &tuple->dst.ip);
+	NFA_NEST_END(skb, nest_parms);
+
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO);
+	ctnetlink_dump_tuples_proto(skb, tuple);
+	NFA_NEST_END(skb, nest_parms);
+
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_status(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	u_int32_t status = htonl((u_int32_t) ct->status);
+	NFA_PUT(skb, CTA_STATUS, sizeof(status), &status);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_timeout(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	long timeout_l = ct->timeout.expires - jiffies;
+	u_int32_t timeout;
+
+	if (timeout_l < 0)
+		timeout = 0;
+	else
+		timeout = htonl(timeout_l / HZ);
+	
+	NFA_PUT(skb, CTA_TIMEOUT, sizeof(timeout), &timeout);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	struct ip_conntrack_protocol *proto = ip_conntrack_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
+
+	struct nfattr *nest_proto;
+	int ret;
+	
+	if (!proto || !proto->to_nfattr)
+		return 0;
+	
+	nest_proto = NFA_NEST(skb, CTA_PROTOINFO);
+
+	ret = proto->to_nfattr(skb, nest_proto, ct);
+
+	ip_conntrack_proto_put(proto);
+
+	NFA_NEST_END(skb, nest_proto);
+
+	return ret;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	struct nfattr *nest_helper;
+
+	if (!ct->helper)
+		return 0;
+		
+	nest_helper = NFA_NEST(skb, CTA_HELP);
+	NFA_PUT(skb, CTA_HELP_NAME, CTA_HELP_MAXNAMESIZE, &ct->helper->name);
+
+	if (ct->helper->to_nfattr)
+		ct->helper->to_nfattr(skb, ct);
+
+	NFA_NEST_END(skb, nest_helper);
+
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+#ifdef CONFIG_IP_NF_CT_ACCT
+static inline int
+ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *ct,
+			enum ip_conntrack_dir dir)
+{
+	enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
+	struct nfattr *nest_count = NFA_NEST(skb, type);
+	u_int64_t tmp;
+
+	tmp = cpu_to_be64(ct->counters[dir].packets);
+	NFA_PUT(skb, CTA_COUNTERS_PACKETS, sizeof(u_int64_t), &tmp);
+
+	tmp = cpu_to_be64(ct->counters[dir].bytes);
+	NFA_PUT(skb, CTA_COUNTERS_BYTES, sizeof(u_int64_t), &tmp);
+
+	NFA_NEST_END(skb, nest_count);
+
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+#else
+#define ctnetlink_dump_counters(a, b, c) (0)
+#endif
+
+#ifdef CONFIG_IP_NF_CONNTRACK_MARK
+static inline int
+ctnetlink_dump_mark(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	u_int32_t mark = htonl(ct->mark);
+
+	NFA_PUT(skb, CTA_MARK, sizeof(u_int32_t), &mark);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+#else
+#define ctnetlink_dump_mark(a, b) (0)
+#endif
+
+static inline int
+ctnetlink_dump_id(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	u_int32_t id = htonl(ct->id);
+	NFA_PUT(skb, CTA_ID, sizeof(u_int32_t), &id);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_use(struct sk_buff *skb, const struct ip_conntrack *ct)
+{
+	unsigned int use = htonl(atomic_read(&ct->ct_general.use));
+	
+	NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use);
+	return 0;
+
+nfattr_failure:
+	return -1;
+}
+
+#define tuple(ct, dir) (&(ct)->tuplehash[dir].tuple)
+
+static int
+ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
+		    int event, int nowait, 
+		    const struct ip_conntrack *ct)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	struct nfattr *nest_parms;
+	unsigned char *b;
+
+	b = skb->tail;
+
+	event |= NFNL_SUBSYS_CTNETLINK << 8;
+	nlh    = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
+	nfmsg  = NLMSG_DATA(nlh);
+
+	nlh->nlmsg_flags    = (nowait && pid) ? NLM_F_MULTI : 0;
+	nfmsg->nfgen_family = AF_INET;
+	nfmsg->version      = NFNETLINK_V0;
+	nfmsg->res_id	    = 0;
+
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG);
+	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+		goto nfattr_failure;
+	NFA_NEST_END(skb, nest_parms);
+	
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY);
+	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+		goto nfattr_failure;
+	NFA_NEST_END(skb, nest_parms);
+
+	if (ctnetlink_dump_status(skb, ct) < 0 ||
+	    ctnetlink_dump_timeout(skb, ct) < 0 ||
+	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
+	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
+	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
+	    ctnetlink_dump_mark(skb, ct) < 0 ||
+	    ctnetlink_dump_id(skb, ct) < 0 ||
+	    ctnetlink_dump_use(skb, ct) < 0)
+		goto nfattr_failure;
+
+	nlh->nlmsg_len = skb->tail - b;
+	return skb->len;
+
+nlmsg_failure:
+nfattr_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
+static int ctnetlink_conntrack_event(struct notifier_block *this,
+                                     unsigned long events, void *ptr)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	struct nfattr *nest_parms;
+	struct ip_conntrack *ct = (struct ip_conntrack *)ptr;
+	struct sk_buff *skb;
+	unsigned int type;
+	unsigned char *b;
+	unsigned int flags = 0, groups;
+
+	/* ignore our fake conntrack entry */
+	if (ct == &ip_conntrack_untracked)
+		return NOTIFY_DONE;
+
+	if (events & IPCT_DESTROY) {
+		type = IPCTNL_MSG_CT_DELETE;
+		groups = NF_NETLINK_CONNTRACK_DESTROY;
+		goto alloc_skb;
+	}
+	if (events & (IPCT_NEW | IPCT_RELATED)) {
+		type = IPCTNL_MSG_CT_NEW;
+		flags = NLM_F_CREATE|NLM_F_EXCL;
+		/* dump everything */
+		events = ~0UL;
+		groups = NF_NETLINK_CONNTRACK_NEW;
+		goto alloc_skb;
+	}
+	if (events & (IPCT_STATUS |
+		      IPCT_PROTOINFO |
+		      IPCT_HELPER |
+		      IPCT_HELPINFO |
+		      IPCT_NATINFO)) {
+		type = IPCTNL_MSG_CT_NEW;
+		groups = NF_NETLINK_CONNTRACK_UPDATE;
+		goto alloc_skb;
+	} 
+	
+	return NOTIFY_DONE;
+
+alloc_skb:
+  /* FIXME: Check if there are any listeners before, don't hurt performance */
+	
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		return NOTIFY_DONE;
+
+	b = skb->tail;
+
+	type |= NFNL_SUBSYS_CTNETLINK << 8;
+	nlh   = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg));
+	nfmsg = NLMSG_DATA(nlh);
+
+	nlh->nlmsg_flags    = flags;
+	nfmsg->nfgen_family = AF_INET;
+	nfmsg->version	= NFNETLINK_V0;
+	nfmsg->res_id	= 0;
+
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG);
+	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+		goto nfattr_failure;
+	NFA_NEST_END(skb, nest_parms);
+	
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY);
+	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+		goto nfattr_failure;
+	NFA_NEST_END(skb, nest_parms);
+	
+	/* NAT stuff is now a status flag */
+	if ((events & IPCT_STATUS || events & IPCT_NATINFO)
+	    && ctnetlink_dump_status(skb, ct) < 0)
+		goto nfattr_failure;
+	if (events & IPCT_REFRESH
+	    && ctnetlink_dump_timeout(skb, ct) < 0)
+		goto nfattr_failure;
+	if (events & IPCT_PROTOINFO
+	    && ctnetlink_dump_protoinfo(skb, ct) < 0)
+		goto nfattr_failure;
+	if (events & IPCT_HELPINFO
+	    && ctnetlink_dump_helpinfo(skb, ct) < 0)
+		goto nfattr_failure;
+
+	if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
+	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
+		goto nfattr_failure;
+
+	nlh->nlmsg_len = skb->tail - b;
+	nfnetlink_send(skb, 0, groups, 0);
+	return NOTIFY_DONE;
+
+nlmsg_failure:
+nfattr_failure:
+	kfree_skb(skb);
+	return NOTIFY_DONE;
+}
+#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */
+
+static int ctnetlink_done(struct netlink_callback *cb)
+{
+	DEBUGP("entered %s\n", __FUNCTION__);
+	return 0;
+}
+
+static int
+ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ip_conntrack *ct = NULL;
+	struct ip_conntrack_tuple_hash *h;
+	struct list_head *i;
+	u_int32_t *id = (u_int32_t *) &cb->args[1];
+
+	DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, 
+			cb->args[0], *id);
+
+	read_lock_bh(&ip_conntrack_lock);
+	for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) {
+		list_for_each(i, &ip_conntrack_hash[cb->args[0]]) {
+			h = (struct ip_conntrack_tuple_hash *) i;
+			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+			ct = tuplehash_to_ctrack(h);
+			if (ct->id <= *id)
+				continue;
+			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
+		                        	cb->nlh->nlmsg_seq,
+						IPCTNL_MSG_CT_NEW,
+						1, ct) < 0)
+				goto out;
+			*id = ct->id;
+		}
+	}
+out:	
+	read_unlock_bh(&ip_conntrack_lock);
+
+	DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
+
+	return skb->len;
+}
+
+#ifdef CONFIG_IP_NF_CT_ACCT
+static int
+ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ip_conntrack *ct = NULL;
+	struct ip_conntrack_tuple_hash *h;
+	struct list_head *i;
+	u_int32_t *id = (u_int32_t *) &cb->args[1];
+
+	DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, 
+			cb->args[0], *id);
+
+	write_lock_bh(&ip_conntrack_lock);
+	for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) {
+		list_for_each(i, &ip_conntrack_hash[cb->args[0]]) {
+			h = (struct ip_conntrack_tuple_hash *) i;
+			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+			ct = tuplehash_to_ctrack(h);
+			if (ct->id <= *id)
+				continue;
+			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
+		                        	cb->nlh->nlmsg_seq,
+						IPCTNL_MSG_CT_NEW,
+						1, ct) < 0)