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, 135 insertions, 52 deletions

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0fb86442544b..a763c96ecde4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -9,17 +9,71 @@
 #include <linux/udp.h>
 #include <net/dst_metadata.h>
 
+/* VXLAN protocol (RFC 7348) header:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R|               Reserved                        |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                VXLAN Network Identifier (VNI) |   Reserved    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * I = VXLAN Network Identifier (VNI) present.
+ */
+struct vxlanhdr {
+	__be32 vx_flags;
+	__be32 vx_vni;
+};
+
+/* VXLAN header flags. */
+#define VXLAN_HF_VNI	cpu_to_be32(BIT(27))
+
+#define VXLAN_N_VID     (1u << 24)
+#define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
+#define VXLAN_VNI_MASK	cpu_to_be32(VXLAN_VID_MASK << 8)
+#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+
 #define VNI_HASH_BITS	10
 #define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
+#define FDB_HASH_BITS	8
+#define FDB_HASH_SIZE	(1<<FDB_HASH_BITS)
+
+/* Remote checksum offload for VXLAN (VXLAN_F_REMCSUM_[RT]X):
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R|R|R|C|              Reserved                   |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |           VXLAN Network Identifier (VNI)      |O| Csum start  |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C = Remote checksum offload bit. When set indicates that the
+ *     remote checksum offload data is present.
+ *
+ * O = Offset bit. Indicates the checksum offset relative to
+ *     checksum start.
+ *
+ * Csum start = Checksum start divided by two.
+ *
+ * http://tools.ietf.org/html/draft-herbert-vxlan-rco
+ */
+
+/* VXLAN-RCO header flags. */
+#define VXLAN_HF_RCO	cpu_to_be32(BIT(21))
+
+/* Remote checksum offload header option */
+#define VXLAN_RCO_MASK	cpu_to_be32(0x7f)  /* Last byte of vni field */
+#define VXLAN_RCO_UDP	cpu_to_be32(0x80)  /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT	1		   /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (0x7f << VXLAN_RCO_SHIFT)
 
 /*
- * VXLAN Group Based Policy Extension:
+ * VXLAN Group Based Policy Extension (VXLAN_F_GBP):
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R|        Group Policy ID        |
+ * |G|R|R|R|I|R|R|R|R|D|R|R|A|R|R|R|        Group Policy ID        |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |                VXLAN Network Identifier (VNI) |   Reserved    |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  *
+ * G = Group Policy ID present.
+ *
  * D = Don't Learn bit. When set, this bit indicates that the egress
  *     VTEP MUST NOT learn the source address of the encapsulated frame.
  *
@@ -27,18 +81,18 @@
  *     this packet. Policies MUST NOT be applied by devices when the
  *     A bit is set.
  *
- * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
+ * https://tools.ietf.org/html/draft-smith-vxlan-group-policy
  */
 struct vxlanhdr_gbp {
-	__u8	vx_flags;
+	u8	vx_flags;
 #ifdef __LITTLE_ENDIAN_BITFIELD
-	__u8	reserved_flags1:3,
+	u8	reserved_flags1:3,
 		policy_applied:1,
 		reserved_flags2:2,
 		dont_learn:1,
 		reserved_flags3:1;
 #elif defined(__BIG_ENDIAN_BITFIELD)
-	__u8	reserved_flags1:1,
+	u8	reserved_flags1:1,
 		dont_learn:1,
 		reserved_flags2:2,
 		policy_applied:1,
@@ -50,7 +104,10 @@ struct vxlanhdr_gbp {
 	__be32	vx_vni;
 };
 
-#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
+/* VXLAN-GBP header flags. */
+#define VXLAN_HF_GBP	cpu_to_be32(BIT(31))
+
+#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | cpu_to_be32(0xFFFFFF))
 
 /* skb->mark mapping
  *
@@ -62,44 +119,6 @@ struct vxlanhdr_gbp {
 #define VXLAN_GBP_POLICY_APPLIED	(BIT(3) << 16)
 #define VXLAN_GBP_ID_MASK		(0xFFFF)
 
-/* VXLAN protocol header:
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |G|R|R|R|I|R|R|C|               Reserved                        |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |                VXLAN Network Identifier (VNI) |   Reserved    |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- *
- * G = 1	Group Policy (VXLAN-GBP)
- * I = 1	VXLAN Network Identifier (VNI) present
- * C = 1	Remote checksum offload (RCO)
- */
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-};
-
-/* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(21)
-#define VXLAN_HF_VNI BIT(27)
-#define VXLAN_HF_GBP BIT(31)
-
-/* Remote checksum offload header option */
-#define VXLAN_RCO_MASK  0x7f    /* Last byte of vni field */
-#define VXLAN_RCO_UDP   0x80    /* Indicate UDP RCO (TCP when not set *) */
-#define VXLAN_RCO_SHIFT 1       /* Left shift of start */
-#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
-#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
-
-#define VXLAN_N_VID     (1u << 24)
-#define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
-#define VXLAN_VNI_MASK  (VXLAN_VID_MASK << 8)
-#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
-
-#define VNI_HASH_BITS	10
-#define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
-#define FDB_HASH_BITS	8
-#define FDB_HASH_SIZE	(1<<FDB_HASH_BITS)
-
 struct vxlan_metadata {
 	u32		gbp;
 };
@@ -125,23 +144,25 @@ union vxlan_addr {
 struct vxlan_rdst {
 	union vxlan_addr	 remote_ip;
 	__be16			 remote_port;
-	u32			 remote_vni;
+	__be32			 remote_vni;
 	u32			 remote_ifindex;
 	struct list_head	 list;
 	struct rcu_head		 rcu;
+	struct dst_cache	 dst_cache;
 };
 
 struct vxlan_config {
 	union vxlan_addr	remote_ip;
 	union vxlan_addr	saddr;
-	u32			vni;
+	__be32			vni;
 	int			remote_ifindex;
 	int			mtu;
 	__be16			dst_port;
-	__u16			port_min;
-	__u16			port_max;
-	__u8			tos;
-	__u8			ttl;
+	u16			port_min;
+	u16			port_max;
+	u8			tos;
+	u8			ttl;
+	__be32			label;
 	u32			flags;
 	unsigned long		age_interval;
 	unsigned int		addrmax;
@@ -177,7 +198,7 @@ struct vxlan_dev {
 #define VXLAN_F_L2MISS			0x08
 #define VXLAN_F_L3MISS			0x10
 #define VXLAN_F_IPV6			0x20
-#define VXLAN_F_UDP_CSUM		0x40
+#define VXLAN_F_UDP_ZERO_CSUM_TX	0x40
 #define VXLAN_F_UDP_ZERO_CSUM6_TX	0x80
 #define VXLAN_F_UDP_ZERO_CSUM6_RX	0x100
 #define VXLAN_F_REMCSUM_TX		0x200
@@ -242,6 +263,68 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
 /* IPv6 header + UDP + VXLAN + Ethernet header */
 #define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
 
+static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb)
+{
+	return (struct vxlanhdr *)(udp_hdr(skb) + 1);
+}
+
+static inline __be32 vxlan_vni(__be32 vni_field)
+{
+#if defined(__BIG_ENDIAN)
+	return vni_field >> 8;
+#else
+	return (vni_field & VXLAN_VNI_MASK) << 8;
+#endif
+}
+
+static inline __be32 vxlan_vni_field(__be32 vni)
+{
+#if defined(__BIG_ENDIAN)
+	return vni << 8;
+#else
+	return vni >> 8;
+#endif
+}
+
+static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id)
+{
+#if defined(__BIG_ENDIAN)
+	return tun_id;
+#else
+	return tun_id >> 32;
+#endif
+}
+
+static inline __be64 vxlan_vni_to_tun_id(__be32 vni)
+{
+#if defined(__BIG_ENDIAN)
+	return (__be64)vni;
+#else
+	return (__be64)vni << 32;
+#endif
+}
+
+static inline size_t vxlan_rco_start(__be32 vni_field)
+{
+	return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+}
+
+static inline size_t vxlan_rco_offset(__be32 vni_field)
+{
+	return (vni_field & VXLAN_RCO_UDP) ?
+		offsetof(struct udphdr, check) :
+		offsetof(struct tcphdr, check);
+}
+
+static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset)
+{
+	__be32 vni_field = cpu_to_be32(start >> VXLAN_RCO_SHIFT);
+
+	if (offset == offsetof(struct udphdr, check))
+		vni_field |= VXLAN_RCO_UDP;
+	return vni_field;
+}
+
 #if IS_ENABLED(CONFIG_VXLAN)
 void vxlan_get_rx_port(struct net_device *netdev);
 #else