net: move the nat function to nf_nat_ovs for ovs and tc

There are two nat functions are nearly the same in both OVS and
TC code, (ovs_)ct_nat_execute() and ovs_ct_nat/tcf_ct_act_nat().

This patch creates nf_nat_ovs.c under netfilter and moves them
there then exports nf_ct_nat() so that it can be shared by both
OVS and TC, and keeps the nat (type) check and nat flag update
in OVS and TC's own place, as these parts are different between
OVS and TC.

Note that in OVS nat function it was using skb->protocol to get
the proto as it already skips vlans in key_extract(), while it
doesn't in TC, and TC has to call skb_protocol() to get proto.
So in nf_ct_nat_execute(), we keep using skb_protocol() which
works for both OVS and TC contrack.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netfilter/nf_nat.h

@@ -104,6 +104,10 @@ unsigned int
 nf_nat_inet_fn(void *priv, struct sk_buff *skb,
 	       const struct nf_hook_state *state);
 
+int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct,
+	      enum ip_conntrack_info ctinfo, int *action,
+	      const struct nf_nat_range2 *range, bool commit);
+
 static inline int nf_nat_initialized(const struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {

net/netfilter/Kconfig

@@ -459,6 +459,9 @@ config NF_NAT_REDIRECT
 config NF_NAT_MASQUERADE
 	bool
 
+config NF_NAT_OVS
+	bool
+
 config NETFILTER_SYNPROXY
 	tristate
 

net/netfilter/Makefile

@@ -59,6 +59,7 @@ obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o
 obj-$(CONFIG_NF_NAT) += nf_nat.o
 nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
 nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o
+nf_nat-$(CONFIG_NF_NAT_OVS) += nf_nat_ovs.o
 
 ifeq ($(CONFIG_NF_NAT),m)
 nf_nat-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_nat_bpf.o

net/netfilter/nf_nat_ovs.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Support nat functions for openvswitch and used by OVS and TC conntrack. */
+
+#include <net/netfilter/nf_nat.h>
+
+/* Modelled after nf_nat_ipv[46]_fn().
+ * range is only used for new, uninitialized NAT state.
+ * Returns either NF_ACCEPT or NF_DROP.
+ */
+static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
+			     enum ip_conntrack_info ctinfo, int *action,
+			     const struct nf_nat_range2 *range,
+			     enum nf_nat_manip_type maniptype)
+{
+	__be16 proto = skb_protocol(skb, true);
+	int hooknum, err = NF_ACCEPT;
+
+	/* See HOOK2MANIP(). */
+	if (maniptype == NF_NAT_MANIP_SRC)
+		hooknum = NF_INET_LOCAL_IN; /* Source NAT */
+	else
+		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		if (proto == htons(ETH_P_IP) &&
+		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   hooknum))
+				err = NF_DROP;
+			goto out;
+		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
+			__be16 frag_off;
+			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+			int hdrlen = ipv6_skip_exthdr(skb,
+						      sizeof(struct ipv6hdr),
+						      &nexthdr, &frag_off);
+
+			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+				if (!nf_nat_icmpv6_reply_translation(skb, ct,
+								     ctinfo,
+								     hooknum,
+								     hdrlen))
+					err = NF_DROP;
+				goto out;
+			}
+		}
+		/* Non-ICMP, fall thru to initialize if needed. */
+		fallthrough;
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			/* Initialize according to the NAT action. */
+			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
+				/* Action is set up to establish a new
+				 * mapping.
+				 */
+				? nf_nat_setup_info(ct, range, maniptype)
+				: nf_nat_alloc_null_binding(ct, hooknum);
+			if (err != NF_ACCEPT)
+				goto out;
+		}
+		break;
+
+	case IP_CT_ESTABLISHED:
+	case IP_CT_ESTABLISHED_REPLY:
+		break;
+
+	default:
+		err = NF_DROP;
+		goto out;
+	}
+
+	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+	if (err == NF_ACCEPT)
+		*action |= BIT(maniptype);
+out:
+	return err;
+}
+
+int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct,
+	      enum ip_conntrack_info ctinfo, int *action,
+	      const struct nf_nat_range2 *range, bool commit)
+{
+	enum nf_nat_manip_type maniptype;
+	int err, ct_action = *action;
+
+	*action = 0;
+
+	/* Add NAT extension if not confirmed yet. */
+	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
+		return NF_DROP;   /* Can't NAT. */
+
+	if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
+	    (ctinfo != IP_CT_RELATED || commit)) {
+		/* NAT an established or related connection like before. */
+		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
+			/* This is the REPLY direction for a connection
+			 * for which NAT was applied in the forward
+			 * direction.  Do the reverse NAT.
+			 */
+			maniptype = ct->status & IPS_SRC_NAT
+				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
+		else
+			maniptype = ct->status & IPS_SRC_NAT
+				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
+	} else if (ct_action & BIT(NF_NAT_MANIP_SRC)) {
+		maniptype = NF_NAT_MANIP_SRC;
+	} else if (ct_action & BIT(NF_NAT_MANIP_DST)) {
+		maniptype = NF_NAT_MANIP_DST;
+	} else {
+		return NF_ACCEPT;
+	}
+
+	err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, maniptype);
+	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
+		if (ct->status & IPS_SRC_NAT) {
+			if (maniptype == NF_NAT_MANIP_SRC)
+				maniptype = NF_NAT_MANIP_DST;
+			else
+				maniptype = NF_NAT_MANIP_SRC;
+
+			err = nf_ct_nat_execute(skb, ct, ctinfo, action, range,
+						maniptype);
+		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
+			err = nf_ct_nat_execute(skb, ct, ctinfo, action, NULL,
+						NF_NAT_MANIP_SRC);
+		}
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(nf_ct_nat);

net/openvswitch/Kconfig

@@ -15,6 +15,7 @@ config OPENVSWITCH
 	select NET_MPLS_GSO
 	select DST_CACHE
 	select NET_NSH
+	select NF_NAT_OVS if NF_NAT
 	help
 	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
 	  environments.  In addition to supporting a variety of features

net/openvswitch/conntrack.c

@@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key,
 	}
 }
 
-/* Modelled after nf_nat_ipv[46]_fn().
- * range is only used for new, uninitialized NAT state.
- * Returns either NF_ACCEPT or NF_DROP.
- */
-static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
-			      enum ip_conntrack_info ctinfo,
-			      const struct nf_nat_range2 *range,
-			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
-{
-	int hooknum, err = NF_ACCEPT;
-
-	/* See HOOK2MANIP(). */
-	if (maniptype == NF_NAT_MANIP_SRC)
-		hooknum = NF_INET_LOCAL_IN; /* Source NAT */
-	else
-		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (IS_ENABLED(CONFIG_NF_NAT) &&
-		    skb->protocol == htons(ETH_P_IP) &&
-		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   hooknum))
-				err = NF_DROP;
-			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) &&
-			   skb->protocol == htons(ETH_P_IPV6)) {
-			__be16 frag_off;
-			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-			int hdrlen = ipv6_skip_exthdr(skb,
-						      sizeof(struct ipv6hdr),
-						      &nexthdr, &frag_off);
-
-			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-				if (!nf_nat_icmpv6_reply_translation(skb, ct,
-								     ctinfo,
-								     hooknum,
-								     hdrlen))
-					err = NF_DROP;
-				goto out;
-			}
-		}
-		/* Non-ICMP, fall thru to initialize if needed. */
-		fallthrough;
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			/* Initialize according to the NAT action. */
-			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
-				/* Action is set up to establish a new
-				 * mapping.
-				 */
-				? nf_nat_setup_info(ct, range, maniptype)
-				: nf_nat_alloc_null_binding(ct, hooknum);
-			if (err != NF_ACCEPT)
-				goto out;
-		}
-		break;
-
-	case IP_CT_ESTABLISHED:
-	case IP_CT_ESTABLISHED_REPLY:
-		break;
-
-	default:
-		err = NF_DROP;
-		goto out;
-	}
-
-	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
-out:
-	/* Update the flow key if NAT successful. */
-	if (err == NF_ACCEPT)
-		ovs_nat_update_key(key, skb, maniptype);
-
-	return err;
-}
-
 /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
 static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 		      const struct ovs_conntrack_info *info,
 		      struct sk_buff *skb, struct nf_conn *ct,
 		      enum ip_conntrack_info ctinfo)
 {
-	enum nf_nat_manip_type maniptype;
-	int err;
+	int err, action = 0;
 
 	if (!(info->nat & OVS_CT_NAT))
 		return NF_ACCEPT;
+	if (info->nat & OVS_CT_SRC_NAT)
+		action |= BIT(NF_NAT_MANIP_SRC);
+	if (info->nat & OVS_CT_DST_NAT)
+		action |= BIT(NF_NAT_MANIP_DST);
 
-	/* Add NAT extension if not confirmed yet. */
-	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
-		return NF_DROP;   /* Can't NAT. */
+	err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit);
 
-	/* Determine NAT type.
-	 * Check if the NAT type can be deduced from the tracked connection.
-	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
-	 * when committing.
-	 */
-	if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK &&
-	    (ctinfo != IP_CT_RELATED || info->commit)) {
-		/* NAT an established or related connection like before. */
-		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
-			/* This is the REPLY direction for a connection
-			 * for which NAT was applied in the forward
-			 * direction.  Do the reverse NAT.
-			 */
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
-		else
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
-	} else if (info->nat & OVS_CT_SRC_NAT) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (info->nat & OVS_CT_DST_NAT) {
-		maniptype = NF_NAT_MANIP_DST;
-	} else {
-		return NF_ACCEPT; /* Connection is not NATed. */
-	}
-	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
-
-	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
-		if (ct->status & IPS_SRC_NAT) {
-			if (maniptype == NF_NAT_MANIP_SRC)
-				maniptype = NF_NAT_MANIP_DST;
-			else
-				maniptype = NF_NAT_MANIP_SRC;
-
-			err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
-						 maniptype, key);
-		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
-			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
-						 NF_NAT_MANIP_SRC, key);
-		}
-	}
+	if (action & BIT(NF_NAT_MANIP_SRC))
+		ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC);
+	if (action & BIT(NF_NAT_MANIP_DST))
+		ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
 
 	return err;
 }

net/sched/Kconfig

@@ -977,6 +977,7 @@ config NET_ACT_TUNNEL_KEY
 config NET_ACT_CT
 	tristate "connection tracking tc action"
 	depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE
+	select NF_NAT_OVS if NF_NAT
 	help
 	  Say Y here to allow sending the packets to conntrack module.
 

net/sched/act_ct.c

@@ -864,90 +864,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head)
 	tcf_ct_params_free(params);
 }
 
-#if IS_ENABLED(CONFIG_NF_NAT)
-/* Modelled after nf_nat_ipv[46]_fn().
- * range is only used for new, uninitialized NAT state.
- * Returns either NF_ACCEPT or NF_DROP.
- */
-static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
-			  enum ip_conntrack_info ctinfo,
-			  const struct nf_nat_range2 *range,
-			  enum nf_nat_manip_type maniptype)
-{
-	__be16 proto = skb_protocol(skb, true);
-	int hooknum, err = NF_ACCEPT;
-
-	/* See HOOK2MANIP(). */
-	if (maniptype == NF_NAT_MANIP_SRC)
-		hooknum = NF_INET_LOCAL_IN; /* Source NAT */
-	else
-		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (proto == htons(ETH_P_IP) &&
-		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   hooknum))
-				err = NF_DROP;
-			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
-			__be16 frag_off;
-			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-			int hdrlen = ipv6_skip_exthdr(skb,
-						      sizeof(struct ipv6hdr),
-						      &nexthdr, &frag_off);
-
-			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-				if (!nf_nat_icmpv6_reply_translation(skb, ct,
-								     ctinfo,
-								     hooknum,
-								     hdrlen))
-					err = NF_DROP;
-				goto out;
-			}
-		}
-		/* Non-ICMP, fall thru to initialize if needed. */
-		fallthrough;
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			/* Initialize according to the NAT action. */
-			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
-				/* Action is set up to establish a new
-				 * mapping.
-				 */
-				? nf_nat_setup_info(ct, range, maniptype)
-				: nf_nat_alloc_null_binding(ct, hooknum);
-			if (err != NF_ACCEPT)
-				goto out;
-		}
-		break;
-
-	case IP_CT_ESTABLISHED:
-	case IP_CT_ESTABLISHED_REPLY:
-		break;
-
-	default:
-		err = NF_DROP;
-		goto out;
-	}
-
-	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
-out:
-	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;
-	}
-	return err;
-}
-#endif /* CONFIG_NF_NAT */
-
 static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
@@ -987,52 +903,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
 			  bool commit)
 {
 #if IS_ENABLED(CONFIG_NF_NAT)
-	int err;
-	enum nf_nat_manip_type maniptype;
+	int err, action = 0;
 
 	if (!(ct_action & TCA_CT_ACT_NAT))
 		return NF_ACCEPT;
+	if (ct_action & TCA_CT_ACT_NAT_SRC)
+		action |= BIT(NF_NAT_MANIP_SRC);
+	if (ct_action & TCA_CT_ACT_NAT_DST)
+		action |= BIT(NF_NAT_MANIP_DST);
 
-	/* Add NAT extension if not confirmed yet. */
-	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
-		return NF_DROP;   /* Can't NAT. */
-
-	if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
-	    (ctinfo != IP_CT_RELATED || commit)) {
-		/* NAT an established or related connection like before. */
-		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
-			/* This is the REPLY direction for a connection
-			 * for which NAT was applied in the forward
-			 * direction.  Do the reverse NAT.
-			 */
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
-		else
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
-	} else if (ct_action & TCA_CT_ACT_NAT_SRC) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
-		maniptype = NF_NAT_MANIP_DST;
-	} else {
-		return NF_ACCEPT;
-	}
+	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
+
+	if (action & BIT(NF_NAT_MANIP_SRC))
+		tc_skb_cb(skb)->post_ct_snat = 1;
+	if (action & BIT(NF_NAT_MANIP_DST))
+		tc_skb_cb(skb)->post_ct_dnat = 1;
 
-	err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
-	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
-		if (ct->status & IPS_SRC_NAT) {
-			if (maniptype == NF_NAT_MANIP_SRC)
-				maniptype = NF_NAT_MANIP_DST;
-			else
-				maniptype = NF_NAT_MANIP_SRC;
-
-			err = ct_nat_execute(skb, ct, ctinfo, range,
-					     maniptype);
-		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
-			err = ct_nat_execute(skb, ct, ctinfo, NULL,
-					     NF_NAT_MANIP_SRC);
-		}
-	}
 	return err;
 #else
 	return NF_ACCEPT;