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, 47 insertions, 16 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 81c81ead9a35..3a4898ec8c67 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -66,6 +66,7 @@
 #include <linux/atomic.h>
 #include <net/dst.h>
 #include <net/checksum.h>
+#include <net/tcp_states.h>
 #include <linux/net_tstamp.h>
 
 struct cgroup;
@@ -189,15 +190,15 @@ struct sock_common {
 		struct hlist_nulls_node skc_portaddr_node;
 	};
 	struct proto		*skc_prot;
-#ifdef CONFIG_NET_NS
-	struct net	 	*skc_net;
-#endif
+	possible_net_t		skc_net;
 
 #if IS_ENABLED(CONFIG_IPV6)
 	struct in6_addr		skc_v6_daddr;
 	struct in6_addr		skc_v6_rcv_saddr;
 #endif
 
+	atomic64_t		skc_cookie;
+
 	/*
 	 * fields between dontcopy_begin/dontcopy_end
 	 * are not copied in sock_copy()
@@ -328,6 +329,7 @@ struct sock {
 #define sk_net			__sk_common.skc_net
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr	__sk_common.skc_v6_rcv_saddr
+#define sk_cookie		__sk_common.skc_cookie
 
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
@@ -402,8 +404,8 @@ struct sock {
 	rwlock_t		sk_callback_lock;
 	int			sk_err,
 				sk_err_soft;
-	unsigned short		sk_ack_backlog;
-	unsigned short		sk_max_ack_backlog;
+	u32			sk_ack_backlog;
+	u32			sk_max_ack_backlog;
 	__u32			sk_priority;
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	__u32			sk_cgrp_prioidx;
@@ -957,10 +959,9 @@ struct proto {
 	int			(*compat_ioctl)(struct sock *sk,
 					unsigned int cmd, unsigned long arg);
 #endif
-	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
-					   struct msghdr *msg, size_t len);
-	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
-					   struct msghdr *msg,
+	int			(*sendmsg)(struct sock *sk, struct msghdr *msg,
+					   size_t len);
+	int			(*recvmsg)(struct sock *sk, struct msghdr *msg,
 					   size_t len, int noblock, int flags,
 					   int *addr_len);
 	int			(*sendpage)(struct sock *sk, struct page *page,
@@ -1561,9 +1562,8 @@ int sock_no_listen(struct socket *, int);
 int sock_no_shutdown(struct socket *, int);
 int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
 int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
-int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t);
-int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
-		    int);
+int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
+int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
 int sock_no_mmap(struct file *file, struct socket *sock,
 		 struct vm_area_struct *vma);
 ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
@@ -1575,8 +1575,8 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
  */
 int sock_common_getsockopt(struct socket *sock, int level, int optname,
 				  char __user *optval, int __user *optlen);
-int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size, int flags);
+int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			int flags);
 int sock_common_setsockopt(struct socket *sock, int level, int optname,
 				  char __user *optval, unsigned int optlen);
 int compat_sock_common_getsockopt(struct socket *sock, int level,
@@ -1625,7 +1625,7 @@ static inline void sock_put(struct sock *sk)
 		sk_free(sk);
 }
 /* Generic version of sock_put(), dealing with all sockets
- * (TCP_TIMEWAIT, ESTABLISHED...)
+ * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...)
  */
 void sock_gen_put(struct sock *sk);
 
@@ -2079,6 +2079,29 @@ static inline int sock_intr_errno(long timeo)
 	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
 }
 
+struct sock_skb_cb {
+	u32 dropcount;
+};
+
+/* Store sock_skb_cb at the end of skb->cb[] so protocol families
+ * using skb->cb[] would keep using it directly and utilize its
+ * alignement guarantee.
+ */
+#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \
+			    sizeof(struct sock_skb_cb)))
+
+#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
+			    SOCK_SKB_CB_OFFSET))
+
+#define sock_skb_cb_check_size(size) \
+	BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET)
+
+static inline void
+sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
+{
+	SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops);
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2181,7 +2204,7 @@ static inline void sk_change_net(struct sock *sk, struct net *net)
 
 	if (!net_eq(current_net, net)) {
 		put_net(current_net);
-		sock_net_set(sk, hold_net(net));
+		sock_net_set(sk, net);
 	}
 }
 
@@ -2197,6 +2220,14 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb)
 	return NULL;
 }
 
+/* This helper checks if a socket is a full socket,
+ * ie _not_ a timewait or request socket.
+ */
+static inline bool sk_fullsock(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
+}
+
 void sock_enable_timestamp(struct sock *sk, int flag);
 int sock_get_timestamp(struct sock *, struct timeval __user *);
 int sock_get_timestampns(struct sock *, struct timespec __user *);