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

Pull networking fixes from David Miller:

 1) When we run a tap on netlink sockets, we have to copy mmap'd SKBs
    instead of cloning them.  From Daniel Borkmann.

 2) When converting classical BPF into eBPF, fix the setting of the
    source reg to BPF_REG_X.  From Tycho Andersen.

 3) Fix igmpv3/mldv2 report parsing in the bridge multicast code, from
    Linus Lussing.

 4) Fix dst refcounting for ipv6 tunnels, from Martin KaFai Lau.

 5) Set NLM_F_REPLACE flag properly when replacing ipv6 routes, from
    Roopa Prabhu.

 6) Add some new cxgb4 PCI device IDs, from Hariprasad Shenai.

 7) Fix headroom tests and SKB leaks in ipv6 fragmentation code, from
    Florian Westphal.

 8) Check DMA mapping errors in bna driver, from Ivan Vecera.

 9) Several 8139cp bug fixes (dev_kfree_skb_any in interrupt context,
    misclearing of interrupt status in TX timeout handler, etc.) from
    David Woodhouse.

10) In tipc, reset SKB header pointer after skb_linearize(), from Erik
    Hugne.

11) Fix autobind races et al. in netlink code, from Herbert Xu with
    help from Tejun Heo and others.

12) Missing SET_NETDEV_DEV in sunvnet driver, from Sowmini Varadhan.

13) Fix various races in timewait timer and reqsk_queue_hadh_req, from
    Eric Dumazet.

14) Fix array overruns in mac80211, from Johannes Berg and Dan
    Carpenter.

15) Fix data race in rhashtable_rehash_one(), from Dmitriy Vyukov.

16) Fix race between poll_one_napi and napi_disable, from Neil Horman.

17) Fix byte order in geneve tunnel port config, from John W Linville.

18) Fix handling of ARP replies over lightweight tunnels, from Jiri
    Benc.

19) We can loop when fib rule dumps cross multiple SKBs, fix from Wilson
    Kok and Roopa Prabhu.

20) Several reference count handling bug fixes in the PHY/MDIO layer
    from Russel King.

21) Fix lockdep splat in ppp_dev_uninit(), from Guillaume Nault.

22) Fix crash in icmp_route_lookup(), from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  net: Fix panic in icmp_route_lookup
  net: update docbook comment for __mdiobus_register()
  ppp: fix lockdep splat in ppp_dev_uninit()
  net: via/Kconfig: GENERIC_PCI_IOMAP required if PCI not selected
  phy: marvell: add link partner advertised modes
  net: fix net_device refcounting
  phy: add phy_device_remove()
  phy: fixed-phy: properly validate phy in fixed_phy_update_state()
  net: fix phy refcounting in a bunch of drivers
  of_mdio: fix MDIO phy device refcounting
  phy: add proper phy struct device refcounting
  phy: fix mdiobus module safety
  net: dsa: fix of_mdio_find_bus() device refcount leak
  phy: fix of_mdio_find_bus() device refcount leak
  ip6_tunnel: Reduce log level in ip6_tnl_err() to debug
  ip6_gre: Reduce log level in ip6gre_err() to debug
  fib_rules: fix fib rule dumps across multiple skbs
  bnx2x: byte swap rss_key to comply to Toeplitz specs
  net: revert "net_sched: move tp->root allocation into fw_init()"
  lwtunnel: remove source and destination UDP port config option
  ...

11 files changed, 62 insertions, 27 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88a00694eda5..2d15e3831440 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n)
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
 	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
+	clear_bit(NAPI_STATE_NPSVC, &n->state);
 }
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 962387a192f1..4a4e3a092337 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -19,6 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
+#include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/mod_devicetable.h>
@@ -153,6 +154,7 @@ struct sk_buff;
  * PHYs should register using this structure
  */
 struct mii_bus {
+	struct module *owner;
 	const char *name;
 	char id[MII_BUS_ID_SIZE];
 	void *priv;
@@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void)
 	return mdiobus_alloc_size(0);
 }
 
-int mdiobus_register(struct mii_bus *bus);
+int __mdiobus_register(struct mii_bus *bus, struct module *owner);
+#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE)
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
 struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv);
@@ -742,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 				     struct phy_c45_device_ids *c45_ids);
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
+void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2738d355cdf9..2b0a30a6e31c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -179,6 +179,9 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	__u16			frag_max_size;
 	struct net_device	*physindev;
+
+	/* always valid & non-NULL from FORWARD on, for physdev match */
+	struct net_device	*physoutdev;
 	union {
 		/* prerouting: detect dnat in orig/reply direction */
 		__be32          ipv4_daddr;
@@ -189,9 +192,6 @@ struct nf_bridge_info {
 		 * skb is out in neigh layer.
 		 */
 		char neigh_header[8];
-
-		/* always valid & non-NULL from FORWARD on, for physdev match */
-		struct net_device *physoutdev;
 	};
 };
 #endif
@@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
diff --git a/include/net/flow.h b/include/net/flow.h
index acd6a096250e..9b85db85f13c 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -35,6 +35,7 @@ struct flowi_common {
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
 #define FLOWI_FLAG_VRFSRC		0x04
+#define FLOWI_FLAG_SKIP_NH_OIF		0x08
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
 };
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 879d6e5a973b..186f3a1e1b1f 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -110,7 +110,19 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 			   struct inet_hashinfo *hashinfo);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo);
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
+			  bool rearm);
+
+static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, false);
+}
+
+static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, true);
+}
+
 void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 063d30474cf6..aaf9700fc9e5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -275,7 +275,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	     struct nl_info *info, struct mx6_config *mxc);
 int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+		     unsigned int flags);
 
 void fib6_run_gc(unsigned long expires, struct net *net, bool force);
 
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index b8529aa1dae7..fa915fa0f703 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -32,6 +32,12 @@ struct __ip6_tnl_parm {
 	__be32			o_key;
 };
 
+struct ip6_tnl_dst {
+	seqlock_t lock;
+	struct dst_entry __rcu *dst;
+	u32 cookie;
+};
+
 /* IPv6 tunnel */
 struct ip6_tnl {
 	struct ip6_tnl __rcu *next;	/* next tunnel in list */
@@ -39,8 +45,7 @@ struct ip6_tnl {
 	struct net *net;	/* netns for packet i/o */
 	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
 	struct flowi fl;	/* flowi template for xmit */
-	struct dst_entry *dst_cache;    /* cached dst */
-	u32 dst_cookie;
+	struct ip6_tnl_dst __percpu *dst_cache;	/* cached dst */
 
 	int err_count;
 	unsigned long err_time;
@@ -60,9 +65,11 @@ struct ipv6_tlv_tnl_enc_lim {
 	__u8 encap_limit;	/* tunnel encapsulation limit   */
 } __packed;
 
-struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t);
+struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t);
+int ip6_tnl_dst_init(struct ip6_tnl *t);
+void ip6_tnl_dst_destroy(struct ip6_tnl *t);
 void ip6_tnl_dst_reset(struct ip6_tnl *t);
-void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst);
+void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst);
 int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
 		const struct in6_addr *raddr);
 int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
@@ -79,7 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	struct net_device_stats *stats = &dev->stats;
 	int pkt_len, err;
 
-	pkt_len = skb->len;
+	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out_sk(sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a37d0432bebd..727d6e9a9685 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -236,8 +236,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 	rcu_read_lock();
 
 	tb = fib_get_table(net, RT_TABLE_MAIN);
-	if (tb && !fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF))
-		err = 0;
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF);
+
+	if (err == -EAGAIN)
+		err = -ENETUNREACH;
 
 	rcu_read_unlock();
 
@@ -258,7 +261,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 			     struct fib_result *res, unsigned int flags)
 {
 	struct fib_table *tb;
-	int err;
+	int err = -ENETUNREACH;
 
 	flags |= FIB_LOOKUP_NOREF;
 	if (net->ipv4.fib_has_custom_rules)
@@ -268,15 +271,20 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 
 	res->tclassid = 0;
 
-	for (err = 0; !err; err = -ENETUNREACH) {
-		tb = rcu_dereference_rtnl(net->ipv4.fib_main);
-		if (tb && !fib_table_lookup(tb, flp, res, flags))
-			break;
+	tb = rcu_dereference_rtnl(net->ipv4.fib_main);
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags);
+
+	if (!err)
+		goto out;
+
+	tb = rcu_dereference_rtnl(net->ipv4.fib_default);
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags);
 
-		tb = rcu_dereference_rtnl(net->ipv4.fib_default);
-		if (tb && !fib_table_lookup(tb, flp, res, flags))
-			break;
-	}
+out:
+	if (err == -EAGAIN)
+		err = -ENETUNREACH;
 
 	rcu_read_unlock();
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 9a6a3ba888e8..f6dafec9102c 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -276,6 +276,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
 int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, u8 proto,
 		  u8 tos, u8 ttl, __be16 df, bool xnet);
+struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
+					     gfp_t flags);
 
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
 					 int gso_type_mask);
diff --git a/include/net/route.h b/include/net/route.h
index cc61cb95f059..f46af256880c 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -255,7 +255,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
 	if (netif_index_is_vrf(sock_net(sk), oif))
-		flow_flags |= FLOWI_FLAG_VRFSRC;
+		flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF;
 
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
 			   protocol, flow_flags, dst, src, dport, sport);
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
index 34141a5dfe74..f8b01887a495 100644
--- a/include/uapi/linux/lwtunnel.h
+++ b/include/uapi/linux/lwtunnel.h
@@ -21,8 +21,6 @@ enum lwtunnel_ip_t {
 	LWTUNNEL_IP_SRC,
 	LWTUNNEL_IP_TTL,
 	LWTUNNEL_IP_TOS,
-	LWTUNNEL_IP_SPORT,
-	LWTUNNEL_IP_DPORT,
 	LWTUNNEL_IP_FLAGS,
 	__LWTUNNEL_IP_MAX,
 };
@@ -36,8 +34,6 @@ enum lwtunnel_ip6_t {
 	LWTUNNEL_IP6_SRC,
 	LWTUNNEL_IP6_HOPLIMIT,
 	LWTUNNEL_IP6_TC,
-	LWTUNNEL_IP6_SPORT,
-	LWTUNNEL_IP6_DPORT,
 	LWTUNNEL_IP6_FLAGS,
 	__LWTUNNEL_IP6_MAX,
 };