net: openvswitch: Fix ct_state nat flags for conns arriving from tc

Netfilter conntrack maintains NAT flags per connection indicating
whether NAT was configured for the connection. Openvswitch maintains
NAT flags on the per packet flow key ct_state field, indicating
whether NAT was actually executed on the packet.

When a packet misses from tc to ovs the conntrack NAT flags are set.
However, NAT was not necessarily executed on the packet because the
connection's state might still be in NEW state. As such, openvswitch
wrongly assumes that NAT was executed and sets an incorrect flow key
NAT flags.

Fix this, by flagging to openvswitch which NAT was actually done in
act_ct via tc_skb_ext and tc_skb_cb to the openvswitch module, so
the packet flow key NAT flags will be correctly set.

Fixes: b57dc7c1 ("net/sched: Introduce action ct")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20220106153804.26451-1-paulb@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/skbuff.h

@@ -287,7 +287,9 @@ struct tc_skb_ext {
 	__u32 chain;
 	__u16 mru;
 	__u16 zone;
-	bool post_ct;
+	u8 post_ct:1;
+	u8 post_ct_snat:1;
+	u8 post_ct_dnat:1;
 };
 #endif
 

include/net/pkt_sched.h

@@ -197,7 +197,9 @@ struct tc_skb_cb {
 	struct qdisc_skb_cb qdisc_cb;
 
 	u16 mru;
-	bool post_ct;
+	u8 post_ct:1;
+	u8 post_ct_snat:1;
+	u8 post_ct_dnat:1;
 	u16 zone; /* Only valid if post_ct = true */
 };
 

net/openvswitch/flow.c

@@ -859,7 +859,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 	struct tc_skb_ext *tc_ext;
 #endif
-	bool post_ct = false;
+	bool post_ct = false, post_ct_snat = false, post_ct_dnat = false;
 	int res, err;
 	u16 zone = 0;
 
@@ -900,6 +900,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
 		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 		post_ct = tc_ext ? tc_ext->post_ct : false;
+		post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;
+		post_ct_dnat = post_ct ? tc_ext->post_ct_dnat : false;
 		zone = post_ct ? tc_ext->zone : 0;
 	} else {
 		key->recirc_id = 0;
@@ -911,8 +913,16 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	err = key_extract(skb, key);
 	if (!err) {
 		ovs_ct_fill_key(skb, key, post_ct);   /* Must be after key_extract(). */
-		if (post_ct && !skb_get_nfct(skb))
-			key->ct_zone = zone;
+		if (post_ct) {
+			if (!skb_get_nfct(skb)) {
+				key->ct_zone = zone;
+			} else {
+				if (!post_ct_dnat)
+					key->ct_state &= ~OVS_CS_F_DST_NAT;
+				if (!post_ct_snat)
+					key->ct_state &= ~OVS_CS_F_SRC_NAT;
+			}
+		}
 	}
 	return err;
 }

net/sched/act_ct.c

@@ -839,6 +839,12 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	}
 
 	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+	if (err == NF_ACCEPT) {
+		if (maniptype == NF_NAT_MANIP_SRC)
+			tc_skb_cb(skb)->post_ct_snat = 1;
+		if (maniptype == NF_NAT_MANIP_DST)
+			tc_skb_cb(skb)->post_ct_dnat = 1;
+	}
 out:
 	return err;
 }

net/sched/cls_api.c

@@ -1625,6 +1625,8 @@ int tcf_classify(struct sk_buff *skb,
 		ext->chain = last_executed_chain;
 		ext->mru = cb->mru;
 		ext->post_ct = cb->post_ct;
+		ext->post_ct_snat = cb->post_ct_snat;
+		ext->post_ct_dnat = cb->post_ct_dnat;
 		ext->zone = cb->zone;
 	}