net: extract nf_ct_handle_fragments to nf_conntrack_ovs

Now handle_fragments() in OVS and TC have the similar code, and
this patch removes the duplicate code by moving the function
to nf_conntrack_ovs.

Note that skb_clear_hash(skb) or skb->ignore_df = 1 should be
done only when defrag returns 0, as it does in other places
in kernel.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/netfilter/nf_conntrack.h

@@ -363,6 +363,8 @@ static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net)
 }
 
 int nf_ct_skb_network_trim(struct sk_buff *skb, int family);
+int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
+			   u16 zone, u8 family, u8 *proto, u16 *mru);
 
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)

net/netfilter/nf_conntrack_ovs.c

@@ -3,6 +3,8 @@
 
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/ipv6_frag.h>
 #include <net/ip.h>
 
 /* 'skb' should already be pulled to nh_ofs. */
@@ -128,3 +130,49 @@ int nf_ct_skb_network_trim(struct sk_buff *skb, int family)
 	return pskb_trim_rcsum(skb, len);
 }
 EXPORT_SYMBOL_GPL(nf_ct_skb_network_trim);
+
+/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
+ * value if 'skb' is freed.
+ */
+int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
+			   u16 zone, u8 family, u8 *proto, u16 *mru)
+{
+	int err;
+
+	if (family == NFPROTO_IPV4) {
+		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
+
+		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+		local_bh_disable();
+		err = ip_defrag(net, skb, user);
+		local_bh_enable();
+		if (err)
+			return err;
+
+		*mru = IPCB(skb)->frag_max_size;
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+	} else if (family == NFPROTO_IPV6) {
+		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
+
+		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+		err = nf_ct_frag6_gather(net, skb, user);
+		if (err) {
+			if (err != -EINPROGRESS)
+				kfree_skb(skb);
+			return err;
+		}
+
+		*proto = ipv6_hdr(skb)->nexthdr;
+		*mru = IP6CB(skb)->frag_max_size;
+#endif
+	} else {
+		kfree_skb(skb);
+		return -EPFNOSUPPORT;
+	}
+
+	skb_clear_hash(skb);
+	skb->ignore_df = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nf_ct_handle_fragments);

net/openvswitch/conntrack.c

@@ -435,56 +435,13 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key,
 	return 0;
 }
 
-/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
- * value if 'skb' is freed.
- */
-static int handle_fragments(struct net *net, struct sk_buff *skb,
-			    u16 zone, u8 family, u8 *proto, u16 *mru)
-{
-	int err;
-
-	if (family == NFPROTO_IPV4) {
-		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-		err = ip_defrag(net, skb, user);
-		if (err)
-			return err;
-
-		*mru = IPCB(skb)->frag_max_size;
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-	} else if (family == NFPROTO_IPV6) {
-		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
-		err = nf_ct_frag6_gather(net, skb, user);
-		if (err) {
-			if (err != -EINPROGRESS)
-				kfree_skb(skb);
-			return err;
-		}
-
-		*proto = ipv6_hdr(skb)->nexthdr;
-		*mru = IP6CB(skb)->frag_max_size;
-#endif
-	} else {
-		kfree_skb(skb);
-		return -EPFNOSUPPORT;
-	}
-
-	skb_clear_hash(skb);
-	skb->ignore_df = 1;
-
-	return 0;
-}
-
 static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key,
 				   u16 zone, int family, struct sk_buff *skb)
 {
 	struct ovs_skb_cb ovs_cb = *OVS_CB(skb);
 	int err;
 
-	err = handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru);
+	err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru);
 	if (err)
 		return err;
 

net/sched/act_ct.c

@@ -778,49 +778,6 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
 	return 0;
 }
 
-static int handle_fragments(struct net *net, struct sk_buff *skb,
-			    u16 zone, u8 family, u16 *mru)
-{
-	int err;
-
-	if (family == NFPROTO_IPV4) {
-		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-		local_bh_disable();
-		err = ip_defrag(net, skb, user);
-		local_bh_enable();
-		if (err && err != -EINPROGRESS)
-			return err;
-
-		if (!err)
-			*mru = IPCB(skb)->frag_max_size;
-	} else { /* NFPROTO_IPV6 */
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
-		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
-
-		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
-		err = nf_ct_frag6_gather(net, skb, user);
-		if (err && err != -EINPROGRESS)
-			goto out_free;
-
-		if (!err)
-			*mru = IP6CB(skb)->frag_max_size;
-#else
-		err = -EOPNOTSUPP;
-		goto out_free;
-#endif
-	}
-
-	skb_clear_hash(skb);
-	skb->ignore_df = 1;
-	return err;
-
-out_free:
-	kfree_skb(skb);
-	return err;
-}
-
 static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 				   u8 family, u16 zone, bool *defrag)
 {
@@ -828,6 +785,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
+	u8 proto;
 	u16 mru;
 
 	/* Previously seen (loopback)? Ignore. */
@@ -843,7 +801,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		return err;
 
 	skb_get(skb);
-	err = handle_fragments(net, skb, zone, family, &mru);
+	err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru);
 	if (err)
 		return err;