summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/addr.c
blob: eaec8d7a3b7372094cdabcb98c2277fd46bb93cf (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
/*
 * 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/addrconf.h>
#include <net/ip6_route.h>
#include <rdma/ib_addr.h>

MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("IB Address Translation");
MODULE_LICENSE("Dual BSD/GPL");

struct addr_req {
	struct list_head list;
	struct sockaddr_storage src_addr;
	struct sockaddr_storage dst_addr;
	struct rdma_dev_addr *addr;
	struct rdma_addr_client *client;
	void *context;
	void (*callback)(int status, struct sockaddr *src_addr,
			 struct rdma_dev_addr *addr, void *context);
	unsigned long timeout;
	int status;
};

static void process_req(struct work_struct *work);

static DEFINE_MUTEX(lock);
static LIST_HEAD(req_list);
static DECLARE_DELAYED_WORK(work, process_req);
static struct workqueue_struct *addr_wq;

void rdma_addr_register_client(struct rdma_addr_client *client)
{
	atomic_set(&client->refcount, 1);
	init_completion(&client->comp);
}
EXPORT_SYMBOL(rdma_addr_register_client);

static inline void put_client(struct rdma_addr_client *client)
{
	if (atomic_dec_and_test(&client->refcount))
		complete(&client->comp);
}

void rdma_addr_unregister_client(struct rdma_addr_client *client)
{
	put_client(client);
	wait_for_completion(&client->comp);
}
EXPORT_SYMBOL(rdma_addr_unregister_client);

int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
		     const unsigned char *dst_dev_addr)
{
	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);
	if (dst_dev_addr)
		memcpy(dev_addr->dst_dev_addr, dst_dev_addr, MAX_ADDR_LEN);
	dev_addr->bound_dev_if = dev->ifindex;
	return 0;
}
EXPORT_SYMBOL(rdma_copy_addr);

int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
{
	struct net_device *dev;
	int ret = -EADDRNOTAVAIL;

	if (dev_addr->bound_dev_if) {
		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
		if (!dev)
			return -ENODEV;
		ret = rdma_copy_addr(dev_addr, dev, NULL);
		dev_put(dev);
		return ret;
	}

	switch (addr->sa_family) {
	case AF_INET:
		dev = ip_dev_find(&init_net,
			((struct sockaddr_in *) addr)->sin_addr.s_addr);

		if (!dev)
			return ret;

		ret = rdma_copy_addr(dev_addr, dev, NULL);
		dev_put(dev);
		break;

#if IS_ENABLED(CONFIG_IPV6)
	case AF_INET6:
		rcu_read_lock();
		for_each_netdev_rcu(&init_net, dev) {
			if (ipv6_chk_addr(&init_net,
					  &((struct sockaddr_in6 *) addr)->sin6_addr,
					  dev, 1)) {
				ret = rdma_copy_addr(dev_addr, dev, NULL);
				break;
			}
		}
		rcu_read_unlock();
		break;
#endif
	}
	return ret;
}
EXPORT_SYMBOL(rdma_translate_ip);

static void set_timeout(unsigned long time)
{
	unsigned long delay;

	delay = time - jiffies;
	if ((long)delay <= 0)
		delay = 1;

	mod_delayed_work(addr_wq, &work, delay);
}

static void queue_req(struct addr_req *req)
{
	struct addr_req *temp_req;

	mutex_lock(&lock);
	list_for_each_entry_reverse(temp_req, &req_list, list) {
		if (time_after_eq(req->timeout, temp_req->timeout))
			break;
	}

	list_add(&req->list, &temp_req->list);

	if (req_list.next == &req->list)
		set_timeout(req->timeout);
	mutex_unlock(&lock);
}

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

	n = dst_neigh_lookup(dst, daddr);

	rcu_read_lock();
	if (!n || !(n->nud_state & NUD_VALID)) {
		if (n)
			neigh_event_send(n, NULL);
		ret = -ENODATA;
	} else {
		ret = rdma_copy_addr(dev_addr, dst->dev, n->ha);
	}
	rcu_read_unlock();

	if (n)
		neigh_release(n);

	return ret;
}

static int addr4_resolve(struct sockaddr_in *src_in,
			 struct sockaddr_in *dst_in,
			 struct rdma_dev_addr *addr)
{
	__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(&init_net, &fl4);
	if (IS_ERR(rt)) {
		ret = PTR_ERR(rt);
		goto out;
	}
	src_in->sin_family = AF_INET;
	src_in->sin_addr.s_addr = fl4.saddr;

	if (rt->dst.dev->flags & IFF_LOOPBACK) {
		ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
		if (!ret)
			memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
		goto put;
	}

	/* If the device does ARP internally, return 'done' */
	if (rt->dst.dev->flags & IFF_NOARP) {
		ret = rdma_copy_addr(addr, rt->dst.dev, NULL);
		goto put;
	}

	ret = dst_fetch_ha(&rt->dst, addr, &fl4.daddr);
put:
	ip_rt_put(rt);
out:
	return ret;
}

#if IS_ENABLED(CONFIG_IPV6)
static int addr6_resolve(struct sockaddr_in6 *src_in,
			 struct sockaddr_in6 *dst_in,
			 struct rdma_dev_addr *addr)
{
	struct flowi6 fl6;
	struct dst_entry *dst;
	int ret;

	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 = ip6_route_output(&init_net, NULL, &fl6);
	if ((ret = dst->error))
		goto put;

	if (ipv6_addr_any(&fl6.saddr)) {
		ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev,
					 &fl6.daddr, 0, &fl6.saddr);
		if (ret)
			goto put;

		src_in->sin6_family = AF_INET6;
		src_in->sin6_addr = fl6.saddr;
	}

	if (dst->dev->flags & IFF_LOOPBACK) {
		ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
		if (!ret)
			memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
		goto put;
	}

	/* If the device does ARP internally, return 'done' */
	if (dst->dev->flags & IFF_NOARP) {
		ret = rdma_copy_addr(addr, dst->dev, NULL);
		goto put;
	}

	ret = dst_fetch_ha(dst, addr, &fl6.daddr);
put:
	dst_release(dst);
	return ret;
}
#else
static int addr6_resolve(struct sockaddr_in6 *src_in,
			 struct sockaddr_in6 *dst_in,
			 struct rdma_dev_addr *addr)
{
	return -EADDRNOTAVAIL;
}
#endif

static int addr_resolve(struct sockaddr *src_in,
			struct sockaddr *dst_in,
			struct rdma_dev_addr *addr)
{
	if (src_in->sa_family == AF_INET) {
		return addr4_resolve((struct sockaddr_in *) src_in,
			(struct sockaddr_in *) dst_in, addr);
	} else
		return addr6_resolve((struct sockaddr_in6 *) src_in,
			(struct sockaddr_in6 *) dst_in, addr);
}

static void process_req(struct work_struct *work)
{
	struct addr_req *req, *temp_req;
	struct sockaddr *src_in, *dst_in;
	struct list_head done_list;

	INIT_LIST_HEAD(&done_list);

	mutex_lock(&lock);
	list_for_each_entry_safe(req, temp_req, &req_list, list) {
		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);
			if (req->status && time_after_eq(jiffies, req->timeout))
				req->status = -ETIMEDOUT;
			else if (req->status == -ENODATA)
				continue;
		}
		list_move_tail(&req->list, &done_list);
	}

	if (!list_empty(&req_list)) {
		req = list_entry(req_list.next, struct addr_req, list);
		set_timeout(req->timeout);
	}
	mutex_unlock(&lock);

	list_for_each_entry_safe(req, temp_req, &done_list, list) {
		list_del(&req->list);
		req->callback(req->status, (struct sockaddr *) &req->src_addr,
			req->addr, req->context);
		put_client(req->client);
		kfree(req);
	}
}

int rdma_resolve_ip(struct rdma_addr_client *client,
		    struct sockaddr *src_addr, struct sockaddr *dst_addr,
		    struct rdma_dev_addr *addr, int timeout_ms,
		    void (*callback)(int status, struct sockaddr *src_addr,
				     struct rdma_dev_addr *addr, void *context),
		    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, ip_addr_size(src_addr));
	} else {
		src_in->sa_family = dst_addr->sa_family;
	}

	memcpy(dst_in, dst_addr, ip_addr_size(dst_addr));
	req->addr = addr;
	req->callback = callback;
	req->context = context;
	req->client = client;
	atomic_inc(&client->refcount);

	req->status = addr_resolve(src_in, dst_in, addr);
	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;
		atomic_dec(&client->refcount);
		goto err;
	}
	return ret;
err:
	kfree(req);
	return ret;
}
EXPORT_SYMBOL(rdma_resolve_ip);

void rdma_addr_cancel(struct rdma_dev_addr *addr)
{
	struct addr_req *req, *temp_req;

	mutex_lock(&lock);
	list_for_each_entry_safe(req, temp_req, &req_list, list) {
		if (req->addr == addr) {
			req->status = -ECANCELED;
			req->timeout = jiffies;
			list_move(&req->list, &req_list);
			set_timeout(req->timeout);
			break;
		}
	}
	mutex_unlock(&lock);
}
EXPORT_SYMBOL(rdma_addr_cancel);

static int netevent_callback(struct notifier_block *self, unsigned long event,
	void *ctx)
{
	if (event == NETEVENT_NEIGH_UPDATE) {
		struct neighbour *neigh = ctx;

		if (neigh->nud_state & NUD_VALID) {
			set_timeout(jiffies);
		}
	}
	return 0;
}

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

static int __init addr_init(void)
{
	addr_wq = create_singlethread_workqueue("ib_addr");
	if (!addr_wq)
		return -ENOMEM;

	register_netevent_notifier(&nb);
	return 0;
}

static void __exit addr_cleanup(void)
{
	unregister_netevent_notifier(&nb);
	destroy_workqueue(addr_wq);
}

module_init(addr_init);
module_exit(addr_cleanup);