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, 21 insertions, 20 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index 9b9ca2839399..1a98f1ca1638 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -100,24 +100,20 @@ int igmp_mc_init(void);
  *	Functions provided by ip.c
  */
 
-int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
+int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 			  __be32 saddr, __be32 daddr,
 			  struct ip_options_rcu *opt);
 int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	   struct net_device *orig_dev);
 int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
-int ip_output(struct sock *sk, struct sk_buff *skb);
-int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
-		   int (*output)(struct sock *, struct sk_buff *));
+int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		   int (*output)(struct net *, struct sock *, struct sk_buff *));
 void ip_send_check(struct iphdr *ip);
-int __ip_local_out(struct sk_buff *skb);
-int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
-static inline int ip_local_out(struct sk_buff *skb)
-{
-	return ip_local_out_sk(skb->sk, skb);
-}
+int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
+int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 
 int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 void ip_init(void);
@@ -282,10 +278,12 @@ int ip_decrease_ttl(struct iphdr *iph)
 }
 
 static inline
-int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
+int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
 {
-	return  inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO ||
-		(inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT &&
+	u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
+
+	return  pmtudisc == IP_PMTUDISC_DO ||
+		(pmtudisc == IP_PMTUDISC_WANT &&
 		 !(dst_metric_locked(dst, RTAX_MTU)));
 }
 
@@ -321,12 +319,15 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 
 static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
 {
-	if (!skb->sk || ip_sk_use_pmtu(skb->sk)) {
+	struct sock *sk = skb->sk;
+
+	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
+
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
-	} else {
-		return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
 	}
+
+	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
@@ -505,11 +506,11 @@ static inline bool ip_defrag_user_in_between(u32 user,
 	return user >= lower_bond && user <= upper_bond;
 }
 
-int ip_defrag(struct sk_buff *skb, u32 user);
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #ifdef CONFIG_INET
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #else
-static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	return skb;
 }