datapath: add Ethernet push and pop actions

Upstream commit:
    commit 91820da6ae85904d95ed53bf3a83f9ec44a6b80a
    Author: Jiri Benc <jbenc@redhat.com>
    Date:   Thu Nov 10 16:28:23 2016 +0100

    openvswitch: add Ethernet push and pop actions

    It's not allowed to push Ethernet header in front of another Ethernet
    header.

    It's not allowed to pop Ethernet header if there's a vlan tag. This
    preserves the invariant that L3 packet never has a vlan tag.

    Based on previous versions by Lorand Jakab and Simon Horman.

    Signed-off-by: Lorand Jakab <lojakab@cisco.com>
    Signed-off-by: Simon Horman <simon.horman@netronome.com>
    Signed-off-by: Jiri Benc <jbenc@redhat.com>
    Acked-by: Pravin B Shelar <pshelar@ovn.org>
    Signed-off-by: David S. Miller <davem@davemloft.net>

[Committer notes]

Fix build with the upstream commit by folding in the required switch
case enum handlers.

Signed-off-by: Yi Yang <yi.y.yang@intel.com>
Signed-off-by: Joe Stringer <joe@ovn.org>

datapath/actions.c

@@ -310,6 +310,47 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	return 0;
 }
 
+/* pop_eth does not support VLAN packets as this action is never called
+ * for them.
+ */
+static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	skb_pull_rcsum(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	/* safe right before invalidate_flow_key */
+	key->mac_proto = MAC_PROTO_NONE;
+	invalidate_flow_key(key);
+	return 0;
+}
+
+static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
+		    const struct ovs_action_push_eth *ethh)
+{
+	struct ethhdr *hdr;
+
+	/* Add the new Ethernet header */
+	if (skb_cow_head(skb, ETH_HLEN) < 0)
+		return -ENOMEM;
+
+	skb_push(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	hdr = eth_hdr(skb);
+	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
+	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
+	hdr->h_proto = skb->protocol;
+
+	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+
+	/* safe right before invalidate_flow_key */
+	key->mac_proto = MAC_PROTO_ETHERNET;
+	invalidate_flow_key(key);
+	return 0;
+}
+
 static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
 				  __be32 addr, __be32 new_addr)
 {
@@ -1184,6 +1225,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			if (err)
 				return err == -EINPROGRESS ? 0 : err;
 			break;
+
+		case OVS_ACTION_ATTR_PUSH_ETH:
+			err = push_eth(skb, key, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_POP_ETH:
+			err = pop_eth(skb, key);
+			break;
 		}
 
 		if (unlikely(err)) {

datapath/flow_netlink.c

@@ -2388,6 +2388,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
 			[OVS_ACTION_ATTR_CT] = (u32)-1,
 			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
+			[OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
+			[OVS_ACTION_ATTR_POP_ETH] = 0,
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -2522,6 +2524,22 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			skip_copy = true;
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_ETH:
+			/* Disallow pushing an Ethernet header if one
+			 * is already present */
+			if (mac_proto != MAC_PROTO_NONE)
+				return -EINVAL;
+			mac_proto = MAC_PROTO_NONE;
+			break;
+
+		case OVS_ACTION_ATTR_POP_ETH:
+			if (mac_proto != MAC_PROTO_ETHERNET)
+				return -EINVAL;
+			if (vlan_tci & htons(VLAN_TAG_PRESENT))
+				return -EINVAL;
+			mac_proto = MAC_PROTO_ETHERNET;
+			break;
+
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;

datapath/linux/compat/include/linux/openvswitch.h

@@ -711,6 +711,15 @@ enum ovs_ct_attr {
 
 #define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1)
 
+/*
+ * struct ovs_action_push_eth - %OVS_ACTION_ATTR_PUSH_ETH action argument.
+ * @addresses: Source and destination MAC addresses.
+ * @eth_type: Ethernet type
+ */
+struct ovs_action_push_eth {
+	struct ovs_key_ethernet addresses;
+};
+
 /**
  * enum ovs_nat_attr - Attributes for %OVS_CT_ATTR_NAT.
  *
@@ -783,6 +792,10 @@ enum ovs_nat_attr {
  * is no MPLS label stack, as determined by ethertype, no action is taken.
  * @OVS_ACTION_ATTR_CT: Track the connection. Populate the conntrack-related
  * entries in the flow key.
+ * @OVS_ACTION_ATTR_PUSH_ETH: Push a new outermost Ethernet header onto the
+ * packet.
+ * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the
+ * packet.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -815,6 +828,8 @@ enum ovs_action_attr {
 				       * bits. */
 	OVS_ACTION_ATTR_CT,           /* Nested OVS_CT_ATTR_* . */
 	OVS_ACTION_ATTR_TRUNC,        /* u32 struct ovs_action_trunc. */
+	OVS_ACTION_ATTR_PUSH_ETH,     /* struct ovs_action_push_eth. */
+	OVS_ACTION_ATTR_POP_ETH,      /* No argument. */
 
 #ifndef __KERNEL__
 	OVS_ACTION_ATTR_TUNNEL_PUSH,   /* struct ovs_action_push_tnl*/

lib/dpif-netdev.c

@@ -4783,6 +4783,8 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
     case OVS_ACTION_ATTR_HASH:
     case OVS_ACTION_ATTR_UNSPEC:
     case OVS_ACTION_ATTR_TRUNC:
+    case OVS_ACTION_ATTR_PUSH_ETH:
+    case OVS_ACTION_ATTR_POP_ETH:
     case OVS_ACTION_ATTR_CLONE:
     case __OVS_ACTION_ATTR_MAX:
         OVS_NOT_REACHED();

lib/dpif.c

@@ -1182,6 +1182,8 @@ dpif_execute_helper_cb(void *aux_, struct dp_packet_batch *packets_,
     case OVS_ACTION_ATTR_SET_MASKED:
     case OVS_ACTION_ATTR_SAMPLE:
     case OVS_ACTION_ATTR_TRUNC:
+    case OVS_ACTION_ATTR_PUSH_ETH:
+    case OVS_ACTION_ATTR_POP_ETH:
     case OVS_ACTION_ATTR_CLONE:
     case OVS_ACTION_ATTR_UNSPEC:
     case __OVS_ACTION_ATTR_MAX:

lib/odp-execute.c

@@ -580,6 +580,8 @@ requires_datapath_assistance(const struct nlattr *a)
     case OVS_ACTION_ATTR_PUSH_MPLS:
     case OVS_ACTION_ATTR_POP_MPLS:
     case OVS_ACTION_ATTR_TRUNC:
+    case OVS_ACTION_ATTR_PUSH_ETH:
+    case OVS_ACTION_ATTR_POP_ETH:
     case OVS_ACTION_ATTR_CLONE:
         return false;
 
@@ -730,6 +732,8 @@ odp_execute_actions(void *dp, struct dp_packet_batch *batch, bool steal,
         case OVS_ACTION_ATTR_USERSPACE:
         case OVS_ACTION_ATTR_RECIRC:
         case OVS_ACTION_ATTR_CT:
+        case OVS_ACTION_ATTR_PUSH_ETH:
+        case OVS_ACTION_ATTR_POP_ETH:
         case OVS_ACTION_ATTR_UNSPEC:
         case __OVS_ACTION_ATTR_MAX:
             OVS_NOT_REACHED();

lib/odp-util.c

@@ -124,6 +124,8 @@ odp_action_len(uint16_t type)
     case OVS_ACTION_ATTR_SET_MASKED: return ATTR_LEN_VARIABLE;
     case OVS_ACTION_ATTR_SAMPLE: return ATTR_LEN_VARIABLE;
     case OVS_ACTION_ATTR_CT: return ATTR_LEN_VARIABLE;
+    case OVS_ACTION_ATTR_PUSH_ETH: return sizeof(struct ovs_action_push_eth);
+    case OVS_ACTION_ATTR_POP_ETH: return 0;
     case OVS_ACTION_ATTR_CLONE: return ATTR_LEN_VARIABLE;
 
     case OVS_ACTION_ATTR_UNSPEC:
@@ -850,6 +852,16 @@ format_odp_action(struct ds *ds, const struct nlattr *a)
         format_odp_key_attr(nl_attr_get(a), NULL, NULL, ds, true);
         ds_put_cstr(ds, ")");
         break;
+    case OVS_ACTION_ATTR_PUSH_ETH: {
+        const struct ovs_action_push_eth *eth = nl_attr_get(a);
+        ds_put_format(ds, "push_eth(src="ETH_ADDR_FMT",dst="ETH_ADDR_FMT")",
+                      ETH_ADDR_ARGS(eth->addresses.eth_src),
+                      ETH_ADDR_ARGS(eth->addresses.eth_dst));
+        break;
+    }
+    case OVS_ACTION_ATTR_POP_ETH:
+        ds_put_cstr(ds, "pop_eth");
+        break;
     case OVS_ACTION_ATTR_PUSH_VLAN: {
         const struct ovs_action_push_vlan *vlan = nl_attr_get(a);
         ds_put_cstr(ds, "push_vlan(");

ofproto/ofproto-dpif-sflow.c

@@ -1164,6 +1164,13 @@ dpif_sflow_read_actions(const struct flow *flow,
 	    dpif_sflow_pop_mpls_lse(sflow_actions);
 	    break;
 	}
+        case OVS_ACTION_ATTR_PUSH_ETH:
+        case OVS_ACTION_ATTR_POP_ETH:
+            /* TODO: SFlow does not currently define a MAC-in-MAC
+             * encapsulation structure.  We could use an extension
+             * structure to report this.
+             */
+            break;
 	case OVS_ACTION_ATTR_SAMPLE:
 	case OVS_ACTION_ATTR_CLONE:
 	case OVS_ACTION_ATTR_UNSPEC: