-
Notifications
You must be signed in to change notification settings - Fork 102
/
memcontrol.h
1807 lines (1479 loc) · 44.6 KB
/
memcontrol.h
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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* 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>
*/
#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 obj_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_SWAP = NR_VM_NODE_STAT_ITEMS,
MEMCG_SOCK,
MEMCG_PERCPU_B,
MEMCG_NR_STAT,
};
enum memcg_memory_event {
MEMCG_LOW,
MEMCG_HIGH,
MEMCG_MAX,
MEMCG_OOM,
MEMCG_OOM_KILL,
MEMCG_SWAP_HIGH,
MEMCG_SWAP_MAX,
MEMCG_SWAP_FAIL,
MEMCG_NR_MEMORY_EVENTS,
};
struct mem_cgroup_reclaim_cookie {
pg_data_t *pgdat;
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;
refcount_t ref;
};
/*
* Per memcg event counter is incremented at every pagein/pageout. With THP,
* it will be incremented by the number of pages. This counter is used
* to 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_NTARGETS,
};
struct memcg_vmstats_percpu {
/* Local (CPU and cgroup) page state & events */
long state[MEMCG_NR_STAT];
unsigned long events[NR_VM_EVENT_ITEMS];
/* Delta calculation for lockless upward propagation */
long state_prev[MEMCG_NR_STAT];
unsigned long events_prev[NR_VM_EVENT_ITEMS];
/* Cgroup1: threshold notifications & softlimit tree updates */
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
};
struct memcg_vmstats {
/* Aggregated (CPU and subtree) page state & events */
long state[MEMCG_NR_STAT];
unsigned long events[NR_VM_EVENT_ITEMS];
/* Pending child counts during tree propagation */
long state_pending[MEMCG_NR_STAT];
unsigned long events_pending[NR_VM_EVENT_ITEMS];
};
struct mem_cgroup_reclaim_iter {
struct mem_cgroup *position;
/* scan generation, increased every round-trip */
unsigned int generation;
};
/*
* Bitmap and deferred work of shrinker::id corresponding to memcg-aware
* shrinkers, which have elements charged to this memcg.
*/
struct shrinker_info {
struct rcu_head rcu;
atomic_long_t *nr_deferred;
unsigned long *map;
};
struct lruvec_stats_percpu {
/* Local (CPU and cgroup) state */
long state[NR_VM_NODE_STAT_ITEMS];
/* Delta calculation for lockless upward propagation */
long state_prev[NR_VM_NODE_STAT_ITEMS];
};
struct lruvec_stats {
/* Aggregated (CPU and subtree) state */
long state[NR_VM_NODE_STAT_ITEMS];
/* Pending child counts during tree propagation */
long state_pending[NR_VM_NODE_STAT_ITEMS];
};
/*
* per-node information in memory controller.
*/
struct mem_cgroup_per_node {
struct lruvec lruvec;
struct lruvec_stats_percpu __percpu *lruvec_stats_percpu;
struct lruvec_stats lruvec_stats;
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
struct mem_cgroup_reclaim_iter iter;
struct shrinker_info __rcu *shrinker_info;
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;
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[];
};
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;
};
#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
/*
* Remember four most recent foreign writebacks with dirty pages in this
* cgroup. Inode sharing is expected to be uncommon and, even if we miss
* one in a given round, we're likely to catch it later if it keeps
* foreign-dirtying, so a fairly low count should be enough.
*
* See mem_cgroup_track_foreign_dirty_slowpath() for details.
*/
#define MEMCG_CGWB_FRN_CNT 4
struct memcg_cgwb_frn {
u64 bdi_id; /* bdi->id of the foreign inode */
int memcg_id; /* memcg->css.id of foreign inode */
u64 at; /* jiffies_64 at the time of dirtying */
struct wb_completion done; /* tracks in-flight foreign writebacks */
};
/*
* Bucket for arbitrarily byte-sized objects charged to a memory
* cgroup. The bucket can be reparented in one piece when the cgroup
* is destroyed, without having to round up the individual references
* of all live memory objects in the wild.
*/
struct obj_cgroup {
struct percpu_ref refcnt;
struct mem_cgroup *memcg;
atomic_t nr_charged_bytes;
union {
struct list_head list;
struct rcu_head rcu;
};
};
/*
* 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; /* Both v1 & v2 */
union {
struct page_counter swap; /* v2 only */
struct page_counter memsw; /* v1 only */
};
/* Legacy consumer-oriented counters */
struct page_counter kmem; /* v1 only */
struct page_counter tcpmem; /* v1 only */
/* Range enforcement for interrupt charges */
struct work_struct high_work;
unsigned long soft_limit;
/* vmpressure notifications */
struct vmpressure vmpressure;
/*
* Should the OOM killer kill all belonging tasks, had it kill one?
*/
bool oom_group;
/* protected by memcg_oom_lock */
bool oom_lock;
int under_oom;
int swappiness;
/* OOM-Killer disable */
int oom_kill_disable;
/* memory.events and memory.events.local */
struct cgroup_file events_file;
struct cgroup_file events_local_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_);
/* memory.stat */
struct memcg_vmstats vmstats;
/* memory.events */
atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS];
unsigned long socket_pressure;
/* Legacy tcp memory accounting */
bool tcpmem_active;
int tcpmem_pressure;
#ifdef CONFIG_MEMCG_KMEM
int kmemcg_id;
struct obj_cgroup __rcu *objcg;
struct list_head objcg_list; /* list of inherited objcgs */
#endif
MEMCG_PADDING(_pad2_);
/*
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
atomic_t moving_account;
struct task_struct *move_lock_task;
struct memcg_vmstats_percpu __percpu *vmstats_percpu;
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
struct wb_domain cgwb_domain;
struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
#endif
/* List of events which userspace want to receive */
struct list_head event_list;
spinlock_t event_list_lock;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split deferred_split_queue;
#endif
#ifdef CONFIG_LRU_GEN
/* per-memcg mm_struct list */
struct lru_gen_mm_list mm_list;
#endif
struct mem_cgroup_per_node *nodeinfo[];
};
/*
* 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;
enum page_memcg_data_flags {
/* page->memcg_data is a pointer to an objcgs vector */
MEMCG_DATA_OBJCGS = (1UL << 0),
/* page has been accounted as a non-slab kernel page */
MEMCG_DATA_KMEM = (1UL << 1),
/* the next bit after the last actual flag */
__NR_MEMCG_DATA_FLAGS = (1UL << 2),
};
#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
static inline bool folio_memcg_kmem(struct folio *folio);
/*
* After the initialization objcg->memcg is always pointing at
* a valid memcg, but can be atomically swapped to the parent memcg.
*
* The caller must ensure that the returned memcg won't be released:
* e.g. acquire the rcu_read_lock or css_set_lock.
*/
static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
{
return READ_ONCE(objcg->memcg);
}
/*
* __folio_memcg - Get the memory cgroup associated with a non-kmem folio
* @folio: Pointer to the folio.
*
* Returns a pointer to the memory cgroup associated with the folio,
* or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
* against some type of folios, e.g. slab folios or ex-slab folios or
* kmem folios.
*/
static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
{
unsigned long memcg_data = folio->memcg_data;
VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
* __folio_objcg - get the object cgroup associated with a kmem folio.
* @folio: Pointer to the folio.
*
* Returns a pointer to the object cgroup associated with the folio,
* or NULL. This function assumes that the folio is known to have a
* proper object cgroup pointer. It's not safe to call this function
* against some type of folios, e.g. slab folios or ex-slab folios or
* LRU folios.
*/
static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
{
unsigned long memcg_data = folio->memcg_data;
VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
* folio_memcg - Get the memory cgroup associated with a folio.
* @folio: Pointer to the folio.
*
* Returns a pointer to the memory cgroup associated with the folio,
* or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
* against some type of folios, e.g. slab folios or ex-slab folios.
*
* For a non-kmem folio any of the following ensures folio and memcg binding
* stability:
*
* - the folio lock
* - LRU isolation
* - lock_page_memcg()
* - exclusive reference
*
* For a kmem folio a caller should hold an rcu read lock to protect memcg
* associated with a kmem folio from being released.
*/
static inline struct mem_cgroup *folio_memcg(struct folio *folio)
{
if (folio_memcg_kmem(folio))
return obj_cgroup_memcg(__folio_objcg(folio));
return __folio_memcg(folio);
}
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return folio_memcg(page_folio(page));
}
/**
* folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio.
* @folio: Pointer to the folio.
*
* This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
* against some type of folios, e.g. slab folios or ex-slab folios.
*
* Return: A pointer to the memory cgroup associated with the folio,
* or NULL.
*/
static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
unsigned long memcg_data = READ_ONCE(folio->memcg_data);
VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
WARN_ON_ONCE(!rcu_read_lock_held());
if (memcg_data & MEMCG_DATA_KMEM) {
struct obj_cgroup *objcg;
objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
return obj_cgroup_memcg(objcg);
}
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
* page_memcg_check - get the memory cgroup associated with a page
* @page: a pointer to the page struct
*
* Returns a pointer to the memory cgroup associated with the page,
* or NULL. This function unlike page_memcg() can take any page
* as an argument. It has to be used in cases when it's not known if a page
* has an associated memory cgroup pointer or an object cgroups vector or
* an object cgroup.
*
* For a non-kmem page any of the following ensures page and memcg binding
* stability:
*
* - the page lock
* - LRU isolation
* - lock_page_memcg()
* - exclusive reference
*
* For a kmem page a caller should hold an rcu read lock to protect memcg
* associated with a kmem page from being released.
*/
static inline struct mem_cgroup *page_memcg_check(struct page *page)
{
/*
* Because page->memcg_data might be changed asynchronously
* for slab pages, READ_ONCE() should be used here.
*/
unsigned long memcg_data = READ_ONCE(page->memcg_data);
if (memcg_data & MEMCG_DATA_OBJCGS)
return NULL;
if (memcg_data & MEMCG_DATA_KMEM) {
struct obj_cgroup *objcg;
objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
return obj_cgroup_memcg(objcg);
}
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
#ifdef CONFIG_MEMCG_KMEM
/*
* folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
* @folio: Pointer to the folio.
*
* Checks if the folio has MemcgKmem flag set. The caller must ensure
* that the folio has an associated memory cgroup. It's not safe to call
* this function against some types of folios, e.g. slab folios.
*/
static inline bool folio_memcg_kmem(struct folio *folio)
{
VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page);
VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio);
return folio->memcg_data & MEMCG_DATA_KMEM;
}
/*
* page_objcgs - get the object cgroups vector associated with a page
* @page: a pointer to the page struct
*
* Returns a pointer to the object cgroups vector associated with the page,
* or NULL. This function assumes that the page is known to have an
* associated object cgroups vector. It's not safe to call this function
* against pages, which might have an associated memory cgroup: e.g.
* kernel stack pages.
*/
static inline struct obj_cgroup **page_objcgs(struct page *page)
{
unsigned long memcg_data = READ_ONCE(page->memcg_data);
VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
* page_objcgs_check - get the object cgroups vector associated with a page
* @page: a pointer to the page struct
*
* Returns a pointer to the object cgroups vector associated with the page,
* or NULL. This function is safe to use if the page can be directly associated
* with a memory cgroup.
*/
static inline struct obj_cgroup **page_objcgs_check(struct page *page)
{
unsigned long memcg_data = READ_ONCE(page->memcg_data);
if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
return NULL;
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
#else
static inline bool folio_memcg_kmem(struct folio *folio)
{
return false;
}
static inline struct obj_cgroup **page_objcgs(struct page *page)
{
return NULL;
}
static inline struct obj_cgroup **page_objcgs_check(struct page *page)
{
return NULL;
}
#endif
static inline bool PageMemcgKmem(struct page *page)
{
return folio_memcg_kmem(page_folio(page));
}
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
return (memcg == root_mem_cgroup);
}
static inline bool mem_cgroup_disabled(void)
{
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
static inline void mem_cgroup_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg,
unsigned long *min,
unsigned long *low)
{
*min = *low = 0;
if (mem_cgroup_disabled())
return;
/*
* There is no reclaim protection applied to a targeted reclaim.
* We are special casing this specific case here because
* mem_cgroup_protected calculation is not robust enough to keep
* the protection invariant for calculated effective values for
* parallel reclaimers with different reclaim target. This is
* especially a problem for tail memcgs (as they have pages on LRU)
* which would want to have effective values 0 for targeted reclaim
* but a different value for external reclaim.
*
* Example
* Let's have global and A's reclaim in parallel:
* |
* A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G)
* |\
* | C (low = 1G, usage = 2.5G)
* B (low = 1G, usage = 0.5G)
*
* For the global reclaim
* A.elow = A.low
* B.elow = min(B.usage, B.low) because children_low_usage <= A.elow
* C.elow = min(C.usage, C.low)
*
* With the effective values resetting we have A reclaim
* A.elow = 0
* B.elow = B.low
* C.elow = C.low
*
* If the global reclaim races with A's reclaim then
* B.elow = C.elow = 0 because children_low_usage > A.elow)
* is possible and reclaiming B would be violating the protection.
*
*/
if (root == memcg)
return;
*min = READ_ONCE(memcg->memory.emin);
*low = READ_ONCE(memcg->memory.elow);
}
void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg);
static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
{
/*
* The root memcg doesn't account charges, and doesn't support
* protection.
*/
return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
}
static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
{
if (!mem_cgroup_supports_protection(memcg))
return false;
return READ_ONCE(memcg->memory.elow) >=
page_counter_read(&memcg->memory);
}
static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
{
if (!mem_cgroup_supports_protection(memcg))
return false;
return READ_ONCE(memcg->memory.emin) >=
page_counter_read(&memcg->memory);
}
int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
/**
* mem_cgroup_charge - Charge a newly allocated folio to a cgroup.
* @folio: Folio to charge.
* @mm: mm context of the allocating task.
* @gfp: Reclaim mode.
*
* Try to charge @folio to the memcg that @mm belongs to, reclaiming
* pages according to @gfp if necessary. If @mm is NULL, try to
* charge to the active memcg.
*
* Do not use this for folios allocated for swapin.
*
* Return: 0 on success. Otherwise, an error code is returned.
*/
static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
gfp_t gfp)
{
if (mem_cgroup_disabled())
return 0;
return __mem_cgroup_charge(folio, mm, gfp);
}
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry);
void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
void __mem_cgroup_uncharge(struct folio *folio);
/**
* mem_cgroup_uncharge - Uncharge a folio.
* @folio: Folio to uncharge.
*
* Uncharge a folio previously charged with mem_cgroup_charge().
*/
static inline void mem_cgroup_uncharge(struct folio *folio)
{
if (mem_cgroup_disabled())
return;
__mem_cgroup_uncharge(folio);
}
void __mem_cgroup_uncharge_list(struct list_head *page_list);
static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
{
if (mem_cgroup_disabled())
return;
__mem_cgroup_uncharge_list(page_list);
}
void mem_cgroup_migrate(struct folio *old, struct folio *new);
/**
* mem_cgroup_lruvec - get the lru list vector for a memcg & node
* @memcg: memcg of the wanted lruvec
* @pgdat: pglist_data
*
* Returns the lru list vector holding pages for a given @memcg &
* @pgdat combination. This can be the node lruvec, if the memory
* controller is disabled.
*/
static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
struct pglist_data *pgdat)
{
struct mem_cgroup_per_node *mz;
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
lruvec = &pgdat->__lruvec;
goto out;
}
if (!memcg)
memcg = root_mem_cgroup;
mz = memcg->nodeinfo[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;
}
/**
* folio_lruvec - return lruvec for isolating/putting an LRU folio
* @folio: Pointer to the folio.
*
* This function relies on folio->mem_cgroup being stable.
*/
static inline struct lruvec *folio_lruvec(struct folio *folio)
{
struct mem_cgroup *memcg = folio_memcg(folio);
VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio);
return mem_cgroup_lruvec(memcg, folio_pgdat(folio));
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
struct lruvec *folio_lruvec_lock(struct folio *folio);
struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags);
#ifdef CONFIG_DEBUG_VM
void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio);
#else
static inline
void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
#endif
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
return css ? container_of(css, struct mem_cgroup, css) : NULL;
}
static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
{
return percpu_ref_tryget(&objcg->refcnt);
}
static inline void obj_cgroup_get(struct obj_cgroup *objcg)
{
percpu_ref_get(&objcg->refcnt);
}
static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
unsigned long nr)
{
percpu_ref_get_many(&objcg->refcnt, nr);
}
static inline void obj_cgroup_put(struct obj_cgroup *objcg)
{
percpu_ref_put(&objcg->refcnt);
}
static inline void mem_cgroup_put(struct mem_cgroup *memcg)
{
if (memcg)
css_put(&memcg->css);
}
#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 *mem_cgroup_from_seq(struct seq_file *m)
{
return mem_cgroup_from_css(seq_css(m));
}
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;
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);
}
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zid, int 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 READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
}
void mem_cgroup_handle_over_high(void);
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
struct task_struct *p);
void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
static inline void mem_cgroup_enter_user_fault(void)
{
WARN_ON(current->in_user_fault);
current->in_user_fault = 1;
}
static inline void mem_cgroup_exit_user_fault(void)
{
WARN_ON(!current->in_user_fault);
current->in_user_fault = 0;
}
static inline bool task_in_memcg_oom(struct task_struct *p)
{
return p->memcg_in_oom;
}
bool mem_cgroup_oom_synchronize(bool wait);
struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
struct mem_cgroup *oom_domain);
void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
#ifdef CONFIG_MEMCG_SWAP
extern bool cgroup_memory_noswap;
#endif
void folio_memcg_lock(struct folio *folio);
void folio_memcg_unlock(struct folio *folio);
void lock_page_memcg(struct page *page);
void unlock_page_memcg(struct page *page);
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
/* 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);
}
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{