forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
memcontrol.c
7438 lines (6387 loc) · 191 KB
/
memcontrol.c
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.c - Memory Controller
*
* Copyright IBM Corporation, 2007
* Author Balbir Singh <[email protected]>
*
* Copyright 2007 OpenVZ SWsoft Inc
* Author: Pavel Emelianov <[email protected]>
*
* Memory thresholds
* Copyright (C) 2009 Nokia Corporation
* Author: Kirill A. Shutemov
*
* Kernel Memory Controller
* Copyright (C) 2012 Parallels Inc. and Google Inc.
* Authors: Glauber Costa and Suleiman Souhlal
*
* Native page reclaim
* Charge lifetime sanitation
* Lockless page tracking & accounting
* Unified hierarchy configuration model
* Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
*
* Per memcg lru locking
* Copyright (C) 2020 Alibaba, Inc, Alex Shi
*/
#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/vm_event_item.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/sort.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmpressure.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/file.h>
#include <linux/tracehook.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include "slab.h"
#include <linux/uaccess.h>
#include <trace/events/vmscan.h>
struct cgroup_subsys memory_cgrp_subsys __read_mostly;
EXPORT_SYMBOL(memory_cgrp_subsys);
struct mem_cgroup *root_mem_cgroup __read_mostly;
/* Active memory cgroup to use from an interrupt context */
DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
/* Socket memory accounting disabled? */
static bool cgroup_memory_nosocket __ro_after_init;
/* Kernel memory accounting disabled? */
bool cgroup_memory_nokmem __ro_after_init;
/* Whether the swap controller is active */
#ifdef CONFIG_MEMCG_SWAP
bool cgroup_memory_noswap __ro_after_init;
#else
#define cgroup_memory_noswap 1
#endif
#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif
/* Whether legacy memory+swap accounting is active */
static bool do_memsw_account(void)
{
return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap;
}
#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
/*
* Cgroups above their limits are maintained in a RB-Tree, independent of
* their hierarchy representation
*/
struct mem_cgroup_tree_per_node {
struct rb_root rb_root;
struct rb_node *rb_rightmost;
spinlock_t lock;
};
struct mem_cgroup_tree {
struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
};
static struct mem_cgroup_tree soft_limit_tree __read_mostly;
/* for OOM */
struct mem_cgroup_eventfd_list {
struct list_head list;
struct eventfd_ctx *eventfd;
};
/*
* cgroup_event represents events which userspace want to receive.
*/
struct mem_cgroup_event {
/*
* memcg which the event belongs to.
*/
struct mem_cgroup *memcg;
/*
* eventfd to signal userspace about the event.
*/
struct eventfd_ctx *eventfd;
/*
* Each of these stored in a list by the cgroup.
*/
struct list_head list;
/*
* register_event() callback will be used to add new userspace
* waiter for changes related to this event. Use eventfd_signal()
* on eventfd to send notification to userspace.
*/
int (*register_event)(struct mem_cgroup *memcg,
struct eventfd_ctx *eventfd, const char *args);
/*
* unregister_event() callback will be called when userspace closes
* the eventfd or on cgroup removing. This callback must be set,
* if you want provide notification functionality.
*/
void (*unregister_event)(struct mem_cgroup *memcg,
struct eventfd_ctx *eventfd);
/*
* All fields below needed to unregister event when
* userspace closes eventfd.
*/
poll_table pt;
wait_queue_head_t *wqh;
wait_queue_entry_t wait;
struct work_struct remove;
};
static void mem_cgroup_threshold(struct mem_cgroup *memcg);
static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
/* Stuffs for move charges at task migration. */
/*
* Types of charges to be moved.
*/
#define MOVE_ANON 0x1U
#define MOVE_FILE 0x2U
#define MOVE_MASK (MOVE_ANON | MOVE_FILE)
/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
spinlock_t lock; /* for from, to */
struct mm_struct *mm;
struct mem_cgroup *from;
struct mem_cgroup *to;
unsigned long flags;
unsigned long precharge;
unsigned long moved_charge;
unsigned long moved_swap;
struct task_struct *moving_task; /* a task moving charges */
wait_queue_head_t waitq; /* a waitq for other context */
} mc = {
.lock = __SPIN_LOCK_UNLOCKED(mc.lock),
.waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
};
/*
* Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
* limit reclaim to prevent infinite loops, if they ever occur.
*/
#define MEM_CGROUP_MAX_RECLAIM_LOOPS 100
#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2
/* for encoding cft->private value on file */
enum res_type {
_MEM,
_MEMSWAP,
_OOM_TYPE,
_KMEM,
_TCP,
};
#define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val))
#define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff)
#define MEMFILE_ATTR(val) ((val) & 0xffff)
/* Used for OOM notifier */
#define OOM_CONTROL (0)
/*
* Iteration constructs for visiting all cgroups (under a tree). If
* loops are exited prematurely (break), mem_cgroup_iter_break() must
* be used for reference counting.
*/
#define for_each_mem_cgroup_tree(iter, root) \
for (iter = mem_cgroup_iter(root, NULL, NULL); \
iter != NULL; \
iter = mem_cgroup_iter(root, iter, NULL))
#define for_each_mem_cgroup(iter) \
for (iter = mem_cgroup_iter(NULL, NULL, NULL); \
iter != NULL; \
iter = mem_cgroup_iter(NULL, iter, NULL))
static inline bool task_is_dying(void)
{
return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
(current->flags & PF_EXITING);
}
/* Some nice accessors for the vmpressure. */
struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
{
if (!memcg)
memcg = root_mem_cgroup;
return &memcg->vmpressure;
}
struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
{
return container_of(vmpr, struct mem_cgroup, vmpressure);
}
#ifdef CONFIG_MEMCG_KMEM
extern spinlock_t css_set_lock;
bool mem_cgroup_kmem_disabled(void)
{
return cgroup_memory_nokmem;
}
static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
unsigned int nr_pages);
static void obj_cgroup_release(struct percpu_ref *ref)
{
struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
unsigned int nr_bytes;
unsigned int nr_pages;
unsigned long flags;
/*
* At this point all allocated objects are freed, and
* objcg->nr_charged_bytes can't have an arbitrary byte value.
* However, it can be PAGE_SIZE or (x * PAGE_SIZE).
*
* The following sequence can lead to it:
* 1) CPU0: objcg == stock->cached_objcg
* 2) CPU1: we do a small allocation (e.g. 92 bytes),
* PAGE_SIZE bytes are charged
* 3) CPU1: a process from another memcg is allocating something,
* the stock if flushed,
* objcg->nr_charged_bytes = PAGE_SIZE - 92
* 5) CPU0: we do release this object,
* 92 bytes are added to stock->nr_bytes
* 6) CPU0: stock is flushed,
* 92 bytes are added to objcg->nr_charged_bytes
*
* In the result, nr_charged_bytes == PAGE_SIZE.
* This page will be uncharged in obj_cgroup_release().
*/
nr_bytes = atomic_read(&objcg->nr_charged_bytes);
WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
nr_pages = nr_bytes >> PAGE_SHIFT;
if (nr_pages)
obj_cgroup_uncharge_pages(objcg, nr_pages);
spin_lock_irqsave(&css_set_lock, flags);
list_del(&objcg->list);
spin_unlock_irqrestore(&css_set_lock, flags);
percpu_ref_exit(ref);
kfree_rcu(objcg, rcu);
}
static struct obj_cgroup *obj_cgroup_alloc(void)
{
struct obj_cgroup *objcg;
int ret;
objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
if (!objcg)
return NULL;
ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
GFP_KERNEL);
if (ret) {
kfree(objcg);
return NULL;
}
INIT_LIST_HEAD(&objcg->list);
return objcg;
}
static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
struct mem_cgroup *parent)
{
struct obj_cgroup *objcg, *iter;
objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
spin_lock_irq(&css_set_lock);
/* 1) Ready to reparent active objcg. */
list_add(&objcg->list, &memcg->objcg_list);
/* 2) Reparent active objcg and already reparented objcgs to parent. */
list_for_each_entry(iter, &memcg->objcg_list, list)
WRITE_ONCE(iter->memcg, parent);
/* 3) Move already reparented objcgs to the parent's list */
list_splice(&memcg->objcg_list, &parent->objcg_list);
spin_unlock_irq(&css_set_lock);
percpu_ref_kill(&objcg->refcnt);
}
/*
* This will be used as a shrinker list's index.
* The main reason for not using cgroup id for this:
* this works better in sparse environments, where we have a lot of memcgs,
* but only a few kmem-limited. Or also, if we have, for instance, 200
* memcgs, and none but the 200th is kmem-limited, we'd have to have a
* 200 entry array for that.
*
* The current size of the caches array is stored in memcg_nr_cache_ids. It
* will double each time we have to increase it.
*/
static DEFINE_IDA(memcg_cache_ida);
int memcg_nr_cache_ids;
/* Protects memcg_nr_cache_ids */
static DECLARE_RWSEM(memcg_cache_ids_sem);
void memcg_get_cache_ids(void)
{
down_read(&memcg_cache_ids_sem);
}
void memcg_put_cache_ids(void)
{
up_read(&memcg_cache_ids_sem);
}
/*
* MIN_SIZE is different than 1, because we would like to avoid going through
* the alloc/free process all the time. In a small machine, 4 kmem-limited
* cgroups is a reasonable guess. In the future, it could be a parameter or
* tunable, but that is strictly not necessary.
*
* MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
* this constant directly from cgroup, but it is understandable that this is
* better kept as an internal representation in cgroup.c. In any case, the
* cgrp_id space is not getting any smaller, and we don't have to necessarily
* increase ours as well if it increases.
*/
#define MEMCG_CACHES_MIN_SIZE 4
#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX
/*
* A lot of the calls to the cache allocation functions are expected to be
* inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are
* conditional to this static branch, we'll have to allow modules that does
* kmem_cache_alloc and the such to see this symbol as well
*/
DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
EXPORT_SYMBOL(memcg_kmem_enabled_key);
#endif
/**
* mem_cgroup_css_from_page - css of the memcg associated with a page
* @page: page of interest
*
* If memcg is bound to the default hierarchy, css of the memcg associated
* with @page is returned. The returned css remains associated with @page
* until it is released.
*
* If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
* is returned.
*/
struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
{
struct mem_cgroup *memcg;
memcg = page_memcg(page);
if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg = root_mem_cgroup;
return &memcg->css;
}
/**
* page_cgroup_ino - return inode number of the memcg a page is charged to
* @page: the page
*
* Look up the closest online ancestor of the memory cgroup @page is charged to
* and return its inode number or 0 if @page is not charged to any cgroup. It
* is safe to call this function without holding a reference to @page.
*
* Note, this function is inherently racy, because there is nothing to prevent
* the cgroup inode from getting torn down and potentially reallocated a moment
* after page_cgroup_ino() returns, so it only should be used by callers that
* do not care (such as procfs interfaces).
*/
ino_t page_cgroup_ino(struct page *page)
{
struct mem_cgroup *memcg;
unsigned long ino = 0;
rcu_read_lock();
memcg = page_memcg_check(page);
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg);
if (memcg)
ino = cgroup_ino(memcg->css.cgroup);
rcu_read_unlock();
return ino;
}
static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
struct mem_cgroup_tree_per_node *mctz,
unsigned long new_usage_in_excess)
{
struct rb_node **p = &mctz->rb_root.rb_node;
struct rb_node *parent = NULL;
struct mem_cgroup_per_node *mz_node;
bool rightmost = true;
if (mz->on_tree)
return;
mz->usage_in_excess = new_usage_in_excess;
if (!mz->usage_in_excess)
return;
while (*p) {
parent = *p;
mz_node = rb_entry(parent, struct mem_cgroup_per_node,
tree_node);
if (mz->usage_in_excess < mz_node->usage_in_excess) {
p = &(*p)->rb_left;
rightmost = false;
} else {
p = &(*p)->rb_right;
}
}
if (rightmost)
mctz->rb_rightmost = &mz->tree_node;
rb_link_node(&mz->tree_node, parent, p);
rb_insert_color(&mz->tree_node, &mctz->rb_root);
mz->on_tree = true;
}
static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
struct mem_cgroup_tree_per_node *mctz)
{
if (!mz->on_tree)
return;
if (&mz->tree_node == mctz->rb_rightmost)
mctz->rb_rightmost = rb_prev(&mz->tree_node);
rb_erase(&mz->tree_node, &mctz->rb_root);
mz->on_tree = false;
}
static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
struct mem_cgroup_tree_per_node *mctz)
{
unsigned long flags;
spin_lock_irqsave(&mctz->lock, flags);
__mem_cgroup_remove_exceeded(mz, mctz);
spin_unlock_irqrestore(&mctz->lock, flags);
}
static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
{
unsigned long nr_pages = page_counter_read(&memcg->memory);
unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
unsigned long excess = 0;
if (nr_pages > soft_limit)
excess = nr_pages - soft_limit;
return excess;
}
static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
{
unsigned long excess;
struct mem_cgroup_per_node *mz;
struct mem_cgroup_tree_per_node *mctz;
mctz = soft_limit_tree.rb_tree_per_node[nid];
if (!mctz)
return;
/*
* Necessary to update all ancestors when hierarchy is used.
* because their event counter is not touched.
*/
for (; memcg; memcg = parent_mem_cgroup(memcg)) {
mz = memcg->nodeinfo[nid];
excess = soft_limit_excess(memcg);
/*
* We have to update the tree if mz is on RB-tree or
* mem is over its softlimit.
*/
if (excess || mz->on_tree) {
unsigned long flags;
spin_lock_irqsave(&mctz->lock, flags);
/* if on-tree, remove it */
if (mz->on_tree)
__mem_cgroup_remove_exceeded(mz, mctz);
/*
* Insert again. mz->usage_in_excess will be updated.
* If excess is 0, no tree ops.
*/
__mem_cgroup_insert_exceeded(mz, mctz, excess);
spin_unlock_irqrestore(&mctz->lock, flags);
}
}
}
static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
struct mem_cgroup_tree_per_node *mctz;
struct mem_cgroup_per_node *mz;
int nid;
for_each_node(nid) {
mz = memcg->nodeinfo[nid];
mctz = soft_limit_tree.rb_tree_per_node[nid];
if (mctz)
mem_cgroup_remove_exceeded(mz, mctz);
}
}
static struct mem_cgroup_per_node *
__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
struct mem_cgroup_per_node *mz;
retry:
mz = NULL;
if (!mctz->rb_rightmost)
goto done; /* Nothing to reclaim from */
mz = rb_entry(mctz->rb_rightmost,
struct mem_cgroup_per_node, tree_node);
/*
* Remove the node now but someone else can add it back,
* we will to add it back at the end of reclaim to its correct
* position in the tree.
*/
__mem_cgroup_remove_exceeded(mz, mctz);
if (!soft_limit_excess(mz->memcg) ||
!css_tryget(&mz->memcg->css))
goto retry;
done:
return mz;
}
static struct mem_cgroup_per_node *
mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
struct mem_cgroup_per_node *mz;
spin_lock_irq(&mctz->lock);
mz = __mem_cgroup_largest_soft_limit_node(mctz);
spin_unlock_irq(&mctz->lock);
return mz;
}
/*
* memcg and lruvec stats flushing
*
* Many codepaths leading to stats update or read are performance sensitive and
* adding stats flushing in such codepaths is not desirable. So, to optimize the
* flushing the kernel does:
*
* 1) Periodically and asynchronously flush the stats every 2 seconds to not let
* rstat update tree grow unbounded.
*
* 2) Flush the stats synchronously on reader side only when there are more than
* (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
* will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
* only for 2 seconds due to (1).
*/
static void flush_memcg_stats_dwork(struct work_struct *w);
static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
static DEFINE_SPINLOCK(stats_flush_lock);
static DEFINE_PER_CPU(unsigned int, stats_updates);
static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
static inline void memcg_rstat_updated(struct mem_cgroup *memcg)
{
cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
if (!(__this_cpu_inc_return(stats_updates) % MEMCG_CHARGE_BATCH))
atomic_inc(&stats_flush_threshold);
}
static void __mem_cgroup_flush_stats(void)
{
unsigned long flag;
if (!spin_trylock_irqsave(&stats_flush_lock, flag))
return;
cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
atomic_set(&stats_flush_threshold, 0);
spin_unlock_irqrestore(&stats_flush_lock, flag);
}
void mem_cgroup_flush_stats(void)
{
if (atomic_read(&stats_flush_threshold) > num_online_cpus())
__mem_cgroup_flush_stats();
}
static void flush_memcg_stats_dwork(struct work_struct *w)
{
mem_cgroup_flush_stats();
queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
}
/**
* __mod_memcg_state - update cgroup memory statistics
* @memcg: the memory cgroup
* @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
* @val: delta to add to the counter, can be negative
*/
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
{
if (mem_cgroup_disabled())
return;
__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
memcg_rstat_updated(memcg);
}
/* idx can be of type enum memcg_stat_item or node_stat_item. */
static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
{
long x = 0;
int cpu;
for_each_possible_cpu(cpu)
x += per_cpu(memcg->vmstats_percpu->state[idx], cpu);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val)
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup *memcg;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
memcg = pn->memcg;
/* Update memcg */
__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
/* Update lruvec */
__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
memcg_rstat_updated(memcg);
}
/**
* __mod_lruvec_state - update lruvec memory statistics
* @lruvec: the lruvec
* @idx: the stat item
* @val: delta to add to the counter, can be negative
*
* The lruvec is the intersection of the NUMA node and a cgroup. This
* function updates the all three counters that are affected by a
* change of state at this level: per-node, per-cgroup, per-lruvec.
*/
void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val)
{
/* Update node */
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
/* Update memcg and lruvec */
if (!mem_cgroup_disabled())
__mod_memcg_lruvec_state(lruvec, idx, val);
}
void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
int val)
{
struct page *head = compound_head(page); /* rmap on tail pages */
struct mem_cgroup *memcg;
pg_data_t *pgdat = page_pgdat(page);
struct lruvec *lruvec;
rcu_read_lock();
memcg = page_memcg(head);
/* Untracked pages have no memcg, no lruvec. Update only the node */
if (!memcg) {
rcu_read_unlock();
__mod_node_page_state(pgdat, idx, val);
return;
}
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
rcu_read_unlock();
}
EXPORT_SYMBOL(__mod_lruvec_page_state);
void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
{
pg_data_t *pgdat = page_pgdat(virt_to_page(p));
struct mem_cgroup *memcg;
struct lruvec *lruvec;
rcu_read_lock();
memcg = mem_cgroup_from_obj(p);
/*
* Untracked pages have no memcg, no lruvec. Update only the
* node. If we reparent the slab objects to the root memcg,
* when we free the slab object, we need to update the per-memcg
* vmstats to keep it correct for the root memcg.
*/
if (!memcg) {
__mod_node_page_state(pgdat, idx, val);
} else {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
rcu_read_unlock();
}
/*
* mod_objcg_mlstate() may be called with irq enabled, so
* mod_memcg_lruvec_state() should be used.
*/
static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
struct pglist_data *pgdat,
enum node_stat_item idx, int nr)
{
struct mem_cgroup *memcg;
struct lruvec *lruvec;
rcu_read_lock();
memcg = obj_cgroup_memcg(objcg);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
mod_memcg_lruvec_state(lruvec, idx, nr);
rcu_read_unlock();
}
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
* @idx: the event item
* @count: the number of events that occurred
*/
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
unsigned long count)
{
if (mem_cgroup_disabled())
return;
__this_cpu_add(memcg->vmstats_percpu->events[idx], count);
memcg_rstat_updated(memcg);
}
static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
{
return READ_ONCE(memcg->vmstats.events[event]);
}
static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
{
long x = 0;
int cpu;
for_each_possible_cpu(cpu)
x += per_cpu(memcg->vmstats_percpu->events[event], cpu);
return x;
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
int nr_pages)
{
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
__count_memcg_events(memcg, PGPGIN, 1);
else {
__count_memcg_events(memcg, PGPGOUT, 1);
nr_pages = -nr_pages; /* for event */
}
__this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages);
}
static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
enum mem_cgroup_events_target target)
{
unsigned long val, next;
val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events);
next = __this_cpu_read(memcg->vmstats_percpu->targets[target]);
/* from time_after() in jiffies.h */
if ((long)(next - val) < 0) {
switch (target) {
case MEM_CGROUP_TARGET_THRESH:
next = val + THRESHOLDS_EVENTS_TARGET;
break;
case MEM_CGROUP_TARGET_SOFTLIMIT:
next = val + SOFTLIMIT_EVENTS_TARGET;
break;
default:
break;
}
__this_cpu_write(memcg->vmstats_percpu->targets[target], next);
return true;
}
return false;
}
/*
* Check events in order.
*
*/
static void memcg_check_events(struct mem_cgroup *memcg, int nid)
{
/* threshold event is triggered in finer grain than soft limit */
if (unlikely(mem_cgroup_event_ratelimit(memcg,
MEM_CGROUP_TARGET_THRESH))) {
bool do_softlimit;
do_softlimit = mem_cgroup_event_ratelimit(memcg,
MEM_CGROUP_TARGET_SOFTLIMIT);
mem_cgroup_threshold(memcg);
if (unlikely(do_softlimit))
mem_cgroup_update_tree(memcg, nid);
}
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
/*
* mm_update_next_owner() may clear mm->owner to NULL
* if it races with swapoff, page migration, etc.
* So this can be called with p == NULL.
*/
if (unlikely(!p))
return NULL;
return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
}
EXPORT_SYMBOL(mem_cgroup_from_task);
static __always_inline struct mem_cgroup *active_memcg(void)
{
if (!in_task())
return this_cpu_read(int_active_memcg);
else
return current->active_memcg;
}
/**
* get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg.
* @mm: mm from which memcg should be extracted. It can be NULL.
*
* Obtain a reference on mm->memcg and returns it if successful. If mm
* is NULL, then the memcg is chosen as follows:
* 1) The active memcg, if set.
* 2) current->mm->memcg, if available
* 3) root memcg
* If mem_cgroup is disabled, NULL is returned.
*/
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return NULL;
/*
* Page cache insertions can happen without an
* actual mm context, e.g. during disk probing
* on boot, loopback IO, acct() writes etc.
*
* No need to css_get on root memcg as the reference
* counting is disabled on the root level in the
* cgroup core. See CSS_NO_REF.
*/
if (unlikely(!mm)) {
memcg = active_memcg();
if (unlikely(memcg)) {
/* remote memcg must hold a ref */
css_get(&memcg->css);
return memcg;
}
mm = current->mm;
if (unlikely(!mm))
return root_mem_cgroup;
}
rcu_read_lock();
do {
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (unlikely(!memcg))
memcg = root_mem_cgroup;
} while (!css_tryget(&memcg->css));
rcu_read_unlock();
return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);
static __always_inline bool memcg_kmem_bypass(void)
{
/* Allow remote memcg charging from any context. */
if (unlikely(active_memcg()))
return false;
/* Memcg to charge can't be determined. */
if (!in_task() || !current->mm || (current->flags & PF_KTHREAD))
return true;
return false;
}
/**
* mem_cgroup_iter - iterate over memory cgroup hierarchy
* @root: hierarchy root
* @prev: previously returned memcg, NULL on first invocation
* @reclaim: cookie for shared reclaim walks, NULL for full walks
*
* Returns references to children of the hierarchy below @root, or
* @root itself, or %NULL after a full round-trip.
*
* Caller must pass the return value in @prev on subsequent
* invocations for reference counting, or use mem_cgroup_iter_break()
* to cancel a hierarchy walk before the round-trip is complete.
*
* Reclaimers can specify a node in @reclaim to divide up the memcgs
* in the hierarchy among all concurrent reclaimers operating on the
* same node.
*/
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
struct mem_cgroup *prev,
struct mem_cgroup_reclaim_cookie *reclaim)
{
struct mem_cgroup_reclaim_iter *iter;
struct cgroup_subsys_state *css = NULL;
struct mem_cgroup *memcg = NULL;
struct mem_cgroup *pos = NULL;
if (mem_cgroup_disabled())
return NULL;
if (!root)