summaryrefslogtreecommitdiff
path: root/mm/memcontrol.c
blob: bdac56009a38c0c84cd36bbf1bd474537af76a17 (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
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
// 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
 */

#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/vm_event_item.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/sort.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmpressure.h>
#include <linux/mm_inline.h>
#include <linux/swap_cgroup.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/lockdep.h>
#include <linux/file.h>
#include <linux/tracehook.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
#include "slab.h"

#include <linux/uaccess.h>

#include <trace/events/vmscan.h>

struct cgroup_subsys memory_cgrp_subsys __read_mostly;
EXPORT_SYMBOL(memory_cgrp_subsys);

struct mem_cgroup *root_mem_cgroup __read_mostly;

#define MEM_CGROUP_RECLAIM_RETRIES	5

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

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

/* Whether the swap controller is active */
#ifdef CONFIG_MEMCG_SWAP
int do_swap_account __read_mostly;
#else
#define do_swap_account		0
#endif

#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif

/* Whether legacy memory+swap accounting is active */
static bool do_memsw_account(void)
{
	return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account;
}

static const char *const mem_cgroup_lru_names[] = {
	"inactive_anon",
	"active_anon",
	"inactive_file",
	"active_file",
	"unevictable",
};

#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
#define NUMAINFO_EVENTS_TARGET	1024

/*
 * Cgroups above their limits are maintained in a RB-Tree, independent of
 * their hierarchy representation
 */

struct mem_cgroup_tree_per_node {
	struct rb_root rb_root;
	struct rb_node *rb_rightmost;
	spinlock_t lock;
};

struct mem_cgroup_tree {
	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
};

static struct mem_cgroup_tree soft_limit_tree __read_mostly;

/* for OOM */
struct mem_cgroup_eventfd_list {
	struct list_head list;
	struct eventfd_ctx *eventfd;
};

/*
 * cgroup_event represents events which userspace want to receive.
 */
struct mem_cgroup_event {
	/*
	 * memcg which the event belongs to.
	 */
	struct mem_cgroup *memcg;
	/*
	 * eventfd to signal userspace about the event.
	 */
	struct eventfd_ctx *eventfd;
	/*
	 * Each of these stored in a list by the cgroup.
	 */
	struct list_head list;
	/*
	 * register_event() callback will be used to add new userspace
	 * waiter for changes related to this event.  Use eventfd_signal()
	 * on eventfd to send notification to userspace.
	 */
	int (*register_event)(struct mem_cgroup *memcg,
			      struct eventfd_ctx *eventfd, const char *args);
	/*
	 * unregister_event() callback will be called when userspace closes
	 * the eventfd or on cgroup removing.  This callback must be set,
	 * if you want provide notification functionality.
	 */
	void (*unregister_event)(struct mem_cgroup *memcg,
				 struct eventfd_ctx *eventfd);
	/*
	 * All fields below needed to unregister event when
	 * userspace closes eventfd.
	 */
	poll_table pt;
	wait_queue_head_t *wqh;
	wait_queue_entry_t wait;
	struct work_struct remove;
};

static void mem_cgroup_threshold(struct mem_cgroup *memcg);
static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);

/* Stuffs for move charges at task migration. */
/*
 * Types of charges to be moved.
 */
#define MOVE_ANON	0x1U
#define MOVE_FILE	0x2U
#define MOVE_MASK	(MOVE_ANON | MOVE_FILE)

/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
	spinlock_t	  lock; /* for from, to */
	struct mm_struct  *mm;
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	unsigned long flags;
	unsigned long precharge;
	unsigned long moved_charge;
	unsigned long moved_swap;
	struct task_struct *moving_task;	/* a task moving charges */
	wait_queue_head_t waitq;		/* a waitq for other context */
} mc = {
	.lock = __SPIN_LOCK_UNLOCKED(mc.lock),
	.waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
};

/*
 * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
 * limit reclaim to prevent infinite loops, if they ever occur.
 */
#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_ANON,
	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
	NR_CHARGE_TYPE,
};

/* for encoding cft->private value on file */
enum res_type {
	_MEM,
	_MEMSWAP,
	_OOM_TYPE,
	_KMEM,
	_TCP,
};

#define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
#define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)
/* Used for OOM nofiier */
#define OOM_CONTROL		(0)

/*
 * Iteration constructs for visiting all cgroups (under a tree).  If
 * loops are exited prematurely (break), mem_cgroup_iter_break() must
 * be used for reference counting.
 */
#define for_each_mem_cgroup_tree(iter, root)		\
	for (iter = mem_cgroup_iter(root, NULL, NULL);	\
	     iter != NULL;				\
	     iter = mem_cgroup_iter(root, iter, NULL))

#define for_each_mem_cgroup(iter)			\
	for (iter = mem_cgroup_iter(NULL, NULL, NULL);	\
	     iter != NULL;				\
	     iter = mem_cgroup_iter(NULL, iter, NULL))

static inline bool should_force_charge(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 cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
{
	return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
}

#ifdef CONFIG_MEMCG_KMEM
/*
 * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
 * The main reason for not using cgroup id for this:
 *  this works better in sparse environments, where we have a lot of memcgs,
 *  but only a few kmem-limited. Or also, if we have, for instance, 200
 *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
 *  200 entry array for that.
 *
 * The current size of the caches array is stored in memcg_nr_cache_ids. It
 * will double each time we have to increase it.
 */
static DEFINE_IDA(memcg_cache_ida);
int memcg_nr_cache_ids;

/* Protects memcg_nr_cache_ids */
static DECLARE_RWSEM(memcg_cache_ids_sem);

void memcg_get_cache_ids(void)
{
	down_read(&memcg_cache_ids_sem);
}

void memcg_put_cache_ids(void)
{
	up_read(&memcg_cache_ids_sem);
}

/*
 * MIN_SIZE is different than 1, because we would like to avoid going through
 * the alloc/free process all the time. In a small machine, 4 kmem-limited
 * cgroups is a reasonable guess. In the future, it could be a parameter or
 * tunable, but that is strictly not necessary.
 *
 * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
 * this constant directly from cgroup, but it is understandable that this is
 * better kept as an internal representation in cgroup.c. In any case, the
 * cgrp_id space is not getting any smaller, and we don't have to necessarily
 * increase ours as well if it increases.
 */
#define MEMCG_CACHES_MIN_SIZE 4
#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX

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

struct workqueue_struct *memcg_kmem_cache_wq;
#endif

static int memcg_shrinker_map_size;
static DEFINE_MUTEX(memcg_shrinker_map_mutex);

static void memcg_free_shrinker_map_rcu(struct rcu_head *head)
{
	kvfree(container_of(head, struct memcg_shrinker_map, rcu));
}

static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg,
					 int size, int old_size)
{
	struct memcg_shrinker_map *new, *old;
	int nid;

	lockdep_assert_held(&memcg_shrinker_map_mutex);

	for_each_node(nid) {
		old = rcu_dereference_protected(
			mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
		/* Not yet online memcg */
		if (!old)
			return 0;

		new = kvmalloc(sizeof(*new) + size, GFP_KERNEL);
		if (!new)
			return -ENOMEM;

		/* Set all old bits, clear all new bits */
		memset(new->map, (int)0xff, old_size);
		memset((void *)new->map + old_size, 0, size - old_size);

		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new);
		call_rcu(&old->rcu, memcg_free_shrinker_map_rcu);
	}

	return 0;
}

static void memcg_free_shrinker_maps(struct mem_cgroup *memcg)
{
	struct mem_cgroup_per_node *pn;
	struct memcg_shrinker_map *map;
	int nid;

	if (mem_cgroup_is_root(memcg))
		return;

	for_each_node(nid) {
		pn = mem_cgroup_nodeinfo(memcg, nid);
		map = rcu_dereference_protected(pn->shrinker_map, true);
		if (map)
			kvfree(map);
		rcu_assign_pointer(pn->shrinker_map, NULL);
	}
}

static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg)
{
	struct memcg_shrinker_map *map;
	int nid, size, ret = 0;

	if (mem_cgroup_is_root(memcg))
		return 0;

	mutex_lock(&memcg_shrinker_map_mutex);
	size = memcg_shrinker_map_size;
	for_each_node(nid) {
		map = kvzalloc(sizeof(*map) + size, GFP_KERNEL);
		if (!map) {
			memcg_free_shrinker_maps(memcg);
			ret = -ENOMEM;
			break;
		}
		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
	}
	mutex_unlock(&memcg_shrinker_map_mutex);

	return ret;
}

int memcg_expand_shrinker_maps(int new_id)
{
	int size, old_size, ret = 0;
	struct mem_cgroup *memcg;

	size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long);
	old_size = memcg_shrinker_map_size;
	if (size <= old_size)
		return 0;

	mutex_lock(&memcg_shrinker_map_mutex);
	if (!root_mem_cgroup)
		goto unlock;

	for_each_mem_cgroup(memcg) {
		if (mem_cgroup_is_root(memcg))
			continue;
		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
		if (ret)
			goto unlock;
	}
unlock:
	if (!ret)
		memcg_shrinker_map_size = size;
	mutex_unlock(&memcg_shrinker_map_mutex);
	return ret;
}

void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
{
	if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
		struct memcg_shrinker_map *map;

		rcu_read_lock();
		map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
		/* Pairs with smp mb in shrink_slab() */
		smp_mb__before_atomic();
		set_bit(shrinker_id, map->map);
		rcu_read_unlock();
	}
}

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

	memcg = page->mem_cgroup;

	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();
	if (PageHead(page) && PageSlab(page))
		memcg = memcg_from_slab_page(page);
	else
		memcg = READ_ONCE(page->mem_cgroup);
	while (memcg && !(memcg->css.flags & CSS_ONLINE))
		memcg = parent_mem_cgroup(memcg);
	if (memcg)
		ino = cgroup_ino(memcg->css.cgroup);
	rcu_read_unlock();
	return ino;
}

static struct mem_cgroup_per_node *
mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
{
	int nid = page_to_nid(page);

	return memcg->nodeinfo[nid];
}

static struct mem_cgroup_tree_per_node *
soft_limit_tree_node(int nid)
{
	return soft_limit_tree.rb_tree_per_node[nid];
}

static struct mem_cgroup_tree_per_node *
soft_limit_tree_from_page(struct page *page)
{
	int nid = page_to_nid(page);

	return soft_limit_tree.rb_tree_per_node[nid];
}

static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
					 struct mem_cgroup_tree_per_node *mctz,
					 unsigned long new_usage_in_excess)
{
	struct rb_node **p = &mctz->rb_root.rb_node;
	struct rb_node *parent = NULL;
	struct mem_cgroup_per_node *mz_node;
	bool rightmost = true;

	if (mz->on_tree)
		return;

	mz->usage_in_excess = new_usage_in_excess;
	if (!mz->usage_in_excess)
		return;
	while (*p) {
		parent = *p;
		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
					tree_node);
		if (mz->usage_in_excess < mz_node->usage_in_excess) {
			p = &(*p)->rb_left;
			rightmost = false;
		}

		/*
		 * We can't avoid mem cgroups that are over their soft
		 * limit by the same amount
		 */
		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
			p = &(*p)->rb_right;
	}

	if (rightmost)
		mctz->rb_rightmost = &mz->tree_node;

	rb_link_node(&mz->tree_node, parent, p);
	rb_insert_color(&mz->tree_node, &mctz->rb_root);
	mz->on_tree = true;
}

static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
					 struct mem_cgroup_tree_per_node *mctz)
{
	if (!mz->on_tree)
		return;

	if (&mz->tree_node == mctz->rb_rightmost)
		mctz->rb_rightmost = rb_prev(&mz->tree_node);

	rb_erase(&mz->tree_node, &mctz->rb_root);
	mz->on_tree = false;
}

static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
				       struct mem_cgroup_tree_per_node *mctz)
{
	unsigned long flags;

	spin_lock_irqsave(&mctz->lock, flags);
	__mem_cgroup_remove_exceeded(mz, mctz);
	spin_unlock_irqrestore(&mctz->lock, flags);
}

static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
{
	unsigned long nr_pages = page_counter_read(&memcg->memory);
	unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
	unsigned long excess = 0;

	if (nr_pages > soft_limit)
		excess = nr_pages - soft_limit;

	return excess;
}

static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
{
	unsigned long excess;
	struct mem_cgroup_per_node *mz;
	struct mem_cgroup_tree_per_node *mctz;

	mctz = soft_limit_tree_from_page(page);
	if (!mctz)
		return;
	/*
	 * Necessary to update all ancestors when hierarchy is used.
	 * because their event counter is not touched.
	 */
	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
		mz = mem_cgroup_page_nodeinfo(memcg, page);
		excess = soft_limit_excess(memcg);
		/*
		 * We have to update the tree if mz is on RB-tree or
		 * mem is over its softlimit.
		 */
		if (excess || mz->on_tree) {
			unsigned long flags;

			spin_lock_irqsave(&mctz->lock, flags);
			/* if on-tree, remove it */
			if (mz->on_tree)
				__mem_cgroup_remove_exceeded(mz, mctz);
			/*
			 * Insert again. mz->usage_in_excess will be updated.
			 * If excess is 0, no tree ops.
			 */
			__mem_cgroup_insert_exceeded(mz, mctz, excess);
			spin_unlock_irqrestore(&mctz->lock, flags);
		}
	}
}

static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
	struct mem_cgroup_tree_per_node *mctz;
	struct mem_cgroup_per_node *mz;
	int nid;

	for_each_node(nid) {
		mz = mem_cgroup_nodeinfo(memcg, nid);
		mctz = soft_limit_tree_node(nid);
		if (mctz)
			mem_cgroup_remove_exceeded(mz, mctz);
	}
}

static struct mem_cgroup_per_node *
__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
	struct mem_cgroup_per_node *mz;

retry:
	mz = NULL;
	if (!mctz->rb_rightmost)
		goto done;		/* Nothing to reclaim from */

	mz = rb_entry(mctz->rb_rightmost,
		      struct mem_cgroup_per_node, tree_node);
	/*
	 * Remove the node now but someone else can add it back,
	 * we will to add it back at the end of reclaim to its correct
	 * position in the tree.
	 */
	__mem_cgroup_remove_exceeded(mz, mctz);
	if (!soft_limit_excess(mz->memcg) ||
	    !css_tryget_online(&mz->memcg->css))
		goto retry;
done:
	return mz;
}

static struct mem_cgroup_per_node *
mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
{
	struct mem_cgroup_per_node *mz;

	spin_lock_irq(&mctz->lock);
	mz = __mem_cgroup_largest_soft_limit_node(mctz);
	spin_unlock_irq(&mctz->lock);
	return mz;
}

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

	if (mem_cgroup_disabled())
		return;

	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup *mi;

		/*
		 * Batch local counters to keep them in sync with
		 * the hierarchical ones.
		 */
		__this_cpu_add(memcg->vmstats_local->stat[idx], x);
		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
			atomic_long_add(x, &mi->vmstats[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->vmstats_percpu->stat[idx], x);
}

static struct mem_cgroup_per_node *
parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
{
	struct mem_cgroup *parent;

	parent = parent_mem_cgroup(pn->memcg);
	if (!parent)
		return NULL;
	return mem_cgroup_nodeinfo(parent, nid);
}

/**
 * __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)
{
	pg_data_t *pgdat = lruvec_pgdat(lruvec);
	struct mem_cgroup_per_node *pn;
	struct mem_cgroup *memcg;
	long x;

	/* Update node */
	__mod_node_page_state(pgdat, idx, val);

	if (mem_cgroup_disabled())
		return;

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

	/* Update memcg */
	__mod_memcg_state(memcg, idx, val);

	/* Update lruvec */
	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);

	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup_per_node *pi;

		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
			atomic_long_add(x, &pi->lruvec_stat[idx]);
		x = 0;
	}
	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}

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

	rcu_read_lock();
	memcg = memcg_from_slab_page(page);

	/* Untracked pages have no memcg, no lruvec. Update only the node */
	if (!memcg || memcg == root_mem_cgroup) {
		__mod_node_page_state(pgdat, idx, val);
	} else {
		lruvec = mem_cgroup_lruvec(pgdat, memcg);
		__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 occured
 */
void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
			  unsigned long count)
{
	unsigned long x;

	if (mem_cgroup_disabled())
		return;

	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
		struct mem_cgroup *mi;

		/*
		 * Batch local counters to keep them in sync with
		 * the hierarchical ones.
		 */
		__this_cpu_add(memcg->vmstats_local->events[idx], x);
		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
			atomic_long_add(x, &mi->vmevents[idx]);
		x = 0;
	}
	__this_cpu_write(memcg->vmstats_percpu->events[idx], x);
}

static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
{
	return atomic_long_read(&memcg->vmevents[event]);
}

static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
{
	long x = 0;
	int cpu;

	for_each_possible_cpu(cpu)
		x += per_cpu(memcg->vmstats_local->events[event], cpu);
	return x;
}

static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
					 struct page *page,
					 bool compound, int nr_pages)
{
	/*
	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
	 * counted as CACHE even if it's on ANON LRU.
	 */
	if (PageAnon(page))
		__mod_memcg_state(memcg, MEMCG_RSS, nr_pages);
	else {
		__mod_memcg_state(memcg, MEMCG_CACHE, nr_pages);
		if (PageSwapBacked(page))
			__mod_memcg_state(memcg, NR_SHMEM, nr_pages);
	}

	if (compound) {
		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
		__mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages);
	}

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

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

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

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

/*
 * Check events in order.
 *
 */
static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
{
	/* threshold event is triggered in finer grain than soft limit */
	if (unlikely(mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_THRESH))) {
		bool do_softlimit;
		bool do_numainfo __maybe_unused;

		do_softlimit = mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_SOFTLIMIT);
#if MAX_NUMNODES > 1
		do_numainfo = mem_cgroup_event_ratelimit(memcg,
						MEM_CGROUP_TARGET_NUMAINFO);
#endif
		mem_cgroup_threshold(memcg);
		if (unlikely(do_softlimit))
			mem_cgroup_update_tree(memcg, page);
#if MAX_NUMNODES > 1
		if (unlikely(do_numainfo))
			atomic_inc(&memcg->numainfo_events);
#endif
	}
}

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);

/**
 * 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. Otherwise
 * root_mem_cgroup is returned. However 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;

	rcu_read_lock();
	do {
		/*
		 * Page cache insertions can happen withou an
		 * actual mm context, e.g. during disk probing
		 * on boot, loopback IO, acct() writes etc.
		 */
		if (unlikely(!mm))
			memcg = root_mem_cgroup;
		else {
			memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
			if (unlikely(!memcg))
				memcg = root_mem_cgroup;
		}
	} while (!css_tryget_online(&memcg->css));
	rcu_read_unlock();
	return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);

/**
 * get_mem_cgroup_from_page: Obtain a reference on given page's memcg.
 * @page: page from which memcg should be extracted.
 *
 * Obtain a reference on page->memcg and returns it if successful. Otherwise
 * root_mem_cgroup is returned.
 */
struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
{
	struct mem_cgroup *memcg = page->mem_cgroup;

	if (mem_cgroup_disabled())
		return NULL;

	rcu_read_lock();
	if (!memcg || !css_tryget_online(&memcg->css))
		memcg = root_mem_cgroup;
	rcu_read_unlock();
	return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_page);

/**
 * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
 */
static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
{
	if (unlikely(current->active_memcg)) {
		struct mem_cgroup *memcg = root_mem_cgroup;

		rcu_read_lock();
		if (css_tryget_online(&current->active_memcg->css))
			memcg = current->active_memcg;
		rcu_read_unlock();
		return memcg;
	}
	return get_mem_cgroup_from_mm(current->mm);
}

/**
 * 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 and a priority level in @reclaim to
 * divide up the memcgs in the hierarchy among all concurrent
 * reclaimers operating on the same node and priority.
 */
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 *uninitialized_var(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;

	if (prev && !reclaim)
		pos = prev;

	if (!root->use_hierarchy && root != root_mem_cgroup) {
		if (prev)
			goto out;
		return root;
	}

	rcu_read_lock();

	if (reclaim) {
		struct mem_cgroup_per_node *mz;

		mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
		iter = &mz->iter[reclaim->priority];

		if (prev && 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);
		}
	}

	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.
		 */
		memcg = mem_cgroup_from_css(css);

		if (css == &root->css)
			break;

		if (css_tryget(css))
			break;

		memcg = NULL;
	}

	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++;
		else if (!prev)
			reclaim->generation = iter->generation;
	}

out_unlock:
	rcu_read_unlock();
out:
	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;
	int i;

	for_each_node(nid) {
		mz = mem_cgroup_nodeinfo(from, nid);
		for (i = 0; i <= DEF_PRIORITY; i++) {
			iter = &mz->iter[i];
			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 cgruop1 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 (last != root_mem_cgroup)
		__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 and returns the value.
 * Otherwise, it will iterate over all tasks and return 0.
 *
 * This function must not be called for the root memory cgroup.
 */
int 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(memcg == root_mem_cgroup);

	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;
		}
	}
	return ret;
}

/**
 * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
 * @page: the page
 * @pgdat: pgdat of the page
 *
 * This function is only safe when following the LRU page isolation
 * and putback protocol: the LRU lock must be held, and the page must
 * either be PageLRU() or the caller must have isolated/allocated it.
 */
struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
{
	struct mem_cgroup_per_node *mz;
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	if (mem_cgroup_disabled()) {
		lruvec = &pgdat->lruvec;
		goto out;
	}

	memcg = page->mem_cgroup;
	/*
	 * Swapcache readahead pages are added to the LRU - and
	 * possibly migrated - before they are charged.
	 */
	if (!memcg)
		memcg = root_mem_cgroup;

	mz = mem_cgroup_page_nodeinfo(memcg, page);
	lruvec = &mz->lruvec;
out:
	/*
	 * Since a node can be onlined after the mem_cgroup was created,
	 * we have to be prepared to initialize lruvec->zone here;
	 * and if offlined then reonlined, we need to reinitialize it.
	 */
	if (unlikely(lruvec->pgdat != pgdat))
		lruvec->pgdat = pgdat;
	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 (that ordering being
 * so as to allow it to check that lru_size 0 is consistent with list_empty).
 */
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;
}

/*
 * A routine for checking "mem" is under move_account() or not.
 *
 * Checking a cgroup is mc.from or mc.to or under hierarchy of
 * moving cgroups. This is for waiting at high-memory pressure
 * caused by "move".
 */
static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
{
	struct mem_cgroup *from;
	struct mem_cgroup *to;
	bool ret = false;
	/*
	 * Unlike task_move routines, we access mc.to, mc.from not under
	 * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
	 */
	spin_lock(&mc.lock);
	from = mc.from;
	to = mc.to;
	if (!from)
		goto unlock;

	ret = mem_cgroup_is_descendant(from, memcg) ||
		mem_cgroup_is_descendant(to, memcg);
unlock:
	spin_unlock(&mc.lock);
	return ret;
}

static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
{
	if (mc.moving_task && current != mc.moving_task) {
		if (mem_cgroup_under_move(memcg)) {
			DEFINE_WAIT(wait);
			prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
			/* moving charge context might have finished. */
			if (mc.moving_task)
				schedule();
			finish_wait(&mc.waitq, &wait);
			return true;
		}
	}
	return false;
}

static char *memory_stat_format(struct mem_cgroup *memcg)
{
	struct seq_buf s;
	int i;

	seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE);
	if (!s.buffer)
		return NULL;

	/*
	 * 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:
	 */

	seq_buf_printf(&s, "anon %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_RSS) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_CACHE) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "kernel_stack %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
		       1024);
	seq_buf_printf(&s, "slab %llu\n",
		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "sock %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
		       PAGE_SIZE);

	seq_buf_printf(&s, "shmem %llu\n",
		       (u64)memcg_page_state(memcg, NR_SHMEM) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_mapped %llu\n",
		       (u64)memcg_page_state(memcg, NR_FILE_MAPPED) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_dirty %llu\n",
		       (u64)memcg_page_state(memcg, NR_FILE_DIRTY) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "file_writeback %llu\n",
		       (u64)memcg_page_state(memcg, NR_WRITEBACK) *
		       PAGE_SIZE);

	/*
	 * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter
	 * with the NR_ANON_THP vm counter, but right now it's a pain in the
	 * arse because it requires migrating the work out of rmap to a place
	 * where the page->mem_cgroup is set up and stable.
	 */
	seq_buf_printf(&s, "anon_thp %llu\n",
		       (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) *
		       PAGE_SIZE);

	for (i = 0; i < NR_LRU_LISTS; i++)
		seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i],
			       (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
			       PAGE_SIZE);

	seq_buf_printf(&s, "slab_reclaimable %llu\n",
		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
		       PAGE_SIZE);
	seq_buf_printf(&s, "slab_unreclaimable %llu\n",
		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
		       PAGE_SIZE);

	/* Accumulated memory events */

	seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT));
	seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT));

	seq_buf_printf(&s, "workingset_refault %lu\n",
		       memcg_page_state(memcg, WORKINGSET_REFAULT));
	seq_buf_printf(&s, "workingset_activate %lu\n",
		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));

	seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL));
	seq_buf_printf(&s, "pgscan %lu\n",
		       memcg_events(memcg, PGSCAN_KSWAPD) +
		       memcg_events(memcg, PGSCAN_DIRECT));
	seq_buf_printf(&s, "pgsteal %lu\n",
		       memcg_events(memcg, PGSTEAL_KSWAPD) +
		       memcg_events(memcg, PGSTEAL_DIRECT));
	seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE));
	seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE));
	seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE));
	seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED));

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	seq_buf_printf(&s, "thp_fault_alloc %lu\n",
		       memcg_events(memcg, THP_FAULT_ALLOC));
	seq_buf_printf(&s, "thp_collapse_alloc %lu\n",
		       memcg_events(memcg, THP_COLLAPSE_ALLOC));
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

	/* The above should easily fit into one page */
	WARN_ON_ONCE(seq_buf_has_overflowed(&s));

	return s.buffer;
}

#define K(x) ((x) << (PAGE_SHIFT-10))
/**
 * 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)
{
	char *buf;

	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
		K((u64)page_counter_read(&memcg->memory)),
		K((u64)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)memcg->swap.max), memcg->swap.failcnt);
	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);
	}

	pr_info("Memory cgroup stats for ");
	pr_cont_cgroup_path(memcg->css.cgroup);
	pr_cont(":");
	buf = memory_stat_format(memcg);
	if (!buf)
		return;
	pr_info("%s", buf);
	kfree(buf);
}

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

	max = memcg->memory.max;
	if (mem_cgroup_swappiness(memcg)) {
		unsigned long memsw_max;
		unsigned long swap_max;

		memsw_max = memcg->memsw.max;
		swap_max = memcg->swap.max;
		swap_max = min(swap_max, (unsigned long)total_swap_pages);
		max = min(max + swap_max, memsw_max);
	}
	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;

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

#if MAX_NUMNODES > 1

/**
 * test_mem_cgroup_node_reclaimable
 * @memcg: the target memcg
 * @nid: the node ID to be checked.
 * @noswap : specify true here if the user wants flle only information.
 *
 * This function returns whether the specified memcg contains any
 * reclaimable pages on a node. Returns true if there are any reclaimable
 * pages in the node.
 */
static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
		int nid, bool noswap)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);

	if (lruvec_page_state(lruvec, NR_INACTIVE_FILE) ||
	    lruvec_page_state(lruvec, NR_ACTIVE_FILE))
		return true;
	if (noswap || !total_swap_pages)
		return false;
	if (lruvec_page_state(lruvec, NR_INACTIVE_ANON) ||
	    lruvec_page_state(lruvec, NR_ACTIVE_ANON))
		return true;
	return false;

}

/*
 * Always updating the nodemask is not very good - even if we have an empty
 * list or the wrong list here, we can start from some node and traverse all
 * nodes based on the zonelist. So update the list loosely once per 10 secs.
 *
 */
static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
{
	int nid;
	/*
	 * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
	 * pagein/pageout changes since the last update.
	 */
	if (!atomic_read(&memcg->numainfo_events))
		return;
	if (atomic_inc_return(&memcg->numainfo_updating) > 1)
		return;

	/* make a nodemask where this memcg uses memory from */
	memcg->scan_nodes = node_states[N_MEMORY];

	for_each_node_mask(nid, node_states[N_MEMORY]) {

		if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
			node_clear(nid, memcg->scan_nodes);
	}

	atomic_set(&memcg->numainfo_events, 0);
	atomic_set(&memcg->numainfo_updating, 0);
}

/*
 * Selecting a node where we start reclaim from. Because what we need is just
 * reducing usage counter, start from anywhere is O,K. Considering
 * memory reclaim from current node, there are pros. and cons.
 *
 * Freeing memory from current node means freeing memory from a node which
 * we'll use or we've used. So, it may make LRU bad. And if several threads
 * hit limits, it will see a contention on a node. But freeing from remote
 * node means more costs for memory reclaim because of memory latency.
 *
 * Now, we use round-robin. Better algorithm is welcomed.
 */
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
	int node;

	mem_cgroup_may_update_nodemask(memcg);
	node = memcg->last_scanned_node;

	node = next_node_in(node, memcg->scan_nodes);
	/*
	 * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages
	 * last time it really checked all the LRUs due to rate limiting.
	 * Fallback to the current node in that case for simplicity.
	 */
	if (unlikely(node == MAX_NUMNODES))
		node = numa_node_id();

	memcg->last_scanned_node = node;
	return node;
}
#else
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
	return 0;
}
#endif

static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
				   pg_data_t *pgdat,
				   gfp_t gfp_mask,
				   unsigned long *total_scanned)
{
	struct mem_cgroup *victim = NULL;
	int total = 0;
	int loop = 0;
	unsigned long excess;
	unsigned long nr_scanned;
	struct mem_cgroup_reclaim_cookie reclaim = {
		.pgdat = pgdat,
		.priority = 0,
	};

	excess = soft_limit_excess(root_memcg);

	while (1) {
		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
		if (!victim) {
			loop++;
			if (loop >= 2) {
				/*
				 * If we have not been able to reclaim
				 * anything, it might because there are
				 * no reclaimable pages under this hierarchy
				 */
				if (!total)
					break;
				/*
				 * We want to do more targeted reclaim.
				 * excess >> 2 is not to excessive so as to
				 * reclaim too much, nor too less that we keep
				 * coming back to reclaim from this cgroup
				 */
				if (total >= (excess >> 2) ||
					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
					break;
			}
			continue;
		}
		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
					pgdat, &nr_scanned);
		*total_scanned += nr_scanned;
		if (!soft_limit_excess(root_memcg))
			break;
	}
	mem_cgroup_iter_break(root_memcg, victim);
	return total;
}

#ifdef CONFIG_LOCKDEP
static struct lockdep_map memcg_oom_lock_dep_map = {
	.name = "memcg_oom_lock",
};
#endif

static DEFINE_SPINLOCK(memcg_oom_lock);

/*
 * Check OOM-Killer is already running under our hierarchy.
 * If someone is running, return false.
 */
static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter, *failed = NULL;

	spin_lock(&memcg_oom_lock);

	for_each_mem_cgroup_tree(iter, memcg) {
		if (iter->oom_lock) {
			/*
			 * this subtree of our hierarchy is already locked
			 * so we cannot give a lock.
			 */
			failed = iter;
			mem_cgroup_iter_break(memcg, iter);
			break;
		} else
			iter->oom_lock = true;
	}

	if (failed) {
		/*
		 * OK, we failed to lock the whole subtree so we have
		 * to clean up what we set up to the failing subtree
		 */
		for_each_mem_cgroup_tree(iter, memcg) {
			if (iter == failed) {
				mem_cgroup_iter_break(memcg, iter);
				break;
			}
			iter->oom_lock = false;
		}
	} else
		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);

	spin_unlock(&memcg_oom_lock);

	return !failed;
}

static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	spin_lock(&memcg_oom_lock);
	mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_);
	for_each_mem_cgroup_tree(iter, memcg)
		iter->oom_lock = false;
	spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		iter->under_oom++;
	spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	/*
	 * When a new child is created while the hierarchy is under oom,
	 * mem_cgroup_oom_lock() may not be called. Watch for underflow.
	 */
	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		if (iter->under_oom > 0)
			iter->under_oom--;
	spin_unlock(&memcg_oom_lock);
}

static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);

struct oom_wait_info {
	struct mem_cgroup *memcg;
	wait_queue_entry_t	wait;
};

static int memcg_oom_wake_function(wait_queue_entry_t *wait,
	unsigned mode, int sync, void *arg)
{
	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
	struct mem_cgroup *oom_wait_memcg;
	struct oom_wait_info *oom_wait_info;

	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
	oom_wait_memcg = oom_wait_info->memcg;

	if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
	    !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
		return 0;
	return autoremove_wake_function(wait, mode, sync, arg);
}

static void memcg_oom_recover(struct mem_cgroup *memcg)
{
	/*
	 * For the following lockless ->under_oom test, the only required
	 * guarantee is that it must see the state asserted by an OOM when
	 * this function is called as a result of userland actions
	 * triggered by the notification of the OOM.  This is trivially
	 * achieved by invoking mem_cgroup_mark_under_oom() before
	 * triggering notification.
	 */
	if (memcg && memcg->under_oom)
		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}

enum oom_status {
	OOM_SUCCESS,
	OOM_FAILED,
	OOM_ASYNC,
	OOM_SKIPPED
};

static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
	enum oom_status ret;
	bool locked;

	if (order > PAGE_ALLOC_COSTLY_ORDER)
		return OOM_SKIPPED;

	memcg_memory_event(memcg, MEMCG_OOM);

	/*
	 * We are in the middle of the charge context here, so we
	 * don't want to block when potentially sitting on a callstack
	 * that holds all kinds of filesystem and mm locks.
	 *
	 * cgroup1 allows disabling the OOM killer and waiting for outside
	 * handling until the charge can succeed; remember the context and put
	 * the task to sleep at the end of the page fault when all locks are
	 * released.
	 *
	 * On the other hand, in-kernel OOM killer allows for an async victim
	 * memory reclaim (oom_reaper) and that means that we are not solely
	 * relying on the oom victim to make a forward progress and we can
	 * invoke the oom killer here.
	 *
	 * Please note that mem_cgroup_out_of_memory might fail to find a
	 * victim and then we have to bail out from the charge path.
	 */
	if (memcg->oom_kill_disable) {
		if (!current->in_user_fault)
			return OOM_SKIPPED;
		css_get(&memcg->css);
		current->memcg_in_oom = memcg;
		current->memcg_oom_gfp_mask = mask;
		current->memcg_oom_order = order;

		return OOM_ASYNC;
	}

	mem_cgroup_mark_under_oom(memcg);

	locked = mem_cgroup_oom_trylock(memcg);

	if (locked)
		mem_cgroup_oom_notify(memcg);

	mem_cgroup_unmark_under_oom(memcg);
	if (mem_cgroup_out_of_memory(memcg, mask, order))
		ret = OOM_SUCCESS;
	else
		ret = OOM_FAILED;

	if (locked)
		mem_cgroup_oom_unlock(memcg);

	return ret;
}

/**
 * mem_cgroup_oom_synchronize - complete memcg OOM handling
 * @handle: actually kill/wait or just clean up the OOM state
 *
 * This has to be called at the end of a page fault if the memcg OOM
 * handler was enabled.
 *
 * Memcg supports userspace OOM handling where failed allocations must
 * sleep on a waitqueue until the userspace task resolves the
 * situation.  Sleeping directly in the charge context with all kinds
 * of locks held is not a good idea, instead we remember an OOM state
 * in the task and mem_cgroup_oom_synchronize() has to be called at
 * the end of the page fault to complete the OOM handling.
 *
 * Returns %true if an ongoing memcg OOM situation was detected and
 * completed, %false otherwise.
 */
bool mem_cgroup_oom_synchronize(bool handle)
{
	struct mem_cgroup *memcg = current->memcg_in_oom;
	struct oom_wait_info owait;
	bool locked;

	/* OOM is global, do not handle */
	if (!memcg)
		return false;

	if (!handle)
		goto cleanup;

	owait.memcg = memcg;
	owait.wait.flags = 0;
	owait.wait.func = memcg_oom_wake_function;
	owait.wait.private = current;
	INIT_LIST_HEAD(&owait.wait.entry);

	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
	mem_cgroup_mark_under_oom(memcg);

	locked = mem_cgroup_oom_trylock(memcg);

	if (locked)
		mem_cgroup_oom_notify(memcg);

	if (locked && !memcg->oom_kill_disable) {
		mem_cgroup_unmark_under_oom(memcg);
		finish_wait(&memcg_oom_waitq, &owait.wait);
		mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
					 current->memcg_oom_order);
	} else {
		schedule();
		mem_cgroup_unmark_under_oom(memcg);
		finish_wait(&memcg_oom_waitq, &owait.wait);
	}

	if (locked) {
		mem_cgroup_oom_unlock(memcg);
		/*
		 * There is no guarantee that an OOM-lock contender
		 * sees the wakeups triggered by the OOM kill
		 * uncharges.  Wake any sleepers explicitely.
		 */
		memcg_oom_recover(memcg);
	}
cleanup:
	current->memcg_in_oom = NULL;
	css_put(&memcg->css);
	return true;
}

/**
 * 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 (memcg == root_mem_cgroup)
		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 (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");
}

/**
 * lock_page_memcg - lock a page->mem_cgroup binding
 * @page: the page
 *
 * This function protects unlocked LRU pages from being moved to
 * another cgroup.
 *
 * It ensures lifetime of the returned memcg. Caller is responsible
 * for the lifetime of the page; __unlock_page_memcg() is available
 * when @page might get freed inside the locked section.
 */
struct mem_cgroup *lock_page_memcg(struct page *page)
{
	struct mem_cgroup *memcg;
	unsigned long flags;

	/*
	 * The RCU lock is held throughout the transaction.  The fast
	 * path can get away without acquiring the memcg->move_lock
	 * because page moving starts with an RCU grace period.
	 *
	 * The RCU lock also protects the memcg from being freed when
	 * the page state that is going to change is the only thing
	 * preventing the page itself from being freed. E.g. writeback
	 * doesn't hold a page reference and relies on PG_writeback to
	 * keep off truncation, migration and so forth.
         */
	rcu_read_lock();

	if (mem_cgroup_disabled())
		return NULL;
again:
	memcg = page->mem_cgroup;
	if (unlikely(!memcg))
		return NULL;

	if (atomic_read(&memcg->moving_account) <= 0)
		return memcg;

	spin_lock_irqsave(&memcg->move_lock, flags);
	if (memcg != page->mem_cgroup) {
		spin_unlock_irqrestore(&memcg->move_lock, flags);
		goto again;
	}

	/*
	 * When charge migration first begins, we can have locked and
	 * unlocked page stat updates happening concurrently.  Track
	 * the task who has the lock for unlock_page_memcg().
	 */
	memcg->move_lock_task = current;
	memcg->move_lock_flags = flags;

	return memcg;
}
EXPORT_SYMBOL(lock_page_memcg);

/**
 * __unlock_page_memcg - unlock and unpin a memcg
 * @memcg: the memcg
 *
 * Unlock and unpin a memcg returned by lock_page_memcg().
 */
void __unlock_page_memcg(struct mem_cgroup *memcg)
{
	if (memcg && memcg->move_lock_task == current) {
		unsigned long flags = memcg->move_lock_flags;

		memcg->move_lock_task = NULL;
		memcg->move_lock_flags = 0;

		spin_unlock_irqrestore(&memcg->move_lock, flags);
	}

	rcu_read_unlock();
}

/**
 * unlock_page_memcg - unlock a page->mem_cgroup binding
 * @page: the page
 */
void unlock_page_memcg(struct page *page)
{
	__unlock_page_memcg(page->mem_cgroup);
}
EXPORT_SYMBOL(unlock_page_memcg);

struct memcg_stock_pcp {
	struct mem_cgroup *cached; /* this never be root cgroup */
	unsigned int nr_pages;
	struct work_struct work;
	unsigned long flags;
#define FLUSHING_CACHED_CHARGE	0
};
static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
static DEFINE_MUTEX(percpu_charge_mutex);

/**
 * 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 long flags;
	bool ret = false;

	if (nr_pages > MEMCG_CHARGE_BATCH)
		return ret;

	local_irq_save(flags);

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

	local_irq_restore(flags);

	return ret;
}

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

	if (stock->nr_pages) {
		page_counter_uncharge(&old->memory, stock->nr_pages);
		if (do_memsw_account())
			page_counter_uncharge(&old->memsw, stock->nr_pages);
		css_put_many(&old->css, stock->nr_pages);
		stock->nr_pages = 0;
	}
	stock->cached = NULL;
}

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

	/*
	 * The only protection from memory hotplug vs. drain_stock races is
	 * that we always operate on local CPU stock here with IRQ disabled
	 */
	local_irq_save(flags);

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

	local_irq_restore(flags);
}

/*
 * 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 long flags;

	local_irq_save(flags);

	stock = this_cpu_ptr(&memcg_stock);
	if (stock->cached != memcg) { /* reset if necessary */
		drain_stock(stock);
		stock->cached = memcg;
	}
	stock->nr_pages += nr_pages;

	if (stock->nr_pages > MEMCG_CHARGE_BATCH)
		drain_stock(stock);

	local_irq_restore(flags);
}

/*
 * Drains all per-CPU charge caches for given root_memcg resp. subtree
 * of the hierarchy under it.
 */
static 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.
	 */
	curcpu = get_cpu();
	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 = stock->cached;
		if (memcg && stock->nr_pages &&
		    mem_cgroup_is_descendant(memcg, 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
				schedule_work_on(cpu, &stock->work);
		}
	}
	put_cpu();
	mutex_unlock(&percpu_charge_mutex);
}

static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
	struct memcg_stock_pcp *stock;
	struct mem_cgroup *memcg, *mi;

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

	for_each_mem_cgroup(memcg) {
		int i;

		for (i = 0; i < MEMCG_NR_STAT; i++) {
			int nid;
			long x;

			x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0);
			if (x)
				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
					atomic_long_add(x, &memcg->vmstats[i]);

			if (i >= NR_VM_NODE_STAT_ITEMS)
				continue;

			for_each_node(nid) {
				struct mem_cgroup_per_node *pn;

				pn = mem_cgroup_nodeinfo(memcg, nid);
				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
				if (x)
					do {
						atomic_long_add(x, &pn->lruvec_stat[i]);
					} while ((pn = parent_nodeinfo(pn, nid)));
			}
		}

		for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
			long x;

			x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0);
			if (x)
				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
					atomic_long_add(x, &memcg->vmevents[i]);
		}
	}

	return 0;
}

static void reclaim_high(struct mem_cgroup *memcg,
			 unsigned int nr_pages,
			 gfp_t gfp_mask)
{
	do {
		if (page_counter_read(&memcg->memory) <= memcg->high)
			continue;
		memcg_memory_event(memcg, MEMCG_HIGH);
		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
	} while ((memcg = parent_mem_cgroup(memcg)));
}

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 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

/*
 * Scheduled by try_charge() to be executed from the userland return path
 * and reclaims memory over the high limit.
 */
void mem_cgroup_handle_over_high(void)
{
	unsigned long usage, high, clamped_high;
	unsigned long pflags;
	unsigned long penalty_jiffies, overage;
	unsigned int nr_pages = current->memcg_nr_pages_over_high;
	struct mem_cgroup *memcg;

	if (likely(!nr_pages))
		return;

	memcg = get_mem_cgroup_from_mm(current->mm);
	reclaim_high(memcg, nr_pages, GFP_KERNEL);
	current->memcg_nr_pages_over_high = 0;

	/*
	 * memory.high is breached and reclaim is unable to keep up. Throttle
	 * allocators proactively to slow down excessive growth.
	 *
	 * 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.
	 */

	usage = page_counter_read(&memcg->memory);
	high = READ_ONCE(memcg->high);

	if (usage <= high)
		goto out;

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

	overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
			  clamped_high);

	penalty_jiffies = ((u64)overage * overage * HZ)
		>> (MEMCG_DELAY_PRECISION_SHIFT + 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.
	 */
	penalty_jiffies = penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;

	/*
	 * 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 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);
}

static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
		      unsigned int nr_pages)
{
	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
	struct mem_cgroup *mem_over_limit;
	struct page_counter *counter;
	unsigned long nr_reclaimed;
	bool may_swap = true;
	bool drained = false;
	enum oom_status oom_status;

	if (mem_cgroup_is_root(memcg))
		return 0;
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);
		may_swap = false;
	}

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

	/*
	 * Unlike in global OOM situations, memcg is not in a physical
	 * memory shortage.  Allow dying and OOM-killed tasks to
	 * bypass the last charges so that they can exit quickly and
	 * free their memory.
	 */
	if (unlikely(should_force_charge()))
		goto force;

	/*
	 * 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);

	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
						    gfp_mask, may_swap);

	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 (mem_cgroup_wait_acct_move(mem_over_limit))
		goto retry;

	if (nr_retries--)
		goto retry;

	if (gfp_mask & __GFP_RETRY_MAYFAIL)
		goto nomem;

	if (gfp_mask & __GFP_NOFAIL)
		goto force;

	if (fatal_signal_pending(current))
		goto force;

	/*
	 * 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.
	 */
	oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask,
		       get_order(nr_pages * PAGE_SIZE));
	switch (oom_status) {
	case OOM_SUCCESS:
		nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
		goto retry;
	case OOM_FAILED:
		goto force;
	default:
		goto nomem;
	}
nomem:
	if (!(gfp_mask & __GFP_NOFAIL))
		return -ENOMEM;
force:
	/*
	 * 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);
	css_get_many(&memcg->css, nr_pages);

	return 0;

done_restock:
	css_get_many(&memcg->css, batch);
	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 {
		if (page_counter_read(&memcg->memory) > memcg->high) {
			/* Don't bother a random interrupted task */
			if (in_interrupt()) {
				schedule_work(&memcg->high_work);
				break;
			}
			current->memcg_nr_pages_over_high += batch;
			set_notify_resume(current);
			break;
		}
	} while ((memcg = parent_mem_cgroup(memcg)));

	return 0;
}

static void 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);

	css_put_many(&memcg->css, nr_pages);
}

static void lock_page_lru(struct page *page, int *isolated)
{
	pg_data_t *pgdat = page_pgdat(page);

	spin_lock_irq(&pgdat->lru_lock);
	if (PageLRU(page)) {
		struct lruvec *lruvec;

		lruvec = mem_cgroup_page_lruvec(page, pgdat);
		ClearPageLRU(page);
		del_page_from_lru_list(page, lruvec, page_lru(page));
		*isolated = 1;
	} else
		*isolated = 0;
}

static void unlock_page_lru(struct page *page, int isolated)
{
	pg_data_t *pgdat = page_pgdat(page);

	if (isolated) {
		struct lruvec *lruvec;

		lruvec = mem_cgroup_page_lruvec(page, pgdat);
		VM_BUG_ON_PAGE(PageLRU(page), page);
		SetPageLRU(page);
		add_page_to_lru_list(page, lruvec, page_lru(page));
	}
	spin_unlock_irq(&pgdat->lru_lock);
}

static void commit_charge(struct page *page, struct mem_cgroup *memcg,
			  bool lrucare)
{
	int isolated;

	VM_BUG_ON_PAGE(page->mem_cgroup, page);

	/*
	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
	 * may already be on some other mem_cgroup's LRU.  Take care of it.
	 */
	if (lrucare)
		lock_page_lru(page, &isolated);

	/*
	 * Nobody should be changing or seriously looking at
	 * page->mem_cgroup at this point:
	 *
	 * - the page is uncharged
	 *
	 * - the page is off-LRU
	 *
	 * - an anonymous fault has exclusive page access, except for
	 *   a locked page table
	 *
	 * - a page cache insertion, a swapin fault, or a migration
	 *   have the page locked
	 */
	page->mem_cgroup = memcg;

	if (lrucare)
		unlock_page_lru(page, isolated);
}

#ifdef CONFIG_MEMCG_KMEM
static int memcg_alloc_cache_id(void)
{
	int id, size;
	int err;

	id = ida_simple_get(&memcg_cache_ida,
			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
	if (id < 0)
		return id;

	if (id < memcg_nr_cache_ids)
		return id;

	/*
	 * There's no space for the new id in memcg_caches arrays,
	 * so we have to grow them.
	 */
	down_write(&memcg_cache_ids_sem);

	size = 2 * (id + 1);
	if (size < MEMCG_CACHES_MIN_SIZE)
		size = MEMCG_CACHES_MIN_SIZE;
	else if (size > MEMCG_CACHES_MAX_SIZE)
		size = MEMCG_CACHES_MAX_SIZE;

	err = memcg_update_all_caches(size);
	if (!err)
		err = memcg_update_all_list_lrus(size);
	if (!err)
		memcg_nr_cache_ids = size;

	up_write(&memcg_cache_ids_sem);

	if (err) {
		ida_simple_remove(&memcg_cache_ida, id);
		return err;
	}
	return id;
}

static void memcg_free_cache_id(int id)
{
	ida_simple_remove(&memcg_cache_ida, id);
}

struct memcg_kmem_cache_create_work {
	struct mem_cgroup *memcg;
	struct kmem_cache *cachep;
	struct work_struct work;
};

static void memcg_kmem_cache_create_func(struct work_struct *w)
{
	struct memcg_kmem_cache_create_work *cw =
		container_of(w, struct memcg_kmem_cache_create_work, work);
	struct mem_cgroup *memcg = cw->memcg;
	struct kmem_cache *cachep = cw->cachep;

	memcg_create_kmem_cache(memcg, cachep);

	css_put(&memcg->css);
	kfree(cw);
}

/*
 * Enqueue the creation of a per-memcg kmem_cache.
 */
static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
					       struct kmem_cache *cachep)
{
	struct memcg_kmem_cache_create_work *cw;

	if (!css_tryget_online(&memcg->css))
		return;

	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
	if (!cw)
		return;

	cw->memcg = memcg;
	cw->cachep = cachep;
	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);

	queue_work(memcg_kmem_cache_wq, &cw->work);
}

static inline bool memcg_kmem_bypass(void)
{
	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
		return true;
	return false;
}

/**
 * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
 * @cachep: the original global kmem cache
 *
 * Return the kmem_cache we're supposed to use for a slab allocation.
 * We try to use the current memcg's version of the cache.
 *
 * If the cache does not exist yet, if we are the first user of it, we
 * create it asynchronously in a workqueue and let the current allocation
 * go through with the original cache.
 *
 * This function takes a reference to the cache it returns to assure it
 * won't get destroyed while we are working with it. Once the caller is
 * done with it, memcg_kmem_put_cache() must be called to release the
 * reference.
 */
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
{
	struct mem_cgroup *memcg;
	struct kmem_cache *memcg_cachep;
	struct memcg_cache_array *arr;
	int kmemcg_id;

	VM_BUG_ON(!is_root_cache(cachep));

	if (memcg_kmem_bypass())
		return cachep;

	rcu_read_lock();

	if (unlikely(current->active_memcg))
		memcg = current->active_memcg;
	else
		memcg = mem_cgroup_from_task(current);

	if (!memcg || memcg == root_mem_cgroup)
		goto out_unlock;

	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
	if (kmemcg_id < 0)
		goto out_unlock;

	arr = rcu_dereference(cachep->memcg_params.memcg_caches);

	/*
	 * Make sure we will access the up-to-date value. The code updating
	 * memcg_caches issues a write barrier to match the data dependency
	 * barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
	 */
	memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);

	/*
	 * If we are in a safe context (can wait, and not in interrupt
	 * context), we could be be predictable and return right away.
	 * This would guarantee that the allocation being performed
	 * already belongs in the new cache.
	 *
	 * However, there are some clashes that can arrive from locking.
	 * For instance, because we acquire the slab_mutex while doing
	 * memcg_create_kmem_cache, this means no further allocation
	 * could happen with the slab_mutex held. So it's better to
	 * defer everything.
	 *
	 * If the memcg is dying or memcg_cache is about to be released,
	 * don't bother creating new kmem_caches. Because memcg_cachep
	 * is ZEROed as the fist step of kmem offlining, we don't need
	 * percpu_ref_tryget_live() here. css_tryget_online() check in
	 * memcg_schedule_kmem_cache_create() will prevent us from
	 * creation of a new kmem_cache.
	 */
	if (unlikely(!memcg_cachep))
		memcg_schedule_kmem_cache_create(memcg, cachep);
	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
		cachep = memcg_cachep;
out_unlock:
	rcu_read_unlock();
	return cachep;
}

/**
 * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
 * @cachep: the cache returned by memcg_kmem_get_cache
 */
void memcg_kmem_put_cache(struct kmem_cache *cachep)
{
	if (!is_root_cache(cachep))
		percpu_ref_put(&cachep->memcg_params.refcnt);
}

/**
 * __memcg_kmem_charge_memcg: charge a kmem page
 * @page: page to charge
 * @gfp: reclaim mode
 * @order: allocation order
 * @memcg: memory cgroup to charge
 *
 * Returns 0 on success, an error code on failure.
 */
int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
			    struct mem_cgroup *memcg)
{
	unsigned int nr_pages = 1 << order;
	struct page_counter *counter;
	int ret;

	ret = try_charge(memcg, gfp, nr_pages);
	if (ret)
		return ret;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
	    !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {

		/*
		 * Enforce __GFP_NOFAIL allocation because callers are not
		 * prepared to see failures and likely do not have any failure
		 * handling code.
		 */
		if (gfp & __GFP_NOFAIL) {
			page_counter_charge(&memcg->kmem, nr_pages);
			return 0;
		}
		cancel_charge(memcg, nr_pages);
		return -ENOMEM;
	}
	return 0;
}

/**
 * __memcg_kmem_charge: 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(struct page *page, gfp_t gfp, int order)
{
	struct mem_cgroup *memcg;
	int ret = 0;

	if (memcg_kmem_bypass())
		return 0;

	memcg = get_mem_cgroup_from_current();
	if (!mem_cgroup_is_root(memcg)) {
		ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
		if (!ret) {
			page->mem_cgroup = memcg;
			__SetPageKmemcg(page);
		}
	}
	css_put(&memcg->css);
	return ret;
}

/**
 * __memcg_kmem_uncharge_memcg: uncharge a kmem page
 * @memcg: memcg to uncharge
 * @nr_pages: number of pages to uncharge
 */
void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg,
				 unsigned int nr_pages)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
		page_counter_uncharge(&memcg->kmem, nr_pages);

	page_counter_uncharge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_uncharge(&memcg->memsw, nr_pages);
}
/**
 * __memcg_kmem_uncharge: uncharge a kmem page
 * @page: page to uncharge
 * @order: allocation order
 */
void __memcg_kmem_uncharge(struct page *page, int order)
{
	struct mem_cgroup *memcg = page->mem_cgroup;
	unsigned int nr_pages = 1 << order;

	if (!memcg)
		return;

	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
	__memcg_kmem_uncharge_memcg(memcg, nr_pages);
	page->mem_cgroup = NULL;

	/* slab pages do not have PageKmemcg flag set */
	if (PageKmemcg(page))
		__ClearPageKmemcg(page);

	css_put_many(&memcg->css, nr_pages);
}
#endif /* CONFIG_MEMCG_KMEM */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE

/*
 * Because tail pages are not marked as "used", set it. We're under
 * pgdat->lru_lock and migration entries setup in all page mappings.
 */
void mem_cgroup_split_huge_fixup(struct page *head)
{
	int i;

	if (mem_cgroup_disabled())
		return;

	for (i = 1; i < HPAGE_PMD_NR; i++)
		head[i].mem_cgroup = head->mem_cgroup;

	__mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifdef CONFIG_MEMCG_SWAP
/**
 * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
 * @entry: swap entry to be moved
 * @from:  mem_cgroup which the entry is moved from
 * @to:  mem_cgroup which the entry is moved to
 *
 * It succeeds only when the swap_cgroup's record for this entry is the same
 * as the mem_cgroup's id of @from.
 *
 * Returns 0 on success, -EINVAL on failure.
 *
 * The caller must have charged to @to, IOW, called page_counter_charge() about
 * both res and memsw, and called css_get().
 */
static int mem_cgroup_move_swap_account(swp_entry_t entry,
				struct mem_cgroup *from, struct mem_cgroup *to)
{
	unsigned short old_id, new_id;

	old_id = mem_cgroup_id(from);
	new_id = mem_cgroup_id(to);

	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
		mod_memcg_state(from, MEMCG_SWAP, -1);
		mod_memcg_state(to, MEMCG_SWAP, 1);
		return 0;
	}
	return -EINVAL;
}
#else
static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
				struct mem_cgroup *from, struct mem_cgroup *to)
{
	return -EINVAL;
}
#endif

static DEFINE_MUTEX(memcg_max_mutex);

static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
				 unsigned long max, bool memsw)
{
	bool enlarge = false;
	bool drained = false;
	int ret;
	bool limits_invariant;
	struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;

	do {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		mutex_lock(&memcg_max_mutex);
		/*
		 * Make sure that the new limit (memsw or memory limit) doesn't
		 * break our basic invariant rule memory.max <= memsw.max.
		 */
		limits_invariant = memsw ? max >= memcg->memory.max :
					   max <= memcg->memsw.max;
		if (!limits_invariant) {
			mutex_unlock(&memcg_max_mutex);
			ret = -EINVAL;
			break;
		}
		if (max > counter->max)
			enlarge = true;
		ret = page_counter_set_max(counter, max);
		mutex_unlock(&memcg_max_mutex);

		if (!ret)
			break;

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

		if (!try_to_free_mem_cgroup_pages(memcg, 1,
					GFP_KERNEL, !memsw)) {
			ret = -EBUSY;
			break;
		}
	} while (true);

	if (!ret && enlarge)
		memcg_oom_recover(memcg);

	return ret;
}

unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
					    gfp_t gfp_mask,
					    unsigned long *total_scanned)
{
	unsigned long nr_reclaimed = 0;
	struct mem_cgroup_per_node *mz, *next_mz = NULL;
	unsigned long reclaimed;
	int loop = 0;
	struct mem_cgroup_tree_per_node *mctz;
	unsigned long excess;
	unsigned long nr_scanned;

	if (order > 0)
		return 0;

	mctz = soft_limit_tree_node(pgdat->node_id);

	/*
	 * Do not even bother to check the largest node if the root
	 * is empty. Do it lockless to prevent lock bouncing. Races
	 * are acceptable as soft limit is best effort anyway.
	 */
	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
		return 0;

	/*
	 * This loop can run a while, specially if mem_cgroup's continuously
	 * keep exceeding their soft limit and putting the system under
	 * pressure
	 */
	do {
		if (next_mz)
			mz = next_mz;
		else
			mz = mem_cgroup_largest_soft_limit_node(mctz);
		if (!mz)
			break;

		nr_scanned = 0;
		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
						    gfp_mask, &nr_scanned);
		nr_reclaimed += reclaimed;
		*total_scanned += nr_scanned;
		spin_lock_irq(&mctz->lock);
		__mem_cgroup_remove_exceeded(mz, mctz);

		/*
		 * If we failed to reclaim anything from this memory cgroup
		 * it is time to move on to the next cgroup
		 */
		next_mz = NULL;
		if (!reclaimed)
			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);

		excess = soft_limit_excess(mz->memcg);
		/*
		 * One school of thought says that we should not add
		 * back the node to the tree if reclaim returns 0.
		 * But our reclaim could return 0, simply because due
		 * to priority we are exposing a smaller subset of
		 * memory to reclaim from. Consider this as a longer
		 * term TODO.
		 */
		/* If excess == 0, no tree ops */
		__mem_cgroup_insert_exceeded(mz, mctz, excess);
		spin_unlock_irq(&mctz->lock);
		css_put(&mz->memcg->css);
		loop++;
		/*
		 * Could not reclaim anything and there are no more
		 * mem cgroups to try or we seem to be looping without
		 * reclaiming anything.
		 */
		if (!nr_reclaimed &&
			(next_mz == NULL ||
			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
			break;
	} while (!nr_reclaimed);
	if (next_mz)
		css_put(&next_mz->memcg->css);
	return nr_reclaimed;
}

/*
 * Test whether @memcg has children, dead or alive.  Note that this
 * function doesn't care whether @memcg has use_hierarchy enabled and
 * returns %true if there are child csses according to the cgroup
 * hierarchy.  Testing use_hierarchy is the caller's responsiblity.
 */
static inline bool memcg_has_children(struct mem_cgroup *memcg)
{
	bool ret;

	rcu_read_lock();
	ret = css_next_child(NULL, &memcg->css);
	rcu_read_unlock();
	return ret;
}

/*
 * Reclaims as many pages from the given memcg as possible.
 *
 * Caller is responsible for holding css reference for memcg.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
{
	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;

	/* we call try-to-free pages for make this cgroup empty */
	lru_add_drain_all();

	drain_all_stock(memcg);

	/* try to free all pages in this cgroup */
	while (nr_retries && page_counter_read(&memcg->memory)) {
		int progress;

		if (signal_pending(current))
			return -EINTR;

		progress = try_to_free_mem_cgroup_pages(memcg, 1,
							GFP_KERNEL, true);
		if (!progress) {
			nr_retries--;
			/* maybe some writeback is necessary */
			congestion_wait(BLK_RW_ASYNC, HZ/10);
		}

	}

	return 0;
}

static ssize_t mem_cgroup_force_empty_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));

	if (mem_cgroup_is_root(memcg))
		return -EINVAL;
	return mem_cgroup_force_empty(memcg) ?: nbytes;
}

static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
				     struct cftype *cft)
{
	return mem_cgroup_from_css(css)->use_hierarchy;
}

static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
				      struct cftype *cft, u64 val)
{
	int retval = 0;
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);

	if (memcg->use_hierarchy == val)
		return 0;

	/*
	 * If parent's use_hierarchy is set, we can't make any modifications
	 * in the child subtrees. If it is unset, then the change can
	 * occur, provided the current cgroup has no children.
	 *
	 * For the root cgroup, parent_mem is NULL, we allow value to be
	 * set if there are no children.
	 */
	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
				(val == 1 || val == 0)) {
		if (!memcg_has_children(memcg))
			memcg->use_hierarchy = val;
		else
			retval = -EBUSY;
	} else
		retval = -EINVAL;

	return retval;
}

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

	if (mem_cgroup_is_root(memcg)) {
		val = memcg_page_state(memcg, MEMCG_CACHE) +
			memcg_page_state(memcg, MEMCG_RSS);
		if (swap)
			val += memcg_page_state(memcg, MEMCG_SWAP);
	} else {
		if (!swap)
			val = page_counter_read(&memcg->memory);
		else
			val = page_counter_read(&memcg->memsw);
	}
	return val;
}

enum {
	RES_USAGE,
	RES_LIMIT,
	RES_MAX_USAGE,
	RES_FAILCNT,
	RES_SOFT_LIMIT,
};

static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct page_counter *counter;

	switch (MEMFILE_TYPE(cft->private)) {
	case _MEM:
		counter = &memcg->memory;
		break;
	case _MEMSWAP:
		counter = &memcg->memsw;
		break;
	case _KMEM:
		counter = &memcg->kmem;
		break;
	case _TCP:
		counter = &memcg->tcpmem;
		break;
	default:
		BUG();
	}

	switch (MEMFILE_ATTR(cft->private)) {
	case RES_USAGE:
		if (counter == &memcg->memory)
			return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
		if (counter == &memcg->memsw)
			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
		return (u64)page_counter_read(counter) * PAGE_SIZE;
	case RES_LIMIT:
		return (u64)counter->max * PAGE_SIZE;
	case RES_MAX_USAGE:
		return (u64)counter->watermark * PAGE_SIZE;
	case RES_FAILCNT:
		return counter->failcnt;
	case RES_SOFT_LIMIT:
		return (u64)memcg->soft_limit * PAGE_SIZE;
	default:
		BUG();
	}
}

static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
{
	unsigned long stat[MEMCG_NR_STAT];
	struct mem_cgroup *mi;
	int node, cpu, i;
	int min_idx, max_idx;

	if (slab_only) {
		min_idx = NR_SLAB_RECLAIMABLE;
		max_idx = NR_SLAB_UNRECLAIMABLE;
	} else {
		min_idx = 0;
		max_idx = MEMCG_NR_STAT;
	}

	for (i = min_idx; i < max_idx; i++)
		stat[i] = 0;

	for_each_online_cpu(cpu)
		for (i = min_idx; i < max_idx; i++)
			stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);

	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
		for (i = min_idx; i < max_idx; i++)
			atomic_long_add(stat[i], &mi->vmstats[i]);

	if (!slab_only)
		max_idx = NR_VM_NODE_STAT_ITEMS;

	for_each_node(node) {
		struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
		struct mem_cgroup_per_node *pi;

		for (i = min_idx; i < max_idx; i++)
			stat[i] = 0;

		for_each_online_cpu(cpu)
			for (i = min_idx; i < max_idx; i++)
				stat[i] += per_cpu(
					pn->lruvec_stat_cpu->count[i], cpu);

		for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
			for (i = min_idx; i < max_idx; i++)
				atomic_long_add(stat[i], &pi->lruvec_stat[i]);
	}
}

static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
{
	unsigned long events[NR_VM_EVENT_ITEMS];
	struct mem_cgroup *mi;
	int cpu, i;

	for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
		events[i] = 0;

	for_each_online_cpu(cpu)
		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
			events[i] += per_cpu(memcg->vmstats_percpu->events[i],
					     cpu);

	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
			atomic_long_add(events[i], &mi->vmevents[i]);
}

#ifdef CONFIG_MEMCG_KMEM
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
	int memcg_id;

	if (cgroup_memory_nokmem)
		return 0;

	BUG_ON(memcg->kmemcg_id >= 0);
	BUG_ON(memcg->kmem_state);

	memcg_id = memcg_alloc_cache_id();
	if (memcg_id < 0)
		return memcg_id;

	static_branch_inc(&memcg_kmem_enabled_key);
	/*
	 * A memory cgroup is considered kmem-online as soon as it gets
	 * kmemcg_id. Setting the id after enabling static branching will
	 * guarantee no one starts accounting before all call sites are
	 * patched.
	 */
	memcg->kmemcg_id = memcg_id;
	memcg->kmem_state = KMEM_ONLINE;
	INIT_LIST_HEAD(&memcg->kmem_caches);

	return 0;
}

static void memcg_offline_kmem(struct mem_cgroup *memcg)
{
	struct cgroup_subsys_state *css;
	struct mem_cgroup *parent, *child;
	int kmemcg_id;

	if (memcg->kmem_state != KMEM_ONLINE)
		return;
	/*
	 * Clear the online state before clearing memcg_caches array
	 * entries. The slab_mutex in memcg_deactivate_kmem_caches()
	 * guarantees that no cache will be created for this cgroup
	 * after we are done (see memcg_create_kmem_cache()).
	 */
	memcg->kmem_state = KMEM_ALLOCATED;

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

	/*
	 * Deactivate and reparent kmem_caches. Then flush percpu
	 * slab statistics to have precise values at the parent and
	 * all ancestor levels. It's required to keep slab stats
	 * accurate after the reparenting of kmem_caches.
	 */
	memcg_deactivate_kmem_caches(memcg, parent);
	memcg_flush_percpu_vmstats(memcg, true);

	kmemcg_id = memcg->kmemcg_id;
	BUG_ON(kmemcg_id < 0);

	/*
	 * Change kmemcg_id of this cgroup and all its descendants to the
	 * parent's id, and then move all entries from this cgroup's list_lrus
	 * to ones of the parent. After we have finished, all list_lrus
	 * corresponding to this cgroup are guaranteed to remain empty. The
	 * ordering is imposed by list_lru_node->lock taken by
	 * memcg_drain_all_list_lrus().
	 */
	rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
	css_for_each_descendant_pre(css, &memcg->css) {
		child = mem_cgroup_from_css(css);
		BUG_ON(child->kmemcg_id != kmemcg_id);
		child->kmemcg_id = parent->kmemcg_id;
		if (!memcg->use_hierarchy)
			break;
	}
	rcu_read_unlock();

	memcg_drain_all_list_lrus(kmemcg_id, parent);

	memcg_free_cache_id(kmemcg_id);
}

static void memcg_free_kmem(struct mem_cgroup *memcg)
{
	/* css_alloc() failed, offlining didn't happen */
	if (unlikely(memcg->kmem_state == KMEM_ONLINE))
		memcg_offline_kmem(memcg);

	if (memcg->kmem_state == KMEM_ALLOCATED) {
		WARN_ON(!list_empty(&memcg->kmem_caches));
		static_branch_dec(&memcg_kmem_enabled_key);
	}
}
#else
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
	return 0;
}
static void memcg_offline_kmem(struct mem_cgroup *memcg)
{
}
static void memcg_free_kmem(struct mem_cgroup *memcg)
{
}
#endif /* CONFIG_MEMCG_KMEM */

static int memcg_update_kmem_max(struct mem_cgroup *memcg,
				 unsigned long max)
{
	int ret;

	mutex_lock(&memcg_max_mutex);
	ret = page_counter_set_max(&memcg->kmem, max);
	mutex_unlock(&memcg_max_mutex);
	return ret;
}

static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max)
{
	int ret;

	mutex_lock(&memcg_max_mutex);

	ret = page_counter_set_max(&memcg->tcpmem, max);
	if (ret)
		goto out;

	if (!memcg->tcpmem_active) {
		/*
		 * The active flag needs to be written after the static_key
		 * update. This is what guarantees that the socket activation
		 * function is the last one to run. See mem_cgroup_sk_alloc()
		 * for details, and note that we don't mark any socket as
		 * belonging to this memcg until that flag is up.
		 *
		 * We need to do this, because static_keys will span multiple
		 * sites, but we can't control their order. If we mark a socket
		 * as accounted, but the accounting functions are not patched in
		 * yet, we'll lose accounting.
		 *
		 * We never race with the readers in mem_cgroup_sk_alloc(),
		 * because when this value change, the code to process it is not
		 * patched in yet.
		 */
		static_branch_inc(&memcg_sockets_enabled_key);
		memcg->tcpmem_active = true;
	}
out:
	mutex_unlock(&memcg_max_mutex);
	return ret;
}

/*
 * The user of this function is...
 * RES_LIMIT.
 */
static ssize_t mem_cgroup_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 nr_pages;
	int ret;

	buf = strstrip(buf);
	ret = page_counter_memparse(buf, "-1", &nr_pages);
	if (ret)
		return ret;

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_LIMIT:
		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
			ret = -EINVAL;
			break;
		}
		switch (MEMFILE_TYPE(of_cft(of)->private)) {
		case _MEM:
			ret = mem_cgroup_resize_max(memcg, nr_pages, false);
			break;
		case _MEMSWAP:
			ret = mem_cgroup_resize_max(memcg, nr_pages, true);
			break;
		case _KMEM:
			pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
				     "Please report your usecase to linux-mm@kvack.org if you "
				     "depend on this functionality.\n");
			ret = memcg_update_kmem_max(memcg, nr_pages);
			break;
		case _TCP:
			ret = memcg_update_tcp_max(memcg, nr_pages);
			break;
		}
		break;
	case RES_SOFT_LIMIT:
		memcg->soft_limit = nr_pages;
		ret = 0;
		break;
	}
	return ret ?: nbytes;
}

static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
				size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	struct page_counter *counter;

	switch (MEMFILE_TYPE(of_cft(of)->private)) {
	case _MEM:
		counter = &memcg->memory;
		break;
	case _MEMSWAP:
		counter = &memcg->memsw;
		break;
	case _KMEM:
		counter = &memcg->kmem;
		break;
	case _TCP:
		counter = &memcg->tcpmem;
		break;
	default:
		BUG();
	}

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_MAX_USAGE:
		page_counter_reset_watermark(counter);
		break;
	case RES_FAILCNT:
		counter->failcnt = 0;
		break;
	default:
		BUG();
	}

	return nbytes;
}

static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
					struct cftype *cft)
{
	return mem_cgroup_from_css(css)->move_charge_at_immigrate;
}

#ifdef CONFIG_MMU
static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
					struct cftype *cft, u64 val)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	if (val & ~MOVE_MASK)
		return -EINVAL;

	/*
	 * No kind of locking is needed in here, because ->can_attach() will
	 * check this value once in the beginning of the process, and then carry
	 * on with stale data. This means that changes to this value will only
	 * affect task migrations starting after the change.
	 */
	memcg->move_charge_at_immigrate = val;
	return 0;
}
#else
static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
					struct cftype *cft, u64 val)
{
	return -ENOSYS;
}
#endif

#ifdef CONFIG_NUMA

#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
#define LRU_ALL	     ((1 << NR_LRU_LISTS) - 1)

static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
					   int nid, unsigned int lru_mask)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
	unsigned long nr = 0;
	enum lru_list lru;

	VM_BUG_ON((unsigned)nid >= nr_node_ids);

	for_each_lru(lru) {
		if (!(BIT(lru) & lru_mask))
			continue;
		nr += lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
	}
	return nr;
}

static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
					     unsigned int lru_mask)
{
	unsigned long nr = 0;
	enum lru_list lru;

	for_each_lru(lru) {
		if (!(BIT(lru) & lru_mask))
			continue;
		nr += memcg_page_state_local(memcg, NR_LRU_BASE + lru);
	}
	return nr;
}

static int memcg_numa_stat_show(struct seq_file *m, void *v)
{
	struct numa_stat {
		const char *name;
		unsigned int lru_mask;
	};

	static const struct numa_stat stats[] = {
		{ "total", LRU_ALL },
		{ "file", LRU_ALL_FILE },
		{ "anon", LRU_ALL_ANON },
		{ "unevictable", BIT(LRU_UNEVICTABLE) },
	};
	const struct numa_stat *stat;
	int nid;
	unsigned long nr;
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
		nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask);
		seq_printf(m, "%s=%lu", stat->name, nr);
		for_each_node_state(nid, N_MEMORY) {
			nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
							  stat->lru_mask);
			seq_printf(m, " N%d=%lu", nid, nr);
		}
		seq_putc(m, '\n');
	}

	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
		struct mem_cgroup *iter;

		nr = 0;
		for_each_mem_cgroup_tree(iter, memcg)
			nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask);
		seq_printf(m, "hierarchical_%s=%lu", stat->name, nr);
		for_each_node_state(nid, N_MEMORY) {
			nr = 0;
			for_each_mem_cgroup_tree(iter, memcg)
				nr += mem_cgroup_node_nr_lru_pages(
					iter, nid, stat->lru_mask);
			seq_printf(m, " N%d=%lu", nid, nr);
		}
		seq_putc(m, '\n');
	}

	return 0;
}
#endif /* CONFIG_NUMA */

static const unsigned int memcg1_stats[] = {
	MEMCG_CACHE,
	MEMCG_RSS,
	MEMCG_RSS_HUGE,
	NR_SHMEM,
	NR_FILE_MAPPED,
	NR_FILE_DIRTY,
	NR_WRITEBACK,
	MEMCG_SWAP,
};

static const char *const memcg1_stat_names[] = {
	"cache",
	"rss",
	"rss_huge",
	"shmem",
	"mapped_file",
	"dirty",
	"writeback",
	"swap",
};

/* Universal VM events cgroup1 shows, original sort order */
static const unsigned int memcg1_events[] = {
	PGPGIN,
	PGPGOUT,
	PGFAULT,
	PGMAJFAULT,
};

static const char *const memcg1_event_names[] = {
	"pgpgin",
	"pgpgout",
	"pgfault",
	"pgmajfault",
};

static int memcg_stat_show(struct seq_file *m, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
	unsigned long memory, memsw;
	struct mem_cgroup *mi;
	unsigned int i;

	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);

	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
			continue;
		seq_printf(m, "%s %lu\n", memcg1_stat_names[i],
			   memcg_page_state_local(memcg, memcg1_stats[i]) *
			   PAGE_SIZE);
	}

	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
		seq_printf(m, "%s %lu\n", memcg1_event_names[i],
			   memcg_events_local(memcg, memcg1_events[i]));

	for (i = 0; i < NR_LRU_LISTS; i++)
		seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i],
			   memcg_page_state_local(memcg, NR_LRU_BASE + i) *
			   PAGE_SIZE);

	/* Hierarchical information */
	memory = memsw = PAGE_COUNTER_MAX;
	for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
		memory = min(memory, mi->memory.max);
		memsw = min(memsw, mi->memsw.max);
	}
	seq_printf(m, "hierarchical_memory_limit %llu\n",
		   (u64)memory * PAGE_SIZE);
	if (do_memsw_account())
		seq_printf(m, "hierarchical_memsw_limit %llu\n",
			   (u64)memsw * PAGE_SIZE);

	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
			continue;
		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
			   (u64)memcg_page_state(memcg, memcg1_stats[i]) *
			   PAGE_SIZE);
	}

	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
		seq_printf(m, "total_%s %llu\n", memcg1_event_names[i],
			   (u64)memcg_events(memcg, memcg1_events[i]));

	for (i = 0; i < NR_LRU_LISTS; i++)
		seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i],
			   (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
			   PAGE_SIZE);

#ifdef CONFIG_DEBUG_VM
	{
		pg_data_t *pgdat;
		struct mem_cgroup_per_node *mz;
		struct zone_reclaim_stat *rstat;
		unsigned long recent_rotated[2] = {0, 0};
		unsigned long recent_scanned[2] = {0, 0};

		for_each_online_pgdat(pgdat) {
			mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
			rstat = &mz->lruvec.reclaim_stat;

			recent_rotated[0] += rstat->recent_rotated[0];
			recent_rotated[1] += rstat->recent_rotated[1];
			recent_scanned[0] += rstat->recent_scanned[0];
			recent_scanned[1] += rstat->recent_scanned[1];
		}
		seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]);
		seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]);
		seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]);
		seq_printf(m, "recent_scanned_file %lu\n", recent_scanned[1]);
	}
#endif

	return 0;
}

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

	return mem_cgroup_swappiness(memcg);
}

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

	if (val > 100)
		return -EINVAL;

	if (css->parent)
		memcg->swappiness = val;
	else
		vm_swappiness = val;

	return 0;
}

static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
{
	struct mem_cgroup_threshold_ary *t;
	unsigned long usage;
	int i;

	rcu_read_lock();
	if (!swap)
		t = rcu_dereference(memcg->thresholds.primary);
	else
		t = rcu_dereference(memcg->memsw_thresholds.primary);

	if (!t)
		goto unlock;

	usage = mem_cgroup_usage(memcg, swap);

	/*
	 * current_threshold points to threshold just below or equal to usage.
	 * If it's not true, a threshold was crossed after last
	 * call of __mem_cgroup_threshold().
	 */
	i = t->current_threshold;

	/*
	 * Iterate backward over array of thresholds starting from
	 * current_threshold and check if a threshold is crossed.
	 * If none of thresholds below usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
		eventfd_signal(t->entries[i].eventfd, 1);

	/* i = current_threshold + 1 */
	i++;

	/*
	 * Iterate forward over array of thresholds starting from
	 * current_threshold+1 and check if a threshold is crossed.
	 * If none of thresholds above usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
		eventfd_signal(t->entries[i].eventfd, 1);

	/* Update current_threshold */
	t->current_threshold = i - 1;
unlock:
	rcu_read_unlock();
}

static void mem_cgroup_threshold(struct mem_cgroup *memcg)
{
	while (memcg) {
		__mem_cgroup_threshold(memcg, false);
		if (do_memsw_account())
			__mem_cgroup_threshold(memcg, true);

		memcg = parent_mem_cgroup(memcg);
	}
}

static int compare_thresholds(const void *a, const void *b)
{
	const struct mem_cgroup_threshold *_a = a;
	const struct mem_cgroup_threshold *_b = b;

	if (_a->threshold > _b->threshold)
		return 1;

	if (_a->threshold < _b->threshold)
		return -1;

	return 0;
}

static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
{
	struct mem_cgroup_eventfd_list *ev;

	spin_lock(&memcg_oom_lock);

	list_for_each_entry(ev, &memcg->oom_notify, list)
		eventfd_signal(ev->eventfd, 1);

	spin_unlock(&memcg_oom_lock);
	return 0;
}

static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, memcg)
		mem_cgroup_oom_notify_cb(iter);
}

static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args, enum res_type type)
{
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	unsigned long threshold;
	unsigned long usage;
	int i, size, ret;

	ret = page_counter_memparse(args, "-1", &threshold);
	if (ret)
		return ret;

	mutex_lock(&memcg->thresholds_lock);

	if (type == _MEM) {
		thresholds = &memcg->thresholds;
		usage = mem_cgroup_usage(memcg, false);
	} else if (type == _MEMSWAP) {
		thresholds = &memcg->memsw_thresholds;
		usage = mem_cgroup_usage(memcg, true);
	} else
		BUG();

	/* Check if a threshold crossed before adding a new one */
	if (thresholds->primary)
		__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	size = thresholds->primary ? thresholds->primary->size + 1 : 1;

	/* Allocate memory for new array of thresholds */
	new = kmalloc(struct_size(new, entries, size), GFP_KERNEL);
	if (!new) {
		ret = -ENOMEM;
		goto unlock;
	}
	new->size = size;

	/* Copy thresholds (if any) to new array */
	if (thresholds->primary) {
		memcpy(new->entries, thresholds->primary->entries, (size - 1) *
				sizeof(struct mem_cgroup_threshold));
	}

	/* Add new threshold */
	new->entries[size - 1].eventfd = eventfd;
	new->entries[size - 1].threshold = threshold;

	/* Sort thresholds. Registering of new threshold isn't time-critical */
	sort(new->entries, size, sizeof(struct mem_cgroup_threshold),
			compare_thresholds, NULL);

	/* Find current threshold */
	new->current_threshold = -1;
	for (i = 0; i < size; i++) {
		if (new->entries[i].threshold <= usage) {
			/*
			 * new->current_threshold will not be used until
			 * rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		} else
			break;
	}

	/* Free old spare buffer and save old primary buffer as spare */
	kfree(thresholds->spare);
	thresholds->spare = thresholds->primary;

	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

unlock:
	mutex_unlock(&memcg->thresholds_lock);

	return ret;
}

static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM);
}

static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP);
}

static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, enum res_type type)
{
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	unsigned long usage;
	int i, j, size;

	mutex_lock(&memcg->thresholds_lock);

	if (type == _MEM) {
		thresholds = &memcg->thresholds;
		usage = mem_cgroup_usage(memcg, false);
	} else if (type == _MEMSWAP) {
		thresholds = &memcg->memsw_thresholds;
		usage = mem_cgroup_usage(memcg, true);
	} else
		BUG();

	if (!thresholds->primary)
		goto unlock;

	/* Check if a threshold crossed before removing */
	__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	/* Calculate new number of threshold */
	size = 0;
	for (i = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd != eventfd)
			size++;
	}

	new = thresholds->spare;

	/* Set thresholds array to NULL if we don't have thresholds */
	if (!size) {
		kfree(new);
		new = NULL;
		goto swap_buffers;
	}

	new->size = size;

	/* Copy thresholds and find current threshold */
	new->current_threshold = -1;
	for (i = 0, j = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd == eventfd)
			continue;

		new->entries[j] = thresholds->primary->entries[i];
		if (new->entries[j].threshold <= usage) {
			/*
			 * new->current_threshold will not be used
			 * until rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		}
		j++;
	}

swap_buffers:
	/* Swap primary and spare array */
	thresholds->spare = thresholds->primary;

	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

	/* If all events are unregistered, free the spare array */
	if (!new) {
		kfree(thresholds->spare);
		thresholds->spare = NULL;
	}
unlock:
	mutex_unlock(&memcg->thresholds_lock);
}

static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM);
}

static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP);
}

static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	struct mem_cgroup_eventfd_list *event;

	event = kmalloc(sizeof(*event),	GFP_KERNEL);
	if (!event)
		return -ENOMEM;

	spin_lock(&memcg_oom_lock);

	event->eventfd = eventfd;
	list_add(&event->list, &memcg->oom_notify);

	/* already in OOM ? */
	if (memcg->under_oom)
		eventfd_signal(eventfd, 1);
	spin_unlock(&memcg_oom_lock);

	return 0;
}

static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	struct mem_cgroup_eventfd_list *ev, *tmp;

	spin_lock(&memcg_oom_lock);

	list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) {
		if (ev->eventfd == eventfd) {
			list_del(&ev->list);
			kfree(ev);
		}
	}

	spin_unlock(&memcg_oom_lock);
}

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

	seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
	seq_printf(sf, "oom_kill %lu\n",
		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
	return 0;
}

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

	/* cannot set to root cgroup and only 0 and 1 are allowed */
	if (!css->parent || !((val == 0) || (val == 1)))
		return -EINVAL;

	memcg->oom_kill_disable = val;
	if (!val)
		memcg_oom_recover(memcg);

	return 0;
}

#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;
}

/*
 * idx can be of type enum memcg_stat_item or node_stat_item.
 * Keep in sync with memcg_exact_page().
 */
static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
{
	long x = atomic_long_read(&memcg->vmstats[idx]);
	int cpu;

	for_each_online_cpu(cpu)
		x += per_cpu_ptr(memcg->vmstats_percpu, cpu)->stat[idx];
	if (x < 0)
		x = 0;
	return x;
}

/**
 * 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;

	*pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);

	/* this should eventually include NR_UNSTABLE_NFS */
	*pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
	*pfilepages = memcg_exact_page_state(memcg, NR_INACTIVE_FILE) +
			memcg_exact_page_state(memcg, NR_ACTIVE_FILE);
	*pheadroom = PAGE_COUNTER_MAX;

	while ((parent = parent_mem_cgroup(memcg))) {
		unsigned long ceiling = min(memcg->memory.max, memcg->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
 * trackes 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 repatedly and
 * severely throttled after making some progress after each
 * dirty_expire_interval while the underyling 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 page *page,
					     struct bdi_writeback *wb)
{
	struct mem_cgroup *memcg = page->mem_cgroup;
	struct memcg_cgwb_frn *frn;
	u64 now = get_jiffies_64();
	u64 oldest_at = now;
	int oldest = -1;
	int i;

	trace_track_foreign_dirty(page, 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, 0,
					       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 */

/*
 * DO NOT USE IN NEW FILES.
 *
 * "cgroup.event_control" implementation.
 *
 * This is way over-engineered.  It tries to support fully configurable
 * events for each user.  Such level of flexibility is completely
 * unnecessary especially in the light of the planned unified hierarchy.
 *
 * Please deprecate this and replace with something simpler if at all
 * possible.
 */

/*
 * Unregister event and free resources.
 *
 * Gets called from workqueue.
 */
static void memcg_event_remove(struct work_struct *work)
{
	struct mem_cgroup_event *event =
		container_of(work, struct mem_cgroup_event, remove);
	struct mem_cgroup *memcg = event->memcg;

	remove_wait_queue(event->wqh, &event->wait);

	event->unregister_event(memcg, event->eventfd);

	/* Notify userspace the event is going away. */
	eventfd_signal(event->eventfd, 1);

	eventfd_ctx_put(event->eventfd);
	kfree(event);
	css_put(&memcg->css);
}

/*
 * Gets called on EPOLLHUP on eventfd when user closes it.
 *
 * Called with wqh->lock held and interrupts disabled.
 */
static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
			    int sync, void *key)
{
	struct mem_cgroup_event *event =
		container_of(wait, struct mem_cgroup_event, wait);
	struct mem_cgroup *memcg = event->memcg;
	__poll_t flags = key_to_poll(key);

	if (flags & EPOLLHUP) {
		/*
		 * If the event has been detached at cgroup removal, we
		 * can simply return knowing the other side will cleanup
		 * for us.
		 *
		 * We can't race against event freeing since the other
		 * side will require wqh->lock via remove_wait_queue(),
		 * which we hold.
		 */
		spin_lock(&memcg->event_list_lock);
		if (!list_empty(&event->list)) {
			list_del_init(&event->list);
			/*
			 * We are in atomic context, but cgroup_event_remove()
			 * may sleep, so we have to call it in workqueue.
			 */
			schedule_work(&event->remove);
		}
		spin_unlock(&memcg->event_list_lock);
	}

	return 0;
}

static void memcg_event_ptable_queue_proc(struct file *file,
		wait_queue_head_t *wqh, poll_table *pt)
{
	struct mem_cgroup_event *event =
		container_of(pt, struct mem_cgroup_event, pt);

	event->wqh = wqh;
	add_wait_queue(wqh, &event->wait);
}

/*
 * DO NOT USE IN NEW FILES.
 *
 * Parse input and register new cgroup event handler.
 *
 * Input must be in format '<event_fd> <control_fd> <args>'.
 * Interpretation of args is defined by control file implementation.
 */
static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
					 char *buf, size_t nbytes, loff_t off)
{
	struct cgroup_subsys_state *css = of_css(of);
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup_event *event;
	struct cgroup_subsys_state *cfile_css;
	unsigned int efd, cfd;
	struct fd efile;
	struct fd cfile;
	const char *name;
	char *endp;
	int ret;

	buf = strstrip(buf);

	efd = simple_strtoul(buf, &endp, 10);
	if (*endp != ' ')
		return -EINVAL;
	buf = endp + 1;

	cfd = simple_strtoul(buf, &endp, 10);
	if ((*endp != ' ') && (*endp != '\0'))
		return -EINVAL;
	buf = endp + 1;

	event = kzalloc(sizeof(*event), GFP_KERNEL);
	if (!event)
		return -ENOMEM;

	event->memcg = memcg;
	INIT_LIST_HEAD(&event->list);
	init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc);
	init_waitqueue_func_entry(&event->wait, memcg_event_wake);
	INIT_WORK(&event->remove, memcg_event_remove);

	efile = fdget(efd);
	if (!efile.file) {
		ret = -EBADF;
		goto out_kfree;
	}

	event->eventfd = eventfd_ctx_fileget(efile.file);
	if (IS_ERR(event->eventfd)) {
		ret = PTR_ERR(event->eventfd);
		goto out_put_efile;
	}

	cfile = fdget(cfd);
	if (!cfile.file) {
		ret = -EBADF;
		goto out_put_eventfd;
	}

	/* the process need read permission on control file */
	/* AV: shouldn't we check that it's been opened for read instead? */
	ret = inode_permission(file_inode(cfile.file), MAY_READ);
	if (ret < 0)
		goto out_put_cfile;

	/*
	 * Determine the event callbacks and set them in @event.  This used
	 * to be done via struct cftype but cgroup core no longer knows
	 * about these events.  The following is crude but the whole thing
	 * is for compatibility anyway.
	 *
	 * DO NOT ADD NEW FILES.
	 */
	name = cfile.file->f_path.dentry->d_name.name;

	if (!strcmp(name, "memory.usage_in_bytes")) {
		event->register_event = mem_cgroup_usage_register_event;
		event->unregister_event = mem_cgroup_usage_unregister_event;
	} else if (!strcmp(name, "memory.oom_control")) {
		event->register_event = mem_cgroup_oom_register_event;
		event->unregister_event = mem_cgroup_oom_unregister_event;
	} else if (!strcmp(name, "memory.pressure_level")) {
		event->register_event = vmpressure_register_event;
		event->unregister_event = vmpressure_unregister_event;
	} else if (!strcmp(name, "memory.memsw.usage_in_bytes")) {
		event->register_event = memsw_cgroup_usage_register_event;
		event->unregister_event = memsw_cgroup_usage_unregister_event;
	} else {
		ret = -EINVAL;
		goto out_put_cfile;
	}

	/*
	 * Verify @cfile should belong to @css.  Also, remaining events are
	 * automatically removed on cgroup destruction but the removal is
	 * asynchronous, so take an extra ref on @css.
	 */
	cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent,
					       &memory_cgrp_subsys);
	ret = -EINVAL;
	if (IS_ERR(cfile_css))
		goto out_put_cfile;
	if (cfile_css != css) {
		css_put(cfile_css);
		goto out_put_cfile;
	}

	ret = event->register_event(memcg, event->eventfd, buf);
	if (ret)
		goto out_put_css;

	vfs_poll(efile.file, &event->pt);

	spin_lock(&memcg->event_list_lock);
	list_add(&event->list, &memcg->event_list);
	spin_unlock(&memcg->event_list_lock);

	fdput(cfile);
	fdput(efile);

	return nbytes;

out_put_css:
	css_put(css);
out_put_cfile:
	fdput(cfile);
out_put_eventfd:
	eventfd_ctx_put(event->eventfd);
out_put_efile:
	fdput(efile);
out_kfree:
	kfree(event);

	return ret;
}

static struct cftype mem_cgroup_legacy_files[] = {
	{
		.name = "usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "soft_limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "failcnt",
		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "stat",
		.seq_show = memcg_stat_show,
	},
	{
		.name = "force_empty",
		.write = mem_cgroup_force_empty_write,
	},
	{
		.name = "use_hierarchy",
		.write_u64 = mem_cgroup_hierarchy_write,
		.read_u64 = mem_cgroup_hierarchy_read,
	},
	{
		.name = "cgroup.event_control",		/* XXX: for compat */
		.write = memcg_write_event_control,
		.flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE,
	},
	{
		.name = "swappiness",
		.read_u64 = mem_cgroup_swappiness_read,
		.write_u64 = mem_cgroup_swappiness_write,
	},
	{
		.name = "move_charge_at_immigrate",
		.read_u64 = mem_cgroup_move_charge_read,
		.write_u64 = mem_cgroup_move_charge_write,
	},
	{
		.name = "oom_control",
		.seq_show = mem_cgroup_oom_control_read,
		.write_u64 = mem_cgroup_oom_control_write,
		.private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
	},
	{
		.name = "pressure_level",
	},
#ifdef CONFIG_NUMA
	{
		.name = "numa_stat",
		.seq_show = memcg_numa_stat_show,
	},
#endif
	{
		.name = "kmem.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.failcnt",
		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
	{
		.name = "kmem.slabinfo",
		.seq_start = memcg_slab_start,
		.seq_next = memcg_slab_next,
		.seq_stop = memcg_slab_stop,
		.seq_show = memcg_slab_show,
	},
#endif
	{
		.name = "kmem.tcp.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.failcnt",
		.private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{ },	/* terminate */
};

/*
 * 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 oflline 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.
 */

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;
	}
}

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

static 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);
}

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

	pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat);
	if (!pn->lruvec_stat_local) {
		kfree(pn);
		return 1;
	}

	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
	if (!pn->lruvec_stat_cpu) {
		free_percpu(pn->lruvec_stat_local);
		kfree(pn);
		return 1;
	}

	lruvec_init(&pn->lruvec);
	pn->usage_in_excess = 0;
	pn->on_tree = false;
	pn->memcg = memcg;

	memcg->nodeinfo[node] = pn;
	return 0;
}

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_stat_cpu);
	free_percpu(pn->lruvec_stat_local);
	kfree(pn);
}

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

	/*
	 * Flush percpu vmstats and vmevents to guarantee the value correctness
	 * on parent's and all ancestor levels.
	 */
	memcg_flush_percpu_vmstats(memcg, false);
	memcg_flush_percpu_vmevents(memcg);
	for_each_node(node)
		free_mem_cgroup_per_node_info(memcg, node);
	free_percpu(memcg->vmstats_percpu);
	free_percpu(memcg->vmstats_local);
	kfree(memcg);
}

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

static struct mem_cgroup *mem_cgroup_alloc(void)
{
	struct mem_cgroup *memcg;
	unsigned int size;
	int node;
	int __maybe_unused i;

	size = sizeof(struct mem_cgroup);
	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);

	memcg = kzalloc(size, GFP_KERNEL);
	if (!memcg)
		return NULL;

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

	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
	if (!memcg->vmstats_local)
		goto fail;

	memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
	if (!memcg->vmstats_percpu)
		goto fail;

	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);
	memcg->last_scanned_node = MAX_NUMNODES;
	INIT_LIST_HEAD(&memcg->oom_notify);
	mutex_init(&memcg->thresholds_lock);
	spin_lock_init(&memcg->move_lock);
	vmpressure_init(&memcg->vmpressure);
	INIT_LIST_HEAD(&memcg->event_list);
	spin_lock_init(&memcg->event_list_lock);
	memcg->socket_pressure = jiffies;
#ifdef CONFIG_MEMCG_KMEM
	memcg->kmemcg_id = -1;
#endif
#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
	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
	return memcg;
fail:
	mem_cgroup_id_remove(memcg);
	__mem_cgroup_free(memcg);
	return NULL;
}

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;
	long error = -ENOMEM;

	memcg = mem_cgroup_alloc();
	if (!memcg)
		return ERR_PTR(error);

	memcg->high = PAGE_COUNTER_MAX;
	memcg->soft_limit = PAGE_COUNTER_MAX;
	if (parent) {
		memcg->swappiness = mem_cgroup_swappiness(parent);
		memcg->oom_kill_disable = parent->oom_kill_disable;
	}
	if (parent && parent->use_hierarchy) {
		memcg->use_hierarchy = true;
		page_counter_init(&memcg->memory, &parent->memory);
		page_counter_init(&memcg->swap, &parent->swap);
		page_counter_init(&memcg->memsw, &parent->memsw);
		page_counter_init(&memcg->kmem, &parent->kmem);
		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
	} else {
		page_counter_init(&memcg->memory, NULL);
		page_counter_init(&memcg->swap, NULL);
		page_counter_init(&memcg->memsw, NULL);
		page_counter_init(&memcg->kmem, NULL);
		page_counter_init(&memcg->tcpmem, NULL);
		/*
		 * Deeper hierachy with use_hierarchy == false doesn't make
		 * much sense so let cgroup subsystem know about this
		 * unfortunate state in our controller.
		 */
		if (parent != root_mem_cgroup)
			memory_cgrp_subsys.broken_hierarchy = true;
	}

	/* The following stuff does not apply to the root */
	if (!parent) {
#ifdef CONFIG_MEMCG_KMEM
		INIT_LIST_HEAD(&memcg->kmem_caches);
#endif
		root_mem_cgroup = memcg;
		return &memcg->css;
	}

	error = memcg_online_kmem(memcg);
	if (error)
		goto fail;

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

	return &memcg->css;
fail:
	mem_cgroup_id_remove(memcg);
	mem_cgroup_free(memcg);
	return ERR_PTR(-ENOMEM);
}

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

	/*
	 * A memcg must be visible for memcg_expand_shrinker_maps()
	 * by the time the maps are allocated. So, we allocate maps
	 * here, when for_each_mem_cgroup() can't skip it.
	 */
	if (memcg_alloc_shrinker_maps(memcg)) {
		mem_cgroup_id_remove(memcg);
		return -ENOMEM;
	}

	/* Online state pins memcg ID, memcg ID pins CSS */
	refcount_set(&memcg->id.ref, 1);
	css_get(css);
	return 0;
}

static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup_event *event, *tmp;

	/*
	 * Unregister events and notify userspace.
	 * Notify userspace about cgroup removing only after rmdir of cgroup
	 * directory to avoid race between userspace and kernelspace.
	 */
	spin_lock(&memcg->event_list_lock);
	list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
		list_del_init(&event->list);
		schedule_work(&event->remove);
	}
	spin_unlock(&memcg->event_list_lock);

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

	memcg_offline_kmem(memcg);
	wb_memcg_offline(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);
}

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) && memcg->tcpmem_active)
		static_branch_dec(&memcg_sockets_enabled_key);

	vmpressure_cleanup(&memcg->vmpressure);
	cancel_work_sync(&memcg->high_work);
	mem_cgroup_remove_from_trees(memcg);
	memcg_free_shrinker_maps(memcg);
	memcg_free_kmem(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);
	page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX);
	page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
	page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
	page_counter_set_min(&memcg->memory, 0);
	page_counter_set_low(&memcg->memory, 0);
	memcg->high = PAGE_COUNTER_MAX;
	memcg->soft_limit = PAGE_COUNTER_MAX;
	memcg_wb_domain_size_changed(memcg);
}

#ifdef CONFIG_MMU
/* Handlers for move charge at task migration. */
static int mem_cgroup_do_precharge(unsigned long count)
{
	int ret;

	/* Try a single bulk charge without reclaim first, kswapd may wake */
	ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count);
	if (!ret) {
		mc.precharge += count;
		return ret;
	}

	/* Try charges one by one with reclaim, but do not retry */
	while (count--) {
		ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
		if (ret)
			return ret;
		mc.precharge++;
		cond_resched();
	}
	return 0;
}

union mc_target {
	struct page	*page;
	swp_entry_t	ent;
};

enum mc_target_type {
	MC_TARGET_NONE = 0,
	MC_TARGET_PAGE,
	MC_TARGET_SWAP,
	MC_TARGET_DEVICE,
};

static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
						unsigned long addr, pte_t ptent)
{
	struct page *page = vm_normal_page(vma, addr, ptent);

	if (!page || !page_mapped(page))
		return NULL;
	if (PageAnon(page)) {
		if (!(mc.flags & MOVE_ANON))
			return NULL;
	} else {
		if (!(mc.flags & MOVE_FILE))
			return NULL;
	}
	if (!get_page_unless_zero(page))
		return NULL;

	return page;
}

#if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE)
static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
			pte_t ptent, swp_entry_t *entry)
{
	struct page *page = NULL;
	swp_entry_t ent = pte_to_swp_entry(ptent);

	if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent))
		return NULL;

	/*
	 * Handle MEMORY_DEVICE_PRIVATE which are ZONE_DEVICE page belonging to
	 * a device and because they are not accessible by CPU they are store
	 * as special swap entry in the CPU page table.
	 */
	if (is_device_private_entry(ent)) {
		page = device_private_entry_to_page(ent);
		/*
		 * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have
		 * a refcount of 1 when free (unlike normal page)
		 */
		if (!page_ref_add_unless(page, 1, 1))
			return NULL;
		return page;
	}

	/*
	 * Because lookup_swap_cache() updates some statistics counter,
	 * we call find_get_page() with swapper_space directly.
	 */
	page = find_get_page(swap_address_space(ent), swp_offset(ent));
	if (do_memsw_account())
		entry->val = ent.val;

	return page;
}
#else
static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
			pte_t ptent, swp_entry_t *entry)
{
	return NULL;
}
#endif

static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
			unsigned long addr, pte_t ptent, swp_entry_t *entry)
{
	struct page *page = NULL;
	struct address_space *mapping;
	pgoff_t pgoff;

	if (!vma->vm_file) /* anonymous vma */
		return NULL;
	if (!(mc.flags & MOVE_FILE))
		return NULL;

	mapping = vma->vm_file->f_mapping;
	pgoff = linear_page_index(vma, addr);

	/* page is moved even if it's not RSS of this task(page-faulted). */
#ifdef CONFIG_SWAP
	/* shmem/tmpfs may report page out on swap: account for that too. */
	if (shmem_mapping(mapping)) {
		page = find_get_entry(mapping, pgoff);
		if (xa_is_value(page)) {
			swp_entry_t swp = radix_to_swp_entry(page);
			if (do_memsw_account())
				*entry = swp;
			page = find_get_page(swap_address_space(swp),
					     swp_offset(swp));
		}
	} else
		page = find_get_page(mapping, pgoff);
#else
	page = find_get_page(mapping, pgoff);
#endif
	return page;
}

/**
 * mem_cgroup_move_account - move account of the page
 * @page: the page
 * @compound: charge the page as compound or small page
 * @from: mem_cgroup which the page is moved from.
 * @to:	mem_cgroup which the page is moved to. @from != @to.
 *
 * The caller must make sure the page is not on LRU (isolate_page() is useful.)
 *
 * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
 * from old cgroup.
 */
static int mem_cgroup_move_account(struct page *page,
				   bool compound,
				   struct mem_cgroup *from,
				   struct mem_cgroup *to)
{
	unsigned long flags;
	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
	int ret;
	bool anon;

	VM_BUG_ON(from == to);
	VM_BUG_ON_PAGE(PageLRU(page), page);
	VM_BUG_ON(compound && !PageTransHuge(page));

	/*
	 * Prevent mem_cgroup_migrate() from looking at
	 * page->mem_cgroup of its source page while we change it.
	 */
	ret = -EBUSY;
	if (!trylock_page(page))
		goto out;

	ret = -EINVAL;
	if (page->mem_cgroup != from)
		goto out_unlock;

	anon = PageAnon(page);

	spin_lock_irqsave(&from->move_lock, flags);

	if (!anon && page_mapped(page)) {
		__mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages);
		__mod_memcg_state(to, NR_FILE_MAPPED, nr_pages);
	}

	/*
	 * move_lock grabbed above and caller set from->moving_account, so
	 * mod_memcg_page_state will serialize updates to PageDirty.
	 * So mapping should be stable for dirty pages.
	 */
	if (!anon && PageDirty(page)) {
		struct address_space *mapping = page_mapping(page);

		if (mapping_cap_account_dirty(mapping)) {
			__mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages);
			__mod_memcg_state(to, NR_FILE_DIRTY, nr_pages);
		}
	}

	if (PageWriteback(page)) {
		__mod_memcg_state(from, NR_WRITEBACK, -nr_pages);
		__mod_memcg_state(to, NR_WRITEBACK, nr_pages);
	}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	if (compound && !list_empty(page_deferred_list(page))) {
		spin_lock(&from->deferred_split_queue.split_queue_lock);
		list_del_init(page_deferred_list(page));
		from->deferred_split_queue.split_queue_len--;
		spin_unlock(&from->deferred_split_queue.split_queue_lock);
	}
#endif
	/*
	 * It is safe to change page->mem_cgroup here because the page
	 * is referenced, charged, and isolated - we can't race with
	 * uncharging, charging, migration, or LRU putback.
	 */

	/* caller should have done css_get */
	page->mem_cgroup = to;

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	if (compound && list_empty(page_deferred_list(page))) {
		spin_lock(&to->deferred_split_queue.split_queue_lock);
		list_add_tail(page_deferred_list(page),
			      &to->deferred_split_queue.split_queue);
		to->deferred_split_queue.split_queue_len++;
		spin_unlock(&to->deferred_split_queue.split_queue_lock);
	}
#endif

	spin_unlock_irqrestore(&from->move_lock, flags);

	ret = 0;

	local_irq_disable();
	mem_cgroup_charge_statistics(to, page, compound, nr_pages);
	memcg_check_events(to, page);
	mem_cgroup_charge_statistics(from, page, compound, -nr_pages);
	memcg_check_events(from, page);
	local_irq_enable();
out_unlock:
	unlock_page(page);
out:
	return ret;
}

/**
 * get_mctgt_type - get target type of moving charge
 * @vma: the vma the pte to be checked belongs
 * @addr: the address corresponding to the pte to be checked
 * @ptent: the pte to be checked
 * @target: the pointer the target page or swap ent will be stored(can be NULL)
 *
 * Returns
 *   0(MC_TARGET_NONE): if the pte is not a target for move charge.
 *   1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
 *     move charge. if @target is not NULL, the page is stored in target->page
 *     with extra refcnt got(Callers should handle it).
 *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
 *     target for charge migration. if @target is not NULL, the entry is stored
 *     in target->ent.
 *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_PRIVATE
 *     (so ZONE_DEVICE page and thus not on the lru).
 *     For now we such page is charge like a regular page would be as for all
 *     intent and purposes it is just special memory taking the place of a
 *     regular page.
 *
 *     See Documentations/vm/hmm.txt and include/linux/hmm.h
 *
 * Called with pte lock held.
 */

static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
		unsigned long addr, pte_t ptent, union mc_target *target)
{
	struct page *page = NULL;
	enum mc_target_type ret = MC_TARGET_NONE;
	swp_entry_t ent = { .val = 0 };

	if (pte_present(ptent))
		page = mc_handle_present_pte(vma, addr, ptent);
	else if (is_swap_pte(ptent))
		page = mc_handle_swap_pte(vma, ptent, &ent);
	else if (pte_none(ptent))
		page = mc_handle_file_pte(vma, addr, ptent, &ent);

	if (!page && !ent.val)
		return ret;
	if (page) {
		/*
		 * Do only loose check w/o serialization.
		 * mem_cgroup_move_account() checks the page is valid or
		 * not under LRU exclusion.
		 */
		if (page->mem_cgroup == mc.from) {
			ret = MC_TARGET_PAGE;
			if (is_device_private_page(page))
				ret = MC_TARGET_DEVICE;
			if (target)
				target->page = page;
		}
		if (!ret || !target)
			put_page(page);
	}
	/*
	 * There is a swap entry and a page doesn't exist or isn't charged.
	 * But we cannot move a tail-page in a THP.
	 */
	if (ent.val && !ret && (!page || !PageTransCompound(page)) &&
	    mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) {
		ret = MC_TARGET_SWAP;
		if (target)
			target->ent = ent;
	}
	return ret;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * We don't consider PMD mapped swapping or file mapped pages because THP does
 * not support them for now.
 * Caller should make sure that pmd_trans_huge(pmd) is true.
 */
static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
		unsigned long addr, pmd_t pmd, union mc_target *target)
{
	struct page *page = NULL;
	enum mc_target_type ret = MC_TARGET_NONE;

	if (unlikely(is_swap_pmd(pmd))) {
		VM_BUG_ON(thp_migration_supported() &&
				  !is_pmd_migration_entry(pmd));
		return ret;
	}
	page = pmd_page(pmd);
	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
	if (!(mc.flags & MOVE_ANON))
		return ret;
	if (page->mem_cgroup == mc.from) {
		ret = MC_TARGET_PAGE;
		if (target) {
			get_page(page);
			target->page = page;
		}
	}
	return ret;
}
#else
static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
		unsigned long addr, pmd_t pmd, union mc_target *target)
{
	return MC_TARGET_NONE;
}
#endif

static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
					unsigned long addr, unsigned long end,
					struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;
	pte_t *pte;
	spinlock_t *ptl;

	ptl = pmd_trans_huge_lock(pmd, vma);
	if (ptl) {
		/*
		 * Note their can not be MC_TARGET_DEVICE for now as we do not
		 * support transparent huge page with MEMORY_DEVICE_PRIVATE but
		 * this might change.
		 */
		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
			mc.precharge += HPAGE_PMD_NR;
		spin_unlock(ptl);
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE)
		if (get_mctgt_type(vma, addr, *pte, NULL))
			mc.precharge++;	/* increment precharge temporarily */
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();

	return 0;
}

static const struct mm_walk_ops precharge_walk_ops = {
	.pmd_entry	= mem_cgroup_count_precharge_pte_range,
};

static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
{
	unsigned long precharge;

	down_read(&mm->mmap_sem);
	walk_page_range(mm, 0, mm->highest_vm_end, &precharge_walk_ops, NULL);
	up_read(&mm->mmap_sem);

	precharge = mc.precharge;
	mc.precharge = 0;

	return precharge;
}

static int mem_cgroup_precharge_mc(struct mm_struct *mm)
{
	unsigned long precharge = mem_cgroup_count_precharge(mm);

	VM_BUG_ON(mc.moving_task);
	mc.moving_task = current;
	return mem_cgroup_do_precharge(precharge);
}

/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */
static void __mem_cgroup_clear_mc(void)
{
	struct mem_cgroup *from = mc.from;
	struct mem_cgroup *to = mc.to;

	/* we must uncharge all the leftover precharges from mc.to */
	if (mc.precharge) {
		cancel_charge(mc.to, mc.precharge);
		mc.precharge = 0;
	}
	/*
	 * we didn't uncharge from mc.from at mem_cgroup_move_account(), so
	 * we must uncharge here.
	 */
	if (mc.moved_charge) {
		cancel_charge(mc.from, mc.moved_charge);
		mc.moved_charge = 0;
	}
	/* we must fixup refcnts and charges */
	if (mc.moved_swap) {
		/* uncharge swap account from the old cgroup */
		if (!mem_cgroup_is_root(mc.from))
			page_counter_uncharge(&mc.from->memsw, mc.moved_swap);

		mem_cgroup_id_put_many(mc.from, mc.moved_swap);

		/*
		 * we charged both to->memory and to->memsw, so we
		 * should uncharge to->memory.
		 */
		if (!mem_cgroup_is_root(mc.to))
			page_counter_uncharge(&mc.to->memory, mc.moved_swap);

		mem_cgroup_id_get_many(mc.to, mc.moved_swap);
		css_put_many(&mc.to->css, mc.moved_swap);

		mc.moved_swap = 0;
	}
	memcg_oom_recover(from);
	memcg_oom_recover(to);
	wake_up_all(&mc.waitq);
}

static void mem_cgroup_clear_mc(void)
{
	struct mm_struct *mm = mc.mm;

	/*
	 * we must clear moving_task before waking up waiters at the end of
	 * task migration.
	 */
	mc.moving_task = NULL;
	__mem_cgroup_clear_mc();
	spin_lock(&mc.lock);
	mc.from = NULL;
	mc.to = NULL;
	mc.mm = NULL;
	spin_unlock(&mc.lock);

	mmput(mm);
}

static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
{
	struct cgroup_subsys_state *css;
	struct mem_cgroup *memcg = NULL; /* unneeded init to make gcc happy */
	struct mem_cgroup *from;
	struct task_struct *leader, *p;
	struct mm_struct *mm;
	unsigned long move_flags;
	int ret = 0;

	/* charge immigration isn't supported on the default hierarchy */
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return 0;

	/*
	 * Multi-process migrations only happen on the default hierarchy
	 * where charge immigration is not used.  Perform charge
	 * immigration if @tset contains a leader and whine if there are
	 * multiple.
	 */
	p = NULL;
	cgroup_taskset_for_each_leader(leader, css, tset) {
		WARN_ON_ONCE(p);
		p = leader;
		memcg = mem_cgroup_from_css(css);
	}
	if (!p)
		return 0;

	/*
	 * We are now commited to this value whatever it is. Changes in this
	 * tunable will only affect upcoming migrations, not the current one.
	 * So we need to save it, and keep it going.
	 */
	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
	if (!move_flags)
		return 0;

	from = mem_cgroup_from_task(p);

	VM_BUG_ON(from == memcg);

	mm = get_task_mm(p);
	if (!mm)
		return 0;
	/* We move charges only when we move a owner of the mm */
	if (mm->owner == p) {
		VM_BUG_ON(mc.from);
		VM_BUG_ON(mc.to);
		VM_BUG_ON(mc.precharge);
		VM_BUG_ON(mc.moved_charge);
		VM_BUG_ON(mc.moved_swap);

		spin_lock(&mc.lock);
		mc.mm = mm;
		mc.from = from;
		mc.to = memcg;
		mc.flags = move_flags;
		spin_unlock(&mc.lock);
		/* We set mc.moving_task later */

		ret = mem_cgroup_precharge_mc(mm);
		if (ret)
			mem_cgroup_clear_mc();
	} else {
		mmput(mm);
	}
	return ret;
}

static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
	if (mc.to)
		mem_cgroup_clear_mc();
}

static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct mm_walk *walk)
{
	int ret = 0;
	struct vm_area_struct *vma = walk->vma;
	pte_t *pte;
	spinlock_t *ptl;
	enum mc_target_type target_type;
	union mc_target target;
	struct page *page;

	ptl = pmd_trans_huge_lock(pmd, vma);
	if (ptl) {
		if (mc.precharge < HPAGE_PMD_NR) {
			spin_unlock(ptl);
			return 0;
		}
		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
		if (target_type == MC_TARGET_PAGE) {
			page = target.page;
			if (!isolate_lru_page(page)) {
				if (!mem_cgroup_move_account(page, true,
							     mc.from, mc.to)) {
					mc.precharge -= HPAGE_PMD_NR;
					mc.moved_charge += HPAGE_PMD_NR;
				}
				putback_lru_page(page);
			}
			put_page(page);
		} else if (target_type == MC_TARGET_DEVICE) {
			page = target.page;
			if (!mem_cgroup_move_account(page, true,
						     mc.from, mc.to)) {
				mc.precharge -= HPAGE_PMD_NR;
				mc.moved_charge += HPAGE_PMD_NR;
			}
			put_page(page);
		}
		spin_unlock(ptl);
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
retry:
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; addr += PAGE_SIZE) {
		pte_t ptent = *(pte++);
		bool device = false;
		swp_entry_t ent;

		if (!mc.precharge)
			break;

		switch (get_mctgt_type(vma, addr, ptent, &target)) {
		case MC_TARGET_DEVICE:
			device = true;
			/* fall through */
		case MC_TARGET_PAGE:
			page = target.page;
			/*
			 * We can have a part of the split pmd here. Moving it
			 * can be done but it would be too convoluted so simply
			 * ignore such a partial THP and keep it in original
			 * memcg. There should be somebody mapping the head.
			 */
			if (PageTransCompound(page))
				goto put;
			if (!device && isolate_lru_page(page))
				goto put;
			if (!mem_cgroup_move_account(page, false,
						mc.from, mc.to)) {
				mc.precharge--;
				/* we uncharge from mc.from later. */
				mc.moved_charge++;
			}
			if (!device)
				putback_lru_page(page);
put:			/* get_mctgt_type() gets the page */
			put_page(page);
			break;
		case MC_TARGET_SWAP:
			ent = target.ent;
			if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) {
				mc.precharge--;
				/* we fixup refcnts and charges later. */
				mc.moved_swap++;
			}
			break;
		default:
			break;
		}
	}
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();

	if (addr != end) {
		/*
		 * We have consumed all precharges we got in can_attach().
		 * We try charge one by one, but don't do any additional
		 * charges to mc.to if we have failed in charge once in attach()
		 * phase.
		 */
		ret = mem_cgroup_do_precharge(1);
		if (!ret)
			goto retry;
	}

	return ret;
}

static const struct mm_walk_ops charge_walk_ops = {
	.pmd_entry	= mem_cgroup_move_charge_pte_range,
};

static void mem_cgroup_move_charge(void)
{
	lru_add_drain_all();
	/*
	 * Signal lock_page_memcg() to take the memcg's move_lock
	 * while we're moving its pages to another memcg. Then wait
	 * for already started RCU-only updates to finish.
	 */
	atomic_inc(&mc.from->moving_account);
	synchronize_rcu();
retry:
	if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) {
		/*
		 * Someone who are holding the mmap_sem might be waiting in
		 * waitq. So we cancel all extra charges, wake up all waiters,
		 * and retry. Because we cancel precharges, we might not be able
		 * to move enough charges, but moving charge is a best-effort
		 * feature anyway, so it wouldn't be a big problem.
		 */
		__mem_cgroup_clear_mc();
		cond_resched();
		goto retry;
	}
	/*
	 * When we have consumed all precharges and failed in doing
	 * additional charge, the page walk just aborts.
	 */
	walk_page_range(mc.mm, 0, mc.mm->highest_vm_end, &charge_walk_ops,
			NULL);

	up_read(&mc.mm->mmap_sem);
	atomic_dec(&mc.from->moving_account);
}

static void mem_cgroup_move_task(void)
{
	if (mc.to) {
		mem_cgroup_move_charge();
		mem_cgroup_clear_mc();
	}
}
#else	/* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
{
	return 0;
}
static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
}
static void mem_cgroup_move_task(void)
{
}
#endif

/*
 * Cgroup retains root cgroups across [un]mount cycles making it necessary
 * to verify whether we're attached to the default hierarchy on each mount
 * attempt.
 */
static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
{
	/*
	 * use_hierarchy is forced on the default hierarchy.  cgroup core
	 * guarantees that @root doesn't have any children, so turning it
	 * on for the root memcg is enough.
	 */
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		root_mem_cgroup->use_hierarchy = true;
	else
		root_mem_cgroup->use_hierarchy = false;
}

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 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)->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 long nr_pages;
	unsigned long high;
	int err;

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

	memcg->high = high;

	nr_pages = page_counter_read(&memcg->memory);
	if (nr_pages > high)
		try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
					     GFP_KERNEL, true);

	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 = MEM_CGROUP_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)) {
			err = -EINTR;
			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, true))
				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;
}

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]));
}

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;
}

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

	buf = memory_stat_format(memcg);
	if (!buf)
		return -ENOMEM;
	seq_puts(m, buf);
	kfree(buf);
	return 0;
}

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", 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;

	memcg->oom_group = oom_group;

	return nbytes;
}

static struct cftype memory_files[] = {
	{
		.name = "current",
		.flags = CFTYPE_NOT_ON_ROOT,
		.read_u64 = memory_current_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",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = memory_stat_show,
	},
	{
		.name = "oom.group",
		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
		.seq_show = memory_oom_group_show,
		.write = memory_oom_group_write,
	},
	{ }	/* 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,
	.can_attach = mem_cgroup_can_attach,
	.cancel_attach = mem_cgroup_cancel_attach,
	.post_attach = mem_cgroup_move_task,
	.bind = mem_cgroup_bind,
	.dfl_cftypes = memory_files,
	.legacy_cftypes = mem_cgroup_legacy_files,
	.early_init = 0,
};

/**
 * mem_cgroup_protected - 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.
 *
 * Returns one of the following:
 *   MEMCG_PROT_NONE: cgroup memory is not protected
 *   MEMCG_PROT_LOW: cgroup memory is protected as long there is
 *     an unprotected supply of reclaimable memory from other cgroups.
 *   MEMCG_PROT_MIN: cgroup memory is protected
 *
 * @root is exclusive; it is never protected when looked at directly
 *
 * To provide a proper hierarchical behavior, effective memory.min/low values
 * are used. Below is the description of how effective memory.low is calculated.
 * Effective memory.min values is calculated in the same way.
 *
 * Effective memory.low is always equal or less than the original memory.low.
 * If there is no memory.low overcommittment (which is always true for
 * top-level memory cgroups), these two values are equal.
 * Otherwise, it's a part of parent's effective memory.low,
 * calculated as a cgroup's memory.low usage divided by sum of sibling's
 * memory.low usages, where memory.low usage is the size of actually
 * protected memory.
 *
 *                                             low_usage
 * elow = min( memory.low, parent->elow * ------------------ ),
 *                                        siblings_low_usage
 *
 *             | memory.current, if memory.current < memory.low
 * low_usage = |
 *	       | 0, otherwise.
 *
 *
 * Such definition of the effective memory.low provides the expected
 * hierarchical behavior: parent's memory.low value is limiting
 * children, unprotected memory is reclaimed first and cgroups,
 * which are not using their guarantee do not affect actual memory
 * distribution.
 *
 * For example, if there are memcgs A, A/B, A/C, A/D and A/E:
 *
 *     A      A/memory.low = 2G, A/memory.current = 6G
 *    //\\
 *   BC  DE   B/memory.low = 3G  B/memory.current = 2G
 *            C/memory.low = 1G  C/memory.current = 2G
 *            D/memory.low = 0   D/memory.current = 2G
 *            E/memory.low = 10G E/memory.current = 0
 *
 * and the memory pressure is applied, the following memory distribution
 * is expected (approximately):
 *
 *     A/memory.current = 2G
 *
 *     B/memory.current = 1.3G
 *     C/memory.current = 0.6G
 *     D/memory.current = 0
 *     E/memory.current = 0
 *
 * These calculations require constant tracking of the actual low usages
 * (see propagate_protected_usage()), as well as recursive calculation of
 * effective memory.low values. But as we do call mem_cgroup_protected()
 * path for each memory cgroup top-down from the reclaim,
 * it's possible to optimize this part, and save calculated elow
 * for next usage. This part is intentionally racy, but it's ok,
 * as memory.low is a best-effort mechanism.
 */
enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
						struct mem_cgroup *memcg)
{
	struct mem_cgroup *parent;
	unsigned long emin, parent_emin;
	unsigned long elow, parent_elow;
	unsigned long usage;

	if (mem_cgroup_disabled())
		return MEMCG_PROT_NONE;

	if (!root)
		root = root_mem_cgroup;
	if (memcg == root)
		return MEMCG_PROT_NONE;

	usage = page_counter_read(&memcg->memory);
	if (!usage)
		return MEMCG_PROT_NONE;

	emin = memcg->memory.min;
	elow = memcg->memory.low;

	parent = parent_mem_cgroup(memcg);
	/* No parent means a non-hierarchical mode on v1 memcg */
	if (!parent)
		return MEMCG_PROT_NONE;

	if (parent == root)
		goto exit;

	parent_emin = READ_ONCE(parent->memory.emin);
	emin = min(emin, parent_emin);
	if (emin && parent_emin) {
		unsigned long min_usage, siblings_min_usage;

		min_usage = min(usage, memcg->memory.min);
		siblings_min_usage = atomic_long_read(
			&parent->memory.children_min_usage);

		if (min_usage && siblings_min_usage)
			emin = min(emin, parent_emin * min_usage /
				   siblings_min_usage);
	}

	parent_elow = READ_ONCE(parent->memory.elow);
	elow = min(elow, parent_elow);
	if (elow && parent_elow) {
		unsigned long low_usage, siblings_low_usage;

		low_usage = min(usage, memcg->memory.low);
		siblings_low_usage = atomic_long_read(
			&parent->memory.children_low_usage);

		if (low_usage && siblings_low_usage)
			elow = min(elow, parent_elow * low_usage /
				   siblings_low_usage);
	}

exit:
	memcg->memory.emin = emin;
	memcg->memory.elow = elow;

	if (usage <= emin)
		return MEMCG_PROT_MIN;
	else if (usage <= elow)
		return MEMCG_PROT_LOW;
	else
		return MEMCG_PROT_NONE;
}

/**
 * mem_cgroup_try_charge - try charging a page
 * @page: page to charge
 * @mm: mm context of the victim
 * @gfp_mask: reclaim mode
 * @memcgp: charged memcg return
 * @compound: charge the page as compound or small page
 *
 * Try to charge @page to the memcg that @mm belongs to, reclaiming
 * pages according to @gfp_mask if necessary.
 *
 * Returns 0 on success, with *@memcgp pointing to the charged memcg.
 * Otherwise, an error code is returned.
 *
 * After page->mapping has been set up, the caller must finalize the
 * charge with mem_cgroup_commit_charge().  Or abort the transaction
 * with mem_cgroup_cancel_charge() in case page instantiation fails.
 */
int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
			  bool compound)
{
	struct mem_cgroup *memcg = NULL;
	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
	int ret = 0;

	if (mem_cgroup_disabled())
		goto out;

	if (PageSwapCache(page)) {
		/*
		 * Every swap fault against a single page tries to charge the
		 * page, bail as early as possible.  shmem_unuse() encounters
		 * already charged pages, too.  The USED bit is protected by
		 * the page lock, which serializes swap cache removal, which
		 * in turn serializes uncharging.
		 */
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		if (compound_head(page)->mem_cgroup)
			goto out;

		if (do_swap_account) {
			swp_entry_t ent = { .val = page_private(page), };
			unsigned short id = lookup_swap_cgroup_id(ent);

			rcu_read_lock();
			memcg = mem_cgroup_from_id(id);
			if (memcg && !css_tryget_online(&memcg->css))
				memcg = NULL;
			rcu_read_unlock();
		}
	}

	if (!memcg)
		memcg = get_mem_cgroup_from_mm(mm);

	ret = try_charge(memcg, gfp_mask, nr_pages);

	css_put(&memcg->css);
out:
	*memcgp = memcg;
	return ret;
}

int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
			  bool compound)
{
	struct mem_cgroup *memcg;
	int ret;

	ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound);
	memcg = *memcgp;
	mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask);
	return ret;
}

/**
 * mem_cgroup_commit_charge - commit a page charge
 * @page: page to charge
 * @memcg: memcg to charge the page to
 * @lrucare: page might be on LRU already
 * @compound: charge the page as compound or small page
 *
 * Finalize a charge transaction started by mem_cgroup_try_charge(),
 * after page->mapping has been set up.  This must happen atomically
 * as part of the page instantiation, i.e. under the page table lock
 * for anonymous pages, under the page lock for page and swap cache.
 *
 * In addition, the page must not be on the LRU during the commit, to
 * prevent racing with task migration.  If it might be, use @lrucare.
 *
 * Use mem_cgroup_cancel_charge() to cancel the transaction instead.
 */
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
			      bool lrucare, bool compound)
{
	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;

	VM_BUG_ON_PAGE(!page->mapping, page);
	VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page);

	if (mem_cgroup_disabled())
		return;
	/*
	 * Swap faults will attempt to charge the same page multiple
	 * times.  But reuse_swap_page() might have removed the page
	 * from swapcache already, so we can't check PageSwapCache().
	 */
	if (!memcg)
		return;

	commit_charge(page, memcg, lrucare);

	local_irq_disable();
	mem_cgroup_charge_statistics(memcg, page, compound, nr_pages);
	memcg_check_events(memcg, page);
	local_irq_enable();

	if (do_memsw_account() && PageSwapCache(page)) {
		swp_entry_t entry = { .val = page_private(page) };
		/*
		 * 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, nr_pages);
	}
}

/**
 * mem_cgroup_cancel_charge - cancel a page charge
 * @page: page to charge
 * @memcg: memcg to charge the page to
 * @compound: charge the page as compound or small page
 *
 * Cancel a charge transaction started by mem_cgroup_try_charge().
 */
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
		bool compound)
{
	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;

	if (mem_cgroup_disabled())
		return;
	/*
	 * Swap faults will attempt to charge the same page multiple
	 * times.  But reuse_swap_page() might have removed the page
	 * from swapcache already, so we can't check PageSwapCache().
	 */
	if (!memcg)
		return;

	cancel_charge(memcg, nr_pages);
}

struct uncharge_gather {
	struct mem_cgroup *memcg;
	unsigned long pgpgout;
	unsigned long nr_anon;
	unsigned long nr_file;
	unsigned long nr_kmem;
	unsigned long nr_huge;
	unsigned long nr_shmem;
	struct page *dummy_page;
};

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 nr_pages = ug->nr_anon + ug->nr_file + ug->nr_kmem;
	unsigned long flags;

	if (!mem_cgroup_is_root(ug->memcg)) {
		page_counter_uncharge(&ug->memcg->memory, nr_pages);
		if (do_memsw_account())
			page_counter_uncharge(&ug->memcg->memsw, nr_pages);
		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem)
			page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem);
		memcg_oom_recover(ug->memcg);
	}

	local_irq_save(flags);
	__mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon);
	__mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file);
	__mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge);
	__mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem);
	__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, nr_pages);
	memcg_check_events(ug->memcg, ug->dummy_page);
	local_irq_restore(flags);

	if (!mem_cgroup_is_root(ug->memcg))
		css_put_many(&ug->memcg->css, nr_pages);
}

static void uncharge_page(struct page *page, struct uncharge_gather *ug)
{
	VM_BUG_ON_PAGE(PageLRU(page), page);
	VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) &&
			!PageHWPoison(page) , page);

	if (!page->mem_cgroup)
		return;

	/*
	 * Nobody should be changing or seriously looking at
	 * page->mem_cgroup at this point, we have fully
	 * exclusive access to the page.
	 */

	if (ug->memcg != page->mem_cgroup) {
		if (ug->memcg) {
			uncharge_batch(ug);
			uncharge_gather_clear(ug);
		}
		ug->memcg = page->mem_cgroup;
	}

	if (!PageKmemcg(page)) {
		unsigned int nr_pages = 1;

		if (PageTransHuge(page)) {
			nr_pages = compound_nr(page);
			ug->nr_huge += nr_pages;
		}
		if (PageAnon(page))
			ug->nr_anon += nr_pages;
		else {
			ug->nr_file += nr_pages;
			if (PageSwapBacked(page))
				ug->nr_shmem += nr_pages;
		}
		ug->pgpgout++;
	} else {
		ug->nr_kmem += compound_nr(page);
		__ClearPageKmemcg(page);
	}

	ug->dummy_page = page;
	page->mem_cgroup = NULL;
}

static void uncharge_list(struct list_head *page_list)
{
	struct uncharge_gather ug;
	struct list_head *next;

	uncharge_gather_clear(&ug);

	/*
	 * Note that the list can be a single page->lru; hence the
	 * do-while loop instead of a simple list_for_each_entry().
	 */
	next = page_list->next;
	do {
		struct page *page;

		page = list_entry(next, struct page, lru);
		next = page->lru.next;

		uncharge_page(page, &ug);
	} while (next != page_list);

	if (ug.memcg)
		uncharge_batch(&ug);
}

/**
 * mem_cgroup_uncharge - uncharge a page
 * @page: page to uncharge
 *
 * Uncharge a page previously charged with mem_cgroup_try_charge() and
 * mem_cgroup_commit_charge().
 */
void mem_cgroup_uncharge(struct page *page)
{
	struct uncharge_gather ug;

	if (mem_cgroup_disabled())
		return;

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

	uncharge_gather_clear(&ug);
	uncharge_page(page, &ug);
	uncharge_batch(&ug);
}

/**
 * mem_cgroup_uncharge_list - uncharge a list of page
 * @page_list: list of pages to uncharge
 *
 * Uncharge a list of pages previously charged with
 * mem_cgroup_try_charge() and mem_cgroup_commit_charge().
 */
void mem_cgroup_uncharge_list(struct list_head *page_list)
{
	if (mem_cgroup_disabled())
		return;

	if (!list_empty(page_list))
		uncharge_list(page_list);
}

/**
 * mem_cgroup_migrate - charge a page's replacement
 * @oldpage: currently circulating page
 * @newpage: replacement page
 *
 * Charge @newpage as a replacement page for @oldpage. @oldpage will
 * be uncharged upon free.
 *
 * Both pages must be locked, @newpage->mapping must be set up.
 */
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
{
	struct mem_cgroup *memcg;
	unsigned int nr_pages;
	bool compound;
	unsigned long flags;

	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
	VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
	VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage),
		       newpage);

	if (mem_cgroup_disabled())
		return;

	/* Page cache replacement: new page already charged? */
	if (newpage->mem_cgroup)
		return;

	/* Swapcache readahead pages can get replaced before being charged */
	memcg = oldpage->mem_cgroup;
	if (!memcg)
		return;

	/* Force-charge the new page. The old one will be freed soon */
	compound = PageTransHuge(newpage);
	nr_pages = compound ? hpage_nr_pages(newpage) : 1;

	page_counter_charge(&memcg->memory, nr_pages);
	if (do_memsw_account())
		page_counter_charge(&memcg->memsw, nr_pages);
	css_get_many(&memcg->css, nr_pages);

	commit_charge(newpage, memcg, false);

	local_irq_save(flags);
	mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
	memcg_check_events(memcg, newpage);
	local_irq_restore(flags);
}

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;

	/*
	 * Socket cloning can throw us here with sk_memcg already
	 * filled. It won't however, necessarily happen from
	 * process context. So the test for root memcg given
	 * the current task's memcg won't help us in this case.
	 *
	 * Respecting the original socket's memcg is a better
	 * decision in this case.
	 */
	if (sk->sk_memcg) {
		css_get(&sk->sk_memcg->css);
		return;
	}

	rcu_read_lock();
	memcg = mem_cgroup_from_task(current);
	if (memcg == root_mem_cgroup)
		goto out;
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active)
		goto out;
	if (css_tryget_online(&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
 *
 * Charges @nr_pages to @memcg. Returns %true if the charge fit within
 * @memcg's configured limit, %false if the charge had to be forced.
 */
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
{
	gfp_t gfp_mask = GFP_KERNEL;

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
		struct page_counter *fail;

		if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) {
			memcg->tcpmem_pressure = 0;
			return true;
		}
		page_counter_charge(&memcg->tcpmem, nr_pages);
		memcg->tcpmem_pressure = 1;
		return false;
	}

	/* Don't block in the packet receive path */
	if (in_softirq())
		gfp_mask = GFP_NOWAIT;

	mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);

	if (try_charge(memcg, gfp_mask, nr_pages) == 0)
		return true;

	try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages);
	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)) {
		page_counter_uncharge(&memcg->tcpmem, 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;
	}
	return 0;
}
__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, node;

#ifdef CONFIG_MEMCG_KMEM
	/*
	 * Kmem cache creation is mostly done with the slab_mutex held,
	 * so use a workqueue with limited concurrency to avoid stalling
	 * all worker threads in case lots of cgroups are created and
	 * destroyed simultaneously.
	 */
	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
	BUG_ON(!memcg_kmem_cache_wq);
#endif

	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);

	for_each_node(node) {
		struct mem_cgroup_tree_per_node *rtpn;

		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
				    node_online(node) ? node : NUMA_NO_NODE);

		rtpn->rb_root = RB_ROOT;
		rtpn->rb_rightmost = NULL;
		spin_lock_init(&rtpn->lock);
		soft_limit_tree.rb_tree_per_node[node] = rtpn;
	}

	return 0;
}
subsys_initcall(mem_cgroup_init);

#ifdef CONFIG_MEMCG_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(memcg == root_mem_cgroup)) {
			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
 * @page: page whose memsw charge to transfer
 * @entry: swap entry to move the charge to
 *
 * Transfer the memsw charge of @page to @entry.
 */
void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
	struct mem_cgroup *memcg, *swap_memcg;
	unsigned int nr_entries;
	unsigned short oldid;

	VM_BUG_ON_PAGE(PageLRU(page), page);
	VM_BUG_ON_PAGE(page_count(page), page);

	if (!do_memsw_account())
		return;

	memcg = page->mem_cgroup;

	/* Readahead page, never charged */
	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 = hpage_nr_pages(page);
	/* 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_PAGE(oldid, page);
	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);

	page->mem_cgroup = NULL;

	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.
	 */
	VM_BUG_ON(!irqs_disabled());
	mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page),
				     -nr_entries);
	memcg_check_events(memcg, page);

	if (!mem_cgroup_is_root(memcg))
		css_put_many(&memcg->css, nr_entries);
}

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

	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account)
		return 0;

	memcg = page->mem_cgroup;

	/* Readahead page, never charged */
	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_PAGE(oldid, page);
	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;

	if (!do_swap_account)
		return;

	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 (cgroup_subsys_on_dfl(memory_cgrp_subsys))
				page_counter_uncharge(&memcg->swap, nr_pages);
			else
				page_counter_uncharge(&memcg->memsw, 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 (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return nr_swap_pages;
	for (; memcg != root_mem_cgroup; 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 page *page)
{
	struct mem_cgroup *memcg;

	VM_BUG_ON_PAGE(!PageLocked(page), page);

	if (vm_swap_full())
		return true;
	if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return false;

	memcg = page->mem_cgroup;
	if (!memcg)
		return false;

	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
		if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.max)
			return true;

	return false;
}

/* for remember boot option*/
#ifdef CONFIG_MEMCG_SWAP_ENABLED
static int really_do_swap_account __initdata = 1;
#else
static int really_do_swap_account __initdata;
#endif

static int __init enable_swap_account(char *s)
{
	if (!strcmp(s, "1"))
		really_do_swap_account = 1;
	else if (!strcmp(s, "0"))
		really_do_swap_account = 0;
	return 1;
}
__setup("swapaccount=", enable_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 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, "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.max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = swap_max_show,
		.write = swap_max_write,
	},
	{
		.name = "swap.events",
		.flags = CFTYPE_NOT_ON_ROOT,
		.file_offset = offsetof(struct mem_cgroup, swap_events_file),
		.seq_show = swap_events_show,
	},
	{ }	/* terminate */
};

static struct cftype memsw_cgroup_files[] = {
	{
		.name = "memsw.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.failcnt",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{ },	/* terminate */
};

static int __init mem_cgroup_swap_init(void)
{
	if (!mem_cgroup_disabled() && really_do_swap_account) {
		do_swap_account = 1;
		WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys,
					       swap_files));
		WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys,
						  memsw_cgroup_files));
	}
	return 0;
}
subsys_initcall(mem_cgroup_swap_init);

#endif /* CONFIG_MEMCG_SWAP */