aboutsummaryrefslogtreecommitdiffstats
path: root/net/tipc/subscr.c
blob: 1a5b9a6bd128f177bb267089b6773ae9990feeca (plain) (blame)
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
/*
 * net/tipc/subscr.c: TIPC network topology service
 *
 * Copyright (c) 2000-2006, Ericsson AB
 * Copyright (c) 2005-2007, Wind River Systems
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. 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.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "core.h"
#include "dbg.h"
#include "name_table.h"
#include "port.h"
#include "ref.h"
#include "subscr.h"

/**
 * struct subscriber - TIPC network topology subscriber
 * @port_ref: object reference to server port connecting to subscriber
 * @lock: pointer to spinlock controlling access to subscriber's server port
 * @subscriber_list: adjacent subscribers in top. server's list of subscribers
 * @subscription_list: list of subscription objects for this subscriber
 */

struct subscriber {
	u32 port_ref;
	spinlock_t *lock;
	struct list_head subscriber_list;
	struct list_head subscription_list;
};

/**
 * struct top_srv - TIPC network topology subscription service
 * @user_ref: TIPC userid of subscription service
 * @setup_port: reference to TIPC port that handles subscription requests
 * @subscription_count: number of active subscriptions (not subscribers!)
 * @subscriber_list: list of ports subscribing to service
 * @lock: spinlock govering access to subscriber list
 */

struct top_srv {
	u32 user_ref;
	u32 setup_port;
	atomic_t subscription_count;
	struct list_head subscriber_list;
	spinlock_t lock;
};

static struct top_srv topsrv = { 0 };

/**
 * subscr_send_event - send a message containing a tipc_event to the subscriber
 *
 * Note: Must not hold subscriber's server port lock, since tipc_send() will
 *       try to take the lock if the message is rejected and returned!
 */

static void subscr_send_event(struct subscription *sub,
			      u32 found_lower,
			      u32 found_upper,
			      u32 event,
			      u32 port_ref,
			      u32 node)
{
	struct iovec msg_sect;

	msg_sect.iov_base = (void *)&sub->evt;
	msg_sect.iov_len = sizeof(struct tipc_event);

	sub->evt.event = htonl(event);
	sub->evt.found_lower = htonl(found_lower);
	sub->evt.found_upper = htonl(found_upper);
	sub->evt.port.ref = htonl(port_ref);
	sub->evt.port.node = htonl(node);
	tipc_send(sub->server_ref, 1, &msg_sect);
}

/**
 * tipc_subscr_overlap - test for subscription overlap with the given values
 *
 * Returns 1 if there is overlap, otherwise 0.
 */

int tipc_subscr_overlap(struct subscription *sub,
			u32 found_lower,
			u32 found_upper)

{
	if (found_lower < sub->seq.lower)
		found_lower = sub->seq.lower;
	if (found_upper > sub->seq.upper)
		found_upper = sub->seq.upper;
	if (found_lower > found_upper)
		return 0;
	return 1;
}

/**
 * tipc_subscr_report_overlap - issue event if there is subscription overlap
 *
 * Protected by nameseq.lock in name_table.c
 */

void tipc_subscr_report_overlap(struct subscription *sub,
				u32 found_lower,
				u32 found_upper,
				u32 event,
				u32 port_ref,
				u32 node,
				int must)
{
	if (!tipc_subscr_overlap(sub, found_lower, found_upper))
		return;
	if (!must && !(sub->filter & TIPC_SUB_PORTS))
		return;

	sub->event_cb(sub, found_lower, found_upper, event, port_ref, node);
}

/**
 * subscr_timeout - subscription timeout has occurred
 */

static void subscr_timeout(struct subscription *sub)
{
	struct port *server_port;

	/* Validate server port reference (in case subscriber is terminating) */

	server_port = tipc_port_lock(sub->server_ref);
	if (server_port == NULL)
		return;

	/* Validate timeout (in case subscription is being cancelled) */

	if (sub->timeout == TIPC_WAIT_FOREVER) {
		tipc_port_unlock(server_port);
		return;
	}

	/* Unlink subscription from name table */

	tipc_nametbl_unsubscribe(sub);

	/* Unlink subscription from subscriber */

	list_del(&sub->subscription_list);

	/* Release subscriber's server port */

	tipc_port_unlock(server_port);

	/* Notify subscriber of timeout */

	subscr_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
			  TIPC_SUBSCR_TIMEOUT, 0, 0);

	/* Now destroy subscription */

	k_term_timer(&sub->timer);
	kfree(sub);
	atomic_dec(&topsrv.subscription_count);
}

/**
 * subscr_del - delete a subscription within a subscription list
 *
 * Called with subscriber port locked.
 */

static void subscr_del(struct subscription *sub)
{
	tipc_nametbl_unsubscribe(sub);
	list_del(&sub->subscription_list);
	kfree(sub);
	atomic_dec(&topsrv.subscription_count);
}

/**
 * subscr_terminate - terminate communication with a subscriber
 *
 * Called with subscriber port locked.  Routine must temporarily release lock
 * to enable subscription timeout routine(s) to finish without deadlocking;
 * the lock is then reclaimed to allow caller to release it upon return.
 * (This should work even in the unlikely event some other thread creates
 * a new object reference in the interim that uses this lock; this routine will
 * simply wait for it to be released, then claim it.)
 */

static void subscr_terminate(struct subscriber *subscriber)
{
	u32 port_ref;
	struct subscription *sub;
	struct subscription *sub_temp;

	/* Invalidate subscriber reference */

	port_ref = subscriber->port_ref;
	subscriber->port_ref = 0;
	spin_unlock_bh(subscriber->lock);

	/* Sever connection to subscriber */

	tipc_shutdown(port_ref);
	tipc_deleteport(port_ref);

	/* Destroy any existing subscriptions for subscriber */

	list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
				 subscription_list) {
		if (sub->timeout != TIPC_WAIT_FOREVER) {
			k_cancel_timer(&sub->timer);
			k_term_timer(&sub->timer);
		}
		dbg("Term: Removing sub %u,%u,%u from subscriber %x list\n",
		    sub->seq.type, sub->seq.lower, sub->seq.upper, subscriber);
		subscr_del(sub);
	}

	/* Remove subscriber from topology server's subscriber list */

	spin_lock_bh(&topsrv.lock);
	list_del(&subscriber->subscriber_list);
	spin_unlock_bh(&topsrv.lock);

	/* Reclaim subscriber lock */

	spin_lock_bh(subscriber->lock);

	/* Now destroy subscriber */

	kfree(subscriber);
}

/**
 * subscr_cancel - handle subscription cancellation request
 *
 * Called with subscriber port locked.  Routine must temporarily release lock
 * to enable the subscription timeout routine to finish without deadlocking;
 * the lock is then reclaimed to allow caller to release it upon return.
 *
 * Note that fields of 's' use subscriber's endianness!
 */

static void subscr_cancel(struct tipc_subscr *s,
			  struct subscriber *subscriber)
{
	struct subscription *sub;
	struct subscription *sub_temp;
	__u32 type, lower, upper, timeout, filter;
	int found = 0;

	/* Find first matching subscription, exit if not found */

	type = ntohl(s->seq.type);
	lower = ntohl(s->seq.lower);
	upper = ntohl(s->seq.upper);
	timeout = ntohl(s->timeout);
	filter = ntohl(s->filter) & ~TIPC_SUB_CANCEL;

	list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
				 subscription_list) {
			if ((type == sub->seq.type) &&
			    (lower == sub->seq.lower) &&
			    (upper == sub->seq.upper) &&
			    (timeout == sub->timeout) &&
                            (filter == sub->filter) &&
                             !memcmp(s->usr_handle,sub->evt.s.usr_handle,
				     sizeof(s->usr_handle)) ){
				found = 1;
				break;
			}
	}
	if (!found)
		return;

	/* Cancel subscription timer (if used), then delete subscription */

	if (sub->timeout != TIPC_WAIT_FOREVER) {
		sub->timeout = TIPC_WAIT_FOREVER;
		spin_unlock_bh(subscriber->lock);
		k_cancel_timer(&sub->timer);
		k_term_timer(&sub->timer);
		spin_lock_bh(subscriber->lock);
	}
	dbg("Cancel: removing sub %u,%u,%u from subscriber %p list\n",
	    sub->seq.type, sub->seq.lower, sub->seq.upper, subscriber);
	subscr_del(sub);
}

/**
 * subscr_subscribe - create subscription for subscriber
 *
 * Called with subscriber port locked.
 */

static struct subscription *subscr_subscribe(struct tipc_subscr *s,
					     struct subscriber *subscriber)
{
	struct subscription *sub;

	/* Detect & process a subscription cancellation request */

	if (ntohl(s->filter) & TIPC_SUB_CANCEL) {
		subscr_cancel(s, subscriber);
		return NULL;
	}

	/* Refuse subscription if global limit exceeded */

	if (atomic_read(&topsrv.subscription_count) >= tipc_max_subscriptions) {
		warn("Subscription rejected, subscription limit reached (%u)\n",
		     tipc_max_subscriptions);
		subscr_terminate(subscriber);
		return NULL;
	}

	/* Allocate subscription object */

	sub = kmalloc(sizeof(*sub), GFP_ATOMIC);
	if (!sub) {
		warn("Subscription rejected, no memory\n");
		subscr_terminate(subscriber);
		return NULL;
	}

	/* Initialize subscription object */

	sub->seq.type = ntohl(s->seq.type);
	sub->seq.lower = ntohl(s->seq.lower);
	sub->seq.upper = ntohl(s->seq.upper);
	sub->timeout = ntohl(s->timeout);
	sub->filter = ntohl(s->filter);
	if ((sub->filter && (sub->filter != TIPC_SUB_PORTS)) ||
	    (sub->seq.lower > sub->seq.upper)) {
		warn("Subscription rejected, illegal request\n");
		kfree(sub);
		subscr_terminate(subscriber);
		return NULL;
	}
	sub->event_cb = subscr_send_event;
	INIT_LIST_HEAD(&sub->nameseq_list);
	list_add(&sub->subscription_list, &subscriber->subscription_list);
	sub->server_ref = subscriber->port_ref;
	memcpy(&sub->evt.s, s, sizeof(struct tipc_subscr));
	atomic_inc(&topsrv.subscription_count);
	if (sub->timeout != TIPC_WAIT_FOREVER) {
		k_init_timer(&sub->timer,
			     (Handler)subscr_timeout, (unsigned long)sub);
		k_start_timer(&sub->timer, sub->timeout);
	}

	return sub;
}

/**
 * subscr_conn_shutdown_event - handle termination request from subscriber
 *
 * Called with subscriber's server port unlocked.
 */

static void subscr_conn_shutdown_event(void *usr_handle,
				       u32 port_ref,
				       struct sk_buff **buf,
				       unsigned char const *data,
				       unsigned int size,
				       int reason)
{
	struct subscriber *subscriber = usr_handle;
	spinlock_t *subscriber_lock;

	if (tipc_port_lock(port_ref) == NULL)
		return;

	subscriber_lock = subscriber->lock;
	subscr_terminate(subscriber);
	spin_unlock_bh(subscriber_lock);
}

/**
 * subscr_conn_msg_event - handle new subscription request from subscriber
 *
 * Called with subscriber's server port unlocked.
 */

static void subscr_conn_msg_event(void *usr_handle,
				  u32 port_ref,
				  struct sk_buff **buf,
				  const unchar *data,
				  u32 size)
{
	struct subscriber *subscriber = usr_handle;
	spinlock_t *subscriber_lock;
	struct subscription *sub;

	/*
	 * Lock subscriber's server port (& make a local copy of lock pointer,
	 * in case subscriber is deleted while processing subscription request)
	 */

	if (tipc_port_lock(port_ref) == NULL)
		return;

	subscriber_lock = subscriber->lock;

	if (size != sizeof(struct tipc_subscr)) {
		subscr_terminate(subscriber);
		spin_unlock_bh(subscriber_lock);
	} else {
		sub = subscr_subscribe((struct tipc_subscr *)data, subscriber);
		spin_unlock_bh(subscriber_lock);
		if (sub != NULL) {

			/*
			 * We must release the server port lock before adding a
			 * subscription to the name table since TIPC needs to be
			 * able to (re)acquire the port lock if an event message
			 * issued by the subscription process is rejected and
			 * returned.  The subscription cannot be deleted while
			 * it is being added to the name table because:
			 * a) the single-threading of the native API port code
			 *    ensures the subscription cannot be cancelled and
			 *    the subscriber connection cannot be broken, and
			 * b) the name table lock ensures the subscription
			 *    timeout code cannot delete the subscription,
			 * so the subscription object is still protected.
			 */

			tipc_nametbl_subscribe(sub);
		}
	}
}

/**
 * subscr_named_msg_event - handle request to establish a new subscriber
 */

static void subscr_named_msg_event(void *usr_handle,
				   u32 port_ref,
				   struct sk_buff **buf,
				   const unchar *data,
				   u32 size,
				   u32 importance,
				   struct tipc_portid const *orig,
				   struct tipc_name_seq const *dest)
{
	static struct iovec msg_sect = {NULL, 0};

	struct subscriber *subscriber;
	u32 server_port_ref;

	/* Create subscriber object */

	subscriber = kzalloc(sizeof(struct subscriber), GFP_ATOMIC);
	if (subscriber == NULL) {
		warn("Subscriber rejected, no memory\n");
		return;
	}
	INIT_LIST_HEAD(&subscriber->subscription_list);
	INIT_LIST_HEAD(&subscriber->subscriber_list);

	/* Create server port & establish connection to subscriber */

	tipc_createport(topsrv.user_ref,
			subscriber,
			importance,
			NULL,
			NULL,
			subscr_conn_shutdown_event,
			NULL,
			NULL,
			subscr_conn_msg_event,
			NULL,
			&subscriber->port_ref);
	if (subscriber->port_ref == 0) {
		warn("Subscriber rejected, unable to create port\n");
		kfree(subscriber);
		return;
	}
	tipc_connect2port(subscriber->port_ref, orig);

	/* Lock server port (& save lock address for future use) */

	subscriber->lock = tipc_port_lock(subscriber->port_ref)->publ.lock;

	/* Add subscriber to topology server's subscriber list */

	spin_lock_bh(&topsrv.lock);
	list_add(&subscriber->subscriber_list, &topsrv.subscriber_list);
	spin_unlock_bh(&topsrv.lock);

	/* Unlock server port */

	server_port_ref = subscriber->port_ref;
	spin_unlock_bh(subscriber->lock);

	/* Send an ACK- to complete connection handshaking */

	tipc_send(server_port_ref, 1, &msg_sect);

	/* Handle optional subscription request */

	if (size != 0) {
		subscr_conn_msg_event(subscriber, server_port_ref,
				      buf, data, size);
	}
}

int tipc_subscr_start(void)
{
	struct tipc_name_seq seq = {TIPC_TOP_SRV, TIPC_TOP_SRV, TIPC_TOP_SRV};
	int res = -1;

	memset(&topsrv, 0, sizeof (topsrv));
	spin_lock_init(&topsrv.lock);
	INIT_LIST_HEAD(&topsrv.subscriber_list);

	spin_lock_bh(&topsrv.lock);
	res = tipc_attach(&topsrv.user_ref, NULL, NULL);
	if (res) {
		spin_unlock_bh(&topsrv.lock);
		return res;
	}

	res = tipc_createport(topsrv.user_ref,
			      NULL,
			      TIPC_CRITICAL_IMPORTANCE,
			      NULL,
			      NULL,
			      NULL,
			      NULL,
			      subscr_named_msg_event,
			      NULL,
			      NULL,
			      &topsrv.setup_port);
	if (res)
		goto failed;

	res = tipc_nametbl_publish_rsv(topsrv.setup_port, TIPC_NODE_SCOPE, &seq);
	if (res)
		goto failed;

	spin_unlock_bh(&topsrv.lock);
	return 0;

failed:
	err("Failed to create subscription service\n");
	tipc_detach(topsrv.user_ref);
	topsrv.user_ref = 0;
	spin_unlock_bh(&topsrv.lock);
	return res;
}

void tipc_subscr_stop(void)
{
	struct subscriber *subscriber;
	struct subscriber *subscriber_temp;
	spinlock_t *subscriber_lock;

	if (topsrv.user_ref) {
		tipc_deleteport(topsrv.setup_port);
		list_for_each_entry_safe(subscriber, subscriber_temp,
					 &topsrv.subscriber_list,
					 subscriber_list) {
			subscriber_lock = subscriber->lock;
			spin_lock_bh(subscriber_lock);
			subscr_terminate(subscriber);
			spin_unlock_bh(subscriber_lock);
		}
		tipc_detach(topsrv.user_ref);
		topsrv.user_ref = 0;
	}
}


int tipc_ispublished(struct tipc_name const *name)
{
	u32 domain = 0;

	return tipc_nametbl_translate(name->type, name->instance, &domain) != 0;
}

'>bc0d6501a844
303a3acb2362
f0bdc8cdd9a2
303a3acb2362
bc0d6501a844
303a3acb2362


3c798398e393
303a3acb2362
d3d32e69fa36



303a3acb2362

d3d32e69fa36










810ecfa765f8


d3d32e69fa36



3c798398e393
f95a04afa80c

3c798398e393
ec399347d39f
5624a4e445e2
3c798398e393
d3d32e69fa36
5624a4e445e2
810ecfa765f8
ee89f8125217
810ecfa765f8
a2b1693bac45
f95a04afa80c
810ecfa765f8


d3d32e69fa36



829fdb50004d
d3d32e69fa36



f95a04afa80c
d3d32e69fa36

f95a04afa80c
d3d32e69fa36
f95a04afa80c
d3d32e69fa36
f95a04afa80c
d3d32e69fa36






829fdb50004d
d3d32e69fa36



f95a04afa80c
d3d32e69fa36

f95a04afa80c
d3d32e69fa36
f95a04afa80c
829fdb50004d
d3d32e69fa36






f95a04afa80c
d3d32e69fa36













b50da39f5113
d3d32e69fa36
5bc4afb1ec6a


f95a04afa80c

5bc4afb1ec6a


f95a04afa80c
d3d32e69fa36
f95a04afa80c
d3d32e69fa36
5bc4afb1ec6a
d3d32e69fa36
5bc4afb1ec6a


f95a04afa80c

5bc4afb1ec6a


f95a04afa80c

d3d32e69fa36
f95a04afa80c
d3d32e69fa36
f95a04afa80c
d3d32e69fa36
5bc4afb1ec6a
d3d32e69fa36
3a8b31d396b2
16b3de6652c7











492eb21b98f8
bd8815a6d802
16b3de6652c7


16b3de6652c7
492eb21b98f8
16b3de6652c7

























492eb21b98f8
bd8815a6d802
16b3de6652c7



16b3de6652c7
492eb21b98f8
16b3de6652c7


















3a8b31d396b2

da8b066262e1
3a8b31d396b2




da8b066262e1

3a8b31d396b2
3c798398e393

da8b066262e1
34d0f179d6dd
3a8b31d396b2
3c798398e393
726fa6945e6e


34d0f179d6dd
726fa6945e6e

3a8b31d396b2
726fa6945e6e
4bfd482e73b3
726fa6945e6e
e56da7e28796

4bfd482e73b3
da8b066262e1
a2b1693bac45
3c96cb32d318
a2b1693bac45

e56da7e28796
4bfd482e73b3

3a8b31d396b2
da8b066262e1
3a8b31d396b2









7702e8f45b0a
726fa6945e6e
062a644d6121
3a8b31d396b2


726fa6945e6e

34d0f179d6dd
829fdb50004d
34d0f179d6dd
3a8b31d396b2






829fdb50004d
da8b066262e1
34d0f179d6dd
da8b066262e1
3a8b31d396b2

34d0f179d6dd
829fdb50004d
34d0f179d6dd
3c798398e393
31e4c28d95e6
84c124da9ff5
3c798398e393
220841906fcc
4baf6e33251b
31e4c28d95e6

9f13ef678efd
92fb97487a7e
eb95419b023a
9f13ef678efd
eb95419b023a

9f13ef678efd




eb95419b023a
31e4c28d95e6
eb95419b023a
b1c357696184
9f13ef678efd
7ee9c5620504
9f13ef678efd
3c798398e393

c875f4d0250a
b1c357696184
9f13ef678efd




9f13ef678efd
a5567932fc92
0f3942a39ed7
9f13ef678efd
b1c357696184
9f13ef678efd
7ee9c5620504

eb95419b023a
7ee9c5620504
eb95419b023a
7ee9c5620504
3c798398e393
67523c48aa74
31e4c28d95e6

eb95419b023a

31e4c28d95e6
3c798398e393
31e4c28d95e6
eb95419b023a
3c798398e393
31e4c28d95e6


31e4c28d95e6



3381cb8d2ef1
e71357e118bd
31e4c28d95e6

a637120e4902
31e4c28d95e6




5efd611351d1













3c96cb32d318
5efd611351d1











0b462c89e31f






5efd611351d1










6d18b008daf4
3c96cb32d318
6d18b008daf4

5efd611351d1


31e4c28d95e6





eb95419b023a

31e4c28d95e6
bb9d97b6dffa
31e4c28d95e6



924f0d9a2078
bb9d97b6dffa







31e4c28d95e6


073219e995b4
92fb97487a7e


3c798398e393
5577964e6469
1ced953b17bf







676f7c8f84d1
073219e995b4
676f7c8f84d1
8bd435b30eca
a2b1693bac45















3c798398e393
a2b1693bac45

86cde6b62313
a2b1693bac45

159749937a3e
a2b1693bac45



159749937a3e
86cde6b62313

159749937a3e

a2b1693bac45

e5072664f823

86cde6b62313




a2b1693bac45


86cde6b62313




a2b1693bac45

159749937a3e


a2b1693bac45



a2b1693bac45







f95a04afa80c
a2b1693bac45


























b276a876a014
f9fcc2d3919b
a2b1693bac45
























3c798398e393
a2b1693bac45
3c798398e393
a2b1693bac45








6d18b008daf4



a2b1693bac45



f427d909648a

f9fcc2d3919b

a2b1693bac45












3c798398e393

8bd435b30eca
3c798398e393

8bd435b30eca
d5bf02914ea3
3e2520668970
8bd435b30eca
e8989fae38d9
f95a04afa80c


bc0d6501a844

8bd435b30eca


3c798398e393
8bd435b30eca


035d10b2fa7e
8bd435b30eca
3c798398e393

8bd435b30eca
8bd435b30eca
3c798398e393
2cf669a58dc0

8bd435b30eca

bc0d6501a844
8bd435b30eca
3e2520668970
3c798398e393
3e2520668970
8bd435b30eca
3c798398e393

8bd435b30eca
3c798398e393
8bd435b30eca
3c798398e393
3e2520668970
bc0d6501a844

3c798398e393
8bd435b30eca


3c798398e393
2bb566cb68df
44ea53de46a8
8bd435b30eca
3c798398e393
8bd435b30eca
bc0d6501a844
3e2520668970
3c798398e393
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
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160












                                                              
                         
                         
                      
                         
                       
                        
                        
                         
                       
                
 

                       
                                     
 

                                                                         
                              
 
                                                         
 
                                                         
                                                                



                                                         





                                               
                                            
 
              



                       

                                            
 
                               
                    





                                                       
                                    
  
                                                
   

                                                                                
 
                              
              

                                      
                                                              


                            
                    
                                      
                            
                                     
 






                                                                      
                                              
                                                           
                                            
 
                                                  


                                                                 
                                                                   

                                      
 

                                 
                             

         
                    



                        

 










                                                                          

                                                                            
 
                              
 




                                                 



                                                                          

                                                           




                                                                   
                            
         
 











                                                                           
                                                                          




                                            
                                              


                               



                                                                        


                                                              
 
                              
                   
 


                                            
                                             
                                              

                                   
         
 
                      


                                                            

                                         


                        
 
                         


                                                                            
                                      




                                         








                                                           
                                



                                                                         






                                                                   
         
                            
                                  
 




                                               
                            
         
 



                                                                        
            
                             
              
                            
                            
 
 





                                                                     


                                                                           




                                                                          

                                                            
 




                                            




                                                                           
                                                                      




                                             
















                                                                           
 
                                      
 
                                               
 
                                          
              
 
                                                 
                                          

                                                                         
                                                
                                                        
 







                                                           
                                                          
                                     
                                              
 
          



                                                                          
                                                         


                                                           








                                                                           





                                                                           


                                                                       
  
                                        
   
                                                     
 
                                  
 
                                           
 
                                                                  
                                                  
 


                                          


         








                                                                          
 
                                                                                  









                                                           
                                                                               
                                   
                         
                                       
 
                        
 
                                      
 















                                                                        


                                                                            















                                                             

                                                             
 
                                                
                              
              
 













                                                                           
                                    





                                                                        
                                                                   
                                                      
                                                                   
 
                                                                 

                                                             
                 
         
 
                                      
                                       


                 
                                                       
 



                                                                           

 










                                                                     


                                                                          



                                                      
                                                                

                                                                     
                                                                
                                       
 
                              
                      
 
                        
                                                                       
                                                   
                                                       
                                                                       


                                                     



                                                                          
                                     



                                                           
                                       

                     
                                                      
   
                                                                              
 
                                                    






                                                                  
                                     



                                                         
                                       

                           
                                                           
   
                                                                          
                                                          






                                                  
                                                    













                                                                           
                                        
 


                                                   

                                       


                                            
                                                                               
 
                                                                           
 
                                    
 


                                                       

                                         


                                              

                                                                        
 
                                                                       
 
                                                     
 
                                      
 
   











                                                                        
                                            
                    


                                                     
                        
                                                                         

























                                                                            
                                            
                                     



                                                     
                        
                                                                         


















                                                                            

                                                                
                      




                                                                           

                                                                           
   

                                                                       
                                                           
 
                             
                              


                                  
 

                                                                 
 
                                                       
                          
                               

                        
                                               
 
                                                   
                                                              

                                        
 

                                    
                                  
                                                         









                                                                          
                 
                           
         


                         

                   
 
                                  
 






                                                                        
                                                
                                                                
 
                                                      

                            
 
                                    
 
                               
         
                                      
                                               
          
                               

  
   
                                                  
                        
  

                                                                        




                                                                         
                                                              
 
                                                
 
                                    
 
                                                 

                                                                             
                                                  
 




                                                      
                                    
                                                    
                 
         
 
                                      

 
                                                           
 
                                                
 
                                 
                             

 

                                                       
 
                            
 
                          
                                    


                          



                                                    
                                               
                                                    

                                     
                                                       




                                           













                                                                         
                                  











                                                                       






                                                                       










                                                                        
                                     
                            

                                       


                           





                                                                           

                                                            
 
                                 



                                                                         
                                             







                                                           


                   
                                          


                                         
                                       
                                      







                                                                          
  
                                     
 
   















                                                                          
                                                         

                       
                                         

                                        
                       



                                         
                                          

                                                          

                               

                                  

                                                    




                                                                           


                                     




                                                             

                          


                                         



                                    







                                                         
                                                                     


























                                                                                 
                                     
                                      
























                                                                         
                                                            
 
                              








                                              



                                                                       



                                                                       

                                                 

                                              












                                                

                                                  
  

                                                                          
   
                                                   
 
                   
 


                                                                    

                                     


                                            
                                     


                                
 
                                       

                              
 
                                                                       
                         

                                                                     

                
                                       
                   
 
                                         
 
   

                                                      
  
                                                  
   
                                                      
 

                                     
                                                    


                                       
                         
                                                
 
                                         
                                       
           
                                       
 
                                           
/*
 * Common Block IO controller cgroup interface
 *
 * Based on ideas and code from CFQ, CFS and BFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
 * 	              Nauman Rafique <nauman@google.com>
 */
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/genhd.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include "blk-cgroup.h"
#include "blk.h"

#define MAX_KEY_LEN 100

static DEFINE_MUTEX(blkcg_pol_mutex);

struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT,
			    .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, };
EXPORT_SYMBOL_GPL(blkcg_root);

static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];

static bool blkcg_policy_enabled(struct request_queue *q,
				 const struct blkcg_policy *pol)
{
	return pol && test_bit(pol->plid, q->blkcg_pols);
}

/**
 * blkg_free - free a blkg
 * @blkg: blkg to free
 *
 * Free @blkg which may be partially allocated.
 */
static void blkg_free(struct blkcg_gq *blkg)
{
	int i;

	if (!blkg)
		return;

	for (i = 0; i < BLKCG_MAX_POLS; i++)
		kfree(blkg->pd[i]);

	blk_exit_rl(&blkg->rl);
	kfree(blkg);
}

/**
 * blkg_alloc - allocate a blkg
 * @blkcg: block cgroup the new blkg is associated with
 * @q: request_queue the new blkg is associated with
 * @gfp_mask: allocation mask to use
 *
 * Allocate a new blkg assocating @blkcg and @q.
 */
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
				   gfp_t gfp_mask)
{
	struct blkcg_gq *blkg;
	int i;

	/* alloc and init base part */
	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
	if (!blkg)
		return NULL;

	blkg->q = q;
	INIT_LIST_HEAD(&blkg->q_node);
	blkg->blkcg = blkcg;
	atomic_set(&blkg->refcnt, 1);

	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
	if (blkcg != &blkcg_root) {
		if (blk_init_rl(&blkg->rl, q, gfp_mask))
			goto err_free;
		blkg->rl.blkg = blkg;
	}

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkg_policy_data *pd;

		if (!blkcg_policy_enabled(q, pol))
			continue;

		/* alloc per-policy data and attach it to blkg */
		pd = kzalloc_node(pol->pd_size, gfp_mask, q->node);
		if (!pd)
			goto err_free;

		blkg->pd[i] = pd;
		pd->blkg = blkg;
		pd->plid = i;
	}

	return blkg;

err_free:
	blkg_free(blkg);
	return NULL;
}

/**
 * __blkg_lookup - internal version of blkg_lookup()
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 * @update_hint: whether to update lookup hint with the result or not
 *
 * This is internal version and shouldn't be used by policy
 * implementations.  Looks up blkgs for the @blkcg - @q pair regardless of
 * @q's bypass state.  If @update_hint is %true, the caller should be
 * holding @q->queue_lock and lookup hint is updated on success.
 */
struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q,
			       bool update_hint)
{
	struct blkcg_gq *blkg;

	blkg = rcu_dereference(blkcg->blkg_hint);
	if (blkg && blkg->q == q)
		return blkg;

	/*
	 * Hint didn't match.  Look up from the radix tree.  Note that the
	 * hint can only be updated under queue_lock as otherwise @blkg
	 * could have already been removed from blkg_tree.  The caller is
	 * responsible for grabbing queue_lock if @update_hint.
	 */
	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
	if (blkg && blkg->q == q) {
		if (update_hint) {
			lockdep_assert_held(q->queue_lock);
			rcu_assign_pointer(blkcg->blkg_hint, blkg);
		}
		return blkg;
	}

	return NULL;
}

/**
 * blkg_lookup - lookup blkg for the specified blkcg - q pair
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 *
 * Lookup blkg for the @blkcg - @q pair.  This function should be called
 * under RCU read lock and is guaranteed to return %NULL if @q is bypassing
 * - see blk_queue_bypass_start() for details.
 */
struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q)
{
	WARN_ON_ONCE(!rcu_read_lock_held());

	if (unlikely(blk_queue_bypass(q)))
		return NULL;
	return __blkg_lookup(blkcg, q, false);
}
EXPORT_SYMBOL_GPL(blkg_lookup);

/*
 * If @new_blkg is %NULL, this function tries to allocate a new one as
 * necessary using %GFP_ATOMIC.  @new_blkg is always consumed on return.
 */
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
				    struct request_queue *q,
				    struct blkcg_gq *new_blkg)
{
	struct blkcg_gq *blkg;
	int i, ret;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(q->queue_lock);

	/* blkg holds a reference to blkcg */
	if (!css_tryget_online(&blkcg->css)) {
		ret = -EINVAL;
		goto err_free_blkg;
	}

	/* allocate */
	if (!new_blkg) {
		new_blkg = blkg_alloc(blkcg, q, GFP_ATOMIC);
		if (unlikely(!new_blkg)) {
			ret = -ENOMEM;
			goto err_put_css;
		}
	}
	blkg = new_blkg;

	/* link parent */
	if (blkcg_parent(blkcg)) {
		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
		if (WARN_ON_ONCE(!blkg->parent)) {
			ret = -EINVAL;
			goto err_put_css;
		}
		blkg_get(blkg->parent);
	}

	/* invoke per-policy init */
	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_init_fn)
			pol->pd_init_fn(blkg);
	}

	/* insert */
	spin_lock(&blkcg->lock);
	ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
	if (likely(!ret)) {
		hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
		list_add(&blkg->q_node, &q->blkg_list);

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkg->pd[i] && pol->pd_online_fn)
				pol->pd_online_fn(blkg);
		}
	}
	blkg->online = true;
	spin_unlock(&blkcg->lock);

	if (!ret) {
		if (blkcg == &blkcg_root) {
			q->root_blkg = blkg;
			q->root_rl.blkg = blkg;
		}
		return blkg;
	}

	/* @blkg failed fully initialized, use the usual release path */
	blkg_put(blkg);
	return ERR_PTR(ret);

err_put_css:
	css_put(&blkcg->css);
err_free_blkg:
	blkg_free(new_blkg);
	return ERR_PTR(ret);
}

/**
 * blkg_lookup_create - lookup blkg, try to create one if not there
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 *
 * Lookup blkg for the @blkcg - @q pair.  If it doesn't exist, try to
 * create one.  blkg creation is performed recursively from blkcg_root such
 * that all non-root blkg's have access to the parent blkg.  This function
 * should be called under RCU read lock and @q->queue_lock.
 *
 * Returns pointer to the looked up or created blkg on success, ERR_PTR()
 * value on error.  If @q is dead, returns ERR_PTR(-EINVAL).  If @q is not
 * dead and bypassing, returns ERR_PTR(-EBUSY).
 */
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q)
{
	struct blkcg_gq *blkg;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(q->queue_lock);

	/*
	 * This could be the first entry point of blkcg implementation and
	 * we shouldn't allow anything to go through for a bypassing queue.
	 */
	if (unlikely(blk_queue_bypass(q)))
		return ERR_PTR(blk_queue_dying(q) ? -EINVAL : -EBUSY);

	blkg = __blkg_lookup(blkcg, q, true);
	if (blkg)
		return blkg;

	/*
	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
	 * non-root blkgs have access to their parents.
	 */
	while (true) {
		struct blkcg *pos = blkcg;
		struct blkcg *parent = blkcg_parent(blkcg);

		while (parent && !__blkg_lookup(parent, q, false)) {
			pos = parent;
			parent = blkcg_parent(parent);
		}

		blkg = blkg_create(pos, q, NULL);
		if (pos == blkcg || IS_ERR(blkg))
			return blkg;
	}
}
EXPORT_SYMBOL_GPL(blkg_lookup_create);

static void blkg_destroy(struct blkcg_gq *blkg)
{
	struct blkcg *blkcg = blkg->blkcg;
	int i;

	lockdep_assert_held(blkg->q->queue_lock);
	lockdep_assert_held(&blkcg->lock);

	/* Something wrong if we are trying to remove same group twice */
	WARN_ON_ONCE(list_empty(&blkg->q_node));
	WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_offline_fn)
			pol->pd_offline_fn(blkg);
	}
	blkg->online = false;

	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
	list_del_init(&blkg->q_node);
	hlist_del_init_rcu(&blkg->blkcg_node);

	/*
	 * Both setting lookup hint to and clearing it from @blkg are done
	 * under queue_lock.  If it's not pointing to @blkg now, it never
	 * will.  Hint assignment itself can race safely.
	 */
	if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
		rcu_assign_pointer(blkcg->blkg_hint, NULL);

	/*
	 * If root blkg is destroyed.  Just clear the pointer since root_rl
	 * does not take reference on root blkg.
	 */
	if (blkcg == &blkcg_root) {
		blkg->q->root_blkg = NULL;
		blkg->q->root_rl.blkg = NULL;
	}

	/*
	 * Put the reference taken at the time of creation so that when all
	 * queues are gone, group can be destroyed.
	 */
	blkg_put(blkg);
}

/**
 * blkg_destroy_all - destroy all blkgs associated with a request_queue
 * @q: request_queue of interest
 *
 * Destroy all blkgs associated with @q.
 */
static void blkg_destroy_all(struct request_queue *q)
{
	struct blkcg_gq *blkg, *n;

	lockdep_assert_held(q->queue_lock);

	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
		struct blkcg *blkcg = blkg->blkcg;

		spin_lock(&blkcg->lock);
		blkg_destroy(blkg);
		spin_unlock(&blkcg->lock);
	}
}

/*
 * A group is RCU protected, but having an rcu lock does not mean that one
 * can access all the fields of blkg and assume these are valid.  For
 * example, don't try to follow throtl_data and request queue links.
 *
 * Having a reference to blkg under an rcu allows accesses to only values
 * local to groups like group stats and group rate limits.
 */
void __blkg_release_rcu(struct rcu_head *rcu_head)
{
	struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head);
	int i;

	/* tell policies that this one is being freed */
	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_exit_fn)
			pol->pd_exit_fn(blkg);
	}

	/* release the blkcg and parent blkg refs this blkg has been holding */
	css_put(&blkg->blkcg->css);
	if (blkg->parent)
		blkg_put(blkg->parent);

	blkg_free(blkg);
}
EXPORT_SYMBOL_GPL(__blkg_release_rcu);

/*
 * The next function used by blk_queue_for_each_rl().  It's a bit tricky
 * because the root blkg uses @q->root_rl instead of its own rl.
 */
struct request_list *__blk_queue_next_rl(struct request_list *rl,
					 struct request_queue *q)
{
	struct list_head *ent;
	struct blkcg_gq *blkg;

	/*
	 * Determine the current blkg list_head.  The first entry is
	 * root_rl which is off @q->blkg_list and mapped to the head.
	 */
	if (rl == &q->root_rl) {
		ent = &q->blkg_list;
		/* There are no more block groups, hence no request lists */
		if (list_empty(ent))
			return NULL;
	} else {
		blkg = container_of(rl, struct blkcg_gq, rl);
		ent = &blkg->q_node;
	}

	/* walk to the next list_head, skip root blkcg */
	ent = ent->next;
	if (ent == &q->root_blkg->q_node)
		ent = ent->next;
	if (ent == &q->blkg_list)
		return NULL;

	blkg = container_of(ent, struct blkcg_gq, q_node);
	return &blkg->rl;
}

static int blkcg_reset_stats(struct cgroup_subsys_state *css,
			     struct cftype *cftype, u64 val)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct blkcg_gq *blkg;
	int i;

	/*
	 * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
	 * which ends up putting cgroup's internal cgroup_tree_mutex under
	 * it; however, cgroup_tree_mutex is nested above cgroup file
	 * active protection and grabbing blkcg_pol_mutex from a cgroup
	 * file operation creates a possible circular dependency.  cgroup
	 * internal locking is planned to go through further simplification
	 * and this issue should go away soon.  For now, let's trylock
	 * blkcg_pol_mutex and restart the write on failure.
	 *
	 * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
	 */
	if (!mutex_trylock(&blkcg_pol_mutex))
		return restart_syscall();
	spin_lock_irq(&blkcg->lock);

	/*
	 * Note that stat reset is racy - it doesn't synchronize against
	 * stat updates.  This is a debug feature which shouldn't exist
	 * anyway.  If you get hit by a race, retry.
	 */
	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkcg_policy_enabled(blkg->q, pol) &&
			    pol->pd_reset_stats_fn)
				pol->pd_reset_stats_fn(blkg);
		}
	}

	spin_unlock_irq(&blkcg->lock);
	mutex_unlock(&blkcg_pol_mutex);
	return 0;
}

static const char *blkg_dev_name(struct blkcg_gq *blkg)
{
	/* some drivers (floppy) instantiate a queue w/o disk registered */
	if (blkg->q->backing_dev_info.dev)
		return dev_name(blkg->q->backing_dev_info.dev);
	return NULL;
}

/**
 * blkcg_print_blkgs - helper for printing per-blkg data
 * @sf: seq_file to print to
 * @blkcg: blkcg of interest
 * @prfill: fill function to print out a blkg
 * @pol: policy in question
 * @data: data to be passed to @prfill
 * @show_total: to print out sum of prfill return values or not
 *
 * This function invokes @prfill on each blkg of @blkcg if pd for the
 * policy specified by @pol exists.  @prfill is invoked with @sf, the
 * policy data and @data and the matching queue lock held.  If @show_total
 * is %true, the sum of the return values from @prfill is printed with
 * "Total" label at the end.
 *
 * This is to be used to construct print functions for
 * cftype->read_seq_string method.
 */
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
		       u64 (*prfill)(struct seq_file *,
				     struct blkg_policy_data *, int),
		       const struct blkcg_policy *pol, int data,
		       bool show_total)
{
	struct blkcg_gq *blkg;
	u64 total = 0;

	rcu_read_lock();
	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
		spin_lock_irq(blkg->q->queue_lock);
		if (blkcg_policy_enabled(blkg->q, pol))
			total += prfill(sf, blkg->pd[pol->plid], data);
		spin_unlock_irq(blkg->q->queue_lock);
	}
	rcu_read_unlock();

	if (show_total)
		seq_printf(sf, "Total %llu\n", (unsigned long long)total);
}
EXPORT_SYMBOL_GPL(blkcg_print_blkgs);

/**
 * __blkg_prfill_u64 - prfill helper for a single u64 value
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @v: value to print
 *
 * Print @v to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
{
	const char *dname = blkg_dev_name(pd->blkg);

	if (!dname)
		return 0;

	seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_u64);

/**
 * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @rwstat: rwstat to print
 *
 * Print @rwstat to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
			 const struct blkg_rwstat *rwstat)
{
	static const char *rwstr[] = {
		[BLKG_RWSTAT_READ]	= "Read",
		[BLKG_RWSTAT_WRITE]	= "Write",
		[BLKG_RWSTAT_SYNC]	= "Sync",
		[BLKG_RWSTAT_ASYNC]	= "Async",
	};
	const char *dname = blkg_dev_name(pd->blkg);
	u64 v;
	int i;

	if (!dname)
		return 0;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
			   (unsigned long long)rwstat->cnt[i]);

	v = rwstat->cnt[BLKG_RWSTAT_READ] + rwstat->cnt[BLKG_RWSTAT_WRITE];
	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);

/**
 * blkg_prfill_stat - prfill callback for blkg_stat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_stat in @pd
 *
 * prfill callback for printing a blkg_stat.
 */
u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off)
{
	return __blkg_prfill_u64(sf, pd, blkg_stat_read((void *)pd + off));
}
EXPORT_SYMBOL_GPL(blkg_prfill_stat);

/**
 * blkg_prfill_rwstat - prfill callback for blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_rwstat in @pd
 *
 * prfill callback for printing a blkg_rwstat.
 */
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
		       int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd + off);

	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);

/**
 * blkg_stat_recursive_sum - collect hierarchical blkg_stat
 * @pd: policy private data of interest
 * @off: offset to the blkg_stat in @pd
 *
 * Collect the blkg_stat specified by @off from @pd and all its online
 * descendants and return the sum.  The caller must be holding the queue
 * lock for online tests.
 */
u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off)
{
	struct blkcg_policy *pol = blkcg_policy[pd->plid];
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	u64 sum = 0;

	lockdep_assert_held(pd->blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
		struct blkg_stat *stat = (void *)pos_pd + off;

		if (pos_blkg->online)
			sum += blkg_stat_read(stat);
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_stat_recursive_sum);

/**
 * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
 * @pd: policy private data of interest
 * @off: offset to the blkg_stat in @pd
 *
 * Collect the blkg_rwstat specified by @off from @pd and all its online
 * descendants and return the sum.  The caller must be holding the queue
 * lock for online tests.
 */
struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
					     int off)
{
	struct blkcg_policy *pol = blkcg_policy[pd->plid];
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	struct blkg_rwstat sum = { };
	int i;

	lockdep_assert_held(pd->blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
		struct blkg_rwstat *rwstat = (void *)pos_pd + off;
		struct blkg_rwstat tmp;

		if (!pos_blkg->online)
			continue;

		tmp = blkg_rwstat_read(rwstat);

		for (i = 0; i < BLKG_RWSTAT_NR; i++)
			sum.cnt[i] += tmp.cnt[i];
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);

/**
 * blkg_conf_prep - parse and prepare for per-blkg config update
 * @blkcg: target block cgroup
 * @pol: target policy
 * @input: input string
 * @ctx: blkg_conf_ctx to be filled
 *
 * Parse per-blkg config update from @input and initialize @ctx with the
 * result.  @ctx->blkg points to the blkg to be updated and @ctx->v the new
 * value.  This function returns with RCU read lock and queue lock held and
 * must be paired with blkg_conf_finish().
 */
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
		   const char *input, struct blkg_conf_ctx *ctx)
	__acquires(rcu) __acquires(disk->queue->queue_lock)
{
	struct gendisk *disk;
	struct blkcg_gq *blkg;
	unsigned int major, minor;
	unsigned long long v;
	int part, ret;

	if (sscanf(input, "%u:%u %llu", &major, &minor, &v) != 3)
		return -EINVAL;

	disk = get_gendisk(MKDEV(major, minor), &part);
	if (!disk || part)
		return -EINVAL;

	rcu_read_lock();
	spin_lock_irq(disk->queue->queue_lock);

	if (blkcg_policy_enabled(disk->queue, pol))
		blkg = blkg_lookup_create(blkcg, disk->queue);
	else
		blkg = ERR_PTR(-EINVAL);

	if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		rcu_read_unlock();
		spin_unlock_irq(disk->queue->queue_lock);
		put_disk(disk);
		/*
		 * If queue was bypassing, we should retry.  Do so after a
		 * short msleep().  It isn't strictly necessary but queue
		 * can be bypassing for some time and it's always nice to
		 * avoid busy looping.
		 */
		if (ret == -EBUSY) {
			msleep(10);
			ret = restart_syscall();
		}
		return ret;
	}

	ctx->disk = disk;
	ctx->blkg = blkg;
	ctx->v = v;
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_conf_prep);

/**
 * blkg_conf_finish - finish up per-blkg config update
 * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep()
 *
 * Finish up after per-blkg config update.  This function must be paired
 * with blkg_conf_prep().
 */
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
{
	spin_unlock_irq(ctx->disk->queue->queue_lock);
	rcu_read_unlock();
	put_disk(ctx->disk);
}
EXPORT_SYMBOL_GPL(blkg_conf_finish);

struct cftype blkcg_files[] = {
	{
		.name = "reset_stats",
		.write_u64 = blkcg_reset_stats,
	},
	{ }	/* terminate */
};

/**
 * blkcg_css_offline - cgroup css_offline callback
 * @css: css of interest
 *
 * This function is called when @css is about to go away and responsible
 * for shooting down all blkgs associated with @css.  blkgs should be
 * removed while holding both q and blkcg locks.  As blkcg lock is nested
 * inside q lock, this function performs reverse double lock dancing.
 *
 * This is the blkcg counterpart of ioc_release_fn().
 */
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);

	spin_lock_irq(&blkcg->lock);

	while (!hlist_empty(&blkcg->blkg_list)) {
		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
						struct blkcg_gq, blkcg_node);
		struct request_queue *q = blkg->q;

		if (spin_trylock(q->queue_lock)) {
			blkg_destroy(blkg);
			spin_unlock(q->queue_lock);
		} else {
			spin_unlock_irq(&blkcg->lock);
			cpu_relax();
			spin_lock_irq(&blkcg->lock);
		}
	}

	spin_unlock_irq(&blkcg->lock);
}

static void blkcg_css_free(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);

	if (blkcg != &blkcg_root)
		kfree(blkcg);
}

static struct cgroup_subsys_state *
blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct blkcg *blkcg;

	if (!parent_css) {
		blkcg = &blkcg_root;
		goto done;
	}

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

	blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT;
	blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT;
done:
	spin_lock_init(&blkcg->lock);
	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
	INIT_HLIST_HEAD(&blkcg->blkg_list);

	return &blkcg->css;
}

/**
 * blkcg_init_queue - initialize blkcg part of request queue
 * @q: request_queue to initialize
 *
 * Called from blk_alloc_queue_node(). Responsible for initializing blkcg
 * part of new request_queue @q.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int blkcg_init_queue(struct request_queue *q)
{
	might_sleep();

	return blk_throtl_init(q);
}

/**
 * blkcg_drain_queue - drain blkcg part of request_queue
 * @q: request_queue to drain
 *
 * Called from blk_drain_queue().  Responsible for draining blkcg part.
 */
void blkcg_drain_queue(struct request_queue *q)
{
	lockdep_assert_held(q->queue_lock);

	/*
	 * @q could be exiting and already have destroyed all blkgs as
	 * indicated by NULL root_blkg.  If so, don't confuse policies.
	 */
	if (!q->root_blkg)
		return;

	blk_throtl_drain(q);
}

/**
 * blkcg_exit_queue - exit and release blkcg part of request_queue
 * @q: request_queue being released
 *
 * Called from blk_release_queue().  Responsible for exiting blkcg part.
 */
void blkcg_exit_queue(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	blkg_destroy_all(q);
	spin_unlock_irq(q->queue_lock);

	blk_throtl_exit(q);
}

/*
 * We cannot support shared io contexts, as we have no mean to support
 * two tasks with the same ioc in two different groups without major rework
 * of the main cic data structures.  For now we allow a task to change
 * its cgroup only if it's the only owner of its ioc.
 */
static int blkcg_can_attach(struct cgroup_subsys_state *css,
			    struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct io_context *ioc;
	int ret = 0;

	/* task_lock() is needed to avoid races with exit_io_context() */
	cgroup_taskset_for_each(task, tset) {
		task_lock(task);
		ioc = task->io_context;
		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
			ret = -EINVAL;
		task_unlock(task);
		if (ret)
			break;
	}
	return ret;
}

struct cgroup_subsys blkio_cgrp_subsys = {
	.css_alloc = blkcg_css_alloc,
	.css_offline = blkcg_css_offline,
	.css_free = blkcg_css_free,
	.can_attach = blkcg_can_attach,
	.legacy_cftypes = blkcg_files,
#ifdef CONFIG_MEMCG
	/*
	 * This ensures that, if available, memcg is automatically enabled
	 * together on the default hierarchy so that the owner cgroup can
	 * be retrieved from writeback pages.
	 */
	.depends_on = 1 << memory_cgrp_id,
#endif
};
EXPORT_SYMBOL_GPL(blkio_cgrp_subsys);

/**
 * blkcg_activate_policy - activate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to activate
 *
 * Activate @pol on @q.  Requires %GFP_KERNEL context.  @q goes through
 * bypass mode to populate its blkgs with policy_data for @pol.
 *
 * Activation happens with @q bypassed, so nobody would be accessing blkgs
 * from IO path.  Update of each blkg is protected by both queue and blkcg
 * locks so that holding either lock and testing blkcg_policy_enabled() is
 * always enough for dereferencing policy data.
 *
 * The caller is responsible for synchronizing [de]activations and policy
 * [un]registerations.  Returns 0 on success, -errno on failure.
 */
int blkcg_activate_policy(struct request_queue *q,
			  const struct blkcg_policy *pol)
{
	LIST_HEAD(pds);
	struct blkcg_gq *blkg, *new_blkg;
	struct blkg_policy_data *pd, *n;
	int cnt = 0, ret;
	bool preloaded;

	if (blkcg_policy_enabled(q, pol))
		return 0;

	/* preallocations for root blkg */
	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
	if (!new_blkg)
		return -ENOMEM;

	blk_queue_bypass_start(q);

	preloaded = !radix_tree_preload(GFP_KERNEL);

	/*
	 * Make sure the root blkg exists and count the existing blkgs.  As
	 * @q is bypassing at this point, blkg_lookup_create() can't be
	 * used.  Open code it.
	 */
	spin_lock_irq(q->queue_lock);

	rcu_read_lock();
	blkg = __blkg_lookup(&blkcg_root, q, false);
	if (blkg)
		blkg_free(new_blkg);
	else
		blkg = blkg_create(&blkcg_root, q, new_blkg);
	rcu_read_unlock();

	if (preloaded)
		radix_tree_preload_end();

	if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		goto out_unlock;
	}

	list_for_each_entry(blkg, &q->blkg_list, q_node)
		cnt++;

	spin_unlock_irq(q->queue_lock);

	/* allocate policy_data for all existing blkgs */
	while (cnt--) {
		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
		if (!pd) {
			ret = -ENOMEM;
			goto out_free;
		}
		list_add_tail(&pd->alloc_node, &pds);
	}

	/*
	 * Install the allocated pds.  With @q bypassing, no new blkg
	 * should have been created while the queue lock was dropped.
	 */
	spin_lock_irq(q->queue_lock);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		if (WARN_ON(list_empty(&pds))) {
			/* umm... this shouldn't happen, just abort */
			ret = -ENOMEM;
			goto out_unlock;
		}
		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
		list_del_init(&pd->alloc_node);

		/* grab blkcg lock too while installing @pd on @blkg */
		spin_lock(&blkg->blkcg->lock);

		blkg->pd[pol->plid] = pd;
		pd->blkg = blkg;
		pd->plid = pol->plid;
		pol->pd_init_fn(blkg);

		spin_unlock(&blkg->blkcg->lock);
	}

	__set_bit(pol->plid, q->blkcg_pols);
	ret = 0;
out_unlock:
	spin_unlock_irq(q->queue_lock);
out_free:
	blk_queue_bypass_end(q);
	list_for_each_entry_safe(pd, n, &pds, alloc_node)
		kfree(pd);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);

/**
 * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to deactivate
 *
 * Deactivate @pol on @q.  Follows the same synchronization rules as
 * blkcg_activate_policy().
 */
void blkcg_deactivate_policy(struct request_queue *q,
			     const struct blkcg_policy *pol)
{
	struct blkcg_gq *blkg;

	if (!blkcg_policy_enabled(q, pol))
		return;

	blk_queue_bypass_start(q);
	spin_lock_irq(q->queue_lock);

	__clear_bit(pol->plid, q->blkcg_pols);

	/* if no policy is left, no need for blkgs - shoot them down */
	if (bitmap_empty(q->blkcg_pols, BLKCG_MAX_POLS))
		blkg_destroy_all(q);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		/* grab blkcg lock too while removing @pd from @blkg */
		spin_lock(&blkg->blkcg->lock);

		if (pol->pd_offline_fn)
			pol->pd_offline_fn(blkg);
		if (pol->pd_exit_fn)
			pol->pd_exit_fn(blkg);

		kfree(blkg->pd[pol->plid]);
		blkg->pd[pol->plid] = NULL;

		spin_unlock(&blkg->blkcg->lock);
	}

	spin_unlock_irq(q->queue_lock);
	blk_queue_bypass_end(q);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);

/**
 * blkcg_policy_register - register a blkcg policy
 * @pol: blkcg policy to register
 *
 * Register @pol with blkcg core.  Might sleep and @pol may be modified on
 * successful registration.  Returns 0 on success and -errno on failure.
 */
int blkcg_policy_register(struct blkcg_policy *pol)
{
	int i, ret;

	if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
		return -EINVAL;

	mutex_lock(&blkcg_pol_mutex);

	/* find an empty slot */
	ret = -ENOSPC;
	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (!blkcg_policy[i])
			break;
	if (i >= BLKCG_MAX_POLS)
		goto out_unlock;

	/* register and update blkgs */
	pol->plid = i;
	blkcg_policy[i] = pol;

	/* everything is in place, add intf files for the new policy */
	if (pol->cftypes)
		WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
						  pol->cftypes));
	ret = 0;
out_unlock:
	mutex_unlock(&blkcg_pol_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_policy_register);

/**
 * blkcg_policy_unregister - unregister a blkcg policy
 * @pol: blkcg policy to unregister
 *
 * Undo blkcg_policy_register(@pol).  Might sleep.
 */
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
	mutex_lock(&blkcg_pol_mutex);

	if (WARN_ON(blkcg_policy[pol->plid] != pol))
		goto out_unlock;

	/* kill the intf files first */
	if (pol->cftypes)
		cgroup_rm_cftypes(pol->cftypes);

	/* unregister and update blkgs */
	blkcg_policy[pol->plid] = NULL;
out_unlock:
	mutex_unlock(&blkcg_pol_mutex);
}
EXPORT_SYMBOL_GPL(blkcg_policy_unregister);