summaryrefslogtreecommitdiff
path: root/mm/damon/core.c
blob: 6482d510dcbe315ed1479280cfd8655db2327217 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Data Access Monitor
 *
 * Author: SeongJae Park <sjpark@amazon.de>
 */

#define pr_fmt(fmt) "damon: " fmt

#include <linux/damon.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/mm.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;

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

	region->ar.start = start;
	region->ar.end = end;
	region->nr_accesses = 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)
{
	kfree(r);
}

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

struct damos *damon_new_scheme(
		unsigned long min_sz_region, unsigned long max_sz_region,
		unsigned int min_nr_accesses, unsigned int max_nr_accesses,
		unsigned int min_age_region, unsigned int max_age_region,
		enum damos_action action, struct damos_quota *quota,
		struct damos_watermarks *wmarks)
{
	struct damos *scheme;

	scheme = kmalloc(sizeof(*scheme), GFP_KERNEL);
	if (!scheme)
		return NULL;
	scheme->min_sz_region = min_sz_region;
	scheme->max_sz_region = max_sz_region;
	scheme->min_nr_accesses = min_nr_accesses;
	scheme->max_nr_accesses = max_nr_accesses;
	scheme->min_age_region = min_age_region;
	scheme->max_age_region = max_age_region;
	scheme->action = action;
	scheme->stat = (struct damos_stat){};
	INIT_LIST_HEAD(&scheme->list);

	scheme->quota.ms = quota->ms;
	scheme->quota.sz = quota->sz;
	scheme->quota.reset_interval = quota->reset_interval;
	scheme->quota.weight_sz = quota->weight_sz;
	scheme->quota.weight_nr_accesses = quota->weight_nr_accesses;
	scheme->quota.weight_age = quota->weight_age;
	scheme->quota.total_charged_sz = 0;
	scheme->quota.total_charged_ns = 0;
	scheme->quota.esz = 0;
	scheme->quota.charged_sz = 0;
	scheme->quota.charged_from = 0;
	scheme->quota.charge_target_from = NULL;
	scheme->quota.charge_addr_from = 0;

	scheme->wmarks.metric = wmarks->metric;
	scheme->wmarks.interval = wmarks->interval;
	scheme->wmarks.high = wmarks->high;
	scheme->wmarks.mid = wmarks->mid;
	scheme->wmarks.low = wmarks->low;
	scheme->wmarks.activated = true;

	return scheme;
}

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

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)
{
	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(unsigned long id)
{
	struct damon_target *t;

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

	t->id = id;
	t->nr_regions = 0;
	INIT_LIST_HEAD(&t->regions_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;

	ctx->sample_interval = 5 * 1000;
	ctx->aggr_interval = 100 * 1000;
	ctx->primitive_update_interval = 60 * 1000 * 1000;

	ktime_get_coarse_ts64(&ctx->last_aggregation);
	ctx->last_primitive_update = ctx->last_aggregation;

	mutex_init(&ctx->kdamond_lock);

	ctx->min_nr_regions = 10;
	ctx->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->primitive.cleanup) {
		ctx->primitive.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);
}

/**
 * damon_set_targets() - Set monitoring targets.
 * @ctx:	monitoring context
 * @ids:	array of target ids
 * @nr_ids:	number of entries in @ids
 *
 * This function should not be called while the kdamond is running.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_set_targets(struct damon_ctx *ctx,
		      unsigned long *ids, ssize_t nr_ids)
{
	ssize_t i;
	struct damon_target *t, *next;

	damon_destroy_targets(ctx);

	for (i = 0; i < nr_ids; i++) {
		t = damon_new_target(ids[i]);
		if (!t) {
			/* The caller should do cleanup of the ids itself */
			damon_for_each_target_safe(t, next, ctx)
				damon_destroy_target(t);
			return -ENOMEM;
		}
		damon_add_target(ctx, t);
	}

	return 0;
}

/**
 * damon_set_attrs() - Set attributes for the monitoring.
 * @ctx:		monitoring context
 * @sample_int:		time interval between samplings
 * @aggr_int:		time interval between aggregations
 * @primitive_upd_int:	time interval between monitoring primitive updates
 * @min_nr_reg:		minimal number of regions
 * @max_nr_reg:		maximum number of regions
 *
 * This function should not be called while the kdamond is running.
 * Every time interval is in micro-seconds.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
		    unsigned long aggr_int, unsigned long primitive_upd_int,
		    unsigned long min_nr_reg, unsigned long max_nr_reg)
{
	if (min_nr_reg < 3)
		return -EINVAL;
	if (min_nr_reg > max_nr_reg)
		return -EINVAL;

	ctx->sample_interval = sample_int;
	ctx->aggr_interval = aggr_int;
	ctx->primitive_update_interval = primitive_upd_int;
	ctx->min_nr_regions = min_nr_reg;
	ctx->max_nr_regions = max_nr_reg;

	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.
 *
 * Return: 0 if success, or negative error code otherwise.
 */
int 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]);
	return 0;
}

/**
 * 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 += r->ar.end - r->ar.start;
	}

	if (ctx->min_nr_regions)
		sz /= ctx->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;
		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;
		}
	}
	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
 *
 * 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 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)
{
	int i;
	int err = 0;

	mutex_lock(&damon_lock);
	if (nr_running_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++;
	}
	mutex_unlock(&damon_lock);

	return err;
}

/*
 * __damon_stop() - Stops monitoring of 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(tsk);
		put_task_struct(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)
			return err;
	}

	return err;
}

/*
 * damon_check_reset_time_interval() - Check if a time interval is elapsed.
 * @baseline:	the time to check whether the interval has elapsed since
 * @interval:	the time interval (microseconds)
 *
 * See whether the given time interval has passed since the given baseline
 * time.  If so, it also updates the baseline to current time for next check.
 *
 * Return:	true if the time interval has passed, or false otherwise.
 */
static bool damon_check_reset_time_interval(struct timespec64 *baseline,
		unsigned long interval)
{
	struct timespec64 now;

	ktime_get_coarse_ts64(&now);
	if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) <
			interval * 1000)
		return false;
	*baseline = now;
	return true;
}

/*
 * Check whether it is time to flush the aggregated information
 */
static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
{
	return damon_check_reset_time_interval(&ctx->last_aggregation,
			ctx->aggr_interval);
}

/*
 * Reset the aggregated monitoring results ('nr_accesses' of each region).
 */
static void kdamond_reset_aggregated(struct damon_ctx *c)
{
	struct damon_target *t;

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

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

static void damon_split_region_at(struct damon_ctx *ctx,
		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;

	sz = r->ar.end - r->ar.start;
	return s->min_sz_region <= sz && sz <= s->max_sz_region &&
		s->min_nr_accesses <= r->nr_accesses &&
		r->nr_accesses <= s->max_nr_accesses &&
		s->min_age_region <= r->age && r->age <= s->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->primitive.get_scheme_score)
		return ret;

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

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;
		unsigned long sz = r->ar.end - r->ar.start;
		struct timespec64 begin, end;
		unsigned long sz_applied = 0;

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

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

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

			if (quota->charge_addr_from && r->ar.start <
					quota->charge_addr_from) {
				sz = ALIGN_DOWN(quota->charge_addr_from -
						r->ar.start, DAMON_MIN_REGION);
				if (!sz) {
					if (r->ar.end - r->ar.start <=
							DAMON_MIN_REGION)
						continue;
					sz = DAMON_MIN_REGION;
				}
				damon_split_region_at(c, t, r, sz);
				r = damon_next_region(r);
				sz = r->ar.end - r->ar.start;
			}
			quota->charge_target_from = NULL;
			quota->charge_addr_from = 0;
		}

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

		/* Apply the scheme */
		if (c->primitive.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(c, t, r, sz);
			}
			ktime_get_coarse_ts64(&begin);
			sz_applied = c->primitive.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:
		s->stat.nr_tried++;
		s->stat.sz_tried += sz;
		if (sz_applied)
			s->stat.nr_applied++;
		s->stat.sz_applied += sz_applied;
	}
}

/* Shouldn't be called if quota->ms and quota->sz are zero */
static void damos_set_effective_quota(struct damos_quota *quota)
{
	unsigned long throughput;
	unsigned long esz;

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

	if (quota->total_charged_ns)
		throughput = quota->total_charged_sz * 1000000 /
			quota->total_charged_ns;
	else
		throughput = PAGE_SIZE * 1024;
	esz = throughput * quota->ms;

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

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

	damon_for_each_scheme(s, c) {
		struct damos_quota *quota = &s->quota;
		unsigned long cumulated_sz;
		unsigned int score, max_score = 0;

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

		if (!quota->ms && !quota->sz)
			continue;

		/* 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->primitive.get_scheme_score)
			continue;

		/* 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->primitive.get_scheme_score(
						c, t, r, s);
				quota->histogram[score] +=
					r->ar.end - r->ar.start;
				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;
	}

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

static inline unsigned long sz_damon_region(struct damon_region *r)
{
	return r->ar.end - r->ar.start;
}

/*
 * 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 = sz_damon_region(l), sz_r = sz_damon_region(r);

	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
			(sz_l + sz_r);
	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 &&
		    sz_damon_region(prev) + sz_damon_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_ctx *ctx,
		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;

	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_ctx *ctx,
				     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 = r->ar.end - r->ar.start;

		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(ctx, 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->max_nr_regions / 2)
		return;

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

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

	last_nr_regions = nr_regions;
}

/*
 * Check whether it is time to check and apply the target monitoring regions
 *
 * Returns true if it is.
 */
static bool kdamond_need_update_primitive(struct damon_ctx *ctx)
{
	return damon_check_reset_time_interval(&ctx->last_primitive_update,
			ctx->primitive_update_interval);
}

/*
 * 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->primitive.target_valid)
		return false;

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

	return true;
}

static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric)
{
	struct sysinfo i;

	switch (metric) {
	case DAMOS_WMARK_FREE_MEM_RATE:
		si_meminfo(&i);
		return i.freeram * 1000 / i.totalram;
	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;

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

		kdamond_usleep(min_wait_time);
	}
	return -EBUSY;
}

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

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

	if (ctx->primitive.init)
		ctx->primitive.init(ctx);
	if (ctx->callback.before_start && ctx->callback.before_start(ctx))
		done = true;

	sz_limit = damon_region_sz_limit(ctx);

	while (!kdamond_need_stop(ctx) && !done) {
		if (kdamond_wait_activation(ctx))
			continue;

		if (ctx->primitive.prepare_access_checks)
			ctx->primitive.prepare_access_checks(ctx);
		if (ctx->callback.after_sampling &&
				ctx->callback.after_sampling(ctx))
			done = true;

		kdamond_usleep(ctx->sample_interval);

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

		if (kdamond_aggregate_interval_passed(ctx)) {
			kdamond_merge_regions(ctx,
					max_nr_accesses / 10,
					sz_limit);
			if (ctx->callback.after_aggregation &&
					ctx->callback.after_aggregation(ctx))
				done = true;
			kdamond_apply_schemes(ctx);
			kdamond_reset_aggregated(ctx);
			kdamond_split_regions(ctx);
			if (ctx->primitive.reset_aggregated)
				ctx->primitive.reset_aggregated(ctx);
		}

		if (kdamond_need_update_primitive(ctx)) {
			if (ctx->primitive.update)
				ctx->primitive.update(ctx);
			sz_limit = damon_region_sz_limit(ctx);
		}
	}
	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->primitive.cleanup)
		ctx->primitive.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--;
	mutex_unlock(&damon_lock);

	return 0;
}

#include "core-test.h"