summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-cache-policy-smq.c
blob: 48a4a826ae07649419d033b99c564b2adb9da6ea (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
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
/*
 * Copyright (C) 2015 Red Hat. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm-cache-policy.h"
#include "dm-cache-policy-internal.h"
#include "dm.h"

#include <linux/hash.h>
#include <linux/jiffies.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/math64.h>

#define DM_MSG_PREFIX "cache-policy-smq"

/*----------------------------------------------------------------*/

/*
 * Safe division functions that return zero on divide by zero.
 */
static unsigned safe_div(unsigned n, unsigned d)
{
	return d ? n / d : 0u;
}

static unsigned safe_mod(unsigned n, unsigned d)
{
	return d ? n % d : 0u;
}

/*----------------------------------------------------------------*/

struct entry {
	unsigned hash_next:28;
	unsigned prev:28;
	unsigned next:28;
	unsigned level:7;
	bool dirty:1;
	bool allocated:1;
	bool sentinel:1;

	dm_oblock_t oblock;
};

/*----------------------------------------------------------------*/

#define INDEXER_NULL ((1u << 28u) - 1u)

/*
 * An entry_space manages a set of entries that we use for the queues.
 * The clean and dirty queues share entries, so this object is separate
 * from the queue itself.
 */
struct entry_space {
	struct entry *begin;
	struct entry *end;
};

static int space_init(struct entry_space *es, unsigned nr_entries)
{
	if (!nr_entries) {
		es->begin = es->end = NULL;
		return 0;
	}

	es->begin = vzalloc(sizeof(struct entry) * nr_entries);
	if (!es->begin)
		return -ENOMEM;

	es->end = es->begin + nr_entries;
	return 0;
}

static void space_exit(struct entry_space *es)
{
	vfree(es->begin);
}

static struct entry *__get_entry(struct entry_space *es, unsigned block)
{
	struct entry *e;

	e = es->begin + block;
	BUG_ON(e >= es->end);

	return e;
}

static unsigned to_index(struct entry_space *es, struct entry *e)
{
	BUG_ON(e < es->begin || e >= es->end);
	return e - es->begin;
}

static struct entry *to_entry(struct entry_space *es, unsigned block)
{
	if (block == INDEXER_NULL)
		return NULL;

	return __get_entry(es, block);
}

/*----------------------------------------------------------------*/

struct ilist {
	unsigned nr_elts;	/* excluding sentinel entries */
	unsigned head, tail;
};

static void l_init(struct ilist *l)
{
	l->nr_elts = 0;
	l->head = l->tail = INDEXER_NULL;
}

static struct entry *l_head(struct entry_space *es, struct ilist *l)
{
	return to_entry(es, l->head);
}

static struct entry *l_tail(struct entry_space *es, struct ilist *l)
{
	return to_entry(es, l->tail);
}

static struct entry *l_next(struct entry_space *es, struct entry *e)
{
	return to_entry(es, e->next);
}

static struct entry *l_prev(struct entry_space *es, struct entry *e)
{
	return to_entry(es, e->prev);
}

static bool l_empty(struct ilist *l)
{
	return l->head == INDEXER_NULL;
}

static void l_add_head(struct entry_space *es, struct ilist *l, struct entry *e)
{
	struct entry *head = l_head(es, l);

	e->next = l->head;
	e->prev = INDEXER_NULL;

	if (head)
		head->prev = l->head = to_index(es, e);
	else
		l->head = l->tail = to_index(es, e);

	if (!e->sentinel)
		l->nr_elts++;
}

static void l_add_tail(struct entry_space *es, struct ilist *l, struct entry *e)
{
	struct entry *tail = l_tail(es, l);

	e->next = INDEXER_NULL;
	e->prev = l->tail;

	if (tail)
		tail->next = l->tail = to_index(es, e);
	else
		l->head = l->tail = to_index(es, e);

	if (!e->sentinel)
		l->nr_elts++;
}

static void l_add_before(struct entry_space *es, struct ilist *l,
			 struct entry *old, struct entry *e)
{
	struct entry *prev = l_prev(es, old);

	if (!prev)
		l_add_head(es, l, e);

	else {
		e->prev = old->prev;
		e->next = to_index(es, old);
		prev->next = old->prev = to_index(es, e);

		if (!e->sentinel)
			l->nr_elts++;
	}
}

static void l_del(struct entry_space *es, struct ilist *l, struct entry *e)
{
	struct entry *prev = l_prev(es, e);
	struct entry *next = l_next(es, e);

	if (prev)
		prev->next = e->next;
	else
		l->head = e->next;

	if (next)
		next->prev = e->prev;
	else
		l->tail = e->prev;

	if (!e->sentinel)
		l->nr_elts--;
}

static struct entry *l_pop_tail(struct entry_space *es, struct ilist *l)
{
	struct entry *e;

	for (e = l_tail(es, l); e; e = l_prev(es, e))
		if (!e->sentinel) {
			l_del(es, l, e);
			return e;
		}

	return NULL;
}

/*----------------------------------------------------------------*/

/*
 * The stochastic-multi-queue is a set of lru lists stacked into levels.
 * Entries are moved up levels when they are used, which loosely orders the
 * most accessed entries in the top levels and least in the bottom.  This
 * structure is *much* better than a single lru list.
 */
#define MAX_LEVELS 64u

struct queue {
	struct entry_space *es;

	unsigned nr_elts;
	unsigned nr_levels;
	struct ilist qs[MAX_LEVELS];

	/*
	 * We maintain a count of the number of entries we would like in each
	 * level.
	 */
	unsigned last_target_nr_elts;
	unsigned nr_top_levels;
	unsigned nr_in_top_levels;
	unsigned target_count[MAX_LEVELS];
};

static void q_init(struct queue *q, struct entry_space *es, unsigned nr_levels)
{
	unsigned i;

	q->es = es;
	q->nr_elts = 0;
	q->nr_levels = nr_levels;

	for (i = 0; i < q->nr_levels; i++) {
		l_init(q->qs + i);
		q->target_count[i] = 0u;
	}

	q->last_target_nr_elts = 0u;
	q->nr_top_levels = 0u;
	q->nr_in_top_levels = 0u;
}

static unsigned q_size(struct queue *q)
{
	return q->nr_elts;
}

/*
 * Insert an entry to the back of the given level.
 */
static void q_push(struct queue *q, struct entry *e)
{
	if (!e->sentinel)
		q->nr_elts++;

	l_add_tail(q->es, q->qs + e->level, e);
}

static void q_push_before(struct queue *q, struct entry *old, struct entry *e)
{
	if (!e->sentinel)
		q->nr_elts++;

	l_add_before(q->es, q->qs + e->level, old, e);
}

static void q_del(struct queue *q, struct entry *e)
{
	l_del(q->es, q->qs + e->level, e);
	if (!e->sentinel)
		q->nr_elts--;
}

/*
 * Return the oldest entry of the lowest populated level.
 */
static struct entry *q_peek(struct queue *q, unsigned max_level, bool can_cross_sentinel)
{
	unsigned level;
	struct entry *e;

	max_level = min(max_level, q->nr_levels);

	for (level = 0; level < max_level; level++)
		for (e = l_head(q->es, q->qs + level); e; e = l_next(q->es, e)) {
			if (e->sentinel) {
				if (can_cross_sentinel)
					continue;
				else
					break;
			}

			return e;
		}

	return NULL;
}

static struct entry *q_pop(struct queue *q)
{
	struct entry *e = q_peek(q, q->nr_levels, true);

	if (e)
		q_del(q, e);

	return e;
}

/*
 * Pops an entry from a level that is not past a sentinel.
 */
static struct entry *q_pop_old(struct queue *q, unsigned max_level)
{
	struct entry *e = q_peek(q, max_level, false);

	if (e)
		q_del(q, e);

	return e;
}

/*
 * This function assumes there is a non-sentinel entry to pop.  It's only
 * used by redistribute, so we know this is true.  It also doesn't adjust
 * the q->nr_elts count.
 */
static struct entry *__redist_pop_from(struct queue *q, unsigned level)
{
	struct entry *e;

	for (; level < q->nr_levels; level++)
		for (e = l_head(q->es, q->qs + level); e; e = l_next(q->es, e))
			if (!e->sentinel) {
				l_del(q->es, q->qs + e->level, e);
				return e;
			}

	return NULL;
}

static void q_set_targets_subrange_(struct queue *q, unsigned nr_elts, unsigned lbegin, unsigned lend)
{
	unsigned level, nr_levels, entries_per_level, remainder;

	BUG_ON(lbegin > lend);
	BUG_ON(lend > q->nr_levels);
	nr_levels = lend - lbegin;
	entries_per_level = safe_div(nr_elts, nr_levels);
	remainder = safe_mod(nr_elts, nr_levels);

	for (level = lbegin; level < lend; level++)
		q->target_count[level] =
			(level < (lbegin + remainder)) ? entries_per_level + 1u : entries_per_level;
}

/*
 * Typically we have fewer elements in the top few levels which allows us
 * to adjust the promote threshold nicely.
 */
static void q_set_targets(struct queue *q)
{
	if (q->last_target_nr_elts == q->nr_elts)
		return;

	q->last_target_nr_elts = q->nr_elts;

	if (q->nr_top_levels > q->nr_levels)
		q_set_targets_subrange_(q, q->nr_elts, 0, q->nr_levels);

	else {
		q_set_targets_subrange_(q, q->nr_in_top_levels,
					q->nr_levels - q->nr_top_levels, q->nr_levels);

		if (q->nr_in_top_levels < q->nr_elts)
			q_set_targets_subrange_(q, q->nr_elts - q->nr_in_top_levels,
						0, q->nr_levels - q->nr_top_levels);
		else
			q_set_targets_subrange_(q, 0, 0, q->nr_levels - q->nr_top_levels);
	}
}

static void q_redistribute(struct queue *q)
{
	unsigned target, level;
	struct ilist *l, *l_above;
	struct entry *e;

	q_set_targets(q);

	for (level = 0u; level < q->nr_levels - 1u; level++) {
		l = q->qs + level;
		target = q->target_count[level];

		/*
		 * Pull down some entries from the level above.
		 */
		while (l->nr_elts < target) {
			e = __redist_pop_from(q, level + 1u);
			if (!e) {
				/* bug in nr_elts */
				break;
			}

			e->level = level;
			l_add_tail(q->es, l, e);
		}

		/*
		 * Push some entries up.
		 */
		l_above = q->qs + level + 1u;
		while (l->nr_elts > target) {
			e = l_pop_tail(q->es, l);

			if (!e)
				/* bug in nr_elts */
				break;

			e->level = level + 1u;
			l_add_head(q->es, l_above, e);
		}
	}
}

static void q_requeue_before(struct queue *q, struct entry *dest, struct entry *e, unsigned extra_levels)
{
	struct entry *de;
	unsigned new_level;

	q_del(q, e);

	if (extra_levels && (e->level < q->nr_levels - 1u)) {
		new_level = min(q->nr_levels - 1u, e->level + extra_levels);
		for (de = l_head(q->es, q->qs + new_level); de; de = l_next(q->es, de)) {
			if (de->sentinel)
				continue;

			q_del(q, de);
			de->level = e->level;

			if (dest)
				q_push_before(q, dest, de);
			else
				q_push(q, de);
			break;
		}

		e->level = new_level;
	}

	q_push(q, e);
}

static void q_requeue(struct queue *q, struct entry *e, unsigned extra_levels)
{
	q_requeue_before(q, NULL, e, extra_levels);
}

/*----------------------------------------------------------------*/

#define FP_SHIFT 8
#define SIXTEENTH (1u << (FP_SHIFT - 4u))
#define EIGHTH (1u << (FP_SHIFT - 3u))

struct stats {
	unsigned hit_threshold;
	unsigned hits;
	unsigned misses;
};

enum performance {
	Q_POOR,
	Q_FAIR,
	Q_WELL
};

static void stats_init(struct stats *s, unsigned nr_levels)
{
	s->hit_threshold = (nr_levels * 3u) / 4u;
	s->hits = 0u;
	s->misses = 0u;
}

static void stats_reset(struct stats *s)
{
	s->hits = s->misses = 0u;
}

static void stats_level_accessed(struct stats *s, unsigned level)
{
	if (level >= s->hit_threshold)
		s->hits++;
	else
		s->misses++;
}

static void stats_miss(struct stats *s)
{
	s->misses++;
}

/*
 * There are times when we don't have any confidence in the hotspot queue.
 * Such as when a fresh cache is created and the blocks have been spread
 * out across the levels, or if an io load changes.  We detect this by
 * seeing how often a lookup is in the top levels of the hotspot queue.
 */
static enum performance stats_assess(struct stats *s)
{
	unsigned confidence = safe_div(s->hits << FP_SHIFT, s->hits + s->misses);

	if (confidence < SIXTEENTH)
		return Q_POOR;

	else if (confidence < EIGHTH)
		return Q_FAIR;

	else
		return Q_WELL;
}

/*----------------------------------------------------------------*/

struct hash_table {
	struct entry_space *es;
	unsigned long long hash_bits;
	unsigned *buckets;
};

/*
 * All cache entries are stored in a chained hash table.  To save space we
 * use indexing again, and only store indexes to the next entry.
 */
static int h_init(struct hash_table *ht, struct entry_space *es, unsigned nr_entries)
{
	unsigned i, nr_buckets;

	ht->es = es;
	nr_buckets = roundup_pow_of_two(max(nr_entries / 4u, 16u));
	ht->hash_bits = ffs(nr_buckets) - 1;

	ht->buckets = vmalloc(sizeof(*ht->buckets) * nr_buckets);
	if (!ht->buckets)
		return -ENOMEM;

	for (i = 0; i < nr_buckets; i++)
		ht->buckets[i] = INDEXER_NULL;

	return 0;
}

static void h_exit(struct hash_table *ht)
{
	vfree(ht->buckets);
}

static struct entry *h_head(struct hash_table *ht, unsigned bucket)
{
	return to_entry(ht->es, ht->buckets[bucket]);
}

static struct entry *h_next(struct hash_table *ht, struct entry *e)
{
	return to_entry(ht->es, e->hash_next);
}

static void __h_insert(struct hash_table *ht, unsigned bucket, struct entry *e)
{
	e->hash_next = ht->buckets[bucket];
	ht->buckets[bucket] = to_index(ht->es, e);
}

static void h_insert(struct hash_table *ht, struct entry *e)
{
	unsigned h = hash_64(from_oblock(e->oblock), ht->hash_bits);
	__h_insert(ht, h, e);
}

static struct entry *__h_lookup(struct hash_table *ht, unsigned h, dm_oblock_t oblock,
				struct entry **prev)
{
	struct entry *e;

	*prev = NULL;
	for (e = h_head(ht, h); e; e = h_next(ht, e)) {
		if (e->oblock == oblock)
			return e;

		*prev = e;
	}

	return NULL;
}

static void __h_unlink(struct hash_table *ht, unsigned h,
		       struct entry *e, struct entry *prev)
{
	if (prev)
		prev->hash_next = e->hash_next;
	else
		ht->buckets[h] = e->hash_next;
}

/*
 * Also moves each entry to the front of the bucket.
 */
static struct entry *h_lookup(struct hash_table *ht, dm_oblock_t oblock)
{
	struct entry *e, *prev;
	unsigned h = hash_64(from_oblock(oblock), ht->hash_bits);

	e = __h_lookup(ht, h, oblock, &prev);
	if (e && prev) {
		/*
		 * Move to the front because this entry is likely
		 * to be hit again.
		 */
		__h_unlink(ht, h, e, prev);
		__h_insert(ht, h, e);
	}

	return e;
}

static void h_remove(struct hash_table *ht, struct entry *e)
{
	unsigned h = hash_64(from_oblock(e->oblock), ht->hash_bits);
	struct entry *prev;

	/*
	 * The down side of using a singly linked list is we have to
	 * iterate the bucket to remove an item.
	 */
	e = __h_lookup(ht, h, e->oblock, &prev);
	if (e)
		__h_unlink(ht, h, e, prev);
}

/*----------------------------------------------------------------*/

struct entry_alloc {
	struct entry_space *es;
	unsigned begin;

	unsigned nr_allocated;
	struct ilist free;
};

static void init_allocator(struct entry_alloc *ea, struct entry_space *es,
			   unsigned begin, unsigned end)
{
	unsigned i;

	ea->es = es;
	ea->nr_allocated = 0u;
	ea->begin = begin;

	l_init(&ea->free);
	for (i = begin; i != end; i++)
		l_add_tail(ea->es, &ea->free, __get_entry(ea->es, i));
}

static void init_entry(struct entry *e)
{
	/*
	 * We can't memset because that would clear the hotspot and
	 * sentinel bits which remain constant.
	 */
	e->hash_next = INDEXER_NULL;
	e->next = INDEXER_NULL;
	e->prev = INDEXER_NULL;
	e->level = 0u;
	e->allocated = true;
}

static struct entry *alloc_entry(struct entry_alloc *ea)
{
	struct entry *e;

	if (l_empty(&ea->free))
		return NULL;

	e = l_pop_tail(ea->es, &ea->free);
	init_entry(e);
	ea->nr_allocated++;

	return e;
}

/*
 * This assumes the cblock hasn't already been allocated.
 */
static struct entry *alloc_particular_entry(struct entry_alloc *ea, unsigned i)
{
	struct entry *e = __get_entry(ea->es, ea->begin + i);

	BUG_ON(e->allocated);

	l_del(ea->es, &ea->free, e);
	init_entry(e);
	ea->nr_allocated++;

	return e;
}

static void free_entry(struct entry_alloc *ea, struct entry *e)
{
	BUG_ON(!ea->nr_allocated);
	BUG_ON(!e->allocated);

	ea->nr_allocated--;
	e->allocated = false;
	l_add_tail(ea->es, &ea->free, e);
}

static bool allocator_empty(struct entry_alloc *ea)
{
	return l_empty(&ea->free);
}

static unsigned get_index(struct entry_alloc *ea, struct entry *e)
{
	return to_index(ea->es, e) - ea->begin;
}

static struct entry *get_entry(struct entry_alloc *ea, unsigned index)
{
	return __get_entry(ea->es, ea->begin + index);
}

/*----------------------------------------------------------------*/

#define NR_HOTSPOT_LEVELS 64u
#define NR_CACHE_LEVELS 64u

#define WRITEBACK_PERIOD (10 * HZ)
#define DEMOTE_PERIOD (60 * HZ)

#define HOTSPOT_UPDATE_PERIOD (HZ)
#define CACHE_UPDATE_PERIOD (10u * HZ)

struct smq_policy {
	struct dm_cache_policy policy;

	/* protects everything */
	struct mutex lock;
	dm_cblock_t cache_size;
	sector_t cache_block_size;

	sector_t hotspot_block_size;
	unsigned nr_hotspot_blocks;
	unsigned cache_blocks_per_hotspot_block;
	unsigned hotspot_level_jump;

	struct entry_space es;
	struct entry_alloc writeback_sentinel_alloc;
	struct entry_alloc demote_sentinel_alloc;
	struct entry_alloc hotspot_alloc;
	struct entry_alloc cache_alloc;

	unsigned long *hotspot_hit_bits;
	unsigned long *cache_hit_bits;

	/*
	 * We maintain three queues of entries.  The cache proper,
	 * consisting of a clean and dirty queue, containing the currently
	 * active mappings.  The hotspot queue uses a larger block size to
	 * track blocks that are being hit frequently and potential
	 * candidates for promotion to the cache.
	 */
	struct queue hotspot;
	struct queue clean;
	struct queue dirty;

	struct stats hotspot_stats;
	struct stats cache_stats;

	/*
	 * Keeps track of time, incremented by the core.  We use this to
	 * avoid attributing multiple hits within the same tick.
	 *
	 * Access to tick_protected should be done with the spin lock held.
	 * It's copied to tick at the start of the map function (within the
	 * mutex).
	 */
	spinlock_t tick_lock;
	unsigned tick_protected;
	unsigned tick;

	/*
	 * The hash tables allows us to quickly find an entry by origin
	 * block.
	 */
	struct hash_table table;
	struct hash_table hotspot_table;

	bool current_writeback_sentinels;
	unsigned long next_writeback_period;

	bool current_demote_sentinels;
	unsigned long next_demote_period;

	unsigned write_promote_level;
	unsigned read_promote_level;

	unsigned long next_hotspot_period;
	unsigned long next_cache_period;
};

/*----------------------------------------------------------------*/

static struct entry *get_sentinel(struct entry_alloc *ea, unsigned level, bool which)
{
	return get_entry(ea, which ? level : NR_CACHE_LEVELS + level);
}

static struct entry *writeback_sentinel(struct smq_policy *mq, unsigned level)
{
	return get_sentinel(&mq->writeback_sentinel_alloc, level, mq->current_writeback_sentinels);
}

static struct entry *demote_sentinel(struct smq_policy *mq, unsigned level)
{
	return get_sentinel(&mq->demote_sentinel_alloc, level, mq->current_demote_sentinels);
}

static void __update_writeback_sentinels(struct smq_policy *mq)
{
	unsigned level;
	struct queue *q = &mq->dirty;
	struct entry *sentinel;

	for (level = 0; level < q->nr_levels; level++) {
		sentinel = writeback_sentinel(mq, level);
		q_del(q, sentinel);
		q_push(q, sentinel);
	}
}

static void __update_demote_sentinels(struct smq_policy *mq)
{
	unsigned level;
	struct queue *q = &mq->clean;
	struct entry *sentinel;

	for (level = 0; level < q->nr_levels; level++) {
		sentinel = demote_sentinel(mq, level);
		q_del(q, sentinel);
		q_push(q, sentinel);
	}
}

static void update_sentinels(struct smq_policy *mq)
{
	if (time_after(jiffies, mq->next_writeback_period)) {
		__update_writeback_sentinels(mq);
		mq->next_writeback_period = jiffies + WRITEBACK_PERIOD;
		mq->current_writeback_sentinels = !mq->current_writeback_sentinels;
	}

	if (time_after(jiffies, mq->next_demote_period)) {
		__update_demote_sentinels(mq);
		mq->next_demote_period = jiffies + DEMOTE_PERIOD;
		mq->current_demote_sentinels = !mq->current_demote_sentinels;
	}
}

static void __sentinels_init(struct smq_policy *mq)
{
	unsigned level;
	struct entry *sentinel;

	for (level = 0; level < NR_CACHE_LEVELS; level++) {
		sentinel = writeback_sentinel(mq, level);
		sentinel->level = level;
		q_push(&mq->dirty, sentinel);

		sentinel = demote_sentinel(mq, level);
		sentinel->level = level;
		q_push(&mq->clean, sentinel);
	}
}

static void sentinels_init(struct smq_policy *mq)
{
	mq->next_writeback_period = jiffies + WRITEBACK_PERIOD;
	mq->next_demote_period = jiffies + DEMOTE_PERIOD;

	mq->current_writeback_sentinels = false;
	mq->current_demote_sentinels = false;
	__sentinels_init(mq);

	mq->current_writeback_sentinels = !mq->current_writeback_sentinels;
	mq->current_demote_sentinels = !mq->current_demote_sentinels;
	__sentinels_init(mq);
}

/*----------------------------------------------------------------*/

/*
 * These methods tie together the dirty queue, clean queue and hash table.
 */
static void push_new(struct smq_policy *mq, struct entry *e)
{
	struct queue *q = e->dirty ? &mq->dirty : &mq->clean;
	h_insert(&mq->table, e);
	q_push(q, e);
}

static void push(struct smq_policy *mq, struct entry *e)
{
	struct entry *sentinel;

	h_insert(&mq->table, e);

	/*
	 * Punch this into the queue just in front of the sentinel, to
	 * ensure it's cleaned straight away.
	 */
	if (e->dirty) {
		sentinel = writeback_sentinel(mq, e->level);
		q_push_before(&mq->dirty, sentinel, e);
	} else {
		sentinel = demote_sentinel(mq, e->level);
		q_push_before(&mq->clean, sentinel, e);
	}
}

/*
 * Removes an entry from cache.  Removes from the hash table.
 */
static void __del(struct smq_policy *mq, struct queue *q, struct entry *e)
{
	q_del(q, e);
	h_remove(&mq->table, e);
}

static void del(struct smq_policy *mq, struct entry *e)
{
	__del(mq, e->dirty ? &mq->dirty : &mq->clean, e);
}

static struct entry *pop_old(struct smq_policy *mq, struct queue *q, unsigned max_level)
{
	struct entry *e = q_pop_old(q, max_level);
	if (e)
		h_remove(&mq->table, e);
	return e;
}

static dm_cblock_t infer_cblock(struct smq_policy *mq, struct entry *e)
{
	return to_cblock(get_index(&mq->cache_alloc, e));
}

static void requeue(struct smq_policy *mq, struct entry *e)
{
	struct entry *sentinel;

	if (!test_and_set_bit(from_cblock(infer_cblock(mq, e)), mq->cache_hit_bits)) {
		if (e->dirty) {
			sentinel = writeback_sentinel(mq, e->level);
			q_requeue_before(&mq->dirty, sentinel, e, 1u);
		} else {
			sentinel = demote_sentinel(mq, e->level);
			q_requeue_before(&mq->clean, sentinel, e, 1u);
		}
	}
}

static unsigned default_promote_level(struct smq_policy *mq)
{
	/*
	 * The promote level depends on the current performance of the
	 * cache.
	 *
	 * If the cache is performing badly, then we can't afford
	 * to promote much without causing performance to drop below that
	 * of the origin device.
	 *
	 * If the cache is performing well, then we don't need to promote
	 * much.  If it isn't broken, don't fix it.
	 *
	 * If the cache is middling then we promote more.
	 *
	 * This scheme reminds me of a graph of entropy vs probability of a
	 * binary variable.
	 */
	static unsigned table[] = {1, 1, 1, 2, 4, 6, 7, 8, 7, 6, 4, 4, 3, 3, 2, 2, 1};

	unsigned hits = mq->cache_stats.hits;
	unsigned misses = mq->cache_stats.misses;
	unsigned index = safe_div(hits << 4u, hits + misses);
	return table[index];
}

static void update_promote_levels(struct smq_policy *mq)
{
	/*
	 * If there are unused cache entries then we want to be really
	 * eager to promote.
	 */
	unsigned threshold_level = allocator_empty(&mq->cache_alloc) ?
		default_promote_level(mq) : (NR_HOTSPOT_LEVELS / 2u);

	/*
	 * If the hotspot queue is performing badly then we have little
	 * confidence that we know which blocks to promote.  So we cut down
	 * the amount of promotions.
	 */
	switch (stats_assess(&mq->hotspot_stats)) {
	case Q_POOR:
		threshold_level /= 4u;
		break;

	case Q_FAIR:
		threshold_level /= 2u;
		break;

	case Q_WELL:
		break;
	}

	mq->read_promote_level = NR_HOTSPOT_LEVELS - threshold_level;
	mq->write_promote_level = (NR_HOTSPOT_LEVELS - threshold_level) + 2u;
}

/*
 * If the hotspot queue is performing badly, then we try and move entries
 * around more quickly.
 */
static void update_level_jump(struct smq_policy *mq)
{
	switch (stats_assess(&mq->hotspot_stats)) {
	case Q_POOR:
		mq->hotspot_level_jump = 4u;
		break;

	case Q_FAIR:
		mq->hotspot_level_jump = 2u;
		break;

	case Q_WELL:
		mq->hotspot_level_jump = 1u;
		break;
	}
}

static void end_hotspot_period(struct smq_policy *mq)
{
	clear_bitset(mq->hotspot_hit_bits, mq->nr_hotspot_blocks);
	update_promote_levels(mq);

	if (time_after(jiffies, mq->next_hotspot_period)) {
		update_level_jump(mq);
		q_redistribute(&mq->hotspot);
		stats_reset(&mq->hotspot_stats);
		mq->next_hotspot_period = jiffies + HOTSPOT_UPDATE_PERIOD;
	}
}

static void end_cache_period(struct smq_policy *mq)
{
	if (time_after(jiffies, mq->next_cache_period)) {
		clear_bitset(mq->cache_hit_bits, from_cblock(mq->cache_size));

		q_redistribute(&mq->dirty);
		q_redistribute(&mq->clean);
		stats_reset(&mq->cache_stats);

		mq->next_cache_period = jiffies + CACHE_UPDATE_PERIOD;
	}
}

static int demote_cblock(struct smq_policy *mq,
			 struct policy_locker *locker,
			 dm_oblock_t *oblock)
{
	struct entry *demoted = q_peek(&mq->clean, mq->clean.nr_levels, false);
	if (!demoted)
		/*
		 * We could get a block from mq->dirty, but that
		 * would add extra latency to the triggering bio as it
		 * waits for the writeback.  Better to not promote this
		 * time and hope there's a clean block next time this block
		 * is hit.
		 */
		return -ENOSPC;

	if (locker->fn(locker, demoted->oblock))
		/*
		 * We couldn't lock this block.
		 */
		return -EBUSY;

	del(mq, demoted);
	*oblock = demoted->oblock;
	free_entry(&mq->cache_alloc, demoted);

	return 0;
}

enum promote_result {
	PROMOTE_NOT,
	PROMOTE_TEMPORARY,
	PROMOTE_PERMANENT
};

/*
 * Converts a boolean into a promote result.
 */
static enum promote_result maybe_promote(bool promote)
{
	return promote ? PROMOTE_PERMANENT : PROMOTE_NOT;
}

static enum promote_result should_promote(struct smq_policy *mq, struct entry *hs_e, struct bio *bio,
					  bool fast_promote)
{
	if (bio_data_dir(bio) == WRITE) {
		if (!allocator_empty(&mq->cache_alloc) && fast_promote)
			return PROMOTE_TEMPORARY;

		else
			return maybe_promote(hs_e->level >= mq->write_promote_level);
	} else
		return maybe_promote(hs_e->level >= mq->read_promote_level);
}

static void insert_in_cache(struct smq_policy *mq, dm_oblock_t oblock,
			    struct policy_locker *locker,
			    struct policy_result *result, enum promote_result pr)
{
	int r;
	struct entry *e;

	if (allocator_empty(&mq->cache_alloc)) {
		result->op = POLICY_REPLACE;
		r = demote_cblock(mq, locker, &result->old_oblock);
		if (r) {
			result->op = POLICY_MISS;
			return;
		}

	} else
		result->op = POLICY_NEW;

	e = alloc_entry(&mq->cache_alloc);
	BUG_ON(!e);
	e->oblock = oblock;

	if (pr == PROMOTE_TEMPORARY)
		push(mq, e);
	else
		push_new(mq, e);

	result->cblock = infer_cblock(mq, e);
}

static dm_oblock_t to_hblock(struct smq_policy *mq, dm_oblock_t b)
{
	sector_t r = from_oblock(b);
	(void) sector_div(r, mq->cache_blocks_per_hotspot_block);
	return to_oblock(r);
}

static struct entry *update_hotspot_queue(struct smq_policy *mq, dm_oblock_t b, struct bio *bio)
{
	unsigned hi;
	dm_oblock_t hb = to_hblock(mq, b);
	struct entry *e = h_lookup(&mq->hotspot_table, hb);

	if (e) {
		stats_level_accessed(&mq->hotspot_stats, e->level);

		hi = get_index(&mq->hotspot_alloc, e);
		q_requeue(&mq->hotspot, e,
			  test_and_set_bit(hi, mq->hotspot_hit_bits) ?
			  0u : mq->hotspot_level_jump);

	} else {
		stats_miss(&mq->hotspot_stats);

		e = alloc_entry(&mq->hotspot_alloc);
		if (!e) {
			e = q_pop(&mq->hotspot);
			if (e) {
				h_remove(&mq->hotspot_table, e);
				hi = get_index(&mq->hotspot_alloc, e);
				clear_bit(hi, mq->hotspot_hit_bits);
			}

		}

		if (e) {
			e->oblock = hb;
			q_push(&mq->hotspot, e);
			h_insert(&mq->hotspot_table, e);
		}
	}

	return e;
}

/*
 * Looks the oblock up in the hash table, then decides whether to put in
 * pre_cache, or cache etc.
 */
static int map(struct smq_policy *mq, struct bio *bio, dm_oblock_t oblock,
	       bool can_migrate, bool fast_promote,
	       struct policy_locker *locker, struct policy_result *result)
{
	struct entry *e, *hs_e;
	enum promote_result pr;

	hs_e = update_hotspot_queue(mq, oblock, bio);

	e = h_lookup(&mq->table, oblock);
	if (e) {
		stats_level_accessed(&mq->cache_stats, e->level);

		requeue(mq, e);
		result->op = POLICY_HIT;
		result->cblock = infer_cblock(mq, e);

	} else {
		stats_miss(&mq->cache_stats);

		pr = should_promote(mq, hs_e, bio, fast_promote);
		if (pr == PROMOTE_NOT)
			result->op = POLICY_MISS;

		else {
			if (!can_migrate) {
				result->op = POLICY_MISS;
				return -EWOULDBLOCK;
			}

			insert_in_cache(mq, oblock, locker, result, pr);
		}
	}

	return 0;
}

/*----------------------------------------------------------------*/

/*
 * Public interface, via the policy struct.  See dm-cache-policy.h for a
 * description of these.
 */

static struct smq_policy *to_smq_policy(struct dm_cache_policy *p)
{
	return container_of(p, struct smq_policy, policy);
}

static void smq_destroy(struct dm_cache_policy *p)
{
	struct smq_policy *mq = to_smq_policy(p);

	h_exit(&mq->hotspot_table);
	h_exit(&mq->table);
	free_bitset(mq->hotspot_hit_bits);
	free_bitset(mq->cache_hit_bits);
	space_exit(&mq->es);
	kfree(mq);
}

static void copy_tick(struct smq_policy *mq)
{
	unsigned long flags, tick;

	spin_lock_irqsave(&mq->tick_lock, flags);
	tick = mq->tick_protected;
	if (tick != mq->tick) {
		update_sentinels(mq);
		end_hotspot_period(mq);
		end_cache_period(mq);
		mq->tick = tick;
	}
	spin_unlock_irqrestore(&mq->tick_lock, flags);
}

static bool maybe_lock(struct smq_policy *mq, bool can_block)
{
	if (can_block) {
		mutex_lock(&mq->lock);
		return true;
	} else
		return mutex_trylock(&mq->lock);
}

static int smq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
		   bool can_block, bool can_migrate, bool fast_promote,
		   struct bio *bio, struct policy_locker *locker,
		   struct policy_result *result)
{
	int r;
	struct smq_policy *mq = to_smq_policy(p);

	result->op = POLICY_MISS;

	if (!maybe_lock(mq, can_block))
		return -EWOULDBLOCK;

	copy_tick(mq);
	r = map(mq, bio, oblock, can_migrate, fast_promote, locker, result);
	mutex_unlock(&mq->lock);

	return r;
}

static int smq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
{
	int r;
	struct smq_policy *mq = to_smq_policy(p);
	struct entry *e;

	if (!mutex_trylock(&mq->lock))
		return -EWOULDBLOCK;

	e = h_lookup(&mq->table, oblock);
	if (e) {
		*cblock = infer_cblock(mq, e);
		r = 0;
	} else
		r = -ENOENT;

	mutex_unlock(&mq->lock);

	return r;
}

static void __smq_set_clear_dirty(struct smq_policy *mq, dm_oblock_t oblock, bool set)
{
	struct entry *e;

	e = h_lookup(&mq->table, oblock);
	BUG_ON(!e);

	del(mq, e);
	e->dirty = set;
	push(mq, e);
}

static void smq_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
{
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	__smq_set_clear_dirty(mq, oblock, true);
	mutex_unlock(&mq->lock);
}

static void smq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
{
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	__smq_set_clear_dirty(mq, oblock, false);
	mutex_unlock(&mq->lock);
}

static int smq_load_mapping(struct dm_cache_policy *p,
			    dm_oblock_t oblock, dm_cblock_t cblock,
			    uint32_t hint, bool hint_valid)
{
	struct smq_policy *mq = to_smq_policy(p);
	struct entry *e;

	e = alloc_particular_entry(&mq->cache_alloc, from_cblock(cblock));
	e->oblock = oblock;
	e->dirty = false;	/* this gets corrected in a minute */
	e->level = hint_valid ? min(hint, NR_CACHE_LEVELS - 1) : 1;
	push(mq, e);

	return 0;
}

static int smq_save_hints(struct smq_policy *mq, struct queue *q,
			  policy_walk_fn fn, void *context)
{
	int r;
	unsigned level;
	struct entry *e;

	for (level = 0; level < q->nr_levels; level++)
		for (e = l_head(q->es, q->qs + level); e; e = l_next(q->es, e)) {
			if (!e->sentinel) {
				r = fn(context, infer_cblock(mq, e),
				       e->oblock, e->level);
				if (r)
					return r;
			}
		}

	return 0;
}

static int smq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn,
			     void *context)
{
	struct smq_policy *mq = to_smq_policy(p);
	int r = 0;

	mutex_lock(&mq->lock);

	r = smq_save_hints(mq, &mq->clean, fn, context);
	if (!r)
		r = smq_save_hints(mq, &mq->dirty, fn, context);

	mutex_unlock(&mq->lock);

	return r;
}

static void __remove_mapping(struct smq_policy *mq, dm_oblock_t oblock)
{
	struct entry *e;

	e = h_lookup(&mq->table, oblock);
	BUG_ON(!e);

	del(mq, e);
	free_entry(&mq->cache_alloc, e);
}

static void smq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
{
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	__remove_mapping(mq, oblock);
	mutex_unlock(&mq->lock);
}

static int __remove_cblock(struct smq_policy *mq, dm_cblock_t cblock)
{
	struct entry *e = get_entry(&mq->cache_alloc, from_cblock(cblock));

	if (!e || !e->allocated)
		return -ENODATA;

	del(mq, e);
	free_entry(&mq->cache_alloc, e);

	return 0;
}

static int smq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock)
{
	int r;
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	r = __remove_cblock(mq, cblock);
	mutex_unlock(&mq->lock);

	return r;
}


#define CLEAN_TARGET_CRITICAL 5u /* percent */

static bool clean_target_met(struct smq_policy *mq, bool critical)
{
	if (critical) {
		/*
		 * Cache entries may not be populated.  So we're cannot rely on the
		 * size of the clean queue.
		 */
		unsigned nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty);
		unsigned target = from_cblock(mq->cache_size) * CLEAN_TARGET_CRITICAL / 100u;

		return nr_clean >= target;
	} else
		return !q_size(&mq->dirty);
}

static int __smq_writeback_work(struct smq_policy *mq, dm_oblock_t *oblock,
				dm_cblock_t *cblock, bool critical_only)
{
	struct entry *e = NULL;
	bool target_met = clean_target_met(mq, critical_only);

	if (critical_only)
		/*
		 * Always try and keep the bottom level clean.
		 */
		e = pop_old(mq, &mq->dirty, target_met ? 1u : mq->dirty.nr_levels);

	else
		e = pop_old(mq, &mq->dirty, mq->dirty.nr_levels);

	if (!e)
		return -ENODATA;

	*oblock = e->oblock;
	*cblock = infer_cblock(mq, e);
	e->dirty = false;
	push_new(mq, e);

	return 0;
}

static int smq_writeback_work(struct dm_cache_policy *p, dm_oblock_t *oblock,
			      dm_cblock_t *cblock, bool critical_only)
{
	int r;
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	r = __smq_writeback_work(mq, oblock, cblock, critical_only);
	mutex_unlock(&mq->lock);

	return r;
}

static void __force_mapping(struct smq_policy *mq,
			    dm_oblock_t current_oblock, dm_oblock_t new_oblock)
{
	struct entry *e = h_lookup(&mq->table, current_oblock);

	if (e) {
		del(mq, e);
		e->oblock = new_oblock;
		e->dirty = true;
		push(mq, e);
	}
}

static void smq_force_mapping(struct dm_cache_policy *p,
			      dm_oblock_t current_oblock, dm_oblock_t new_oblock)
{
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	__force_mapping(mq, current_oblock, new_oblock);
	mutex_unlock(&mq->lock);
}

static dm_cblock_t smq_residency(struct dm_cache_policy *p)
{
	dm_cblock_t r;
	struct smq_policy *mq = to_smq_policy(p);

	mutex_lock(&mq->lock);
	r = to_cblock(mq->cache_alloc.nr_allocated);
	mutex_unlock(&mq->lock);

	return r;
}

static void smq_tick(struct dm_cache_policy *p, bool can_block)
{
	struct smq_policy *mq = to_smq_policy(p);
	unsigned long flags;

	spin_lock_irqsave(&mq->tick_lock, flags);
	mq->tick_protected++;
	spin_unlock_irqrestore(&mq->tick_lock, flags);

	if (can_block) {
		mutex_lock(&mq->lock);
		copy_tick(mq);
		mutex_unlock(&mq->lock);
	}
}

/* Init the policy plugin interface function pointers. */
static void init_policy_functions(struct smq_policy *mq)
{
	mq->policy.destroy = smq_destroy;
	mq->policy.map = smq_map;
	mq->policy.lookup = smq_lookup;
	mq->policy.set_dirty = smq_set_dirty;
	mq->policy.clear_dirty = smq_clear_dirty;
	mq->policy.load_mapping = smq_load_mapping;
	mq->policy.walk_mappings = smq_walk_mappings;
	mq->policy.remove_mapping = smq_remove_mapping;
	mq->policy.remove_cblock = smq_remove_cblock;
	mq->policy.writeback_work = smq_writeback_work;
	mq->policy.force_mapping = smq_force_mapping;
	mq->policy.residency = smq_residency;
	mq->policy.tick = smq_tick;
}

static bool too_many_hotspot_blocks(sector_t origin_size,
				    sector_t hotspot_block_size,
				    unsigned nr_hotspot_blocks)
{
	return (hotspot_block_size * nr_hotspot_blocks) > origin_size;
}

static void calc_hotspot_params(sector_t origin_size,
				sector_t cache_block_size,
				unsigned nr_cache_blocks,
				sector_t *hotspot_block_size,
				unsigned *nr_hotspot_blocks)
{
	*hotspot_block_size = cache_block_size * 16u;
	*nr_hotspot_blocks = max(nr_cache_blocks / 4u, 1024u);

	while ((*hotspot_block_size > cache_block_size) &&
	       too_many_hotspot_blocks(origin_size, *hotspot_block_size, *nr_hotspot_blocks))
		*hotspot_block_size /= 2u;
}

static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
					  sector_t origin_size,
					  sector_t cache_block_size)
{
	unsigned i;
	unsigned nr_sentinels_per_queue = 2u * NR_CACHE_LEVELS;
	unsigned total_sentinels = 2u * nr_sentinels_per_queue;
	struct smq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL);

	if (!mq)
		return NULL;

	init_policy_functions(mq);
	mq->cache_size = cache_size;
	mq->cache_block_size = cache_block_size;

	calc_hotspot_params(origin_size, cache_block_size, from_cblock(cache_size),
			    &mq->hotspot_block_size, &mq->nr_hotspot_blocks);

	mq->cache_blocks_per_hotspot_block = div64_u64(mq->hotspot_block_size, mq->cache_block_size);
	mq->hotspot_level_jump = 1u;
	if (space_init(&mq->es, total_sentinels + mq->nr_hotspot_blocks + from_cblock(cache_size))) {
		DMERR("couldn't initialize entry space");
		goto bad_pool_init;
	}

	init_allocator(&mq->writeback_sentinel_alloc, &mq->es, 0, nr_sentinels_per_queue);
        for (i = 0; i < nr_sentinels_per_queue; i++)
		get_entry(&mq->writeback_sentinel_alloc, i)->sentinel = true;

	init_allocator(&mq->demote_sentinel_alloc, &mq->es, nr_sentinels_per_queue, total_sentinels);
        for (i = 0; i < nr_sentinels_per_queue; i++)
		get_entry(&mq->demote_sentinel_alloc, i)->sentinel = true;

	init_allocator(&mq->hotspot_alloc, &mq->es, total_sentinels,
		       total_sentinels + mq->nr_hotspot_blocks);

	init_allocator(&mq->cache_alloc, &mq->es,
		       total_sentinels + mq->nr_hotspot_blocks,
		       total_sentinels + mq->nr_hotspot_blocks + from_cblock(cache_size));

	mq->hotspot_hit_bits = alloc_bitset(mq->nr_hotspot_blocks);
	if (!mq->hotspot_hit_bits) {
		DMERR("couldn't allocate hotspot hit bitset");
		goto bad_hotspot_hit_bits;
	}
	clear_bitset(mq->hotspot_hit_bits, mq->nr_hotspot_blocks);

	if (from_cblock(cache_size)) {
		mq->cache_hit_bits = alloc_bitset(from_cblock(cache_size));
		if (!mq->cache_hit_bits) {
			DMERR("couldn't allocate cache hit bitset");
			goto bad_cache_hit_bits;
		}
		clear_bitset(mq->cache_hit_bits, from_cblock(mq->cache_size));
	} else
		mq->cache_hit_bits = NULL;

	mq->tick_protected = 0;
	mq->tick = 0;
	mutex_init(&mq->lock);
	spin_lock_init(&mq->tick_lock);

	q_init(&mq->hotspot, &mq->es, NR_HOTSPOT_LEVELS);
	mq->hotspot.nr_top_levels = 8;
	mq->hotspot.nr_in_top_levels = min(mq->nr_hotspot_blocks / NR_HOTSPOT_LEVELS,
					   from_cblock(mq->cache_size) / mq->cache_blocks_per_hotspot_block);

	q_init(&mq->clean, &mq->es, NR_CACHE_LEVELS);
	q_init(&mq->dirty, &mq->es, NR_CACHE_LEVELS);

	stats_init(&mq->hotspot_stats, NR_HOTSPOT_LEVELS);
	stats_init(&mq->cache_stats, NR_CACHE_LEVELS);

	if (h_init(&mq->table, &mq->es, from_cblock(cache_size)))
		goto bad_alloc_table;

	if (h_init(&mq->hotspot_table, &mq->es, mq->nr_hotspot_blocks))
		goto bad_alloc_hotspot_table;

	sentinels_init(mq);
	mq->write_promote_level = mq->read_promote_level = NR_HOTSPOT_LEVELS;

	mq->next_hotspot_period = jiffies;
	mq->next_cache_period = jiffies;

	return &mq->policy;

bad_alloc_hotspot_table:
	h_exit(&mq->table);
bad_alloc_table:
	free_bitset(mq->cache_hit_bits);
bad_cache_hit_bits:
	free_bitset(mq->hotspot_hit_bits);
bad_hotspot_hit_bits:
	space_exit(&mq->es);
bad_pool_init:
	kfree(mq);

	return NULL;
}

/*----------------------------------------------------------------*/

static struct dm_cache_policy_type smq_policy_type = {
	.name = "smq",
	.version = {1, 0, 0},
	.hint_size = 4,
	.owner = THIS_MODULE,
	.create = smq_create
};

static struct dm_cache_policy_type default_policy_type = {
	.name = "default",
	.version = {1, 4, 0},
	.hint_size = 4,
	.owner = THIS_MODULE,
	.create = smq_create,
	.real = &smq_policy_type
};

static int __init smq_init(void)
{
	int r;

	r = dm_cache_policy_register(&smq_policy_type);
	if (r) {
		DMERR("register failed %d", r);
		return -ENOMEM;
	}

	r = dm_cache_policy_register(&default_policy_type);
	if (r) {
		DMERR("register failed (as default) %d", r);
		dm_cache_policy_unregister(&smq_policy_type);
		return -ENOMEM;
	}

	return 0;
}

static void __exit smq_exit(void)
{
	dm_cache_policy_unregister(&smq_policy_type);
	dm_cache_policy_unregister(&default_policy_type);
}

module_init(smq_init);
module_exit(smq_exit);

MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("smq cache policy");