path: root/net/ipv4/ip_vti.c

/*
 *	Linux NET3: IP/IP protocol decoder modified to support
 *		    virtual tunnel interface
 *
 *	Authors:
 *		Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012
 *
 *	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.
 *
 */

/*
   This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c

   For comments look at net/ipv4/ip_gre.c --ANK
 */


#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

#define HASH_SIZE  16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1))

static struct rtnl_link_ops vti_link_ops __read_mostly;

static int vti_net_id __read_mostly;
struct vti_net {
	struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_wc[1];
	struct ip_tunnel __rcu **tunnels[4];

	struct net_device *fb_tunnel_dev;
};

static int vti_fb_tunnel_init(struct net_device *dev);
static int vti_tunnel_init(struct net_device *dev);
static void vti_tunnel_setup(struct net_device *dev);
static void vti_dev_free(struct net_device *dev);
static int vti_tunnel_bind_dev(struct net_device *dev);

/* Locking : hash tables are protected by RCU and RTNL */

#define for_each_ip_tunnel_rcu(start) \
	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))

/* often modified stats are per cpu, other are shared (netdev->stats) */
struct pcpu_tstats {
	u64	rx_packets;
	u64	rx_bytes;
	u64	tx_packets;
	u64	tx_bytes;
	struct	u64_stats_sync	syncp;
};

#define VTI_XMIT(stats1, stats2) do {				\
	int err;						\
	int pkt_len = skb->len;					\
	err = dst_output(skb);					\
	if (net_xmit_eval(err) == 0) {				\
		u64_stats_update_begin(&(stats1)->syncp);	\
		(stats1)->tx_bytes += pkt_len;			\
		(stats1)->tx_packets++;				\
		u64_stats_update_end(&(stats1)->syncp);		\
	} else {						\
		(stats2)->tx_errors++;				\
		(stats2)->tx_aborted_errors++;			\
	}							\
} while (0)


static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev,
						 struct rtnl_link_stats64 *tot)
{
	int i;

	for_each_possible_cpu(i) {
		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
		unsigned int start;

		do {
			start = u64_stats_fetch_begin_bh(&tstats->syncp);
			rx_packets = tstats->rx_packets;
			tx_packets = tstats->tx_packets;
			rx_bytes = tstats->rx_bytes;
			tx_bytes = tstats->tx_bytes;
		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));

		tot->rx_packets += rx_packets;
		tot->tx_packets += tx_packets;
		tot->rx_bytes   += rx_bytes;
		tot->tx_bytes   += tx_bytes;
	}

	tot->multicast = dev->stats.multicast;
	tot->rx_crc_errors = dev->stats.rx_crc_errors;
	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
	tot->rx_length_errors = dev->stats.rx_length_errors;
	tot->rx_errors = dev->stats.rx_errors;
	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
	tot->tx_dropped = dev->stats.tx_dropped;
	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
	tot->tx_errors = dev->stats.tx_errors;

	return tot;
}

static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
					   __be32 remote, __be32 local)
{
	unsigned h0 = HASH(remote);
	unsigned h1 = HASH(local);
	struct ip_tunnel *t;
	struct vti_net *ipn = net_generic(net, vti_net_id);

	for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
		if (local == t->parms.iph.saddr &&
		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;
	for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;

	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
			return t;

	for_each_ip_tunnel_rcu(ipn->tunnels_wc[0])
		if (t && (t->dev->flags&IFF_UP))