summaryrefslogtreecommitdiffstats
path: root/drivers/net/ipvlan/ipvlan_main.c
blob: c6aa667b50cdfcaf78f9af0d9111cc8c1c627dc8 (plain)
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
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
/* 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 ipvl_nf_hook_refcnt = 0;

static struct nf_hook_ops ipvl_nfops[] __read_mostly = {
	{
		.hook     = ipvlan_nf_input,
		.pf       = NFPROTO_IPV4,
		.hooknum  = NF_INET_LOCAL_IN,
		.priority = INT_MAX,
	},
	{
		.hook     = ipvlan_nf_input,
		.pf       = NFPROTO_IPV6,
		.hooknum  = NF_INET_LOCAL_IN,
		.priority = INT_MAX,
	},
};

static const struct l3mdev_ops ipvl_l3mdev_ops = {
	.l3mdev_l3_rcv = ipvlan_l3_rcv,
};

static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
{
	ipvlan->dev->mtu = dev->mtu;
}

static int ipvlan_register_nf_hook(void)
{
	int err = 0;

	if (!ipvl_nf_hook_refcnt) {
		err = _nf_register_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops));
		if (!err)
			ipvl_nf_hook_refcnt = 1;
	} else {
		ipvl_nf_hook_refcnt++;
	}

	return err;
}

static void ipvlan_unregister_nf_hook(void)
{
	WARN_ON(!ipvl_nf_hook_refcnt);

	ipvl_nf_hook_refcnt--;
	if (!ipvl_nf_hook_refcnt)
		_nf_unregister_hooks(ipvl_nfops, ARRAY_SIZE(ipvl_nfops));
}

static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
{
	struct ipvl_dev *ipvlan;
	struct net_device *mdev = port->dev;
	int err = 0;

	ASSERT_RTNL();
	if (port->mode != nval) {
		if (nval == IPVLAN_MODE_L3S) {
			/* New mode is L3S */
			err = ipvlan_register_nf_hook();
			if (!err) {
				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
				mdev->priv_flags |= IFF_L3MDEV_MASTER;
			} else
				return err;
		} else if (port->mode == IPVLAN_MODE_L3S) {
			/* Old mode was L3S */
			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
			ipvlan_unregister_nf_hook();
			mdev->l3mdev_ops = NULL;
		}
		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
				ipvlan->dev->flags |= IFF_NOARP;
			else
				ipvlan->dev->flags &= ~IFF_NOARP;
		}
		port->mode = nval;
	}
	return err;
}

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;
	}

	if (netif_is_macvlan_port(dev)) {
		netdev_err(dev, "Master is a macvlan port.\n");
		return -EBUSY;
	}

	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]);

	skb_queue_head_init(&port->backlog);
	INIT_WORK(&port->wq, ipvlan_process_multicast);

	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;
	if (port->mode == IPVLAN_MODE_L3S) {
		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
		ipvlan_unregister_nf_hook();
		dev->l3mdev_ops = NULL;
	}
	netdev_rx_handler_unregister(dev);
	cancel_work_sync(&port->wq);
	__skb_queue_purge(&port->backlog);
	kfree_rcu(port, rcu);
}

#define IPVLAN_FEATURES \
	(NETIF_F_SG | NETIF_F_HW_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 int ipvlan_init(struct net_device *dev)
{
	struct ipvl_dev *ipvlan = netdev_priv(dev);
	const struct net_device *phy_dev = ipvlan->phy_dev;
	struct ipvl_port *port = ipvlan->port;

	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->gso_max_segs = phy_dev->gso_max_segs;
	dev->hard_header_len = phy_dev->hard_header_len;

	netdev_lockdep_set_classes(dev);

	ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats);
	if (!ipvlan->pcpu_stats)
		return -ENOMEM;

	port->count += 1;

	return 0;
}

static void ipvlan_uninit(struct net_device *dev)
{
	struct ipvl_dev *ipvlan = netdev_priv(dev);
	struct ipvl_port *port = ipvlan->port;

	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 ||
	    ipvlan->port->mode == IPVLAN_MODE_L3S)
		dev->flags |= IFF_NOARP;
	else
		dev->flags &= ~IFF_NOARP;

	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);

	list_for_each_entry(addr, &ipvlan->addrs, anode)
		ipvlan_ht_addr_del(addr);

	return 0;
}

static 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_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);

		/* Turn-on broadcast bit irrespective of address family,
		 * since broadcast is deferred to a work-queue, hence no
		 * impact on fast-path processing.
		 */
		__set_bit(ipvlan_mac_hash(dev->broadcast), 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 int ipvlan_get_iflink(const struct net_device *dev)
{
	struct ipvl_dev *ipvlan = netdev_priv(dev);

	return ipvlan->phy_dev->ifindex;
}

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,
	.ndo_get_iflink		= ipvlan_get_iflink,
};

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,
	.parse		= eth_header_parse,
	.cache		= eth_header_cache,
	.cache_update	= eth_header_cache_update,
};

static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev,
					     struct ethtool_link_ksettings *cmd)
{
	const struct ipvl_dev *ipvlan = netdev_priv(dev);

	return __ethtool_get_link_ksettings(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_link_ksettings	= ipvlan_ethtool_get_link_ksettings,
	.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);
	int err = 0;

	if (data && data[IFLA_IPVLAN_MODE]) {
		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);

		err = ipvlan_set_port_mode(port, nmode);
	}
	return err;
}

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;
	u16 mode = IPVLAN_MODE_L3;

	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 (netif_is_ipvlan(phy_dev)) {
		struct ipvl_dev *tmp = netdev_priv(phy_dev);

		phy_dev = tmp->phy_dev;
	} else if (!netif_is_ipvlan_port(phy_dev)) {
		err = ipvlan_port_create(phy_dev);
		if (err < 0)
			return err;
	}

	if (data && data[IFLA_IPVLAN_MODE])
		mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);

	port = ipvlan_port_get_rtnl(phy_dev);
	ipvlan->phy_dev = phy_dev;
	ipvlan->dev = dev;
	ipvlan->port = port;
	ipvlan->sfeatures = IPVLAN_FEATURES;
	ipvlan_adjust_mtu(ipvlan, phy_dev);
	INIT_LIST_HEAD(&ipvlan->addrs);

	/* 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;

	err = register_netdevice(dev);
	if (err < 0)
		return err;

	err = netdev_upper_dev_link(phy_dev, dev);
	if (err) {
		unregister_netdevice(dev);
		return err;
	}
	err = ipvlan_set_port_mode(port, mode);
	if (err) {
		unregister_netdevice(dev);
		return err;
	}

	list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
	netif_stacked_transfer_operstate(phy_dev, dev);
	return 0;
}

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;

	list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
		ipvlan_ht_addr_del(addr);
		list_del(&addr->anode);
		kfree_rcu(addr, rcu);
	}

	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 | IFF_NO_QUEUE;
	dev->netdev_ops = &ipvlan_netdev_ops;
	dev->destructor = free_netdev;
	dev->header_ops = &ipvlan_header_ops;
	dev->ethtool_ops = &ipvlan_ethtool_ops;
}

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,
};

static 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 (!netif_is_ipvlan_port(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;
			ipvlan->dev->gso_max_segs = dev->gso_max_segs;
			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->port, 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(&addr->anode, &ipvlan->addrs);

	/* If the interface is not up, the address will be added to the hash
	 * list by ipvlan_open.
	 */
	if (netif_running(ipvlan->dev))
		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_find_addr(ipvlan, ip6_addr, true);
	if (!addr)
		return;

	ipvlan_ht_addr_del(addr);
	list_del(&addr->anode);
	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);

	/* FIXME IPv6 autoconf calls us from bh without RTNL */
	if (in_softirq())
		return NOTIFY_DONE;

	if (!netif_is_ipvlan(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->port, 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(&addr->anode, &ipvlan->addrs);

	/* If the interface is not up, the address will be added to the hash
	 * list by ipvlan_open.
	 */
	if (netif_running(ipvlan->dev))
		ipvlan_ht_addr_add(ipvlan, addr);

	return 0;
}

static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
{
	struct ipvl_addr *addr;

	addr = ipvlan_find_addr(ipvlan, ip4_addr, false);
	if (!addr)
		return;

	ipvlan_ht_addr_del(addr);
	list_del(&addr->anode);
	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 (!netif_is_ipvlan(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");