aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/xen-netback/interface.c
blob: b7d41f8c338a8372cea8bfe6649386c6a0d8b090 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
/*
 * Network-device interface management.
 *
 * Copyright (c) 2004-2005, Keir Fraser
 *
 * 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; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include "common.h"

#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>

#include <xen/events.h>
#include <asm/xen/hypercall.h>

#define XENVIF_QUEUE_LENGTH 32

void xenvif_get(struct xenvif *vif)
{
	atomic_inc(&vif->refcnt);
}

void xenvif_put(struct xenvif *vif)
{
	if (atomic_dec_and_test(&vif->refcnt))
		wake_up(&vif->waiting_to_free);
}

int xenvif_schedulable(struct xenvif *vif)
{
	return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
}

static int xenvif_rx_schedulable(struct xenvif *vif)
{
	return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif);
}

static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
{
	struct xenvif *vif = dev_id;

	if (vif->netbk == NULL)
		return IRQ_NONE;

	xen_netbk_schedule_xenvif(vif);

	if (xenvif_rx_schedulable(vif))
		netif_wake_queue(vif->dev);

	return IRQ_HANDLED;
}

static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);

	BUG_ON(skb->dev != dev);

	if (vif->netbk == NULL)
		goto drop;

	/* Drop the packet if the target domain has no receive buffers. */
	if (!xenvif_rx_schedulable(vif))
		goto drop;

	/* Reserve ring slots for the worst-case number of fragments. */
	vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb);
	xenvif_get(vif);

	if (vif->can_queue && xen_netbk_must_stop_queue(vif))
		netif_stop_queue(dev);

	xen_netbk_queue_tx_skb(vif, skb);

	return NETDEV_TX_OK;

 drop:
	vif->dev->stats.tx_dropped++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb)
{
	netif_rx_ni(skb);
}

void xenvif_notify_tx_completion(struct xenvif *vif)
{
	if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
		netif_wake_queue(vif->dev);
}

static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	return &vif->dev->stats;
}

static void xenvif_up(struct xenvif *vif)
{
	xen_netbk_add_xenvif(vif);
	enable_irq(vif->irq);
	xen_netbk_check_rx_xenvif(vif);
}

static void xenvif_down(struct xenvif *vif)
{
	disable_irq(vif->irq);
	xen_netbk_deschedule_xenvif(vif);
	xen_netbk_remove_xenvif(vif);
}

static int xenvif_open(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (netif_carrier_ok(dev))
		xenvif_up(vif);
	netif_start_queue(dev);
	return 0;
}

static int xenvif_close(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (netif_carrier_ok(dev))
		xenvif_down(vif);
	netif_stop_queue(dev);
	return 0;
}

static int xenvif_change_mtu(struct net_device *dev, int mtu)
{
	struct xenvif *vif = netdev_priv(dev);
	int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN;

	if (mtu > max)
		return -EINVAL;
	dev->mtu = mtu;
	return 0;
}

static netdev_features_t xenvif_fix_features(struct net_device *dev,
	netdev_features_t features)
{
	struct xenvif *vif = netdev_priv(dev);

	if (!vif->can_sg)
		features &= ~NETIF_F_SG;
	if (!vif->gso && !vif->gso_prefix)
		features &= ~NETIF_F_TSO;
	if (!vif->csum)
		features &= ~NETIF_F_IP_CSUM;

	return features;
}

static const struct xenvif_stat {
	char name[ETH_GSTRING_LEN];
	u16 offset;
} xenvif_stats[] = {
	{
		"rx_gso_checksum_fixup",
		offsetof(struct xenvif, rx_gso_checksum_fixup)
	},
};

static int xenvif_get_sset_count(struct net_device *dev, int string_set)
{
	switch (string_set) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(xenvif_stats);
	default:
		return -EINVAL;
	}
}

static void xenvif_get_ethtool_stats(struct net_device *dev,
				     struct ethtool_stats *stats, u64 * data)
{
	void *vif = netdev_priv(dev);
	int i;

	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
		data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
}

static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
	int i;

	switch (stringset) {
	case ETH_SS_STATS:
		for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
			memcpy(data + i * ETH_GSTRING_LEN,
			       xenvif_stats[i].name, ETH_GSTRING_LEN);
		break;
	}
}

static const struct ethtool_ops xenvif_ethtool_ops = {
	.get_link	= ethtool_op_get_link,

	.get_sset_count = xenvif_get_sset_count,
	.get_ethtool_stats = xenvif_get_ethtool_stats,
	.get_strings = xenvif_get_strings,
};

static const struct net_device_ops xenvif_netdev_ops = {
	.ndo_start_xmit	= xenvif_start_xmit,
	.ndo_get_stats	= xenvif_get_stats,
	.ndo_open	= xenvif_open,
	.ndo_stop	= xenvif_close,
	.ndo_change_mtu	= xenvif_change_mtu,
	.ndo_fix_features = xenvif_fix_features,
};

struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
			    unsigned int handle)
{
	int err;
	struct net_device *dev;
	struct xenvif *vif;
	char name[IFNAMSIZ] = {};

	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
	dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
	if (dev == NULL) {
		pr_warn("Could not allocate netdev\n");
		return ERR_PTR(-ENOMEM);
	}

	SET_NETDEV_DEV(dev, parent);

	vif = netdev_priv(dev);
	vif->domid  = domid;
	vif->handle = handle;
	vif->netbk  = NULL;
	vif->can_sg = 1;
	vif->csum = 1;
	atomic_set(&vif->refcnt, 1);
	init_waitqueue_head(&vif->waiting_to_free);
	vif->dev = dev;
	INIT_LIST_HEAD(&vif->schedule_list);
	INIT_LIST_HEAD(&vif->notify_list);

	vif->credit_bytes = vif->remaining_credit = ~0UL;
	vif->credit_usec  = 0UL;
	init_timer(&vif->credit_timeout);
	/* Initialize 'expires' now: it's used to track the credit window. */
	vif->credit_timeout.expires = jiffies;

	dev->netdev_ops	= &xenvif_netdev_ops;
	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
	dev->features = dev->hw_features;
	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);

	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;

	/*
	 * Initialise a dummy MAC address. We choose the numerically
	 * largest non-broadcast address to prevent the address getting
	 * stolen by an Ethernet bridge for STP purposes.
	 * (FE:FF:FF:FF:FF:FF)
	 */
	memset(dev->dev_addr, 0xFF, ETH_ALEN);
	dev->dev_addr[0] &= ~0x01;

	netif_carrier_off(dev);

	err = register_netdev(dev);
	if (err) {
		netdev_warn(dev, "Could not register device: err=%d\n", err);
		free_netdev(dev);
		return ERR_PTR(err);
	}

	netdev_dbg(dev, "Successfully created xenvif\n");
	return vif;
}

int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
		   unsigned long rx_ring_ref, unsigned int evtchn)
{
	int err = -ENOMEM;

	/* Already connected through? */
	if (vif->irq)
		return 0;

	err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
	if (err < 0)
		goto err;

	err = bind_interdomain_evtchn_to_irqhandler(
		vif->domid, evtchn, xenvif_interrupt, 0,
		vif->dev->name, vif);
	if (err < 0)
		goto err_unmap;
	vif->irq = err;
	disable_irq(vif->irq);

	xenvif_get(vif);

	rtnl_lock();
	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
		dev_set_mtu(vif->dev, ETH_DATA_LEN);
	netdev_update_features(vif->dev);
	netif_carrier_on(vif->dev);
	if (netif_running(vif->dev))
		xenvif_up(vif);
	rtnl_unlock();

	return 0;
err_unmap:
	xen_netbk_unmap_frontend_rings(vif);
err:
	return err;
}

void xenvif_disconnect(struct xenvif *vif)
{
	struct net_device *dev = vif->dev;
	if (netif_carrier_ok(dev)) {
		rtnl_lock();
		netif_carrier_off(dev); /* discard queued packets */
		if (netif_running(dev))
			xenvif_down(vif);
		rtnl_unlock();
		xenvif_put(vif);
	}

	atomic_dec(&vif->refcnt);
	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);

	del_timer_sync(&vif->credit_timeout);

	if (vif->irq)
		unbind_from_irqhandler(vif->irq, vif);

	unregister_netdev(vif->dev);

	xen_netbk_unmap_frontend_rings(vif);

	free_netdev(vif->dev);
}
s='alt'>


                                                       
                                                   







                                                                        

                                                                 





























                                                                        

                                                                   



















                                                                    







                                                             

                                                                 
 

                                                                        


                                           


                                                                   





                                                           

                                   
                                       

                         










                                                                               






                                                                     
                







                                                    
                                                                         
































                                                                         
                                                 




                                     



                                                           









                               




                                                                    
 

                                                                   
 
                                                           

                                                                           

                                       
 


                                            
 


                                                 

         

                                                                 




                                                     
                                           

                                           
                                               
                                                 

  
                                                    
 

                                                  

 
                                                  
 




                                                    









                                                                       
 
                                   

 
                                                                 


                                                    
 


                                               







                                                       


                                                   
                                  
 
                                                                            
                


                                               
                 



                                                    
                                                                 
                                                 





                                               
                                             




































                                                                          
                                    
 

                                                  




                                                                      
                                
 
                                    
                                                 
































































                                                                               
                                                             



























                                                                
/*
 *	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/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

static struct rtnl_link_ops vti_link_ops __read_mostly;

static int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);

static int vti_err(struct sk_buff *skb, u32 info)
{

	/* All the routers (except for Linux) return only
	 * 8 bytes of packet payload. It means, that precise relaying of
	 * ICMP in the real Internet is absolutely infeasible.
	 */
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
	struct iphdr *iph = (struct iphdr *)skb->data;
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	struct ip_tunnel *t;
	int err;

	switch (type) {
	default:
	case ICMP_PARAMETERPROB:
		return 0;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return 0;
		default:
			/* All others are translated to HOST_UNREACH. */
			break;
		}
		break;
	case ICMP_TIME_EXCEEDED:
		if (code != ICMP_EXC_TTL)
			return 0;
		break;
	}

	err = -ENOENT;

	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
			     iph->daddr, iph->saddr, 0);
	if (t == NULL)
		goto out;

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
				 t->parms.link, 0, IPPROTO_IPIP, 0);
		err = 0;
		goto out;
	}

	err = 0;
	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
		goto out;

	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
		t->err_count++;
	else
		t->err_count = 1;
	t->err_time = jiffies;
out:
	return err;
}

/* We dont digest the packet therefore let the packet pass */
static int vti_rcv(struct sk_buff *skb)
{
	struct ip_tunnel *tunnel;
	const struct iphdr *iph = ip_hdr(skb);
	struct net *net = dev_net(skb->dev);
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);

	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
				  iph->saddr, iph->daddr, 0);
	if (tunnel != NULL) {
		struct pcpu_tstats *tstats;

		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
			return -1;

		tstats = this_cpu_ptr(tunnel->dev->tstats);
		u64_stats_update_begin(&tstats->syncp);
		tstats->rx_packets++;
		tstats->rx_bytes += skb->len;
		u64_stats_update_end(&tstats->syncp);

		skb->mark = 0;
		secpath_reset(skb);
		skb->dev = tunnel->dev;
		return 1;
	}

	return -1;
}

/* This function assumes it is being called from dev_queue_xmit()
 * and that skb is filled properly by that function.
 */

static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr  *tiph = &tunnel->parms.iph;
	u8     tos;
	struct rtable *rt;		/* Route to the other host */
	struct net_device *tdev;	/* Device to other host */
	struct iphdr  *old_iph = ip_hdr(skb);
	__be32 dst = tiph->daddr;
	struct flowi4 fl4;
	int err;

	if (skb->protocol != htons(ETH_P_IP))
		goto tx_error;

	tos = old_iph->tos;

	memset(&fl4, 0, sizeof(fl4));
	flowi4_init_output(&fl4, tunnel->parms.link,
			   be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
			   RT_SCOPE_UNIVERSE,
			   IPPROTO_IPIP, 0,
			   dst, tiph->saddr, 0, 0);
	rt = ip_route_output_key(dev_net(dev), &fl4);
	if (IS_ERR(rt)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}
	/* if there is no transform then this tunnel is not functional.
	 * Or if the xfrm is not mode tunnel.
	 */
	if (!rt->dst.xfrm ||
	    rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}
	tdev = rt->dst.dev;

	if (tdev == dev) {
		ip_rt_put(rt);
		dev->stats.collisions++;
		goto tx_error;
	}

	if (tunnel->err_count > 0) {
		if (time_before(jiffies,
				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
			tunnel->err_count--;
			dst_link_failure(skb);
		} else
			tunnel->err_count = 0;
	}

	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);
	nf_reset(skb);
	skb->dev = skb_dst(skb)->dev;

	err = dst_output(skb);
	if (net_xmit_eval(err) == 0)
		err = skb->len;
	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
	return NETDEV_TX_OK;

tx_error_icmp:
	dst_link_failure(skb);
tx_error:
	dev->stats.tx_errors++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static int
vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip_tunnel_parm p;

	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
		return -EFAULT;

	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
		    p.iph.ihl != 5)
			return -EINVAL;
	}

	err = ip_tunnel_ioctl(dev, &p, cmd);
	if (err)
		return err;

	if (cmd != SIOCDELTUNNEL) {
		p.i_flags |= GRE_KEY | VTI_ISVTI;
		p.o_flags |= GRE_KEY;
	}

	if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
		return -EFAULT;
	return 0;
}

static const struct net_device_ops vti_netdev_ops = {
	.ndo_init	= vti_tunnel_init,
	.ndo_uninit	= ip_tunnel_uninit,
	.ndo_start_xmit	= vti_tunnel_xmit,
	.ndo_do_ioctl	= vti_tunnel_ioctl,
	.ndo_change_mtu	= ip_tunnel_change_mtu,
	.ndo_get_stats64 = ip_tunnel_get_stats64,
};

static void vti_tunnel_setup(struct net_device *dev)
{
	dev->netdev_ops		= &vti_netdev_ops;
	ip_tunnel_setup(dev, vti_net_id);
}

static int vti_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	memcpy(dev->dev_addr, &iph->saddr, 4);
	memcpy(dev->broadcast, &iph->daddr, 4);

	dev->type		= ARPHRD_TUNNEL;
	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
	dev->mtu		= ETH_DATA_LEN;
	dev->flags		= IFF_NOARP;
	dev->iflink		= 0;
	dev->addr_len		= 4;
	dev->features		|= NETIF_F_NETNS_LOCAL;
	dev->features		|= NETIF_F_LLTX;
	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;

	return ip_tunnel_init(dev);
}

static void __net_init vti_fb_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	iph->version		= 4;
	iph->protocol		= IPPROTO_IPIP;
	iph->ihl		= 5;
}

static struct xfrm_tunnel vti_handler __read_mostly = {
	.handler	=	vti_rcv,
	.err_handler	=	vti_err,
	.priority	=	1,
};

static int __net_init vti_init_net(struct net *net)
{
	int err;
	struct ip_tunnel_net *itn;

	err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0");
	if (err)
		return err;
	itn = net_generic(net, vti_net_id);
	vti_fb_tunnel_init(itn->fb_tunnel_dev);
	return 0;
}

static void __net_exit vti_exit_net(struct net *net)
{
	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
	ip_tunnel_delete_net(itn, &vti_link_ops);
}

static struct pernet_operations vti_net_ops = {
	.init = vti_init_net,
	.exit = vti_exit_net,
	.id   = &vti_net_id,
	.size = sizeof(struct ip_tunnel_net),
};

static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
{
	return 0;
}

static void vti_netlink_parms(struct nlattr *data[],
			      struct ip_tunnel_parm *parms)
{
	memset(parms, 0, sizeof(*parms));

	parms->iph.protocol = IPPROTO_IPIP;

	if (!data)
		return;

	if (data[IFLA_VTI_LINK])
		parms->link = nla_get_u32(data[IFLA_VTI_LINK]);

	if (data[IFLA_VTI_IKEY])
		parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);

	if (data[IFLA_VTI_OKEY])
		parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);

	if (data[IFLA_VTI_LOCAL])
		parms->iph.saddr = nla_get_be32(data[IFLA_VTI_LOCAL]);

	if (data[IFLA_VTI_REMOTE])
		parms->iph.daddr = nla_get_be32(data[IFLA_VTI_REMOTE]);

}

static int vti_newlink(struct net *src_net, struct net_device *dev,
		       struct nlattr *tb[], struct nlattr *data[])
{
	struct ip_tunnel_parm parms;

	vti_netlink_parms(data, &parms);
	return ip_tunnel_newlink(dev, tb, &parms);
}

static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
			  struct nlattr *data[])
{
	struct ip_tunnel_parm p;

	vti_netlink_parms(data, &p);
	return ip_tunnel_changelink(dev, tb, &p);
}

static size_t vti_get_size(const struct net_device *dev)
{
	return
		/* IFLA_VTI_LINK */
		nla_total_size(4) +
		/* IFLA_VTI_IKEY */
		nla_total_size(4) +
		/* IFLA_VTI_OKEY */
		nla_total_size(4) +
		/* IFLA_VTI_LOCAL */
		nla_total_size(4) +
		/* IFLA_VTI_REMOTE */
		nla_total_size(4) +
		0;
}

static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);
	struct ip_tunnel_parm *p = &t->parms;

	nla_put_u32(skb, IFLA_VTI_LINK, p->link);
	nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key);
	nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key);
	nla_put_be32(skb, IFLA_VTI_LOCAL, p->iph.saddr);
	nla_put_be32(skb, IFLA_VTI_REMOTE, p->iph.daddr);

	return 0;
}

static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
	[IFLA_VTI_LINK]		= { .type = NLA_U32 },
	[IFLA_VTI_IKEY]		= { .type = NLA_U32 },
	[IFLA_VTI_OKEY]		= { .type = NLA_U32 },
	[IFLA_VTI_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
	[IFLA_VTI_REMOTE]	= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
};

static struct rtnl_link_ops vti_link_ops __read_mostly = {
	.kind		= "vti",
	.maxtype	= IFLA_VTI_MAX,
	.policy		= vti_policy,
	.priv_size	= sizeof(struct ip_tunnel),
	.setup		= vti_tunnel_setup,
	.validate	= vti_tunnel_validate,
	.newlink	= vti_newlink,
	.changelink	= vti_changelink,
	.get_size	= vti_get_size,
	.fill_info	= vti_fill_info,
};

static int __init vti_init(void)
{
	int err;

	pr_info("IPv4 over IPSec tunneling driver\n");

	err = register_pernet_device(&vti_net_ops);
	if (err < 0)
		return err;
	err = xfrm4_mode_tunnel_input_register(&vti_handler);
	if (err < 0) {
		unregister_pernet_device(&vti_net_ops);
		pr_info("vti init: can't register tunnel\n");
	}

	err = rtnl_link_register(&vti_link_ops);
	if (err < 0)
		goto rtnl_link_failed;

	return err;

rtnl_link_failed:
	xfrm4_mode_tunnel_input_deregister(&vti_handler);
	unregister_pernet_device(&vti_net_ops);
	return err;
}

static void __exit vti_fini(void)
{
	rtnl_link_unregister(&vti_link_ops);
	if (xfrm4_mode_tunnel_input_deregister(&vti_handler))
		pr_info("vti close: can't deregister tunnel\n");

	unregister_pernet_device(&vti_net_ops);
}

module_init(vti_init);
module_exit(vti_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");