openvswitch: Properly set L4 keys on "later" IP fragments

When IP fragments are reassembled before being sent to conntrack, the
key from the last fragment is used.  Unless there are reordering
issues, the last fragment received will not contain the L4 ports, so the
key for the reassembled datagram won't contain them.  This patch updates
the key once we have a reassembled datagram.

The handle_fragments() function works on L3 headers so we pull the L3/L4
flow key update code from key_extract into a new function
'key_extract_l3l4'.  Then we add a another new function
ovs_flow_key_update_l3l4() and export it so that it is accessible by
handle_fragments() for conntrack packet reassembly.

Co-authored-by: Justin Pettit <jpettit@ovn.org>
Signed-off-by: Greg Rose <gvrose8192@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 89 insertions, 66 deletions

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index bc89e16e0505..005f7622edac 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -523,78 +523,15 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key)
 }
 
 /**
- * key_extract - extracts a flow key from an Ethernet frame.
+ * key_extract_l3l4 - extracts L3/L4 header information.
  * @skb: sk_buff that contains the frame, with skb->data pointing to the
- * Ethernet header
+ *       L3 header
  * @key: output flow key
  *
- * The caller must ensure that skb->len >= ETH_HLEN.
- *
- * Returns 0 if successful, otherwise a negative errno value.
- *
- * Initializes @skb header fields as follows:
- *
- *    - skb->mac_header: the L2 header.
- *
- *    - skb->network_header: just past the L2 header, or just past the
- *      VLAN header, to the first byte of the L2 payload.
- *
- *    - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
- *      on output, then just past the IP header, if one is present and
- *      of a correct length, otherwise the same as skb->network_header.
- *      For other key->eth.type values it is left untouched.
- *
- *    - skb->protocol: the type of the data starting at skb->network_header.
- *      Equals to key->eth.type.
  */
-static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	int error;
-	struct ethhdr *eth;
-
-	/* Flags are always used as part of stats */
-	key->tp.flags = 0;
-
-	skb_reset_mac_header(skb);
-
-	/* Link layer. */
-	clear_vlan(key);
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		if (unlikely(eth_type_vlan(skb->protocol)))
-			return -EINVAL;
-
-		skb_reset_network_header(skb);
-		key->eth.type = skb->protocol;
-	} else {
-		eth = eth_hdr(skb);
-		ether_addr_copy(key->eth.src, eth->h_source);
-		ether_addr_copy(key->eth.dst, eth->h_dest);
-
-		__skb_pull(skb, 2 * ETH_ALEN);
-		/* We are going to push all headers that we pull, so no need to
-		* update skb->csum here.
-		*/
-
-		if (unlikely(parse_vlan(skb, key)))
-			return -ENOMEM;
-
-		key->eth.type = parse_ethertype(skb);
-		if (unlikely(key->eth.type == htons(0)))
-			return -ENOMEM;
-
-		/* Multiple tagged packets need to retain TPID to satisfy
-		 * skb_vlan_pop(), which will later shift the ethertype into
-		 * skb->protocol.
-		 */
-		if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
-			skb->protocol = key->eth.cvlan.tpid;
-		else
-			skb->protocol = key->eth.type;
-
-		skb_reset_network_header(skb);
-		__skb_push(skb, skb->data - skb_mac_header(skb));
-	}
-	skb_reset_mac_len(skb);
 
 	/* Network layer. */
 	if (key->eth.type == htons(ETH_P_IP)) {
@@ -788,6 +725,92 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	return 0;
 }
 
+/**
+ * key_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @key: output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Returns 0 if successful, otherwise a negative errno value.
+ *
+ * Initializes @skb header fields as follows:
+ *
+ *    - skb->mac_header: the L2 header.
+ *
+ *    - skb->network_header: just past the L2 header, or just past the
+ *      VLAN header, to the first byte of the L2 payload.
+ *
+ *    - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
+ *      on output, then just past the IP header, if one is present and
+ *      of a correct length, otherwise the same as skb->network_header.
+ *      For other key->eth.type values it is left untouched.
+ *
+ *    - skb->protocol: the type of the data starting at skb->network_header.
+ *      Equals to key->eth.type.
+ */
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct ethhdr *eth;
+
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
+	skb_reset_mac_header(skb);
+
+	/* Link layer. */
+	clear_vlan(key);
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+		if (unlikely(eth_type_vlan(skb->protocol)))
+			return -EINVAL;
+
+		skb_reset_network_header(skb);
+		key->eth.type = skb->protocol;
+	} else {
+		eth = eth_hdr(skb);
+		ether_addr_copy(key->eth.src, eth->h_source);
+		ether_addr_copy(key->eth.dst, eth->h_dest);
+
+		__skb_pull(skb, 2 * ETH_ALEN);
+		/* We are going to push all headers that we pull, so no need to
+		 * update skb->csum here.
+		 */
+
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+		key->eth.type = parse_ethertype(skb);
+		if (unlikely(key->eth.type == htons(0)))
+			return -ENOMEM;
+
+		/* Multiple tagged packets need to retain TPID to satisfy
+		 * skb_vlan_pop(), which will later shift the ethertype into
+		 * skb->protocol.
+		 */
+		if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
+			skb->protocol = key->eth.cvlan.tpid;
+		else
+			skb->protocol = key->eth.type;
+
+		skb_reset_network_header(skb);
+		__skb_push(skb, skb->data - skb_mac_header(skb));
+	}
+
+	skb_reset_mac_len(skb);
+
+	/* Fill out L3/L4 key info, if any */
+	return key_extract_l3l4(skb, key);
+}
+
+/* In the case of conntrack fragment handling it expects L3 headers,
+ * add a helper.
+ */
+int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	return key_extract_l3l4(skb, key);
+}
+
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	int res;