[PATCH nf-next v4 0/3] Netfilter zone directions

[PATCH nf-next v4 0/3] Netfilter zone directions

[Daniel Borkmann]

This is a rework of the originally named flextuples [1] patch set,
but after discussions from NFWS completely reworked towards
integration into the existing zones infrastructure.

Please see individual patches for details.

Thanks!

 [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/

v3 -> v4:
 - Rebased & retested everything onto latest nf-next
 - Added nested CTA_TUPLE_ZONE attribute with direction meta data
 - Renamed CTA_DIR; sysctl was already in it's own function
v2 -> v3:
 - Have a global default zone object, use it directly
 - Do not touch uapi-exposed ct->status bits, but integrate
   the marking flag into the zones structure
 - Rebased onto latest nf-next, rerun all stress tests
v1 -> v2:
 - Reworked entire set, integration into zones
 - Rebased onto latest nf-next

Daniel Borkmann (3):
  netfilter: nf_conntrack: push zone object into functions
  netfilter: nf_conntrack: add direction support for zones
  netfilter: nf_conntrack: add efficient mark to zone mapping

 include/net/netfilter/nf_conntrack.h               |  10 +-
 include/net/netfilter/nf_conntrack_core.h          |   3 +-
 include/net/netfilter/nf_conntrack_expect.h        |  11 +-
 include/net/netfilter/nf_conntrack_zones.h         |  99 ++++++++++-
 include/uapi/linux/netfilter/nfnetlink_conntrack.h |  16 ++
 include/uapi/linux/netfilter/xt_CT.h               |   8 +-
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c     |   2 +-
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c       |   4 +-
 net/ipv4/netfilter/nf_defrag_ipv4.c                |  17 +-
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c     |   2 +-
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c     |   5 +-
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c          |  18 +-
 net/netfilter/ipvs/ip_vs_nfct.c                    |   2 +-
 net/netfilter/nf_conntrack_core.c                  | 134 +++++++-------
 net/netfilter/nf_conntrack_expect.c                |  21 ++-
 net/netfilter/nf_conntrack_netlink.c               | 196 ++++++++++++++++-----
 net/netfilter/nf_conntrack_pptp.c                  |   3 +-
 net/netfilter/nf_conntrack_standalone.c            |  30 +++-
 net/netfilter/nf_nat_core.c                        |  24 +--
 net/netfilter/nf_synproxy_core.c                   |   4 +-
 net/netfilter/xt_CT.c                              |  26 ++-
 net/netfilter/xt_connlimit.c                       |   9 +-
 net/sched/act_connmark.c                           |   6 +-
 23 files changed, 468 insertions(+), 182 deletions(-)

-- 
1.9.3

[PATCH v4 1/3] netfilter: nf_conntrack: push zone object into functions

[Daniel Borkmann]

This patch replaces the zone id which is pushed down into functions
with the actual zone object. It's a bigger one-time change, but
needed for later on extending zones with a direction parameter, and
thus decoupling this additional information from all call-sites.

No functional changes in this patch.

The default zone becomes a global const object, namely nf_ct_zone_dflt
and will be returned directly in various cases, one being, when there's
f.e. no zoning support.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/netfilter/nf_conntrack.h           | 10 ++-
 include/net/netfilter/nf_conntrack_core.h      |  3 +-
 include/net/netfilter/nf_conntrack_expect.h    | 11 +++-
 include/net/netfilter/nf_conntrack_zones.h     | 33 +++++++---
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c |  2 +-
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c   |  3 +-
 net/ipv4/netfilter/nf_defrag_ipv4.c            | 11 ++--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c |  2 +-
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c |  3 +-
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      | 12 ++--
 net/netfilter/ipvs/ip_vs_nfct.c                |  2 +-
 net/netfilter/nf_conntrack_core.c              | 75 ++++++++++++++---------
 net/netfilter/nf_conntrack_expect.c            | 21 ++++---
 net/netfilter/nf_conntrack_netlink.c           | 84 ++++++++++++++------------
 net/netfilter/nf_conntrack_pptp.c              |  3 +-
 net/netfilter/nf_conntrack_standalone.c        | 17 ++++--
 net/netfilter/nf_nat_core.c                    | 19 +++---
 net/netfilter/nf_synproxy_core.c               |  4 +-
 net/netfilter/xt_CT.c                          |  6 +-
 net/netfilter/xt_connlimit.c                   |  9 +--
 net/sched/act_connmark.c                       |  5 +-
 21 files changed, 203 insertions(+), 132 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37cd391..f5e23c6 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -250,8 +250,12 @@ void nf_ct_untracked_status_or(unsigned long bits);
 void nf_ct_iterate_cleanup(struct net *net,
 			   int (*iter)(struct nf_conn *i, void *data),
 			   void *data, u32 portid, int report);
+
+struct nf_conntrack_zone;
+
 void nf_conntrack_free(struct nf_conn *ct);
-struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
+struct nf_conn *nf_conntrack_alloc(struct net *net,
+				   const struct nf_conntrack_zone *zone,
 				   const struct nf_conntrack_tuple *orig,
 				   const struct nf_conntrack_tuple *repl,
 				   gfp_t gfp);
@@ -291,7 +295,9 @@ extern unsigned int nf_conntrack_max;
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
-struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
+				 const struct nf_conntrack_zone *zone,
+				 gfp_t flags);
 
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index f2f0fa3..c03f9c4 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -52,7 +52,8 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 
 /* Find a connection corresponding to a tuple. */
 struct nf_conntrack_tuple_hash *
-nf_conntrack_find_get(struct net *net, u16 zone,
+nf_conntrack_find_get(struct net *net,
+		      const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple);
 
 int __nf_conntrack_confirm(struct sk_buff *skb);
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 3f3aecb..dce56f0 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -4,7 +4,9 @@
 
 #ifndef _NF_CONNTRACK_EXPECT_H
 #define _NF_CONNTRACK_EXPECT_H
+
 #include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 
 extern unsigned int nf_ct_expect_hsize;
 extern unsigned int nf_ct_expect_max;
@@ -76,15 +78,18 @@ int nf_conntrack_expect_init(void);
 void nf_conntrack_expect_fini(void);
 
 struct nf_conntrack_expect *
-__nf_ct_expect_find(struct net *net, u16 zone,
+__nf_ct_expect_find(struct net *net,
+		    const struct nf_conntrack_zone *zone,
 		    const struct nf_conntrack_tuple *tuple);
 
 struct nf_conntrack_expect *
-nf_ct_expect_find_get(struct net *net, u16 zone,
+nf_ct_expect_find_get(struct net *net,
+		      const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple);
 
 struct nf_conntrack_expect *
-nf_ct_find_expectation(struct net *net, u16 zone,
+nf_ct_find_expectation(struct net *net,
+		       const struct nf_conntrack_zone *zone,
 		       const struct nf_conntrack_tuple *tuple);
 
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h
index 034efe8..0788bb0 100644
--- a/include/net/netfilter/nf_conntrack_zones.h
+++ b/include/net/netfilter/nf_conntrack_zones.h
@@ -1,25 +1,38 @@
 #ifndef _NF_CONNTRACK_ZONES_H
 #define _NF_CONNTRACK_ZONES_H
 
-#define NF_CT_DEFAULT_ZONE	0
-
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-#include <net/netfilter/nf_conntrack_extend.h>
+#define NF_CT_DEFAULT_ZONE_ID	0
 
 struct nf_conntrack_zone {
 	u16	id;
 };
 
-static inline u16 nf_ct_zone(const struct nf_conn *ct)
+extern const struct nf_conntrack_zone nf_ct_zone_dflt;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_extend.h>
+
+static inline const struct nf_conntrack_zone *
+nf_ct_zone(const struct nf_conn *ct)
 {
+	const struct nf_conntrack_zone *nf_ct_zone = NULL;
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
-	struct nf_conntrack_zone *nf_ct_zone;
 	nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE);
-	if (nf_ct_zone)
-		return nf_ct_zone->id;
 #endif
-	return NF_CT_DEFAULT_ZONE;
+	return nf_ct_zone ? nf_ct_zone : &nf_ct_zone_dflt;
 }
 
-#endif /* CONFIG_NF_CONNTRACK || CONFIG_NF_CONNTRACK_MODULE */
+static inline const struct nf_conntrack_zone *
+nf_ct_zone_tmpl(const struct nf_conn *tmpl)
+{
+	return tmpl ? nf_ct_zone(tmpl) : &nf_ct_zone_dflt;
+}
+
+static inline bool nf_ct_zone_equal(const struct nf_conn *a,
+				    const struct nf_conntrack_zone *b)
+{
+	return nf_ct_zone(a)->id == b->id;
+}
+#endif /* IS_ENABLED(CONFIG_NF_CONNTRACK) */
 #endif /* _NF_CONNTRACK_ZONES_H */
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 30ad955..8a2caaf 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -280,7 +280,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 		return -EINVAL;
 	}
 
-	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
 	if (h) {
 		struct sockaddr_in sin;
 		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 80d5554..8a2f41c 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -134,9 +134,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	struct nf_conntrack_tuple innertuple, origtuple;
 	const struct nf_conntrack_l4proto *innerproto;
 	const struct nf_conntrack_tuple_hash *h;
-	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+	const struct nf_conntrack_zone *zone;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
+	zone = nf_ct_zone_tmpl(tmpl);
 
 	/* Are they talking about one of our connections? */
 	if (!nf_ct_get_tuplepr(skb,
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index b69e82b..20fe8e6 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -43,19 +43,18 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 					      struct sk_buff *skb)
 {
-	u16 zone = NF_CT_DEFAULT_ZONE;
-
+	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (skb->nfct)
-		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+		zone_id = nf_ct_zone((struct nf_conn *)skb->nfct)->id;
 #endif
 	if (nf_bridge_in_prerouting(skb))
-		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
+		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
 
 	if (hooknum == NF_INET_PRE_ROUTING)
-		return IP_DEFRAG_CONNTRACK_IN + zone;
+		return IP_DEFRAG_CONNTRACK_IN + zone_id;
 	else
-		return IP_DEFRAG_CONNTRACK_OUT + zone;
+		return IP_DEFRAG_CONNTRACK_OUT + zone_id;
 }
 
 static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4ba0c34..7302900 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -251,7 +251,7 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 	if (*len < 0 || (unsigned int) *len < sizeof(sin6))
 		return -EINVAL;
 
-	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
 	if (!h) {
 		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
 			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 90388d6..2029141 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -150,7 +150,6 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_tuple intuple, origtuple;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_l4proto *inproto;
-	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
 
@@ -177,7 +176,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 
 	*ctinfo = IP_CT_RELATED;
 
-	h = nf_conntrack_find_get(net, zone, &intuple);
+	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl), &intuple);
 	if (!h) {
 		pr_debug("icmpv6_error: no match\n");
 		return -NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 267fb8d..9d3de9b 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -33,20 +33,18 @@
 static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 						struct sk_buff *skb)
 {
-	u16 zone = NF_CT_DEFAULT_ZONE;
-
+	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (skb->nfct)
-		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+		zone_id = nf_ct_zone((struct nf_conn *)skb->nfct)->id;
 #endif
 	if (nf_bridge_in_prerouting(skb))
-		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
+		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
 
 	if (hooknum == NF_INET_PRE_ROUTING)
-		return IP6_DEFRAG_CONNTRACK_IN + zone;
+		return IP6_DEFRAG_CONNTRACK_IN + zone_id;
 	else
-		return IP6_DEFRAG_CONNTRACK_OUT + zone;
-
+		return IP6_DEFRAG_CONNTRACK_OUT + zone_id;
 }
 
 static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index 5882bbf..1361845 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -274,7 +274,7 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 		" for conn " FMT_CONN "\n",
 		__func__, ARG_TUPLE(&tuple), ARG_CONN(cp));
 
-	h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE,
+	h = nf_conntrack_find_get(ip_vs_conn_net(cp), &nf_ct_zone_dflt,
 				  &tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 651039a..0bb26e8 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -126,7 +126,8 @@ EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
 unsigned int nf_conntrack_hash_rnd __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_rnd);
 
-static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone)
+static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
+			      const struct nf_conntrack_zone *zone)
 {
 	unsigned int n;
 
@@ -135,7 +136,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone)
 	 * three bytes manually.
 	 */
 	n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
-	return jhash2((u32 *)tuple, n, zone ^ nf_conntrack_hash_rnd ^
+	return jhash2((u32 *)tuple, n, zone->id ^ nf_conntrack_hash_rnd ^
 		      (((__force __u16)tuple->dst.u.all << 16) |
 		      tuple->dst.protonum));
 }
@@ -151,12 +152,14 @@ static u32 hash_bucket(u32 hash, const struct net *net)
 }
 
 static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
-				  u16 zone, unsigned int size)
+				  const struct nf_conntrack_zone *zone,
+				  unsigned int size)
 {
 	return __hash_bucket(hash_conntrack_raw(tuple, zone), size);
 }
 
-static inline u_int32_t hash_conntrack(const struct net *net, u16 zone,
+static inline u_int32_t hash_conntrack(const struct net *net,
+				       const struct nf_conntrack_zone *zone,
 				       const struct nf_conntrack_tuple *tuple)
 {
 	return __hash_conntrack(tuple, zone, net->ct.htable_size);
@@ -288,7 +291,9 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
 }
 
 /* Released via destroy_conntrack() */
-struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
+				 const struct nf_conntrack_zone *zone,
+				 gfp_t flags)
 {
 	struct nf_conn *tmpl;
 
@@ -306,7 +311,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
 		nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC);
 		if (!nf_ct_zone)
 			goto out_free;
-		nf_ct_zone->id = zone;
+		nf_ct_zone->id = zone->id;
 	}
 #endif
 	atomic_set(&tmpl->ct_general.use, 0);
@@ -371,11 +376,12 @@ destroy_conntrack(struct nf_conntrack *nfct)
 
 static void nf_ct_delete_from_lists(struct nf_conn *ct)
 {
+	const struct nf_conntrack_zone *zone;
 	struct net *net = nf_ct_net(ct);
 	unsigned int hash, reply_hash;
-	u16 zone = nf_ct_zone(ct);
 	unsigned int sequence;
 
+	zone = nf_ct_zone(ct);
 	nf_ct_helper_destroy(ct);
 
 	local_bh_disable();
@@ -431,8 +437,8 @@ static void death_by_timeout(unsigned long ul_conntrack)
 
 static inline bool
 nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
-			const struct nf_conntrack_tuple *tuple,
-			u16 zone)
+		const struct nf_conntrack_tuple *tuple,
+		const struct nf_conntrack_zone *zone)
 {
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 
@@ -440,8 +446,8 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
 	 * so we need to check that the conntrack is confirmed
 	 */
 	return nf_ct_tuple_equal(tuple, &h->tuple) &&
-		nf_ct_zone(ct) == zone &&
-		nf_ct_is_confirmed(ct);
+	       nf_ct_zone_equal(ct, zone) &&
+	       nf_ct_is_confirmed(ct);
 }
 
 /*
@@ -450,7 +456,7 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
  *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
  */
 static struct nf_conntrack_tuple_hash *
-____nf_conntrack_find(struct net *net, u16 zone,
+____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple, u32 hash)
 {
 	struct nf_conntrack_tuple_hash *h;
@@ -486,7 +492,7 @@ begin:
 
 /* Find a connection corresponding to a tuple. */
 static struct nf_conntrack_tuple_hash *
-__nf_conntrack_find_get(struct net *net, u16 zone,
+__nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
 			const struct nf_conntrack_tuple *tuple, u32 hash)
 {
 	struct nf_conntrack_tuple_hash *h;
@@ -513,7 +519,7 @@ begin:
 }
 
 struct nf_conntrack_tuple_hash *
-nf_conntrack_find_get(struct net *net, u16 zone,
+nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple)
 {
 	return __nf_conntrack_find_get(net, zone, tuple,
@@ -536,11 +542,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 int
 nf_conntrack_hash_check_insert(struct nf_conn *ct)
 {
+	const struct nf_conntrack_zone *zone;
 	struct net *net = nf_ct_net(ct);
 	unsigned int hash, reply_hash;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
-	u16 zone;
 	unsigned int sequence;
 
 	zone = nf_ct_zone(ct);
@@ -558,12 +564,12 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				      &h->tuple) &&
-		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
 			goto out;
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
-		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
 			goto out;
 
 	add_timer(&ct->timeout);
@@ -588,6 +594,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
 {
+	const struct nf_conntrack_zone *zone;
 	unsigned int hash, reply_hash;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
@@ -596,7 +603,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
-	u16 zone;
 	unsigned int sequence;
 
 	ct = nf_ct_get(skb, &ctinfo);
@@ -649,12 +655,12 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				      &h->tuple) &&
-		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
 			goto out;
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
-		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
 			goto out;
 
 	/* Timer relative to confirmation time, not original
@@ -707,11 +713,14 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 			 const struct nf_conn *ignored_conntrack)
 {
 	struct net *net = nf_ct_net(ignored_conntrack);
+	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	struct nf_conn *ct;
-	u16 zone = nf_ct_zone(ignored_conntrack);
-	unsigned int hash = hash_conntrack(net, zone, tuple);
+	unsigned int hash;
+
+	zone = nf_ct_zone(ignored_conntrack);
+	hash = hash_conntrack(net, zone, tuple);
 
 	/* Disable BHs the entire time since we need to disable them at
 	 * least once for the stats anyway.
@@ -721,7 +730,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (ct != ignored_conntrack &&
 		    nf_ct_tuple_equal(tuple, &h->tuple) &&
-		    nf_ct_zone(ct) == zone) {
+		    nf_ct_zone_equal(ct, zone)) {
 			NF_CT_STAT_INC(net, found);
 			rcu_read_unlock_bh();
 			return 1;
@@ -810,7 +819,8 @@ void init_nf_conntrack_hash_rnd(void)
 }
 
 static struct nf_conn *
-__nf_conntrack_alloc(struct net *net, u16 zone,
+__nf_conntrack_alloc(struct net *net,
+		     const struct nf_conntrack_zone *zone,
 		     const struct nf_conntrack_tuple *orig,
 		     const struct nf_conntrack_tuple *repl,
 		     gfp_t gfp, u32 hash)
@@ -864,7 +874,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 		nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC);
 		if (!nf_ct_zone)
 			goto out_free;
-		nf_ct_zone->id = zone;
+		nf_ct_zone->id = zone->id;
 	}
 #endif
 	/* Because we use RCU lookups, we set ct_general.use to zero before
@@ -881,7 +891,8 @@ out_free:
 #endif
 }
 
-struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
+struct nf_conn *nf_conntrack_alloc(struct net *net,
+				   const struct nf_conntrack_zone *zone,
 				   const struct nf_conntrack_tuple *orig,
 				   const struct nf_conntrack_tuple *repl,
 				   gfp_t gfp)
@@ -923,7 +934,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_tuple repl_tuple;
 	struct nf_conntrack_ecache *ecache;
 	struct nf_conntrack_expect *exp = NULL;
-	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+	const struct nf_conntrack_zone *zone;
 	struct nf_conn_timeout *timeout_ext;
 	unsigned int *timeouts;
 
@@ -932,6 +943,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 		return NULL;
 	}
 
+	zone = nf_ct_zone_tmpl(tmpl);
 	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
 				  hash);
 	if (IS_ERR(ct))
@@ -1026,10 +1038,10 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  int *set_reply,
 		  enum ip_conntrack_info *ctinfo)
 {
+	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
-	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
 	u32 hash;
 
 	if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
@@ -1040,6 +1052,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	}
 
 	/* look for tuple match */
+	zone = nf_ct_zone_tmpl(tmpl);
 	hash = hash_conntrack_raw(&tuple, zone);
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
@@ -1290,6 +1303,12 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
 }
 EXPORT_SYMBOL_GPL(__nf_ct_kill_acct);
 
+/* Built-in default zone used e.g. by modules. */
+const struct nf_conntrack_zone nf_ct_zone_dflt = {
+	.id	= NF_CT_DEFAULT_ZONE_ID,
+};
+EXPORT_SYMBOL_GPL(nf_ct_zone_dflt);
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = {
 	.len	= sizeof(struct nf_conntrack_zone),
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index b45a422..980db85 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -88,7 +88,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
 }
 
 struct nf_conntrack_expect *
-__nf_ct_expect_find(struct net *net, u16 zone,
+__nf_ct_expect_find(struct net *net,
+		    const struct nf_conntrack_zone *zone,
 		    const struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_expect *i;
@@ -100,7 +101,7 @@ __nf_ct_expect_find(struct net *net, u16 zone,
 	h = nf_ct_expect_dst_hash(tuple);
 	hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
 		if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-		    nf_ct_zone(i->master) == zone)
+		    nf_ct_zone_equal(i->master, zone))
 			return i;
 	}
 	return NULL;
@@ -109,7 +110,8 @@ EXPORT_SYMBOL_GPL(__nf_ct_expect_find);
 
 /* Just find a expectation corresponding to a tuple. */
 struct nf_conntrack_expect *
-nf_ct_expect_find_get(struct net *net, u16 zone,
+nf_ct_expect_find_get(struct net *net,
+		      const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_expect *i;
@@ -127,7 +129,8 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get);
 /* If an expectation for this connection is found, it gets delete from
  * global list then returned. */
 struct nf_conntrack_expect *
-nf_ct_find_expectation(struct net *net, u16 zone,
+nf_ct_find_expectation(struct net *net,
+		       const struct nf_conntrack_zone *zone,
 		       const struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_expect *i, *exp = NULL;
@@ -140,7 +143,7 @@ nf_ct_find_expectation(struct net *net, u16 zone,
 	hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
 		if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
 		    nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-		    nf_ct_zone(i->master) == zone) {
+		    nf_ct_zone_equal(i->master, zone)) {
 			exp = i;
 			break;
 		}
@@ -220,16 +223,16 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 	}
 
 	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
-	       nf_ct_zone(a->master) == nf_ct_zone(b->master);
+	       nf_ct_zone_equal(a->master, nf_ct_zone(b->master));
 }
 
 static inline int expect_matches(const struct nf_conntrack_expect *a,
 				 const struct nf_conntrack_expect *b)
 {
 	return a->master == b->master && a->class == b->class &&
-		nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
-		nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
-		nf_ct_zone(a->master) == nf_ct_zone(b->master);
+	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
+	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
+	       nf_ct_zone_equal(a->master, nf_ct_zone(b->master));
 }
 
 /* Generally a bad idea to call this: could have matched already. */
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 6b8b0ab..95f7f01 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -458,6 +458,7 @@ static int
 ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 		    struct nf_conn *ct)
 {
+	const struct nf_conntrack_zone *zone;
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	struct nlattr *nest_parms;
@@ -487,8 +488,9 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	if (nf_ct_zone(ct) &&
-	    nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct))))
+	zone = nf_ct_zone(ct);
+	if (zone->id != NF_CT_DEFAULT_ZONE_ID &&
+	    nla_put_be16(skb, CTA_ZONE, htons(zone->id)))
 		goto nla_put_failure;
 
 	if (ctnetlink_dump_status(skb, ct) < 0 ||
@@ -609,6 +611,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 static int
 ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 {
+	const struct nf_conntrack_zone *zone;
 	struct net *net;
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
@@ -669,8 +672,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	if (nf_ct_zone(ct) &&
-	    nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct))))
+	zone = nf_ct_zone(ct);
+	if (zone->id != NF_CT_DEFAULT_ZONE_ID &&
+	    nla_put_be16(skb, CTA_ZONE, htons(zone->id)))
 		goto nla_put_failure;
 
 	if (ctnetlink_dump_id(skb, ct) < 0)
@@ -965,17 +969,18 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 }
 
 static int
-ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone)
+ctnetlink_parse_zone(const struct nlattr *attr,
+		     struct nf_conntrack_zone *zone)
 {
-	if (attr)
+	zone->id = NF_CT_DEFAULT_ZONE_ID;
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
-		*zone = ntohs(nla_get_be16(attr));
+	if (attr)
+		zone->id = ntohs(nla_get_be16(attr));
 #else
+	if (attr)
 		return -EOPNOTSUPP;
 #endif
-	else
-		*zone = 0;
-
 	return 0;
 }
 
@@ -1058,7 +1063,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conn *ct;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
-	u16 zone;
+	struct nf_conntrack_zone zone;
 	int err;
 
 	err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
@@ -1078,7 +1083,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	h = nf_conntrack_find_get(net, zone, &tuple);
+	h = nf_conntrack_find_get(net, &zone, &tuple);
 	if (!h)
 		return -ENOENT;
 
@@ -1112,7 +1117,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct sk_buff *skb2 = NULL;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
-	u16 zone;
+	struct nf_conntrack_zone zone;
 	int err;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
@@ -1147,7 +1152,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	h = nf_conntrack_find_get(net, zone, &tuple);
+	h = nf_conntrack_find_get(net, &zone, &tuple);
 	if (!h)
 		return -ENOENT;
 
@@ -1645,7 +1650,8 @@ ctnetlink_change_conntrack(struct nf_conn *ct,
 }
 
 static struct nf_conn *
-ctnetlink_create_conntrack(struct net *net, u16 zone,
+ctnetlink_create_conntrack(struct net *net,
+			   const struct nf_conntrack_zone *zone,
 			   const struct nlattr * const cda[],
 			   struct nf_conntrack_tuple *otuple,
 			   struct nf_conntrack_tuple *rtuple,
@@ -1804,7 +1810,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nf_conn *ct;
 	u_int8_t u3 = nfmsg->nfgen_family;
-	u16 zone;
+	struct nf_conntrack_zone zone;
 	int err;
 
 	err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
@@ -1824,9 +1830,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	}
 
 	if (cda[CTA_TUPLE_ORIG])
-		h = nf_conntrack_find_get(net, zone, &otuple);
+		h = nf_conntrack_find_get(net, &zone, &otuple);
 	else if (cda[CTA_TUPLE_REPLY])
-		h = nf_conntrack_find_get(net, zone, &rtuple);
+		h = nf_conntrack_find_get(net, &zone, &rtuple);
 
 	if (h == NULL) {
 		err = -ENOENT;
@@ -1836,7 +1842,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 			if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY])
 				return -EINVAL;
 
-			ct = ctnetlink_create_conntrack(net, zone, cda, &otuple,
+			ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple,
 							&rtuple, u3);
 			if (IS_ERR(ct))
 				return PTR_ERR(ct);
@@ -2091,6 +2097,7 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
 static int
 ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct)
 {
+	const struct nf_conntrack_zone *zone;
 	struct nlattr *nest_parms;
 
 	rcu_read_lock();
@@ -2108,10 +2115,10 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	if (nf_ct_zone(ct)) {
-		if (nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct))))
-			goto nla_put_failure;
-	}
+	zone = nf_ct_zone(ct);
+	if (zone->id != NF_CT_DEFAULT_ZONE_ID &&
+	    nla_put_be16(skb, CTA_ZONE, htons(zone->id)))
+		goto nla_put_failure;
 
 	if (ctnetlink_dump_id(skb, ct) < 0)
 		goto nla_put_failure;
@@ -2612,7 +2619,7 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
-	u16 zone = 0;
+	struct nf_conntrack_zone zone;
 	struct netlink_dump_control c = {
 		.dump = ctnetlink_exp_ct_dump_table,
 		.done = ctnetlink_exp_done,
@@ -2622,13 +2629,11 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (cda[CTA_EXPECT_ZONE]) {
-		err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
-		if (err < 0)
-			return err;
-	}
+	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+	if (err < 0)
+		return err;
 
-	h = nf_conntrack_find_get(net, zone, &tuple);
+	h = nf_conntrack_find_get(net, &zone, &tuple);
 	if (!h)
 		return -ENOENT;
 
@@ -2652,7 +2657,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	struct sk_buff *skb2;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
-	u16 zone;
+	struct nf_conntrack_zone zone;
 	int err;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
@@ -2681,7 +2686,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	exp = nf_ct_expect_find_get(net, zone, &tuple);
+	exp = nf_ct_expect_find_get(net, &zone, &tuple);
 	if (!exp)
 		return -ENOENT;
 
@@ -2732,8 +2737,8 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct hlist_node *next;
 	u_int8_t u3 = nfmsg->nfgen_family;
+	struct nf_conntrack_zone zone;
 	unsigned int i;
-	u16 zone;
 	int err;
 
 	if (cda[CTA_EXPECT_TUPLE]) {
@@ -2747,7 +2752,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 			return err;
 
 		/* bump usage count to 2 */
-		exp = nf_ct_expect_find_get(net, zone, &tuple);
+		exp = nf_ct_expect_find_get(net, &zone, &tuple);
 		if (!exp)
 			return -ENOENT;
 
@@ -2937,7 +2942,8 @@ err_out:
 }
 
 static int
-ctnetlink_create_expect(struct net *net, u16 zone,
+ctnetlink_create_expect(struct net *net,
+			const struct nf_conntrack_zone *zone,
 			const struct nlattr * const cda[],
 			u_int8_t u3, u32 portid, int report)
 {
@@ -3011,7 +3017,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_expect *exp;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
-	u16 zone;
+	struct nf_conntrack_zone zone;
 	int err;
 
 	if (!cda[CTA_EXPECT_TUPLE]
@@ -3028,14 +3034,12 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 		return err;
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	exp = __nf_ct_expect_find(net, zone, &tuple);
-
+	exp = __nf_ct_expect_find(net, &zone, &tuple);
 	if (!exp) {
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 		err = -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_CREATE) {
-			err = ctnetlink_create_expect(net, zone, cda,
-						      u3,
+			err = ctnetlink_create_expect(net, &zone, cda, u3,
 						      NETLINK_CB(skb).portid,
 						      nlmsg_report(nlh));
 		}
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 825c3e3..5588c7a 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -143,13 +143,14 @@ static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
 				  const struct nf_conntrack_tuple *t)
 {
 	const struct nf_conntrack_tuple_hash *h;
+	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn *sibling;
-	u16 zone = nf_ct_zone(ct);
 
 	pr_debug("trying to timeout ct or exp for tuple ");
 	nf_ct_dump_tuple(t);
 
+	zone = nf_ct_zone(ct);
 	h = nf_conntrack_find_get(net, zone, t);
 	if (h)  {
 		sibling = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index fc823fa..28c8b2b 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -140,6 +140,17 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 }
 #endif
 
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct)
+{
+	seq_printf(s, "zone=%u ", nf_ct_zone(ct)->id);
+}
+#else
+static inline void ct_show_zone(struct seq_file *s, const struct nf_conn *ct)
+{
+}
+#endif
+
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
 static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
 {
@@ -228,11 +239,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 #endif
 
 	ct_show_secctx(s, ct);
-
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	seq_printf(s, "zone=%u ", nf_ct_zone(ct));
-#endif
-
+	ct_show_zone(s, ct);
 	ct_show_delta_time(s, ct);
 
 	seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use));
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 4e0b478..65ebaf9 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -118,14 +118,15 @@ EXPORT_SYMBOL(nf_xfrm_me_harder);
 
 /* We keep an extra hash for each conntrack, for fast searching. */
 static inline unsigned int
-hash_by_src(const struct net *net, u16 zone,
+hash_by_src(const struct net *net,
+	    const struct nf_conntrack_zone *zone,
 	    const struct nf_conntrack_tuple *tuple)
 {
 	unsigned int hash;
 
 	/* Original src, to ensure we map it consistently if poss. */
 	hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
-		      tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd);
+		      tuple->dst.protonum ^ zone->id ^ nf_conntrack_hash_rnd);
 
 	return reciprocal_scale(hash, net->ct.nat_htable_size);
 }
@@ -185,7 +186,8 @@ same_src(const struct nf_conn *ct,
 
 /* Only called for SRC manip */
 static int
-find_appropriate_src(struct net *net, u16 zone,
+find_appropriate_src(struct net *net,
+		     const struct nf_conntrack_zone *zone,
 		     const struct nf_nat_l3proto *l3proto,
 		     const struct nf_nat_l4proto *l4proto,
 		     const struct nf_conntrack_tuple *tuple,
@@ -198,7 +200,7 @@ find_appropriate_src(struct net *net, u16 zone,
 
 	hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) {
 		ct = nat->ct;
-		if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
+		if (same_src(ct, tuple) && nf_ct_zone_equal(ct, zone)) {
 			/* Copy source part from reply tuple. */
 			nf_ct_invert_tuplepr(result,
 				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@@ -218,7 +220,8 @@ find_appropriate_src(struct net *net, u16 zone,
  * the ip with the lowest src-ip/dst-ip/proto usage.
  */
 static void
-find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
+find_best_ips_proto(const struct nf_conntrack_zone *zone,
+		    struct nf_conntrack_tuple *tuple,
 		    const struct nf_nat_range *range,
 		    const struct nf_conn *ct,
 		    enum nf_nat_manip_type maniptype)
@@ -258,7 +261,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
 	 */
 	j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3) / sizeof(u32),
 		   range->flags & NF_NAT_RANGE_PERSISTENT ?
-			0 : (__force u32)tuple->dst.u3.all[max] ^ zone);
+			0 : (__force u32)tuple->dst.u3.all[max] ^ zone->id);
 
 	full_range = false;
 	for (i = 0; i <= max; i++) {
@@ -297,10 +300,12 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 struct nf_conn *ct,
 		 enum nf_nat_manip_type maniptype)
 {
+	const struct nf_conntrack_zone *zone;
 	const struct nf_nat_l3proto *l3proto;
 	const struct nf_nat_l4proto *l4proto;
 	struct net *net = nf_ct_net(ct);
-	u16 zone = nf_ct_zone(ct);
+
+	zone = nf_ct_zone(ct);
 
 	rcu_read_lock();
 	l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 71f1e9f..58b2e84 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -17,10 +17,12 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_tcpudp.h>
 #include <linux/netfilter/xt_SYNPROXY.h>
+
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_synproxy.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 
 int synproxy_net_id;
 EXPORT_SYMBOL_GPL(synproxy_net_id);
@@ -352,7 +354,7 @@ static int __net_init synproxy_net_init(struct net *net)
 	struct nf_conn *ct;
 	int err = -ENOMEM;
 
-	ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL);
+	ct = nf_ct_tmpl_alloc(net, &nf_ct_zone_dflt, GFP_KERNEL);
 	if (IS_ERR(ct)) {
 		err = PTR_ERR(ct);
 		goto err1;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index c663003..29e2856 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -184,6 +184,7 @@ out:
 static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			  struct xt_ct_target_info_v1 *info)
 {
+	struct nf_conntrack_zone zone;
 	struct nf_conn *ct;
 	int ret = -EOPNOTSUPP;
 
@@ -201,7 +202,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	if (ret < 0)
 		goto err1;
 
-	ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL);
+	memset(&zone, 0, sizeof(zone));
+	zone.id = info->zone;
+
+	ct = nf_ct_tmpl_alloc(par->net, &zone, GFP_KERNEL);
 	ret = PTR_ERR(ct);
 	if (IS_ERR(ct))
 		goto err2;
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 29ba621..075d89d 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -134,7 +134,7 @@ static bool add_hlist(struct hlist_head *head,
 static unsigned int check_hlist(struct net *net,
 				struct hlist_head *head,
 				const struct nf_conntrack_tuple *tuple,
-				u16 zone,
+				const struct nf_conntrack_zone *zone,
 				bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
@@ -201,7 +201,7 @@ static unsigned int
 count_tree(struct net *net, struct rb_root *root,
 	   const struct nf_conntrack_tuple *tuple,
 	   const union nf_inet_addr *addr, const union nf_inet_addr *mask,
-	   u8 family, u16 zone)
+	   u8 family, const struct nf_conntrack_zone *zone)
 {
 	struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
 	struct rb_node **rbnode, *parent;
@@ -290,7 +290,8 @@ static int count_them(struct net *net,
 		      const struct nf_conntrack_tuple *tuple,
 		      const union nf_inet_addr *addr,
 		      const union nf_inet_addr *mask,
-		      u_int8_t family, u16 zone)
+		      u_int8_t family,
+		      const struct nf_conntrack_zone *zone)
 {
 	struct rb_root *root;
 	int count;
@@ -321,10 +322,10 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	union nf_inet_addr addr;
 	struct nf_conntrack_tuple tuple;
 	const struct nf_conntrack_tuple *tuple_ptr = &tuple;
+	const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	unsigned int connections;
-	u16 zone = NF_CT_DEFAULT_ZONE;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (ct != NULL) {
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index f2b5402..e67a1bd 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -37,6 +37,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
 	struct nf_conntrack_tuple tuple;
 	enum ip_conntrack_info ctinfo;
 	struct tcf_connmark_info *ca = a->priv;
+	struct nf_conntrack_zone zone;
 	struct nf_conn *c;
 	int proto;
 
@@ -70,7 +71,9 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
 			       proto, &tuple))
 		goto out;
 
-	thash = nf_conntrack_find_get(dev_net(skb->dev), ca->zone, &tuple);
+	zone.id = ca->zone;
+
+	thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple);
 	if (!thash)
 		goto out;
 
-- 
1.9.3

Re: [PATCH v4 1/3] netfilter: nf_conntrack: push zone object into functions

[Pablo Neira Ayuso]

On Sat, Aug 08, 2015 at 09:40:01PM +0200, Daniel Borkmann wrote:
> This patch replaces the zone id which is pushed down into functions
> with the actual zone object. It's a bigger one-time change, but
> needed for later on extending zones with a direction parameter, and
> thus decoupling this additional information from all call-sites.
> 
> No functional changes in this patch.
> 
> The default zone becomes a global const object, namely nf_ct_zone_dflt
> and will be returned directly in various cases, one being, when there's
> f.e. no zoning support.

Applied, thanks Daniel.

[PATCH v4 2/3] netfilter: nf_conntrack: add direction support for zones

[Daniel Borkmann]

This work adds a direction parameter to netfilter zones, so identity
separation can be performed only in original/reply or both directions
(default). This basically opens up the possibility of doing NAT with
conflicting IP address/port tuples from multiple, isolated tenants
on a host (e.g. from a netns) without requiring each tenant to NAT
twice resp. to use its own dedicated IP address to SNAT to, meaning
overlapping tuples can be made unique with the zone identifier in
original direction, where the NAT engine will then allocate a unique
tuple in the commonly shared default zone for the reply direction.
In some restricted, local DNAT cases, also port redirection could be
used for making the reply traffic unique w/o requiring SNAT.

The consensus we've reached and discussed at NFWS and since the initial
implementation [1] was to directly integrate the direction meta data
into the existing zones infrastructure, as opposed to the ct->mark
approach we proposed initially.

As we pass the nf_conntrack_zone object directly around, we don't have
to touch all call-sites, but only those, that contain equality checks
of zones. Thus, based on the current direction (original or reply),
we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID.
CT expectations are direction-agnostic entities when expectations are
being compared among themselves, so we can only use the identifier
in this case.

Note that zone identifiers can not be included into the hash mix
anymore as they don't contain a "stable" value that would be equal
for both directions at all times, f.e. if only zone->id would
unconditionally be xor'ed into the table slot hash, then replies won't
find the corresponding conntracking entry anymore.

If no particular direction is specified when configuring zones, the
behaviour is exactly as we expect currently (both directions).

Support has been added for the CT netlink interface as well as the
x_tables raw CT target, which both already offer existing interfaces
to user space for the configuration of zones.

Below a minimal, simplified collision example (script in [2]) with
netperf sessions:

  +--- tenant-1 ---+   mark := 1
  |    netperf     |--+
  +----------------+  |                CT zone := mark [ORIGINAL]
   [ip,sport] := X   +--------------+  +--- gateway ---+
                     | mark routing |--|     SNAT      |-- ... +
                     +--------------+  +---------------+       |
  +--- tenant-2 ---+  |                                     ~~~|~~~
  |    netperf     |--+                +-----------+           |
  +----------------+   mark := 2       | netserver |------ ... +
   [ip,sport] := X                     +-----------+
                                        [ip,port] := Y
On the gateway netns, example:

  iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL
  iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully

  iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark
  iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark

conntrack -L from gateway netns:

  netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns

  tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865
                           src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024
               [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0
                         zone=1 use=1 zone-dir=original

  tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865
                           src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555
               [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0
                         zone=2 use=1 zone-dir=original

  tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768
                        src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438
               [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0
                         zone=1 use=1 zone-dir=original

  tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206
                        src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889
               [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0
                         zone=2 use=2 zone-dir=original

Taking this further, test script in [2] creates 200 tenants and runs
original-tuple colliding netperf sessions each. A conntrack -L dump in
the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED
state as expected.

I also did run various other tests with some permutations of the script,
to mention some: SNAT in random/random-fully/persistent mode, no zones (no
overlaps), static zones (original, reply, both directions), etc.

  [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/
  [2] https://paste.fedoraproject.org/242835/65657871/

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/netfilter/nf_conntrack_zones.h         |  31 +++++-
 include/uapi/linux/netfilter/nfnetlink_conntrack.h |  16 +++
 include/uapi/linux/netfilter/xt_CT.h               |   6 +-
 net/ipv4/netfilter/nf_defrag_ipv4.c                |   8 +-
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c          |   8 +-
 net/netfilter/nf_conntrack_core.c                  |  53 ++++-----
 net/netfilter/nf_conntrack_expect.c                |   8 +-
 net/netfilter/nf_conntrack_netlink.c               | 124 +++++++++++++++++++--
 net/netfilter/nf_conntrack_standalone.c            |  15 ++-
 net/netfilter/nf_nat_core.c                        |  13 +--
 net/netfilter/xt_CT.c                              |  17 ++-
 net/sched/act_connmark.c                           |   1 +
 12 files changed, 243 insertions(+), 57 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h
index 0788bb0..3942ddf 100644
--- a/include/net/netfilter/nf_conntrack_zones.h
+++ b/include/net/netfilter/nf_conntrack_zones.h
@@ -1,10 +1,18 @@
 #ifndef _NF_CONNTRACK_ZONES_H
 #define _NF_CONNTRACK_ZONES_H
 
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+
 #define NF_CT_DEFAULT_ZONE_ID	0
 
+#define NF_CT_ZONE_DIR_ORIG	(1 << IP_CT_DIR_ORIGINAL)
+#define NF_CT_ZONE_DIR_REPL	(1 << IP_CT_DIR_REPLY)
+
+#define NF_CT_DEFAULT_ZONE_DIR	(NF_CT_ZONE_DIR_ORIG | NF_CT_ZONE_DIR_REPL)
+
 struct nf_conntrack_zone {
 	u16	id;
+	u16	dir;
 };
 
 extern const struct nf_conntrack_zone nf_ct_zone_dflt;
@@ -29,8 +37,29 @@ nf_ct_zone_tmpl(const struct nf_conn *tmpl)
 	return tmpl ? nf_ct_zone(tmpl) : &nf_ct_zone_dflt;
 }
 
+static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone,
+					  enum ip_conntrack_dir dir)
+{
+	return zone->dir & (1 << dir);
+}
+
+static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone,
+				enum ip_conntrack_dir dir)
+{
+	return nf_ct_zone_matches_dir(zone, dir) ?
+	       zone->id : NF_CT_DEFAULT_ZONE_ID;
+}
+
 static inline bool nf_ct_zone_equal(const struct nf_conn *a,
-				    const struct nf_conntrack_zone *b)
+				    const struct nf_conntrack_zone *b,
+				    enum ip_conntrack_dir dir)
+{
+	return nf_ct_zone_id(nf_ct_zone(a), dir) ==
+	       nf_ct_zone_id(b, dir);
+}
+
+static inline bool nf_ct_zone_equal_any(const struct nf_conn *a,
+					const struct nf_conntrack_zone *b)
 {
 	return nf_ct_zone(a)->id == b->id;
 }
diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index acad6c5..3bf4cb0 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -53,6 +53,7 @@ enum ctattr_type {
 	CTA_MARK_MASK,
 	CTA_LABELS,
 	CTA_LABELS_MASK,
+	CTA_TUPLE_ZONE,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -260,4 +261,19 @@ enum ctattr_expect_stats {
 };
 #define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1)
 
+enum ctattr_zone {
+	CTA_ZONE_UNSPEC,
+	CTA_ZONE_DIR,
+	__CTA_ZONE_MAX,
+};
+#define CTA_ZONE_MAX (__CTA_ZONE_MAX - 1)
+
+enum ctattr_zone_dir {
+	CTA_ZONE_DIR_UNSPEC,
+	CTA_ZONE_DIR_ORIG,
+	CTA_ZONE_DIR_REPL,
+	__CTA_ZONE_DIR_MAX
+};
+#define CTA_ZONE_DIR_MAX (__CTA_ZONE_DIR_MAX - 1)
+
 #endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/uapi/linux/netfilter/xt_CT.h b/include/uapi/linux/netfilter/xt_CT.h
index 5a688c1..452005f 100644
--- a/include/uapi/linux/netfilter/xt_CT.h
+++ b/include/uapi/linux/netfilter/xt_CT.h
@@ -6,7 +6,11 @@
 enum {
 	XT_CT_NOTRACK		= 1 << 0,
 	XT_CT_NOTRACK_ALIAS	= 1 << 1,
-	XT_CT_MASK		= XT_CT_NOTRACK | XT_CT_NOTRACK_ALIAS,
+	XT_CT_ZONE_DIR_ORIG	= 1 << 2,
+	XT_CT_ZONE_DIR_REPL	= 1 << 3,
+
+	XT_CT_MASK		= XT_CT_NOTRACK | XT_CT_NOTRACK_ALIAS |
+				  XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL,
 };
 
 struct xt_ct_target_info {
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 20fe8e6..9306ec4 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -45,8 +45,12 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 {
 	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	if (skb->nfct)
-		zone_id = nf_ct_zone((struct nf_conn *)skb->nfct)->id;
+	if (skb->nfct) {
+		enum ip_conntrack_info ctinfo;
+		const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+		zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+	}
 #endif
 	if (nf_bridge_in_prerouting(skb))
 		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 9d3de9b..6d9c0b3 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -35,8 +35,12 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 {
 	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	if (skb->nfct)
-		zone_id = nf_ct_zone((struct nf_conn *)skb->nfct)->id;
+	if (skb->nfct) {
+		enum ip_conntrack_info ctinfo;
+		const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+		zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+	}
 #endif
 	if (nf_bridge_in_prerouting(skb))
 		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0bb26e8..acc0622 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -126,8 +126,7 @@ EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
 unsigned int nf_conntrack_hash_rnd __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_rnd);
 
-static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_zone *zone)
+static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple)
 {
 	unsigned int n;
 
@@ -136,7 +135,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
 	 * three bytes manually.
 	 */
 	n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
-	return jhash2((u32 *)tuple, n, zone->id ^ nf_conntrack_hash_rnd ^
+	return jhash2((u32 *)tuple, n, nf_conntrack_hash_rnd ^
 		      (((__force __u16)tuple->dst.u.all << 16) |
 		      tuple->dst.protonum));
 }
@@ -152,17 +151,15 @@ static u32 hash_bucket(u32 hash, const struct net *net)
 }
 
 static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
-				  const struct nf_conntrack_zone *zone,
 				  unsigned int size)
 {
-	return __hash_bucket(hash_conntrack_raw(tuple, zone), size);
+	return __hash_bucket(hash_conntrack_raw(tuple), size);
 }
 
 static inline u_int32_t hash_conntrack(const struct net *net,
-				       const struct nf_conntrack_zone *zone,
 				       const struct nf_conntrack_tuple *tuple)
 {
-	return __hash_conntrack(tuple, zone, net->ct.htable_size);
+	return __hash_conntrack(tuple, net->ct.htable_size);
 }
 
 bool
@@ -312,6 +309,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 		if (!nf_ct_zone)
 			goto out_free;
 		nf_ct_zone->id = zone->id;
+		nf_ct_zone->dir = zone->dir;
 	}
 #endif
 	atomic_set(&tmpl->ct_general.use, 0);
@@ -376,20 +374,18 @@ destroy_conntrack(struct nf_conntrack *nfct)
 
 static void nf_ct_delete_from_lists(struct nf_conn *ct)
 {
-	const struct nf_conntrack_zone *zone;
 	struct net *net = nf_ct_net(ct);
 	unsigned int hash, reply_hash;
 	unsigned int sequence;
 
-	zone = nf_ct_zone(ct);
 	nf_ct_helper_destroy(ct);
 
 	local_bh_disable();
 	do {
 		sequence = read_seqcount_begin(&net->ct.generation);
-		hash = hash_conntrack(net, zone,
+		hash = hash_conntrack(net,
 				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-		reply_hash = hash_conntrack(net, zone,
+		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
 
@@ -446,7 +442,7 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
 	 * so we need to check that the conntrack is confirmed
 	 */
 	return nf_ct_tuple_equal(tuple, &h->tuple) &&
-	       nf_ct_zone_equal(ct, zone) &&
+	       nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&
 	       nf_ct_is_confirmed(ct);
 }
 
@@ -523,7 +519,7 @@ nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
 		      const struct nf_conntrack_tuple *tuple)
 {
 	return __nf_conntrack_find_get(net, zone, tuple,
-				       hash_conntrack_raw(tuple, zone));
+				       hash_conntrack_raw(tuple));
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
 
@@ -554,9 +550,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 	local_bh_disable();
 	do {
 		sequence = read_seqcount_begin(&net->ct.generation);
-		hash = hash_conntrack(net, zone,
+		hash = hash_conntrack(net,
 				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-		reply_hash = hash_conntrack(net, zone,
+		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
 
@@ -564,12 +560,14 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				      &h->tuple) &&
-		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
+				     NF_CT_DIRECTION(h)))
 			goto out;
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
-		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
+				     NF_CT_DIRECTION(h)))
 			goto out;
 
 	add_timer(&ct->timeout);
@@ -623,7 +621,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		/* reuse the hash saved before */
 		hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
 		hash = hash_bucket(hash, net);
-		reply_hash = hash_conntrack(net, zone,
+		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 
 	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
@@ -655,12 +653,14 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				      &h->tuple) &&
-		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
+				     NF_CT_DIRECTION(h)))
 			goto out;
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
-		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone))
+		    nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
+				     NF_CT_DIRECTION(h)))
 			goto out;
 
 	/* Timer relative to confirmation time, not original
@@ -720,7 +720,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 	unsigned int hash;
 
 	zone = nf_ct_zone(ignored_conntrack);
-	hash = hash_conntrack(net, zone, tuple);
+	hash = hash_conntrack(net, tuple);
 
 	/* Disable BHs the entire time since we need to disable them at
 	 * least once for the stats anyway.
@@ -730,7 +730,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (ct != ignored_conntrack &&
 		    nf_ct_tuple_equal(tuple, &h->tuple) &&
-		    nf_ct_zone_equal(ct, zone)) {
+		    nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h))) {
 			NF_CT_STAT_INC(net, found);
 			rcu_read_unlock_bh();
 			return 1;
@@ -830,7 +830,7 @@ __nf_conntrack_alloc(struct net *net,
 	if (unlikely(!nf_conntrack_hash_rnd)) {
 		init_nf_conntrack_hash_rnd();
 		/* recompute the hash as nf_conntrack_hash_rnd is initialized */
-		hash = hash_conntrack_raw(orig, zone);
+		hash = hash_conntrack_raw(orig);
 	}
 
 	/* We don't want any race condition at early drop stage */
@@ -875,6 +875,7 @@ __nf_conntrack_alloc(struct net *net,
 		if (!nf_ct_zone)
 			goto out_free;
 		nf_ct_zone->id = zone->id;
+		nf_ct_zone->dir = zone->dir;
 	}
 #endif
 	/* Because we use RCU lookups, we set ct_general.use to zero before
@@ -1053,7 +1054,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 
 	/* look for tuple match */
 	zone = nf_ct_zone_tmpl(tmpl);
-	hash = hash_conntrack_raw(&tuple, zone);
+	hash = hash_conntrack_raw(&tuple);
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
 		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
@@ -1306,6 +1307,7 @@ EXPORT_SYMBOL_GPL(__nf_ct_kill_acct);
 /* Built-in default zone used e.g. by modules. */
 const struct nf_conntrack_zone nf_ct_zone_dflt = {
 	.id	= NF_CT_DEFAULT_ZONE_ID,
+	.dir	= NF_CT_DEFAULT_ZONE_DIR,
 };
 EXPORT_SYMBOL_GPL(nf_ct_zone_dflt);
 
@@ -1617,8 +1619,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 					struct nf_conntrack_tuple_hash, hnnode);
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			hlist_nulls_del_rcu(&h->hnnode);
-			bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct),
-						  hashsize);
+			bucket = __hash_conntrack(&h->tuple, hashsize);
 			hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
 		}
 	}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 980db85..acf5c7b 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -101,7 +101,7 @@ __nf_ct_expect_find(struct net *net,
 	h = nf_ct_expect_dst_hash(tuple);
 	hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
 		if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-		    nf_ct_zone_equal(i->master, zone))
+		    nf_ct_zone_equal_any(i->master, zone))
 			return i;
 	}
 	return NULL;
@@ -143,7 +143,7 @@ nf_ct_find_expectation(struct net *net,
 	hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
 		if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
 		    nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-		    nf_ct_zone_equal(i->master, zone)) {
+		    nf_ct_zone_equal_any(i->master, zone)) {
 			exp = i;
 			break;
 		}
@@ -223,7 +223,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 	}
 
 	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
-	       nf_ct_zone_equal(a->master, nf_ct_zone(b->master));
+	       nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
 }
 
 static inline int expect_matches(const struct nf_conntrack_expect *a,
@@ -232,7 +232,7 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
 	return a->master == b->master && a->class == b->class &&
 	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
 	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
-	       nf_ct_zone_equal(a->master, nf_ct_zone(b->master));
+	       nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
 }
 
 /* Generally a bad idea to call this: could have matched already. */
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 95f7f01..65e9ebc 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -330,6 +330,58 @@ nla_put_failure:
 #define ctnetlink_dump_secctx(a, b) (0)
 #endif
 
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+static u16 ctnetlink_to_zone_dir(enum ctattr_zone_dir dir)
+{
+	switch (dir) {
+	case CTA_ZONE_DIR_ORIG:
+		return NF_CT_ZONE_DIR_ORIG;
+	case CTA_ZONE_DIR_REPL:
+		return NF_CT_ZONE_DIR_REPL;
+	default:
+		return NF_CT_DEFAULT_ZONE_DIR;
+	}
+}
+
+static enum ctattr_zone_dir ctnetlink_from_zone_dir(u16 dir)
+{
+	switch (dir) {
+	case NF_CT_ZONE_DIR_ORIG:
+		return CTA_ZONE_DIR_ORIG;
+	case NF_CT_ZONE_DIR_REPL:
+		return CTA_ZONE_DIR_REPL;
+	default:
+		return CTA_ZONE_DIR_UNSPEC;
+	}
+}
+
+static int ctnetlink_dump_tuple_zone(struct sk_buff *skb,
+				     const struct nf_conn *ct)
+{
+	const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
+	struct nlattr *nest_tuple_zone;
+
+	if (zone->dir == NF_CT_DEFAULT_ZONE_DIR)
+		return 0;
+
+	nest_tuple_zone = nla_nest_start(skb, CTA_TUPLE_ZONE | NLA_F_NESTED);
+	if (!nest_tuple_zone)
+		goto nla_put_failure;
+
+	if (nla_put_u8(skb, CTA_ZONE_DIR,
+		       ctnetlink_from_zone_dir(zone->dir)))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest_tuple_zone);
+
+	return 0;
+nla_put_failure:
+	return -1;
+}
+#else
+#define ctnetlink_dump_tuple_zone(a, b) (0)
+#endif
+
 #ifdef CONFIG_NF_CONNTRACK_LABELS
 static int ctnetlink_label_size(const struct nf_conn *ct)
 {
@@ -501,6 +553,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_mark(skb, ct) < 0 ||
 	    ctnetlink_dump_secctx(skb, ct) < 0 ||
+	    ctnetlink_dump_tuple_zone(skb, ct) < 0 ||
 	    ctnetlink_dump_labels(skb, ct) < 0 ||
 	    ctnetlink_dump_id(skb, ct) < 0 ||
 	    ctnetlink_dump_use(skb, ct) < 0 ||
@@ -563,6 +616,22 @@ ctnetlink_secctx_size(const struct nf_conn *ct)
 #endif
 }
 
+static inline int
+ctnetlink_tuple_zone_size(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
+
+	if (zone->dir == NF_CT_DEFAULT_ZONE_DIR)
+		return 0;
+
+	return nla_total_size(0) + /* CTA_TUPLE_ZONE */
+	       nla_total_size(sizeof(u_int8_t)); /* CTA_ZONE_DIR */
+#else
+	return 0;
+#endif
+}
+
 static inline size_t
 ctnetlink_timestamp_size(const struct nf_conn *ct)
 {
@@ -602,6 +671,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
 #endif
+	       + ctnetlink_tuple_zone_size(ct)
 	       + ctnetlink_proto_size(ct)
 	       + ctnetlink_label_size(ct)
 	       ;
@@ -677,6 +747,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 	    nla_put_be16(skb, CTA_ZONE, htons(zone->id)))
 		goto nla_put_failure;
 
+	if (ctnetlink_dump_tuple_zone(skb, ct) < 0)
+		goto nla_put_failure;
+
 	if (ctnetlink_dump_id(skb, ct) < 0)
 		goto nla_put_failure;
 
@@ -968,17 +1041,39 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 	return 0;
 }
 
+static const struct nla_policy zone_nla_policy[CTA_ZONE_MAX + 1] = {
+	[CTA_ZONE_DIR]		= { .type = NLA_U8 },
+};
+
 static int
-ctnetlink_parse_zone(const struct nlattr *attr,
+ctnetlink_parse_zone(const struct nlattr *attr_zone,
+		     const struct nlattr *attr_tuple_zone,
 		     struct nf_conntrack_zone *zone)
 {
-	zone->id = NF_CT_DEFAULT_ZONE_ID;
+	zone->id  = NF_CT_DEFAULT_ZONE_ID;
+	zone->dir = NF_CT_DEFAULT_ZONE_DIR;
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
-	if (attr)
-		zone->id = ntohs(nla_get_be16(attr));
+	if (attr_zone)
+		zone->id = ntohs(nla_get_be16(attr_zone));
+	if (attr_tuple_zone) {
+		struct nlattr *tb[CTA_ZONE_MAX + 1];
+		u8 ct_dir;
+		int err;
+
+		err = nla_parse_nested(tb, CTA_ZONE_MAX, attr_tuple_zone,
+				       zone_nla_policy);
+		if (err < 0)
+			return err;
+
+		if (!tb[CTA_ZONE_DIR])
+			return -EINVAL;
+
+		ct_dir = nla_get_u8(tb[CTA_ZONE_DIR]);
+		zone->dir = ctnetlink_to_zone_dir(ct_dir);
+	}
 #else
-	if (attr)
+	if (attr_zone || attr_tuple_zone)
 		return -EOPNOTSUPP;
 #endif
 	return 0;
@@ -1026,6 +1121,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 	[CTA_NAT_SEQ_ADJ_ORIG]  = { .type = NLA_NESTED },
 	[CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED },
 	[CTA_ZONE]		= { .type = NLA_U16 },
+	[CTA_TUPLE_ZONE]	= { .type = NLA_NESTED },
 	[CTA_MARK_MASK]		= { .type = NLA_U32 },
 	[CTA_LABELS]		= { .type = NLA_BINARY,
 				    .len = NF_CT_LABELS_MAX_SIZE },
@@ -1066,7 +1162,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_zone zone;
 	int err;
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_ZONE], cda[CTA_TUPLE_ZONE], &zone);
 	if (err < 0)
 		return err;
 
@@ -1138,7 +1234,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_ZONE], cda[CTA_TUPLE_ZONE], &zone);
 	if (err < 0)
 		return err;
 
@@ -1813,7 +1909,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_zone zone;
 	int err;
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_ZONE], cda[CTA_TUPLE_ZONE], &zone);
 	if (err < 0)
 		return err;
 
@@ -2090,6 +2186,7 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
 #endif
+	       + ctnetlink_tuple_zone_size(ct)
 	       + ctnetlink_proto_size(ct)
 	       ;
 }
@@ -2120,6 +2217,9 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct)
 	    nla_put_be16(skb, CTA_ZONE, htons(zone->id)))
 		goto nla_put_failure;
 
+	if (ctnetlink_dump_tuple_zone(skb, ct) < 0)
+		goto nla_put_failure;
+
 	if (ctnetlink_dump_id(skb, ct) < 0)
 		goto nla_put_failure;
 
@@ -2629,7 +2729,7 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], NULL, &zone);
 	if (err < 0)
 		return err;
 
@@ -2672,7 +2772,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 		}
 	}
 
-	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], NULL, &zone);
 	if (err < 0)
 		return err;
 
@@ -2743,7 +2843,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 
 	if (cda[CTA_EXPECT_TUPLE]) {
 		/* delete a single expect by tuple */
-		err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+		err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], NULL, &zone);
 		if (err < 0)
 			return err;
 
@@ -3025,7 +3125,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 	    || !cda[CTA_EXPECT_MASTER])
 		return -EINVAL;
 
-	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+	err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], NULL, &zone);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 28c8b2b..5d81b99 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -143,7 +143,20 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct)
 {
-	seq_printf(s, "zone=%u ", nf_ct_zone(ct)->id);
+	const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
+
+	seq_printf(s, "zone=%u ", zone->id);
+
+	switch (zone->dir) {
+	case NF_CT_ZONE_DIR_ORIG:
+		seq_puts(s, "zone-dir=ORIGINAL ");
+		break;
+	case NF_CT_ZONE_DIR_REPL:
+		seq_puts(s, "zone-dir=REPLY ");
+		break;
+	default:
+		break;
+	}
 }
 #else
 static inline void ct_show_zone(struct seq_file *s, const struct nf_conn *ct)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 65ebaf9..5113dfd 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -118,15 +118,13 @@ EXPORT_SYMBOL(nf_xfrm_me_harder);
 
 /* We keep an extra hash for each conntrack, for fast searching. */
 static inline unsigned int
-hash_by_src(const struct net *net,
-	    const struct nf_conntrack_zone *zone,
-	    const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple)
 {
 	unsigned int hash;
 
 	/* Original src, to ensure we map it consistently if poss. */
 	hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
-		      tuple->dst.protonum ^ zone->id ^ nf_conntrack_hash_rnd);
+		      tuple->dst.protonum ^ nf_conntrack_hash_rnd);
 
 	return reciprocal_scale(hash, net->ct.nat_htable_size);
 }
@@ -194,13 +192,14 @@ find_appropriate_src(struct net *net,
 		     struct nf_conntrack_tuple *result,
 		     const struct nf_nat_range *range)
 {
-	unsigned int h = hash_by_src(net, zone, tuple);
+	unsigned int h = hash_by_src(net, tuple);
 	const struct nf_conn_nat *nat;
 	const struct nf_conn *ct;
 
 	hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) {
 		ct = nat->ct;
-		if (same_src(ct, tuple) && nf_ct_zone_equal(ct, zone)) {
+		if (same_src(ct, tuple) &&
+		    nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) {
 			/* Copy source part from reply tuple. */
 			nf_ct_invert_tuplepr(result,
 				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@@ -425,7 +424,7 @@ nf_nat_setup_info(struct nf_conn *ct,
 	if (maniptype == NF_NAT_MANIP_SRC) {
 		unsigned int srchash;
 
-		srchash = hash_by_src(net, nf_ct_zone(ct),
+		srchash = hash_by_src(net,
 				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 		spin_lock_bh(&nf_nat_lock);
 		/* nf_conntrack_alter_reply might re-allocate extension aera */
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 29e2856..536cb67 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -181,6 +181,19 @@ out:
 #endif
 }
 
+static u16 xt_ct_flags_to_dir(const struct xt_ct_target_info_v1 *info)
+{
+	switch (info->flags & (XT_CT_ZONE_DIR_ORIG |
+			       XT_CT_ZONE_DIR_REPL)) {
+	case XT_CT_ZONE_DIR_ORIG:
+		return NF_CT_ZONE_DIR_ORIG;
+	case XT_CT_ZONE_DIR_REPL:
+		return NF_CT_ZONE_DIR_REPL;
+	default:
+		return NF_CT_DEFAULT_ZONE_DIR;
+	}
+}
+
 static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			  struct xt_ct_target_info_v1 *info)
 {
@@ -194,7 +207,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	}
 
 #ifndef CONFIG_NF_CONNTRACK_ZONES
-	if (info->zone)
+	if (info->zone || info->flags & (XT_CT_ZONE_DIR_ORIG |
+					 XT_CT_ZONE_DIR_REPL))
 		goto err1;
 #endif
 
@@ -204,6 +218,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 
 	memset(&zone, 0, sizeof(zone));
 	zone.id = info->zone;
+	zone.dir = xt_ct_flags_to_dir(info);
 
 	ct = nf_ct_tmpl_alloc(par->net, &zone, GFP_KERNEL);
 	ret = PTR_ERR(ct);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index e67a1bd..5019a47 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -72,6 +72,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
 		goto out;
 
 	zone.id = ca->zone;
+	zone.dir = NF_CT_DEFAULT_ZONE_DIR;
 
 	thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple);
 	if (!thash)
-- 
1.9.3

Re: [PATCH v4 2/3] netfilter: nf_conntrack: add direction support for zones

[Pablo Neira Ayuso]

Hi Daniel,

I have applied 1/3 so you don't need to resend, but I still need one
more change in this patch, see below.

On Sat, Aug 08, 2015 at 09:40:02PM +0200, Daniel Borkmann wrote:
> diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
> index acad6c5..3bf4cb0 100644
> --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
> +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
> @@ -53,6 +53,7 @@ enum ctattr_type {
>  	CTA_MARK_MASK,
>  	CTA_LABELS,
>  	CTA_LABELS_MASK,
> +	CTA_TUPLE_ZONE,

I remember to have suggested to place this in ctattr_tuple:

http://www.spinics.net/lists/netfilter-devel/msg37593.html

The zone is part of the tuple in an optional fashion, so it should
appear there. The direction is already implicit based on
CTA_TUPLE_ORIG or CTA_TUPLE_REPLY.

>  	__CTA_MAX
>  };
>  #define CTA_MAX (__CTA_MAX - 1)
> @@ -260,4 +261,19 @@ enum ctattr_expect_stats {
>  };
>  #define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1)
>  
> +enum ctattr_zone {
> +	CTA_ZONE_UNSPEC,
> +	CTA_ZONE_DIR,
> +	__CTA_ZONE_MAX,
> +};
> +#define CTA_ZONE_MAX (__CTA_ZONE_MAX - 1)
> +
> +enum ctattr_zone_dir {
> +	CTA_ZONE_DIR_UNSPEC,
> +	CTA_ZONE_DIR_ORIG,
> +	CTA_ZONE_DIR_REPL,
> +	__CTA_ZONE_DIR_MAX
> +};
> +#define CTA_ZONE_DIR_MAX (__CTA_ZONE_DIR_MAX - 1)

With the change above we can skip this CTA_ZONE_DIR.

> +
>  #endif /* _IPCONNTRACK_NETLINK_H */
[...]
> diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
> index 28c8b2b..5d81b99 100644
> --- a/net/netfilter/nf_conntrack_standalone.c
> +++ b/net/netfilter/nf_conntrack_standalone.c
> @@ -143,7 +143,20 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
>  #ifdef CONFIG_NF_CONNTRACK_ZONES
>  static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct)
>  {
> -	seq_printf(s, "zone=%u ", nf_ct_zone(ct)->id);
> +	const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
> +
> +	seq_printf(s, "zone=%u ", zone->id);
> +
> +	switch (zone->dir) {
> +	case NF_CT_ZONE_DIR_ORIG:
> +		seq_puts(s, "zone-dir=ORIGINAL ");
> +		break;
> +	case NF_CT_ZONE_DIR_REPL:
> +		seq_puts(s, "zone-dir=REPLY ");
> +		break;

I'd suggest the output shows the zone on the corresponding tuple, eg.
in case it only applies to the original tuple:

udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone=1 \
               src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1

We have a more compact output IMO.

Please, don't forget that you also have to update
libnetfilter_conntrack and conntrack to get this feature available
from there. I'll take this patchset to the kernel so you have the time
to update the userspace side later on without blocking this further.

Thanks.

Re: [PATCH v4 2/3] netfilter: nf_conntrack: add direction support for zones

[Daniel Borkmann]

Hi Pablo,

thanks a lot for applying patch 1/3!

On 08/12/2015 07:48 PM, Pablo Neira Ayuso wrote:
...
> On Sat, Aug 08, 2015 at 09:40:02PM +0200, Daniel Borkmann wrote:
>> diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
>> index acad6c5..3bf4cb0 100644
>> --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
>> +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
>> @@ -53,6 +53,7 @@ enum ctattr_type {
>>   	CTA_MARK_MASK,
>>   	CTA_LABELS,
>>   	CTA_LABELS_MASK,
>> +	CTA_TUPLE_ZONE,
>
> I remember to have suggested to place this in ctattr_tuple:
>
> http://www.spinics.net/lists/netfilter-devel/msg37593.html
>
> The zone is part of the tuple in an optional fashion, so it should
> appear there. The direction is already implicit based on
> CTA_TUPLE_ORIG or CTA_TUPLE_REPLY.

Sorry, seems like I totally misunderstood your email. :/

I thought to place a CTA_ZONE_DIR attribute into a new nested CTA_TUPLE_ZONE
container, where also possible future meta data can be placed there.

Thus, we'd have CTA_ZONE as the id itself and CTA_TUPLE_ZONE with additional
optional data related to the zone, but it seems this was your /initial/
suggestion (modulo the attribute name). I actually find this approach quite
reasonable, probably that's why my mind stuck to it too much. ;)

But you are basically saying to add the nested CTA_TUPLE_ZONE container here,
that is part of a nested CTA_TUPLE_ORIG and/or CTA_TUPLE_REPLY attribute ...

enum ctattr_tuple {
	CTA_TUPLE_UNSPEC,
	CTA_TUPLE_IP,
	CTA_TUPLE_PROTO,
	CTA_TUPLE_ZONE,  <---
	__CTA_TUPLE_MAX
};

... where CTA_TUPLE_ZONE would be a container for further attributes, say
CTA_TUPLE_ZONE_ID, which is then the actual NLA_U16 zone id, right?

So, we'd have a zone id spread in 3 possible places, and additional (future)
meta data spread around in 2 possible places, hmm ... Okay, lets say, we'd
add future attribute X and Y to zones. Now, if I want a zone only in ORIG
dir or only in REPLY dir, that works fine from ctnetlink perspective, even
with your idea that there could be two different non-default zones entirely.

But, lets say I just want to use a traditional zones config (as in: nowadays)
and have my tuple for /one/ particular zone id that is the same in /both/
directions. That would mean I have to duplicate my parameters X and Y across
CTA_TUPLE_ORIG and CTA_TUPLE_REPLY, right? Or, we'd add a third attribute
set (as in: CTA_ZONE_INFO) only for the single zone in both directions?

So far I find the current approach a bit cleaner to be honest (I can, of
course, still change the CTA_TUPLE_ZONE back into CTA_ZONE_INFO name) ...
but when the time comes where someone really should need two /non-default/
zones for a single tuple, don't we need a global setting as in this patch
here anyway (due to reasons above)? (I'm fine either way, I'm just asking on
how we want to handle this in an ideal/clean way.)

...
> I'd suggest the output shows the zone on the corresponding tuple, eg.
> in case it only applies to the original tuple:
>
> udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone=1 \
>                 src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1
>
> We have a more compact output IMO.

Okay, that's fine by me. It would mean we'd see zone=1 twice in case a
direction was not specified (thus, both directions apply), but I think
that should be totally okay for the stand-alone interface (and in future
conntrack -L).

> Please, don't forget that you also have to update
> libnetfilter_conntrack and conntrack to get this feature available
> from there. I'll take this patchset to the kernel so you have the time
> to update the userspace side later on without blocking this further.

Thanks, yes, after Plumbers I'll add proper support for both.

For testing that the netlink interface works, I had a local hack, but
will get properly ready after the kernel and iptables patches. Was planning
to do this anyway.

Thanks again,
Daniel

Re: [PATCH v4 2/3] netfilter: nf_conntrack: add direction support for zones

[Pablo Neira Ayuso]

On Wed, Aug 12, 2015 at 10:05:11PM +0200, Daniel Borkmann wrote:
[...]
> But you are basically saying to add the nested CTA_TUPLE_ZONE container here,
> that is part of a nested CTA_TUPLE_ORIG and/or CTA_TUPLE_REPLY attribute ...
> 
> enum ctattr_tuple {
> 	CTA_TUPLE_UNSPEC,
> 	CTA_TUPLE_IP,
> 	CTA_TUPLE_PROTO,
> 	CTA_TUPLE_ZONE,  <---
> 	__CTA_TUPLE_MAX
> };

Right.

> ... where CTA_TUPLE_ZONE would be a container for further attributes, say
> CTA_TUPLE_ZONE_ID, which is then the actual NLA_U16 zone id, right?

Question is if we really need a nested attribute or not here, we've
been discussing this before but future requirements are not clear. I
think it would be good to keep those in mind to enhance this the right
way.

So, going back to this, I think the idea is to add new commands to
ctnetlink to create zone objects with specific settings at some point,
so we get three new enum cntl_msg_types.

        IPCTNL_MSG_CT_NEW_ZONE
        IPCTNL_MSG_CT_GET_ZONE
        IPCTNL_MSG_CT_DEL_ZONE

These new messages allow us to create/delete/retrieve custom zones
with specific settings, each zone can be represented by:

enum ctattr_zone {
        CTA_ZONE_UNSPEC,
        CTA_ZONE_ID,
        CTA_ZONE_CONFIG,
        __CTA_ZONE_MAX
};

The CTA_ZONE_CONFIG is a nested attribute with specific configuration
for this zone, eg. the maximum number of connections.

The custom zone can be used from the CT target, so we not only set a
zone ID to the conntrack but we also can attach configurations.

There's a problem though: By the time -j CT --zone X is loaded, the
zone ID may not exists, so we need a new --zone-template X to
explicitly refer to zones that are created via ctnetlink.

> So, we'd have a zone id spread in 3 possible places, and additional (future)
> meta data spread around in 2 possible places, hmm ... Okay, lets say, we'd
> add future attribute X and Y to zones. Now, if I want a zone only in ORIG
> dir or only in REPLY dir, that works fine from ctnetlink perspective, even
> with your idea that there could be two different non-default zones entirely.

If we ever get connection limiting per zone as Thomas suggested during
NFWS, I think we may well have two different non-default zones, what
it comes to my mind is a simple scenario with two uplinks, each uplink
becomes a zone with different connection limits.

> But, lets say I just want to use a traditional zones config (as in: nowadays)
> and have my tuple for /one/ particular zone id that is the same in /both/
> directions. That would mean I have to duplicate my parameters X and Y across
> CTA_TUPLE_ORIG and CTA_TUPLE_REPLY, right? Or, we'd add a third attribute
> set (as in: CTA_ZONE_INFO) only for the single zone in both directions?

CTA_ZONE can still be used to set a zone for both directions, we can
get rid of that. The new CTA_TUPLE_ZONE allows you to set the zone at
per-tuple level. We only have to be careful on how to interpret if the
user sends us two of them that have overlapping semantics.

> So far I find the current approach a bit cleaner to be honest (I can, of
> course, still change the CTA_TUPLE_ZONE back into CTA_ZONE_INFO name) ...
> but when the time comes where someone really should need two /non-default/
> zones for a single tuple, don't we need a global setting as in this patch
> here anyway (due to reasons above)? (I'm fine either way, I'm just asking on
> how we want to handle this in an ideal/clean way.)
> 
> ...
> >I'd suggest the output shows the zone on the corresponding tuple, eg.
> >in case it only applies to the original tuple:
> >
> >udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone=1 \
> >                src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1
> >
> >We have a more compact output IMO.
> 
> Okay, that's fine by me. It would mean we'd see zone=1 twice in case a
> direction was not specified (thus, both directions apply), but I think
> that should be totally okay for the stand-alone interface (and in future
> conntrack -L).

I think we can leave it the same way it looks now when the zone
applies to two directions, but looking at this output now this may
look ambiguous when the zone is in the reply tuple, so I think we have
to add different tags, ie.

1) When the zone is used from the original tuple:

udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone-orig=1 \
               src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1

2) When used from the reply tuple:

udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 \
               src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 zone-reply=X [ASSURED] mark=0 use=1

3) When used in both (existing output):

udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 \
               src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 zone=1 use=1

> >Please, don't forget that you also have to update
> >libnetfilter_conntrack and conntrack to get this feature available
> >from there. I'll take this patchset to the kernel so you have the time
> >to update the userspace side later on without blocking this further.
> 
> Thanks, yes, after Plumbers I'll add proper support for both.
> 
> For testing that the netlink interface works, I had a local hack, but
> will get properly ready after the kernel and iptables patches. Was planning
> to do this anyway.

Thanks, the userspace chunks are also good to have, many people rely
on the ctnetlink interface already and the userspace utilities to
interact with it.

Re: [PATCH v4 2/3] netfilter: nf_conntrack: add direction support for zones

[Daniel Borkmann]

On 08/13/2015 11:50 AM, Pablo Neira Ayuso wrote:
> On Wed, Aug 12, 2015 at 10:05:11PM +0200, Daniel Borkmann wrote:
> [...]
>> But you are basically saying to add the nested CTA_TUPLE_ZONE container here,
>> that is part of a nested CTA_TUPLE_ORIG and/or CTA_TUPLE_REPLY attribute ...
>>
>> enum ctattr_tuple {
>> 	CTA_TUPLE_UNSPEC,
>> 	CTA_TUPLE_IP,
>> 	CTA_TUPLE_PROTO,
>> 	CTA_TUPLE_ZONE,  <---
>> 	__CTA_TUPLE_MAX
>> };
>
> Right.
>
>> ... where CTA_TUPLE_ZONE would be a container for further attributes, say
>> CTA_TUPLE_ZONE_ID, which is then the actual NLA_U16 zone id, right?
>
> Question is if we really need a nested attribute or not here, we've
> been discussing this before but future requirements are not clear. I
> think it would be good to keep those in mind to enhance this the right
> way.
>
> So, going back to this, I think the idea is to add new commands to
> ctnetlink to create zone objects with specific settings at some point,
> so we get three new enum cntl_msg_types.
>
>          IPCTNL_MSG_CT_NEW_ZONE
>          IPCTNL_MSG_CT_GET_ZONE
>          IPCTNL_MSG_CT_DEL_ZONE
>
> These new messages allow us to create/delete/retrieve custom zones
> with specific settings, each zone can be represented by:
>
> enum ctattr_zone {
>          CTA_ZONE_UNSPEC,
>          CTA_ZONE_ID,
>          CTA_ZONE_CONFIG,
>          __CTA_ZONE_MAX
> };
>
> The CTA_ZONE_CONFIG is a nested attribute with specific configuration
> for this zone, eg. the maximum number of connections.
>
> The custom zone can be used from the CT target, so we not only set a
> zone ID to the conntrack but we also can attach configurations.
>
> There's a problem though: By the time -j CT --zone X is loaded, the
> zone ID may not exists, so we need a new --zone-template X to
> explicitly refer to zones that are created via ctnetlink.

Yes, right. So the above makes sense to me. You would create zones with a
specific configuration attached over a separate interface.

And then, you could use the CTA_ZONE or CTA_TUPLE_ZONE (both NLA_U16 attrs
that represent the zone id) to look up a specific zone to be used. As a result,
that would mean, it might be best to have CTA_TUPLE_ZONE as NLA_U16. Seems a
clean way forward to me.

>> So, we'd have a zone id spread in 3 possible places, and additional (future)
>> meta data spread around in 2 possible places, hmm ... Okay, lets say, we'd
>> add future attribute X and Y to zones. Now, if I want a zone only in ORIG
>> dir or only in REPLY dir, that works fine from ctnetlink perspective, even
>> with your idea that there could be two different non-default zones entirely.
>
> If we ever get connection limiting per zone as Thomas suggested during
> NFWS, I think we may well have two different non-default zones, what
> it comes to my mind is a simple scenario with two uplinks, each uplink
> becomes a zone with different connection limits.
>
>> But, lets say I just want to use a traditional zones config (as in: nowadays)
>> and have my tuple for /one/ particular zone id that is the same in /both/
>> directions. That would mean I have to duplicate my parameters X and Y across
>> CTA_TUPLE_ORIG and CTA_TUPLE_REPLY, right? Or, we'd add a third attribute
>> set (as in: CTA_ZONE_INFO) only for the single zone in both directions?
>
> CTA_ZONE can still be used to set a zone for both directions, we can
> get rid of that. The new CTA_TUPLE_ZONE allows you to set the zone at
> per-tuple level. We only have to be careful on how to interpret if the
> user sends us two of them that have overlapping semantics.

Right, we'd need to reject conflicting configurations, of course.

>> So far I find the current approach a bit cleaner to be honest (I can, of
>> course, still change the CTA_TUPLE_ZONE back into CTA_ZONE_INFO name) ...
>> but when the time comes where someone really should need two /non-default/
>> zones for a single tuple, don't we need a global setting as in this patch
>> here anyway (due to reasons above)? (I'm fine either way, I'm just asking on
>> how we want to handle this in an ideal/clean way.)
>>
>> ...
>>> I'd suggest the output shows the zone on the corresponding tuple, eg.
>>> in case it only applies to the original tuple:
>>>
>>> udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone=1 \
>>>                 src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1
>>>
>>> We have a more compact output IMO.
>>
>> Okay, that's fine by me. It would mean we'd see zone=1 twice in case a
>> direction was not specified (thus, both directions apply), but I think
>> that should be totally okay for the stand-alone interface (and in future
>> conntrack -L).
>
> I think we can leave it the same way it looks now when the zone
> applies to two directions, but looking at this output now this may
> look ambiguous when the zone is in the reply tuple, so I think we have
> to add different tags, ie.
>
> 1) When the zone is used from the original tuple:
>
> udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 zone-orig=1 \
>                 src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 use=1
>
> 2) When used from the reply tuple:
>
> udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 \
>                 src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 zone-reply=X [ASSURED] mark=0 use=1
>
> 3) When used in both (existing output):
>
> udp      17 29 src=192.168.2.195 dst=192.168.2.1 sport=40446 dport=53 \
>                 src=192.168.2.1 dst=192.168.2.195 sport=53 dport=40446 [ASSURED] mark=0 zone=1 use=1

Agreed, sounds good. Will change it into this representation.

Thanks Pablo!

Best,
Daniel

[PATCH v4 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping

[Daniel Borkmann]

This work adds the possibility of deriving the zone id from the skb->mark
field in a scalable manner. This allows for having only a single template
serving hundreds/thousands of different zones, for example, instead of the
need to have one match for each zone as an extra CT jump target.

Note that we'd need to have this information attached to the template as at
the time when we're trying to lookup a possible ct object, we already need
to know zone information for a possible match when going into
__nf_conntrack_find_get(). This work provides a minimal implementation for
a possible mapping.

In order to not add/expose an extra ct->status bit, the zone structure has
been extended to carry a flag for deriving the mark.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/netfilter/nf_conntrack_zones.h     | 45 +++++++++++++++++++++--
 include/uapi/linux/netfilter/xt_CT.h           |  4 ++-
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c   |  3 +-
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c |  4 ++-
 net/netfilter/nf_conntrack_core.c              | 50 +++++++++-----------------
 net/netfilter/nf_conntrack_netlink.c           |  4 +--
 net/netfilter/xt_CT.c                          |  5 ++-
 7 files changed, 72 insertions(+), 43 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h
index 3942ddf..5316c7b 100644
--- a/include/net/netfilter/nf_conntrack_zones.h
+++ b/include/net/netfilter/nf_conntrack_zones.h
@@ -10,9 +10,12 @@
 
 #define NF_CT_DEFAULT_ZONE_DIR	(NF_CT_ZONE_DIR_ORIG | NF_CT_ZONE_DIR_REPL)
 
+#define NF_CT_FLAG_MARK		1
+
 struct nf_conntrack_zone {
 	u16	id;
-	u16	dir;
+	u8	flags;
+	u8	dir;
 };
 
 extern const struct nf_conntrack_zone nf_ct_zone_dflt;
@@ -32,9 +35,45 @@ nf_ct_zone(const struct nf_conn *ct)
 }
 
 static inline const struct nf_conntrack_zone *
-nf_ct_zone_tmpl(const struct nf_conn *tmpl)
+nf_ct_zone_init(struct nf_conntrack_zone *zone, u16 id, u8 dir, u8 flags)
+{
+	zone->id = id;
+	zone->flags = flags;
+	zone->dir = dir;
+
+	return zone;
+}
+
+static inline const struct nf_conntrack_zone *
+nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb,
+		struct nf_conntrack_zone *tmp)
+{
+	const struct nf_conntrack_zone *zone;
+
+	if (!tmpl)
+		return &nf_ct_zone_dflt;
+
+	zone = nf_ct_zone(tmpl);
+	if (zone->flags & NF_CT_FLAG_MARK)
+		zone = nf_ct_zone_init(tmp, skb->mark, zone->dir, 0);
+
+	return zone;
+}
+
+static inline int nf_ct_zone_add(struct nf_conn *ct, gfp_t flags,
+				 const struct nf_conntrack_zone *info)
 {
-	return tmpl ? nf_ct_zone(tmpl) : &nf_ct_zone_dflt;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	struct nf_conntrack_zone *nf_ct_zone;
+
+	nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, flags);
+	if (!nf_ct_zone)
+		return -ENOMEM;
+
+	nf_ct_zone_init(nf_ct_zone, info->id, info->dir,
+			info->flags);
+#endif
+	return 0;
 }
 
 static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone,
diff --git a/include/uapi/linux/netfilter/xt_CT.h b/include/uapi/linux/netfilter/xt_CT.h
index 452005f..9e52041 100644
--- a/include/uapi/linux/netfilter/xt_CT.h
+++ b/include/uapi/linux/netfilter/xt_CT.h
@@ -8,9 +8,11 @@ enum {
 	XT_CT_NOTRACK_ALIAS	= 1 << 1,
 	XT_CT_ZONE_DIR_ORIG	= 1 << 2,
 	XT_CT_ZONE_DIR_REPL	= 1 << 3,
+	XT_CT_ZONE_MARK		= 1 << 4,
 
 	XT_CT_MASK		= XT_CT_NOTRACK | XT_CT_NOTRACK_ALIAS |
-				  XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL,
+				  XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL |
+				  XT_CT_ZONE_MARK,
 };
 
 struct xt_ct_target_info {
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 8a2f41c..cdde3ec 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -135,9 +135,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	const struct nf_conntrack_l4proto *innerproto;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_zone *zone;
+	struct nf_conntrack_zone tmp;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
-	zone = nf_ct_zone_tmpl(tmpl);
+	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
 	if (!nf_ct_get_tuplepr(skb,
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 2029141..0e6fae1 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -150,6 +150,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_tuple intuple, origtuple;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_l4proto *inproto;
+	struct nf_conntrack_zone tmp;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
 
@@ -176,7 +177,8 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 
 	*ctinfo = IP_CT_RELATED;
 
-	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl), &intuple);
+	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
+				  &intuple);
 	if (!h) {
 		pr_debug("icmpv6_error: no match\n");
 		return -NF_ACCEPT;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index acc0622..48521d6 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -301,25 +301,15 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 	tmpl->status = IPS_TEMPLATE;
 	write_pnet(&tmpl->ct_net, net);
 
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	if (zone) {
-		struct nf_conntrack_zone *nf_ct_zone;
-
-		nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC);
-		if (!nf_ct_zone)
-			goto out_free;
-		nf_ct_zone->id = zone->id;
-		nf_ct_zone->dir = zone->dir;
-	}
-#endif
+	if (nf_ct_zone_add(tmpl, flags, zone) < 0)
+		goto out_free;
+
 	atomic_set(&tmpl->ct_general.use, 0);
 
 	return tmpl;
-#ifdef CONFIG_NF_CONNTRACK_ZONES
 out_free:
 	kfree(tmpl);
 	return NULL;
-#endif
 }
 EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
 
@@ -850,10 +840,9 @@ __nf_conntrack_alloc(struct net *net,
 	 * SLAB_DESTROY_BY_RCU.
 	 */
 	ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp);
-	if (ct == NULL) {
-		atomic_dec(&net->ct.count);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (ct == NULL)
+		goto out;
+
 	spin_lock_init(&ct->lock);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
@@ -867,29 +856,20 @@ __nf_conntrack_alloc(struct net *net,
 	memset(&ct->__nfct_init_offset[0], 0,
 	       offsetof(struct nf_conn, proto) -
 	       offsetof(struct nf_conn, __nfct_init_offset[0]));
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	if (zone) {
-		struct nf_conntrack_zone *nf_ct_zone;
-
-		nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC);
-		if (!nf_ct_zone)
-			goto out_free;
-		nf_ct_zone->id = zone->id;
-		nf_ct_zone->dir = zone->dir;
-	}
-#endif
+
+	if (zone && nf_ct_zone_add(ct, GFP_ATOMIC, zone) < 0)
+		goto out_free;
+
 	/* Because we use RCU lookups, we set ct_general.use to zero before
 	 * this is inserted in any list.
 	 */
 	atomic_set(&ct->ct_general.use, 0);
 	return ct;
-
-#ifdef CONFIG_NF_CONNTRACK_ZONES
 out_free:
-	atomic_dec(&net->ct.count);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
+out:
+	atomic_dec(&net->ct.count);
 	return ERR_PTR(-ENOMEM);
-#endif
 }
 
 struct nf_conn *nf_conntrack_alloc(struct net *net,
@@ -937,6 +917,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_expect *exp = NULL;
 	const struct nf_conntrack_zone *zone;
 	struct nf_conn_timeout *timeout_ext;
+	struct nf_conntrack_zone tmp;
 	unsigned int *timeouts;
 
 	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
@@ -944,7 +925,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 		return NULL;
 	}
 
-	zone = nf_ct_zone_tmpl(tmpl);
+	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
 				  hash);
 	if (IS_ERR(ct))
@@ -1042,6 +1023,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
+	struct nf_conntrack_zone tmp;
 	struct nf_conn *ct;
 	u32 hash;
 
@@ -1053,7 +1035,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	}
 
 	/* look for tuple match */
-	zone = nf_ct_zone_tmpl(tmpl);
+	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 	hash = hash_conntrack_raw(&tuple);
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 65e9ebc..a4150f2 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1050,8 +1050,8 @@ ctnetlink_parse_zone(const struct nlattr *attr_zone,
 		     const struct nlattr *attr_tuple_zone,
 		     struct nf_conntrack_zone *zone)
 {
-	zone->id  = NF_CT_DEFAULT_ZONE_ID;
-	zone->dir = NF_CT_DEFAULT_ZONE_DIR;
+	nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID,
+			NF_CT_DEFAULT_ZONE_DIR, 0);
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	if (attr_zone)
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 536cb67..3465098 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -208,7 +208,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 
 #ifndef CONFIG_NF_CONNTRACK_ZONES
 	if (info->zone || info->flags & (XT_CT_ZONE_DIR_ORIG |
-					 XT_CT_ZONE_DIR_REPL))
+					 XT_CT_ZONE_DIR_REPL |
+					 XT_CT_ZONE_MARK))
 		goto err1;
 #endif
 
@@ -219,6 +220,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	memset(&zone, 0, sizeof(zone));
 	zone.id = info->zone;
 	zone.dir = xt_ct_flags_to_dir(info);
+	if (info->flags & XT_CT_ZONE_MARK)
+		zone.flags |= NF_CT_FLAG_MARK;
 
 	ct = nf_ct_tmpl_alloc(par->net, &zone, GFP_KERNEL);
 	ret = PTR_ERR(ct);
-- 
1.9.3