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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 203 insertions, 143 deletions

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f9e556b..332b5a0 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -59,6 +59,7 @@
 #include "vport-netdev.h"
 
 int ovs_net_id __read_mostly;
+EXPORT_SYMBOL_GPL(ovs_net_id);
 
 static struct genl_family dp_packet_genl_family;
 static struct genl_family dp_flow_genl_family;
@@ -130,27 +131,41 @@ int lockdep_ovsl_is_held(void)
 	else
 		return 1;
 }
+EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
 #endif
 
 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 *);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
+				  const struct sw_flow_key *,
 				  const struct dp_upcall_info *);
 
-/* Must be called with rcu_read_lock or ovs_mutex. */
-static struct datapath *get_dp(struct net *net, int dp_ifindex)
+/* Must be called with rcu_read_lock. */
+static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
 {
-	struct datapath *dp = NULL;
-	struct net_device *dev;
+	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
 
-	rcu_read_lock();
-	dev = dev_get_by_index_rcu(net, dp_ifindex);
 	if (dev) {
 		struct vport *vport = ovs_internal_dev_get_vport(dev);
 		if (vport)
-			dp = vport->dp;
+			return vport->dp;
 	}
+
+	return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+	struct datapath *dp;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	rcu_read_lock();
+	dp = get_dp_rcu(net, dp_ifindex);
 	rcu_read_unlock();
 
 	return dp;
@@ -163,7 +178,7 @@ const char *ovs_dp_name(const struct datapath *dp)
 	return vport->ops->get_name(vport);
 }
 
-static int get_dpifindex(struct datapath *dp)
+static int get_dpifindex(const struct datapath *dp)
 {
 	struct vport *local;
 	int ifindex;
@@ -185,6 +200,7 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 {
 	struct datapath *dp = container_of(rcu, struct datapath, rcu);
 
+	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp->ports);
@@ -243,6 +259,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 	const struct vport *p = OVS_CB(skb)->input_vport;
 	struct datapath *dp = p->dp;
 	struct sw_flow *flow;
+	struct sw_flow_actions *sf_acts;
 	struct dp_stats_percpu *stats;
 	u64 *stats_counter;
 	u32 n_mask_hit;
@@ -256,10 +273,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		int error;
 
 		upcall.cmd = OVS_PACKET_CMD_MISS;
-		upcall.key = key;
 		upcall.userdata = NULL;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
-		error = ovs_dp_upcall(dp, skb, &upcall);
+		upcall.egress_tun_info = NULL;
+		error = ovs_dp_upcall(dp, skb, key, &upcall);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -268,10 +285,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		goto out;
 	}
 
-	OVS_CB(skb)->flow = flow;
+	ovs_flow_stats_update(flow, key->tp.flags, skb);
+	sf_acts = rcu_dereference(flow->sf_acts);
+	ovs_execute_actions(dp, skb, sf_acts, key);
 
-	ovs_flow_stats_update(OVS_CB(skb)->flow, key->tp.flags, skb);
-	ovs_execute_actions(dp, skb, key);
 	stats_counter = &stats->n_hit;
 
 out:
@@ -283,6 +300,7 @@ 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)
 {
 	struct dp_stats_percpu *stats;
@@ -294,9 +312,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 	else
-		err = queue_gso_packets(dp, skb, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info);
 	if (err)
 		goto err;
 
@@ -313,39 +331,43 @@ 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)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
-	struct dp_upcall_info later_info;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
+	struct ovs_skb_cb ovs_cb;
 	int err;
 
+	ovs_cb = *OVS_CB(skb);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		*OVS_CB(skb) = ovs_cb;
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 		if (err)
 			break;
 
-		if (skb == segs && gso_type & SKB_GSO_UDP) {
-			/* The initial flow key extracted by ovs_flow_extract()
-			 * in this case is for a first fragment, so we need to
-			 * properly mark later fragments.
-			 */
-			later_key = *upcall_info->key;
-			later_key.ip.frag = OVS_FRAG_TYPE_LATER;
-
-			later_info = *upcall_info;
-			later_info.key = &later_key;
-			upcall_info = &later_info;
-		}
 	} while ((skb = skb->next));
 
 	/* Free all of the segments. */
@@ -360,46 +382,26 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	return err;
 }
 
-static size_t key_attr_size(void)
-{
-	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
-		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
-		  + nla_total_size(8)   /* OVS_TUNNEL_KEY_ATTR_ID */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TOS */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TTL */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
-		  + nla_total_size(256)   /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
-		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_8021Q */
-		+ nla_total_size(0)   /* OVS_KEY_ATTR_ENCAP */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
-		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
-		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
-}
-
-static size_t upcall_msg_size(const struct nlattr *userdata,
+static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 			      unsigned int hdrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
-		+ nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
 
 	/* OVS_PACKET_ATTR_USERDATA */
-	if (userdata)
-		size += NLA_ALIGN(userdata->nla_len);
+	if (upcall_info->userdata)
+		size += NLA_ALIGN(upcall_info->userdata->nla_len);
+
+	/* OVS_PACKET_ATTR_EGRESS_TUN_KEY */
+	if (upcall_info->egress_tun_info)
+		size += nla_total_size(ovs_tun_key_attr_size());
 
 	return size;
 }
 
 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)
 {
 	struct ovs_header *upcall;
@@ -423,11 +425,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb));
+		nskb = __vlan_hwaccel_push_inside(nskb);
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb->vlan_tci = 0;
 		skb = nskb;
 	}
 
@@ -450,7 +451,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info->userdata, hlen);
+	len = upcall_msg_size(upcall_info, hlen);
 	user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -462,7 +463,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	upcall->dp_ifindex = dp_ifindex;
 
 	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
-	err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+	err = ovs_nla_put_flow(key, key, user_skb);
 	BUG_ON(err);
 	nla_nest_end(user_skb, nla);
 
@@ -471,6 +472,14 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 			  nla_len(upcall_info->userdata),
 			  nla_data(upcall_info->userdata));
 
+	if (upcall_info->egress_tun_info) {
+		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		err = ovs_nla_put_egress_tunnel_key(user_skb,
+						    upcall_info->egress_tun_info);
+		BUG_ON(err);
+		nla_nest_end(user_skb, nla);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
@@ -510,11 +519,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *acts;
 	struct sk_buff *packet;
 	struct sw_flow *flow;
+	struct sw_flow_actions *sf_acts;
 	struct datapath *dp;
 	struct ethhdr *eth;
 	struct vport *input_vport;
 	int len;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	err = -EINVAL;
 	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
@@ -548,29 +559,22 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_skb;
 
 	err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet,
-					     &flow->key);
+					     &flow->key, log);
 	if (err)
 		goto err_flow_free;
 
-	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
-	err = PTR_ERR(acts);
-	if (IS_ERR(acts))
-		goto err_flow_free;
-
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, 0, &acts);
+				   &flow->key, &acts, log);
 	if (err)
 		goto err_flow_free;
 
 	rcu_assign_pointer(flow->sf_acts, acts);
-
 	OVS_CB(packet)->egress_tun_info = NULL;
-	OVS_CB(packet)->flow = flow;
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
 		goto err_unlock;
@@ -583,9 +587,10 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 
 	OVS_CB(packet)->input_vport = input_vport;
+	sf_acts = rcu_dereference(flow->sf_acts);
 
 	local_bh_disable();
-	err = ovs_execute_actions(dp, packet, &flow->key);
+	err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
 	local_bh_enable();
 	rcu_read_unlock();
 
@@ -628,7 +633,7 @@ static struct genl_family dp_packet_genl_family = {
 	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
 };
 
-static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
+static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats,
 			 struct ovs_dp_megaflow_stats *mega_stats)
 {
 	int i;
@@ -662,8 +667,8 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 {
 	return NLMSG_ALIGN(sizeof(struct ovs_header))
-		+ nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_KEY */
-		+ nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_MASK */
+		+ nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_MASK */
 		+ nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */
 		+ nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */
 		+ nla_total_size(8) /* OVS_FLOW_ATTR_USED */
@@ -671,58 +676,67 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 }
 
 /* Called with ovs_mutex or RCU read lock. */
-static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
-				  struct sk_buff *skb, u32 portid,
-				  u32 seq, u32 flags, u8 cmd)
+static int ovs_flow_cmd_fill_match(const struct sw_flow *flow,
+				   struct sk_buff *skb)
 {
-	const int skb_orig_len = skb->len;
-	struct nlattr *start;
-	struct ovs_flow_stats stats;
-	__be16 tcp_flags;
-	unsigned long used;
-	struct ovs_header *ovs_header;
 	struct nlattr *nla;
 	int err;
 
-	ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
-	if (!ovs_header)
-		return -EMSGSIZE;
-
-	ovs_header->dp_ifindex = dp_ifindex;
-
 	/* Fill flow key. */
 	nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
 	if (!nla)
-		goto nla_put_failure;
+		return -EMSGSIZE;
 
 	err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb);
 	if (err)
-		goto error;
+		return err;
+
 	nla_nest_end(skb, nla);
 
+	/* Fill flow mask. */
 	nla = nla_nest_start(skb, OVS_FLOW_ATTR_MASK);
 	if (!nla)
-		goto nla_put_failure;
+		return -EMSGSIZE;
 
 	err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb);
 	if (err)
-		goto error;
+		return err;
 
 	nla_nest_end(skb, nla);
+	return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_stats(const struct sw_flow *flow,
+				   struct sk_buff *skb)
+{
+	struct ovs_flow_stats stats;
+	__be16 tcp_flags;
+	unsigned long used;
 
 	ovs_flow_stats_get(flow, &stats, &used, &tcp_flags);
 
 	if (used &&
 	    nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
-		goto nla_put_failure;
+		return -EMSGSIZE;
 
 	if (stats.n_packets &&
 	    nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats))
-		goto nla_put_failure;
+		return -EMSGSIZE;
 
 	if ((u8)ntohs(tcp_flags) &&
 	     nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags)))
-		goto nla_put_failure;
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow,
+				     struct sk_buff *skb, int skb_orig_len)
+{
+	struct nlattr *start;
+	int err;
 
 	/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
 	 * this is the first flow to be dumped into 'skb'.  This is unusual for
@@ -746,17 +760,47 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 			nla_nest_end(skb, start);
 		else {
 			if (skb_orig_len)
-				goto error;
+				return err;
 
 			nla_nest_cancel(skb, start);
 		}
-	} else if (skb_orig_len)
-		goto nla_put_failure;
+	} else if (skb_orig_len) {
+		return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
+				  struct sk_buff *skb, u32 portid,
+				  u32 seq, u32 flags, u8 cmd)
+{
+	const int skb_orig_len = skb->len;
+	struct ovs_header *ovs_header;
+	int err;
+
+	ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family,
+				 flags, cmd);
+	if (!ovs_header)
+		return -EMSGSIZE;
+
+	ovs_header->dp_ifindex = dp_ifindex;
+
+	err = ovs_flow_cmd_fill_match(flow, skb);
+	if (err)
+		goto error;
+
+	err = ovs_flow_cmd_fill_stats(flow, skb);
+	if (err)
+		goto error;
+
+	err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len);
+	if (err)
+		goto error;
 
 	return genlmsg_end(skb, ovs_header);
 
-nla_put_failure:
-	err = -EMSGSIZE;
 error:
 	genlmsg_cancel(skb, ovs_header);
 	return err;
@@ -811,13 +855,18 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Must have key and actions. */
 	error = -EINVAL;
-	if (!a[OVS_FLOW_ATTR_KEY])
+	if (!a[OVS_FLOW_ATTR_KEY]) {
+		OVS_NLERR(log, "Flow key attr not present in new flow.");
 		goto error;
-	if (!a[OVS_FLOW_ATTR_ACTIONS])
+	}
+	if (!a[OVS_FLOW_ATTR_ACTIONS]) {
+		OVS_NLERR(log, "Flow actions attr not present in new flow.");
 		goto error;
+	}
 
 	/* Most of the time we need to allocate a new flow, do it before
 	 * locking.
@@ -830,24 +879,19 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	/* Extract key. */
 	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto err_kfree_flow;
 
 	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
 
 	/* Validate actions. */
-	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
-	error = PTR_ERR(acts);
-	if (IS_ERR(acts))
-		goto err_kfree_flow;
-
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     0, &acts);
+				     &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-		goto err_kfree_acts;
+		OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
+		goto err_kfree_flow;
 	}
 
 	reply = ovs_flow_cmd_alloc_info(acts, info, false);
@@ -899,6 +943,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		}
 		/* The unmasked key has to be the same for flow updates. */
 		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+			/* Look for any overlapping flow. */
 			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 			if (!flow) {
 				error = -ENOENT;
@@ -938,23 +983,21 @@ error:
 	return error;
 }
 
+/* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
 static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 						const struct sw_flow_key *key,
-						const struct sw_flow_mask *mask)
+						const struct sw_flow_mask *mask,
+						bool log)
 {
 	struct sw_flow_actions *acts;
 	struct sw_flow_key masked_key;
 	int error;
 
-	acts = ovs_nla_alloc_flow_actions(nla_len(a));
-	if (IS_ERR(acts))
-		return acts;
-
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-		kfree(acts);
+		OVS_NLERR(log,
+			  "Actions may not be safe on all matching packets");
 		return ERR_PTR(error);
 	}
 
@@ -973,29 +1016,31 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Extract key. */
 	error = -EINVAL;
-	if (!a[OVS_FLOW_ATTR_KEY])
+	if (!a[OVS_FLOW_ATTR_KEY]) {
+		OVS_NLERR(log, "Flow key attribute not present in set flow.");
 		goto error;
+	}
 
 	ovs_match_init(&match, &key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto error;
 
 	/* Validate actions. */
 	if (a[OVS_FLOW_ATTR_ACTIONS]) {
-		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask,
+					log);
 		if (IS_ERR(acts)) {
 			error = PTR_ERR(acts);
 			goto error;
 		}
-	}
 
-	/* Can allocate before locking if have acts. */
-	if (acts) {
+		/* Can allocate before locking if have acts. */
 		reply = ovs_flow_cmd_alloc_info(acts, info, false);
 		if (IS_ERR(reply)) {
 			error = PTR_ERR(reply);
@@ -1070,14 +1115,16 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow get message rejected, Key attribute missing.\n");
+		OVS_NLERR(log,
+			  "Flow get message rejected, Key attribute missing.");
 		return -EINVAL;
 	}
 
 	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log);
 	if (err)
 		return err;
 
@@ -1118,10 +1165,12 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (likely(a[OVS_FLOW_ATTR_KEY])) {
 		ovs_match_init(&match, &key, NULL);
-		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
 		if (unlikely(err))
 			return err;
 	}
@@ -1179,7 +1228,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	struct datapath *dp;
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	if (!dp) {
 		rcu_read_unlock();
 		return -ENODEV;
@@ -1211,8 +1260,10 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_MASK] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG },
 };
 
 static const struct genl_ops dp_flow_genl_ops[] = {
@@ -1313,7 +1364,7 @@ static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
 
 /* Called with rcu_read_lock or ovs_mutex. */
 static struct datapath *lookup_datapath(struct net *net,
-					struct ovs_header *ovs_header,
+					const struct ovs_header *ovs_header,
 					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
 {
 	struct datapath *dp;
@@ -1341,7 +1392,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in
 	dp->user_features = 0;
 }
 
-static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+static void ovs_dp_change(struct datapath *dp, struct nlattr *a[])
 {
 	if (a[OVS_DP_ATTR_USER_FEATURES])
 		dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
@@ -1442,7 +1493,7 @@ err_destroy_ports_array:
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
-	ovs_flow_tbl_destroy(&dp->table, false);
+	ovs_flow_tbl_destroy(&dp->table);
 err_free_dp:
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
@@ -1474,8 +1525,6 @@ static void __dp_destroy(struct datapath *dp)
 	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 
 	/* RCU destroy the flow table */
-	ovs_flow_tbl_destroy(&dp->table, true);
-
 	call_rcu(&dp->rcu, destroy_dp_rcu);
 }
 
@@ -1707,7 +1756,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 
 /* Called with ovs_mutex or RCU read lock. */
 static struct vport *lookup_vport(struct net *net,
-				  struct ovs_header *ovs_header,
+				  const struct ovs_header *ovs_header,
 				  struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
 {
 	struct datapath *dp;
@@ -1764,6 +1813,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
+restart:
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
@@ -1795,8 +1845,11 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	vport = new_vport(&parms);
 	err = PTR_ERR(vport);
-	if (IS_ERR(vport))
+	if (IS_ERR(vport)) {
+		if (err == -EAGAIN)
+			goto restart;
 		goto exit_unlock_free;
+	}
 
 	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
 				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
@@ -1939,7 +1992,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int i, j = 0;
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	if (!dp) {
 		rcu_read_unlock();
 		return -ENODEV;
@@ -2112,12 +2165,18 @@ static int __init dp_init(void)
 	if (err)
 		goto error_netns_exit;
 
+	err = ovs_netdev_init();
+	if (err)
+		goto error_unreg_notifier;
+
 	err = dp_register_genl();
 	if (err < 0)
-		goto error_unreg_notifier;
+		goto error_unreg_netdev;
 
 	return 0;
 
+error_unreg_netdev:
+	ovs_netdev_exit();
 error_unreg_notifier:
 	unregister_netdevice_notifier(&ovs_dp_device_notifier);
 error_netns_exit:
@@ -2137,6 +2196,7 @@ error:
 static void dp_cleanup(void)
 {
 	dp_unregister_genl(ARRAY_SIZE(dp_genl_families));
+	ovs_netdev_exit();
 	unregister_netdevice_notifier(&ovs_dp_device_notifier);
 	unregister_pernet_device(&ovs_net_ops);
 	rcu_barrier();