unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS;
}
+static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed,
+ __be32 *protocol,
+ struct sk_buff *skb, u32 vxflags)
+{
+ struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)unparsed;
+
+ /* Need to have Next Protocol set for interfaces in GPE mode. */
+ if (!gpe->np_applied)
+ return false;
+ /* "The initial version is 0. If a receiver does not support the
+ * version indicated it MUST drop the packet.
+ */
+ if (gpe->version != 0)
+ return false;
+ /* "When the O bit is set to 1, the packet is an OAM packet and OAM
+ * processing MUST occur." However, we don't implement OAM
+ * processing, thus drop the packet.
+ */
+ if (gpe->oam_flag)
+ return false;
+
+ switch (gpe->next_protocol) {
+ case VXLAN_GPE_NP_IPV4:
+ *protocol = htons(ETH_P_IP);
+ break;
+ case VXLAN_GPE_NP_IPV6:
+ *protocol = htons(ETH_P_IPV6);
+ break;
+ case VXLAN_GPE_NP_ETHERNET:
+ *protocol = htons(ETH_P_TEB);
+ break;
+ default:
+ return false;
+ }
+
+ unparsed->vx_flags &= ~VXLAN_GPE_USED_BITS;
+ return true;
+}
+
static bool vxlan_set_mac(struct vxlan_dev *vxlan,
struct vxlan_sock *vs,
struct sk_buff *skb)
struct vxlanhdr unparsed;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
+ __be32 protocol = htons(ETH_P_TEB);
+ bool raw_proto = false;
void *oiph;
- /* Need Vxlan and inner Ethernet header to be present */
+ /* Need UDP and VXLAN header to be present */
if (!pskb_may_pull(skb, VXLAN_HLEN))
return 1;
if (!vxlan)
goto drop;
- if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB),
- !net_eq(vxlan->net, dev_net(vxlan->dev))))
- goto drop;
+ /* For backwards compatibility, only allow reserved fields to be
+ * used by VXLAN extensions if explicitly requested.
+ */
+ if (vs->flags & VXLAN_F_GPE) {
+ if (!vxlan_parse_gpe_hdr(&unparsed, &protocol, skb, vs->flags))
+ goto drop;
+ raw_proto = true;
+ }
+
+ if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto,
+ !net_eq(vxlan->net, dev_net(vxlan->dev))))
+ goto drop;
if (vxlan_collect_metadata(vs)) {
__be32 vni = vxlan_vni(vxlan_hdr(skb)->vx_vni);
memset(md, 0, sizeof(*md));
}
- /* For backwards compatibility, only allow reserved fields to be
- * used by VXLAN extensions if explicitly requested.
- */
if (vs->flags & VXLAN_F_REMCSUM_RX)
if (!vxlan_remcsum(&unparsed, skb, vs->flags))
goto drop;
if (vs->flags & VXLAN_F_GBP)
vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md);
+ /* Note that GBP and GPE can never be active together. This is
+ * ensured in vxlan_dev_configure.
+ */
if (unparsed.vx_flags || unparsed.vx_vni) {
/* If there are any unprocessed flags remaining treat
goto drop;
}
- if (!vxlan_set_mac(vxlan, vs, skb))
- goto drop;
+ if (!raw_proto) {
+ if (!vxlan_set_mac(vxlan, vs, skb))
+ goto drop;
+ } else {
+ skb->dev = vxlan->dev;
+ skb->pkt_type = PACKET_HOST;
+ }
oiph = skb_network_header(skb);
skb_reset_network_header(skb);
gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
}
+static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, u32 vxflags,
+ __be16 protocol)
+{
+ struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh;
+
+ gpe->np_applied = 1;
+
+ switch (protocol) {
+ case htons(ETH_P_IP):
+ gpe->next_protocol = VXLAN_GPE_NP_IPV4;
+ return 0;
+ case htons(ETH_P_IPV6):
+ gpe->next_protocol = VXLAN_GPE_NP_IPV6;
+ return 0;
+ case htons(ETH_P_TEB):
+ gpe->next_protocol = VXLAN_GPE_NP_ETHERNET;
+ return 0;
+ }
+ return -EPFNOSUPPORT;
+}
+
static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
int iphdr_len, __be32 vni,
struct vxlan_metadata *md, u32 vxflags,
int min_headroom;
int err;
int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+ __be16 inner_protocol = htons(ETH_P_TEB);
if ((vxflags & VXLAN_F_REMCSUM_TX) &&
skb->ip_summed == CHECKSUM_PARTIAL) {
/* Need space for new headers (invalidates iph ptr) */
err = skb_cow_head(skb, min_headroom);
- if (unlikely(err)) {
- kfree_skb(skb);
- return err;
- }
+ if (unlikely(err))
+ goto out_free;
skb = vlan_hwaccel_push_inside(skb);
if (WARN_ON(!skb))
if (vxflags & VXLAN_F_GBP)
vxlan_build_gbp_hdr(vxh, vxflags, md);
+ if (vxflags & VXLAN_F_GPE) {
+ err = vxlan_build_gpe_hdr(vxh, vxflags, skb->protocol);
+ if (err < 0)
+ goto out_free;
+ inner_protocol = skb->protocol;
+ }
- skb_set_inner_protocol(skb, htons(ETH_P_TEB));
+ skb_set_inner_protocol(skb, inner_protocol);
return 0;
+
+out_free:
+ kfree_skb(skb);
+ return err;
}
static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
.ndo_fill_metadata_dst = vxlan_fill_metadata_dst,
};
+static const struct net_device_ops vxlan_netdev_raw_ops = {
+ .ndo_init = vxlan_init,
+ .ndo_uninit = vxlan_uninit,
+ .ndo_open = vxlan_open,
+ .ndo_stop = vxlan_stop,
+ .ndo_start_xmit = vxlan_xmit,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_change_mtu = vxlan_change_mtu,
+ .ndo_fill_metadata_dst = vxlan_fill_metadata_dst,
+};
+
/* Info for udev, that this is a virtual tunnel endpoint */
static struct device_type vxlan_type = {
.name = "vxlan",
dev->netdev_ops = &vxlan_netdev_ether_ops;
}
+static void vxlan_raw_setup(struct net_device *dev)
+{
+ dev->type = ARPHRD_NONE;
+ dev->hard_header_len = 0;
+ dev->addr_len = 0;
+ dev->mtu = ETH_DATA_LEN;
+ dev->tx_queue_len = 1000;
+ dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+ dev->netdev_ops = &vxlan_netdev_raw_ops;
+}
+
static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
[IFLA_VXLAN_ID] = { .type = NLA_U32 },
[IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
[IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 },
[IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 },
[IFLA_VXLAN_GBP] = { .type = NLA_FLAG, },
+ [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, },
[IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG },
};
__be16 default_port = vxlan->cfg.dst_port;
struct net_device *lowerdev = NULL;
- vxlan_ether_setup(dev);
+ if (conf->flags & VXLAN_F_GPE) {
+ if (conf->flags & ~VXLAN_F_ALLOWED_GPE)
+ return -EINVAL;
+ /* For now, allow GPE only together with COLLECT_METADATA.
+ * This can be relaxed later; in such case, the other side
+ * of the PtP link will have to be provided.
+ */
+ if (!(conf->flags & VXLAN_F_COLLECT_METADATA))
+ return -EINVAL;
+
+ vxlan_raw_setup(dev);
+ } else {
+ vxlan_ether_setup(dev);
+ }
vxlan->net = src_net;
dev->needed_headroom = needed_headroom;
memcpy(&vxlan->cfg, conf, sizeof(*conf));
- if (!vxlan->cfg.dst_port)
- vxlan->cfg.dst_port = default_port;
+ if (!vxlan->cfg.dst_port) {
+ if (conf->flags & VXLAN_F_GPE)
+ vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */
+ else
+ vxlan->cfg.dst_port = default_port;
+ }
vxlan->flags |= conf->flags;
if (!vxlan->cfg.age_interval)
if (data[IFLA_VXLAN_GBP])
conf.flags |= VXLAN_F_GBP;
+ if (data[IFLA_VXLAN_GPE])
+ conf.flags |= VXLAN_F_GPE;
+
if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
case -EEXIST:
pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni));
break;
+
+ case -EINVAL:
+ pr_info("unsupported combination of extensions\n");
+ break;
}
return err;
nla_put_flag(skb, IFLA_VXLAN_GBP))
goto nla_put_failure;
+ if (vxlan->flags & VXLAN_F_GPE &&
+ nla_put_flag(skb, IFLA_VXLAN_GPE))
+ goto nla_put_failure;
+
if (vxlan->flags & VXLAN_F_REMCSUM_NOPARTIAL &&
nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL))
goto nla_put_failure;
#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;
};
#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);
projects / users / hch / configfs.git / commitdiff