__u8 ttl;
u32 flags; /* VXLAN_F_* in vxlan.h */
- struct work_struct sock_work;
- struct work_struct igmp_join;
- struct work_struct igmp_leave;
-
unsigned long age_interval;
struct timer_list age_timer;
spinlock_t hash_lock;
static u32 vxlan_salt __read_mostly;
static struct workqueue_struct *vxlan_wq;
-static void vxlan_sock_work(struct work_struct *work);
-
#if IS_ENABLED(CONFIG_IPV6)
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
- if (a->sa.sa_family != b->sa.sa_family)
- return false;
- if (a->sa.sa_family == AF_INET6)
- return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
- else
- return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
+ if (a->sa.sa_family != b->sa.sa_family)
+ return false;
+ if (a->sa.sa_family == AF_INET6)
+ return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
+ else
+ return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}
static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
{
- if (ipa->sa.sa_family == AF_INET6)
- return ipv6_addr_any(&ipa->sin6.sin6_addr);
- else
- return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_any(&ipa->sin6.sin6_addr);
+ else
+ return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
}
static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
{
- if (ipa->sa.sa_family == AF_INET6)
- return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
- else
- return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
+ else
+ return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
}
static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
- if (nla_len(nla) >= sizeof(struct in6_addr)) {
- nla_memcpy(&ip->sin6.sin6_addr, nla, sizeof(struct in6_addr));
- ip->sa.sa_family = AF_INET6;
- return 0;
- } else if (nla_len(nla) >= sizeof(__be32)) {
- ip->sin.sin_addr.s_addr = nla_get_be32(nla);
- ip->sa.sa_family = AF_INET;
- return 0;
- } else {
- return -EAFNOSUPPORT;
- }
+ if (nla_len(nla) >= sizeof(struct in6_addr)) {
+ ip->sin6.sin6_addr = nla_get_in6_addr(nla);
+ ip->sa.sa_family = AF_INET6;
+ return 0;
+ } else if (nla_len(nla) >= sizeof(__be32)) {
+ ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
+ ip->sa.sa_family = AF_INET;
+ return 0;
+ } else {
+ return -EAFNOSUPPORT;
+ }
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
- const union vxlan_addr *ip)
+ const union vxlan_addr *ip)
{
- if (ip->sa.sa_family == AF_INET6)
- return nla_put(skb, attr, sizeof(struct in6_addr), &ip->sin6.sin6_addr);
- else
- return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
+ if (ip->sa.sa_family == AF_INET6)
+ return nla_put_in6_addr(skb, attr, &ip->sin6.sin6_addr);
+ else
+ return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}
#else /* !CONFIG_IPV6 */
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
- return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
+ return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}
static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
{
- return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+ return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
}
static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
{
- return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+ return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
}
static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
- if (nla_len(nla) >= sizeof(struct in6_addr)) {
- return -EAFNOSUPPORT;
- } else if (nla_len(nla) >= sizeof(__be32)) {
- ip->sin.sin_addr.s_addr = nla_get_be32(nla);
- ip->sa.sa_family = AF_INET;
- return 0;
- } else {
- return -EAFNOSUPPORT;
- }
+ if (nla_len(nla) >= sizeof(struct in6_addr)) {
+ return -EAFNOSUPPORT;
+ } else if (nla_len(nla) >= sizeof(__be32)) {
+ ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
+ ip->sa.sa_family = AF_INET;
+ return 0;
+ } else {
+ return -EAFNOSUPPORT;
+ }
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
- const union vxlan_addr *ip)
+ const union vxlan_addr *ip)
{
- return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
+ return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}
#endif
/* Watch incoming packets to learn mapping between Ethernet address
* and Tunnel endpoint.
- * Return true if packet is bogus and should be droppped.
+ * Return true if packet is bogus and should be dropped.
*/
static bool vxlan_snoop(struct net_device *dev,
union vxlan_addr *src_ip, const u8 *src_mac)
return false;
}
-static void vxlan_sock_hold(struct vxlan_sock *vs)
-{
- atomic_inc(&vs->refcnt);
-}
-
void vxlan_sock_release(struct vxlan_sock *vs)
{
struct sock *sk = vs->sock->sk;
}
EXPORT_SYMBOL_GPL(vxlan_sock_release);
-/* Callback to update multicast group membership when first VNI on
- * multicast asddress is brought up
- * Done as workqueue because ip_mc_join_group acquires RTNL.
+/* Update multicast group membership when first VNI on
+ * multicast address is brought up
*/
-static void vxlan_igmp_join(struct work_struct *work)
+static int vxlan_igmp_join(struct vxlan_dev *vxlan)
{
- struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
+ int ret = -EINVAL;
lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
.imr_ifindex = ifindex,
};
- ip_mc_join_group(sk, &mreq);
+ ret = ip_mc_join_group(sk, &mreq);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
- &ip->sin6.sin6_addr);
+ ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
+ &ip->sin6.sin6_addr);
#endif
}
release_sock(sk);
- vxlan_sock_release(vs);
- dev_put(vxlan->dev);
+ return ret;
}
/* Inverse of vxlan_igmp_join when last VNI is brought down */
-static void vxlan_igmp_leave(struct work_struct *work)
+static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
{
- struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
+ int ret = -EINVAL;
lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
.imr_ifindex = ifindex,
};
- ip_mc_leave_group(sk, &mreq);
+ ret = ip_mc_leave_group(sk, &mreq);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
- &ip->sin6.sin6_addr);
+ ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
+ &ip->sin6.sin6_addr);
#endif
}
-
release_sock(sk);
- vxlan_sock_release(vs);
- dev_put(vxlan->dev);
+ return ret;
}
static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
* this as a malformed packet. This behavior diverges from
* VXLAN RFC (RFC7348) which stipulates that bits in reserved
* in reserved fields are to be ignored. The approach here
- * maintains compatbility with previous stack code, and also
+ * maintains compatibility with previous stack code, and also
* is more robust and provides a little more security in
* adding extensions to VXLAN.
*/
}
#if IS_ENABLED(CONFIG_IPV6)
-static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
+static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb,
struct net_device *dev, struct in6_addr *saddr,
struct in6_addr *daddr, __u8 prio, __u8 ttl,
__be16 src_port, __be16 dst_port,
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
- udp_tunnel6_xmit_skb(dst, skb, dev, saddr, daddr, prio,
+ udp_tunnel6_xmit_skb(dst, sk, skb, dev, saddr, daddr, prio,
ttl, src_port, dst_port,
!!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
return 0;
}
#endif
-int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
__be16 src_port, __be16 dst_port,
struct vxlan_metadata *md, bool xnet, u32 vxflags)
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
- return udp_tunnel_xmit_skb(rt, skb, src, dst, tos,
+ return udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos,
ttl, df, src_port, dst_port, xnet,
!(vxflags & VXLAN_F_UDP_CSUM));
}
struct vxlan_rdst *rdst, bool did_rsc)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct sock *sk = vxlan->vn_sock->sock->sk;
struct rtable *rt = NULL;
const struct iphdr *old_iph;
struct flowi4 fl4;
md.vni = htonl(vni << 8);
md.gbp = skb->mark;
- err = vxlan_xmit_skb(rt, skb, fl4.saddr,
+ err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
src_port, dst_port, &md,
!net_eq(vxlan->net, dev_net(vxlan->dev)),
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- struct sock *sk = vxlan->vn_sock->sock->sk;
struct dst_entry *ndst;
struct flowi6 fl6;
u32 flags;
md.vni = htonl(vni << 8);
md.gbp = skb->mark;
- err = vxlan6_xmit_skb(ndst, skb, dev, &fl6.saddr, &fl6.daddr,
+ err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr,
0, ttl, src_port, dst_port, &md,
!net_eq(vxlan->net, dev_net(vxlan->dev)),
vxlan->flags);
static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
{
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
__u32 vni = vxlan->default_dst.remote_vni;
vxlan->vn_sock = vs;
+ spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
+ spin_unlock(&vn->sock_lock);
}
/* Setup stats when device is created */
static int vxlan_init(struct net_device *dev)
{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
- struct vxlan_sock *vs;
- bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
-
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
- vxlan->dst_port, vxlan->flags);
- if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) {
- /* If we have a socket with same port already, reuse it */
- vxlan_vs_add_dev(vs, vxlan);
- } else {
- /* otherwise make new socket outside of RTNL */
- dev_hold(dev);
- queue_work(vxlan_wq, &vxlan->sock_work);
- }
- spin_unlock(&vn->sock_lock);
-
return 0;
}
static void vxlan_uninit(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_sock *vs = vxlan->vn_sock;
vxlan_fdb_delete_default(vxlan);
- if (vs)
- vxlan_sock_release(vs);
free_percpu(dev->tstats);
}
static int vxlan_open(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_sock *vs = vxlan->vn_sock;
+ struct vxlan_sock *vs;
+ int ret = 0;
- /* socket hasn't been created */
- if (!vs)
- return -ENOTCONN;
+ vs = vxlan_sock_add(vxlan->net, vxlan->dst_port, vxlan_rcv, NULL,
+ false, vxlan->flags);
+ if (IS_ERR(vs))
+ return PTR_ERR(vs);
+
+ vxlan_vs_add_dev(vs, vxlan);
if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
- vxlan_sock_hold(vs);
- dev_hold(dev);
- queue_work(vxlan_wq, &vxlan->igmp_join);
+ ret = vxlan_igmp_join(vxlan);
+ if (ret) {
+ vxlan_sock_release(vs);
+ return ret;
+ }
}
if (vxlan->age_interval)
mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL);
- return 0;
+ return ret;
}
/* Purge the forwarding table */
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
struct vxlan_sock *vs = vxlan->vn_sock;
+ int ret = 0;
- if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
- !vxlan_group_used(vn, vxlan)) {
- vxlan_sock_hold(vs);
- dev_hold(dev);
- queue_work(vxlan_wq, &vxlan->igmp_leave);
- }
+ if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
+ !vxlan_group_used(vn, vxlan))
+ ret = vxlan_igmp_leave(vxlan);
del_timer_sync(&vxlan->age_timer);
vxlan_flush(vxlan);
+ vxlan_sock_release(vs);
- return 0;
+ return ret;
}
/* Stub, nothing needs to be done. */
INIT_LIST_HEAD(&vxlan->next);
spin_lock_init(&vxlan->hash_lock);
- INIT_WORK(&vxlan->igmp_join, vxlan_igmp_join);
- INIT_WORK(&vxlan->igmp_leave, vxlan_igmp_leave);
- INIT_WORK(&vxlan->sock_work, vxlan_sock_work);
init_timer_deferrable(&vxlan->age_timer);
vxlan->age_timer.function = vxlan_cleanup;
!(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
} else {
udp_conf.family = AF_INET;
- udp_conf.local_ip.s_addr = INADDR_ANY;
}
udp_conf.local_udp_port = port;
sock = vxlan_create_sock(net, ipv6, port, flags);
if (IS_ERR(sock)) {
+ pr_info("Cannot bind port %d, err=%ld\n", ntohs(port),
+ PTR_ERR(sock));
kfree(vs);
return ERR_CAST(sock);
}
struct vxlan_sock *vs;
bool ipv6 = flags & VXLAN_F_IPV6;
- vs = vxlan_socket_create(net, port, rcv, data, flags);
- if (!IS_ERR(vs))
- return vs;
-
- if (no_share) /* Return error if sharing is not allowed. */
- return vs;
-
- spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, flags);
- if (vs && ((vs->rcv != rcv) ||
- !atomic_add_unless(&vs->refcnt, 1, 0)))
- vs = ERR_PTR(-EBUSY);
- spin_unlock(&vn->sock_lock);
-
- if (!vs)
- vs = ERR_PTR(-EINVAL);
+ if (!no_share) {
+ spin_lock(&vn->sock_lock);
+ vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port,
+ flags);
+ if (vs && vs->rcv == rcv) {
+ if (!atomic_add_unless(&vs->refcnt, 1, 0))
+ vs = ERR_PTR(-EBUSY);
+ spin_unlock(&vn->sock_lock);
+ return vs;
+ }
+ spin_unlock(&vn->sock_lock);
+ }
- return vs;
+ return vxlan_socket_create(net, port, rcv, data, flags);
}
EXPORT_SYMBOL_GPL(vxlan_sock_add);
-/* Scheduled at device creation to bind to a socket */
-static void vxlan_sock_work(struct work_struct *work)
-{
- struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, sock_work);
- struct net *net = vxlan->net;
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- __be16 port = vxlan->dst_port;
- struct vxlan_sock *nvs;
-
- nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags);
- spin_lock(&vn->sock_lock);
- if (!IS_ERR(nvs))
- vxlan_vs_add_dev(nvs, vxlan);
- spin_unlock(&vn->sock_lock);
-
- dev_put(vxlan->dev);
-}
-
static int vxlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
/* 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.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]);
} else if (data[IFLA_VXLAN_GROUP6]) {
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
- nla_memcpy(&dst->remote_ip.sin6.sin6_addr, data[IFLA_VXLAN_GROUP6],
- sizeof(struct in6_addr));
+ dst->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]);
dst->remote_ip.sa.sa_family = AF_INET6;
use_ipv6 = true;
}
if (data[IFLA_VXLAN_LOCAL]) {
- vxlan->saddr.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ vxlan->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]);
vxlan->saddr.sa.sa_family = AF_INET;
} else if (data[IFLA_VXLAN_LOCAL6]) {
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
/* TODO: respect scope id */
- nla_memcpy(&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6],
- sizeof(struct in6_addr));
+ vxlan->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]);
vxlan->saddr.sa.sa_family = AF_INET6;
use_ipv6 = true;
}
if (!vxlan_addr_any(&dst->remote_ip)) {
if (dst->remote_ip.sa.sa_family == AF_INET) {
- if (nla_put_be32(skb, IFLA_VXLAN_GROUP,
- dst->remote_ip.sin.sin_addr.s_addr))
+ if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP,
+ dst->remote_ip.sin.sin_addr.s_addr))
goto nla_put_failure;
#if IS_ENABLED(CONFIG_IPV6)
} else {
- if (nla_put(skb, IFLA_VXLAN_GROUP6, sizeof(struct in6_addr),
- &dst->remote_ip.sin6.sin6_addr))
+ if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6,
+ &dst->remote_ip.sin6.sin6_addr))
goto nla_put_failure;
#endif
}
if (!vxlan_addr_any(&vxlan->saddr)) {
if (vxlan->saddr.sa.sa_family == AF_INET) {
- if (nla_put_be32(skb, IFLA_VXLAN_LOCAL,
- vxlan->saddr.sin.sin_addr.s_addr))
+ if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL,
+ vxlan->saddr.sin.sin_addr.s_addr))
goto nla_put_failure;
#if IS_ENABLED(CONFIG_IPV6)
} else {
- if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr),
- &vxlan->saddr.sin6.sin6_addr))
+ if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6,
+ &vxlan->saddr.sin6.sin6_addr))
goto nla_put_failure;
#endif
}
projects / firefly-linux-kernel-4.4.55.git / blobdiff