Message-ID: <20120925150957.78591205@nehalam.linuxnetplumber.net>
Date:	Tue, 25 Sep 2012 15:09:57 -0700
From:	Stephen Hemminger <shemminger@...tta.com>
To:	Jesse Gross <jesse@...ira.com>, Chris Wright <chrisw@...hat.com>,
	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org
Subject: [PATCHv5 net-next] vxlan: virtual extensible lan

This is an implementation of Virtual eXtensible Local Area Network
as described in draft RFC:
  http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-02

The driver integrates a Virtual Tunnel Endpoint (VTEP) functionality
that learns MAC to IP address mapping. 

This implementation has not been tested for Interoperation with
other equipment.

Signed-off-by: Stephen Hemminger <shemminger@...tta.com>

---
v5 - drop MTU discovery since network is overlaid
     use common code to do ECN decapsulation
v4 - fix ecn and set state of fdb entries
v3 - fix ordering of change versus migration message
v2 - fix use of ip header after pskb_may_pull

 Documentation/networking/vxlan.txt |   36 +
 drivers/net/Kconfig                |   13 
 drivers/net/Makefile               |    1 
 drivers/net/vxlan.c                | 1164 +++++++++++++++++++++++++++++++++++++
 include/linux/if_link.h            |   14 
 5 files changed, 1228 insertions(+)

--- a/drivers/net/Kconfig	2012-09-24 17:23:51.888577602 -0700
+++ b/drivers/net/Kconfig	2012-09-25 14:03:41.564362855 -0700
@@ -149,6 +149,19 @@ config MACVTAP
 	  To compile this driver as a module, choose M here: the module
 	  will be called macvtap.
 
+config VXLAN
+       tristate "Virtual eXtensible Local Area Network (VXLAN)"
+       depends on EXPERIMENTAL
+       ---help---
+	  This allows one to create vxlan virtual interfaces that provide
+	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
+	  to tunnel virtual network infrastructure in virtualized environments.
+	  For more information see:
+	    http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-02
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called vxlan.
+
 config NETCONSOLE
 	tristate "Network console logging support"
 	---help---
--- a/drivers/net/Makefile	2012-09-24 17:23:51.888577602 -0700
+++ b/drivers/net/Makefile	2012-09-25 14:03:41.564362855 -0700
@@ -21,6 +21,7 @@ obj-$(CONFIG_NET_TEAM) += team/
 obj-$(CONFIG_TUN) += tun.o
 obj-$(CONFIG_VETH) += veth.o
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
+obj-$(CONFIG_VXLAN) += vxlan.o
 
 #
 # Networking Drivers
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ b/drivers/net/vxlan.c	2012-09-25 15:08:03.546231656 -0700
@@ -0,0 +1,1164 @@
+/*
+ * 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/version.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	"0.0"
+
+#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 VXLAN_N_VID	(1u << 24)
+#define VXLAN_VID_MASK	(VXLAN_N_VID - 1)
+
+#define FDB_AGE_INTERVAL (10 * HZ)	/* rescan interval */
+#define FDB_AGE_TIME	 (300 * HZ)	/* drop if not used in 5 min */
+
+#define VXLAN_FLAGS 0x08000000	/* struct vxlanhdr.vx_flags required value. */
+
+/* VXLAN protocol header */
+struct vxlanhdr {
+	__be32 vx_flags;
+	__be32 vx_vni;
+};
+
+#define VXLAN_HEADROOM (sizeof(struct iphdr)		\
+			+ sizeof(struct udphdr)		\
+			+ sizeof(struct vxlanhdr))
+
+/* UDP port for VXLAN traffic. */
+static unsigned int vxlan_port __read_mostly = 8472;
+module_param_named(port, vxlan_port, uint, 0);
+MODULE_PARM_DESC(vxlan_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;
+
+	struct timer_list age_timer;
+	spinlock_t	  hash_lock;
+	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, VNI_HASH_BITS)];
+}
+
+/* Look up VNI in a per net namespace table */
+static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id)
+{
+	struct vxlan_dev *vxlan;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_rcu(vxlan, node, vni_head(net, id), hlist) {
+		if (vxlan->vni == id)
+			return vxlan;
+	}
+
+	return NULL;
+}
+
+/* Fill in neighbour message in skbuff. */
+static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
+			   const struct vxlan_fdb *fdb,
+			   u32 portid, u32 seq, int type, unsigned int flags)
+{
+	unsigned long now = jiffies;
+	struct nda_cacheinfo ci;
+	struct nlmsghdr *nlh;
+	struct ndmsg *ndm;
+
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ndm = nlmsg_data(nlh);
+	memset(ndm, 0, sizeof(*ndm));
+	ndm->ndm_family	= AF_BRIDGE;
+	ndm->ndm_state = fdb->state;
+
+	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
+		goto nla_put_failure;
+
+	if (nla_put_be32(skb, NDA_DST, fdb->remote_ip))
+		goto nla_put_failure;
+
+	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_confirmed = 0;
+	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_refcnt	 = 0;
+
+	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+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 nda_cacheinfo));
+}
+
+static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
+			     const struct vxlan_fdb *fdb, int type)
+{
+	struct net *net = dev_net(vxlan->dev);
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+}
+
+/* Hash Ethernet address */
+static u32 eth_hash(const unsigned char *addr)
+{
+	/* could be optimized for unaligned access */
+	u32 a = addr[5] << 8 | addr[4];
+	u32 b = addr[3] << 24 | addr[2] << 16 | addr[1] << 8 | addr[0];
+
+	return jhash_2words(a, b, vxlan_salt);
+}
+
+/* Hash chain to use given mac address */
+static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
+						const u8 *mac)
+{
+	return &vxlan->fdb_head[hash_32(eth_hash(mac), FDB_HASH_BITS)];
+}
+
+/* Look up Ethernet address in forwarding table */
+static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
+					const u8 *mac)
+
+{
+	struct hlist_head *head = vxlan_fdb_head(vxlan, mac);
+	struct vxlan_fdb *f;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_rcu(f, node, head, hlist) {
+		if (compare_ether_addr(mac, f->eth_addr) == 0)
+			return f;
+	}
+
+	return NULL;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+			    const u8 *mac, __be32 ip,
+			    __u16 state, __u16 flags)
+{
+	struct vxlan_fdb *f;
+
+	f = vxlan_find_mac(vxlan, mac);
+	if (f) {
+		if (flags & NLM_F_EXCL) {
+			netdev_dbg(vxlan->dev,
+				   "lost race to create %pM\n", mac);
+			return -EEXIST;
+		}
+	} else {
+		if (!(flags & NLM_F_CREATE))
+			return -ENOENT;
+
+		netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip);
+		f = kmalloc(sizeof(*f), GFP_ATOMIC);
+		if (!f)
+			return -ENOMEM;
+
+		f->remote_ip = ip;
+		memcpy(f->eth_addr, mac, ETH_ALEN);
+		hlist_add_head_rcu(&f->hlist,
+				   vxlan_fdb_head(vxlan, mac));
+		f->state = 0;
+	}
+
+	if (f->state != state) {
+		f->state = state;
+		f->updated = f->used = jiffies;
+		vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
+	}
+
+	return 0;
+}
+
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+{
+	netdev_dbg(vxlan->dev,
+		    "delete %pM\n", f->eth_addr);
+
+	vxlan_fdb_notify(vxlan, f, RTM_DELNEIGH);
+
+	hlist_del_rcu(&f->hlist);
+	kfree_rcu(f, rcu);
+}
+
+/* Add static entry (via netlink) */
+static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			 struct net_device *dev,
+			 const unsigned char *addr, u16 flags)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	__be32 ip;
+	int err;
+
+	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
+		pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
+		return -EINVAL;
+	}
+
+	if (tb[NDA_DST] == NULL)
+		return -EINVAL;
+
+	if (nla_len(tb[NDA_DST]) != sizeof(__be32))
+		return -EAFNOSUPPORT;
+
+	ip = nla_get_be32(tb[NDA_DST]);
+
+	spin_lock_bh(&vxlan->hash_lock);
+	err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags);
+	spin_unlock_bh(&vxlan->hash_lock);
+
+	return err;
+}
+
+/* Delete entry (via netlink) */
+static int vxlan_fdb_delete(struct ndmsg *ndm, struct net_device *dev,
+			    const unsigned char *addr)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f;
+	int err = -ENOENT;
+
+	spin_lock_bh(&vxlan->hash_lock);
+	f = vxlan_find_mac(vxlan, addr);
+	if (f) {
+		vxlan_fdb_destroy(vxlan, f);
+		err = 0;
+	}
+	spin_unlock_bh(&vxlan->hash_lock);
+
+	return err;
+}
+
+/* Dump forwarding table */
+static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			  struct net_device *dev, int idx)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	unsigned int h;
+
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		struct vxlan_fdb *f;
+		struct hlist_node *n;
+
+		hlist_for_each_entry_rcu(f, n, &vxlan->fdb_head[h], hlist) {
+			if (idx < cb->args[0])
+				goto skip;
+
+			if (vxlan_fdb_info(skb, vxlan, f,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    RTM_NEWNEIGH,
+					    NLM_F_MULTI) < 0)
+				break;
+skip:
+			++idx;
+		}
+	}
+
+	return idx;
+}
+
+/* Watch incoming packets to learn mapping between Ethernet address
+ * and Tunnel endpoint.
+ */
+static void vxlan_snoop(struct net_device *dev,
+			__be32 src_ip, const u8 *src_mac)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f;
+	int err;
+
+	f = vxlan_find_mac(vxlan, src_mac);
+	if (likely(f)) {
+		f->used = jiffies;
+		if (likely(f->remote_ip == src_ip))
+			return;
+
+		if (net_ratelimit())
+			netdev_info(dev,
+				    "%pM migrated from %pI4 to %pI4\n",
+				    src_mac, &f->remote_ip, &src_ip);
+
+		f->remote_ip = src_ip;
+		f->updated = jiffies;
+	} else {
+		/* learned new entry */
+		spin_lock(&vxlan->hash_lock);
+		err = vxlan_fdb_create(vxlan, src_mac, src_ip,
+				       NUD_REACHABLE,
+				       NLM_F_EXCL|NLM_F_CREATE);
+		spin_unlock(&vxlan->hash_lock);
+	}
+}
+
+
+/* See if multicast group is already in use by other ID */
+static bool vxlan_group_used(struct vxlan_net *vn,
+			     const struct vxlan_dev *this)
+{
+	const struct vxlan_dev *vxlan;
+	struct hlist_node *node;
+	unsigned h;
+
+	for (h = 0; h < VNI_HASH_SIZE; ++h)
+		hlist_for_each_entry(vxlan, node, &vn->vni_list[h], hlist) {
+			if (vxlan == this)
+				continue;
+
+			if (!netif_running(vxlan->dev))
+				continue;
+
+			if (vxlan->gaddr == this->gaddr)
+				return true;
+		}
+
+	return false;
+}
+
+/* kernel equivalent to IP_ADD_MEMBERSHIP */
+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;
+	struct ip_mreqn mreq = {
+		.imr_multiaddr.s_addr = vxlan->gaddr,
+	};
+	int err;
+
+	if (vxlan_group_used(vn, vxlan))
+		return 0;
+
+	/* Need to drop RTNL to call multicast join */
+	rtnl_unlock();
+	lock_sock(sk);
+	err = ip_mc_join_group(sk, &mreq);
+	release_sock(sk);
+	rtnl_lock();
+
+	return err;
+}
+
+
+/* kernel equivalent to IP_DROP_MEMBERSHIP */
+static int vxlan_leave_group(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	int err = 0;
+	struct sock *sk = vn->sock->sk;
+	struct ip_mreqn mreq = {
+		.imr_multiaddr.s_addr = vxlan->gaddr,
+	};
+
+	if (vxlan_group_used(vn, vxlan))
+		return 0;
+
+	/* Need to drop RTNL to call multicast leave */
+	rtnl_unlock();
+	lock_sock(sk);
+	err = ip_mc_leave_group(sk, &mreq);
+	release_sock(sk);
+	rtnl_lock();
+
+	return err;
+}
+
+/* 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 vxlanhdr *vxh;
+	struct vxlan_dev *vxlan;
+	struct vxlan_stats *stats;
+	__u32 vni;
+	int err;
+
+	/* pop off outer UDP header */
+	__skb_pull(skb, sizeof(struct udphdr));
+
+	/* Need Vxlan and inner Ethernet header to be present */
+	if (!pskb_may_pull(skb,
+			   sizeof(struct vxlanhdr) + sizeof(struct ethhdr)))
+		goto error;
+
+	oip = ip_hdr(skb);
+
+	/* Drop packets with reserved bits set */
+	vxh = (struct vxlanhdr *) skb->data;
+	if (vxh->vx_flags != htonl(VXLAN_FLAGS) ||
+	    (vxh->vx_vni & htonl(0xff)))
+		goto error;
+
+	__skb_pull(skb, sizeof(struct vxlanhdr));
+
+	/* Is this VNI defined? */
+	vni = ntohl(vxh->vx_vni) >> 8;
+	vxlan = vxlan_find_vni(sock_net(sk), vni);
+	if (!vxlan)
+		goto drop;
+
+	/* Ignore packets if device is not up */
+	if (!netif_running(vxlan->dev))
+		goto drop;
+
+	/* Re-examine inner Ethernet packet */
+	skb->protocol = eth_type_trans(skb, vxlan->dev);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Ignore packet loops (and multicast echo) */
+	if (compare_ether_addr(eth_hdr(skb)->h_source,
+			       vxlan->dev->dev_addr) == 0)
+		goto drop;
+
+	/* Check for multicast group configuration errors */
+	if (IN_MULTICAST(ntohl(oip->daddr)) &&
+	    oip->daddr != vxlan->gaddr) {
+		if (net_ratelimit())
+			netdev_notice(vxlan->dev,
+				      "group address %pI4 does not match\n",
+				      &oip->daddr);
+		goto drop;
+	}
+
+	if (vxlan->learn)
+		vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source);
+
+	__skb_tunnel_rx(skb, vxlan->dev);
+	skb_reset_network_header(skb);
+
+	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 (err > 1) {
+			++vxlan->dev->stats.rx_frame_errors;
+			++vxlan->dev->stats.rx_errors;
+			goto drop;
+		}
+	}
+
+	stats = this_cpu_ptr(vxlan->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	netif_rx(skb);
+
+	return 0;
+error:
+	/* Put UDP header back */
+	__skb_push(skb, sizeof(struct udphdr));
+
+	return 1;
+drop:
+	/* Consume bad packet */
+	kfree_skb(skb);
+	return 0;
+}
+
+/* Extract dsfield from inner protocol */
+static inline u8 vxlan_get_dsfield(const struct iphdr *iph,
+				   const struct sk_buff *skb)
+{
+	if (skb->protocol == htons(ETH_P_IP))
+		return iph->tos;
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return ipv6_get_dsfield((const struct ipv6hdr *)iph);
+	else
+		return 0;
+}
+
+/* Propogate ECN bits out */
+static inline u8 vxlan_ecn_encap(u8 tos,
+				 const struct iphdr *iph,
+				 const struct sk_buff *skb)
+{
+	u8 inner = vxlan_get_dsfield(iph, skb);
+
+	return INET_ECN_encapsulate(tos, inner);
+}
+
+/* Transmit local packets over Vxlan
+ *
+ * Outer IP header inherits ECN and DF from inner header.
+ * Outer UDP destination is the VXLAN assigned port.
+ *           source port is based on hash of flow if available
+ *                       otherwise use a random value
+ */
+static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct rtable *rt;
+	const struct ethhdr *eth;
+	const struct iphdr *old_iph;
+	struct iphdr *iph;
+	struct vxlanhdr *vxh;
+	struct udphdr *uh;
+	struct flowi4 fl4;
+	struct vxlan_fdb *f;
+	unsigned int pkt_len = skb->len;
+	u32 hash;
+	__be32 dst;
+	__be16 df = 0;
+	__u8 tos, ttl;
+	int err;
+
+	/* Need space for new headers (invalidates iph ptr) */
+	if (skb_cow_head(skb, VXLAN_HEADROOM))
+		goto drop;
+
+	eth = (void *)skb->data;
+	old_iph = ip_hdr(skb);
+
+	if (!is_multicast_ether_addr(eth->h_dest) &&
+	    (f = vxlan_find_mac(vxlan, eth->h_dest)))
+		dst = f->remote_ip;
+	else if (vxlan->gaddr) {
+		dst = vxlan->gaddr;
+	} else
+		goto drop;
+
+	ttl = vxlan->ttl;
+	if (!ttl && IN_MULTICAST(ntohl(dst)))
+		ttl = 1;
+
+	tos = vxlan->tos;
+	if (tos == 1)
+		tos = vxlan_get_dsfield(old_iph, skb);
+
+	hash = skb_get_rxhash(skb);
+
+	rt = ip_route_output_gre(dev_net(dev), &fl4, dst,
+				 vxlan->saddr, vxlan->vni,
+				 RT_TOS(tos), vxlan->link);
+	if (IS_ERR(rt)) {
+		netdev_dbg(dev, "no route to %pI4\n", &dst);
+		dev->stats.tx_carrier_errors++;
+		goto tx_error;
+	}
+
+	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(&(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);
+
+	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
+	vxh->vx_flags = htonl(VXLAN_FLAGS);
+	vxh->vx_vni = htonl(vxlan->vni << 8);
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = htons(vxlan_port);
+	uh->source = hash ? :random32();
+
+	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	= vxlan_ecn_encap(tos, old_iph, skb);
+	iph->daddr	= fl4.daddr;
+	iph->saddr	= fl4.saddr;
+	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+	/* See __IPTUNNEL_XMIT */
+	skb->ip_summed = CHECKSUM_NONE;
+	ip_select_ident(iph, &rt->dst, NULL);
+
+	err = ip_local_out(skb);
+	if (likely(net_xmit_eval(err) == 0)) {
+		struct vxlan_stats *stats = this_cpu_ptr(vxlan->stats);
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->tx_packets++;
+		stats->tx_bytes += pkt_len;
+		u64_stats_update_end(&stats->syncp);
+	} else {
+		dev->stats.tx_errors++;
+		dev->stats.tx_aborted_errors++;
+	}
+	return NETDEV_TX_OK;
+
+drop:
+	dev->stats.tx_dropped++;
+	goto tx_free;
+
+tx_error:
+	dev->stats.tx_errors++;
+tx_free:
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+/* Walk the forwarding table and purge stale entries */
+static void vxlan_cleanup(unsigned long arg)
+{
+	struct vxlan_dev *vxlan = (struct vxlan_dev *) arg;
+	unsigned long next_timer = jiffies + FDB_AGE_INTERVAL;
+	unsigned int h;
+
+	if (!netif_running(vxlan->dev))
+		return;
+
+	spin_lock_bh(&vxlan->hash_lock);
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		struct hlist_node *p, *n;
+		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
+			struct vxlan_fdb *f
+				= container_of(p, struct vxlan_fdb, hlist);
+			unsigned long timeout = f->used + FDB_AGE_TIME;
+
+			if (f->state == NUD_PERMANENT)
+				continue;
+
+			if (time_before_eq(timeout, jiffies)) {
+				netdev_dbg(vxlan->dev,
+					   "garbage collect %pM\n",
+					   f->eth_addr);
+				f->state = NUD_STALE;
+				vxlan_fdb_destroy(vxlan, f);
+			} else if (time_before(timeout, next_timer))
+				next_timer = timeout;
+		}
+	}
+	spin_unlock_bh(&vxlan->hash_lock);
+
+	mod_timer(&vxlan->age_timer, next_timer);
+}
+
+/* Setup stats when device is created */
+static int vxlan_init(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	vxlan->stats = alloc_percpu(struct vxlan_stats);
+	if (!vxlan->stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/* Start ageing timer and join group when device is brought up */
+static int vxlan_open(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
+	if (vxlan->gaddr) {
+		err = vxlan_join_group(dev);
+		if (err)
+			return err;
+	}
+
+	mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL);
+	return 0;
+}
+
+/* Purge the forwarding table */
+static void vxlan_flush(struct vxlan_dev *vxlan)
+{
+	unsigned h;
+
+	spin_lock_bh(&vxlan->hash_lock);
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		struct hlist_node *p, *n;
+		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
+			struct vxlan_fdb *f
+				= container_of(p, struct vxlan_fdb, hlist);
+			vxlan_fdb_destroy(vxlan, f);
+		}
+	}
+	spin_unlock_bh(&vxlan->hash_lock);
+}
+
+/* Cleanup timer and forwarding table on shutdown */
+static int vxlan_stop(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	if (vxlan->gaddr)
+		vxlan_leave_group(dev);
+
+	del_timer_sync(&vxlan->age_timer);
+
+	vxlan_flush(vxlan);
+
+	return 0;
+}
+
+/* Merge per-cpu statistics */
+static struct rtnl_link_stats64 *vxlan_stats64(struct net_device *dev,
+					       struct rtnl_link_stats64 *stats)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_stats tmp, sum = { 0 };
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		unsigned int start;
+		const struct vxlan_stats *stats
+			= per_cpu_ptr(vxlan->stats, cpu);
+
+		do {
+			start = u64_stats_fetch_begin_bh(&stats->syncp);
+			memcpy(&tmp, stats, sizeof(tmp));
+		} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+
+		sum.tx_bytes   += tmp.tx_bytes;
+		sum.tx_packets += tmp.tx_packets;
+		sum.rx_bytes   += tmp.rx_bytes;
+		sum.rx_packets += tmp.rx_packets;
+	}
+
+	stats->tx_bytes   = sum.tx_bytes;
+	stats->tx_packets = sum.tx_packets;
+	stats->rx_bytes   = sum.rx_bytes;
+	stats->rx_packets = sum.rx_packets;
+
+	stats->tx_dropped = dev->stats.tx_dropped;
+	stats->tx_errors  = dev->stats.tx_errors;
+	stats->tx_carrier_errors  = dev->stats.tx_carrier_errors;
+	stats->collisions  = dev->stats.collisions;
+
+	return stats;
+}
+
+/* Stub, nothing needs to be done. */
+static void vxlan_set_multicast_list(struct net_device *dev)
+{
+}
+
+static const struct net_device_ops vxlan_netdev_ops = {
+	.ndo_init		= vxlan_init,
+	.ndo_open		= vxlan_open,
+	.ndo_stop		= vxlan_stop,
+	.ndo_start_xmit		= vxlan_xmit,
+	.ndo_get_stats64	= vxlan_stats64,
+	.ndo_set_rx_mode	= vxlan_set_multicast_list,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_fdb_add		= vxlan_fdb_add,
+	.ndo_fdb_del		= vxlan_fdb_delete,
+	.ndo_fdb_dump		= vxlan_fdb_dump,
+};
+
+/* Info for udev, that this is a virtual tunnel endpoint */
+static struct device_type vxlan_type = {
+	.name = "vxlan",
+};
+
+static void vxlan_free(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	free_percpu(vxlan->stats);
+	free_netdev(dev);
+}
+
+/* Initialize the device structure. */
+static void vxlan_setup(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	unsigned h;
+
+	eth_hw_addr_random(dev);
+	ether_setup(dev);
+
+	dev->netdev_ops = &vxlan_netdev_ops;
+	dev->destructor = vxlan_free;
+	SET_NETDEV_DEVTYPE(dev, &vxlan_type);
+
+	dev->tx_queue_len = 0;
+	dev->features	|= NETIF_F_LLTX;
+	dev->features	|= NETIF_F_NETNS_LOCAL;
+	dev->priv_flags	&= ~IFF_XMIT_DST_RELEASE;
+
+	spin_lock_init(&vxlan->hash_lock);
+
+	init_timer_deferrable(&vxlan->age_timer);
+	vxlan->age_timer.function = vxlan_cleanup;
+	vxlan->age_timer.data = (unsigned long) vxlan;
+
+	vxlan->dev = dev;
+
+	for (h = 0; h < FDB_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
+}
+
+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_LINK]	= { .type = NLA_U32 },
+	[IFLA_VXLAN_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
+	[IFLA_VXLAN_TOS]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_TTL]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_LEARNING]	= { .type = NLA_U8 },
+};
+
+static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) {
+			pr_debug("invalid link address (not ethernet)\n");
+			return -EINVAL;
+		}
+
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) {
+			pr_debug("invalid all zero ethernet address\n");
+			return -EADDRNOTAVAIL;
+		}
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	if (data[IFLA_VXLAN_ID]) {
+		__u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
+		if (id >= VXLAN_VID_MASK)
+			return -ERANGE;
+	}
+
+	if (data[IFLA_VXLAN_GROUP]) {
+		__be32 gaddr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+		if (!IN_MULTICAST(ntohl(gaddr))) {
+			pr_debug("group address is not IPv4 multicast\n");
+			return -EADDRNOTAVAIL;
+		}
+	}
+
+	return 0;
+}
+
+static int vxlan_newlink(struct net *net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[])
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	__u32 vni;
+	int err;
+
+	if (!data[IFLA_VXLAN_ID])
+		return -EINVAL;
+
+	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
+	if (vxlan_find_vni(net, vni)) {
+		pr_info("duplicate VNI %u\n", vni);
+		return -EEXIST;
+	}
+	vxlan->vni = vni;
+
+	if (data[IFLA_VXLAN_GROUP])
+		vxlan->gaddr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+
+	if (data[IFLA_VXLAN_LOCAL])
+		vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+
+	if (data[IFLA_VXLAN_LINK])
+		vxlan->link = nla_get_u32(data[IFLA_VXLAN_LINK]);
+
+	if (data[IFLA_VXLAN_TOS])
+		vxlan->tos  = nla_get_u8(data[IFLA_VXLAN_TOS]);
+
+	if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING]))
+		vxlan->learn = true;
+
+	err = register_netdevice(dev);
+	if (!err)
+		hlist_add_head_rcu(&vxlan->hlist, vni_head(net, vxlan->vni));
+
+	return err;
+}
+
+static void vxlan_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	hlist_del_rcu(&vxlan->hlist);
+
+	unregister_netdevice_queue(dev, head);
+}
+
+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(__u32)) +	/* IFLA_VXLAN_LINK */
+		nla_total_size(sizeof(__be32))+	/* IFLA_VXLAN_LOCAL */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
+		0;
+}
+
+static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	const struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	if (nla_put_u32(skb, IFLA_VXLAN_ID, vxlan->vni))
+		goto nla_put_failure;
+
+	if (vxlan->gaddr && nla_put_u32(skb, IFLA_VXLAN_GROUP, vxlan->gaddr))
+		goto nla_put_failure;
+
+	if (vxlan->link && nla_put_u32(skb, IFLA_VXLAN_LINK, vxlan->link))
+		goto nla_put_failure;
+
+	if (vxlan->saddr && nla_put_u32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr))
+		goto nla_put_failure;
+
+	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_LEARNING, vxlan->learn))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
+	.kind		= "vxlan",
+	.maxtype	= IFLA_VXLAN_MAX,
+	.policy		= vxlan_policy,
+	.priv_size	= sizeof(struct vxlan_dev),
+	.setup		= vxlan_setup,
+	.validate	= vxlan_validate,
+	.newlink	= vxlan_newlink,
+	.dellink	= vxlan_dellink,
+	.get_size	= vxlan_get_size,
+	.fill_info	= vxlan_fill_info,
+};
+
+static __net_init int vxlan_init_net(struct net *net)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct sock *sk;
+	struct sockaddr_in addr;
+	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;
+	}
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = INADDR_ANY;
+	addr.sin_port = htons(vxlan_port);
+
+	rc = kernel_bind(vn->sock, (struct sockaddr *) &addr, sizeof(addr));
+	if (rc < 0) {
+		pr_debug("bind for port %u failed %d\n", vxlan_port, rc);
+		sock_release(vn->sock);
+		vn->sock = NULL;
+		return rc;
+	}
+
+	/* Disable multicast loopback */
+	sk = vn->sock->sk;
+	inet_sk(sk)->mc_loop = 0;
+
+	/* Mark socket as an encapsulation socket. */
+	udp_sk(sk)->encap_type = 1;
+	udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
+	udp_encap_enable();
+
+	for (h = 0; h < VNI_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&vn->vni_list[h]);
+
+	return 0;
+}
+
+static __net_exit void vxlan_exit_net(struct net *net)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+
+	if (vn->sock) {
+		sock_release(vn->sock);
+		vn->sock = NULL;
+	}
+}
+
+static struct pernet_operations vxlan_net_ops = {
+	.init = vxlan_init_net,
+	.exit = vxlan_exit_net,
+	.id   = &vxlan_net_id,
+	.size = sizeof(struct vxlan_net),
+};
+
+static int __init vxlan_init_module(void)
+{
+	int rc;
+
+	get_random_bytes(&vxlan_salt, sizeof(vxlan_salt));
+
+	rc = register_pernet_device(&vxlan_net_ops);
+	if (rc)
+		goto out1;
+
+	rc = rtnl_link_register(&vxlan_link_ops);
+	if (rc)
+		goto out2;
+
+	return 0;
+
+out2:
+	unregister_pernet_device(&vxlan_net_ops);
+out1:
+	return rc;
+}
+module_init(vxlan_init_module);
+
+static void __exit vxlan_cleanup_module(void)
+{
+	rtnl_link_unregister(&vxlan_link_ops);
+	unregister_pernet_device(&vxlan_net_ops);
+}
+module_exit(vxlan_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_VERSION(VXLAN_VERSION);
+MODULE_AUTHOR("Stephen Hemminger <shemminger@...tta.com>");
+MODULE_ALIAS_RTNL_LINK("vxlan");
--- a/include/linux/if_link.h	2012-09-24 17:23:51.888577602 -0700
+++ b/include/linux/if_link.h	2012-09-25 14:03:41.568362815 -0700
@@ -272,6 +272,20 @@ enum macvlan_mode {
 
 #define MACVLAN_FLAG_NOPROMISC	1
 
+/* VXLAN section */
+enum {
+	IFLA_VXLAN_UNSPEC,
+	IFLA_VXLAN_ID,
+	IFLA_VXLAN_GROUP,
+	IFLA_VXLAN_LINK,
+	IFLA_VXLAN_LOCAL,
+	IFLA_VXLAN_TTL,
+	IFLA_VXLAN_TOS,
+	IFLA_VXLAN_LEARNING,
+	__IFLA_VXLAN_MAX
+};
+#define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
+
 /* SR-IOV virtual function management section */
 
 enum {
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ b/Documentation/networking/vxlan.txt	2012-09-25 14:03:41.568362815 -0700
@@ -0,0 +1,36 @@
+Virtual eXtensible Local Area Networking documentation
+======================================================
+
+The VXLAN protocol is a tunnelling protocol that is designed to
+solve the problem of limited number of available VLAN's (4096).
+With VXLAN identifier is expanded to 24 bits.
+
+It is a draft RFC standard, that is implemented by Cisco Nexus,
+Vmware and Brocade. The protocol runs over UDP using a single
+destination port (still not standardized by IANA).
+This document describes the Linux kernel tunnel device,
+there is also an implantation of VXLAN for Openvswitch.
+
+Unlike most tunnels, a VXLAN is a 1 to N network, not just point
+to point. A VXLAN device can either dynamically learn the IP address
+of the other end, in a manner similar to a learning bridge, or the
+forwarding entries can be configured statically.
+
+The management of vxlan is done in a similar fashion to it's
+too closest neighbors GRE and VLAN. Configuring VXLAN requires
+the version of iproute2 that matches the kernel release
+where VXLAN was first merged upstream.
+
+1. Create vxlan device
+  # ip li add vxlan0 type vxlan id 42 group 239.1.1.1 dev eth1
+
+This creates a new device (vxlan0). The device uses the
+the multicast group 239.1.1.1 over eth1 to handle packets where
+no entry is in the forwarding table.
+
+2. Delete vxlan device
+  # ip link delete vxlan0
+
+3. Show vxlan info
+  # ip -d show vxlan0
+
--
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