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
  ...

1 files changed, 111 insertions, 45 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index da4b33bea982..076df5360ba5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -61,6 +61,9 @@ struct wireless_dev;
 /* 802.15.4 specific */
 struct wpan_dev;
 struct mpls_dev;
+/* UDP Tunnel offloads */
+struct udp_tunnel_info;
+struct bpf_prog;
 
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -90,7 +93,6 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_XMIT_SUCCESS	0x00
 #define NET_XMIT_DROP		0x01	/* skb dropped			*/
 #define NET_XMIT_CN		0x02	/* congestion notification	*/
-#define NET_XMIT_POLICED	0x03	/* skb is shot by police	*/
 #define NET_XMIT_MASK		0x0f	/* qdisc flags in net/sch_generic.h */
 
 /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
@@ -785,6 +787,7 @@ enum {
 	TC_SETUP_MQPRIO,
 	TC_SETUP_CLSU32,
 	TC_SETUP_CLSFLOWER,
+	TC_SETUP_MATCHALL,
 };
 
 struct tc_cls_u32_offload;
@@ -795,9 +798,37 @@ struct tc_to_netdev {
 		u8 tc;
 		struct tc_cls_u32_offload *cls_u32;
 		struct tc_cls_flower_offload *cls_flower;
+		struct tc_cls_matchall_offload *cls_mall;
 	};
 };
 
+/* These structures hold the attributes of xdp state that are being passed
+ * to the netdevice through the xdp op.
+ */
+enum xdp_netdev_command {
+	/* Set or clear a bpf program used in the earliest stages of packet
+	 * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee
+	 * is responsible for calling bpf_prog_put on any old progs that are
+	 * stored. In case of error, the callee need not release the new prog
+	 * reference, but on success it takes ownership and must bpf_prog_put
+	 * when it is no longer used.
+	 */
+	XDP_SETUP_PROG,
+	/* Check if a bpf program is set on the device.  The callee should
+	 * return true if a program is currently attached and running.
+	 */
+	XDP_QUERY_PROG,
+};
+
+struct netdev_xdp {
+	enum xdp_netdev_command command;
+	union {
+		/* XDP_SETUP_PROG */
+		struct bpf_prog *prog;
+		/* XDP_QUERY_PROG */
+		bool prog_attached;
+	};
+};
 
 /*
  * This structure defines the management hooks for network devices.
@@ -1025,31 +1056,18 @@ struct tc_to_netdev {
  *	not implement this, it is assumed that the hw is not able to have
  *	multiple net devices on single physical port.
  *
- * void (*ndo_add_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify a driver about the UDP port and socket
- *	address family that vxlan is listening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	vxlan_net->sock_lock.
- *
- * void (*ndo_add_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify a driver about the UDP port and socket
- *	address family that geneve is listnening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	geneve_net->sock_lock.
- *
- * void (*ndo_del_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify the driver about a UDP port and socket
- *	address family that geneve is not listening to anymore. The operation
- *	is protected by the geneve_net->sock_lock.
- *
- * void (*ndo_del_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify the driver about a UDP port and socket
- *	address family that vxlan is not listening to anymore. The operation
- *	is protected by the vxlan_net->sock_lock.
+ * void (*ndo_udp_tunnel_add)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify a driver about the UDP port and socket
+ *	address family that a UDP tunnel is listnening to. It is called only
+ *	when a new port starts listening. The operation is protected by the
+ *	RTNL.
+ *
+ * void (*ndo_udp_tunnel_del)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify the driver about a UDP port and socket
+ *	address family that the UDP tunnel is not listening to anymore. The
+ *	operation is protected by the RTNL.
  *
  * void* (*ndo_dfwd_add_station)(struct net_device *pdev,
  *				 struct net_device *dev)
@@ -1099,6 +1117,9 @@ struct tc_to_netdev {
  *	appropriate rx headroom value allows avoiding skb head copy on
  *	forward. Setting a negative value resets the rx headroom to the
  *	default value.
+ * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp);
+ *	This function is used to set or query state related to XDP on the
+ *	netdevice. See definition of enum xdp_netdev_command for details.
  *
  */
 struct net_device_ops {
@@ -1221,8 +1242,10 @@ struct net_device_ops {
 						    netdev_features_t features);
 	int			(*ndo_set_features)(struct net_device *dev,
 						    netdev_features_t features);
-	int			(*ndo_neigh_construct)(struct neighbour *n);
-	void			(*ndo_neigh_destroy)(struct neighbour *n);
+	int			(*ndo_neigh_construct)(struct net_device *dev,
+						       struct neighbour *n);
+	void			(*ndo_neigh_destroy)(struct net_device *dev,
+						     struct neighbour *n);
 
 	int			(*ndo_fdb_add)(struct ndmsg *ndm,
 					       struct nlattr *tb[],
@@ -1258,18 +1281,10 @@ struct net_device_ops {
 							struct netdev_phys_item_id *ppid);
 	int			(*ndo_get_phys_port_name)(struct net_device *dev,
 							  char *name, size_t len);
-	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_add_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
-	void			(*ndo_del_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
+	void			(*ndo_udp_tunnel_add)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
+	void			(*ndo_udp_tunnel_del)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
 	void*			(*ndo_dfwd_add_station)(struct net_device *pdev,
 							struct net_device *dev);
 	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
@@ -1289,6 +1304,8 @@ struct net_device_ops {
 						       struct sk_buff *skb);
 	void			(*ndo_set_rx_headroom)(struct net_device *dev,
 						       int needed_headroom);
+	int			(*ndo_xdp)(struct net_device *dev,
+					   struct netdev_xdp *xdp);
 };
 
 /**
@@ -1457,6 +1474,8 @@ enum netdev_priv_flags {
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@ethtool_ops:	Management operations
+ *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
+ *			discovery handling. Necessary for e.g. 6LoWPAN.
  *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
  *			of Layer 2 headers.
  *
@@ -1484,8 +1503,7 @@ enum netdev_priv_flags {
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
- * 	@neigh_priv_len;	Used in neigh_alloc(),
- * 				initialized only in atm/clip.c
+ *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
  * 	@dev_port:		Used to differentiate devices that share
@@ -1594,7 +1612,8 @@ enum netdev_priv_flags {
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *
- *	@qdisc_tx_busylock:	XXX: need comments on this one
+ *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
+ *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -1673,6 +1692,9 @@ struct net_device {
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	const struct l3mdev_ops	*l3mdev_ops;
 #endif
+#if IS_ENABLED(CONFIG_IPV6)
+	const struct ndisc_ops *ndisc_ops;
+#endif
 
 	const struct header_ops *header_ops;
 
@@ -1862,6 +1884,7 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct lock_class_key	*qdisc_tx_busylock;
+	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -1944,6 +1967,23 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_running_key;		\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	(dev)->qdisc_running_key = &qdisc_running_key;		\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key); 		\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
@@ -2233,8 +2273,8 @@ struct netdev_lag_lower_state_info {
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
 #define NETDEV_CHANGELOWERSTATE	0x001B
-#define NETDEV_OFFLOAD_PUSH_VXLAN	0x001C
-#define NETDEV_OFFLOAD_PUSH_GENEVE	0x001D
+#define NETDEV_UDP_TUNNEL_PUSH_INFO	0x001C
+#define NETDEV_CHANGE_TX_QUEUE_LEN	0x001E
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2370,6 +2410,8 @@ void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
 DECLARE_PER_CPU(int, xmit_recursion);
+#define XMIT_RECURSION_LIMIT	10
+
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(xmit_recursion);
@@ -3250,6 +3292,7 @@ int dev_get_phys_port_id(struct net_device *dev,
 int dev_get_phys_port_name(struct net_device *dev,
 			   char *name, size_t len);
 int dev_change_proto_down(struct net_device *dev, bool proto_down);
+int dev_change_xdp_fd(struct net_device *dev, int fd);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
@@ -3799,12 +3842,30 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 
 void *netdev_lower_get_next(struct net_device *dev,
 				struct list_head **iter);
+
 #define netdev_for_each_lower_dev(dev, ldev, iter) \
 	for (iter = (dev)->adj_list.lower.next, \
 	     ldev = netdev_lower_get_next(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
+struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+					     struct list_head **iter);
+struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
+						 struct list_head **iter);
+
+#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
+	for (iter = (dev)->all_adj_list.lower.next, \
+	     ldev = netdev_all_lower_get_next(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_all_lower_get_next(dev, &(iter)))
+
+#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
+	for (iter = (dev)->all_adj_list.lower.next, \
+	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
+
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
@@ -3820,6 +3881,10 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
 void netdev_lower_state_changed(struct net_device *lower_dev,
 				void *lower_state_info);
+int netdev_default_l2upper_neigh_construct(struct net_device *dev,
+					   struct neighbour *n);
+void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
+					  struct neighbour *n);
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
@@ -4012,6 +4077,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }