#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/version.h>
-#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,26)
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/rculist.h>
#include <linux/udp.h>
+#include <linux/module.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/ip_tunnels.h>
-#include <net/udp.h>
#include <net/rtnetlink.h>
#include <net/route.h>
#include <net/dsfield.h>
#include "datapath.h"
#include "vport.h"
+#include "vport-vxlan.h"
/**
* struct vxlan_port - Keeps track of open UDP ports
struct vxlan_port {
struct vxlan_sock *vs;
char name[IFNAMSIZ];
+ u32 exts; /* VXLAN_F_* in <net/vxlan.h> */
};
+static struct vport_ops ovs_vxlan_vport_ops;
+
static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
{
return vport_priv(vport);
}
-/* Called with rcu_read_lock and BH disabled. */
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
+ struct vxlan_metadata *md)
{
- struct ovs_key_ipv4_tunnel tun_key;
+ struct ovs_tunnel_info tun_info;
+ struct vxlan_port *vxlan_port;
struct vport *vport = vs->data;
struct iphdr *iph;
+ struct ovs_vxlan_opts opts = {
+ .gbp = md->gbp,
+ };
__be64 key;
+ __be16 flags;
+
+ flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0);
+ vxlan_port = vxlan_vport(vport);
+ if (vxlan_port->exts & VXLAN_F_GBP && md->gbp)
+ flags |= TUNNEL_VXLAN_OPT;
/* Save outer tunnel values */
iph = ip_hdr(skb);
- key = cpu_to_be64(ntohl(vx_vni) >> 8);
- ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY);
+ key = cpu_to_be64(ntohl(md->vni) >> 8);
+ ovs_flow_tun_info_init(&tun_info, iph,
+ udp_hdr(skb)->source, udp_hdr(skb)->dest,
+ key, flags, &opts, sizeof(opts));
- ovs_vport_receive(vport, skb, &tun_key);
+ ovs_vport_receive(vport, skb, &tun_info);
}
static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
return -EMSGSIZE;
+
+ if (vxlan_port->exts) {
+ struct nlattr *exts;
+
+ exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION);
+ if (!exts)
+ return -EMSGSIZE;
+
+ if (vxlan_port->exts & VXLAN_F_GBP &&
+ nla_put_flag(skb, OVS_VXLAN_EXT_GBP))
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, exts);
+ }
+
return 0;
}
ovs_vport_deferred_free(vport);
}
+static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = {
+ [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, },
+};
+
+static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr)
+{
+ struct nlattr *exts[OVS_VXLAN_EXT_MAX+1];
+ struct vxlan_port *vxlan_port;
+ int err;
+
+ if (nla_len(attr) < sizeof(struct nlattr))
+ return -EINVAL;
+
+ err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy);
+ if (err < 0)
+ return err;
+
+ vxlan_port = vxlan_vport(vport);
+
+ if (exts[OVS_VXLAN_EXT_GBP])
+ vxlan_port->exts |= VXLAN_F_GBP;
+
+ return 0;
+}
+
static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
{
struct net *net = ovs_dp_get_net(parms->dp);
vxlan_port = vxlan_vport(vport);
strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
- vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true);
+ a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
+ if (a) {
+ err = vxlan_configure_exts(vport, a);
+ if (err) {
+ ovs_vport_free(vport);
+ goto error;
+ }
+ }
+
+ vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true,
+ vxlan_port->exts);
if (IS_ERR(vs)) {
ovs_vport_free(vport);
return (void *)vs;
return ERR_PTR(err);
}
+static int vxlan_ext_gbp(struct sk_buff *skb)
+{
+ const struct ovs_tunnel_info *tun_info;
+ const struct ovs_vxlan_opts *opts;
+
+ tun_info = OVS_CB(skb)->egress_tun_info;
+ opts = tun_info->options;
+
+ if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT &&
+ tun_info->options_len >= sizeof(*opts))
+ return opts->gbp;
+ else
+ return 0;
+}
+
static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
+ struct ovs_key_ipv4_tunnel *tun_key;
+ struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sport(vxlan_port->vs->sock->sk);
- struct net *net = ovs_dp_get_net(vport->dp);
+ struct vxlan_metadata md = {0};
struct rtable *rt;
__be16 src_port;
__be32 saddr;
__be16 df;
- int port_min;
- int port_max;
int err;
+ u32 vxflags;
- if (unlikely(!OVS_CB(skb)->tun_key)) {
+ if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
- forward_ip_summed(skb, true);
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
- saddr = OVS_CB(skb)->tun_key->ipv4_src;
+ saddr = tun_key->ipv4_src;
rt = find_route(ovs_dp_get_net(vport->dp),
- &saddr,
- OVS_CB(skb)->tun_key->ipv4_dst,
- IPPROTO_UDP,
- OVS_CB(skb)->tun_key->ipv4_tos,
- skb_get_mark(skb));
+ &saddr, tun_key->ipv4_dst,
+ IPPROTO_UDP, tun_key->ipv4_tos,
+ skb->mark);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto error;
}
- df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
- htons(IP_DF) : 0;
-
- skb->local_df = 1;
+ df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+ skb->ignore_df = 1;
- inet_get_local_port_range(&port_min, &port_max);
- src_port = vxlan_src_port(port_min, port_max, skb);
+ src_port = udp_flow_src_port(net, skb, 0, 0, true);
+ md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
+ md.gbp = vxlan_ext_gbp(skb);
+ vxflags = vxlan_port->exts |
+ (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0);
- err = vxlan_xmit_skb(net, vxlan_port->vs, rt, skb,
- saddr, OVS_CB(skb)->tun_key->ipv4_dst,
- OVS_CB(skb)->tun_key->ipv4_tos,
- OVS_CB(skb)->tun_key->ipv4_ttl, df,
+ err = vxlan_xmit_skb(rt, vxlan_port->vs->sock->sk, skb,
+ saddr, tun_key->ipv4_dst,
+ tun_key->ipv4_tos,
+ tun_key->ipv4_ttl, df,
src_port, dst_port,
- htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
+ &md, false, vxflags);
if (err < 0)
ip_rt_put(rt);
+ return err;
error:
+ kfree_skb(skb);
return err;
}
+static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *egress_tun_info)
+{
+ struct net *net = ovs_dp_get_net(vport->dp);
+ struct vxlan_port *vxlan_port = vxlan_vport(vport);
+ __be16 dst_port = inet_sport(vxlan_port->vs->sock->sk);
+ __be16 src_port;
+
+ src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+ return ovs_tunnel_get_egress_info(egress_tun_info, net,
+ OVS_CB(skb)->egress_tun_info,
+ IPPROTO_UDP, skb->mark,
+ src_port, dst_port);
+}
+
static const char *vxlan_get_name(const struct vport *vport)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
return vxlan_port->name;
}
-const struct vport_ops ovs_vxlan_vport_ops = {
- .type = OVS_VPORT_TYPE_VXLAN,
- .create = vxlan_tnl_create,
- .destroy = vxlan_tnl_destroy,
- .get_name = vxlan_get_name,
- .get_options = vxlan_get_options,
- .send = vxlan_tnl_send,
+static struct vport_ops ovs_vxlan_vport_ops = {
+ .type = OVS_VPORT_TYPE_VXLAN,
+ .create = vxlan_tnl_create,
+ .destroy = vxlan_tnl_destroy,
+ .get_name = vxlan_get_name,
+ .get_options = vxlan_get_options,
+ .send = vxlan_tnl_send,
+ .get_egress_tun_info = vxlan_get_egress_tun_info,
+ .owner = THIS_MODULE,
};
-#else
-#warning VXLAN tunneling will not be available on kernels before 2.6.26
-#endif /* Linux kernel < 2.6.26 */
+
+static int __init ovs_vxlan_tnl_init(void)
+{
+ return ovs_vport_ops_register(&ovs_vxlan_vport_ops);
+}
+
+static void __exit ovs_vxlan_tnl_exit(void)
+{
+ ovs_vport_ops_unregister(&ovs_vxlan_vport_ops);
+}
+
+module_init(ovs_vxlan_tnl_init);
+module_exit(ovs_vxlan_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: VXLAN switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-4");