path: root/drivers/net/vxlan.c

/*
 * VXLAN: Virtual eXtensiable Local Area Network
 *
 * Copyright (c) 2012 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.
 *
 * TODO
 *  - use IANA UDP port number (when defined)
 *  - IPv6 (not in RFC)
 */

#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/hash.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.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>

#define VXLAN_VERSION	"0.1"

#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)
/* VLAN + IP header + UDP + VXLAN */
#define VXLAN_HEADROOM (4 + 20 + 8 + 8)

#define VXLAN_FLAGS 0x08000000	/* struct vxlanhdr.vx_flags required value. */

/* VXLAN protocol header */
struct vxlanhdr {
	__be32 vx_flags;
	__be32 vx_vni;
};

/* UDP port for VXLAN traffic. */
static unsigned int vxlan_port __read_mostly = 8472;
module_param_named(udp_port, vxlan_port, uint, 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");

/* per-net private data for this module */
static unsigned int vxlan_net_id;
struct vxlan_net {
	struct socket	  *sock;	/* UDP encap socket */
	struct hlist_head vni_list[VNI_HASH_SIZE];
};

/* 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;
	__be32		  remote_ip;
	u16		  state;	/* see ndm_state */
	u8		  eth_addr[ETH_ALEN];
};

/* Per-cpu network traffic stats */
struct vxlan_stats {
	u64			rx_packets;
	u64			rx_bytes;
	u64			tx_packets;
	u64			tx_bytes;
	struct u64_stats_sync	syncp;
};

/* Pseudo network device */
struct vxlan_dev {
	struct hlist_node hlist;
	struct net_device *dev;
	struct vxlan_stats __percpu *stats;
	__u32		  vni;		/* virtual network id */
	__be32	          gaddr;	/* multicast group */
	__be32		  saddr;	/* source address */
	unsigned int      link;		/* link to multicast over */
	__u8		  tos;		/* TOS override */
	__u8		  ttl;
	bool		  learn;

	unsigned long	  age_interval;
	struct timer_list age_timer;
	spinlock_t	  hash_lock;
	unsigned int	  addrcnt;
	unsigned int	  addrmax;
	unsigned int	  addrexceeded;

	struct hlist_head fdb_head[FDB_HASH_SIZE];
};

/* salt for hash table */
static u32 vxlan_salt __read_mostly;

static inline struct hlist_head *vni_head(struct net *net, u32 id)
{
	struct vxlan_net *vn = net_generic(net, vxlan_net_id);

	return &vn->vni_list[hash_32(id,