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>

1 files changed, 130 insertions, 0 deletions

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
new file mode 100644
index 000000000000..ab3e7614ed71
--- /dev/null
+++ b/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 */