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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 54 insertions, 33 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index e23717013a4e..f570e75e3da9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -150,6 +150,10 @@ typedef __u64 __bitwise __addrpair;
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
+ *	@skc_flags: place holder for sk_flags
+ *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
+ *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ *	@skc_incoming_cpu: record/match cpu processing incoming packets
  *	@skc_refcnt: reference count
  *
  *	This is the minimal network layer representation of sockets, the header
@@ -200,6 +204,16 @@ struct sock_common {
 
 	atomic64_t		skc_cookie;
 
+	/* following fields are padding to force
+	 * offset(struct sock, sk_refcnt) == 128 on 64bit arches
+	 * assuming IPV6 is enabled. We use this padding differently
+	 * for different kind of 'sockets'
+	 */
+	union {
+		unsigned long	skc_flags;
+		struct sock	*skc_listener; /* request_sock */
+		struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */
+	};
 	/*
 	 * fields between dontcopy_begin/dontcopy_end
 	 * are not copied in sock_copy()
@@ -212,9 +226,20 @@ struct sock_common {
 		struct hlist_nulls_node skc_nulls_node;
 	};
 	int			skc_tx_queue_mapping;
+	union {
+		int		skc_incoming_cpu;
+		u32		skc_rcv_wnd;
+		u32		skc_tw_rcv_nxt; /* struct tcp_timewait_sock  */
+	};
+
 	atomic_t		skc_refcnt;
 	/* private: */
 	int                     skc_dontcopy_end[0];
+	union {
+		u32		skc_rxhash;
+		u32		skc_window_clamp;
+		u32		skc_tw_snd_nxt; /* struct tcp_timewait_sock */
+	};
 	/* public: */
 };
 
@@ -243,8 +268,6 @@ struct cg_proto;
   *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
-  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
-  *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
@@ -273,8 +296,6 @@ struct cg_proto;
   *	@sk_rcvlowat: %SO_RCVLOWAT setting
   *	@sk_rcvtimeo: %SO_RCVTIMEO setting
   *	@sk_sndtimeo: %SO_SNDTIMEO setting
-  *	@sk_rxhash: flow hash received from netif layer
-  *	@sk_incoming_cpu: record cpu processing incoming packets
   *	@sk_txhash: computed flow hash for use on transmit
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
@@ -331,6 +352,9 @@ struct sock {
 #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
+#define sk_incoming_cpu		__sk_common.skc_incoming_cpu
+#define sk_flags		__sk_common.skc_flags
+#define sk_rxhash		__sk_common.skc_rxhash
 
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
@@ -350,14 +374,6 @@ struct sock {
 	} sk_backlog;
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 	int			sk_forward_alloc;
-#ifdef CONFIG_RPS
-	__u32			sk_rxhash;
-#endif
-	u16			sk_incoming_cpu;
-	/* 16bit hole
-	 * Warned : sk_incoming_cpu can be set from softirq,
-	 * Do not use this hole without fully understanding possible issues.
-	 */
 
 	__u32			sk_txhash;
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -373,7 +389,6 @@ struct sock {
 #ifdef CONFIG_XFRM
 	struct xfrm_policy	*sk_policy[2];
 #endif
-	unsigned long 		sk_flags;
 	struct dst_entry	*sk_rx_dst;
 	struct dst_entry __rcu	*sk_dst_cache;
 	spinlock_t		sk_dst_lock;
@@ -759,7 +774,7 @@ static inline int sk_memalloc_socks(void)
 
 #endif
 
-static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
+static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask)
 {
 	return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
 }
@@ -1522,6 +1537,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size);
 void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
 
+struct sockcm_cookie {
+	u32 mark;
+};
+
+int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
+		   struct sockcm_cookie *sockc);
+
 /*
  * Functions to fill in entries in struct proto_ops when a protocol
  * does not implement a particular function.
@@ -1662,12 +1684,16 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 kuid_t sock_i_uid(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
-static inline void sk_set_txhash(struct sock *sk)
+static inline u32 net_tx_rndhash(void)
 {
-	sk->sk_txhash = prandom_u32();
+	u32 v = prandom_u32();
+
+	return v ?: 1;
+}
 
-	if (unlikely(!sk->sk_txhash))
-		sk->sk_txhash = 1;
+static inline void sk_set_txhash(struct sock *sk)
+{
+	sk->sk_txhash = net_tx_rndhash();
 }
 
 static inline void sk_rethink_txhash(struct sock *sk)
@@ -1925,6 +1951,8 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
 	}
 }
 
+void skb_set_owner_w(struct sk_buff *skb, struct sock *sk);
+
 /*
  *	Queue a received datagram if it will fit. Stream and sequenced
  *	protocols can't normally use this as they need to fit buffers in
@@ -1933,21 +1961,6 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
  *	Inlined as it's very short and called for pretty much every
  *	packet ever received.
  */
-
-static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = sock_wfree;
-	skb_set_hash_from_sk(skb, sk);
-	/*
-	 * We used to take a refcount on sk, but following operation
-	 * is enough to guarantee sk_free() wont free this sock until
-	 * all in-flight packets are completed
-	 */
-	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
-}
-
 static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 {
 	skb_orphan(skb);
@@ -2205,6 +2218,14 @@ static inline bool sk_fullsock(const struct sock *sk)
 	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
 }
 
+/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
+ * SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
+ */
+static inline bool sk_listener(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & (TCPF_LISTEN | 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 *);