ipvlan: Initial check-in of the IPVLAN driver.

                            IPVLAN Driver HOWTO

Initial Release:

	Mahesh Bandewar <maheshb AT google.com>

1. Introduction:

	This is conceptually very similar to the macvlan driver with one major

exception of using L3 for mux-ing /demux-ing among slaves. This property makes

the master device share the L2 with it's slave devices. I have developed this

driver in conjuntion with network namespaces and not sure if there is use case

outside of it.

2. Building and Installation:

	In order to build the driver, please select the config item CONFIG_IPVLAN.

The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module

(CONFIG_IPVLAN=m).

3. Configuration:

	There are no module parameters for this driver and it can be configured

using IProute2/ip utility.

	ip link add link <master-dev> <slave-dev> type ipvlan mode { l2 | L3 }

	e.g. ip link add link ipvl0 eth0 type ipvlan mode l2

4. Operating modes:

	IPvlan has two modes of operation - L2 and L3. For a given master device,

you can select one of these two modes and all slaves on that master will

operate in the same (selected) mode. The RX mode is almost identical except

that in L3 mode the slaves wont receive any multicast / broadcast traffic.

L3 mode is more restrictive since routing is controlled from the other (mostly)

default namespace.

4.1 L2 mode:

	In this mode TX processing happens on the stack instance attached to the

slave device and packets are switched and queued to the master device to send

out. In this mode the slaves will RX/TX multicast and broadcast (if applicable)

as well.

4.2 L3 mode:

	In this mode TX processing upto L3 happens on the stack instance attached

to the slave device and packets are switched to the stack instance of the

master device for the L2 processing and routing from that instance will be

used before packets are queued on the outbound device. In this mode the slaves

will not receive nor can send multicast / broadcast traffic.

5. What to choose (macvlan vs. ipvlan)?

	These two devices are very similar in many regards and the specific use

case could very well define which device to choose. if one of the following

situations defines your use case then you can choose to use ipvlan -

	(a) The Linux host that is connected to the external switch / router has

policy configured that allows only one mac per port.

	(b) No of virtual devices created on a master exceed the mac capacity and

puts the NIC in promiscous mode and degraded performance is a concern.

	(c) If the slave device is to be put into the hostile / untrusted network

namespace where L2 on the slave could be changed / misused.

6. Example configuration:

  +=============================================================+

  |  Host: host1                                                |

  |                                                             |

  |   +----------------------+      +----------------------+    |

  |   |   NS:ns0             |      |  NS:ns1              |    |

  |   |                      |      |                      |    |

  |   |                      |      |                      |    |

  |   |        ipvl0         |      |         ipvl1        |    |

  |   +----------#-----------+      +-----------#----------+    |

  |              #                              #               |

  |              ################################               |

  |                              # eth0                         |

  +==============================#==============================+

	(a) Create two network namespaces - ns0, ns1

		ip netns add ns0

		ip netns add ns1

	(b) Create two ipvlan slaves on eth0 (master device)

		ip link add link eth0 ipvl0 type ipvlan mode l2

		ip link add link eth0 ipvl1 type ipvlan mode l2

	(c) Assign slaves to the respective network namespaces

		ip link set dev ipvl0 netns ns0

		ip link set dev ipvl1 netns ns1

	(d) Now switch to the namespace (ns0 or ns1) to configure the slave devices

		- For ns0

			(1) ip netns exec ns0 bash

			(2) ip link set dev ipvl0 up

			(3) ip link set dev lo up

			(4) ip -4 addr add 127.0.0.1 dev lo

			(5) ip -4 addr add $IPADDR dev ipvl0

			(6) ip -4 route add default via $ROUTER dev ipvl0

		- For ns1

			(1) ip netns exec ns1 bash

			(2) ip link set dev ipvl1 up

			(3) ip link set dev lo up

			(4) ip -4 addr add 127.0.0.1 dev lo

			(5) ip -4 addr add $IPADDR dev ipvl1

			(6) ip -4 route add default via $ROUTER dev ipvl1

	  To compile this driver as a module, choose M here: the module

	  will be called macvtap.

config IPVLAN

    tristate "IP-VLAN support"

    ---help---

      This allows one to create virtual devices off of a main interface

      and packets will be delivered based on the dest L3 (IPv6/IPv4 addr)

      on packets. All interfaces (including the main interface) share L2

      making it transparent to the connected L2 switch.

      Ipvlan devices can be added using the "ip" command from the

      iproute2 package starting with the iproute2-X.Y.ZZ release:

      "ip link add link <main-dev> [ NAME ] type ipvlan"

      To compile this driver as a module, choose M here: the module

      will be called ipvlan.

config VXLAN

       tristate "Virtual eXtensible Local Area Network (VXLAN)"

       depends on INET

# Networking Core Drivers

#

obj-$(CONFIG_BONDING) += bonding/

obj-$(CONFIG_IPVLAN) += ipvlan/

obj-$(CONFIG_DUMMY) += dummy.o

obj-$(CONFIG_EQUALIZER) += eql.o

obj-$(CONFIG_IFB) += ifb.o

#

# Makefile for the Ethernet Ipvlan driver

#

obj-$(CONFIG_IPVLAN) += ipvlan.o

ipvlan-objs := ipvlan_core.o ipvlan_main.o

/*

 * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>

 *

 * This program is free software; you can redistribute it and/or

 * modify it under the terms of the GNU General Public License as

 * published by the Free Software Foundation; either version 2 of

 * the License, or (at your option) any later version.

 *

 */

#ifndef __IPVLAN_H

#define __IPVLAN_H

#include <linux/kernel.h>

#include <linux/types.h>

#include <linux/module.h>

#include <linux/init.h>

#include <linux/rculist.h>

#include <linux/notifier.h>

#include <linux/netdevice.h>

#include <linux/etherdevice.h>

#include <linux/if_arp.h>

#include <linux/if_link.h>

#include <linux/if_vlan.h>

#include <linux/ip.h>

#include <linux/inetdevice.h>

#include <net/rtnetlink.h>

#include <net/gre.h>

#include <net/route.h>

#include <net/addrconf.h>

#define IPVLAN_DRV	"ipvlan"

#define IPV_DRV_VER	"0.1"

#define IPVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)

#define IPVLAN_HASH_MASK	(IPVLAN_HASH_SIZE - 1)

#define IPVLAN_MAC_FILTER_BITS	8

#define IPVLAN_MAC_FILTER_SIZE	(1 << IPVLAN_MAC_FILTER_BITS)

#define IPVLAN_MAC_FILTER_MASK	(IPVLAN_MAC_FILTER_SIZE - 1)

typedef enum {

	IPVL_IPV6 = 0,

	IPVL_ICMPV6,

	IPVL_IPV4,

	IPVL_ARP,

} ipvl_hdr_type;

struct ipvl_pcpu_stats {

	u64			rx_pkts;

	u64			rx_bytes;

	u64			rx_mcast;

	u64			tx_pkts;

	u64			tx_bytes;

	struct u64_stats_sync	syncp;

	u32			rx_errs;

	u32			tx_drps;

};

struct ipvl_port;

struct ipvl_dev {

	struct net_device	*dev;

	struct list_head	pnode;

	struct ipvl_port	*port;

	struct net_device	*phy_dev;

	struct list_head	addrs;

	int			ipv4cnt;

	int			ipv6cnt;

	struct ipvl_pcpu_stats	*pcpu_stats;

	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);

	netdev_features_t	sfeatures;

	u32			msg_enable;

	u16			mtu_adj;

};

struct ipvl_addr {

	struct ipvl_dev		*master; /* Back pointer to master */

	union {

		struct in6_addr	ip6;	 /* IPv6 address on logical interface */

		struct in_addr	ip4;	 /* IPv4 address on logical interface */

	} ipu;

#define ip6addr	ipu.ip6

#define ip4addr ipu.ip4

	struct hlist_node	hlnode;  /* Hash-table linkage */

	struct list_head	anode;   /* logical-interface linkage */

	struct rcu_head		rcu;

	ipvl_hdr_type		atype;

};

struct ipvl_port {

	struct net_device	*dev;

	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];

	struct list_head	ipvlans;

	struct rcu_head		rcu;

	int			count;

	u16			mode;

};

static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)

{

	return rcu_dereference(d->rx_handler_data);

}

static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)

{

	return rtnl_dereference(d->rx_handler_data);

}

static inline bool ipvlan_dev_master(struct net_device *d)

{

	return d->priv_flags & IFF_IPVLAN_MASTER;

}

static inline bool ipvlan_dev_slave(struct net_device *d)

{

	return d->priv_flags & IFF_IPVLAN_SLAVE;

}

void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev);

void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval);

void ipvlan_init_secret(void);

unsigned int ipvlan_mac_hash(const unsigned char *addr);

rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);

int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);

void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);

bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6);

struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,

					const void *iaddr, bool is_v6);

void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync);

#endif /* __IPVLAN_H */