[NETFILTER]: Add ctnetlink port for nf_conntrack

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 1973 insertions, 34 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 794c41d19b2..7d55f9cbd85 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -95,4 +95,11 @@ config NF_CONNTRACK_FTP
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CT_NETLINK
+	tristate 'Connection tracking netlink interface (EXPERIMENTAL)'
+	depends on EXPERIMENTAL && NF_CONNTRACK && NETFILTER_NETLINK
+	depends on NF_CONNTRACK!=y || NETFILTER_NETLINK!=m
+	help
+	  This option enables support for a netlink-based userspace interface
+
 endmenu
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 55f019ad2c0..cb2183145c3 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -13,3 +13,6 @@ obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
 
 # SCTP protocol connection tracking
 obj-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o
+
+# netlink interface for nf_conntrack
+obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0c5b01d732d..62bb509f05d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -82,6 +82,8 @@ unsigned int nf_ct_log_invalid;
 static LIST_HEAD(unconfirmed);
 static int nf_conntrack_vmalloc;
 
+static unsigned int nf_conntrack_next_id = 1;
+static unsigned int nf_conntrack_expect_next_id = 1;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 struct notifier_block *nf_conntrack_chain;
 struct notifier_block *nf_conntrack_expect_chain;
@@ -184,7 +186,7 @@ DECLARE_MUTEX(nf_ct_cache_mutex);
 
 extern struct nf_conntrack_protocol nf_conntrack_generic_protocol;
 struct nf_conntrack_protocol *
-nf_ct_find_proto(u_int16_t l3proto, u_int8_t protocol)
+__nf_ct_proto_find(u_int16_t l3proto, u_int8_t protocol)
 {
 	if (unlikely(nf_ct_protos[l3proto] == NULL))
 		return &nf_conntrack_generic_protocol;
@@ -192,6 +194,50 @@ nf_ct_find_proto(u_int16_t l3proto, u_int8_t protocol)
 	return nf_ct_protos[l3proto][protocol];
 }
 
+/* this is guaranteed to always return a valid protocol helper, since
+ * it falls back to generic_protocol */
+struct nf_conntrack_protocol *
+nf_ct_proto_find_get(u_int16_t l3proto, u_int8_t protocol)
+{
+	struct nf_conntrack_protocol *p;
+
+	preempt_disable();
+	p = __nf_ct_proto_find(l3proto, protocol);
+	if (p) {
+		if (!try_module_get(p->me))
+			p = &nf_conntrack_generic_protocol;
+	}
+	preempt_enable();
+	
+	return p;
+}
+
+void nf_ct_proto_put(struct nf_conntrack_protocol *p)
+{
+	module_put(p->me);
+}
+
+struct nf_conntrack_l3proto *
+nf_ct_l3proto_find_get(u_int16_t l3proto)
+{
+	struct nf_conntrack_l3proto *p;
+
+	preempt_disable();
+	p = __nf_ct_l3proto_find(l3proto);
+	if (p) {
+		if (!try_module_get(p->me))
+			p = &nf_conntrack_generic_l3proto;
+	}
+	preempt_enable();
+
+	return p;
+}
+
+void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p)
+{
+	module_put(p->me);
+}
+
 static int nf_conntrack_hash_rnd_initted;
 static unsigned int nf_conntrack_hash_rnd;
 
@@ -384,7 +430,7 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 }
 
 /* nf_conntrack_expect helper functions */
-static void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
+void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
 {
 	ASSERT_WRITE_LOCK(&nf_conntrack_lock);
 	NF_CT_ASSERT(!timer_pending(&exp->timeout));
@@ -404,6 +450,33 @@ static void expectation_timed_out(unsigned long ul_expect)
 	nf_conntrack_expect_put(exp);
 }
 
+struct nf_conntrack_expect *
+__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
+{
+	struct nf_conntrack_expect *i;
+	
+	list_for_each_entry(i, &nf_conntrack_expect_list, list) {
+		if (nf_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 nf_conntrack_expect *
+nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
+{
+	struct nf_conntrack_expect *i;
+	
+	read_lock_bh(&nf_conntrack_lock);
+	i = __nf_conntrack_expect_find(tuple);
+	read_unlock_bh(&nf_conntrack_lock);
+
+	return i;
+}
+
 /* If an expectation for this connection is found, it gets delete from
  * global list then returned. */
 static struct nf_conntrack_expect *
@@ -432,7 +505,7 @@ find_expectation(const struct nf_conntrack_tuple *tuple)
 }
 
 /* delete all expectations for this conntrack */
-static void remove_expectations(struct nf_conn *ct)
+void nf_ct_remove_expectations(struct nf_conn *ct)
 {
 	struct nf_conntrack_expect *i, *tmp;
 
@@ -462,7 +535,7 @@ clean_from_lists(struct nf_conn *ct)
 	LIST_DELETE(&nf_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]);
 
 	/* Destroy all pending expectations */
-	remove_expectations(ct);
+	nf_ct_remove_expectations(ct);
 }
 
 static void
@@ -482,12 +555,11 @@ 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 nf_conntrack_lock!!! -HW */
-	l3proto = nf_ct_find_l3proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num);
+	l3proto = __nf_ct_l3proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num);
 	if (l3proto && l3proto->destroy)
 		l3proto->destroy(ct);
 
-	proto = nf_ct_find_proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num,
-				 ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum);
+	proto = __nf_ct_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum);
 	if (proto && proto->destroy)
 		proto->destroy(ct);
 
@@ -499,7 +571,7 @@ 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);
+	nf_ct_remove_expectations(ct);
 
 	/* We overload first tuple to link into unconfirmed list. */
 	if (!nf_ct_is_confirmed(ct)) {
@@ -540,7 +612,7 @@ conntrack_tuple_cmp(const struct nf_conntrack_tuple_hash *i,
 		&& nf_ct_tuple_equal(tuple, &i->tuple);
 }
 
-static struct nf_conntrack_tuple_hash *
+struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(const struct nf_conntrack_tuple *tuple,
 		    const struct nf_conn *ignored_conntrack)
 {
@@ -575,6 +647,29 @@ nf_conntrack_find_get(const struct nf_conntrack_tuple *tuple,
 	return h;
 }
 
+static void __nf_conntrack_hash_insert(struct nf_conn *ct,
+				       unsigned int hash,
+				       unsigned int repl_hash) 
+{
+	ct->id = ++nf_conntrack_next_id;
+	list_prepend(&nf_conntrack_hash[hash],
+		     &ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
+	list_prepend(&nf_conntrack_hash[repl_hash],
+		     &ct->tuplehash[IP_CT_DIR_REPLY].list);
+}
+
+void nf_conntrack_hash_insert(struct nf_conn *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(&nf_conntrack_lock);
+	__nf_conntrack_hash_insert(ct, hash, repl_hash);
+	write_unlock_bh(&nf_conntrack_lock);
+}
+
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff **pskb)
@@ -621,10 +716,7 @@ __nf_conntrack_confirm(struct sk_buff **pskb)
 		/* Remove from unconfirmed list */
 		list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
 
-		list_prepend(&nf_conntrack_hash[hash],
-			     &ct->tuplehash[IP_CT_DIR_ORIGINAL]);
-		list_prepend(&nf_conntrack_hash[repl_hash],
-			     &ct->tuplehash[IP_CT_DIR_REPLY]);
+		__nf_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. */
@@ -708,13 +800,41 @@ static inline int helper_cmp(const struct nf_conntrack_helper *i,
 }
 
 static struct nf_conntrack_helper *
-nf_ct_find_helper(const struct nf_conntrack_tuple *tuple)
+__nf_ct_helper_find(const struct nf_conntrack_tuple *tuple)
 {
 	return LIST_FIND(&helpers, helper_cmp,
 			 struct nf_conntrack_helper *,
 			 tuple);
 }
 
+struct nf_conntrack_helper *
+nf_ct_helper_find_get( const struct nf_conntrack_tuple *tuple)
+{
+	struct nf_conntrack_helper *helper;
+
+	/* need nf_conntrack_lock to assure that helper exists until
+	 * try_module_get() is called */
+	read_lock_bh(&nf_conntrack_lock);
+
+	helper = __nf_ct_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(&nf_conntrack_lock);
+
+	return helper;
+}
+
+void nf_ct_helper_put(struct nf_conntrack_helper *helper)
+{
+	module_put(helper->me);
+}
+
 static struct nf_conn *
 __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 		     const struct nf_conntrack_tuple *repl,
@@ -744,7 +864,7 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 	/*  find features needed by this conntrack. */
 	features = l3proto->get_features(orig);
 	read_lock_bh(&nf_conntrack_lock);
-	if (nf_ct_find_helper(repl) != NULL)
+	if (__nf_ct_helper_find(repl) != NULL)
 		features |= NF_CT_F_HELP;
 	read_unlock_bh(&nf_conntrack_lock);
 
@@ -794,7 +914,7 @@ struct nf_conn *nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 {
 	struct nf_conntrack_l3proto *l3proto;
 
-	l3proto = nf_ct_find_l3proto(orig->src.l3num);
+	l3proto = __nf_ct_l3proto_find(orig->src.l3num);
 	return __nf_conntrack_alloc(orig, repl, l3proto);
 }
 
@@ -853,7 +973,7 @@ init_conntrack(const struct nf_conntrack_tuple *tuple,
 		nf_conntrack_get(&conntrack->master->ct_general);
 		NF_CT_STAT_INC(expect_new);
 	} else {
-		conntrack->helper = nf_ct_find_helper(&repl_tuple);
+		conntrack->helper = __nf_ct_helper_find(&repl_tuple);
 
 		NF_CT_STAT_INC(new);
         }
@@ -947,13 +1067,13 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb)
 		return NF_ACCEPT;
 	}
 
-	l3proto = nf_ct_find_l3proto((u_int16_t)pf);
+	l3proto = __nf_ct_l3proto_find((u_int16_t)pf);
 	if ((ret = l3proto->prepare(pskb, hooknum, &dataoff, &protonum)) <= 0) {
 		DEBUGP("not prepared to track yet or error occured\n");
 		return -ret;
 	}
 
-	proto = nf_ct_find_proto((u_int16_t)pf, protonum);
+	proto = __nf_ct_proto_find((u_int16_t)pf, protonum);
 
 	/* It may be an special packet, error, unclean...
 	 * inverse of the return code tells to the netfilter
@@ -1002,9 +1122,9 @@ int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
 			 const struct nf_conntrack_tuple *orig)
 {
 	return nf_ct_invert_tuple(inverse, orig,
-				  nf_ct_find_l3proto(orig->src.l3num),
-				  nf_ct_find_proto(orig->src.l3num,
-						   orig->dst.protonum));
+				  __nf_ct_l3proto_find(orig->src.l3num),
+				  __nf_ct_proto_find(orig->src.l3num,
+						     orig->dst.protonum));
 }
 
 /* Would two expected things clash? */
@@ -1096,6 +1216,7 @@ static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp)
 	exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ;
 	add_timer(&exp->timeout);
 
+	exp->id = ++nf_conntrack_expect_next_id;
 	atomic_inc(&exp->use);
 	NF_CT_STAT_INC(expect_create);
 }
@@ -1176,7 +1297,7 @@ void nf_conntrack_alter_reply(struct nf_conn *conntrack,
 
 	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
 	if (!conntrack->master && conntrack->expecting == 0)
-		conntrack->helper = nf_ct_find_helper(newreply);
+		conntrack->helper = __nf_ct_helper_find(newreply);
 	write_unlock_bh(&nf_conntrack_lock);
 }
 
@@ -1201,6 +1322,19 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 	return 0;
 }
 
+struct nf_conntrack_helper *
+__nf_conntrack_helper_find_byname(const char *name)
+{
+	struct nf_conntrack_helper *h;
+
+	list_for_each_entry(h, &helpers, list) {
+		if (!strcmp(h->name, name))
+			return h;
+	}
+
+	return NULL;
+}
+
 static inline int unhelp(struct nf_conntrack_tuple_hash *i,
 			 const struct nf_conntrack_helper *me)
 {
@@ -1284,6 +1418,51 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 		nf_conntrack_event_cache(event, skb);
 }
 
+#if defined(CONFIG_NF_CT_NETLINK) || \
+    defined(CONFIG_NF_CT_NETLINK_MODULE)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
+/* 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 nf_ct_port_tuple_to_nfattr(struct sk_buff *skb,
+			       const struct nf_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;
+}
+
+static const size_t cta_min_proto[CTA_PROTO_MAX] = {
+	[CTA_PROTO_SRC_PORT-1]  = sizeof(u_int16_t),
+	[CTA_PROTO_DST_PORT-1]  = sizeof(u_int16_t)
+};
+
+int nf_ct_port_nfattr_to_tuple(struct nfattr *tb[],
+			       struct nf_conntrack_tuple *t)
+{
+	if (!tb[CTA_PROTO_SRC_PORT-1] || !tb[CTA_PROTO_DST_PORT-1])
+		return -EINVAL;
+
+	if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
+		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
+
 /* Used by ipt_REJECT and ip6t_REJECT. */
 void __nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
 {
@@ -1366,6 +1545,11 @@ static void free_conntrack_hash(struct list_head *hash, int vmalloced, int size)
 			   get_order(sizeof(struct list_head) * size));
 }
 
+void nf_conntrack_flush()
+{
+	nf_ct_iterate_cleanup(kill_all, NULL);
+}
+
 /* Mishearing the voices in his head, our hero wonders how he's
    supposed to kill the mall. */
 void nf_conntrack_cleanup(void)
@@ -1379,7 +1563,7 @@ void nf_conntrack_cleanup(void)
 
 	nf_ct_event_cache_flush();
  i_see_dead_people:
-	nf_ct_iterate_cleanup(kill_all, NULL);
+	nf_conntrack_flush();
 	if (atomic_read(&nf_conntrack_count) != 0) {
 		schedule();
 		goto i_see_dead_people;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
new file mode 100644
index 00000000000..4f2e50952a1
--- /dev/null
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -0,0 +1,1642 @@
+/* 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.
+ *
+ * Derived from ip_conntrack_netlink.c: Port by Pablo Neira Ayuso (05/11/14)
+ */
+
+#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/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_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[] = "0.92";
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+
+static inline int
+ctnetlink_dump_tuples_proto(struct sk_buff *skb, 
+			    const struct nf_conntrack_tuple *tuple)
+{
+	struct nf_conntrack_protocol *proto;
+	int ret = 0;
+
+	NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum);
+
+	/* If no protocol helper is found, this function will return the
+	 * generic protocol helper, so proto won't *ever* be NULL */
+	proto = nf_ct_proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+	if (likely(proto->tuple_to_nfattr))
+		ret = proto->tuple_to_nfattr(skb, tuple);
+	
+	nf_ct_proto_put(proto);
+
+	return ret;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_tuples(struct sk_buff *skb, 
+		      const struct nf_conntrack_tuple *tuple)
+{
+	struct nfattr *nest_parms;
+	struct nf_conntrack_l3proto *l3proto;
+	int ret = 0;
+	
+	l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+	
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_IP);
+	if (likely(l3proto->tuple_to_nfattr))
+		ret = l3proto->tuple_to_nfattr(skb, tuple);
+	NFA_NEST_END(skb, nest_parms);
+
+	nf_ct_l3proto_put(l3proto);
+
+	if (unlikely(ret < 0))
+		return ret;
+
+	nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO);
+	ret = ctnetlink_dump_tuples_proto(skb, tuple);
+	NFA_NEST_END(skb, nest_parms);
+
+	return ret;
+
+nfattr_failure:
+	return -1;
+}
+
+static inline int
+ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *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 nf_conn *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 nf_conn *ct)
+{
+	struct nf_conntrack_protocol *proto = nf_ct_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
+	struct nfattr *nest_proto;
+	int ret;
+
+	if (!proto->to_nfattr) {
+		nf_ct_proto_put(proto);
+		return 0;
+	}
+	
+	nest_proto = NFA_NEST(skb, CTA_PROTOINFO);
+
+	ret = proto->to_nfattr(skb, nest_proto, ct);
+
+	nf_ct_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 nf_conn *ct)
+{
+	struct nfattr *nest_helper;
+
+	if (!ct->helper)
+		return 0;
+		
+	nest_helper = NFA_NEST(skb, CTA_HELP);
+	NFA_PUT(skb, CTA_HELP_NAME, strlen(ct->helper->name), 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_NF_CT_ACCT
+static inline int
+ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *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_int32_t tmp;
+
+	tmp = htonl(ct->counters[dir].packets);
+	NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp);
+
+	tmp = htonl(ct->counters[dir].bytes);
+	NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(u_int32_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_NF_CONNTRACK_MARK
+static inline int
+ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *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 nf_conn *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 nf_conn *ct)
+{
+	u_int32_t 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 nf_conn *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 = 
+		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+	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_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 nf_conn *ct = (struct nf_conn *)ptr;
+	struct sk_buff *skb;
+	unsigned int type;
+	unsigned char *b;
+	unsigned int flags = 0, group;
+
+	/* ignore our fake conntrack entry */
+	if (ct == &nf_conntrack_untracked)
+		return NOTIFY_DONE;
+
+	if (events & IPCT_DESTROY) {
+		type = IPCTNL_MSG_CT_DELETE;
+		group = NFNLGRP_CONNTRACK_DESTROY;
+	} else  if (events & (IPCT_NEW | IPCT_RELATED)) {
+		type = IPCTNL_MSG_CT_NEW;
+		flags = NLM_F_CREATE|NLM_F_EXCL;
+		/* dump everything */
+		events = ~0UL;
+		group = NFNLGRP_CONNTRACK_NEW;
+	} else  if (events & (IPCT_STATUS |
+		      IPCT_PROTOINFO |
+		      IPCT_HELPER |
+		      IPCT_HELPINFO |
+		      IPCT_NATINFO)) {
+		type = IPCTNL_MSG_CT_NEW;
+		group = NFNLGRP_CONNTRACK_UPDATE;
+	} else
+		return NOTIFY_DONE;
+	
+  /* 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 = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+	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, group, 0);
+	return NOTIFY_DONE;
+
+nlmsg_failure:
+nfattr_failure:
+	kfree_skb(skb);
+	return NOTIFY_DONE;
+}
+#endif /* CONFIG_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 nf_conn *ct = NULL;
+	struct nf_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(&nf_conntrack_lock);
+	for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++, *id = 0) {
+		list_for_each_prev(i, &nf_conntrack_hash[cb->args[0]]) {
+			h = (struct nf_conntrack_tuple_hash *) i;
+			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+			ct = nf_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(&nf_conntrack_lock);
+
+	DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
+
+	return skb->len;
+}
+
+#ifdef CONFIG_NF_CT_ACCT
+static int
+ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct nf_conn *ct = NULL;
+	struct nf_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(&nf_conntrack_lock);
+	for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++, *id = 0) {
+		list_for_each_prev(i, &nf_conntrack_hash[cb->args[0]]) {
+			h = (struct nf_conntrack_tuple_hash *) i;
+			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+			ct = nf_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;
+
+			memset(&ct->counters, 0, sizeof(ct->counters));
+		}
+	}
+out:	
+	write_unlock_bh(&nf_conntrack_lock);
+
+	DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
+
+	return skb->len;
+}
+#endif
+
+static inline int
+ctnetlink_parse_tuple_ip(struct nfattr *attr, struct nf_conntrack_tuple *tuple)
+{
+	struct nfattr *tb[CTA_IP_MAX];
+	struct nf_conntrack_l3proto *l3proto;
+	int ret = 0;
+
+	DEBUGP("entered %s\n", __FUNCTION__);
+
+	nfattr_parse_nested(tb, CTA_IP_MAX, attr);
+
+	l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+
+	if (likely(l3proto->nfattr_to_tuple))
+		ret = l3proto->nfattr_to_tuple(tb, tuple);
+
+	nf_ct_l3proto_put(l3proto);
+
+	DEBUGP("leaving\n");
+
+	return ret;
+}
+
+static const size_t cta_min_proto[CTA_PROTO_MAX] = {
+	[CTA_PROTO_NUM-1]	= sizeof(u_int8_t),
+};
+
+static inline int
+ctnetlink_parse_tuple_proto(struct nfattr *attr, 
+			    struct nf_conntrack_tuple *tuple)
+{
+	struct nfattr *tb[CTA_PROTO_MAX];
+	struct nf_conntrack_protocol *proto;
+	int ret = 0;
+
+	DEBUGP("entered %s\n", __FUNCTION__);
+
+	nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);
+
+	if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
+		return -EINVAL;
+
+	if (!tb[CTA_PROTO_NUM-1])
+		return -EINVAL;
+	tuple->dst.protonum = *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_NUM-1]);
+
+	proto = nf_ct_proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+
+	if (likely(proto->nfattr_to_tuple))
+		ret = proto->nfattr_to_tuple(tb, tuple);
+
+	nf_ct_proto_put(proto);
+	
+	return ret;
+}
+
+static inline int
+ctnetlink_parse_tuple(struct nfattr *cda[], struct nf_conntrack_tuple *tuple,
+		      enum ctattr_tuple type, u_int8_t l3num)
+{
+	struct nfattr *tb[CTA_TUPLE_MAX];
+	int err;
+
+	DEBUGP("entered %s\n", __FUNCTION__);
+
+	memset(tuple, 0, sizeof(*tuple));
+
+	nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]);
+
+	if (!tb[CTA_TUPLE_IP-1])
+		return -EINVAL;
+
+	tuple->src.l3num = l3num;
+
+	err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP-1], tuple);
+	if (err < 0)
+		return err;
+
+	if (!tb[CTA_TUPLE_PROTO-1])
+		return -EINVAL;
+
+	err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO-1], tuple);
+	if (err < 0)
+		return err;
+
+	/* orig and expect tuples get DIR_ORIGINAL */
+	if (type == CTA_TUPLE_REPLY)
+		tuple->dst.dir = IP_CT_DIR_REPLY;
+	else
+		tuple->dst.dir = IP_CT_DIR_ORIGINAL;
+
+	NF_CT_DUMP_TUPLE(tuple);
+
+	DEBUGP("leaving\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_IP_NF_NAT_NEEDED
+static const size_t cta_min_protonat[CTA_PROTONAT_MAX] = {
+	[CTA_PROTONAT_PORT_MIN-1]       = sizeof(u_int16_t),
+	[CTA_PROTONAT_PORT_MAX-1]       = sizeof(u_int16_t),
+};
+
+static int ctnetlink_parse_nat_proto(struct nfattr *attr,
+				     const struct nf_conn *ct,
+				     struct ip_nat_range *range)
+{
+	struct nfattr *tb[CTA_PROTONAT_MAX];
+	struct ip_nat_protocol *npt;
+
+	DEBUGP("entered %s\n", __FUNCTION__);
+
+	nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr);
+
+	if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat))
+		return -EINVAL;
+
+	npt = ip_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
+
+	if (!npt->nfattr_to_range) {
+		ip_nat_proto_put(npt);
+		return 0;
+	}
+
+	/* nfattr_to_range returns 1 if it parsed, 0 if not, neg. on error */
+	if (npt->nfattr_to_range(tb, range) > 0)
+		range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+
+	ip_nat_proto_put(npt);
+
+	DEBUGP("leaving\n");
+	return 0;
+}
+
+static const size_t cta_min_nat[CTA_NAT_MAX] = {
+	[CTA_NAT_MINIP-1]       = sizeof(u_int32_t),
+	[CTA_NAT_MAXIP-1]       = sizeof(u_int32_t),
+};
+
+static inline int
+ctnetlink_parse_nat(struct nfattr *cda[],
+		    const struct nf_conn *ct, struct ip_nat_range *range)
+{
+	struct nfattr *tb[CTA_NAT_MAX];
+	int err;
+
+	DEBUGP("entered %s\n", __FUNCTION__);
+
+	memset(range, 0, sizeof(*range));
+	
+	nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]);
+
+	if (nfattr_bad_size(tb, CTA_NAT_MAX, cta_min_nat))
+		return -EINVAL;
+
+	if (tb[CTA_NAT_MINIP-1])
+		range->min_ip = *(u_i