Merge git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net coming late
in the 5.17-rc process:

1) Revert port remap to mitigate shadowing service ports, this is causing
   problems in existing setups and this mitigation can be achieved with
   explicit ruleset, eg.

	... tcp sport < 16386 tcp dport >= 32768 masquerade random

  This patches provided a built-in policy similar to the one described above.

2) Disable register tracking infrastructure in nf_tables. Florian reported
   two issues:

   - Existing expressions with no implemented .reduce interface
     that causes data-store on register should cancel the tracking.
   - Register clobbering might be possible storing data on registers that
     are larger than 32-bits.

   This might lead to generating incorrect ruleset bytecode. These two
   issues are scheduled to be addressed in the next release cycle.

* git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nf_tables: disable register tracking
  Revert "netfilter: conntrack: tag conntracks picked up in local out hook"
  Revert "netfilter: nat: force port remap to prevent shadowing well-known ports"
====================

Link: https://lore.kernel.org/r/20220312220315.64531-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 12 insertions, 49 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 8731d5bcb47d..b08b70989d2c 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -97,7 +97,6 @@ struct nf_conn {
 	unsigned long status;
 
 	u16		cpu;
-	u16		local_origin:1;
 	possible_net_t ct_net;
 
 #if IS_ENABLED(CONFIG_NF_NAT)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d6aa5b47031e..bf1e17c678f1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1748,9 +1748,6 @@ resolve_normal_ct(struct nf_conn *tmpl,
 			return 0;
 		if (IS_ERR(h))
 			return PTR_ERR(h);
-
-		ct = nf_ct_tuplehash_to_ctrack(h);
-		ct->local_origin = state->hook == NF_INET_LOCAL_OUT;
 	}
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 2d06a66899b2..ffcf6529afc3 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -494,38 +494,6 @@ another_round:
 	goto another_round;
 }
 
-static bool tuple_force_port_remap(const struct nf_conntrack_tuple *tuple)
-{
-	u16 sp, dp;
-
-	switch (tuple->dst.protonum) {
-	case IPPROTO_TCP:
-		sp = ntohs(tuple->src.u.tcp.port);
-		dp = ntohs(tuple->dst.u.tcp.port);
-		break;
-	case IPPROTO_UDP:
-	case IPPROTO_UDPLITE:
-		sp = ntohs(tuple->src.u.udp.port);
-		dp = ntohs(tuple->dst.u.udp.port);
-		break;
-	default:
-		return false;
-	}
-
-	/* IANA: System port range: 1-1023,
-	 *         user port range: 1024-49151,
-	 *      private port range: 49152-65535.
-	 *
-	 * Linux default ephemeral port range is 32768-60999.
-	 *
-	 * Enforce port remapping if sport is significantly lower
-	 * than dport to prevent NAT port shadowing, i.e.
-	 * accidental match of 'new' inbound connection vs.
-	 * existing outbound one.
-	 */
-	return sp < 16384 && dp >= 32768;
-}
-
 /* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING,
  * we change the source to map into the range. For NF_INET_PRE_ROUTING
  * and NF_INET_LOCAL_OUT, we change the destination to map into the
@@ -539,17 +507,11 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 struct nf_conn *ct,
 		 enum nf_nat_manip_type maniptype)
 {
-	bool random_port = range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL;
 	const struct nf_conntrack_zone *zone;
 	struct net *net = nf_ct_net(ct);
 
 	zone = nf_ct_zone(ct);
 
-	if (maniptype == NF_NAT_MANIP_SRC &&
-	    !random_port &&
-	    !ct->local_origin)
-		random_port = tuple_force_port_remap(orig_tuple);
-
 	/* 1) If this srcip/proto/src-proto-part is currently mapped,
 	 * and that same mapping gives a unique tuple within the given
 	 * range, use that.
@@ -558,7 +520,8 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 * So far, we don't do local source mappings, so multiple
 	 * manips not an issue.
 	 */
-	if (maniptype == NF_NAT_MANIP_SRC && !random_port) {
+	if (maniptype == NF_NAT_MANIP_SRC &&
+	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		/* try the original tuple first */
 		if (in_range(orig_tuple, range)) {
 			if (!nf_nat_used_tuple(orig_tuple, ct)) {
@@ -582,7 +545,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 */
 
 	/* Only bother mapping if it's not already in range and unique */
-	if (!random_port) {
+	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
 			if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) &&
 			    l4proto_in_range(tuple, maniptype,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c86748b3873b..d71a33ae39b3 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8260,6 +8260,12 @@ void nf_tables_trans_destroy_flush_work(void)
 }
 EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work);
 
+static bool nft_expr_reduce(struct nft_regs_track *track,
+			    const struct nft_expr *expr)
+{
+	return false;
+}
+
 static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain)
 {
 	const struct nft_expr *expr, *last;
@@ -8307,8 +8313,7 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha
 		nft_rule_for_each_expr(expr, last, rule) {
 			track.cur = expr;
 
-			if (expr->ops->reduce &&
-			    expr->ops->reduce(&track, expr)) {
+			if (nft_expr_reduce(&track, expr)) {
 				expr = track.cur;
 				continue;
 			}
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 79fe627b9e81..eb8543b9a5c4 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -880,9 +880,8 @@ EOF
 		return $ksft_skip
 	fi
 
-	# test default behaviour. Packet from ns1 to ns0 is not redirected
-	# due to automatic port translation.
-	test_port_shadow "default" "ROUTER"
+	# test default behaviour. Packet from ns1 to ns0 is redirected to ns2.
+	test_port_shadow "default" "CLIENT"
 
 	# test packet filter based mitigation: prevent forwarding of
 	# packets claiming to come from the service port.