summaryrefslogtreecommitdiffstats
path: root/block/elevator.c
blob: 153926a909011e5f2a9759d19e90ab74ef00f405 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
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
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
/*
 *  Block device elevator/IO-scheduler.
 *
 *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
 *
 * 30042000 Jens Axboe <axboe@kernel.dk> :
 *
 * Split the elevator a bit so that it is possible to choose a different
 * one or even write a new "plug in". There are three pieces:
 * - elevator_fn, inserts a new request in the queue list
 * - elevator_merge_fn, decides whether a new buffer can be merged with
 *   an existing request
 * - elevator_dequeue_fn, called when a request is taken off the active list
 *
 * 20082000 Dave Jones <davej@suse.de> :
 * Removed tests for max-bomb-segments, which was breaking elvtune
 *  when run without -bN
 *
 * Jens:
 * - Rework again to work with bio instead of buffer_heads
 * - loose bi_dev comparisons, partition handling is right now
 * - completely modularize elevator setup and teardown
 *
 */
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>

#include <trace/events/block.h>

#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-wbt.h"

static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);

/*
 * Merge hash stuff.
 */
#define rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))

/*
 * Query io scheduler to see if the current process issuing bio may be
 * merged with rq.
 */
static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
{
	struct request_queue *q = rq->q;
	struct elevator_queue *e = q->elevator;

	if (e->uses_mq && e->type->ops.mq.allow_merge)
		return e->type->ops.mq.allow_merge(q, rq, bio);
	else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn)
		return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);

	return 1;
}

/*
 * can we safely merge with this request?
 */
bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
{
	if (!blk_rq_merge_ok(rq, bio))
		return false;

	if (!elv_iosched_allow_bio_merge(rq, bio))
		return false;

	return true;
}
EXPORT_SYMBOL(elv_bio_merge_ok);

static struct elevator_type *elevator_find(const char *name)
{
	struct elevator_type *e;

	list_for_each_entry(e, &elv_list, list) {
		if (!strcmp(e->elevator_name, name))
			return e;
	}

	return NULL;
}

static void elevator_put(struct elevator_type *e)
{
	module_put(e->elevator_owner);
}

static struct elevator_type *elevator_get(const char *name, bool try_loading)
{
	struct elevator_type *e;

	spin_lock(&elv_list_lock);

	e = elevator_find(name);
	if (!e && try_loading) {
		spin_unlock(&elv_list_lock);
		request_module("%s-iosched", name);
		spin_lock(&elv_list_lock);
		e = elevator_find(name);
	}

	if (e && !try_module_get(e->elevator_owner))
		e = NULL;

	spin_unlock(&elv_list_lock);

	return e;
}

static char chosen_elevator[ELV_NAME_MAX];

static int __init elevator_setup(char *str)
{
	/*
	 * Be backwards-compatible with previous kernels, so users
	 * won't get the wrong elevator.
	 */
	strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
	return 1;
}

__setup("elevator=", elevator_setup);

/* called during boot to load the elevator chosen by the elevator param */
void __init load_default_elevator_module(void)
{
	struct elevator_type *e;

	if (!chosen_elevator[0])
		return;

	spin_lock(&elv_list_lock);
	e = elevator_find(chosen_elevator);
	spin_unlock(&elv_list_lock);

	if (!e)
		request_module("%s-iosched", chosen_elevator);
}

static struct kobj_type elv_ktype;

struct elevator_queue *elevator_alloc(struct request_queue *q,
				  struct elevator_type *e)
{
	struct elevator_queue *eq;

	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
	if (unlikely(!eq))
		return NULL;

	eq->type = e;
	kobject_init(&eq->kobj, &elv_ktype);
	mutex_init(&eq->sysfs_lock);
	hash_init(eq->hash);
	eq->uses_mq = e->uses_mq;

	return eq;
}
EXPORT_SYMBOL(elevator_alloc);

static void elevator_release(struct kobject *kobj)
{
	struct elevator_queue *e;

	e = container_of(kobj, struct elevator_queue, kobj);
	elevator_put(e->type);
	kfree(e);
}

int elevator_init(struct request_queue *q, char *name)
{
	struct elevator_type *e = NULL;
	int err;

	/*
	 * q->sysfs_lock must be held to provide mutual exclusion between
	 * elevator_switch() and here.
	 */
	lockdep_assert_held(&q->sysfs_lock);

	if (unlikely(q->elevator))
		return 0;

	INIT_LIST_HEAD(&q->queue_head);
	q->last_merge = NULL;
	q->end_sector = 0;
	q->boundary_rq = NULL;

	if (name) {
		e = elevator_get(name, true);
		if (!e)
			return -EINVAL;
	}

	/*
	 * Use the default elevator specified by config boot param for
	 * non-mq devices, or by config option. Don't try to load modules
	 * as we could be running off async and request_module() isn't
	 * allowed from async.
	 */
	if (!e && !q->mq_ops && *chosen_elevator) {
		e = elevator_get(chosen_elevator, false);
		if (!e)
			printk(KERN_ERR "I/O scheduler %s not found\n",
							chosen_elevator);
	}

	if (!e) {
		/*
		 * For blk-mq devices, we default to using mq-deadline,
		 * if available, for single queue devices. If deadline
		 * isn't available OR we have multiple queues, default
		 * to "none".
		 */
		if (q->mq_ops) {
			if (q->nr_hw_queues == 1)
				e = elevator_get("mq-deadline", false);
			if (!e)
				return 0;
		} else
			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);

		if (!e) {
			printk(KERN_ERR
				"Default I/O scheduler not found. " \
				"Using noop.\n");
			e = elevator_get("noop", false);
		}
	}

	if (e->uses_mq)
		err = blk_mq_init_sched(q, e);
	else
		err = e->ops.sq.elevator_init_fn(q, e);
	if (err)
		elevator_put(e);
	return err;
}
EXPORT_SYMBOL(elevator_init);

void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
	mutex_lock(&e->sysfs_lock);
	if (e->uses_mq && e->type->ops.mq.exit_sched)
		blk_mq_exit_sched(q, e);
	else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
		e->type->ops.sq.elevator_exit_fn(e);
	mutex_unlock(&e->sysfs_lock);

	kobject_put(&e->kobj);
}
EXPORT_SYMBOL(elevator_exit);

static inline void __elv_rqhash_del(struct request *rq)
{
	hash_del(&rq->hash);
	rq->rq_flags &= ~RQF_HASHED;
}

void elv_rqhash_del(struct request_queue *q, struct request *rq)
{
	if (ELV_ON_HASH(rq))
		__elv_rqhash_del(rq);
}
EXPORT_SYMBOL_GPL(elv_rqhash_del);

void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	BUG_ON(ELV_ON_HASH(rq));
	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
	rq->rq_flags |= RQF_HASHED;
}
EXPORT_SYMBOL_GPL(elv_rqhash_add);

void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
	__elv_rqhash_del(rq);
	elv_rqhash_add(q, rq);
}

struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
	struct elevator_queue *e = q->elevator;
	struct hlist_node *next;
	struct request *rq;

	hash_for_each_possible_safe(e->hash, rq, next, hash, offset) {
		BUG_ON(!ELV_ON_HASH(rq));

		if (unlikely(!rq_mergeable(rq))) {
			__elv_rqhash_del(rq);
			continue;
		}

		if (rq_hash_key(rq) == offset)
			return rq;
	}

	return NULL;
}

/*
 * RB-tree support functions for inserting/lookup/removal of requests
 * in a sorted RB tree.
 */
void elv_rb_add(struct rb_root *root, struct request *rq)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct request *__rq;

	while (*p) {
		parent = *p;
		__rq = rb_entry(parent, struct request, rb_node);

		if (blk_rq_pos(rq) < blk_rq_pos(__rq))
			p = &(*p)->rb_left;
		else if (blk_rq_pos(rq) >= blk_rq_pos(__rq))
			p = &(*p)->rb_right;
	}

	rb_link_node(&rq->rb_node, parent, p);
	rb_insert_color(&rq->rb_node, root);
}
EXPORT_SYMBOL(elv_rb_add);

void elv_rb_del(struct rb_root *root, struct request *rq)
{
	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
	rb_erase(&rq->rb_node, root);
	RB_CLEAR_NODE(&rq->rb_node);
}
EXPORT_SYMBOL(elv_rb_del);

struct request *elv_rb_find(struct rb_root *root, sector_t sector)
{
	struct rb_node *n = root->rb_node;
	struct request *rq;

	while (n) {
		rq = rb_entry(n, struct request, rb_node);

		if (sector < blk_rq_pos(rq))
			n = n->rb_left;
		else if (sector > blk_rq_pos(rq))
			n = n->rb_right;
		else
			return rq;
	}

	return NULL;
}
EXPORT_SYMBOL(elv_rb_find);

/*
 * Insert rq into dispatch queue of q.  Queue lock must be held on
 * entry.  rq is sort instead into the dispatch queue. To be used by
 * specific elevators.
 */
void elv_dispatch_sort(struct request_queue *q, struct request *rq)
{
	sector_t boundary;
	struct list_head *entry;

	if (q->last_merge == rq)
		q->last_merge = NULL;

	elv_rqhash_del(q, rq);

	q->nr_sorted--;

	boundary = q->end_sector;
	list_for_each_prev(entry, &q->queue_head) {
		struct request *pos = list_entry_rq(entry);

		if (req_op(rq) != req_op(pos))
			break;
		if (rq_data_dir(rq) != rq_data_dir(pos))
			break;
		if (pos->rq_flags & (RQF_STARTED | RQF_SOFTBARRIER))
			break;
		if (blk_rq_pos(rq) >= boundary) {
			if (blk_rq_pos(pos) < boundary)
				continue;
		} else {
			if (blk_rq_pos(pos) >= boundary)
				break;
		}
		if (blk_rq_pos(rq) >= blk_rq_pos(pos))
			break;
	}

	list_add(&rq->queuelist, entry);
}
EXPORT_SYMBOL(elv_dispatch_sort);

/*
 * Insert rq into dispatch queue of q.  Queue lock must be held on
 * entry.  rq is added to the back of the dispatch queue. To be used by
 * specific elevators.
 */
void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
{
	if (q->last_merge == rq)
		q->last_merge = NULL;

	elv_rqhash_del(q, rq);

	q->nr_sorted--;

	q->end_sector = rq_end_sector(rq);
	q->boundary_rq = rq;
	list_add_tail(&rq->queuelist, &q->queue_head);
}
EXPORT_SYMBOL(elv_dispatch_add_tail);

enum elv_merge elv_merge(struct request_queue *q, struct request **req,
		struct bio *bio)
{
	struct elevator_queue *e = q->elevator;
	struct request *__rq;

	/*
	 * Levels of merges:
	 * 	nomerges:  No merges at all attempted
	 * 	noxmerges: Only simple one-hit cache try
	 * 	merges:	   All merge tries attempted
	 */
	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
		return ELEVATOR_NO_MERGE;

	/*
	 * First try one-hit cache.
	 */
	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
		enum elv_merge ret = blk_try_merge(q->last_merge, bio);

		if (ret != ELEVATOR_NO_MERGE) {
			*req = q->last_merge;
			return ret;
		}
	}

	if (blk_queue_noxmerges(q))
		return ELEVATOR_NO_MERGE;

	/*
	 * See if our hash lookup can find a potential backmerge.
	 */
	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
	if (__rq && elv_bio_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_BACK_MERGE;
	}

	if (e->uses_mq && e->type->ops.mq.request_merge)
		return e->type->ops.mq.request_merge(q, req, bio);
	else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn)
		return e->type->ops.sq.elevator_merge_fn(q, req, bio);

	return ELEVATOR_NO_MERGE;
}

/*
 * Attempt to do an insertion back merge. Only check for the case where
 * we can append 'rq' to an existing request, so we can throw 'rq' away
 * afterwards.
 *
 * Returns true if we merged, false otherwise
 */
bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
{
	struct request *__rq;
	bool ret;

	if (blk_queue_nomerges(q))
		return false;

	/*
	 * First try one-hit cache.
	 */
	if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq))
		return true;

	if (blk_queue_noxmerges(q))
		return false;

	ret = false;
	/*
	 * See if our hash lookup can find a potential backmerge.
	 */
	while (1) {
		__rq = elv_rqhash_find(q, blk_rq_pos(rq));
		if (!__rq || !blk_attempt_req_merge(q, __rq, rq))
			break;

		/* The merged request could be merged with others, try again */
		ret = true;
		rq = __rq;
	}

	return ret;
}

void elv_merged_request(struct request_queue *q, struct request *rq,
		enum elv_merge type)
{
	struct elevator_queue *e = q->elevator;

	if (e->uses_mq && e->type->ops.mq.request_merged)
		e->type->ops.mq.request_merged(q, rq, type);
	else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn)
		e->type->ops.sq.elevator_merged_fn(q, rq, type);

	if (type == ELEVATOR_BACK_MERGE)
		elv_rqhash_reposition(q, rq);

	q->last_merge = rq;
}

void elv_merge_requests(struct request_queue *q, struct request *rq,
			     struct request *next)
{
	struct elevator_queue *e = q->elevator;
	bool next_sorted = false;

	if (e->uses_mq && e->type->ops.mq.requests_merged)
		e->type->ops.mq.requests_merged(q, rq, next);
	else if (e->type->ops.sq.elevator_merge_req_fn) {
		next_sorted = (__force bool)(next->rq_flags & RQF_SORTED);
		if (next_sorted)
			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
	}

	elv_rqhash_reposition(q, rq);

	if (next_sorted) {
		elv_rqhash_del(q, next);
		q->nr_sorted--;
	}

	q->last_merge = rq;
}

void elv_bio_merged(struct request_queue *q, struct request *rq,
			struct bio *bio)
{
	struct elevator_queue *e = q->elevator;

	if (WARN_ON_ONCE(e->uses_mq))
		return;

	if (e->type->ops.sq.elevator_bio_merged_fn)
		e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
}

#ifdef CONFIG_PM
static void blk_pm_requeue_request(struct request *rq)
{
	if (rq->q->dev && !(rq->rq_flags & RQF_PM))
		rq->q->nr_pending--;
}

static void blk_pm_add_request(struct request_queue *q, struct request *rq)
{
	if (q->dev && !(rq->rq_flags & RQF_PM) && q->nr_pending++ == 0 &&
	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
		pm_request_resume(q->dev);
}
#else
static inline void blk_pm_requeue_request(struct request *rq) {}
static inline void blk_pm_add_request(struct request_queue *q,
				      struct request *rq)
{
}
#endif

void elv_requeue_request(struct request_queue *q, struct request *rq)
{
	/*
	 * it already went through dequeue, we need to decrement the
	 * in_flight count again
	 */
	if (blk_account_rq(rq)) {
		q->in_flight[rq_is_sync(rq)]--;
		if (rq->rq_flags & RQF_SORTED)
			elv_deactivate_rq(q, rq);
	}

	rq->rq_flags &= ~RQF_STARTED;

	blk_pm_requeue_request(rq);

	__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
}

void elv_drain_elevator(struct request_queue *q)
{
	struct elevator_queue *e = q->elevator;
	static int printed;

	if (WARN_ON_ONCE(e->uses_mq))
		return;

	lockdep_assert_held(q->queue_lock);

	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
		;
	if (q->nr_sorted && printed++ < 10) {
		printk(KERN_ERR "%s: forced dispatching is broken "
		       "(nr_sorted=%u), please report this\n",
		       q->elevator->type->elevator_name, q->nr_sorted);
	}
}

void __elv_add_request(struct request_queue *q, struct request *rq, int where)
{
	trace_block_rq_insert(q, rq);

	blk_pm_add_request(q, rq);

	rq->q = q;

	if (rq->rq_flags & RQF_SOFTBARRIER) {
		/* barriers are scheduling boundary, update end_sector */
		if (!blk_rq_is_passthrough(rq)) {
			q->end_sector = rq_end_sector(rq);
			q->boundary_rq = rq;
		}
	} else if (!(rq->rq_flags & RQF_ELVPRIV) &&
		    (where == ELEVATOR_INSERT_SORT ||
		     where == ELEVATOR_INSERT_SORT_MERGE))
		where = ELEVATOR_INSERT_BACK;

	switch (where) {
	case ELEVATOR_INSERT_REQUEUE:
	case ELEVATOR_INSERT_FRONT:
		rq->rq_flags |= RQF_SOFTBARRIER;
		list_add(&rq->queuelist, &q->queue_head);
		break;

	case ELEVATOR_INSERT_BACK:
		rq->rq_flags |= RQF_SOFTBARRIER;
		elv_drain_elevator(q);
		list_add_tail(&rq->queuelist, &q->queue_head);
		/*
		 * We kick the queue here for the following reasons.
		 * - The elevator might have returned NULL previously
		 *   to delay requests and returned them now.  As the
		 *   queue wasn't empty before this request, ll_rw_blk
		 *   won't run the queue on return, resulting in hang.
		 * - Usually, back inserted requests won't be merged
		 *   with anything.  There's no point in delaying queue
		 *   processing.
		 */
		__blk_run_queue(q);
		break;

	case ELEVATOR_INSERT_SORT_MERGE:
		/*
		 * If we succeed in merging this request with one in the
		 * queue already, we are done - rq has now been freed,
		 * so no need to do anything further.
		 */
		if (elv_attempt_insert_merge(q, rq))
			break;
		/* fall through */
	case ELEVATOR_INSERT_SORT:
		BUG_ON(blk_rq_is_passthrough(rq));
		rq->rq_flags |= RQF_SORTED;
		q->nr_sorted++;
		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}

		/*
		 * Some ioscheds (cfq) run q->request_fn directly, so
		 * rq cannot be accessed after calling
		 * elevator_add_req_fn.
		 */
		q->elevator->type->ops.sq.elevator_add_req_fn(q, rq);
		break;

	case ELEVATOR_INSERT_FLUSH:
		rq->rq_flags |= RQF_SOFTBARRIER;
		blk_insert_flush(rq);
		break;
	default:
		printk(KERN_ERR "%s: bad insertion point %d\n",
		       __func__, where);
		BUG();
	}
}
EXPORT_SYMBOL(__elv_add_request);

void elv_add_request(struct request_queue *q, struct request *rq, int where)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	__elv_add_request(q, rq, where);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(elv_add_request);

struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->uses_mq && e->type->ops.mq.next_request)
		return e->type->ops.mq.next_request(q, rq);
	else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn)
		return e->type->ops.sq.elevator_latter_req_fn(q, rq);

	return NULL;
}

struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (e->uses_mq && e->type->ops.mq.former_request)
		return e->type->ops.mq.former_request(q, rq);
	if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn)
		return e->type->ops.sq.elevator_former_req_fn(q, rq);
	return NULL;
}

int elv_set_request(struct request_queue *q, struct request *rq,
		    struct bio *bio, gfp_t gfp_mask)
{
	struct elevator_queue *e = q->elevator;

	if (WARN_ON_ONCE(e->uses_mq))
		return 0;

	if (e->type->ops.sq.elevator_set_req_fn)
		return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
	return 0;
}

void elv_put_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (WARN_ON_ONCE(e->uses_mq))
		return;

	if (e->type->ops.sq.elevator_put_req_fn)
		e->type->ops.sq.elevator_put_req_fn(rq);
}

int elv_may_queue(struct request_queue *q, unsigned int op)
{
	struct elevator_queue *e = q->elevator;

	if (WARN_ON_ONCE(e->uses_mq))
		return 0;

	if (e->type->ops.sq.elevator_may_queue_fn)
		return e->type->ops.sq.elevator_may_queue_fn(q, op);

	return ELV_MQUEUE_MAY;
}

void elv_completed_request(struct request_queue *q, struct request *rq)
{
	struct elevator_queue *e = q->elevator;

	if (WARN_ON_ONCE(e->uses_mq))
		return;

	/*
	 * request is released from the driver, io must be done
	 */
	if (blk_account_rq(rq)) {
		q->in_flight[rq_is_sync(rq)]--;
		if ((rq->rq_flags & RQF_SORTED) &&
		    e->type->ops.sq.elevator_completed_req_fn)
			e->type->ops.sq.elevator_completed_req_fn(q, rq);
	}
}

#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)

static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct elv_fs_entry *entry = to_elv(attr);
	struct elevator_queue *e;
	ssize_t error;

	if (!entry->show)
		return -EIO;

	e = container_of(kobj, struct elevator_queue, kobj);
	mutex_lock(&e->sysfs_lock);
	error = e->type ? entry->show(e, page) : -ENOENT;
	mutex_unlock(&e->sysfs_lock);
	return error;
}

static ssize_t
elv_attr_store(struct kobject *kobj, struct attribute *attr,
	       const char *page, size_t length)
{
	struct elv_fs_entry *entry = to_elv(attr);
	struct elevator_queue *e;
	ssize_t error;

	if (!entry->store)
		return -EIO;

	e = container_of(kobj, struct elevator_queue, kobj);
	mutex_lock(&e->sysfs_lock);
	error = e->type ? entry->store(e, page, length) : -ENOENT;
	mutex_unlock(&e->sysfs_lock);
	return error;
}

static const struct sysfs_ops elv_sysfs_ops = {
	.show	= elv_attr_show,
	.store	= elv_attr_store,
};

static struct kobj_type elv_ktype = {
	.sysfs_ops	= &elv_sysfs_ops,
	.release	= elevator_release,
};

int elv_register_queue(struct request_queue *q)
{
	struct elevator_queue *e = q->elevator;
	int error;

	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
	if (!error) {
		struct elv_fs_entry *attr = e->type->elevator_attrs;
		if (attr) {
			while (attr->attr.name) {
				if (sysfs_create_file(&e->kobj, &attr->attr))
					break;
				attr++;
			}
		}
		kobject_uevent(&e->kobj, KOBJ_ADD);
		e->registered = 1;
		if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
			e->type->ops.sq.elevator_registered_fn(q);
	}
	return error;
}
EXPORT_SYMBOL(elv_register_queue);

void elv_unregister_queue(struct request_queue *q)
{
	if (q) {
		struct elevator_queue *e = q->elevator;

		kobject_uevent(&e->kobj, KOBJ_REMOVE);
		kobject_del(&e->kobj);
		e->registered = 0;
		/* Re-enable throttling in case elevator disabled it */
		wbt_enable_default(q);
	}
}
EXPORT_SYMBOL(elv_unregister_queue);

int elv_register(struct elevator_type *e)
{
	char *def = "";

	/* create icq_cache if requested */
	if (e->icq_size) {
		if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
		    WARN_ON(e->icq_align < __alignof__(struct io_cq)))
			return -EINVAL;

		snprintf(e->icq_cache_name, sizeof(e->icq_cache_name),
			 "%s_io_cq", e->elevator_name);
		e->icq_cache = kmem_cache_create(e->icq_cache_name, e->icq_size,
						 e->icq_align, 0, NULL);
		if (!e->icq_cache)
			return -ENOMEM;
	}

	/* register, don't allow duplicate names */
	spin_lock(&elv_list_lock);
	if (elevator_find(e->elevator_name)) {
		spin_unlock(&elv_list_lock);
		if (e->icq_cache)
			kmem_cache_destroy(e->icq_cache);
		return -EBUSY;
	}
	list_add_tail(&e->list, &elv_list);
	spin_unlock(&elv_list_lock);

	/* print pretty message */
	if (!strcmp(e->elevator_name, chosen_elevator) ||
			(!*chosen_elevator &&
			 !strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
				def = " (default)";

	printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
								def);
	return 0;
}
EXPORT_SYMBOL_GPL(elv_register);

void elv_unregister(struct elevator_type *e)
{
	/* unregister */
	spin_lock(&elv_list_lock);
	list_del_init(&e->list);
	spin_unlock(&elv_list_lock);

	/*
	 * Destroy icq_cache if it exists.  icq's are RCU managed.  Make
	 * sure all RCU operations are complete before proceeding.
	 */
	if (e->icq_cache) {
		rcu_barrier();
		kmem_cache_destroy(e->icq_cache);
		e->icq_cache = NULL;
	}
}
EXPORT_SYMBOL_GPL(elv_unregister);

static int elevator_switch_mq(struct request_queue *q,
			      struct elevator_type *new_e)
{
	int ret;

	blk_mq_freeze_queue(q);

	if (q->elevator) {
		if (q->elevator->registered)
			elv_unregister_queue(q);
		ioc_clear_queue(q);
		elevator_exit(q, q->elevator);
	}

	ret = blk_mq_init_sched(q, new_e);
	if (ret)
		goto out;

	if (new_e) {
		ret = elv_register_queue(q);
		if (ret) {
			elevator_exit(q, q->elevator);
			goto out;
		}
	}

	if (new_e)
		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
	else
		blk_add_trace_msg(q, "elv switch: none");

out:
	blk_mq_unfreeze_queue(q);
	return ret;
}

/*
 * switch to new_e io scheduler. be careful not to introduce deadlocks -
 * we don't free the old io scheduler, before we have allocated what we
 * need for the new one. this way we have a chance of going back to the old
 * one, if the new one fails init for some reason.
 */
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
	struct elevator_queue *old = q->elevator;
	bool old_registered = false;
	int err;

	if (q->mq_ops)
		return elevator_switch_mq(q, new_e);

	/*
	 * Turn on BYPASS and drain all requests w/ elevator private data.
	 * Block layer doesn't call into a quiesced elevator - all requests
	 * are directly put on the dispatch list without elevator data
	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
	 * merge happens either.
	 */
	if (old) {
		old_registered = old->registered;

		blk_queue_bypass_start(q);

		/* unregister and clear all auxiliary data of the old elevator */
		if (old_registered)
			elv_unregister_queue(q);

		ioc_clear_queue(q);
	}

	/* allocate, init and register new elevator */
	err = new_e->ops.sq.elevator_init_fn(q, new_e);
	if (err)
		goto fail_init;

	err = elv_register_queue(q);
	if (err)
		goto fail_register;

	/* done, kill the old one and finish */
	if (old) {
		elevator_exit(q, old);
		blk_queue_bypass_end(q);
	}

	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);

	return 0;

fail_register:
	elevator_exit(q, q->elevator);
fail_init:
	/* switch failed, restore and re-register old elevator */
	if (old) {
		q->elevator = old;
		elv_register_queue(q);
		blk_queue_bypass_end(q);
	}

	return err;
}

/*
 * Switch this queue to the given IO scheduler.
 */
static int __elevator_change(struct request_queue *q, const char *name)
{
	char elevator_name[ELV_NAME_MAX];
	struct elevator_type *e;

	/* Make sure queue is not in the middle of being removed */
	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
		return -ENOENT;

	/*
	 * Special case for mq, turn off scheduling
	 */
	if (q->mq_ops && !strncmp(name, "none", 4))
		return elevator_switch(q, NULL);

	strlcpy(elevator_name, name, sizeof(elevator_name));
	e = elevator_get(strstrip(elevator_name), true);
	if (!e)
		return -EINVAL;

	if (q->elevator &&
	    !strcmp(elevator_name, q->elevator->type->elevator_name)) {
		elevator_put(e);
		return 0;
	}

	if (!e->uses_mq && q->mq_ops) {
		elevator_put(e);
		return -EINVAL;
	}
	if (e->uses_mq && !q->mq_ops) {
		elevator_put(e);
		return -EINVAL;
	}

	return elevator_switch(q, e);
}

static inline bool elv_support_iosched(struct request_queue *q)
{
	if (q->mq_ops && q->tag_set && (q->tag_set->flags &
				BLK_MQ_F_NO_SCHED))
		return false;
	return true;
}

ssize_t elv_iosched_store(struct request_queue *q, const char *name,
			  size_t count)
{
	int ret;

	if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q))
		return count;

	ret = __elevator_change(q, name);
	if (!ret)
		return count;

	return ret;
}

ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
	struct elevator_queue *e = q->elevator;
	struct elevator_type *elv = NULL;
	struct elevator_type *__e;
	int len = 0;

	if (!blk_queue_stackable(q))
		return sprintf(name, "none\n");

	if (!q->elevator)
		len += sprintf(name+len, "[none] ");
	else
		elv = e->type;

	spin_lock(&elv_list_lock);
	list_for_each_entry(__e, &elv_list, list) {
		if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) {
			len += sprintf(name+len, "[%s] ", elv->elevator_name);
			continue;
		}
		if (__e->uses_mq && q->mq_ops && elv_support_iosched(q))
			len += sprintf(name+len, "%s ", __e->elevator_name);
		else if (!__e->uses_mq && !q->mq_ops)
			len += sprintf(name+len, "%s ", __e->elevator_name);
	}
	spin_unlock(&elv_list_lock);

	if (q->mq_ops && q->elevator)
		len += sprintf(name+len, "none");

	len += sprintf(len+name, "\n");
	return len;
}

struct request *elv_rb_former_request(struct request_queue *q,
				      struct request *rq)
{
	struct rb_node *rbprev = rb_prev(&rq->rb_node);

	if (rbprev)
		return rb_entry_rq(rbprev);

	return NULL;
}
EXPORT_SYMBOL(elv_rb_former_request);

struct request *elv_rb_latter_request(struct request_queue *q,
				      struct request *rq)
{
	struct rb_node *rbnext = rb_next(&rq->rb_node);

	if (rbnext)
		return rb_entry_rq(rbnext);

	return NULL;
}
EXPORT_SYMBOL(elv_rb_latter_request);