summaryrefslogtreecommitdiffstats
path: root/block/blk-cgroup.c
blob: cfdda44f4a0b6cbcef1b85508e241f36cec664ab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
/*
 * 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_SPINLOCK(blkio_list_lock);
static LIST_HEAD(blkio_list);

static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);

/* List of groups pending per cpu stats allocation */
static DEFINE_SPINLOCK(alloc_list_lock);
static LIST_HEAD(alloc_list);

static void blkio_stat_alloc_fn(struct work_struct *);
static DECLARE_DELAYED_WORK(blkio_stat_alloc_work, blkio_stat_alloc_fn);

struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkio_root_cgroup);

static struct blkio_policy_type *blkio_policy[BLKIO_NR_POLICIES];

struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
			    struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);

static struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
{
	return container_of(task_subsys_state(tsk, blkio_subsys_id),
			    struct blkio_cgroup, css);
}

struct blkio_cgroup *bio_blkio_cgroup(struct bio *bio)
{
	if (bio && bio->bi_css)
		return container_of(bio->bi_css, struct blkio_cgroup, css);
	return task_blkio_cgroup(current);
}
EXPORT_SYMBOL_GPL(bio_blkio_cgroup);

/*
 * Worker for allocating per cpu stat for blk groups. This is scheduled on
 * the system_nrt_wq once there are some groups on the alloc_list waiting
 * for allocation.
 */
static void blkio_stat_alloc_fn(struct work_struct *work)
{
	static void *pcpu_stats[BLKIO_NR_POLICIES];
	struct delayed_work *dwork = to_delayed_work(work);
	struct blkio_group *blkg;
	int i;
	bool empty = false;

alloc_stats:
	for (i = 0; i < BLKIO_NR_POLICIES; i++) {
		if (pcpu_stats[i] != NULL)
			continue;

		pcpu_stats[i] = alloc_percpu(struct blkio_group_stats_cpu);

		/* Allocation failed. Try again after some time. */
		if (pcpu_stats[i] == NULL) {
			queue_delayed_work(system_nrt_wq, dwork,
						msecs_to_jiffies(10));
			return;
		}
	}

	spin_lock_irq(&blkio_list_lock);
	spin_lock(&alloc_list_lock);

	/* cgroup got deleted or queue exited. */
	if (!list_empty(&alloc_list)) {
		blkg = list_first_entry(&alloc_list, struct blkio_group,
						alloc_node);
		for (i = 0; i < BLKIO_NR_POLICIES; i++) {
			struct blkg_policy_data *pd = blkg->pd[i];

			if (blkio_policy[i] && pd && !pd->stats_cpu)
				swap(pd->stats_cpu, pcpu_stats[i]);
		}

		list_del_init(&blkg->alloc_node);
	}

	empty = list_empty(&alloc_list);

	spin_unlock(&alloc_list_lock);
	spin_unlock_irq(&blkio_list_lock);

	if (!empty)
		goto alloc_stats;
}

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

	if (!blkg)
		return;

	for (i = 0; i < BLKIO_NR_POLICIES; i++) {
		struct blkio_policy_type *pol = blkio_policy[i];
		struct blkg_policy_data *pd = blkg->pd[i];

		if (!pd)
			continue;

		if (pol && pol->ops.blkio_exit_group_fn)
			pol->ops.blkio_exit_group_fn(blkg);

		free_percpu(pd->stats_cpu);
		kfree(pd);
	}

	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
 *
 * Allocate a new blkg assocating @blkcg and @q.
 */
static struct blkio_group *blkg_alloc(struct blkio_cgroup *blkcg,
				      struct request_queue *q)
{
	struct blkio_group *blkg;
	int i;

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

	blkg->q = q;
	INIT_LIST_HEAD(&blkg->q_node);
	INIT_LIST_HEAD(&blkg->alloc_node);
	blkg->blkcg = blkcg;
	blkg->refcnt = 1;
	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));

	for (i = 0; i < BLKIO_NR_POLICIES; i++) {
		struct blkio_policy_type *pol = blkio_policy[i];
		struct blkg_policy_data *pd;

		if (!pol)
			continue;

		/* alloc per-policy data and attach it to blkg */
		pd = kzalloc_node(sizeof(*pd) + pol->pdata_size, GFP_ATOMIC,
				  q->node);
		if (!pd) {
			blkg_free(blkg);
			return NULL;
		}

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

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

		if (pol)
			pol->ops.blkio_init_group_fn(blkg);
	}

	return blkg;
}

struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
				       struct request_queue *q,
				       bool for_root)
	__releases(q->queue_lock) __acquires(q->queue_lock)
{
	struct blkio_group *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.
	 * The following can be removed if blkg lookup is guaranteed to
	 * fail on a bypassing queue.
	 */
	if (unlikely(blk_queue_bypass(q)) && !for_root)
		return ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);

	blkg = blkg_lookup(blkcg, q);
	if (blkg)
		return blkg;

	/* blkg holds a reference to blkcg */
	if (!css_tryget(&blkcg->css))
		return ERR_PTR(-EINVAL);

	/*
	 * Allocate and initialize.
	 */
	blkg = blkg_alloc(blkcg, q);

	/* did alloc fail? */
	if (unlikely(!blkg)) {
		blkg = ERR_PTR(-ENOMEM);
		goto out;
	}

	/* insert */
	spin_lock(&blkcg->lock);
	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
	list_add(&blkg->q_node, &q->blkg_list);
	spin_unlock(&blkcg->lock);

	spin_lock(&alloc_list_lock);
	list_add(&blkg->alloc_node, &alloc_list);
	/* Queue per cpu stat allocation from worker thread. */
	queue_delayed_work(system_nrt_wq, &blkio_stat_alloc_work, 0);
	spin_unlock(&alloc_list_lock);
out:
	return blkg;
}
EXPORT_SYMBOL_GPL(blkg_lookup_create);

/* called under rcu_read_lock(). */
struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
				struct request_queue *q)
{
	struct blkio_group *blkg;
	struct hlist_node *n;

	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node)
		if (blkg->q == q)
			return blkg;
	return NULL;
}
EXPORT_SYMBOL_GPL(blkg_lookup);

static void blkg_destroy(struct blkio_group *blkg)
{
	struct request_queue *q = blkg->q;
	struct blkio_cgroup *blkcg = blkg->blkcg;

	lockdep_assert_held(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));
	list_del_init(&blkg->q_node);
	hlist_del_init_rcu(&blkg->blkcg_node);

	spin_lock(&alloc_list_lock);
	list_del_init(&blkg->alloc_node);
	spin_unlock(&alloc_list_lock);

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

/*
 * XXX: This updates blkg policy data in-place for root blkg, which is
 * necessary across elevator switch and policy registration as root blkgs
 * aren't shot down.  This broken and racy implementation is temporary.
 * Eventually, blkg shoot down will be replaced by proper in-place update.
 */
void update_root_blkg_pd(struct request_queue *q, enum blkio_policy_id plid)
{
	struct blkio_policy_type *pol = blkio_policy[plid];
	struct blkio_group *blkg = blkg_lookup(&blkio_root_cgroup, q);
	struct blkg_policy_data *pd;

	if (!blkg)
		return;

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

	if (!pol)
		return;

	pd = kzalloc(sizeof(*pd) + pol->pdata_size, GFP_KERNEL);
	WARN_ON_ONCE(!pd);

	pd->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
	WARN_ON_ONCE(!pd->stats_cpu);

	blkg->pd[plid] = pd;
	pd->blkg = blkg;
	pol->ops.blkio_init_group_fn(blkg);
}
EXPORT_SYMBOL_GPL(update_root_blkg_pd);

/**
 * blkg_destroy_all - destroy all blkgs associated with a request_queue
 * @q: request_queue of interest
 * @destroy_root: whether to destroy root blkg or not
 *
 * Destroy blkgs associated with @q.  If @destroy_root is %true, all are
 * destroyed; otherwise, root blkg is left alone.
 */
void blkg_destroy_all(struct request_queue *q, bool destroy_root)
{
	struct blkio_group *blkg, *n;

	spin_lock_irq(q->queue_lock);

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

		/* skip root? */
		if (!destroy_root && blkg->blkcg == &blkio_root_cgroup)
			continue;

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

	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blkg_destroy_all);

static void blkg_rcu_free(struct rcu_head *rcu_head)
{
	blkg_free(container_of(rcu_head, struct blkio_group, rcu_head));
}

void __blkg_release(struct blkio_group *blkg)
{
	/* release the extra blkcg reference this blkg has been holding */
	css_put(&blkg->blkcg->css);

	/*
	 * A group is freed in rcu manner. 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 acess to only
	 * values local to groups like group stats and group rate limits
	 */
	call_rcu(&blkg->rcu_head, blkg_rcu_free);
}
EXPORT_SYMBOL_GPL(__blkg_release);

static void blkio_reset_stats_cpu(struct blkio_group *blkg, int plid)
{
	struct blkg_policy_data *pd = blkg->pd[plid];
	int cpu;

	if (pd->stats_cpu == NULL)
		return;

	for_each_possible_cpu(cpu) {
		struct blkio_group_stats_cpu *sc =
			per_cpu_ptr(pd->stats_cpu, cpu);

		blkg_rwstat_reset(&sc->service_bytes);
		blkg_rwstat_reset(&sc->serviced);
	}
}

static int
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
	struct blkio_group *blkg;
	struct hlist_node *n;

	spin_lock(&blkio_list_lock);
	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, n, &blkcg->blkg_list, blkcg_node) {
		struct blkio_policy_type *pol;

		list_for_each_entry(pol, &blkio_list, list) {
			blkio_reset_stats_cpu(blkg, pol->plid);

			if (pol->ops.blkio_reset_group_stats_fn)
				pol->ops.blkio_reset_group_stats_fn(blkg);
		}
	}

	spin_unlock_irq(&blkcg->lock);
	spin_unlock(&blkio_list_lock);
	return 0;
}

static const char *blkg_dev_name(struct blkio_group *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.  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 blkio_cgroup *blkcg,
		       u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int),
		       int pol, int data, bool show_total)
{
	struct blkio_group *blkg;
	struct hlist_node *n;
	u64 total = 0;

	spin_lock_irq(&blkcg->lock);
	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
		if (blkg->pd[pol])
			total += prfill(sf, blkg->pd[pol], data);
	spin_unlock_irq(&blkcg->lock);

	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 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 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;
}

static 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->pdata + off));
}

static u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
			      int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd->pdata + off);

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

/* print blkg_stat specified by BLKCG_STAT_PRIV() */
int blkcg_print_stat(struct cgroup *cgrp, struct cftype *cft,
		     struct seq_file *sf)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgrp);

	blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat,
			  BLKCG_STAT_POL(cft->private),
			  BLKCG_STAT_OFF(cft->private), false);
	return 0;
}
EXPORT_SYMBOL_GPL(blkcg_print_stat);

/* print blkg_rwstat specified by BLKCG_STAT_PRIV() */
int blkcg_print_rwstat(struct cgroup *cgrp, struct cftype *cft,
		       struct seq_file *sf)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgrp);

	blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat,
			  BLKCG_STAT_POL(cft->private),
			  BLKCG_STAT_OFF(cft->private), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkcg_print_rwstat);

/**
 * blkg_conf_prep - parse and prepare for per-blkg config update
 * @blkcg: target block cgroup
 * @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 locked and must be paired
 * with blkg_conf_finish().
 */
int blkg_conf_prep(struct blkio_cgroup *blkcg, const char *input,
		   struct blkg_conf_ctx *ctx)
	__acquires(rcu)
{
	struct gendisk *disk;
	struct blkio_group *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);
	blkg = blkg_lookup_create(blkcg, disk->queue, false);
	spin_unlock_irq(disk->queue->queue_lock);

	if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		rcu_read_unlock();
		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(rcu)
{
	rcu_read_unlock();
	put_disk(ctx->disk);
}
EXPORT_SYMBOL_GPL(blkg_conf_finish);

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

/**
 * blkiocg_pre_destroy - cgroup pre_destroy callback
 * @cgroup: cgroup of interest
 *
 * This function is called when @cgroup is about to go away and responsible
 * for shooting down all blkgs associated with @cgroup.  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 int blkiocg_pre_destroy(struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);

	spin_lock_irq(&blkcg->lock);

	while (!hlist_empty(&blkcg->blkg_list)) {
		struct blkio_group *blkg = hlist_entry(blkcg->blkg_list.first,
						struct blkio_group, 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);
	return 0;
}

static void blkiocg_destroy(struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);

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

static struct cgroup_subsys_state *blkiocg_create(struct cgroup *cgroup)
{
	static atomic64_t id_seq = ATOMIC64_INIT(0);
	struct blkio_cgroup *blkcg;
	struct cgroup *parent = cgroup->parent;

	if (!parent) {
		blkcg = &blkio_root_cgroup;
		goto done;
	}

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

	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
	blkcg->id = atomic64_inc_return(&id_seq); /* root is 0, start from 1 */
done:
	spin_lock_init(&blkcg->lock);
	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)
{
	int ret;

	might_sleep();

	ret = blk_throtl_init(q);
	if (ret)
		return ret;

	mutex_lock(&all_q_mutex);
	INIT_LIST_HEAD(&q->all_q_node);
	list_add_tail(&q->all_q_node, &all_q_list);
	mutex_unlock(&all_q_mutex);

	return 0;
}

/**
 * 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);

	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)
{
	mutex_lock(&all_q_mutex);
	list_del_init(&q->all_q_node);
	mutex_unlock(&all_q_mutex);

	blkg_destroy_all(q, true);

	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 blkiocg_can_attach(struct cgroup *cgrp, 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, cgrp, 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;
}

static void blkcg_bypass_start(void)
	__acquires(&all_q_mutex)
{
	struct request_queue *q;

	mutex_lock(&all_q_mutex);

	list_for_each_entry(q, &all_q_list, all_q_node) {
		blk_queue_bypass_start(q);
		blkg_destroy_all(q, false);
	}
}

static void blkcg_bypass_end(void)
	__releases(&all_q_mutex)
{
	struct request_queue *q;

	list_for_each_entry(q, &all_q_list, all_q_node)
		blk_queue_bypass_end(q);

	mutex_unlock(&all_q_mutex);
}

struct cgroup_subsys blkio_subsys = {
	.name = "blkio",
	.create = blkiocg_create,
	.can_attach = blkiocg_can_attach,
	.pre_destroy = blkiocg_pre_destroy,
	.destroy = blkiocg_destroy,
	.subsys_id = blkio_subsys_id,
	.base_cftypes = blkio_files,
	.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);

void blkio_policy_register(struct blkio_policy_type *blkiop)
{
	struct request_queue *q;

	blkcg_bypass_start();
	spin_lock(&blkio_list_lock);

	BUG_ON(blkio_policy[blkiop->plid]);
	blkio_policy[blkiop->plid] = blkiop;
	list_add_tail(&blkiop->list, &blkio_list);

	spin_unlock(&blkio_list_lock);
	list_for_each_entry(q, &all_q_list, all_q_node)
		update_root_blkg_pd(q, blkiop->plid);
	blkcg_bypass_end();

	if (blkiop->cftypes)
		WARN_ON(cgroup_add_cftypes(&blkio_subsys, blkiop->cftypes));
}
EXPORT_SYMBOL_GPL(blkio_policy_register);

void blkio_policy_unregister(struct blkio_policy_type *blkiop)
{
	struct request_queue *q;

	if (blkiop->cftypes)
		cgroup_rm_cftypes(&blkio_subsys, blkiop->cftypes);

	blkcg_bypass_start();
	spin_lock(&blkio_list_lock);

	BUG_ON(blkio_policy[blkiop->plid] != blkiop);
	blkio_policy[blkiop->plid] = NULL;
	list_del_init(&blkiop->list);

	spin_unlock(&blkio_list_lock);
	list_for_each_entry(q, &all_q_list, all_q_node)
		update_root_blkg_pd(q, blkiop->plid);
	blkcg_bypass_end();
}
EXPORT_SYMBOL_GPL(blkio_policy_unregister);