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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 44 insertions, 11 deletions

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index dda9abf6b89c..c35dda9ec991 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -7,12 +7,15 @@
 #include <linux/socket.h>
 #include <linux/types.h>
 #include <linux/u64_stats_sync.h>
+#include <linux/bitops.h>
+
 #include <net/dsfield.h>
 #include <net/gro_cells.h>
 #include <net/inet_ecn.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/lwtunnel.h>
+#include <net/dst_cache.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -47,6 +50,7 @@ struct ip_tunnel_key {
 	__be16			tun_flags;
 	u8			tos;		/* TOS for IPv4, TC for IPv6 */
 	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
+	__be32			label;		/* Flow Label for IPv6 */
 	__be16			tp_src;
 	__be16			tp_dst;
 };
@@ -55,8 +59,16 @@ struct ip_tunnel_key {
 #define IP_TUNNEL_INFO_TX	0x01	/* represents tx tunnel parameters */
 #define IP_TUNNEL_INFO_IPV6	0x02	/* key contains IPv6 addresses */
 
+/* Maximum tunnel options length. */
+#define IP_TUNNEL_OPTS_MAX					\
+	GENMASK((FIELD_SIZEOF(struct ip_tunnel_info,		\
+			      options_len) * BITS_PER_BYTE) - 1, 0)
+
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache	dst_cache;
+#endif
 	u8			options_len;
 	u8			mode;
 };
@@ -85,11 +97,6 @@ struct ip_tunnel_prl_entry {
 	struct rcu_head			rcu_head;
 };
 
-struct ip_tunnel_dst {
-	struct dst_entry __rcu 		*dst;
-	__be32				 saddr;
-};
-
 struct metadata_dst;
 
 struct ip_tunnel {
@@ -108,7 +115,7 @@ struct ip_tunnel {
 	int		tun_hlen;	/* Precalculated header length */
 	int		mlink;
 
-	struct ip_tunnel_dst __percpu *dst_cache;
+	struct dst_cache dst_cache;
 
 	struct ip_tunnel_parm parms;
 
@@ -141,6 +148,7 @@ struct ip_tunnel {
 #define TUNNEL_CRIT_OPT		__cpu_to_be16(0x0400)
 #define TUNNEL_GENEVE_OPT	__cpu_to_be16(0x0800)
 #define TUNNEL_VXLAN_OPT	__cpu_to_be16(0x1000)
+#define TUNNEL_NOCACHE		__cpu_to_be16(0x2000)
 
 #define TUNNEL_OPTIONS_PRESENT	(TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT)
 
@@ -181,7 +189,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 
 static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 				      __be32 saddr, __be32 daddr,
-				      u8 tos, u8 ttl,
+				      u8 tos, u8 ttl, __be32 label,
 				      __be16 tp_src, __be16 tp_dst,
 				      __be64 tun_id, __be16 tun_flags)
 {
@@ -192,6 +200,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 	       0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
 	key->tos = tos;
 	key->ttl = ttl;
+	key->label = label;
 	key->tun_flags = tun_flags;
 
 	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
@@ -207,6 +216,20 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 		       0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
 }
 
+static inline bool
+ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
+			   const struct ip_tunnel_info *info)
+{
+	if (skb->mark)
+		return false;
+	if (!info)
+		return true;
+	if (info->key.tun_flags & TUNNEL_NOCACHE)
+		return false;
+
+	return true;
+}
+
 static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
 					       *tun_info)
 {
@@ -248,7 +271,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
-void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
@@ -273,15 +295,15 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 	return INET_ECN_encapsulate(tos, inner);
 }
 
-int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
+int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto,
+			 bool xnet);
 void 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);
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
 
 static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 {
@@ -356,6 +378,17 @@ static inline void ip_tunnel_unneed_metadata(void)
 {
 }
 
+static inline void ip_tunnel_info_opts_get(void *to,
+					   const struct ip_tunnel_info *info)
+{
+}
+
+static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
+					   const void *from, int len)
+{
+	info->options_len = 0;
+}
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */