aboutsummaryrefslogtreecommitdiff
path: root/block/as-iosched.c
blob: 4513fc59c9da5503c5cde98b3e7de1bb97633f8a (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
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
/*
 *  Anticipatory & deadline i/o scheduler.
 *
 *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
 *                     Nick Piggin <nickpiggin@yahoo.com.au>
 *
 */
#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/rbtree.h>
#include <linux/interrupt.h>

#define REQ_SYNC	1
#define REQ_ASYNC	0

/*
 * See Documentation/block/as-iosched.txt
 */

/*
 * max time before a read is submitted.
 */
#define default_read_expire (HZ / 8)

/*
 * ditto for writes, these limits are not hard, even
 * if the disk is capable of satisfying them.
 */
#define default_write_expire (HZ / 4)

/*
 * read_batch_expire describes how long we will allow a stream of reads to
 * persist before looking to see whether it is time to switch over to writes.
 */
#define default_read_batch_expire (HZ / 2)

/*
 * write_batch_expire describes how long we want a stream of writes to run for.
 * This is not a hard limit, but a target we set for the auto-tuning thingy.
 * See, the problem is: we can send a lot of writes to disk cache / TCQ in
 * a short amount of time...
 */
#define default_write_batch_expire (HZ / 8)

/*
 * max time we may wait to anticipate a read (default around 6ms)
 */
#define default_antic_expire ((HZ / 150) ? HZ / 150 : 1)

/*
 * Keep track of up to 20ms thinktimes. We can go as big as we like here,
 * however huge values tend to interfere and not decay fast enough. A program
 * might be in a non-io phase of operation. Waiting on user input for example,
 * or doing a lengthy computation. A small penalty can be justified there, and
 * will still catch out those processes that constantly have large thinktimes.
 */
#define MAX_THINKTIME (HZ/50UL)

/* Bits in as_io_context.state */
enum as_io_states {
	AS_TASK_RUNNING=0,	/* Process has not exited */
	AS_TASK_IOSTARTED,	/* Process has started some IO */
	AS_TASK_IORUNNING,	/* Process has completed some IO */
};

enum anticipation_status {
	ANTIC_OFF=0,		/* Not anticipating (normal operation)	*/
	ANTIC_WAIT_REQ,		/* The last read has not yet completed  */
	ANTIC_WAIT_NEXT,	/* Currently anticipating a request vs
				   last read (which has completed) */
	ANTIC_FINISHED,		/* Anticipating but have found a candidate
				 * or timed out */
};

struct as_data {
	/*
	 * run time data
	 */

	struct request_queue *q;	/* the "owner" queue */

	/*
	 * requests (as_rq s) are present on both sort_list and fifo_list
	 */
	struct rb_root sort_list[2];
	struct list_head fifo_list[2];

	struct request *next_rq[2];	/* next in sort order */
	sector_t last_sector[2];	/* last REQ_SYNC & REQ_ASYNC sectors */

	unsigned long exit_prob;	/* probability a task will exit while
					   being waited on */
	unsigned long exit_no_coop;	/* probablility an exited task will
					   not be part of a later cooperating
					   request */
	unsigned long new_ttime_total; 	/* mean thinktime on new proc */
	unsigned long new_ttime_mean;
	u64 new_seek_total;		/* mean seek on new proc */
	sector_t new_seek_mean;

	unsigned long current_batch_expires;
	unsigned long last_check_fifo[2];
	int changed_batch;		/* 1: waiting for old batch to end */
	int new_batch;			/* 1: waiting on first read complete */
	int batch_data_dir;		/* current batch REQ_SYNC / REQ_ASYNC */
	int write_batch_count;		/* max # of reqs in a write batch */
	int current_write_count;	/* how many requests left this batch */
	int write_batch_idled;		/* has the write batch gone idle? */

	enum anticipation_status antic_status;
	unsigned long antic_start;	/* jiffies: when it started */
	struct timer_list antic_timer;	/* anticipatory scheduling timer */
	struct work_struct antic_work;	/* Deferred unplugging */
	struct io_context *io_context;	/* Identify the expected process */
	int ioc_finished; /* IO associated with io_context is finished */
	int nr_dispatched;

	/*
	 * settings that change how the i/o scheduler behaves
	 */
	unsigned long fifo_expire[2];
	unsigned long batch_expire[2];
	unsigned long antic_expire;
};

/*
 * per-request data.
 */
enum arq_state {
	AS_RQ_NEW=0,		/* New - not referenced and not on any lists */
	AS_RQ_QUEUED,		/* In the request queue. It belongs to the
				   scheduler */
	AS_RQ_DISPATCHED,	/* On the dispatch list. It belongs to the
				   driver now */
	AS_RQ_PRESCHED,		/* Debug poisoning for requests being used */
	AS_RQ_REMOVED,
	AS_RQ_MERGED,
	AS_RQ_POSTSCHED,	/* when they shouldn't be */
};

#define RQ_IOC(rq)	((struct io_context *) (rq)->elevator_private)
#define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
#define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)

static DEFINE_PER_CPU(unsigned long, ioc_count);
static struct completion *ioc_gone;

static void as_move_to_dispatch(struct as_data *ad, struct request *rq);
static void as_antic_stop(struct as_data *ad);

/*
 * IO Context helper functions
 */

/* Called to deallocate the as_io_context */
static void free_as_io_context(struct as_io_context *aic)
{
	kfree(aic);
	elv_ioc_count_dec(ioc_count);
	if (ioc_gone && !elv_ioc_count_read(ioc_count))
		complete(ioc_gone);
}

static void as_trim(struct io_context *ioc)
{
	if (ioc->aic)
		free_as_io_context(ioc->aic);
	ioc->aic = NULL;
}

/* Called when the task exits */
static void exit_as_io_context(struct as_io_context *aic)
{
	WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state));
	clear_bit(AS_TASK_RUNNING, &aic->state);
}

static struct as_io_context *alloc_as_io_context(void)
{
	struct as_io_context *ret;

	ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
	if (ret) {
		ret->dtor = free_as_io_context;
		ret->exit = exit_as_io_context;
		ret->state = 1 << AS_TASK_RUNNING;
		atomic_set(&ret->nr_queued, 0);
		atomic_set(&ret->nr_dispatched, 0);
		spin_lock_init(&ret->lock);
		ret->ttime_total = 0;
		ret->ttime_samples = 0;
		ret->ttime_mean = 0;
		ret->seek_total = 0;
		ret->seek_samples = 0;
		ret->seek_mean = 0;
		elv_ioc_count_inc(ioc_count);
	}

	return ret;
}

/*
 * If the current task has no AS IO context then create one and initialise it.
 * Then take a ref on the task's io context and return it.
 */
static struct io_context *as_get_io_context(int node)
{
	struct io_context *ioc = get_io_context(GFP_ATOMIC, node);
	if (ioc && !ioc->aic) {
		ioc->aic = alloc_as_io_context();
		if (!ioc->aic) {
			put_io_context(ioc);
			ioc = NULL;
		}
	}
	return ioc;
}

static void as_put_io_context(struct request *rq)
{
	struct as_io_context *aic;

	if (unlikely(!RQ_IOC(rq)))
		return;

	aic = RQ_IOC(rq)->aic;

	if (rq_is_sync(rq) && aic) {
		spin_lock(&aic->lock);
		set_bit(AS_TASK_IORUNNING, &aic->state);
		aic->last_end_request = jiffies;
		spin_unlock(&aic->lock);
	}

	put_io_context(RQ_IOC(rq));
}

/*
 * rb tree support functions
 */
#define RQ_RB_ROOT(ad, rq)	(&(ad)->sort_list[rq_is_sync((rq))])

static void as_add_rq_rb(struct as_data *ad, struct request *rq)
{
	struct request *alias;

	while ((unlikely(alias = elv_rb_add(RQ_RB_ROOT(ad, rq), rq)))) {
		as_move_to_dispatch(ad, alias);
		as_antic_stop(ad);
	}
}

static inline void as_del_rq_rb(struct as_data *ad, struct request *rq)
{
	elv_rb_del(RQ_RB_ROOT(ad, rq), rq);
}

/*
 * IO Scheduler proper
 */

#define MAXBACK (1024 * 1024)	/*
				 * Maximum distance the disk will go backward
				 * for a request.
				 */

#define BACK_PENALTY	2

/*
 * as_choose_req selects the preferred one of two requests of the same data_dir
 * ignoring time - eg. timeouts, which is the job of as_dispatch_request
 */
static struct request *
as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2)
{
	int data_dir;
	sector_t last, s1, s2, d1, d2;
	int r1_wrap=0, r2_wrap=0;	/* requests are behind the disk head */
	const sector_t maxback = MAXBACK;

	if (rq1 == NULL || rq1 == rq2)
		return rq2;
	if (rq2 == NULL)
		return rq1;

	data_dir = rq_is_sync(rq1);

	last = ad->last_sector[data_dir];
	s1 = rq1->sector;
	s2 = rq2->sector;

	BUG_ON(data_dir != rq_is_sync(rq2));

	/*
	 * Strict one way elevator _except_ in the case where we allow
	 * short backward seeks which are biased as twice the cost of a
	 * similar forward seek.
	 */
	if (s1 >= last)
		d1 = s1 - last;
	else if (s1+maxback >= last)
		d1 = (last - s1)*BACK_PENALTY;
	else {
		r1_wrap = 1;
		d1 = 0; /* shut up, gcc */
	}

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2+maxback >= last)
		d2 = (last - s2)*BACK_PENALTY;
	else {
		r2_wrap = 1;
		d2 = 0;
	}

	/* Found required data */
	if (!r1_wrap && r2_wrap)
		return rq1;
	else if (!r2_wrap && r1_wrap)
		return rq2;
	else if (r1_wrap && r2_wrap) {
		/* both behind the head */
		if (s1 <= s2)
			return rq1;
		else
			return rq2;
	}

	/* Both requests in front of the head */
	if (d1 < d2)
		return rq1;
	else if (d2 < d1)
		return rq2;
	else {
		if (s1 >= s2)
			return rq1;
		else
			return rq2;
	}
}

/*
 * as_find_next_rq finds the next request after @prev in elevator order.
 * this with as_choose_req form the basis for how the scheduler chooses
 * what request to process next. Anticipation works on top of this.
 */
static struct request *
as_find_next_rq(struct as_data *ad, struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next = NULL, *prev = NULL;

	BUG_ON(RB_EMPTY_NODE(&last->rb_node));

	if (rbprev)
		prev = rb_entry_rq(rbprev);

	if (rbnext)
		next = rb_entry_rq(rbnext);
	else {
		const int data_dir = rq_is_sync(last);

		rbnext = rb_first(&ad->sort_list[data_dir]);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return as_choose_req(ad, next, prev);
}

/*
 * anticipatory scheduling functions follow
 */

/*
 * as_antic_expired tells us when we have anticipated too long.
 * The funny "absolute difference" math on the elapsed time is to handle
 * jiffy wraps, and disks which have been idle for 0x80000000 jiffies.
 */
static int as_antic_expired(struct as_data *ad)
{
	long delta_jif;

	delta_jif = jiffies - ad->antic_start;
	if (unlikely(delta_jif < 0))
		delta_jif = -delta_jif;
	if (delta_jif < ad->antic_expire)
		return 0;

	return 1;
}

/*
 * as_antic_waitnext starts anticipating that a nice request will soon be
 * submitted. See also as_antic_waitreq
 */
static void as_antic_waitnext(struct as_data *ad)
{
	unsigned long timeout;

	BUG_ON(ad->antic_status != ANTIC_OFF
			&& ad->antic_status != ANTIC_WAIT_REQ);

	timeout = ad->antic_start + ad->antic_expire;

	mod_timer(&ad->antic_timer, timeout);

	ad->antic_status = ANTIC_WAIT_NEXT;
}

/*
 * as_antic_waitreq starts anticipating. We don't start timing the anticipation
 * until the request that we're anticipating on has finished. This means we
 * are timing from when the candidate process wakes up hopefully.
 */
static void as_antic_waitreq(struct as_data *ad)
{
	BUG_ON(ad->antic_status == ANTIC_FINISHED);
	if (ad->antic_status == ANTIC_OFF) {
		if (!ad->io_context || ad->ioc_finished)
			as_antic_waitnext(ad);
		else
			ad->antic_status = ANTIC_WAIT_REQ;
	}
}

/*
 * This is called directly by the functions in this file to stop anticipation.
 * We kill the timer and schedule a call to the request_fn asap.
 */
static void as_antic_stop(struct as_data *ad)
{
	int status = ad->antic_status;

	if (status == ANTIC_WAIT_REQ || status == ANTIC_WAIT_NEXT) {
		if (status == ANTIC_WAIT_NEXT)
			del_timer(&ad->antic_timer);
		ad->antic_status = ANTIC_FINISHED;
		/* see as_work_handler */
		kblockd_schedule_work(&ad->antic_work);
	}
}

/*
 * as_antic_timeout is the timer function set by as_antic_waitnext.
 */
static void as_antic_timeout(unsigned long data)
{
	struct request_queue *q = (struct request_queue *)data;
	struct as_data *ad = q->elevator->elevator_data;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	if (ad->antic_status == ANTIC_WAIT_REQ
			|| ad->antic_status == ANTIC_WAIT_NEXT) {
		struct as_io_context *aic = ad->io_context->aic;

		ad->antic_status = ANTIC_FINISHED;
		kblockd_schedule_work(&ad->antic_work);

		if (aic->ttime_samples == 0) {
			/* process anticipated on has exited or timed out*/
			ad->exit_prob = (7*ad->exit_prob + 256)/8;
		}
		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
			/* process not "saved" by a cooperating request */
			ad->exit_no_coop = (7*ad->exit_no_coop + 256)/8;
		}
	}
	spin_unlock_irqrestore(q->queue_lock, flags);
}

static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic,
				unsigned long ttime)
{
	/* fixed point: 1.0 == 1<<8 */
	if (aic->ttime_samples == 0) {
		ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8;
		ad->new_ttime_mean = ad->new_ttime_total / 256;

		ad->exit_prob = (7*ad->exit_prob)/8;
	}
	aic->ttime_samples = (7*aic->ttime_samples + 256) / 8;
	aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8;
	aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples;
}

static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic,
				sector_t sdist)
{
	u64 total;

	if (aic->seek_samples == 0) {
		ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8;
		ad->new_seek_mean = ad->new_seek_total / 256;
	}

	/*
	 * Don't allow the seek distance to get too large from the
	 * odd fragment, pagein, etc
	 */
	if (aic->seek_samples <= 60) /* second&third seek */
		sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024);
	else
		sdist = min(sdist, (aic->seek_mean * 4)	+ 2*1024*64);

	aic->seek_samples = (7*aic->seek_samples + 256) / 8;
	aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8;
	total = aic->seek_total + (aic->seek_samples/2);
	do_div(total, aic->seek_samples);
	aic->seek_mean = (sector_t)total;
}

/*
 * as_update_iohist keeps a decaying histogram of IO thinktimes, and
 * updates @aic->ttime_mean based on that. It is called when a new
 * request is queued.
 */
static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
				struct request *rq)
{
	int data_dir = rq_is_sync(rq);
	unsigned long thinktime = 0;
	sector_t seek_dist;

	if (aic == NULL)
		return;

	if (data_dir == REQ_SYNC) {
		unsigned long in_flight = atomic_read(&aic->nr_queued)
					+ atomic_read(&aic->nr_dispatched);
		spin_lock(&aic->lock);
		if (test_bit(AS_TASK_IORUNNING, &aic->state) ||
			test_bit(AS_TASK_IOSTARTED, &aic->state)) {
			/* Calculate read -> read thinktime */
			if (test_bit(AS_TASK_IORUNNING, &aic->state)
							&& in_flight == 0) {
				thinktime = jiffies - aic->last_end_request;
				thinktime = min(thinktime, MAX_THINKTIME-1);
			}
			as_update_thinktime(ad, aic, thinktime);

			/* Calculate read -> read seek distance */
			if (aic->last_request_pos < rq->sector)
				seek_dist = rq->sector - aic->last_request_pos;
			else
				seek_dist = aic->last_request_pos - rq->sector;
			as_update_seekdist(ad, aic, seek_dist);
		}
		aic->last_request_pos = rq->sector + rq->nr_sectors;
		set_bit(AS_TASK_IOSTARTED, &aic->state);
		spin_unlock(&aic->lock);
	}
}

/*
 * as_close_req decides if one request is considered "close" to the
 * previous one issued.
 */
static int as_close_req(struct as_data *ad, struct as_io_context *aic,
			struct request *rq)
{
	unsigned long delay;	/* jiffies */
	sector_t last = ad->last_sector[ad->batch_data_dir];
	sector_t next = rq->sector;
	sector_t delta; /* acceptable close offset (in sectors) */
	sector_t s;

	if (ad->antic_status == ANTIC_OFF || !ad->ioc_finished)
		delay = 0;
	else
		delay = jiffies - ad->antic_start;

	if (delay == 0)
		delta = 8192;
	else if (delay <= (20 * HZ / 1000) && delay <= ad->antic_expire)
		delta = 8192 << delay;
	else
		return 1;

	if ((last <= next + (delta>>1)) && (next <= last + delta))
		return 1;

	if (last < next)
		s = next - last;
	else
		s = last - next;

	if (aic->seek_samples == 0) {
		/*
		 * Process has just started IO. Use past statistics to
		 * gauge success possibility
		 */
		if (ad->new_seek_mean > s) {
			/* this request is better than what we're expecting */
			return 1;
		}

	} else {
		if (aic->seek_mean > s) {
			/* this request is better than what we're expecting */
			return 1;
		}
	}

	return 0;
}

/*
 * as_can_break_anticipation returns true if we have been anticipating this
 * request.
 *
 * It also returns true if the process against which we are anticipating
 * submits a write - that's presumably an fsync, O_SYNC write, etc. We want to
 * dispatch it ASAP, because we know that application will not be submitting
 * any new reads.
 *
 * If the task which has submitted the request has exited, break anticipation.
 *
 * If this task has queued some other IO, do not enter enticipation.
 */
static int as_can_break_anticipation(struct as_data *ad, struct request *rq)
{
	struct io_context *ioc;
	struct as_io_context *aic;

	ioc = ad->io_context;
	BUG_ON(!ioc);

	if (rq && ioc == RQ_IOC(rq)) {
		/* request from same process */
		return 1;
	}

	if (ad->ioc_finished && as_antic_expired(ad)) {
		/*
		 * In this situation status should really be FINISHED,
		 * however the timer hasn't had the chance to run yet.
		 */
		return 1;
	}

	aic = ioc->aic;
	if (!aic)
		return 0;

	if (atomic_read(&aic->nr_queued) > 0) {
		/* process has more requests queued */
		return 1;
	}

	if (atomic_read(&aic->nr_dispatched) > 0) {
		/* process has more requests dispatched */
		return 1;
	}

	if (rq && rq_is_sync(rq) && as_close_req(ad, aic, rq)) {
		/*
		 * Found a close request that is not one of ours.
		 *
		 * This makes close requests from another process update
		 * our IO history. Is generally useful when there are
		 * two or more cooperating processes working in the same
		 * area.
		 */
		if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
			if (aic->ttime_samples == 0)
				ad->exit_prob = (7*ad->exit_prob + 256)/8;

			ad->exit_no_coop = (7*ad->exit_no_coop)/8;
		}

		as_update_iohist(ad, aic, rq);
		return 1;
	}

	if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
		/* process anticipated on has exited */
		if (aic->ttime_samples == 0)
			ad->exit_prob = (7*ad->exit_prob + 256)/8;

		if (ad->exit_no_coop > 128)
			return 1;
	}

	if (aic->ttime_samples == 0) {
		if (ad->new_ttime_mean > ad->antic_expire)
			return 1;
		if (ad->exit_prob * ad->exit_no_coop > 128*256)
			return 1;
	} else if (aic->ttime_mean > ad->antic_expire) {
		/* the process thinks too much between requests */
		return 1;
	}

	return 0;
}

/*
 * as_can_anticipate indicates whether we should either run rq
 * or keep anticipating a better request.
 */
static int as_can_anticipate(struct as_data *ad, struct request *rq)
{
	if (!ad->io_context)
		/*
		 * Last request submitted was a write
		 */
		return 0;

	if (ad->antic_status == ANTIC_FINISHED)
		/*
		 * Don't restart if we have just finished. Run the next request
		 */
		return 0;

	if (as_can_break_anticipation(ad, rq))
		/*
		 * This request is a good candidate. Don't keep anticipating,
		 * run it.
		 */
		return 0;

	/*
	 * OK from here, we haven't finished, and don't have a decent request!
	 * Status is either ANTIC_OFF so start waiting,
	 * ANTIC_WAIT_REQ so continue waiting for request to finish
	 * or ANTIC_WAIT_NEXT so continue waiting for an acceptable request.
	 */

	return 1;
}

/*
 * as_update_rq must be called whenever a request (rq) is added to
 * the sort_list. This function keeps caches up to date, and checks if the
 * request might be one we are "anticipating"
 */
static void as_update_rq(struct as_data *ad, struct request *rq)
{
	const int data_dir = rq_is_sync(rq);

	/* keep the next_rq cache up to date */
	ad->next_rq[data_dir] = as_choose_req(ad, rq, ad->next_rq[data_dir]);

	/*
	 * have we been anticipating this request?
	 * or does it come from the same process as the one we are anticipating
	 * for?
	 */
	if (ad->antic_status == ANTIC_WAIT_REQ
			|| ad->antic_status == ANTIC_WAIT_NEXT) {
		if (as_can_break_anticipation(ad, rq))
			as_antic_stop(ad);
	}
}

/*
 * Gathers timings and resizes the write batch automatically
 */
static void update_write_batch(struct as_data *ad)
{
	unsigned long batch = ad->batch_expire[REQ_ASYNC];
	long write_time;

	write_time = (jiffies - ad->current_batch_expires) + batch;
	if (write_time < 0)
		write_time = 0;

	if (write_time > batch && !ad->write_batch_idled) {
		if (write_time > batch * 3)
			ad->write_batch_count /= 2;
		else
			ad->write_batch_count--;
	} else if (write_time < batch && ad->current_write_count == 0) {
		if (batch > write_time * 3)
			ad->write_batch_count *= 2;
		else
			ad->write_batch_count++;
	}

	if (ad->write_batch_count < 1)
		ad->write_batch_count = 1;
}

/*
 * as_completed_request is to be called when a request has completed and
 * returned something to the requesting process, be it an error or data.
 */
static void as_completed_request(struct request_queue *q, struct request *rq)
{
	struct as_data *ad = q->elevator->elevator_data;

	WARN_ON(!list_empty(&rq->queuelist));

	if (RQ_STATE(rq) != AS_RQ_REMOVED) {
		printk("rq->state %d\n", RQ_STATE(rq));
		WARN_ON(1);
		goto out;
	}

	if (ad->changed_batch && ad->nr_dispatched == 1) {
		kblockd_schedule_work(&ad->antic_work);
		ad->changed_batch = 0;

		if (ad->batch_data_dir == REQ_SYNC)
			ad->new_batch = 1;
	}
	WARN_ON(ad->nr_dispatched == 0);
	ad->nr_dispatched--;

	/*
	 * Start counting the batch from when a request of that direction is
	 * actually serviced. This should help devices with big TCQ windows
	 * and writeback caches
	 */
	if (ad->new_batch && ad->batch_data_dir == rq_is_sync(rq)) {
		update_write_batch(ad);
		ad->current_batch_expires = jiffies +
				ad->batch_expire[REQ_SYNC];
		ad->new_batch = 0;
	}

	if (ad->io_context == RQ_IOC(rq) && ad->io_context) {
		ad->antic_start = jiffies;
		ad->ioc_finished = 1;
		if (ad->antic_status == ANTIC_WAIT_REQ) {
			/*
			 * We were waiting on this request, now anticipate
			 * the next one
			 */
			as_antic_waitnext(ad);
		}
	}

	as_put_io_context(rq);
out:
	RQ_SET_STATE(rq, AS_RQ_POSTSCHED);
}

/*
 * as_remove_queued_request removes a request from the pre dispatch queue
 * without updating refcounts. It is expected the caller will drop the
 * reference unless it replaces the request at somepart of the elevator
 * (ie. the dispatch queue)
 */
static void as_remove_queued_request(struct request_queue *q,
				     struct request *rq)
{
	const int data_dir = rq_is_sync(rq);
	struct as_data *ad = q->elevator->elevator_data;
	struct io_context *ioc;

	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);

	ioc = RQ_IOC(rq);
	if (ioc && ioc->aic) {
		BUG_ON(!atomic_read(&ioc->aic->nr_queued));
		atomic_dec(&ioc->aic->nr_queued);
	}

	/*
	 * Update the "next_rq" cache if we are about to remove its
	 * entry
	 */
	if (ad->next_rq[data_dir] == rq)
		ad->next_rq[data_dir] = as_find_next_rq(ad, rq);

	rq_fifo_clear(rq);
	as_del_rq_rb(ad, rq);
}

/*
 * as_fifo_expired returns 0 if there are no expired requests on the fifo,
 * 1 otherwise.  It is ratelimited so that we only perform the check once per
 * `fifo_expire' interval.  Otherwise a large number of expired requests
 * would create a hopeless seekstorm.
 *
 * See as_antic_expired comment.
 */
static int as_fifo_expired(struct as_data *ad, int adir)
{
	struct request *rq;
	long delta_jif;

	delta_jif = jiffies - ad->last_check_fifo[adir];
	if (unlikely(delta_jif < 0))
		delta_jif = -delta_jif;
	if (delta_jif < ad->fifo_expire[adir])
		return 0;

	ad->last_check_fifo[adir] = jiffies;

	if (list_empty(&ad->fifo_list[adir]))
		return 0;

	rq = rq_entry_fifo(ad->fifo_list[adir].next);

	return time_after(jiffies, rq_fifo_time(rq));
}

/*
 * as_batch_expired returns true if the current batch has expired. A batch
 * is a set of reads or a set of writes.
 */
static inline int as_batch_expired(struct as_data *ad)
{
	if (ad->changed_batch || ad->new_batch)
		return 0;

	if (ad->batch_data_dir == REQ_SYNC)
		/* TODO! add a check so a complete fifo gets written? */
		return time_after(jiffies, ad->current_batch_expires);

	return time_after(jiffies, ad->current_batch_expires)
		|| ad->current_write_count == 0;
}

/*
 * move an entry to dispatch queue
 */
static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
{
	const int data_dir = rq_is_sync(rq);

	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));

	as_antic_stop(ad);
	ad->antic_status = ANTIC_OFF;

	/*
	 * This has to be set in order to be correctly updated by
	 * as_find_next_rq
	 */
	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;

	if (data_dir == REQ_SYNC) {
		struct io_context *ioc = RQ_IOC(rq);
		/* In case we have to anticipate after this */
		copy_io_context(&ad->io_context, &ioc);
	} else {
		if (ad->io_context) {
			put_io_context(ad->io_context);
			ad->io_context = NULL;
		}

		if (ad->current_write_count != 0)
			ad->current_write_count--;
	}
	ad->ioc_finished = 0;

	ad->next_rq[data_dir] = as_find_next_rq(ad, rq);

	/*
	 * take it off the sort and fifo list, add to dispatch queue
	 */
	as_remove_queued_request(ad->q, rq);
	WARN_ON(RQ_STATE(rq) != AS_RQ_QUEUED);

	elv_dispatch_sort(ad->q, rq);

	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
	ad->nr_dispatched++;
}

/*
 * as_dispatch_request selects the best request according to
 * read/write expire, batch expire, etc, and moves it to the dispatch
 * queue. Returns 1 if a request was found, 0 otherwise.
 */
static int as_dispatch_request(struct request_queue *q, int force)
{
	struct as_data *ad = q->elevator->elevator_data;
	const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
	const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);
	struct request *rq;

	if (unlikely(force)) {
		/*
		 * Forced dispatch, accounting is useless.  Reset
		 * accounting states and dump fifo_lists.  Note that
		 * batch_data_dir is reset to REQ_SYNC to avoid
		 * screwing write batch accounting as write batch
		 * accounting occurs on W->R transition.
		 */
		int dispatched = 0;

		ad->batch_data_dir = REQ_SYNC;
		ad->changed_batch = 0;
		ad->new_batch = 0;

		while (ad->next_rq[REQ_SYNC]) {
			as_move_to_dispatch(ad, ad->next_rq[REQ_SYNC]);
			dispatched++;
		}
		ad->last_check_fifo[REQ_SYNC] = jiffies;

		while (ad->next_rq[REQ_ASYNC]) {
			as_move_to_dispatch(ad, ad->next_rq[REQ_ASYNC]);
			dispatched++;
		}
		ad->last_check_fifo[REQ_ASYNC] = jiffies;

		return dispatched;
	}

	/* Signal that the write batch was uncontended, so we can't time it */
	if (ad->batch_data_dir == REQ_ASYNC && !reads) {
		if (ad->current_write_count == 0 || !writes)
			ad->write_batch_idled = 1;
	}

	if (!(reads || writes)
		|| ad->antic_status == ANTIC_WAIT_REQ
		|| ad->antic_status == ANTIC_WAIT_NEXT
		|| ad->changed_batch)
		return 0;

	if (!(reads && writes && as_batch_expired(ad))) {
		/*
		 * batch is still running or no reads or no writes
		 */
		rq = ad->next_rq[ad->batch_data_dir];

		if (ad->batch_data_dir == REQ_SYNC && ad->antic_expire) {
			if (as_fifo_expired(ad, REQ_SYNC))
				goto fifo_expired;

			if (as_can_anticipate(ad, rq)) {
				as_antic_waitreq(ad);
				return 0;
			}
		}

		if (rq) {
			/* we have a "next request" */
			if (reads && !writes)
				ad->current_batch_expires =
					jiffies + ad->batch_expire[REQ_SYNC];
			goto dispatch_request;
		}
	}

	/*
	 * at this point we are not running a batch. select the appropriate
	 * data direction (read / write)
	 */

	if (reads) {
		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_SYNC]));

		if (writes && ad->batch_data_dir == REQ_SYNC)
			/*
			 * Last batch was a read, switch to writes
			 */
			goto dispatch_writes;

		if (ad->batch_data_dir == REQ_ASYNC) {
			WARN_ON(ad->new_batch);
			ad->changed_batch = 1;
		}
		ad->batch_data_dir = REQ_SYNC;
		rq = rq_entry_fifo(ad->fifo_list[REQ_SYNC].next);
		ad->last_check_fifo[ad->batch_data_dir] = jiffies;
		goto dispatch_request;
	}

	/*
	 * the last batch was a read
	 */

	if (writes) {
dispatch_writes:
		BUG_ON(RB_EMPTY_ROOT(&ad->sort_list[REQ_ASYNC]));

		if (ad->batch_data_dir == REQ_SYNC) {
			ad->changed_batch = 1;

			/*
			 * new_batch might be 1 when the queue runs out of
			 * reads. A subsequent submission of a write might
			 * cause a change of batch before the read is finished.
			 */
			ad->new_batch = 0;
		}
		ad->batch_data_dir = REQ_ASYNC;
		ad->current_write_count = ad->write_batch_count;
		ad->write_batch_idled = 0;
		rq = ad->next_rq[ad->batch_data_dir];
		goto dispatch_request;
	}

	BUG();
	return 0;

dispatch_request:
	/*
	 * If a request has expired, service it.
	 */

	if (as_fifo_expired(ad, ad->batch_data_dir)) {
fifo_expired:
		rq = rq_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
	}

	if (ad->changed_batch) {
		WARN_ON(ad->new_batch);

		if (ad->nr_dispatched)
			return 0;

		if (ad->batch_data_dir == REQ_ASYNC)
			ad->current_batch_expires = jiffies +
					ad->batch_expire[REQ_ASYNC];
		else
			ad->new_batch = 1;

		ad->changed_batch = 0;
	}

	/*
	 * rq is the selected appropriate request.
	 */
	as_move_to_dispatch(ad, rq);

	return 1;
}

/*
 * add rq to rbtree and fifo
 */
static void as_add_request(struct request_queue *q, struct request *rq)
{
	struct as_data *ad = q->elevator->elevator_data;
	int data_dir;

	RQ_SET_STATE(rq, AS_RQ_NEW);

	data_dir = rq_is_sync(rq);

	rq->elevator_private = as_get_io_context(q->node);

	if (RQ_IOC(rq)) {
		as_update_iohist(ad, RQ_IOC(rq)->aic, rq);
		atomic_inc(&RQ_IOC(rq)->aic->nr_queued);
	}

	as_add_rq_rb(ad, rq);

	/*
	 * set expire time and add to fifo list
	 */
	rq_set_fifo_time(rq, jiffies + ad->fifo_expire[data_dir]);
	list_add_tail(&rq->queuelist, &ad->fifo_list[data_dir]);

	as_update_rq(ad, rq); /* keep state machine up to date */
	RQ_SET_STATE(rq, AS_RQ_QUEUED);
}

static void as_activate_request(struct request_queue *q, struct request *rq)
{
	WARN_ON(RQ_STATE(rq) != AS_RQ_DISPATCHED);
	RQ_SET_STATE(rq, AS_RQ_REMOVED);
	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
		atomic_dec(&RQ_IOC(rq)->aic->nr_dispatched);
}

static void as_deactivate_request(struct request_queue *q, struct request *rq)
{
	WARN_ON(RQ_STATE(rq) != AS_RQ_REMOVED);
	RQ_SET_STATE(rq, AS_RQ_DISPATCHED);
	if (RQ_IOC(rq) && RQ_IOC(rq)->aic)
		atomic_inc(&RQ_IOC(rq)->aic->nr_dispatched);
}

/*
 * as_queue_empty tells us if there are requests left in the device. It may
 * not be the case that a driver can get the next request even if the queue
 * is not empty - it is used in the block layer to check for plugging and
 * merging opportunities
 */
static int as_queue_empty(struct request_queue *q)
{
	struct as_data *ad = q->elevator->elevator_data;

	return list_empty(&ad->fifo_list[REQ_ASYNC])
		&& list_empty(&ad->fifo_list[REQ_SYNC]);
}

static int
as_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
	struct as_data *ad = q->elevator->elevator_data;
	sector_t rb_key = bio->bi_sector + bio_sectors(bio);
	struct request *__rq;

	/*
	 * check for front merge
	 */
	__rq = elv_rb_find(&ad->sort_list[bio_data_dir(bio)], rb_key);
	if (__rq && elv_rq_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_FRONT_MERGE;
	}

	return ELEVATOR_NO_MERGE;
}

static void as_merged_request(struct request_queue *q, struct request *req,
			      int type)
{
	struct as_data *ad = q->elevator->elevator_data;

	/*
	 * if the merge was a front merge, we need to reposition request
	 */
	if (type == ELEVATOR_FRONT_MERGE) {
		as_del_rq_rb(ad, req);
		as_add_rq_rb(ad, req);
		/*
		 * Note! At this stage of this and the next function, our next
		 * request may not be optimal - eg the request may have "grown"
		 * behind the disk head. We currently don't bother adjusting.
		 */
	}
}

static void as_merged_requests(struct request_queue *q, struct request *req,
			 	struct request *next)
{
	/*
	 * if next expires before rq, assign its expire time to arq
	 * and move into next position (next will be deleted) in fifo
	 */
	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
			struct io_context *rioc = RQ_IOC(req);
			struct io_context *nioc = RQ_IOC(next);

			list_move(&req->queuelist, &next->queuelist);
			rq_set_fifo_time(req, rq_fifo_time(next));
			/*
			 * Don't copy here but swap, because when anext is
			 * removed below, it must contain the unused context
			 */
			swap_io_context(&rioc, &nioc);
		}
	}

	/*
	 * kill knowledge of next, this one is a goner
	 */
	as_remove_queued_request(q, next);
	as_put_io_context(next);

	RQ_SET_STATE(next, AS_RQ_MERGED);
}

/*
 * This is executed in a "deferred" process context, by kblockd. It calls the
 * driver's request_fn so the driver can submit that request.
 *
 * IMPORTANT! This guy will reenter the elevator, so set up all queue global
 * state before calling, and don't rely on any state over calls.
 *
 * FIXME! dispatch queue is not a queue at all!
 */
static void as_work_handler(struct work_struct *work)
{
	struct as_data *ad = container_of(work, struct as_data, antic_work);
	struct request_queue *q = ad->q;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_start_queueing(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

static int as_may_queue(struct request_queue *q, int rw)
{
	int ret = ELV_MQUEUE_MAY;
	struct as_data *ad = q->elevator->elevator_data;
	struct io_context *ioc;
	if (ad->antic_status == ANTIC_WAIT_REQ ||
			ad->antic_status == ANTIC_WAIT_NEXT) {
		ioc = as_get_io_context(q->node);
		if (ad->io_context == ioc)
			ret = ELV_MQUEUE_MUST;
		put_io_context(ioc);
	}

	return ret;
}

static void as_exit_queue(elevator_t *e)
{
	struct as_data *ad = e->elevator_data;

	del_timer_sync(&ad->antic_timer);
	kblockd_flush_work(&ad->antic_work);

	BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC]));
	BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC]));

	put_io_context(ad->io_context);
	kfree(ad);
}

/*
 * initialize elevator private data (as_data).
 */
static void *as_init_queue(struct request_queue *q)
{
	struct as_data *ad;

	ad = kmalloc_node(sizeof(*ad), GFP_KERNEL | __GFP_ZERO, q->node);
	if (!ad)
		return NULL;

	ad->q = q; /* Identify what queue the data belongs to */

	/* anticipatory scheduling helpers */
	ad->antic_timer.function = as_antic_timeout;
	ad->antic_timer.data = (unsigned long)q;
	init_timer(&ad->antic_timer);
	INIT_WORK(&ad->antic_work, as_work_handler);

	INIT_LIST_HEAD(&ad->fifo_list[REQ_SYNC]);
	INIT_LIST_HEAD(&ad->fifo_list[REQ_ASYNC]);
	ad->sort_list[REQ_SYNC] = RB_ROOT;
	ad->sort_list[REQ_ASYNC] = RB_ROOT;
	ad->fifo_expire[REQ_SYNC] = default_read_expire;
	ad->fifo_expire[REQ_ASYNC] = default_write_expire;
	ad->antic_expire = default_antic_expire;
	ad->batch_expire[REQ_SYNC] = default_read_batch_expire;
	ad->batch_expire[REQ_ASYNC] = default_write_batch_expire;

	ad->current_batch_expires = jiffies + ad->batch_expire[REQ_SYNC];
	ad->write_batch_count = ad->batch_expire[REQ_ASYNC] / 10;
	if (ad->write_batch_count < 2)
		ad->write_batch_count = 2;

	return ad;
}

/*
 * sysfs parts below
 */

static ssize_t
as_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%d\n", var);
}

static ssize_t
as_var_store(unsigned long *var, const char *page, size_t count)
{
	char *p = (char *) page;

	*var = simple_strtoul(p, &p, 10);
	return count;
}

static ssize_t est_time_show(elevator_t *e, char *page)
{
	struct as_data *ad = e->elevator_data;
	int pos = 0;

	pos += sprintf(page+pos, "%lu %% exit probability\n",
				100*ad->exit_prob/256);
	pos += sprintf(page+pos, "%lu %% probability of exiting without a "
				"cooperating process submitting IO\n",
				100*ad->exit_no_coop/256);
	pos += sprintf(page+pos, "%lu ms new thinktime\n", ad->new_ttime_mean);
	pos += sprintf(page+pos, "%llu sectors new seek distance\n",
				(unsigned long long)ad->new_seek_mean);

	return pos;
}

#define SHOW_FUNCTION(__FUNC, __VAR)				\
static ssize_t __FUNC(elevator_t *e, char *page)		\
{								\
	struct as_data *ad = e->elevator_data;			\
	return as_var_show(jiffies_to_msecs((__VAR)), (page));	\
}
SHOW_FUNCTION(as_read_expire_show, ad->fifo_expire[REQ_SYNC]);
SHOW_FUNCTION(as_write_expire_show, ad->fifo_expire[REQ_ASYNC]);
SHOW_FUNCTION(as_antic_expire_show, ad->antic_expire);
SHOW_FUNCTION(as_read_batch_expire_show, ad->batch_expire[REQ_SYNC]);
SHOW_FUNCTION(as_write_batch_expire_show, ad->batch_expire[REQ_ASYNC]);
#undef SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)				\
static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
{									\
	struct as_data *ad = e->elevator_data;				\
	int ret = as_var_store(__PTR, (page), count);			\
	if (*(__PTR) < (MIN))						\
		*(__PTR) = (MIN);					\
	else if (*(__PTR) > (MAX))					\
		*(__PTR) = (MAX);					\
	*(__PTR) = msecs_to_jiffies(*(__PTR));				\
	return ret;							\
}
STORE_FUNCTION(as_read_expire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX);
STORE_FUNCTION(as_write_expire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX);
STORE_FUNCTION(as_antic_expire_store, &ad->antic_expire, 0, INT_MAX);
STORE_FUNCTION(as_read_batch_expire_store,
			&ad->batch_expire[REQ_SYNC], 0, INT_MAX);
STORE_FUNCTION(as_write_batch_expire_store,
			&ad->batch_expire[REQ_ASYNC], 0, INT_MAX);
#undef STORE_FUNCTION

#define AS_ATTR(name) \
	__ATTR(name, S_IRUGO|S_IWUSR, as_##name##_show, as_##name##_store)

static struct elv_fs_entry as_attrs[] = {
	__ATTR_RO(est_time),
	AS_ATTR(read_expire),
	AS_ATTR(write_expire),
	AS_ATTR(antic_expire),
	AS_ATTR(read_batch_expire),
	AS_ATTR(write_batch_expire),
	__ATTR_NULL
};

static struct elevator_type iosched_as = {
	.ops = {
		.elevator_merge_fn = 		as_merge,
		.elevator_merged_fn =		as_merged_request,
		.elevator_merge_req_fn =	as_merged_requests,
		.elevator_dispatch_fn =		as_dispatch_request,
		.elevator_add_req_fn =		as_add_request,
		.elevator_activate_req_fn =	as_activate_request,
		.elevator_deactivate_req_fn = 	as_deactivate_request,
		.elevator_queue_empty_fn =	as_queue_empty,
		.elevator_completed_req_fn =	as_completed_request,
		.elevator_former_req_fn =	elv_rb_former_request,
		.elevator_latter_req_fn =	elv_rb_latter_request,
		.elevator_may_queue_fn =	as_may_queue,
		.elevator_init_fn =		as_init_queue,
		.elevator_exit_fn =		as_exit_queue,
		.trim =				as_trim,
	},

	.elevator_attrs = as_attrs,
	.elevator_name = "anticipatory",
	.elevator_owner = THIS_MODULE,
};

static int __init as_init(void)
{
	return elv_register(&iosched_as);
}

static void __exit as_exit(void)
{
	DECLARE_COMPLETION_ONSTACK(all_gone);
	elv_unregister(&iosched_as);
	ioc_gone = &all_gone;
	/* ioc_gone's update must be visible before reading ioc_count */
	smp_wmb();
	if (elv_ioc_count_read(ioc_count))
		wait_for_completion(ioc_gone);
	synchronize_rcu();
}

module_init(as_init);
module_exit(as_exit);

MODULE_AUTHOR("Nick Piggin");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("anticipatory IO scheduler");