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, 137 insertions, 8 deletions

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8214cb..9a6a3ba 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -4,14 +4,15 @@
 #include <linux/if_tunnel.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/socket.h>
 #include <linux/types.h>
 #include <linux/u64_stats_sync.h>
 #include <net/dsfield.h>
 #include <net/gro_cells.h>
 #include <net/inet_ecn.h>
-#include <net/ip.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
+#include <net/lwtunnel.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -22,6 +23,44 @@
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
 
+/* Used to memset ip_tunnel padding. */
+#define IP_TUNNEL_KEY_SIZE	offsetofend(struct ip_tunnel_key, tp_dst)
+
+/* Used to memset ipv4 address padding. */
+#define IP_TUNNEL_KEY_IPV4_PAD	offsetofend(struct ip_tunnel_key, u.ipv4.dst)
+#define IP_TUNNEL_KEY_IPV4_PAD_LEN				\
+	(FIELD_SIZEOF(struct ip_tunnel_key, u) -		\
+	 FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))
+
+struct ip_tunnel_key {
+	__be64			tun_id;
+	union {
+		struct {
+			__be32	src;
+			__be32	dst;
+		} ipv4;
+		struct {
+			struct in6_addr src;
+			struct in6_addr dst;
+		} ipv6;
+	} u;
+	__be16			tun_flags;
+	u8			tos;		/* TOS for IPv4, TC for IPv6 */
+	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
+	__be16			tp_src;
+	__be16			tp_dst;
+};
+
+/* Flags for ip_tunnel_info mode. */
+#define IP_TUNNEL_INFO_TX	0x01	/* represents tx tunnel parameters */
+#define IP_TUNNEL_INFO_IPV6	0x02	/* key contains IPv6 addresses */
+
+struct ip_tunnel_info {
+	struct ip_tunnel_key	key;
+	u8			options_len;
+	u8			mode;
+};
+
 /* 6rd prefix/relay information */
 #ifdef CONFIG_IPV6_SIT_6RD
 struct ip_tunnel_6rd_parm {
@@ -33,8 +72,8 @@ struct ip_tunnel_6rd_parm {
 #endif
 
 struct ip_tunnel_encap {
-	__u16			type;
-	__u16			flags;
+	u16			type;
+	u16			flags;
 	__be16			sport;
 	__be16			dport;
 };
@@ -51,6 +90,8 @@ struct ip_tunnel_dst {
 	__be32				 saddr;
 };
 
+struct metadata_dst;
+
 struct ip_tunnel {
 	struct ip_tunnel __rcu	*next;
 	struct hlist_node hash_node;
@@ -62,8 +103,8 @@ struct ip_tunnel {
 					 * arrived */
 
 	/* These four fields used only by GRE */
-	__u32		i_seqno;	/* The last seen seqno	*/
-	__u32		o_seqno;	/* The last output seqno */
+	u32		i_seqno;	/* The last seen seqno	*/
+	u32		o_seqno;	/* The last output seqno */
 	int		tun_hlen;	/* Precalculated header length */
 	int		mlink;
 
@@ -84,6 +125,7 @@ struct ip_tunnel {
 	unsigned int		prl_count;	/* # of entries in PRL */
 	int			ip_tnl_net_id;
 	struct gro_cells	gro_cells;
+	bool			collect_md;
 };
 
 #define TUNNEL_CSUM		__cpu_to_be16(0x01)
@@ -118,6 +160,7 @@ struct tnl_ptk_info {
 struct ip_tunnel_net {
 	struct net_device *fb_tunnel_dev;
 	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
+	struct ip_tunnel __rcu *collect_md_tun;
 };
 
 struct ip_tunnel_encap_ops {
@@ -136,6 +179,40 @@ int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 			    unsigned int num);
 
+static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
+				      __be32 saddr, __be32 daddr,
+				      u8 tos, u8 ttl,
+				      __be16 tp_src, __be16 tp_dst,
+				      __be64 tun_id, __be16 tun_flags)
+{
+	key->tun_id = tun_id;
+	key->u.ipv4.src = saddr;
+	key->u.ipv4.dst = daddr;
+	memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD,
+	       0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
+	key->tos = tos;
+	key->ttl = ttl;
+	key->tun_flags = tun_flags;
+
+	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+	 * the upper tunnel are used.
+	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+	 */
+	key->tp_src = tp_src;
+	key->tp_dst = tp_dst;
+
+	/* Clear struct padding. */
+	if (sizeof(*key) != IP_TUNNEL_KEY_SIZE)
+		memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE,
+		       0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
+}
+
+static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
+					       *tun_info)
+{
+	return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET;
+}
+
 #ifdef CONFIG_INET
 
 int ip_tunnel_init(struct net_device *dev);
@@ -163,7 +240,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 key);
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
-		  const struct tnl_ptk_info *tpi, bool log_ecn_error);
+		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
+		  bool log_ecn_error);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 			 struct ip_tunnel_parm *p);
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
@@ -196,8 +274,8 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 
 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);
+		  __be32 src, __be32 dst, u8 proto,
+		  u8 tos, u8 ttl, __be16 df, bool xnet);
 
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
 					 int gso_type_mask);
@@ -221,6 +299,57 @@ static inline void iptunnel_xmit_stats(int err,
 	}
 }
 
+static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info)
+{
+	return info + 1;
+}
+
+static inline void ip_tunnel_info_opts_get(void *to,
+					   const struct ip_tunnel_info *info)
+{
+	memcpy(to, info + 1, info->options_len);
+}
+
+static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
+					   const void *from, int len)
+{
+	memcpy(ip_tunnel_info_opts(info), from, len);
+	info->options_len = len;
+}
+
+static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
+{
+	return (struct ip_tunnel_info *)lwtstate->data;
+}
+
+extern struct static_key ip_tunnel_metadata_cnt;
+
+/* Returns > 0 if metadata should be collected */
+static inline int ip_tunnel_collect_metadata(void)
+{
+	return static_key_false(&ip_tunnel_metadata_cnt);
+}
+
+void __init ip_tunnel_core_init(void);
+
+void ip_tunnel_need_metadata(void);
+void ip_tunnel_unneed_metadata(void);
+
+#else /* CONFIG_INET */
+
+static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
+{
+	return NULL;
+}
+
+static inline void ip_tunnel_need_metadata(void)
+{
+}
+
+static inline void ip_tunnel_unneed_metadata(void)
+{
+}
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */