aboutsummaryrefslogtreecommitdiffstats
path: root/mm/memcontrol.c
blob: e93a4db93fbef21af1caf5ffcfbc3acedfb18d52 (plain) (blame)
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
/* memcontrol.c - 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.
 */

#include <linux/res_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.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/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/mm_inline.h>

#include <asm/uaccess.h>

struct cgroup_subsys mem_cgroup_subsys __read_mostly;
static struct kmem_cache *page_cgroup_cache __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES	5

/*
 * Statistics for memory cgroup.
 */
enum mem_cgroup_stat_index {
	/*
	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
	 */
	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as rss */
	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */

	MEM_CGROUP_STAT_NSTATS,
};

struct mem_cgroup_stat_cpu {
	s64 count[MEM_CGROUP_STAT_NSTATS];
} ____cacheline_aligned_in_smp;

struct mem_cgroup_stat {
	struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
};

/*
 * For accounting under irq disable, no need for increment preempt count.
 */
static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat,
		enum mem_cgroup_stat_index idx, int val)
{
	int cpu = smp_processor_id();
	stat->cpustat[cpu].count[idx] += val;
}

static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
		enum mem_cgroup_stat_index idx)
{
	int cpu;
	s64 ret = 0;
	for_each_possible_cpu(cpu)
		ret += stat->cpustat[cpu].count[idx];
	return ret;
}

/*
 * per-zone information in memory controller.
 */
struct mem_cgroup_per_zone {
	/*
	 * spin_lock to protect the per cgroup LRU
	 */
	spinlock_t		lru_lock;
	struct list_head	lists[NR_LRU_LISTS];
	unsigned long		count[NR_LRU_LISTS];
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])

struct mem_cgroup_per_node {
	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};

struct mem_cgroup_lru_info {
	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
};

/*
 * 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.
 *
 * TODO: Add a water mark for the memory controller. Reclaim will begin when
 * we hit the water mark. May be even add a low water mark, such that
 * no reclaim occurs from a cgroup at it's low water mark, this is
 * a feature that will be implemented much later in the future.
 */
struct mem_cgroup {
	struct cgroup_subsys_state css;
	/*
	 * the counter to account for memory usage
	 */
	struct res_counter res;
	/*
	 * Per cgroup active and inactive list, similar to the
	 * per zone LRU lists.
	 */
	struct mem_cgroup_lru_info info;

	int	prev_priority;	/* for recording reclaim priority */
	/*
	 * statistics.
	 */
	struct mem_cgroup_stat stat;
};
static struct mem_cgroup init_mem_cgroup;

/*
 * We use the lower bit of the page->page_cgroup pointer as a bit spin
 * lock.  We need to ensure that page->page_cgroup is at least two
 * byte aligned (based on comments from Nick Piggin).  But since
 * bit_spin_lock doesn't actually set that lock bit in a non-debug
 * uniprocessor kernel, we should avoid setting it here too.
 */
#define PAGE_CGROUP_LOCK_BIT 	0x0
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
#else
#define PAGE_CGROUP_LOCK	0x0
#endif

/*
 * A page_cgroup page is associated with every page descriptor. The
 * page_cgroup helps us identify information about the cgroup
 */
struct page_cgroup {
	struct list_head lru;		/* per cgroup LRU list */
	struct page *page;
	struct mem_cgroup *mem_cgroup;
	int flags;
};
#define PAGE_CGROUP_FLAG_CACHE	   (0x1)	/* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE    (0x2)	/* page is active in this cgroup */
#define PAGE_CGROUP_FLAG_FILE	   (0x4)	/* page is file system backed */
#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8)	/* page is unevictableable */

static int page_cgroup_nid(struct page_cgroup *pc)
{
	return page_to_nid(pc->page);
}

static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
	return page_zonenum(pc->page);
}

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_MAPPED,
	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
};

/*
 * Always modified under lru lock. Then, not necessary to preempt_disable()
 */
static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
					bool charge)
{
	int val = (charge)? 1 : -1;
	struct mem_cgroup_stat *stat = &mem->stat;

	VM_BUG_ON(!irqs_disabled());
	if (flags & PAGE_CGROUP_FLAG_CACHE)
		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
	else
		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);

	if (charge)
		__mem_cgroup_stat_add_safe(stat,
				MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
	else
		__mem_cgroup_stat_add_safe(stat,
				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
}

static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}

static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
	struct mem_cgroup *mem = pc->mem_cgroup;
	int nid = page_cgroup_nid(pc);
	int zid = page_cgroup_zid(pc);

	return mem_cgroup_zoneinfo(mem, nid, zid);
}

static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
					enum lru_list idx)
{
	int nid, zid;
	struct mem_cgroup_per_zone *mz;
	u64 total = 0;

	for_each_online_node(nid)
		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
			mz = mem_cgroup_zoneinfo(mem, nid, zid);
			total += MEM_CGROUP_ZSTAT(mz, idx);
		}
	return total;
}

static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont,
				mem_cgroup_subsys_id), struct mem_cgroup,
				css);
}

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 container_of(task_subsys_state(p, mem_cgroup_subsys_id),
				struct mem_cgroup, css);
}

static inline int page_cgroup_locked(struct page *page)
{
	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}

static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
{
	VM_BUG_ON(!page_cgroup_locked(page));
	page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
}

struct page_cgroup *page_get_page_cgroup(struct page *page)
{
	return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
}

static void lock_page_cgroup(struct page *page)
{
	bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}

static int try_lock_page_cgroup(struct page *page)
{
	return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}

static void unlock_page_cgroup(struct page *page)
{
	bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}

static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
			struct page_cgroup *pc)
{
	int lru = LRU_BASE;

	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
		lru = LRU_UNEVICTABLE;
	else {
		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
			lru += LRU_ACTIVE;
		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
			lru += LRU_FILE;
	}

	MEM_CGROUP_ZSTAT(mz, lru) -= 1;

	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
	list_del(&pc->lru);
}

static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
				struct page_cgroup *pc)
{
	int lru = LRU_BASE;

	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
		lru = LRU_UNEVICTABLE;
	else {
		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
			lru += LRU_ACTIVE;
		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
			lru += LRU_FILE;
	}

	MEM_CGROUP_ZSTAT(mz, lru) += 1;
	list_add(&pc->lru, &mz->lists[lru]);

	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
}

static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
{
	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
	int active    = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
	int file      = pc->flags & PAGE_CGROUP_FLAG_FILE;
	int unevictable = pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE;
	enum lru_list from = unevictable ? LRU_UNEVICTABLE :
				(LRU_FILE * !!file + !!active);

	if (lru == from)
		return;

	MEM_CGROUP_ZSTAT(mz, from) -= 1;

	if (is_unevictable_lru(lru)) {
		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
		pc->flags |= PAGE_CGROUP_FLAG_UNEVICTABLE;
	} else {
		if (is_active_lru(lru))
			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
		else
			pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
		pc->flags &= ~PAGE_CGROUP_FLAG_UNEVICTABLE;
	}

	MEM_CGROUP_ZSTAT(mz, lru) += 1;
	list_move(&pc->lru, &mz->lists[lru]);
}

int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
	int ret;

	task_lock(task);
	ret = task->mm && mm_match_cgroup(task->mm, mem);
	task_unlock(task);
	return ret;
}

/*
 * This routine assumes that the appropriate zone's lru lock is already held
 */
void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
{
	struct page_cgroup *pc;
	struct mem_cgroup_per_zone *mz;
	unsigned long flags;

	if (mem_cgroup_subsys.disabled)
		return;

	/*
	 * We cannot lock_page_cgroup while holding zone's lru_lock,
	 * because other holders of lock_page_cgroup can be interrupted
	 * with an attempt to rotate_reclaimable_page.  But we cannot
	 * safely get to page_cgroup without it, so just try_lock it:
	 * mem_cgroup_isolate_pages allows for page left on wrong list.
	 */
	if (!try_lock_page_cgroup(page))
		return;

	pc = page_get_page_cgroup(page);
	if (pc) {
		mz = page_cgroup_zoneinfo(pc);
		spin_lock_irqsave(&mz->lru_lock, flags);
		__mem_cgroup_move_lists(pc, lru);
		spin_unlock_irqrestore(&mz->lru_lock, flags);
	}
	unlock_page_cgroup(page);
}

/*
 * Calculate mapped_ratio under memory controller. This will be used in
 * vmscan.c for deteremining we have to reclaim mapped pages.
 */
int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
{
	long total, rss;

	/*
	 * usage is recorded in bytes. But, here, we assume the number of
	 * physical pages can be represented by "long" on any arch.
	 */
	total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
	return (int)((rss * 100L) / total);
}

/*
 * prev_priority control...this will be used in memory reclaim path.
 */
int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
{
	return mem->prev_priority;
}

void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
{
	if (priority < mem->prev_priority)
		mem->prev_priority = priority;
}

void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
{
	mem->prev_priority = priority;
}

/*
 * Calculate # of pages to be scanned in this priority/zone.
 * See also vmscan.c
 *
 * priority starts from "DEF_PRIORITY" and decremented in each loop.
 * (see include/linux/mmzone.h)
 */

long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
					int priority, enum lru_list lru)
{
	long nr_pages;
	int nid = zone->zone_pgdat->node_id;
	int zid = zone_idx(zone);
	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);

	nr_pages = MEM_CGROUP_ZSTAT(mz, lru);

	return (nr_pages >> priority);
}

unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
					struct list_head *dst,
					unsigned long *scanned, int order,
					int mode, struct zone *z,
					struct mem_cgroup *mem_cont,
					int active, int file)
{
	unsigned long nr_taken = 0;
	struct page *page;
	unsigned long scan;
	LIST_HEAD(pc_list);
	struct list_head *src;
	struct page_cgroup *pc, *tmp;
	int nid = z->zone_pgdat->node_id;
	int zid = zone_idx(z);
	struct mem_cgroup_per_zone *mz;
	int lru = LRU_FILE * !!file + !!active;

	BUG_ON(!mem_cont);
	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
	src = &mz->lists[lru];

	spin_lock(&mz->lru_lock);
	scan = 0;
	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
		if (scan >= nr_to_scan)
			break;
		page = pc->page;

		if (unlikely(!PageLRU(page)))
			continue;

		/*
		 * TODO: play better with lumpy reclaim, grabbing anything.
		 */
		if (PageUnevictable(page) ||
		    (PageActive(page) && !active) ||
		    (!PageActive(page) && active)) {
			__mem_cgroup_move_lists(pc, page_lru(page));
			continue;
		}

		scan++;
		list_move(&pc->lru, &pc_list);

		if (__isolate_lru_page(page, mode, file) == 0) {
			list_move(&page->lru, dst);
			nr_taken++;
		}
	}

	list_splice(&pc_list, src);
	spin_unlock(&mz->lru_lock);

	*scanned = scan;
	return nr_taken;
}

/*
 * Charge the memory controller for page usage.
 * Return
 * 0 if the charge was successful
 * < 0 if the cgroup is over its limit
 */
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
				gfp_t gfp_mask, enum charge_type ctype,
				struct mem_cgroup *memcg)
{
	struct mem_cgroup *mem;
	struct page_cgroup *pc;
	unsigned long flags;
	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct mem_cgroup_per_zone *mz;

	pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
	if (unlikely(pc == NULL))
		goto err;

	/*
	 * We always charge the cgroup the mm_struct belongs to.
	 * The mm_struct's mem_cgroup changes on task migration if the
	 * thread group leader migrates. It's possible that mm is not
	 * set, if so charge the init_mm (happens for pagecache usage).
	 */
	if (likely(!memcg)) {
		rcu_read_lock();
		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!mem)) {
			rcu_read_unlock();
			kmem_cache_free(page_cgroup_cache, pc);
			return 0;
		}
		/*
		 * For every charge from the cgroup, increment reference count
		 */
		css_get(&mem->css);
		rcu_read_unlock();
	} else {
		mem = memcg;
		css_get(&memcg->css);
	}

	while (res_counter_charge(&mem->res, PAGE_SIZE)) {
		if (!(gfp_mask & __GFP_WAIT))
			goto out;

		if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
			continue;

		/*
		 * try_to_free_mem_cgroup_pages() might not give us a full
		 * picture of reclaim. Some pages are reclaimed and might be
		 * moved to swap cache or just unmapped from the cgroup.
		 * Check the limit again to see if the reclaim reduced the
		 * current usage of the cgroup before giving up
		 */
		if (res_counter_check_under_limit(&mem->res))
			continue;

		if (!nr_retries--) {
			mem_cgroup_out_of_memory(mem, gfp_mask);
			goto out;
		}
	}

	pc->mem_cgroup = mem;
	pc->page = page;
	/*
	 * If a page is accounted as a page cache, insert to inactive list.
	 * If anon, insert to active list.
	 */
	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
		pc->flags = PAGE_CGROUP_FLAG_CACHE;
		if (page_is_file_cache(page))
			pc->flags |= PAGE_CGROUP_FLAG_FILE;
		else
			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
	} else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
		pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
	else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
		pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;

	lock_page_cgroup(page);
	if (unlikely(page_get_page_cgroup(page))) {
		unlock_page_cgroup(page);
		res_counter_uncharge(&mem->res, PAGE_SIZE);
		css_put(&mem->css);
		kmem_cache_free(page_cgroup_cache, pc);
		goto done;
	}
	page_assign_page_cgroup(page, pc);

	mz = page_cgroup_zoneinfo(pc);
	spin_lock_irqsave(&mz->lru_lock, flags);
	__mem_cgroup_add_list(mz, pc);
	spin_unlock_irqrestore(&mz->lru_lock, flags);

	unlock_page_cgroup(page);
done:
	return 0;
out:
	css_put(&mem->css);
	kmem_cache_free(page_cgroup_cache, pc);
err:
	return -ENOMEM;
}

int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
{
	if (mem_cgroup_subsys.disabled)
		return 0;

	/*
	 * If already mapped, we don't have to account.
	 * If page cache, page->mapping has address_space.
	 * But page->mapping may have out-of-use anon_vma pointer,
	 * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
	 * is NULL.
  	 */
	if (page_mapped(page) || (page->mapping && !PageAnon(page)))
		return 0;
	if (unlikely(!mm))
		mm = &init_mm;
	return mem_cgroup_charge_common(page, mm, gfp_mask,
				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
}

int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
				gfp_t gfp_mask)
{
	if (mem_cgroup_subsys.disabled)
		return 0;

	/*
	 * Corner case handling. This is called from add_to_page_cache()
	 * in usual. But some FS (shmem) precharges this page before calling it
	 * and call add_to_page_cache() with GFP_NOWAIT.
	 *
	 * For GFP_NOWAIT case, the page may be pre-charged before calling
	 * add_to_page_cache(). (See shmem.c) check it here and avoid to call
	 * charge twice. (It works but has to pay a bit larger cost.)
	 */
	if (!(gfp_mask & __GFP_WAIT)) {
		struct page_cgroup *pc;

		lock_page_cgroup(page);
		pc = page_get_page_cgroup(page);
		if (pc) {
			VM_BUG_ON(pc->page != page);
			VM_BUG_ON(!pc->mem_cgroup);
			unlock_page_cgroup(page);
			return 0;
		}
		unlock_page_cgroup(page);
	}

	if (unlikely(!mm))
		mm = &init_mm;

	return mem_cgroup_charge_common(page, mm, gfp_mask,
				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
}

/*
 * uncharge if !page_mapped(page)
 */
static void
__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
{
	struct page_cgroup *pc;
	struct mem_cgroup *mem;
	struct mem_cgroup_per_zone *mz;
	unsigned long flags;

	if (mem_cgroup_subsys.disabled)
		return;

	/*
	 * Check if our page_cgroup is valid
	 */
	lock_page_cgroup(page);
	pc = page_get_page_cgroup(page);
	if (unlikely(!pc))
		goto unlock;

	VM_BUG_ON(pc->page != page);

	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
	    && ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
		|| page_mapped(page)))
		goto unlock;

	mz = page_cgroup_zoneinfo(pc);
	spin_lock_irqsave(&mz->lru_lock, flags);
	__mem_cgroup_remove_list(mz, pc);
	spin_unlock_irqrestore(&mz->lru_lock, flags);

	page_assign_page_cgroup(page, NULL);
	unlock_page_cgroup(page);

	mem = pc->mem_cgroup;
	res_counter_uncharge(&mem->res, PAGE_SIZE);
	css_put(&mem->css);

	kmem_cache_free(page_cgroup_cache, pc);
	return;
unlock:
	unlock_page_cgroup(page);
}

void mem_cgroup_uncharge_page(struct page *page)
{
	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
}

void mem_cgroup_uncharge_cache_page(struct page *page)
{
	VM_BUG_ON(page_mapped(page));
	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}

/*
 * Before starting migration, account against new page.
 */
int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
{
	struct page_cgroup *pc;
	struct mem_cgroup *mem = NULL;
	enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
	int ret = 0;

	if (mem_cgroup_subsys.disabled)
		return 0;

	lock_page_cgroup(page);
	pc = page_get_page_cgroup(page);
	if (pc) {
		mem = pc->mem_cgroup;
		css_get(&mem->css);
		if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
			if (page_is_file_cache(page))
				ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
			else
				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
		}
	}
	unlock_page_cgroup(page);
	if (mem) {
		ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
			ctype, mem);
		css_put(&mem->css);
	}
	return ret;
}

/* remove redundant charge if migration failed*/
void mem_cgroup_end_migration(struct page *newpage)
{
	/*
	 * At success, page->mapping is not NULL.
	 * special rollback care is necessary when
	 * 1. at migration failure. (newpage->mapping is cleared in this case)
	 * 2. the newpage was moved but not remapped again because the task
	 *    exits and the newpage is obsolete. In this case, the new page
	 *    may be a swapcache. So, we just call mem_cgroup_uncharge_page()
	 *    always for avoiding mess. The  page_cgroup will be removed if
	 *    unnecessary. File cache pages is still on radix-tree. Don't
	 *    care it.
	 */
	if (!newpage->mapping)
		__mem_cgroup_uncharge_common(newpage,
					 MEM_CGROUP_CHARGE_TYPE_FORCE);
	else if (PageAnon(newpage))
		mem_cgroup_uncharge_page(newpage);
}

/*
 * A call to try to shrink memory usage under specified resource controller.
 * This is typically used for page reclaiming for shmem for reducing side
 * effect of page allocation from shmem, which is used by some mem_cgroup.
 */
int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
{
	struct mem_cgroup *mem;
	int progress = 0;
	int retry = MEM_CGROUP_RECLAIM_RETRIES;

	if (mem_cgroup_subsys.disabled)
		return 0;
	if (!mm)
		return 0;

	rcu_read_lock();
	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
	if (unlikely(!mem)) {
		rcu_read_unlock();
		return 0;
	}
	css_get(&mem->css);
	rcu_read_unlock();

	do {
		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
		progress += res_counter_check_under_limit(&mem->res);
	} while (!progress && --retry);

	css_put(&mem->css);
	if (!retry)
		return -ENOMEM;
	return 0;
}

int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
{

	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
	int progress;
	int ret = 0;

	while (res_counter_set_limit(&memcg->res, val)) {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}
		if (!retry_count) {
			ret = -EBUSY;
			break;
		}
		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
		if (!progress)
			retry_count--;
	}
	return ret;
}


/*
 * This routine traverse page_cgroup in given list and drop them all.
 * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
 */
#define FORCE_UNCHARGE_BATCH	(128)
static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
			    struct mem_cgroup_per_zone *mz,
			    enum lru_list lru)
{
	struct page_cgroup *pc;
	struct page *page;
	int count = FORCE_UNCHARGE_BATCH;
	unsigned long flags;
	struct list_head *list;

	list = &mz->lists[lru];

	spin_lock_irqsave(&mz->lru_lock, flags);
	while (!list_empty(list)) {
		pc = list_entry(list->prev, struct page_cgroup, lru);
		page = pc->page;
		get_page(page);
		spin_unlock_irqrestore(&mz->lru_lock, flags);
		/*
		 * Check if this page is on LRU. !LRU page can be found
		 * if it's under page migration.
		 */
		if (PageLRU(page)) {
			__mem_cgroup_uncharge_common(page,
					MEM_CGROUP_CHARGE_TYPE_FORCE);
			put_page(page);
			if (--count <= 0) {
				count = FORCE_UNCHARGE_BATCH;
				cond_resched();
			}
		} else
			cond_resched();
		spin_lock_irqsave(&mz->lru_lock, flags);
	}
	spin_unlock_irqrestore(&mz->lru_lock, flags);
}

/*
 * make mem_cgroup's charge to be 0 if there is no task.
 * This enables deleting this mem_cgroup.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *mem)
{
	int ret = -EBUSY;
	int node, zid;

	css_get(&mem->css);
	/*
	 * page reclaim code (kswapd etc..) will move pages between
	 * active_list <-> inactive_list while we don't take a lock.
	 * So, we have to do loop here until all lists are empty.
	 */
	while (mem->res.usage > 0) {
		if (atomic_read(&mem->css.cgroup->count) > 0)
			goto out;
		for_each_node_state(node, N_POSSIBLE)
			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
				struct mem_cgroup_per_zone *mz;
				enum lru_list l;
				mz = mem_cgroup_zoneinfo(mem, node, zid);
				for_each_lru(l)
					mem_cgroup_force_empty_list(mem, mz, l);
			}
	}
	ret = 0;
out:
	css_put(&mem->css);
	return ret;
}

static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
				    cft->private);
}
/*
 * The user of this function is...
 * RES_LIMIT.
 */
static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
			    const char *buffer)
{
	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
	unsigned long long val;
	int ret;

	switch (cft->private) {
	case RES_LIMIT:
		/* This function does all necessary parse...reuse it */
		ret = res_counter_memparse_write_strategy(buffer, &val);
		if (!ret)
			ret = mem_cgroup_resize_limit(memcg, val);
		break;
	default:
		ret = -EINVAL; /* should be BUG() ? */
		break;
	}
	return ret;
}

static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
	struct mem_cgroup *mem;

	mem = mem_cgroup_from_cont(cont);
	switch (event) {
	case RES_MAX_USAGE:
		res_counter_reset_max(&mem->res);
		break;
	case RES_FAILCNT:
		res_counter_reset_failcnt(&mem->res);
		break;
	}
	return 0;
}

static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
{
	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
}

static const struct mem_cgroup_stat_desc {
	const char *msg;
	u64 unit;
} mem_cgroup_stat_desc[] = {
	[MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
	[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
	[MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
	[MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
};

static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
				 struct cgroup_map_cb *cb)
{
	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
	struct mem_cgroup_stat *stat = &mem_cont->stat;
	int i;

	for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
		s64 val;

		val = mem_cgroup_read_stat(stat, i);
		val *= mem_cgroup_stat_desc[i].unit;
		cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
	}
	/* showing # of active pages */
	{
		unsigned long active_anon, inactive_anon;
		unsigned long active_file, inactive_file;
		unsigned long unevictable;

		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_INACTIVE_ANON);
		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_ACTIVE_ANON);
		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_INACTIVE_FILE);
		active_file = mem_cgroup_get_all_zonestat(mem_cont,
						LRU_ACTIVE_FILE);
		unevictable = mem_cgroup_get_all_zonestat(mem_cont,
							LRU_UNEVICTABLE);

		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);

	}
	return 0;
}

static struct cftype mem_cgroup_files[] = {
	{
		.name = "usage_in_bytes",
		.private = RES_USAGE,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "max_usage_in_bytes",
		.private = RES_MAX_USAGE,
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "limit_in_bytes",
		.private = RES_LIMIT,
		.write_string = mem_cgroup_write,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "failcnt",
		.private = RES_FAILCNT,
		.trigger = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read,
	},
	{
		.name = "force_empty",
		.trigger = mem_force_empty_write,
	},
	{
		.name = "stat",
		.read_map = mem_control_stat_show,
	},
};

static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup_per_zone *mz;
	enum lru_list l;
	int zone, tmp = node;
	/*
	 * This routine is called against possible nodes.
	 * But it's BUG to call kmalloc() against offline node.
	 *
	 * TODO: this routine can waste much memory for nodes which will
	 *       never be onlined. It's better to use memory hotplug callback
	 *       function.
	 */
	if (!node_state(node, N_NORMAL_MEMORY))
		tmp = -1;
	pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
	if (!pn)
		return 1;

	mem->info.nodeinfo[node] = pn;
	memset(pn, 0, sizeof(*pn));

	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
		mz = &pn->zoneinfo[zone];
		spin_lock_init(&mz->lru_lock);
		for_each_lru(l)
			INIT_LIST_HEAD(&mz->lists[l]);
	}
	return 0;
}

static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
	kfree(mem->info.nodeinfo[node]);
}

static struct mem_cgroup *mem_cgroup_alloc(void)
{
	struct mem_cgroup *mem;

	if (sizeof(*mem) < PAGE_SIZE)
		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
	else
		mem = vmalloc(sizeof(*mem));

	if (mem)
		memset(mem, 0, sizeof(*mem));
	return mem;
}

static void mem_cgroup_free(struct mem_cgroup *mem)
{
	if (sizeof(*mem) < PAGE_SIZE)
		kfree(mem);
	else
		vfree(mem);
}


static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct mem_cgroup *mem;
	int node;

	if (unlikely((cont->parent) == NULL)) {
		mem = &init_mem_cgroup;
		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
	} else {
		mem = mem_cgroup_alloc();
		if (!mem)
			return ERR_PTR(-ENOMEM);
	}

	res_counter_init(&mem->res);

	for_each_node_state(node, N_POSSIBLE)
		if (alloc_mem_cgroup_per_zone_info(mem, node))
			goto free_out;

	return &mem->css;
free_out:
	for_each_node_state(node, N_POSSIBLE)
		free_mem_cgroup_per_zone_info(mem, node);
	if (cont->parent != NULL)
		mem_cgroup_free(mem);
	return ERR_PTR(-ENOMEM);
}

static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
					struct cgroup *cont)
{
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
	mem_cgroup_force_empty(mem);
}

static void mem_cgroup_destroy(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	int node;
	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);

	for_each_node_state(node, N_POSSIBLE)
		free_mem_cgroup_per_zone_info(mem, node);

	mem_cgroup_free(mem_cgroup_from_cont(cont));
}

static int mem_cgroup_populate(struct cgroup_subsys *ss,
				struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, mem_cgroup_files,
					ARRAY_SIZE(mem_cgroup_files));
}

static void mem_cgroup_move_task(struct cgroup_subsys *ss,
				struct cgroup *cont,
				struct cgroup *old_cont,
				struct task_struct *p)
{
	struct mm_struct *mm;
	struct mem_cgroup *mem, *old_mem;

	mm = get_task_mm(p);
	if (mm == NULL)
		return;

	mem = mem_cgroup_from_cont(cont);
	old_mem = mem_cgroup_from_cont(old_cont);

	/*
	 * Only thread group leaders are allowed to migrate, the mm_struct is
	 * in effect owned by the leader
	 */
	if (!thread_group_leader(p))
		goto out;

out:
	mmput(mm);
}

struct cgroup_subsys mem_cgroup_subsys = {
	.name = "memory",
	.subsys_id = mem_cgroup_subsys_id,
	.create = mem_cgroup_create,
	.pre_destroy = mem_cgroup_pre_destroy,
	.destroy = mem_cgroup_destroy,
	.populate = mem_cgroup_populate,
	.attach = mem_cgroup_move_task,
	.early_init = 0,
};