* [Patch net-next v6 4/5] vxlan: add ipv6 support
2013-04-24 5:54 [Patch net-next v6 0/5] vxlan: add ipv6 support Cong Wang
` (2 preceding siblings ...)
2013-04-24 5:54 ` [Patch net-next v6 3/5] ipv6: export in6addr_loopback to modules Cong Wang
@ 2013-04-24 5:54 ` Cong Wang
2013-04-29 15:52 ` David Miller
2013-04-24 5:54 ` [Patch net-next v6 5/5] ipv6: Add generic UDP Tunnel segmentation Cong Wang
4 siblings, 1 reply; 8+ messages in thread
From: Cong Wang @ 2013-04-24 5:54 UTC (permalink / raw)
To: netdev; +Cc: David Stevens, Stephen Hemminger, David S. Miller, Cong Wang
From: Cong Wang <amwang@redhat.com>
This patch adds IPv6 support to vxlan device, as the new version
RFC already mentions it:
http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-03
There are still few things need to fix, e.g. scope id for ll addr,
as pointed out by David, I put them in my TODO list.
Cc: David Stevens <dlstevens@us.ibm.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
drivers/net/vxlan.c | 636 +++++++++++++++++++++++++++++++++---------
include/uapi/linux/if_link.h | 2 +
2 files changed, 502 insertions(+), 136 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a0ca469..be42e00 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -9,7 +9,6 @@
*
* TODO
* - use IANA UDP port number (when defined)
- * - IPv6 (not in RFC)
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -42,6 +41,11 @@
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#include <net/ip6_tunnel.h>
+#endif
#define VXLAN_VERSION "0.1"
@@ -56,6 +60,7 @@
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
/* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
+#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
@@ -81,9 +86,15 @@ struct vxlan_net {
struct hlist_head vni_list[VNI_HASH_SIZE];
};
+union vxlan_addr {
+ struct sockaddr_in sin;
+ struct sockaddr_in6 sin6;
+ struct sockaddr sa;
+};
+
struct vxlan_rdst {
struct rcu_head rcu;
- __be32 remote_ip;
+ union vxlan_addr remote_ip;
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
@@ -107,7 +118,7 @@ struct vxlan_dev {
struct hlist_node hlist;
struct net_device *dev;
struct vxlan_rdst default_dst; /* default destination */
- __be32 saddr; /* source address */
+ union vxlan_addr saddr; /* source address */
__u16 port_min; /* source port range */
__u16 port_max;
__u8 tos; /* TOS override */
@@ -129,6 +140,69 @@ struct vxlan_dev {
#define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10
+static inline
+bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ 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
+#endif
+ 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 IS_ENABLED(CONFIG_IPV6)
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_any(&ipa->sin6.sin6_addr);
+ else
+#endif
+ return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+}
+
+static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
+ else
+#endif
+ 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)) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&ip->sin6.sin6_addr, nla, sizeof(struct in6_addr));
+ ip->sa.sa_family = AF_INET6;
+ return 0;
+#else
+ return -EAFNOSUPPORT;
+#endif
+ } 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;
+ }
+}
+
+static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
+ const union vxlan_addr *ip)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ip->sa.sa_family == AF_INET6)
+ return nla_put(skb, attr, sizeof(struct in6_addr), &ip->sin6.sin6_addr);
+ else
+#endif
+ return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
+}
+
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
@@ -175,7 +249,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
if (type == RTM_GETNEIGH) {
ndm->ndm_family = AF_INET;
- send_ip = rdst->remote_ip != htonl(INADDR_ANY);
+ send_ip = !vxlan_addr_any(&rdst->remote_ip);
send_eth = !is_zero_ether_addr(fdb->eth_addr);
} else
ndm->ndm_family = AF_BRIDGE;
@@ -187,7 +261,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure;
- if (send_ip && nla_put_be32(skb, NDA_DST, rdst->remote_ip))
+ if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip))
goto nla_put_failure;
if (rdst->remote_port && rdst->remote_port != vxlan_port &&
@@ -219,7 +293,7 @@ static inline size_t vxlan_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
- + nla_total_size(sizeof(__be32)) /* NDA_DST */
+ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */
+ nla_total_size(sizeof(__be32)) /* NDA_PORT */
+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
@@ -252,14 +326,14 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
-static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
+static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb f;
memset(&f, 0, sizeof f);
f.state = NUD_STALE;
- f.remote.remote_ip = ipa; /* goes to NDA_DST */
+ f.remote.remote_ip = *ipa; /* goes to NDA_DST */
f.remote.remote_vni = VXLAN_N_VID;
vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
@@ -314,14 +388,14 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
}
/* Add/update destinations for multicast */
-static int vxlan_fdb_append(struct vxlan_fdb *f,
- __be32 ip, __u32 port, __u32 vni, __u32 ifindex)
+static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip,
+ __u32 port, __u32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd_prev, *rd;
rd_prev = NULL;
for (rd = &f->remote; rd; rd = rd->remote_next) {
- if (rd->remote_ip == ip &&
+ if (vxlan_addr_equal(&rd->remote_ip, ip) &&
rd->remote_port == port &&
rd->remote_vni == vni &&
rd->remote_ifindex == ifindex)
@@ -331,7 +405,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
- rd->remote_ip = ip;
+ rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
@@ -342,7 +416,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
/* Add new entry to forwarding table -- assumes lock held */
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
- const u8 *mac, __be32 ip,
+ const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
__u32 port, __u32 vni, __u32 ifindex,
__u8 ndm_flags)
@@ -382,13 +456,20 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax)
return -ENOSPC;
- netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ip->sa.sa_family == AF_INET6)
+ netdev_dbg(vxlan->dev, "add %pM -> %pI6\n", mac,
+ &ip->sin6.sin6_addr);
+ else
+#endif
+ netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac,
+ &ip->sin.sin_addr.s_addr);
f = kmalloc(sizeof(*f), GFP_ATOMIC);
if (!f)
return -ENOMEM;
notify = 1;
- f->remote.remote_ip = ip;
+ f->remote.remote_ip = *ip;
f->remote.remote_port = port;
f->remote.remote_vni = vni;
f->remote.remote_ifindex = ifindex;
@@ -441,7 +522,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct net *net = dev_net(vxlan->dev);
- __be32 ip;
+ union vxlan_addr ip;
u32 port, vni, ifindex;
int err;
@@ -454,10 +535,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
if (tb[NDA_DST] == NULL)
return -EINVAL;
- if (nla_len(tb[NDA_DST]) != sizeof(__be32))
- return -EAFNOSUPPORT;
-
- ip = nla_get_be32(tb[NDA_DST]);
+ err = vxlan_nla_get_addr(&ip, tb[NDA_DST]);
+ if (err)
+ return err;
if (tb[NDA_PORT]) {
if (nla_len(tb[NDA_PORT]) != sizeof(u32))
@@ -487,7 +567,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
ifindex = 0;
spin_lock_bh(&vxlan->hash_lock);
- err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags, port,
+ err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, port,
vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock);
@@ -551,7 +631,7 @@ skip:
* and Tunnel endpoint.
*/
static void vxlan_snoop(struct net_device *dev,
- __be32 src_ip, const u8 *src_mac)
+ union vxlan_addr *src_ip, const u8 *src_mac)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
@@ -560,15 +640,25 @@ static void vxlan_snoop(struct net_device *dev,
f = vxlan_find_mac(vxlan, src_mac);
if (likely(f)) {
f->used = jiffies;
- if (likely(f->remote.remote_ip == src_ip))
+ if (likely(vxlan_addr_equal(&f->remote.remote_ip, src_ip)))
return;
- if (net_ratelimit())
- netdev_info(dev,
- "%pM migrated from %pI4 to %pI4\n",
- src_mac, &f->remote.remote_ip, &src_ip);
+ if (net_ratelimit()) {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (src_ip->sa.sa_family == AF_INET6)
+ netdev_info(dev,
+ "%pM migrated from %pI6 to %pI6\n",
+ src_mac, &f->remote.remote_ip.sin6.sin6_addr,
+ &src_ip->sin6.sin6_addr);
+ else
+#endif
+ netdev_info(dev,
+ "%pM migrated from %pI4 to %pI4\n",
+ src_mac, &f->remote.remote_ip.sin.sin_addr.s_addr,
+ &src_ip->sin.sin_addr.s_addr);
+ }
- f->remote.remote_ip = src_ip;
+ f->remote.remote_ip = *src_ip;
f->updated = jiffies;
} else {
/* learned new entry */
@@ -599,7 +689,8 @@ static bool vxlan_group_used(struct vxlan_net *vn,
if (!netif_running(vxlan->dev))
continue;
- if (vxlan->default_dst.remote_ip == this->default_dst.remote_ip)
+ if (vxlan_addr_equal(&vxlan->default_dst.remote_ip,
+ &this->default_dst.remote_ip))
return true;
}
@@ -612,8 +703,9 @@ static int vxlan_join_group(struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct sock *sk = vn->sock->sk;
+ union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip,
+ .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = vxlan->default_dst.remote_ifindex,
};
int err;
@@ -625,7 +717,13 @@ static int vxlan_join_group(struct net_device *dev)
/* Need to drop RTNL to call multicast join */
rtnl_unlock();
lock_sock(sk);
- err = ip_mc_join_group(sk, &mreq);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
+ err = ipv6_mcast_ops->ipv6_sock_mc_join(sk, vxlan->default_dst.remote_ifindex,
+ &ip->sin6.sin6_addr);
+ else
+#endif
+ err = ip_mc_join_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
@@ -640,8 +738,9 @@ static int vxlan_leave_group(struct net_device *dev)
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
int err = 0;
struct sock *sk = vn->sock->sk;
+ union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip,
+ .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = vxlan->default_dst.remote_ifindex,
};
@@ -652,7 +751,13 @@ static int vxlan_leave_group(struct net_device *dev)
/* Need to drop RTNL to call multicast leave */
rtnl_unlock();
lock_sock(sk);
- err = ip_mc_leave_group(sk, &mreq);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
+ err = ipv6_mcast_ops->ipv6_sock_mc_drop(sk, vxlan->default_dst.remote_ifindex,
+ &ip->sin6.sin6_addr);
+ else
+#endif
+ err = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
@@ -662,12 +767,16 @@ static int vxlan_leave_group(struct net_device *dev)
/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
- struct iphdr *oip;
+ struct iphdr *oip = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct ipv6hdr *oip6 = NULL;
+#endif
struct vxlanhdr *vxh;
struct vxlan_dev *vxlan;
struct pcpu_tstats *stats;
+ union vxlan_addr src_ip;
__u32 vni;
- int err;
+ int err = 0;
/* pop off outer UDP header */
__skb_pull(skb, sizeof(struct udphdr));
@@ -704,7 +813,13 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
skb_reset_mac_header(skb);
/* Re-examine inner Ethernet packet */
- oip = ip_hdr(skb);
+ if (skb->protocol == htons(ETH_P_IP))
+ oip = ip_hdr(skb);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (skb->protocol == htons(ETH_P_IPV6))
+ oip6 = ipv6_hdr(skb);
+#endif
+
skb->protocol = eth_type_trans(skb, vxlan->dev);
/* Ignore packet loops (and multicast echo) */
@@ -712,8 +827,19 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
vxlan->dev->dev_addr) == 0)
goto drop;
- if (vxlan->flags & VXLAN_F_LEARN)
- vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source);
+ if (vxlan->flags & VXLAN_F_LEARN) {
+ if (oip) {
+ src_ip.sin.sin_addr.s_addr = oip->saddr;
+ src_ip.sa.sa_family = AF_INET;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ if (oip6) {
+ src_ip.sin6.sin6_addr = oip6->saddr;
+ src_ip.sa.sa_family = AF_INET6;
+ }
+#endif
+ vxlan_snoop(skb->dev, &src_ip, eth_hdr(skb)->h_source);
+ }
__skb_tunnel_rx(skb, vxlan->dev);
skb_reset_network_header(skb);
@@ -729,11 +855,24 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
skb->encapsulation = 0;
- err = IP_ECN_decapsulate(oip, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (oip6)
+ err = IP6_ECN_decapsulate(oip6, skb);
+#endif
+ if (oip)
+ err = IP_ECN_decapsulate(oip, skb);
+
if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &oip->saddr, oip->tos);
+ if (log_ecn_error) {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (oip6)
+ net_info_ratelimited("non-ECT from %pI6\n",
+ &oip6->saddr);
+#endif
+ if (oip)
+ net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+ &oip->saddr, oip->tos);
+ }
if (err > 1) {
++vxlan->dev->stats.rx_frame_errors;
++vxlan->dev->stats.rx_errors;
@@ -768,6 +907,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
u8 *arpptr, *sha;
__be32 sip, tip;
struct neighbour *n;
+ union vxlan_addr ipa;
if (dev->flags & IFF_NOARP)
goto out;
@@ -809,7 +949,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
}
f = vxlan_find_mac(vxlan, n->ha);
- if (f && f->remote.remote_ip == htonl(INADDR_ANY)) {
+ if (f && vxlan_addr_any(&f->remote.remote_ip)) {
/* bridge-local neighbor */
neigh_release(n);
goto out;
@@ -827,8 +967,11 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
if (netif_rx_ni(reply) == NET_RX_DROP)
dev->stats.rx_dropped++;
- } else if (vxlan->flags & VXLAN_F_L3MISS)
- vxlan_ip_miss(dev, tip);
+ } else if (vxlan->flags & VXLAN_F_L3MISS) {
+ ipa.sin.sin_addr.s_addr = tip;
+ ipa.sa.sa_family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ }
out:
consume_skb(skb);
return NETDEV_TX_OK;
@@ -850,6 +993,14 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
pip = ip_hdr(skb);
n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
+ if (!n && vxlan->flags & VXLAN_F_L3MISS) {
+ union vxlan_addr ipa;
+ ipa.sin.sin_addr.s_addr = pip->daddr;
+ ipa.sa.sa_family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ return false;
+ }
+
break;
default:
return false;
@@ -866,8 +1017,8 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
}
neigh_release(n);
return diff;
- } else if (vxlan->flags & VXLAN_F_L3MISS)
- vxlan_ip_miss(dev, pip->daddr);
+ }
+
return false;
}
@@ -877,7 +1028,8 @@ static void vxlan_sock_free(struct sk_buff *skb)
}
/* On transmit, associate with the tunnel socket */
-static void vxlan_set_owner(struct net_device *dev, struct sk_buff *skb)
+static inline void vxlan_set_owner(struct net_device *dev,
+ struct sk_buff *skb)
{
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct sock *sk = vn->sock->sk;
@@ -926,15 +1078,26 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
{
struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
+ union vxlan_addr loopback;
skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0;
skb->dev = dst_vxlan->dev;
__skb_pull(skb, skb_network_offset(skb));
+ if (dst_vxlan->default_dst.remote_ip.sa.sa_family == AF_INET) {
+ loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ loopback.sa.sa_family = AF_INET;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else {
+ loopback.sin6.sin6_addr = in6addr_loopback;
+ loopback.sa.sa_family = AF_INET6;
+ }
+#endif
+
if (dst_vxlan->flags & VXLAN_F_LEARN)
- vxlan_snoop(skb->dev, htonl(INADDR_LOOPBACK),
- eth_hdr(skb)->h_source);
+ vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->tx_packets++;
@@ -956,22 +1119,29 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct rtable *rt;
- const struct iphdr *old_iph;
+ const struct iphdr *old_iph = NULL;
struct iphdr *iph;
struct vxlanhdr *vxh;
struct udphdr *uh;
struct flowi4 fl4;
- __be32 dst;
- __u16 src_port, dst_port;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct flowi6 fl6;
+ struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+ struct sock *sk = vn->sock->sk;
+ struct ipv6hdr *ip6h;
+#endif
+ const union vxlan_addr *dst;
+ struct dst_entry *ndst = NULL;
+ __u16 src_port = 0, dst_port;
u32 vni;
__be16 df = 0;
__u8 tos, ttl;
dst_port = rdst->remote_port ? rdst->remote_port : vxlan_port;
vni = rdst->remote_vni;
- dst = rdst->remote_ip;
+ dst = &rdst->remote_ip;
- if (!dst) {
+ if (vxlan_addr_any(dst)) {
if (did_rsc) {
/* short-circuited back to local bridge */
vxlan_encap_bypass(skb, vxlan, vxlan);
@@ -985,60 +1155,119 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
skb->encapsulation = 1;
}
- /* Need space for new headers (invalidates iph ptr) */
- if (skb_cow_head(skb, VXLAN_HEADROOM))
- goto drop;
+ ttl = vxlan->ttl;
+ tos = vxlan->tos;
+ if (dst->sa.sa_family == AF_INET) {
+ /* Need space for new headers (invalidates iph ptr) */
+ if (skb_cow_head(skb, VXLAN_HEADROOM))
+ goto drop;
- old_iph = ip_hdr(skb);
+ old_iph = ip_hdr(skb);
+ if (!ttl && IN_MULTICAST(ntohl(dst->sin.sin_addr.s_addr)))
+ ttl = 1;
- ttl = vxlan->ttl;
- if (!ttl && IN_MULTICAST(ntohl(dst)))
- ttl = 1;
+ if (tos == 1)
+ tos = ip_tunnel_get_dsfield(old_iph, skb);
- tos = vxlan->tos;
- if (tos == 1)
- tos = ip_tunnel_get_dsfield(old_iph, skb);
-
- src_port = vxlan_src_port(vxlan, skb);
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = rdst->remote_ifindex;
- fl4.flowi4_tos = RT_TOS(tos);
- fl4.daddr = dst;
- fl4.saddr = vxlan->saddr;
-
- rt = ip_route_output_key(dev_net(dev), &fl4);
- if (IS_ERR(rt)) {
- netdev_dbg(dev, "no route to %pI4\n", &dst);
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
+ src_port = vxlan_src_port(vxlan, skb);
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n", &dst);
- ip_rt_put(rt);
- dev->stats.collisions++;
- goto tx_error;
- }
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = rdst->remote_ifindex;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.daddr = dst->sin.sin_addr.s_addr;
+ fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
- /* Bypass encapsulation if the destination is local */
- if (rt->rt_flags & RTCF_LOCAL &&
- !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
+ rt = ip_route_output_key(dev_net(dev), &fl4);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to %pI4\n",
+ &dst->sin.sin_addr.s_addr);
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
- ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni);
- if (!dst_vxlan)
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n",
+ &dst->sin.sin_addr.s_addr);
+ ip_rt_put(rt);
+ dev->stats.collisions++;
goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return NETDEV_TX_OK;
+ }
+
+ /* Bypass encapsulation if the destination is local */
+ if (rt->rt_flags & RTCF_LOCAL &&
+ !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ ip_rt_put(rt);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni);
+ if (!dst_vxlan)
+ goto tx_error;
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return NETDEV_TX_OK;
+ }
+
+ ndst = &rt->dst;
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ const struct ipv6hdr *old_iph6;
+ u32 flags;
+
+ /* Need space for new headers (invalidates ipv6h ptr) */
+ if (skb_cow_head(skb, VXLAN6_HEADROOM))
+ goto drop;
+
+ old_iph6 = ipv6_hdr(skb);
+ if (!ttl && ipv6_addr_is_multicast(&dst->sin6.sin6_addr))
+ ttl = 1;
+
+ if (tos == 1)
+ tos = ipv6_get_dsfield(old_iph6);
+
+ src_port = vxlan_src_port(vxlan, skb);
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = rdst->remote_ifindex;
+ fl6.flowi6_tos = RT_TOS(tos);
+ fl6.daddr = dst->sin6.sin6_addr;
+ fl6.saddr = vxlan->saddr.sin6.sin6_addr;
+ fl6.flowi6_proto = skb->protocol;
+
+ if (ip6_dst_lookup(sk, &ndst, &fl6)) {
+ netdev_dbg(dev, "no route to %pI6\n",
+ &dst->sin6.sin6_addr);
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
+
+ if (ndst->dev == dev) {
+ netdev_dbg(dev, "circular route to %pI6\n",
+ &dst->sin6.sin6_addr);
+ dst_release(ndst);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+
+ /* Bypass encapsulation if the destination is local */
+ flags = ((struct rt6_info *)ndst)->rt6i_flags;
+ if (flags & RTF_LOCAL &&
+ !(flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ dst_release(ndst);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni);
+ if (!dst_vxlan)
+ goto tx_error;
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return NETDEV_TX_OK;
+ }
+#endif
}
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
+ skb_dst_set(skb, ndst);
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_FLAGS);
@@ -1054,27 +1283,63 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
uh->len = htons(skb->len);
uh->check = 0;
- __skb_push(skb, sizeof(*iph));
- skb_reset_network_header(skb);
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_UDP;
- iph->tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
- iph->daddr = dst;
- iph->saddr = fl4.saddr;
- iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
- nf_reset(skb);
+ if (dst->sa.sa_family == AF_INET) {
+ __skb_push(skb, sizeof(*iph));
+ skb_reset_network_header(skb);
+ iph = ip_hdr(skb);
+ iph->version = 4;
+ iph->ihl = sizeof(struct iphdr) >> 2;
+ iph->frag_off = df;
+ iph->protocol = IPPROTO_UDP;
+ iph->tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ iph->daddr = dst->sin.sin_addr.s_addr;
+ iph->saddr = fl4.saddr;
+ iph->ttl = ttl ? : ip4_dst_hoplimit(ndst);
+ tunnel_ip_select_ident(skb, old_iph, ndst);
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (!skb_is_gso(skb) && !(ndst->dev->features & NETIF_F_IPV6_CSUM)) {
+ __wsum csum = skb_checksum(skb, 0, skb->len, 0);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ uh->check = csum_ipv6_magic(&fl6.saddr, &fl6.daddr, skb->len,
+ IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_ipv6_magic(&fl6.saddr, &fl6.daddr,
+ skb->len, IPPROTO_UDP, 0);
+ }
+
+ __skb_push(skb, sizeof(*ip6h));
+ skb_reset_network_header(skb);
+ ip6h = ipv6_hdr(skb);
+ ip6h->version = 6;
+ ip6h->priority = 0;
+ ip6h->flow_lbl[0] = 0;
+ ip6h->flow_lbl[1] = 0;
+ ip6h->flow_lbl[2] = 0;
+ ip6h->payload_len = htons(skb->len);
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->hop_limit = ttl ? : ip6_dst_hoplimit(ndst);
+ ip6h->daddr = fl6.daddr;
+ ip6h->saddr = fl6.saddr;
+#endif
+ }
vxlan_set_owner(dev, skb);
if (handle_offloads(skb))
goto drop;
- iptunnel_xmit(skb, dev);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (dst->sa.sa_family == AF_INET6)
+ ip6tunnel_xmit(skb, dev);
+ else
+#endif
+ iptunnel_xmit(skb, dev);
return NETDEV_TX_OK;
drop:
@@ -1122,7 +1387,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
if (f == NULL) {
rdst0 = &vxlan->default_dst;
- if (rdst0->remote_ip == htonl(INADDR_ANY) &&
+ if (vxlan_addr_any(&rdst0->remote_ip) &&
(vxlan->flags & VXLAN_F_L2MISS) &&
!is_multicast_ether_addr(eth->h_dest))
vxlan_fdb_miss(vxlan, eth->h_dest);
@@ -1200,7 +1465,7 @@ static int vxlan_open(struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev);
int err;
- if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+ if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
err = vxlan_join_group(dev);
if (err)
return err;
@@ -1234,7 +1499,7 @@ static int vxlan_stop(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)))
+ if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip))
vxlan_leave_group(dev);
del_timer_sync(&vxlan->age_timer);
@@ -1284,7 +1549,12 @@ static void vxlan_setup(struct net_device *dev)
eth_hw_addr_random(dev);
ether_setup(dev);
- dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
+ dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+ else
+#endif
+ dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = vxlan_free;
@@ -1321,8 +1591,10 @@ static void vxlan_setup(struct net_device *dev)
static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
[IFLA_VXLAN_ID] = { .type = NLA_U32 },
[IFLA_VXLAN_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_VXLAN_REMOTE6] = { .len = sizeof(struct in6_addr) },
[IFLA_VXLAN_LINK] = { .type = NLA_U32 },
[IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
+ [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) },
[IFLA_VXLAN_TOS] = { .type = NLA_U8 },
[IFLA_VXLAN_TTL] = { .type = NLA_U8 },
[IFLA_VXLAN_LEARNING] = { .type = NLA_U8 },
@@ -1402,11 +1674,31 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
}
dst->remote_vni = vni;
- if (data[IFLA_VXLAN_REMOTE])
- dst->remote_ip = nla_get_be32(data[IFLA_VXLAN_REMOTE]);
+ if (data[IFLA_VXLAN_REMOTE]) {
+ dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_REMOTE]);
+ dst->remote_ip.sa.sa_family = AF_INET;
+ } else if (data[IFLA_VXLAN_REMOTE6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&dst->remote_ip.sin6.sin6_addr, data[IFLA_VXLAN_REMOTE6],
+ sizeof(struct in6_addr));
+ dst->remote_ip.sa.sa_family = AF_INET6;
+#else
+ return -EPFNOSUPPORT;
+#endif
+ }
- if (data[IFLA_VXLAN_LOCAL])
- vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ if (data[IFLA_VXLAN_LOCAL]) {
+ vxlan->saddr.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ vxlan->saddr.sa.sa_family = AF_INET;
+ } else if (data[IFLA_VXLAN_LOCAL6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6],
+ sizeof(struct in6_addr));
+ vxlan->saddr.sa.sa_family = AF_INET6;
+#else
+ return -EPFNOSUPPORT;
+#endif
+ }
if (data[IFLA_VXLAN_LINK] &&
(dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
@@ -1484,9 +1776,9 @@ static size_t vxlan_get_size(const struct net_device *dev)
{
return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */
- nla_total_size(sizeof(__be32)) +/* IFLA_VXLAN_REMOTE */
+ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_REMOTE{6} */
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */
- nla_total_size(sizeof(__be32))+ /* IFLA_VXLAN_LOCAL */
+ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
@@ -1512,14 +1804,34 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni))
goto nla_put_failure;
- if (dst->remote_ip && nla_put_be32(skb, IFLA_VXLAN_REMOTE, dst->remote_ip))
- goto nla_put_failure;
+ if (!vxlan_addr_any(&dst->remote_ip)) {
+ if (dst->remote_ip.sa.sa_family == AF_INET) {
+ if (nla_put_be32(skb, IFLA_VXLAN_REMOTE, dst->remote_ip.sin.sin_addr.s_addr))
+ goto nla_put_failure;
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (nla_put(skb, IFLA_VXLAN_REMOTE6, sizeof(struct in6_addr),
+ &dst->remote_ip.sin6.sin6_addr))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex))
goto nla_put_failure;
- if (vxlan->saddr && nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr))
- goto nla_put_failure;
+ 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))
+ goto nla_put_failure;
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr),
+ &vxlan->saddr.sin6.sin6_addr))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
@@ -1558,38 +1870,87 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
.fill_info = vxlan_fill_info,
};
-static __net_init int vxlan_init_net(struct net *net)
+/* Create UDP socket for encapsulation receive. AF_INET6 socket
+ * could be used for both IPv4 and IPv6 communications.
+ */
+#if IS_ENABLED(CONFIG_IPV6)
+static __net_init int create_sock(struct net *net, struct sock **sk)
+{
+ struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+ struct sockaddr_in6 vxlan_addr = {
+ .sin6_family = AF_INET6,
+ .sin6_port = htons(vxlan_port),
+ };
+ int rc;
+
+ rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &vn->sock);
+ if (rc < 0) {
+ pr_debug("UDP socket create failed\n");
+ return rc;
+ }
+ /* Put in proper namespace */
+ *sk = vn->sock->sk;
+ sk_change_net(*sk, net);
+
+ rc = kernel_bind(vn->sock, (struct sockaddr *)&vxlan_addr,
+ sizeof(struct sockaddr_in6));
+ if (rc < 0) {
+ pr_debug("bind for UDP socket %pI6:%u (%d)\n",
+ &vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc);
+ sk_release_kernel(*sk);
+ vn->sock = NULL;
+ return rc;
+ }
+
+ /* At this point, IPv6 module should have been loaded in
+ * sock_create_kern().
+ */
+ BUG_ON(!ipv6_mcast_ops);
+ return 0;
+}
+#else
+static __net_init int create_sock(struct net *net, struct sock **sk)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- struct sock *sk;
struct sockaddr_in vxlan_addr = {
.sin_family = AF_INET,
+ .sin_port = htons(vxlan_port),
.sin_addr.s_addr = htonl(INADDR_ANY),
};
int rc;
- unsigned h;
- /* Create UDP socket for encapsulation receive. */
rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vn->sock);
if (rc < 0) {
pr_debug("UDP socket create failed\n");
return rc;
}
/* Put in proper namespace */
- sk = vn->sock->sk;
- sk_change_net(sk, net);
-
- vxlan_addr.sin_port = htons(vxlan_port);
+ *sk = vn->sock->sk;
+ sk_change_net(*sk, net);
- rc = kernel_bind(vn->sock, (struct sockaddr *) &vxlan_addr,
- sizeof(vxlan_addr));
+ rc = kernel_bind(vn->sock, (struct sockaddr *)&vxlan_addr,
+ sizeof(struct sockaddr_in));
if (rc < 0) {
pr_debug("bind for UDP socket %pI4:%u (%d)\n",
&vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
- sk_release_kernel(sk);
+ sk_release_kernel(*sk);
vn->sock = NULL;
return rc;
}
+ return 0;
+}
+#endif
+
+static __net_init int vxlan_init_net(struct net *net)
+{
+ struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+ struct sock *sk;
+ int rc;
+ unsigned h;
+
+ rc = create_sock(net, &sk);
+ if (rc < 0)
+ return rc;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
@@ -1598,6 +1959,9 @@ static __net_init int vxlan_init_net(struct net *net)
udp_sk(sk)->encap_type = 1;
udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
udp_encap_enable();
+#if IS_ENABLED(CONFIG_IPV6)
+ udpv6_encap_enable();
+#endif
for (h = 0; h < VNI_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&vn->vni_list[h]);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index e316354..92ae9bd 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -310,6 +310,8 @@ enum {
IFLA_VXLAN_RSC,
IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS,
+ IFLA_VXLAN_REMOTE6,
+ IFLA_VXLAN_LOCAL6,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
--
1.7.7.6
^ permalink raw reply related [flat|nested] 8+ messages in thread