summaryrefslogtreecommitdiff
path: root/mm/memcontrol.c
blob: 960371788687720de58cdf146b900d6efb66c04c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
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
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
// SPDX-License-Identifier: GPL-2.0-or-later
/* 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>
 *
 * Memory thresholds
 * Copyright (C) 2009 Nokia Corporation
 * Author: Kirill A. Shutemov
 *
 * Kernel Memory Controller
 * Copyright (C) 2012 Parallels Inc. and Google Inc.
 * Authors: Glauber Costa and Suleiman Souhlal
 *
 * Native page reclaim
 * Charge lifetime sanitation
 * Lockless page tracking & accounting
 * Unified hierarchy configuration model
 * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
 *
 * Per memcg lru locking
 * Copyright (C) 2020 Alibaba, Inc, Alex Shi
 */

#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/vm_event_item.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/parser.h>
#include <linux/vmpressure.h>
#include <linux/memremap.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/resume_user_mode.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
#include <linux/sched/isolation.h>
#include <linux/kmemleak.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include "slab.h"
#include "memcontrol-v1.h"

#include <linux/uaccess.h>

#include <trace/events/vmscan.h>

struct cgroup_subsys memory_cgrp_subsys __read_mostly;
EXPORT_SYMBOL(memory_cgrp_subsys);

struct mem_cgroup *root_mem_cgroup __read_mostly;

/* Active memory cgroup to use from an interrupt context */
DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);

/* Socket memory accounting disabled? */
static bool cgroup_memory_nosocket __ro_after_init;

/* Kernel memory accounting disabled? */
static bool cgroup_memory_nokmem __ro_after_init;

/* BPF memory accounting disabled? */
static bool cgroup_memory_nobpf __ro_after_init;

#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif

#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024

static inline bool task_is_dying(void)
{
	return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
		(current->flags & PF_EXITING);
}

/* Some nice accessors for the vmpressure. */
struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
{
	if (!memcg)
		memcg = root_mem_cgroup;
	return &memcg->vmpressure;
}

struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
{
	return container_of(vmpr, struct mem_cgroup, vmpressure);
}

#define CURRENT_OBJCG_UPDATE_BIT 0
#define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT)

static DEFINE_SPINLOCK(objcg_lock);

bool mem_cgroup_kmem_disabled(void)
{
	return cgroup_memory_nokmem;
}

static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
				      unsigned int nr_pages);

static void obj_cgroup_release(struct percpu_ref *ref)
{
	struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
	unsigned int nr_bytes;
	unsigned int nr_pages;
	unsigned long flags;

	/*
	 * At this point all allocated objects are freed, and
	 * objcg->nr_charged_bytes can't have an arbitrary byte value.
	 * However, it can be PAGE_SIZE or (x * PAGE_SIZE).
	 *
	 * The following sequence can lead to it:
	 * 1) CPU0: objcg == stock->cached_objcg
	 * 2) CPU1: we do a small allocation (e.g. 92 bytes),
	 *          PAGE_SIZE bytes are charged
	 * 3) CPU1: a process from another memcg is allocating something,
	 *          the stock if flushed,
	 *          objcg->nr_charged_bytes = PAGE_SIZE - 92
	 * 5) CPU0: we do release this object,
	 *          92 bytes are added to stock->nr_bytes
	 * 6) CPU0: stock is flushed,
	 *          92 bytes are added to objcg->nr_charged_bytes
	 *
	 * In the result, nr_charged_bytes == PAGE_SIZE.
	 * This page will be uncharged in obj_cgroup_release().
	 */
	nr_bytes = atomic_read(&objcg->nr_charged_bytes);
	WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
	nr_pages = nr_bytes >> PAGE_SHIFT;

	if (nr_pages)
		obj_cgroup_uncharge_pages(objcg, nr_pages);

	spin_lock_irqsave(&objcg_lock, flags);
	list_del(&objcg->list);
	spin_unlock_irqrestore(&objcg_lock, flags);

	percpu_ref_exit(ref);
	kfree_rcu(objcg, rcu);
}

static struct obj_cgroup *obj_cgroup_alloc(void)
{
	struct obj_cgroup *objcg;
	int ret;

	objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
	if (!objcg)
		return NULL;

	ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
			      GFP_KERNEL);
	if (ret) {
		kfree(objcg);
		return NULL;
	}
	INIT_LIST_HEAD(&objcg->list);
	return objcg;
}

static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
				  struct mem_cgroup *parent)
{
	struct obj_cgroup *objcg, *iter;

	objcg = rcu_replace_pointer(memcg->objcg, NULL, true);

	spin_lock_irq(&objcg_lock);

	/* 1) Ready to reparent active objcg. */
	list_add(&objcg->list, &memcg->objcg_list);
	/* 2) Reparent active objcg and already reparented objcgs to parent. */
	list_for_each_entry(iter, &memcg->objcg_list, list)
		WRITE_ONCE(iter->memcg, parent);
	/* 3) Move already reparented objcgs to the parent's list */
	list_splice(&memcg->objcg_list, &parent->objcg_list);

	spin_unlock_irq(&objcg_lock);

	percpu_ref_kill(&objcg->refcnt);
}

/*
 * A lot of the calls to the cache allocation functions are expected to be
 * inlined by the compiler. Since the calls to memcg_slab_post_alloc_hook() are
 * conditional to this static branch, we'll have to allow modules that does
 * kmem_cache_alloc and the such to see this symbol as well
 */
DEFINE_STATIC_KEY_FALSE(memcg_kmem_online_key);
EXPORT_SYMBOL(memcg_kmem_online_key);

DEFINE_STATIC_KEY_FALSE(memcg_bpf_enabled_key);
EXPORT_SYMBOL(memcg_bpf_enabled_key);

/**
 * mem_cgroup_css_from_folio - css of the memcg associated with a folio
 * @folio: folio of interest
 *
 * If memcg is bound to the default hierarchy, css of the memcg associated
 * with @folio is returned.  The returned css remains associated with @folio
 * until it is released.
 *
 * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
 * is returned.
 */
struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio)
{
	struct mem_cgroup *memcg = folio_memcg(folio);

	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
		memcg = root_mem_cgroup;

	return &memcg->css;
}

/**
 * page_cgroup_ino - return inode number of the memcg a page is charged to
 * @page: the page
 *
 * Look up the closest online ancestor of the memory cgroup @page is charged to
 * and return its inode number or 0 if @page is not charged to any cgroup. It
 * is safe to call this function without holding a reference to @page.
 *
 * Note, this function is inherently racy, because there is nothing to prevent
 * the cgroup inode from getting torn down and potentially reallocated a moment
 * after page_cgroup_ino() returns, so it only should be used by callers that
 * do not care (such as procfs interfaces).
 */
ino_t page_cgroup_ino(struct page *page)
{
	struct mem_cgroup *memcg;
	unsigned long ino = 0;

	rcu_read_lock();
	/* page_folio() is racy here, but the entire function is racy anyway */
	memcg = folio_memcg_check(page_folio(page));

	while (memcg && !(memcg->css.flags & CSS_ONLINE))
		memcg = parent_mem_cgroup(memcg);
	if (memcg)
		ino = cgroup_ino(memcg->css.cgroup);
	rcu_read_unlock();
	return ino;
}

/* Subset of node_stat_item for memcg stats */
static const unsigned int memcg_node_stat_items[] = {
	NR_INACTIVE_ANON,
	NR_ACTIVE_ANON,
	NR_INACTIVE_FILE,
	NR_ACTIVE_FILE,
	NR_UNEVICTABLE,
	NR_SLAB_RECLAIMABLE_B,
	NR_SLAB_UNRECLAIMABLE_B,
	WORKINGSET_REFAULT_ANON,
	WORKINGSET_REFAULT_FILE,
	WORKINGSET_ACTIVATE_ANON,
	WORKINGSET_ACTIVATE_FILE,
	WORKINGSET_RESTORE_ANON,
	WORKINGSET_RESTORE_FILE,
	WORKINGSET_NODERECLAIM,
	NR_ANON_MAPPED,
	NR_FILE_MAPPED,
	NR_FILE_PAGES,
	NR_FILE_DIRTY,
	NR_WRITEBACK,
	NR_SHMEM,
	NR_SHMEM_THPS,
	NR_FILE_THPS,
	NR_ANON_THPS,
	NR_KERNEL_STACK_KB,
	NR_PAGETABLE,
	NR_SECONDARY_PAGETABLE,
#ifdef CONFIG_SWAP
	NR_SWAPCACHE,
#endif
};

static const unsigned int memcg_stat_items[] = {
	MEMCG_SWAP,
	MEMCG_SOCK,
	MEMCG_PERCPU_B,
	MEMCG_VMALLOC,
	MEMCG_KMEM,
	MEMCG_ZSWAP_B,
	MEMCG_ZSWAPPED,
};

#define NR_MEMCG_NODE_STAT_ITEMS ARRAY_SIZE(memcg_node_stat_items)
#define MEMCG_VMSTAT_SIZE (NR_MEMCG_NODE_STAT_ITEMS + \
			   ARRAY_SIZE(memcg_stat_items))
static int8_t mem_cgroup_stats_index[MEMCG_NR_STAT] __read_mostly;

static void init_memcg_stats(void)
{
	int8_t i, j = 0;

	BUILD_BUG_ON(MEMCG_NR_STAT >= S8_MAX);

	for (i = 0; i < NR_MEMCG_NODE_STAT_ITEMS; ++i)
		mem_cgroup_stats_index[memcg_node_stat_items[i]] = ++j;

	for (i = 0; i < ARRAY_SIZE(memcg_stat_items); ++i)
		mem_cgroup_stats_index[memcg_stat_items[i]] = ++j;
}

static inline int memcg_stats_index(int idx)
{
	return mem_cgroup_stats_index[idx] - 1;
}

struct lruvec_stats_percpu {
	/* Local (CPU and cgroup) state */
	long state[NR_MEMCG_NODE_STAT_ITEMS];

	/* Delta calculation for lockless upward propagation */
	long state_prev[NR_MEMCG_NODE_STAT_ITEMS];
};

struct lruvec_stats {
	/* Aggregated (CPU and subtree) state */
	long state[NR_MEMCG_NODE_STAT_ITEMS];

	/* Non-hierarchical (CPU aggregated) state */
	long state_local[NR_MEMCG_NODE_STAT_ITEMS];

	/* Pending child counts during tree propagation */
	long state_pending[NR_MEMCG_NODE_STAT_ITEMS];
};

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

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

	i = memcg_stats_index(idx);
	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return 0;

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	x = READ_ONCE(pn->lruvec_stats->state[i]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

unsigned long lruvec_page_state_local(struct lruvec *lruvec,
				      enum node_stat_item idx)
{
	struct mem_cgroup_per_node *pn;
	long x;
	int i;

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

	i = memcg_stats_index(idx);
	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return 0;

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	x = READ_ONCE(pn->lruvec_stats->state_local[i]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

/* Subset of vm_event_item to report for memcg event stats */
static const unsigned int memcg_vm_event_stat[] = {
	PGPGIN,
	PGPGOUT,
	PGSCAN_KSWAPD,
	PGSCAN_DIRECT,
	PGSCAN_KHUGEPAGED,
	PGSTEAL_KSWAPD,
	PGSTEAL_DIRECT,
	PGSTEAL_KHUGEPAGED,
	PGFAULT,
	PGMAJFAULT,
	PGREFILL,
	PGACTIVATE,
	PGDEACTIVATE,
	PGLAZYFREE,
	PGLAZYFREED,
#ifdef CONFIG_ZSWAP
	ZSWPIN,
	ZSWPOUT,
	ZSWPWB,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	THP_FAULT_ALLOC,
	THP_COLLAPSE_ALLOC,
	THP_SWPOUT,
	THP_SWPOUT_FALLBACK,
#endif
};

#define NR_MEMCG_EVENTS ARRAY_SIZE(memcg_vm_event_stat)
static int8_t mem_cgroup_events_index[NR_VM_EVENT_ITEMS] __read_mostly;

static void init_memcg_events(void)
{
	int8_t i;

	BUILD_BUG_ON(NR_VM_EVENT_ITEMS >= S8_MAX);

	for (i = 0; i < NR_MEMCG_EVENTS; ++i)
		mem_cgroup_events_index[memcg_vm_event_stat[i]] = i + 1;
}

static inline int memcg_events_index(enum vm_event_item idx)
{
	return mem_cgroup_events_index[idx] - 1;
}

struct memcg_vmstats_percpu {
	/* Stats updates since the last flush */
	unsigned int			stats_updates;

	/* Cached pointers for fast iteration in memcg_rstat_updated() */
	struct memcg_vmstats_percpu	*parent;
	struct memcg_vmstats		*vmstats;

	/* The above should fit a single cacheline for memcg_rstat_updated() */

	/* Local (CPU and cgroup) page state & events */
	long			state[MEMCG_VMSTAT_SIZE];
	unsigned long		events[NR_MEMCG_EVENTS];

	/* Delta calculation for lockless upward propagation */
	long			state_prev[MEMCG_VMSTAT_SIZE];
	unsigned long		events_prev[NR_MEMCG_EVENTS];

	/* Cgroup1: threshold notifications & softlimit tree updates */
	unsigned long		nr_page_events;
	unsigned long		targets[MEM_CGROUP_NTARGETS];
} ____cacheline_aligned;

struct memcg_vmstats {
	/* Aggregated (CPU and subtree) page state & events */
	long			state[MEMCG_VMSTAT_SIZE];
	unsigned long		events[NR_MEMCG_EVENTS];

	/* Non-hierarchical (CPU aggregated) page state & events */
	long			state_local[MEMCG_VMSTAT_SIZE];
	unsigned long		events_local[NR_MEMCG_EVENTS];

	/* Pending child counts during tree propagation */
	long			state_pending[MEMCG_VMSTAT_SIZE];
	unsigned long		events_pending[NR_MEMCG_EVENTS];

	/* Stats updates since the last flush */
	atomic64_t		stats_updates;
};

/*
 * memcg and lruvec stats flushing
 *
 * Many codepaths leading to stats update or read are performance sensitive and
 * adding stats flushing in such codepaths is not desirable. So, to optimize the
 * flushing the kernel does:
 *
 * 1) Periodically and asynchronously flush the stats every 2 seconds to not let
 *    rstat update tree grow unbounded.
 *
 * 2) Flush the stats synchronously on reader side only when there are more than
 *    (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
 *    will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
 *    only for 2 seconds due to (1).
 */
static void flush_memcg_stats_dwork(struct work_struct *w);
static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
static u64 flush_last_time;

#define FLUSH_TIME (2UL*HZ)

/*
 * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
 * not rely on this as part of an acquired spinlock_t lock. These functions are
 * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
 * is sufficient.
 */
static void memcg_stats_lock(void)
{
	preempt_disable_nested();
	VM_WARN_ON_IRQS_ENABLED();
}

static void __memcg_stats_lock(void)
{
	preempt_disable_nested();
}

static void memcg_stats_unlock(void)
{
	preempt_enable_nested();
}


static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
{
	return atomic64_read(&vmstats->stats_updates) >
		MEMCG_CHARGE_BATCH * num_online_cpus();
}

static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
{
	struct memcg_vmstats_percpu *statc;
	int cpu = smp_processor_id();
	unsigned int stats_updates;

	if (!val)
		return;

	cgroup_rstat_updated(memcg->css.cgroup, cpu);
	statc = this_cpu_ptr(memcg->vmstats_percpu);
	for (; statc; statc = statc->parent) {
		stats_updates = READ_ONCE(statc->stats_updates) + abs(val);
		WRITE_ONCE(statc->stats_updates, stats_updates);
		if (stats_updates < MEMCG_CHARGE_BATCH)
			continue;

		/*
		 * If @memcg is already flush-able, increasing stats_updates is
		 * redundant. Avoid the overhead of the atomic update.
		 */
		if (!memcg_vmstats_needs_flush(statc->vmstats))
			atomic64_add(stats_updates,
				     &statc->vmstats->stats_updates);
		WRITE_ONCE(statc->stats_updates, 0);
	}
}

static void do_flush_stats(struct mem_cgroup *memcg)
{
	if (mem_cgroup_is_root(memcg))
		WRITE_ONCE(flush_last_time, jiffies_64);

	cgroup_rstat_flush(memcg->css.cgroup);
}

/*
 * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree
 * @memcg: root of the subtree to flush
 *
 * Flushing is serialized by the underlying global rstat lock. There is also a
 * minimum amount of work to be done even if there are no stat updates to flush.
 * Hence, we only flush the stats if the updates delta exceeds a threshold. This
 * avoids unnecessary work and contention on the underlying lock.
 */
void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
{
	if (mem_cgroup_disabled())
		return;

	if (!memcg)
		memcg = root_mem_cgroup;

	if (memcg_vmstats_needs_flush(memcg->vmstats))
		do_flush_stats(memcg);
}

void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
{
	/* Only flush if the periodic flusher is one full cycle late */
	if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
		mem_cgroup_flush_stats(memcg);
}

static void flush_memcg_stats_dwork(struct work_struct *w)
{
	/*
	 * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
	 * in latency-sensitive paths is as cheap as possible.
	 */
	do_flush_stats(root_mem_cgroup);
	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
}

unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{
	long x;
	int i = memcg_stats_index(idx);

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return 0;

	x = READ_ONCE(memcg->vmstats->state[i]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

static int memcg_page_state_unit(int item);

/*
 * Normalize the value passed into memcg_rstat_updated() to be in pages. Round
 * up non-zero sub-page updates to 1 page as zero page updates are ignored.
 */
static int memcg_state_val_in_pages(int idx, int val)
{
	int unit = memcg_page_state_unit(idx);

	if (!val || unit == PAGE_SIZE)
		return val;
	else
		return max(val * unit / PAGE_SIZE, 1UL);
}

/**
 * __mod_memcg_state - update cgroup memory statistics
 * @memcg: the memory cgroup
 * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
 * @val: delta to add to the counter, can be negative
 */
void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
		       int val)
{
	int i = memcg_stats_index(idx);

	if (mem_cgroup_disabled())
		return;

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return;

	__this_cpu_add(memcg->vmstats_percpu->state[i], val);
	memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val));
}

/* idx can be of type enum memcg_stat_item or node_stat_item. */
unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
{
	long x;
	int i = memcg_stats_index(idx);

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return 0;

	x = READ_ONCE(memcg->vmstats->state_local[i]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

static void __mod_memcg_lruvec_state(struct lruvec *lruvec,
				     enum node_stat_item idx,
				     int val)
{
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup *memcg;
	int i = memcg_stats_index(idx);

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return;

	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	memcg = pn->memcg;

	/*
	 * The caller from rmap relies on disabled preemption because they never
	 * update their counter from in-interrupt context. For these two
	 * counters we check that the update is never performed from an
	 * interrupt context while other caller need to have disabled interrupt.
	 */
	__memcg_stats_lock();
	if (IS_ENABLED(CONFIG_DEBUG_VM)) {
		switch (idx) {
		case NR_ANON_MAPPED:
		case NR_FILE_MAPPED:
		case NR_ANON_THPS:
			WARN_ON_ONCE(!in_task());
			break;
		default:
			VM_WARN_ON_IRQS_ENABLED();
		}
	}

	/* Update memcg */
	__this_cpu_add(memcg->vmstats_percpu->state[i], val);

	/* Update lruvec */
	__this_cpu_add(pn->lruvec_stats_percpu->state[i], val);

	memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val));
	memcg_stats_unlock();
}

/**
 * __mod_lruvec_state - update lruvec memory statistics
 * @lruvec: the lruvec
 * @idx: the stat item
 * @val: delta to add to the counter, can be negative
 *
 * The lruvec is the intersection of the NUMA node and a cgroup. This
 * function updates the all three counters that are affected by a
 * change of state at this level: per-node, per-cgroup, per-lruvec.
 */
void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
			int val)
{
	/* Update node */
	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);

	/* Update memcg and lruvec */
	if (!mem_cgroup_disabled())
		__mod_memcg_lruvec_state(lruvec, idx, val);
}

void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx,
			     int val)
{
	struct mem_cgroup *memcg;
	pg_data_t *pgdat = folio_pgdat(folio);
	struct lruvec *lruvec;

	rcu_read_lock();
	memcg = folio_memcg(folio);
	/* Untracked pages have no memcg, no lruvec. Update only the node */
	if (!memcg) {
		rcu_read_unlock();
		__mod_node_page_state(pgdat, idx, val);
		return;
	}

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	__mod_lruvec_state(lruvec, idx, val);
	rcu_read_unlock();
}
EXPORT_SYMBOL(__lruvec_stat_mod_folio);

void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
{
	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	rcu_read_lock();
	memcg = mem_cgroup_from_slab_obj(p);

	/*
	 * Untracked pages have no memcg, no lruvec. Update only the
	 * node. If we reparent the slab objects to the root memcg,
	 * when we free the slab object, we need to update the per-memcg
	 * vmstats to keep it correct for the root memcg.
	 */
	if (!memcg) {
		__mod_node_page_state(pgdat, idx, val);
	} else {
		lruvec = mem_cgroup_lruvec(memcg, pgdat);
		__mod_lruvec_state(lruvec, idx, val);
	}
	rcu_read_unlock();
}

/**
 * __count_memcg_events - account VM events in a cgroup
 * @memcg: the memory cgroup
 * @idx: the event item
 * @count: the number of events that occurred
 */
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
			  unsigned long count)
{
	int i = memcg_events_index(idx);

	if (mem_cgroup_disabled())
		return;

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, idx))
		return;

	memcg_stats_lock();
	__this_cpu_add(memcg->vmstats_percpu->events[i], count);
	memcg_rstat_updated(memcg, count);
	memcg_stats_unlock();
}

unsigned long memcg_events(struct mem_cgroup *memcg, int event)
{
	int i = memcg_events_index(event);

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, event))
		return 0;

	return READ_ONCE(memcg->vmstats->events[i]);
}

unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
{
	int i = memcg_events_index(event);

	if (WARN_ONCE(i < 0, "%s: missing stat item %d\n", __func__, event))
		return 0;

	return READ_ONCE(memcg->vmstats->events_local[i]);
}

void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, int nr_pages)
{
	/* pagein of a big page is an event. So, ignore page size */
	if (nr_pages > 0)
		__count_memcg_events(memcg, PGPGIN, 1);
	else {
		__count_memcg_events(memcg, PGPGOUT, 1);
		nr_pages = -nr_pages; /* for event */
	}

	__this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages);
}

bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
				enum mem_cgroup_events_target target)
{
	unsigned long val, next;

	val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events);
	next = __this_cpu_read(memcg->vmstats_percpu->targets[target]);
	/* from time_after() in jiffies.h */
	if ((long)(next - val) < 0) {
		switch (target) {
		case MEM_CGROUP_TARGET_THRESH:
			next = val + THRESHOLDS_EVENTS_TARGET;
			break;
		case MEM_CGROUP_TARGET_SOFTLIMIT:
			next = val + SOFTLIMIT_EVENTS_TARGET;
			break;
		default:
			break;
		}
		__this_cpu_write(memcg->vmstats_percpu->targets[target], next);
		return true;
	}
	return false;
}

struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
	/*
	 * mm_update_next_owner() may clear mm->owner to NULL
	 * if it races with swapoff, page migration, etc.
	 * So this can be called with p == NULL.
	 */
	if (unlikely(!p))
		return NULL;

	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
}
EXPORT_SYMBOL(mem_cgroup_from_task);

static __always_inline struct mem_cgroup *active_memcg(void)
{
	if (!in_task())
		return this_cpu_read(int_active_memcg);
	else
		return current->active_memcg;
}

/**
 * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg.
 * @mm: mm from which memcg should be extracted. It can be NULL.
 *
 * Obtain a reference on mm->memcg and returns it if successful. If mm
 * is NULL, then the memcg is chosen as follows:
 * 1) The active memcg, if set.
 * 2) current->mm->memcg, if available
 * 3) root memcg
 * If mem_cgroup is disabled, NULL is returned.
 */
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return NULL;

	/*
	 * Page cache insertions can happen without an
	 * actual mm context, e.g. during disk probing
	 * on boot, loopback IO, acct() writes etc.
	 *
	 * No need to css_get on root memcg as the reference
	 * counting is disabled on the root level in the
	 * cgroup core. See CSS_NO_REF.
	 */
	if (unlikely(!mm)) {
		memcg = active_memcg();
		if (unlikely(memcg)) {
			/* remote memcg must hold a ref */
			css_get(&memcg->css);
			return memcg;
		}
		mm = current->mm;
		if (unlikely(!mm))
			return root_mem_cgroup;
	}

	rcu_read_lock();
	do {
		memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!memcg))
			memcg = root_mem_cgroup;
	} while (!css_tryget(&memcg->css));
	rcu_read_unlock();
	return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);

/**
 * get_mem_cgroup_from_current - Obtain a reference on current task's memcg.
 */
struct mem_cgroup *get_mem_cgroup_from_current(void)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return NULL;

again:
	rcu_read_lock();
	memcg = mem_cgroup_from_task(current);
	if (!css_tryget(&memcg->css)) {
		rcu_read_unlock();
		goto again;
	}
	rcu_read_unlock();
	return memcg;
}

/**
 * mem_cgroup_iter - iterate over memory cgroup hierarchy
 * @root: hierarchy root
 * @prev: previously returned memcg, NULL on first invocation
 * @reclaim: cookie for shared reclaim walks, NULL for full walks
 *
 * Returns references to children of the hierarchy below @root, or
 * @root itself, or %NULL after a full round-trip.
 *
 * Caller must pass the return value in @prev on subsequent
 * invocations for reference counting, or use mem_cgroup_iter_break()
 * to cancel a hierarchy walk before the round-trip is complete.
 *
 * Reclaimers can specify a node in @reclaim to divide up the memcgs
 * in the hierarchy among all concurrent reclaimers operating on the
 * same node.
 */
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
				   struct mem_cgroup *prev,
				   struct mem_cgroup_reclaim_cookie *reclaim)
{
	struct mem_cgroup_reclaim_iter *iter;
	struct cgroup_subsys_state *css = NULL;
	struct mem_cgroup *memcg = NULL;
	struct mem_cgroup *pos = NULL;

	if (mem_cgroup_disabled())
		return NULL;

	if (!root)
		root = root_mem_cgroup;

	rcu_read_lock();

	if (reclaim) {
		struct mem_cgroup_per_node *mz;

		mz = root->nodeinfo[reclaim->pgdat->node_id];
		iter = &mz->iter;

		/*
		 * On start, join the current reclaim iteration cycle.
		 * Exit when a concurrent walker completes it.
		 */
		if (!prev)
			reclaim->generation = iter->generation;
		else if (reclaim->generation != iter->generation)
			goto out_unlock;

		while (1) {
			pos = READ_ONCE(iter->position);
			if (!pos || css_tryget(&pos->css))
				break;
			/*
			 * css reference reached zero, so iter->position will
			 * be cleared by ->css_released. However, we should not
			 * rely on this happening soon, because ->css_released
			 * is called from a work queue, and by busy-waiting we
			 * might block it. So we clear iter->position right
			 * away.
			 */
			(void)cmpxchg(&iter->position, pos, NULL);
		}
	} else if (prev) {
		pos = prev;
	}

	if (pos)
		css = &pos->css;

	for (;;) {
		css = css_next_descendant_pre(css, &root->css);
		if (!css) {
			/*
			 * Reclaimers share the hierarchy walk, and a
			 * new one might jump in right at the end of
			 * the hierarchy - make sure they see at least
			 * one group and restart from the beginning.
			 */
			if (!prev)
				continue;
			break;
		}

		/*
		 * Verify the css and acquire a reference.  The root
		 * is provided by the caller, so we know it's alive
		 * and kicking, and don't take an extra reference.
		 */
		if (css == &root->css || css_tryget(css)) {
			memcg = mem_cgroup_from_css(css);
			break;
		}
	}

	if (reclaim) {
		/*
		 * The position could have already been updated by a competing
		 * thread, so check that the value hasn't changed since we read
		 * it to avoid reclaiming from the same cgroup twice.
		 */
		(void)cmpxchg(&iter->position, pos, memcg);

		if (pos)
			css_put(&pos->css);

		if (!memcg)
			iter->generation++;
	}

out_unlock:
	rcu_read_unlock();
	if (prev && prev != root)
		css_put(&prev->css);

	return memcg;
}

/**
 * mem_cgroup_iter_break - abort a hierarchy walk prematurely
 * @root: hierarchy root
 * @prev: last visited hierarchy member as returned by mem_cgroup_iter()
 */
void mem_cgroup_iter_break(struct mem_cgroup *root,
			   struct mem_cgroup *prev)
{
	if (!root)
		root = root_mem_cgroup;
	if (prev && prev != root)
		css_put(&prev->css);
}

static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
					struct mem_cgroup *dead_memcg)
{
	struct mem_cgroup_reclaim_iter *iter;
	struct mem_cgroup_per_node *mz;
	int nid;

	for_each_node(nid) {
		mz = from->nodeinfo[nid];
		iter = &mz->iter;
		cmpxchg(&iter->position, dead_memcg, NULL);
	}
}

static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
{
	struct mem_cgroup *memcg = dead_memcg;
	struct mem_cgroup *last;

	do {
		__invalidate_reclaim_iterators(memcg, dead_memcg);
		last = memcg;
	} while ((memcg = parent_mem_cgroup(memcg)));

	/*
	 * When cgroup1 non-hierarchy mode is used,
	 * parent_mem_cgroup() does not walk all the way up to the
	 * cgroup root (root_mem_cgroup). So we have to handle
	 * dead_memcg from cgroup root separately.
	 */
	if (!mem_cgroup_is_root(last))
		__invalidate_reclaim_iterators(root_mem_cgroup,
						dead_memcg);
}

/**
 * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
 * @memcg: hierarchy root
 * @fn: function to call for each task
 * @arg: argument passed to @fn
 *
 * This function iterates over tasks attached to @memcg or to any of its
 * descendants and calls @fn for each task. If @fn returns a non-zero
 * value, the function breaks the iteration loop. Otherwise, it will iterate
 * over all tasks and return 0.
 *
 * This function must not be called for the root memory cgroup.
 */
void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
			   int (*fn)(struct task_struct *, void *), void *arg)
{
	struct mem_cgroup *iter;
	int ret = 0;

	BUG_ON(mem_cgroup_is_root(memcg));

	for_each_mem_cgroup_tree(iter, memcg) {
		struct css_task_iter it;
		struct task_struct *task;

		css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
		while (!ret && (task = css_task_iter_next(&it)))
			ret = fn(task, arg);
		css_task_iter_end(&it);
		if (ret) {
			mem_cgroup_iter_break(memcg, iter);
			break;
		}
	}
}

#ifdef CONFIG_DEBUG_VM
void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
	struct mem_cgroup *memcg;

	if (mem_cgroup_disabled())
		return;

	memcg = folio_memcg(folio);

	if (!memcg)
		VM_BUG_ON_FOLIO(!mem_cgroup_is_root(lruvec_memcg(lruvec)), folio);
	else
		VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
}
#endif

/**
 * folio_lruvec_lock - Lock the lruvec for a folio.
 * @folio: Pointer to the folio.
 *
 * These functions are safe to use under any of the following conditions:
 * - folio locked
 * - folio_test_lru false
 * - folio_memcg_lock()
 * - folio frozen (refcount of 0)
 *
 * Return: The lruvec this folio is on with its lock held.
 */
struct lruvec *folio_lruvec_lock(struct folio *folio)
{
	struct lruvec *lruvec = folio_lruvec(folio);

	spin_lock(&lruvec->lru_lock);
	lruvec_memcg_debug(lruvec, folio);

	return lruvec;
}

/**
 * folio_lruvec_lock_irq - Lock the lruvec for a folio.
 * @folio: Pointer to the folio.
 *
 * These functions are safe to use under any of the following conditions:
 * - folio locked
 * - folio_test_lru false
 * - folio_memcg_lock()
 * - folio frozen (refcount of 0)
 *
 * Return: The lruvec this folio is on with its lock held and interrupts
 * disabled.
 */
struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
	struct lruvec *lruvec = folio_lruvec(folio);

	spin_lock_irq(&lruvec->lru_lock);
	lruvec_memcg_debug(lruvec, folio);

	return lruvec;
}

/**
 * folio_lruvec_lock_irqsave - Lock the lruvec for a folio.
 * @folio: Pointer to the folio.
 * @flags: Pointer to irqsave flags.
 *
 * These functions are safe to use under any of the following conditions:
 * - folio locked
 * - folio_test_lru false
 * - folio_memcg_lock()
 * - folio frozen (refcount of 0)
 *
 * Return: The lruvec this folio is on with its lock held and interrupts
 * disabled.
 */
struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
		unsigned long *flags)
{
	struct lruvec *lruvec = folio_lruvec(folio);

	spin_lock_irqsave(&lruvec->lru_lock, *flags);
	lruvec_memcg_debug(lruvec, folio);

	return lruvec;
}

/**
 * mem_cgroup_update_lru_size - account for adding or removing an lru page
 * @lruvec: mem_cgroup per zone lru vector
 * @lru: index of lru list the page is sitting on
 * @zid: zone id of the accounted pages
 * @nr_pages: positive when adding or negative when removing
 *
 * This function must be called under lru_lock, just before a page is added
 * to or just after a page is removed from an lru list.
 */
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
				int zid, int nr_pages)
{
	struct mem_cgroup_per_node *mz;
	unsigned long *lru_size;
	long size;

	if (mem_cgroup_disabled())
		return;

	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
	lru_size = &mz->lru_zone_size[zid][lru];

	if (nr_pages < 0)
		*lru_size += nr_pages;

	size = *lru_size;
	if (WARN_ONCE(size < 0,
		"%s(%p, %d, %d): lru_size %ld\n",
		__func__, lruvec, lru, nr_pages, size)) {
		VM_BUG_ON(1);
		*lru_size = 0;
	}

	if (nr_pages > 0)
		*lru_size += nr_pages;
}

/**
 * mem_cgroup_margin - calculate chargeable space of a memory cgroup
 * @memcg: the memory cgroup
 *
 * Returns the maximum amount of memory @mem can be charged with, in
 * pages.
 */
static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
{
	unsigned long margin = 0;
	unsigned long count;
	unsigned long limit;

	count = page_counter_read(&memcg->memory);
	limit = READ_ONCE(memcg->memory.max);
	if (count < limit)
		margin = limit - count;

	if (do_memsw_account()) {
		count = page_counter_read(&memcg->memsw);
		limit = READ_ONCE(memcg->memsw.max);
		if (count < limit)
			margin = min(margin, limit - count);
		else
			margin = 0;
	}

	return margin;
}

struct memory_stat {
	const char *name;
	unsigned int idx;
};

static const struct memory_stat memory_stats[] = {
	{ "anon",			NR_ANON_MAPPED			},
	{ "file",			NR_FILE_PAGES			},
	{ "kernel",			MEMCG_KMEM			},
	{ "kernel_stack",		NR_KERNEL_STACK_KB		},
	{ "pagetables",			NR_PAGETABLE			},
	{ "sec_pagetables",		NR_SECONDARY_PAGETABLE		},
	{ "percpu",			MEMCG_PERCPU_B			},
	{ "sock",			MEMCG_SOCK			},
	{ "vmalloc",			MEMCG_VMALLOC			},
	{ "shmem",			NR_SHMEM			},
#ifdef CONFIG_ZSWAP
	{ "zswap",			MEMCG_ZSWAP_B			},
	{ "zswapped",			MEMCG_ZSWAPPED			},
#endif
	{ "file_mapped",		NR_FILE_MAPPED			},
	{ "file_dirty",			NR_FILE_DIRTY			},
	{ "file_writeback",		NR_WRITEBACK			},
#ifdef CONFIG_SWAP
	{ "swapcached",			NR_SWAPCACHE			},
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	{ "anon_thp",			NR_ANON_THPS			},
	{ "file_thp",			NR_FILE_THPS			},
	{ "shmem_thp",			NR_SHMEM_THPS			},
#endif
	{ "inactive_anon",		NR_INACTIVE_ANON		},
	{ "active_anon",		NR_ACTIVE_ANON			},
	{ "inactive_file",		NR_INACTIVE_FILE		},
	{ "active_file",		NR_ACTIVE_FILE			},
	{ "unevictable",		NR_UNEVICTABLE			},
	{ "slab_reclaimable",		NR_SLAB_RECLAIMABLE_B		},
	{ "slab_unreclaimable",		NR_SLAB_UNRECLAIMABLE_B		},

	/* The memory events */
	{ "workingset_refault_anon",	WORKINGSET_REFAULT_ANON		},
	{ "workingset_refault_file",	WORKINGSET_REFAULT_FILE		},
	{ "workingset_activate_anon",	WORKINGSET_ACTIVATE_ANON	},
	{ "workingset_activate_file",	WORKINGSET_ACTIVATE_FILE	},
	{ "workingset_restore_anon",	WORKINGSET_RESTORE_ANON		},
	{ "workingset_restore_file",	WORKINGSET_RESTORE_FILE		},
	{ "workingset_nodereclaim",	WORKINGSET_NODERECLAIM		},
};

/* The actual unit of the state item, not the same as the output unit */
static int memcg_page_state_unit(int item)
{
	switch (item) {
	case MEMCG_PERCPU_B:
	case MEMCG_ZSWAP_B:
	case NR_SLAB_RECLAIMABLE_B:
	case NR_SLAB_UNRECLAIMABLE_B:
		return 1;
	case NR_KERNEL_STACK_KB:
		return SZ_1K;
	default:
		return PAGE_SIZE;
	}
}

/* Translate stat items to the correct unit for memory.stat output */
static int memcg_page_state_output_unit(int item)
{
	/*
	 * Workingset state is actually in pages, but we export it to userspace
	 * as a scalar count of events, so special case it here.
	 */
	switch (item) {
	case WORKINGSET_REFAULT_ANON:
	case WORKINGSET_REFAULT_FILE:
	case WORKINGSET_ACTIVATE_ANON:
	case WORKINGSET_ACTIVATE_FILE:
	case WORKINGSET_RESTORE_ANON:
	case WORKINGSET_RESTORE_FILE:
	case WORKINGSET_NODERECLAIM:
		return 1;
	default:
		return memcg_page_state_unit(item);
	}
}

unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item)
{
	return memcg_page_state(memcg, item) *
		memcg_page_state_output_unit(item);
}

unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item)
{
	return memcg_page_state_local(memcg, item) *
		memcg_page_state_output_unit(item);
}

static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
	int i;

	/*
	 * Provide statistics on the state of the memory subsystem as
	 * well as cumulative event counters that show past behavior.
	 *
	 * This list is ordered following a combination of these gradients:
	 * 1) generic big picture -> specifics and details
	 * 2) reflecting userspace activity -> reflecting kernel heuristics
	 *
	 * Current memory state:
	 */
	mem_cgroup_flush_stats(memcg);

	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
		u64 size;

		size = memcg_page_state_output(memcg, memory_stats[i].idx);
		seq_buf_printf(s, "%s %llu\n", memory_stats[i].name, size);

		if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) {
			size += memcg_page_state_output(memcg,
							NR_SLAB_RECLAIMABLE_B);
			seq_buf_printf(s, "slab %llu\n", size);
		}
	}

	/* Accumulated memory events */
	seq_buf_printf(s, "pgscan %lu\n",
		       memcg_events(memcg, PGSCAN_KSWAPD) +
		       memcg_events(memcg, PGSCAN_DIRECT) +
		       memcg_events(memcg, PGSCAN_KHUGEPAGED));
	seq_buf_printf(s, "pgsteal %lu\n",
		       memcg_events(memcg, PGSTEAL_KSWAPD) +
		       memcg_events(memcg, PGSTEAL_DIRECT) +
		       memcg_events(memcg, PGSTEAL_KHUGEPAGED));

	for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) {
		if (memcg_vm_event_stat[i] == PGPGIN ||
		    memcg_vm_event_stat[i] == PGPGOUT)
			continue;

		seq_buf_printf(s, "%s %lu\n",
			       vm_event_name(memcg_vm_event_stat[i]),
			       memcg_events(memcg, memcg_vm_event_stat[i]));
	}
}

static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		memcg_stat_format(memcg, s);
	else
		memcg1_stat_format(memcg, s);
	if (seq_buf_has_overflowed(s))
		pr_warn("%s: Warning, stat buffer overflow, please report\n", __func__);
}

/**
 * mem_cgroup_print_oom_context: Print OOM information relevant to
 * memory controller.
 * @memcg: The memory cgroup that went over limit
 * @p: Task that is going to be killed
 *
 * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
 * enabled
 */
void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
{
	rcu_read_lock();

	if (memcg) {
		pr_cont(",oom_memcg=");
		pr_cont_cgroup_path(memcg->css.cgroup);
	} else
		pr_cont(",global_oom");
	if (p) {
		pr_cont(",task_memcg=");
		pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
	}
	rcu_read_unlock();
}

/**
 * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
 * memory controller.
 * @memcg: The memory cgroup that went over limit
 */
void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{
	/* Use static buffer, for the caller is holding oom_lock. */
	static char buf[PAGE_SIZE];
	struct seq_buf s;

	lockdep_assert_held(&oom_lock);

	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
		K((u64)page_counter_read(&memcg->memory)),
		K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt);
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->swap)),
			K((u64)READ_ONCE(memcg->swap.max)), memcg->swap.failcnt);
#ifdef CONFIG_MEMCG_V1
	else {
		pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->memsw)),
			K((u64)memcg->memsw.max), memcg->memsw.failcnt);
		pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
			K((u64)page_counter_read(&memcg->kmem)),
			K((u64)memcg->kmem.max), memcg->kmem.failcnt);
	}
#endif

	pr_info("Memory cgroup stats for ");
	pr_cont_cgroup_path(memcg->css.cgroup);
	pr_cont(":");
	seq_buf_init(&s, buf, sizeof(buf));
	memory_stat_format(memcg, &s);
	seq_buf_do_printk(&s, KERN_INFO);
}

/*
 * Return the memory (and swap, if configured) limit for a memcg.
 */
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
{
	unsigned long max = READ_ONCE(memcg->memory.max);

	if (do_memsw_account()) {
		if (mem_cgroup_swappiness(memcg)) {
			/* Calculate swap excess capacity from memsw limit */
			unsigned long swap = READ_ONCE(memcg->memsw.max) - max;

			max += min(swap, (unsigned long)total_swap_pages);
		}
	} else {
		if (mem_cgroup_swappiness(memcg))
			max += min(READ_ONCE(memcg->swap.max),
				   (unsigned long)total_swap_pages);
	}
	return max;
}

unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
{
	return page_counter_read(&memcg->memory);
}

static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
				     int order)
{
	struct oom_control oc = {
		.zonelist = NULL,
		.nodemask = NULL,
		.memcg = memcg,
		.gfp_mask = gfp_mask,
		.order = order,
	};
	bool ret = true;

	if (mutex_lock_killable(&oom_lock))
		return true;

	if (mem_cgroup_margin(memcg) >= (1 << order))
		goto unlock;

	/*
	 * A few threads which were not waiting at mutex_lock_killable() can
	 * fail to bail out. Therefore, check again after holding oom_lock.
	 */
	ret = task_is_dying() || out_of_memory(&oc);

unlock:
	mutex_unlock(&oom_lock);
	return ret;
}

/*
 * Returns true if successfully killed one or more processes. Though in some
 * corner cases it can return true even without killing any process.
 */
static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
	bool locked, ret;

	if (order > PAGE_ALLOC_COSTLY_ORDER)
		return false;

	memcg_memory_event(memcg, MEMCG_OOM);

	if (!memcg1_oom_prepare(memcg, &locked))
		return false;

	ret = mem_cgroup_out_of_memory(memcg, mask, order);

	memcg1_oom_finish(memcg, locked);

	return ret;
}

/**
 * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM
 * @victim: task to be killed by the OOM killer
 * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM
 *
 * Returns a pointer to a memory cgroup, which has to be cleaned up
 * by killing all belonging OOM-killable tasks.
 *
 * Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
 */
struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
					    struct mem_cgroup *oom_domain)
{
	struct mem_cgroup *oom_group = NULL;
	struct mem_cgroup *memcg;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return NULL;

	if (!oom_domain)
		oom_domain = root_mem_cgroup;

	rcu_read_lock();

	memcg = mem_cgroup_from_task(victim);
	if (mem_cgroup_is_root(memcg))
		goto out;

	/*
	 * If the victim task has been asynchronously moved to a different
	 * memory cgroup, we might end up killing tasks outside oom_domain.
	 * In this case it's better to ignore memory.group.oom.
	 */
	if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain)))
		goto out;

	/*
	 * Traverse the memory cgroup hierarchy from the victim task's
	 * cgroup up to the OOMing cgroup (or root) to find the
	 * highest-level memory cgroup with oom.group set.
	 */
	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
		if (READ_ONCE(memcg->oom_group))
			oom_group = memcg;

		if (memcg == oom_domain)
			break;
	}

	if (oom_group)
		css_get(&oom_group->css);
out:
	rcu_read_unlock();

	return oom_group;
}

void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
{
	pr_info("Tasks in ");
	pr_cont_cgroup_path(memcg->css.cgroup);
	pr_cont(" are going to be killed due to memory.oom.group set\n");
}

struct memcg_stock_pcp {
	local_lock_t stock_lock;
	struct mem_cgroup *cached; /* this never be root cgroup */
	unsigned int nr_pages;

	struct obj_cgroup *cached_objcg;
	struct pglist_data *cached_pgdat;
	unsigned int nr_bytes;
	int nr_slab_reclaimable_b;
	int nr_slab_unreclaimable_b;

	struct work_struct work;
	unsigned long flags;
#define FLUSHING_CACHED_CHARGE	0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
	.stock_lock = INIT_LOCAL_LOCK(stock_lock),
};
static DEFINE_MUTEX(percpu_charge_mutex);

static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock);
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
				     struct mem_cgroup *root_memcg);

/**
 * consume_stock: Try to consume stocked charge on this cpu.
 * @memcg: memcg to consume from.
 * @nr_pages: how many pages to charge.
 *
 * The charges will only happen if @memcg matches the current cpu's memcg
 * stock, and at least @nr_pages are available in that stock.  Failure to
 * service an allocation will refill the stock.
 *
 * returns true if successful, false otherwise.
 */
static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	struct memcg_stock_pcp *stock;
	unsigned int stock_pages;
	unsigned long flags;
	bool ret = false;

	if (nr_pages > MEMCG_CHARGE_BATCH)
		return ret;

	local_lock_irqsave(&memcg_stock.stock_lock, flags);

	stock = this_cpu_ptr(&memcg_stock);
	stock_pages = READ_ONCE(stock->nr_pages);
	if (memcg == READ_ONCE(stock->cached) && stock_pages >= nr_pages) {
		WRITE_ONCE(stock->nr_pages, stock_pages - nr_pages);
		ret = true;
	}

	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);

	return ret;
}

/*
 * Returns stocks cached in percpu and reset cached information.
 */
static void drain_stock(struct memcg_stock_pcp *stock)
{
	unsigned int stock_pages = READ_ONCE(stock->nr_pages);
	struct mem_cgroup *old = READ_ONCE(stock->cached);

	if (!old)
		return;

	if (stock_pages) {
		page_counter_uncharge(&old->memory, stock_pages);
		if (do_memsw_account())
			page_counter_uncharge(&old->memsw, stock_pages);

		WRITE_ONCE(stock->nr_pages, 0);
	}

	css_put(&old->css);
	WRITE_ONCE(stock->cached, NULL);
}

static void drain_local_stock(struct work_struct *dummy)
{
	struct memcg_stock_pcp *stock;
	struct obj_cgroup *old = NULL;
	unsigned long flags;

	/*
	 * The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
	 * drain_stock races is that we always operate on local CPU stock
	 * here with IRQ disabled
	 */
	local_lock_irqsave(&memcg_stock.stock_lock, flags);

	stock = this_cpu_ptr(&memcg_stock);
	old = drain_obj_stock(stock);
	drain_stock(stock);
	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);

	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
	obj_cgroup_put(old);
}

/*
 * Cache charges(val) to local per_cpu area.
 * This will be consumed by consume_stock() function, later.
 */
static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	struct memcg_stock_pcp *stock;
	unsigned int stock_pages;

	stock = this_cpu_ptr(&memcg_stock);
	if (READ_ONCE(stock->cached) != memcg) { /* reset if necessary */
		drain_stock(stock);
		css_get(&memcg->css);
		WRITE_ONCE(stock->cached, memcg);
	}
	stock_pages = READ_ONCE(stock->nr_pages) + nr_pages;
	WRITE_ONCE(stock->nr_pages, stock_pages);

	if (stock_pages > MEMCG_CHARGE_BATCH)
		drain_stock(stock);
}

static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	unsigned long flags;

	local_lock_irqsave(&memcg_stock.stock_lock, flags);
	__refill_stock(memcg, nr_pages);
	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
}

/*
 * Drains all per-CPU charge caches for given root_memcg resp. subtree
 * of the hierarchy under it.
 */
void drain_all_stock(struct mem_cgroup *root_memcg)
{
	int cpu, curcpu;

	/* If someone's already draining, avoid adding running more workers. */
	if (!mutex_trylock(&percpu_charge_mutex))
		return;
	/*
	 * Notify other cpus that system-wide "drain" is running
	 * We do not care about races with the cpu hotplug because cpu down
	 * as well as workers from this path always operate on the local
	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
	 */
	migrate_disable();
	curcpu = smp_processor_id();
	for_each_online_cpu(cpu) {
		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
		struct mem_cgroup *memcg;
		bool flush = false;

		rcu_read_lock();
		memcg = READ_ONCE(stock->cached);
		if (memcg && READ_ONCE(stock->nr_pages) &&
		    mem_cgroup_is_descendant(memcg, root_memcg))
			flush = true;
		else if (obj_stock_flush_required(stock, root_memcg))
			flush = true;
		rcu_read_unlock();

		if (flush &&
		    !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
			if (cpu == curcpu)
				drain_local_stock(&stock->work);
			else if (!cpu_is_isolated(cpu))
				schedule_work_on(cpu, &stock->work);
		}
	}
	migrate_enable();
	mutex_unlock(&percpu_charge_mutex);
}

static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
	struct memcg_stock_pcp *stock;

	stock = &per_cpu(memcg_stock, cpu);
	drain_stock(stock);

	return 0;
}

static unsigned long reclaim_high(struct mem_cgroup *memcg,
				  unsigned int nr_pages,
				  gfp_t gfp_mask)
{
	unsigned long nr_reclaimed = 0;

	do {
		unsigned long pflags;

		if (page_counter_read(&memcg->memory) <=
		    READ_ONCE(memcg->memory.high))
			continue;

		memcg_memory_event(memcg, MEMCG_HIGH);

		psi_memstall_enter(&pflags);
		nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
							gfp_mask,
							MEMCG_RECLAIM_MAY_SWAP,
							NULL);
		psi_memstall_leave(&pflags);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));

	return nr_reclaimed;
}

static void high_work_func(struct work_struct *work)
{
	struct mem_cgroup *memcg;

	memcg = container_of(work, struct mem_cgroup, high_work);
	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}

/*
 * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
 * enough to still cause a significant slowdown in most cases, while still
 * allowing diagnostics and tracing to proceed without becoming stuck.
 */
#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)

/*
 * When calculating the delay, we use these either side of the exponentiation to
 * maintain precision and scale to a reasonable number of jiffies (see the table
 * below.
 *
 * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
 *   overage ratio to a delay.
 * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the
 *   proposed penalty in order to reduce to a reasonable number of jiffies, and
 *   to produce a reasonable delay curve.
 *
 * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
 * reasonable delay curve compared to precision-adjusted overage, not
 * penalising heavily at first, but still making sure that growth beyond the
 * limit penalises misbehaviour cgroups by slowing them down exponentially. For
 * example, with a high of 100 megabytes:
 *
 *  +-------+------------------------+
 *  | usage | time to allocate in ms |
 *  +-------+------------------------+
 *  | 100M  |                      0 |
 *  | 101M  |                      6 |
 *  | 102M  |                     25 |
 *  | 103M  |                     57 |
 *  | 104M  |                    102 |
 *  | 105M  |                    159 |
 *  | 106M  |                    230 |
 *  | 107M  |                    313 |
 *  | 108M  |                    409 |
 *  | 109M  |                    518 |
 *  | 110M  |                    639 |
 *  | 111M  |                    774 |
 *  | 112M  |                    921 |
 *  | 113M  |                   1081 |
 *  | 114M  |                   1254 |
 *  | 115M  |                   1439 |
 *  | 116M  |                   1638 |
 *  | 117M  |                   1849 |
 *  | 118M  |                   2000 |
 *  | 119M  |                   2000 |
 *  | 120M  |                   2000 |
 *  +-------+------------------------+
 */
 #define MEMCG_DELAY_PRECISION_SHIFT 20
 #define MEMCG_DELAY_SCALING_SHIFT 14

static u64 calculate_overage(unsigned long usage, unsigned long high)
{
	u64 overage;

	if (usage <= high)
		return 0;

	/*
	 * Prevent division by 0 in overage calculation by acting as if
	 * it was a threshold of 1 page
	 */
	high = max(high, 1UL);

	overage = usage - high;
	overage <<= MEMCG_DELAY_PRECISION_SHIFT;
	return div64_u64(overage, high);
}

static u64 mem_find_max_overage(struct mem_cgroup *memcg)
{
	u64 overage, max_overage = 0;

	do {
		overage = calculate_overage(page_counter_read(&memcg->memory),
					    READ_ONCE(memcg->memory.high));
		max_overage = max(overage, max_overage);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));

	return max_overage;
}

static u64 swap_find_max_overage(struct mem_cgroup *memcg)
{
	u64 overage, max_overage = 0;

	do {
		overage = calculate_overage(page_counter_read(&memcg->swap),
					    READ_ONCE(memcg->swap.high));
		if (overage)
			memcg_memory_event(memcg, MEMCG_SWAP_HIGH);
		max_overage = max(overage, max_overage);
	} while ((memcg = parent_mem_cgroup(memcg)) &&
		 !mem_cgroup_is_root(memcg));

	return max_overage;
}

/*
 * Get the number of jiffies that we should penalise a mischievous cgroup which
 * is exceeding its memory.high by checking both it and its ancestors.
 */
static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
					  unsigned int nr_pages,
					  u64 max_overage)
{
	unsigned long penalty_jiffies;

	if (!max_overage)
		return 0;

	/*
	 * We use overage compared to memory.high to calculate the number of
	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
	 * fairly lenient on small overages, and increasingly harsh when the
	 * memcg in question makes it clear that it has no intention of stopping
	 * its crazy behaviour, so we exponentially increase the delay based on
	 * overage amount.
	 */
	penalty_jiffies = max_overage * max_overage * HZ;
	penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
	penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;

	/*
	 * Factor in the task's own contribution to the overage, such that four
	 * N-sized allocations are throttled approximately the same as one
	 * 4N-sized allocation.
	 *
	 * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
	 * larger the current charge patch is than that.
	 */
	return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
}

/*
 * Reclaims memory over the high limit. Called directly from
 * try_charge() (context permitting), as well as from the userland
 * return path where reclaim is always able to block.
 */
void mem_cgroup_handle_over_high(gfp_t gfp_mask)
{
	unsigned long penalty_jiffies;
	unsigned long pflags;
	unsigned long nr_reclaimed;
	unsigned int nr_pages = current->memcg_nr_pages_over_high;
	int nr_retries = MAX_RECLAIM_RETRIES;
	struct mem_cgroup *memcg;
	bool in_retry = false;

	if (likely(!nr_pages))
		return;

	memcg = get_mem_cgroup_from_mm(current->mm);
	current->memcg_nr_pages_over_high = 0;

retry_reclaim:
	/*
	 * Bail if the task is already exiting. Unlike memory.max,
	 * memory.high enforcement isn't as strict, and there is no
	 * OOM killer involved, which means the excess could already
	 * be much bigger (and still growing) than it could for
	 * memory.max; the dying task could get stuck in fruitless
	 * reclaim for a long time, which isn't desirable.
	 */
	if (task_is_dying())
		goto out;

	/*
	 * The allocating task should reclaim at least the batch size, but for
	 * subsequent retries we only want to do what's necessary to prevent oom
	 * or breaching resource isolation.
	 *
	 * This is distinct from memory.max or page allocator behaviour because
	 * memory.high is currently batched, whereas memory.max and the page
	 * allocator run every time an allocation is made.
	 */
	nr_reclaimed = reclaim_high(memcg,
				    in_retry ? SWAP_CLUSTER_MAX : nr_pages,
				    gfp_mask);

	/*
	 * memory.high is breached and reclaim is unable to keep up. Throttle
	 * allocators proactively to slow down excessive growth.
	 */
	penalty_jiffies = calculate_high_delay(memcg, nr_pages,
					       mem_find_max_overage(memcg));

	penalty_jiffies += calculate_high_delay(memcg, nr_pages,
						swap_find_max_overage(memcg));

	/*
	 * Clamp the max delay per usermode return so as to still keep the
	 * application moving forwards and also permit diagnostics, albeit
	 * extremely slowly.
	 */
	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);

	/*
	 * Don't sleep if the amount of jiffies this memcg owes us is so low
	 * that it's not even worth doing, in an attempt to be nice to those who
	 * go only a small amount over their memory.high value and maybe haven't
	 * been aggressively reclaimed enough yet.
	 */
	if (penalty_jiffies <= HZ / 100)
		goto out;

	/*
	 * If reclaim is making forward progress but we're still over
	 * memory.high, we want to encourage that rather than doing allocator
	 * throttling.
	 */
	if (nr_reclaimed || nr_retries--) {
		in_retry = true;
		goto retry_reclaim;
	}

	/*
	 * Reclaim didn't manage to push usage below the limit, slow
	 * this allocating task down.
	 *
	 * If we exit early, we're guaranteed to die (since
	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
	 * need to account for any ill-begotten jiffies to pay them off later.
	 */
	psi_memstall_enter(&pflags);
	schedule_timeout_killable(penalty_jiffies);
	psi_memstall_leave(&pflags);

out:
	css_put(&memcg->css);
}

int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
		     unsigned int nr_pages)
{
	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
	int nr_retries = MAX_RECLAIM_RETRIES;
	struct mem_cgroup *mem_over_limit;
	struct page_counter *counter;
	unsigned long nr_reclaimed;
	bool passed_oom = false;
	unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP;
	bool drained = false;
	bool raised_max_event = false;
	unsigned long pflags;

retry:
	if (consume_stock(memcg, nr_pages))
		return 0;

	if (!do_memsw_account() ||
	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
		if (page_counter_try_charge(&memcg->memory, batch, &counter))
			goto done_restock;
		if (do_memsw_account())
			page_counter_uncharge(&memcg->memsw, batch);
		mem_over_limit = mem_cgroup_from_counter(counter, memory);
	} else {
		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
		reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP;
	}

	if (batch > nr_pages) {
		batch = nr_pages;
		goto retry;
	}

	/*
	 * Prevent unbounded recursion when reclaim operations need to
	 * allocate memory. This might exceed the limits temporarily,
	 * but we prefer facilitating memory reclaim and getting back
	 * under the limit over triggering OOM kills in these cases.
	 */
	if (unlikely(current->flags & PF_MEMALLOC))
		goto force;

	if (unlikely(task_in_memcg_oom(current)))
		goto nomem;

	if (!gfpflags_allow_blocking(gfp_mask))
		goto nomem;

	memcg_memory_event(mem_over_limit, MEMCG_MAX);
	raised_max_event = true;

	psi_memstall_enter(&pflags);
	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
						    gfp_mask, reclaim_options, NULL);
	psi_memstall_leave(&pflags);

	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
		goto retry;

	if (!drained) {
		drain_all_stock(mem_over_limit);
		drained = true;
		goto retry;
	}

	if (gfp_mask & __GFP_NORETRY)
		goto nomem;
	/*
	 * Even though the limit is exceeded at this point, reclaim
	 * may have been able to free some pages.  Retry the charge
	 * before killing the task.
	 *
	 * Only for regular pages, though: huge pages are rather
	 * unlikely to succeed so close to the limit, and we fall back
	 * to regular pages anyway in case of failure.
	 */
	if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER))
		goto retry;
	/*
	 * At task move, charge accounts can be doubly counted. So, it's
	 * better to wait until the end of task_move if something is going on.
	 */
	if (memcg1_wait_acct_move(mem_over_limit))
		goto retry;

	if (nr_retries--)
		goto retry;

	if (gfp_mask & __GFP_RETRY_MAYFAIL)
		goto nomem;

	/* Avoid endless loop for tasks bypassed by the oom killer */
	if (passed_oom && task_is_dying())
		goto nomem;

	/*
	 * keep retrying as long as the memcg oom killer is able to make
	 * a forward progress or bypass the charge if the oom killer
	 * couldn't make any progress.
	 */
	if (mem_cgroup_oom(mem_over_limit, gfp_mask,
			   get_order(nr_pages * PAGE_SIZE))) {
		passed_oom = true;
		nr_retries = MAX_RECLAIM_RETRIES;
		goto retry;
	}
nomem:
	/*
	 * Memcg doesn't have a dedicated reserve for atomic
	 * allocations. But like the global atomic pool, we need to
	 * put the burden of reclaim on regular allocation requests
	 * and let these go through as privileged allocations.
	 */
	if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH)))
		return -ENOMEM;
force:
	/*
	 * If the allocation has to be enforced, don't forget to raise
	 * a MEMCG_MAX event.
	 */
	if (!raised_max_event)
		memcg_memory_event(mem_over_limit, MEMCG_MAX);

	/*
	 * The allocation either can't fail or will lead to more memory
	 * being freed very soon.  Allow memory usage go over the limit
	 * temporarily by force charging it.
	 */
	page_counter_charge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_charge(&memcg->memsw, nr_pages);

	return 0;

done_restock:
	if (batch > nr_pages)
		refill_stock(memcg, batch - nr_pages);

	/*
	 * If the hierarchy is above the normal consumption range, schedule
	 * reclaim on returning to userland.  We can perform reclaim here
	 * if __GFP_RECLAIM but let's always punt for simplicity and so that
	 * GFP_KERNEL can consistently be used during reclaim.  @memcg is
	 * not recorded as it most likely matches current's and won't
	 * change in the meantime.  As high limit is checked again before
	 * reclaim, the cost of mismatch is negligible.
	 */
	do {
		bool mem_high, swap_high;

		mem_high = page_counter_read(&memcg->memory) >
			READ_ONCE(memcg->memory.high);
		swap_high = page_counter_read(&memcg->swap) >
			READ_ONCE(memcg->swap.high);

		/* Don't bother a random interrupted task */
		if (!in_task()) {
			if (mem_high) {
				schedule_work(&memcg->high_work);
				break;
			}
			continue;
		}

		if (mem_high || swap_high) {
			/*
			 * The allocating tasks in this cgroup will need to do
			 * reclaim or be throttled to prevent further growth
			 * of the memory or swap footprints.
			 *
			 * Target some best-effort fairness between the tasks,
			 * and distribute reclaim work and delay penalties
			 * based on how much each task is actually allocating.
			 */
			current->memcg_nr_pages_over_high += batch;
			set_notify_resume(current);
			break;
		}
	} while ((memcg = parent_mem_cgroup(memcg)));

	/*
	 * Reclaim is set up above to be called from the userland
	 * return path. But also attempt synchronous reclaim to avoid
	 * excessive overrun while the task is still inside the
	 * kernel. If this is successful, the return path will see it
	 * when it rechecks the overage and simply bail out.
	 */
	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
	    !(current->flags & PF_MEMALLOC) &&
	    gfpflags_allow_blocking(gfp_mask))
		mem_cgroup_handle_over_high(gfp_mask);
	return 0;
}

/**
 * mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call.
 * @memcg: memcg previously charged.
 * @nr_pages: number of pages previously charged.
 */
void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	if (mem_cgroup_is_root(memcg))
		return;

	page_counter_uncharge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_uncharge(&memcg->memsw, nr_pages);
}

static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
	VM_BUG_ON_FOLIO(folio_memcg(folio), folio);
	/*
	 * Any of the following ensures page's memcg stability:
	 *
	 * - the page lock
	 * - LRU isolation
	 * - folio_memcg_lock()
	 * - exclusive reference
	 * - mem_cgroup_trylock_pages()
	 */
	folio->memcg_data = (unsigned long)memcg;
}

/**
 * mem_cgroup_commit_charge - commit a previously successful try_charge().
 * @folio: folio to commit the charge to.
 * @memcg: memcg previously charged.
 */
void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
	css_get(&memcg->css);
	commit_charge(folio, memcg);

	local_irq_disable();
	mem_cgroup_charge_statistics(memcg, folio_nr_pages(folio));
	memcg1_check_events(memcg, folio_nid(folio));
	local_irq_enable();
}

static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg,
				       struct pglist_data *pgdat,
				       enum node_stat_item idx, int nr)
{
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	rcu_read_lock();
	memcg = obj_cgroup_memcg(objcg);
	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	__mod_memcg_lruvec_state(lruvec, idx, nr);
	rcu_read_unlock();
}

static __always_inline
struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
{
	/*
	 * Slab objects are accounted individually, not per-page.
	 * Memcg membership data for each individual object is saved in
	 * slab->obj_exts.
	 */
	if (folio_test_slab(folio)) {
		struct slabobj_ext *obj_exts;
		struct slab *slab;
		unsigned int off;

		slab = folio_slab(folio);
		obj_exts = slab_obj_exts(slab);
		if (!obj_exts)
			return NULL;

		off = obj_to_index(slab->slab_cache, slab, p);
		if (obj_exts[off].objcg)
			return obj_cgroup_memcg(obj_exts[off].objcg);

		return NULL;
	}

	/*
	 * folio_memcg_check() is used here, because in theory we can encounter
	 * a folio where the slab flag has been cleared already, but
	 * slab->obj_exts has not been freed yet
	 * folio_memcg_check() will guarantee that a proper memory
	 * cgroup pointer or NULL will be returned.
	 */
	return folio_memcg_check(folio);
}

/*
 * Returns a pointer to the memory cgroup to which the kernel object is charged.
 *
 * A passed kernel object can be a slab object, vmalloc object or a generic
 * kernel page, so different mechanisms for getting the memory cgroup pointer
 * should be used.
 *
 * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
 * can not know for sure how the kernel object is implemented.
 * mem_cgroup_from_obj() can be safely used in such cases.
 *
 * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
 * cgroup_mutex, etc.
 */
struct mem_cgroup *mem_cgroup_from_obj(void *p)
{
	struct folio *folio;

	if (mem_cgroup_disabled())
		return NULL;

	if (unlikely(is_vmalloc_addr(p)))
		folio = page_folio(vmalloc_to_page(p));
	else
		folio = virt_to_folio(p);

	return mem_cgroup_from_obj_folio(folio, p);
}

/*
 * Returns a pointer to the memory cgroup to which the kernel object is charged.
 * Similar to mem_cgroup_from_obj(), but faster and not suitable for objects,
 * allocated using vmalloc().
 *
 * A passed kernel object must be a slab object or a generic kernel page.
 *
 * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
 * cgroup_mutex, etc.
 */
struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
{
	if (mem_cgroup_disabled())
		return NULL;

	return mem_cgroup_from_obj_folio(virt_to_folio(p), p);
}

static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
{
	struct obj_cgroup *objcg = NULL;

	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
		objcg = rcu_dereference(memcg->objcg);
		if (likely(objcg && obj_cgroup_tryget(objcg)))
			break;
		objcg = NULL;
	}
	return objcg;
}

static struct obj_cgroup *current_objcg_update(void)
{
	struct mem_cgroup *memcg;
	struct obj_cgroup *old, *objcg = NULL;

	do {
		/* Atomically drop the update bit. */
		old = xchg(&current->objcg, NULL);
		if (old) {
			old = (struct obj_cgroup *)
				((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG);
			obj_cgroup_put(old);

			old = NULL;
		}

		/* If new objcg is NULL, no reason for the second atomic update. */
		if (!current->mm || (current->flags & PF_KTHREAD))
			return NULL;

		/*
		 * Release the objcg pointer from the previous iteration,
		 * if try_cmpxcg() below fails.
		 */
		if (unlikely(objcg)) {
			obj_cgroup_put(objcg);
			objcg = NULL;
		}

		/*
		 * Obtain the new objcg pointer. The current task can be
		 * asynchronously moved to another memcg and the previous
		 * memcg can be offlined. So let's get the memcg pointer
		 * and try get a reference to objcg under a rcu read lock.
		 */

		rcu_read_lock();
		memcg = mem_cgroup_from_task(current);
		objcg = __get_obj_cgroup_from_memcg(memcg);
		rcu_read_unlock();

		/*
		 * Try set up a new objcg pointer atomically. If it
		 * fails, it means the update flag was set concurrently, so
		 * the whole procedure should be repeated.
		 */
	} while (!try_cmpxchg(&current->objcg, &old, objcg));

	return objcg;
}

__always_inline struct obj_cgroup *current_obj_cgroup(void)
{
	struct mem_cgroup *memcg;
	struct obj_cgroup *objcg;

	if (in_task()) {
		memcg = current->active_memcg;
		if (unlikely(memcg))
			goto from_memcg;

		objcg = READ_ONCE(current->objcg);
		if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG))
			objcg = current_objcg_update();
		/*
		 * Objcg reference is kept by the task, so it's safe
		 * to use the objcg by the current task.
		 */
		return objcg;
	}

	memcg = this_cpu_read(int_active_memcg);
	if (unlikely(memcg))
		goto from_memcg;

	return NULL;

from_memcg:
	objcg = NULL;
	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
		/*
		 * Memcg pointer is protected by scope (see set_active_memcg())
		 * and is pinning the corresponding objcg, so objcg can't go
		 * away and can be used within the scope without any additional
		 * protection.
		 */
		objcg = rcu_dereference_check(memcg->objcg, 1);
		if (likely(objcg))
			break;
	}

	return objcg;
}

struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
{
	struct obj_cgroup *objcg;

	if (!memcg_kmem_online())
		return NULL;

	if (folio_memcg_kmem(folio)) {
		objcg = __folio_objcg(folio);
		obj_cgroup_get(objcg);
	} else {
		struct mem_cgroup *memcg;

		rcu_read_lock();
		memcg = __folio_memcg(folio);
		if (memcg)
			objcg = __get_obj_cgroup_from_memcg(memcg);
		else
			objcg = NULL;
		rcu_read_unlock();
	}
	return objcg;
}

/*
 * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
 * @objcg: object cgroup to uncharge
 * @nr_pages: number of pages to uncharge
 */
static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
				      unsigned int nr_pages)
{
	struct mem_cgroup *memcg;

	memcg = get_mem_cgroup_from_objcg(objcg);

	mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
	memcg1_account_kmem(memcg, -nr_pages);
	refill_stock(memcg, nr_pages);

	css_put(&memcg->css);
}

/*
 * obj_cgroup_charge_pages: charge a number of kernel pages to a objcg
 * @objcg: object cgroup to charge
 * @gfp: reclaim mode
 * @nr_pages: number of pages to charge
 *
 * Returns 0 on success, an error code on failure.
 */
static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
				   unsigned int nr_pages)
{
	struct mem_cgroup *memcg;
	int ret;

	memcg = get_mem_cgroup_from_objcg(objcg);

	ret = try_charge_memcg(memcg, gfp, nr_pages);
	if (ret)
		goto out;

	mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
	memcg1_account_kmem(memcg, nr_pages);
out:
	css_put(&memcg->css);

	return ret;
}

/**
 * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup
 * @page: page to charge
 * @gfp: reclaim mode
 * @order: allocation order
 *
 * Returns 0 on success, an error code on failure.
 */
int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
{
	struct obj_cgroup *objcg;
	int ret = 0;

	objcg = current_obj_cgroup();
	if (objcg) {
		ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
		if (!ret) {
			obj_cgroup_get(objcg);
			page->memcg_data = (unsigned long)objcg |
				MEMCG_DATA_KMEM;
			return 0;
		}
	}
	return ret;
}

/**
 * __memcg_kmem_uncharge_page: uncharge a kmem page
 * @page: page to uncharge
 * @order: allocation order
 */
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
	struct folio *folio = page_folio(page);
	struct obj_cgroup *objcg;
	unsigned int nr_pages = 1 << order;

	if (!folio_memcg_kmem(folio))
		return;

	objcg = __folio_objcg(folio);
	obj_cgroup_uncharge_pages(objcg, nr_pages);
	folio->memcg_data = 0;
	obj_cgroup_put(objcg);
}

static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
		     enum node_stat_item idx, int nr)
{
	struct memcg_stock_pcp *stock;
	struct obj_cgroup *old = NULL;
	unsigned long flags;
	int *bytes;

	local_lock_irqsave(&memcg_stock.stock_lock, flags);
	stock = this_cpu_ptr(&memcg_stock);

	/*
	 * Save vmstat data in stock and skip vmstat array update unless
	 * accumulating over a page of vmstat data or when pgdat or idx
	 * changes.
	 */
	if (READ_ONCE(stock->cached_objcg) != objcg) {
		old = drain_obj_stock(stock);
		obj_cgroup_get(objcg);
		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
		WRITE_ONCE(stock->cached_objcg, objcg);
		stock->cached_pgdat = pgdat;
	} else if (stock->cached_pgdat != pgdat) {
		/* Flush the existing cached vmstat data */
		struct pglist_data *oldpg = stock->cached_pgdat;

		if (stock->nr_slab_reclaimable_b) {
			__mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B,
					  stock->nr_slab_reclaimable_b);
			stock->nr_slab_reclaimable_b = 0;
		}
		if (stock->nr_slab_unreclaimable_b) {
			__mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B,
					  stock->nr_slab_unreclaimable_b);
			stock->nr_slab_unreclaimable_b = 0;
		}
		stock->cached_pgdat = pgdat;
	}

	bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
					       : &stock->nr_slab_unreclaimable_b;
	/*
	 * Even for large object >= PAGE_SIZE, the vmstat data will still be
	 * cached locally at least once before pushing it out.
	 */
	if (!*bytes) {
		*bytes = nr;
		nr = 0;
	} else {
		*bytes += nr;
		if (abs(*bytes) > PAGE_SIZE) {
			nr = *bytes;
			*bytes = 0;
		} else {
			nr = 0;
		}
	}
	if (nr)
		__mod_objcg_mlstate(objcg, pgdat, idx, nr);

	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
	obj_cgroup_put(old);
}

static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
{
	struct memcg_stock_pcp *stock;
	unsigned long flags;
	bool ret = false;

	local_lock_irqsave(&memcg_stock.stock_lock, flags);

	stock = this_cpu_ptr(&memcg_stock);
	if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
		stock->nr_bytes -= nr_bytes;
		ret = true;
	}

	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);

	return ret;
}

static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
{
	struct obj_cgroup *old = READ_ONCE(stock->cached_objcg);

	if (!old)
		return NULL;

	if (stock->nr_bytes) {
		unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
		unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);

		if (nr_pages) {
			struct mem_cgroup *memcg;

			memcg = get_mem_cgroup_from_objcg(old);

			mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
			memcg1_account_kmem(memcg, -nr_pages);
			__refill_stock(memcg, nr_pages);

			css_put(&memcg->css);
		}

		/*
		 * The leftover is flushed to the centralized per-memcg value.
		 * On the next attempt to refill obj stock it will be moved
		 * to a per-cpu stock (probably, on an other CPU), see
		 * refill_obj_stock().
		 *
		 * How often it's flushed is a trade-off between the memory
		 * limit enforcement accuracy and potential CPU contention,
		 * so it might be changed in the future.
		 */
		atomic_add(nr_bytes, &old->nr_charged_bytes);
		stock->nr_bytes = 0;
	}

	/*
	 * Flush the vmstat data in current stock
	 */
	if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) {
		if (stock->nr_slab_reclaimable_b) {
			__mod_objcg_mlstate(old, stock->cached_pgdat,
					  NR_SLAB_RECLAIMABLE_B,
					  stock->nr_slab_reclaimable_b);
			stock->nr_slab_reclaimable_b = 0;
		}
		if (stock->nr_slab_unreclaimable_b) {
			__mod_objcg_mlstate(old, stock->cached_pgdat,
					  NR_SLAB_UNRECLAIMABLE_B,
					  stock->nr_slab_unreclaimable_b);
			stock->nr_slab_unreclaimable_b = 0;
		}
		stock->cached_pgdat = NULL;
	}

	WRITE_ONCE(stock->cached_objcg, NULL);
	/*
	 * The `old' objects needs to be released by the caller via
	 * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock.
	 */
	return old;
}

static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
				     struct mem_cgroup *root_memcg)
{
	struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg);
	struct mem_cgroup *memcg;

	if (objcg) {
		memcg = obj_cgroup_memcg(objcg);
		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
			return true;
	}

	return false;
}

static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
			     bool allow_uncharge)
{
	struct memcg_stock_pcp *stock;
	struct obj_cgroup *old = NULL;
	unsigned long flags;
	unsigned int nr_pages = 0;

	local_lock_irqsave(&memcg_stock.stock_lock, flags);

	stock = this_cpu_ptr(&memcg_stock);
	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
		old = drain_obj_stock(stock);
		obj_cgroup_get(objcg);
		WRITE_ONCE(stock->cached_objcg, objcg);
		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
		allow_uncharge = true;	/* Allow uncharge when objcg changes */
	}
	stock->nr_bytes += nr_bytes;

	if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
		nr_pages = stock->nr_bytes >> PAGE_SHIFT;
		stock->nr_bytes &= (PAGE_SIZE - 1);
	}

	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
	obj_cgroup_put(old);

	if (nr_pages)
		obj_cgroup_uncharge_pages(objcg, nr_pages);
}

int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
{
	unsigned int nr_pages, nr_bytes;
	int ret;

	if (consume_obj_stock(objcg, size))
		return 0;

	/*
	 * In theory, objcg->nr_charged_bytes can have enough
	 * pre-charged bytes to satisfy the allocation. However,
	 * flushing objcg->nr_charged_bytes requires two atomic
	 * operations, and objcg->nr_charged_bytes can't be big.
	 * The shared objcg->nr_charged_bytes can also become a
	 * performance bottleneck if all tasks of the same memcg are
	 * trying to update it. So it's better to ignore it and try
	 * grab some new pages. The stock's nr_bytes will be flushed to
	 * objcg->nr_charged_bytes later on when objcg changes.
	 *
	 * The stock's nr_bytes may contain enough pre-charged bytes
	 * to allow one less page from being charged, but we can't rely
	 * on the pre-charged bytes not being changed outside of
	 * consume_obj_stock() or refill_obj_stock(). So ignore those
	 * pre-charged bytes as well when charging pages. To avoid a
	 * page uncharge right after a page charge, we set the
	 * allow_uncharge flag to false when calling refill_obj_stock()
	 * to temporarily allow the pre-charged bytes to exceed the page
	 * size limit. The maximum reachable value of the pre-charged
	 * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data
	 * race.
	 */
	nr_pages = size >> PAGE_SHIFT;
	nr_bytes = size & (PAGE_SIZE - 1);

	if (nr_bytes)
		nr_pages += 1;

	ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages);
	if (!ret && nr_bytes)
		refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false);

	return ret;
}

void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
{
	refill_obj_stock(objcg, size, true);
}

static inline size_t obj_full_size(struct kmem_cache *s)
{
	/*
	 * For each accounted object there is an extra space which is used
	 * to store obj_cgroup membership. Charge it too.
	 */
	return s->size + sizeof(struct obj_cgroup *);
}

bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
				  gfp_t flags, size_t size, void **p)
{
	struct obj_cgroup *objcg;
	struct slab *slab;
	unsigned long off;
	size_t i;

	/*
	 * The obtained objcg pointer is safe to use within the current scope,
	 * defined by current task or set_active_memcg() pair.
	 * obj_cgroup_get() is used to get a permanent reference.
	 */
	objcg = current_obj_cgroup();
	if (!objcg)
		return true;

	/*
	 * slab_alloc_node() avoids the NULL check, so we might be called with a
	 * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill
	 * the whole requested size.
	 * return success as there's nothing to free back
	 */
	if (unlikely(*p == NULL))
		return true;

	flags &= gfp_allowed_mask;

	if (lru) {
		int ret;
		struct mem_cgroup *memcg;

		memcg = get_mem_cgroup_from_objcg(objcg);
		ret = memcg_list_lru_alloc(memcg, lru, flags);
		css_put(&memcg->css);

		if (ret)
			return false;
	}

	if (obj_cgroup_charge(objcg, flags, size * obj_full_size(s)))
		return false;

	for (i = 0; i < size; i++) {
		slab = virt_to_slab(p[i]);

		if (!slab_obj_exts(slab) &&
		    alloc_slab_obj_exts(slab, s, flags, false)) {
			obj_cgroup_uncharge(objcg, obj_full_size(s));
			continue;
		}

		off = obj_to_index(s, slab, p[i]);
		obj_cgroup_get(objcg);
		slab_obj_exts(slab)[off].objcg = objcg;
		mod_objcg_state(objcg, slab_pgdat(slab),
				cache_vmstat_idx(s), obj_full_size(s));
	}

	return true;
}

void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
			    void **p, int objects, struct slabobj_ext *obj_exts)
{
	for (int i = 0; i < objects; i++) {
		struct obj_cgroup *objcg;
		unsigned int off;

		off = obj_to_index(s, slab, p[i]);
		objcg = obj_exts[off].objcg;
		if (!objcg)
			continue;

		obj_exts[off].objcg = NULL;
		obj_cgroup_uncharge(objcg, obj_full_size(s));
		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
				-obj_full_size(s));
		obj_cgroup_put(objcg);
	}
}

/*
 * Because folio_memcg(head) is not set on tails, set it now.
 */
void split_page_memcg(struct page *head, int old_order, int new_order)
{
	struct folio *folio = page_folio(head);
	struct mem_cgroup *memcg = folio_memcg(folio);
	int i;
	unsigned int old_nr = 1 << old_order;
	unsigned int new_nr = 1 << new_order;

	if (mem_cgroup_disabled() || !memcg)
		return;

	for (i = new_nr; i < old_nr; i += new_nr)
		folio_page(folio, i)->memcg_data = folio->memcg_data;

	if (folio_memcg_kmem(folio))
		obj_cgroup_get_many(__folio_objcg(folio), old_nr / new_nr - 1);
	else
		css_get_many(&memcg->css, old_nr / new_nr - 1);
}

unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
	unsigned long val;

	if (mem_cgroup_is_root(memcg)) {
		/*
		 * Approximate root's usage from global state. This isn't
		 * perfect, but the root usage was always an approximation.
		 */
		val = global_node_page_state(NR_FILE_PAGES) +
			global_node_page_state(NR_ANON_MAPPED);
		if (swap)
			val += total_swap_pages - get_nr_swap_pages();
	} else {
		if (!swap)
			val = page_counter_read(&memcg->memory);
		else
			val = page_counter_read(&memcg->memsw);
	}
	return val;
}

static int memcg_online_kmem(struct mem_cgroup *memcg)
{
	struct obj_cgroup *objcg;

	if (mem_cgroup_kmem_disabled())
		return 0;

	if (unlikely(mem_cgroup_is_root(memcg)))
		return 0;

	objcg = obj_cgroup_alloc();
	if (!objcg)
		return -ENOMEM;

	objcg->memcg = memcg;
	rcu_assign_pointer(memcg->objcg, objcg);
	obj_cgroup_get(objcg);
	memcg->orig_objcg = objcg;

	static_branch_enable(&memcg_kmem_online_key);

	memcg->kmemcg_id = memcg->id.id;

	return 0;
}

static void memcg_offline_kmem(struct mem_cgroup *memcg)
{
	struct mem_cgroup *parent;

	if (mem_cgroup_kmem_disabled())
		return;

	if (unlikely(mem_cgroup_is_root(memcg)))
		return;

	parent = parent_mem_cgroup(memcg);
	if (!parent)
		parent = root_mem_cgroup;

	memcg_reparent_objcgs(memcg, parent);

	/*
	 * After we have finished memcg_reparent_objcgs(), all list_lrus
	 * corresponding to this cgroup are guaranteed to remain empty.
	 * The ordering is imposed by list_lru_node->lock taken by
	 * memcg_reparent_list_lrus().
	 */
	memcg_reparent_list_lrus(memcg, parent);
}

#ifdef CONFIG_CGROUP_WRITEBACK

#include <trace/events/writeback.h>

static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
	return wb_domain_init(&memcg->cgwb_domain, gfp);
}

static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
{
	wb_domain_exit(&memcg->cgwb_domain);
}

static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
{
	wb_domain_size_changed(&memcg->cgwb_domain);
}

struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);

	if (!memcg->css.parent)
		return NULL;

	return &memcg->cgwb_domain;
}

/**
 * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
 * @wb: bdi_writeback in question
 * @pfilepages: out parameter for number of file pages
 * @pheadroom: out parameter for number of allocatable pages according to memcg
 * @pdirty: out parameter for number of dirty pages
 * @pwriteback: out parameter for number of pages under writeback
 *
 * Determine the numbers of file, headroom, dirty, and writeback pages in
 * @wb's memcg.  File, dirty and writeback are self-explanatory.  Headroom
 * is a bit more involved.
 *
 * A memcg's headroom is "min(max, high) - used".  In the hierarchy, the
 * headroom is calculated as the lowest headroom of itself and the
 * ancestors.  Note that this doesn't consider the actual amount of
 * available memory in the system.  The caller should further cap
 * *@pheadroom accordingly.
 */
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
			 unsigned long *pheadroom, unsigned long *pdirty,
			 unsigned long *pwriteback)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
	struct mem_cgroup *parent;

	mem_cgroup_flush_stats_ratelimited(memcg);

	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
	*pfilepages = memcg_page_state(memcg, NR_INACTIVE_FILE) +
			memcg_page_state(memcg, NR_ACTIVE_FILE);

	*pheadroom = PAGE_COUNTER_MAX;
	while ((parent = parent_mem_cgroup(memcg))) {
		unsigned long ceiling = min(READ_ONCE(memcg->memory.max),
					    READ_ONCE(memcg->memory.high));
		unsigned long used = page_counter_read(&memcg->memory);

		*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
		memcg = parent;
	}
}

/*
 * Foreign dirty flushing
 *
 * There's an inherent mismatch between memcg and writeback.  The former
 * tracks ownership per-page while the latter per-inode.  This was a
 * deliberate design decision because honoring per-page ownership in the
 * writeback path is complicated, may lead to higher CPU and IO overheads
 * and deemed unnecessary given that write-sharing an inode across
 * different cgroups isn't a common use-case.
 *
 * Combined with inode majority-writer ownership switching, this works well
 * enough in most cases but there are some pathological cases.  For
 * example, let's say there are two cgroups A and B which keep writing to
 * different but confined parts of the same inode.  B owns the inode and
 * A's memory is limited far below B's.  A's dirty ratio can rise enough to
 * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
 * triggering background writeback.  A will be slowed down without a way to
 * make writeback of the dirty pages happen.
 *
 * Conditions like the above can lead to a cgroup getting repeatedly and
 * severely throttled after making some progress after each
 * dirty_expire_interval while the underlying IO device is almost
 * completely idle.
 *
 * Solving this problem completely requires matching the ownership tracking
 * granularities between memcg and writeback in either direction.  However,
 * the more egregious behaviors can be avoided by simply remembering the
 * most recent foreign dirtying events and initiating remote flushes on
 * them when local writeback isn't enough to keep the memory clean enough.
 *
 * The following two functions implement such mechanism.  When a foreign
 * page - a page whose memcg and writeback ownerships don't match - is
 * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
 * bdi_writeback on the page owning memcg.  When balance_dirty_pages()
 * decides that the memcg needs to sleep due to high dirty ratio, it calls
 * mem_cgroup_flush_foreign() which queues writeback on the recorded
 * foreign bdi_writebacks which haven't expired.  Both the numbers of
 * recorded bdi_writebacks and concurrent in-flight foreign writebacks are
 * limited to MEMCG_CGWB_FRN_CNT.
 *
 * The mechanism only remembers IDs and doesn't hold any object references.
 * As being wrong occasionally doesn't matter, updates and accesses to the
 * records are lockless and racy.
 */
void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
					     struct bdi_writeback *wb)
{
	struct mem_cgroup *memcg = folio_memcg(folio);
	struct memcg_cgwb_frn *frn;
	u64 now = get_jiffies_64();
	u64 oldest_at = now;
	int oldest = -1;
	int i;

	trace_track_foreign_dirty(folio, wb);

	/*
	 * Pick the slot to use.  If there is already a slot for @wb, keep
	 * using it.  If not replace the oldest one which isn't being
	 * written out.
	 */
	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
		frn = &memcg->cgwb_frn[i];
		if (frn->bdi_id == wb->bdi->id &&
		    frn->memcg_id == wb->memcg_css->id)
			break;
		if (time_before64(frn->at, oldest_at) &&
		    atomic_read(&frn->done.cnt) == 1) {
			oldest = i;
			oldest_at = frn->at;
		}
	}

	if (i < MEMCG_CGWB_FRN_CNT) {
		/*
		 * Re-using an existing one.  Update timestamp lazily to
		 * avoid making the cacheline hot.  We want them to be
		 * reasonably up-to-date and significantly shorter than
		 * dirty_expire_interval as that's what expires the record.
		 * Use the shorter of 1s and dirty_expire_interval / 8.
		 */
		unsigned long update_intv =
			min_t(unsigned long, HZ,
			      msecs_to_jiffies(dirty_expire_interval * 10) / 8);

		if (time_before64(frn->at, now - update_intv))
			frn->at = now;
	} else if (oldest >= 0) {
		/* replace the oldest free one */
		frn = &memcg->cgwb_frn[oldest];
		frn->bdi_id = wb->bdi->id;
		frn->memcg_id = wb->memcg_css->id;
		frn->at = now;
	}
}

/* issue foreign writeback flushes for recorded foreign dirtying events */
void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
	unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
	u64 now = jiffies_64;
	int i;

	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
		struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];

		/*
		 * If the record is older than dirty_expire_interval,
		 * writeback on it has already started.  No need to kick it
		 * off again.  Also, don't start a new one if there's
		 * already one in flight.
		 */
		if (time_after64(frn->at, now - intv) &&
		    atomic_read(&frn->done.cnt) == 1) {
			frn->at = 0;
			trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
					       WB_REASON_FOREIGN_FLUSH,
					       &frn->done);
		}
	}
}

#else	/* CONFIG_CGROUP_WRITEBACK */

static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
	return 0;
}

static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
{
}

static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
{
}

#endif	/* CONFIG_CGROUP_WRITEBACK */

/*
 * Private memory cgroup IDR
 *
 * Swap-out records and page cache shadow entries need to store memcg
 * references in constrained space, so we maintain an ID space that is
 * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
 * memory-controlled cgroups to 64k.
 *
 * However, there usually are many references to the offline CSS after
 * the cgroup has been destroyed, such as page cache or reclaimable
 * slab objects, that don't need to hang on to the ID. We want to keep
 * those dead CSS from occupying IDs, or we might quickly exhaust the
 * relatively small ID space and prevent the creation of new cgroups
 * even when there are much fewer than 64k cgroups - possibly none.
 *
 * Maintain a private 16-bit ID space for memcg, and allow the ID to
 * be freed and recycled when it's no longer needed, which is usually
 * when the CSS is offlined.
 *
 * The only exception to that are records of swapped out tmpfs/shmem
 * pages that need to be attributed to live ancestors on swapin. But
 * those references are manageable from userspace.
 */

#define MEM_CGROUP_ID_MAX	((1UL << MEM_CGROUP_ID_SHIFT) - 1)
static DEFINE_IDR(mem_cgroup_idr);

static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
{
	if (memcg->id.id > 0) {
		idr_remove(&mem_cgroup_idr, memcg->id.id);
		memcg->id.id = 0;
	}
}

void __maybe_unused mem_cgroup_id_get_many(struct mem_cgroup *memcg,
					   unsigned int n)
{
	refcount_add(n, &memcg->id.ref);
}

void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
{
	if (refcount_sub_and_test(n, &memcg->id.ref)) {
		mem_cgroup_id_remove(memcg);

		/* Memcg ID pins CSS */
		css_put(&memcg->css);
	}
}

static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
{
	mem_cgroup_id_put_many(memcg, 1);
}

/**
 * mem_cgroup_from_id - look up a memcg from a memcg id
 * @id: the memcg id to look up
 *
 * Caller must hold rcu_read_lock().
 */
struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
{
	WARN_ON_ONCE(!rcu_read_lock_held());
	return idr_find(&mem_cgroup_idr, id);
}

#ifdef CONFIG_SHRINKER_DEBUG
struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino)
{
	struct cgroup *cgrp;
	struct cgroup_subsys_state *css;
	struct mem_cgroup *memcg;

	cgrp = cgroup_get_from_id(ino);
	if (IS_ERR(cgrp))
		return ERR_CAST(cgrp);

	css = cgroup_get_e_css(cgrp, &memory_cgrp_subsys);
	if (css)
		memcg = container_of(css, struct mem_cgroup, css);
	else
		memcg = ERR_PTR(-ENOENT);

	cgroup_put(cgrp);

	return memcg;
}
#endif

static bool alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
{
	struct mem_cgroup_per_node *pn;

	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, node);
	if (!pn)
		return false;

	pn->lruvec_stats = kzalloc_node(sizeof(struct lruvec_stats),
					GFP_KERNEL_ACCOUNT, node);
	if (!pn->lruvec_stats)
		goto fail;

	pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
						   GFP_KERNEL_ACCOUNT);
	if (!pn->lruvec_stats_percpu)
		goto fail;

	lruvec_init(&pn->lruvec);
	pn->memcg = memcg;

	memcg->nodeinfo[node] = pn;
	return true;
fail:
	kfree(pn->lruvec_stats);
	kfree(pn);
	return false;
}

static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
{
	struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];

	if (!pn)
		return;

	free_percpu(pn->lruvec_stats_percpu);
	kfree(pn->lruvec_stats);
	kfree(pn);
}

static void __mem_cgroup_free(struct mem_cgroup *memcg)
{
	int node;

	obj_cgroup_put(memcg->orig_objcg);

	for_each_node(node)
		free_mem_cgroup_per_node_info(memcg, node);
	kfree(memcg->vmstats);
	free_percpu(memcg->vmstats_percpu);
	kfree(memcg);
}

static void mem_cgroup_free(struct mem_cgroup *memcg)
{
	lru_gen_exit_memcg(memcg);
	memcg_wb_domain_exit(memcg);
	__mem_cgroup_free(memcg);
}

static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
{
	struct memcg_vmstats_percpu *statc, *pstatc;
	struct mem_cgroup *memcg;
	int node, cpu;
	int __maybe_unused i;
	long error = -ENOMEM;

	memcg = kzalloc(struct_size(memcg, nodeinfo, nr_node_ids), GFP_KERNEL);
	if (!memcg)
		return ERR_PTR(error);

	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
				 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL);
	if (memcg->id.id < 0) {
		error = memcg->id.id;
		goto fail;
	}

	memcg->vmstats = kzalloc(sizeof(struct memcg_vmstats),
				 GFP_KERNEL_ACCOUNT);
	if (!memcg->vmstats)
		goto fail;

	memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu,
						 GFP_KERNEL_ACCOUNT);
	if (!memcg->vmstats_percpu)
		goto fail;

	for_each_possible_cpu(cpu) {
		if (parent)
			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
		statc->parent = parent ? pstatc : NULL;
		statc->vmstats = memcg->vmstats;
	}

	for_each_node(node)
		if (!alloc_mem_cgroup_per_node_info(memcg, node))
			goto fail;

	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
		goto fail;

	INIT_WORK(&memcg->high_work, high_work_func);
	vmpressure_init(&memcg->vmpressure);
	memcg->socket_pressure = jiffies;
	memcg1_memcg_init(memcg);
	memcg->kmemcg_id = -1;
	INIT_LIST_HEAD(&memcg->objcg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
	INIT_LIST_HEAD(&memcg->cgwb_list);
	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
		memcg->cgwb_frn[i].done =
			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
	INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
	memcg->deferred_split_queue.split_queue_len = 0;
#endif
	lru_gen_init_memcg(memcg);
	return memcg;
fail:
	mem_cgroup_id_remove(memcg);
	__mem_cgroup_free(memcg);
	return ERR_PTR(error);
}

static struct cgroup_subsys_state * __ref
mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
	struct mem_cgroup *memcg, *old_memcg;

	old_memcg = set_active_memcg(parent);
	memcg = mem_cgroup_alloc(parent);
	set_active_memcg(old_memcg);
	if (IS_ERR(memcg))
		return ERR_CAST(memcg);

	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
	memcg1_soft_limit_reset(memcg);
#ifdef CONFIG_ZSWAP
	memcg->zswap_max = PAGE_COUNTER_MAX;
	WRITE_ONCE(memcg->zswap_writeback,
		!parent || READ_ONCE(parent->zswap_writeback));
#endif
	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
	if (parent) {
		WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent));

		page_counter_init(&memcg->memory, &parent->memory);
		page_counter_init(&memcg->swap, &parent->swap);
#ifdef CONFIG_MEMCG_V1
		WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable));
		page_counter_init(&memcg->kmem, &parent->kmem);
		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
#endif
	} else {
		init_memcg_stats();
		init_memcg_events();
		page_counter_init(&memcg->memory, NULL);
		page_counter_init(&memcg->swap, NULL);
#ifdef CONFIG_MEMCG_V1
		page_counter_init(&memcg->kmem, NULL);
		page_counter_init(&memcg->tcpmem, NULL);
#endif
		root_mem_cgroup = memcg;
		return &memcg->css;
	}

	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
		static_branch_inc(&memcg_sockets_enabled_key);

	if (!cgroup_memory_nobpf)
		static_branch_inc(&memcg_bpf_enabled_key);

	return &memcg->css;
}

static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	if (memcg_online_kmem(memcg))
		goto remove_id;

	/*
	 * A memcg must be visible for expand_shrinker_info()
	 * by the time the maps are allocated. So, we allocate maps
	 * here, when for_each_mem_cgroup() can't skip it.
	 */
	if (alloc_shrinker_info(memcg))
		goto offline_kmem;

	if (unlikely(mem_cgroup_is_root(memcg)) && !mem_cgroup_disabled())
		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
				   FLUSH_TIME);
	lru_gen_online_memcg(memcg);

	/* Online state pins memcg ID, memcg ID pins CSS */
	refcount_set(&memcg->id.ref, 1);
	css_get(css);

	/*
	 * Ensure mem_cgroup_from_id() works once we're fully online.
	 *
	 * We could do this earlier and require callers to filter with
	 * css_tryget_online(). But right now there are no users that
	 * need earlier access, and the workingset code relies on the
	 * cgroup tree linkage (mem_cgroup_get_nr_swap_pages()). So
	 * publish it here at the end of onlining. This matches the
	 * regular ID destruction during offlining.
	 */
	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);

	return 0;
offline_kmem:
	memcg_offline_kmem(memcg);
remove_id:
	mem_cgroup_id_remove(memcg);
	return -ENOMEM;
}

static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	memcg1_css_offline(memcg);

	page_counter_set_min(&memcg->memory, 0);
	page_counter_set_low(&memcg->memory, 0);

	zswap_memcg_offline_cleanup(memcg);

	memcg_offline_kmem(memcg);
	reparent_shrinker_deferred(memcg);
	wb_memcg_offline(memcg);
	lru_gen_offline_memcg(memcg);

	drain_all_stock(memcg);

	mem_cgroup_id_put(memcg);
}

static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	invalidate_reclaim_iterators(memcg);
	lru_gen_release_memcg(memcg);
}

static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	int __maybe_unused i;

#ifdef CONFIG_CGROUP_WRITEBACK
	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
		wb_wait_for_completion(&memcg->cgwb_frn[i].done);
#endif
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
		static_branch_dec(&memcg_sockets_enabled_key);

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg1_tcpmem_active(memcg))
		static_branch_dec(&memcg_sockets_enabled_key);

	if (!cgroup_memory_nobpf)
		static_branch_dec(&memcg_bpf_enabled_key);

	vmpressure_cleanup(&memcg->vmpressure);
	cancel_work_sync(&memcg->high_work);
	memcg1_remove_from_trees(memcg);
	free_shrinker_info(memcg);
	mem_cgroup_free(memcg);
}

/**
 * mem_cgroup_css_reset - reset the states of a mem_cgroup
 * @css: the target css
 *
 * Reset the states of the mem_cgroup associated with @css.  This is
 * invoked when the userland requests disabling on the default hierarchy
 * but the memcg is pinned through dependency.  The memcg should stop
 * applying policies and should revert to the vanilla state as it may be
 * made visible again.
 *
 * The current implementation only resets the essential configurations.
 * This needs to be expanded to cover all the visible parts.
 */
static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX);
	page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX);
#ifdef CONFIG_MEMCG_V1
	page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
	page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
#endif
	page_counter_set_min(&memcg->memory, 0);
	page_counter_set_low(&memcg->memory, 0);
	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
	memcg1_soft_limit_reset(memcg);
	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
	memcg_wb_domain_size_changed(memcg);
}

static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
	struct memcg_vmstats_percpu *statc;
	long delta, delta_cpu, v;
	int i, nid;

	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);

	for (i = 0; i < MEMCG_VMSTAT_SIZE; i++) {
		/*
		 * Collect the aggregated propagation counts of groups
		 * below us. We're in a per-cpu loop here and this is
		 * a global counter, so the first cycle will get them.
		 */
		delta = memcg->vmstats->state_pending[i];
		if (delta)
			memcg->vmstats->state_pending[i] = 0;

		/* Add CPU changes on this level since the last flush */
		delta_cpu = 0;
		v = READ_ONCE(statc->state[i]);
		if (v != statc->state_prev[i]) {
			delta_cpu = v - statc->state_prev[i];
			delta += delta_cpu;
			statc->state_prev[i] = v;
		}

		/* Aggregate counts on this level and propagate upwards */
		if (delta_cpu)
			memcg->vmstats->state_local[i] += delta_cpu;

		if (delta) {
			memcg->vmstats->state[i] += delta;
			if (parent)
				parent->vmstats->state_pending[i] += delta;
		}
	}

	for (i = 0; i < NR_MEMCG_EVENTS; i++) {
		delta = memcg->vmstats->events_pending[i];
		if (delta)
			memcg->vmstats->events_pending[i] = 0;

		delta_cpu = 0;
		v = READ_ONCE(statc->events[i]);
		if (v != statc->events_prev[i]) {
			delta_cpu = v - statc->events_prev[i];
			delta += delta_cpu;
			statc->events_prev[i] = v;
		}

		if (delta_cpu)
			memcg->vmstats->events_local[i] += delta_cpu;

		if (delta) {
			memcg->vmstats->events[i] += delta;
			if (parent)
				parent->vmstats->events_pending[i] += delta;
		}
	}

	for_each_node_state(nid, N_MEMORY) {
		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
		struct lruvec_stats *lstats = pn->lruvec_stats;
		struct lruvec_stats *plstats = NULL;
		struct lruvec_stats_percpu *lstatc;

		if (parent)
			plstats = parent->nodeinfo[nid]->lruvec_stats;

		lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);

		for (i = 0; i < NR_MEMCG_NODE_STAT_ITEMS; i++) {
			delta = lstats->state_pending[i];
			if (delta)
				lstats->state_pending[i] = 0;

			delta_cpu = 0;
			v = READ_ONCE(lstatc->state[i]);
			if (v != lstatc->state_prev[i]) {
				delta_cpu = v - lstatc->state_prev[i];
				delta += delta_cpu;
				lstatc->state_prev[i] = v;
			}

			if (delta_cpu)
				lstats->state_local[i] += delta_cpu;

			if (delta) {
				lstats->state[i] += delta;
				if (plstats)
					plstats->state_pending[i] += delta;
			}
		}
	}
	WRITE_ONCE(statc->stats_updates, 0);
	/* We are in a per-cpu loop here, only do the atomic write once */
	if (atomic64_read(&memcg->vmstats->stats_updates))
		atomic64_set(&memcg->vmstats->stats_updates, 0);
}

static void mem_cgroup_fork(struct task_struct *task)
{
	/*
	 * Set the update flag to cause task->objcg to be initialized lazily
	 * on the first allocation. It can be done without any synchronization
	 * because it's always performed on the current task, so does
	 * current_objcg_update().
	 */
	task->objcg = (struct obj_cgroup *)CURRENT_OBJCG_UPDATE_FLAG;
}

static void mem_cgroup_exit(struct task_struct *task)
{
	struct obj_cgroup *objcg = task->objcg;

	objcg = (struct obj_cgroup *)
		((unsigned long)objcg & ~CURRENT_OBJCG_UPDATE_FLAG);
	obj_cgroup_put(objcg);

	/*
	 * Some kernel allocations can happen after this point,
	 * but let's ignore them. It can be done without any synchronization
	 * because it's always performed on the current task, so does
	 * current_objcg_update().
	 */
	task->objcg = NULL;
}

#ifdef CONFIG_LRU_GEN
static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *css;

	/* find the first leader if there is any */
	cgroup_taskset_for_each_leader(task, css, tset)
		break;

	if (!task)
		return;

	task_lock(task);
	if (task->mm && READ_ONCE(task->mm->owner) == task)
		lru_gen_migrate_mm(task->mm);
	task_unlock(task);
}
#else
static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) {}
#endif /* CONFIG_LRU_GEN */

static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *css;

	cgroup_taskset_for_each(task, css, tset) {
		/* atomically set the update bit */
		set_bit(CURRENT_OBJCG_UPDATE_BIT, (unsigned long *)&task->objcg);
	}
}

static void mem_cgroup_attach(struct cgroup_taskset *tset)
{
	mem_cgroup_lru_gen_attach(tset);
	mem_cgroup_kmem_attach(tset);
}

static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
{
	if (value == PAGE_COUNTER_MAX)
		seq_puts(m, "max\n");
	else
		seq_printf(m, "%llu\n", (u64)value * PAGE_SIZE);

	return 0;
}

static u64 memory_current_read(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE;
}

static u64 memory_peak_read(struct cgroup_subsys_state *css,
			    struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	return (u64)memcg->memory.watermark * PAGE_SIZE;
}

static int memory_min_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->memory.min));
}

static ssize_t memory_min_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long min;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &min);
	if (err)
		return err;

	page_counter_set_min(&memcg->memory, min);

	return nbytes;
}

static int memory_low_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->memory.low));
}

static ssize_t memory_low_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long low;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &low);
	if (err)
		return err;

	page_counter_set_low(&memcg->memory, low);

	return nbytes;
}

static int memory_high_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->memory.high));
}

static ssize_t memory_high_write(struct kernfs_open_file *of,
				 char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
	bool drained = false;
	unsigned long high;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &high);
	if (err)
		return err;

	page_counter_set_high(&memcg->memory, high);

	for (;;) {
		unsigned long nr_pages = page_counter_read(&memcg->memory);
		unsigned long reclaimed;

		if (nr_pages <= high)
			break;

		if (signal_pending(current))
			break;

		if (!drained) {
			drain_all_stock(memcg);
			drained = true;
			continue;
		}

		reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL);

		if (!reclaimed && !nr_retries--)
			break;
	}

	memcg_wb_domain_size_changed(memcg);
	return nbytes;
}

static int memory_max_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->memory.max));
}

static ssize_t memory_max_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned int nr_reclaims = MAX_RECLAIM_RETRIES;
	bool drained = false;
	unsigned long max;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &max);
	if (err)
		return err;

	xchg(&memcg->memory.max, max);

	for (;;) {
		unsigned long nr_pages = page_counter_read(&memcg->memory);

		if (nr_pages <= max)
			break;

		if (signal_pending(current))
			break;

		if (!drained) {
			drain_all_stock(memcg);
			drained = true;
			continue;
		}

		if (nr_reclaims) {
			if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL))
				nr_reclaims--;
			continue;
		}

		memcg_memory_event(memcg, MEMCG_OOM);
		if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0))
			break;
	}

	memcg_wb_domain_size_changed(memcg);
	return nbytes;
}

/*
 * Note: don't forget to update the 'samples/cgroup/memcg_event_listener'
 * if any new events become available.
 */
static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
{
	seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW]));
	seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH]));
	seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX]));
	seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM]));
	seq_printf(m, "oom_kill %lu\n",
		   atomic_long_read(&events[MEMCG_OOM_KILL]));
	seq_printf(m, "oom_group_kill %lu\n",
		   atomic_long_read(&events[MEMCG_OOM_GROUP_KILL]));
}

static int memory_events_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	__memory_events_show(m, memcg->memory_events);
	return 0;
}

static int memory_events_local_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	__memory_events_show(m, memcg->memory_events_local);
	return 0;
}

int memory_stat_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	struct seq_buf s;

	if (!buf)
		return -ENOMEM;
	seq_buf_init(&s, buf, PAGE_SIZE);
	memory_stat_format(memcg, &s);
	seq_puts(m, buf);
	kfree(buf);
	return 0;
}

#ifdef CONFIG_NUMA
static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec,
						     int item)
{
	return lruvec_page_state(lruvec, item) *
		memcg_page_state_output_unit(item);
}

static int memory_numa_stat_show(struct seq_file *m, void *v)
{
	int i;
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	mem_cgroup_flush_stats(memcg);

	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
		int nid;

		if (memory_stats[i].idx >= NR_VM_NODE_STAT_ITEMS)
			continue;

		seq_printf(m, "%s", memory_stats[i].name);
		for_each_node_state(nid, N_MEMORY) {
			u64 size;
			struct lruvec *lruvec;

			lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
			size = lruvec_page_state_output(lruvec,
							memory_stats[i].idx);
			seq_printf(m, " N%d=%llu", nid, size);
		}
		seq_putc(m, '\n');
	}

	return 0;
}
#endif

static int memory_oom_group_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	seq_printf(m, "%d\n", READ_ONCE(memcg->oom_group));

	return 0;
}

static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
				      char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	int ret, oom_group;

	buf = strstrip(buf);
	if (!buf)
		return -EINVAL;

	ret = kstrtoint(buf, 0, &oom_group);
	if (ret)
		return ret;

	if (oom_group != 0 && oom_group != 1)
		return -EINVAL;

	WRITE_ONCE(memcg->oom_group, oom_group);

	return nbytes;
}

enum {
	MEMORY_RECLAIM_SWAPPINESS = 0,
	MEMORY_RECLAIM_NULL,
};

static const match_table_t tokens = {
	{ MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
	{ MEMORY_RECLAIM_NULL, NULL },
};

static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
			      size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
	unsigned long nr_to_reclaim, nr_reclaimed = 0;
	int swappiness = -1;
	unsigned int reclaim_options;
	char *old_buf, *start;
	substring_t args[MAX_OPT_ARGS];

	buf = strstrip(buf);

	old_buf = buf;
	nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
	if (buf == old_buf)
		return -EINVAL;

	buf = strstrip(buf);

	while ((start = strsep(&buf, " ")) != NULL) {
		if (!strlen(start))
			continue;
		switch (match_token(start, tokens, args)) {
		case MEMORY_RECLAIM_SWAPPINESS:
			if (match_int(&args[0], &swappiness))
				return -EINVAL;
			if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS)
				return -EINVAL;
			break;
		default:
			return -EINVAL;
		}
	}

	reclaim_options	= MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
	while (nr_reclaimed < nr_to_reclaim) {
		/* Will converge on zero, but reclaim enforces a minimum */
		unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
		unsigned long reclaimed;

		if (signal_pending(current))
			return -EINTR;

		/*
		 * This is the final attempt, drain percpu lru caches in the
		 * hope of introducing more evictable pages for
		 * try_to_free_mem_cgroup_pages().
		 */
		if (!nr_retries)
			lru_add_drain_all();

		reclaimed = try_to_free_mem_cgroup_pages(memcg,
					batch_size, GFP_KERNEL,
					reclaim_options,
					swappiness == -1 ? NULL : &swappiness);

		if (!reclaimed && !nr_retries--)
			return -EAGAIN;

		nr_reclaimed += reclaimed;
	}

	return nbytes;
}

static struct cftype memory_files[] = {
	{
		.name = "current",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = memory_current_read,
	},
	{
		.name = "peak",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = memory_peak_read,
	},
	{
		.name = "min",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = memory_min_show,
		.write = memory_min_write,
	},
	{
		.name = "low",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = memory_low_show,
		.write = memory_low_write,
	},
	{
		.name = "high",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = memory_high_show,
		.write = memory_high_write,
	},
	{
		.name = "max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = memory_max_show,
		.write = memory_max_write,
	},
	{
		.name = "events",
		.flags = CFTYPE_NOT_ON_ROOT,
		.file_offset = offsetof(struct mem_cgroup, events_file),
		.seq_show = memory_events_show,
	},
	{
		.name = "events.local",
		.flags = CFTYPE_NOT_ON_ROOT,
		.file_offset = offsetof(struct mem_cgroup, events_local_file),
		.seq_show = memory_events_local_show,
	},
	{
		.name = "stat",
		.seq_show = memory_stat_show,
	},
#ifdef CONFIG_NUMA
	{
		.name = "numa_stat",
		.seq_show = memory_numa_stat_show,
	},
#endif
	{
		.name = "oom.group",
		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
		.seq_show = memory_oom_group_show,
		.write = memory_oom_group_write,
	},
	{
		.name = "reclaim",
		.flags = CFTYPE_NS_DELEGATABLE,
		.write = memory_reclaim,
	},
	{ }	/* terminate */
};

struct cgroup_subsys memory_cgrp_subsys = {
	.css_alloc = mem_cgroup_css_alloc,
	.css_online = mem_cgroup_css_online,
	.css_offline = mem_cgroup_css_offline,
	.css_released = mem_cgroup_css_released,
	.css_free = mem_cgroup_css_free,
	.css_reset = mem_cgroup_css_reset,
	.css_rstat_flush = mem_cgroup_css_rstat_flush,
	.attach = mem_cgroup_attach,
	.fork = mem_cgroup_fork,
	.exit = mem_cgroup_exit,
	.dfl_cftypes = memory_files,
#ifdef CONFIG_MEMCG_V1
	.can_attach = memcg1_can_attach,
	.cancel_attach = memcg1_cancel_attach,
	.post_attach = memcg1_move_task,
	.legacy_cftypes = mem_cgroup_legacy_files,
#endif
	.early_init = 0,
};

/**
 * mem_cgroup_calculate_protection - check if memory consumption is in the normal range
 * @root: the top ancestor of the sub-tree being checked
 * @memcg: the memory cgroup to check
 *
 * WARNING: This function is not stateless! It can only be used as part
 *          of a top-down tree iteration, not for isolated queries.
 */
void mem_cgroup_calculate_protection(struct mem_cgroup *root,
				     struct mem_cgroup *memcg)
{
	bool recursive_protection =
		cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT;

	if (mem_cgroup_disabled())
		return;

	if (!root)
		root = root_mem_cgroup;

	page_counter_calculate_protection(&root->memory, &memcg->memory, recursive_protection);
}

static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
			gfp_t gfp)
{
	int ret;

	ret = try_charge(memcg, gfp, folio_nr_pages(folio));
	if (ret)
		goto out;

	mem_cgroup_commit_charge(folio, memcg);
out:
	return ret;
}

int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
{
	struct mem_cgroup *memcg;
	int ret;

	memcg = get_mem_cgroup_from_mm(mm);
	ret = charge_memcg(folio, memcg, gfp);
	css_put(&memcg->css);

	return ret;
}

/**
 * mem_cgroup_hugetlb_try_charge - try to charge the memcg for a hugetlb folio
 * @memcg: memcg to charge.
 * @gfp: reclaim mode.
 * @nr_pages: number of pages to charge.
 *
 * This function is called when allocating a huge page folio to determine if
 * the memcg has the capacity for it. It does not commit the charge yet,
 * as the hugetlb folio itself has not been obtained from the hugetlb pool.
 *
 * Once we have obtained the hugetlb folio, we can call
 * mem_cgroup_commit_charge() to commit the charge. If we fail to obtain the
 * folio, we should instead call mem_cgroup_cancel_charge() to undo the effect
 * of try_charge().
 *
 * Returns 0 on success. Otherwise, an error code is returned.
 */
int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
			long nr_pages)
{
	/*
	 * If hugetlb memcg charging is not enabled, do not fail hugetlb allocation,
	 * but do not attempt to commit charge later (or cancel on error) either.
	 */
	if (mem_cgroup_disabled() || !memcg ||
		!cgroup_subsys_on_dfl(memory_cgrp_subsys) ||
		!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING))
		return -EOPNOTSUPP;

	if (try_charge(memcg, gfp, nr_pages))
		return -ENOMEM;

	return 0;
}

/**
 * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin.
 * @folio: folio to charge.
 * @mm: mm context of the victim
 * @gfp: reclaim mode
 * @entry: swap entry for which the folio is allocated
 *
 * This function charges a folio allocated for swapin. Please call this before
 * adding the folio to the swapcache.
 *
 * Returns 0 on success. Otherwise, an error code is returned.
 */
int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
				  gfp_t gfp, swp_entry_t entry)
{
	struct mem_cgroup *memcg;
	unsigned short id;
	int ret;

	if (mem_cgroup_disabled())
		return 0;

	id = lookup_swap_cgroup_id(entry);
	rcu_read_lock();
	memcg = mem_cgroup_from_id(id);
	if (!memcg || !css_tryget_online(&memcg->css))
		memcg = get_mem_cgroup_from_mm(mm);
	rcu_read_unlock();

	ret = charge_memcg(folio, memcg, gfp);

	css_put(&memcg->css);
	return ret;
}

/*
 * mem_cgroup_swapin_uncharge_swap - uncharge swap slot
 * @entry: swap entry for which the page is charged
 *
 * Call this function after successfully adding the charged page to swapcache.
 *
 * Note: This function assumes the page for which swap slot is being uncharged
 * is order 0 page.
 */
void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
{
	/*
	 * Cgroup1's unified memory+swap counter has been charged with the
	 * new swapcache page, finish the transfer by uncharging the swap
	 * slot. The swap slot would also get uncharged when it dies, but
	 * it can stick around indefinitely and we'd count the page twice
	 * the entire time.
	 *
	 * Cgroup2 has separate resource counters for memory and swap,
	 * so this is a non-issue here. Memory and swap charge lifetimes
	 * correspond 1:1 to page and swap slot lifetimes: we charge the
	 * page to memory here, and uncharge swap when the slot is freed.
	 */
	if (!mem_cgroup_disabled() && do_memsw_account()) {
		/*
		 * The swap entry might not get freed for a long time,
		 * let's not wait for it.  The page already received a
		 * memory+swap charge, drop the swap entry duplicate.
		 */
		mem_cgroup_uncharge_swap(entry, 1);
	}
}

struct uncharge_gather {
	struct mem_cgroup *memcg;
	unsigned long nr_memory;
	unsigned long pgpgout;
	unsigned long nr_kmem;
	int nid;
};

static inline void uncharge_gather_clear(struct uncharge_gather *ug)
{
	memset(ug, 0, sizeof(*ug));
}

static void uncharge_batch(const struct uncharge_gather *ug)
{
	unsigned long flags;

	if (ug->nr_memory) {
		page_counter_uncharge(&ug->memcg->memory, ug->nr_memory);
		if (do_memsw_account())
			page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory);
		if (ug->nr_kmem) {
			mod_memcg_state(ug->memcg, MEMCG_KMEM, -ug->nr_kmem);
			memcg1_account_kmem(ug->memcg, -ug->nr_kmem);
		}
		memcg1_oom_recover(ug->memcg);
	}

	local_irq_save(flags);
	__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory);
	memcg1_check_events(ug->memcg, ug->nid);
	local_irq_restore(flags);

	/* drop reference from uncharge_folio */
	css_put(&ug->memcg->css);
}

static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
{
	long nr_pages;
	struct mem_cgroup *memcg;
	struct obj_cgroup *objcg;

	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
	VM_BUG_ON_FOLIO(folio_order(folio) > 1 &&
			!folio_test_hugetlb(folio) &&
			!list_empty(&folio->_deferred_list), folio);

	/*
	 * Nobody should be changing or seriously looking at
	 * folio memcg or objcg at this point, we have fully
	 * exclusive access to the folio.
	 */
	if (folio_memcg_kmem(folio)) {
		objcg = __folio_objcg(folio);
		/*
		 * This get matches the put at the end of the function and
		 * kmem pages do not hold memcg references anymore.
		 */
		memcg = get_mem_cgroup_from_objcg(objcg);
	} else {
		memcg = __folio_memcg(folio);
	}

	if (!memcg)
		return;

	if (ug->memcg != memcg) {
		if (ug->memcg) {
			uncharge_batch(ug);
			uncharge_gather_clear(ug);
		}
		ug->memcg = memcg;
		ug->nid = folio_nid(folio);

		/* pairs with css_put in uncharge_batch */
		css_get(&memcg->css);
	}

	nr_pages = folio_nr_pages(folio);

	if (folio_memcg_kmem(folio)) {
		ug->nr_memory += nr_pages;
		ug->nr_kmem += nr_pages;

		folio->memcg_data = 0;
		obj_cgroup_put(objcg);
	} else {
		/* LRU pages aren't accounted at the root level */
		if (!mem_cgroup_is_root(memcg))
			ug->nr_memory += nr_pages;
		ug->pgpgout++;

		folio->memcg_data = 0;
	}

	css_put(&memcg->css);
}

void __mem_cgroup_uncharge(struct folio *folio)
{
	struct uncharge_gather ug;

	/* Don't touch folio->lru of any random page, pre-check: */
	if (!folio_memcg(folio))
		return;

	uncharge_gather_clear(&ug);
	uncharge_folio(folio, &ug);
	uncharge_batch(&ug);
}

void __mem_cgroup_uncharge_folios(struct folio_batch *folios)
{
	struct uncharge_gather ug;
	unsigned int i;

	uncharge_gather_clear(&ug);
	for (i = 0; i < folios->nr; i++)
		uncharge_folio(folios->folios[i], &ug);
	if (ug.memcg)
		uncharge_batch(&ug);
}

/**
 * mem_cgroup_replace_folio - Charge a folio's replacement.
 * @old: Currently circulating folio.
 * @new: Replacement folio.
 *
 * Charge @new as a replacement folio for @old. @old will
 * be uncharged upon free.
 *
 * Both folios must be locked, @new->mapping must be set up.
 */
void mem_cgroup_replace_folio(struct folio *old, struct folio *new)
{
	struct mem_cgroup *memcg;
	long nr_pages = folio_nr_pages(new);
	unsigned long flags;

	VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
	VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
	VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new);
	VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new);

	if (mem_cgroup_disabled())
		return;

	/* Page cache replacement: new folio already charged? */
	if (folio_memcg(new))
		return;

	memcg = folio_memcg(old);
	VM_WARN_ON_ONCE_FOLIO(!memcg, old);
	if (!memcg)
		return;

	/* Force-charge the new page. The old one will be freed soon */
	if (!mem_cgroup_is_root(memcg)) {
		page_counter_charge(&memcg->memory, nr_pages);
		if (do_memsw_account())
			page_counter_charge(&memcg->memsw, nr_pages);
	}

	css_get(&memcg->css);
	commit_charge(new, memcg);

	local_irq_save(flags);
	mem_cgroup_charge_statistics(memcg, nr_pages);
	memcg1_check_events(memcg, folio_nid(new));
	local_irq_restore(flags);
}

/**
 * mem_cgroup_migrate - Transfer the memcg data from the old to the new folio.
 * @old: Currently circulating folio.
 * @new: Replacement folio.
 *
 * Transfer the memcg data from the old folio to the new folio for migration.
 * The old folio's data info will be cleared. Note that the memory counters
 * will remain unchanged throughout the process.
 *
 * Both folios must be locked, @new->mapping must be set up.
 */
void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
	struct mem_cgroup *memcg;

	VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
	VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
	VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new);
	VM_BUG_ON_FOLIO(folio_nr_pages(old) != folio_nr_pages(new), new);
	VM_BUG_ON_FOLIO(folio_test_lru(old), old);

	if (mem_cgroup_disabled())
		return;

	memcg = folio_memcg(old);
	/*
	 * Note that it is normal to see !memcg for a hugetlb folio.
	 * For e.g, itt could have been allocated when memory_hugetlb_accounting
	 * was not selected.
	 */
	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(old) && !memcg, old);
	if (!memcg)
		return;

	/* Transfer the charge and the css ref */
	commit_charge(new, memcg);
	old->memcg_data = 0;
}

DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
EXPORT_SYMBOL(memcg_sockets_enabled_key);

void mem_cgroup_sk_alloc(struct sock *sk)
{
	struct mem_cgroup *memcg;

	if (!mem_cgroup_sockets_enabled)
		return;

	/* Do not associate the sock with unrelated interrupted task's memcg. */
	if (!in_task())
		return;

	rcu_read_lock();
	memcg = mem_cgroup_from_task(current);
	if (mem_cgroup_is_root(memcg))
		goto out;
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg1_tcpmem_active(memcg))
		goto out;
	if (css_tryget(&memcg->css))
		sk->sk_memcg = memcg;
out:
	rcu_read_unlock();
}

void mem_cgroup_sk_free(struct sock *sk)
{
	if (sk->sk_memcg)
		css_put(&sk->sk_memcg->css);
}

/**
 * mem_cgroup_charge_skmem - charge socket memory
 * @memcg: memcg to charge
 * @nr_pages: number of pages to charge
 * @gfp_mask: reclaim mode
 *
 * Charges @nr_pages to @memcg. Returns %true if the charge fit within
 * @memcg's configured limit, %false if it doesn't.
 */
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
			     gfp_t gfp_mask)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return memcg1_charge_skmem(memcg, nr_pages, gfp_mask);

	if (try_charge(memcg, gfp_mask, nr_pages) == 0) {
		mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
		return true;
	}

	return false;
}

/**
 * mem_cgroup_uncharge_skmem - uncharge socket memory
 * @memcg: memcg to uncharge
 * @nr_pages: number of pages to uncharge
 */
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
		memcg1_uncharge_skmem(memcg, nr_pages);
		return;
	}

	mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages);

	refill_stock(memcg, nr_pages);
}

static int __init cgroup_memory(char *s)
{
	char *token;

	while ((token = strsep(&s, ",")) != NULL) {
		if (!*token)
			continue;
		if (!strcmp(token, "nosocket"))
			cgroup_memory_nosocket = true;
		if (!strcmp(token, "nokmem"))
			cgroup_memory_nokmem = true;
		if (!strcmp(token, "nobpf"))
			cgroup_memory_nobpf = true;
	}
	return 1;
}
__setup("cgroup.memory=", cgroup_memory);

/*
 * subsys_initcall() for memory controller.
 *
 * Some parts like memcg_hotplug_cpu_dead() have to be initialized from this
 * context because of lock dependencies (cgroup_lock -> cpu hotplug) but
 * basically everything that doesn't depend on a specific mem_cgroup structure
 * should be initialized from here.
 */
static int __init mem_cgroup_init(void)
{
	int cpu;

	/*
	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
	 * used for per-memcg-per-cpu caching of per-node statistics. In order
	 * to work fine, we should make sure that the overfill threshold can't
	 * exceed S32_MAX / PAGE_SIZE.
	 */
	BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);

	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
				  memcg_hotplug_cpu_dead);

	for_each_possible_cpu(cpu)
		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
			  drain_local_stock);

	return 0;
}
subsys_initcall(mem_cgroup_init);

#ifdef CONFIG_SWAP
static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
{
	while (!refcount_inc_not_zero(&memcg->id.ref)) {
		/*
		 * The root cgroup cannot be destroyed, so it's refcount must
		 * always be >= 1.
		 */
		if (WARN_ON_ONCE(mem_cgroup_is_root(memcg))) {
			VM_BUG_ON(1);
			break;
		}
		memcg = parent_mem_cgroup(memcg);
		if (!memcg)
			memcg = root_mem_cgroup;
	}
	return memcg;
}

/**
 * mem_cgroup_swapout - transfer a memsw charge to swap
 * @folio: folio whose memsw charge to transfer
 * @entry: swap entry to move the charge to
 *
 * Transfer the memsw charge of @folio to @entry.
 */
void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
{
	struct mem_cgroup *memcg, *swap_memcg;
	unsigned int nr_entries;
	unsigned short oldid;

	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
	VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);

	if (mem_cgroup_disabled())
		return;

	if (!do_memsw_account())
		return;

	memcg = folio_memcg(folio);

	VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
	if (!memcg)
		return;

	/*
	 * In case the memcg owning these pages has been offlined and doesn't
	 * have an ID allocated to it anymore, charge the closest online
	 * ancestor for the swap instead and transfer the memory+swap charge.
	 */
	swap_memcg = mem_cgroup_id_get_online(memcg);
	nr_entries = folio_nr_pages(folio);
	/* Get references for the tail pages, too */
	if (nr_entries > 1)
		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
	oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
				   nr_entries);
	VM_BUG_ON_FOLIO(oldid, folio);
	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);

	folio->memcg_data = 0;

	if (!mem_cgroup_is_root(memcg))
		page_counter_uncharge(&memcg->memory, nr_entries);

	if (memcg != swap_memcg) {
		if (!mem_cgroup_is_root(swap_memcg))
			page_counter_charge(&swap_memcg->memsw, nr_entries);
		page_counter_uncharge(&memcg->memsw, nr_entries);
	}

	/*
	 * Interrupts should be disabled here because the caller holds the
	 * i_pages lock which is taken with interrupts-off. It is
	 * important here to have the interrupts disabled because it is the
	 * only synchronisation we have for updating the per-CPU variables.
	 */
	memcg_stats_lock();
	mem_cgroup_charge_statistics(memcg, -nr_entries);
	memcg_stats_unlock();
	memcg1_check_events(memcg, folio_nid(folio));

	css_put(&memcg->css);
}

/**
 * __mem_cgroup_try_charge_swap - try charging swap space for a folio
 * @folio: folio being added to swap
 * @entry: swap entry to charge
 *
 * Try to charge @folio's memcg for the swap space at @entry.
 *
 * Returns 0 on success, -ENOMEM on failure.
 */
int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
{
	unsigned int nr_pages = folio_nr_pages(folio);
	struct page_counter *counter;
	struct mem_cgroup *memcg;
	unsigned short oldid;

	if (do_memsw_account())
		return 0;

	memcg = folio_memcg(folio);

	VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
	if (!memcg)
		return 0;

	if (!entry.val) {
		memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
		return 0;
	}

	memcg = mem_cgroup_id_get_online(memcg);

	if (!mem_cgroup_is_root(memcg) &&
	    !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) {
		memcg_memory_event(memcg, MEMCG_SWAP_MAX);
		memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
		mem_cgroup_id_put(memcg);
		return -ENOMEM;
	}

	/* Get references for the tail pages, too */
	if (nr_pages > 1)
		mem_cgroup_id_get_many(memcg, nr_pages - 1);
	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
	VM_BUG_ON_FOLIO(oldid, folio);
	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);

	return 0;
}

/**
 * __mem_cgroup_uncharge_swap - uncharge swap space
 * @entry: swap entry to uncharge
 * @nr_pages: the amount of swap space to uncharge
 */
void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
{
	struct mem_cgroup *memcg;
	unsigned short id;

	id = swap_cgroup_record(entry, 0, nr_pages);
	rcu_read_lock();
	memcg = mem_cgroup_from_id(id);
	if (memcg) {
		if (!mem_cgroup_is_root(memcg)) {
			if (do_memsw_account())
				page_counter_uncharge(&memcg->memsw, nr_pages);
			else
				page_counter_uncharge(&memcg->swap, nr_pages);
		}
		mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages);
		mem_cgroup_id_put_many(memcg, nr_pages);
	}
	rcu_read_unlock();
}

long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
{
	long nr_swap_pages = get_nr_swap_pages();

	if (mem_cgroup_disabled() || do_memsw_account())
		return nr_swap_pages;
	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg))
		nr_swap_pages = min_t(long, nr_swap_pages,
				      READ_ONCE(memcg->swap.max) -
				      page_counter_read(&memcg->swap));
	return nr_swap_pages;
}

bool mem_cgroup_swap_full(struct folio *folio)
{
	struct mem_cgroup *memcg;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);

	if (vm_swap_full())
		return true;
	if (do_memsw_account())
		return false;

	memcg = folio_memcg(folio);
	if (!memcg)
		return false;

	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
		unsigned long usage = page_counter_read(&memcg->swap);

		if (usage * 2 >= READ_ONCE(memcg->swap.high) ||
		    usage * 2 >= READ_ONCE(memcg->swap.max))
			return true;
	}

	return false;
}

static int __init setup_swap_account(char *s)
{
	bool res;

	if (!kstrtobool(s, &res) && !res)
		pr_warn_once("The swapaccount=0 commandline option is deprecated "
			     "in favor of configuring swap control via cgroupfs. "
			     "Please report your usecase to linux-mm@kvack.org if you "
			     "depend on this functionality.\n");
	return 1;
}
__setup("swapaccount=", setup_swap_account);

static u64 swap_current_read(struct cgroup_subsys_state *css,
			     struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE;
}

static u64 swap_peak_read(struct cgroup_subsys_state *css,
			  struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	return (u64)memcg->swap.watermark * PAGE_SIZE;
}

static int swap_high_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->swap.high));
}

static ssize_t swap_high_write(struct kernfs_open_file *of,
			       char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long high;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &high);
	if (err)
		return err;

	page_counter_set_high(&memcg->swap, high);

	return nbytes;
}

static int swap_max_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->swap.max));
}

static ssize_t swap_max_write(struct kernfs_open_file *of,
			      char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long max;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &max);
	if (err)
		return err;

	xchg(&memcg->swap.max, max);

	return nbytes;
}

static int swap_events_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	seq_printf(m, "high %lu\n",
		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH]));
	seq_printf(m, "max %lu\n",
		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX]));
	seq_printf(m, "fail %lu\n",
		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_FAIL]));

	return 0;
}

static struct cftype swap_files[] = {
	{
		.name = "swap.current",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = swap_current_read,
	},
	{
		.name = "swap.high",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = swap_high_show,
		.write = swap_high_write,
	},
	{
		.name = "swap.max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = swap_max_show,
		.write = swap_max_write,
	},
	{
		.name = "swap.peak",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = swap_peak_read,
	},
	{
		.name = "swap.events",
		.flags = CFTYPE_NOT_ON_ROOT,
		.file_offset = offsetof(struct mem_cgroup, swap_events_file),
		.seq_show = swap_events_show,
	},
	{ }	/* terminate */
};

#ifdef CONFIG_ZSWAP
/**
 * obj_cgroup_may_zswap - check if this cgroup can zswap
 * @objcg: the object cgroup
 *
 * Check if the hierarchical zswap limit has been reached.
 *
 * This doesn't check for specific headroom, and it is not atomic
 * either. But with zswap, the size of the allocation is only known
 * once compression has occurred, and this optimistic pre-check avoids
 * spending cycles on compression when there is already no room left
 * or zswap is disabled altogether somewhere in the hierarchy.
 */
bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
{
	struct mem_cgroup *memcg, *original_memcg;
	bool ret = true;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return true;

	original_memcg = get_mem_cgroup_from_objcg(objcg);
	for (memcg = original_memcg; !mem_cgroup_is_root(memcg);
	     memcg = parent_mem_cgroup(memcg)) {
		unsigned long max = READ_ONCE(memcg->zswap_max);
		unsigned long pages;

		if (max == PAGE_COUNTER_MAX)
			continue;
		if (max == 0) {
			ret = false;
			break;
		}

		/*
		 * mem_cgroup_flush_stats() ignores small changes. Use
		 * do_flush_stats() directly to get accurate stats for charging.
		 */
		do_flush_stats(memcg);
		pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
		if (pages < max)
			continue;
		ret = false;
		break;
	}
	mem_cgroup_put(original_memcg);
	return ret;
}

/**
 * obj_cgroup_charge_zswap - charge compression backend memory
 * @objcg: the object cgroup
 * @size: size of compressed object
 *
 * This forces the charge after obj_cgroup_may_zswap() allowed
 * compression and storage in zwap for this cgroup to go ahead.
 */
void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size)
{
	struct mem_cgroup *memcg;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return;

	VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC));

	/* PF_MEMALLOC context, charging must succeed */
	if (obj_cgroup_charge(objcg, GFP_KERNEL, size))
		VM_WARN_ON_ONCE(1);

	rcu_read_lock();
	memcg = obj_cgroup_memcg(objcg);
	mod_memcg_state(memcg, MEMCG_ZSWAP_B, size);
	mod_memcg_state(memcg, MEMCG_ZSWAPPED, 1);
	rcu_read_unlock();
}

/**
 * obj_cgroup_uncharge_zswap - uncharge compression backend memory
 * @objcg: the object cgroup
 * @size: size of compressed object
 *
 * Uncharges zswap memory on page in.
 */
void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
{
	struct mem_cgroup *memcg;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return;

	obj_cgroup_uncharge(objcg, size);

	rcu_read_lock();
	memcg = obj_cgroup_memcg(objcg);
	mod_memcg_state(memcg, MEMCG_ZSWAP_B, -size);
	mod_memcg_state(memcg, MEMCG_ZSWAPPED, -1);
	rcu_read_unlock();
}

bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
{
	/* if zswap is disabled, do not block pages going to the swapping device */
	return !zswap_is_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
}

static u64 zswap_current_read(struct cgroup_subsys_state *css,
			      struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	mem_cgroup_flush_stats(memcg);
	return memcg_page_state(memcg, MEMCG_ZSWAP_B);
}

static int zswap_max_show(struct seq_file *m, void *v)
{
	return seq_puts_memcg_tunable(m,
		READ_ONCE(mem_cgroup_from_seq(m)->zswap_max));
}

static ssize_t zswap_max_write(struct kernfs_open_file *of,
			       char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long max;
	int err;

	buf = strstrip(buf);
	err = page_counter_memparse(buf, "max", &max);
	if (err)
		return err;

	xchg(&memcg->zswap_max, max);

	return nbytes;
}

static int zswap_writeback_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback));
	return 0;
}

static ssize_t zswap_writeback_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	int zswap_writeback;
	ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback);

	if (parse_ret)
		return parse_ret;

	if (zswap_writeback != 0 && zswap_writeback != 1)
		return -EINVAL;

	WRITE_ONCE(memcg->zswap_writeback, zswap_writeback);
	return nbytes;
}

static struct cftype zswap_files[] = {
	{
		.name = "zswap.current",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = zswap_current_read,
	},
	{
		.name = "zswap.max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = zswap_max_show,
		.write = zswap_max_write,
	},
	{
		.name = "zswap.writeback",
		.seq_show = zswap_writeback_show,
		.write = zswap_writeback_write,
	},
	{ }	/* terminate */
};
#endif /* CONFIG_ZSWAP */

static int __init mem_cgroup_swap_init(void)
{
	if (mem_cgroup_disabled())
		return 0;

	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files));
#ifdef CONFIG_MEMCG_V1
	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files));
#endif
#ifdef CONFIG_ZSWAP
	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, zswap_files));
#endif
	return 0;
}
subsys_initcall(mem_cgroup_swap_init);

#endif /* CONFIG_SWAP */