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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 113 insertions, 27 deletions

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 5af66b26ebdd..851d5412a299 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -222,6 +222,7 @@ struct ip6_flowlabel {
 	struct in6_addr		dst;
 	struct ipv6_txoptions	*opt;
 	unsigned long		linger;
+	struct rcu_head		rcu;
 	u8			share;
 	union {
 		struct pid *pid;
@@ -238,6 +239,7 @@ struct ip6_flowlabel {
 struct ipv6_fl_socklist {
 	struct ipv6_fl_socklist	*next;
 	struct ip6_flowlabel	*fl;
+	struct rcu_head		rcu;
 };
 
 extern struct ip6_flowlabel	*fl6_sock_lookup(struct sock *sk, __be32 label);
@@ -288,12 +290,12 @@ static inline int ip6_frag_nqueues(struct net *net)
 
 static inline int ip6_frag_mem(struct net *net)
 {
-	return atomic_read(&net->ipv6.frags.mem);
+	return sum_frag_mem_limit(&net->ipv6.frags);
 }
 #endif
 
-#define IPV6_FRAG_HIGH_THRESH	(256 * 1024)	/* 262144 */
-#define IPV6_FRAG_LOW_THRESH	(192 * 1024)	/* 196608 */
+#define IPV6_FRAG_HIGH_THRESH	(4 * 1024*1024)	/* 4194304 */
+#define IPV6_FRAG_LOW_THRESH	(3 * 1024*1024)	/* 3145728 */
 #define IPV6_FRAG_TIMEOUT	(60 * HZ)	/* 60 seconds */
 
 extern int __ipv6_addr_type(const struct in6_addr *addr);
@@ -355,14 +357,32 @@ static inline void ipv6_addr_prefix(struct in6_addr *pfx,
 		pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b);
 }
 
+static inline void __ipv6_addr_set_half(__be32 *addr,
+					__be32 wh, __be32 wl)
+{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+#if defined(__BIG_ENDIAN)
+	if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) {
+		*(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl));
+		return;
+	}
+#elif defined(__LITTLE_ENDIAN)
+	if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) {
+		*(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh));
+		return;
+	}
+#endif
+#endif
+	addr[0] = wh;
+	addr[1] = wl;
+}
+
 static inline void ipv6_addr_set(struct in6_addr *addr, 
 				     __be32 w1, __be32 w2,
 				     __be32 w3, __be32 w4)
 {
-	addr->s6_addr32[0] = w1;
-	addr->s6_addr32[1] = w2;
-	addr->s6_addr32[2] = w3;
-	addr->s6_addr32[3] = w4;
+	__ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2);
+	__ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4);
 }
 
 static inline bool ipv6_addr_equal(const struct in6_addr *a1,
@@ -381,9 +401,37 @@ static inline bool ipv6_addr_equal(const struct in6_addr *a1,
 #endif
 }
 
-static inline bool __ipv6_prefix_equal(const __be32 *a1, const __be32 *a2,
-				       unsigned int prefixlen)
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+static inline bool __ipv6_prefix_equal64_half(const __be64 *a1,
+					      const __be64 *a2,
+					      unsigned int len)
+{
+	if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len))))
+		return false;
+	return true;
+}
+
+static inline bool ipv6_prefix_equal(const struct in6_addr *addr1,
+				     const struct in6_addr *addr2,
+				     unsigned int prefixlen)
+{
+	const __be64 *a1 = (const __be64 *)addr1;
+	const __be64 *a2 = (const __be64 *)addr2;
+
+	if (prefixlen >= 64) {
+		if (a1[0] ^ a2[0])
+			return false;
+		return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64);
+	}
+	return __ipv6_prefix_equal64_half(a1, a2, prefixlen);
+}
+#else
+static inline bool ipv6_prefix_equal(const struct in6_addr *addr1,
+				     const struct in6_addr *addr2,
+				     unsigned int prefixlen)
 {
+	const __be32 *a1 = addr1->s6_addr32;
+	const __be32 *a2 = addr2->s6_addr32;
 	unsigned int pdw, pbi;
 
 	/* check complete u32 in prefix */
@@ -398,14 +446,7 @@ static inline bool __ipv6_prefix_equal(const __be32 *a1, const __be32 *a2,
 
 	return true;
 }
-
-static inline bool ipv6_prefix_equal(const struct in6_addr *a1,
-				     const struct in6_addr *a2,
-				     unsigned int prefixlen)
-{
-	return __ipv6_prefix_equal(a1->s6_addr32, a2->s6_addr32,
-				   prefixlen);
-}
+#endif
 
 struct inet_frag_queue;
 
@@ -475,14 +516,25 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a)
 
 static inline bool ipv6_addr_loopback(const struct in6_addr *a)
 {
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	const unsigned long *ul = (const unsigned long *)a;
+
+	return (ul[0] | (ul[1] ^ cpu_to_be64(1))) == 0UL;
+#else
 	return (a->s6_addr32[0] | a->s6_addr32[1] |
 		a->s6_addr32[2] | (a->s6_addr32[3] ^ htonl(1))) == 0;
+#endif
 }
 
 static inline bool ipv6_addr_v4mapped(const struct in6_addr *a)
 {
-	return (a->s6_addr32[0] | a->s6_addr32[1] |
-		 (a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0;
+	return (
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+		*(__be64 *)a |
+#else
+		(a->s6_addr32[0] | a->s6_addr32[1]) |
+#endif
+		(a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0UL;
 }
 
 /*
@@ -507,7 +559,7 @@ static inline void ipv6_addr_set_v4mapped(const __be32 addr,
  * find the first different bit between two addresses
  * length of address must be a multiple of 32bits
  */
-static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen)
+static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen)
 {
 	const __be32 *a1 = token1, *a2 = token2;
 	int i;
@@ -539,6 +591,33 @@ static inline int __ipv6_addr_diff(const void *token1, const void *token2, int a
 	return addrlen << 5;
 }
 
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen)
+{
+	const __be64 *a1 = token1, *a2 = token2;
+	int i;
+
+	addrlen >>= 3;
+
+	for (i = 0; i < addrlen; i++) {
+		__be64 xb = a1[i] ^ a2[i];
+		if (xb)
+			return i * 64 + 63 - __fls(be64_to_cpu(xb));
+	}
+
+	return addrlen << 6;
+}
+#endif
+
+static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen)
+{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	if (__builtin_constant_p(addrlen) && !(addrlen & 7))
+		return __ipv6_addr_diff64(token1, token2, addrlen);
+#endif
+	return __ipv6_addr_diff32(token1, token2, addrlen);
+}
+
 static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2)
 {
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
@@ -547,6 +626,20 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 extern void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 
 /*
+ *	Header manipulation
+ */
+static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass,
+				__be32 flowlabel)
+{
+	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel;
+}
+
+static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr)
+{
+	return *(__be32 *)hdr & IPV6_FLOWINFO_MASK;
+}
+
+/*
  *	Prototypes exported by ipv6
  */
 
@@ -570,13 +663,6 @@ extern int			ip6_xmit(struct sock *sk,
 					 struct ipv6_txoptions *opt,
 					 int tclass);
 
-extern int			ip6_nd_hdr(struct sock *sk,
-					   struct sk_buff *skb,
-					   struct net_device *dev,
-					   const struct in6_addr *saddr,
-					   const struct in6_addr *daddr,
-					   int proto, int len);
-
 extern int			ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
 
 extern int			ip6_append_data(struct sock *sk,