Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

7 files changed, 127 insertions, 45 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 9a3eb7a0ebf4..1ecbd7715f6d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -750,6 +750,14 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 	if (likely(vport)) {
 		u16 mru = OVS_CB(skb)->mru;
+		u32 cutlen = OVS_CB(skb)->cutlen;
+
+		if (unlikely(cutlen > 0)) {
+			if (skb->len - cutlen > ETH_HLEN)
+				pskb_trim(skb, skb->len - cutlen);
+			else
+				pskb_trim(skb, ETH_HLEN);
+		}
 
 		if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
 			ovs_vport_send(vport, skb);
@@ -775,7 +783,8 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr,
-			    const struct nlattr *actions, int actions_len)
+			    const struct nlattr *actions, int actions_len,
+			    uint32_t cutlen)
 {
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
@@ -822,7 +831,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 		} /* End of switch. */
 	}
 
-	return ovs_dp_upcall(dp, skb, key, &upcall);
+	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
 static int sample(struct datapath *dp, struct sk_buff *skb,
@@ -832,6 +841,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	const struct nlattr *acts_list = NULL;
 	const struct nlattr *a;
 	int rem;
+	u32 cutlen = 0;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -858,13 +868,24 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 		return 0;
 
 	/* The only known usage of sample action is having a single user-space
+	 * action, or having a truncate action followed by a single user-space
 	 * action. Treat this usage as a special case.
 	 * The output_userspace() should clone the skb to be sent to the
 	 * user space. This skb will be consumed by its caller.
 	 */
+	if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
+		struct ovs_action_trunc *trunc = nla_data(a);
+
+		if (skb->len > trunc->max_len)
+			cutlen = skb->len - trunc->max_len;
+
+		a = nla_next(a, &rem);
+	}
+
 	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
 		   nla_is_last(a, rem)))
-		return output_userspace(dp, skb, key, a, actions, actions_len);
+		return output_userspace(dp, skb, key, a, actions,
+					actions_len, cutlen);
 
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (!skb)
@@ -1051,6 +1072,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			if (out_skb)
 				do_output(dp, out_skb, prev_port, key);
 
+			OVS_CB(skb)->cutlen = 0;
 			prev_port = -1;
 		}
 
@@ -1059,8 +1081,18 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			prev_port = nla_get_u32(a);
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (skb->len > trunc->max_len)
+				OVS_CB(skb)->cutlen = skb->len - trunc->max_len;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_USERSPACE:
-			output_userspace(dp, skb, key, a, attr, len);
+			output_userspace(dp, skb, key, a, attr,
+						     len, OVS_CB(skb)->cutlen);
+			OVS_CB(skb)->cutlen = 0;
 			break;
 
 		case OVS_ACTION_ATTR_HASH:
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index d84312584ee4..c644c78ed485 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -135,7 +135,7 @@ static void ovs_ct_get_labels(const struct nf_conn *ct,
 	struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
 
 	if (cl) {
-		size_t len = cl->words * sizeof(long);
+		size_t len = sizeof(cl->bits);
 
 		if (len > OVS_CT_LABELS_LEN)
 			len = OVS_CT_LABELS_LEN;
@@ -274,7 +274,7 @@ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key,
 		nf_ct_labels_ext_add(ct);
 		cl = nf_ct_labels_find(ct);
 	}
-	if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN)
+	if (!cl || sizeof(cl->bits) < OVS_CT_LABELS_LEN)
 		return -ENOSPC;
 
 	err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask,
@@ -834,6 +834,17 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 	return 0;
 }
 
+static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
+{
+	size_t i;
+
+	for (i = 0; i < sizeof(*labels); i++)
+		if (labels->ct_labels[i])
+			return true;
+
+	return false;
+}
+
 /* Lookup connection and confirm if unconfirmed. */
 static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 			 const struct ovs_conntrack_info *info,
@@ -844,24 +855,32 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 	err = __ovs_ct_lookup(net, key, info, skb);
 	if (err)
 		return err;
-	/* This is a no-op if the connection has already been confirmed. */
+
+	/* Apply changes before confirming the connection so that the initial
+	 * conntrack NEW netlink event carries the values given in the CT
+	 * action.
+	 */
+	if (info->mark.mask) {
+		err = ovs_ct_set_mark(skb, key, info->mark.value,
+				      info->mark.mask);
+		if (err)
+			return err;
+	}
+	if (labels_nonzero(&info->labels.mask)) {
+		err = ovs_ct_set_labels(skb, key, &info->labels.value,
+					&info->labels.mask);
+		if (err)
+			return err;
+	}
+	/* This will take care of sending queued events even if the connection
+	 * is already confirmed.
+	 */
 	if (nf_conntrack_confirm(skb) != NF_ACCEPT)
 		return -EINVAL;
 
 	return 0;
 }
 
-static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
-{
-	size_t i;
-
-	for (i = 0; i < sizeof(*labels); i++)
-		if (labels->ct_labels[i])
-			return true;
-
-	return false;
-}
-
 /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
  * value if 'skb' is freed.
  */
@@ -886,19 +905,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 		err = ovs_ct_commit(net, key, info, skb);
 	else
 		err = ovs_ct_lookup(net, key, info, skb);
-	if (err)
-		goto err;
 
-	if (info->mark.mask) {
-		err = ovs_ct_set_mark(skb, key, info->mark.value,
-				      info->mark.mask);
-		if (err)
-			goto err;
-	}
-	if (labels_nonzero(&info->labels.mask))
-		err = ovs_ct_set_labels(skb, key, &info->labels.value,
-					&info->labels.mask);
-err:
 	skb_push(skb, nh_ofs);
 	if (err)
 		kfree_skb(skb);
@@ -1155,6 +1162,20 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 		}
 	}
 
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	if (!info->commit && info->mark.mask) {
+		OVS_NLERR(log,
+			  "Setting conntrack mark requires 'commit' flag.");
+		return -EINVAL;
+	}
+#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+	if (!info->commit && labels_nonzero(&info->labels.mask)) {
+		OVS_NLERR(log,
+			  "Setting conntrack labels requires 'commit' flag.");
+		return -EINVAL;
+	}
+#endif
 	if (rem > 0) {
 		OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem);
 		return -EINVAL;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 856bd8dba676..524c0fd3078e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -137,10 +137,12 @@ EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
 static struct vport *new_vport(const struct vport_parms *);
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
 			     const struct sw_flow_key *,
-			     const struct dp_upcall_info *);
+			     const struct dp_upcall_info *,
+			     uint32_t cutlen);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct sw_flow_key *,
-				  const struct dp_upcall_info *);
+				  const struct dp_upcall_info *,
+				  uint32_t cutlen);
 
 /* Must be called with rcu_read_lock. */
 static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
@@ -275,7 +277,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		upcall.cmd = OVS_PACKET_CMD_MISS;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
 		upcall.mru = OVS_CB(skb)->mru;
-		error = ovs_dp_upcall(dp, skb, key, &upcall);
+		error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -300,7 +302,8 @@ out:
 
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		  const struct sw_flow_key *key,
-		  const struct dp_upcall_info *upcall_info)
+		  const struct dp_upcall_info *upcall_info,
+		  uint32_t cutlen)
 {
 	struct dp_stats_percpu *stats;
 	int err;
@@ -311,9 +314,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 	else
-		err = queue_gso_packets(dp, skb, key, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info, cutlen);
 	if (err)
 		goto err;
 
@@ -331,7 +334,8 @@ err:
 
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct sw_flow_key *key,
-			     const struct dp_upcall_info *upcall_info)
+			     const struct dp_upcall_info *upcall_info,
+				 uint32_t cutlen)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
@@ -360,7 +364,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
 
@@ -383,7 +387,8 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
-		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(sizeof(unsigned int)); /* OVS_PACKET_ATTR_LEN */
 
 	/* OVS_PACKET_ATTR_USERDATA */
 	if (upcall_info->userdata)
@@ -416,7 +421,8 @@ static void pad_packet(struct datapath *dp, struct sk_buff *skb)
 
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 				  const struct sw_flow_key *key,
-				  const struct dp_upcall_info *upcall_info)
+				  const struct dp_upcall_info *upcall_info,
+				  uint32_t cutlen)
 {
 	struct ovs_header *upcall;
 	struct sk_buff *nskb = NULL;
@@ -461,7 +467,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -509,15 +515,25 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		pad_packet(dp, user_skb);
 	}
 
+	/* Add OVS_PACKET_ATTR_LEN when packet is truncated */
+	if (cutlen > 0) {
+		if (nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN,
+				skb->len)) {
+			err = -ENOBUFS;
+			goto out;
+		}
+		pad_packet(dp, user_skb);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
 		err = -ENOBUFS;
 		goto out;
 	}
-	nla->nla_len = nla_attr_size(skb->len);
+	nla->nla_len = nla_attr_size(skb->len - cutlen);
 
-	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len - cutlen, hlen);
 	if (err)
 		goto out;
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 427e39a045cf..ab85c1cae255 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -100,11 +100,13 @@ struct datapath {
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
 
@@ -194,7 +196,8 @@ extern struct genl_family dp_vport_genl_family;
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
-		  const struct sw_flow_key *, const struct dp_upcall_info *);
+		  const struct sw_flow_key *, const struct dp_upcall_info *,
+		  uint32_t cutlen);
 
 const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 0bb650f4f219..c78a6a1476fb 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2229,6 +2229,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
 			[OVS_ACTION_ATTR_CT] = (u32)-1,
+			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -2255,6 +2256,14 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			const struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (trunc->max_len < ETH_HLEN)
+				return -EINVAL;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_HASH: {
 			const struct ovs_action_hash *act_hash = nla_data(a);
 
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 2ee48e447b72..434e04c3a189 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -195,7 +195,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 	}
 
 	vport->dev = alloc_netdev(sizeof(struct internal_dev),
-				  parms->name, NET_NAME_UNKNOWN, do_setup);
+				  parms->name, NET_NAME_USER, do_setup);
 	if (!vport->dev) {
 		err = -ENOMEM;
 		goto error_free_vport;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 31cbc8c5c7db..6b21fd068d87 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -444,6 +444,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 
 	OVS_CB(skb)->input_vport = vport;
 	OVS_CB(skb)->mru = 0;
+	OVS_CB(skb)->cutlen = 0;
 	if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
 		u32 mark;