summaryrefslogtreecommitdiff
path: root/net/rxrpc/local_object.c
blob: b67dec9454980c46ba7afaa69064782f15d4a803 (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
/* Local endpoint object management
 *
 * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public Licence
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/udp.h>
#include <linux/ip.h>
#include <linux/hashtable.h>
#include <net/sock.h>
#include <net/udp.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"

static void rxrpc_local_processor(struct work_struct *);
static void rxrpc_local_rcu(struct rcu_head *);

/*
 * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
 * same or greater than.
 *
 * We explicitly don't compare the RxRPC service ID as we want to reject
 * conflicting uses by differing services.  Further, we don't want to share
 * addresses with different options (IPv6), so we don't compare those bits
 * either.
 */
static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
				const struct sockaddr_rxrpc *srx)
{
	long diff;

	diff = ((local->srx.transport_type - srx->transport_type) ?:
		(local->srx.transport_len - srx->transport_len) ?:
		(local->srx.transport.family - srx->transport.family));
	if (diff != 0)
		return diff;

	switch (srx->transport.family) {
	case AF_INET:
		/* If the choice of UDP port is left up to the transport, then
		 * the endpoint record doesn't match.
		 */
		return ((u16 __force)local->srx.transport.sin.sin_port -
			(u16 __force)srx->transport.sin.sin_port) ?:
			memcmp(&local->srx.transport.sin.sin_addr,
			       &srx->transport.sin.sin_addr,
			       sizeof(struct in_addr));
#ifdef CONFIG_AF_RXRPC_IPV6
	case AF_INET6:
		/* If the choice of UDP6 port is left up to the transport, then
		 * the endpoint record doesn't match.
		 */
		return ((u16 __force)local->srx.transport.sin6.sin6_port -
			(u16 __force)srx->transport.sin6.sin6_port) ?:
			memcmp(&local->srx.transport.sin6.sin6_addr,
			       &srx->transport.sin6.sin6_addr,
			       sizeof(struct in6_addr));
#endif
	default:
		BUG();
	}
}

/*
 * Allocate a new local endpoint.
 */
static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
					     const struct sockaddr_rxrpc *srx)
{
	struct rxrpc_local *local;

	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
	if (local) {
		atomic_set(&local->usage, 1);
		local->rxnet = rxnet;
		INIT_LIST_HEAD(&local->link);
		INIT_WORK(&local->processor, rxrpc_local_processor);
		init_rwsem(&local->defrag_sem);
		skb_queue_head_init(&local->reject_queue);
		skb_queue_head_init(&local->event_queue);
		local->client_conns = RB_ROOT;
		spin_lock_init(&local->client_conns_lock);
		spin_lock_init(&local->lock);
		rwlock_init(&local->services_lock);
		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
		memcpy(&local->srx, srx, sizeof(*srx));
		local->srx.srx_service = 0;
		trace_rxrpc_local(local, rxrpc_local_new, 1, NULL);
	}

	_leave(" = %p", local);
	return local;
}

/*
 * create the local socket
 * - must be called with rxrpc_local_mutex locked
 */
static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
{
	struct sock *usk;
	int ret, opt;

	_enter("%p{%d,%d}",
	       local, local->srx.transport_type, local->srx.transport.family);

	/* create a socket to represent the local endpoint */
	ret = sock_create_kern(net, local->srx.transport.family,
			       local->srx.transport_type, 0, &local->socket);
	if (ret < 0) {
		_leave(" = %d [socket]", ret);
		return ret;
	}

	/* set the socket up */
	usk = local->socket->sk;
	inet_sk(usk)->mc_loop = 0;

	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
	inet_inc_convert_csum(usk);

	rcu_assign_sk_user_data(usk, local);

	udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC;
	udp_sk(usk)->encap_rcv = rxrpc_input_packet;
	udp_sk(usk)->encap_destroy = NULL;
	udp_sk(usk)->gro_receive = NULL;
	udp_sk(usk)->gro_complete = NULL;

	udp_encap_enable();
#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6)
	if (local->srx.transport.family == AF_INET6)
		udpv6_encap_enable();
#endif
	usk->sk_error_report = rxrpc_error_report;

	/* if a local address was supplied then bind it */
	if (local->srx.transport_len > sizeof(sa_family_t)) {
		_debug("bind");
		ret = kernel_bind(local->socket,
				  (struct sockaddr *)&local->srx.transport,
				  local->srx.transport_len);
		if (ret < 0) {
			_debug("bind failed %d", ret);
			goto error;
		}
	}

	switch (local->srx.transport.family) {
	case AF_INET6:
		/* we want to receive ICMPv6 errors */
		opt = 1;
		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
					(char *) &opt, sizeof(opt));
		if (ret < 0) {
			_debug("setsockopt failed");
			goto error;
		}

		/* we want to set the don't fragment bit */
		opt = IPV6_PMTUDISC_DO;
		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
					(char *) &opt, sizeof(opt));
		if (ret < 0) {
			_debug("setsockopt failed");
			goto error;
		}

		/* Fall through and set IPv4 options too otherwise we don't get
		 * errors from IPv4 packets sent through the IPv6 socket.
		 */
		/* Fall through */
	case AF_INET:
		/* we want to receive ICMP errors */
		opt = 1;
		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
					(char *) &opt, sizeof(opt));
		if (ret < 0) {
			_debug("setsockopt failed");
			goto error;
		}

		/* we want to set the don't fragment bit */
		opt = IP_PMTUDISC_DO;
		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
					(char *) &opt, sizeof(opt));
		if (ret < 0) {
			_debug("setsockopt failed");
			goto error;
		}

		/* We want receive timestamps. */
		opt = 1;
		ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS_OLD,
					(char *)&opt, sizeof(opt));
		if (ret < 0) {
			_debug("setsockopt failed");
			goto error;
		}
		break;

	default:
		BUG();
	}

	_leave(" = 0");
	return 0;

error:
	kernel_sock_shutdown(local->socket, SHUT_RDWR);
	local->socket->sk->sk_user_data = NULL;
	sock_release(local->socket);
	local->socket = NULL;

	_leave(" = %d", ret);
	return ret;
}

/*
 * Look up or create a new local endpoint using the specified local address.
 */
struct rxrpc_local *rxrpc_lookup_local(struct net *net,
				       const struct sockaddr_rxrpc *srx)
{
	struct rxrpc_local *local;
	struct rxrpc_net *rxnet = rxrpc_net(net);
	struct list_head *cursor;
	const char *age;
	long diff;
	int ret;

	_enter("{%d,%d,%pISp}",
	       srx->transport_type, srx->transport.family, &srx->transport);

	mutex_lock(&rxnet->local_mutex);

	for (cursor = rxnet->local_endpoints.next;
	     cursor != &rxnet->local_endpoints;
	     cursor = cursor->next) {
		local = list_entry(cursor, struct rxrpc_local, link);

		diff = rxrpc_local_cmp_key(local, srx);
		if (diff < 0)
			continue;
		if (diff > 0)
			break;

		/* Services aren't allowed to share transport sockets, so
		 * reject that here.  It is possible that the object is dying -
		 * but it may also still have the local transport address that
		 * we want bound.
		 */
		if (srx->srx_service) {
			local = NULL;
			goto addr_in_use;
		}

		/* Found a match.  We replace a dying object.  Attempting to
		 * bind the transport socket may still fail if we're attempting
		 * to use a local address that the dying object is still using.
		 */
		if (!rxrpc_get_local_maybe(local)) {
			cursor = cursor->next;
			list_del_init(&local->link);
			break;
		}

		age = "old";
		goto found;
	}

	local = rxrpc_alloc_local(rxnet, srx);
	if (!local)
		goto nomem;

	ret = rxrpc_open_socket(local, net);
	if (ret < 0)
		goto sock_error;

	list_add_tail(&local->link, cursor);
	age = "new";

found:
	mutex_unlock(&rxnet->local_mutex);

	_net("LOCAL %s %d {%pISp}",
	     age, local->debug_id, &local->srx.transport);

	_leave(" = %p", local);
	return local;

nomem:
	ret = -ENOMEM;
sock_error:
	mutex_unlock(&rxnet->local_mutex);
	if (local)
		call_rcu(&local->rcu, rxrpc_local_rcu);
	_leave(" = %d", ret);
	return ERR_PTR(ret);

addr_in_use:
	mutex_unlock(&rxnet->local_mutex);
	_leave(" = -EADDRINUSE");
	return ERR_PTR(-EADDRINUSE);
}

/*
 * Get a ref on a local endpoint.
 */
struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)
{
	const void *here = __builtin_return_address(0);
	int n;

	n = atomic_inc_return(&local->usage);
	trace_rxrpc_local(local, rxrpc_local_got, n, here);
	return local;
}

/*
 * Get a ref on a local endpoint unless its usage has already reached 0.
 */
struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
{
	const void *here = __builtin_return_address(0);

	if (local) {
		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
		if (n > 0)
			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
		else
			local = NULL;
	}
	return local;
}

/*
 * Queue a local endpoint.
 */
void rxrpc_queue_local(struct rxrpc_local *local)
{
	const void *here = __builtin_return_address(0);

	if (rxrpc_queue_work(&local->processor))
		trace_rxrpc_local(local, rxrpc_local_queued,
				  atomic_read(&local->usage), here);
}

/*
 * A local endpoint reached its end of life.
 */
static void __rxrpc_put_local(struct rxrpc_local *local)
{
	_enter("%d", local->debug_id);
	rxrpc_queue_work(&local->processor);
}

/*
 * Drop a ref on a local endpoint.
 */
void rxrpc_put_local(struct rxrpc_local *local)
{
	const void *here = __builtin_return_address(0);
	int n;

	if (local) {
		n = atomic_dec_return(&local->usage);
		trace_rxrpc_local(local, rxrpc_local_put, n, here);

		if (n == 0)
			__rxrpc_put_local(local);
	}
}

/*
 * Destroy a local endpoint's socket and then hand the record to RCU to dispose
 * of.
 *
 * Closing the socket cannot be done from bottom half context or RCU callback
 * context because it might sleep.
 */
static void rxrpc_local_destroyer(struct rxrpc_local *local)
{
	struct socket *socket = local->socket;
	struct rxrpc_net *rxnet = local->rxnet;

	_enter("%d", local->debug_id);

	/* We can get a race between an incoming call packet queueing the
	 * processor again and the work processor starting the destruction
	 * process which will shut down the UDP socket.
	 */
	if (local->dead) {
		_leave(" [already dead]");
		return;
	}
	local->dead = true;

	mutex_lock(&rxnet->local_mutex);
	list_del_init(&local->link);
	mutex_unlock(&rxnet->local_mutex);

	ASSERT(RB_EMPTY_ROOT(&local->client_conns));
	ASSERT(!local->service);

	if (socket) {
		local->socket = NULL;
		kernel_sock_shutdown(socket, SHUT_RDWR);
		socket->sk->sk_user_data = NULL;
		sock_release(socket);
	}

	/* At this point, there should be no more packets coming in to the
	 * local endpoint.
	 */
	rxrpc_purge_queue(&local->reject_queue);
	rxrpc_purge_queue(&local->event_queue);

	_debug("rcu local %d", local->debug_id);
	call_rcu(&local->rcu, rxrpc_local_rcu);
}

/*
 * Process events on an endpoint
 */
static void rxrpc_local_processor(struct work_struct *work)
{
	struct rxrpc_local *local =
		container_of(work, struct rxrpc_local, processor);
	bool again;

	trace_rxrpc_local(local, rxrpc_local_processing,
			  atomic_read(&local->usage), NULL);

	do {
		again = false;
		if (atomic_read(&local->usage) == 0)
			return rxrpc_local_destroyer(local);

		if (!skb_queue_empty(&local->reject_queue)) {
			rxrpc_reject_packets(local);
			again = true;
		}

		if (!skb_queue_empty(&local->event_queue)) {
			rxrpc_process_local_events(local);
			again = true;
		}
	} while (again);
}

/*
 * Destroy a local endpoint after the RCU grace period expires.
 */
static void rxrpc_local_rcu(struct rcu_head *rcu)
{
	struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu);

	_enter("%d", local->debug_id);

	ASSERT(!work_pending(&local->processor));

	_net("DESTROY LOCAL %d", local->debug_id);
	kfree(local);
	_leave("");
}

/*
 * Verify the local endpoint list is empty by this point.
 */
void rxrpc_destroy_all_locals(struct rxrpc_net *rxnet)
{
	struct rxrpc_local *local;

	_enter("");

	flush_workqueue(rxrpc_workqueue);

	if (!list_empty(&rxnet->local_endpoints)) {
		mutex_lock(&rxnet->local_mutex);
		list_for_each_entry(local, &rxnet->local_endpoints, link) {
			pr_err("AF_RXRPC: Leaked local %p {%d}\n",
			       local, atomic_read(&local->usage));
		}
		mutex_unlock(&rxnet->local_mutex);
		BUG();
	}
}