Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

r8152 conflicts are the NAPI fixes in 'net' overlapping with
some tasklet stuff in net-next

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

58 files changed, 588 insertions, 404 deletions

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 240ed70912d6..d78938e3e008 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -277,17 +277,23 @@ static u8 batadv_hop_penalty(u8 tq, const struct batadv_priv *bat_priv)
  * batadv_iv_ogm_aggr_packet() - checks if there is another OGM attached
  * @buff_pos: current position in the skb
  * @packet_len: total length of the skb
- * @tvlv_len: tvlv length of the previously considered OGM
+ * @ogm_packet: potential OGM in buffer
  *
  * Return: true if there is enough space for another OGM, false otherwise.
  */
-static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
-				      __be16 tvlv_len)
+static bool
+batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
+			  const struct batadv_ogm_packet *ogm_packet)
 {
 	int next_buff_pos = 0;
 
-	next_buff_pos += buff_pos + BATADV_OGM_HLEN;
-	next_buff_pos += ntohs(tvlv_len);
+	/* check if there is enough space for the header */
+	next_buff_pos += buff_pos + sizeof(*ogm_packet);
+	if (next_buff_pos > packet_len)
+		return false;
+
+	/* check if there is enough space for the optional TVLV */
+	next_buff_pos += ntohs(ogm_packet->tvlv_len);
 
 	return (next_buff_pos <= packet_len) &&
 	       (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
@@ -315,7 +321,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 
 	/* adjust all flags and log packets */
 	while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len,
-					 batadv_ogm_packet->tvlv_len)) {
+					 batadv_ogm_packet)) {
 		/* we might have aggregated direct link packets with an
 		 * ordinary base packet
 		 */
@@ -1704,7 +1710,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
 
 	/* unpack the aggregated packets and process them one by one */
 	while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb),
-					 ogm_packet->tvlv_len)) {
+					 ogm_packet)) {
 		batadv_iv_ogm_process(skb, ogm_offset, if_incoming);
 
 		ogm_offset += BATADV_OGM_HLEN;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 319249f0f85f..dc4f7430cb5a 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -806,17 +806,23 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv,
  * batadv_v_ogm_aggr_packet() - checks if there is another OGM aggregated
  * @buff_pos: current position in the skb
  * @packet_len: total length of the skb
- * @tvlv_len: tvlv length of the previously considered OGM
+ * @ogm2_packet: potential OGM2 in buffer
  *
  * Return: true if there is enough space for another OGM, false otherwise.
  */
-static bool batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
-				     __be16 tvlv_len)
+static bool
+batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
+			 const struct batadv_ogm2_packet *ogm2_packet)
 {
 	int next_buff_pos = 0;
 
-	next_buff_pos += buff_pos + BATADV_OGM2_HLEN;
-	next_buff_pos += ntohs(tvlv_len);
+	/* check if there is enough space for the header */
+	next_buff_pos += buff_pos + sizeof(*ogm2_packet);
+	if (next_buff_pos > packet_len)
+		return false;
+
+	/* check if there is enough space for the optional TVLV */
+	next_buff_pos += ntohs(ogm2_packet->tvlv_len);
 
 	return (next_buff_pos <= packet_len) &&
 	       (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
@@ -993,7 +999,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 	ogm_packet = (struct batadv_ogm2_packet *)skb->data;
 
 	while (batadv_v_ogm_aggr_packet(ogm_offset, skb_headlen(skb),
-					ogm_packet->tvlv_len)) {
+					ogm_packet)) {
 		batadv_v_ogm_process(skb, ogm_offset, if_incoming);
 
 		ogm_offset += BATADV_OGM2_HLEN;
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 1804e867f715..7c9e92b2f806 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -53,7 +53,7 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 			goto err;
 
 		br_vlan_get_proto(br_dev, &p_proto);
-		nft_reg_store16(dest, p_proto);
+		nft_reg_store16(dest, htons(p_proto));
 		return;
 	}
 	default:
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 5d6724cee38f..4f75df40fb12 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -136,8 +136,10 @@ void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
 	if (key) {
 		kfree(key->key);
 		key->key = NULL;
-		crypto_free_sync_skcipher(key->tfm);
-		key->tfm = NULL;
+		if (key->tfm) {
+			crypto_free_sync_skcipher(key->tfm);
+			key->tfm = NULL;
+		}
 	}
 }
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2cf27da1baeb..849380a622ef 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work)
 		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
-		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+		    !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
 			skb_queue_head(&npinfo->txq, skb);
 			HARD_TX_UNLOCK(dev, txq);
 			local_irq_restore(flags);
@@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 				HARD_TX_UNLOCK(dev, txq);
 
-				if (status == NETDEV_TX_OK)
+				if (dev_xmit_complete(status))
 					break;
 
 			}
@@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 	}
 
-	if (status != NETDEV_TX_OK) {
+	if (!dev_xmit_complete(status)) {
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index e44e6275b0a1..9c1cc2482b68 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -28,6 +28,7 @@
  *
  * RSV - VID[9]:
  *	To be used for further expansion of SWITCH_ID or for other purposes.
+ *	Must be transmitted as zero and ignored on receive.
  *
  * SWITCH_ID - VID[8:6]:
  *	Index of switch within DSA tree. Must be between 0 and
@@ -35,6 +36,7 @@
  *
  * RSV - VID[5:4]:
  *	To be used for further expansion of PORT or for other purposes.
+ *	Must be transmitted as zero and ignored on receive.
  *
  * PORT - VID[3:0]:
  *	Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 051ef10374f6..94df48bcecc2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+	if (skb && !skb->len) {
+		tcp_unlink_write_queue(skb, sk);
+		if (tcp_write_queue_empty(sk))
+			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -1064,6 +1080,7 @@ out:
 	return copied;
 
 do_error:
+	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
 	if (copied)
 		goto out;
 out_err:
@@ -1389,18 +1406,11 @@ out_nopush:
 	sock_zerocopy_put(uarg);
 	return copied + copied_syn;
 
+do_error:
+	skb = tcp_write_queue_tail(sk);
 do_fault:
-	if (!skb->len) {
-		tcp_unlink_write_queue(skb, sk);
-		/* It is the one place in all of TCP, except connection
-		 * reset, where we can be unlinking the send_head.
-		 */
-		if (tcp_write_queue_empty(sk))
-			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-		sk_wmem_free_skb(sk, skb);
-	}
+	tcp_remove_empty_skb(sk, skb);
 
-do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5c46bc4c7e8d..42abc9bd687a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2053,7 +2053,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor))
+		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
 			return false;
 
 		len -= skb->len;
@@ -2170,6 +2170,7 @@ static int tcp_mtu_probe(struct sock *sk)
 			 * we need to propagate it to the new skb.
 			 */
 			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
+			tcp_skb_collapse_tstamp(nskb, skb);
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f3f13c37916..eaa4c2cc2fbb 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -787,14 +787,15 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	if (pmc) {
 		im->idev = pmc->idev;
 		if (im->mca_sfmode == MCAST_INCLUDE) {
-			im->mca_tomb = pmc->mca_tomb;
-			im->mca_sources = pmc->mca_sources;
+			swap(im->mca_tomb, pmc->mca_tomb);
+			swap(im->mca_sources, pmc->mca_sources);
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
 				psf->sf_crcount = idev->mc_qrv;
 		} else {
 			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
+		ip6_mc_clear_src(pmc);
 		kfree(pmc);
 	}
 	spin_unlock_bh(&im->mca_lock);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3c1ab870fefe..768d14c9a716 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2447,11 +2447,13 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
 		      skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) &&
 		     sdata->control_port_over_nl80211)) {
 		struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-		bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
+		bool noencrypt = !(status->flag & RX_FLAG_DECRYPTED);
 
 		cfg80211_rx_control_port(dev, skb, noencrypt);
 		dev_kfree_skb(skb);
 	} else {
+		memset(skb->cb, 0, sizeof(skb->cb));
+
 		/* deliver to local stack */
 		if (rx->napi)
 			napi_gro_receive(rx->napi, skb);
@@ -2546,8 +2548,6 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 
 	if (skb) {
 		skb->protocol = eth_type_trans(skb, dev);
-		memset(skb->cb, 0, sizeof(skb->cb));
-
 		ieee80211_deliver_skb_to_local_stack(skb, rx);
 	}
 
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index c57d2348c505..9eca90414bb7 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -322,7 +322,7 @@ static int find_pattern(const char *data, size_t dlen,
 		i++;
 	}
 
-	pr_debug("Skipped up to `%c'!\n", skip);
+	pr_debug("Skipped up to 0x%hhx delimiter!\n", skip);
 
 	*numoff = i;
 	*numlen = getnum(data + i, dlen - i, cmd, term, numoff);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index d97f4ea47cf3..88d4127df863 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -1035,9 +1035,14 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_COUNT].data = &net->ct.count;
 	table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
 	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
+	table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct;
+	table[NF_SYSCTL_CT_HELPER].data = &net->ct.sysctl_auto_assign_helper;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events;
 #endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp;
+#endif
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout;
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout;
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index d68c801dd614..b9e7dd6e60ce 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -228,7 +228,6 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 {
 	skb_orphan(skb);
 	skb_dst_set_noref(skb, dst);
-	skb->tstamp = 0;
 	dst_output(state->net, state->sk, skb);
 	return NF_STOLEN;
 }
@@ -284,6 +283,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
 	iph = ip_hdr(skb);
 	ip_decrease_ttl(iph);
+	skb->tstamp = 0;
 
 	if (unlikely(dst_xfrm(&rt->dst))) {
 		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
@@ -512,6 +512,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
 	ip6h = ipv6_hdr(skb);
 	ip6h->hop_limit--;
+	skb->tstamp = 0;
 
 	if (unlikely(dst_xfrm(&rt->dst))) {
 		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index ead7c6022208..b92b22ce8abd 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -101,11 +101,9 @@ static int physdev_mt_check(const struct xt_mtchk_param *par)
 	if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) &&
 	    (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) ||
 	     info->invert & XT_PHYSDEV_OP_BRIDGED) &&
-	    par->hook_mask & ((1 << NF_INET_LOCAL_OUT) |
-	    (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) {
+	    par->hook_mask & (1 << NF_INET_LOCAL_OUT)) {
 		pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n");
-		if (par->hook_mask & (1 << NF_INET_LOCAL_OUT))
-			return -EINVAL;
+		return -EINVAL;
 	}
 
 	if (!brnf_probed) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index d8da6477d6be..05249eb45082 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -525,6 +525,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 		return -EPFNOSUPPORT;
 	}
 
+	/* The key extracted from the fragment that completed this datagram
+	 * likely didn't have an L4 header, so regenerate it.
+	 */
+	ovs_flow_key_update_l3l4(skb, key);
+
 	key->ip.frag = OVS_FRAG_TYPE_NONE;
 	skb_clear_hash(skb);
 	skb->ignore_df = 1;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index bc89e16e0505..9d81d2c7bf82 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)) {
@@ -623,6 +560,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		offset = nh->frag_off & htons(IP_OFFSET);
 		if (offset) {
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
+			memset(&key->tp, 0, sizeof(key->tp));
 			return 0;
 		}
 		if (nh->frag_off & htons(IP_MF) ||
@@ -740,8 +678,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			return error;
 		}
 
-		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+		if (key->ip.frag == OVS_FRAG_TYPE_LATER) {
+			memset(&key->tp, 0, sizeof(key->tp));
 			return 0;
+		}
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 
@@ -788,6 +728,92 @@ 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_vl