static int tunnel_key_dump_addresses(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
unsigned short family = ip_tunnel_info_af(info);
if (family == AF_INET) {
__be32 saddr = info->key.u.ipv4.src;
__be32 daddr = info->key.u.ipv4.dst;
if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) &&
!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr))
return 0;
}
if (family == AF_INET6) {
const struct in6_addr *saddr6 = &info->key.u.ipv6.src;
const struct in6_addr *daddr6 = &info->key.u.ipv6.dst;
if (!nla_put_in6_addr(skb,
TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) &&
!nla_put_in6_addr(skb,
TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6))
return 0;
}
return -EINVAL;
}
static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
int tunnel_hlen;
__be16 df, flags;
int err;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
key = &tun_info->key;
rt = gre_get_rt(skb, dev, &fl, key);
if (IS_ERR(rt))
goto err_free_skb;
tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr);
if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
int head_delta = SKB_DATA_ALIGN(min_headroom -
skb_headroom(skb) +
16);
err = pskb_expand_head(skb, max_t(int, head_delta, 0),
0, GFP_ATOMIC);
if (unlikely(err))
goto err_free_rt;
}
static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
struct bnxt_tc_actions *actions,
const struct tc_action *tc_act)
{
struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act);
struct ip_tunnel_key *tun_key = &tun_info->key;
if (ip_tunnel_info_af(tun_info) != AF_INET) {
netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
return -EOPNOTSUPP;
}
actions->tun_encap_key = *tun_key;
actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP;
return 0;
}
int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
struct net *net,
struct sk_buff *skb,
u8 ipproto,
__be16 tp_src,
__be16 tp_dst)
{
struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info;
struct ip_tunnel_info *tun_info = skb_tunnel_info(skb);
const struct ip_tunnel_key *tun_key;
u32 skb_mark = skb->mark;
struct rtable *rt;
struct flowi4 fl;
if (unlikely(!tun_info))
return -EINVAL;
if (ip_tunnel_info_af(tun_info) != AF_INET)
return -EINVAL;
tun_key = &tun_info->key;
/* Route lookup to get srouce IP address.
* The process may need to be changed if the corresponding process
* in vports ops changed.
*/
rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
/* Generate egress_tun_info based on tun_info,
* saddr, tp_src and tp_dst
*/
ip_tunnel_key_init(&egress_tun_info->key,
fl.saddr, tun_key->u.ipv4.dst,
tun_key->tos,
tun_key->ttl,
tp_src, tp_dst,
tun_key->tun_id,
tun_key->tun_flags);
egress_tun_info->options_len = tun_info->options_len;
egress_tun_info->mode = tun_info->mode;
upcall->egress_tun_opts = ip_tunnel_info_opts(tun_info);
return 0;
}
static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
{
struct net *net = ovs_dp_get_net(parms->dp);
struct nlattr *options = parms->options;
struct net_device *dev;
struct vport *vport;
struct nlattr *a;
int err;
struct vxlan_config conf = {
.no_share = true,
.flags = VXLAN_F_COLLECT_METADATA,
};
if (!options) {
err = -EINVAL;
goto error;
}
a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
if (a && nla_len(a) == sizeof(u16)) {
conf.dst_port = htons(nla_get_u16(a));
} else {
/* Require destination port from userspace. */
err = -EINVAL;
goto error;
}
vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms);
if (IS_ERR(vport))
return vport;
a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
if (a) {
err = vxlan_configure_exts(vport, a, &conf);
if (err) {
ovs_vport_free(vport);
goto error;
}
}
rtnl_lock();
dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf);
if (IS_ERR(dev)) {
rtnl_unlock();
ovs_vport_free(vport);
return ERR_CAST(dev);
}
dev_change_flags(dev, dev->flags | IFF_UP);
rtnl_unlock();
return vport;
error:
return ERR_PTR(err);
}
static struct vport *vxlan_create(const struct vport_parms *parms)
{
struct vport *vport;
vport = vxlan_tnl_create(parms);
if (IS_ERR(vport))
return vport;
return ovs_netdev_link(vport, parms->name);
}
static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
struct dp_upcall_info *upcall)
{
struct vxlan_dev *vxlan = netdev_priv(vport->dev);
struct net *net = ovs_dp_get_net(vport->dp);
unsigned short family = ip_tunnel_info_af(upcall->egress_tun_info);
__be16 dst_port = vxlan_dev_dst_port(vxlan, family);
__be16 src_port;
int port_min;
int port_max;
inet_get_local_port_range(net, &port_min, &port_max);
src_port = udp_flow_src_port(net, skb, 0, 0, true);
return ovs_tunnel_get_egress_info(upcall, net,
skb, IPPROTO_UDP,
src_port, dst_port);
}
static struct vport_ops ovs_vxlan_netdev_vport_ops = {
.type = OVS_VPORT_TYPE_VXLAN,
.create = vxlan_create,
.destroy = ovs_netdev_tunnel_destroy,
.get_options = vxlan_get_options,
.send = ovs_netdev_send,
.get_egress_tun_info = vxlan_get_egress_tun_info,
};
static int __init ovs_vxlan_tnl_init(void)
{
return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops);
}
static void __exit ovs_vxlan_tnl_exit(void)
{
ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops);
}
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
u32 headroom = sizeof(struct iphdr);
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
const struct iphdr *inner_iph;
struct rtable *rt;
struct flowi4 fl4;
__be16 df = 0;
u8 tos, ttl;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto tx_error;
key = &tun_info->key;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
tos = key->tos;
if (tos == 1) {
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
RT_TOS(tos), tunnel->parms.link);
if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
goto tx_error;
rt = ip_route_output_key(tunnel->net, &fl4);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = key->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
if (key->tun_flags & TUNNEL_DONT_FRAGMENT)
df = htons(IP_DF);
else if (skb->protocol == htons(ETH_P_IP))
df = inner_iph->frag_off & htons(IP_DF);
headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
if (headroom > dev->needed_headroom)
dev->needed_headroom = headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
ip_rt_put(rt);
goto tx_dropped;
}
iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
return;
tx_error:
dev->stats.tx_errors++;
goto kfree;
tx_dropped:
dev->stats.tx_dropped++;
kfree:
kfree_skb(skb);
}
