From 0c867c9bf84ce2a998f83725bd363f66ce84d548 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 5 Apr 2016 14:47:10 +0200 Subject: vxlan: move Ethernet initialization to a separate function This will allow to initialize vxlan in ARPHRD_NONE mode based on the passed rtnl attributes. v2: renamed "l2mode" to "ether". Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1c0fa364323e..6bd5b874ead7 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2404,7 +2404,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return 0; } -static const struct net_device_ops vxlan_netdev_ops = { +static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, @@ -2458,10 +2458,6 @@ static void vxlan_setup(struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; - eth_hw_addr_random(dev); - ether_setup(dev); - - dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = free_netdev; SET_NETDEV_DEVTYPE(dev, &vxlan_type); @@ -2476,8 +2472,7 @@ static void vxlan_setup(struct net_device *dev) dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; netif_keep_dst(dev); - dev->priv_flags &= ~IFF_TX_SKB_SHARING; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; + dev->priv_flags |= IFF_NO_QUEUE; INIT_LIST_HEAD(&vxlan->next); spin_lock_init(&vxlan->hash_lock); @@ -2496,6 +2491,15 @@ static void vxlan_setup(struct net_device *dev) INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } +static void vxlan_ether_setup(struct net_device *dev) +{ + eth_hw_addr_random(dev); + ether_setup(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &vxlan_netdev_ether_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) }, @@ -2722,6 +2726,8 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, __be16 default_port = vxlan->cfg.dst_port; struct net_device *lowerdev = NULL; + vxlan_ether_setup(dev); + vxlan->net = src_net; dst->remote_vni = conf->vni; -- cgit v1.2.3-59-g8ed1b From 47e5d1b06305e73afc917f47b65490adb06c7194 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 5 Apr 2016 14:47:11 +0200 Subject: vxlan: move fdb code to common location in vxlan_xmit Handle VXLAN_F_COLLECT_METADATA before VXLAN_F_PROXY. The latter does not make sense with the former, as it needs populated fdb which does not happen in metadata mode. After this cleanup, the fdb code in vxlan_xmit is moved to a common location and can be later skipped for VXLAN-GPE which does not necessarily carry inner Ethernet header. v2: changed commit description to not reference L3 mode Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6bd5b874ead7..d62eebaa9720 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2106,9 +2106,17 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) info = skb_tunnel_info(skb); skb_reset_mac_header(skb); - eth = eth_hdr(skb); - if ((vxlan->flags & VXLAN_F_PROXY)) { + if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { + if (info && info->mode & IP_TUNNEL_INFO_TX) + vxlan_xmit_one(skb, dev, NULL, false); + else + kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (vxlan->flags & VXLAN_F_PROXY) { + eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -2123,18 +2131,10 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb); } - eth = eth_hdr(skb); #endif } - if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { - if (info && info->mode & IP_TUNNEL_INFO_TX) - vxlan_xmit_one(skb, dev, NULL, false); - else - kfree_skb(skb); - return NETDEV_TX_OK; - } - + eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest); did_rsc = false; -- cgit v1.2.3-59-g8ed1b From a6d5bbf34efa8330af7b0b1dba0f38148516ed97 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 5 Apr 2016 14:47:12 +0200 Subject: ip_tunnel: implement __iptunnel_pull_header Allow calling of iptunnel_pull_header without special casing ETH_P_TEB inner protocol. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 11 +++++++++-- net/ipv4/ip_tunnel_core.c | 8 ++++---- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 56050f913339..16435d8b1f93 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -295,8 +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, - bool xnet); +int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool raw_proto, bool xnet); + +static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool xnet) +{ + return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, 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); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index b3ab1205dfdf..43445df61efd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -86,15 +86,15 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(iptunnel_xmit); -int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, - bool xnet) +int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool raw_proto, bool xnet) { if (unlikely(!pskb_may_pull(skb, hdr_len))) return -ENOMEM; skb_pull_rcsum(skb, hdr_len); - if (inner_proto == htons(ETH_P_TEB)) { + if (!raw_proto && inner_proto == htons(ETH_P_TEB)) { struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) @@ -117,7 +117,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, return iptunnel_pull_offloads(skb); } -EXPORT_SYMBOL_GPL(iptunnel_pull_header); +EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) -- cgit v1.2.3-59-g8ed1b From e1e5314de08ba6003b358125eafc9ad9e75a950c Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 5 Apr 2016 14:47:13 +0200 Subject: 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 Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 170 ++++++++++++++++++++++++++++++++++++++----- include/net/vxlan.h | 68 +++++++++++++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 222 insertions(+), 17 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index d62eebaa9720..51cccddfe403 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1192,6 +1192,45 @@ out: 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) @@ -1257,9 +1296,11 @@ static int vxlan_rcv(struct sock *sk, 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; @@ -1283,9 +1324,18 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) 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); @@ -1304,14 +1354,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) 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 @@ -1325,8 +1375,13 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) 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); @@ -1685,6 +1740,27 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags, 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, @@ -1694,6 +1770,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, 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) { @@ -1712,10 +1789,8 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, /* 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)) @@ -1744,9 +1819,19 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, 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, @@ -2421,6 +2506,17 @@ static const struct net_device_ops vxlan_netdev_ether_ops = { .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", @@ -2500,6 +2596,17 @@ static void vxlan_ether_setup(struct net_device *dev) 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) }, @@ -2526,6 +2633,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [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 }, }; @@ -2726,7 +2834,20 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, __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; @@ -2789,8 +2910,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, 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) @@ -2961,6 +3086,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, 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; @@ -2977,6 +3105,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, 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; @@ -3104,6 +3236,10 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) 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; 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) -- cgit v1.2.3-59-g8ed1b