Merge branch 'ovs-L3-encap'

Jiri Benc says:

====================
openvswitch: support for layer 3 encapsulated packets

At the core of this patch set is removing the assumption in Open vSwitch
datapath that all packets have Ethernet header.

The implementation relies on the presence of pop_eth and push_eth actions
in datapath flows to facilitate adding and removing Ethernet headers as
appropriate. The construction of such flows is left up to user-space.

This series is based on work by Simon Horman, Lorand Jakab, Thomas Morin and
others. I kept Lorand's and Simon's s-o-b in the patches that are derived
from v11 to record their authorship of parts of the code.

Changes from v12 to v13:

* Addressed Pravin's feedback.
* Removed the GRE vport conversion patch; L3 GRE ports should be created by
  rtnetlink instead.

Main changes from v11 to v12:

* The patches were restructured and split differently for easier review.
* They were rebased and adjusted to the current net-next. Especially MPLS
  handling is different (and easier) thanks to the recent MPLS GSO rework.
* Several bugs were discovered and fixed. The most notable is fragment
  handling: header adjustment for ARPHRD_NONE devices on tx needs to be done
  after refragmentation, not before it. This required significant changes in
  the patchset. Another one is stricter checking of attributes (match on L2
  vs. L3 packet) at the kernel level.
* Instead of is_layer3 bool, a mac_proto field is used.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 81 insertions, 24 deletions

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 22087062bd10..08aa926cd5cf 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -334,14 +334,17 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
 	return 1;
 }
 
-static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+static void clear_vlan(struct sw_flow_key *key)
 {
-	int res;
-
 	key->eth.vlan.tci = 0;
 	key->eth.vlan.tpid = 0;
 	key->eth.cvlan.tci = 0;
 	key->eth.cvlan.tpid = 0;
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int res;
 
 	if (skb_vlan_tag_present(skb)) {
 		key->eth.vlan.tci = htons(skb->vlan_tci);
@@ -483,17 +486,20 @@ invalid:
  *
  * Returns 0 if successful, otherwise a negative errno value.
  *
- * Initializes @skb header pointers as follows:
+ * Initializes @skb header fields as follows:
  *
- *    - skb->mac_header: the Ethernet header.
+ *    - skb->mac_header: the L2 header.
  *
- *    - skb->network_header: just past the Ethernet header, or just past the
- *      VLAN header, to the first byte of the Ethernet payload.
+ *    - 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)
 {
@@ -505,28 +511,35 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 	skb_reset_mac_header(skb);
 
-	/* Link layer.  We are guaranteed to have at least the 14 byte Ethernet
-	 * header in the linear data area.
-	 */
-	eth = eth_hdr(skb);
-	ether_addr_copy(key->eth.src, eth->h_source);
-	ether_addr_copy(key->eth.dst, eth->h_dest);
+	/* Link layer. */
+	clear_vlan(key);
+	if (key->mac_proto == MAC_PROTO_NONE) {
+		if (unlikely(eth_type_vlan(skb->protocol)))
+			return -EINVAL;
 
-	__skb_pull(skb, 2 * ETH_ALEN);
-	/* We are going to push all headers that we pull, so no need to
-	 * update skb->csum here.
-	 */
+		skb_reset_network_header(skb);
+	} else {
+		eth = eth_hdr(skb);
+		ether_addr_copy(key->eth.src, eth->h_source);
+		ether_addr_copy(key->eth.dst, eth->h_dest);
 
-	if (unlikely(parse_vlan(skb, key)))
-		return -ENOMEM;
+		__skb_pull(skb, 2 * ETH_ALEN);
+		/* We are going to push all headers that we pull, so no need to
+		* update skb->csum here.
+		*/
 
-	key->eth.type = parse_ethertype(skb);
-	if (unlikely(key->eth.type == htons(0)))
-		return -ENOMEM;
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+		skb->protocol = parse_ethertype(skb);
+		if (unlikely(skb->protocol == htons(0)))
+			return -ENOMEM;
 
-	skb_reset_network_header(skb);
+		skb_reset_network_header(skb);
+		__skb_push(skb, skb->data - skb_mac_header(skb));
+	}
 	skb_reset_mac_len(skb);
-	__skb_push(skb, skb->data - skb_mac_header(skb));
+	key->eth.type = skb->protocol;
 
 	/* Network layer. */
 	if (key->eth.type == htons(ETH_P_IP)) {
@@ -721,9 +734,25 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 	return key_extract(skb, key);
 }
 
+static int key_extract_mac_proto(struct sk_buff *skb)
+{
+	switch (skb->dev->type) {
+	case ARPHRD_ETHER:
+		return MAC_PROTO_ETHERNET;
+	case ARPHRD_NONE:
+		if (skb->protocol == htons(ETH_P_TEB))
+			return MAC_PROTO_ETHERNET;
+		return MAC_PROTO_NONE;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
 int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
+	int res;
+
 	/* Extract metadata from packet. */
 	if (tun_info) {
 		key->tun_proto = ip_tunnel_info_af(tun_info);
@@ -751,6 +780,10 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	key->phy.skb_mark = skb->mark;
 	ovs_ct_fill_key(skb, key);
 	key->ovs_flow_hash = 0;
+	res = key_extract_mac_proto(skb);
+	if (res < 0)
+		return res;
+	key->mac_proto = res;
 	key->recirc_id = 0;
 
 	return key_extract(skb, key);
@@ -767,5 +800,29 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
 	if (err)
 		return err;
 
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+		/* key_extract assumes that skb->protocol is set-up for
+		 * layer 3 packets which is the case for other callers,
+		 * in particular packets recieved from the network stack.
+		 * Here the correct value can be set from the metadata
+		 * extracted above.
+		 */
+		skb->protocol = key->eth.type;
+	} else {
+		struct ethhdr *eth;
+
+		skb_reset_mac_header(skb);
+		eth = eth_hdr(skb);
+
+		/* Normally, setting the skb 'protocol' field would be
+		 * handled by a call to eth_type_trans(), but it assumes
+		 * there's a sending device, which we may not have.
+		 */
+		if (eth_proto_is_802_3(eth->h_proto))
+			skb->protocol = eth->h_proto;
+		else
+			skb->protocol = htons(ETH_P_802_2);
+	}
+
 	return key_extract(skb, key);
 }