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, 42 insertions, 19 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cfba99b2c2a4..02f96dcbcf02 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -72,6 +72,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 static int ipip6_tunnel_init(struct net_device *dev);
 static void ipip6_tunnel_setup(struct net_device *dev);
 static void ipip6_dev_free(struct net_device *dev);
+static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
+		      __be32 *v4dst);
 static struct rtnl_link_ops sit_link_ops __read_mostly;
 
 static int sit_net_id __read_mostly;
@@ -590,17 +592,21 @@ out:
 	return err;
 }
 
+static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr,
+				  const struct in6_addr *v6addr)
+{
+	__be32 v4embed = 0;
+	if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed)
+		return true;
+	return false;
+}
+
 static int ipip6_rcv(struct sk_buff *skb)
 {
-	const struct iphdr *iph;
+	const struct iphdr *iph = ip_hdr(skb);
 	struct ip_tunnel *tunnel;
 	int err;
 
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-		goto out;
-
-	iph = ip_hdr(skb);
-
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
@@ -613,10 +619,19 @@ static int ipip6_rcv(struct sk_buff *skb)
 		skb->protocol = htons(ETH_P_IPV6);
 		skb->pkt_type = PACKET_HOST;
 
-		if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
-		    !isatap_chksrc(skb, iph, tunnel)) {
-			tunnel->dev->stats.rx_errors++;
-			goto out;
+		if (tunnel->dev->priv_flags & IFF_ISATAP) {
+			if (!isatap_chksrc(skb, iph, tunnel)) {
+				tunnel->dev->stats.rx_errors++;
+				goto out;
+			}
+		} else {
+			if (is_spoofed_6rd(tunnel, iph->saddr,
+					   &ipv6_hdr(skb)->saddr) ||
+			    is_spoofed_6rd(tunnel, iph->daddr,
+					   &ipv6_hdr(skb)->daddr)) {
+				tunnel->dev->stats.rx_errors++;
+				goto out;
+			}
 		}
 
 		__skb_tunnel_rx(skb, tunnel->dev);
@@ -650,14 +665,12 @@ out:
 }
 
 /*
- * Returns the embedded IPv4 address if the IPv6 address
- * comes from 6rd / 6to4 (RFC 3056) addr space.
+ * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
+ * stores the embedded IPv4 address in v4dst and returns true.
  */
-static inline
-__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel)
+static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
+		      __be32 *v4dst)
 {
-	__be32 dst = 0;
-
 #ifdef CONFIG_IPV6_SIT_6RD
 	if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
 			      tunnel->ip6rd.prefixlen)) {
@@ -676,14 +689,24 @@ __be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 			d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >>
 			     (32 - pbi1);
 
-		dst = tunnel->ip6rd.relay_prefix | htonl(d);
+		*v4dst = tunnel->ip6rd.relay_prefix | htonl(d);
+		return true;
 	}
 #else
 	if (v6dst->s6_addr16[0] == htons(0x2002)) {
 		/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
-		memcpy(&dst, &v6dst->s6_addr16[1], 4);
+		memcpy(v4dst, &v6dst->s6_addr16[1], 4);
+		return true;
 	}
 #endif
+	return false;
+}
+
+static inline __be32 try_6rd(struct ip_tunnel *tunnel,
+			     const struct in6_addr *v6dst)
+{
+	__be32 dst = 0;
+	check_6rd(tunnel, v6dst, &dst);
 	return dst;
 }
 
@@ -744,7 +767,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	if (!dst)
-		dst = try_6rd(&iph6->daddr, tunnel);
+		dst = try_6rd(tunnel, &iph6->daddr);
 
 	if (!dst) {
 		struct neighbour *neigh = NULL;