vxlan: implement GPE

Implement VXLAN-GPE. Only COLLECT_METADATA is supported for now (it is
possible to support static configuration, too, if there is demand for it).

The GPE header parsing has to be moved before iptunnel_pull_header, as we
need to know the protocol.

v2: Removed what was called "L2 mode" in v1 of the patchset. Only "L3 mode"
    (now called "raw mode") is added by this patch. This mode does not allow
    Ethernet header to be encapsulated in VXLAN-GPE when using ip route to
    specify the encapsulation, IP header is encapsulated instead. The patch
    does support Ethernet to be encapsulated, though, using ETH_P_TEB in
    skb->protocol. This will be utilized by other COLLECT_METADATA users
    (openvswitch in particular).

    If there is ever demand for Ethernet encapsulation with VXLAN-GPE using
    ip route, it's easy to add a new flag switching the interface to
    "Ethernet mode" (called "L2 mode" in v1 of this patchset). For now,
    leave this out, it seems we don't need it.

    Disallowed more flag combinations, especially RCO with GPE.
    Added comment explaining that GBP and GPE cannot be set together.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 69 insertions, 0 deletions

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 73ed2e951c02..dcc6f4057115 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -119,6 +119,64 @@ struct vxlanhdr_gbp {
 #define VXLAN_GBP_POLICY_APPLIED	(BIT(3) << 16)
 #define VXLAN_GBP_ID_MASK		(0xFFFF)
 
+/*
+ * VXLAN Generic Protocol Extension (VXLAN_F_GPE):
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|Ver|I|P|R|O|       Reserved                |Next Protocol  |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                VXLAN Network Identifier (VNI) |   Reserved    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Ver = Version. Indicates VXLAN GPE protocol version.
+ *
+ * P = Next Protocol Bit. The P bit is set to indicate that the
+ *     Next Protocol field is present.
+ *
+ * O = OAM Flag Bit. The O bit is set to indicate that the packet
+ *     is an OAM packet.
+ *
+ * Next Protocol = This 8 bit field indicates the protocol header
+ * immediately following the VXLAN GPE header.
+ *
+ * https://tools.ietf.org/html/draft-ietf-nvo3-vxlan-gpe-01
+ */
+
+struct vxlanhdr_gpe {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	u8	oam_flag:1,
+		reserved_flags1:1,
+		np_applied:1,
+		instance_applied:1,
+		version:2,
+reserved_flags2:2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	u8	reserved_flags2:2,
+		version:2,
+		instance_applied:1,
+		np_applied:1,
+		reserved_flags1:1,
+		oam_flag:1;
+#endif
+	u8	reserved_flags3;
+	u8	reserved_flags4;
+	u8	next_protocol;
+	__be32	vx_vni;
+};
+
+/* VXLAN-GPE header flags. */
+#define VXLAN_HF_VER	cpu_to_be32(BIT(29) | BIT(28))
+#define VXLAN_HF_NP	cpu_to_be32(BIT(26))
+#define VXLAN_HF_OAM	cpu_to_be32(BIT(24))
+
+#define VXLAN_GPE_USED_BITS (VXLAN_HF_VER | VXLAN_HF_NP | VXLAN_HF_OAM | \
+			     cpu_to_be32(0xff))
+
+/* VXLAN-GPE header Next Protocol. */
+#define VXLAN_GPE_NP_IPV4      0x01
+#define VXLAN_GPE_NP_IPV6      0x02
+#define VXLAN_GPE_NP_ETHERNET  0x03
+#define VXLAN_GPE_NP_NSH       0x04
+
 struct vxlan_metadata {
 	u32		gbp;
 };
@@ -206,16 +264,26 @@ struct vxlan_dev {
 #define VXLAN_F_GBP			0x800
 #define VXLAN_F_REMCSUM_NOPARTIAL	0x1000
 #define VXLAN_F_COLLECT_METADATA	0x2000
+#define VXLAN_F_GPE			0x4000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
  */
 #define VXLAN_F_RCV_FLAGS		(VXLAN_F_GBP |			\
+					 VXLAN_F_GPE |			\
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
 					 VXLAN_F_REMCSUM_RX |		\
 					 VXLAN_F_REMCSUM_NOPARTIAL |	\
 					 VXLAN_F_COLLECT_METADATA)
 
+/* Flags that can be set together with VXLAN_F_GPE. */
+#define VXLAN_F_ALLOWED_GPE		(VXLAN_F_GPE |			\
+					 VXLAN_F_IPV6 |			\
+					 VXLAN_F_UDP_ZERO_CSUM_TX |	\
+					 VXLAN_F_UDP_ZERO_CSUM6_TX |	\
+					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
+					 VXLAN_F_COLLECT_METADATA)
+
 struct net_device *vxlan_dev_create(struct net *net, const char *name,
 				    u8 name_assign_type, struct vxlan_config *conf);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c488066fb53a..9427f17d06d6 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -488,6 +488,7 @@ enum {
 	IFLA_VXLAN_REMCSUM_NOPARTIAL,
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
+	IFLA_VXLAN_GPE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)