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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 76 insertions, 2 deletions

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 21ace5a2bf7c..70f2628be6fa 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -17,11 +17,13 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
+#include <net/addrconf.h>
 #include <net/inet_connection_sock.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
 #include <net/secure_seq.h>
 #include <net/ip.h>
+#include <net/sock_reuseport.h>
 
 u32 inet6_ehashfn(const struct net *net,
 		  const struct in6_addr *laddr, const u16 lport,
@@ -121,7 +123,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 }
 
 struct sock *inet6_lookup_listener(struct net *net,
-		struct inet_hashinfo *hashinfo, const struct in6_addr *saddr,
+		struct inet_hashinfo *hashinfo,
+		struct sk_buff *skb, int doff,
+		const struct in6_addr *saddr,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif)
 {
@@ -129,6 +133,7 @@ struct sock *inet6_lookup_listener(struct net *net,
 	const struct hlist_nulls_node *node;
 	struct sock *result;
 	int score, hiscore, matches = 0, reuseport = 0;
+	bool select_ok = true;
 	u32 phash = 0;
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
@@ -146,6 +151,15 @@ begin:
 			if (reuseport) {
 				phash = inet6_ehashfn(net, daddr, hnum,
 						      saddr, sport);
+				if (select_ok) {
+					struct sock *sk2;
+					sk2 = reuseport_select_sock(sk, phash,
+								    skb, doff);
+					if (sk2) {
+						result = sk2;
+						goto found;
+					}
+				}
 				matches = 1;
 			}
 		} else if (score == hiscore && reuseport) {
@@ -163,11 +177,13 @@ begin:
 	if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE)
 		goto begin;
 	if (result) {
+found:
 		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
 			result = NULL;
 		else if (unlikely(compute_score(result, net, hnum, daddr,
 				  dif) < hiscore)) {
 			sock_put(result);
+			select_ok = false;
 			goto begin;
 		}
 	}
@@ -177,6 +193,7 @@ begin:
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+			  struct sk_buff *skb, int doff,
 			  const struct in6_addr *saddr, const __be16 sport,
 			  const struct in6_addr *daddr, const __be16 dport,
 			  const int dif)
@@ -184,7 +201,8 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 	struct sock *sk;
 
 	local_bh_disable();
-	sk = __inet6_lookup(net, hashinfo, saddr, sport, daddr, ntohs(dport), dif);
+	sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
+			    ntohs(dport), dif);
 	local_bh_enable();
 
 	return sk;
@@ -274,3 +292,59 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 				   __inet6_check_established);
 }
 EXPORT_SYMBOL_GPL(inet6_hash_connect);
+
+int inet6_hash(struct sock *sk)
+{
+	if (sk->sk_state != TCP_CLOSE) {
+		local_bh_disable();
+		__inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
+		local_bh_enable();
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(inet6_hash);
+
+/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
+ *                          only, and any IPv4 addresses if not IPv6 only
+ * match_wildcard == false: addresses must be exactly the same, i.e.
+ *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *                          and 0.0.0.0 equals to 0.0.0.0 only
+ */
+int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+			 bool match_wildcard)
+{
+	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
+	int sk2_ipv6only = inet_v6_ipv6only(sk2);
+	int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
+	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
+
+	/* if both are mapped, treat as IPv4 */
+	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
+		if (!sk2_ipv6only) {
+			if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr)
+				return 1;
+			if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr)
+				return match_wildcard;
+		}
+		return 0;
+	}
+
+	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
+		return 1;
+
+	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	    !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (sk2_rcv_saddr6 &&
+	    ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6))
+		return 1;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipv6_rcv_saddr_equal);