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

Pull networking updates from Davic Miller:

 1) Support busy polling generically, for all NAPI drivers.  From Eric
    Dumazet.

 2) Add byte/packet counter support to nft_ct, from Floriani Westphal.

 3) Add RSS/XPS support to mvneta driver, from Gregory Clement.

 4) Implement IPV6_HDRINCL socket option for raw sockets, from Hannes
    Frederic Sowa.

 5) Add support for T6 adapter to cxgb4 driver, from Hariprasad Shenai.

 6) Add support for VLAN device bridging to mlxsw switch driver, from
    Ido Schimmel.

 7) Add driver for Netronome NFP4000/NFP6000, from Jakub Kicinski.

 8) Provide hwmon interface to mlxsw switch driver, from Jiri Pirko.

 9) Reorganize wireless drivers into per-vendor directories just like we
    do for ethernet drivers.  From Kalle Valo.

10) Provide a way for administrators "destroy" connected sockets via the
    SOCK_DESTROY socket netlink diag operation.  From Lorenzo Colitti.

11) Add support to add/remove multicast routes via netlink, from Nikolay
    Aleksandrov.

12) Make TCP keepalive settings per-namespace, from Nikolay Borisov.

13) Add forwarding and packet duplication facilities to nf_tables, from
    Pablo Neira Ayuso.

14) Dead route support in MPLS, from Roopa Prabhu.

15) TSO support for thunderx chips, from Sunil Goutham.

16) Add driver for IBM's System i/p VNIC protocol, from Thomas Falcon.

17) Rationalize, consolidate, and more completely document the checksum
    offloading facilities in the networking stack.  From Tom Herbert.

18) Support aborting an ongoing scan in mac80211/cfg80211, from
    Vidyullatha Kanchanapally.

19) Use per-bucket spinlock for bpf hash facility, from Tom Leiming.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1375 commits)
  net: bnxt: always return values from _bnxt_get_max_rings
  net: bpf: reject invalid shifts
  phonet: properly unshare skbs in phonet_rcv()
  dwc_eth_qos: Fix dma address for multi-fragment skbs
  phy: remove an unneeded condition
  mdio: remove an unneed condition
  mdio_bus: NULL dereference on allocation error
  net: Fix typo in netdev_intersect_features
  net: freescale: mac-fec: Fix build error from phy_device API change
  net: freescale: ucc_geth: Fix build error from phy_device API change
  bonding: Prevent IPv6 link local address on enslaved devices
  IB/mlx5: Add flow steering support
  net/mlx5_core: Export flow steering API
  net/mlx5_core: Make ipv4/ipv6 location more clear
  net/mlx5_core: Enable flow steering support for the IB driver
  net/mlx5_core: Initialize namespaces only when supported by device
  net/mlx5_core: Set priority attributes
  net/mlx5_core: Connect flow tables
  net/mlx5_core: Introduce modify flow table command
  net/mlx5_core: Managing root flow table
  ...

1 files changed, 23 insertions, 21 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 14d3c0734007..e830c1006935 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -58,6 +58,8 @@
 #include <linux/memcontrol.h>
 #include <linux/static_key.h>
 #include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/cgroup-defs.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
@@ -287,7 +289,6 @@ struct cg_proto;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_priority: %SO_PRIORITY setting
-  *	@sk_cgrp_prioidx: socket group's priority map index
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
   *	@sk_peer_pid: &struct pid for this socket's peer
@@ -308,7 +309,7 @@ struct cg_proto;
   *	@sk_send_head: front of stuff to transmit
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
-  *	@sk_classid: this socket's cgroup classid
+  *	@sk_cgrp_data: cgroup data for this cgroup
   *	@sk_cgrp: this socket's cgroup-specific proto data
   *	@sk_write_pending: a write to stream socket waits to start
   *	@sk_state_change: callback to indicate change in the state of the sock
@@ -317,6 +318,7 @@ struct cg_proto;
   *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
   *	@sk_backlog_rcv: callback to process the backlog
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
+  *	@sk_reuseport_cb: reuseport group container
  */
 struct sock {
 	/*
@@ -425,9 +427,7 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	__u32			sk_priority;
-#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
-	__u32			sk_cgrp_prioidx;
-#endif
+	__u32			sk_mark;
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
@@ -445,10 +445,7 @@ struct sock {
 #ifdef CONFIG_SECURITY
 	void			*sk_security;
 #endif
-	__u32			sk_mark;
-#ifdef CONFIG_CGROUP_NET_CLASSID
-	u32			sk_classid;
-#endif
+	struct sock_cgroup_data	sk_cgrp_data;
 	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
 	void			(*sk_data_ready)(struct sock *sk);
@@ -457,6 +454,7 @@ struct sock {
 	int			(*sk_backlog_rcv)(struct sock *sk,
 						  struct sk_buff *skb);
 	void                    (*sk_destruct)(struct sock *sk);
+	struct sock_reuseport __rcu	*sk_reuseport_cb;
 };
 
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
@@ -778,9 +776,9 @@ static inline int sk_memalloc_socks(void)
 
 #endif
 
-static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask)
+static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask)
 {
-	return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
+	return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
 }
 
 static inline void sk_acceptq_removed(struct sock *sk)
@@ -1067,6 +1065,7 @@ struct proto {
 	void			(*destroy_cgroup)(struct mem_cgroup *memcg);
 	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
 #endif
+	int			(*diag_destroy)(struct sock *sk, int err);
 };
 
 int proto_register(struct proto *prot, int alloc_slab);
@@ -1798,6 +1797,15 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 	sk->sk_route_caps &= ~flags;
 }
 
+static inline bool sk_check_csum_caps(struct sock *sk)
+{
+	return (sk->sk_route_caps & NETIF_F_HW_CSUM) ||
+	       (sk->sk_family == PF_INET &&
+		(sk->sk_route_caps & NETIF_F_IP_CSUM)) ||
+	       (sk->sk_family == PF_INET6 &&
+		(sk->sk_route_caps & NETIF_F_IPV6_CSUM));
+}
+
 static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
 					   struct iov_iter *from, char *to,
 					   int copy, int offset)
@@ -1883,12 +1891,12 @@ static inline bool sk_has_allocations(const struct sock *sk)
 }
 
 /**
- * wq_has_sleeper - check if there are any waiting processes
+ * skwq_has_sleeper - check if there are any waiting processes
  * @wq: struct socket_wq
  *
  * Returns true if socket_wq has waiting processes
  *
- * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
+ * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
  * barrier call. They were added due to the race found within the tcp code.
  *
  * Consider following tcp code paths:
@@ -1914,15 +1922,9 @@ static inline bool sk_has_allocations(const struct sock *sk)
  * data on the socket.
  *
  */
-static inline bool wq_has_sleeper(struct socket_wq *wq)
+static inline bool skwq_has_sleeper(struct socket_wq *wq)
 {
-	/* We need to be sure we are in sync with the
-	 * add_wait_queue modifications to the wait queue.
-	 *
-	 * This memory barrier is paired in the sock_poll_wait.
-	 */
-	smp_mb();
-	return wq && waitqueue_active(&wq->wait);
+	return wq && wq_has_sleeper(&wq->wait);
 }
 
 /**