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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 50 insertions, 68 deletions

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index d5332ddcea3f..4a6009d4486b 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -15,16 +15,20 @@
 #include <net/ipv6.h>
 #include <linux/atomic.h>
 
-struct inetpeer_addr_base {
-	union {
-		__be32			a4;
-		__be32			a6[4];
-		struct in6_addr		in6;
-	};
+/* IPv4 address key for cache lookups */
+struct ipv4_addr_key {
+	__be32	addr;
+	int	vif;
 };
 
+#define INETPEER_MAXKEYSZ   (sizeof(struct in6_addr) / sizeof(u32))
+
 struct inetpeer_addr {
-	struct inetpeer_addr_base	addr;
+	union {
+		struct ipv4_addr_key	a4;
+		struct in6_addr		a6;
+		u32			key[INETPEER_MAXKEYSZ];
+	};
 	__u16				family;
 };
 
@@ -65,69 +69,33 @@ struct inet_peer_base {
 	int			total;
 };
 
-#define INETPEER_BASE_BIT	0x1UL
-
-static inline struct inet_peer *inetpeer_ptr(unsigned long val)
-{
-	BUG_ON(val & INETPEER_BASE_BIT);
-	return (struct inet_peer *) val;
-}
+void inet_peer_base_init(struct inet_peer_base *);
 
-static inline struct inet_peer_base *inetpeer_base_ptr(unsigned long val)
-{
-	if (!(val & INETPEER_BASE_BIT))
-		return NULL;
-	val &= ~INETPEER_BASE_BIT;
-	return (struct inet_peer_base *) val;
-}
+void inet_initpeers(void) __init;
 
-static inline bool inetpeer_ptr_is_peer(unsigned long val)
-{
-	return !(val & INETPEER_BASE_BIT);
-}
+#define INETPEER_METRICS_NEW	(~(u32) 0)
 
-static inline void __inetpeer_ptr_set_peer(unsigned long *val, struct inet_peer *peer)
+static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
 {
-	/* This implicitly clears INETPEER_BASE_BIT */
-	*val = (unsigned long) peer;
+	iaddr->a4.addr = ip;
+	iaddr->family = AF_INET;
 }
 
-static inline bool inetpeer_ptr_set_peer(unsigned long *ptr, struct inet_peer *peer)
+static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
 {
-	unsigned long val = (unsigned long) peer;
-	unsigned long orig = *ptr;
-
-	if (!(orig & INETPEER_BASE_BIT) ||
-	    cmpxchg(ptr, orig, val) != orig)
-		return false;
-	return true;
+	return iaddr->a4.addr;
 }
 
-static inline void inetpeer_init_ptr(unsigned long *ptr, struct inet_peer_base *base)
+static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
+					struct in6_addr *in6)
 {
-	*ptr = (unsigned long) base | INETPEER_BASE_BIT;
+	iaddr->a6 = *in6;
+	iaddr->family = AF_INET6;
 }
 
-static inline void inetpeer_transfer_peer(unsigned long *to, unsigned long *from)
+static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
 {
-	unsigned long val = *from;
-
-	*to = val;
-	if (inetpeer_ptr_is_peer(val)) {
-		struct inet_peer *peer = inetpeer_ptr(val);
-		atomic_inc(&peer->refcnt);
-	}
-}
-
-void inet_peer_base_init(struct inet_peer_base *);
-
-void inet_initpeers(void) __init;
-
-#define INETPEER_METRICS_NEW	(~(u32) 0)
-
-static inline bool inet_metrics_new(const struct inet_peer *p)
-{
-	return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW;
+	return &iaddr->a6;
 }
 
 /* can be called with or without local BH being disabled */
@@ -137,11 +105,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 
 static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
 						__be32 v4daddr,
-						int create)
+						int vif, int create)
 {
 	struct inetpeer_addr daddr;
 
-	daddr.addr.a4 = v4daddr;
+	daddr.a4.addr = v4daddr;
+	daddr.a4.vif = vif;
 	daddr.family = AF_INET;
 	return inet_getpeer(base, &daddr, create);
 }
@@ -152,23 +121,36 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
 {
 	struct inetpeer_addr daddr;
 
-	daddr.addr.in6 = *v6daddr;
+	daddr.a6 = *v6daddr;
 	daddr.family = AF_INET6;
 	return inet_getpeer(base, &daddr, create);
 }
 
+static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
+				    const struct inetpeer_addr *b)
+{
+	int i, n;
+
+	if (a->family == AF_INET)
+		n = sizeof(a->a4) / sizeof(u32);
+	else
+		n = sizeof(a->a6) / sizeof(u32);
+
+	for (i = 0; i < n; i++) {
+		if (a->key[i] == b->key[i])
+			continue;
+		if (a->key[i] < b->key[i])
+			return -1;
+		return 1;
+	}
+
+	return 0;
+}
+
 /* can be called from BH context or outside */
 void inet_putpeer(struct inet_peer *p);
 bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 
 void inetpeer_invalidate_tree(struct inet_peer_base *);
 
-/*
- * temporary check to make sure we dont access rid, tcp_ts,
- * tcp_ts_stamp if no refcount is taken on inet_peer
- */
-static inline void inet_peer_refcheck(const struct inet_peer *p)
-{
-	WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
-}
 #endif /* _NET_INETPEER_H */