return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
}
-/* Find VXLAN socket based on network namespace and UDP port */
-static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port)
+/* Find VXLAN socket based on network namespace, address family and UDP port */
+static struct vxlan_sock *vxlan_find_sock(struct net *net,
+ sa_family_t family, __be16 port)
{
struct vxlan_sock *vs;
hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
- if (inet_sk(vs->sock->sk)->inet_sport == port)
+ if (inet_sk(vs->sock->sk)->inet_sport == port &&
+ inet_sk(vs->sock->sk)->sk.sk_family == family)
return vs;
}
return NULL;
}
/* Look up VNI in a per net namespace table */
-static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port)
+static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id,
+ sa_family_t family, __be16 port)
{
struct vxlan_sock *vs;
- vs = vxlan_find_sock(net, port);
+ vs = vxlan_find_sock(net, family, port);
if (!vs)
return NULL;
if (err)
return err;
+ if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
+ return -EAFNOSUPPORT;
+
spin_lock_bh(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
port, vni, ifindex, ndm->ndm_flags);
neigh_release(n);
+ if (reply == NULL)
+ goto out;
+
skb_reset_mac_header(reply);
__skb_pull(reply, skb_network_offset(reply));
reply->ip_summed = CHECKSUM_UNNECESSARY;
} else if (vxlan->flags & VXLAN_F_L3MISS) {
union vxlan_addr ipa = {
.sin.sin_addr.s_addr = tip,
- .sa.sa_family = AF_INET,
+ .sin.sin_family = AF_INET,
};
vxlan_ip_miss(dev, &ipa);
}
#if IS_ENABLED(CONFIG_IPV6)
+
+static struct sk_buff *vxlan_na_create(struct sk_buff *request,
+ struct neighbour *n, bool isrouter)
+{
+ struct net_device *dev = request->dev;
+ struct sk_buff *reply;
+ struct nd_msg *ns, *na;
+ struct ipv6hdr *pip6;
+ u8 *daddr;
+ int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+ int ns_olen;
+ int i, len;
+
+ if (dev == NULL)
+ return NULL;
+
+ len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+ sizeof(*na) + na_olen + dev->needed_tailroom;
+ reply = alloc_skb(len, GFP_ATOMIC);
+ if (reply == NULL)
+ return NULL;
+
+ reply->protocol = htons(ETH_P_IPV6);
+ reply->dev = dev;
+ skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+ skb_push(reply, sizeof(struct ethhdr));
+ skb_set_mac_header(reply, 0);
+
+ ns = (struct nd_msg *)skb_transport_header(request);
+
+ daddr = eth_hdr(request)->h_source;
+ ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+ for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+ if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+ daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+ break;
+ }
+ }
+
+ /* Ethernet header */
+ ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+ ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+ eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+ reply->protocol = htons(ETH_P_IPV6);
+
+ skb_pull(reply, sizeof(struct ethhdr));
+ skb_set_network_header(reply, 0);
+ skb_put(reply, sizeof(struct ipv6hdr));
+
+ /* IPv6 header */
+
+ pip6 = ipv6_hdr(reply);
+ memset(pip6, 0, sizeof(struct ipv6hdr));
+ pip6->version = 6;
+ pip6->priority = ipv6_hdr(request)->priority;
+ pip6->nexthdr = IPPROTO_ICMPV6;
+ pip6->hop_limit = 255;
+ pip6->daddr = ipv6_hdr(request)->saddr;
+ pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+ skb_pull(reply, sizeof(struct ipv6hdr));
+ skb_set_transport_header(reply, 0);
+
+ na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+ /* Neighbor Advertisement */
+ memset(na, 0, sizeof(*na)+na_olen);
+ na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ na->icmph.icmp6_router = isrouter;
+ na->icmph.icmp6_override = 1;
+ na->icmph.icmp6_solicited = 1;
+ na->target = ns->target;
+ ether_addr_copy(&na->opt[2], n->ha);
+ na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+ na->opt[1] = na_olen >> 3;
+
+ na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+ &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6,
+ csum_partial(na, sizeof(*na)+na_olen, 0));
+
+ pip6->payload_len = htons(sizeof(*na)+na_olen);
+
+ skb_push(reply, sizeof(struct ipv6hdr));
+
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+ return reply;
+}
+
static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct neighbour *n;
- union vxlan_addr ipa;
+ struct nd_msg *msg;
const struct ipv6hdr *iphdr;
const struct in6_addr *saddr, *daddr;
- struct nd_msg *msg;
- struct inet6_dev *in6_dev = NULL;
+ struct neighbour *n;
+ struct inet6_dev *in6_dev;
in6_dev = __in6_dev_get(dev);
if (!in6_dev)
goto out;
- if (!pskb_may_pull(skb, skb->len))
- goto out;
-
iphdr = ipv6_hdr(skb);
saddr = &iphdr->saddr;
daddr = &iphdr->daddr;
- if (ipv6_addr_loopback(daddr) ||
- ipv6_addr_is_multicast(daddr))
- goto out;
-
msg = (struct nd_msg *)skb_transport_header(skb);
if (msg->icmph.icmp6_code != 0 ||
msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
goto out;
- n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev);
+ if (ipv6_addr_loopback(daddr) ||
+ ipv6_addr_is_multicast(&msg->target))
+ goto out;
+
+ n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
if (n) {
struct vxlan_fdb *f;
+ struct sk_buff *reply;
if (!(n->nud_state & NUD_CONNECTED)) {
neigh_release(n);
goto out;
}
- ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target,
- !!in6_dev->cnf.forwarding,
- true, false, false);
+ reply = vxlan_na_create(skb, n,
+ !!(f ? f->flags & NTF_ROUTER : 0));
+
neigh_release(n);
+
+ if (reply == NULL)
+ goto out;
+
+ if (netif_rx_ni(reply) == NET_RX_DROP)
+ dev->stats.rx_dropped++;
+
} else if (vxlan->flags & VXLAN_F_L3MISS) {
- ipa.sin6.sin6_addr = *daddr;
- ipa.sa.sa_family = AF_INET6;
+ union vxlan_addr ipa = {
+ .sin6.sin6_addr = msg->target,
+ .sin6.sin6_family = AF_INET6,
+ };
+
vxlan_ip_miss(dev, &ipa);
}
if (!n && (vxlan->flags & VXLAN_F_L3MISS)) {
union vxlan_addr ipa = {
.sin.sin_addr.s_addr = pip->daddr,
- .sa.sa_family = AF_INET,
+ .sin.sin_family = AF_INET,
};
vxlan_ip_miss(dev, &ipa);
if (!n && (vxlan->flags & VXLAN_F_L3MISS)) {
union vxlan_addr ipa = {
.sin6.sin6_addr = pip6->daddr,
- .sa.sa_family = AF_INET6,
+ .sin6.sin6_family = AF_INET6,
};
vxlan_ip_miss(dev, &ipa);
struct pcpu_sw_netstats *tx_stats, *rx_stats;
union vxlan_addr loopback;
union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
+ struct net_device *dev = skb->dev;
+ int len = skb->len;
tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->tx_packets++;
- tx_stats->tx_bytes += skb->len;
+ tx_stats->tx_bytes += len;
u64_stats_update_end(&tx_stats->syncp);
if (netif_rx(skb) == NET_RX_SUCCESS) {
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->rx_packets++;
- rx_stats->rx_bytes += skb->len;
+ rx_stats->rx_bytes += len;
u64_stats_update_end(&rx_stats->syncp);
} else {
- skb->dev->stats.rx_dropped++;
+ dev->stats.rx_dropped++;
}
}
struct vxlan_dev *dst_vxlan;
ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni,
+ dst->sa.sa_family, dst_port);
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
struct vxlan_dev *dst_vxlan;
dst_release(ndst);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni,
+ dst->sa.sa_family, dst_port);
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
return arp_reduce(dev, skb);
#if IS_ENABLED(CONFIG_IPV6)
else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
- skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) &&
+ pskb_may_pull(skb, sizeof(struct ipv6hdr)
+ + sizeof(struct nd_msg)) &&
ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
struct nd_msg *msg;
msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
return neigh_reduce(dev, skb);
}
+ eth = eth_hdr(skb);
#endif
}
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+ bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
struct vxlan_sock *vs;
int i;
spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
+ vs = vxlan_find_sock(dev_net(dev), ipv6 ? AF_INET6 : AF_INET,
+ vxlan->dst_port);
if (vs) {
/* If we have a socket with same port already, reuse it */
atomic_inc(&vs->refcnt);
eth_hw_addr_random(dev);
ether_setup(dev);
if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
- dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+ dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
else
- dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+ dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = free_netdev;
return vs;
spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(net, port);
+ vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
if (vs) {
if (vs->rcv == rcv)
atomic_inc(&vs->refcnt);
vni = nla_get_u32(data[IFLA_VXLAN_ID]);
dst->remote_vni = vni;
+ /* Unless IPv6 is explicitly requested, assume IPv4 */
+ dst->remote_ip.sa.sa_family = AF_INET;
if (data[IFLA_VXLAN_GROUP]) {
dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
- dst->remote_ip.sa.sa_family = AF_INET;
} else if (data[IFLA_VXLAN_GROUP6]) {
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
if (!tb[IFLA_MTU])
dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- /* update header length based on lower device */
- dev->hard_header_len = lowerdev->hard_header_len +
+ dev->needed_headroom = lowerdev->hard_header_len +
(use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
} else if (use_ipv6)
vxlan->flags |= VXLAN_F_IPV6;
if (data[IFLA_VXLAN_PORT])
vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
- if (vxlan_find_vni(net, vni, vxlan->dst_port)) {
+ if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
+ vxlan->dst_port)) {
pr_info("duplicate VNI %u\n", vni);
return -EEXIST;
}