summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/addr.c
blob: 65e3e7df8a4b07f06c0760cd61f2f26fc906b018 (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
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
/*
 * Copyright (c) 2005 Voltaire Inc.  All rights reserved.
 * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved.
 * Copyright (c) 1999-2005, Mellanox Technologies, Inc. All rights reserved.
 * Copyright (c) 2005 Intel Corporation.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * 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 <linux/mutex.h>
#include <linux/inetdevice.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/module.h>
#include <net/arp.h>
#include <net/neighbour.h>
#include <net/route.h>
#include <net/netevent.h>
#include <net/ipv6_stubs.h>
#include <net/ip6_route.h>
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_sa.h>
#include <rdma/ib.h>
#include <rdma/rdma_netlink.h>
#include <net/netlink.h>

#include "core_priv.h"

struct addr_req {
	struct list_head list;
	struct sockaddr_storage src_addr;
	struct sockaddr_storage dst_addr;
	struct rdma_dev_addr *addr;
	void *context;
	void (*callback)(int status, struct sockaddr *src_addr,
			 struct rdma_dev_addr *addr, void *context);
	unsigned long timeout;
	struct delayed_work work;
	bool resolve_by_gid_attr;	/* Consider gid attr in resolve phase */
	int status;
	u32 seq;
};

static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0);

static DEFINE_SPINLOCK(lock);
static LIST_HEAD(req_list);
static struct workqueue_struct *addr_wq;

static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
	[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
		.len = sizeof(struct rdma_nla_ls_gid),
		.validation_type = NLA_VALIDATE_MIN,
		.min = sizeof(struct rdma_nla_ls_gid)},
};

static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
{
	struct nlattr *tb[LS_NLA_TYPE_MAX] = {};
	int ret;

	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
		return false;

	ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
				   nlmsg_len(nlh), ib_nl_addr_policy, NULL);
	if (ret)
		return false;

	return true;
}

static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
{
	const struct nlattr *head, *curr;
	union ib_gid gid;
	struct addr_req *req;
	int len, rem;
	int found = 0;

	head = (const struct nlattr *)nlmsg_data(nlh);
	len = nlmsg_len(nlh);

	nla_for_each_attr(curr, head, len, rem) {
		if (curr->nla_type == LS_NLA_TYPE_DGID)
			memcpy(&gid, nla_data(curr), nla_len(curr));
	}

	spin_lock_bh(&lock);
	list_for_each_entry(req, &req_list, list) {
		if (nlh->nlmsg_seq != req->seq)
			continue;
		/* We set the DGID part, the rest was set earlier */
		rdma_addr_set_dgid(req->addr, &gid);
		req->status = 0;
		found = 1;
		break;
	}
	spin_unlock_bh(&lock);

	if (!found)
		pr_info("Couldn't find request waiting for DGID: %pI6\n",
			&gid);
}

int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
			     struct nlmsghdr *nlh,
			     struct netlink_ext_ack *extack)
{
	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
	    !(NETLINK_CB(skb).sk))
		return -EPERM;

	if (ib_nl_is_good_ip_resp(nlh))
		ib_nl_process_good_ip_rsep(nlh);

	return 0;
}

static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
			     const void *daddr,
			     u32 seq, u16 family)
{
	struct sk_buff *skb = NULL;
	struct nlmsghdr *nlh;
	struct rdma_ls_ip_resolve_header *header;
	void *data;
	size_t size;
	int attrtype;
	int len;

	if (family == AF_INET) {
		size = sizeof(struct in_addr);
		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4;
	} else {
		size = sizeof(struct in6_addr);
		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6;
	}

	len = nla_total_size(sizeof(size));
	len += NLMSG_ALIGN(sizeof(*header));

	skb = nlmsg_new(len, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS,
			    RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST);
	if (!data) {
		nlmsg_free(skb);
		return -ENODATA;
	}

	/* Construct the family header first */
	header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
	header->ifindex = dev_addr->bound_dev_if;
	nla_put(skb, attrtype, size, daddr);

	/* Repair the nlmsg header length */
	nlmsg_end(skb, nlh);
	rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, GFP_KERNEL);

	/* Make the request retry, so when we get the response from userspace
	 * we will have something.
	 */
	return -ENODATA;
}

int rdma_addr_size(const struct sockaddr *addr)
{
	switch (addr->sa_family) {
	case AF_INET:
		return sizeof(struct sockaddr_in);
	case AF_INET6:
		return sizeof(struct sockaddr_in6);
	case AF_IB:
		return sizeof(struct sockaddr_ib);
	default:
		return 0;
	}
}
EXPORT_SYMBOL(rdma_addr_size);

int rdma_addr_size_in6(struct sockaddr_in6 *addr)
{
	int ret = rdma_addr_size((struct sockaddr *) addr);

	return ret <= sizeof(*addr) ? ret : 0;
}
EXPORT_SYMBOL(rdma_addr_size_in6);

int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr)
{
	int ret = rdma_addr_size((struct sockaddr *) addr);

	return ret <= sizeof(*addr) ? ret : 0;
}
EXPORT_SYMBOL(rdma_addr_size_kss);

/**
 * rdma_copy_src_l2_addr - Copy netdevice source addresses
 * @dev_addr:	Destination address pointer where to copy the addresses
 * @dev:	Netdevice whose source addresses to copy
 *
 * rdma_copy_src_l2_addr() copies source addresses from the specified netdevice.
 * This includes unicast address, broadcast address, device type and
 * interface index.
 */
void rdma_copy_src_l2_addr(struct rdma_dev_addr *dev_addr,
			   const struct net_device *dev)
{
	dev_addr->dev_type = dev->type;
	memcpy(dev_addr->src_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
	memcpy(dev_addr->broadcast, dev->broadcast, MAX_ADDR_LEN);
	dev_addr->bound_dev_if = dev->ifindex;
}
EXPORT_SYMBOL(rdma_copy_src_l2_addr);

static struct net_device *
rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in)
{
	struct net_device *dev = NULL;
	int ret = -EADDRNOTAVAIL;

	switch (src_in->sa_family) {
	case AF_INET:
		dev = __ip_dev_find(net,
				    ((const struct sockaddr_in *)src_in)->sin_addr.s_addr,
				    false);
		if (dev)
			ret = 0;
		break;
#if IS_ENABLED(CONFIG_IPV6)
	case AF_INET6:
		for_each_netdev_rcu(net, dev) {
			if (ipv6_chk_addr(net,
					  &((const struct sockaddr_in6 *)src_in)->sin6_addr,
					  dev, 1)) {
				ret = 0;
				break;
			}
		}
		break;
#endif
	}
	return ret ? ERR_PTR(ret) : dev;
}

int rdma_translate_ip(const struct sockaddr *addr,
		      struct rdma_dev_addr *dev_addr)
{
	struct net_device *dev;

	if (dev_addr->bound_dev_if) {
		dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
		if (!dev)
			return -ENODEV;
		rdma_copy_src_l2_addr(dev_addr, dev);
		dev_put(dev);
		return 0;
	}

	rcu_read_lock();
	dev = rdma_find_ndev_for_src_ip_rcu(dev_addr->net, addr);
	if (!IS_ERR(dev))
		rdma_copy_src_l2_addr(dev_addr, dev);
	rcu_read_unlock();
	return PTR_ERR_OR_ZERO(dev);
}
EXPORT_SYMBOL(rdma_translate_ip);

static void set_timeout(struct addr_req *req, unsigned long time)
{
	unsigned long delay;

	delay = time - jiffies;
	if ((long)delay < 0)
		delay = 0;

	mod_delayed_work(addr_wq, &req->work, delay);
}

static void queue_req(struct addr_req *req)
{
	spin_lock_bh(&lock);
	list_add_tail(&req->list, &req_list);
	set_timeout(req, req->timeout);
	spin_unlock_bh(&lock);
}

static int ib_nl_fetch_ha(struct rdma_dev_addr *dev_addr,
			  const void *daddr, u32 seq, u16 family)
{
	if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
		return -EADDRNOTAVAIL;

	return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
}

static int dst_fetch_ha(const struct dst_entry *dst,
			struct rdma_dev_addr *dev_addr,
			const void *daddr)
{
	struct neighbour *n;
	int ret = 0;

	n = dst_neigh_lookup(dst, daddr);
	if (!n)
		return -ENODATA;

	if (!(n->nud_state & NUD_VALID)) {
		neigh_event_send(n, NULL);
		ret = -ENODATA;
	} else {
		neigh_ha_snapshot(dev_addr->dst_dev_addr, n, dst->dev);
	}

	neigh_release(n);

	return ret;
}

static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
{
	struct rtable *rt;
	struct rt6_info *rt6;

	if (family == AF_INET) {
		rt = container_of(dst, struct rtable, dst);
		return rt->rt_uses_gateway;
	}

	rt6 = container_of(dst, struct rt6_info, dst);
	return rt6->rt6i_flags & RTF_GATEWAY;
}

static int fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
		    const struct sockaddr *dst_in, u32 seq)
{
	const struct sockaddr_in *dst_in4 =
		(const struct sockaddr_in *)dst_in;
	const struct sockaddr_in6 *dst_in6 =
		(const struct sockaddr_in6 *)dst_in;
	const void *daddr = (dst_in->sa_family == AF_INET) ?
		(const void *)&dst_in4->sin_addr.s_addr :
		(const void *)&dst_in6->sin6_addr;
	sa_family_t family = dst_in->sa_family;

	might_sleep();

	/* If we have a gateway in IB mode then it must be an IB network */
	if (has_gateway(dst, family) && dev_addr->network == RDMA_NETWORK_IB)
		return ib_nl_fetch_ha(dev_addr, daddr, seq, family);
	else
		return dst_fetch_ha(dst, dev_addr, daddr);
}

static int addr4_resolve(struct sockaddr *src_sock,
			 const struct sockaddr *dst_sock,
			 struct rdma_dev_addr *addr,
			 struct rtable **prt)
{
	struct sockaddr_in *src_in = (struct sockaddr_in *)src_sock;
	const struct sockaddr_in *dst_in =
			(const struct sockaddr_in *)dst_sock;

	__be32 src_ip = src_in->sin_addr.s_addr;
	__be32 dst_ip = dst_in->sin_addr.s_addr;
	struct rtable *rt;
	struct flowi4 fl4;
	int ret;

	memset(&fl4, 0, sizeof(fl4));
	fl4.daddr = dst_ip;
	fl4.saddr = src_ip;
	fl4.flowi4_oif = addr->bound_dev_if;
	rt = ip_route_output_key(addr->net, &fl4);
	ret = PTR_ERR_OR_ZERO(rt);
	if (ret)
		return ret;

	src_in->sin_addr.s_addr = fl4.saddr;

	addr->hoplimit = ip4_dst_hoplimit(&rt->dst);

	*prt = rt;
	return 0;
}

#if IS_ENABLED(CONFIG_IPV6)
static int addr6_resolve(struct sockaddr *src_sock,
			 const struct sockaddr *dst_sock,
			 struct rdma_dev_addr *addr,
			 struct dst_entry **pdst)
{
	struct sockaddr_in6 *src_in = (struct sockaddr_in6 *)src_sock;
	const struct sockaddr_in6 *dst_in =
				(const struct sockaddr_in6 *)dst_sock;
	struct flowi6 fl6;
	struct dst_entry *dst;

	memset(&fl6, 0, sizeof fl6);
	fl6.daddr = dst_in->sin6_addr;
	fl6.saddr = src_in->sin6_addr;
	fl6.flowi6_oif = addr->bound_dev_if;

	dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL);
	if (IS_ERR(dst))
		return PTR_ERR(dst);

	if (ipv6_addr_any(&src_in->sin6_addr))
		src_in->sin6_addr = fl6.saddr;

	addr->hoplimit = ip6_dst_hoplimit(dst);

	*pdst = dst;
	return 0;
}
#else
static int addr6_resolve(struct sockaddr *src_sock,
			 const struct sockaddr *dst_sock,
			 struct rdma_dev_addr *addr,
			 struct dst_entry **pdst)
{
	return -EADDRNOTAVAIL;
}
#endif

static int addr_resolve_neigh(const struct dst_entry *dst,
			      const struct sockaddr *dst_in,
			      struct rdma_dev_addr *addr,
			      unsigned int ndev_flags,
			      u32 seq)
{
	int ret = 0;

	if (ndev_flags & IFF_LOOPBACK) {
		memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
	} else {
		if (!(ndev_flags & IFF_NOARP)) {
			/* If the device doesn't do ARP internally */
			ret = fetch_ha(dst, addr, dst_in, seq);
		}
	}
	return ret;
}

static int copy_src_l2_addr(struct rdma_dev_addr *dev_addr,
			    const struct sockaddr *dst_in,
			    const struct dst_entry *dst,
			    const struct net_device *ndev)
{
	int ret = 0;

	if (dst->dev->flags & IFF_LOOPBACK)
		ret = rdma_translate_ip(dst_in, dev_addr);
	else
		rdma_copy_src_l2_addr(dev_addr, dst->dev);

	/*
	 * If there's a gateway and type of device not ARPHRD_INFINIBAND,
	 * we're definitely in RoCE v2 (as RoCE v1 isn't routable) set the
	 * network type accordingly.
	 */
	if (has_gateway(dst, dst_in->sa_family) &&
	    ndev->type != ARPHRD_INFINIBAND)
		dev_addr->network = dst_in->sa_family == AF_INET ?
						RDMA_NETWORK_IPV4 :
						RDMA_NETWORK_IPV6;
	else
		dev_addr->network = RDMA_NETWORK_IB;

	return ret;
}

static int rdma_set_src_addr_rcu(struct rdma_dev_addr *dev_addr,
				 unsigned int *ndev_flags,
				 const struct sockaddr *dst_in,
				 const struct dst_entry *dst)
{
	struct net_device *ndev = READ_ONCE(dst->dev);

	*ndev_flags = ndev->flags;
	/* A physical device must be the RDMA device to use */
	if (ndev->flags & IFF_LOOPBACK) {
		/*
		 * RDMA (IB/RoCE, iWarp) doesn't run on lo interface or
		 * loopback IP address. So if route is resolved to loopback
		 * interface, translate that to a real ndev based on non
		 * loopback IP address.
		 */
		ndev = rdma_find_ndev_for_src_ip_rcu(dev_net(ndev), dst_in);
		if (IS_ERR(ndev))
			return -ENODEV;
	}

	return copy_src_l2_addr(dev_addr, dst_in, dst, ndev);
}

static int set_addr_netns_by_gid_rcu(struct rdma_dev_addr *addr)
{
	struct net_device *ndev;

	ndev = rdma_read_gid_attr_ndev_rcu(addr->sgid_attr);
	if (IS_ERR(ndev))
		return PTR_ERR(ndev);

	/*
	 * Since we are holding the rcu, reading net and ifindex
	 * are safe without any additional reference; because
	 * change_net_namespace() in net/core/dev.c does rcu sync
	 * after it changes the state to IFF_DOWN and before
	 * updating netdev fields {net, ifindex}.
	 */
	addr->net = dev_net(ndev);
	addr->bound_dev_if = ndev->ifindex;
	return 0;
}

static void rdma_addr_set_net_defaults(struct rdma_dev_addr *addr)
{
	addr->net = &init_net;
	addr->bound_dev_if = 0;
}

static int addr_resolve(struct sockaddr *src_in,
			const struct sockaddr *dst_in,
			struct rdma_dev_addr *addr,
			bool resolve_neigh,
			bool resolve_by_gid_attr,
			u32 seq)
{
	struct dst_entry *dst = NULL;
	unsigned int ndev_flags = 0;
	struct rtable *rt = NULL;
	int ret;

	if (!addr->net) {
		pr_warn_ratelimited("%s: missing namespace\n", __func__);
		return -EINVAL;
	}

	rcu_read_lock();
	if (resolve_by_gid_attr) {
		if (!addr->sgid_attr) {
			rcu_read_unlock();
			pr_warn_ratelimited("%s: missing gid_attr\n", __func__);
			return -EINVAL;
		}
		/*
		 * If the request is for a specific gid attribute of the
		 * rdma_dev_addr, derive net from the netdevice of the
		 * GID attribute.
		 */
		ret = set_addr_netns_by_gid_rcu(addr);
		if (ret) {
			rcu_read_unlock();
			return ret;
		}
	}
	if (src_in->sa_family == AF_INET) {
		ret = addr4_resolve(src_in, dst_in, addr, &rt);
		dst = &rt->dst;
	} else {
		ret = addr6_resolve(src_in, dst_in, addr, &dst);
	}
	if (ret) {
		rcu_read_unlock();
		goto done;
	}
	ret = rdma_set_src_addr_rcu(addr, &ndev_flags, dst_in, dst);
	rcu_read_unlock();

	/*
	 * Resolve neighbor destination address if requested and
	 * only if src addr translation didn't fail.
	 */
	if (!ret && resolve_neigh)
		ret = addr_resolve_neigh(dst, dst_in, addr, ndev_flags, seq);

	if (src_in->sa_family == AF_INET)
		ip_rt_put(rt);
	else
		dst_release(dst);
done:
	/*
	 * Clear the addr net to go back to its original state, only if it was
	 * derived from GID attribute in this context.
	 */
	if (resolve_by_gid_attr)
		rdma_addr_set_net_defaults(addr);
	return ret;
}

static void process_one_req(struct work_struct *_work)
{
	struct addr_req *req;
	struct sockaddr *src_in, *dst_in;

	req = container_of(_work, struct addr_req, work.work);

	if (req->status == -ENODATA) {
		src_in = (struct sockaddr *)&req->src_addr;
		dst_in = (struct sockaddr *)&req->dst_addr;
		req->status = addr_resolve(src_in, dst_in, req->addr,
					   true, req->resolve_by_gid_attr,
					   req->seq);
		if (req->status && time_after_eq(jiffies, req->timeout)) {
			req->status = -ETIMEDOUT;
		} else if (req->status == -ENODATA) {
			/* requeue the work for retrying again */
			spin_lock_bh(&lock);
			if (!list_empty(&req->list))
				set_timeout(req, req->timeout);
			spin_unlock_bh(&lock);
			return;
		}
	}

	req->callback(req->status, (struct sockaddr *)&req->src_addr,
		req->addr, req->context);
	req->callback = NULL;

	spin_lock_bh(&lock);
	/*
	 * Although the work will normally have been canceled by the workqueue,
	 * it can still be requeued as long as it is on the req_list.
	 */
	cancel_delayed_work(&req->work);
	if (!list_empty(&req->list)) {
		list_del_init(&req->list);
		kfree(req);
	}
	spin_unlock_bh(&lock);
}

int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr,
		    struct rdma_dev_addr *addr, unsigned long timeout_ms,
		    void (*callback)(int status, struct sockaddr *src_addr,
				     struct rdma_dev_addr *addr, void *context),
		    bool resolve_by_gid_attr, void *context)
{
	struct sockaddr *src_in, *dst_in;
	struct addr_req *req;
	int ret = 0;

	req = kzalloc(sizeof *req, GFP_KERNEL);
	if (!req)
		return -ENOMEM;

	src_in = (struct sockaddr *) &req->src_addr;
	dst_in = (struct sockaddr *) &req->dst_addr;

	if (src_addr) {
		if (src_addr->sa_family != dst_addr->sa_family) {
			ret = -EINVAL;
			goto err;
		}

		memcpy(src_in, src_addr, rdma_addr_size(src_addr));
	} else {
		src_in->sa_family = dst_addr->sa_family;
	}

	memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr));
	req->addr = addr;
	req->callback = callback;
	req->context = context;
	req->resolve_by_gid_attr = resolve_by_gid_attr;
	INIT_DELAYED_WORK(&req->work, process_one_req);
	req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);

	req->status = addr_resolve(src_in, dst_in, addr, true,
				   req->resolve_by_gid_attr, req->seq);
	switch (req->status) {
	case 0:
		req->timeout = jiffies;
		queue_req(req);
		break;
	case -ENODATA:
		req->timeout = msecs_to_jiffies(timeout_ms) + jiffies;
		queue_req(req);
		break;
	default:
		ret = req->status;
		goto err;
	}
	return ret;
err:
	kfree(req);
	return ret;
}
EXPORT_SYMBOL(rdma_resolve_ip);

int roce_resolve_route_from_path(struct sa_path_rec *rec,
				 const struct ib_gid_attr *attr)
{
	union {
		struct sockaddr     _sockaddr;
		struct sockaddr_in  _sockaddr_in;
		struct sockaddr_in6 _sockaddr_in6;
	} sgid, dgid;
	struct rdma_dev_addr dev_addr = {};
	int ret;

	might_sleep();

	if (rec->roce.route_resolved)
		return 0;

	rdma_gid2ip((struct sockaddr *)&sgid, &rec->sgid);
	rdma_gid2ip((struct sockaddr *)&dgid, &rec->dgid);

	if (sgid._sockaddr.sa_family != dgid._sockaddr.sa_family)
		return -EINVAL;

	if (!attr || !attr->ndev)
		return -EINVAL;

	dev_addr.net = &init_net;
	dev_addr.sgid_attr = attr;

	ret = addr_resolve((struct sockaddr *)&sgid, (struct sockaddr *)&dgid,
			   &dev_addr, false, true, 0);
	if (ret)
		return ret;

	if ((dev_addr.network == RDMA_NETWORK_IPV4 ||
	     dev_addr.network == RDMA_NETWORK_IPV6) &&
	    rec->rec_type != SA_PATH_REC_TYPE_ROCE_V2)
		return -EINVAL;

	rec->roce.route_resolved = true;
	return 0;
}

/**
 * rdma_addr_cancel - Cancel resolve ip request
 * @addr:	Pointer to address structure given previously
 *		during rdma_resolve_ip().
 * rdma_addr_cancel() is synchronous function which cancels any pending
 * request if there is any.
 */
void rdma_addr_cancel(struct rdma_dev_addr *addr)
{
	struct addr_req *req, *temp_req;
	struct addr_req *found = NULL;

	spin_lock_bh(&lock);
	list_for_each_entry_safe(req, temp_req, &req_list, list) {
		if (req->addr == addr) {
			/*
			 * Removing from the list means we take ownership of
			 * the req
			 */
			list_del_init(&req->list);
			found = req;
			break;
		}
	}
	spin_unlock_bh(&lock);

	if (!found)
		return;

	/*
	 * sync canceling the work after removing it from the req_list
	 * guarentees no work is running and none will be started.
	 */
	cancel_delayed_work_sync(&found->work);
	kfree(found);
}
EXPORT_SYMBOL(rdma_addr_cancel);

struct resolve_cb_context {
	struct completion comp;
	int status;
};

static void resolve_cb(int status, struct sockaddr *src_addr,
	     struct rdma_dev_addr *addr, void *context)
{
	((struct resolve_cb_context *)context)->status = status;
	complete(&((struct resolve_cb_context *)context)->comp);
}

int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
				 const union ib_gid *dgid,
				 u8 *dmac, const struct ib_gid_attr *sgid_attr,
				 int *hoplimit)
{
	struct rdma_dev_addr dev_addr;
	struct resolve_cb_context ctx;
	union {
		struct sockaddr_in  _sockaddr_in;
		struct sockaddr_in6 _sockaddr_in6;
	} sgid_addr, dgid_addr;
	int ret;

	rdma_gid2ip((struct sockaddr *)&sgid_addr, sgid);
	rdma_gid2ip((struct sockaddr *)&dgid_addr, dgid);

	memset(&dev_addr, 0, sizeof(dev_addr));
	dev_addr.net = &init_net;
	dev_addr.sgid_attr = sgid_attr;

	init_completion(&ctx.comp);
	ret = rdma_resolve_ip((struct sockaddr *)&sgid_addr,
			      (struct sockaddr *)&dgid_addr, &dev_addr, 1000,
			      resolve_cb, true, &ctx);
	if (ret)
		return ret;

	wait_for_completion(&ctx.comp);

	ret = ctx.status;
	if (ret)
		return ret;

	memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
	*hoplimit = dev_addr.hoplimit;
	return 0;
}

static int netevent_callback(struct notifier_block *self, unsigned long event,
	void *ctx)
{
	struct addr_req *req;

	if (event == NETEVENT_NEIGH_UPDATE) {
		struct neighbour *neigh = ctx;

		if (neigh->nud_state & NUD_VALID) {
			spin_lock_bh(&lock);
			list_for_each_entry(req, &req_list, list)
				set_timeout(req, jiffies);
			spin_unlock_bh(&lock);
		}
	}
	return 0;
}

static struct notifier_block nb = {
	.notifier_call = netevent_callback
};

int addr_init(void)
{
	addr_wq = alloc_ordered_workqueue("ib_addr", 0);
	if (!addr_wq)
		return -ENOMEM;

	register_netevent_notifier(&nb);

	return 0;
}

void addr_cleanup(void)
{
	unregister_netevent_notifier(&nb);
	destroy_workqueue(addr_wq);
	WARN_ON(!list_empty(&req_list));
}