Commit e4c7ed41 authored by Cong Wang's avatar Cong Wang Committed by David S. Miller

vxlan: add ipv6 support

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

Cc: David Stevens <dlstevens@us.ibm.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: default avatarCong Wang <amwang@redhat.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent caf92bc4
...@@ -6,9 +6,6 @@ ...@@ -6,9 +6,6 @@
* This program is free software; you can redistribute it and/or modify * This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as * it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation. * published by the Free Software Foundation.
*
* TODO
* - IPv6 (not in RFC)
*/ */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
...@@ -43,6 +40,11 @@ ...@@ -43,6 +40,11 @@
#include <net/net_namespace.h> #include <net/net_namespace.h>
#include <net/netns/generic.h> #include <net/netns/generic.h>
#include <net/vxlan.h> #include <net/vxlan.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#endif
#define VXLAN_VERSION "0.1" #define VXLAN_VERSION "0.1"
...@@ -59,6 +61,8 @@ ...@@ -59,6 +61,8 @@
#define VXLAN_VID_MASK (VXLAN_N_VID - 1) #define VXLAN_VID_MASK (VXLAN_N_VID - 1)
/* IP header + UDP + VXLAN + Ethernet header */ /* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14) #define VXLAN_HEADROOM (20 + 8 + 8 + 14)
/* IPv6 header + UDP + VXLAN + Ethernet header */
#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */ #define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
...@@ -92,8 +96,14 @@ struct vxlan_net { ...@@ -92,8 +96,14 @@ struct vxlan_net {
spinlock_t sock_lock; spinlock_t sock_lock;
}; };
union vxlan_addr {
struct sockaddr_in sin;
struct sockaddr_in6 sin6;
struct sockaddr sa;
};
struct vxlan_rdst { struct vxlan_rdst {
__be32 remote_ip; union vxlan_addr remote_ip;
__be16 remote_port; __be16 remote_port;
u32 remote_vni; u32 remote_vni;
u32 remote_ifindex; u32 remote_ifindex;
...@@ -120,7 +130,7 @@ struct vxlan_dev { ...@@ -120,7 +130,7 @@ struct vxlan_dev {
struct vxlan_sock *vn_sock; /* listening socket */ struct vxlan_sock *vn_sock; /* listening socket */
struct net_device *dev; struct net_device *dev;
struct vxlan_rdst default_dst; /* default destination */ struct vxlan_rdst default_dst; /* default destination */
__be32 saddr; /* source address */ union vxlan_addr saddr; /* source address */
__be16 dst_port; __be16 dst_port;
__u16 port_min; /* source port range */ __u16 port_min; /* source port range */
__u16 port_max; __u16 port_max;
...@@ -146,6 +156,7 @@ struct vxlan_dev { ...@@ -146,6 +156,7 @@ struct vxlan_dev {
#define VXLAN_F_RSC 0x04 #define VXLAN_F_RSC 0x04
#define VXLAN_F_L2MISS 0x08 #define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10 #define VXLAN_F_L3MISS 0x10
#define VXLAN_F_IPV6 0x20 /* internal flag */
/* salt for hash table */ /* salt for hash table */
static u32 vxlan_salt __read_mostly; static u32 vxlan_salt __read_mostly;
...@@ -153,6 +164,96 @@ static struct workqueue_struct *vxlan_wq; ...@@ -153,6 +164,96 @@ static struct workqueue_struct *vxlan_wq;
static void vxlan_sock_work(struct work_struct *work); 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;
}
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);
}
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));
}
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;
}
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
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);
}
#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;
}
static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
{
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));
}
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;
}
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
const union vxlan_addr *ip)
{
return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
}
#endif
/* Virtual Network hash table head */ /* Virtual Network hash table head */
static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id) static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
{ {
...@@ -239,7 +340,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, ...@@ -239,7 +340,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
if (type == RTM_GETNEIGH) { if (type == RTM_GETNEIGH) {
ndm->ndm_family = AF_INET; 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); send_eth = !is_zero_ether_addr(fdb->eth_addr);
} else } else
ndm->ndm_family = AF_BRIDGE; ndm->ndm_family = AF_BRIDGE;
...@@ -251,7 +352,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, ...@@ -251,7 +352,7 @@ 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)) if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure; 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; goto nla_put_failure;
if (rdst->remote_port && rdst->remote_port != vxlan->dst_port && if (rdst->remote_port && rdst->remote_port != vxlan->dst_port &&
...@@ -283,7 +384,7 @@ static inline size_t vxlan_nlmsg_size(void) ...@@ -283,7 +384,7 @@ static inline size_t vxlan_nlmsg_size(void)
{ {
return NLMSG_ALIGN(sizeof(struct ndmsg)) return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + 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(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */
+ nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */
+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
...@@ -317,14 +418,14 @@ static void vxlan_fdb_notify(struct vxlan_dev *vxlan, ...@@ -317,14 +418,14 @@ static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); 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_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb f = { struct vxlan_fdb f = {
.state = NUD_STALE, .state = NUD_STALE,
}; };
struct vxlan_rdst remote = { struct vxlan_rdst remote = {
.remote_ip = ipa, /* goes to NDA_DST */ .remote_ip = *ipa, /* goes to NDA_DST */
.remote_vni = VXLAN_N_VID, .remote_vni = VXLAN_N_VID,
}; };
...@@ -397,13 +498,13 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, ...@@ -397,13 +498,13 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
/* caller should hold vxlan->hash_lock */ /* caller should hold vxlan->hash_lock */
static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
__be32 ip, __be16 port, union vxlan_addr *ip, __be16 port,
__u32 vni, __u32 ifindex) __u32 vni, __u32 ifindex)
{ {
struct vxlan_rdst *rd; struct vxlan_rdst *rd;
list_for_each_entry(rd, &f->remotes, list) { list_for_each_entry(rd, &f->remotes, list) {
if (rd->remote_ip == ip && if (vxlan_addr_equal(&rd->remote_ip, ip) &&
rd->remote_port == port && rd->remote_port == port &&
rd->remote_vni == vni && rd->remote_vni == vni &&
rd->remote_ifindex == ifindex) rd->remote_ifindex == ifindex)
...@@ -415,7 +516,7 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, ...@@ -415,7 +516,7 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
/* Replace destination of unicast mac */ /* Replace destination of unicast mac */
static int vxlan_fdb_replace(struct vxlan_fdb *f, static int vxlan_fdb_replace(struct vxlan_fdb *f,
__be32 ip, __be16 port, __u32 vni, __u32 ifindex) union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
{ {
struct vxlan_rdst *rd; struct vxlan_rdst *rd;
...@@ -426,7 +527,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, ...@@ -426,7 +527,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,
rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
if (!rd) if (!rd)
return 0; return 0;
rd->remote_ip = ip; rd->remote_ip = *ip;
rd->remote_port = port; rd->remote_port = port;
rd->remote_vni = vni; rd->remote_vni = vni;
rd->remote_ifindex = ifindex; rd->remote_ifindex = ifindex;
...@@ -435,7 +536,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, ...@@ -435,7 +536,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,
/* Add/update destinations for multicast */ /* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f, static int vxlan_fdb_append(struct vxlan_fdb *f,
__be32 ip, __be16 port, __u32 vni, __u32 ifindex) union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
{ {
struct vxlan_rdst *rd; struct vxlan_rdst *rd;
...@@ -446,7 +547,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, ...@@ -446,7 +547,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
rd = kmalloc(sizeof(*rd), GFP_ATOMIC); rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL) if (rd == NULL)
return -ENOBUFS; return -ENOBUFS;
rd->remote_ip = ip; rd->remote_ip = *ip;
rd->remote_port = port; rd->remote_port = port;
rd->remote_vni = vni; rd->remote_vni = vni;
rd->remote_ifindex = ifindex; rd->remote_ifindex = ifindex;
...@@ -458,7 +559,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, ...@@ -458,7 +559,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
/* Add new entry to forwarding table -- assumes lock held */ /* Add new entry to forwarding table -- assumes lock held */
static int vxlan_fdb_create(struct vxlan_dev *vxlan, 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, __u16 state, __u16 flags,
__be16 port, __u32 vni, __u32 ifindex, __be16 port, __u32 vni, __u32 ifindex,
__u8 ndm_flags) __u8 ndm_flags)
...@@ -517,7 +618,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, ...@@ -517,7 +618,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
(is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
return -EOPNOTSUPP; return -EOPNOTSUPP;
netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip); netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
f = kmalloc(sizeof(*f), GFP_ATOMIC); f = kmalloc(sizeof(*f), GFP_ATOMIC);
if (!f) if (!f)
return -ENOMEM; return -ENOMEM;
...@@ -565,17 +666,26 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) ...@@ -565,17 +666,26 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
} }
static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
__be32 *ip, __be16 *port, u32 *vni, u32 *ifindex) union vxlan_addr *ip, __be16 *port, u32 *vni, u32 *ifindex)
{ {
struct net *net = dev_net(vxlan->dev); struct net *net = dev_net(vxlan->dev);
int err;
if (tb[NDA_DST]) { if (tb[NDA_DST]) {
if (nla_len(tb[NDA_DST]) != sizeof(__be32)) err = vxlan_nla_get_addr(ip, tb[NDA_DST]);
return -EAFNOSUPPORT; if (err)
return err;
*ip = nla_get_be32(tb[NDA_DST]); } else {
union vxlan_addr *remote = &vxlan->default_dst.remote_ip;
if (remote->sa.sa_family == AF_INET) {
ip->sin.sin_addr.s_addr = htonl(INADDR_ANY);
ip->sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
} else { } else {
*ip = htonl(INADDR_ANY); ip->sin6.sin6_addr = in6addr_any;
ip->sa.sa_family = AF_INET6;
#endif
}
} }
if (tb[NDA_PORT]) { if (tb[NDA_PORT]) {
...@@ -618,7 +728,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], ...@@ -618,7 +728,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
{ {
struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_dev *vxlan = netdev_priv(dev);
/* struct net *net = dev_net(vxlan->dev); */ /* struct net *net = dev_net(vxlan->dev); */
__be32 ip; union vxlan_addr ip;
__be16 port; __be16 port;
u32 vni, ifindex; u32 vni, ifindex;
int err; int err;
...@@ -637,7 +747,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], ...@@ -637,7 +747,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
return err; return err;
spin_lock_bh(&vxlan->hash_lock); spin_lock_bh(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags, err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
port, vni, ifindex, ndm->ndm_flags); port, vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock); spin_unlock_bh(&vxlan->hash_lock);
...@@ -652,7 +762,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], ...@@ -652,7 +762,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f; struct vxlan_fdb *f;
struct vxlan_rdst *rd = NULL; struct vxlan_rdst *rd = NULL;
__be32 ip; union vxlan_addr ip;
__be16 port; __be16 port;
u32 vni, ifindex; u32 vni, ifindex;
int err; int err;
...@@ -668,8 +778,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], ...@@ -668,8 +778,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
if (!f) if (!f)
goto out; goto out;
if (ip != htonl(INADDR_ANY)) { if (!vxlan_addr_any(&ip)) {
rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex);
if (!rd) if (!rd)
goto out; goto out;
} }
...@@ -732,7 +842,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, ...@@ -732,7 +842,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
* Return true if packet is bogus and should be droppped. * Return true if packet is bogus and should be droppped.
*/ */
static bool vxlan_snoop(struct net_device *dev, static bool 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_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f; struct vxlan_fdb *f;
...@@ -741,7 +851,7 @@ static bool vxlan_snoop(struct net_device *dev, ...@@ -741,7 +851,7 @@ static bool vxlan_snoop(struct net_device *dev,
if (likely(f)) { if (likely(f)) {
struct vxlan_rdst *rdst = first_remote_rcu(f); struct vxlan_rdst *rdst = first_remote_rcu(f);
if (likely(rdst->remote_ip == src_ip)) if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip)))
return false; return false;
/* Don't migrate static entries, drop packets */ /* Don't migrate static entries, drop packets */
...@@ -750,10 +860,10 @@ static bool vxlan_snoop(struct net_device *dev, ...@@ -750,10 +860,10 @@ static bool vxlan_snoop(struct net_device *dev,
if (net_ratelimit()) if (net_ratelimit())
netdev_info(dev, netdev_info(dev,
"%pM migrated from %pI4 to %pI4\n", "%pM migrated from %pIS to %pIS\n",
src_mac, &rdst->remote_ip, &src_ip); src_mac, &rdst->remote_ip, &src_ip);
rdst->remote_ip = src_ip; rdst->remote_ip = *src_ip;
f->updated = jiffies; f->updated = jiffies;
vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH); vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
} else { } else {
...@@ -775,7 +885,7 @@ static bool vxlan_snoop(struct net_device *dev, ...@@ -775,7 +885,7 @@ static bool vxlan_snoop(struct net_device *dev,
} }
/* See if multicast group is already in use by other ID */ /* See if multicast group is already in use by other ID */
static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip) static bool vxlan_group_used(struct vxlan_net *vn, union vxlan_addr *remote_ip)
{ {
struct vxlan_dev *vxlan; struct vxlan_dev *vxlan;
...@@ -783,7 +893,8 @@ static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip) ...@@ -783,7 +893,8 @@ static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
if (!netif_running(vxlan->dev)) if (!netif_running(vxlan->dev))
continue; continue;
if (vxlan->default_dst.remote_ip == remote_ip) if (vxlan_addr_equal(&vxlan->default_dst.remote_ip,
remote_ip))
return true; return true;
} }
...@@ -819,13 +930,23 @@ static void vxlan_igmp_join(struct work_struct *work) ...@@ -819,13 +930,23 @@ static void vxlan_igmp_join(struct work_struct *work)
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join); struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
struct vxlan_sock *vs = vxlan->vn_sock; struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk; struct sock *sk = vs->sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
struct ip_mreqn mreq = { 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, .imr_ifindex = ifindex,
}; };
lock_sock(sk);
ip_mc_join_group(sk, &mreq); ip_mc_join_group(sk, &mreq);
#if IS_ENABLED(CONFIG_IPV6)
} else {
ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
&ip->sin6.sin6_addr);
#endif
}
release_sock(sk); release_sock(sk);
vxlan_sock_release(vs); vxlan_sock_release(vs);
...@@ -838,13 +959,24 @@ static void vxlan_igmp_leave(struct work_struct *work) ...@@ -838,13 +959,24 @@ static void vxlan_igmp_leave(struct work_struct *work)
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave); struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
struct vxlan_sock *vs = vxlan->vn_sock; struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk; struct sock *sk = vs->sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
struct ip_mreqn mreq = { 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, .imr_ifindex = ifindex,
}; };
lock_sock(sk);
ip_mc_leave_group(sk, &mreq); ip_mc_leave_group(sk, &mreq);
#if IS_ENABLED(CONFIG_IPV6)
} else {
ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
&ip->sin6.sin6_addr);
#endif
}
release_sock(sk); release_sock(sk);
vxlan_sock_release(vs); vxlan_sock_release(vs);
...@@ -896,11 +1028,14 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) ...@@ -896,11 +1028,14 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
static void vxlan_rcv(struct vxlan_sock *vs, static void vxlan_rcv(struct vxlan_sock *vs,
struct sk_buff *skb, __be32 vx_vni) struct sk_buff *skb, __be32 vx_vni)
{ {
struct iphdr *oip; struct iphdr *oip = NULL;
struct ipv6hdr *oip6 = NULL;
struct vxlan_dev *vxlan; struct vxlan_dev *vxlan;
struct pcpu_tstats *stats; struct pcpu_tstats *stats;
union vxlan_addr saddr;
__u32 vni; __u32 vni;
int err; int err = 0;
union vxlan_addr *remote_ip;
vni = ntohl(vx_vni) >> 8; vni = ntohl(vx_vni) >> 8;
/* Is this VNI defined? */ /* Is this VNI defined? */
...@@ -908,6 +1043,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, ...@@ -908,6 +1043,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
if (!vxlan) if (!vxlan)
goto drop; goto drop;
remote_ip = &vxlan->default_dst.remote_ip;
skb_reset_mac_header(skb); skb_reset_mac_header(skb);
skb->protocol = eth_type_trans(skb, vxlan->dev); skb->protocol = eth_type_trans(skb, vxlan->dev);
...@@ -917,9 +1053,20 @@ static void vxlan_rcv(struct vxlan_sock *vs, ...@@ -917,9 +1053,20 @@ static void vxlan_rcv(struct vxlan_sock *vs,
goto drop; goto drop;
/* Re-examine inner Ethernet packet */ /* Re-examine inner Ethernet packet */
if (remote_ip->sa.sa_family == AF_INET) {
oip = ip_hdr(skb); oip = ip_hdr(skb);
saddr.sin.sin_addr.s_addr = oip->saddr;
saddr.sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
} else {
oip6 = ipv6_hdr(skb);
saddr.sin6.sin6_addr = oip6->saddr;
saddr.sa.sa_family = AF_INET6;
#endif
}
if ((vxlan->flags & VXLAN_F_LEARN) && if ((vxlan->flags & VXLAN_F_LEARN) &&
vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source)) vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
goto drop; goto drop;
skb_reset_network_header(skb); skb_reset_network_header(skb);
...@@ -935,11 +1082,20 @@ static void vxlan_rcv(struct vxlan_sock *vs, ...@@ -935,11 +1082,20 @@ static void vxlan_rcv(struct vxlan_sock *vs,
skb->encapsulation = 0; skb->encapsulation = 0;
if (oip6)
err = IP6_ECN_decapsulate(oip6, skb);
if (oip)
err = IP_ECN_decapsulate(oip, skb); err = IP_ECN_decapsulate(oip, skb);
if (unlikely(err)) { if (unlikely(err)) {
if (log_ecn_error) if (log_ecn_error) {
if (oip6)
net_info_ratelimited("non-ECT from %pI6\n",
&oip6->saddr);
if (oip)
net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
&oip->saddr, oip->tos); &oip->saddr, oip->tos);
}
if (err > 1) { if (err > 1) {
++vxlan->dev->stats.rx_frame_errors; ++vxlan->dev->stats.rx_frame_errors;
++vxlan->dev->stats.rx_errors; ++vxlan->dev->stats.rx_errors;
...@@ -1009,7 +1165,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) ...@@ -1009,7 +1165,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
} }
f = vxlan_find_mac(vxlan, n->ha); f = vxlan_find_mac(vxlan, n->ha);
if (f && first_remote_rcu(f)->remote_ip == htonl(INADDR_ANY)) { if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
/* bridge-local neighbor */ /* bridge-local neighbor */
neigh_release(n); neigh_release(n);
goto out; goto out;
...@@ -1027,8 +1183,14 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) ...@@ -1027,8 +1183,14 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
if (netif_rx_ni(reply) == NET_RX_DROP) if (netif_rx_ni(reply) == NET_RX_DROP)
dev->stats.rx_dropped++; dev->stats.rx_dropped++;
} else if (vxlan->flags & VXLAN_F_L3MISS) } else if (vxlan->flags & VXLAN_F_L3MISS) {
vxlan_ip_miss(dev, tip); union vxlan_addr ipa = {
.sin.sin_addr.s_addr = tip,
.sa.sa_family = AF_INET,
};
vxlan_ip_miss(dev, &ipa);
}
out: out:
consume_skb(skb); consume_skb(skb);
return NETDEV_TX_OK; return NETDEV_TX_OK;
...@@ -1050,6 +1212,16 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) ...@@ -1050,6 +1212,16 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false; return false;
pip = ip_hdr(skb); pip = ip_hdr(skb);
n = neigh_lookup(&arp_tbl, &pip->daddr, dev); n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
if (!n && (vxlan->flags & VXLAN_F_L3MISS)) {
union vxlan_addr ipa = {
.sin.sin_addr.s_addr = pip->daddr,
.sa.sa_family = AF_INET,
};
vxlan_ip_miss(dev, &ipa);
return false;
}
break; break;
default: default:
return false; return false;
...@@ -1066,8 +1238,8 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) ...@@ -1066,8 +1238,8 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
} }
neigh_release(n); neigh_release(n);
return diff; return diff;
} else if (vxlan->flags & VXLAN_F_L3MISS) }
vxlan_ip_miss(dev, pip->daddr);
return false; return false;
} }
...@@ -1118,6 +1290,102 @@ static int handle_offloads(struct sk_buff *skb) ...@@ -1118,6 +1290,102 @@ static int handle_offloads(struct sk_buff *skb)
return 0; return 0;
} }
#if IS_ENABLED(CONFIG_IPV6)
static int vxlan6_xmit_skb(struct net *net, struct vxlan_sock *vs,
struct dst_entry *dst, 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, __be32 vni)
{
struct ipv6hdr *ip6h;
struct vxlanhdr *vxh;
struct udphdr *uh;
int min_headroom;
int err;
if (!skb->encapsulation) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
+ VXLAN_HLEN + sizeof(struct ipv6hdr)
+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
/* Need space for new headers (invalidates iph ptr) */
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
return err;
if (vlan_tx_tag_present(skb)) {
if (WARN_ON(!__vlan_put_tag(skb,
skb->vlan_proto,
vlan_tx_tag_get(skb))))
return -ENOMEM;
skb->vlan_tci = 0;
}
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_FLAGS);
vxh->vx_vni = vni;
__skb_push(skb, sizeof(*uh));
skb_reset_transport_header(skb);
uh = udp_hdr(skb);
uh->dest = dst_port;
uh->source = src_port;
uh->len = htons(skb->len);
uh->check = 0;
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, dst);
if (!skb_is_gso(skb) && !(dst->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(saddr, 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(saddr, 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 = prio;
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;
ip6h->daddr = *daddr;
ip6h->saddr = *saddr;
vxlan_set_owner(vs->sock->sk, skb);
err = handle_offloads(skb);
if (err)
return err;
ip6tunnel_xmit(skb, dev);
return 0;
}
#endif
int vxlan_xmit_skb(struct net *net, struct vxlan_sock *vs, int vxlan_xmit_skb(struct net *net, struct vxlan_sock *vs,
struct rtable *rt, struct sk_buff *skb, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
...@@ -1182,15 +1450,26 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, ...@@ -1182,15 +1450,26 @@ 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 *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
union vxlan_addr loopback;
union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
skb->pkt_type = PACKET_HOST; skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0; skb->encapsulation = 0;
skb->dev = dst_vxlan->dev; skb->dev = dst_vxlan->dev;
__skb_pull(skb, skb_network_offset(skb)); __skb_pull(skb, skb_network_offset(skb));
if (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) if (dst_vxlan->flags & VXLAN_F_LEARN)
vxlan_snoop(skb->dev, htonl(INADDR_LOOPBACK), vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source);
eth_hdr(skb)->h_source);
u64_stats_update_begin(&tx_stats->syncp); u64_stats_update_begin(&tx_stats->syncp);
tx_stats->tx_packets++; tx_stats->tx_packets++;
...@@ -1211,11 +1490,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ...@@ -1211,11 +1490,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_rdst *rdst, bool did_rsc) struct vxlan_rdst *rdst, bool did_rsc)
{ {
struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_dev *vxlan = netdev_priv(dev);
struct rtable *rt; struct rtable *rt = NULL;
const struct iphdr *old_iph; const struct iphdr *old_iph;
struct flowi4 fl4; struct flowi4 fl4;
__be32 dst; union vxlan_addr *dst;
__be16 src_port, dst_port; __be16 src_port = 0, dst_port;
u32 vni; u32 vni;
__be16 df = 0; __be16 df = 0;
__u8 tos, ttl; __u8 tos, ttl;
...@@ -1223,9 +1502,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ...@@ -1223,9 +1502,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
vni = rdst->remote_vni; vni = rdst->remote_vni;
dst = rdst->remote_ip; dst = &rdst->remote_ip;
if (!dst) { if (vxlan_addr_any(dst)) {
if (did_rsc) { if (did_rsc) {
/* short-circuited back to local bridge */ /* short-circuited back to local bridge */
vxlan_encap_bypass(skb, vxlan, vxlan); vxlan_encap_bypass(skb, vxlan, vxlan);
...@@ -1237,7 +1516,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ...@@ -1237,7 +1516,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
old_iph = ip_hdr(skb); old_iph = ip_hdr(skb);
ttl = vxlan->ttl; ttl = vxlan->ttl;
if (!ttl && IN_MULTICAST(ntohl(dst))) if (!ttl && vxlan_addr_multicast(dst))
ttl = 1; ttl = 1;
tos = vxlan->tos; tos = vxlan->tos;
...@@ -1246,23 +1525,26 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ...@@ -1246,23 +1525,26 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
src_port = vxlan_src_port(vxlan->port_min, vxlan->port_max, skb); src_port = vxlan_src_port(vxlan->port_min, vxlan->port_max, skb);
if (dst->sa.sa_family == AF_INET) {
memset(&fl4, 0, sizeof(fl4)); memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_oif = rdst->remote_ifindex; fl4.flowi4_oif = rdst->remote_ifindex;
fl4.flowi4_tos = RT_TOS(tos); fl4.flowi4_tos = RT_TOS(tos);
fl4.daddr = dst; fl4.daddr = dst->sin.sin_addr.s_addr;
fl4.saddr = vxlan->saddr; fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
rt = ip_route_output_key(dev_net(dev), &fl4); rt = ip_route_output_key(dev_net(dev), &fl4);
if (IS_ERR(rt)) { if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &dst); netdev_dbg(dev, "no route to %pI4\n",
&dst->sin.sin_addr.s_addr);
dev->stats.tx_carrier_errors++; dev->stats.tx_carrier_errors++;
goto tx_error; goto tx_error;
} }
if (rt->dst.dev == dev) { if (rt->dst.dev == dev) {
netdev_dbg(dev, "circular route to %pI4\n", &dst); netdev_dbg(dev, "circular route to %pI4\n",
&dst->sin.sin_addr.s_addr);
dev->stats.collisions++; dev->stats.collisions++;
goto rt_tx_error; goto tx_error;
} }
/* Bypass encapsulation if the destination is local */ /* Bypass encapsulation if the destination is local */
...@@ -1282,12 +1564,62 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ...@@ -1282,12 +1564,62 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
err = vxlan_xmit_skb(dev_net(dev), vxlan->vn_sock, rt, skb, err = vxlan_xmit_skb(dev_net(dev), vxlan->vn_sock, rt, skb,
fl4.saddr, dst, tos, ttl, df, fl4.saddr, dst->sin.sin_addr.s_addr,
src_port, dst_port, htonl(vni << 8)); tos, ttl, df, src_port, dst_port,
htonl(vni << 8));
if (err < 0) if (err < 0)
goto rt_tx_error; goto rt_tx_error;
iptunnel_xmit_stats(err, &dev->stats, dev->tstats); 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;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = rdst->remote_ifindex;
fl6.daddr = dst->sin6.sin6_addr;
fl6.saddr = vxlan->saddr.sin6.sin6_addr;
fl6.flowi6_proto = skb->protocol;
if (ipv6_stub->ipv6_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, dst_port);
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
return;
}
ttl = ttl ? : ip6_dst_hoplimit(ndst);
err = vxlan6_xmit_skb(dev_net(dev), vxlan->vn_sock, ndst, skb,
dev, &fl6.saddr, &fl6.daddr, 0, ttl,
src_port, dst_port, htonl(vni << 8));
#endif
}
return; return;
...@@ -1464,8 +1796,8 @@ static int vxlan_open(struct net_device *dev) ...@@ -1464,8 +1796,8 @@ static int vxlan_open(struct net_device *dev)
if (!vs) if (!vs)
return -ENOTCONN; return -ENOTCONN;
if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) && if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
vxlan_group_used(vn, vxlan->default_dst.remote_ip)) { vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs); vxlan_sock_hold(vs);
dev_hold(dev); dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_join); queue_work(vxlan_wq, &vxlan->igmp_join);
...@@ -1503,8 +1835,8 @@ static int vxlan_stop(struct net_device *dev) ...@@ -1503,8 +1835,8 @@ static int vxlan_stop(struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_sock *vs = vxlan->vn_sock; struct vxlan_sock *vs = vxlan->vn_sock;
if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) && if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) { ! vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs); vxlan_sock_hold(vs);
dev_hold(dev); dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_leave); queue_work(vxlan_wq, &vxlan->igmp_leave);
...@@ -1552,6 +1884,9 @@ static void vxlan_setup(struct net_device *dev) ...@@ -1552,6 +1884,9 @@ static void vxlan_setup(struct net_device *dev)
eth_hw_addr_random(dev); eth_hw_addr_random(dev);
ether_setup(dev); ether_setup(dev);
if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
else
dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM; dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops; dev->netdev_ops = &vxlan_netdev_ops;
...@@ -1597,8 +1932,10 @@ static void vxlan_setup(struct net_device *dev) ...@@ -1597,8 +1932,10 @@ static void vxlan_setup(struct net_device *dev)
static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
[IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_ID] = { .type = NLA_U32 },
[IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, [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_LINK] = { .type = NLA_U32 },
[IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, [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_TOS] = { .type = NLA_U8 },
[IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 },
[IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 },
...@@ -1669,58 +2006,132 @@ static void vxlan_del_work(struct work_struct *work) ...@@ -1669,58 +2006,132 @@ static void vxlan_del_work(struct work_struct *work)
kfree_rcu(vs, rcu); kfree_rcu(vs, rcu);
} }
static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, #if IS_ENABLED(CONFIG_IPV6)
vxlan_rcv_t *rcv, void *data) /* Create UDP socket for encapsulation receive. AF_INET6 socket
* could be used for both IPv4 and IPv6 communications, but
* users may set bindv6only=1.
*/
static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
{
struct sock *sk;
struct socket *sock;
struct sockaddr_in6 vxlan_addr = {
.sin6_family = AF_INET6,
.sin6_port = port,
};
int rc, val = 1;
rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (rc < 0) {
pr_debug("UDPv6 socket create failed\n");
return rc;
}
/* Put in proper namespace */
sk = sock->sk;
sk_change_net(sk, net);
kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
(char *)&val, sizeof(val));
rc = kernel_bind(sock, (struct sockaddr *)&vxlan_addr,
sizeof(struct sockaddr_in6));
if (rc < 0) {
pr_debug("bind for UDPv6 socket %pI6:%u (%d)\n",
&vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc);
sk_release_kernel(sk);
return rc;
}
/* At this point, IPv6 module should have been loaded in
* sock_create_kern().
*/
BUG_ON(!ipv6_stub);
*psock = sock;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
return 0;
}
#else
static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
{
return -EPFNOSUPPORT;
}
#endif
static int create_v4_sock(struct net *net, __be16 port, struct socket **psock)
{ {
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
struct sock *sk; struct sock *sk;
struct socket *sock;
struct sockaddr_in vxlan_addr = { struct sockaddr_in vxlan_addr = {
.sin_family = AF_INET, .sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY), .sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = port, .sin_port = port,
}; };
int rc; int rc;
unsigned int h;
vs = kmalloc(sizeof(*vs), GFP_KERNEL);
if (!vs) {
pr_debug("memory alocation failure\n");
return ERR_PTR(-ENOMEM);
}
for (h = 0; h < VNI_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&vs->vni_list[h]);
INIT_WORK(&vs->del_work, vxlan_del_work);
/* Create UDP socket for encapsulation receive. */ /* Create UDP socket for encapsulation receive. */
rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vs->sock); rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (rc < 0) { if (rc < 0) {
pr_debug("UDP socket create failed\n"); pr_debug("UDP socket create failed\n");
kfree(vs); return rc;
return ERR_PTR(rc);
} }
/* Put in proper namespace */ /* Put in proper namespace */
sk = vs->sock->sk; sk = sock->sk;
sk_change_net(sk, net); sk_change_net(sk, net);
rc = kernel_bind(vs->sock, (struct sockaddr *) &vxlan_addr, rc = kernel_bind(sock, (struct sockaddr *) &vxlan_addr,
sizeof(vxlan_addr)); sizeof(vxlan_addr));
if (rc < 0) { if (rc < 0) {
pr_debug("bind for UDP socket %pI4:%u (%d)\n", pr_debug("bind for UDP socket %pI4:%u (%d)\n",
&vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc); &vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
sk_release_kernel(sk); sk_release_kernel(sk);
return rc;
}
*psock = sock;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
return 0;
}
/* Create new listen socket if needed */
static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data, bool ipv6)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
struct socket *sock;
struct sock *sk;
int rc = 0;
unsigned int h;
vs = kmalloc(sizeof(*vs), GFP_KERNEL);
if (!vs)
return ERR_PTR(-ENOMEM);
for (h = 0; h < VNI_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&vs->vni_list[h]);
INIT_WORK(&vs->del_work, vxlan_del_work);
if (ipv6)
rc = create_v6_sock(net, port, &sock);
else
rc = create_v4_sock(net, port, &sock);
if (rc < 0) {
kfree(vs); kfree(vs);
return ERR_PTR(rc); return ERR_PTR(rc);
} }
vs->sock = sock;
sk = sock->sk;
atomic_set(&vs->refcnt, 1); atomic_set(&vs->refcnt, 1);
vs->rcv = rcv; vs->rcv = rcv;
vs->data = data; vs->data = data;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
spin_lock(&vn->sock_lock); spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
spin_unlock(&vn->sock_lock); spin_unlock(&vn->sock_lock);
...@@ -1728,18 +2139,24 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, ...@@ -1728,18 +2139,24 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
/* Mark socket as an encapsulation socket. */ /* Mark socket as an encapsulation socket. */
udp_sk(sk)->encap_type = 1; udp_sk(sk)->encap_type = 1;
udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv; udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6)
ipv6_stub->udpv6_encap_enable();
else
#endif
udp_encap_enable(); udp_encap_enable();
return vs; return vs;
} }
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data, vxlan_rcv_t *rcv, void *data,
bool no_share) bool no_share, bool ipv6)
{ {
struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs; struct vxlan_sock *vs;
vs = vxlan_socket_create(net, port, rcv, data); vs = vxlan_socket_create(net, port, rcv, data, ipv6);
if (!IS_ERR(vs)) if (!IS_ERR(vs))
return vs; return vs;
...@@ -1772,7 +2189,7 @@ static void vxlan_sock_work(struct work_struct *work) ...@@ -1772,7 +2189,7 @@ static void vxlan_sock_work(struct work_struct *work)
__be16 port = vxlan->dst_port; __be16 port = vxlan->dst_port;
struct vxlan_sock *nvs; struct vxlan_sock *nvs;
nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false); nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags & VXLAN_F_IPV6);
spin_lock(&vn->sock_lock); spin_lock(&vn->sock_lock);
if (!IS_ERR(nvs)) if (!IS_ERR(nvs))
vxlan_vs_add_dev(nvs, vxlan); vxlan_vs_add_dev(nvs, vxlan);
...@@ -1789,6 +2206,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, ...@@ -1789,6 +2206,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst *dst = &vxlan->default_dst;
__u32 vni; __u32 vni;
int err; int err;
bool use_ipv6 = false;
if (!data[IFLA_VXLAN_ID]) if (!data[IFLA_VXLAN_ID])
return -EINVAL; return -EINVAL;
...@@ -1796,11 +2214,32 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, ...@@ -1796,11 +2214,32 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
vni = nla_get_u32(data[IFLA_VXLAN_ID]); vni = nla_get_u32(data[IFLA_VXLAN_ID]);
dst->remote_vni = vni; dst->remote_vni = vni;
if (data[IFLA_VXLAN_GROUP]) if (data[IFLA_VXLAN_GROUP]) {
dst->remote_ip = nla_get_be32(data[IFLA_VXLAN_GROUP]); dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
dst->remote_ip.sa.sa_family = AF_INET;
} 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.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.sa.sa_family = AF_INET;
} else if (data[IFLA_VXLAN_LOCAL6]) {
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
if (data[IFLA_VXLAN_LOCAL]) /* TODO: respect scope id */
vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]); nla_memcpy(&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6],
sizeof(struct in6_addr));
vxlan->saddr.sa.sa_family = AF_INET6;
use_ipv6 = true;
}
if (data[IFLA_VXLAN_LINK] && if (data[IFLA_VXLAN_LINK] &&
(dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) { (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
...@@ -1812,12 +2251,23 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, ...@@ -1812,12 +2251,23 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
return -ENODEV; return -ENODEV;
} }
#if IS_ENABLED(CONFIG_IPV6)
if (use_ipv6) {
struct inet6_dev *idev = __in6_dev_get(lowerdev);
if (idev && idev->cnf.disable_ipv6) {
pr_info("IPv6 is disabled via sysctl\n");
return -EPERM;
}
vxlan->flags |= VXLAN_F_IPV6;
}
#endif
if (!tb[IFLA_MTU]) if (!tb[IFLA_MTU])
dev->mtu = lowerdev->mtu - VXLAN_HEADROOM; dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
/* update header length based on lower device */ /* update header length based on lower device */
dev->hard_header_len = lowerdev->hard_header_len + dev->hard_header_len = lowerdev->hard_header_len +
VXLAN_HEADROOM; (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
} }
if (data[IFLA_VXLAN_TOS]) if (data[IFLA_VXLAN_TOS])
...@@ -1868,7 +2318,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, ...@@ -1868,7 +2318,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
/* create an fdb entry for default destination */ /* create an fdb entry for default destination */
err = vxlan_fdb_create(vxlan, all_zeros_mac, err = vxlan_fdb_create(vxlan, all_zeros_mac,
vxlan->default_dst.remote_ip, &vxlan->default_dst.remote_ip,
NUD_REACHABLE|NUD_PERMANENT, NUD_REACHABLE|NUD_PERMANENT,
NLM_F_EXCL|NLM_F_CREATE, NLM_F_EXCL|NLM_F_CREATE,
vxlan->dst_port, vxlan->default_dst.remote_vni, vxlan->dst_port, vxlan->default_dst.remote_vni,
...@@ -1905,9 +2355,9 @@ static size_t vxlan_get_size(const struct net_device *dev) ...@@ -1905,9 +2355,9 @@ static size_t vxlan_get_size(const struct net_device *dev)
{ {
return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ 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(__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_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
...@@ -1934,14 +2384,36 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) ...@@ -1934,14 +2384,36 @@ 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)) if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni))
goto nla_put_failure; goto nla_put_failure;
if (dst->remote_ip && nla_put_be32(skb, IFLA_VXLAN_GROUP, dst->remote_ip)) 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))
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))
goto nla_put_failure; goto nla_put_failure;
#endif
}
}
if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex))
goto nla_put_failure; goto nla_put_failure;
if (vxlan->saddr && nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr)) 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;
#if IS_ENABLED(CONFIG_IPV6)
} else {
if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr),
&vxlan->saddr.sin6.sin6_addr))
goto nla_put_failure; goto nla_put_failure;
#endif
}
}
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
......
...@@ -25,7 +25,7 @@ struct vxlan_sock { ...@@ -25,7 +25,7 @@ struct vxlan_sock {
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data, vxlan_rcv_t *rcv, void *data,
bool no_share); bool no_share, bool ipv6);
void vxlan_sock_release(struct vxlan_sock *vs); void vxlan_sock_release(struct vxlan_sock *vs);
......
...@@ -314,6 +314,8 @@ enum { ...@@ -314,6 +314,8 @@ enum {
IFLA_VXLAN_L2MISS, IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS, IFLA_VXLAN_L3MISS,
IFLA_VXLAN_PORT, /* destination port */ IFLA_VXLAN_PORT, /* destination port */
IFLA_VXLAN_GROUP6,
IFLA_VXLAN_LOCAL6,
__IFLA_VXLAN_MAX __IFLA_VXLAN_MAX
}; };
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
......
...@@ -123,7 +123,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) ...@@ -123,7 +123,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
vxlan_port = vxlan_vport(vport); vxlan_port = vxlan_vport(vport);
strncpy(vxlan_port->name, parms->name, IFNAMSIZ); strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true); vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, false);
if (IS_ERR(vs)) { if (IS_ERR(vs)) {
ovs_vport_free(vport); ovs_vport_free(vport);
return (void *)vs; return (void *)vs;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment