summaryrefslogtreecommitdiff
path: root/mm/damon/core.c
blob: 939ecfcd4641f27593f43dc3a15665ceaf6c37aa (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
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
// SPDX-License-Identifier: GPL-2.0
/*
 * Data Access Monitor
 *
 * Author: SeongJae Park <sj@kernel.org>
 */

#define pr_fmt(fmt) "damon: " fmt

#include <linux/damon.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/mm.h>
#include <linux/psi.h>
#include <linux/slab.h>
#include <linux/string.h>

#define CREATE_TRACE_POINTS
#include <trace/events/damon.h>

#ifdef CONFIG_DAMON_KUNIT_TEST
#undef DAMON_MIN_REGION
#define DAMON_MIN_REGION 1
#endif

static DEFINE_MUTEX(damon_lock);
static int nr_running_ctxs;
static bool running_exclusive_ctxs;

static DEFINE_MUTEX(damon_ops_lock);
static struct damon_operations damon_registered_ops[NR_DAMON_OPS];

static struct kmem_cache *damon_region_cache __ro_after_init;

/* Should be called under damon_ops_lock with id smaller than NR_DAMON_OPS */
static bool __damon_is_registered_ops(enum damon_ops_id id)
{
	struct damon_operations empty_ops = {};

	if (!memcmp(&empty_ops, &damon_registered_ops[id], sizeof(empty_ops)))
		return false;
	return true;
}

/**
 * damon_is_registered_ops() - Check if a given damon_operations is registered.
 * @id:	Id of the damon_operations to check if registered.
 *
 * Return: true if the ops is set, false otherwise.
 */
bool damon_is_registered_ops(enum damon_ops_id id)
{
	bool registered;

	if (id >= NR_DAMON_OPS)
		return false;
	mutex_lock(&damon_ops_lock);
	registered = __damon_is_registered_ops(id);
	mutex_unlock(&damon_ops_lock);
	return registered;
}

/**
 * damon_register_ops() - Register a monitoring operations set to DAMON.
 * @ops:	monitoring operations set to register.
 *
 * This function registers a monitoring operations set of valid &struct
 * damon_operations->id so that others can find and use them later.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_register_ops(struct damon_operations *ops)
{
	int err = 0;

	if (ops->id >= NR_DAMON_OPS)
		return -EINVAL;
	mutex_lock(&damon_ops_lock);
	/* Fail for already registered ops */
	if (__damon_is_registered_ops(ops->id)) {
		err = -EINVAL;
		goto out;
	}
	damon_registered_ops[ops->id] = *ops;
out:
	mutex_unlock(&damon_ops_lock);
	return err;
}

/**
 * damon_select_ops() - Select a monitoring operations to use with the context.
 * @ctx:	monitoring context to use the operations.
 * @id:		id of the registered monitoring operations to select.
 *
 * This function finds registered monitoring operations set of @id and make
 * @ctx to use it.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id)
{
	int err = 0;

	if (id >= NR_DAMON_OPS)
		return -EINVAL;

	mutex_lock(&damon_ops_lock);
	if (!__damon_is_registered_ops(id))
		err = -EINVAL;
	else
		ctx->ops = damon_registered_ops[id];
	mutex_unlock(&damon_ops_lock);
	return err;
}

/*
 * Construct a damon_region struct
 *
 * Returns the pointer to the new struct if success, or NULL otherwise
 */
struct damon_region *damon_new_region(unsigned long start, unsigned long end)
{
	struct damon_region *region;

	region = kmem_cache_alloc(damon_region_cache, GFP_KERNEL);
	if (!region)
		return NULL;

	region->ar.start = start;
	region->ar.end = end;
	region->nr_accesses = 0;
	region->nr_accesses_bp = 0;
	INIT_LIST_HEAD(&region->list);

	region->age = 0;
	region->last_nr_accesses = 0;

	return region;
}

void damon_add_region(struct damon_region *r, struct damon_target *t)
{
	list_add_tail(&r->list, &t->regions_list);
	t->nr_regions++;
}

static void damon_del_region(struct damon_region *r, struct damon_target *t)
{
	list_del(&r->list);
	t->nr_regions--;
}

static void damon_free_region(struct damon_region *r)
{
	kmem_cache_free(damon_region_cache, r);
}

void damon_destroy_region(struct damon_region *r, struct damon_target *t)
{
	damon_del_region(r, t);
	damon_free_region(r);
}

/*
 * Check whether a region is intersecting an address range
 *
 * Returns true if it is.
 */
static bool damon_intersect(struct damon_region *r,
		struct damon_addr_range *re)
{
	return !(r->ar.end <= re->start || re->end <= r->ar.start);
}

/*
 * Fill holes in regions with new regions.
 */
static int damon_fill_regions_holes(struct damon_region *first,
		struct damon_region *last, struct damon_target *t)
{
	struct damon_region *r = first;

	damon_for_each_region_from(r, t) {
		struct damon_region *next, *newr;

		if (r == last)
			break;
		next = damon_next_region(r);
		if (r->ar.end != next->ar.start) {
			newr = damon_new_region(r->ar.end, next->ar.start);
			if (!newr)
				return -ENOMEM;
			damon_insert_region(newr, r, next, t);
		}
	}
	return 0;
}

/*
 * damon_set_regions() - Set regions of a target for given address ranges.
 * @t:		the given target.
 * @ranges:	array of new monitoring target ranges.
 * @nr_ranges:	length of @ranges.
 *
 * This function adds new regions to, or modify existing regions of a
 * monitoring target to fit in specific ranges.
 *
 * Return: 0 if success, or negative error code otherwise.
 */
int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
		unsigned int nr_ranges)
{
	struct damon_region *r, *next;
	unsigned int i;
	int err;

	/* Remove regions which are not in the new ranges */
	damon_for_each_region_safe(r, next, t) {
		for (i = 0; i < nr_ranges; i++) {
			if (damon_intersect(r, &ranges[i]))
				break;
		}
		if (i == nr_ranges)
			damon_destroy_region(r, t);
	}

	r = damon_first_region(t);
	/* Add new regions or resize existing regions to fit in the ranges */
	for (i = 0; i < nr_ranges; i++) {
		struct damon_region *first = NULL, *last, *newr;
		struct damon_addr_range *range;

		range = &ranges[i];
		/* Get the first/last regions intersecting with the range */
		damon_for_each_region_from(r, t) {
			if (damon_intersect(r, range)) {
				if (!first)
					first = r;
				last = r;
			}
			if (r->ar.start >= range->end)
				break;
		}
		if (!first) {
			/* no region intersects with this range */
			newr = damon_new_region(
					ALIGN_DOWN(range->start,
						DAMON_MIN_REGION),
					ALIGN(range->end, DAMON_MIN_REGION));
			if (!newr)
				return -ENOMEM;
			damon_insert_region(newr, damon_prev_region(r), r, t);
		} else {
			/* resize intersecting regions to fit in this range */
			first->ar.start = ALIGN_DOWN(range->start,
					DAMON_MIN_REGION);
			last->ar.end = ALIGN(range->end, DAMON_MIN_REGION);

			/* fill possible holes in the range */
			err = damon_fill_regions_holes(first, last, t);
			if (err)
				return err;
		}
	}
	return 0;
}

struct damos_filter *damos_new_filter(enum damos_filter_type type,
		bool matching)
{
	struct damos_filter *filter;

	filter = kmalloc(sizeof(*filter), GFP_KERNEL);
	if (!filter)
		return NULL;
	filter->type = type;
	filter->matching = matching;
	INIT_LIST_HEAD(&filter->list);
	return filter;
}

void damos_add_filter(struct damos *s, struct damos_filter *f)
{
	list_add_tail(&f->list, &s->filters);
}

static void damos_del_filter(struct damos_filter *f)
{
	list_del(&f->list);
}

static void damos_free_filter(struct damos_filter *f)
{
	kfree(f);
}

void damos_destroy_filter(struct damos_filter *f)
{
	damos_del_filter(f);
	damos_free_filter(f);
}

struct damos_quota_goal *damos_new_quota_goal(
		enum damos_quota_goal_metric metric,
		unsigned long target_value)
{
	struct damos_quota_goal *goal;

	goal = kmalloc(sizeof(*goal), GFP_KERNEL);
	if (!goal)
		return NULL;
	goal->metric = metric;
	goal->target_value = target_value;
	INIT_LIST_HEAD(&goal->list);
	return goal;
}

void damos_add_quota_goal(struct damos_quota *q, struct damos_quota_goal *g)
{
	list_add_tail(&g->list, &q->goals);
}

static void damos_del_quota_goal(struct damos_quota_goal *g)
{
	list_del(&g->list);
}

static void damos_free_quota_goal(struct damos_quota_goal *g)
{
	kfree(g);
}

void damos_destroy_quota_goal(struct damos_quota_goal *g)
{
	damos_del_quota_goal(g);
	damos_free_quota_goal(g);
}

/* initialize fields of @quota that normally API users wouldn't set */
static struct damos_quota *damos_quota_init(struct damos_quota *quota)
{
	quota->esz = 0;
	quota->total_charged_sz = 0;
	quota->total_charged_ns = 0;
	quota->charged_sz = 0;
	quota->charged_from = 0;
	quota->charge_target_from = NULL;
	quota->charge_addr_from = 0;
	quota->esz_bp = 0;
	return quota;
}

struct damos *damon_new_scheme(struct damos_access_pattern *pattern,
			enum damos_action action,
			unsigned long apply_interval_us,
			struct damos_quota *quota,
			struct damos_watermarks *wmarks)
{
	struct damos *scheme;

	scheme = kmalloc(sizeof(*scheme), GFP_KERNEL);
	if (!scheme)
		return NULL;
	scheme->pattern = *pattern;
	scheme->action = action;
	scheme->apply_interval_us = apply_interval_us;
	/*
	 * next_apply_sis will be set when kdamond starts.  While kdamond is
	 * running, it will also updated when it is added to the DAMON context,
	 * or damon_attrs are updated.
	 */
	scheme->next_apply_sis = 0;
	INIT_LIST_HEAD(&scheme->filters);
	scheme->stat = (struct damos_stat){};
	INIT_LIST_HEAD(&scheme->list);

	scheme->quota = *(damos_quota_init(quota));
	/* quota.goals should be separately set by caller */
	INIT_LIST_HEAD(&scheme->quota.goals);

	scheme->wmarks = *wmarks;
	scheme->wmarks.activated = true;

	return scheme;
}

static void damos_set_next_apply_sis(struct damos *s, struct damon_ctx *ctx)
{
	unsigned long sample_interval = ctx->attrs.sample_interval ?
		ctx->attrs.sample_interval : 1;
	unsigned long apply_interval = s->apply_interval_us ?
		s->apply_interval_us : ctx->attrs.aggr_interval;

	s->next_apply_sis = ctx->passed_sample_intervals +
		apply_interval / sample_interval;
}

void damon_add_scheme(struct damon_ctx *ctx, struct damos *s)
{
	list_add_tail(&s->list, &ctx->schemes);
	damos_set_next_apply_sis(s, ctx);
}

static void damon_del_scheme(struct damos *s)
{
	list_del(&s->list);
}

static void damon_free_scheme(struct damos *s)
{
	kfree(s);
}

void damon_destroy_scheme(struct damos *s)
{
	struct damos_quota_goal *g, *g_next;
	struct damos_filter *f, *next;

	damos_for_each_quota_goal_safe(g, g_next, &s->quota)
		damos_destroy_quota_goal(g);

	damos_for_each_filter_safe(f, next, s)
		damos_destroy_filter(f);
	damon_del_scheme(s);
	damon_free_scheme(s);
}

/*
 * Construct a damon_target struct
 *
 * Returns the pointer to the new struct if success, or NULL otherwise
 */
struct damon_target *damon_new_target(void)
{
	struct damon_target *t;

	t = kmalloc(sizeof(*t), GFP_KERNEL);
	if (!t)
		return NULL;

	t->pid = NULL;
	t->nr_regions = 0;
	INIT_LIST_HEAD(&t->regions_list);
	INIT_LIST_HEAD(&t->list);

	return t;
}

void damon_add_target(struct damon_ctx *ctx, struct damon_target *t)
{
	list_add_tail(&t->list, &ctx->adaptive_targets);
}

bool damon_targets_empty(struct damon_ctx *ctx)
{
	return list_empty(&ctx->adaptive_targets);
}

static void damon_del_target(struct damon_target *t)
{
	list_del(&t->list);
}

void damon_free_target(struct damon_target *t)
{
	struct damon_region *r, *next;

	damon_for_each_region_safe(r, next, t)
		damon_free_region(r);
	kfree(t);
}

void damon_destroy_target(struct damon_target *t)
{
	damon_del_target(t);
	damon_free_target(t);
}

unsigned int damon_nr_regions(struct damon_target *t)
{
	return t->nr_regions;
}

struct damon_ctx *damon_new_ctx(void)
{
	struct damon_ctx *ctx;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return NULL;

	init_completion(&ctx->kdamond_started);

	ctx->attrs.sample_interval = 5 * 1000;
	ctx->attrs.aggr_interval = 100 * 1000;
	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;

	ctx->passed_sample_intervals = 0;
	/* These will be set from kdamond_init_intervals_sis() */
	ctx->next_aggregation_sis = 0;
	ctx->next_ops_update_sis = 0;

	mutex_init(&ctx->kdamond_lock);

	ctx->attrs.min_nr_regions = 10;
	ctx->attrs.max_nr_regions = 1000;

	INIT_LIST_HEAD(&ctx->adaptive_targets);
	INIT_LIST_HEAD(&ctx->schemes);

	return ctx;
}

static void damon_destroy_targets(struct damon_ctx *ctx)
{
	struct damon_target *t, *next_t;

	if (ctx->ops.cleanup) {
		ctx->ops.cleanup(ctx);
		return;
	}

	damon_for_each_target_safe(t, next_t, ctx)
		damon_destroy_target(t);
}

void damon_destroy_ctx(struct damon_ctx *ctx)
{
	struct damos *s, *next_s;

	damon_destroy_targets(ctx);

	damon_for_each_scheme_safe(s, next_s, ctx)
		damon_destroy_scheme(s);

	kfree(ctx);
}

static unsigned int damon_age_for_new_attrs(unsigned int age,
		struct damon_attrs *old_attrs, struct damon_attrs *new_attrs)
{
	return age * old_attrs->aggr_interval / new_attrs->aggr_interval;
}

/* convert access ratio in bp (per 10,000) to nr_accesses */
static unsigned int damon_accesses_bp_to_nr_accesses(
		unsigned int accesses_bp, struct damon_attrs *attrs)
{
	return accesses_bp * damon_max_nr_accesses(attrs) / 10000;
}

/* convert nr_accesses to access ratio in bp (per 10,000) */
static unsigned int damon_nr_accesses_to_accesses_bp(
		unsigned int nr_accesses, struct damon_attrs *attrs)
{
	return nr_accesses * 10000 / damon_max_nr_accesses(attrs);
}

static unsigned int damon_nr_accesses_for_new_attrs(unsigned int nr_accesses,
		struct damon_attrs *old_attrs, struct damon_attrs *new_attrs)
{
	return damon_accesses_bp_to_nr_accesses(
			damon_nr_accesses_to_accesses_bp(
				nr_accesses, old_attrs),
			new_attrs);
}

static void damon_update_monitoring_result(struct damon_region *r,
		struct damon_attrs *old_attrs, struct damon_attrs *new_attrs)
{
	r->nr_accesses = damon_nr_accesses_for_new_attrs(r->nr_accesses,
			old_attrs, new_attrs);
	r->nr_accesses_bp = r->nr_accesses * 10000;
	r->age = damon_age_for_new_attrs(r->age, old_attrs, new_attrs);
}

/*
 * region->nr_accesses is the number of sampling intervals in the last
 * aggregation interval that access to the region has found, and region->age is
 * the number of aggregation intervals that its access pattern has maintained.
 * For the reason, the real meaning of the two fields depend on current
 * sampling interval and aggregation interval.  This function updates
 * ->nr_accesses and ->age of given damon_ctx's regions for new damon_attrs.
 */
static void damon_update_monitoring_results(struct damon_ctx *ctx,
		struct damon_attrs *new_attrs)
{
	struct damon_attrs *old_attrs = &ctx->attrs;
	struct damon_target *t;
	struct damon_region *r;

	/* if any interval is zero, simply forgive conversion */
	if (!old_attrs->sample_interval || !old_attrs->aggr_interval ||
			!new_attrs->sample_interval ||
			!new_attrs->aggr_interval)
		return;

	damon_for_each_target(t, ctx)
		damon_for_each_region(r, t)
			damon_update_monitoring_result(
					r, old_attrs, new_attrs);
}

/**
 * damon_set_attrs() - Set attributes for the monitoring.
 * @ctx:		monitoring context
 * @attrs:		monitoring attributes
 *
 * This function should be called while the kdamond is not running, or an
 * access check results aggregation is not ongoing (e.g., from
 * &struct damon_callback->after_aggregation or
 * &struct damon_callback->after_wmarks_check callbacks).
 *
 * Every time interval is in micro-seconds.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs)
{
	unsigned long sample_interval = attrs->sample_interval ?
		attrs->sample_interval : 1;
	struct damos *s;

	if (attrs->min_nr_regions < 3)
		return -EINVAL;
	if (attrs->min_nr_regions > attrs->max_nr_regions)
		return -EINVAL;
	if (attrs->sample_interval > attrs->aggr_interval)
		return -EINVAL;

	ctx->next_aggregation_sis = ctx->passed_sample_intervals +
		attrs->aggr_interval / sample_interval;
	ctx->next_ops_update_sis = ctx->passed_sample_intervals +
		attrs->ops_update_interval / sample_interval;

	damon_update_monitoring_results(ctx, attrs);
	ctx->attrs = *attrs;

	damon_for_each_scheme(s, ctx)
		damos_set_next_apply_sis(s, ctx);

	return 0;
}

/**
 * damon_set_schemes() - Set data access monitoring based operation schemes.
 * @ctx:	monitoring context
 * @schemes:	array of the schemes
 * @nr_schemes:	number of entries in @schemes
 *
 * This function should not be called while the kdamond of the context is
 * running.
 */
void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes,
			ssize_t nr_schemes)
{
	struct damos *s, *next;
	ssize_t i;

	damon_for_each_scheme_safe(s, next, ctx)
		damon_destroy_scheme(s);
	for (i = 0; i < nr_schemes; i++)
		damon_add_scheme(ctx, schemes[i]);
}

/**
 * damon_nr_running_ctxs() - Return number of currently running contexts.
 */
int damon_nr_running_ctxs(void)
{
	int nr_ctxs;

	mutex_lock(&damon_lock);
	nr_ctxs = nr_running_ctxs;
	mutex_unlock(&damon_lock);

	return nr_ctxs;
}

/* Returns the size upper limit for each monitoring region */
static unsigned long damon_region_sz_limit(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct damon_region *r;
	unsigned long sz = 0;

	damon_for_each_target(t, ctx) {
		damon_for_each_region(r, t)
			sz += damon_sz_region(r);
	}

	if (ctx->attrs.min_nr_regions)
		sz /= ctx->attrs.min_nr_regions;
	if (sz < DAMON_MIN_REGION)
		sz = DAMON_MIN_REGION;

	return sz;
}

static int kdamond_fn(void *data);

/*
 * __damon_start() - Starts monitoring with given context.
 * @ctx:	monitoring context
 *
 * This function should be called while damon_lock is hold.
 *
 * Return: 0 on success, negative error code otherwise.
 */
static int __damon_start(struct damon_ctx *ctx)
{
	int err = -EBUSY;

	mutex_lock(&ctx->kdamond_lock);
	if (!ctx->kdamond) {
		err = 0;
		reinit_completion(&ctx->kdamond_started);
		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
				nr_running_ctxs);
		if (IS_ERR(ctx->kdamond)) {
			err = PTR_ERR(ctx->kdamond);
			ctx->kdamond = NULL;
		} else {
			wait_for_completion(&ctx->kdamond_started);
		}
	}
	mutex_unlock(&ctx->kdamond_lock);

	return err;
}

/**
 * damon_start() - Starts the monitorings for a given group of contexts.
 * @ctxs:	an array of the pointers for contexts to start monitoring
 * @nr_ctxs:	size of @ctxs
 * @exclusive:	exclusiveness of this contexts group
 *
 * This function starts a group of monitoring threads for a group of monitoring
 * contexts.  One thread per each context is created and run in parallel.  The
 * caller should handle synchronization between the threads by itself.  If
 * @exclusive is true and a group of threads that created by other
 * 'damon_start()' call is currently running, this function does nothing but
 * returns -EBUSY.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive)
{
	int i;
	int err = 0;

	mutex_lock(&damon_lock);
	if ((exclusive && nr_running_ctxs) ||
			(!exclusive && running_exclusive_ctxs)) {
		mutex_unlock(&damon_lock);
		return -EBUSY;
	}

	for (i = 0; i < nr_ctxs; i++) {
		err = __damon_start(ctxs[i]);
		if (err)
			break;
		nr_running_ctxs++;
	}
	if (exclusive && nr_running_ctxs)
		running_exclusive_ctxs = true;
	mutex_unlock(&damon_lock);

	return err;
}

/*
 * __damon_stop() - Stops monitoring of a given context.
 * @ctx:	monitoring context
 *
 * Return: 0 on success, negative error code otherwise.
 */
static int __damon_stop(struct damon_ctx *ctx)
{
	struct task_struct *tsk;

	mutex_lock(&ctx->kdamond_lock);
	tsk = ctx->kdamond;
	if (tsk) {
		get_task_struct(tsk);
		mutex_unlock(&ctx->kdamond_lock);
		kthread_stop_put(tsk);
		return 0;
	}
	mutex_unlock(&ctx->kdamond_lock);

	return -EPERM;
}

/**
 * damon_stop() - Stops the monitorings for a given group of contexts.
 * @ctxs:	an array of the pointers for contexts to stop monitoring
 * @nr_ctxs:	size of @ctxs
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_stop(struct damon_ctx **ctxs, int nr_ctxs)
{
	int i, err = 0;

	for (i = 0; i < nr_ctxs; i++) {
		/* nr_running_ctxs is decremented in kdamond_fn */
		err = __damon_stop(ctxs[i]);
		if (err)
			break;
	}
	return err;
}

/*
 * Reset the aggregated monitoring results ('nr_accesses' of each region).
 */
static void kdamond_reset_aggregated(struct damon_ctx *c)
{
	struct damon_target *t;
	unsigned int ti = 0;	/* target's index */

	damon_for_each_target(t, c) {
		struct damon_region *r;

		damon_for_each_region(r, t) {
			trace_damon_aggregated(ti, r, damon_nr_regions(t));
			r->last_nr_accesses = r->nr_accesses;
			r->nr_accesses = 0;
		}
		ti++;
	}
}

static void damon_split_region_at(struct damon_target *t,
				  struct damon_region *r, unsigned long sz_r);

static bool __damos_valid_target(struct damon_region *r, struct damos *s)
{
	unsigned long sz;
	unsigned int nr_accesses = r->nr_accesses_bp / 10000;

	sz = damon_sz_region(r);
	return s->pattern.min_sz_region <= sz &&
		sz <= s->pattern.max_sz_region &&
		s->pattern.min_nr_accesses <= nr_accesses &&
		nr_accesses <= s->pattern.max_nr_accesses &&
		s->pattern.min_age_region <= r->age &&
		r->age <= s->pattern.max_age_region;
}

static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t,
		struct damon_region *r, struct damos *s)
{
	bool ret = __damos_valid_target(r, s);

	if (!ret || !s->quota.esz || !c->ops.get_scheme_score)
		return ret;

	return c->ops.get_scheme_score(c, t, r, s) >= s->quota.min_score;
}

/*
 * damos_skip_charged_region() - Check if the given region or starting part of
 * it is already charged for the DAMOS quota.
 * @t:	The target of the region.
 * @rp:	The pointer to the region.
 * @s:	The scheme to be applied.
 *
 * If a quota of a scheme has exceeded in a quota charge window, the scheme's
 * action would applied to only a part of the target access pattern fulfilling
 * regions.  To avoid applying the scheme action to only already applied
 * regions, DAMON skips applying the scheme action to the regions that charged
 * in the previous charge window.
 *
 * This function checks if a given region should be skipped or not for the
 * reason.  If only the starting part of the region has previously charged,
 * this function splits the region into two so that the second one covers the
 * area that not charged in the previous charge widnow and saves the second
 * region in *rp and returns false, so that the caller can apply DAMON action
 * to the second one.
 *
 * Return: true if the region should be entirely skipped, false otherwise.
 */
static bool damos_skip_charged_region(struct damon_target *t,
		struct damon_region **rp, struct damos *s)
{
	struct damon_region *r = *rp;
	struct damos_quota *quota = &s->quota;
	unsigned long sz_to_skip;

	/* Skip previously charged regions */
	if (quota->charge_target_from) {
		if (t != quota->charge_target_from)
			return true;
		if (r == damon_last_region(t)) {
			quota->charge_target_from = NULL;
			quota->charge_addr_from = 0;
			return true;
		}
		if (quota->charge_addr_from &&
				r->ar.end <= quota->charge_addr_from)
			return true;

		if (quota->charge_addr_from && r->ar.start <
				quota->charge_addr_from) {
			sz_to_skip = ALIGN_DOWN(quota->charge_addr_from -
					r->ar.start, DAMON_MIN_REGION);
			if (!sz_to_skip) {
				if (damon_sz_region(r) <= DAMON_MIN_REGION)
					return true;
				sz_to_skip = DAMON_MIN_REGION;
			}
			damon_split_region_at(t, r, sz_to_skip);
			r = damon_next_region(r);
			*rp = r;
		}
		quota->charge_target_from = NULL;
		quota->charge_addr_from = 0;
	}
	return false;
}

static void damos_update_stat(struct damos *s,
		unsigned long sz_tried, unsigned long sz_applied)
{
	s->stat.nr_tried++;
	s->stat.sz_tried += sz_tried;
	if (sz_applied)
		s->stat.nr_applied++;
	s->stat.sz_applied += sz_applied;
}

static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
		struct damon_region *r, struct damos_filter *filter)
{
	bool matched = false;
	struct damon_target *ti;
	int target_idx = 0;
	unsigned long start, end;

	switch (filter->type) {
	case DAMOS_FILTER_TYPE_TARGET:
		damon_for_each_target(ti, ctx) {
			if (ti == t)
				break;
			target_idx++;
		}
		matched = target_idx == filter->target_idx;
		break;
	case DAMOS_FILTER_TYPE_ADDR:
		start = ALIGN_DOWN(filter->addr_range.start, DAMON_MIN_REGION);
		end = ALIGN_DOWN(filter->addr_range.end, DAMON_MIN_REGION);

		/* inside the range */
		if (start <= r->ar.start && r->ar.end <= end) {
			matched = true;
			break;
		}
		/* outside of the range */
		if (r->ar.end <= start || end <= r->ar.start) {
			matched = false;
			break;
		}
		/* start before the range and overlap */
		if (r->ar.start < start) {
			damon_split_region_at(t, r, start - r->ar.start);
			matched = false;
			break;
		}
		/* start inside the range */
		damon_split_region_at(t, r, end - r->ar.start);
		matched = true;
		break;
	default:
		return false;
	}

	return matched == filter->matching;
}

static bool damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
		struct damon_region *r, struct damos *s)
{
	struct damos_filter *filter;

	damos_for_each_filter(filter, s) {
		if (__damos_filter_out(ctx, t, r, filter))
			return true;
	}
	return false;
}

static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
		struct damon_region *r, struct damos *s)
{
	struct damos_quota *quota = &s->quota;
	unsigned long sz = damon_sz_region(r);
	struct timespec64 begin, end;
	unsigned long sz_applied = 0;
	int err = 0;
	/*
	 * We plan to support multiple context per kdamond, as DAMON sysfs
	 * implies with 'nr_contexts' file.  Nevertheless, only single context
	 * per kdamond is supported for now.  So, we can simply use '0' context
	 * index here.
	 */
	unsigned int cidx = 0;
	struct damos *siter;		/* schemes iterator */
	unsigned int sidx = 0;
	struct damon_target *titer;	/* targets iterator */
	unsigned int tidx = 0;
	bool do_trace = false;

	/* get indices for trace_damos_before_apply() */
	if (trace_damos_before_apply_enabled()) {
		damon_for_each_scheme(siter, c) {
			if (siter == s)
				break;
			sidx++;
		}
		damon_for_each_target(titer, c) {
			if (titer == t)
				break;
			tidx++;
		}
		do_trace = true;
	}

	if (c->ops.apply_scheme) {
		if (quota->esz && quota->charged_sz + sz > quota->esz) {
			sz = ALIGN_DOWN(quota->esz - quota->charged_sz,
					DAMON_MIN_REGION);
			if (!sz)
				goto update_stat;
			damon_split_region_at(t, r, sz);
		}
		if (damos_filter_out(c, t, r, s))
			return;
		ktime_get_coarse_ts64(&begin);
		if (c->callback.before_damos_apply)
			err = c->callback.before_damos_apply(c, t, r, s);
		if (!err) {
			trace_damos_before_apply(cidx, sidx, tidx, r,
					damon_nr_regions(t), do_trace);
			sz_applied = c->ops.apply_scheme(c, t, r, s);
		}
		ktime_get_coarse_ts64(&end);
		quota->total_charged_ns += timespec64_to_ns(&end) -
			timespec64_to_ns(&begin);
		quota->charged_sz += sz;
		if (quota->esz && quota->charged_sz >= quota->esz) {
			quota->charge_target_from = t;
			quota->charge_addr_from = r->ar.end + 1;
		}
	}
	if (s->action != DAMOS_STAT)
		r->age = 0;

update_stat:
	damos_update_stat(s, sz, sz_applied);
}

static void damon_do_apply_schemes(struct damon_ctx *c,
				   struct damon_target *t,
				   struct damon_region *r)
{
	struct damos *s;

	damon_for_each_scheme(s, c) {
		struct damos_quota *quota = &s->quota;

		if (c->passed_sample_intervals != s->next_apply_sis)
			continue;

		if (!s->wmarks.activated)
			continue;

		/* Check the quota */
		if (quota->esz && quota->charged_sz >= quota->esz)
			continue;

		if (damos_skip_charged_region(t, &r, s))
			continue;

		if (!damos_valid_target(c, t, r, s))
			continue;

		damos_apply_scheme(c, t, r, s);
	}
}

/*
 * damon_feed_loop_next_input() - get next input to achieve a target score.
 * @last_input	The last input.
 * @score	Current score that made with @last_input.
 *
 * Calculate next input to achieve the target score, based on the last input
 * and current score.  Assuming the input and the score are positively
 * proportional, calculate how much compensation should be added to or
 * subtracted from the last input as a proportion of the last input.  Avoid
 * next input always being zero by setting it non-zero always.  In short form
 * (assuming support of float and signed calculations), the algorithm is as
 * below.
 *
 * next_input = max(last_input * ((goal - current) / goal + 1), 1)
 *
 * For simple implementation, we assume the target score is always 10,000.  The
 * caller should adjust @score for this.
 *
 * Returns next input that assumed to achieve the target score.
 */
static unsigned long damon_feed_loop_next_input(unsigned long last_input,
		unsigned long score)
{
	const unsigned long goal = 10000;
	unsigned long score_goal_diff = max(goal, score) - min(goal, score);
	unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal;
	unsigned long compensation = last_input * score_goal_diff_bp / 10000;
	/* Set minimum input as 10000 to avoid compensation be zero */
	const unsigned long min_input = 10000;

	if (goal > score)
		return last_input + compensation;
	if (last_input > compensation + min_input)
		return last_input - compensation;
	return min_input;
}

#ifdef CONFIG_PSI

static u64 damos_get_some_mem_psi_total(void)
{
	if (static_branch_likely(&psi_disabled))
		return 0;
	return div_u64(psi_system.total[PSI_AVGS][PSI_MEM * 2],
			NSEC_PER_USEC);
}

#else	/* CONFIG_PSI */

static inline u64 damos_get_some_mem_psi_total(void)
{
	return 0;
};

#endif	/* CONFIG_PSI */

static void damos_set_quota_goal_current_value(struct damos_quota_goal *goal)
{
	u64 now_psi_total;

	switch (goal->metric) {
	case DAMOS_QUOTA_USER_INPUT:
		/* User should already set goal->current_value */
		break;
	case DAMOS_QUOTA_SOME_MEM_PSI_US:
		now_psi_total = damos_get_some_mem_psi_total();
		goal->current_value = now_psi_total - goal->last_psi_total;
		goal->last_psi_total = now_psi_total;
		break;
	default:
		break;
	}
}

/* Return the highest score since it makes schemes least aggressive */
static unsigned long damos_quota_score(struct damos_quota *quota)
{
	struct damos_quota_goal *goal;
	unsigned long highest_score = 0;

	damos_for_each_quota_goal(goal, quota) {
		damos_set_quota_goal_current_value(goal);
		highest_score = max(highest_score,
				goal->current_value * 10000 /
				goal->target_value);
	}

	return highest_score;
}

/*
 * Called only if quota->ms, or quota->sz are set, or quota->goals is not empty
 */
static void damos_set_effective_quota(struct damos_quota *quota)
{
	unsigned long throughput;
	unsigned long esz;

	if (!quota->ms && list_empty(&quota->goals)) {
		quota->esz = quota->sz;
		return;
	}

	if (!list_empty(&quota->goals)) {
		unsigned long score = damos_quota_score(quota);

		quota->esz_bp = damon_feed_loop_next_input(
				max(quota->esz_bp, 10000UL),
				score);
		esz = quota->esz_bp / 10000;
	}

	if (quota->ms) {
		if (quota->total_charged_ns)
			throughput = quota->total_charged_sz * 1000000 /
				quota->total_charged_ns;
		else
			throughput = PAGE_SIZE * 1024;
		if (!list_empty(&quota->goals))
			esz = min(throughput * quota->ms, esz);
		else
			esz = throughput * quota->ms;
	}

	if (quota->sz && quota->sz < esz)
		esz = quota->sz;

	quota->esz = esz;
}

static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
{
	struct damos_quota *quota = &s->quota;
	struct damon_target *t;
	struct damon_region *r;
	unsigned long cumulated_sz;
	unsigned int score, max_score = 0;

	if (!quota->ms && !quota->sz && list_empty(&quota->goals))
		return;

	/* New charge window starts */
	if (time_after_eq(jiffies, quota->charged_from +
				msecs_to_jiffies(quota->reset_interval))) {
		if (quota->esz && quota->charged_sz >= quota->esz)
			s->stat.qt_exceeds++;
		quota->total_charged_sz += quota->charged_sz;
		quota->charged_from = jiffies;
		quota->charged_sz = 0;
		damos_set_effective_quota(quota);
	}

	if (!c->ops.get_scheme_score)
		return;

	/* Fill up the score histogram */
	memset(quota->histogram, 0, sizeof(quota->histogram));
	damon_for_each_target(t, c) {
		damon_for_each_region(r, t) {
			if (!__damos_valid_target(r, s))
				continue;
			score = c->ops.get_scheme_score(c, t, r, s);
			quota->histogram[score] += damon_sz_region(r);
			if (score > max_score)
				max_score = score;
		}
	}

	/* Set the min score limit */
	for (cumulated_sz = 0, score = max_score; ; score--) {
		cumulated_sz += quota->histogram[score];
		if (cumulated_sz >= quota->esz || !score)
			break;
	}
	quota->min_score = score;
}

static void kdamond_apply_schemes(struct damon_ctx *c)
{
	struct damon_target *t;
	struct damon_region *r, *next_r;
	struct damos *s;
	unsigned long sample_interval = c->attrs.sample_interval ?
		c->attrs.sample_interval : 1;
	bool has_schemes_to_apply = false;

	damon_for_each_scheme(s, c) {
		if (c->passed_sample_intervals != s->next_apply_sis)
			continue;

		if (!s->wmarks.activated)
			continue;

		has_schemes_to_apply = true;

		damos_adjust_quota(c, s);
	}

	if (!has_schemes_to_apply)
		return;

	damon_for_each_target(t, c) {
		damon_for_each_region_safe(r, next_r, t)
			damon_do_apply_schemes(c, t, r);
	}

	damon_for_each_scheme(s, c) {
		if (c->passed_sample_intervals != s->next_apply_sis)
			continue;
		s->next_apply_sis +=
			(s->apply_interval_us ? s->apply_interval_us :
			 c->attrs.aggr_interval) / sample_interval;
	}
}

/*
 * Merge two adjacent regions into one region
 */
static void damon_merge_two_regions(struct damon_target *t,
		struct damon_region *l, struct damon_region *r)
{
	unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r);

	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
			(sz_l + sz_r);
	l->nr_accesses_bp = l->nr_accesses * 10000;
	l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r);
	l->ar.end = r->ar.end;
	damon_destroy_region(r, t);
}

/*
 * Merge adjacent regions having similar access frequencies
 *
 * t		target affected by this merge operation
 * thres	'->nr_accesses' diff threshold for the merge
 * sz_limit	size upper limit of each region
 */
static void damon_merge_regions_of(struct damon_target *t, unsigned int thres,
				   unsigned long sz_limit)
{
	struct damon_region *r, *prev = NULL, *next;

	damon_for_each_region_safe(r, next, t) {
		if (abs(r->nr_accesses - r->last_nr_accesses) > thres)
			r->age = 0;
		else
			r->age++;

		if (prev && prev->ar.end == r->ar.start &&
		    abs(prev->nr_accesses - r->nr_accesses) <= thres &&
		    damon_sz_region(prev) + damon_sz_region(r) <= sz_limit)
			damon_merge_two_regions(t, prev, r);
		else
			prev = r;
	}
}

/*
 * Merge adjacent regions having similar access frequencies
 *
 * threshold	'->nr_accesses' diff threshold for the merge
 * sz_limit	size upper limit of each region
 *
 * This function merges monitoring target regions which are adjacent and their
 * access frequencies are similar.  This is for minimizing the monitoring
 * overhead under the dynamically changeable access pattern.  If a merge was
 * unnecessarily made, later 'kdamond_split_regions()' will revert it.
 */
static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold,
				  unsigned long sz_limit)
{
	struct damon_target *t;

	damon_for_each_target(t, c)
		damon_merge_regions_of(t, threshold, sz_limit);
}

/*
 * Split a region in two
 *
 * r		the region to be split
 * sz_r		size of the first sub-region that will be made
 */
static void damon_split_region_at(struct damon_target *t,
				  struct damon_region *r, unsigned long sz_r)
{
	struct damon_region *new;

	new = damon_new_region(r->ar.start + sz_r, r->ar.end);
	if (!new)
		return;

	r->ar.end = new->ar.start;

	new->age = r->age;
	new->last_nr_accesses = r->last_nr_accesses;
	new->nr_accesses_bp = r->nr_accesses_bp;
	new->nr_accesses = r->nr_accesses;

	damon_insert_region(new, r, damon_next_region(r), t);
}

/* Split every region in the given target into 'nr_subs' regions */
static void damon_split_regions_of(struct damon_target *t, int nr_subs)
{
	struct damon_region *r, *next;
	unsigned long sz_region, sz_sub = 0;
	int i;

	damon_for_each_region_safe(r, next, t) {
		sz_region = damon_sz_region(r);

		for (i = 0; i < nr_subs - 1 &&
				sz_region > 2 * DAMON_MIN_REGION; i++) {
			/*
			 * Randomly select size of left sub-region to be at
			 * least 10 percent and at most 90% of original region
			 */
			sz_sub = ALIGN_DOWN(damon_rand(1, 10) *
					sz_region / 10, DAMON_MIN_REGION);
			/* Do not allow blank region */
			if (sz_sub == 0 || sz_sub >= sz_region)
				continue;

			damon_split_region_at(t, r, sz_sub);
			sz_region = sz_sub;
		}
	}
}

/*
 * Split every target region into randomly-sized small regions
 *
 * This function splits every target region into random-sized small regions if
 * current total number of the regions is equal or smaller than half of the
 * user-specified maximum number of regions.  This is for maximizing the
 * monitoring accuracy under the dynamically changeable access patterns.  If a
 * split was unnecessarily made, later 'kdamond_merge_regions()' will revert
 * it.
 */
static void kdamond_split_regions(struct damon_ctx *ctx)
{
	struct damon_target *t;
	unsigned int nr_regions = 0;
	static unsigned int last_nr_regions;
	int nr_subregions = 2;

	damon_for_each_target(t, ctx)
		nr_regions += damon_nr_regions(t);

	if (nr_regions > ctx->attrs.max_nr_regions / 2)
		return;

	/* Maybe the middle of the region has different access frequency */
	if (last_nr_regions == nr_regions &&
			nr_regions < ctx->attrs.max_nr_regions / 3)
		nr_subregions = 3;

	damon_for_each_target(t, ctx)
		damon_split_regions_of(t, nr_subregions);

	last_nr_regions = nr_regions;
}

/*
 * Check whether current monitoring should be stopped
 *
 * The monitoring is stopped when either the user requested to stop, or all
 * monitoring targets are invalid.
 *
 * Returns true if need to stop current monitoring.
 */
static bool kdamond_need_stop(struct damon_ctx *ctx)
{
	struct damon_target *t;

	if (kthread_should_stop())
		return true;

	if (!ctx->ops.target_valid)
		return false;

	damon_for_each_target(t, ctx) {
		if (ctx->ops.target_valid(t))
			return false;
	}

	return true;
}

static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric)
{
	switch (metric) {
	case DAMOS_WMARK_FREE_MEM_RATE:
		return global_zone_page_state(NR_FREE_PAGES) * 1000 /
		       totalram_pages();
	default:
		break;
	}
	return -EINVAL;
}

/*
 * Returns zero if the scheme is active.  Else, returns time to wait for next
 * watermark check in micro-seconds.
 */
static unsigned long damos_wmark_wait_us(struct damos *scheme)
{
	unsigned long metric;

	if (scheme->wmarks.metric == DAMOS_WMARK_NONE)
		return 0;

	metric = damos_wmark_metric_value(scheme->wmarks.metric);
	/* higher than high watermark or lower than low watermark */
	if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) {
		if (scheme->wmarks.activated)
			pr_debug("deactivate a scheme (%d) for %s wmark\n",
					scheme->action,
					metric > scheme->wmarks.high ?
					"high" : "low");
		scheme->wmarks.activated = false;
		return scheme->wmarks.interval;
	}

	/* inactive and higher than middle watermark */
	if ((scheme->wmarks.high >= metric && metric >= scheme->wmarks.mid) &&
			!scheme->wmarks.activated)
		return scheme->wmarks.interval;

	if (!scheme->wmarks.activated)
		pr_debug("activate a scheme (%d)\n", scheme->action);
	scheme->wmarks.activated = true;
	return 0;
}

static void kdamond_usleep(unsigned long usecs)
{
	/* See Documentation/timers/timers-howto.rst for the thresholds */
	if (usecs > 20 * USEC_PER_MSEC)
		schedule_timeout_idle(usecs_to_jiffies(usecs));
	else
		usleep_idle_range(usecs, usecs + 1);
}

/* Returns negative error code if it's not activated but should return */
static int kdamond_wait_activation(struct damon_ctx *ctx)
{
	struct damos *s;
	unsigned long wait_time;
	unsigned long min_wait_time = 0;
	bool init_wait_time = false;

	while (!kdamond_need_stop(ctx)) {
		damon_for_each_scheme(s, ctx) {
			wait_time = damos_wmark_wait_us(s);
			if (!init_wait_time || wait_time < min_wait_time) {
				init_wait_time = true;
				min_wait_time = wait_time;
			}
		}
		if (!min_wait_time)
			return 0;

		kdamond_usleep(min_wait_time);

		if (ctx->callback.after_wmarks_check &&
				ctx->callback.after_wmarks_check(ctx))
			break;
	}
	return -EBUSY;
}

static void kdamond_init_intervals_sis(struct damon_ctx *ctx)
{
	unsigned long sample_interval = ctx->attrs.sample_interval ?
		ctx->attrs.sample_interval : 1;
	unsigned long apply_interval;
	struct damos *scheme;

	ctx->passed_sample_intervals = 0;
	ctx->next_aggregation_sis = ctx->attrs.aggr_interval / sample_interval;
	ctx->next_ops_update_sis = ctx->attrs.ops_update_interval /
		sample_interval;

	damon_for_each_scheme(scheme, ctx) {
		apply_interval = scheme->apply_interval_us ?
			scheme->apply_interval_us : ctx->attrs.aggr_interval;
		scheme->next_apply_sis = apply_interval / sample_interval;
	}
}

/*
 * The monitoring daemon that runs as a kernel thread
 */
static int kdamond_fn(void *data)
{
	struct damon_ctx *ctx = data;
	struct damon_target *t;
	struct damon_region *r, *next;
	unsigned int max_nr_accesses = 0;
	unsigned long sz_limit = 0;

	pr_debug("kdamond (%d) starts\n", current->pid);

	complete(&ctx->kdamond_started);
	kdamond_init_intervals_sis(ctx);

	if (ctx->ops.init)
		ctx->ops.init(ctx);
	if (ctx->callback.before_start && ctx->callback.before_start(ctx))
		goto done;

	sz_limit = damon_region_sz_limit(ctx);

	while (!kdamond_need_stop(ctx)) {
		/*
		 * ctx->attrs and ctx->next_{aggregation,ops_update}_sis could
		 * be changed from after_wmarks_check() or after_aggregation()
		 * callbacks.  Read the values here, and use those for this
		 * iteration.  That is, damon_set_attrs() updated new values
		 * are respected from next iteration.
		 */
		unsigned long next_aggregation_sis = ctx->next_aggregation_sis;
		unsigned long next_ops_update_sis = ctx->next_ops_update_sis;
		unsigned long sample_interval = ctx->attrs.sample_interval;

		if (kdamond_wait_activation(ctx))
			break;

		if (ctx->ops.prepare_access_checks)
			ctx->ops.prepare_access_checks(ctx);
		if (ctx->callback.after_sampling &&
				ctx->callback.after_sampling(ctx))
			break;

		kdamond_usleep(sample_interval);
		ctx->passed_sample_intervals++;

		if (ctx->ops.check_accesses)
			max_nr_accesses = ctx->ops.check_accesses(ctx);

		if (ctx->passed_sample_intervals == next_aggregation_sis) {
			kdamond_merge_regions(ctx,
					max_nr_accesses / 10,
					sz_limit);
			if (ctx->callback.after_aggregation &&
					ctx->callback.after_aggregation(ctx))
				break;
		}

		/*
		 * do kdamond_apply_schemes() after kdamond_merge_regions() if
		 * possible, to reduce overhead
		 */
		if (!list_empty(&ctx->schemes))
			kdamond_apply_schemes(ctx);

		sample_interval = ctx->attrs.sample_interval ?
			ctx->attrs.sample_interval : 1;
		if (ctx->passed_sample_intervals == next_aggregation_sis) {
			ctx->next_aggregation_sis = next_aggregation_sis +
				ctx->attrs.aggr_interval / sample_interval;

			kdamond_reset_aggregated(ctx);
			kdamond_split_regions(ctx);
			if (ctx->ops.reset_aggregated)
				ctx->ops.reset_aggregated(ctx);
		}

		if (ctx->passed_sample_intervals == next_ops_update_sis) {
			ctx->next_ops_update_sis = next_ops_update_sis +
				ctx->attrs.ops_update_interval /
				sample_interval;
			if (ctx->ops.update)
				ctx->ops.update(ctx);
			sz_limit = damon_region_sz_limit(ctx);
		}
	}
done:
	damon_for_each_target(t, ctx) {
		damon_for_each_region_safe(r, next, t)
			damon_destroy_region(r, t);
	}

	if (ctx->callback.before_terminate)
		ctx->callback.before_terminate(ctx);
	if (ctx->ops.cleanup)
		ctx->ops.cleanup(ctx);

	pr_debug("kdamond (%d) finishes\n", current->pid);
	mutex_lock(&ctx->kdamond_lock);
	ctx->kdamond = NULL;
	mutex_unlock(&ctx->kdamond_lock);

	mutex_lock(&damon_lock);
	nr_running_ctxs--;
	if (!nr_running_ctxs && running_exclusive_ctxs)
		running_exclusive_ctxs = false;
	mutex_unlock(&damon_lock);

	return 0;
}

/*
 * struct damon_system_ram_region - System RAM resource address region of
 *				    [@start, @end).
 * @start:	Start address of the region (inclusive).
 * @end:	End address of the region (exclusive).
 */
struct damon_system_ram_region {
	unsigned long start;
	unsigned long end;
};

static int walk_system_ram(struct resource *res, void *arg)
{
	struct damon_system_ram_region *a = arg;

	if (a->end - a->start < resource_size(res)) {
		a->start = res->start;
		a->end = res->end;
	}
	return 0;
}

/*
 * Find biggest 'System RAM' resource and store its start and end address in
 * @start and @end, respectively.  If no System RAM is found, returns false.
 */
static bool damon_find_biggest_system_ram(unsigned long *start,
						unsigned long *end)

{
	struct damon_system_ram_region arg = {};

	walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram);
	if (arg.end <= arg.start)
		return false;

	*start = arg.start;
	*end = arg.end;
	return true;
}

/**
 * damon_set_region_biggest_system_ram_default() - Set the region of the given
 * monitoring target as requested, or biggest 'System RAM'.
 * @t:		The monitoring target to set the region.
 * @start:	The pointer to the start address of the region.
 * @end:	The pointer to the end address of the region.
 *
 * This function sets the region of @t as requested by @start and @end.  If the
 * values of @start and @end are zero, however, this function finds the biggest
 * 'System RAM' resource and sets the region to cover the resource.  In the
 * latter case, this function saves the start and end addresses of the resource
 * in @start and @end, respectively.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_set_region_biggest_system_ram_default(struct damon_target *t,
			unsigned long *start, unsigned long *end)
{
	struct damon_addr_range addr_range;

	if (*start > *end)
		return -EINVAL;

	if (!*start && !*end &&
		!damon_find_biggest_system_ram(start, end))
		return -EINVAL;

	addr_range.start = *start;
	addr_range.end = *end;
	return damon_set_regions(t, &addr_range, 1);
}

/*
 * damon_moving_sum() - Calculate an inferred moving sum value.
 * @mvsum:	Inferred sum of the last @len_window values.
 * @nomvsum:	Non-moving sum of the last discrete @len_window window values.
 * @len_window:	The number of last values to take care of.
 * @new_value:	New value that will be added to the pseudo moving sum.
 *
 * Moving sum (moving average * window size) is good for handling noise, but
 * the cost of keeping past values can be high for arbitrary window size.  This
 * function implements a lightweight pseudo moving sum function that doesn't
 * keep the past window values.
 *
 * It simply assumes there was no noise in the past, and get the no-noise
 * assumed past value to drop from @nomvsum and @len_window.  @nomvsum is a
 * non-moving sum of the last window.  For example, if @len_window is 10 and we
 * have 25 values, @nomvsum is the sum of the 11th to 20th values of the 25
 * values.  Hence, this function simply drops @nomvsum / @len_window from
 * given @mvsum and add @new_value.
 *
 * For example, if @len_window is 10 and @nomvsum is 50, the last 10 values for
 * the last window could be vary, e.g., 0, 10, 0, 10, 0, 10, 0, 0, 0, 20.  For
 * calculating next moving sum with a new value, we should drop 0 from 50 and
 * add the new value.  However, this function assumes it got value 5 for each
 * of the last ten times.  Based on the assumption, when the next value is
 * measured, it drops the assumed past value, 5 from the current sum, and add
 * the new value to get the updated pseduo-moving average.
 *
 * This means the value could have errors, but the errors will be disappeared
 * for every @len_window aligned calls.  For example, if @len_window is 10, the
 * pseudo moving sum with 11th value to 19th value would have an error.  But
 * the sum with 20th value will not have the error.
 *
 * Return: Pseudo-moving average after getting the @new_value.
 */
static unsigned int damon_moving_sum(unsigned int mvsum, unsigned int nomvsum,
		unsigned int len_window, unsigned int new_value)
{
	return mvsum - nomvsum / len_window + new_value;
}

/**
 * damon_update_region_access_rate() - Update the access rate of a region.
 * @r:		The DAMON region to update for its access check result.
 * @accessed:	Whether the region has accessed during last sampling interval.
 * @attrs:	The damon_attrs of the DAMON context.
 *
 * Update the access rate of a region with the region's last sampling interval
 * access check result.
 *
 * Usually this will be called by &damon_operations->check_accesses callback.
 */
void damon_update_region_access_rate(struct damon_region *r, bool accessed,
		struct damon_attrs *attrs)
{
	unsigned int len_window = 1;

	/*
	 * sample_interval can be zero, but cannot be larger than
	 * aggr_interval, owing to validation of damon_set_attrs().
	 */
	if (attrs->sample_interval)
		len_window = damon_max_nr_accesses(attrs);
	r->nr_accesses_bp = damon_moving_sum(r->nr_accesses_bp,
			r->last_nr_accesses * 10000, len_window,
			accessed ? 10000 : 0);

	if (accessed)
		r->nr_accesses++;
}

static int __init damon_init(void)
{
	damon_region_cache = KMEM_CACHE(damon_region, 0);
	if (unlikely(!damon_region_cache)) {
		pr_err("creating damon_region_cache fails\n");
		return -ENOMEM;
	}

	return 0;
}

subsys_initcall(damon_init);

#include "core-test.h"