summaryrefslogtreecommitdiff
path: root/include/linux/memcontrol.h
blob: 680d3395fc838269870fb836664826fa296cc9e9 (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
/* memcontrol.h - Memory Controller
 *
 * Copyright IBM Corporation, 2007
 * Author Balbir Singh <balbir@linux.vnet.ibm.com>
 *
 * Copyright 2007 OpenVZ SWsoft Inc
 * Author: Pavel Emelianov <xemul@openvz.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 */

#ifndef _LINUX_MEMCONTROL_H
#define _LINUX_MEMCONTROL_H
#include <linux/cgroup.h>
#include <linux/vm_event_item.h>
#include <linux/hardirq.h>
#include <linux/jump_label.h>
#include <linux/page_counter.h>
#include <linux/vmpressure.h>
#include <linux/eventfd.h>
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/writeback.h>
#include <linux/page-flags.h>

struct mem_cgroup;
struct page;
struct mm_struct;
struct kmem_cache;

/* Cgroup-specific page state, on top of universal node page state */
enum memcg_stat_item {
	MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS,
	MEMCG_RSS,
	MEMCG_RSS_HUGE,
	MEMCG_SWAP,
	MEMCG_SOCK,
	/* XXX: why are these zone and not node counters? */
	MEMCG_KERNEL_STACK_KB,
	MEMCG_NR_STAT,
};

enum memcg_memory_event {
	MEMCG_LOW,
	MEMCG_HIGH,
	MEMCG_MAX,
	MEMCG_OOM,
	MEMCG_OOM_KILL,
	MEMCG_SWAP_MAX,
	MEMCG_SWAP_FAIL,
	MEMCG_NR_MEMORY_EVENTS,
};

enum mem_cgroup_protection {
	MEMCG_PROT_NONE,
	MEMCG_PROT_LOW,
	MEMCG_PROT_MIN,
};

struct mem_cgroup_reclaim_cookie {
	pg_data_t *pgdat;
	int priority;
	unsigned int generation;
};

#ifdef CONFIG_MEMCG

#define MEM_CGROUP_ID_SHIFT	16
#define MEM_CGROUP_ID_MAX	USHRT_MAX

struct mem_cgroup_id {
	int id;
	atomic_t ref;
};

/*
 * Per memcg event counter is incremented at every pagein/pageout. With THP,
 * it will be incremated by the number of pages. This counter is used for
 * for trigger some periodic events. This is straightforward and better
 * than using jiffies etc. to handle periodic memcg event.
 */
enum mem_cgroup_events_target {
	MEM_CGROUP_TARGET_THRESH,
	MEM_CGROUP_TARGET_SOFTLIMIT,
	MEM_CGROUP_TARGET_NUMAINFO,
	MEM_CGROUP_NTARGETS,
};

struct mem_cgroup_stat_cpu {
	long count[MEMCG_NR_STAT];
	unsigned long events[NR_VM_EVENT_ITEMS];
	unsigned long nr_page_events;
	unsigned long targets[MEM_CGROUP_NTARGETS];
};

struct mem_cgroup_reclaim_iter {
	struct mem_cgroup *position;
	/* scan generation, increased every round-trip */
	unsigned int generation;
};

struct lruvec_stat {
	long count[NR_VM_NODE_STAT_ITEMS];
};

/*
 * per-zone information in memory controller.
 */
struct mem_cgroup_per_node {
	struct lruvec		lruvec;

	struct lruvec_stat __percpu *lruvec_stat_cpu;
	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];

	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];

	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];

	struct rb_node		tree_node;	/* RB tree node */
	unsigned long		usage_in_excess;/* Set to the value by which */
						/* the soft limit is exceeded*/
	bool			on_tree;
	bool			congested;	/* memcg has many dirty pages */
						/* backed by a congested BDI */

	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
						/* use container_of	   */
};

struct mem_cgroup_threshold {
	struct eventfd_ctx *eventfd;
	unsigned long threshold;
};

/* For threshold */
struct mem_cgroup_threshold_ary {
	/* An array index points to threshold just below or equal to usage. */
	int current_threshold;
	/* Size of entries[] */
	unsigned int size;
	/* Array of thresholds */
	struct mem_cgroup_threshold entries[0];
};

struct mem_cgroup_thresholds {
	/* Primary thresholds array */
	struct mem_cgroup_threshold_ary *primary;
	/*
	 * Spare threshold array.
	 * This is needed to make mem_cgroup_unregister_event() "never fail".
	 * It must be able to store at least primary->size - 1 entries.
	 */
	struct mem_cgroup_threshold_ary *spare;
};

enum memcg_kmem_state {
	KMEM_NONE,
	KMEM_ALLOCATED,
	KMEM_ONLINE,
};

#if defined(CONFIG_SMP)
struct memcg_padding {
	char x[0];
} ____cacheline_internodealigned_in_smp;
#define MEMCG_PADDING(name)      struct memcg_padding name;
#else
#define MEMCG_PADDING(name)
#endif

/*
 * The memory controller data structure. The memory controller controls both
 * page cache and RSS per cgroup. We would eventually like to provide
 * statistics based on the statistics developed by Rik Van Riel for clock-pro,
 * to help the administrator determine what knobs to tune.
 */
struct mem_cgroup {
	struct cgroup_subsys_state css;

	/* Private memcg ID. Used to ID objects that outlive the cgroup */
	struct mem_cgroup_id id;

	/* Accounted resources */
	struct page_counter memory;
	struct page_counter swap;

	/* Legacy consumer-oriented counters */
	struct page_counter memsw;
	struct page_counter kmem;
	struct page_counter tcpmem;

	/* Upper bound of normal memory consumption range */
	unsigned long high;

	/* Range enforcement for interrupt charges */
	struct work_struct high_work;

	unsigned long soft_limit;

	/* vmpressure notifications */
	struct vmpressure vmpressure;

	/*
	 * Should the accounting and control be hierarchical, per subtree?
	 */
	bool use_hierarchy;

	/* protected by memcg_oom_lock */
	bool		oom_lock;
	int		under_oom;

	int	swappiness;
	/* OOM-Killer disable */
	int		oom_kill_disable;

	/* memory.events */
	struct cgroup_file events_file;

	/* handle for "memory.swap.events" */
	struct cgroup_file swap_events_file;

	/* protect arrays of thresholds */
	struct mutex thresholds_lock;

	/* thresholds for memory usage. RCU-protected */
	struct mem_cgroup_thresholds thresholds;

	/* thresholds for mem+swap usage. RCU-protected */
	struct mem_cgroup_thresholds memsw_thresholds;

	/* For oom notifier event fd */
	struct list_head oom_notify;

	/*
	 * Should we move charges of a task when a task is moved into this
	 * mem_cgroup ? And what type of charges should we move ?
	 */
	unsigned long move_charge_at_immigrate;
	/* taken only while moving_account > 0 */
	spinlock_t		move_lock;
	unsigned long		move_lock_flags;

	MEMCG_PADDING(_pad1_);

	/*
	 * set > 0 if pages under this cgroup are moving to other cgroup.
	 */
	atomic_t		moving_account;
	struct task_struct	*move_lock_task;

	/* memory.stat */
	struct mem_cgroup_stat_cpu __percpu *stat_cpu;

	MEMCG_PADDING(_pad2_);

	atomic_long_t		stat[MEMCG_NR_STAT];
	atomic_long_t		events[NR_VM_EVENT_ITEMS];
	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];

	unsigned long		socket_pressure;

	/* Legacy tcp memory accounting */
	bool			tcpmem_active;
	int			tcpmem_pressure;

#ifndef CONFIG_SLOB
        /* Index in the kmem_cache->memcg_params.memcg_caches array */
	int kmemcg_id;
	enum memcg_kmem_state kmem_state;
	struct list_head kmem_caches;
#endif

	int last_scanned_node;
#if MAX_NUMNODES > 1
	nodemask_t	scan_nodes;
	atomic_t	numainfo_events;
	atomic_t	numainfo_updating;
#endif

#ifdef CONFIG_CGROUP_WRITEBACK
	struct list_head cgwb_list;
	struct wb_domain cgwb_domain;
#endif

	/* List of events which userspace want to receive */
	struct list_head event_list;
	spinlock_t event_list_lock;

	struct mem_cgroup_per_node *nodeinfo[0];
	/* WARNING: nodeinfo must be the last member here */
};

/*
 * size of first charge trial. "32" comes from vmscan.c's magic value.
 * TODO: maybe necessary to use big numbers in big irons.
 */
#define MEMCG_CHARGE_BATCH 32U

extern struct mem_cgroup *root_mem_cgroup;

static inline bool mem_cgroup_disabled(void)
{
	return !cgroup_subsys_enabled(memory_cgrp_subsys);
}

enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
						struct mem_cgroup *memcg);

int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
			  bool compound);
int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
			  bool compound);
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
			      bool lrucare, bool compound);
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
		bool compound);
void mem_cgroup_uncharge(struct page *page);
void mem_cgroup_uncharge_list(struct list_head *page_list);

void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);

static struct mem_cgroup_per_node *
mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
{
	return memcg->nodeinfo[nid];
}

/**
 * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
 * @node: node of the wanted lruvec
 * @memcg: memcg of the wanted lruvec
 *
 * Returns the lru list vector holding pages for a given @node or a given
 * @memcg and @zone. This can be the node lruvec, if the memory controller
 * is disabled.
 */
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
				struct mem_cgroup *memcg)
{
	struct mem_cgroup_per_node *mz;
	struct lruvec *lruvec;

	if (mem_cgroup_disabled()) {
		lruvec = node_lruvec(pgdat);
		goto out;
	}

	mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
	lruvec = &mz->lruvec;
out:
	/*
	 * Since a node can be onlined after the mem_cgroup was created,
	 * we have to be prepared to initialize lruvec->pgdat here;
	 * and if offlined then reonlined, we need to reinitialize it.
	 */
	if (unlikely(lruvec->pgdat != pgdat))
		lruvec->pgdat = pgdat;
	return lruvec;
}

struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);

bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);

static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
	return css ? container_of(css, struct mem_cgroup, css) : NULL;
}

#define mem_cgroup_from_counter(counter, member)	\
	container_of(counter, struct mem_cgroup, member)

struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
				   struct mem_cgroup *,
				   struct mem_cgroup_reclaim_cookie *);
void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
int mem_cgroup_scan_tasks(struct mem_cgroup *,
			  int (*)(struct task_struct *, void *), void *);

static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
	if (mem_cgroup_disabled())
		return 0;

	return memcg->id.id;
}
struct mem_cgroup *mem_cgroup_from_id(unsigned short id);

static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
	struct mem_cgroup_per_node *mz;

	if (mem_cgroup_disabled())
		return NULL;

	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	return mz->memcg;
}

/**
 * parent_mem_cgroup - find the accounting parent of a memcg
 * @memcg: memcg whose parent to find
 *
 * Returns the parent memcg, or NULL if this is the root or the memory
 * controller is in legacy no-hierarchy mode.
 */
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
	if (!memcg->memory.parent)
		return NULL;
	return mem_cgroup_from_counter(memcg->memory.parent, memory);
}

static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
			      struct mem_cgroup *root)
{
	if (root == memcg)
		return true;
	if (!root->use_hierarchy)
		return false;
	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
}

static inline bool mm_match_cgroup(struct mm_struct *mm,
				   struct mem_cgroup *memcg)
{
	struct mem_cgroup *task_memcg;
	bool match = false;

	rcu_read_lock();
	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (task_memcg)
		match = mem_cgroup_is_descendant(task_memcg, memcg);
	rcu_read_unlock();
	return match;
}

struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
ino_t page_cgroup_ino(struct page *page);

static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
{
	if (mem_cgroup_disabled())
		return true;
	return !!(memcg->css.flags & CSS_ONLINE);
}

/*
 * For memory reclaim.
 */
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);

void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
		int zid, int nr_pages);

unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
					   int nid, unsigned int lru_mask);

static inline
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
	struct mem_cgroup_per_node *mz;
	unsigned long nr_pages = 0;
	int zid;

	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	for (zid = 0; zid < MAX_NR_ZONES; zid++)
		nr_pages += mz->lru_zone_size[zid][lru];
	return nr_pages;
}

static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
		enum lru_list lru, int zone_idx)
{
	struct mem_cgroup_per_node *mz;

	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	return mz->lru_zone_size[zone_idx][lru];
}

void mem_cgroup_handle_over_high(void);

unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);

void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
				struct task_struct *p);

static inline void mem_cgroup_oom_enable(void)
{
	WARN_ON(current->memcg_may_oom);
	current->memcg_may_oom = 1;
}

static inline void mem_cgroup_oom_disable(void)
{
	WARN_ON(!current->memcg_may_oom);
	current->memcg_may_oom = 0;
}

static inline bool task_in_memcg_oom(struct task_struct *p)
{
	return p->memcg_in_oom;
}

bool mem_cgroup_oom_synchronize(bool wait);

#ifdef CONFIG_MEMCG_SWAP
extern int do_swap_account;
#endif

struct mem_cgroup *lock_page_memcg(struct page *page);
void __unlock_page_memcg(struct mem_cgroup *memcg);
void unlock_page_memcg(struct page *page);

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
					     int idx)
{
	long x = atomic_long_read(&memcg->stat[idx]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
				     int idx, int val)
{
	long x;

	if (mem_cgroup_disabled())
		return;

	x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		atomic_long_add(x, &memcg->stat[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->stat_cpu->count[idx], x);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void mod_memcg_state(struct mem_cgroup *memcg,
				   int idx, int val)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_memcg_state(memcg, idx, val);
	local_irq_restore(flags);
}

/**
 * mod_memcg_page_state - update page state statistics
 * @page: the page
 * @idx: page state item to account
 * @val: number of pages (positive or negative)
 *
 * The @page must be locked or the caller must use lock_page_memcg()
 * to prevent double accounting when the page is concurrently being
 * moved to another memcg:
 *
 *   lock_page(page) or lock_page_memcg(page)
 *   if (TestClearPageState(page))
 *     mod_memcg_page_state(page, state, -1);
 *   unlock_page(page) or unlock_page_memcg(page)
 *
 * Kernel pages are an exception to this, since they'll never move.
 */
static inline void __mod_memcg_page_state(struct page *page,
					  int idx, int val)
{
	if (page->mem_cgroup)
		__mod_memcg_state(page->mem_cgroup, idx, val);
}

static inline void mod_memcg_page_state(struct page *page,
					int idx, int val)
{
	if (page->mem_cgroup)
		mod_memcg_state(page->mem_cgroup, idx, val);
}

static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
					      enum node_stat_item idx)
{
	struct mem_cgroup_per_node *pn;
	long x;

	if (mem_cgroup_disabled())
		return node_page_state(lruvec_pgdat(lruvec), idx);

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	x = atomic_long_read(&pn->lruvec_stat[idx]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

static inline void __mod_lruvec_state(struct lruvec *lruvec,
				      enum node_stat_item idx, int val)
{
	struct mem_cgroup_per_node *pn;
	long x;

	/* Update node */
	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);

	if (mem_cgroup_disabled())
		return;

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);

	/* Update memcg */
	__mod_memcg_state(pn->memcg, idx, val);

	/* Update lruvec */
	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		atomic_long_add(x, &pn->lruvec_stat[idx]);
		x = 0;
	}
	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}

static inline void mod_lruvec_state(struct lruvec *lruvec,
				    enum node_stat_item idx, int val)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_lruvec_state(lruvec, idx, val);
	local_irq_restore(flags);
}

static inline void __mod_lruvec_page_state(struct page *page,
					   enum node_stat_item idx, int val)
{
	pg_data_t *pgdat = page_pgdat(page);
	struct lruvec *lruvec;

	/* Untracked pages have no memcg, no lruvec. Update only the node */
	if (!page->mem_cgroup) {
		__mod_node_page_state(pgdat, idx, val);
		return;
	}

	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
	__mod_lruvec_state(lruvec, idx, val);
}

static inline void mod_lruvec_page_state(struct page *page,
					 enum node_stat_item idx, int val)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_lruvec_page_state(page, idx, val);
	local_irq_restore(flags);
}

unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
						gfp_t gfp_mask,
						unsigned long *total_scanned);

static inline void __count_memcg_events(struct mem_cgroup *memcg,
					enum vm_event_item idx,
					unsigned long count)
{
	unsigned long x;

	if (mem_cgroup_disabled())
		return;

	x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
		atomic_long_add(x, &memcg->events[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->stat_cpu->events[idx], x);
}

static inline void count_memcg_events(struct mem_cgroup *memcg,
				      enum vm_event_item idx,
				      unsigned long count)
{
	unsigned long flags;

	local_irq_save(flags);
	__count_memcg_events(memcg, idx, count);
	local_irq_restore(flags);
}

static inline void count_memcg_page_event(struct page *page,
					  enum vm_event_item idx)
{
	if (page->mem_cgroup)
		count_memcg_events(page->mem_cgroup, idx, 1);
}

static inline void count_memcg_event_mm(struct mm_struct *mm,
					enum vm_event_item idx)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return;

	rcu_read_lock();
	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (likely(memcg))
		count_memcg_events(memcg, idx, 1);
	rcu_read_unlock();
}

static inline void memcg_memory_event(struct mem_cgroup *memcg,
				      enum memcg_memory_event event)
{
	atomic_long_inc(&memcg->memory_events[event]);
	cgroup_file_notify(&memcg->events_file);
}

static inline void memcg_memory_event_mm(struct mm_struct *mm,
					 enum memcg_memory_event event)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return;

	rcu_read_lock();
	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (likely(memcg))
		memcg_memory_event(memcg, event);
	rcu_read_unlock();
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void mem_cgroup_split_huge_fixup(struct page *head);
#endif

#else /* CONFIG_MEMCG */

#define MEM_CGROUP_ID_SHIFT	0
#define MEM_CGROUP_ID_MAX	0

struct mem_cgroup;

static inline bool mem_cgroup_disabled(void)
{
	return true;
}

static inline void memcg_memory_event(struct mem_cgroup *memcg,
				      enum memcg_memory_event event)
{
}

static inline void memcg_memory_event_mm(struct mm_struct *mm,
					 enum memcg_memory_event event)
{
}

static inline enum mem_cgroup_protection mem_cgroup_protected(
	struct mem_cgroup *root, struct mem_cgroup *memcg)
{
	return MEMCG_PROT_NONE;
}

static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
					gfp_t gfp_mask,
					struct mem_cgroup **memcgp,
					bool compound)
{
	*memcgp = NULL;
	return 0;
}

static inline int mem_cgroup_try_charge_delay(struct page *page,
					      struct mm_struct *mm,
					      gfp_t gfp_mask,
					      struct mem_cgroup **memcgp,
					      bool compound)
{
	*memcgp = NULL;
	return 0;
}

static inline void mem_cgroup_commit_charge(struct page *page,
					    struct mem_cgroup *memcg,
					    bool lrucare, bool compound)
{
}

static inline void mem_cgroup_cancel_charge(struct page *page,
					    struct mem_cgroup *memcg,
					    bool compound)
{
}

static inline void mem_cgroup_uncharge(struct page *page)
{
}

static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
{
}

static inline void mem_cgroup_migrate(struct page *old, struct page *new)
{
}

static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
				struct mem_cgroup *memcg)
{
	return node_lruvec(pgdat);
}

static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
						    struct pglist_data *pgdat)
{
	return &pgdat->lruvec;
}

static inline bool mm_match_cgroup(struct mm_struct *mm,
		struct mem_cgroup *memcg)
{
	return true;
}

static inline bool task_in_mem_cgroup(struct task_struct *task,
				      const struct mem_cgroup *memcg)
{
	return true;
}

static inline struct mem_cgroup *
mem_cgroup_iter(struct mem_cgroup *root,
		struct mem_cgroup *prev,
		struct mem_cgroup_reclaim_cookie *reclaim)
{
	return NULL;
}

static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
					 struct mem_cgroup *prev)
{
}

static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
		int (*fn)(struct task_struct *, void *), void *arg)
{
	return 0;
}

static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
	return 0;
}

static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
	WARN_ON_ONCE(id);
	/* XXX: This should always return root_mem_cgroup */
	return NULL;
}

static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
	return NULL;
}

static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
{
	return true;
}

static inline unsigned long
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
	return 0;
}
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
		enum lru_list lru, int zone_idx)
{
	return 0;
}

static inline unsigned long
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
			     int nid, unsigned int lru_mask)
{
	return 0;
}

static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
	return 0;
}

static inline void
mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
{
}

static inline struct mem_cgroup *lock_page_memcg(struct page *page)
{
	return NULL;
}

static inline void __unlock_page_memcg(struct mem_cgroup *memcg)
{
}

static inline void unlock_page_memcg(struct page *page)
{
}

static inline void mem_cgroup_handle_over_high(void)
{
}

static inline void mem_cgroup_oom_enable(void)
{
}

static inline void mem_cgroup_oom_disable(void)
{
}

static inline bool task_in_memcg_oom(struct task_struct *p)
{
	return false;
}

static inline bool mem_cgroup_oom_synchronize(bool wait)
{
	return false;
}

static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
					     int idx)
{
	return 0;
}

static inline void __mod_memcg_state(struct mem_cgroup *memcg,
				     int idx,
				     int nr)
{
}

static inline void mod_memcg_state(struct mem_cgroup *memcg,
				   int idx,
				   int nr)
{
}

static inline void __mod_memcg_page_state(struct page *page,
					  int idx,
					  int nr)
{
}

static inline void mod_memcg_page_state(struct page *page,
					int idx,
					int nr)
{
}

static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
					      enum node_stat_item idx)
{
	return node_page_state(lruvec_pgdat(lruvec), idx);
}

static inline void __mod_lruvec_state(struct lruvec *lruvec,
				      enum node_stat_item idx, int val)
{
	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
}

static inline void mod_lruvec_state(struct lruvec *lruvec,
				    enum node_stat_item idx, int val)
{
	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
}

static inline void __mod_lruvec_page_state(struct page *page,
					   enum node_stat_item idx, int val)
{
	__mod_node_page_state(page_pgdat(page), idx, val);
}

static inline void mod_lruvec_page_state(struct page *page,
					 enum node_stat_item idx, int val)
{
	mod_node_page_state(page_pgdat(page), idx, val);
}

static inline
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
					    gfp_t gfp_mask,
					    unsigned long *total_scanned)
{
	return 0;
}

static inline void mem_cgroup_split_huge_fixup(struct page *head)
{
}

static inline void count_memcg_events(struct mem_cgroup *memcg,
				      enum vm_event_item idx,
				      unsigned long count)
{
}

static inline void count_memcg_page_event(struct page *page,
					  int idx)
{
}

static inline
void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
{
}
#endif /* CONFIG_MEMCG */

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __inc_memcg_state(struct mem_cgroup *memcg,
				     int idx)
{
	__mod_memcg_state(memcg, idx, 1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __dec_memcg_state(struct mem_cgroup *memcg,
				     int idx)
{
	__mod_memcg_state(memcg, idx, -1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __inc_memcg_page_state(struct page *page,
					  int idx)
{
	__mod_memcg_page_state(page, idx, 1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __dec_memcg_page_state(struct page *page,
					  int idx)
{
	__mod_memcg_page_state(page, idx, -1);
}

static inline void __inc_lruvec_state(struct lruvec *lruvec,
				      enum node_stat_item idx)
{
	__mod_lruvec_state(lruvec, idx, 1);
}

static inline void __dec_lruvec_state(struct lruvec *lruvec,
				      enum node_stat_item idx)
{
	__mod_lruvec_state(lruvec, idx, -1);
}

static inline void __inc_lruvec_page_state(struct page *page,
					   enum node_stat_item idx)
{
	__mod_lruvec_page_state(page, idx, 1);
}

static inline void __dec_lruvec_page_state(struct page *page,
					   enum node_stat_item idx)
{
	__mod_lruvec_page_state(page, idx, -1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_state(struct mem_cgroup *memcg,
				   int idx)
{
	mod_memcg_state(memcg, idx, 1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void dec_memcg_state(struct mem_cgroup *memcg,
				   int idx)
{
	mod_memcg_state(memcg, idx, -1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_page_state(struct page *page,
					int idx)
{
	mod_memcg_page_state(page, idx, 1);
}

/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void dec_memcg_page_state(struct page *page,
					int idx)
{
	mod_memcg_page_state(page, idx, -1);
}

static inline void inc_lruvec_state(struct lruvec *lruvec,
				    enum node_stat_item idx)
{
	mod_lruvec_state(lruvec, idx, 1);
}

static inline void dec_lruvec_state(struct lruvec *lruvec,
				    enum node_stat_item idx)
{
	mod_lruvec_state(lruvec, idx, -1);
}

static inline void inc_lruvec_page_state(struct page *page,
					 enum node_stat_item idx)
{
	mod_lruvec_page_state(page, idx, 1);
}

static inline void dec_lruvec_page_state(struct page *page,
					 enum node_stat_item idx)
{
	mod_lruvec_page_state(page, idx, -1);
}

#ifdef CONFIG_CGROUP_WRITEBACK

struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
			 unsigned long *pheadroom, unsigned long *pdirty,
			 unsigned long *pwriteback);

#else	/* CONFIG_CGROUP_WRITEBACK */

static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
{
	return NULL;
}

static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
				       unsigned long *pfilepages,
				       unsigned long *pheadroom,
				       unsigned long *pdirty,
				       unsigned long *pwriteback)
{
}

#endif	/* CONFIG_CGROUP_WRITEBACK */

struct sock;
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
#ifdef CONFIG_MEMCG
extern struct static_key_false memcg_sockets_enabled_key;
#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
void mem_cgroup_sk_alloc(struct sock *sk);
void mem_cgroup_sk_free(struct sock *sk);
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
		return true;
	do {
		if (time_before(jiffies, memcg->socket_pressure))
			return true;
	} while ((memcg = parent_mem_cgroup(memcg)));
	return false;
}
#else
#define mem_cgroup_sockets_enabled 0
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
static inline void mem_cgroup_sk_free(struct sock *sk) { };
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
	return false;
}
#endif

struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
void memcg_kmem_put_cache(struct kmem_cache *cachep);
int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
			    struct mem_cgroup *memcg);
int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
void memcg_kmem_uncharge(struct page *page, int order);

#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
extern struct static_key_false memcg_kmem_enabled_key;
extern struct workqueue_struct *memcg_kmem_cache_wq;

extern int memcg_nr_cache_ids;
void memcg_get_cache_ids(void);
void memcg_put_cache_ids(void);

/*
 * Helper macro to loop through all memcg-specific caches. Callers must still
 * check if the cache is valid (it is either valid or NULL).
 * the slab_mutex must be held when looping through those caches
 */
#define for_each_memcg_cache_index(_idx)	\
	for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)

static inline bool memcg_kmem_enabled(void)
{
	return static_branch_unlikely(&memcg_kmem_enabled_key);
}

/*
 * helper for accessing a memcg's index. It will be used as an index in the
 * child cache array in kmem_cache, and also to derive its name. This function
 * will return -1 when this is not a kmem-limited memcg.
 */
static inline int memcg_cache_id(struct mem_cgroup *memcg)
{
	return memcg ? memcg->kmemcg_id : -1;
}

#else
#define for_each_memcg_cache_index(_idx)	\
	for (; NULL; )

static inline bool memcg_kmem_enabled(void)
{
	return false;
}

static inline int memcg_cache_id(struct mem_cgroup *memcg)
{
	return -1;
}

static inline void memcg_get_cache_ids(void)
{
}

static inline void memcg_put_cache_ids(void)
{
}

#endif /* CONFIG_MEMCG && !CONFIG_SLOB */

#endif /* _LINUX_MEMCONTROL_H */