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
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Swap reorganised 29.12.95, Stephen Tweedie.
* kswapd added: 7.1.96 sct
* Removed kswapd_ctl limits, and swap out as many pages as needed
* to bring the system back to freepages.high: 2.4.97, Rik van Riel.
* Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
* Multiqueue VM started 5.8.00, Rik van Riel.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmpressure.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h> /* for buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/compaction.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/migrate.h>
#include <linux/delayacct.h>
#include <linux/sysctl.h>
#include <linux/memory-tiers.h>
#include <linux/oom.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/printk.h>
#include <linux/dax.h>
#include <linux/psi.h>
#include <linux/pagewalk.h>
#include <linux/shmem_fs.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/khugepaged.h>
#include <linux/rculist_nulls.h>
#include <linux/random.h>
#include <linux/srcu.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
#include <linux/balloon_compaction.h>
#include <linux/sched/sysctl.h>
#include "internal.h"
#include "swap.h"
#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>
struct scan_control {
/* How many pages shrink_list() should reclaim */
unsigned long nr_to_reclaim;
/*
* Nodemask of nodes allowed by the caller. If NULL, all nodes
* are scanned.
*/
nodemask_t *nodemask;
/*
* The memory cgroup that hit its limit and as a result is the
* primary target of this reclaim invocation.
*/
struct mem_cgroup *target_mem_cgroup;
/*
* Scan pressure balancing between anon and file LRUs
*/
unsigned long anon_cost;
unsigned long file_cost;
/* Can active folios be deactivated as part of reclaim? */
#define DEACTIVATE_ANON 1
#define DEACTIVATE_FILE 2
unsigned int may_deactivate:2;
unsigned int force_deactivate:1;
unsigned int skipped_deactivate:1;
/* Writepage batching in laptop mode; RECLAIM_WRITE */
unsigned int may_writepage:1;
/* Can mapped folios be reclaimed? */
unsigned int may_unmap:1;
/* Can folios be swapped as part of reclaim? */
unsigned int may_swap:1;
/* Proactive reclaim invoked by userspace through memory.reclaim */
unsigned int proactive:1;
/*
* Cgroup memory below memory.low is protected as long as we
* don't threaten to OOM. If any cgroup is reclaimed at
* reduced force or passed over entirely due to its memory.low
* setting (memcg_low_skipped), and nothing is reclaimed as a
* result, then go back for one more cycle that reclaims the protected
* memory (memcg_low_reclaim) to avert OOM.
*/
unsigned int memcg_low_reclaim:1;
unsigned int memcg_low_skipped:1;
unsigned int hibernation_mode:1;
/* One of the zones is ready for compaction */
unsigned int compaction_ready:1;
/* There is easily reclaimable cold cache in the current node */
unsigned int cache_trim_mode:1;
/* The file folios on the current node are dangerously low */
unsigned int file_is_tiny:1;
/* Always discard instead of demoting to lower tier memory */
unsigned int no_demotion:1;
/* Allocation order */
s8 order;
/* Scan (total_size >> priority) pages at once */
s8 priority;
/* The highest zone to isolate folios for reclaim from */
s8 reclaim_idx;
/* This context's GFP mask */
gfp_t gfp_mask;
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
/* Number of pages freed so far during a call to shrink_zones() */
unsigned long nr_reclaimed;
struct {
unsigned int dirty;
unsigned int unqueued_dirty;
unsigned int congested;
unsigned int writeback;
unsigned int immediate;
unsigned int file_taken;
unsigned int taken;
} nr;
/* for recording the reclaimed slab by now */
struct reclaim_state reclaim_state;
};
#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_folio(_folio, _base, _field) \
do { \
if ((_folio)->lru.prev != _base) { \
struct folio *prev; \
\
prev = lru_to_folio(&(_folio->lru)); \
prefetchw(&prev->_field); \
} \
} while (0)
#else
#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0)
#endif
/*
* From 0 .. 200. Higher means more swappy.
*/
int vm_swappiness = 60;
LIST_HEAD(shrinker_list);
DECLARE_RWSEM(shrinker_rwsem);
DEFINE_SRCU(shrinker_srcu);
static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0);
#ifdef CONFIG_MEMCG
static int shrinker_nr_max;
/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
static inline int shrinker_map_size(int nr_items)
{
return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long));
}
static inline int shrinker_defer_size(int nr_items)
{
return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t));
}
static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
int nid)
{
return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info,
&shrinker_srcu,
lockdep_is_held(&shrinker_rwsem));
}
static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg,
int nid)
{
return srcu_dereference(memcg->nodeinfo[nid]->shrinker_info,
&shrinker_srcu);
}
static void free_shrinker_info_rcu(struct rcu_head *head)
{
kvfree(container_of(head, struct shrinker_info, rcu));
}
static int expand_one_shrinker_info(struct mem_cgroup *memcg,
int map_size, int defer_size,
int old_map_size, int old_defer_size,
int new_nr_max)
{
struct shrinker_info *new, *old;
struct mem_cgroup_per_node *pn;
int nid;
int size = map_size + defer_size;
for_each_node(nid) {
pn = memcg->nodeinfo[nid];
old = shrinker_info_protected(memcg, nid);
/* Not yet online memcg */
if (!old)
return 0;
/* Already expanded this shrinker_info */
if (new_nr_max <= old->map_nr_max)
continue;
new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
if (!new)
return -ENOMEM;
new->nr_deferred = (atomic_long_t *)(new + 1);
new->map = (void *)new->nr_deferred + defer_size;
new->map_nr_max = new_nr_max;
/* map: set all old bits, clear all new bits */
memset(new->map, (int)0xff, old_map_size);
memset((void *)new->map + old_map_size, 0, map_size - old_map_size);
/* nr_deferred: copy old values, clear all new values */
memcpy(new->nr_deferred, old->nr_deferred, old_defer_size);
memset((void *)new->nr_deferred + old_defer_size, 0,
defer_size - old_defer_size);
rcu_assign_pointer(pn->shrinker_info, new);
call_srcu(&shrinker_srcu, &old->rcu, free_shrinker_info_rcu);
}
return 0;
}
void free_shrinker_info(struct mem_cgroup *memcg)
{
struct mem_cgroup_per_node *pn;
struct shrinker_info *info;
int nid;
for_each_node(nid) {
pn = memcg->nodeinfo[nid];
info = rcu_dereference_protected(pn->shrinker_info, true);
kvfree(info);
rcu_assign_pointer(pn->shrinker_info, NULL);
}
}
int alloc_shrinker_info(struct mem_cgroup *memcg)
{
struct shrinker_info *info;
int nid, size, ret = 0;
int map_size, defer_size = 0;
down_write(&shrinker_rwsem);
map_size = shrinker_map_size(shrinker_nr_max);
defer_size = shrinker_defer_size(shrinker_nr_max);
size = map_size + defer_size;
for_each_node(nid) {
info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
if (!info) {
free_shrinker_info(memcg);
ret = -ENOMEM;
break;
}
info->nr_deferred = (atomic_long_t *)(info + 1);
info->map = (void *)info->nr_deferred + defer_size;
info->map_nr_max = shrinker_nr_max;
rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
}
up_write(&shrinker_rwsem);
return ret;
}
static int expand_shrinker_info(int new_id)
{
int ret = 0;
int new_nr_max = round_up(new_id + 1, BITS_PER_LONG);
int map_size, defer_size = 0;
int old_map_size, old_defer_size = 0;
struct mem_cgroup *memcg;
if (!root_mem_cgroup)
goto out;
lockdep_assert_held(&shrinker_rwsem);
map_size = shrinker_map_size(new_nr_max);
defer_size = shrinker_defer_size(new_nr_max);
old_map_size = shrinker_map_size(shrinker_nr_max);
old_defer_size = shrinker_defer_size(shrinker_nr_max);
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
ret = expand_one_shrinker_info(memcg, map_size, defer_size,
old_map_size, old_defer_size,
new_nr_max);
if (ret) {
mem_cgroup_iter_break(NULL, memcg);
goto out;
}
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
out:
if (!ret)
shrinker_nr_max = new_nr_max;
return ret;
}
void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
{
if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
struct shrinker_info *info;
int srcu_idx;
srcu_idx = srcu_read_lock(&shrinker_srcu);
info = shrinker_info_srcu(memcg, nid);
if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) {
/* Pairs with smp mb in shrink_slab() */
smp_mb__before_atomic();
set_bit(shrinker_id, info->map);
}
srcu_read_unlock(&shrinker_srcu, srcu_idx);
}
}
static DEFINE_IDR(shrinker_idr);
static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
int id, ret = -ENOMEM;
if (mem_cgroup_disabled())
return -ENOSYS;
down_write(&shrinker_rwsem);
id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL);
if (id < 0)
goto unlock;
if (id >= shrinker_nr_max) {
if (expand_shrinker_info(id)) {
idr_remove(&shrinker_idr, id);
goto unlock;
}
}
shrinker->id = id;
ret = 0;
unlock:
up_write(&shrinker_rwsem);
return ret;
}
static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
int id = shrinker->id;
BUG_ON(id < 0);
lockdep_assert_held(&shrinker_rwsem);
idr_remove(&shrinker_idr, id);
}
static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
struct shrinker_info *info;
info = shrinker_info_srcu(memcg, nid);
return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0);
}
static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
struct shrinker_info *info;
info = shrinker_info_srcu(memcg, nid);
return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]);
}
void reparent_shrinker_deferred(struct mem_cgroup *memcg)
{
int i, nid;
long nr;
struct mem_cgroup *parent;
struct shrinker_info *child_info, *parent_info;
parent = parent_mem_cgroup(memcg);
if (!parent)
parent = root_mem_cgroup;
/* Prevent from concurrent shrinker_info expand */
down_write(&shrinker_rwsem);
for_each_node(nid) {
child_info = shrinker_info_protected(memcg, nid);
parent_info = shrinker_info_protected(parent, nid);
for (i = 0; i < child_info->map_nr_max; i++) {
nr = atomic_long_read(&child_info->nr_deferred[i]);
atomic_long_add(nr, &parent_info->nr_deferred[i]);
}
}
up_write(&shrinker_rwsem);
}
static bool cgroup_reclaim(struct scan_control *sc)
{
return sc->target_mem_cgroup;
}
static bool global_reclaim(struct scan_control *sc)
{
return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup);
}
/**
* writeback_throttling_sane - is the usual dirty throttling mechanism available?
* @sc: scan_control in question
*
* The normal page dirty throttling mechanism in balance_dirty_pages() is
* completely broken with the legacy memcg and direct stalling in
* shrink_folio_list() is used for throttling instead, which lacks all the
* niceties such as fairness, adaptive pausing, bandwidth proportional
* allocation and configurability.
*
* This function tests whether the vmscan currently in progress can assume
* that the normal dirty throttling mechanism is operational.
*/
static bool writeback_throttling_sane(struct scan_control *sc)
{
if (!cgroup_reclaim(sc))
return true;
#ifdef CONFIG_CGROUP_WRITEBACK
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return true;
#endif
return false;
}
#else
static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
return -ENOSYS;
}
static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
}
static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
return 0;
}
static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
struct mem_cgroup *memcg)
{
return 0;
}
static bool cgroup_reclaim(struct scan_control *sc)
{
return false;
}
static bool global_reclaim(struct scan_control *sc)
{
return true;
}
static bool writeback_throttling_sane(struct scan_control *sc)
{
return true;
}
#endif
static void set_task_reclaim_state(struct task_struct *task,
struct reclaim_state *rs)
{
/* Check for an overwrite */
WARN_ON_ONCE(rs && task->reclaim_state);
/* Check for the nulling of an already-nulled member */
WARN_ON_ONCE(!rs && !task->reclaim_state);
task->reclaim_state = rs;
}
/*
* flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to
* scan_control->nr_reclaimed.
*/
static void flush_reclaim_state(struct scan_control *sc)
{
/*
* Currently, reclaim_state->reclaimed includes three types of pages
* freed outside of vmscan:
* (1) Slab pages.
* (2) Clean file pages from pruned inodes (on highmem systems).
* (3) XFS freed buffer pages.
*
* For all of these cases, we cannot universally link the pages to a
* single memcg. For example, a memcg-aware shrinker can free one object
* charged to the target memcg, causing an entire page to be freed.
* If we count the entire page as reclaimed from the memcg, we end up
* overestimating the reclaimed amount (potentially under-reclaiming).
*
* Only count such pages for global reclaim to prevent under-reclaiming
* from the target memcg; preventing unnecessary retries during memcg
* charging and false positives from proactive reclaim.
*
* For uncommon cases where the freed pages were actually mostly
* charged to the target memcg, we end up underestimating the reclaimed
* amount. This should be fine. The freed pages will be uncharged
* anyway, even if they are not counted here properly, and we will be
* able to make forward progress in charging (which is usually in a
* retry loop).
*
* We can go one step further, and report the uncharged objcg pages in
* memcg reclaim, to make reporting more accurate and reduce
* underestimation, but it's probably not worth the complexity for now.
*/
if (current->reclaim_state && global_reclaim(sc)) {
sc->nr_reclaimed += current->reclaim_state->reclaimed;
current->reclaim_state->reclaimed = 0;
}
}
static long xchg_nr_deferred(struct shrinker *shrinker,
struct shrink_control *sc)
{
int nid = sc->nid;
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
nid = 0;
if (sc->memcg &&
(shrinker->flags & SHRINKER_MEMCG_AWARE))
return xchg_nr_deferred_memcg(nid, shrinker,
sc->memcg);
return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
}
static long add_nr_deferred(long nr, struct shrinker *shrinker,
struct shrink_control *sc)
{
int nid = sc->nid;
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
nid = 0;
if (sc->memcg &&
(shrinker->flags & SHRINKER_MEMCG_AWARE))
return add_nr_deferred_memcg(nr, nid, shrinker,
sc->memcg);
return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
}
static bool can_demote(int nid, struct scan_control *sc)
{
if (!numa_demotion_enabled)
return false;
if (sc && sc->no_demotion)
return false;
if (next_demotion_node(nid) == NUMA_NO_NODE)
return false;
return true;
}
static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
int nid,
struct scan_control *sc)
{
if (memcg == NULL) {
/*
* For non-memcg reclaim, is there
* space in any swap device?
*/
if (get_nr_swap_pages() > 0)
return true;
} else {
/* Is the memcg below its swap limit? */
if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
return true;
}
/*
* The page can not be swapped.
*
* Can it be reclaimed from this node via demotion?
*/
return can_demote(nid, sc);
}
/*
* This misses isolated folios which are not accounted for to save counters.
* As the data only determines if reclaim or compaction continues, it is
* not expected that isolated folios will be a dominating factor.
*/
unsigned long zone_reclaimable_pages(struct zone *zone)
{
unsigned long nr;
nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
return nr;
}
/**
* lruvec_lru_size - Returns the number of pages on the given LRU list.
* @lruvec: lru vector
* @lru: lru to use
* @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list)
*/
static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
int zone_idx)
{
unsigned long size = 0;
int zid;
for (zid = 0; zid <= zone_idx; zid++) {
struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
if (!managed_zone(zone))
continue;
if (!mem_cgroup_disabled())
size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
else
size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
}
return size;
}
/*
* Add a shrinker callback to be called from the vm.
*/
static int __prealloc_shrinker(struct shrinker *shrinker)
{
unsigned int size;
int err;
if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
err = prealloc_memcg_shrinker(shrinker);
if (err != -ENOSYS)
return err;
shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
}
size = sizeof(*shrinker->nr_deferred);
if (shrinker->flags & SHRINKER_NUMA_AWARE)
size *= nr_node_ids;
shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
if (!shrinker->nr_deferred)
return -ENOMEM;
return 0;
}
#ifdef CONFIG_SHRINKER_DEBUG
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
va_list ap;
int err;
va_start(ap, fmt);
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
va_end(ap);
if (!shrinker->name)
return -ENOMEM;
err = __prealloc_shrinker(shrinker);
if (err) {
kfree_const(shrinker->name);
shrinker->name = NULL;
}
return err;
}
#else
int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
return __prealloc_shrinker(shrinker);
}
#endif
void free_prealloced_shrinker(struct shrinker *shrinker)
{
#ifdef CONFIG_SHRINKER_DEBUG
kfree_const(shrinker->name);
shrinker->name = NULL;
#endif
if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
down_write(&shrinker_rwsem);
unregister_memcg_shrinker(shrinker);
up_write(&shrinker_rwsem);
return;
}
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
void register_shrinker_prepared(struct shrinker *shrinker)
{
down_write(&shrinker_rwsem);
list_add_tail_rcu(&shrinker->list, &shrinker_list);
shrinker->flags |= SHRINKER_REGISTERED;
shrinker_debugfs_add(shrinker);
up_write(&shrinker_rwsem);
}
static int __register_shrinker(struct shrinker *shrinker)
{
int err = __prealloc_shrinker(shrinker);
if (err)
return err;
register_shrinker_prepared(shrinker);
return 0;
}
#ifdef CONFIG_SHRINKER_DEBUG
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
va_list ap;
int err;
va_start(ap, fmt);
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
va_end(ap);
if (!shrinker->name)
return -ENOMEM;
err = __register_shrinker(shrinker);
if (err) {
kfree_const(shrinker->name);
shrinker->name = NULL;
}
return err;
}
#else
int register_shrinker(struct shrinker *shrinker, const char *fmt, ...)
{
return __register_shrinker(shrinker);
}
#endif
EXPORT_SYMBOL(register_shrinker);
/*
* Remove one
*/
void unregister_shrinker(struct shrinker *shrinker)
{
struct dentry *debugfs_entry;
int debugfs_id;
if (!(shrinker->flags & SHRINKER_REGISTERED))
return;
down_write(&shrinker_rwsem);
list_del_rcu(&shrinker->list);
shrinker->flags &= ~SHRINKER_REGISTERED;
if (shrinker->flags & SHRINKER_MEMCG_AWARE)
unregister_memcg_shrinker(shrinker);
debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id);
up_write(&shrinker_rwsem);
atomic_inc(&shrinker_srcu_generation);
synchronize_srcu(&shrinker_srcu);
shrinker_debugfs_remove(debugfs_entry, debugfs_id);
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);
/**
* synchronize_shrinkers - Wait for all running shrinkers to complete.
*
* This is equivalent to calling unregister_shrink() and register_shrinker(),
* but atomically and with less overhead. This is useful to guarantee that all
* shrinker invocations have seen an update, before freeing memory, similar to
* rcu.
*/
void synchronize_shrinkers(void)
{
down_write(&shrinker_rwsem);
up_write(&shrinker_rwsem);
atomic_inc(&shrinker_srcu_generation);
synchronize_srcu(&shrinker_srcu);
}
EXPORT_SYMBOL(synchronize_shrinkers);
#define SHRINK_BATCH 128
static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
struct shrinker *shrinker, int priority)
{
unsigned long freed = 0;
unsigned long long delta;
long total_scan;
long freeable;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
long scanned = 0, next_deferred;
freeable = shrinker->count_objects(shrinker, shrinkctl);
if (freeable == 0 || freeable == SHRINK_EMPTY)
return freeable;
/*
* copy the current shrinker scan count into a local variable
* and zero it so that other concurrent shrinker invocations
* don't also do this scanning work.
*/
nr = xchg_nr_deferred(shrinker, shrinkctl);
if (shrinker->seeks) {
delta = freeable >> priority;
delta *= 4;
do_div(delta, shrinker->seeks);
} else {
/*
* These objects don't require any IO to create. Trim
* them aggressively under memory pressure to keep
* them from causing refetches in the IO caches.
*/
delta = freeable / 2;
}
total_scan = nr >> priority;
total_scan += delta;
total_scan = min(total_scan, (2 * freeable));
trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
freeable, delta, total_scan, priority);
/*
* Normally, we should not scan less than batch_size objects in one
* pass to avoid too frequent shrinker calls, but if the slab has less
* than batch_size objects in total and we are really tight on memory,
* we will try to reclaim all available objects, otherwise we can end
* up failing allocations although there are plenty of reclaimable
* objects spread over several slabs with usage less than the
* batch_size.
*
* We detect the "tight on memory" situations by looking at the total
* number of objects we want to scan (total_scan). If it is greater
* than the total number of objects on slab (freeable), we must be
* scanning at high prio and therefore should try to reclaim as much as
* possible.
*/
while (total_scan >= batch_size ||
total_scan >= freeable) {
unsigned long ret;
unsigned long nr_to_scan = min(batch_size, total_scan);
shrinkctl->nr_to_scan = nr_to_scan;
shrinkctl->nr_scanned = nr_to_scan;
ret = shrinker->scan_objects(shrinker, shrinkctl);
if (ret == SHRINK_STOP)
break;
freed += ret;
count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned);
total_scan -= shrinkctl->nr_scanned;
scanned += shrinkctl->nr_scanned;
cond_resched();
}
/*
* The deferred work is increased by any new work (delta) that wasn't
* done, decreased by old deferred work that was done now.
*
* And it is capped to two times of the freeable items.
*/
next_deferred = max_t(long, (nr + delta - scanned), 0);
next_deferred = min(next_deferred, (2 * freeable));
/*
* move the unused scan count back into the shrinker in a
* manner that handles concurrent updates.
*/
new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);
trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
return freed;
}
#ifdef CONFIG_MEMCG
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
struct shrinker_info *info;
unsigned long ret, freed = 0;
int srcu_idx, generation;
int i = 0;
if (!mem_cgroup_online(memcg))
return 0;
again:
srcu_idx = srcu_read_lock(&shrinker_srcu);
info = shrinker_info_srcu(memcg, nid);
if (unlikely(!info))
goto unlock;
generation = atomic_read(&shrinker_srcu_generation);
for_each_set_bit_from(i, info->map, info->map_nr_max) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
struct shrinker *shrinker;
shrinker = idr_find(&shrinker_idr, i);
if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) {
if (!shrinker)
clear_bit(i, info->map);
continue;
}
/* Call non-slab shrinkers even though kmem is disabled */
if (!memcg_kmem_online() &&
!(shrinker->flags & SHRINKER_NONSLAB))
continue;
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY) {
clear_bit(i, info->map);
/*
* After the shrinker reported that it had no objects to
* free, but before we cleared the corresponding bit in
* the memcg shrinker map, a new object might have been
* added. To make sure, we have the bit set in this
* case, we invoke the shrinker one more time and reset
* the bit if it reports that it is not empty anymore.
* The memory barrier here pairs with the barrier in
* set_shrinker_bit():
*
* list_lru_add() shrink_slab_memcg()
* list_add_tail() clear_bit()
* <MB> <MB>
* set_bit() do_shrink_slab()
*/
smp_mb__after_atomic();
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
else
set_shrinker_bit(memcg, nid, i);
}
freed += ret;
if (atomic_read(&shrinker_srcu_generation) != generation) {
srcu_read_unlock(&shrinker_srcu, srcu_idx);
i++;
goto again;
}
}
unlock:
srcu_read_unlock(&shrinker_srcu, srcu_idx);
return freed;
}
#else /* CONFIG_MEMCG */
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
return 0;
}
#endif /* CONFIG_MEMCG */
/**
* shrink_slab - shrink slab caches
* @gfp_mask: allocation context
* @nid: node whose slab caches to target
* @memcg: memory cgroup whose slab caches to target
* @priority: the reclaim priority
*
* Call the shrink functions to age shrinkable caches.
*
* @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
* unaware shrinkers will receive a node id of 0 instead.
*
* @memcg specifies the memory cgroup to target. Unaware shrinkers
* are called only if it is the root cgroup.
*
* @priority is sc->priority, we take the number of objects and >> by priority
* in order to get the scan target.
*
* Returns the number of reclaimed slab objects.
*/
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
int priority)
{
unsigned long ret, freed = 0;
struct shrinker *shrinker;
int srcu_idx, generation;
/*
* The root memcg might be allocated even though memcg is disabled
* via "cgroup_disable=memory" boot parameter. This could make
* mem_cgroup_is_root() return false, then just run memcg slab
* shrink, but skip global shrink. This may result in premature
* oom.
*/
if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
srcu_idx = srcu_read_lock(&shrinker_srcu);
generation = atomic_read(&shrinker_srcu_generation);
list_for_each_entry_srcu(shrinker, &shrinker_list, list,
srcu_read_lock_held(&shrinker_srcu)) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
freed += ret;
if (atomic_read(&shrinker_srcu_generation) != generation) {
freed = freed ? : 1;
break;
}
}
srcu_read_unlock(&shrinker_srcu, srcu_idx);
cond_resched();
return freed;
}
static unsigned long drop_slab_node(int nid)
{
unsigned long freed = 0;
struct mem_cgroup *memcg = NULL;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
return freed;
}
void drop_slab(void)
{
int nid;
int shift = 0;
unsigned long freed;
do {
freed = 0;
for_each_online_node(nid) {
if (fatal_signal_pending(current))
return;
freed += drop_slab_node(nid);
}
} while ((freed >> shift++) > 1);
}
static int reclaimer_offset(void)
{
BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
PGSCAN_DIRECT - PGSCAN_KSWAPD);
BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);
if (current_is_kswapd())
return 0;
if (current_is_khugepaged())
return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD;
return PGSTEAL_DIRECT - PGSTEAL_KSWAPD;
}
static inline int is_page_cache_freeable(struct folio *folio)
{
/*
* A freeable page cache folio is referenced only by the caller
* that isolated the folio, the page cache and optional filesystem
* private data at folio->private.
*/
return folio_ref_count(folio) - folio_test_private(folio) ==
1 + folio_nr_pages(folio);
}
/*
* We detected a synchronous write error writing a folio out. Probably
* -ENOSPC. We need to propagate that into the address_space for a subsequent
* fsync(), msync() or close().
*
* The tricky part is that after writepage we cannot touch the mapping: nothing
* prevents it from being freed up. But we have a ref on the folio and once
* that folio is locked, the mapping is pinned.
*
* We're allowed to run sleeping folio_lock() here because we know the caller has
* __GFP_FS.
*/
static void handle_write_error(struct address_space *mapping,
struct folio *folio, int error)
{
folio_lock(folio);
if (folio_mapping(folio) == mapping)
mapping_set_error(mapping, error);
folio_unlock(folio);
}
static bool skip_throttle_noprogress(pg_data_t *pgdat)
{
int reclaimable = 0, write_pending = 0;
int i;
/*
* If kswapd is disabled, reschedule if necessary but do not
* throttle as the system is likely near OOM.
*/
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
/*
* If there are a lot of dirty/writeback folios then do not
* throttle as throttling will occur when the folios cycle
* towards the end of the LRU if still under writeback.
*/
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
reclaimable += zone_reclaimable_pages(zone);
write_pending += zone_page_state_snapshot(zone,
NR_ZONE_WRITE_PENDING);
}
if (2 * write_pending <= reclaimable)
return true;
return false;
}
void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
{
wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
long timeout, ret;
DEFINE_WAIT(wait);
/*
* Do not throttle user workers, kthreads other than kswapd or
* workqueues. They may be required for reclaim to make
* forward progress (e.g. journalling workqueues or kthreads).
*/
if (!current_is_kswapd() &&
current->flags & (PF_USER_WORKER|PF_KTHREAD)) {
cond_resched();
return;
}
/*
* These figures are pulled out of thin air.
* VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
* parallel reclaimers which is a short-lived event so the timeout is
* short. Failing to make progress or waiting on writeback are
* potentially long-lived events so use a longer timeout. This is shaky
* logic as a failure to make progress could be due to anything from
* writeback to a slow device to excessive referenced folios at the tail
* of the inactive LRU.
*/
switch(reason) {
case VMSCAN_THROTTLE_WRITEBACK:
timeout = HZ/10;
if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
WRITE_ONCE(pgdat->nr_reclaim_start,
node_page_state(pgdat, NR_THROTTLED_WRITTEN));
}
break;
case VMSCAN_THROTTLE_CONGESTED:
fallthrough;
case VMSCAN_THROTTLE_NOPROGRESS:
if (skip_throttle_noprogress(pgdat)) {
cond_resched();
return;
}
timeout = 1;
break;
case VMSCAN_THROTTLE_ISOLATED:
timeout = HZ/50;
break;
default:
WARN_ON_ONCE(1);
timeout = HZ;
break;
}
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = schedule_timeout(timeout);
finish_wait(wqh, &wait);
if (reason == VMSCAN_THROTTLE_WRITEBACK)
atomic_dec(&pgdat->nr_writeback_throttled);
trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
jiffies_to_usecs(timeout - ret),
reason);
}
/*
* Account for folios written if tasks are throttled waiting on dirty
* folios to clean. If enough folios have been cleaned since throttling
* started then wakeup the throttled tasks.
*/
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
int nr_throttled)
{
unsigned long nr_written;
node_stat_add_folio(folio, NR_THROTTLED_WRITTEN);
/*
* This is an inaccurate read as the per-cpu deltas may not
* be synchronised. However, given that the system is
* writeback throttled, it is not worth taking the penalty
* of getting an accurate count. At worst, the throttle
* timeout guarantees forward progress.
*/
nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) -
READ_ONCE(pgdat->nr_reclaim_start);
if (nr_written > SWAP_CLUSTER_MAX * nr_throttled)
wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]);
}
/* possible outcome of pageout() */
typedef enum {
/* failed to write folio out, folio is locked */
PAGE_KEEP,
/* move folio to the active list, folio is locked */
PAGE_ACTIVATE,
/* folio has been sent to the disk successfully, folio is unlocked */
PAGE_SUCCESS,
/* folio is clean and locked */
PAGE_CLEAN,
} pageout_t;
/*
* pageout is called by shrink_folio_list() for each dirty folio.
* Calls ->writepage().
*/
static pageout_t pageout(struct folio *folio, struct address_space *mapping,
struct swap_iocb **plug)
{
/*
* If the folio is dirty, only perform writeback if that write
* will be non-blocking. To prevent this allocation from being
* stalled by pagecache activity. But note that there may be
* stalls if we need to run get_block(). We could test
* PagePrivate for that.
*
* If this process is currently in __generic_file_write_iter() against
* this folio's queue, we can perform writeback even if that
* will block.
*
* If the folio is swapcache, write it back even if that would
* block, for some throttling. This happens by accident, because
* swap_backing_dev_info is bust: it doesn't reflect the
* congestion state of the swapdevs. Easy to fix, if needed.
*/
if (!is_page_cache_freeable(folio))
return PAGE_KEEP;
if (!mapping) {
/*
* Some data journaling orphaned folios can have
* folio->mapping == NULL while being dirty with clean buffers.
*/
if (folio_test_private(folio)) {
if (try_to_free_buffers(folio)) {
folio_clear_dirty(folio);
pr_info("%s: orphaned folio\n", __func__);
return PAGE_CLEAN;
}
}
return PAGE_KEEP;
}
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
if (folio_clear_dirty_for_io(folio)) {
int res;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
.for_reclaim = 1,
.swap_plug = plug,
};
folio_set_reclaim(folio);
res = mapping->a_ops->writepage(&folio->page, &wbc);
if (res < 0)
handle_write_error(mapping, folio, res);
if (res == AOP_WRITEPAGE_ACTIVATE) {
folio_clear_reclaim(folio);
return PAGE_ACTIVATE;
}
if (!folio_test_writeback(folio)) {
/* synchronous write or broken a_ops? */
folio_clear_reclaim(folio);
}
trace_mm_vmscan_write_folio(folio);
node_stat_add_folio(folio, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
return PAGE_CLEAN;
}
/*
* Same as remove_mapping, but if the folio is removed from the mapping, it
* gets returned with a refcount of 0.
*/
static int __remove_mapping(struct address_space *mapping, struct folio *folio,
bool reclaimed, struct mem_cgroup *target_memcg)
{
int refcount;
void *shadow = NULL;
BUG_ON(!folio_test_locked(folio));
BUG_ON(mapping != folio_mapping(folio));
if (!folio_test_swapcache(folio))
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
/*
* The non racy check for a busy folio.
*
* Must be careful with the order of the tests. When someone has
* a ref to the folio, it may be possible that they dirty it then
* drop the reference. So if the dirty flag is tested before the
* refcount here, then the following race may occur:
*
* get_user_pages(&page);
* [user mapping goes away]
* write_to(page);
* !folio_test_dirty(folio) [good]
* folio_set_dirty(folio);
* folio_put(folio);
* !refcount(folio) [good, discard it]
*
* [oops, our write_to data is lost]
*
* Reversing the order of the tests ensures such a situation cannot
* escape unnoticed. The smp_rmb is needed to ensure the folio->flags
* load is not satisfied before that of folio->_refcount.
*
* Note that if the dirty flag is always set via folio_mark_dirty,
* and thus under the i_pages lock, then this ordering is not required.
*/
refcount = 1 + folio_nr_pages(folio);
if (!folio_ref_freeze(folio, refcount))
goto cannot_free;
/* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */
if (unlikely(folio_test_dirty(folio))) {
folio_ref_unfreeze(folio, refcount);
goto cannot_free;
}
if (folio_test_swapcache(folio)) {
swp_entry_t swap = folio_swap_entry(folio);
if (reclaimed && !mapping_exiting(mapping))
shadow = workingset_eviction(folio, target_memcg);
__delete_from_swap_cache(folio, swap, shadow);
mem_cgroup_swapout(folio, swap);
xa_unlock_irq(&mapping->i_pages);
put_swap_folio(folio, swap);
} else {
void (*free_folio)(struct folio *);
free_folio = mapping->a_ops->free_folio;
/*
* Remember a shadow entry for reclaimed file cache in
* order to detect refaults, thus thrashing, later on.
*
* But don't store shadows in an address space that is
* already exiting. This is not just an optimization,
* inode reclaim needs to empty out the radix tree or
* the nodes are lost. Don't plant shadows behind its
* back.
*
* We also don't store shadows for DAX mappings because the
* only page cache folios found in these are zero pages
* covering holes, and because we don't want to mix DAX
* exceptional entries and shadow exceptional entries in the
* same address_space.
*/
if (reclaimed && folio_is_file_lru(folio) &&
!mapping_exiting(mapping) && !dax_mapping(mapping))
shadow = workingset_eviction(folio, target_memcg);
__filemap_remove_folio(folio, shadow);
xa_unlock_irq(&mapping->i_pages);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
if (free_folio)
free_folio(folio);
}
return 1;
cannot_free:
xa_unlock_irq(&mapping->i_pages);
if (!folio_test_swapcache(folio))
spin_unlock(&mapping->host->i_lock);
return 0;
}
/**
* remove_mapping() - Attempt to remove a folio from its mapping.
* @mapping: The address space.
* @folio: The folio to remove.
*
* If the folio is dirty, under writeback or if someone else has a ref
* on it, removal will fail.
* Return: The number of pages removed from the mapping. 0 if the folio
* could not be removed.
* Context: The caller should have a single refcount on the folio and
* hold its lock.
*/
long remove_mapping(struct address_space *mapping, struct folio *folio)
{
if (__remove_mapping(mapping, folio, false, NULL)) {
/*
* Unfreezing the refcount with 1 effectively
* drops the pagecache ref for us without requiring another
* atomic operation.
*/
folio_ref_unfreeze(folio, 1);
return folio_nr_pages(folio);
}
return 0;
}
/**
* folio_putback_lru - Put previously isolated folio onto appropriate LRU list.
* @folio: Folio to be returned to an LRU list.
*
* Add previously isolated @folio to appropriate LRU list.
* The folio may still be unevictable for other reasons.
*
* Context: lru_lock must not be held, interrupts must be enabled.
*/
void folio_putback_lru(struct folio *folio)
{
folio_add_lru(folio);
folio_put(folio); /* drop ref from isolate */
}
enum folio_references {
FOLIOREF_RECLAIM,
FOLIOREF_RECLAIM_CLEAN,
FOLIOREF_KEEP,
FOLIOREF_ACTIVATE,
};
static enum folio_references folio_check_references(struct folio *folio,
struct scan_control *sc)
{
int referenced_ptes, referenced_folio;
unsigned long vm_flags;
referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
&vm_flags);
referenced_folio = folio_test_clear_referenced(folio);
/*
* The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
* Let the folio, now marked Mlocked, be moved to the unevictable list.
*/
if (vm_flags & VM_LOCKED)
return FOLIOREF_ACTIVATE;
/* rmap lock contention: rotate */
if (referenced_ptes == -1)
return FOLIOREF_KEEP;
if (referenced_ptes) {
/*
* All mapped folios start out with page table
* references from the instantiating fault, so we need
* to look twice if a mapped file/anon folio is used more
* than once.
*
* Mark it and spare it for another trip around the
* inactive list. Another page table reference will
* lead to its activation.
*
* Note: the mark is set for activated folios as well
* so that recently deactivated but used folios are
* quickly recovered.
*/
folio_set_referenced(folio);
if (referenced_folio || referenced_ptes > 1)
return FOLIOREF_ACTIVATE;
/*
* Activate file-backed executable folios after first usage.
*/
if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio))
return FOLIOREF_ACTIVATE;
return FOLIOREF_KEEP;
}
/* Reclaim if clean, defer dirty folios to writeback */
if (referenced_folio && folio_is_file_lru(folio))
return FOLIOREF_RECLAIM_CLEAN;
return FOLIOREF_RECLAIM;
}
/* Check if a folio is dirty or under writeback */
static void folio_check_dirty_writeback(struct folio *folio,
bool *dirty, bool *writeback)
{
struct address_space *mapping;
/*
* Anonymous folios are not handled by flushers and must be written
* from reclaim context. Do not stall reclaim based on them.
* MADV_FREE anonymous folios are put into inactive file list too.
* They could be mistakenly treated as file lru. So further anon
* test is needed.
*/
if (!folio_is_file_lru(folio) ||
(folio_test_anon(folio) && !folio_test_swapbacked(folio))) {
*dirty = false;
*writeback = false;
return;
}
/* By default assume that the folio flags are accurate */
*dirty = folio_test_dirty(folio);
*writeback = folio_test_writeback(folio);
/* Verify dirty/writeback state if the filesystem supports it */
if (!folio_test_private(folio))
return;
mapping = folio_mapping(folio);
if (mapping && mapping->a_ops->is_dirty_writeback)
mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
}
static struct page *alloc_demote_page(struct page *page, unsigned long private)
{
struct page *target_page;
nodemask_t *allowed_mask;
struct migration_target_control *mtc;
mtc = (struct migration_target_control *)private;
allowed_mask = mtc->nmask;
/*
* make sure we allocate from the target node first also trying to
* demote or reclaim pages from the target node via kswapd if we are
* low on free memory on target node. If we don't do this and if
* we have free memory on the slower(lower) memtier, we would start
* allocating pages from slower(lower) memory tiers without even forcing
* a demotion of cold pages from the target memtier. This can result
* in the kernel placing hot pages in slower(lower) memory tiers.
*/
mtc->nmask = NULL;
mtc->gfp_mask |= __GFP_THISNODE;
target_page = alloc_migration_target(page, (unsigned long)mtc);
if (target_page)
return target_page;
mtc->gfp_mask &= ~__GFP_THISNODE;
mtc->nmask = allowed_mask;
return alloc_migration_target(page, (unsigned long)mtc);
}
/*
* Take folios on @demote_folios and attempt to demote them to another node.
* Folios which are not demoted are left on @demote_folios.
*/
static unsigned int demote_folio_list(struct list_head *demote_folios,
struct pglist_data *pgdat)
{
int target_nid = next_demotion_node(pgdat->node_id);
unsigned int nr_succeeded;
nodemask_t allowed_mask;
struct migration_target_control mtc = {
/*
* Allocate from 'node', or fail quickly and quietly.
* When this happens, 'page' will likely just be discarded
* instead of migrated.
*/
.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN |
__GFP_NOMEMALLOC | GFP_NOWAIT,
.nid = target_nid,
.nmask = &allowed_mask
};
if (list_empty(demote_folios))
return 0;
if (target_nid == NUMA_NO_NODE)
return 0;
node_get_allowed_targets(pgdat, &allowed_mask);
/* Demotion ignores all cpuset and mempolicy settings */
migrate_pages(demote_folios, alloc_demote_page, NULL,
(unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
&nr_succeeded);
__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
return nr_succeeded;
}
static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
{
if (gfp_mask & __GFP_FS)
return true;
if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
return false;
/*
* We can "enter_fs" for swap-cache with only __GFP_IO
* providing this isn't SWP_FS_OPS.
* ->flags can be updated non-atomicially (scan_swap_map_slots),
* but that will never affect SWP_FS_OPS, so the data_race
* is safe.
*/
return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
}
/*
* shrink_folio_list() returns the number of reclaimed pages
*/
static unsigned int shrink_folio_list(struct list_head *folio_list,
struct pglist_data *pgdat, struct scan_control *sc,
struct reclaim_stat *stat, bool ignore_references)
{
LIST_HEAD(ret_folios);
LIST_HEAD(free_folios);
LIST_HEAD(demote_folios);
unsigned int nr_reclaimed = 0;
unsigned int pgactivate = 0;
bool do_demote_pass;
struct swap_iocb *plug = NULL;
memset(stat, 0, sizeof(*stat));
cond_resched();
do_demote_pass = can_demote(pgdat->node_id, sc);
retry:
while (!list_empty(folio_list)) {
struct address_space *mapping;
struct folio *folio;
enum folio_references references = FOLIOREF_RECLAIM;
bool dirty, writeback;
unsigned int nr_pages;
cond_resched();
folio = lru_to_folio(folio_list);
list_del(&folio->lru);
if (!folio_trylock(folio))
goto keep;
VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
nr_pages = folio_nr_pages(folio);
/* Account the number of base pages */
sc->nr_scanned += nr_pages;
if (unlikely(!folio_evictable(folio)))
goto activate_locked;
if (!sc->may_unmap && folio_mapped(folio))
goto keep_locked;
/* folio_update_gen() tried to promote this page? */
if (lru_gen_enabled() && !ignore_references &&
folio_mapped(folio) && folio_test_referenced(folio))
goto keep_locked;
/*
* The number of dirty pages determines if a node is marked
* reclaim_congested. kswapd will stall and start writing
* folios if the tail of the LRU is all dirty unqueued folios.
*/
folio_check_dirty_writeback(folio, &dirty, &writeback);
if (dirty || writeback)
stat->nr_dirty += nr_pages;
if (dirty && !writeback)
stat->nr_unqueued_dirty += nr_pages;
/*
* Treat this folio as congested if folios are cycling
* through the LRU so quickly that the folios marked
* for immediate reclaim are making it to the end of
* the LRU a second time.
*/
if (writeback && folio_test_reclaim(folio))
stat->nr_congested += nr_pages;
/*
* If a folio at the tail of the LRU is under writeback, there
* are three cases to consider.
*
* 1) If reclaim is encountering an excessive number
* of folios under writeback and this folio has both
* the writeback and reclaim flags set, then it
* indicates that folios are being queued for I/O but
* are being recycled through the LRU before the I/O
* can complete. Waiting on the folio itself risks an
* indefinite stall if it is impossible to writeback
* the folio due to I/O error or disconnected storage
* so instead note that the LRU is being scanned too
* quickly and the caller can stall after the folio
* list has been processed.
*
* 2) Global or new memcg reclaim encounters a folio that is
* not marked for immediate reclaim, or the caller does not
* have __GFP_FS (or __GFP_IO if it's simply going to swap,
* not to fs). In this case mark the folio for immediate
* reclaim and continue scanning.
*
* Require may_enter_fs() because we would wait on fs, which
* may not have submitted I/O yet. And the loop driver might
* enter reclaim, and deadlock if it waits on a folio for
* which it is needed to do the write (loop masks off
* __GFP_IO|__GFP_FS for this reason); but more thought
* would probably show more reasons.
*
* 3) Legacy memcg encounters a folio that already has the
* reclaim flag set. memcg does not have any dirty folio
* throttling so we could easily OOM just because too many
* folios are in writeback and there is nothing else to
* reclaim. Wait for the writeback to complete.
*
* In cases 1) and 2) we activate the folios to get them out of
* the way while we continue scanning for clean folios on the
* inactive list and refilling from the active list. The
* observation here is that waiting for disk writes is more
* expensive than potentially causing reloads down the line.
* Since they're marked for immediate reclaim, they won't put
* memory pressure on the cache working set any longer than it
* takes to write them to disk.
*/
if (folio_test_writeback(folio)) {
/* Case 1 above */
if (current_is_kswapd() &&
folio_test_reclaim(folio) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
stat->nr_immediate += nr_pages;
goto activate_locked;
/* Case 2 above */
} else if (writeback_throttling_sane(sc) ||
!folio_test_reclaim(folio) ||
!may_enter_fs(folio, sc->gfp_mask)) {
/*
* This is slightly racy -
* folio_end_writeback() might have
* just cleared the reclaim flag, then
* setting the reclaim flag here ends up
* interpreted as the readahead flag - but
* that does not matter enough to care.
* What we do want is for this folio to
* have the reclaim flag set next time
* memcg reclaim reaches the tests above,
* so it will then wait for writeback to
* avoid OOM; and it's also appropriate
* in global reclaim.
*/
folio_set_reclaim(folio);
stat->nr_writeback += nr_pages;
goto activate_locked;
/* Case 3 above */
} else {
folio_unlock(folio);
folio_wait_writeback(folio);
/* then go back and try same folio again */
list_add_tail(&folio->lru, folio_list);
continue;
}
}
if (!ignore_references)
references = folio_check_references(folio, sc);
switch (references) {
case FOLIOREF_ACTIVATE:
goto activate_locked;
case FOLIOREF_KEEP:
stat->nr_ref_keep += nr_pages;
goto keep_locked;
case FOLIOREF_RECLAIM:
case FOLIOREF_RECLAIM_CLEAN:
; /* try to reclaim the folio below */
}
/*
* Before reclaiming the folio, try to relocate
* its contents to another node.
*/
if (do_demote_pass &&
(thp_migration_supported() || !folio_test_large(folio))) {
list_add(&folio->lru, &demote_folios);
folio_unlock(folio);
continue;
}
/*
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
* Lazyfree folio could be freed directly
*/
if (folio_test_anon(folio) && folio_test_swapbacked(folio)) {
if (!folio_test_swapcache(folio)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (folio_maybe_dma_pinned(folio))
goto keep_locked;
if (folio_test_large(folio)) {
/* cannot split folio, skip it */
if (!can_split_folio(folio, NULL))
goto activate_locked;
/*
* Split folios without a PMD map right
* away. Chances are some or all of the
* tail pages can be freed without IO.
*/
if (!folio_entire_mapcount(folio) &&
split_folio_to_list(folio,
folio_list))
goto activate_locked;
}
if (!add_to_swap(folio)) {
if (!folio_test_large(folio))
goto activate_locked_split;
/* Fallback to swap normal pages */
if (split_folio_to_list(folio,
folio_list))
goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_vm_event(THP_SWPOUT_FALLBACK);
#endif
if (!add_to_swap(folio))
goto activate_locked_split;
}
}
} else if (folio_test_swapbacked(folio) &&
folio_test_large(folio)) {
/* Split shmem folio */
if (split_folio_to_list(folio, folio_list))
goto keep_locked;
}
/*
* If the folio was split above, the tail pages will make
* their own pass through this function and be accounted
* then.
*/
if ((nr_pages > 1) && !folio_test_large(folio)) {
sc->nr_scanned -= (nr_pages - 1);
nr_pages = 1;
}
/*
* The folio is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
if (folio_mapped(folio)) {
enum ttu_flags flags = TTU_BATCH_FLUSH;
bool was_swapbacked = folio_test_swapbacked(folio);
if (folio_test_pmd_mappable(folio))
flags |= TTU_SPLIT_HUGE_PMD;
try_to_unmap(folio, flags);
if (folio_mapped(folio)) {
stat->nr_unmap_fail += nr_pages;
if (!was_swapbacked &&
folio_test_swapbacked(folio))
stat->nr_lazyfree_fail += nr_pages;
goto activate_locked;
}
}
/*
* Folio is unmapped now so it cannot be newly pinned anymore.
* No point in trying to reclaim folio if it is pinned.
* Furthermore we don't want to reclaim underlying fs metadata
* if the folio is pinned and thus potentially modified by the
* pinning process as that may upset the filesystem.
*/
if (folio_maybe_dma_pinned(folio))
goto activate_locked;
mapping = folio_mapping(folio);
if (folio_test_dirty(folio)) {
/*
* Only kswapd can writeback filesystem folios
* to avoid risk of stack overflow. But avoid
* injecting inefficient single-folio I/O into
* flusher writeback as much as possible: only
* write folios when we've encountered many
* dirty folios, and when we've already scanned
* the rest of the LRU for clean folios and see
* the same dirty folios again (with the reclaim
* flag set).
*/
if (folio_is_file_lru(folio) &&
(!current_is_kswapd() ||
!folio_test_reclaim(folio) ||
!test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
* Similar in principle to folio_deactivate()
* except we already have the folio isolated
* and know it's dirty
*/
node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
nr_pages);
folio_set_reclaim(folio);
goto activate_locked;
}
if (references == FOLIOREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs(folio, sc->gfp_mask))
goto keep_locked;
if (!sc->may_writepage)
goto keep_locked;
/*
* Folio is dirty. Flush the TLB if a writable entry
* potentially exists to avoid CPU writes after I/O
* starts and then write it out here.
*/
try_to_unmap_flush_dirty();
switch (pageout(folio, mapping, &plug)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
goto activate_locked;
case PAGE_SUCCESS:
stat->nr_pageout += nr_pages;
if (folio_test_writeback(folio))
goto keep;
if (folio_test_dirty(folio))
goto keep;
/*
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the folio.
*/
if (!folio_trylock(folio))
goto keep;
if (folio_test_dirty(folio) ||
folio_test_writeback(folio))
goto keep_locked;
mapping = folio_mapping(folio);
fallthrough;
case PAGE_CLEAN:
; /* try to free the folio below */
}
}
/*
* If the folio has buffers, try to free the buffer
* mappings associated with this folio. If we succeed
* we try to free the folio as well.
*
* We do this even if the folio is dirty.
* filemap_release_folio() does not perform I/O, but it
* is possible for a folio to have the dirty flag set,
* but it is actually clean (all its buffers are clean).
* This happens if the buffers were written out directly,
* with submit_bh(). ext3 will do this, as well as
* the blockdev mapping. filemap_release_folio() will
* discover that cleanness and will drop the buffers
* and mark the folio clean - it can be freed.
*
* Rarely, folios can have buffers and no ->mapping.
* These are the folios which were not successfully
* invalidated in truncate_cleanup_folio(). We try to
* drop those buffers here and if that worked, and the
* folio is no longer mapped into process address space
* (refcount == 1) it can be freed. Otherwise, leave
* the folio on the LRU so it is swappable.
*/
if (folio_has_private(folio)) {
if (!filemap_release_folio(folio, sc->gfp_mask))
goto activate_locked;
if (!mapping && folio_ref_count(folio) == 1) {
folio_unlock(folio);
if (folio_put_testzero(folio))
goto free_it;
else {
/*
* rare race with speculative reference.
* the speculative reference will free
* this folio shortly, so we may
* increment nr_reclaimed here (and
* leave it off the LRU).
*/
nr_reclaimed += nr_pages;
continue;
}
}
}
if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
/* follow __remove_mapping for reference */
if (!folio_ref_freeze(folio, 1))
goto keep_locked;
/*
* The folio has only one reference left, which is
* from the isolation. After the caller puts the
* folio back on the lru and drops the reference, the
* folio will be freed anyway. It doesn't matter
* which lru it goes on. So we don't bother checking
* the dirty flag here.
*/
count_vm_events(PGLAZYFREED, nr_pages);
count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
} else if (!mapping || !__remove_mapping(mapping, folio, true,
sc->target_mem_cgroup))
goto keep_locked;
folio_unlock(folio);
free_it:
/*
* Folio may get swapped out as a whole, need to account
* all pages in it.
*/
nr_reclaimed += nr_pages;
/*
* Is there need to periodically free_folio_list? It would
* appear not as the counts should be low
*/
if (unlikely(folio_test_large(folio)))
destroy_large_folio(folio);
else
list_add(&folio->lru, &free_folios);
continue;
activate_locked_split:
/*
* The tail pages that are failed to add into swap cache
* reach here. Fixup nr_scanned and nr_pages.
*/
if (nr_pages > 1) {
sc->nr_scanned -= (nr_pages - 1);
nr_pages = 1;
}
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (folio_test_swapcache(folio) &&
(mem_cgroup_swap_full(folio) || folio_test_mlocked(folio)))
folio_free_swap(folio);
VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
if (!folio_test_mlocked(folio)) {
int type = folio_is_file_lru(folio);
folio_set_active(folio);
stat->nr_activate[type] += nr_pages;
count_memcg_folio_events(folio, PGACTIVATE, nr_pages);
}
keep_locked:
folio_unlock(folio);
keep:
list_add(&folio->lru, &ret_folios);
VM_BUG_ON_FOLIO(folio_test_lru(folio) ||
folio_test_unevictable(folio), folio);
}
/* 'folio_list' is always empty here */
/* Migrate folios selected for demotion */
nr_reclaimed += demote_folio_list(&demote_folios, pgdat);
/* Folios that could not be demoted are still in @demote_folios */
if (!list_empty(&demote_folios)) {
/* Folios which weren't demoted go back on @folio_list */
list_splice_init(&demote_folios, folio_list);
/*
* goto retry to reclaim the undemoted folios in folio_list if
* desired.
*
* Reclaiming directly from top tier nodes is not often desired
* due to it breaking the LRU ordering: in general memory
* should be reclaimed from lower tier nodes and demoted from
* top tier nodes.
*
* However, disabling reclaim from top tier nodes entirely
* would cause ooms in edge scenarios where lower tier memory
* is unreclaimable for whatever reason, eg memory being
* mlocked or too hot to reclaim. We can disable reclaim
* from top tier nodes in proactive reclaim though as that is
* not real memory pressure.
*/
if (!sc->proactive) {
do_demote_pass = false;
goto retry;
}
}
pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
mem_cgroup_uncharge_list(&free_folios);
try_to_unmap_flush();
free_unref_page_list(&free_folios);
list_splice(&ret_folios, folio_list);
count_vm_events(PGACTIVATE, pgactivate);
if (plug)
swap_write_unplug(plug);
return nr_reclaimed;
}
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *folio_list)
{
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
};
struct reclaim_stat stat;
unsigned int nr_reclaimed;
struct folio *folio, *next;
LIST_HEAD(clean_folios);
unsigned int noreclaim_flag;
list_for_each_entry_safe(folio, next, folio_list, lru) {
if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) &&
!folio_test_dirty(folio) && !__folio_test_movable(folio) &&
!folio_test_unevictable(folio)) {
folio_clear_active(folio);
list_move(&folio->lru, &clean_folios);
}
}
/*
* We should be safe here since we are only dealing with file pages and
* we are not kswapd and therefore cannot write dirty file pages. But
* call memalloc_noreclaim_save() anyway, just in case these conditions
* change in the future.
*/
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc,
&stat, true);
memalloc_noreclaim_restore(noreclaim_flag);
list_splice(&clean_folios, folio_list);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-(long)nr_reclaimed);
/*
* Since lazyfree pages are isolated from file LRU from the beginning,
* they will rotate back to anonymous LRU in the end if it failed to
* discard so isolated count will be mismatched.
* Compensate the isolated count for both LRU lists.
*/
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
stat.nr_lazyfree_fail);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-(long)stat.nr_lazyfree_fail);
return nr_reclaimed;
}
/*
* Update LRU sizes after isolating pages. The LRU size updates must
* be complete before mem_cgroup_update_lru_size due to a sanity check.
*/
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
enum lru_list lru, unsigned long *nr_zone_taken)
{
int zid;
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
if (!nr_zone_taken[zid])
continue;
update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
}
}
/*
* Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
*
* lruvec->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
* For pagecache intensive workloads, this function is the hottest
* spot in the kernel (apart from copy_*_user functions).
*
* Lru_lock must be held before calling this function.
*
* @nr_to_scan: The number of eligible pages to look through on the list.
* @lruvec: The LRU vector to pull pages from.
* @dst: The temp list to put pages on to.
* @nr_scanned: The number of pages that were scanned.
* @sc: The scan_control struct for this reclaim session
* @lru: LRU list id for isolating
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
struct lruvec *lruvec, struct list_head *dst,
unsigned long *nr_scanned, struct scan_control *sc,
enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long skipped = 0;
unsigned long scan, total_scan, nr_pages;
LIST_HEAD(folios_skipped);
total_scan = 0;
scan = 0;
while (scan < nr_to_scan && !list_empty(src)) {
struct list_head *move_to = src;
struct folio *folio;
folio = lru_to_folio(src);
prefetchw_prev_lru_folio(folio, src, flags);
nr_pages = folio_nr_pages(folio);
total_scan += nr_pages;
if (folio_zonenum(folio) > sc->reclaim_idx) {
nr_skipped[folio_zonenum(folio)] += nr_pages;
move_to = &folios_skipped;
goto move;
}
/*
* Do not count skipped folios because that makes the function
* return with no isolated folios if the LRU mostly contains
* ineligible folios. This causes the VM to not reclaim any
* folios, triggering a premature OOM.
* Account all pages in a folio.
*/
scan += nr_pages;
if (!folio_test_lru(folio))
goto move;
if (!sc->may_unmap && folio_mapped(folio))
goto move;
/*
* Be careful not to clear the lru flag until after we're
* sure the folio is not being freed elsewhere -- the
* folio release code relies on it.
*/
if (unlikely(!folio_try_get(folio)))
goto move;
if (!folio_test_clear_lru(folio)) {
/* Another thread is already isolating this folio */
folio_put(folio);
goto move;
}
nr_taken += nr_pages;
nr_zone_taken[folio_zonenum(folio)] += nr_pages;
move_to = dst;
move:
list_move(&folio->lru, move_to);
}
/*
* Splice any skipped folios to the start of the LRU list. Note that
* this disrupts the LRU order when reclaiming for lower zones but
* we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
* scanning would soon rescan the same folios to skip and waste lots
* of cpu cycles.
*/
if (!list_empty(&folios_skipped)) {
int zid;
list_splice(&folios_skipped, src);
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
if (!nr_skipped[zid])
continue;
__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
skipped += nr_skipped[zid];
}
}
*nr_scanned = total_scan;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
total_scan, skipped, nr_taken,
sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru);
update_lru_sizes(lruvec, lru, nr_zone_taken);
return nr_taken;
}
/**
* folio_isolate_lru() - Try to isolate a folio from its LRU list.
* @folio: Folio to isolate from its LRU list.
*
* Isolate a @folio from an LRU list and adjust the vmstat statistic
* corresponding to whatever LRU list the folio was on.
*
* The folio will have its LRU flag cleared. If it was found on the
* active list, it will have the Active flag set. If it was found on the
* unevictable list, it will have the Unevictable flag set. These flags
* may need to be cleared by the caller before letting the page go.
*
* Context:
*
* (1) Must be called with an elevated refcount on the folio. This is a
* fundamental difference from isolate_lru_folios() (which is called
* without a stable reference).
* (2) The lru_lock must not be held.
* (3) Interrupts must be enabled.
*
* Return: true if the folio was removed from an LRU list.
* false if the folio was not on an LRU list.
*/
bool folio_isolate_lru(struct folio *folio)
{
bool ret = false;
VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio);
if (folio_test_clear_lru(folio)) {
struct lruvec *lruvec;
folio_get(folio);
lruvec = folio_lruvec_lock_irq(folio);
lruvec_del_folio(lruvec, folio);
unlock_page_lruvec_irq(lruvec);
ret = true;
}
return ret;
}
/*
* A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
* then get rescheduled. When there are massive number of tasks doing page
* allocation, such sleeping direct reclaimers may keep piling up on each CPU,
* the LRU list will go small and be scanned faster than necessary, leading to
* unnecessary swapping, thrashing and OOM.
*/
static int too_many_isolated(struct pglist_data *pgdat, int file,
struct scan_control *sc)
{
unsigned long inactive, isolated;
bool too_many;
if (current_is_kswapd())
return 0;
if (!writeback_throttling_sane(sc))
return 0;
if (file) {
inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
} else {
inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
}
/*
* GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
* won't get blocked by normal direct-reclaimers, forming a circular
* deadlock.
*/
if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
inactive >>= 3;
too_many = isolated > inactive;
/* Wake up tasks throttled due to too_many_isolated. */
if (!too_many)
wake_throttle_isolated(pgdat);
return too_many;
}
/*
* move_folios_to_lru() moves folios from private @list to appropriate LRU list.
* On return, @list is reused as a list of folios to be freed by the caller.
*
* Returns the number of pages moved to the given lruvec.
*/
static unsigned int move_folios_to_lru(struct lruvec *lruvec,
struct list_head *list)
{
int nr_pages, nr_moved = 0;
LIST_HEAD(folios_to_free);
while (!list_empty(list)) {
struct folio *folio = lru_to_folio(list);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
list_del(&folio->lru);
if (unlikely(!folio_evictable(folio))) {
spin_unlock_irq(&lruvec->lru_lock);
folio_putback_lru(folio);
spin_lock_irq(&lruvec->lru_lock);
continue;
}
/*
* The folio_set_lru needs to be kept here for list integrity.
* Otherwise:
* #0 move_folios_to_lru #1 release_pages
* if (!folio_put_testzero())
* if (folio_put_testzero())
* !lru //skip lru_lock
* folio_set_lru()
* list_add(&folio->lru,)
* list_add(&folio->lru,)
*/
folio_set_lru(folio);
if (unlikely(folio_put_testzero(folio))) {
__folio_clear_lru_flags(folio);
if (unlikely(folio_test_large(folio))) {
spin_unlock_irq(&lruvec->lru_lock);
destroy_large_folio(folio);
spin_lock_irq(&lruvec->lru_lock);
} else
list_add(&folio->lru, &folios_to_free);
continue;
}
/*
* All pages were isolated from the same lruvec (and isolation
* inhibits memcg migration).
*/
VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
lruvec_add_folio(lruvec, folio);
nr_pages = folio_nr_pages(folio);
nr_moved += nr_pages;
if (folio_test_active(folio))
workingset_age_nonresident(lruvec, nr_pages);
}
/*
* To save our caller's stack, now use input list for pages to free.
*/
list_splice(&folios_to_free, list);
return nr_moved;
}
/*
* If a kernel thread (such as nfsd for loop-back mounts) services a backing
* device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case
* we should not throttle. Otherwise it is safe to do so.
*/
static int current_may_throttle(void)
{
return !(current->flags & PF_LOCAL_THROTTLE);
}
/*
* shrink_inactive_list() is a helper for shrink_node(). It returns the number
* of reclaimed pages
*/
static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
struct lruvec *lruvec, struct scan_control *sc,
enum lru_list lru)
{
LIST_HEAD(folio_list);
unsigned long nr_scanned;
unsigned int nr_reclaimed = 0;
unsigned long nr_taken;
struct reclaim_stat stat;
bool file = is_file_lru(lru);
enum vm_event_item item;
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
bool stalled = false;
while (unlikely(too_many_isolated(pgdat, file, sc))) {
if (stalled)
return 0;
/* wait a bit for the reclaimer. */
stalled = true;
reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
return SWAP_CLUSTER_MAX;
}
lru_add_drain();
spin_lock_irq(&lruvec->lru_lock);
nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list,
&nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
item = PGSCAN_KSWAPD + reclaimer_offset();
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_scanned);
__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
__count_vm_events(PGSCAN_ANON + file, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
if (nr_taken == 0)
return 0;
nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false);
spin_lock_irq(&lruvec->lru_lock);
move_folios_to_lru(lruvec, &folio_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
item = PGSTEAL_KSWAPD + reclaimer_offset();
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_reclaimed);
__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
spin_unlock_irq(&lruvec->lru_lock);
lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed);
mem_cgroup_uncharge_list(&folio_list);
free_unref_page_list(&folio_list);
/*
* If dirty folios are scanned that are not queued for IO, it
* implies that flushers are not doing their job. This can
* happen when memory pressure pushes dirty folios to the end of
* the LRU before the dirty limits are breached and the dirty
* data has expired. It can also happen when the proportion of
* dirty folios grows not through writes but through memory
* pressure reclaiming all the clean cache. And in some cases,
* the flushers simply cannot keep up with the allocation
* rate. Nudge the flusher threads in case they are asleep.
*/
if (stat.nr_unqueued_dirty == nr_taken) {
wakeup_flusher_threads(WB_REASON_VMSCAN);
/*
* For cgroupv1 dirty throttling is achieved by waking up
* the kernel flusher here and later waiting on folios
* which are in writeback to finish (see shrink_folio_list()).
*
* Flusher may not be able to issue writeback quickly
* enough for cgroupv1 writeback throttling to work
* on a large system.
*/
if (!writeback_throttling_sane(sc))
reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
sc->nr.dirty += stat.nr_dirty;
sc->nr.congested += stat.nr_congested;
sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
sc->nr.writeback += stat.nr_writeback;
sc->nr.immediate += stat.nr_immediate;
sc->nr.taken += nr_taken;
if (file)
sc->nr.file_taken += nr_taken;
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
nr_scanned, nr_reclaimed, &stat, sc->priority, file);
return nr_reclaimed;
}
/*
* shrink_active_list() moves folios from the active LRU to the inactive LRU.
*
* We move them the other way if the folio is referenced by one or more
* processes.
*
* If the folios are mostly unmapped, the processing is fast and it is
* appropriate to hold lru_lock across the whole operation. But if
* the folios are mapped, the processing is slow (folio_referenced()), so
* we should drop lru_lock around each folio. It's impossible to balance
* this, so instead we remove the folios from the LRU while processing them.
* It is safe to rely on the active flag against the non-LRU folios in here
* because nobody will play with that bit on a non-LRU folio.
*
* The downside is that we have to touch folio->_refcount against each folio.
* But we had to alter folio->flags anyway.
*/
static void shrink_active_list(unsigned long nr_to_scan,
struct lruvec *lruvec,
struct scan_control *sc,
enum lru_list lru)
{
unsigned long nr_taken;
unsigned long nr_scanned;
unsigned long vm_flags;
LIST_HEAD(l_hold); /* The folios which were snipped off */
LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
unsigned nr_deactivate, nr_activate;
unsigned nr_rotated = 0;
int file = is_file_lru(lru);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
lru_add_drain();
spin_lock_irq(&lruvec->lru_lock);
nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
if (!cgroup_reclaim(sc))
__count_vm_events(PGREFILL, nr_scanned);
__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
spin_unlock_irq(&lruvec->lru_lock);
while (!list_empty(&l_hold)) {
struct folio *folio;
cond_resched();
folio = lru_to_folio(&l_hold);
list_del(&folio->lru);
if (unlikely(!folio_evictable(folio))) {
folio_putback_lru(folio);
continue;
}
if (unlikely(buffer_heads_over_limit)) {
if (folio_test_private(folio) && folio_trylock(folio)) {
if (folio_test_private(folio))
filemap_release_folio(folio, 0);
folio_unlock(folio);
}
}
/* Referenced or rmap lock contention: rotate */
if (folio_referenced(folio, 0, sc->target_mem_cgroup,
&vm_flags) != 0) {
/*
* Identify referenced, file-backed active folios and
* give them one more trip around the active list. So
* that executable code get better chances to stay in
* memory under moderate memory pressure. Anon folios
* are not likely to be evicted by use-once streaming
* IO, plus JVM can create lots of anon VM_EXEC folios,
* so we ignore them here.
*/
if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
nr_rotated += folio_nr_pages(folio);
list_add(&folio->lru, &l_active);
continue;
}
}
folio_clear_active(folio); /* we are de-activating */
folio_set_workingset(folio);
list_add(&folio->lru, &l_inactive);
}
/*
* Move folios back to the lru list.
*/
spin_lock_irq(&lruvec->lru_lock);
nr_activate = move_folios_to_lru(lruvec, &l_active);
nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);
/* Keep all free folios in l_active list */
list_splice(&l_inactive, &l_active);
__count_vm_events(PGDEACTIVATE, nr_deactivate);
__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&lruvec->lru_lock);
if (nr_rotated)
lru_note_cost(lruvec, file, 0, nr_rotated);
mem_cgroup_uncharge_list(&l_active);
free_unref_page_list(&l_active);
trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
nr_deactivate, nr_rotated, sc->priority, file);
}
static unsigned int reclaim_folio_list(struct list_head *folio_list,
struct pglist_data *pgdat)
{
struct reclaim_stat dummy_stat;
unsigned int nr_reclaimed;
struct folio *folio;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_writepage = 1,
.may_unmap = 1,
.may_swap = 1,
.no_demotion = 1,
};
nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, false);
while (!list_empty(folio_list)) {
folio = lru_to_folio(folio_list);
list_del(&folio->lru);
folio_putback_lru(folio);
}
return nr_reclaimed;
}
unsigned long reclaim_pages(struct list_head *folio_list)
{
int nid;
unsigned int nr_reclaimed = 0;
LIST_HEAD(node_folio_list);
unsigned int noreclaim_flag;
if (list_empty(folio_list))
return nr_reclaimed;
noreclaim_flag = memalloc_noreclaim_save();
nid = folio_nid(lru_to_folio(folio_list));
do {
struct folio *folio = lru_to_folio(folio_list);
if (nid == folio_nid(folio)) {
folio_clear_active(folio);
list_move(&folio->lru, &node_folio_list);
continue;
}
nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
nid = folio_nid(lru_to_folio(folio_list));
} while (!list_empty(folio_list));
nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
memalloc_noreclaim_restore(noreclaim_flag);
return nr_reclaimed;
}
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct lruvec *lruvec, struct scan_control *sc)
{
if (is_active_lru(lru)) {
if (sc->may_deactivate & (1 << is_file_lru(lru)))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
else
sc->skipped_deactivate = 1;
return 0;
}
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
/*
* The inactive anon list should be small enough that the VM never has
* to do too much work.
*
* The inactive file list should be small enough to leave most memory
* to the established workingset on the scan-resistant active list,
* but large enough to avoid thrashing the aggregate readahead window.
*
* Both inactive lists should also be large enough that each inactive
* folio has a chance to be referenced again before it is reclaimed.
*
* If that fails and refaulting is observed, the inactive list grows.
*
* The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios
* on this LRU, maintained by the pageout code. An inactive_ratio
* of 3 means 3:1 or 25% of the folios are kept on the inactive list.
*
* total target max
* memory ratio inactive
* -------------------------------------
* 10MB 1 5MB
* 100MB 1 50MB
* 1GB 3 250MB
* 10GB 10 0.9GB
* 100GB 31 3GB
* 1TB 101 10GB
* 10TB 320 32GB
*/
static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
{
enum lru_list active_lru = inactive_lru + LRU_ACTIVE;
unsigned long inactive, active;
unsigned long inactive_ratio;
unsigned long gb;
inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
gb = (inactive + active) >> (30 - PAGE_SHIFT);
if (gb)
inactive_ratio = int_sqrt(10 * gb);
else
inactive_ratio = 1;
return inactive * inactive_ratio < active;
}
enum scan_balance {
SCAN_EQUAL,
SCAN_FRACT,
SCAN_ANON,
SCAN_FILE,
};
static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
{
unsigned long file;
struct lruvec *target_lruvec;
if (lru_gen_enabled())
return;
target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
/*
* Flush the memory cgroup stats, so that we read accurate per-memcg
* lruvec stats for heuristics.
*/
mem_cgroup_flush_stats();
/*
* Determine the scan balance between anon and file LRUs.
*/
spin_lock_irq(&target_lruvec->lru_lock);
sc->anon_cost = target_lruvec->anon_cost;
sc->file_cost = target_lruvec->file_cost;
spin_unlock_irq(&target_lruvec->lru_lock);
/*
* Target desirable inactive:active list ratios for the anon
* and file LRU lists.
*/
if (!sc->force_deactivate) {
unsigned long refaults;
/*
* When refaults are being observed, it means a new
* workingset is being established. Deactivate to get
* rid of any stale active pages quickly.
*/
refaults = lruvec_page_state(target_lruvec,
WORKINGSET_ACTIVATE_ANON);
if (refaults != target_lruvec->refaults[WORKINGSET_ANON] ||
inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
sc->may_deactivate |= DEACTIVATE_ANON;
else
sc->may_deactivate &= ~DEACTIVATE_ANON;
refaults = lruvec_page_state(target_lruvec,
WORKINGSET_ACTIVATE_FILE);
if (refaults != target_lruvec->refaults[WORKINGSET_FILE] ||
inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
sc->may_deactivate |= DEACTIVATE_FILE;
else
sc->may_deactivate &= ~DEACTIVATE_FILE;
} else
sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
/*
* If we have plenty of inactive file pages that aren't
* thrashing, try to reclaim those first before touching
* anonymous pages.
*/
file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
sc->cache_trim_mode = 1;
else
sc->cache_trim_mode = 0;
/*
* Prevent the reclaimer from falling into the cache trap: as
* cache pages start out inactive, every cache fault will tip
* the scan balance towards the file LRU. And as the file LRU
* shrinks, so does the window for rotation from references.
* This means we have a runaway feedback loop where a tiny
* thrashing file LRU becomes infinitely more attractive than
* anon pages. Try to detect this based on file LRU size.
*/
if (!cgroup_reclaim(sc)) {
unsigned long total_high_wmark = 0;
unsigned long free, anon;
int z;
free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
file = node_page_state(pgdat, NR_ACTIVE_FILE) +
node_page_state(pgdat, NR_INACTIVE_FILE);
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = &pgdat->node_zones[z];
if (!managed_zone(zone))
continue;
total_high_wmark += high_wmark_pages(zone);
}
/*
* Consider anon: if that's low too, this isn't a
* runaway file reclaim problem, but rather just
* extreme pressure. Reclaim as per usual then.
*/
anon = node_page_state(pgdat, NR_INACTIVE_ANON);
sc->file_is_tiny =
file + free <= total_high_wmark &&
!(sc->may_deactivate & DEACTIVATE_ANON) &&
anon >> sc->priority;
}
}
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned.
*
* nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan
* nr[2] = file inactive folios to scan; nr[3] = file active folios to scan
*/
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
unsigned long *nr)
{
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
unsigned long anon_cost, file_cost, total_cost;
int swappiness = mem_cgroup_swappiness(memcg);
u64 fraction[ANON_AND_FILE];
u64 denominator = 0; /* gcc */
enum scan_balance scan_balance;
unsigned long ap, fp;
enum lru_list lru;
/* If we have no swap space, do not bother scanning anon folios. */
if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Global reclaim will swap to prevent OOM even with no
* swappiness, but memcg users want to use this knob to
* disable swapping for individual groups completely when
* using the memory controller's swap limit feature would be
* too expensive.
*/
if (cgroup_reclaim(sc) && !swappiness) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Do not apply any pressure balancing cleverness when the
* system is close to OOM, scan both anon and file equally
* (unless the swappiness setting disagrees with swapping).
*/
if (!sc->priority && swappiness) {
scan_balance = SCAN_EQUAL;
goto out;
}
/*
* If the system is almost out of file pages, force-scan anon.
*/
if (sc->file_is_tiny) {
scan_balance = SCAN_ANON;
goto out;
}
/*
* If there is enough inactive page cache, we do not reclaim
* anything from the anonymous working right now.
*/
if (sc->cache_trim_mode) {
scan_balance = SCAN_FILE;
goto out;
}
scan_balance = SCAN_FRACT;
/*
* Calculate the pressure balance between anon and file pages.
*
* The amount of pressure we put on each LRU is inversely
* proportional to the cost of reclaiming each list, as
* determined by the share of pages that are refaulting, times
* the relative IO cost of bringing back a swapped out
* anonymous page vs reloading a filesystem page (swappiness).
*
* Although we limit that influence to ensure no list gets
* left behind completely: at least a third of the pressure is
* applied, before swappiness.
*
* With swappiness at 100, anon and file have equal IO cost.
*/
total_cost = sc->anon_cost + sc->file_cost;
anon_cost = total_cost + sc->anon_cost;
file_cost = total_cost + sc->file_cost;
total_cost = anon_cost + file_cost;
ap = swappiness * (total_cost + 1);
ap /= anon_cost + 1;
fp = (200 - swappiness) * (total_cost + 1);
fp /= file_cost + 1;
fraction[0] = ap;
fraction[1] = fp;
denominator = ap + fp;
out:
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
unsigned long lruvec_size;
unsigned long low, min;
unsigned long scan;
lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
mem_cgroup_protection(sc->target_mem_cgroup, memcg,
&min, &low);
if (min || low) {
/*
* Scale a cgroup's reclaim pressure by proportioning
* its current usage to its memory.low or memory.min
* setting.
*
* This is important, as otherwise scanning aggression
* becomes extremely binary -- from nothing as we
* approach the memory protection threshold, to totally
* nominal as we exceed it. This results in requiring
* setting extremely liberal protection thresholds. It
* also means we simply get no protection at all if we
* set it too low, which is not ideal.
*
* If there is any protection in place, we reduce scan
* pressure by how much of the total memory used is
* within protection thresholds.
*
* There is one special case: in the first reclaim pass,
* we skip over all groups that are within their low
* protection. If that fails to reclaim enough pages to
* satisfy the reclaim goal, we come back and override
* the best-effort low protection. However, we still
* ideally want to honor how well-behaved groups are in
* that case instead of simply punishing them all
* equally. As such, we reclaim them based on how much
* memory they are using, reducing the scan pressure
* again by how much of the total memory used is under
* hard protection.
*/
unsigned long cgroup_size = mem_cgroup_size(memcg);
unsigned long protection;
/* memory.low scaling, make sure we retry before OOM */
if (!sc->memcg_low_reclaim && low > min) {
protection = low;
sc->memcg_low_skipped = 1;
} else {
protection = min;
}
/* Avoid TOCTOU with earlier protection check */
cgroup_size = max(cgroup_size, protection);
scan = lruvec_size - lruvec_size * protection /
(cgroup_size + 1);
/*
* Minimally target SWAP_CLUSTER_MAX pages to keep
* reclaim moving forwards, avoiding decrementing
* sc->priority further than desirable.
*/
scan = max(scan, SWAP_CLUSTER_MAX);
} else {
scan = lruvec_size;
}
scan >>= sc->priority;
/*
* If the cgroup's already been deleted, make sure to
* scrape out the remaining cache.
*/
if (!scan && !mem_cgroup_online(memcg))
scan = min(lruvec_size, SWAP_CLUSTER_MAX);
switch (scan_balance) {
case SCAN_EQUAL:
/* Scan lists relative to size */
break;
case SCAN_FRACT:
/*
* Scan types proportional to swappiness and
* their relative recent reclaim efficiency.
* Make sure we don't miss the last page on
* the offlined memory cgroups because of a
* round-off error.
*/
scan = mem_cgroup_online(memcg) ?
div64_u64(scan * fraction[file], denominator) :
DIV64_U64_ROUND_UP(scan * fraction[file],
denominator);
break;
case SCAN_FILE:
case SCAN_ANON:
/* Scan one type exclusively */
if ((scan_balance == SCAN_FILE) != file)
scan = 0;
break;
default:
/* Look ma, no brain */
BUG();
}
nr[lru] = scan;
}
}
/*
* Anonymous LRU management is a waste if there is
* ultimately no way to reclaim the memory.
*/
static bool can_age_anon_pages(struct pglist_data *pgdat,
struct scan_control *sc)
{
/* Aging the anon LRU is valuable if swap is present: */
if (total_swap_pages > 0)
return true;
/* Also valuable if anon pages can be demoted: */
return can_demote(pgdat->node_id, sc);
}
#ifdef CONFIG_LRU_GEN
#ifdef CONFIG_LRU_GEN_ENABLED
DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS);
#define get_cap(cap) static_branch_likely(&lru_gen_caps[cap])
#else
DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
#define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap])
#endif
/******************************************************************************
* shorthand helpers
******************************************************************************/
#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset))
#define DEFINE_MAX_SEQ(lruvec) \
unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq)
#define DEFINE_MIN_SEQ(lruvec) \
unsigned long min_seq[ANON_AND_FILE] = { \
READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \
READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \
}
#define for_each_gen_type_zone(gen, type, zone) \
for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \
for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
#define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS)
#define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS)
static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
{
struct pglist_data *pgdat = NODE_DATA(nid);
#ifdef CONFIG_MEMCG
if (memcg) {
struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
/* see the comment in mem_cgroup_lruvec() */
if (!lruvec->pgdat)
lruvec->pgdat = pgdat;
return lruvec;
}
#endif
VM_WARN_ON_ONCE(!mem_cgroup_disabled());
return &pgdat->__lruvec;
}
static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
{
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
if (!sc->may_swap)
return 0;
if (!can_demote(pgdat->node_id, sc) &&
mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
return 0;
return mem_cgroup_swappiness(memcg);
}
static int get_nr_gens(struct lruvec *lruvec, int type)
{
return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1;
}
static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
{
/* see the comment on lru_gen_folio */
return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
}
/******************************************************************************
* Bloom filters
******************************************************************************/
/*
* Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when
* n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of
* bits in a bitmap, k is the number of hash functions and n is the number of
* inserted items.
*
* Page table walkers use one of the two filters to reduce their search space.
* To get rid of non-leaf entries that no longer have enough leaf entries, the
* aging uses the double-buffering technique to flip to the other filter each
* time it produces a new generation. For non-leaf entries that have enough
* leaf entries, the aging carries them over to the next generation in
* walk_pmd_range(); the eviction also report them when walking the rmap
* in lru_gen_look_around().
*
* For future optimizations:
* 1. It's not necessary to keep both filters all the time. The spare one can be
* freed after the RCU grace period and reallocated if needed again.
* 2. And when reallocating, it's worth scaling its size according to the number
* of inserted entries in the other filter, to reduce the memory overhead on
* small systems and false positives on large systems.
* 3. Jenkins' hash function is an alternative to Knuth's.
*/
#define BLOOM_FILTER_SHIFT 15
static inline int filter_gen_from_seq(unsigned long seq)
{
return seq % NR_BLOOM_FILTERS;
}
static void get_item_key(void *item, int *key)
{
u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2);
BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32));
key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1);
key[1] = hash >> BLOOM_FILTER_SHIFT;
}
static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
{
int key[2];
unsigned long *filter;
int gen = filter_gen_from_seq(seq);
filter = READ_ONCE(lruvec->mm_state.filters[gen]);
if (!filter)
return true;
get_item_key(item, key);
return test_bit(key[0], filter) && test_bit(key[1], filter);
}
static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
{
int key[2];
unsigned long *filter;
int gen = filter_gen_from_seq(seq);
filter = READ_ONCE(lruvec->mm_state.filters[gen]);
if (!filter)
return;
get_item_key(item, key);
if (!test_bit(key[0], filter))
set_bit(key[0], filter);
if (!test_bit(key[1], filter))
set_bit(key[1], filter);
}
static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
{
unsigned long *filter;
int gen = filter_gen_from_seq(seq);
filter = lruvec->mm_state.filters[gen];
if (filter) {
bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
return;
}
filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT),
__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
WRITE_ONCE(lruvec->mm_state.filters[gen], filter);
}
/******************************************************************************
* mm_struct list
******************************************************************************/
static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
{
static struct lru_gen_mm_list mm_list = {
.fifo = LIST_HEAD_INIT(mm_list.fifo),
.lock = __SPIN_LOCK_UNLOCKED(mm_list.lock),
};
#ifdef CONFIG_MEMCG
if (memcg)
return &memcg->mm_list;
#endif
VM_WARN_ON_ONCE(!mem_cgroup_disabled());
return &mm_list;
}
void lru_gen_add_mm(struct mm_struct *mm)
{
int nid;
struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list));
#ifdef CONFIG_MEMCG
VM_WARN_ON_ONCE(mm->lru_gen.memcg);
mm->lru_gen.memcg = memcg;
#endif
spin_lock(&mm_list->lock);
for_each_node_state(nid, N_MEMORY) {
struct lruvec *lruvec = get_lruvec(memcg, nid);
/* the first addition since the last iteration */
if (lruvec->mm_state.tail == &mm_list->fifo)
lruvec->mm_state.tail = &mm->lru_gen.list;
}
list_add_tail(&mm->lru_gen.list, &mm_list->fifo);
spin_unlock(&mm_list->lock);
}
void lru_gen_del_mm(struct mm_struct *mm)
{
int nid;
struct lru_gen_mm_list *mm_list;
struct mem_cgroup *memcg = NULL;
if (list_empty(&mm->lru_gen.list))
return;
#ifdef CONFIG_MEMCG
memcg = mm->lru_gen.memcg;
#endif
mm_list = get_mm_list(memcg);
spin_lock(&mm_list->lock);
for_each_node(nid) {
struct lruvec *lruvec = get_lruvec(memcg, nid);
/* where the current iteration continues after */
if (lruvec->mm_state.head == &mm->lru_gen.list)
lruvec->mm_state.head = lruvec->mm_state.head->prev;
/* where the last iteration ended before */
if (lruvec->mm_state.tail == &mm->lru_gen.list)
lruvec->mm_state.tail = lruvec->mm_state.tail->next;
}
list_del_init(&mm->lru_gen.list);
spin_unlock(&mm_list->lock);
#ifdef CONFIG_MEMCG
mem_cgroup_put(mm->lru_gen.memcg);
mm->lru_gen.memcg = NULL;
#endif
}
#ifdef CONFIG_MEMCG
void lru_gen_migrate_mm(struct mm_struct *mm)
{
struct mem_cgroup *memcg;
struct task_struct *task = rcu_dereference_protected(mm->owner, true);
VM_WARN_ON_ONCE(task->mm != mm);
lockdep_assert_held(&task->alloc_lock);
/* for mm_update_next_owner() */
if (mem_cgroup_disabled())
return;
/* migration can happen before addition */
if (!mm->lru_gen.memcg)
return;
rcu_read_lock();
memcg = mem_cgroup_from_task(task);
rcu_read_unlock();
if (memcg == mm->lru_gen.memcg)
return;
VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));
lru_gen_del_mm(mm);
lru_gen_add_mm(mm);
}
#endif
static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last)
{
int i;
int hist;
lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
if (walk) {
hist = lru_hist_from_seq(walk->max_seq);
for (i = 0; i < NR_MM_STATS; i++) {
WRITE_ONCE(lruvec->mm_state.stats[hist][i],
lruvec->mm_state.stats[hist][i] + walk->mm_stats[i]);
walk->mm_stats[i] = 0;
}
}
if (NR_HIST_GENS > 1 && last) {
hist = lru_hist_from_seq(lruvec->mm_state.seq + 1);
for (i = 0; i < NR_MM_STATS; i++)
WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0);
}
}
static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk)
{
int type;
unsigned long size = 0;
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
return true;
clear_bit(key, &mm->lru_gen.bitmap);
for (type = !walk->can_swap; type < ANON_AND_FILE; type++) {
size += type ? get_mm_counter(mm, MM_FILEPAGES) :
get_mm_counter(mm, MM_ANONPAGES) +
get_mm_counter(mm, MM_SHMEMPAGES);
}
if (size < MIN_LRU_BATCH)
return true;
return !mmget_not_zero(mm);
}
static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
struct mm_struct **iter)
{
bool first = false;
bool last = false;
struct mm_struct *mm = NULL;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
/*
* mm_state->seq is incremented after each iteration of mm_list. There
* are three interesting cases for this page table walker:
* 1. It tries to start a new iteration with a stale max_seq: there is
* nothing left to do.
* 2. It started the next iteration: it needs to reset the Bloom filter
* so that a fresh set of PTE tables can be recorded.
* 3. It ended the current iteration: it needs to reset the mm stats
* counters and tell its caller to increment max_seq.
*/
spin_lock(&mm_list->lock);
VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq);
if (walk->max_seq <= mm_state->seq)
goto done;
if (!mm_state->head)
mm_state->head = &mm_list->fifo;
if (mm_state->head == &mm_list->fifo)
first = true;
do {
mm_state->head = mm_state->head->next;
if (mm_state->head == &mm_list->fifo) {
WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
last = true;
break;
}
/* force scan for those added after the last iteration */
if (!mm_state->tail || mm_state->tail == mm_state->head) {
mm_state->tail = mm_state->head->next;
walk->force_scan = true;
}
mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
if (should_skip_mm(mm, walk))
mm = NULL;
} while (!mm);
done:
if (*iter || last)
reset_mm_stats(lruvec, walk, last);
spin_unlock(&mm_list->lock);
if (mm && first)
reset_bloom_filter(lruvec, walk->max_seq + 1);
if (*iter)
mmput_async(*iter);
*iter = mm;
return last;
}
static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq)
{
bool success = false;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
spin_lock(&mm_list->lock);
VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq);
if (max_seq > mm_state->seq) {
mm_state->head = NULL;
mm_state->tail = NULL;
WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
reset_mm_stats(lruvec, NULL, true);
success = true;
}
spin_unlock(&mm_list->lock);
return success;
}
/******************************************************************************
* PID controller
******************************************************************************/
/*
* A feedback loop based on Proportional-Integral-Derivative (PID) controller.
*
* The P term is refaulted/(evicted+protected) from a tier in the generation
* currently being evicted; the I term is the exponential moving average of the
* P term over the generations previously evicted, using the smoothing factor
* 1/2; the D term isn't supported.
*
* The setpoint (SP) is always the first tier of one type; the process variable
* (PV) is either any tier of the other type or any other tier of the same
* type.
*
* The error is the difference between the SP and the PV; the correction is to
* turn off protection when SP>PV or turn on protection when SP<PV.
*
* For future optimizations:
* 1. The D term may discount the other two terms over time so that long-lived
* generations can resist stale information.
*/
struct ctrl_pos {
unsigned long refaulted;
unsigned long total;
int gain;
};
static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
struct ctrl_pos *pos)
{
struct lru_gen_folio *lrugen = &lruvec->lrugen;
int hist = lru_hist_from_seq(lrugen->min_seq[type]);
pos->refaulted = lrugen->avg_refaulted[type][tier] +
atomic_long_read(&lrugen->refaulted[hist][type][tier]);
pos->total = lrugen->avg_total[type][tier] +
atomic_long_read(&lrugen->evicted[hist][type][tier]);
if (tier)
pos->total += lrugen->protected[hist][type][tier - 1];
pos->gain = gain;
}
static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
{
int hist, tier;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1;
unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1;
lockdep_assert_held(&lruvec->lru_lock);
if (!carryover && !clear)
return;
hist = lru_hist_from_seq(seq);
for (tier = 0; tier < MAX_NR_TIERS; tier++) {
if (carryover) {
unsigned long sum;
sum = lrugen->avg_refaulted[type][tier] +
atomic_long_read(&lrugen->refaulted[hist][type][tier]);
WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);
sum = lrugen->avg_total[type][tier] +
atomic_long_read(&lrugen->evicted[hist][type][tier]);
if (tier)
sum += lrugen->protected[hist][type][tier - 1];
WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
}
if (clear) {
atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
if (tier)
WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
}
}
}
static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
{
/*
* Return true if the PV has a limited number of refaults or a lower
* refaulted/total than the SP.
*/
return pv->refaulted < MIN_LRU_BATCH ||
pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <=
(sp->refaulted + 1) * pv->total * pv->gain;
}
/******************************************************************************
* the aging
******************************************************************************/
/* promote pages accessed through page tables */
static int folio_update_gen(struct folio *folio, int gen)
{
unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
VM_WARN_ON_ONCE(!rcu_read_lock_held());
do {
/* lru_gen_del_folio() has isolated this page? */
if (!(old_flags & LRU_GEN_MASK)) {
/* for shrink_folio_list() */
new_flags = old_flags | BIT(PG_referenced);
continue;
}
new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
}
/* protect pages accessed multiple times through file descriptors */
static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
int type = folio_is_file_lru(folio);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio);
do {
new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
/* folio_update_gen() has promoted this page? */
if (new_gen >= 0 && new_gen != old_gen)
return new_gen;
new_gen = (old_gen + 1) % MAX_NR_GENS;
new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
/* for folio_end_writeback() */
if (reclaiming)
new_flags |= BIT(PG_reclaim);
} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
lru_gen_update_size(lruvec, folio, old_gen, new_gen);
return new_gen;
}
static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio,
int old_gen, int new_gen)
{
int type = folio_is_file_lru(folio);
int zone = folio_zonenum(folio);
int delta = folio_nr_pages(folio);
VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS);
VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS);
walk->batched++;
walk->nr_pages[old_gen][type][zone] -= delta;
walk->nr_pages[new_gen][type][zone] += delta;
}
static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk)
{
int gen, type, zone;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
walk->batched = 0;
for_each_gen_type_zone(gen, type, zone) {
enum lru_list lru = type * LRU_INACTIVE_FILE;
int delta = walk->nr_pages[gen][type][zone];
if (!delta)
continue;
walk->nr_pages[gen][type][zone] = 0;
WRITE_ONCE(lrugen->nr_pages[gen][type][zone],
lrugen->nr_pages[gen][type][zone] + delta);
if (lru_gen_is_active(lruvec, gen))
lru += LRU_ACTIVE;
__update_lru_size(lruvec, lru, zone, delta);
}
}
static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args)
{
struct address_space *mapping;
struct vm_area_struct *vma = args->vma;
struct lru_gen_mm_walk *walk = args->private;
if (!vma_is_accessible(vma))
return true;
if (is_vm_hugetlb_page(vma))
return true;
if (!vma_has_recency(vma))
return true;
if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL))
return true;
if (vma == get_gate_vma(vma->vm_mm))
return true;
if (vma_is_anonymous(vma))
return !walk->can_swap;
if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
return true;
mapping = vma->vm_file->f_mapping;
if (mapping_unevictable(mapping))
return true;
if (shmem_mapping(mapping))
return !walk->can_swap;
/* to exclude special mappings like dax, etc. */
return !mapping->a_ops->read_folio;
}
/*
* Some userspace memory allocators map many single-page VMAs. Instead of
* returning back to the PGD table for each of such VMAs, finish an entire PMD
* table to reduce zigzags and improve cache performance.
*/
static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args,
unsigned long *vm_start, unsigned long *vm_end)
{
unsigned long start = round_up(*vm_end, size);
unsigned long end = (start | ~mask) + 1;
VMA_ITERATOR(vmi, args->mm, start);
VM_WARN_ON_ONCE(mask & size);
VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask));
for_each_vma(vmi, args->vma) {
if (end && end <= args->vma->vm_start)
return false;
if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args))
continue;
*vm_start = max(start, args->vma->vm_start);
*vm_end = min(end - 1, args->vma->vm_end - 1) + 1;
return true;
}
return false;
}
static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
{
unsigned long pfn = pte_pfn(pte);
VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end);
if (!pte_present(pte) || is_zero_pfn(pfn))
return -1;
if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
return -1;
if (WARN_ON_ONCE(!pfn_valid(pfn)))
return -1;
return pfn;
}
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
{
unsigned long pfn = pmd_pfn(pmd);
VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end);
if (!pmd_present(pmd) || is_huge_zero_pmd(pmd))
return -1;
if (WARN_ON_ONCE(pmd_devmap(pmd)))
return -1;
if (WARN_ON_ONCE(!pfn_valid(pfn)))
return -1;
return pfn;
}
#endif
static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
struct pglist_data *pgdat, bool can_swap)
{
struct folio *folio;
/* try to avoid unnecessary memory loads */
if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
return NULL;
folio = pfn_folio(pfn);
if (folio_nid(folio) != pgdat->node_id)
return NULL;
if (folio_memcg_rcu(folio) != memcg)
return NULL;
/* file VMAs can contain anon pages from COW */
if (!folio_is_file_lru(folio) && !can_swap)
return NULL;
return folio;
}
static bool suitable_to_scan(int total, int young)
{
int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8);
/* suitable if the average number of young PTEs per cacheline is >=1 */
return young * n >= total;
}
static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
struct mm_walk *args)
{
int i;
pte_t *pte;
spinlock_t *ptl;
unsigned long addr;
int total = 0;
int young = 0;
struct lru_gen_mm_walk *walk = args->private;
struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
int old_gen, new_gen = lru_gen_from_seq(walk->max_seq);
VM_WARN_ON_ONCE(pmd_leaf(*pmd));
ptl = pte_lockptr(args->mm, pmd);
if (!spin_trylock(ptl))
return false;
arch_enter_lazy_mmu_mode();
pte = pte_offset_map(pmd, start & PMD_MASK);
restart:
for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) {
unsigned long pfn;
struct folio *folio;
total++;
walk->mm_stats[MM_LEAF_TOTAL]++;
pfn = get_pte_pfn(pte[i], args->vma, addr);
if (pfn == -1)
continue;
if (!pte_young(pte[i])) {
walk->mm_stats[MM_LEAF_OLD]++;
continue;
}
folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
if (!folio)
continue;
if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
VM_WARN_ON_ONCE(true);
young++;
walk->mm_stats[MM_LEAF_YOUNG]++;
if (pte_dirty(pte[i]) && !folio_test_dirty(folio) &&
!(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
!folio_test_swapcache(folio)))
folio_mark_dirty(folio);
old_gen = folio_update_gen(folio, new_gen);
if (old_gen >= 0 && old_gen != new_gen)
update_batch_size(walk, folio, old_gen, new_gen);
}
if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end))
goto restart;
pte_unmap(pte);
arch_leave_lazy_mmu_mode();
spin_unlock(ptl);
return suitable_to_scan(total, young);
}
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma,
struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
{
int i;
pmd_t *pmd;
spinlock_t *ptl;
struct lru_gen_mm_walk *walk = args->private;
struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
int old_gen, new_gen = lru_gen_from_seq(walk->max_seq);
VM_WARN_ON_ONCE(pud_leaf(*pud));
/* try to batch at most 1+MIN_LRU_BATCH+1 entries */
if (*first == -1) {
*first = addr;
bitmap_zero(bitmap, MIN_LRU_BATCH);
return;
}
i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first);
if (i && i <= MIN_LRU_BATCH) {
__set_bit(i - 1, bitmap);
return;
}
pmd = pmd_offset(pud, *first);
ptl = pmd_lockptr(args->mm, pmd);
if (!spin_trylock(ptl))
goto done;
arch_enter_lazy_mmu_mode();
do {
unsigned long pfn;
struct folio *folio;
/* don't round down the first address */
addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
pfn = get_pmd_pfn(pmd[i], vma, addr);
if (pfn == -1)
goto next;
if (!pmd_trans_huge(pmd[i])) {
if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
pmdp_test_and_clear_young(vma, addr, pmd + i);
goto next;
}
folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
if (!folio)
goto next;
if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
goto next;
walk->mm_stats[MM_LEAF_YOUNG]++;
if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) &&
!(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
!folio_test_swapcache(folio)))
folio_mark_dirty(folio);
old_gen = folio_update_gen(folio, new_gen);
if (old_gen >= 0 && old_gen != new_gen)
update_batch_size(walk, folio, old_gen, new_gen);
next:
i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1;
} while (i <= MIN_LRU_BATCH);
arch_leave_lazy_mmu_mode();
spin_unlock(ptl);
done:
*first = -1;
}
#else
static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma,
struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
{
}
#endif
static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
struct mm_walk *args)
{
int i;
pmd_t *pmd;
unsigned long next;
unsigned long addr;
struct vm_area_struct *vma;
unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)];
unsigned long first = -1;
struct lru_gen_mm_walk *walk = args->private;
VM_WARN_ON_ONCE(pud_leaf(*pud));
/*
* Finish an entire PMD in two passes: the first only reaches to PTE
* tables to avoid taking the PMD lock; the second, if necessary, takes
* the PMD lock to clear the accessed bit in PMD entries.
*/
pmd = pmd_offset(pud, start & PUD_MASK);
restart:
/* walk_pte_range() may call get_next_vma() */
vma = args->vma;
for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) {
pmd_t val = pmdp_get_lockless(pmd + i);
next = pmd_addr_end(addr, end);
if (!pmd_present(val) || is_huge_zero_pmd(val)) {
walk->mm_stats[MM_LEAF_TOTAL]++;
continue;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (pmd_trans_huge(val)) {
unsigned long pfn = pmd_pfn(val);
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
walk->mm_stats[MM_LEAF_TOTAL]++;
if (!pmd_young(val)) {
walk->mm_stats[MM_LEAF_OLD]++;
continue;
}
/* try to avoid unnecessary memory loads */
if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
continue;
walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
continue;
}
#endif
walk->mm_stats[MM_NONLEAF_TOTAL]++;
if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) {
if (!pmd_young(val))
continue;
walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
}
if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
continue;
walk->mm_stats[MM_NONLEAF_FOUND]++;
if (!walk_pte_range(&val, addr, next, args))
continue;
walk->mm_stats[MM_NONLEAF_ADDED]++;
/* carry over to the next generation */
update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i);
}
walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first);
if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end))
goto restart;
}
static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end,
struct mm_walk *args)
{
int i;
pud_t *pud;
unsigned long addr;
unsigned long next;
struct lru_gen_mm_walk *walk = args->private;
VM_WARN_ON_ONCE(p4d_leaf(*p4d));
pud = pud_offset(p4d, start & P4D_MASK);
restart:
for (i = pud_index(start), addr = start; addr != end; i++, addr = next) {
pud_t val = READ_ONCE(pud[i]);
next = pud_addr_end(addr, end);
if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val)))
continue;
walk_pmd_range(&val, addr, next, args);
if (need_resched() || walk->batched >= MAX_LRU_BATCH) {
end = (addr | ~PUD_MASK) + 1;
goto done;
}
}
if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end))
goto restart;
end = round_up(end, P4D_SIZE);
done:
if (!end || !args->vma)
return 1;
walk->next_addr = max(end, args->vma->vm_start);
return -EAGAIN;
}
static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_mm_walk *walk)
{
static const struct mm_walk_ops mm_walk_ops = {
.test_walk = should_skip_vma,
.p4d_entry = walk_pud_range,
};
int err;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
walk->next_addr = FIRST_USER_ADDRESS;
do {
DEFINE_MAX_SEQ(lruvec);
err = -EBUSY;
/* another thread might have called inc_max_seq() */
if (walk->max_seq != max_seq)
break;
/* folio_update_gen() requires stable folio_memcg() */
if (!mem_cgroup_trylock_pages(memcg))
break;
/* the caller might be holding the lock for write */
if (mmap_read_trylock(mm)) {
err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk);
mmap_read_unlock(mm);
}
mem_cgroup_unlock_pages();
if (walk->batched) {
spin_lock_irq(&lruvec->lru_lock);
reset_batch_size(lruvec, walk);
spin_unlock_irq(&lruvec->lru_lock);
}
cond_resched();
} while (err == -EAGAIN);
}
static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc)
{
struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
if (pgdat && current_is_kswapd()) {
VM_WARN_ON_ONCE(walk);
walk = &pgdat->mm_walk;
} else if (!walk && force_alloc) {
VM_WARN_ON_ONCE(current_is_kswapd());
walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
}
current->reclaim_state->mm_walk = walk;
return walk;
}
static void clear_mm_walk(void)
{
struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages)));
VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats)));
current->reclaim_state->mm_walk = NULL;
if (!current_is_kswapd())
kfree(walk);
}
static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
{
int zone;
int remaining = MAX_LRU_BATCH;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
if (type == LRU_GEN_ANON && !can_swap)
goto done;
/* prevent cold/hot inversion if force_scan is true */
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
struct list_head *head = &lrugen->folios[old_gen][type][zone];
while (!list_empty(head)) {
struct folio *folio = lru_to_folio(head);
VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
new_gen = folio_inc_gen(lruvec, folio, false);
list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]);
if (!--remaining)
return false;
}
}
done:
reset_ctrl_pos(lruvec, type, true);
WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
return true;
}
static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
{
int gen, type, zone;
bool success = false;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
DEFINE_MIN_SEQ(lruvec);
VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
/* find the oldest populated generation */
for (type = !can_swap; type < ANON_AND_FILE; type++) {
while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) {
gen = lru_gen_from_seq(min_seq[type]);
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
if (!list_empty(&lrugen->folios[gen][type][zone]))
goto next;
}
min_seq[type]++;
}
next:
;
}
/* see the comment on lru_gen_folio */
if (can_swap) {
min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
}
for (type = !can_swap; type < ANON_AND_FILE; type++) {
if (min_seq[type] == lrugen->min_seq[type])
continue;
reset_ctrl_pos(lruvec, type, true);
WRITE_ONCE(lrugen->min_seq[type], min_seq[type]);
success = true;
}
return success;
}
static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
{
int prev, next;
int type, zone;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
spin_lock_irq(&lruvec->lru_lock);
VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
for (type = ANON_AND_FILE - 1; type >= 0; type--) {
if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
continue;
VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap));
while (!inc_min_seq(lruvec, type, can_swap)) {
spin_unlock_irq(&lruvec->lru_lock);
cond_resched();
spin_lock_irq(&lruvec->lru_lock);
}
}
/*
* Update the active/inactive LRU sizes for compatibility. Both sides of
* the current max_seq need to be covered, since max_seq+1 can overlap
* with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do
* overlap, cold/hot inversion happens.
*/
prev = lru_gen_from_seq(lrugen->max_seq - 1);
next = lru_gen_from_seq(lrugen->max_seq + 1);
for (type = 0; type < ANON_AND_FILE; type++) {
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
enum lru_list lru = type * LRU_INACTIVE_FILE;
long delta = lrugen->nr_pages[prev][type][zone] -
lrugen->nr_pages[next][type][zone];
if (!delta)
continue;
__update_lru_size(lruvec, lru, zone, delta);
__update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta);
}
}
for (type = 0; type < ANON_AND_FILE; type++)
reset_ctrl_pos(lruvec, type, false);
WRITE_ONCE(lrugen->timestamps[next], jiffies);
/* make sure preceding modifications appear */
smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
spin_unlock_irq(&lruvec->lru_lock);
}
static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
struct scan_control *sc, bool can_swap, bool force_scan)
{
bool success;
struct lru_gen_mm_walk *walk;
struct mm_struct *mm = NULL;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq));
/* see the comment in iterate_mm_list() */
if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) {
success = false;
goto done;
}
/*
* If the hardware doesn't automatically set the accessed bit, fallback
* to lru_gen_look_around(), which only clears the accessed bit in a
* handful of PTEs. Spreading the work out over a period of time usually
* is less efficient, but it avoids bursty page faults.
*/
if (!arch_has_hw_pte_young() || !get_cap(LRU_GEN_MM_WALK)) {
success = iterate_mm_list_nowalk(lruvec, max_seq);
goto done;
}
walk = set_mm_walk(NULL, true);
if (!walk) {
success = iterate_mm_list_nowalk(lruvec, max_seq);
goto done;
}
walk->lruvec = lruvec;
walk->max_seq = max_seq;
walk->can_swap = can_swap;
walk->force_scan = force_scan;
do {
success = iterate_mm_list(lruvec, walk, &mm);
if (mm)
walk_mm(lruvec, mm, walk);
} while (mm);
done:
if (success)
inc_max_seq(lruvec, can_swap, force_scan);
return success;
}
/******************************************************************************
* working set protection
******************************************************************************/
static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
{
int gen, type, zone;
unsigned long total = 0;
bool can_swap = get_swappiness(lruvec, sc);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MAX_SEQ(lruvec);
DEFINE_MIN_SEQ(lruvec);
for (type = !can_swap; type < ANON_AND_FILE; type++) {
unsigned long seq;
for (seq = min_seq[type]; seq <= max_seq; seq++) {
gen = lru_gen_from_seq(seq);
for (zone = 0; zone < MAX_NR_ZONES; zone++)
total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
}
}
/* whether the size is big enough to be helpful */
return mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
}
static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc,
unsigned long min_ttl)
{
int gen;
unsigned long birth;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MIN_SEQ(lruvec);
/* see the comment on lru_gen_folio */
gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
if (time_is_after_jiffies(birth + min_ttl))
return false;
if (!lruvec_is_sizable(lruvec, sc))
return false;
mem_cgroup_calculate_protection(NULL, memcg);
return !mem_cgroup_below_min(NULL, memcg);
}
/* to protect the working set of the last N jiffies */
static unsigned long lru_gen_min_ttl __read_mostly;
static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
{
struct mem_cgroup *memcg;
unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
VM_WARN_ON_ONCE(!current_is_kswapd());
/* check the order to exclude compaction-induced reclaim */
if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY)
return;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) {
mem_cgroup_iter_break(NULL, memcg);
return;
}
cond_resched();
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
/*
* The main goal is to OOM kill if every generation from all memcgs is
* younger than min_ttl. However, another possibility is all memcgs are
* either too small or below min.
*/
if (mutex_trylock(&oom_lock)) {
struct oom_control oc = {
.gfp_mask = sc->gfp_mask,
};
out_of_memory(&oc);
mutex_unlock(&oom_lock);
}
}
/******************************************************************************
* rmap/PT walk feedback
******************************************************************************/
/*
* This function exploits spatial locality when shrink_folio_list() walks the
* rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If
* the scan was done cacheline efficiently, it adds the PMD entry pointing to
* the PTE table to the Bloom filter. This forms a feedback loop between the
* eviction and the aging.
*/
void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
{
int i;
unsigned long start;
unsigned long end;
struct lru_gen_mm_walk *walk;
int young = 0;
pte_t *pte = pvmw->pte;
unsigned long addr = pvmw->address;
struct folio *folio = pfn_folio(pvmw->pfn);
struct mem_cgroup *memcg = folio_memcg(folio);
struct pglist_data *pgdat = folio_pgdat(folio);
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
DEFINE_MAX_SEQ(lruvec);
int old_gen, new_gen = lru_gen_from_seq(max_seq);
lockdep_assert_held(pvmw->ptl);
VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
if (spin_is_contended(pvmw->ptl))
return;
/* avoid taking the LRU lock under the PTL when possible */
walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
start = max(addr & PMD_MASK, pvmw->vma->vm_start);
end = min(addr | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
end = start + MIN_LRU_BATCH * PAGE_SIZE;
else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2)
start = end - MIN_LRU_BATCH * PAGE_SIZE;
else {
start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2;
end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2;
}
}
/* folio_update_gen() requires stable folio_memcg() */
if (!mem_cgroup_trylock_pages(memcg))
return;
arch_enter_lazy_mmu_mode();
pte -= (addr - start) / PAGE_SIZE;
for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) {
unsigned long pfn;
pfn = get_pte_pfn(pte[i], pvmw->vma, addr);
if (pfn == -1)
continue;
if (!pte_young(pte[i]))
continue;
folio = get_pfn_folio(pfn, memcg, pgdat, !walk || walk->can_swap);
if (!folio)
continue;
if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
VM_WARN_ON_ONCE(true);
young++;
if (pte_dirty(pte[i]) && !folio_test_dirty(folio) &&
!(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
!folio_test_swapcache(folio)))
folio_mark_dirty(folio);
if (walk) {
old_gen = folio_update_gen(folio, new_gen);
if (old_gen >= 0 && old_gen != new_gen)
update_batch_size(walk, folio, old_gen, new_gen);
continue;
}
old_gen = folio_lru_gen(folio);
if (old_gen < 0)
folio_set_referenced(folio);
else if (old_gen != new_gen)
folio_activate(folio);
}
arch_leave_lazy_mmu_mode();
mem_cgroup_unlock_pages();
/* feedback from rmap walkers to page table walkers */
if (suitable_to_scan(i, young))
update_bloom_filter(lruvec, max_seq, pvmw->pmd);
}
/******************************************************************************
* memcg LRU
******************************************************************************/
/* see the comment on MEMCG_NR_GENS */
enum {
MEMCG_LRU_NOP,
MEMCG_LRU_HEAD,
MEMCG_LRU_TAIL,
MEMCG_LRU_OLD,
MEMCG_LRU_YOUNG,
};
#ifdef CONFIG_MEMCG
static int lru_gen_memcg_seg(struct lruvec *lruvec)
{
return READ_ONCE(lruvec->lrugen.seg);
}
static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
{
int seg;
int old, new;
int bin = get_random_u32_below(MEMCG_NR_BINS);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
spin_lock(&pgdat->memcg_lru.lock);
VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
seg = 0;
new = old = lruvec->lrugen.gen;
/* see the comment on MEMCG_NR_GENS */
if (op == MEMCG_LRU_HEAD)
seg = MEMCG_LRU_HEAD;
else if (op == MEMCG_LRU_TAIL)
seg = MEMCG_LRU_TAIL;
else if (op == MEMCG_LRU_OLD)
new = get_memcg_gen(pgdat->memcg_lru.seq);
else if (op == MEMCG_LRU_YOUNG)
new = get_memcg_gen(pgdat->memcg_lru.seq + 1);
else
VM_WARN_ON_ONCE(true);
hlist_nulls_del_rcu(&lruvec->lrugen.list);
if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]);
else
hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]);
pgdat->memcg_lru.nr_memcgs[old]--;
pgdat->memcg_lru.nr_memcgs[new]++;
lruvec->lrugen.gen = new;
WRITE_ONCE(lruvec->lrugen.seg, seg);
if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
spin_unlock(&pgdat->memcg_lru.lock);
}
void lru_gen_online_memcg(struct mem_cgroup *memcg)
{
int gen;
int nid;
int bin = get_random_u32_below(MEMCG_NR_BINS);
for_each_node(nid) {
struct pglist_data *pgdat = NODE_DATA(nid);
struct lruvec *lruvec = get_lruvec(memcg, nid);
spin_lock(&pgdat->memcg_lru.lock);
VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list));
gen = get_memcg_gen(pgdat->memcg_lru.seq);
hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
pgdat->memcg_lru.nr_memcgs[gen]++;
lruvec->lrugen.gen = gen;
spin_unlock(&pgdat->memcg_lru.lock);
}
}
void lru_gen_offline_memcg(struct mem_cgroup *memcg)
{
int nid;
for_each_node(nid) {
struct lruvec *lruvec = get_lruvec(memcg, nid);
lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD);
}
}
void lru_gen_release_memcg(struct mem_cgroup *memcg)
{
int gen;
int nid;
for_each_node(nid) {
struct pglist_data *pgdat = NODE_DATA(nid);
struct lruvec *lruvec = get_lruvec(memcg, nid);
spin_lock(&pgdat->memcg_lru.lock);
VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
gen = lruvec->lrugen.gen;
hlist_nulls_del_rcu(&lruvec->lrugen.list);
pgdat->memcg_lru.nr_memcgs[gen]--;
if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq))
WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
spin_unlock(&pgdat->memcg_lru.lock);
}
}
void lru_gen_soft_reclaim(struct lruvec *lruvec)
{
/* see the comment on MEMCG_NR_GENS */
if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD)
lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD);
}
#else /* !CONFIG_MEMCG */
static int lru_gen_memcg_seg(struct lruvec *lruvec)
{
return 0;
}
#endif
/******************************************************************************
* the eviction
******************************************************************************/
static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx)
{
bool success;
int gen = folio_lru_gen(folio);
int type = folio_is_file_lru(folio);
int zone = folio_zonenum(folio);
int delta = folio_nr_pages(folio);
int refs = folio_lru_refs(folio);
int tier = lru_tier_from_refs(refs);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
/* unevictable */
if (!folio_evictable(folio)) {
success = lru_gen_del_folio(lruvec, folio, true);
VM_WARN_ON_ONCE_FOLIO(!success, folio);
folio_set_unevictable(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGCULLED, delta);
return true;
}
/* dirty lazyfree */
if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
success = lru_gen_del_folio(lruvec, folio, true);
VM_WARN_ON_ONCE_FOLIO(!success, folio);
folio_set_swapbacked(folio);
lruvec_add_folio_tail(lruvec, folio);
return true;
}
/* promoted */
if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;
}
/* protected */
if (tier > tier_idx) {
int hist = lru_hist_from_seq(lrugen->min_seq[type]);
gen = folio_inc_gen(lruvec, folio, false);
list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
lrugen->protected[hist][type][tier - 1] + delta);
__mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
return true;
}
/* waiting for writeback */
if (folio_test_locked(folio) || folio_test_writeback(folio) ||
(type == LRU_GEN_FILE && folio_test_dirty(folio))) {
gen = folio_inc_gen(lruvec, folio, true);
list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;
}
return false;
}
static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc)
{
bool success;
/* swapping inhibited */
if (!(sc->gfp_mask & __GFP_IO) &&
(folio_test_dirty(folio) ||
(folio_test_anon(folio) && !folio_test_swapcache(folio))))
return false;
/* raced with release_pages() */
if (!folio_try_get(folio))
return false;
/* raced with another isolation */
if (!folio_test_clear_lru(folio)) {
folio_put(folio);
return false;
}
/* see the comment on MAX_NR_TIERS */
if (!folio_test_referenced(folio))
set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
/* for shrink_folio_list() */
folio_clear_reclaim(folio);
folio_clear_referenced(folio);
success = lru_gen_del_folio(lruvec, folio, true);
VM_WARN_ON_ONCE_FOLIO(!success, folio);
return true;
}
static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
int type, int tier, struct list_head *list)
{
int gen, zone;
enum vm_event_item item;
int sorted = 0;
int scanned = 0;
int isolated = 0;
int remaining = MAX_LRU_BATCH;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
VM_WARN_ON_ONCE(!list_empty(list));
if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
return 0;
gen = lru_gen_from_seq(lrugen->min_seq[type]);
for (zone = sc->reclaim_idx; zone >= 0; zone--) {
LIST_HEAD(moved);
int skipped = 0;
struct list_head *head = &lrugen->folios[gen][type][zone];
while (!list_empty(head)) {
struct folio *folio = lru_to_folio(head);
int delta = folio_nr_pages(folio);
VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
scanned += delta;
if (sort_folio(lruvec, folio, tier))
sorted += delta;
else if (isolate_folio(lruvec, folio, sc)) {
list_add(&folio->lru, list);
isolated += delta;
} else {
list_move(&folio->lru, &moved);
skipped += delta;
}
if (!--remaining || max(isolated, skipped) >= MIN_LRU_BATCH)
break;
}
if (skipped) {
list_splice(&moved, head);
__count_zid_vm_events(PGSCAN_SKIP, zone, skipped);
}
if (!remaining || isolated >= MIN_LRU_BATCH)
break;
}
item = PGSCAN_KSWAPD + reclaimer_offset();
if (!cgroup_reclaim(sc)) {
__count_vm_events(item, isolated);
__count_vm_events(PGREFILL, sorted);
}
__count_memcg_events(memcg, item, isolated);
__count_memcg_events(memcg, PGREFILL, sorted);
__count_vm_events(PGSCAN_ANON + type, isolated);
/*
* There might not be eligible folios due to reclaim_idx. Check the
* remaining to prevent livelock if it's not making progress.
*/
return isolated || !remaining ? scanned : 0;
}
static int get_tier_idx(struct lruvec *lruvec, int type)
{
int tier;
struct ctrl_pos sp, pv;
/*
* To leave a margin for fluctuations, use a larger gain factor (1:2).
* This value is chosen because any other tier would have at least twice
* as many refaults as the first tier.
*/
read_ctrl_pos(lruvec, type, 0, 1, &sp);
for (tier = 1; tier < MAX_NR_TIERS; tier++) {
read_ctrl_pos(lruvec, type, tier, 2, &pv);
if (!positive_ctrl_err(&sp, &pv))
break;
}
return tier - 1;
}
static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
{
int type, tier;
struct ctrl_pos sp, pv;
int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness };
/*
* Compare the first tier of anon with that of file to determine which
* type to scan. Also need to compare other tiers of the selected type
* with the first tier of the other type to determine the last tier (of
* the selected type) to evict.
*/
read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp);
read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv);
type = positive_ctrl_err(&sp, &pv);
read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
for (tier = 1; tier < MAX_NR_TIERS; tier++) {
read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
if (!positive_ctrl_err(&sp, &pv))
break;
}
*tier_idx = tier - 1;
return type;
}
static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
int *type_scanned, struct list_head *list)
{
int i;
int type;
int scanned;
int tier = -1;
DEFINE_MIN_SEQ(lruvec);
/*
* Try to make the obvious choice first. When anon and file are both
* available from the same generation, interpret swappiness 1 as file
* first and 200 as anon first.
*/
if (!swappiness)
type = LRU_GEN_FILE;
else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE])
type = LRU_GEN_ANON;
else if (swappiness == 1)
type = LRU_GEN_FILE;
else if (swappiness == 200)
type = LRU_GEN_ANON;
else
type = get_type_to_scan(lruvec, swappiness, &tier);
for (i = !swappiness; i < ANON_AND_FILE; i++) {
if (tier < 0)
tier = get_tier_idx(lruvec, type);
scanned = scan_folios(lruvec, sc, type, tier, list);
if (scanned)
break;
type = !type;
tier = -1;
}
*type_scanned = type;
return scanned;
}
static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
{
int type;
int scanned;
int reclaimed;
LIST_HEAD(list);
LIST_HEAD(clean);
struct folio *folio;
struct folio *next;
enum vm_event_item item;
struct reclaim_stat stat;
struct lru_gen_mm_walk *walk;
bool skip_retry = false;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
spin_lock_irq(&lruvec->lru_lock);
scanned = isolate_folios(lruvec, sc, swappiness, &type, &list);
scanned += try_to_inc_min_seq(lruvec, swappiness);
if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
scanned = 0;
spin_unlock_irq(&lruvec->lru_lock);
if (list_empty(&list))
return scanned;
retry:
reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
sc->nr_reclaimed += reclaimed;
list_for_each_entry_safe_reverse(folio, next, &list, lru) {
if (!folio_evictable(folio)) {
list_del(&folio->lru);
folio_putback_lru(folio);
continue;
}
if (folio_test_reclaim(folio) &&
(folio_test_dirty(folio) || folio_test_writeback(folio))) {
/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
if (folio_test_workingset(folio))
folio_set_referenced(folio);
continue;
}
if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) ||
folio_mapped(folio) || folio_test_locked(folio) ||
folio_test_dirty(folio) || folio_test_writeback(folio)) {
/* don't add rejected folios to the oldest generation */
set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
BIT(PG_active));
continue;
}
/* retry folios that may have missed folio_rotate_reclaimable() */
list_move(&folio->lru, &clean);
sc->nr_scanned -= folio_nr_pages(folio);
}
spin_lock_irq(&lruvec->lru_lock);
move_folios_to_lru(lruvec, &list);
walk = current->reclaim_state->mm_walk;
if (walk && walk->batched)
reset_batch_size(lruvec, walk);
item = PGSTEAL_KSWAPD + reclaimer_offset();
if (!cgroup_reclaim(sc))
__count_vm_events(item, reclaimed);
__count_memcg_events(memcg, item, reclaimed);
__count_vm_events(PGSTEAL_ANON + type, reclaimed);
spin_unlock_irq(&lruvec->lru_lock);
mem_cgroup_uncharge_list(&list);
free_unref_page_list(&list);
INIT_LIST_HEAD(&list);
list_splice_init(&clean, &list);
if (!list_empty(&list)) {
skip_retry = true;
goto retry;
}
return scanned;
}
static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
{
int gen, type, zone;
unsigned long old = 0;
unsigned long young = 0;
unsigned long total = 0;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MIN_SEQ(lruvec);
/* whether this lruvec is completely out of cold folios */
if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
*nr_to_scan = 0;
return true;
}
for (type = !can_swap; type < ANON_AND_FILE; type++) {
unsigned long seq;
for (seq = min_seq[type]; seq <= max_seq; seq++) {
unsigned long size = 0;
gen = lru_gen_from_seq(seq);
for (zone = 0; zone < MAX_NR_ZONES; zone++)
size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
total += size;
if (seq == max_seq)
young += size;
else if (seq + MIN_NR_GENS == max_seq)
old += size;
}
}
/* try to scrape all its memory if this memcg was deleted */
*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
/*
* The aging tries to be lazy to reduce the overhead, while the eviction
* stalls when the number of generations reaches MIN_NR_GENS. Hence, the
* ideal number of generations is MIN_NR_GENS+1.
*/
if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
return false;
/*
* It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
* of the total number of pages for each generation. A reasonable range
* for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
* aging cares about the upper bound of hot pages, while the eviction
* cares about the lower bound of cold pages.
*/
if (young * MIN_NR_GENS > total)
return true;
if (old * (MIN_NR_GENS + 2) < total)
return true;
return false;
}
/*
* For future optimizations:
* 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
* reclaim.
*/
static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap)
{
unsigned long nr_to_scan;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MAX_SEQ(lruvec);
if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
return 0;
if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
return nr_to_scan;
/* skip the aging path at the default priority */
if (sc->priority == DEF_PRIORITY)
return nr_to_scan;
/* skip this lruvec as it's low on cold folios */
return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
}
static unsigned long get_nr_to_reclaim(struct scan_control *sc)
{
/* don't abort memcg reclaim to ensure fairness */
if (!global_reclaim(sc))
return -1;
return max(sc->nr_to_reclaim, compact_gap(sc->order));
}
static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
long nr_to_scan;
unsigned long scanned = 0;
unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
int swappiness = get_swappiness(lruvec, sc);
/* clean file folios are more likely to exist */
if (swappiness && !(sc->gfp_mask & __GFP_IO))
swappiness = 1;
while (true) {
int delta;
nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
if (nr_to_scan <= 0)
break;
delta = evict_folios(lruvec, sc, swappiness);
if (!delta)
break;
scanned += delta;
if (scanned >= nr_to_scan)
break;
if (sc->nr_reclaimed >= nr_to_reclaim)
break;
cond_resched();
}
/* whether try_to_inc_max_seq() was successful */
return nr_to_scan < 0;
}
static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
{
bool success;
unsigned long scanned = sc->nr_scanned;
unsigned long reclaimed = sc->nr_reclaimed;
int seg = lru_gen_memcg_seg(lruvec);
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
/* see the comment on MEMCG_NR_GENS */
if (!lruvec_is_sizable(lruvec, sc))
return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
mem_cgroup_calculate_protection(NULL, memcg);
if (mem_cgroup_below_min(NULL, memcg))
return MEMCG_LRU_YOUNG;
if (mem_cgroup_below_low(NULL, memcg)) {
/* see the comment on MEMCG_NR_GENS */
if (seg != MEMCG_LRU_TAIL)
return MEMCG_LRU_TAIL;
memcg_memory_event(memcg, MEMCG_LOW);
}
success = try_to_shrink_lruvec(lruvec, sc);
shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority);
if (!sc->proactive)
vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned,
sc->nr_reclaimed - reclaimed);
flush_reclaim_state(sc);
return success ? MEMCG_LRU_YOUNG : 0;
}
#ifdef CONFIG_MEMCG
static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
{
int op;
int gen;
int bin;
int first_bin;
struct lruvec *lruvec;
struct lru_gen_folio *lrugen;
struct mem_cgroup *memcg;
const struct hlist_nulls_node *pos;
unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
restart:
op = 0;
memcg = NULL;
gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
rcu_read_lock();
hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) {
if (op)
lru_gen_rotate_memcg(lruvec, op);
mem_cgroup_put(memcg);
lruvec = container_of(lrugen, struct lruvec, lrugen);
memcg = lruvec_memcg(lruvec);
if (!mem_cgroup_tryget(memcg)) {
op = 0;
memcg = NULL;
continue;
}
rcu_read_unlock();
op = shrink_one(lruvec, sc);
rcu_read_lock();
if (sc->nr_reclaimed >= nr_to_reclaim)
break;
}
rcu_read_unlock();
if (op)
lru_gen_rotate_memcg(lruvec, op);
mem_cgroup_put(memcg);
if (sc->nr_reclaimed >= nr_to_reclaim)
return;
/* restart if raced with lru_gen_rotate_memcg() */
if (gen != get_nulls_value(pos))
goto restart;
/* try the rest of the bins of the current generation */
bin = get_memcg_bin(bin + 1);
if (bin != first_bin)
goto restart;
}
static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
struct blk_plug plug;
VM_WARN_ON_ONCE(global_reclaim(sc));
VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap);
lru_add_drain();
blk_start_plug(&plug);
set_mm_walk(NULL, sc->proactive);
if (try_to_shrink_lruvec(lruvec, sc))
lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG);
clear_mm_walk();
blk_finish_plug(&plug);
}
#else /* !CONFIG_MEMCG */
static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
{
BUILD_BUG();
}
static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
BUILD_BUG();
}
#endif
static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
{
int priority;
unsigned long reclaimable;
struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
return;
/*
* Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
* priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
* estimated reclaimed_to_scanned_ratio = inactive / total.
*/
reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
if (get_swappiness(lruvec, sc))
reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
reclaimable /= MEMCG_NR_GENS;
/* round down reclaimable and round up sc->nr_to_reclaim */
priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
sc->priority = clamp(priority, 0, DEF_PRIORITY);
}
static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
{
struct blk_plug plug;
unsigned long reclaimed = sc->nr_reclaimed;
VM_WARN_ON_ONCE(!global_reclaim(sc));
/*
* Unmapped clean folios are already prioritized. Scanning for more of
* them is likely futile and can cause high reclaim latency when there
* is a large number of memcgs.
*/
if (!sc->may_writepage || !sc->may_unmap)
goto done;
lru_add_drain();
blk_start_plug(&plug);
set_mm_walk(pgdat, sc->proactive);
set_initial_priority(pgdat, sc);
if (current_is_kswapd())
sc->nr_reclaimed = 0;
if (mem_cgroup_disabled())
shrink_one(&pgdat->__lruvec, sc);
else
shrink_many(pgdat, sc);
if (current_is_kswapd())
sc->nr_reclaimed += reclaimed;
clear_mm_walk();
blk_finish_plug(&plug);
done:
/* kswapd should never fail */
pgdat->kswapd_failures = 0;
}
/******************************************************************************
* state change
******************************************************************************/
static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
{
struct lru_gen_folio *lrugen = &lruvec->lrugen;
if (lrugen->enabled) {
enum lru_list lru;
for_each_evictable_lru(lru) {
if (!list_empty(&lruvec->lists[lru]))
return false;
}
} else {
int gen, type, zone;
for_each_gen_type_zone(gen, type, zone) {
if (!list_empty(&lrugen->folios[gen][type][zone]))
return false;
}
}
return true;
}
static bool fill_evictable(struct lruvec *lruvec)
{
enum lru_list lru;
int remaining = MAX_LRU_BATCH;
for_each_evictable_lru(lru) {
int type = is_file_lru(lru);
bool active = is_active_lru(lru);
struct list_head *head = &lruvec->lists[lru];
while (!list_empty(head)) {
bool success;
struct folio *folio = lru_to_folio(head);
VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio);
VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio);
lruvec_del_folio(lruvec, folio);
success = lru_gen_add_folio(lruvec, folio, false);
VM_WARN_ON_ONCE(!success);
if (!--remaining)
return false;
}
}
return true;
}
static bool drain_evictable(struct lruvec *lruvec)
{
int gen, type, zone;
int remaining = MAX_LRU_BATCH;
for_each_gen_type_zone(gen, type, zone) {
struct list_head *head = &lruvec->lrugen.folios[gen][type][zone];
while (!list_empty(head)) {
bool success;
struct folio *folio = lru_to_folio(head);
VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
success = lru_gen_del_folio(lruvec, folio, false);
VM_WARN_ON_ONCE(!success);
lruvec_add_folio(lruvec, folio);
if (!--remaining)
return false;
}
}
return true;
}
static void lru_gen_change_state(bool enabled)
{
static DEFINE_MUTEX(state_mutex);
struct mem_cgroup *memcg;
cgroup_lock();
cpus_read_lock();
get_online_mems();
mutex_lock(&state_mutex);
if (enabled == lru_gen_enabled())
goto unlock;
if (enabled)
static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
else
static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
int nid;
for_each_node(nid) {
struct lruvec *lruvec = get_lruvec(memcg, nid);
spin_lock_irq(&lruvec->lru_lock);
VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
VM_WARN_ON_ONCE(!state_is_valid(lruvec));
lruvec->lrugen.enabled = enabled;
while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) {
spin_unlock_irq(&lruvec->lru_lock);
cond_resched();
spin_lock_irq(&lruvec->lru_lock);
}
spin_unlock_irq(&lruvec->lru_lock);
}
cond_resched();
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
unlock:
mutex_unlock(&state_mutex);
put_online_mems();
cpus_read_unlock();
cgroup_unlock();
}
/******************************************************************************
* sysfs interface
******************************************************************************/
static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
}
/* see Documentation/admin-guide/mm/multigen_lru.rst for details */
static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t len)
{
unsigned int msecs;
if (kstrtouint(buf, 0, &msecs))
return -EINVAL;
WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs));
return len;
}
static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms);
static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
{
unsigned int caps = 0;
if (get_cap(LRU_GEN_CORE))
caps |= BIT(LRU_GEN_CORE);
if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
caps |= BIT(LRU_GEN_MM_WALK);
if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
return sysfs_emit(buf, "0x%04x\n", caps);
}
/* see Documentation/admin-guide/mm/multigen_lru.rst for details */
static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t len)
{
int i;
unsigned int caps;
if (tolower(*buf) == 'n')
caps = 0;
else if (tolower(*buf) == 'y')
caps = -1;
else if (kstrtouint(buf, 0, &caps))
return -EINVAL;
for (i = 0; i < NR_LRU_GEN_CAPS; i++) {
bool enabled = caps & BIT(i);
if (i == LRU_GEN_CORE)
lru_gen_change_state(enabled);
else if (enabled)
static_branch_enable(&lru_gen_caps[i]);
else
static_branch_disable(&lru_gen_caps[i]);
}
return len;
}
static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled);
static struct attribute *lru_gen_attrs[] = {
&lru_gen_min_ttl_attr.attr,
&lru_gen_enabled_attr.attr,
NULL
};
static const struct attribute_group lru_gen_attr_group = {
.name = "lru_gen",
.attrs = lru_gen_attrs,
};
/******************************************************************************
* debugfs interface
******************************************************************************/
static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos)
{
struct mem_cgroup *memcg;
loff_t nr_to_skip = *pos;
m->private = kvmalloc(PATH_MAX, GFP_KERNEL);
if (!m->private)
return ERR_PTR(-ENOMEM);
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
int nid;
for_each_node_state(nid, N_MEMORY) {
if (!nr_to_skip--)
return get_lruvec(memcg, nid);
}
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
return NULL;
}
static void lru_gen_seq_stop(struct seq_file *m, void *v)
{
if (!IS_ERR_OR_NULL(v))
mem_cgroup_iter_break(NULL, lruvec_memcg(v));
kvfree(m->private);
m->private = NULL;
}
static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
int nid = lruvec_pgdat(v)->node_id;
struct mem_cgroup *memcg = lruvec_memcg(v);
++*pos;
nid = next_memory_node(nid);
if (nid == MAX_NUMNODES) {
memcg = mem_cgroup_iter(NULL, memcg, NULL);
if (!memcg)
return NULL;
nid = first_memory_node;
}
return get_lruvec(memcg, nid);
}
static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
unsigned long max_seq, unsigned long *min_seq,
unsigned long seq)
{
int i;
int type, tier;
int hist = lru_hist_from_seq(seq);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
for (tier = 0; tier < MAX_NR_TIERS; tier++) {
seq_printf(m, " %10d", tier);
for (type = 0; type < ANON_AND_FILE; type++) {
const char *s = " ";
unsigned long n[3] = {};
if (seq == max_seq) {
s = "RT ";
n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
} else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
s = "rep";
n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
if (tier)
n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
}
for (i = 0; i < 3; i++)
seq_printf(m, " %10lu%c", n[i], s[i]);
}
seq_putc(m, '\n');
}
seq_puts(m, " ");
for (i = 0; i < NR_MM_STATS; i++) {
const char *s = " ";
unsigned long n = 0;
if (seq == max_seq && NR_HIST_GENS == 1) {
s = "LOYNFA";
n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
} else if (seq != max_seq && NR_HIST_GENS > 1) {
s = "loynfa";
n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
}
seq_printf(m, " %10lu%c", n, s[i]);
}
seq_putc(m, '\n');
}
/* see Documentation/admin-guide/mm/multigen_lru.rst for details */
static int lru_gen_seq_show(struct seq_file *m, void *v)
{
unsigned long seq;
bool full = !debugfs_real_fops(m->file)->write;
struct lruvec *lruvec = v;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
int nid = lruvec_pgdat(lruvec)->node_id;
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MAX_SEQ(lruvec);
DEFINE_MIN_SEQ(lruvec);
if (nid == first_memory_node) {
const char *path = memcg ? m->private : "";
#ifdef CONFIG_MEMCG
if (memcg)
cgroup_path(memcg->css.cgroup, m->private, PATH_MAX);
#endif
seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path);
}
seq_printf(m, " node %5d\n", nid);
if (!full)
seq = min_seq[LRU_GEN_ANON];
else if (max_seq >= MAX_NR_GENS)
seq = max_seq - MAX_NR_GENS + 1;
else
seq = 0;
for (; seq <= max_seq; seq++) {
int type, zone;
int gen = lru_gen_from_seq(seq);
unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth));
for (type = 0; type < ANON_AND_FILE; type++) {
unsigned long size = 0;
char mark = full && seq < min_seq[type] ? 'x' : ' ';
for (zone = 0; zone < MAX_NR_ZONES; zone++)
size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
seq_printf(m, " %10lu%c", size, mark);
}
seq_putc(m, '\n');
if (full)
lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq);
}
return 0;
}
static const struct seq_operations lru_gen_seq_ops = {
.start = lru_gen_seq_start,
.stop = lru_gen_seq_stop,
.next = lru_gen_seq_next,
.show = lru_gen_seq_show,
};
static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
bool can_swap, bool force_scan)
{
DEFINE_MAX_SEQ(lruvec);
DEFINE_MIN_SEQ(lruvec);
if (seq < max_seq)
return 0;
if (seq > max_seq)
return -EINVAL;
if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq)
return -ERANGE;
try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, force_scan);
return 0;
}
static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
int swappiness, unsigned long nr_to_reclaim)
{
DEFINE_MAX_SEQ(lruvec);
if (seq + MIN_NR_GENS > max_seq)
return -EINVAL;
sc->nr_reclaimed = 0;
while (!signal_pending(current)) {
DEFINE_MIN_SEQ(lruvec);
if (seq < min_seq[!swappiness])
return 0;
if (sc->nr_reclaimed >= nr_to_reclaim)
return 0;
if (!evict_folios(lruvec, sc, swappiness))
return 0;
cond_resched();
}
return -EINTR;
}
static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
struct scan_control *sc, int swappiness, unsigned long opt)
{
struct lruvec *lruvec;
int err = -EINVAL;
struct mem_cgroup *memcg = NULL;
if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY))
return -EINVAL;
if (!mem_cgroup_disabled()) {
rcu_read_lock();
memcg = mem_cgroup_from_id(memcg_id);
if (!mem_cgroup_tryget(memcg))
memcg = NULL;
rcu_read_unlock();
if (!memcg)
return -EINVAL;
}
if (memcg_id != mem_cgroup_id(memcg))
goto done;
lruvec = get_lruvec(memcg, nid);
if (swappiness < 0)
swappiness = get_swappiness(lruvec, sc);
else if (swappiness > 200)
goto done;
switch (cmd) {
case '+':
err = run_aging(lruvec, seq, sc, swappiness, opt);
break;
case '-':
err = run_eviction(lruvec, seq, sc, swappiness, opt);
break;
}
done:
mem_cgroup_put(memcg);
return err;
}
/* see Documentation/admin-guide/mm/multigen_lru.rst for details */
static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
size_t len, loff_t *pos)
{
void *buf;
char *cur, *next;
unsigned int flags;
struct blk_plug plug;
int err = -EINVAL;
struct scan_control sc = {
.may_writepage = true,
.may_unmap = true,
.may_swap = true,
.reclaim_idx = MAX_NR_ZONES - 1,
.gfp_mask = GFP_KERNEL,
};
buf = kvmalloc(len + 1, GFP_KERNEL);
if (!buf)
return -ENOMEM;
if (copy_from_user(buf, src, len)) {
kvfree(buf);
return -EFAULT;
}
set_task_reclaim_state(current, &sc.reclaim_state);
flags = memalloc_noreclaim_save();
blk_start_plug(&plug);
if (!set_mm_walk(NULL, true)) {
err = -ENOMEM;
goto done;
}
next = buf;
next[len] = '\0';
while ((cur = strsep(&next, ",;\n"))) {
int n;
int end;
char cmd;
unsigned int memcg_id;
unsigned int nid;
unsigned long seq;
unsigned int swappiness = -1;
unsigned long opt = -1;
cur = skip_spaces(cur);
if (!*cur)
continue;
n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid,
&seq, &end, &swappiness, &end, &opt, &end);
if (n < 4 || cur[end]) {
err = -EINVAL;
break;
}
err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt);
if (err)
break;
}
done:
clear_mm_walk();
blk_finish_plug(&plug);
memalloc_noreclaim_restore(flags);
set_task_reclaim_state(current, NULL);
kvfree(buf);
return err ? : len;
}
static int lru_gen_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &lru_gen_seq_ops);
}
static const struct file_operations lru_gen_rw_fops = {
.open = lru_gen_seq_open,
.read = seq_read,
.write = lru_gen_seq_write,
.llseek = seq_lseek,
.release = seq_release,
};
static const struct file_operations lru_gen_ro_fops = {
.open = lru_gen_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
/******************************************************************************
* initialization
******************************************************************************/
void lru_gen_init_lruvec(struct lruvec *lruvec)
{
int i;
int gen, type, zone;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
lrugen->max_seq = MIN_NR_GENS + 1;
lrugen->enabled = lru_gen_enabled();
for (i = 0; i <= MIN_NR_GENS + 1; i++)
lrugen->timestamps[i] = jiffies;
for_each_gen_type_zone(gen, type, zone)
INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]);
lruvec->mm_state.seq = MIN_NR_GENS;
}
#ifdef CONFIG_MEMCG
void lru_gen_init_pgdat(struct pglist_data *pgdat)
{
int i, j;
spin_lock_init(&pgdat->memcg_lru.lock);
for (i = 0; i < MEMCG_NR_GENS; i++) {
for (j = 0; j < MEMCG_NR_BINS; j++)
INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
}
}
void lru_gen_init_memcg(struct mem_cgroup *memcg)
{
INIT_LIST_HEAD(&memcg->mm_list.fifo);
spin_lock_init(&memcg->mm_list.lock);
}
void lru_gen_exit_memcg(struct mem_cgroup *memcg)
{
int i;
int nid;
VM_WARN_ON_ONCE(!list_empty(&memcg->mm_list.fifo));
for_each_node(nid) {
struct lruvec *lruvec = get_lruvec(memcg, nid);
VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0,
sizeof(lruvec->lrugen.nr_pages)));
lruvec->lrugen.list.next = LIST_POISON1;
for (i = 0; i < NR_BLOOM_FILTERS; i++) {
bitmap_free(lruvec->mm_state.filters[i]);
lruvec->mm_state.filters[i] = NULL;
}
}
}
#endif /* CONFIG_MEMCG */
static int __init init_lru_gen(void)
{
BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
pr_err("lru_gen: failed to create sysfs group\n");
debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops);
debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops);
return 0;
};
late_initcall(init_lru_gen);
#else /* !CONFIG_LRU_GEN */
static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
{
}
static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
}
static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
{
}
#endif /* CONFIG_LRU_GEN */
static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list lru;
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
bool proportional_reclaim;
struct blk_plug plug;
if (lru_gen_enabled() && !global_reclaim(sc)) {
lru_gen_shrink_lruvec(lruvec, sc);
return;
}
get_scan_count(lruvec, sc, nr);
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
/*
* Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
* event that can occur when there is little memory pressure e.g.
* multiple streaming readers/writers. Hence, we do not abort scanning
* when the requested number of pages are reclaimed when scanning at
* DEF_PRIORITY on the assumption that the fact we are direct
* reclaiming implies that kswapd is not keeping up and it is best to
* do a batch of work at once. For memcg reclaim one check is made to
* abort proportional reclaim if either the file or anon lru has already
* dropped to zero at the first pass.
*/
proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
unsigned long nr_anon, nr_file, percentage;
unsigned long nr_scanned;
for_each_evictable_lru(lru) {
if (nr[lru]) {
nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
lruvec, sc);
}
}
cond_resched();
if (nr_reclaimed < nr_to_reclaim || proportional_reclaim)
continue;
/*
* For kswapd and memcg, reclaim at least the number of pages
* requested. Ensure that the anon and file LRUs are scanned
* proportionally what was requested by get_scan_count(). We
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
*/
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
/*
* It's just vindictive to attack the larger once the smaller
* has gone to zero. And given the way we stop scanning the
* smaller below, this makes sure that we only make one nudge
* towards proportionality once we've got nr_to_reclaim.
*/
if (!nr_file || !nr_anon)
break;
if (nr_file > nr_anon) {
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
targets[LRU_ACTIVE_ANON] + 1;
lru = LRU_BASE;
percentage = nr_anon * 100 / scan_target;
} else {
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
targets[LRU_ACTIVE_FILE] + 1;
lru = LRU_FILE;
percentage = nr_file * 100 / scan_target;
}
/* Stop scanning the smaller of the LRU */
nr[lru] = 0;
nr[lru + LRU_ACTIVE] = 0;
/*
* Recalculate the other LRU scan count based on its original
* scan target and the percentage scanning already complete
*/
lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
lru += LRU_ACTIVE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
}
blk_finish_plug(&plug);
sc->nr_reclaimed += nr_reclaimed;
/*
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) &&
inactive_is_low(lruvec, LRU_INACTIVE_ANON))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
sc->priority < DEF_PRIORITY - 2))
return true;
return false;
}
/*
* Reclaim/compaction is used for high-order allocation requests. It reclaims
* order-0 pages before compacting the zone. should_continue_reclaim() returns
* true if more pages should be reclaimed such that when the page allocator
* calls try_to_compact_pages() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
static inline bool should_continue_reclaim(struct pglist_data *pgdat,
unsigned long nr_reclaimed,
struct scan_control *sc)
{
unsigned long pages_for_compaction;
unsigned long inactive_lru_pages;
int z;
/* If not in reclaim/compaction mode, stop */
if (!in_reclaim_compaction(sc))
return false;
/*
* Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX
* number of pages that were scanned. This will return to the caller
* with the risk reclaim/compaction and the resulting allocation attempt
* fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL
* allocations through requiring that the full LRU list has been scanned
* first, by assuming that zero delta of sc->nr_scanned means full LRU
* scan, but that approximation was wrong, and there were corner cases
* where always a non-zero amount of pages were scanned.
*/
if (!nr_reclaimed)
return false;
/* If compaction would go ahead or the allocation would succeed, stop */
for (z = 0; z <= sc->reclaim_idx; z++) {
struct zone *zone = &pgdat->node_zones[z];
if (!managed_zone(zone))
continue;
switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
case COMPACT_SUCCESS:
case COMPACT_CONTINUE:
return false;
default:
/* check next zone */
;
}
}
/*
* If we have not reclaimed enough pages for compaction and the
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = compact_gap(sc->order);
inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
return inactive_lru_pages > pages_for_compaction;
}
static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
{
struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
struct mem_cgroup *memcg;
memcg = mem_cgroup_iter(target_memcg, NULL, NULL);
do {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
unsigned long reclaimed;
unsigned long scanned;
/*
* This loop can become CPU-bound when target memcgs
* aren't eligible for reclaim - either because they
* don't have any reclaimable pages, or because their
* memory is explicitly protected. Avoid soft lockups.
*/
cond_resched();
mem_cgroup_calculate_protection(target_memcg, memcg);
if (mem_cgroup_below_min(target_memcg, memcg)) {
/*
* Hard protection.
* If there is no reclaimable memory, OOM.
*/
continue;
} else if (mem_cgroup_below_low(target_memcg, memcg)) {
/*
* Soft protection.
* Respect the protection only as long as
* there is an unprotected supply
* of reclaimable memory from other cgroups.
*/
if (!sc->memcg_low_reclaim) {
sc->memcg_low_skipped = 1;
continue;
}
memcg_memory_event(memcg, MEMCG_LOW);
}
reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
shrink_lruvec(lruvec, sc);
shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
sc->priority);
/* Record the group's reclaim efficiency */
if (!sc->proactive)
vmpressure(sc->gfp_mask, memcg, false,
sc->nr_scanned - scanned,
sc->nr_reclaimed - reclaimed);
} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
}
static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed;
struct lruvec *target_lruvec;
bool reclaimable = false;
if (lru_gen_enabled() && global_reclaim(sc)) {
lru_gen_shrink_node(pgdat, sc);
return;
}
target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
again:
memset(&sc->nr, 0, sizeof(sc->nr));
nr_reclaimed = sc->nr_reclaimed;
nr_scanned = sc->nr_scanned;
prepare_scan_count(pgdat, sc);
shrink_node_memcgs(pgdat, sc);
flush_reclaim_state(sc);
nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed;
/* Record the subtree's reclaim efficiency */
if (!sc->proactive)
vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
sc->nr_scanned - nr_scanned, nr_node_reclaimed);
if (nr_node_reclaimed)
reclaimable = true;
if (current_is_kswapd()) {
/*
* If reclaim is isolating dirty pages under writeback,
* it implies that the long-lived page allocation rate
* is exceeding the page laundering rate. Either the
* global limits are not being effective at throttling
* processes due to the page distribution throughout
* zones or there is heavy usage of a slow backing
* device. The only option is to throttle from reclaim
* context which is not ideal as there is no guarantee
* the dirtying process is throttled in the same way
* balance_dirty_pages() manages.
*
* Once a node is flagged PGDAT_WRITEBACK, kswapd will
* count the number of pages under pages flagged for
* immediate reclaim and stall if any are encountered
* in the nr_immediate check below.
*/
if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
set_bit(PGDAT_WRITEBACK, &pgdat->flags);
/* Allow kswapd to start writing pages during reclaim.*/
if (sc->nr.unqueued_dirty == sc->nr.file_taken)
set_bit(PGDAT_DIRTY, &pgdat->flags);
/*
* If kswapd scans pages marked for immediate
* reclaim and under writeback (nr_immediate), it
* implies that pages are cycling through the LRU
* faster than they are written so forcibly stall
* until some pages complete writeback.
*/
if (sc->nr.immediate)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
/*
* Tag a node/memcg as congested if all the dirty pages were marked
* for writeback and immediate reclaim (counted in nr.congested).
*
* Legacy memcg will stall in page writeback so avoid forcibly
* stalling in reclaim_throttle().
*/
if ((current_is_kswapd() ||
(cgroup_reclaim(sc) && writeback_throttling_sane(sc))) &&
sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
set_bit(LRUVEC_CONGESTED, &target_lruvec->flags);
/*
* Stall direct reclaim for IO completions if the lruvec is
* node is congested. Allow kswapd to continue until it
* starts encountering unqueued dirty pages or cycling through
* the LRU too quickly.
*/
if (!current_is_kswapd() && current_may_throttle() &&
!sc->hibernation_mode &&
test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);
if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc))
goto again;
/*
* Kswapd gives up on balancing particular nodes after too
* many failures to reclaim anything from them and goes to
* sleep. On reclaim progress, reset the failure counter. A
* successful direct reclaim run will revive a dormant kswapd.
*/
if (reclaimable)
pgdat->kswapd_failures = 0;
}
/*
* Returns true if compaction should go ahead for a costly-order request, or
* the allocation would already succeed without compaction. Return false if we
* should reclaim first.
*/
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
unsigned long watermark;
enum compact_result suitable;
suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
if (suitable == COMPACT_SUCCESS)
/* Allocation should succeed already. Don't reclaim. */
return true;
if (suitable == COMPACT_SKIPPED)
/* Compaction cannot yet proceed. Do reclaim. */
return false;
/*
* Compaction is already possible, but it takes time to run and there
* are potentially other callers using the pages just freed. So proceed
* with reclaim to make a buffer of free pages available to give
* compaction a reasonable chance of completing and allocating the page.
* Note that we won't actually reclaim the whole buffer in one attempt
* as the target watermark in should_continue_reclaim() is lower. But if
* we are already above the high+gap watermark, don't reclaim at all.
*/
watermark = high_wmark_pages(zone) + compact_gap(sc->order);
return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
}
static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
{
/*
* If reclaim is making progress greater than 12% efficiency then
* wake all the NOPROGRESS throttled tasks.
*/
if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) {
wait_queue_head_t *wqh;
wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS];
if (waitqueue_active(wqh))
wake_up(wqh);
return;
}
/*
* Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will
* throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages
* under writeback and marked for immediate reclaim at the tail of the
* LRU.
*/
if (current_is_kswapd() || cgroup_reclaim(sc))
return;
/* Throttle if making no progress at high prioities. */
if (sc->priority == 1 && !sc->nr_reclaimed)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
}
/*
* This is the direct reclaim path, for page-allocating processes. We only
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
{
struct zoneref *z;
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
gfp_t orig_mask;
pg_data_t *last_pgdat = NULL;
pg_data_t *first_pgdat = NULL;
/*
* If the number of buffer_heads in the machine exceeds the maximum
* allowed level, force direct reclaim to scan the highmem zone as
* highmem pages could be pinning lowmem pages storing buffer_heads
*/
orig_mask = sc->gfp_mask;
if (buffer_heads_over_limit) {
sc->gfp_mask |= __GFP_HIGHMEM;
sc->reclaim_idx = gfp_zone(sc->gfp_mask);
}
for_each_zone_zonelist_nodemask(zone, z, zonelist,
sc->reclaim_idx, sc->nodemask) {
/*
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
if (!cgroup_reclaim(sc)) {
if (!cpuset_zone_allowed(zone,
GFP_KERNEL | __GFP_HARDWALL))
continue;
/*
* If we already have plenty of memory free for
* compaction in this zone, don't free any more.
* Even though compaction is invoked for any
* non-zero order, only frequent costly order
* reclamation is disruptive enough to become a
* noticeable problem, like transparent huge
* page allocations.
*/
if (IS_ENABLED(CONFIG_COMPACTION) &&
sc->order > PAGE_ALLOC_COSTLY_ORDER &&
compaction_ready(zone, sc)) {
sc->compaction_ready = true;
continue;
}
/*
* Shrink each node in the zonelist once. If the
* zonelist is ordered by zone (not the default) then a
* node may be shrunk multiple times but in that case
* the user prefers lower zones being preserved.
*/
if (zone->zone_pgdat == last_pgdat)
continue;
/*
* This steals pages from memory cgroups over softlimit
* and returns the number of reclaimed pages and
* scanned pages. This works for global memory pressure
* and balancing, not for a memcg's limit.
*/
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat,
sc->order, sc->gfp_mask,
&nr_soft_scanned);
sc->nr_reclaimed += nr_soft_reclaimed;
sc->nr_scanned += nr_soft_scanned;
/* need some check for avoid more shrink_zone() */
}
if (!first_pgdat)
first_pgdat = zone->zone_pgdat;
/* See comment about same check for global reclaim above */
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
shrink_node(zone->zone_pgdat, sc);
}
if (first_pgdat)
consider_reclaim_throttle(first_pgdat, sc);
/*
* Restore to original mask to avoid the impact on the caller if we
* promoted it to __GFP_HIGHMEM.
*/
sc->gfp_mask = orig_mask;
}
static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
{
struct lruvec *target_lruvec;
unsigned long refaults;
if (lru_gen_enabled())
return;
target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
target_lruvec->refaults[WORKINGSET_ANON] = refaults;
refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
target_lruvec->refaults[WORKINGSET_FILE] = refaults;
}
/*
* This is the main entry point to direct page reclaim.
*
* If a full scan of the inactive list fails to free enough memory then we
* are "out of memory" and something needs to be killed.
*
* If the caller is !__GFP_FS then the probability of a failure is reasonably
* high - the zone may be full of dirty or under-writeback pages, which this
* caller can't do much about. We kick the writeback threads and take explicit
* naps in the hope that some of these pages can be written. But if the
* allocating task holds filesystem locks which prevent writeout this might not
* work, and the allocation attempt will fail.
*
* returns: 0, if no pages reclaimed
* else, the number of pages reclaimed
*/
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
struct scan_control *sc)
{
int initial_priority = sc->priority;
pg_data_t *last_pgdat;
struct zoneref *z;
struct zone *zone;
retry:
delayacct_freepages_start();
if (!cgroup_reclaim(sc))
__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
do {
if (!sc->proactive)
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
sc->priority);
sc->nr_scanned = 0;
shrink_zones(zonelist, sc);
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
break;
if (sc->compaction_ready)
break;
/*
* If we're getting trouble reclaiming, start doing
* writepage even in laptop mode.
*/
if (sc->priority < DEF_PRIORITY - 2)
sc->may_writepage = 1;
} while (--sc->priority >= 0);
last_pgdat = NULL;
for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx,
sc->nodemask) {
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);
if (cgroup_reclaim(sc)) {
struct lruvec *lruvec;
lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup,
zone->zone_pgdat);
clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
}
}
delayacct_freepages_end();
if (sc->nr_reclaimed)
return sc->nr_reclaimed;
/* Aborted reclaim to try compaction? don't OOM, then */
if (sc->compaction_ready)
return 1;
/*
* We make inactive:active ratio decisions based on the node's
* composition of memory, but a restrictive reclaim_idx or a
* memory.low cgroup setting can exempt large amounts of
* memory from reclaim. Neither of which are very common, so
* instead of doing costly eligibility calculations of the
* entire cgroup subtree up front, we assume the estimates are
* good, and retry with forcible deactivation if that fails.
*/
if (sc->skipped_deactivate) {
sc->priority = initial_priority;
sc->force_deactivate = 1;
sc->skipped_deactivate = 0;
goto retry;
}
/* Untapped cgroup reserves? Don't OOM, retry. */
if (sc->memcg_low_skipped) {
sc->priority = initial_priority;
sc->force_deactivate = 0;
sc->memcg_low_reclaim = 1;
sc->memcg_low_skipped = 0;
goto retry;
}
return 0;
}
static bool allow_direct_reclaim(pg_data_t *pgdat)
{
struct zone *zone;
unsigned long pfmemalloc_reserve = 0;
unsigned long free_pages = 0;
int i;
bool wmark_ok;
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
if (!managed_zone(zone))
continue;
if (!zone_reclaimable_pages(zone))
continue;
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
/* If there are no reserves (unexpected config) then do not throttle */
if (!pfmemalloc_reserve)
return true;
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL)
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL);
wake_up_interruptible(&pgdat->kswapd_wait);
}
return wmark_ok;
}
/*
* Throttle direct reclaimers if backing storage is backed by the network
* and the PFMEMALLOC reserve for the preferred node is getting dangerously
* depleted. kswapd will continue to make progress and wake the processes
* when the low watermark is reached.
*
* Returns true if a fatal signal was delivered during throttling. If this
* happens, the page allocator should not consider triggering the OOM killer.
*/
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
struct zoneref *z;
struct zone *zone;
pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
* responsible for cleaning pages necessary for reclaim to make forward
* progress. kjournald for example may enter direct reclaim while
* committing a transaction where throttling it could forcing other
* processes to block on log_wait_commit().
*/
if (current->flags & PF_KTHREAD)
goto out;
/*
* If a fatal signal is pending, this process should not throttle.
* It should return quickly so it can exit and free its memory
*/
if (fatal_signal_pending(current))
goto out;
/*
* Check if the pfmemalloc reserves are ok by finding the first node
* with a usable ZONE_NORMAL or lower zone. The expectation is that
* GFP_KERNEL will be required for allocating network buffers when
* swapping over the network so ZONE_HIGHMEM is unusable.
*
* Throttling is based on the first usable node and throttled processes
* wait on a queue until kswapd makes progress and wakes them. There
* is an affinity then between processes waking up and where reclaim
* progress has been made assuming the process wakes on the same node.
* More importantly, processes running on remote nodes will not compete
* for remote pfmemalloc reserves and processes on different nodes
* should make reasonable progress.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(gfp_mask), nodemask) {
if (zone_idx(zone) > ZONE_NORMAL)
continue;
/* Throttle based on the first usable node */
pgdat = zone->zone_pgdat;
if (allow_direct_reclaim(pgdat))
goto out;
break;
}
/* If no zone was usable by the allocation flags then do not throttle */
if (!pgdat)
goto out;
/* Account for the throttling */
count_vm_event(PGSCAN_DIRECT_THROTTLE);
/*
* If the caller cannot enter the filesystem, it's possible that it
* is due to the caller holding an FS lock or performing a journal
* transaction in the case of a filesystem like ext[3|4]. In this case,
* it is not safe to block on pfmemalloc_wait as kswapd could be
* blocked waiting on the same lock. Instead, throttle for up to a
* second before continuing.
*/
if (!(gfp_mask & __GFP_FS))
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
allow_direct_reclaim(pgdat), HZ);
else
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
allow_direct_reclaim(pgdat));
if (fatal_signal_pending(current))
return true;
out:
return false;
}
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *nodemask)
{
unsigned long nr_reclaimed;
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.gfp_mask = current_gfp_context(gfp_mask),
.reclaim_idx = gfp_zone(gfp_mask),
.order = order,
.nodemask = nodemask,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = 1,
};
/*
* scan_control uses s8 fields for order, priority, and reclaim_idx.
* Confirm they are large enough for max values.
*/
BUILD_BUG_ON(MAX_ORDER >= S8_MAX);
BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
/*
* Do not enter reclaim if fatal signal was delivered while throttled.
* 1 is returned so that the page allocator does not OOM kill at this
* point.
*/
if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
return 1;
set_task_reclaim_state(current, &sc.reclaim_state);
trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
#ifdef CONFIG_MEMCG
/* Only used by soft limit reclaim. Do not reuse for anything else. */
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
unsigned long *nr_scanned)
{
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.target_mem_cgroup = memcg,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.reclaim_idx = MAX_NR_ZONES - 1,
.may_swap = !noswap,
};
WARN_ON_ONCE(!current->reclaim_state);
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
sc.gfp_mask);
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
* if we don't reclaim here, the shrink_node from balance_pgdat
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
shrink_lruvec(lruvec, &sc);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
*nr_scanned = sc.nr_scanned;
return sc.nr_reclaimed;
}
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
unsigned int reclaim_options)
{
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
.reclaim_idx = MAX_NR_ZONES - 1,
.target_mem_cgroup = memcg,
.priority = DEF_PRIORITY,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
};
/*
* Traverse the ZONELIST_FALLBACK zonelist of the current node to put
* equal pressure on all the nodes. This is based on the assumption that
* the reclaim does not bail out early.
*/
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
set_task_reclaim_state(current, &sc.reclaim_state);
trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
memalloc_noreclaim_restore(noreclaim_flag);
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
#endif
static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc)
{
struct mem_cgroup *memcg;
struct lruvec *lruvec;
if (lru_gen_enabled()) {
lru_gen_age_node(pgdat, sc);
return;
}
if (!can_age_anon_pages(pgdat, sc))
return;
lruvec = mem_cgroup_lruvec(NULL, pgdat);
if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON))
return;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
memcg = mem_cgroup_iter(NULL, memcg, NULL);
} while (memcg);
}
static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx)
{
int i;
struct zone *zone;
/*
* Check for watermark boosts top-down as the higher zones
* are more likely to be boosted. Both watermarks and boosts
* should not be checked at the same time as reclaim would
* start prematurely when there is no boosting and a lower
* zone is balanced.
*/
for (i = highest_zoneidx; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (zone->watermark_boost)
return true;
}
return false;
}
/*
* Returns true if there is an eligible zone balanced for the request order
* and highest_zoneidx
*/
static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long mark = -1;
struct zone *zone;
/*
* Check watermarks bottom-up as lower zones are more likely to
* meet watermarks.
*/
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
mark = wmark_pages(zone, WMARK_PROMO);
else
mark = high_wmark_pages(zone);
if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx))
return true;
}
/*
* If a node has no managed zone within highest_zoneidx, it does not
* need balancing by definition. This can happen if a zone-restricted
* allocation tries to wake a remote kswapd.
*/
if (mark == -1)
return true;
return false;
}
/* Clear pgdat state for congested, dirty or under writeback. */
static void clear_pgdat_congested(pg_data_t *pgdat)
{
struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
clear_bit(PGDAT_DIRTY, &pgdat->flags);
clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
}
/*
* Prepare kswapd for sleeping. This verifies that there are no processes
* waiting in throttle_direct_reclaim() and that watermarks have been met.
*
* Returns true if kswapd is ready to sleep
*/
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order,
int highest_zoneidx)
{
/*
* The throttled processes are normally woken up in balance_pgdat() as
* soon as allow_direct_reclaim() is true. But there is a potential
* race between when kswapd checks the watermarks and a process gets
* throttled. There is also a potential race if processes get
* throttled, kswapd wakes, a large process exits thereby balancing the
* zones, which causes kswapd to exit balance_pgdat() before reaching
* the wake up checks. If kswapd is going to sleep, no process should
* be sleeping on pfmemalloc_wait, so wake them now if necessary. If
* the wake up is premature, processes will wake kswapd and get
* throttled again. The difference from wake ups in balance_pgdat() is
* that here we are under prepare_to_wait().
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Hopeless node, leave it to direct reclaim */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
clear_pgdat_congested(pgdat);
return true;
}
return false;
}
/*
* kswapd shrinks a node of pages that are at or below the highest usable
* zone that is currently unbalanced.
*
* Returns true if kswapd scanned at least the requested number of pages to
* reclaim or if the lack of progress was due to pages under writeback.
* This is used to determine if the scanning priority needs to be raised.
*/
static bool kswapd_shrink_node(pg_data_t *pgdat,
struct scan_control *sc)
{
struct zone *zone;
int z;
/* Reclaim a number of pages proportional to the number of zones */
sc->nr_to_reclaim = 0;
for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
if (!managed_zone(zone))
continue;
sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
}
/*
* Historically care was taken to put equal pressure on all zones but
* now pressure is applied based on node LRU order.
*/
shrink_node(pgdat, sc);
/*
* Fragmentation may mean that the system cannot be rebalanced for
* high-order allocations. If twice the allocation size has been
* reclaimed then recheck watermarks only at order-0 to prevent
* excessive reclaim. Assume that a process requested a high-order
* can direct reclaim/compact.
*/
if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
sc->order = 0;
return sc->nr_scanned >= sc->nr_to_reclaim;
}
/* Page allocator PCP high watermark is lowered if reclaim is active. */
static inline void
update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active)
{
int i;
struct zone *zone;
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
if (active)
set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
else
clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags);
}
}
static inline void
set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
update_reclaim_active(pgdat, highest_zoneidx, true);
}
static inline void
clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx)
{
update_reclaim_active(pgdat, highest_zoneidx, false);
}
/*
* For kswapd, balance_pgdat() will reclaim pages across a node from zones
* that are eligible for use by the caller until at least one zone is
* balanced.
*
* Returns the order kswapd finished reclaiming at.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
* found to have free_pages <= high_wmark_pages(zone), any page in that zone
* or lower is eligible for reclaim until at least one usable zone is
* balanced.
*/
static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
unsigned long pflags;
unsigned long nr_boost_reclaim;
unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
bool boosted;
struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.order = order,
.may_unmap = 1,
};
set_task_reclaim_state(current, &sc.reclaim_state);
psi_memstall_enter(&pflags);
__fs_reclaim_acquire(_THIS_IP_);
count_vm_event(PAGEOUTRUN);
/*
* Account for the reclaim boost. Note that the zone boost is left in
* place so that parallel allocations that are near the watermark will
* stall or direct reclaim until kswapd is finished.
*/
nr_boost_reclaim = 0;
for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
nr_boost_reclaim += zone->watermark_boost;
zone_boosts[i] = zone->watermark_boost;
}
boosted = nr_boost_reclaim;
restart:
set_reclaim_active(pgdat, highest_zoneidx);
sc.priority = DEF_PRIORITY;
do {
unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
bool balanced;
bool ret;
sc.reclaim_idx = highest_zoneidx;
/*
* If the number of buffer_heads exceeds the maximum allowed
* then consider reclaiming from all zones. This has a dual
* purpose -- on 64-bit systems it is expected that
* buffer_heads are stripped during active rotation. On 32-bit
* systems, highmem pages can pin lowmem memory and shrinking
* buffers can relieve lowmem pressure. Reclaim may still not
* go ahead if all eligible zones for the original allocation
* request are balanced to avoid excessive reclaim from kswapd.
*/
if (buffer_heads_over_limit) {
for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
sc.reclaim_idx = i;
break;
}
}
/*
* If the pgdat is imbalanced then ignore boosting and preserve
* the watermarks for a later time and restart. Note that the
* zone watermarks will be still reset at the end of balancing
* on the grounds that the normal reclaim should be enough to
* re-evaluate if boosting is required when kswapd next wakes.
*/
balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx);
if (!balanced && nr_boost_reclaim) {
nr_boost_reclaim = 0;
goto restart;
}
/*
* If boosting is not active then only reclaim if there are no
* eligible zones. Note that sc.reclaim_idx is not used as
* buffer_heads_over_limit may have adjusted it.
*/
if (!nr_boost_reclaim && balanced)
goto out;
/* Limit the priority of boosting to avoid reclaim writeback */
if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2)
raise_priority = false;
/*
* Do not writeback or swap pages for boosted reclaim. The
* intent is to relieve pressure not issue sub-optimal IO
* from reclaim context. If no pages are reclaimed, the
* reclaim will be aborted.
*/
sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
sc.may_swap = !nr_boost_reclaim;
/*
* Do some background aging, to give pages a chance to be
* referenced before reclaiming. All pages are rotated
* regardless of classzone as this is about consistent aging.
*/
kswapd_age_node(pgdat, &sc);
/*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
if (sc.priority < DEF_PRIORITY - 2)
sc.may_writepage = 1;
/* Call soft limit reclaim before calling shrink_node. */
sc.nr_scanned = 0;
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
sc.gfp_mask, &nr_soft_scanned);
sc.nr_reclaimed += nr_soft_reclaimed;
/*
* There should be no need to raise the scanning priority if
* enough pages are already being scanned that that high
* watermark would be met at 100% efficiency.
*/
if (kswapd_shrink_node(pgdat, &sc))
raise_priority = false;
/*
* If the low watermark is met there is no need for processes
* to be throttled on pfmemalloc_wait as they should not be
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
allow_direct_reclaim(pgdat))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Check if kswapd should be suspending */
__fs_reclaim_release(_THIS_IP_);
ret = try_to_freeze();
__fs_reclaim_acquire(_THIS_IP_);
if (ret || kthread_should_stop())
break;
/*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);
/*
* If reclaim made no progress for a boost, stop reclaim as
* IO cannot be queued and it could be an infinite loop in
* extreme circumstances.
*/
if (nr_boost_reclaim && !nr_reclaimed)
break;
if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
if (!sc.nr_reclaimed)
pgdat->kswapd_failures++;
out:
clear_reclaim_active(pgdat, highest_zoneidx);
/* If reclaim was boosted, account for the reclaim done in this pass */
if (boosted) {
unsigned long flags;
for (i = 0; i <= highest_zoneidx; i++) {
if (!zone_boosts[i])
continue;
/* Increments are under the zone lock */
zone = pgdat->node_zones + i;
spin_lock_irqsave(&zone->lock, flags);
zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
spin_unlock_irqrestore(&zone->lock, flags);
}
/*
* As there is now likely space, wakeup kcompact to defragment
* pageblocks.
*/
wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx);
}
snapshot_refaults(NULL, pgdat);
__fs_reclaim_release(_THIS_IP_);
psi_memstall_leave(&pflags);
set_task_reclaim_state(current, NULL);
/*
* Return the order kswapd stopped reclaiming at as
* prepare_kswapd_sleep() takes it into account. If another caller
* entered the allocator slow path while kswapd was awake, order will
* remain at the higher level.
*/
return sc.order;
}
/*
* The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to
* be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is
* not a valid index then either kswapd runs for first time or kswapd couldn't
* sleep after previous reclaim attempt (node is still unbalanced). In that
* case return the zone index of the previous kswapd reclaim cycle.
*/
static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
enum zone_type prev_highest_zoneidx)
{
enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
unsigned int highest_zoneidx)
{
long remaining = 0;
DEFINE_WAIT(wait);
if (freezing(current) || kthread_should_stop())
return;
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
/*
* Try to sleep for a short interval. Note that kcompactd will only be
* woken if it is possible to sleep for a short interval. This is
* deliberate on the assumption that if reclaim cannot keep an
* eligible zone balanced that it's also unlikely that compaction will
* succeed.
*/
if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
/*
* Compaction records what page blocks it recently failed to
* isolate pages from and skips them in the future scanning.
* When kswapd is going to sleep, it is reasonable to assume
* that pages and compaction may succeed so reset the cache.
*/
reset_isolation_suitable(pgdat);
/*
* We have freed the memory, now we should compact it to make
* allocation of the requested order possible.
*/
wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx);
remaining = schedule_timeout(HZ/10);
/*
* If woken prematurely then reset kswapd_highest_zoneidx and
* order. The values will either be from a wakeup request or
* the previous request that slept prematurely.
*/
if (remaining) {
WRITE_ONCE(pgdat->kswapd_highest_zoneidx,
kswapd_highest_zoneidx(pgdat,
highest_zoneidx));
if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
}
finish_wait(&pgdat->kswapd_wait, &wait);
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
}
/*
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
if (!remaining &&
prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
* vmstat counters are not perfectly accurate and the estimated
* value for counters such as NR_FREE_PAGES can deviate from the
* true value by nr_online_cpus * threshold. To avoid the zone
* watermarks being breached while under pressure, we reduce the
* per-cpu vmstat threshold while kswapd is awake and restore
* them before going back to sleep.
*/
set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
if (!kthread_should_stop())
schedule();
set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
} else {
if (remaining)
count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
else
count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
}
finish_wait(&pgdat->kswapd_wait, &wait);
}
/*
* The background pageout daemon, started as a kernel thread
* from the init process.
*
* This basically trickles out pages so that we have _some_
* free memory available even if there is no other activity
* that frees anything up. This is needed for things like routing
* etc, where we otherwise might have all activity going on in
* asynchronous contexts that cannot page things out.
*
* If there are applications that are active memory-allocators
* (most normal use), this basically shouldn't matter.
*/
static int kswapd(void *p)
{
unsigned int alloc_order, reclaim_order;
unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
pg_data_t *pgdat = (pg_data_t *)p;
struct task_struct *tsk = current;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
/*
* Tell the memory management that we're a "memory allocator",
* and that if we need more memory we should get access to it
* regardless (see "__alloc_pages()"). "kswapd" should
* never get caught in the normal page freeing logic.
*
* (Kswapd normally doesn't need memory anyway, but sometimes
* you need a small amount of memory in order to be able to
* page out something else, and this flag essentially protects
* us from recursively trying to free more memory as we're
* trying to free the first piece of memory in the first place).
*/
tsk->flags |= PF_MEMALLOC | PF_KSWAPD;
set_freezable();
WRITE_ONCE(pgdat->kswapd_order, 0);
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
atomic_set(&pgdat->nr_writeback_throttled, 0);
for ( ; ; ) {
bool ret;
alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
highest_zoneidx = kswapd_highest_zoneidx(pgdat,
highest_zoneidx);
kswapd_try_sleep:
kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
highest_zoneidx);
/* Read the new order and highest_zoneidx */
alloc_order = READ_ONCE(pgdat->kswapd_order);
highest_zoneidx = kswapd_highest_zoneidx(pgdat,
highest_zoneidx);
WRITE_ONCE(pgdat->kswapd_order, 0);
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
ret = try_to_freeze();
if (kthread_should_stop())
break;
/*
* We can speed up thawing tasks if we don't call balance_pgdat
* after returning from the refrigerator
*/
if (ret)
continue;
/*
* Reclaim begins at the requested order but if a high-order
* reclaim fails then kswapd falls back to reclaiming for
* order-0. If that happens, kswapd will consider sleeping
* for the order it finished reclaiming at (reclaim_order)
* but kcompactd is woken to compact for the original
* request (alloc_order).
*/
trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx,
alloc_order);
reclaim_order = balance_pgdat(pgdat, alloc_order,
highest_zoneidx);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
}
tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD);
return 0;
}
/*
* A zone is low on free memory or too fragmented for high-order memory. If
* kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's
* pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim
* has failed or is not needed, still wake up kcompactd if only compaction is
* needed.
*/
void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
enum zone_type highest_zoneidx)
{
pg_data_t *pgdat;
enum zone_type curr_idx;
if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, gfp_flags))
return;
pgdat = zone->zone_pgdat;
curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx)
WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx);
if (READ_ONCE(pgdat->kswapd_order) < order)
WRITE_ONCE(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
/* Hopeless node, leave it to direct reclaim if possible */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
(pgdat_balanced(pgdat, order, highest_zoneidx) &&
!pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
/*
* There may be plenty of free memory available, but it's too
* fragmented for high-order allocations. Wake up kcompactd
* and rely on compaction_suitable() to determine if it's
* needed. If it fails, it will defer subsequent attempts to
* ratelimit its work.
*/
if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
wakeup_kcompactd(pgdat, order, highest_zoneidx);
return;
}
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order,
gfp_flags);
wake_up_interruptible(&pgdat->kswapd_wait);
}
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
* freed pages.
*
* Rather than trying to age LRUs the aim is to preserve the overall
* LRU order by reclaiming preferentially
* inactive > active > active referenced > active mapped
*/
unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
{
struct scan_control sc = {
.nr_to_reclaim = nr_to_reclaim,
.gfp_mask = GFP_HIGHUSER_MOVABLE,
.reclaim_idx = MAX_NR_ZONES - 1,
.priority = DEF_PRIORITY,
.may_writepage = 1,
.may_unmap = 1,
.may_swap = 1,
.hibernation_mode = 1,
};
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
fs_reclaim_acquire(sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
set_task_reclaim_state(current, &sc.reclaim_state);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
set_task_reclaim_state(current, NULL);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */
/*
* This kswapd start function will be called by init and node-hot-add.
*/
void kswapd_run(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
pgdat_kswapd_lock(pgdat);
if (!pgdat->kswapd) {
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
if (IS_ERR(pgdat->kswapd)) {
/* failure at boot is fatal */
BUG_ON(system_state < SYSTEM_RUNNING);
pr_err("Failed to start kswapd on node %d\n", nid);
pgdat->kswapd = NULL;
}
}
pgdat_kswapd_unlock(pgdat);
}
/*
* Called by memory hotplug when all memory in a node is offlined. Caller must
* be holding mem_hotplug_begin/done().
*/
void kswapd_stop(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
struct task_struct *kswapd;
pgdat_kswapd_lock(pgdat);
kswapd = pgdat->kswapd;
if (kswapd) {
kthread_stop(kswapd);
pgdat->kswapd = NULL;
}
pgdat_kswapd_unlock(pgdat);
}
static int __init kswapd_init(void)
{
int nid;
swap_setup();
for_each_node_state(nid, N_MEMORY)
kswapd_run(nid);
return 0;
}
module_init(kswapd_init)
#ifdef CONFIG_NUMA
/*
* Node reclaim mode
*
* If non-zero call node_reclaim when the number of free pages falls below
* the watermarks.
*/
int node_reclaim_mode __read_mostly;
/*
* Priority for NODE_RECLAIM. This determines the fraction of pages
* of a node considered for each zone_reclaim. 4 scans 1/16th of
* a zone.
*/
#define NODE_RECLAIM_PRIORITY 4
/*
* Percentage of pages in a zone that must be unmapped for node_reclaim to
* occur.
*/
int sysctl_min_unmapped_ratio = 1;
/*
* If the number of slab pages in a zone grows beyond this percentage then
* slab reclaim needs to occur.
*/
int sysctl_min_slab_ratio = 5;
static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
{
unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED);
unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) +
node_page_state(pgdat, NR_ACTIVE_FILE);
/*
* It's possible for there to be more file mapped pages than
* accounted for by the pages on the file LRU lists because
* tmpfs pages accounted for as ANON can also be FILE_MAPPED
*/
return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
}
/* Work out how many page cache pages we can reclaim in this reclaim_mode */
static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat)
{
unsigned long nr_pagecache_reclaimable;
unsigned long delta = 0;
/*
* If RECLAIM_UNMAP is set, then all file pages are considered
* potentially reclaimable. Otherwise, we have to worry about
* pages like swapcache and node_unmapped_file_pages() provides
* a better estimate
*/
if (node_reclaim_mode & RECLAIM_UNMAP)
nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
else
nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);
/* If we can't clean pages, remove dirty pages from consideration */
if (!(node_reclaim_mode & RECLAIM_WRITE))
delta += node_page_state(pgdat, NR_FILE_DIRTY);
/* Watch for any possible underflows due to delta */
if (unlikely(delta > nr_pagecache_reclaimable))
delta = nr_pagecache_reclaimable;
return nr_pagecache_reclaimable - delta;
}
/*
* Try to free up some pages from this node through reclaim.
*/
static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
/* Minimum pages needed in order to stay on node */
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
.gfp_mask = current_gfp_context(gfp_mask),
.order = order,
.priority = NODE_RECLAIM_PRIORITY,
.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
.reclaim_idx = gfp_zone(gfp_mask),
};
unsigned long pflags;
trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
sc.gfp_mask);
cond_resched();
psi_memstall_enter(&pflags);
fs_reclaim_acquire(sc.gfp_mask);
/*
* We need to be able to allocate from the reserves for RECLAIM_UNMAP
*/
noreclaim_flag = memalloc_noreclaim_save();
set_task_reclaim_state(p, &sc.reclaim_state);
if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages ||
node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) {
/*
* Free memory by calling shrink node with increasing
* priorities until we have enough memory freed.
*/
do {
shrink_node(pgdat, &sc);
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
set_task_reclaim_state(p, NULL);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
psi_memstall_leave(&pflags);
trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);
return sc.nr_reclaimed >= nr_pages;
}
int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
{
int ret;
/*
* Node reclaim reclaims unmapped file backed pages and
* slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
* thrown out if the node is overallocated. So we do not reclaim
* if less than a specified percentage of the node is used by
* unmapped file backed pages.
*/
if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
return NODE_RECLAIM_NOSCAN;
/*
* Only run node reclaim on the local node or on nodes that do not
* have associated processors. This will favor the local processor
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
return NODE_RECLAIM_NOSCAN;
if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
return NODE_RECLAIM_NOSCAN;
ret = __node_reclaim(pgdat, gfp_mask, order);
clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
if (!ret)
count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
return ret;
}
#endif
void check_move_unevictable_pages(struct pagevec *pvec)
{
struct folio_batch fbatch;
unsigned i;
folio_batch_init(&fbatch);
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
if (PageTransTail(page))
continue;
folio_batch_add(&fbatch, page_folio(page));
}
check_move_unevictable_folios(&fbatch);
}
EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
/**
* check_move_unevictable_folios - Move evictable folios to appropriate zone
* lru list
* @fbatch: Batch of lru folios to check.
*
* Checks folios for evictability, if an evictable folio is in the unevictable
* lru list, moves it to the appropriate evictable lru list. This function
* should be only used for lru folios.
*/
void check_move_unevictable_folios(struct folio_batch *fbatch)
{
struct lruvec *lruvec = NULL;
int pgscanned = 0;
int pgrescued = 0;
int i;
for (i = 0; i < fbatch->nr; i++) {
struct folio *folio = fbatch->folios[i];
int nr_pages = folio_nr_pages(folio);
pgscanned += nr_pages;
/* block memcg migration while the folio moves between lrus */
if (!folio_test_clear_lru(folio))
continue;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (folio_evictable(folio) && folio_test_unevictable(folio)) {
lruvec_del_folio(lruvec, folio);
folio_clear_unevictable(folio);
lruvec_add_folio(lruvec, folio);
pgrescued += nr_pages;
}
folio_set_lru(folio);
}
if (lruvec) {
__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
unlock_page_lruvec_irq(lruvec);
} else if (pgscanned) {
count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
}
}
EXPORT_SYMBOL_GPL(check_move_unevictable_folios);
|