| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1365387536-25217-3-git-send-email-amwang@redhat.com>
Date: Mon, 8 Apr 2013 10:18:54 +0800
From: Cong Wang <amwang@...hat.com>
To: netdev@...r.kernel.org
Cc: David Stevens <dlstevens@...ibm.com>,
Stephen Hemminger <stephen@...workplumber.org>,
"David S. Miller" <davem@...emloft.net>,
Cong Wang <amwang@...hat.com>
Subject: [Patch net-next v3 3/4] vxlan: add ipv6 support
From: Cong Wang <amwang@...hat.com>
v3: fix many coding style issues
fix some ugly #ifdef
rename vxlan_ip to vxlan_addr
rename ->proto to ->family
rename ->ip4/->ip6 to ->sin/->sin6
v2: fix some compile error when !CONFIG_IPV6
improve some code based on Stephen's comments
use sockaddr suggested by David
This patch adds IPv6 support to vxlan device, as the new version
RFC already mentioned it:
http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-03
Cc: David Stevens <dlstevens@...ibm.com>
Cc: Stephen Hemminger <stephen@...workplumber.org>
Cc: David S. Miller <davem@...emloft.net>
Signed-off-by: Cong Wang <amwang@...hat.com>
---
drivers/net/vxlan.c | 544 ++++++++++++++++++++++++++++++++----------
include/uapi/linux/if_link.h | 2 +
2 files changed, 425 insertions(+), 121 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index cac4e4f..5fbf0ed 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 +86,20 @@ struct vxlan_net {
struct hlist_head vni_list[VNI_HASH_SIZE];
};
+struct vxlan_addr {
+ union {
+ struct sockaddr_in sin;
+ struct sockaddr_in6 sin6;
+ struct sockaddr sa;
+ } u;
+#define sin u.sin.sin_addr.s_addr
+#define sin6 u.sin6.sin6_addr
+#define family u.sa.sa_family
+};
+
struct vxlan_rdst {
struct rcu_head rcu;
- __be32 remote_ip;
+ struct vxlan_addr remote_ip;
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
@@ -106,8 +122,8 @@ struct vxlan_dev {
struct hlist_node hlist;
struct net_device *dev;
__u32 vni; /* virtual network id */
- __be32 gaddr; /* multicast group */
- __be32 saddr; /* source address */
+ struct vxlan_addr gaddr; /* multicast group */
+ struct vxlan_addr saddr; /* source address */
unsigned int link; /* link to multicast over */
__u16 port_min; /* source port range */
__u16 port_max;
@@ -130,6 +146,59 @@ struct vxlan_dev {
#define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10
+static inline
+bool vxlan_addr_equal(const struct vxlan_addr *a, const struct vxlan_addr *b)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (a->family != b->family)
+ return false;
+ if (a->family == AF_INET6)
+ return ipv6_addr_equal(&a->sin6, &b->sin6);
+ else
+#endif
+ return a->sin == b->sin;
+}
+
+static inline bool vxlan_addr_any(const struct vxlan_addr *ipa)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipa->family == AF_INET6)
+ return ipv6_addr_any(&ipa->sin6);
+ else
+#endif
+ return ipa->sin == htonl(INADDR_ANY);
+}
+
+static int vxlan_nla_get_addr(struct vxlan_addr *ip, struct nlattr *nla)
+{
+ if (nla_len(nla) == sizeof(struct in6_addr)) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&ip->sin6, nla, sizeof(struct in6_addr));
+ ip->family = AF_INET6;
+ return 0;
+#else
+ return -EAFNOSUPPORT;
+#endif
+ } else if (nla_len(nla) == sizeof(__be32)) {
+ ip->sin = nla_get_be32(nla);
+ ip->family = AF_INET;
+ return 0;
+ } else {
+ return -EAFNOSUPPORT;
+ }
+}
+
+static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
+ const struct vxlan_addr *ip)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ip->family == AF_INET6)
+ return nla_put(skb, attr, sizeof(struct in6_addr), &ip->sin6);
+ else
+#endif
+ return nla_put_be32(skb, attr, ip->sin);
+}
+
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
@@ -176,7 +245,7 @@ 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;
@@ -188,7 +257,7 @@ 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 &&
@@ -220,7 +289,7 @@ 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 */
@@ -253,14 +322,14 @@ 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, struct 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);
@@ -315,14 +384,14 @@ 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, struct 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)
@@ -332,7 +401,7 @@ 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;
@@ -343,7 +412,7 @@ 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, struct vxlan_addr *ip,
__u16 state, __u16 flags,
__u32 port, __u32 vni, __u32 ifindex)
{
@@ -383,7 +452,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
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;
@@ -435,7 +504,7 @@ 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;
+ struct vxlan_addr ip;
u32 port, vni, ifindex;
int err;
@@ -448,10 +517,9 @@ 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))
@@ -481,7 +549,7 @@ 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);
spin_unlock_bh(&vxlan->hash_lock);
@@ -545,7 +613,7 @@ skip:
* and Tunnel endpoint.
*/
static void vxlan_snoop(struct net_device *dev,
- __be32 src_ip, const u8 *src_mac)
+ struct vxlan_addr *src_ip, const u8 *src_mac)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
@@ -554,7 +622,7 @@ 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())
@@ -562,7 +630,7 @@ static void vxlan_snoop(struct net_device *dev,
"%pM migrated from %pI4 to %pI4\n",
src_mac, &f->remote.remote_ip, &src_ip);
- f->remote.remote_ip = src_ip;
+ f->remote.remote_ip = *src_ip;
f->updated = jiffies;
} else {
/* learned new entry */
@@ -591,7 +659,7 @@ static bool vxlan_group_used(struct vxlan_net *vn,
if (!netif_running(vxlan->dev))
continue;
- if (vxlan->gaddr == this->gaddr)
+ if (vxlan_addr_equal(&vxlan->gaddr, &this->gaddr))
return true;
}
@@ -605,7 +673,7 @@ static int vxlan_join_group(struct net_device *dev)
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct sock *sk = vn->sock->sk;
struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->gaddr,
+ .imr_multiaddr.s_addr = vxlan->gaddr.sin,
.imr_ifindex = vxlan->link,
};
int err;
@@ -617,7 +685,12 @@ 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->gaddr.family == AF_INET6)
+ err = ipv6_sock_mc_join(sk, vxlan->link, &vxlan->gaddr.sin6);
+ else
+#endif
+ err = ip_mc_join_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
@@ -633,7 +706,7 @@ static int vxlan_leave_group(struct net_device *dev)
int err = 0;
struct sock *sk = vn->sock->sk;
struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->gaddr,
+ .imr_multiaddr.s_addr = vxlan->gaddr.sin,
.imr_ifindex = vxlan->link,
};
@@ -644,7 +717,12 @@ 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->gaddr.family == AF_INET6)
+ err = ipv6_sock_mc_drop(sk, vxlan->link, &vxlan->gaddr.sin6);
+ else
+#endif
+ err = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
@@ -654,12 +732,16 @@ 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;
+ struct vxlan_addr src_ip;
__u32 vni;
- int err;
+ int err = 0;
/* pop off outer UDP header */
__skb_pull(skb, sizeof(struct udphdr));
@@ -696,7 +778,13 @@ 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)
+ else
+ oip6 = ipv6_hdr(skb);
+#endif
+
skb->protocol = eth_type_trans(skb, vxlan->dev);
/* Ignore packet loops (and multicast echo) */
@@ -704,8 +792,19 @@ 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 = oip->saddr;
+ src_ip.family = AF_INET;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ if (oip6) {
+ src_ip.sin6 = oip6->saddr;
+ src_ip.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);
@@ -721,11 +820,24 @@ 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;
@@ -760,6 +872,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
u8 *arpptr, *sha;
__be32 sip, tip;
struct neighbour *n;
+ struct vxlan_addr ipa;
if (dev->flags & IFF_NOARP)
goto out;
@@ -801,7 +914,7 @@ 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;
@@ -819,8 +932,11 @@ 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 = tip;
+ ipa.family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ }
out:
consume_skb(skb);
return NETDEV_TX_OK;
@@ -842,6 +958,14 @@ 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) {
+ struct vxlan_addr ipa;
+ ipa.sin = pip->daddr;
+ ipa.family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ return false;
+ }
+
break;
default:
return false;
@@ -858,8 +982,8 @@ 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;
}
@@ -869,7 +993,8 @@ 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;
@@ -917,23 +1042,30 @@ 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;
+#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
unsigned int pkt_len = skb->len;
- __be32 dst;
- __u16 src_port, dst_port;
+ const struct 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) {
__skb_pull(skb, skb_network_offset(skb));
skb->ip_summed = CHECKSUM_NONE;
@@ -961,47 +1093,86 @@ 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->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)))
+ 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);
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = rdst->remote_ifindex;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.daddr = dst->sin;
+ fl4.saddr = vxlan->saddr.sin;
+
+ rt = ip_route_output_key(dev_net(dev), &fl4);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to %pI4\n", &dst->sin);
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
+
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n", &dst->sin);
+ ip_rt_put(rt);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+ ndst = &rt->dst;
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ const struct ipv6hdr *old_iph6;
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n", &dst);
- ip_rt_put(rt);
- dev->stats.collisions++;
- goto tx_error;
+ /* Need space for new headers (invalidates iph ptr) */
+ if (skb_cow_head(skb, VXLAN6_HEADROOM))
+ goto drop;
+
+ old_iph6 = ipv6_hdr(skb);
+ if (!ttl && ipv6_addr_is_multicast(&dst->sin6))
+ 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 = vxlan->link;
+ fl6.flowi6_tos = RT_TOS(tos);
+ fl6.daddr = dst->sin6;
+ fl6.saddr = vxlan->saddr.sin6;
+ fl6.flowi6_proto = skb->protocol;
+
+ if (ip6_dst_lookup(sk, &ndst, &fl6)) {
+ netdev_dbg(dev, "no route to %pI6\n", &dst->sin6);
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
+
+ if (ndst->dev == dev) {
+ netdev_dbg(dev, "circular route to %pI6\n", &dst->sin6);
+ dst_release(ndst);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+#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);
@@ -1017,27 +1188,55 @@ 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->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;
+ 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->ip_summed == CHECKSUM_PARTIAL) {
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ } else
+ uh->check = csum_ipv6_magic(&fl6.saddr, &fl6.daddr,
+ skb->len, IPPROTO_UDP,
+ csum_partial(uh, skb->len, 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 (dst->family == AF_INET)
+ iptunnel_xmit(skb, dev);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ ip6tunnel_xmit(skb, dev);
+#endif
return NETDEV_TX_OK;
drop:
@@ -1084,7 +1283,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
group.remote_next = 0;
rdst0 = &group;
- if (group.remote_ip == htonl(INADDR_ANY) &&
+ if (vxlan_addr_any(&group.remote_ip) &&
(vxlan->flags & VXLAN_F_L2MISS) &&
!is_multicast_ether_addr(eth->h_dest))
vxlan_fdb_miss(vxlan, eth->h_dest);
@@ -1162,7 +1361,7 @@ static int vxlan_open(struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev);
int err;
- if (vxlan->gaddr) {
+ if (!vxlan_addr_any(&vxlan->gaddr)) {
err = vxlan_join_group(dev);
if (err)
return err;
@@ -1196,7 +1395,7 @@ static int vxlan_stop(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- if (vxlan->gaddr)
+ if (!vxlan_addr_any(&vxlan->gaddr))
vxlan_leave_group(dev);
del_timer_sync(&vxlan->age_timer);
@@ -1246,7 +1445,10 @@ 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 (vxlan->gaddr.family == AF_INET)
+ dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+ else
+ dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = vxlan_free;
@@ -1283,8 +1485,10 @@ 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_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_VXLAN_GROUP6] = { .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 },
@@ -1326,6 +1530,17 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
pr_debug("group address is not IPv4 multicast\n");
return -EADDRNOTAVAIL;
}
+ } else if (data[IFLA_VXLAN_GROUP6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr gaddr;
+ nla_memcpy(&gaddr, data[IFLA_VXLAN_GROUP6], sizeof(gaddr));
+ if (!ipv6_addr_is_multicast(&gaddr)) {
+ pr_debug("group address is not IPv6 multicast\n");
+ return -EADDRNOTAVAIL;
+ }
+#else
+ return -EPFNOSUPPORT;
+#endif
}
if (data[IFLA_VXLAN_PORT_RANGE]) {
@@ -1371,11 +1586,31 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
}
vxlan->vni = vni;
- if (data[IFLA_VXLAN_GROUP])
- vxlan->gaddr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+ if (data[IFLA_VXLAN_GROUP]) {
+ vxlan->gaddr.sin = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+ vxlan->gaddr.family = AF_INET;
+ } else if (data[IFLA_VXLAN_GROUP6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&vxlan->gaddr.sin6, data[IFLA_VXLAN_GROUP6],
+ sizeof(struct in6_addr));
+ vxlan->gaddr.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 = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ vxlan->saddr.family = AF_INET;
+ } else if (data[IFLA_VXLAN_LOCAL6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+ nla_memcpy(&vxlan->saddr.sin6, data[IFLA_VXLAN_LOCAL6],
+ sizeof(struct in6_addr));
+ vxlan->saddr.family = AF_INET6;
+#else
+ return -EPFNOSUPPORT;
+#endif
+ }
if (data[IFLA_VXLAN_LINK] &&
(vxlan->link = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
@@ -1453,9 +1688,9 @@ 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_GROUP */
+ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{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 */
@@ -1480,14 +1715,34 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
if (nla_put_u32(skb, IFLA_VXLAN_ID, vxlan->vni))
goto nla_put_failure;
- if (vxlan->gaddr && nla_put_be32(skb, IFLA_VXLAN_GROUP, vxlan->gaddr))
- goto nla_put_failure;
+ if (!vxlan_addr_any(&vxlan->gaddr)) {
+ if (vxlan->gaddr.family == AF_INET) {
+ if (nla_put_be32(skb, IFLA_VXLAN_GROUP, vxlan->gaddr.sin))
+ goto nla_put_failure;
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (nla_put(skb, IFLA_VXLAN_GROUP6, sizeof(struct in6_addr),
+ &vxlan->gaddr.sin6))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (vxlan->link && nla_put_u32(skb, IFLA_VXLAN_LINK, vxlan->link))
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.family == AF_INET) {
+ if (nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr.sin))
+ goto nla_put_failure;
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr),
+ &vxlan->saddr.sin6))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
@@ -1526,38 +1781,82 @@ 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;
+ }
+ 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;
@@ -1566,6 +1865,9 @@ 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 c4edfe1..0eee00f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -308,6 +308,8 @@ enum {
IFLA_VXLAN_RSC,
IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS,
+ IFLA_VXLAN_GROUP6,
+ IFLA_VXLAN_LOCAL6,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists