/*
* VXLAN: Virtual eXtensible Local Area Network
*
* Copyright (c) 2012-2013 Vyatta Inc.
*
* 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
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/rculist.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/hash.h>
#include <linux/ethtool.h>
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/rtnetlink.h>
#include <net/route.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>
#include <net/protocol.h>
#include <net/udp_tunnel.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/ip6_checksum.h>
#endif
#define VXLAN_VERSION "0.1"
#define PORT_HASH_BITS 8
#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
#define FDB_HASH_BITS 8
#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
#define FDB_AGE_DEFAULT 300 /* 5 min */
#define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */
#define VXLAN_N_VID (1u << 24)
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
/* UDP port for VXLAN traffic.
* The IANA assigned port is 4789, but the Linux default is 8472
* for compatibility with early adopters.
*/
static unsigned short vxlan_port __read_mostly = 8472;
module_param_named(udp_port, vxlan_port, ushort, 0444);
MODULE_PARM_DESC(udp_port, "Destination UDP port");
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int vxlan_net_id;
static const u8 all_zeros_mac[ETH_ALEN];
/* per-network namespace private data for this module */
struct vxlan_net {
struct list_head vxlan_list;
struct hlist_head sock_list[PORT_HASH_SIZE];
spinlock_t sock_lock;
};
union vxlan_addr {
struct sockaddr_in sin;
struct sockaddr_in6 sin6;
struct sockaddr sa;
};
struct vxlan_rdst {
union vxlan_addr remote_ip;
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
struct list_head list;
struct rcu_head rcu;
};
/* Forwarding table entry */
struct vxlan_fdb {
struct hlist_node hlist; /* linked list of entries */
struct rcu_head rcu;
unsigned long updated; /* jiffies */
unsigned long used;
struct list_head remotes;
u16 state; /* see ndm_state */
u8 flags; /* see ndm_flags */
u8 eth_addr[ETH_ALEN];
};
/* Pseudo network device */
struct vxlan_dev {
struct hlist_node hlist; /* vni hash table */
struct list_head next; /* vxlan's per namespace list */
struct vxlan_sock *vn_sock; /* listening socket */
struct net_device *dev;
struct net *net; /* netns for packet i/o */
struct vxlan_rdst default_dst; /* default destination */
union vxlan_addr saddr; /* source address */
__be16 dst_port;
__u16 port_min; /* source port range */
__u16 port_max;
__u8 tos; /* TOS override */
__u8 ttl;
u32 flags; /* VXLAN_F_* in vxlan.h */
struct work_struct sock_work;
struct work_struct igmp_join;
struct work_struct igmp_leave;
unsigned long age_interval;
struct timer_list age_timer;
spinlock_t hash_lock;
unsigned int addrcnt;
unsigned int addrmax;
struct hlist_head fdb_head[FDB_HASH_SIZE];
};
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
static struct workqueue_struct *vxlan_wq;
static void vxlan_sock_work(struct work_struct *work);
#if IS_ENABLED(CONFIG_IPV6)
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
if (a->sa.sa_family != b->sa.sa_family)
return false;
if (a->sa.sa_family == AF_INET6)
return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
else
return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}
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 */
static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
{
return &vs->vni_list[hash_32(id, VNI_HASH_BITS)];
}
/* Socket hash table head */
static inline struct hlist_head *vs_head(struct net *net, __be16 port)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
}
/* First remote destination for a forwarding entry.
* Guaranteed to be non-NULL because remotes are never deleted.
*/
static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb)
{
return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list);
}
static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
{
return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
}
/* Find VXLAN socket based on network namespace, address family and UDP port */
static struct vxlan_sock *vxlan_find_sock(struct net *net,
sa_family_t family, __be16 port)
{
struct vxlan_sock *vs;
hlist_for_