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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 98 insertions, 52 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 45109b70664e..af4a1b0adc10 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -660,6 +660,27 @@ __setup("netdev=", netdev_boot_setup);
 *******************************************************************************/
 
 /**
+ *	dev_get_iflink	- get 'iflink' value of a interface
+ *	@dev: targeted interface
+ *
+ *	Indicates the ifindex the interface is linked to.
+ *	Physical interfaces have the same 'ifindex' and 'iflink' values.
+ */
+
+int dev_get_iflink(const struct net_device *dev)
+{
+	if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
+		return dev->netdev_ops->ndo_get_iflink(dev);
+
+	/* If dev->rtnl_link_ops is set, it's a virtual interface. */
+	if (dev->rtnl_link_ops)
+		return 0;
+
+	return dev->ifindex;
+}
+EXPORT_SYMBOL(dev_get_iflink);
+
+/**
  *	__dev_get_by_name	- find a device by its name
  *	@net: the applicable net namespace
  *	@name: name to find
@@ -1385,7 +1406,7 @@ static int __dev_close(struct net_device *dev)
 	return retval;
 }
 
-static int dev_close_many(struct list_head *head)
+int dev_close_many(struct list_head *head, bool unlink)
 {
 	struct net_device *dev, *tmp;
 
@@ -1399,11 +1420,13 @@ static int dev_close_many(struct list_head *head)
 	list_for_each_entry_safe(dev, tmp, head, close_list) {
 		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
 		call_netdevice_notifiers(NETDEV_DOWN, dev);
-		list_del_init(&dev->close_list);
+		if (unlink)
+			list_del_init(&dev->close_list);
 	}
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_close_many);
 
 /**
  *	dev_close - shutdown an interface.
@@ -1420,7 +1443,7 @@ int dev_close(struct net_device *dev)
 		LIST_HEAD(single);
 
 		list_add(&dev->close_list, &single);
-		dev_close_many(&single);
+		dev_close_many(&single, true);
 		list_del(&single);
 	}
 	return 0;
@@ -1607,6 +1630,22 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
+#ifdef CONFIG_NET_CLS_ACT
+static struct static_key ingress_needed __read_mostly;
+
+void net_inc_ingress_queue(void)
+{
+	static_key_slow_inc(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
+
+void net_dec_ingress_queue(void)
+{
+	static_key_slow_dec(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
+#endif
+
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 /* We are not allowed to call static_key_slow_dec() from irq context
@@ -1694,6 +1733,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 	}
 
 	skb_scrub_packet(skb, true);
+	skb->priority = 0;
 	skb->protocol = eth_type_trans(skb, dev);
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
@@ -1737,7 +1777,8 @@ static inline int deliver_skb(struct sk_buff *skb,
 
 static inline void deliver_ptype_list_skb(struct sk_buff *skb,
 					  struct packet_type **pt,
-					  struct net_device *dev, __be16 type,
+					  struct net_device *orig_dev,
+					  __be16 type,
 					  struct list_head *ptype_list)
 {
 	struct packet_type *ptype, *pt_prev = *pt;
@@ -1746,7 +1787,7 @@ static inline void deliver_ptype_list_skb(struct sk_buff *skb,
 		if (ptype->type != type)
 			continue;
 		if (pt_prev)
-			deliver_skb(skb, pt_prev, dev);
+			deliver_skb(skb, pt_prev, orig_dev);
 		pt_prev = ptype;
 	}
 	*pt = pt_prev;
@@ -2559,12 +2600,26 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	return features;
 }
 
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+					  struct net_device *dev,
+					  netdev_features_t features)
+{
+	return features;
+}
+EXPORT_SYMBOL(passthru_features_check);
+
+static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+					     struct net_device *dev,
+					     netdev_features_t features)
+{
+	return vlan_features_check(skb, features);
+}
+
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
 	u16 gso_segs = skb_shinfo(skb)->gso_segs;
-	__be16 protocol = skb->protocol;
 
 	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
@@ -2576,34 +2631,17 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
-	if (!skb_vlan_tag_present(skb)) {
-		if (unlikely(protocol == htons(ETH_P_8021Q) ||
-			     protocol == htons(ETH_P_8021AD))) {
-			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-			protocol = veh->h_vlan_encapsulated_proto;
-		} else {
-			goto finalize;
-		}
-	}
-
-	features = netdev_intersect_features(features,
-					     dev->vlan_features |
-					     NETIF_F_HW_VLAN_CTAG_TX |
-					     NETIF_F_HW_VLAN_STAG_TX);
-
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
+	if (skb_vlan_tagged(skb))
 		features = netdev_intersect_features(features,
-						     NETIF_F_SG |
-						     NETIF_F_HIGHDMA |
-						     NETIF_F_FRAGLIST |
-						     NETIF_F_GEN_CSUM |
+						     dev->vlan_features |
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
-finalize:
 	if (dev->netdev_ops->ndo_features_check)
 		features &= dev->netdev_ops->ndo_features_check(skb, dev,
 								features);
+	else
+		features &= dflt_features_check(skb, dev, features);
 
 	return harmonize_features(skb, features);
 }
@@ -2857,7 +2895,7 @@ EXPORT_SYMBOL(xmit_recursion);
  *	dev_loopback_xmit - loop back @skb
  *	@skb: buffer to transmit
  */
-int dev_loopback_xmit(struct sk_buff *skb)
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	skb_reset_mac_header(skb);
 	__skb_pull(skb, skb_network_offset(skb));
@@ -2995,11 +3033,11 @@ out:
 	return rc;
 }
 
-int dev_queue_xmit(struct sk_buff *skb)
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb)
 {
 	return __dev_queue_xmit(skb, NULL);
 }
-EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_queue_xmit_sk);
 
 int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
 {
@@ -3525,7 +3563,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
 
 	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
-		goto out;
+		return skb;
 
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
@@ -3539,8 +3577,6 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 		return NULL;
 	}
 
-out:
-	skb->tc_verd = 0;
 	return skb;
 }
 #endif
@@ -3676,12 +3712,15 @@ another_round:
 
 skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
-	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
-	if (!skb)
-		goto unlock;
+	if (static_key_false(&ingress_needed)) {
+		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
+		if (!skb)
+			goto unlock;
+	}
+
+	skb->tc_verd = 0;
 ncls:
 #endif
-
 	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
 		goto drop;
 
@@ -3831,13 +3870,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
  *	NET_RX_SUCCESS: no congestion
  *	NET_RX_DROP: packet was dropped
  */
-int netif_receive_skb(struct sk_buff *skb)
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb)
 {
 	trace_netif_receive_skb_entry(skb);
 
 	return netif_receive_skb_internal(skb);
 }
-EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_receive_skb_sk);
 
 /* Network device is going away, flush any packets still pending
  * Called with irqs disabled.
@@ -5914,6 +5953,24 @@ int dev_get_phys_port_id(struct net_device *dev,
 EXPORT_SYMBOL(dev_get_phys_port_id);
 
 /**
+ *	dev_get_phys_port_name - Get device physical port name
+ *	@dev: device
+ *	@name: port name
+ *
+ *	Get device physical port name
+ */
+int dev_get_phys_port_name(struct net_device *dev,
+			   char *name, size_t len)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_phys_port_name)
+		return -EOPNOTSUPP;
+	return ops->ndo_get_phys_port_name(dev, name, len);
+}
+EXPORT_SYMBOL(dev_get_phys_port_name);
+
+/**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
  *
@@ -5970,7 +6027,7 @@ static void rollback_registered_many(struct list_head *head)
 	/* If device is running, close it first. */
 	list_for_each_entry(dev, head, unreg_list)
 		list_add_tail(&dev->close_list, &close_head);
-	dev_close_many(&close_head);
+	dev_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
@@ -6297,8 +6354,6 @@ int register_netdevice(struct net_device *dev)
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 
-	dev->iflink = -1;
-
 	ret = dev_get_valid_name(net, dev, dev->name);
 	if (ret < 0)
 		goto out;
@@ -6328,9 +6383,6 @@ int register_netdevice(struct net_device *dev)
 	else if (__dev_get_by_index(net, dev->ifindex))
 		goto err_uninit;
 
-	if (dev->iflink == -1)
-		dev->iflink = dev->ifindex;
-
 	/* Transfer changeable features to wanted_features and enable
 	 * software offloads (GSO and GRO).
 	 */
@@ -6843,8 +6895,6 @@ void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
 
-	release_net(dev_net(dev));
-
 	netif_free_tx_queues(dev);
 #ifdef CONFIG_SYSFS
 	kvfree(dev->_rx);
@@ -7045,12 +7095,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	dev_net_set(dev, net);
 
 	/* If there is an ifindex conflict assign a new one */
-	if (__dev_get_by_index(net, dev->ifindex)) {
-		int iflink = (dev->iflink == dev->ifindex);
+	if (__dev_get_by_index(net, dev->ifindex))
 		dev->ifindex = dev_new_index(net);
-		if (iflink)
-			dev->iflink = dev->ifindex;
-	}
 
 	/* Send a netdev-add uevent to the new namespace */
 	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);