summaryrefslogtreecommitdiffstats
path: root/drivers/net/ipvlan/ipvlan_core.c
blob: 83ce74acf82d5e08676cb0d796aac1fe1b524071 (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
/* 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 __read_mostly;

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;
}

static 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);
	if (hlist_unhashed(&addr->hlnode))
		hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
}

void ipvlan_ht_addr_del(struct ipvl_addr *addr)
{
	hlist_del_init_rcu(&addr->hlnode);
}

struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
				   const void *iaddr, bool is_v6)
{
	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 addr;
	}
	return NULL;
}

bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6)
{
	struct ipvl_dev *ipvlan;

	ASSERT_RTNL();

	list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
		if (ipvlan_find_addr(ipvlan, 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;
}

void ipvlan_process_multicast(struct work_struct *work)
{
	struct ipvl_port *port = container_of(work, struct ipvl_port, wq);
	struct ethhdr *ethh;
	struct ipvl_dev *ipvlan;
	struct sk_buff *skb, *nskb;
	struct sk_buff_head list;
	unsigned int len;
	unsigned int mac_hash;
	int ret;
	u8 pkt_type;
	bool tx_pkt;

	__skb_queue_head_init(&list);

	spin_lock_bh(&port->backlog.lock);
	skb_queue_splice_tail_init(&port->backlog, &list);
	spin_unlock_bh(&port->backlog.lock);

	while ((skb = __skb_dequeue(&list)) != NULL) {
		struct net_device *dev = skb->dev;
		bool consumed = false;

		ethh = eth_hdr(skb);
		tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
		mac_hash = ipvlan_mac_hash(ethh->h_dest);

		if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
			pkt_type = PACKET_BROADCAST;
		else
			pkt_type = PACKET_MULTICAST;

		rcu_read_lock();
		list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
			if (tx_pkt && (ipvlan->dev == skb->dev))
				continue;
			if (!test_bit(mac_hash, ipvlan->mac_filters))
				continue;
			if (!(ipvlan->dev->flags & IFF_UP))
				continue;
			ret = NET_RX_DROP;
			len = skb->len + ETH_HLEN;
			nskb = skb_clone(skb, GFP_ATOMIC);
			local_bh_disable();
			if (nskb) {
				consumed = true;
				nskb->pkt_type = pkt_type;
				nskb->dev = ipvlan->dev;
				if (tx_pkt)
					ret = dev_forward_skb(ipvlan->dev, nskb);
				else
					ret = netif_rx(nskb);
			}
			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
			local_bh_enable();
		}
		rcu_read_unlock();

		if (tx_pkt) {
			/* If the packet originated here, send it out. */
			skb->dev = port->dev;
			skb->pkt_type = pkt_type;
			dev_queue_xmit(skb);
		} else {
			if (consumed)
				consume_skb(skb);
			else
				kfree_skb(skb);
		}
		if (dev)
			dev_put(dev);
	}
}

static void ipvlan_skb_crossing_ns(struct sk_buff *skb, struct net_device *dev)
{
	bool xnet = true;

	if (dev)
		xnet = !net_eq(dev_net(skb->dev), dev_net(dev));

	skb_scrub_packet(skb, xnet);
	if (dev)
		skb->dev = dev;
}

static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb,
			    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;
	struct sk_buff *skb = *pskb;

	len = skb->len + ETH_HLEN;
	/* Only packets exchanged between two local slaves need to have
	 * device-up check as well as skb-share check.
	 */
	if (local) {
		if (unlikely(!(dev->flags & IFF_UP))) {
			kfree_skb(skb);
			goto out;
		}

		skb = skb_share_check(skb, GFP_ATOMIC);
		if (!skb)
			goto out;

		*pskb = skb;
	}
	ipvlan_skb_crossing_ns(skb, dev);

	if (local) {
		skb->pkt_type = PACKET_HOST;
		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 net *net = dev_net(dev);
	struct rtable *rt;
	int err, ret = NET_XMIT_DROP;
	struct flowi4 fl4 = {
		.flowi4_oif = dev->ifindex,
		.flowi4_tos = RT_TOS(ip4h->tos),
		.flowi4_flags = FLOWI_FLAG_ANYSRC,
		.daddr = ip4h->daddr,
		.saddr = ip4h->saddr,
	};

	rt = ip_route_output_flow(net, &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_set(skb, &rt->dst);
	err = ip_local_out(net, skb->sk, 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 net *net = dev_net(dev);
	struct dst_entry *dst;
	int err, ret = NET_XMIT_DROP;
	struct flowi6 fl6 = {
		.flowi6_iif = 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(net, NULL, &fl6);
	if (dst->error) {
		ret = dst->error;
		dst_release(dst);
		goto err;
	}
	skb_dst_set(skb, dst);
	err = ip6_local_out(net, skb->sk, 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)
{
	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 void ipvlan_multicast_enqueue(struct ipvl_port *port,
				     struct sk_buff *skb, bool tx_pkt)
{
	if (skb->protocol == htons(ETH_P_PAUSE)) {
		kfree_skb(skb);
		return;
	}

	/* Record that the deferred packet is from TX or RX path. By
	 * looking at mac-addresses on packet will lead to erronus decisions.
	 * (This would be true for a loopback-mode on master device or a
	 * hair-pin mode of the switch.)
	 */
	IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;

	spin_lock(&port->backlog.lock);
	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
		if (skb->dev)
			dev_hold(skb->dev);
		__skb_queue_tail(&port->backlog, skb);
		spin_unlock(&port->backlog.lock);
		schedule_work(&port->wq);
	} else {
		spin_unlock(&port->backlog.lock);
		atomic_long_inc(&skb->dev->rx_dropped);
		kfree_skb(skb);
	}
}

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:
	ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev);
	return ipvlan_process_outbound(skb);
}

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)) {
		ipvlan_skb_crossing_ns(skb, NULL);
		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
		return NET_XMIT_SUCCESS;
	}

	ipvlan_skb_crossing_ns(skb, 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_bh(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:
	case IPVLAN_MODE_L3S:
		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, pskb, 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)) {
			struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);

			/* External frames are queued for device local
			 * distribution, but a copy is given to master
			 * straight away to avoid sending duplicates later
			 * when work-queue processes this frame. This is
			 * achieved by returning RX_HANDLER_PASS.
			 */
			if (nskb) {
				ipvlan_skb_crossing_ns(nskb, NULL);
				ipvlan_multicast_enqueue(port, nskb, 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, pskb, 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);
	case IPVLAN_MODE_L3S:
		return RX_HANDLER_PASS;
	}

	/* Should not reach here */
	WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n",
			  port->mode);
	kfree_skb(skb);
	return RX_HANDLER_CONSUMED;
}

static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb,
					    struct net_device *dev)
{
	struct ipvl_addr *addr = NULL;
	struct ipvl_port *port;
	void *lyr3h;
	int addr_type;

	if (!dev || !netif_is_ipvlan_port(dev))
		goto out;

	port = ipvlan_port_get_rcu(dev);
	if (!port || port->mode != IPVLAN_MODE_L3S)
		goto out;

	lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
	if (!lyr3h)
		goto out;

	addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
out:
	return addr;
}

struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb,
			      u16 proto)
{
	struct ipvl_addr *addr;
	struct net_device *sdev;

	addr = ipvlan_skb_to_addr(skb, dev);
	if (!addr)
		goto out;

	sdev = addr->master->dev;
	switch (proto) {
	case AF_INET:
	{
		int err;
		struct iphdr *ip4h = ip_hdr(skb);

		err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr,
					   ip4h->tos, sdev);
		if (unlikely(err))
			goto out;
		break;
	}
	case AF_INET6:
	{
		struct dst_entry *dst;
		struct ipv6hdr *ip6h = ipv6_hdr(skb);
		int flags = RT6_LOOKUP_F_HAS_SADDR;
		struct flowi6 fl6 = {
			.flowi6_iif   = sdev->ifindex,
			.daddr        = ip6h->daddr,
			.saddr        = ip6h->saddr,
			.flowlabel    = ip6_flowinfo(ip6h),
			.flowi6_mark  = skb->mark,
			.flowi6_proto = ip6h->nexthdr,
		};

		skb_dst_drop(skb);
		dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, flags);
		skb_dst_set(skb, dst);
		break;
	}
	default:
		break;
	}

out:
	return skb;
}

unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb,
			     const struct nf_hook_state *state)
{
	struct ipvl_addr *addr;
	unsigned int len;

	addr = ipvlan_skb_to_addr(skb, skb->dev);
	if (!addr)
		goto out;

	skb->dev = addr->master->dev;
	len = skb->len + ETH_HLEN;
	ipvlan_count_rx(addr->master, len, true, false);
out:
	return NF_ACCEPT;
}