netfilter: nf_conntrack: add support for "conntrack zones"

Normally, each connection needs a unique identity. Conntrack zones allow
to specify a numerical zone using the CT target, connections in different
zones can use the same identity.

Example:

iptables -t raw -A PREROUTING -i veth0 -j CT --zone 1
iptables -t raw -A OUTPUT -o veth1 -j CT --zone 1

Signed-off-by: Patrick McHardy <kaber@trash.net>

5 files changed, 32 insertions, 18 deletions

diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index d1ea38a7c490..2bb1f87051c4 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -22,6 +22,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/nf_nat_helper.h>
@@ -266,7 +267,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 		return -EINVAL;
 	}
 
-	h = nf_conntrack_find_get(sock_net(sk), &tuple);
+	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &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 327826a968a8..7404bde95994 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -18,6 +18,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_log.h>
 
 static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ;
@@ -114,13 +115,14 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
 
 /* Returns conntrack if it dealt with ICMP, and filled in skb fields */
 static int
-icmp_error_message(struct net *net, struct sk_buff *skb,
+icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 		 enum ip_conntrack_info *ctinfo,
 		 unsigned int hooknum)
 {
 	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;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
 
@@ -146,7 +148,7 @@ icmp_error_message(struct net *net, struct sk_buff *skb,
 
 	*ctinfo = IP_CT_RELATED;
 
-	h = nf_conntrack_find_get(net, &innertuple);
+	h = nf_conntrack_find_get(net, zone, &innertuple);
 	if (!h) {
 		pr_debug("icmp_error_message: no match\n");
 		return -NF_ACCEPT;
@@ -209,7 +211,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
 	    icmph->type != ICMP_REDIRECT)
 		return NF_ACCEPT;
 
-	return icmp_error_message(net, skb, ctinfo, hooknum);
+	return icmp_error_message(net, tmpl, skb, ctinfo, hooknum);
 }
 
 #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index f6f46686cbc0..d498a704d456 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -16,6 +16,7 @@
 
 #include <linux/netfilter_bridge.h>
 #include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 #include <net/netfilter/nf_conntrack.h>
 
@@ -39,15 +40,20 @@ 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;
+
+	if (skb->nfct)
+		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge &&
 	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
-		return IP_DEFRAG_CONNTRACK_BRIDGE_IN;
+		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
 #endif
 	if (hooknum == NF_INET_PRE_ROUTING)
-		return IP_DEFRAG_CONNTRACK_IN;
+		return IP_DEFRAG_CONNTRACK_IN + zone;
 	else
-		return IP_DEFRAG_CONNTRACK_OUT;
+		return IP_DEFRAG_CONNTRACK_OUT + zone;
 }
 
 static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 26066a2327ad..4595281c2863 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -30,6 +30,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 
 static DEFINE_SPINLOCK(nf_nat_lock);
 
@@ -69,13 +70,14 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put);
 
 /* 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_tuple *tuple)
+hash_by_src(const struct net *net, u16 zone,
+	    const struct nf_conntrack_tuple *tuple)
 {
 	unsigned int hash;
 
 	/* Original src, to ensure we map it consistently if poss. */
 	hash = jhash_3words((__force u32)tuple->src.u3.ip,
-			    (__force u32)tuple->src.u.all,
+			    (__force u32)tuple->src.u.all ^ zone,
 			    tuple->dst.protonum, 0);
 	return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
 }
@@ -139,12 +141,12 @@ same_src(const struct nf_conn *ct,
 
 /* Only called for SRC manip */
 static int
-find_appropriate_src(struct net *net,
+find_appropriate_src(struct net *net, u16 zone,
 		     const struct nf_conntrack_tuple *tuple,
 		     struct nf_conntrack_tuple *result,
 		     const struct nf_nat_range *range)
 {
-	unsigned int h = hash_by_src(net, tuple);
+	unsigned int h = hash_by_src(net, zone, tuple);
 	const struct nf_conn_nat *nat;
 	const struct nf_conn *ct;
 	const struct hlist_node *n;
@@ -152,7 +154,7 @@ find_appropriate_src(struct net *net,
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) {
 		ct = nat->ct;
-		if (same_src(ct, tuple)) {
+		if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
 			/* Copy source part from reply tuple. */
 			nf_ct_invert_tuplepr(result,
 				       &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@@ -175,7 +177,7 @@ find_appropriate_src(struct net *net,
    the ip with the lowest src-ip/dst-ip/proto usage.
 */
 static void
-find_best_ips_proto(struct nf_conntrack_tuple *tuple,
+find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
 		    const struct nf_nat_range *range,
 		    const struct nf_conn *ct,
 		    enum nf_nat_manip_type maniptype)
@@ -209,7 +211,7 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple,
 	maxip = ntohl(range->max_ip);
 	j = jhash_2words((__force u32)tuple->src.u3.ip,
 			 range->flags & IP_NAT_RANGE_PERSISTENT ?
-				0 : (__force u32)tuple->dst.u3.ip, 0);
+				0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
 	j = ((u64)j * (maxip - minip + 1)) >> 32;
 	*var_ipp = htonl(minip + j);
 }
@@ -229,6 +231,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 {
 	struct net *net = nf_ct_net(ct);
 	const struct nf_nat_protocol *proto;
+	u16 zone = nf_ct_zone(ct);
 
 	/* 1) If this srcip/proto/src-proto-part is currently mapped,
 	   and that same mapping gives a unique tuple within the given
@@ -239,7 +242,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	   manips not an issue.  */
 	if (maniptype == IP_NAT_MANIP_SRC &&
 	    !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
-		if (find_appropriate_src(net, orig_tuple, tuple, range)) {
+		if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) {
 			pr_debug("get_unique_tuple: Found current src map\n");
 			if (!nf_nat_used_tuple(tuple, ct))
 				return;
@@ -249,7 +252,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	/* 2) Select the least-used IP/proto combination in the given
 	   range. */
 	*tuple = *orig_tuple;
-	find_best_ips_proto(tuple, range, ct, maniptype);
+	find_best_ips_proto(zone, tuple, range, ct, maniptype);
 
 	/* 3) The per-protocol part of the manip is made to map into
 	   the range to make a unique tuple. */
@@ -327,7 +330,8 @@ nf_nat_setup_info(struct nf_conn *ct,
 	if (have_to_hash) {
 		unsigned int srchash;
 
-		srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+		srchash = hash_by_src(net, nf_ct_zone(ct),
+				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 		spin_lock_bh(&nf_nat_lock);
 		/* nf_conntrack_alter_reply might re-allocate exntension aera */
 		nat = nfct_nat(ct);
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 9eb171056c63..4c060038d29f 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -25,6 +25,7 @@
 #include <net/netfilter/nf_nat_rule.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 
@@ -74,7 +75,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
 
 	pr_debug("trying to unexpect other dir: ");
 	nf_ct_dump_tuple_ip(&t);
-	other_exp = nf_ct_expect_find_get(net, &t);
+	other_exp = nf_ct_expect_find_get(net, nf_ct_zone(ct), &t);
 	if (other_exp) {
 		nf_ct_unexpect_related(other_exp);
 		nf_ct_expect_put(other_exp);