summaryrefslogtreecommitdiffstats
path: root/include/net/vxlan.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-02-10 20:01:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2015-02-10 20:01:30 -0800
commitc5ce28df0e7c01a1de23c36ebdefcd803f2b6cbb (patch)
tree9830baf38832769e1cf621708889111bbe3c93df /include/net/vxlan.h
parent29afc4e9a408f2304e09c6dd0dbcfbd2356d0faa (diff)
parent9399f0c51489ae8c16d6559b82a452fdc1895e91 (diff)
downloadlinux-c5ce28df0e7c01a1de23c36ebdefcd803f2b6cbb.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) More iov_iter conversion work from Al Viro. [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was wrong, and this pull actually adds an extra commit on top of the branch I'm pulling to fix that up, so that the pre-merge state is ok. - Linus ] 2) Various optimizations to the ipv4 forwarding information base trie lookup implementation. From Alexander Duyck. 3) Remove sock_iocb altogether, from CHristoph Hellwig. 4) Allow congestion control algorithm selection via routing metrics. From Daniel Borkmann. 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet. 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet. 7) Add xmit_more support to r8169, e1000, and e1000e drivers. From Florian Westphal. 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross. 9) Add BPF packet actions to packet scheduler, from Jiri Pirko. 10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer. 11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman Kwok. 12) More sanely handle out-of-window dupacks, which can result in serious ACK storms. From Neal Cardwell. 13) Various rhashtable bug fixes and enhancements, from Herbert Xu, Patrick McHardy, and Thomas Graf. 14) Support xmit_more in be2net, from Sathya Perla. 15) Group Policy extensions for vxlan, from Thomas Graf. 16) Remove Checksum Offload support for vxlan, from Tom Herbert. 17) Like ipv4, support lockless transmit over ipv6 UDP sockets. From Vlad Yasevich. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits) crypto: fix af_alg_make_sg() conversion to iov_iter ipv4: Namespecify TCP PMTU mechanism i40e: Fix for stats init function call in Rx setup tcp: don't include Fast Open option in SYN-ACK on pure SYN-data openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set ipv6: Make __ipv6_select_ident static ipv6: Fix fragment id assignment on LE arches. bridge: Fix inability to add non-vlan fdb entry net: Mellanox: Delete unnecessary checks before the function call "vunmap" cxgb4: Add support in cxgb4 to get expansion rom version via ethtool ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version net: dsa: Remove redundant phy_attach() IB/mlx4: Reset flow support for IB kernel ULPs IB/mlx4: Always use the correct port for mirrored multicast attachments net/bonding: Fix potential bad memory access during bonding events tipc: remove tipc_snprintf tipc: nl compat add noop and remove legacy nl framework tipc: convert legacy nl stats show to nl compat tipc: convert legacy nl net id get to nl compat tipc: convert legacy nl net id set to nl compat ...
Diffstat (limited to 'include/net/vxlan.h')
-rw-r--r--include/net/vxlan.h103
1 files changed, 98 insertions, 5 deletions
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 903461aa5644..2927d6244481 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -11,14 +11,96 @@
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
-/* VXLAN protocol header */
+/*
+ * VXLAN Group Based Policy Extension:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R| Group Policy ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VXLAN Network Identifier (VNI) | Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * D = Don't Learn bit. When set, this bit indicates that the egress
+ * VTEP MUST NOT learn the source address of the encapsulated frame.
+ *
+ * A = Indicates that the group policy has already been applied to
+ * 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
+ */
+struct vxlanhdr_gbp {
+ __u8 vx_flags;
+#ifdef __LITTLE_ENDIAN_BITFIELD
+ __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,
+ dont_learn:1,
+ reserved_flags2:2,
+ policy_applied:1,
+ reserved_flags3:3;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ __be16 policy_id;
+ __be32 vx_vni;
+};
+
+#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
+
+/* skb->mark mapping
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|R|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+#define VXLAN_GBP_DONT_LEARN (BIT(6) << 16)
+#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(24)
+#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_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+
+struct vxlan_metadata {
+ __be32 vni;
+ u32 gbp;
+};
+
struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
+typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb,
+ struct vxlan_metadata *md);
/* per UDP socket information */
struct vxlan_sock {
@@ -31,6 +113,7 @@ struct vxlan_sock {
struct hlist_head vni_list[VNI_HASH_SIZE];
atomic_t refcnt;
struct udp_offload udp_offloads;
+ u32 flags;
};
#define VXLAN_F_LEARN 0x01
@@ -42,6 +125,16 @@ struct vxlan_sock {
#define VXLAN_F_UDP_CSUM 0x40
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
+#define VXLAN_F_REMCSUM_TX 0x200
+#define VXLAN_F_REMCSUM_RX 0x400
+#define VXLAN_F_GBP 0x800
+
+/* Flags that are used in the receive patch. These flags must match in
+ * order for a socket to be shareable
+ */
+#define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \
+ VXLAN_F_UDP_ZERO_CSUM6_RX | \
+ VXLAN_F_REMCSUM_RX)
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
@@ -49,10 +142,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
void vxlan_sock_release(struct vxlan_sock *vs);
-int vxlan_xmit_skb(struct vxlan_sock *vs,
- struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
+ __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
+ bool xnet, u32 vxflags);
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
netdev_features_t features)