1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
|
/* 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/kernel.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>
#include <linux/shrinker.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_VMALLOC,
MEMCG_KMEM,
MEMCG_ZSWAP_B,
MEMCG_ZSWAPPED,
MEMCG_NR_STAT,
};
enum memcg_memory_event {
MEMCG_LOW,
MEMCG_HIGH,
MEMCG_MAX,
MEMCG_OOM,
MEMCG_OOM_KILL,
MEMCG_OOM_GROUP_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
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;
struct memcg_vmstats;
struct mem_cgroup_reclaim_iter {
struct mem_cgroup *position;
/* scan generation, increased every round-trip */
unsigned int generation;
};
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];
/* Non-hierarchical (CPU aggregated) state */
long state_local[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[] __counted_by(size);
};
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;
};
/*
* 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; /* protected by objcg_lock */
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;
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
unsigned long zswap_max;
/*
* Prevent pages from this memcg from being written back from zswap to
* swap, and from being swapped out on zswap store failures.
*/
bool zswap_writeback;
#endif
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;
CACHELINE_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];
/*
* Hint of reclaim pressure for socket memroy management. Note
* that this indicator should NOT be used in legacy cgroup mode
* where socket memory is accounted/charged separately.
*/
unsigned long socket_pressure;
/* Legacy tcp memory accounting */
bool tcpmem_active;
int tcpmem_pressure;
#ifdef CONFIG_MEMCG_KMEM
int kmemcg_id;
/*
* memcg->objcg is wiped out as a part of the objcg repaprenting
* process. memcg->orig_objcg preserves a pointer (and a reference)
* to the original objcg until the end of live of memcg.
*/
struct obj_cgroup __rcu *objcg;
struct obj_cgroup *orig_objcg;
/* list of inherited objcgs, protected by objcg_lock */
struct list_head objcg_list;
#endif
CACHELINE_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_WALKS_MMU
/* per-memcg mm_struct list */
struct lru_gen_mm_list mm_list;
#endif
struct mem_cgroup_per_node *nodeinfo[];
};
/*
* size of first charge trial.
* TODO: maybe necessary to use big numbers in big irons or dynamic based of the
* workload.
*/
#define MEMCG_CHARGE_BATCH 64U
extern struct mem_cgroup *root_mem_cgroup;
enum page_memcg_data_flags {
/* page->memcg_data is a pointer to an slabobj_ext vector */
MEMCG_DATA_OBJEXTS = (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 __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS
#else /* CONFIG_MEMCG */
#define __FIRST_OBJEXT_FLAG (1UL << 0)
#endif /* CONFIG_MEMCG */
enum objext_flags {
/* the next bit after the last actual flag */
__NR_OBJEXTS_FLAGS = __FIRST_OBJEXT_FLAG,
};
#define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1)
#ifdef CONFIG_MEMCG
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_OBJEXTS, folio);
VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_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_OBJEXTS, folio);
VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_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
* - folio_memcg_lock()
* - exclusive reference
* - mem_cgroup_trylock_pages()
*
* 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 & ~OBJEXTS_FLAGS_MASK);
return obj_cgroup_memcg(objcg);
}
return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
}
/*
* folio_memcg_check - 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 unlike folio_memcg() can take any folio
* as an argument. It has to be used in cases when it's not known if a folio
* has an associated memory cgroup pointer or an object cgroups vector or
* an object cgroup.
*
* For a non-kmem folio any of the following ensures folio and memcg binding
* stability:
*
* - the folio lock
* - LRU isolation
* - lock_folio_memcg()
* - exclusive reference
* - mem_cgroup_trylock_pages()
*
* 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_check(struct folio *folio)
{
/*
* Because folio->memcg_data might be changed asynchronously
* for slabs, READ_ONCE() should be used here.
*/
unsigned long memcg_data = READ_ONCE(folio->memcg_data);
if (memcg_data & MEMCG_DATA_OBJEXTS)
return NULL;
if (memcg_data & MEMCG_DATA_KMEM) {
struct obj_cgroup *objcg;
objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
return obj_cgroup_memcg(objcg);
}
return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
}
static inline struct mem_cgroup *page_memcg_check(struct page *page)
{
if (PageTail(page))
return NULL;
return folio_memcg_check((struct folio *)page);
}
static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
{
struct mem_cgroup *memcg;
rcu_read_lock();
retry:
memcg = obj_cgroup_memcg(objcg);
if (unlikely(!css_tryget(&memcg->css)))
goto retry;
rcu_read_unlock();
return memcg;
}
#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_OBJEXTS, folio);
return folio->memcg_data & MEMCG_DATA_KMEM;
}
#else
static inline bool folio_memcg_kmem(struct folio *folio)
{
return false;
}
#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_calculate_protection 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_unprotected(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
/*
* The root memcg doesn't account charges, and doesn't support
* protection. The target memcg's protection is ignored, see
* mem_cgroup_calculate_protection() and mem_cgroup_protection()
*/
return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) ||
memcg == target;
}
static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
if (mem_cgroup_unprotected(target, memcg))
return false;
return READ_ONCE(memcg->memory.elow) >=
page_counter_read(&memcg->memory);
}
static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
if (mem_cgroup_unprotected(target, memcg))
return false;
return READ_ONCE(memcg->memory.emin) >=
page_counter_read(&memcg->memory);
}
void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg);
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_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
long nr_pages);
int mem_cgroup_swapin_charge_folio(struct folio *folio, 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_folios(struct folio_batch *folios);
static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
{
if (mem_cgroup_disabled())
return;
__mem_cgroup_uncharge_folios(folios);
}
void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages);
void mem_cgroup_replace_folio(struct folio *old, struct folio *new);
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 mem_cgroup *get_mem_cgroup_from_current(void);
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)
{
if (objcg)
percpu_ref_put(&objcg->refcnt);
}
static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
{
return !memcg || css_tryget(&memcg->css);
}
static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
{
return !memcg || css_tryget_online(&memcg->css);
}
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 *);
void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
int (*)(struct task_struct *, void *), void *arg);
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);
#ifdef CONFIG_SHRINKER_DEBUG
static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg)
{
return memcg ? cgroup_ino(memcg->css.cgroup) : 0;
}
struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino);
#endif
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.
*/
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
return mem_cgroup_from_css(memcg->css.parent);
}
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_folio(struct folio *folio);
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(gfp_t gfp_mask);
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);
void folio_memcg_lock(struct folio *folio);
void folio_memcg_unlock(struct folio *folio);
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
/* try to stablize folio_memcg() for all the pages in a memcg */
static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
{
rcu_read_lock();
if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account))
return true;
rcu_read_unlock();
return false;
}
static inline void mem_cgroup_unlock_pages(void)
{
rcu_read_unlock();
}
/* 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 void mod_memcg_page_state(struct page *page,
int idx, int val)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
rcu_read_lock();
memcg = page_memcg(page);
if (memcg)
mod_memcg_state(memcg, idx, val);
rcu_read_unlock();
}
unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
long x;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
x = READ_ONCE(pn->lruvec_stats.state[idx]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
long x = 0;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val);
void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
int val)
{
unsigned long flags;
local_irq_save(flags);
__mod_lruvec_kmem_state(p, idx, val);
local_irq_restore(flags);
}
static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
unsigned long flags;
local_irq_save(flags);
__mod_memcg_lruvec_state(lruvec, idx, val);
local_irq_restore(flags);
}
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
unsigned long count);
static inline void count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
unsigned long flags;
local_irq_save(flags);
__count_memcg_events(memcg, idx, count);
local_irq_restore(flags);
}
static inline void count_memcg_folio_events(struct folio *folio,
enum vm_event_item idx, unsigned long nr)
{
struct mem_cgroup *memcg = folio_memcg(folio);
if (memcg)
count_memcg_events(memcg, idx, nr);
}
static inline void count_memcg_event_mm(struct mm_struct *mm,
enum vm_event_item idx)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
rcu_read_lock();
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (likely(memcg))
count_memcg_events(memcg, idx, 1);
rcu_read_unlock();
}
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
event == MEMCG_SWAP_FAIL;
atomic_long_inc(&memcg->memory_events_local[event]);
if (!swap_event)
cgroup_file_notify(&memcg->events_local_file);
do {
atomic_long_inc(&memcg->memory_events[event]);
if (swap_event)
cgroup_file_notify(&memcg->swap_events_file);
else
cgroup_file_notify(&memcg->events_file);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
break;
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
break;
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
}
static inline void memcg_memory_event_mm(struct mm_struct *mm,
enum memcg_memory_event event)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
rcu_read_lock();
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (likely(memcg))
memcg_memory_event(memcg, event);
rcu_read_unlock();
}
void split_page_memcg(struct page *head, int old_order, int new_order);
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
#else /* CONFIG_MEMCG */
#define MEM_CGROUP_ID_SHIFT 0
static inline struct mem_cgroup *folio_memcg(struct folio *folio)
{
return NULL;
}
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return NULL;
}
static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
WARN_ON_ONCE(!rcu_read_lock_held());
return NULL;
}
static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
{
return NULL;
}
static inline struct mem_cgroup *page_memcg_check(struct page *page)
{
return NULL;
}
static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
{
return NULL;
}
static inline bool folio_memcg_kmem(struct folio *folio)
{
return false;
}
static inline bool PageMemcgKmem(struct page *page)
{
return false;
}
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
return true;
}
static inline bool mem_cgroup_disabled(void)
{
return true;
}
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
}
static inline void memcg_memory_event_mm(struct mm_struct *mm,
enum memcg_memory_event event)
{
}
static inline void mem_cgroup_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg,
unsigned long *min,
unsigned long *low)
{
*min = *low = 0;
}
static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg)
{
}
static inline bool mem_cgroup_unprotected(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
return true;
}
static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
return false;
}
static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
struct mem_cgroup *memcg)
{
return false;
}
static inline void mem_cgroup_commit_charge(struct folio *folio,
struct mem_cgroup *memcg)
{
}
static inline int mem_cgroup_charge(struct folio *folio,
struct mm_struct *mm, gfp_t gfp)
{
return 0;
}
static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg,
gfp_t gfp, long nr_pages)
{
return 0;
}
static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
struct mm_struct *mm, gfp_t gfp, swp_entry_t entry)
{
return 0;
}
static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
{
}
static inline void mem_cgroup_uncharge(struct folio *folio)
{
}
static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
{
}
static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
unsigned int nr_pages)
{
}
static inline void mem_cgroup_replace_folio(struct folio *old,
struct folio *new)
{
}
static inline void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
}
static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
struct pglist_data *pgdat)
{
return &pgdat->__lruvec;
}
static inline struct lruvec *folio_lruvec(struct folio *folio)
{
struct pglist_data *pgdat = folio_pgdat(folio);
return &pgdat->__lruvec;
}
static inline
void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
return NULL;
}
static inline bool mm_match_cgroup(struct mm_struct *mm,
struct mem_cgroup *memcg)
{
return true;
}
static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
return NULL;
}
static inline struct mem_cgroup *get_mem_cgroup_from_current(void)
{
return NULL;
}
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
{
return NULL;
}
static inline void obj_cgroup_put(struct obj_cgroup *objcg)
{
}
static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
{
return true;
}
static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
{
return true;
}
static inline void mem_cgroup_put(struct mem_cgroup *memcg)
{
}
static inline struct lruvec *folio_lruvec_lock(struct folio *folio)
{
struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irq(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flagsp)
{
struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
return &pgdat->__lruvec;
}
static inline struct mem_cgroup *
mem_cgroup_iter(struct mem_cgroup *root,
struct mem_cgroup *prev,
struct mem_cgroup_reclaim_cookie *reclaim)
{
return NULL;
}
static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
struct mem_cgroup *prev)
{
}
static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
int (*fn)(struct task_struct *, void *), void *arg)
{
}
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
return 0;
}
static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
WARN_ON_ONCE(id);
/* XXX: This should always return root_mem_cgroup */
return NULL;
}
#ifdef CONFIG_SHRINKER_DEBUG
static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg)
{
return 0;
}
static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino)
{
return NULL;
}
#endif
static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
{
return NULL;
}
static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
{
return NULL;
}
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
{
return true;
}
static inline
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
enum lru_list lru, int zone_idx)
{
return 0;
}
static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
return 0;
}
static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
{
return 0;
}
static inline void
mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
{
}
static inline void
mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{
}
static inline void folio_memcg_lock(struct folio *folio)
{
}
static inline void folio_memcg_unlock(struct folio *folio)
{
}
static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
{
/* to match folio_memcg_rcu() */
rcu_read_lock();
return true;
}
static inline void mem_cgroup_unlock_pages(void)
{
rcu_read_unlock();
}
static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
{
}
static inline void mem_cgroup_enter_user_fault(void)
{
}
static inline void mem_cgroup_exit_user_fault(void)
{
}
static inline bool task_in_memcg_oom(struct task_struct *p)
{
return false;
}
static inline bool mem_cgroup_oom_synchronize(bool wait)
{
return false;
}
static inline struct mem_cgroup *mem_cgroup_get_oom_group(
struct task_struct *victim, struct mem_cgroup *oom_domain)
{
return NULL;
}
static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
{
}
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
int idx,
int nr)
{
}
static inline void mod_memcg_state(struct mem_cgroup *memcg,
int idx,
int nr)
{
}
static inline void mod_memcg_page_state(struct page *page,
int idx, int val)
{
}
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{
return 0;
}
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
return node_page_state(lruvec_pgdat(lruvec), idx);
}
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx)
{
return node_page_state(lruvec_pgdat(lruvec), idx);
}
static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
{
}
static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
{
}
static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
}
static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
int val)
{
struct page *page = virt_to_head_page(p);
__mod_node_page_state(page_pgdat(page), idx, val);
}
static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
int val)
{
struct page *page = virt_to_head_page(p);
mod_node_page_state(page_pgdat(page), idx, val);
}
static inline void count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
}
static inline void __count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
}
static inline void count_memcg_folio_events(struct folio *folio,
enum vm_event_item idx, unsigned long nr)
{
}
static inline
void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
{
}
static inline void split_page_memcg(struct page *head, int old_order, int new_order)
{
}
static inline
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned)
{
return 0;
}
#endif /* CONFIG_MEMCG */
/*
* Extended information for slab objects stored as an array in page->memcg_data
* if MEMCG_DATA_OBJEXTS is set.
*/
struct slabobj_ext {
#ifdef CONFIG_MEMCG_KMEM
struct obj_cgroup *objcg;
#endif
#ifdef CONFIG_MEM_ALLOC_PROFILING
union codetag_ref ref;
#endif
} __aligned(8);
static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
{
__mod_lruvec_kmem_state(p, idx, 1);
}
static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
{
__mod_lruvec_kmem_state(p, idx, -1);
}
static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
{
struct mem_cgroup *memcg;
memcg = lruvec_memcg(lruvec);
if (!memcg)
return NULL;
memcg = parent_mem_cgroup(memcg);
if (!memcg)
return NULL;
return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
}
static inline void unlock_page_lruvec(struct lruvec *lruvec)
{
spin_unlock(&lruvec->lru_lock);
}
static inline void unlock_page_lruvec_irq(struct lruvec *lruvec)
{
spin_unlock_irq(&lruvec->lru_lock);
}
static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
unsigned long flags)
{
spin_unlock_irqrestore(&lruvec->lru_lock, flags);
}
/* Test requires a stable page->memcg binding, see page_memcg() */
static inline bool folio_matches_lruvec(struct folio *folio,
struct lruvec *lruvec)
{
return lruvec_pgdat(lruvec) == folio_pgdat(folio) &&
lruvec_memcg(lruvec) == folio_memcg(folio);
}
/* Don't lock again iff page's lruvec locked */
static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
struct lruvec *locked_lruvec)
{
if (locked_lruvec) {
if (folio_matches_lruvec(folio, locked_lruvec))
return locked_lruvec;
unlock_page_lruvec_irq(locked_lruvec);
}
return folio_lruvec_lock_irq(folio);
}
/* Don't lock again iff folio's lruvec locked */
static inline void folio_lruvec_relock_irqsave(struct folio *folio,
struct lruvec **lruvecp, unsigned long *flags)
{
if (*lruvecp) {
if (folio_matches_lruvec(folio, *lruvecp))
return;
unlock_page_lruvec_irqrestore(*lruvecp, *flags);
}
*lruvecp = folio_lruvec_lock_irqsave(folio, flags);
}
#ifdef CONFIG_CGROUP_WRITEBACK
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb);
static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
memcg = folio_memcg(folio);
if (unlikely(memcg && &memcg->css != wb->memcg_css))
mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
}
void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
#else /* CONFIG_CGROUP_WRITEBACK */
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
{
return NULL;
}
static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
unsigned long *pfilepages,
unsigned long *pheadroom,
unsigned long *pdirty,
unsigned long *pwriteback)
{
}
static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
}
static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
{
}
#endif /* CONFIG_CGROUP_WRITEBACK */
struct sock;
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
gfp_t gfp_mask);
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
#ifdef CONFIG_MEMCG
extern struct static_key_false memcg_sockets_enabled_key;
#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
void mem_cgroup_sk_alloc(struct sock *sk);
void mem_cgroup_sk_free(struct sock *sk);
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
return !!memcg->tcpmem_pressure;
do {
if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
return true;
} while ((memcg = parent_mem_cgroup(memcg)));
return false;
}
int alloc_shrinker_info(struct mem_cgroup *memcg);
void free_shrinker_info(struct mem_cgroup *memcg);
void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
void reparent_shrinker_deferred(struct mem_cgroup *memcg);
#else
#define mem_cgroup_sockets_enabled 0
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
static inline void mem_cgroup_sk_free(struct sock *sk) { };
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
{
return false;
}
static inline void set_shrinker_bit(struct mem_cgroup *memcg,
int nid, int shrinker_id)
{
}
#endif
#ifdef CONFIG_MEMCG_KMEM
bool mem_cgroup_kmem_disabled(void);
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
void __memcg_kmem_uncharge_page(struct page *page, int order);
/*
* The returned objcg pointer is safe to use without additional
* protection within a scope. The scope is defined either by
* the current task (similar to the "current" global variable)
* or by set_active_memcg() pair.
* Please, use obj_cgroup_get() to get a reference if the pointer
* needs to be used outside of the local scope.
*/
struct obj_cgroup *current_obj_cgroup(void);
struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio);
static inline struct obj_cgroup *get_obj_cgroup_from_current(void)
{
struct obj_cgroup *objcg = current_obj_cgroup();
if (objcg)
obj_cgroup_get(objcg);
return objcg;
}
int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
extern struct static_key_false memcg_bpf_enabled_key;
static inline bool memcg_bpf_enabled(void)
{
return static_branch_likely(&memcg_bpf_enabled_key);
}
extern struct static_key_false memcg_kmem_online_key;
static inline bool memcg_kmem_online(void)
{
return static_branch_likely(&memcg_kmem_online_key);
}
static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
int order)
{
if (memcg_kmem_online())
return __memcg_kmem_charge_page(page, gfp, order);
return 0;
}
static inline void memcg_kmem_uncharge_page(struct page *page, int order)
{
if (memcg_kmem_online())
__memcg_kmem_uncharge_page(page, order);
}
/*
* A helper for accessing memcg's kmem_id, used for getting
* corresponding LRU lists.
*/
static inline int memcg_kmem_id(struct mem_cgroup *memcg)
{
return memcg ? memcg->kmemcg_id : -1;
}
struct mem_cgroup *mem_cgroup_from_obj(void *p);
struct mem_cgroup *mem_cgroup_from_slab_obj(void *p);
static inline void count_objcg_event(struct obj_cgroup *objcg,
enum vm_event_item idx)
{
struct mem_cgroup *memcg;
if (!memcg_kmem_online())
return;
rcu_read_lock();
memcg = obj_cgroup_memcg(objcg);
count_memcg_events(memcg, idx, 1);
rcu_read_unlock();
}
#else
static inline bool mem_cgroup_kmem_disabled(void)
{
return true;
}
static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
int order)
{
return 0;
}
static inline void memcg_kmem_uncharge_page(struct page *page, int order)
{
}
static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp,
int order)
{
return 0;
}
static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
{
}
static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
{
return NULL;
}
static inline bool memcg_bpf_enabled(void)
{
return false;
}
static inline bool memcg_kmem_online(void)
{
return false;
}
static inline int memcg_kmem_id(struct mem_cgroup *memcg)
{
return -1;
}
static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
{
return NULL;
}
static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
{
return NULL;
}
static inline void count_objcg_event(struct obj_cgroup *objcg,
enum vm_event_item idx)
{
}
#endif /* CONFIG_MEMCG_KMEM */
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
#else
static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
{
return true;
}
static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg,
size_t size)
{
}
static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
size_t size)
{
}
static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
{
/* if zswap is disabled, do not block pages going to the swapping device */
return true;
}
#endif
#endif /* _LINUX_MEMCONTROL_H */
|