netfilter: nf_conntrack: add direction support for zones

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 dump 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 zone-orig=1
                           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 use=1

  tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2
                           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 use=1

  tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1
                        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 use=1

  tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2
                        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 use=2

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>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 27 insertions, 26 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0bb26e84f849..acc06222ce6a 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]);
 		}
 	}