/* UDP port for VXLAN traffic.
* The IANA assigned port is 4789, but the Linux default is 8472
- * for compatability with early adopters.
+ * for compatibility with early adopters.
*/
-static unsigned int vxlan_port __read_mostly = 8472;
-module_param_named(udp_port, vxlan_port, uint, 0444);
+static unsigned short vxlan_port __read_mostly = 8472;
+module_param_named(udp_port, vxlan_port, ushort, 0444);
MODULE_PARM_DESC(udp_port, "Destination UDP port");
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
-static unsigned int vxlan_net_id;
+static int vxlan_net_id;
+
+static const u8 all_zeros_mac[ETH_ALEN];
/* per UDP socket information */
struct vxlan_sock {
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
- struct vxlan_rdst *remote_next;
+ struct list_head list;
};
/* Forwarding table entry */
struct rcu_head rcu;
unsigned long updated; /* jiffies */
unsigned long used;
- struct vxlan_rdst remote;
+ struct list_head remotes;
u16 state; /* see ndm_state */
u8 flags; /* see ndm_flags */
u8 eth_addr[ETH_ALEN];
return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
}
+/* First remote destination for a forwarding entry.
+ * Guaranteed to be non-NULL because remotes are never deleted.
+ */
+static inline struct vxlan_rdst *first_remote(struct vxlan_fdb *fdb)
+{
+ return list_first_or_null_rcu(&fdb->remotes, struct vxlan_rdst, list);
+}
+
/* Find VXLAN socket based on network namespace and UDP port */
static struct vxlan_sock *vxlan_find_port(struct net *net, __be16 port)
{
/* Fill in neighbour message in skbuff. */
static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
- const struct vxlan_fdb *fdb,
- u32 portid, u32 seq, int type, unsigned int flags,
- const struct vxlan_rdst *rdst)
+ const struct vxlan_fdb *fdb,
+ u32 portid, u32 seq, int type, unsigned int flags,
+ const struct vxlan_rdst *rdst)
{
unsigned long now = jiffies;
struct nda_cacheinfo ci;
nla_put_be16(skb, NDA_PORT, rdst->remote_port))
goto nla_put_failure;
if (rdst->remote_vni != vxlan->default_dst.remote_vni &&
- nla_put_be32(skb, NDA_VNI, rdst->remote_vni))
+ nla_put_u32(skb, NDA_VNI, rdst->remote_vni))
goto nla_put_failure;
if (rdst->remote_ifindex &&
nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
}
static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
- const struct vxlan_fdb *fdb, int type)
+ struct vxlan_fdb *fdb, int type)
{
struct net *net = dev_net(vxlan->dev);
struct sk_buff *skb;
if (skb == NULL)
goto errout;
- err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, &fdb->remote);
+ err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, first_remote(fdb));
if (err < 0) {
/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_fdb f;
+ struct vxlan_fdb f = {
+ .state = NUD_STALE,
+ };
+ struct vxlan_rdst remote = {
+ .remote_ip = ipa, /* goes to NDA_DST */
+ .remote_vni = VXLAN_N_VID,
+ };
- memset(&f, 0, sizeof f);
- f.state = NUD_STALE;
- f.remote.remote_ip = ipa; /* goes to NDA_DST */
- f.remote.remote_vni = VXLAN_N_VID;
+ INIT_LIST_HEAD(&f.remotes);
+ list_add_rcu(&remote.list, &f.remotes);
vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
}
static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
{
- struct vxlan_fdb f;
+ struct vxlan_fdb f = {
+ .state = NUD_STALE,
+ };
- memset(&f, 0, sizeof f);
- f.state = NUD_STALE;
+ INIT_LIST_HEAD(&f.remotes);
memcpy(f.eth_addr, eth_addr, ETH_ALEN);
vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
static int vxlan_fdb_append(struct vxlan_fdb *f,
__be32 ip, __be16 port, __u32 vni, __u32 ifindex)
{
- struct vxlan_rdst *rd_prev, *rd;
+ struct vxlan_rdst *rd;
- rd_prev = NULL;
- for (rd = &f->remote; rd; rd = rd->remote_next) {
+ /* protected by vxlan->hash_lock */
+ list_for_each_entry(rd, &f->remotes, list) {
if (rd->remote_ip == ip &&
rd->remote_port == port &&
rd->remote_vni == vni &&
rd->remote_ifindex == ifindex)
return 0;
- rd_prev = rd;
}
+
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
- rd->remote_next = NULL;
- rd_prev->remote_next = rd;
+
+ list_add_tail_rcu(&rd->list, &f->remotes);
+
return 1;
}
return -ENOMEM;
notify = 1;
- f->remote.remote_ip = ip;
- f->remote.remote_port = port;
- f->remote.remote_vni = vni;
- f->remote.remote_ifindex = ifindex;
- f->remote.remote_next = NULL;
f->state = state;
f->flags = ndm_flags;
f->updated = f->used = jiffies;
+ INIT_LIST_HEAD(&f->remotes);
memcpy(f->eth_addr, mac, ETH_ALEN);
+ vxlan_fdb_append(f, ip, port, vni, ifindex);
+
++vxlan->addrcnt;
hlist_add_head_rcu(&f->hlist,
vxlan_fdb_head(vxlan, mac));
static void vxlan_fdb_free(struct rcu_head *head)
{
struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+ struct vxlan_rdst *rd, *nd;
- while (f->remote.remote_next) {
- struct vxlan_rdst *rd = f->remote.remote_next;
-
- f->remote.remote_next = rd->remote_next;
+ list_for_each_entry_safe(rd, nd, &f->remotes, list)
kfree(rd);
- }
kfree(f);
}
hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
struct vxlan_rdst *rd;
- for (rd = &f->remote; rd; rd = rd->remote_next) {
- if (idx < cb->args[0])
- goto skip;
+ if (idx < cb->args[0])
+ goto skip;
+
+ list_for_each_entry_rcu(rd, &f->remotes, list) {
err = vxlan_fdb_info(skb, vxlan, f,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
NLM_F_MULTI, rd);
if (err < 0)
- break;
-skip:
- ++idx;
+ goto out;
}
+skip:
+ ++idx;
}
}
-
+out:
return idx;
}
f = vxlan_find_mac(vxlan, src_mac);
if (likely(f)) {
- if (likely(f->remote.remote_ip == src_ip))
+ struct vxlan_rdst *rdst = first_remote(f);
+
+ if (likely(rdst->remote_ip == src_ip))
return false;
/* Don't migrate static entries, drop packets */
if (net_ratelimit())
netdev_info(dev,
"%pM migrated from %pI4 to %pI4\n",
- src_mac, &f->remote.remote_ip, &src_ip);
+ src_mac, &rdst->remote_ip, &src_ip);
- f->remote.remote_ip = src_ip;
+ rdst->remote_ip = src_ip;
f->updated = jiffies;
vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
} else {
}
f = vxlan_find_mac(vxlan, n->ha);
- if (f && f->remote.remote_ip == htonl(INADDR_ANY)) {
+ if (f && first_remote(f)->remote_ip == htonl(INADDR_ANY)) {
/* bridge-local neighbor */
neigh_release(n);
goto out;
}
}
-static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
- struct vxlan_rdst *rdst, bool did_rsc)
+static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
+ struct vxlan_rdst *rdst, bool did_rsc)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct rtable *rt;
struct flowi4 fl4;
__be32 dst;
__be16 src_port, dst_port;
- u32 vni;
+ u32 vni;
__be16 df = 0;
__u8 tos, ttl;
int err;
if (did_rsc) {
/* short-circuited back to local bridge */
vxlan_encap_bypass(skb, vxlan, vxlan);
- return NETDEV_TX_OK;
+ return;
}
goto drop;
}
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return NETDEV_TX_OK;
+ return;
}
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_FLAGS);
IPPROTO_UDP, tos, ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
- return NETDEV_TX_OK;
+ return;
drop:
dev->stats.tx_dropped++;
dev->stats.tx_errors++;
tx_free:
dev_kfree_skb(skb);
- return NETDEV_TX_OK;
}
/* Transmit local packets over Vxlan
struct vxlan_dev *vxlan = netdev_priv(dev);
struct ethhdr *eth;
bool did_rsc = false;
- struct vxlan_rdst *rdst0, *rdst;
+ struct vxlan_rdst *rdst;
struct vxlan_fdb *f;
- int rc1, rc;
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
}
if (f == NULL) {
- rdst0 = &vxlan->default_dst;
-
- if (rdst0->remote_ip == htonl(INADDR_ANY) &&
- (vxlan->flags & VXLAN_F_L2MISS) &&
- !is_multicast_ether_addr(eth->h_dest))
- vxlan_fdb_miss(vxlan, eth->h_dest);
- } else
- rdst0 = &f->remote;
-
- rc = NETDEV_TX_OK;
+ f = vxlan_find_mac(vxlan, all_zeros_mac);
+ if (f == NULL) {
+ if ((vxlan->flags & VXLAN_F_L2MISS) &&
+ !is_multicast_ether_addr(eth->h_dest))
+ vxlan_fdb_miss(vxlan, eth->h_dest);
+
+ dev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+ }
- /* if there are multiple destinations, send copies */
- for (rdst = rdst0->remote_next; rdst; rdst = rdst->remote_next) {
+ list_for_each_entry_rcu(rdst, &f->remotes, list) {
struct sk_buff *skb1;
skb1 = skb_clone(skb, GFP_ATOMIC);
- if (skb1) {
- rc1 = vxlan_xmit_one(skb1, dev, rdst, did_rsc);
- if (rc == NETDEV_TX_OK)
- rc = rc1;
- }
+ if (skb1)
+ vxlan_xmit_one(skb1, dev, rdst, did_rsc);
}
- rc1 = vxlan_xmit_one(skb, dev, rdst0, did_rsc);
- if (rc == NETDEV_TX_OK)
- rc = rc1;
- return rc;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
}
/* Walk the forwarding table and purge stale entries */
return 0;
}
+static void vxlan_fdb_delete_defualt(struct vxlan_dev *vxlan)
+{
+ struct vxlan_fdb *f;
+
+ spin_lock_bh(&vxlan->hash_lock);
+ f = __vxlan_find_mac(vxlan, all_zeros_mac);
+ if (f)
+ vxlan_fdb_destroy(vxlan, f);
+ spin_unlock_bh(&vxlan->hash_lock);
+}
+
+static void vxlan_uninit(struct net_device *dev)
+{
+ struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+ struct vxlan_sock *vs = vxlan->vn_sock;
+
+ vxlan_fdb_delete_defualt(vxlan);
+
+ if (vs)
+ vxlan_sock_release(vn, vs);
+ free_percpu(dev->tstats);
+}
+
/* Start ageing timer and join group when device is brought up */
static int vxlan_open(struct net_device *dev)
{
hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
struct vxlan_fdb *f
= container_of(p, struct vxlan_fdb, hlist);
- vxlan_fdb_destroy(vxlan, f);
+ /* the all_zeros_mac entry is deleted at vxlan_uninit */
+ if (!is_zero_ether_addr(f->eth_addr))
+ vxlan_fdb_destroy(vxlan, f);
}
}
spin_unlock_bh(&vxlan->hash_lock);
static const struct net_device_ops vxlan_netdev_ops = {
.ndo_init = vxlan_init,
+ .ndo_uninit = vxlan_uninit,
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
.name = "vxlan",
};
-static void vxlan_free(struct net_device *dev)
-{
- free_percpu(dev->tstats);
- free_netdev(dev);
-}
-
/* Initialize the device structure. */
static void vxlan_setup(struct net_device *dev)
{
dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
- dev->destructor = vxlan_free;
+ dev->destructor = free_netdev;
SET_NETDEV_DEVTYPE(dev, &vxlan_type);
dev->tx_queue_len = 0;
struct sockaddr_in vxlan_addr = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
+ .sin_port = port,
};
int rc;
unsigned int h;
sk = vs->sock->sk;
sk_change_net(sk, net);
- vxlan_addr.sin_port = port;
-
rc = kernel_bind(vs->sock, (struct sockaddr *) &vxlan_addr,
sizeof(vxlan_addr));
if (rc < 0) {
SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops);
- err = register_netdevice(dev);
+ /* create an fdb entry for default destination */
+ err = vxlan_fdb_create(vxlan, all_zeros_mac,
+ vxlan->default_dst.remote_ip,
+ NUD_REACHABLE|NUD_PERMANENT,
+ NLM_F_EXCL|NLM_F_CREATE,
+ vxlan->dst_port, vxlan->default_dst.remote_vni,
+ vxlan->default_dst.remote_ifindex, NTF_SELF);
if (err)
return err;
+ err = register_netdevice(dev);
+ if (err) {
+ vxlan_fdb_delete_defualt(vxlan);
+ return err;
+ }
+
list_add(&vxlan->next, &vn->vxlan_list);
return 0;
static void vxlan_dellink(struct net_device *dev, struct list_head *head)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
- struct vxlan_sock *vs = vxlan->vn_sock;
hlist_del_rcu(&vxlan->hlist);
list_del(&vxlan->next);
unregister_netdevice_queue(dev, head);
- if (vs)
- vxlan_sock_release(vn, vs);
}
static size_t vxlan_get_size(const struct net_device *dev)