{
struct vxlan_dev *vxlan;
+ /* For flow based devices, map all packets to VNI 0 */
+ if (vs->flags & VXLAN_F_COLLECT_METADATA)
+ vni = 0;
+
hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
if (vxlan->default_dst.remote_vni == vni)
return vxlan;
}
static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed,
+ struct sk_buff *skb, u32 vxflags,
struct vxlan_metadata *md,
struct metadata_dst *tun_dst)
{
if (gbp->policy_applied)
md->gbp |= VXLAN_GBP_POLICY_APPLIED;
+ /* In flow-based mode, GBP is carried in dst_metadata */
+ if (!(vxflags & VXLAN_F_COLLECT_METADATA))
+ skb->mark = md->gbp;
out:
unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS;
}
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
- struct vxlan_metadata *md, __be32 vni,
+static void vxlan_rcv(struct vxlan_dev *vxlan, struct vxlan_sock *vs,
+ struct sk_buff *skb, struct vxlan_metadata *md,
struct metadata_dst *tun_dst)
{
struct iphdr *oip = NULL;
struct ipv6hdr *oip6 = NULL;
- struct vxlan_dev *vxlan;
struct pcpu_sw_netstats *stats;
union vxlan_addr saddr;
int err = 0;
- /* For flow based devices, map all packets to VNI 0 */
- if (vs->flags & VXLAN_F_COLLECT_METADATA)
- vni = 0;
-
- /* Is this VNI defined? */
- vxlan = vxlan_vs_find_vni(vs, vni);
- if (!vxlan)
- goto drop;
-
skb_reset_mac_header(skb);
- skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
skb->protocol = eth_type_trans(skb, vxlan->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
goto drop;
skb_reset_network_header(skb);
- /* In flow-based mode, GBP is carried in dst_metadata */
- if (!(vs->flags & VXLAN_F_COLLECT_METADATA))
- skb->mark = md->gbp;
if (oip6)
err = IP6_ECN_decapsulate(oip6, skb);
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct metadata_dst *tun_dst = NULL;
+ struct vxlan_dev *vxlan;
struct vxlan_sock *vs;
struct vxlanhdr unparsed;
struct vxlan_metadata _md;
unparsed.vx_flags &= ~VXLAN_HF_VNI;
unparsed.vx_vni &= ~VXLAN_VNI_MASK;
- if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
- goto drop;
-
vs = rcu_dereference_sk_user_data(sk);
if (!vs)
goto drop;
+ vxlan = vxlan_vs_find_vni(vs, vxlan_vni(vxlan_hdr(skb)->vx_vni));
+ 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;
+
if (vxlan_collect_metadata(vs)) {
+ __be32 vni = vxlan_vni(vxlan_hdr(skb)->vx_vni);
+
tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY,
- vxlan_vni(vxlan_hdr(skb)->vx_vni),
- sizeof(*md));
+ vxlan_vni_to_tun_id(vni), sizeof(*md));
if (!tun_dst)
goto drop;
if (!vxlan_remcsum(&unparsed, skb, vs->flags))
goto drop;
if (vs->flags & VXLAN_F_GBP)
- vxlan_parse_gbp_hdr(&unparsed, md, tun_dst);
+ vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md, tun_dst);
if (unparsed.vx_flags || unparsed.vx_vni) {
/* If there are any unprocessed flags remaining treat
goto drop;
}
- vxlan_rcv(vs, skb, md, vxlan_vni(vxlan_hdr(skb)->vx_vni), tun_dst);
+ vxlan_rcv(vxlan, vs, skb, md, tun_dst);
return 0;
drop:
goto drop;
sk = vxlan->vn4_sock->sock->sk;
- if (info) {
- if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
- df = htons(IP_DF);
- } else {
- udp_sum = !!(flags & VXLAN_F_UDP_CSUM);
- }
-
rt = vxlan_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
dst->sin.sin_addr.s_addr, &saddr,
return;
}
+ if (!info)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
+ else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+ df = htons(IP_DF);
+
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
#endif
}
- if (vxlan->flags & VXLAN_F_COLLECT_METADATA &&
- info && info->mode & IP_TUNNEL_INFO_TX) {
- vxlan_xmit_one(skb, dev, NULL, false);
+ 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;
}
{
}
-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+static int __vxlan_change_mtu(struct net_device *dev,
+ struct net_device *lowerdev,
+ struct vxlan_rdst *dst, int new_mtu, bool strict)
{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_rdst *dst = &vxlan->default_dst;
- struct net_device *lowerdev;
- int max_mtu;
+ int max_mtu = IP_MAX_MTU;
- lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
- if (lowerdev == NULL)
- return eth_change_mtu(dev, new_mtu);
+ if (lowerdev)
+ max_mtu = lowerdev->mtu;
if (dst->remote_ip.sa.sa_family == AF_INET6)
- max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+ max_mtu -= VXLAN6_HEADROOM;
else
- max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+ max_mtu -= VXLAN_HEADROOM;
- if (new_mtu < 68 || new_mtu > max_mtu)
+ if (new_mtu < 68)
return -EINVAL;
+ if (new_mtu > max_mtu) {
+ if (strict)
+ return -EINVAL;
+
+ new_mtu = max_mtu;
+ }
+
dev->mtu = new_mtu;
return 0;
}
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_rdst *dst = &vxlan->default_dst;
+ struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+ dst->remote_ifindex);
+ return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
+}
+
static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(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;
INIT_LIST_HEAD(&vxlan->next);
int err;
bool use_ipv6 = false;
__be16 default_port = vxlan->cfg.dst_port;
+ struct net_device *lowerdev = NULL;
vxlan->net = src_net;
}
if (conf->remote_ifindex) {
- struct net_device *lowerdev
- = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+ lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
dst->remote_ifindex = conf->remote_ifindex;
if (!lowerdev) {
needed_headroom = lowerdev->hard_header_len;
}
+ if (conf->mtu) {
+ err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+ if (err)
+ return err;
+ }
+
if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
needed_headroom += VXLAN6_HEADROOM;
else
if (data[IFLA_VXLAN_PORT])
conf.dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
- if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
- conf.flags |= VXLAN_F_UDP_CSUM;
+ if (data[IFLA_VXLAN_UDP_CSUM] &&
+ !nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
+ conf.flags |= VXLAN_F_UDP_ZERO_CSUM_TX;
if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) ||
nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) ||
nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM,
- !!(vxlan->flags & VXLAN_F_UDP_CSUM)) ||
+ !(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) ||
nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) ||
nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
projects / cascardo / linux.git / blobdiff