summaryrefslogtreecommitdiffstats
path: root/block/elevator.c
blob: 8e3fc3afc77b31e0abef2c42b5c1fe315f789968 (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
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
/*
 *  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/delay.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>

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

/*
 * Merge hash stuff.
 */
static const int elv_hash_shift = 6;
#define ELV_HASH_BLOCK(sec)	((sec) >> 3)
#define ELV_HASH_FN(sec)	\
		(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
#define ELV_HASH_ENTRIES	(1 << elv_hash_shift)
#define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))

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

	if (e->ops->elevator_allow_merge_fn)
		return e->ops->elevator_allow_merge_fn(q, rq, bio);

	return 1;
}

/*
 * can we safely merge with this request?
 */
int elv_rq_merge_ok(struct request *rq, struct bio *bio)
{
	if (!rq_mergeable(rq))
		return 0;

	/*
	 * Don't merge file system requests and discard requests
	 */
	if (bio_discard(bio) != bio_discard(rq->bio))
		return 0;

	/*
	 * different data direction or already started, don't merge
	 */
	if (bio_data_dir(bio) != rq_data_dir(rq))
		return 0;

	/*
	 * must be same device and not a special request
	 */
	if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
		return 0;

	/*
	 * only merge integrity protected bio into ditto rq
	 */
	if (bio_integrity(bio) != blk_integrity_rq(rq))
		return 0;

	if (!elv_iosched_allow_merge(rq, bio))
		return 0;

	return 1;
}
EXPORT_SYMBOL(elv_rq_merge_ok);

static inline int elv_try_merge(struct request *__rq, struct bio *bio)
{
	int ret = ELEVATOR_NO_MERGE;

	/*
	 * we can merge and sequence is ok, check if it's possible
	 */
	if (elv_rq_merge_ok(__rq, bio)) {
		if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
			ret = ELEVATOR_BACK_MERGE;
		else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
			ret = ELEVATOR_FRONT_MERGE;
	}

	return ret;
}

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)
{
	struct elevator_type *e;

	spin_lock(&elv_list_lock);

	e = elevator_find(name);
	if (!e) {
		char elv[ELV_NAME_MAX + strlen("-iosched")];

		spin_unlock(&elv_list_lock);

		if (!strcmp(name, "anticipatory"))
			sprintf(elv, "as-iosched");
		else
			sprintf(elv, "%s-iosched", name);

		request_module("%s", elv);
		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 void *elevator_init_queue(struct request_queue *q,
				 struct elevator_queue *eq)
{
	return eq->ops->elevator_init_fn(q);
}

static void elevator_attach(struct request_queue *q, struct elevator_queue *eq,
			   void *data)
{
	q->elevator = eq;
	eq->elevator_data = data;
}

static char chosen_elevator[16];

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

__setup("elevator=", elevator_setup);

static struct kobj_type elv_ktype;

static elevator_t *elevator_alloc(struct request_queue *q,
				  struct elevator_type *e)
{
	elevator_t *eq;
	int i;

	eq = kmalloc_node(sizeof(elevator_t), GFP_KERNEL | __GFP_ZERO, q->node);
	if (unlikely(!eq))
		goto err;

	eq->ops = &e->ops;
	eq->elevator_type = e;
	kobject_init(&eq->kobj, &elv_ktype);
	mutex_init(&eq->sysfs_lock);

	eq->hash = kmalloc_node(sizeof(struct hlist_head) * ELV_HASH_ENTRIES,
					GFP_KERNEL, q->node);
	if (!eq->hash)
		goto err;

	for (i = 0; i < ELV_HASH_ENTRIES; i++)
		INIT_HLIST_HEAD(&eq->hash[i]);

	return eq;
err:
	kfree(eq);
	elevator_put(e);
	return NULL;
}

static void elevator_release(struct kobject *kobj)
{
	elevator_t *e = container_of(kobj, elevator_t, kobj);

	elevator_put(e->elevator_type);
	kfree(e->hash);
	kfree(e);
}

int elevator_init(struct request_queue *q, char *name)
{
	struct elevator_type *e = NULL;
	struct elevator_queue *eq;
	int ret = 0;
	void *data;

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

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

	if (!e && *chosen_elevator) {
		e = elevator_get(chosen_elevator);
		if (!e)
			printk(KERN_ERR "I/O scheduler %s not found\n",
							chosen_elevator);
	}

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

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	data = elevator_init_queue(q, eq);
	if (!data) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}

	elevator_attach(q, eq, data);
	return ret;
}
EXPORT_SYMBOL(elevator_init);

void elevator_exit(elevator_t *e)
{
	mutex_lock(&e->sysfs_lock);
	if (e->ops->elevator_exit_fn)
		e->ops->elevator_exit_fn(e);
	e->ops = NULL;
	mutex_unlock(&e->sysfs_lock);

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

static void elv_activate_rq(struct request_queue *q, struct request *rq)
{
	elevator_t *e = q->elevator;

	if (e->ops->elevator_activate_req_fn)
		e->ops->elevator_activate_req_fn(q, rq);
}

static void elv_deactivate_rq(struct request_queue *q, struct request *rq)
{
	elevator_t *e = q->elevator;

	if (e->ops->elevator_deactivate_req_fn)
		e->ops->elevator_deactivate_req_fn(q, rq);
}

static inline void __elv_rqhash_del(struct request *rq)
{
	hlist_del_init(&rq->hash);
}

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

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

	BUG_ON(ELV_ON_HASH(rq));
	hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
}

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

static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
	elevator_t *e = q->elevator;
	struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
	struct hlist_node *entry, *next;
	struct request *rq;

	hlist_for_each_entry_safe(rq, entry, next, hash_list, hash) {
		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.
 */
struct request *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 (rq->sector < __rq->sector)
			p = &(*p)->rb_left;
		else if (rq->sector > __rq->sector)
			p = &(*p)->rb_right;
		else
			return __rq;
	}

	rb_link_node(&rq->rb_node, parent, p);
	rb_insert_color(&rq->rb_node, root);
	return NULL;
}
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 < rq->sector)
			n = n->rb_left;
		else if (sector > rq->sector)
			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;
	int stop_flags;

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

	elv_rqhash_del(q, rq);

	q->nr_sorted--;

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

		if (blk_discard_rq(rq) != blk_discard_rq(pos))
			break;
		if (rq_data_dir(rq) != rq_data_dir(pos))
			break;
		if (pos->cmd_flags & stop_flags)
			break;
		if (rq->sector >= boundary) {
			if (pos->sector < boundary)
				continue;
		} else {
			if (pos->sector >= boundary)
				break;
		}
		if (rq->sector >= pos->sector)
			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);

int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
	elevator_t *e = q->elevator;
	struct request *__rq;
	int ret;

	/*
	 * First try one-hit cache.
	 */
	if (q->last_merge) {
		ret = elv_try_merge(q->last_merge, bio);
		if (ret != ELEVATOR_NO_MERGE) {
			*req = q->last_merge;
			return ret;
		}
	}

	if (blk_queue_nomerges(q))
		return ELEVATOR_NO_MERGE;

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

	if (e->ops->elevator_merge_fn)
		return e->ops->elevator_merge_fn(q, req, bio);

	return ELEVATOR_NO_MERGE;
}

void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
	elevator_t *e = q->elevator;

	if (e->ops->elevator_merged_fn)
		e->ops->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)
{
	elevator_t *e = q->elevator;

	if (e->ops->elevator_merge_req_fn)
		e->ops->elevator_merge_req_fn(q, rq, next);

	elv_rqhash_reposition(q, rq);
	elv_rqhash_del(q, next);

	q->nr_sorted--;
	q->last_merge = rq;
}

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--;
		if (blk_sorted_rq(rq))
			elv_deactivate_rq(q, rq);
	}

	rq->cmd_flags &= ~REQ_STARTED;

	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
}

static void elv_drain_elevator(struct request_queue *q)
{
	static int printed;
	while (q->elevator->ops->elevator_dispatch_fn(q, 1))
		;
	if (q->nr_sorted == 0)
		return;
	if (printed++ < 10) {
		printk(KERN_ERR "%s: forced dispatching is broken "
		       "(nr_sorted=%u), please report this\n",
		       q->elevator->elevator_type->elevator_name, q->nr_sorted);
	}
}

void elv_insert(struct request_queue *q, struct request *rq, int where)
{
	struct list_head *pos;
	unsigned ordseq;
	int unplug_it = 1;

	blk_add_trace_rq(q, rq, BLK_TA_INSERT);

	rq->q = q;

	switch (where) {
	case ELEVATOR_INSERT_FRONT:
		rq->cmd_flags |= REQ_SOFTBARRIER;

		list_add(&rq->queuelist, &q->queue_head);
		break;

	case ELEVATOR_INSERT_BACK:
		rq->cmd_flags |= REQ_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_remove_plug(q);
		q->request_fn(q);
		break;

	case ELEVATOR_INSERT_SORT:
		BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq));
		rq->cmd_flags |= REQ_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->ops->elevator_add_req_fn(q, rq);
		break;

	case ELEVATOR_INSERT_REQUEUE:
		/*
		 * If ordered flush isn't in progress, we do front
		 * insertion; otherwise, requests should be requeued
		 * in ordseq order.
		 */
		rq->cmd_flags |= REQ_SOFTBARRIER;

		/*
		 * Most requeues happen because of a busy condition,
		 * don't force unplug of the queue for that case.
		 */
		unplug_it = 0;

		if (q->ordseq == 0) {
			list_add(&rq->queuelist, &q->queue_head);
			break;
		}

		ordseq = blk_ordered_req_seq(rq);

		list_for_each(pos, &q->queue_head) {
			struct request *pos_rq = list_entry_rq(pos);
			if (ordseq <= blk_ordered_req_seq(pos_rq))
				break;
		}

		list_add_tail(&rq->queuelist, pos);
		break;

	default:
		printk(KERN_ERR "%s: bad insertion point %d\n",
		       __func__, where);
		BUG();
	}

	if (unplug_it && blk_queue_plugged(q)) {
		int nrq = q->rq.count[READ] + q->rq.count[WRITE]
			- q->in_flight;

		if (nrq >= q->unplug_thresh)
			__generic_unplug_device(q);
	}
}

void __elv_add_request(struct request_queue *q, struct request *rq, int where,
		       int plug)
{
	if (q->ordcolor)
		rq->cmd_flags |= REQ_ORDERED_COLOR;

	if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
		/*
		 * toggle ordered color
		 */
		if (blk_barrier_rq(rq))
			q->ordcolor ^= 1;

		/*
		 * barriers implicitly indicate back insertion
		 */
		if (where == ELEVATOR_INSERT_SORT)
			where = ELEVATOR_INSERT_BACK;

		/*
		 * this request is scheduling boundary, update
		 * end_sector
		 */
		if (blk_fs_request(rq) || blk_discard_rq(rq)) {
			q->end_sector = rq_end_sector(rq);
			q->boundary_rq = rq;
		}
	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
		    where == ELEVATOR_INSERT_SORT)
		where = ELEVATOR_INSERT_BACK;

	if (plug)
		blk_plug_device(q);

	elv_insert(q, rq, where);
}
EXPORT_SYMBOL(__elv_add_request);

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

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

static inline struct request *__elv_next_request(struct request_queue *q)
{
	struct request *rq;

	while (1) {
		while (!list_empty(&q->queue_head)) {
			rq = list_entry_rq(q->queue_head.next);
			if (blk_do_ordered(q, &rq))
				return rq;
		}

		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
			return NULL;
	}
}

struct request *elv_next_request(struct request_queue *q)
{
	struct request *rq;
	int ret;

	while ((rq = __elv_next_request(q)) != NULL) {
		/*
		 * Kill the empty barrier place holder, the driver must
		 * not ever see it.
		 */
		if (blk_empty_barrier(rq)) {
			end_queued_request(rq, 1);
			continue;
		}
		if (!(rq->cmd_flags & REQ_STARTED)) {
			/*
			 * This is the first time the device driver
			 * sees this request (possibly after
			 * requeueing).  Notify IO scheduler.
			 */
			if (blk_sorted_rq(rq))
				elv_activate_rq(q, rq);

			/*
			 * just mark as started even if we don't start
			 * it, a request that has been delayed should
			 * not be passed by new incoming requests
			 */
			rq->cmd_flags |= REQ_STARTED;
			blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
		}

		if (!q->boundary_rq || q->boundary_rq == rq) {
			q->end_sector = rq_end_sector(rq);
			q->boundary_rq = NULL;
		}

		if (rq->cmd_flags & REQ_DONTPREP)
			break;

		if (q->dma_drain_size && rq->data_len) {
			/*
			 * make sure space for the drain appears we
			 * know we can do this because max_hw_segments
			 * has been adjusted to be one fewer than the
			 * device can handle
			 */
			rq->nr_phys_segments++;
		}

		if (!q->prep_rq_fn)
			break;

		ret = q->prep_rq_fn(q, rq);
		if (ret == BLKPREP_OK) {
			break;
		} else if (ret == BLKPREP_DEFER) {
			/*
			 * the request may have been (partially) prepped.
			 * we need to keep this request in the front to
			 * avoid resource deadlock.  REQ_STARTED will
			 * prevent other fs requests from passing this one.
			 */
			if (q->dma_drain_size && rq->data_len &&
			    !(rq->cmd_flags & REQ_DONTPREP)) {
				/*
				 * remove the space for the drain we added
				 * so that we don't add it again
				 */
				--rq->nr_phys_segments;
			}

			rq = NULL;
			break;
		} else if (ret == BLKPREP_KILL) {
			rq->cmd_flags |= REQ_QUIET;
			end_queued_request(rq, 0);
		} else {
			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
			break;
		}
	}

	return rq;
}
EXPORT_SYMBOL(elv_next_request);

void elv_dequeue_request(struct request_queue *q, struct request *rq)
{
	BUG_ON(list_empty(&rq->queuelist));
	BUG_ON(ELV_ON_HASH(rq));

	list_del_init(&rq->queuelist);

	/*
	 * the time frame between a request being removed from the lists
	 * and to it is freed is accounted as io that is in progress at
	 * the driver side.
	 */
	if (blk_account_rq(rq))
		q->in_flight++;
}
EXPORT_SYMBOL(elv_dequeue_request);

int elv_queue_empty(struct request_queue *q)
{
	elevator_t *e = q->elevator;

	if (!list_empty(&q->queue_head))
		return 0;

	if (e->ops->elevator_queue_empty_fn)
		return e->ops->elevator_queue_empty_fn(q);

	return 1;
}
EXPORT_SYMBOL(elv_queue_empty);

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

	if (e->ops->elevator_latter_req_fn)
		return e->ops->elevator_latter_req_fn(q, rq);
	return NULL;
}

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

	if (e->ops->elevator_former_req_fn)
		return e->ops->elevator_former_req_fn(q, rq);
	return NULL;
}

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

	if (e->ops->elevator_set_req_fn)
		return e->ops->elevator_set_req_fn(q, rq, gfp_mask);

	rq->elevator_private = NULL;
	return 0;
}

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

	if (e->ops->elevator_put_req_fn)
		e->ops->elevator_put_req_fn(rq);
}

int elv_may_queue(struct request_queue *q, int rw)
{
	elevator_t *e = q->elevator;

	if (e->ops->elevator_may_queue_fn)
		return e->ops->elevator_may_queue_fn(q, rw);

	return ELV_MQUEUE_MAY;
}

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

	/*
	 * request is released from the driver, io must be done
	 */
	if (blk_account_rq(rq)) {
		q->in_flight--;
		if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
			e->ops->elevator_completed_req_fn(q, rq);
	}

	/*
	 * Check if the queue is waiting for fs requests to be
	 * drained for flush sequence.
	 */
	if (unlikely(q->ordseq)) {
		struct request *first_rq = list_entry_rq(q->queue_head.next);
		if (q->in_flight == 0 &&
		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
		    blk_ordered_req_seq(first_rq) > QUEUE_ORDSEQ_DRAIN) {
			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
			q->request_fn(q);
		}
	}
}

#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)
{
	elevator_t *e = container_of(kobj, elevator_t, kobj);
	struct elv_fs_entry *entry = to_elv(attr);
	ssize_t error;

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

	mutex_lock(&e->sysfs_lock);
	error = e->ops ? 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)
{
	elevator_t *e = container_of(kobj, elevator_t, kobj);
	struct elv_fs_entry *entry = to_elv(attr);
	ssize_t error;

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

	mutex_lock(&e->sysfs_lock);
	error = e->ops ? entry->store(e, page, length) : -ENOENT;
	mutex_unlock(&e->sysfs_lock);
	return error;
}

static 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)
{
	elevator_t *e = q->elevator;
	int error;

	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
	if (!error) {
		struct elv_fs_entry *attr = e->elevator_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);
	}
	return error;
}

static void __elv_unregister_queue(elevator_t *e)
{
	kobject_uevent(&e->kobj, KOBJ_REMOVE);
	kobject_del(&e->kobj);
}

void elv_unregister_queue(struct request_queue *q)
{
	if (q)
		__elv_unregister_queue(q->elevator);
}

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

	spin_lock(&elv_list_lock);
	BUG_ON(elevator_find(e->elevator_name));
	list_add_tail(&e->list, &elv_list);
	spin_unlock(&elv_list_lock);

	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);
}
EXPORT_SYMBOL_GPL(elv_register);

void elv_unregister(struct elevator_type *e)
{
	struct task_struct *g, *p;

	/*
	 * Iterate every thread in the process to remove the io contexts.
	 */
	if (e->ops.trim) {
		read_lock(&tasklist_lock);
		do_each_thread(g, p) {
			task_lock(p);
			if (p->io_context)
				e->ops.trim(p->io_context);
			task_unlock(p);
		} while_each_thread(g, p);
		read_unlock(&tasklist_lock);
	}

	spin_lock(&elv_list_lock);
	list_del_init(&e->list);
	spin_unlock(&elv_list_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);

/*
 * 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)
{
	elevator_t *old_elevator, *e;
	void *data;

	/*
	 * Allocate new elevator
	 */
	e = elevator_alloc(q, new_e);
	if (!e)
		return 0;

	data = elevator_init_queue(q, e);
	if (!data) {
		kobject_put(&e->kobj);
		return 0;
	}

	/*
	 * Turn on BYPASS and drain all requests w/ elevator private data
	 */
	spin_lock_irq(q->queue_lock);

	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);

	elv_drain_elevator(q);

	while (q->rq.elvpriv) {
		blk_remove_plug(q);
		q->request_fn(q);
		spin_unlock_irq(q->queue_lock);
		msleep(10);
		spin_lock_irq(q->queue_lock);
		elv_drain_elevator(q);
	}

	/*
	 * Remember old elevator.
	 */
	old_elevator = q->elevator;

	/*
	 * attach and start new elevator
	 */
	elevator_attach(q, e, data);

	spin_unlock_irq(q->queue_lock);

	__elv_unregister_queue(old_elevator);

	if (elv_register_queue(q))
		goto fail_register;

	/*
	 * finally exit old elevator and turn off BYPASS.
	 */
	elevator_exit(old_elevator);
	spin_lock_irq(q->queue_lock);
	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
	spin_unlock_irq(q->queue_lock);

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

	return 1;

fail_register:
	/*
	 * switch failed, exit the new io scheduler and reattach the old
	 * one again (along with re-adding the sysfs dir)
	 */
	elevator_exit(e);
	q->elevator = old_elevator;
	elv_register_queue(q);

	spin_lock_irq(q->queue_lock);
	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
	spin_unlock_irq(q->queue_lock);

	return 0;
}

ssize_t elv_iosched_store(struct request_queue *q, const char *name,
			  size_t count)
{
	char elevator_name[ELV_NAME_MAX];
	size_t len;
	struct elevator_type *e;

	elevator_name[sizeof(elevator_name) - 1] = '\0';
	strncpy(elevator_name, name, sizeof(elevator_name) - 1);
	len = strlen(elevator_name);

	if (len && elevator_name[len - 1] == '\n')
		elevator_name[len - 1] = '\0';

	e = elevator_get(elevator_name);
	if (!e) {
		printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
		return -EINVAL;
	}

	if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
		elevator_put(e);
		return count;
	}

	if (!elevator_switch(q, e))
		printk(KERN_ERR "elevator: switch to %s failed\n",
							elevator_name);
	return count;
}

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

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

	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);