ipvlan: Initial check-in of the IPVLAN driver.

This driver is very similar to the macvlan driver except that it
uses L3 on the frame to determine the logical interface while
functioning as packet dispatcher. It inherits L2 of the master
device hence the packets on wire will have the same L2 for all
the packets originating from all virtual devices off of the same
master device.

This driver was developed keeping the namespace use-case in
mind. Hence most of the examples given here take that as the
base setup where main-device belongs to the default-ns and
virtual devices are assigned to the additional namespaces.

The device operates in two different modes and the difference
in these two modes in primarily in the TX side.

(a) L2 mode : In this mode, the device behaves as a L2 device.
TX processing upto L2 happens on the stack of the virtual device
associated with (namespace). Packets are switched after that
into the main device (default-ns) and queued for xmit.

RX processing is simple and all multicast, broadcast (if
applicable), and unicast belonging to the address(es) are
delivered to the virtual devices.

(b) L3 mode : In this mode, the device behaves like a L3 device.
TX processing upto L3 happens on the stack of the virtual device
associated with (namespace). Packets are switched to the
main-device (default-ns) for the L2 processing. Hence the routing
table of the default-ns will be used in this mode.

RX processins is somewhat similar to the L2 mode except that in
this mode only Unicast packets are delivered to the virtual device
while main-dev will handle all other packets.

The devices can be added using the "ip" command from the iproute2
package -

	ip link add link <master> <virtual> type ipvlan mode [ l2 | l3 ]

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Laurent Chavey <chavey@google.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Brandon Philips <brandon.philips@coreos.com>
Cc: Pavel Emelianov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ipvlan.txt

@@ -0,0 +1,107 @@
+
+                            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

drivers/net/Kconfig

@@ -145,6 +145,24 @@ config MACVTAP
 	  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

drivers/net/Makefile

@@ -6,6 +6,7 @@
 # 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

drivers/net/ipvlan/Makefile

@@ -0,0 +1,7 @@
+#
+# Makefile for the Ethernet Ipvlan driver
+#
+
+obj-$(CONFIG_IPVLAN) += ipvlan.o
+
+ipvlan-objs := ipvlan_core.o ipvlan_main.o

drivers/net/ipvlan/ipvlan.h

@@ -0,0 +1,130 @@
+/*
+ * 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 */

drivers/net/ipvlan/ipvlan_core.c

@@ -0,0 +1,607 @@
+/* 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.
+ *
+ */
+
+#include "ipvlan.h"
+
+static u32 ipvlan_jhash_secret;
+
+void ipvlan_init_secret(void)
+{
+	net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret));
+}
+
+static void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+			    unsigned int len, bool success, bool mcast)
+{
+	if (!ipvlan)
+		return;
+
+	if (likely(success)) {
+		struct ipvl_pcpu_stats *pcptr;
+
+		pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+		u64_stats_update_begin(&pcptr->syncp);
+		pcptr->rx_pkts++;
+		pcptr->rx_bytes += len;
+		if (mcast)
+			pcptr->rx_mcast++;
+		u64_stats_update_end(&pcptr->syncp);
+	} else {
+		this_cpu_inc(ipvlan->pcpu_stats->rx_errs);
+	}
+}
+
+static u8 ipvlan_get_v6_hash(const void *iaddr)
+{
+	const struct in6_addr *ip6_addr = iaddr;
+
+	return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) &
+	       IPVLAN_HASH_MASK;
+}
+
+static u8 ipvlan_get_v4_hash(const void *iaddr)
+{
+	const struct in_addr *ip4_addr = iaddr;
+
+	return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) &
+	       IPVLAN_HASH_MASK;
+}
+
+struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
+					const void *iaddr, bool is_v6)
+{
+	struct ipvl_addr *addr;
+	u8 hash;
+
+	hash = is_v6 ? ipvlan_get_v6_hash(iaddr) :
+	       ipvlan_get_v4_hash(iaddr);
+	hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) {
+		if (is_v6 && addr->atype == IPVL_IPV6 &&
+		    ipv6_addr_equal(&addr->ip6addr, iaddr))
+			return addr;
+		else if (!is_v6 && addr->atype == IPVL_IPV4 &&
+			 addr->ip4addr.s_addr ==
+				((struct in_addr *)iaddr)->s_addr)
+			return addr;
+	}
+	return NULL;
+}
+
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr)
+{
+	struct ipvl_port *port = ipvlan->port;
+	u8 hash;
+
+	hash = (addr->atype == IPVL_IPV6) ?
+	       ipvlan_get_v6_hash(&addr->ip6addr) :
+	       ipvlan_get_v4_hash(&addr->ip4addr);
+	hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
+}
+
+void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync)
+{
+	hlist_del_rcu(&addr->hlnode);
+	if (sync)
+		synchronize_rcu();
+}
+
+bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
+{
+	struct ipvl_port *port = ipvlan->port;
+	struct ipvl_addr *addr;
+
+	list_for_each_entry(addr, &ipvlan->addrs, anode) {
+		if ((is_v6 && addr->atype == IPVL_IPV6 &&
+		    ipv6_addr_equal(&addr->ip6addr, iaddr)) ||
+		    (!is_v6 && addr->atype == IPVL_IPV4 &&
+		    addr->ip4addr.s_addr == ((struct in_addr *)iaddr)->s_addr))
+			return true;
+	}
+
+	if (ipvlan_ht_addr_lookup(port, iaddr, is_v6))
+		return true;
+
+	return false;
+}
+
+static void *ipvlan_get_L3_hdr(struct sk_buff *skb, int *type)
+{
+	void *lyr3h = NULL;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_ARP): {
+		struct arphdr *arph;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*arph))))
+			return NULL;
+
+		arph = arp_hdr(skb);
+		*type = IPVL_ARP;
+		lyr3h = arph;
+		break;
+	}
+	case htons(ETH_P_IP): {
+		u32 pktlen;
+		struct iphdr *ip4h;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*ip4h))))
+			return NULL;
+
+		ip4h = ip_hdr(skb);
+		pktlen = ntohs(ip4h->tot_len);
+		if (ip4h->ihl < 5 || ip4h->version != 4)
+			return NULL;
+		if (skb->len < pktlen || pktlen < (ip4h->ihl * 4))
+			return NULL;
+
+		*type = IPVL_IPV4;
+		lyr3h = ip4h;
+		break;
+	}
+	case htons(ETH_P_IPV6): {
+		struct ipv6hdr *ip6h;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h))))
+			return NULL;
+
+		ip6h = ipv6_hdr(skb);
+		if (ip6h->version != 6)
+			return NULL;
+
+		*type = IPVL_IPV6;
+		lyr3h = ip6h;
+		/* Only Neighbour Solicitation pkts need different treatment */
+		if (ipv6_addr_any(&ip6h->saddr) &&
+		    ip6h->nexthdr == NEXTHDR_ICMP) {
+			*type = IPVL_ICMPV6;
+			lyr3h = ip6h + 1;
+		}
+		break;
+	}
+	default:
+		return NULL;
+	}
+
+	return lyr3h;
+}
+
+unsigned int ipvlan_mac_hash(const unsigned char *addr)
+{
+	u32 hash = jhash_1word(__get_unaligned_cpu32(addr+2),
+			       ipvlan_jhash_secret);
+
+	return hash & IPVLAN_MAC_FILTER_MASK;
+}
+
+static void ipvlan_multicast_frame(struct ipvl_port *port, struct sk_buff *skb,
+				   const struct ipvl_dev *in_dev, bool local)
+{
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_dev *ipvlan;
+	struct sk_buff *nskb;
+	unsigned int len;
+	unsigned int mac_hash;
+	int ret;
+
+	if (skb->protocol == htons(ETH_P_PAUSE))
+		return;
+
+	list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+		if (local && (ipvlan == in_dev))
+			continue;
+
+		mac_hash = ipvlan_mac_hash(eth->h_dest);
+		if (!test_bit(mac_hash, ipvlan->mac_filters))
+			continue;
+
+		ret = NET_RX_DROP;
+		len = skb->len + ETH_HLEN;
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			goto mcast_acct;
+
+		if (ether_addr_equal(eth->h_dest, ipvlan->phy_dev->broadcast))
+			nskb->pkt_type = PACKET_BROADCAST;
+		else
+			nskb->pkt_type = PACKET_MULTICAST;
+
+		nskb->dev = ipvlan->dev;
+		if (local)
+			ret = dev_forward_skb(ipvlan->dev, nskb);
+		else
+			ret = netif_rx(nskb);
+mcast_acct:
+		ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+	}
+
+	/* Locally generated? ...Forward a copy to the main-device as
+	 * well. On the RX side we'll ignore it (wont give it to any
+	 * of the virtual devices.
+	 */
+	if (local) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (nskb) {
+			if (ether_addr_equal(eth->h_dest, port->dev->broadcast))
+				nskb->pkt_type = PACKET_BROADCAST;
+			else
+				nskb->pkt_type = PACKET_MULTICAST;
+
+			dev_forward_skb(port->dev, nskb);
+		}
+	}
+}
+
+static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb,
+			    bool local)
+{
+	struct ipvl_dev *ipvlan = addr->master;
+	struct net_device *dev = ipvlan->dev;
+	unsigned int len;
+	rx_handler_result_t ret = RX_HANDLER_CONSUMED;
+	bool success = false;
+
+	len = skb->len + ETH_HLEN;
+	if (unlikely(!(dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		goto out;
+	}
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	skb->dev = dev;
+	skb->pkt_type = PACKET_HOST;
+
+	if (local) {
+		if (dev_forward_skb(ipvlan->dev, skb) == NET_RX_SUCCESS)
+			success = true;
+	} else {
+		ret = RX_HANDLER_ANOTHER;
+		success = true;
+	}
+
+out:
+	ipvlan_count_rx(ipvlan, len, success, false);
+	return ret;
+}
+
+static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port,
+					    void *lyr3h, int addr_type,
+					    bool use_dest)
+{
+	struct ipvl_addr *addr = NULL;
+
+	if (addr_type == IPVL_IPV6) {
+		struct ipv6hdr *ip6h;
+		struct in6_addr *i6addr;
+
+		ip6h = (struct ipv6hdr *)lyr3h;
+		i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr;
+		addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+	} else if (addr_type == IPVL_ICMPV6) {
+		struct nd_msg *ndmh;
+		struct in6_addr *i6addr;
+
+		/* Make sure that the NeighborSolicitation ICMPv6 packets
+		 * are handled to avoid DAD issue.
+		 */
+		ndmh = (struct nd_msg *)lyr3h;
+		if (ndmh->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) {
+			i6addr = &ndmh->target;
+			addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+		}
+	} else if (addr_type == IPVL_IPV4) {
+		struct iphdr *ip4h;
+		__be32 *i4addr;
+
+		ip4h = (struct iphdr *)lyr3h;
+		i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr;
+		addr = ipvlan_ht_addr_lookup(port, i4addr, false);
+	} else if (addr_type == IPVL_ARP) {
+		struct arphdr *arph;
+		unsigned char *arp_ptr;
+		__be32 dip;
+
+		arph = (struct arphdr *)lyr3h;
+		arp_ptr = (unsigned char *)(arph + 1);
+		if (use_dest)
+			arp_ptr += (2 * port->dev->addr_len) + 4;
+		else
+			arp_ptr += port->dev->addr_len;
+
+		memcpy(&dip, arp_ptr, 4);
+		addr = ipvlan_ht_addr_lookup(port, &dip, false);
+	}
+
+	return addr;
+}
+
+static int ipvlan_process_v4_outbound(struct sk_buff *skb)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net_device *dev = skb->dev;
+	struct rtable *rt;
+	int err, ret = NET_XMIT_DROP;
+	struct flowi4 fl4 = {
+		.flowi4_oif = dev->iflink,
+		.flowi4_tos = RT_TOS(ip4h->tos),
+		.flowi4_flags = FLOWI_FLAG_ANYSRC,
+		.daddr = ip4h->daddr,
+		.saddr = ip4h->saddr,
+	};
+
+	rt = ip_route_output_flow(dev_net(dev), &fl4, NULL);
+	if (IS_ERR(rt))
+		goto err;
+
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto err;
+	}
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+	err = ip_local_out(skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out;
+err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out:
+	return ret;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net_device *dev = skb->dev;
+	struct dst_entry *dst;
+	int err, ret = NET_XMIT_DROP;
+	struct flowi6 fl6 = {
+		.flowi6_iif = skb->dev->ifindex,
+		.daddr = ip6h->daddr,
+		.saddr = ip6h->saddr,
+		.flowi6_flags = FLOWI_FLAG_ANYSRC,
+		.flowlabel = ip6_flowinfo(ip6h),
+		.flowi6_mark = skb->mark,
+		.flowi6_proto = ip6h->nexthdr,
+	};
+
+	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+	if (IS_ERR(dst))
+		goto err;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+	err = ip6_local_out(skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out;
+err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out:
+	return ret;
+}
+
+static int ipvlan_process_outbound(struct sk_buff *skb,
+				   const struct ipvl_dev *ipvlan)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+	int ret = NET_XMIT_DROP;
+
+	/* In this mode we dont care about multicast and broadcast traffic */
+	if (is_multicast_ether_addr(ethh->h_dest)) {
+		pr_warn_ratelimited("Dropped {multi|broad}cast of type= [%x]\n",
+				    ntohs(skb->protocol));
+		kfree_skb(skb);
+		goto out;
+	}
+
+	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
+	 * will have L2; which need to discarded and processed further
+	 * in the net-ns of the main-device.
+	 */
+	if (skb_mac_header_was_set(skb)) {
+		skb_pull(skb, sizeof(*ethh));
+		skb->mac_header = (typeof(skb->mac_header))~0U;
+		skb_reset_network_header(skb);
+	}
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		ret = ipvlan_process_v6_outbound(skb);
+	else if (skb->protocol == htons(ETH_P_IP))
+		ret = ipvlan_process_v4_outbound(skb);
+	else {
+		pr_warn_ratelimited("Dropped outbound packet type=%x\n",
+				    ntohs(skb->protocol));
+		kfree_skb(skb);
+	}
+out:
+	return ret;
+}
+
+static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	void *lyr3h;
+	struct ipvl_addr *addr;
+	int addr_type;
+
+	lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+	if (!lyr3h)
+		goto out;
+
+	addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+	if (addr)
+		return ipvlan_rcv_frame(addr, skb, true);
+
+out:
+	skb->dev = ipvlan->phy_dev;
+	return ipvlan_process_outbound(skb, ipvlan);
+}
+
+static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_addr *addr;
+	void *lyr3h;
+	int addr_type;
+
+	if (ether_addr_equal(eth->h_dest, eth->h_source)) {
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (lyr3h) {
+			addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+			if (addr)
+				return ipvlan_rcv_frame(addr, skb, true);
+		}
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (!skb)
+			return NET_XMIT_DROP;
+
+		/* Packet definitely does not belong to any of the
+		 * virtual devices, but the dest is local. So forward
+		 * the skb for the main-dev. At the RX side we just return
+		 * RX_PASS for it to be processed further on the stack.
+		 */
+		return dev_forward_skb(ipvlan->phy_dev, skb);
+
+	} else if (is_multicast_ether_addr(eth->h_dest)) {
+		u8 ip_summed = skb->ip_summed;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		ipvlan_multicast_frame(ipvlan->port, skb, ipvlan, true);
+		skb->ip_summed = ip_summed;
+	}
+
+	skb->dev = ipvlan->phy_dev;
+	return dev_queue_xmit(skb);
+}
+
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rcu(ipvlan->phy_dev);
+
+	if (!port)
+		goto out;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
+		goto out;
+
+	switch(port->mode) {
+	case IPVLAN_MODE_L2:
+		return ipvlan_xmit_mode_l2(skb, dev);
+	case IPVLAN_MODE_L3:
+		return ipvlan_xmit_mode_l3(skb, dev);
+	}
+
+	/* Should not reach here */
+	WARN_ONCE(true, "ipvlan_queue_xmit() called for mode = [%hx]\n",
+			  port->mode);
+out:
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+
+static bool ipvlan_external_frame(struct sk_buff *skb, struct ipvl_port *port)
+{
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_addr *addr;
+	void *lyr3h;
+	int addr_type;
+
+	if (ether_addr_equal(eth->h_source, skb->dev->dev_addr)) {
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (!lyr3h)
+			return true;
+
+		addr = ipvlan_addr_lookup(port, lyr3h, addr_type, false);
+		if (addr)
+			return false;
+	}
+
+	return true;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb,
+						 struct ipvl_port *port)
+{
+	void *lyr3h;
+	int addr_type;
+	struct ipvl_addr *addr;
+	struct sk_buff *skb = *pskb;
+	rx_handler_result_t ret = RX_HANDLER_PASS;
+
+	lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+	if (!lyr3h)
+		goto out;
+
+	addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+	if (addr)
+		ret = ipvlan_rcv_frame(addr, skb, false);
+
+out:
+	return ret;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
+						 struct ipvl_port *port)
+{
+	struct sk_buff *skb = *pskb;
+	struct ethhdr *eth = eth_hdr(skb);
+	rx_handler_result_t ret = RX_HANDLER_PASS;
+	void *lyr3h;
+	int addr_type;
+
+	if (is_multicast_ether_addr(eth->h_dest)) {
+		if (ipvlan_external_frame(skb, port))
+			ipvlan_multicast_frame(port, skb, NULL, false);
+	} else {
+		struct ipvl_addr *addr;
+
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (!lyr3h)
+			return ret;
+
+		addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+		if (addr)
+			ret = ipvlan_rcv_frame(addr, skb, false);
+	}
+
+	return ret;
+}
+
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct ipvl_port *port = ipvlan_port_get_rcu(skb->dev);
+
+	if (!port)
+		return RX_HANDLER_PASS;
+
+	switch (port->mode) {
+	case IPVLAN_MODE_L2:
+		return ipvlan_handle_mode_l2(pskb, port);
+	case IPVLAN_MODE_L3:
+		return ipvlan_handle_mode_l3(pskb, port);
+	}
+
+	/* Should not reach here */
+	WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n",
+			  port->mode);
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}

drivers/net/ipvlan/ipvlan_main.c

@@ -0,0 +1,789 @@
+/* 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.
+ *
+ */
+
+#include "ipvlan.h"
+
+void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
+{
+	ipvlan->dev->mtu = dev->mtu - ipvlan->mtu_adj;
+}
+
+void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval)
+{
+	struct ipvl_dev *ipvlan;
+
+	if (port->mode != nval) {
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			if (nval == IPVLAN_MODE_L3)
+				ipvlan->dev->flags |= IFF_NOARP;
+			else
+				ipvlan->dev->flags &= ~IFF_NOARP;
+		}
+		port->mode = nval;
+	}
+}
+
+static int ipvlan_port_create(struct net_device *dev)
+{
+	struct ipvl_port *port;
+	int err, idx;
+
+	if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) {
+		netdev_err(dev, "Master is either lo or non-ether device\n");
+		return -EINVAL;
+	}
+	port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	port->dev = dev;
+	port->mode = IPVLAN_MODE_L3;
+	INIT_LIST_HEAD(&port->ipvlans);
+	for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++)
+		INIT_HLIST_HEAD(&port->hlhead[idx]);
+
+	err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port);
+	if (err)
+		goto err;
+
+	dev->priv_flags |= IFF_IPVLAN_MASTER;
+	return 0;
+
+err:
+	kfree_rcu(port, rcu);
+	return err;
+}
+
+static void ipvlan_port_destroy(struct net_device *dev)
+{
+	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+
+	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
+	netdev_rx_handler_unregister(dev);
+	kfree_rcu(port, rcu);
+}
+
+/* ipvlan network devices have devices nesting below it and are a special
+ * "super class" of normal network devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key ipvlan_netdev_xmit_lock_key;
+static struct lock_class_key ipvlan_netdev_addr_lock_key;
+
+#define IPVLAN_FEATURES \
+	(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
+	 NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
+	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
+
+#define IPVLAN_STATE_MASK \
+	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
+
+static void ipvlan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &ipvlan_netdev_xmit_lock_key);
+}
+
+static void ipvlan_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &ipvlan_netdev_addr_lock_key);
+	netdev_for_each_tx_queue(dev, ipvlan_set_lockdep_class_one, NULL);
+}
+
+static int ipvlan_init(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	const struct net_device *phy_dev = ipvlan->phy_dev;
+
+	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
+		     (phy_dev->state & IPVLAN_STATE_MASK);
+	dev->features = phy_dev->features & IPVLAN_FEATURES;
+	dev->features |= NETIF_F_LLTX;
+	dev->gso_max_size = phy_dev->gso_max_size;
+	dev->iflink = phy_dev->ifindex;
+	dev->hard_header_len = phy_dev->hard_header_len;
+
+	ipvlan_set_lockdep_class(dev);
+
+	ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats);
+	if (!ipvlan->pcpu_stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void ipvlan_uninit(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan->port;
+
+	if (ipvlan->pcpu_stats)
+		free_percpu(ipvlan->pcpu_stats);
+
+	port->count -= 1;
+	if (!port->count)
+		ipvlan_port_destroy(port->dev);
+}
+
+static int ipvlan_open(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+	struct ipvl_addr *addr;
+
+	if (ipvlan->port->mode == IPVLAN_MODE_L3)
+		dev->flags |= IFF_NOARP;
+	else
+		dev->flags &= ~IFF_NOARP;
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry(addr, &ipvlan->addrs, anode)
+			ipvlan_ht_addr_add(ipvlan, addr);
+	}
+	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+}
+
+static int ipvlan_stop(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+	struct ipvl_addr *addr;
+
+	dev_uc_unsync(phy_dev, dev);
+	dev_mc_unsync(phy_dev, dev);
+
+	dev_uc_del(phy_dev, phy_dev->dev_addr);
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry(addr, &ipvlan->addrs, anode)
+			ipvlan_ht_addr_del(addr, !dev->dismantle);
+	}
+	return 0;
+}
+
+netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	int skblen = skb->len;
+	int ret;
+
+	ret = ipvlan_queue_xmit(skb, dev);
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
+		struct ipvl_pcpu_stats *pcptr;
+
+		pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+
+		u64_stats_update_begin(&pcptr->syncp);
+		pcptr->tx_pkts++;
+		pcptr->tx_bytes += skblen;
+		u64_stats_update_end(&pcptr->syncp);
+	} else {
+		this_cpu_inc(ipvlan->pcpu_stats->tx_drps);
+	}
+	return ret;
+}
+
+static netdev_features_t ipvlan_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+}
+
+static void ipvlan_change_rx_flags(struct net_device *dev, int change)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	if (change & IFF_ALLMULTI)
+		dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1);
+}
+
+static void ipvlan_set_broadcast_mac_filter(struct ipvl_dev *ipvlan, bool set)
+{
+	struct net_device *dev = ipvlan->dev;
+	unsigned int hashbit = ipvlan_mac_hash(dev->broadcast);
+
+	if (set && !test_bit(hashbit, ipvlan->mac_filters))
+		__set_bit(hashbit, ipvlan->mac_filters);
+	else if (!set && test_bit(hashbit, ipvlan->mac_filters))
+		__clear_bit(hashbit, ipvlan->mac_filters);
+}
+
+static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+		bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE);
+	} else {
+		struct netdev_hw_addr *ha;
+		DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+
+		bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+		netdev_for_each_mc_addr(ha, dev)
+			__set_bit(ipvlan_mac_hash(ha->addr), mc_filters);
+
+		bitmap_copy(ipvlan->mac_filters, mc_filters,
+			    IPVLAN_MAC_FILTER_SIZE);
+	}
+	dev_uc_sync(ipvlan->phy_dev, dev);
+	dev_mc_sync(ipvlan->phy_dev, dev);
+}
+
+static struct rtnl_link_stats64 *ipvlan_get_stats64(struct net_device *dev,
+						    struct rtnl_link_stats64 *s)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (ipvlan->pcpu_stats) {
+		struct ipvl_pcpu_stats *pcptr;
+		u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes;
+		u32 rx_errs = 0, tx_drps = 0;
+		u32 strt;
+		int idx;
+
+		for_each_possible_cpu(idx) {
+			pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx);
+			do {
+				strt= u64_stats_fetch_begin_irq(&pcptr->syncp);
+				rx_pkts = pcptr->rx_pkts;
+				rx_bytes = pcptr->rx_bytes;
+				rx_mcast = pcptr->rx_mcast;
+				tx_pkts = pcptr->tx_pkts;
+				tx_bytes = pcptr->tx_bytes;
+			} while (u64_stats_fetch_retry_irq(&pcptr->syncp,
+							   strt));
+
+			s->rx_packets += rx_pkts;
+			s->rx_bytes += rx_bytes;
+			s->multicast += rx_mcast;
+			s->tx_packets += tx_pkts;
+			s->tx_bytes += tx_bytes;
+
+			/* u32 values are updated without syncp protection. */
+			rx_errs += pcptr->rx_errs;
+			tx_drps += pcptr->tx_drps;
+		}
+		s->rx_errors = rx_errs;
+		s->rx_dropped = rx_errs;
+		s->tx_dropped = tx_drps;
+	}
+	return s;
+}
+
+static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	return vlan_vid_add(phy_dev, proto, vid);
+}
+
+static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+				   u16 vid)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	vlan_vid_del(phy_dev, proto, vid);
+	return 0;
+}
+
+static const struct net_device_ops ipvlan_netdev_ops = {
+	.ndo_init		= ipvlan_init,
+	.ndo_uninit		= ipvlan_uninit,
+	.ndo_open		= ipvlan_open,
+	.ndo_stop		= ipvlan_stop,
+	.ndo_start_xmit		= ipvlan_start_xmit,
+	.ndo_fix_features	= ipvlan_fix_features,
+	.ndo_change_rx_flags	= ipvlan_change_rx_flags,
+	.ndo_set_rx_mode	= ipvlan_set_multicast_mac_filter,
+	.ndo_get_stats64	= ipvlan_get_stats64,
+	.ndo_vlan_rx_add_vid	= ipvlan_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= ipvlan_vlan_rx_kill_vid,
+};
+
+static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned len)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	/* TODO Probably use a different field than dev_addr so that the
+	 * mac-address on the virtual device is portable and can be carried
+	 * while the packets use the mac-addr on the physical device.
+	 */
+	return dev_hard_header(skb, phy_dev, type, daddr,
+			       saddr ? : dev->dev_addr, len);
+}
+
+static const struct header_ops ipvlan_header_ops = {
+	.create  	= ipvlan_hard_header,
+	.rebuild	= eth_rebuild_header,
+	.parse		= eth_header_parse,
+	.cache		= eth_header_cache,
+	.cache_update	= eth_header_cache_update,
+};
+
+static int ipvlan_ethtool_get_settings(struct net_device *dev,
+				       struct ethtool_cmd *cmd)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return __ethtool_get_settings(ipvlan->phy_dev, cmd);
+}
+
+static void ipvlan_ethtool_get_drvinfo(struct net_device *dev,
+				       struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version));
+}
+
+static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return ipvlan->msg_enable;
+}
+
+static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	ipvlan->msg_enable = value;
+}
+
+static const struct ethtool_ops ipvlan_ethtool_ops = {
+	.get_link	= ethtool_op_get_link,
+	.get_settings	= ipvlan_ethtool_get_settings,
+	.get_drvinfo	= ipvlan_ethtool_get_drvinfo,
+	.get_msglevel	= ipvlan_ethtool_get_msglevel,
+	.set_msglevel	= ipvlan_ethtool_set_msglevel,
+};
+
+static int ipvlan_nl_changelink(struct net_device *dev,
+				struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+
+	if (data && data[IFLA_IPVLAN_MODE]) {
+		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+		ipvlan_set_port_mode(port, nmode);
+	}
+	return 0;
+}
+
+static size_t ipvlan_nl_getsize(const struct net_device *dev)
+{
+	return (0
+		+ nla_total_size(2) /* IFLA_IPVLAN_MODE */
+		);
+}
+
+static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (data && data[IFLA_IPVLAN_MODE]) {
+		u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+		if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int ipvlan_nl_fillinfo(struct sk_buff *skb,
+			      const struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+	int ret = -EINVAL;
+
+	if (!port)
+		goto err;
+
+	ret = -EMSGSIZE;
+	if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode))
+		goto err;
+
+	return 0;
+
+err:
+	return ret;
+}
+
+static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+			   struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port;
+	struct net_device *phy_dev;
+	int err;
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+
+	phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	if (!phy_dev)
+		return -ENODEV;
+
+	if (ipvlan_dev_slave(phy_dev)) {
+		struct ipvl_dev *tmp = netdev_priv(phy_dev);
+
+		phy_dev = tmp->phy_dev;
+	} else if (!ipvlan_dev_master(phy_dev)) {
+		err = ipvlan_port_create(phy_dev);
+		if (err < 0)
+			return err;
+	}
+
+	port = ipvlan_port_get_rtnl(phy_dev);
+	if (data && data[IFLA_IPVLAN_MODE])
+		port->mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+	ipvlan->phy_dev = phy_dev;
+	ipvlan->dev = dev;
+	ipvlan->port = port;
+	ipvlan->sfeatures = IPVLAN_FEATURES;
+	INIT_LIST_HEAD(&ipvlan->addrs);
+	ipvlan->ipv4cnt = 0;
+	ipvlan->ipv6cnt = 0;
+
+	/* TODO Probably put random address here to be presented to the
+	 * world but keep using the physical-dev address for the outgoing
+	 * packets.
+	 */
+	memcpy(dev->dev_addr, phy_dev->dev_addr, ETH_ALEN);
+
+	dev->priv_flags |= IFF_IPVLAN_SLAVE;
+
+	port->count += 1;
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto ipvlan_destroy_port;
+
+	err = netdev_upper_dev_link(phy_dev, dev);
+	if (err)
+		goto ipvlan_destroy_port;
+
+	list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
+	netif_stacked_transfer_operstate(phy_dev, dev);
+	return 0;
+
+ipvlan_destroy_port:
+	port->count -= 1;
+	if (!port->count)
+		ipvlan_port_destroy(phy_dev);
+
+	return err;
+}
+
+static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_addr *addr, *next;
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
+			ipvlan_ht_addr_del(addr, !dev->dismantle);
+			list_del_rcu(&addr->anode);
+		}
+	}
+	list_del_rcu(&ipvlan->pnode);
+	unregister_netdevice_queue(dev, head);
+	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
+}
+
+static void ipvlan_link_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->netdev_ops = &ipvlan_netdev_ops;
+	dev->destructor = free_netdev;
+	dev->header_ops = &ipvlan_header_ops;
+	dev->ethtool_ops = &ipvlan_ethtool_ops;
+	dev->tx_queue_len = 0;
+}
+
+static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
+{
+	[IFLA_IPVLAN_MODE] = { .type = NLA_U16 },
+};
+
+static struct rtnl_link_ops ipvlan_link_ops = {
+	.kind		= "ipvlan",
+	.priv_size	= sizeof(struct ipvl_dev),
+
+	.get_size	= ipvlan_nl_getsize,
+	.policy		= ipvlan_nl_policy,
+	.validate	= ipvlan_nl_validate,
+	.fill_info	= ipvlan_nl_fillinfo,
+	.changelink	= ipvlan_nl_changelink,
+	.maxtype	= IFLA_IPVLAN_MAX,
+
+	.setup		= ipvlan_link_setup,
+	.newlink	= ipvlan_link_new,
+	.dellink	= ipvlan_link_delete,
+};
+
+int ipvlan_link_register(struct rtnl_link_ops *ops)
+{
+	return rtnl_link_register(ops);
+}
+
+static int ipvlan_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ipvl_dev *ipvlan, *next;
+	struct ipvl_port *port;
+	LIST_HEAD(lst_kill);
+
+	if (!ipvlan_dev_master(dev))
+		return NOTIFY_DONE;
+
+	port = ipvlan_port_get_rtnl(dev);
+
+	switch (event) {
+	case NETDEV_CHANGE:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			netif_stacked_transfer_operstate(ipvlan->phy_dev,
+							 ipvlan->dev);
+		break;
+
+	case NETDEV_UNREGISTER:
+		if (dev->reg_state != NETREG_UNREGISTERING)
+			break;
+
+		list_for_each_entry_safe(ipvlan, next, &port->ipvlans,
+					 pnode)
+			ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev,
+							    &lst_kill);
+		unregister_netdevice_many(&lst_kill);
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
+			ipvlan->dev->gso_max_size = dev->gso_max_size;
+			netdev_features_change(ipvlan->dev);
+		}
+		break;
+
+	case NETDEV_CHANGEMTU:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			ipvlan_adjust_mtu(ipvlan, dev);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlying device to change its type. */
+		return NOTIFY_BAD;
+	}
+	return NOTIFY_DONE;
+}
+
+static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	struct ipvl_addr *addr;
+
+	if (ipvlan_addr_busy(ipvlan, ip6_addr, true)) {
+		netif_err(ipvlan, ifup, ipvlan->dev,
+			  "Failed to add IPv6=%pI6c addr for %s intf\n",
+			  ip6_addr, ipvlan->dev->name);
+		return -EINVAL;
+	}
+	addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	addr->master = ipvlan;
+	memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr));
+	addr->atype = IPVL_IPV6;
+	list_add_tail_rcu(&addr->anode, &ipvlan->addrs);
+	ipvlan->ipv6cnt++;
+	ipvlan_ht_addr_add(ipvlan, addr);
+
+	return 0;
+}
+
+static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	struct ipvl_addr *addr;
+
+	addr = ipvlan_ht_addr_lookup(ipvlan->port, ip6_addr, true);
+	if (!addr)
+		return;
+
+	ipvlan_ht_addr_del(addr, true);
+	list_del_rcu(&addr->anode);
+	ipvlan->ipv6cnt--;
+	WARN_ON(ipvlan->ipv6cnt < 0);
+	kfree_rcu(addr, rcu);
+
+	return;
+}
+
+static int ipvlan_addr6_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr;
+	struct net_device *dev = (struct net_device *)if6->idev->dev;
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (!ipvlan_dev_slave(dev))
+		return NOTIFY_DONE;
+
+	if (!ipvlan || !ipvlan->port)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UP:
+		if (ipvlan_add_addr6(ipvlan, &if6->addr))
+			return NOTIFY_BAD;
+		break;
+
+	case NETDEV_DOWN:
+		ipvlan_del_addr6(ipvlan, &if6->addr);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+	struct ipvl_addr *addr;
+
+	if (ipvlan_addr_busy(ipvlan, ip4_addr, false)) {
+		netif_err(ipvlan, ifup, ipvlan->dev,
+			  "Failed to add IPv4=%pI4 on %s intf.\n",
+			  ip4_addr, ipvlan->dev->name);
+		return -EINVAL;
+	}
+	addr = kzalloc(sizeof(struct ipvl_addr), GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+
+	addr->master = ipvlan;
+	memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr));
+	addr->atype = IPVL_IPV4;
+	list_add_tail_rcu(&addr->anode, &ipvlan->addrs);
+	ipvlan->ipv4cnt++;
+	ipvlan_ht_addr_add(ipvlan, addr);
+	ipvlan_set_broadcast_mac_filter(ipvlan, true);
+
+	return 0;
+}
+
+static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+	struct ipvl_addr *addr;
+
+	addr = ipvlan_ht_addr_lookup(ipvlan->port, ip4_addr, false);
+	if (!addr)
+		return;
+
+	ipvlan_ht_addr_del(addr, true);
+	list_del_rcu(&addr->anode);
+	ipvlan->ipv4cnt--;
+	WARN_ON(ipvlan->ipv4cnt < 0);
+	if (!ipvlan->ipv4cnt)
+	    ipvlan_set_broadcast_mac_filter(ipvlan, false);
+	kfree_rcu(addr, rcu);
+
+	return;
+}
+
+static int ipvlan_addr4_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct in_ifaddr *if4 = (struct in_ifaddr *)ptr;
+	struct net_device *dev = (struct net_device *)if4->ifa_dev->dev;
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct in_addr ip4_addr;
+
+	if (!ipvlan_dev_slave(dev))
+		return NOTIFY_DONE;
+
+	if (!ipvlan || !ipvlan->port)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UP:
+		ip4_addr.s_addr = if4->ifa_address;
+		if (ipvlan_add_addr4(ipvlan, &ip4_addr))
+			return NOTIFY_BAD;
+		break;
+
+	case NETDEV_DOWN:
+		ip4_addr.s_addr = if4->ifa_address;
+		ipvlan_del_addr4(ipvlan, &ip4_addr);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_addr4_event,
+};
+
+static struct notifier_block ipvlan_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_device_event,
+};
+
+static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_addr6_event,
+};
+
+static int __init ipvlan_init_module(void)
+{
+	int err;
+
+	ipvlan_init_secret();
+	register_netdevice_notifier(&ipvlan_notifier_block);
+	register_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+	register_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+
+	err = ipvlan_link_register(&ipvlan_link_ops);
+	if (err < 0)
+		goto error;
+
+	return 0;
+error:
+	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+	unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+	unregister_netdevice_notifier(&ipvlan_notifier_block);
+	return err;
+}
+
+static void __exit ipvlan_cleanup_module(void)
+{
+	rtnl_link_unregister(&ipvlan_link_ops);
+	unregister_netdevice_notifier(&ipvlan_notifier_block);
+	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+	unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+}
+
+module_init(ipvlan_init_module);
+module_exit(ipvlan_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
+MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs");
+MODULE_ALIAS_RTNL_LINK("ipvlan");

include/linux/netdevice.h

@@ -1230,6 +1230,8 @@ enum netdev_priv_flags {
 	IFF_LIVE_ADDR_CHANGE		= 1<<20,
 	IFF_MACVLAN			= 1<<21,
 	IFF_XMIT_DST_RELEASE_PERM	= 1<<22,
+	IFF_IPVLAN_MASTER		= 1<<23,
+	IFF_IPVLAN_SLAVE		= 1<<24,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1255,6 +1257,8 @@ enum netdev_priv_flags {
 #define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
 #define IFF_MACVLAN			IFF_MACVLAN
 #define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
+#define IFF_IPVLAN_MASTER		IFF_IPVLAN_MASTER
+#define IFF_IPVLAN_SLAVE		IFF_IPVLAN_SLAVE
 
 /**
  *	struct net_device - The DEVICE structure.

include/uapi/linux/if_link.h

@@ -330,6 +330,21 @@ enum macvlan_macaddr_mode {
 
 #define MACVLAN_FLAG_NOPROMISC	1
 
+/* IPVLAN section */
+enum {
+	IFLA_IPVLAN_UNSPEC,
+	IFLA_IPVLAN_MODE,
+	__IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+	IPVLAN_MODE_L2 = 0,
+	IPVLAN_MODE_L3,
+	IPVLAN_MODE_MAX
+};
+
 /* VXLAN section */
 enum {
 	IFLA_VXLAN_UNSPEC,