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
|
/*
* Generic process-grouping system.
*
* Based originally on the cpuset system, extracted by Paul Menage
* Copyright (C) 2006 Google, Inc
*
* Notifications support
* Copyright (C) 2009 Nokia Corporation
* Author: Kirill A. Shutemov
*
* Copyright notices from the original cpuset code:
* --------------------------------------------------
* Copyright (C) 2003 BULL SA.
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
* Portions derived from Patrick Mochel's sysfs code.
* sysfs is Copyright (c) 2001-3 Patrick Mochel
*
* 2003-10-10 Written by Simon Derr.
* 2003-10-22 Updates by Stephen Hemminger.
* 2004 May-July Rework by Paul Jackson.
* ---------------------------------------------------
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file COPYING in the main directory of the Linux
* distribution for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cgroup.h>
#include <linux/cred.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/init_task.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/magic.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/rwsem.h>
#include <linux/percpu-rwsem.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hashtable.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/atomic.h>
/*
* pidlists linger the following amount before being destroyed. The goal
* is avoiding frequent destruction in the middle of consecutive read calls
* Expiring in the middle is a performance problem not a correctness one.
* 1 sec should be enough.
*/
#define CGROUP_PIDLIST_DESTROY_DELAY HZ
#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \
MAX_CFTYPE_NAME + 2)
/*
* cgroup_mutex is the master lock. Any modification to cgroup or its
* hierarchy must be performed while holding it.
*
* css_set_rwsem protects task->cgroups pointer, the list of css_set
* objects, and the chain of tasks off each css_set.
*
* These locks are exported if CONFIG_PROVE_RCU so that accessors in
* cgroup.h can use them for lockdep annotations.
*/
#ifdef CONFIG_PROVE_RCU
DEFINE_MUTEX(cgroup_mutex);
DECLARE_RWSEM(css_set_rwsem);
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_rwsem);
#else
static DEFINE_MUTEX(cgroup_mutex);
static DECLARE_RWSEM(css_set_rwsem);
#endif
/*
* Protects cgroup_idr and css_idr so that IDs can be released without
* grabbing cgroup_mutex.
*/
static DEFINE_SPINLOCK(cgroup_idr_lock);
/*
* Protects cgroup_subsys->release_agent_path. Modifying it also requires
* cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.
*/
static DEFINE_SPINLOCK(release_agent_path_lock);
struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
#define cgroup_assert_mutex_or_rcu_locked() \
RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
!lockdep_is_held(&cgroup_mutex), \
"cgroup_mutex or RCU read lock required");
/*
* cgroup destruction makes heavy use of work items and there can be a lot
* of concurrent destructions. Use a separate workqueue so that cgroup
* destruction work items don't end up filling up max_active of system_wq
* which may lead to deadlock.
*/
static struct workqueue_struct *cgroup_destroy_wq;
/*
* pidlist destructions need to be flushed on cgroup destruction. Use a
* separate workqueue as flush domain.
*/
static struct workqueue_struct *cgroup_pidlist_destroy_wq;
/* generate an array of cgroup subsystem pointers */
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
static struct cgroup_subsys *cgroup_subsys[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
/* array of cgroup subsystem names */
#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
static const char *cgroup_subsys_name[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
/* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */
#define SUBSYS(_x) \
DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \
DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \
EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \
EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key);
#include <linux/cgroup_subsys.h>
#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key,
static struct static_key_true *cgroup_subsys_enabled_key[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key,
static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
#include <linux/cgroup_subsys.h>
};
#undef SUBSYS
/*
* The default hierarchy, reserved for the subsystems that are otherwise
* unattached - it never has more than a single cgroup, and all tasks are
* part of that cgroup.
*/
struct cgroup_root cgrp_dfl_root;
EXPORT_SYMBOL_GPL(cgrp_dfl_root);
/*
* The default hierarchy always exists but is hidden until mounted for the
* first time. This is for backward compatibility.
*/
static bool cgrp_dfl_root_visible;
/*
* Set by the boot param of the same name and makes subsystems with NULL
* ->dfl_files to use ->legacy_files on the default hierarchy.
*/
static bool cgroup_legacy_files_on_dfl;
/* some controllers are not supported in the default hierarchy */
static unsigned long cgrp_dfl_root_inhibit_ss_mask;
/* The list of hierarchy roots */
static LIST_HEAD(cgroup_roots);
static int cgroup_root_count;
/* hierarchy ID allocation and mapping, protected by cgroup_mutex */
static DEFINE_IDR(cgroup_hierarchy_idr);
/*
* Assign a monotonically increasing serial number to csses. It guarantees
* cgroups with bigger numbers are newer than those with smaller numbers.
* Also, as csses are always appended to the parent's ->children list, it
* guarantees that sibling csses are always sorted in the ascending serial
* number order on the list. Protected by cgroup_mutex.
*/
static u64 css_serial_nr_next = 1;
/*
* These bitmask flags indicate whether tasks in the fork and exit paths have
* fork/exit handlers to call. This avoids us having to do extra work in the
* fork/exit path to check which subsystems have fork/exit callbacks.
*/
static unsigned long have_fork_callback __read_mostly;
static unsigned long have_exit_callback __read_mostly;
/* Ditto for the can_fork callback. */
static unsigned long have_canfork_callback __read_mostly;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
static int rebind_subsystems(struct cgroup_root *dst_root,
unsigned long ss_mask);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
bool visible);
static void css_release(struct percpu_ref *ref);
static void kill_css(struct cgroup_subsys_state *css);
static int cgroup_addrm_files(struct cgroup_subsys_state *css,
struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
/**
* cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID
* @ssid: subsys ID of interest
*
* cgroup_subsys_enabled() can only be used with literal subsys names which
* is fine for individual subsystems but unsuitable for cgroup core. This
* is slower static_key_enabled() based test indexed by @ssid.
*/
static bool cgroup_ssid_enabled(int ssid)
{
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
}
/**
* cgroup_on_dfl - test whether a cgroup is on the default hierarchy
* @cgrp: the cgroup of interest
*
* The default hierarchy is the v2 interface of cgroup and this function
* can be used to test whether a cgroup is on the default hierarchy for
* cases where a subsystem should behave differnetly depending on the
* interface version.
*
* The set of behaviors which change on the default hierarchy are still
* being determined and the mount option is prefixed with __DEVEL__.
*
* List of changed behaviors:
*
* - Mount options "noprefix", "xattr", "clone_children", "release_agent"
* and "name" are disallowed.
*
* - When mounting an existing superblock, mount options should match.
*
* - Remount is disallowed.
*
* - rename(2) is disallowed.
*
* - "tasks" is removed. Everything should be at process granularity. Use
* "cgroup.procs" instead.
*
* - "cgroup.procs" is not sorted. pids will be unique unless they got
* recycled inbetween reads.
*
* - "release_agent" and "notify_on_release" are removed. Replacement
* notification mechanism will be implemented.
*
* - "cgroup.clone_children" is removed.
*
* - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup
* and its descendants contain no task; otherwise, 1. The file also
* generates kernfs notification which can be monitored through poll and
* [di]notify when the value of the file changes.
*
* - cpuset: tasks will be kept in empty cpusets when hotplug happens and
* take masks of ancestors with non-empty cpus/mems, instead of being
* moved to an ancestor.
*
* - cpuset: a task can be moved into an empty cpuset, and again it takes
* masks of ancestors.
*
* - memcg: use_hierarchy is on by default and the cgroup file for the flag
* is not created.
*
* - blkcg: blk-throttle becomes properly hierarchical.
*
* - debug: disallowed on the default hierarchy.
*/
static bool cgroup_on_dfl(const struct cgroup *cgrp)
{
return cgrp->root == &cgrp_dfl_root;
}
/* IDR wrappers which synchronize using cgroup_idr_lock */
static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
gfp_t gfp_mask)
{
int ret;
idr_preload(gfp_mask);
spin_lock_bh(&cgroup_idr_lock);
ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_WAIT);
spin_unlock_bh(&cgroup_idr_lock);
idr_preload_end();
return ret;
}
static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id)
{
void *ret;
spin_lock_bh(&cgroup_idr_lock);
ret = idr_replace(idr, ptr, id);
spin_unlock_bh(&cgroup_idr_lock);
return ret;
}
static void cgroup_idr_remove(struct idr *idr, int id)
{
spin_lock_bh(&cgroup_idr_lock);
idr_remove(idr, id);
spin_unlock_bh(&cgroup_idr_lock);
}
static struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
struct cgroup_subsys_state *parent_css = cgrp->self.parent;
if (parent_css)
return container_of(parent_css, struct cgroup, self);
return NULL;
}
/**
* cgroup_css - obtain a cgroup's css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest (%NULL returns @cgrp->self)
*
* Return @cgrp's css (cgroup_subsys_state) associated with @ss. This
* function must be called either under cgroup_mutex or rcu_read_lock() and
* the caller is responsible for pinning the returned css if it wants to
* keep accessing it outside the said locks. This function may return
* %NULL if @cgrp doesn't have @subsys_id enabled.
*/
static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
if (ss)
return rcu_dereference_check(cgrp->subsys[ss->id],
lockdep_is_held(&cgroup_mutex));
else
return &cgrp->self;
}
/**
* cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest (%NULL returns @cgrp->self)
*
* Similar to cgroup_css() but returns the effective css, which is defined
* as the matching css of the nearest ancestor including self which has @ss
* enabled. If @ss is associated with the hierarchy @cgrp is on, this
* function is guaranteed to return non-NULL css.
*/
static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
lockdep_assert_held(&cgroup_mutex);
if (!ss)
return &cgrp->self;
if (!(cgrp->root->subsys_mask & (1 << ss->id)))
return NULL;
/*
* This function is used while updating css associations and thus
* can't test the csses directly. Use ->child_subsys_mask.
*/
while (cgroup_parent(cgrp) &&
!(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id)))
cgrp = cgroup_parent(cgrp);
return cgroup_css(cgrp, ss);
}
/**
* cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
* @cgrp: the cgroup of interest
* @ss: the subsystem of interest
*
* Find and get the effective css of @cgrp for @ss. The effective css is
* defined as the matching css of the nearest ancestor including self which
* has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on,
* the root css is returned, so this function always returns a valid css.
* The returned css must be put using css_put().
*/
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
rcu_read_lock();
do {
css = cgroup_css(cgrp, ss);
if (css && css_tryget_online(css))
goto out_unlock;
cgrp = cgroup_parent(cgrp);
} while (cgrp);
css = init_css_set.subsys[ss->id];
css_get(css);
out_unlock:
rcu_read_unlock();
return css;
}
/* convenient tests for these bits */
static inline bool cgroup_is_dead(const struct cgroup *cgrp)
{
return !(cgrp->self.flags & CSS_ONLINE);
}
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
{
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of_cft(of);
/*
* This is open and unprotected implementation of cgroup_css().
* seq_css() is only called from a kernfs file operation which has
* an active reference on the file. Because all the subsystem
* files are drained before a css is disassociated with a cgroup,
* the matching css from the cgroup's subsys table is guaranteed to
* be and stay valid until the enclosing operation is complete.
*/
if (cft->ss)
return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
else
return &cgrp->self;
}
EXPORT_SYMBOL_GPL(of_css);
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
* @ancestor: possible ancestor of @cgrp
*
* Test whether @cgrp is a descendant of @ancestor. It also returns %true
* if @cgrp == @ancestor. This function is safe to call as long as @cgrp
* and @ancestor are accessible.
*/
bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
{
while (cgrp) {
if (cgrp == ancestor)
return true;
cgrp = cgroup_parent(cgrp);
}
return false;
}
static int notify_on_release(const struct cgroup *cgrp)
{
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
/**
* for_each_css - iterate all css's of a cgroup
* @css: the iteration cursor
* @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
* @cgrp: the target cgroup to iterate css's of
*
* Should be called under cgroup_[tree_]mutex.
*/
#define for_each_css(css, ssid, cgrp) \
for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
if (!((css) = rcu_dereference_check( \
(cgrp)->subsys[(ssid)], \
lockdep_is_held(&cgroup_mutex)))) { } \
else
/**
* for_each_e_css - iterate all effective css's of a cgroup
* @css: the iteration cursor
* @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
* @cgrp: the target cgroup to iterate css's of
*
* Should be called under cgroup_[tree_]mutex.
*/
#define for_each_e_css(css, ssid, cgrp) \
for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
; \
else
/**
* for_each_subsys - iterate all enabled cgroup subsystems
* @ss: the iteration cursor
* @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
*/
#define for_each_subsys(ss, ssid) \
for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \
(((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
/**
* for_each_subsys_which - filter for_each_subsys with a bitmask
* @ss: the iteration cursor
* @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
* @ss_maskp: a pointer to the bitmask
*
* The block will only run for cases where the ssid-th bit (1 << ssid) of
* mask is set to 1.
*/
#define for_each_subsys_which(ss, ssid, ss_maskp) \
if (!CGROUP_SUBSYS_COUNT) /* to avoid spurious gcc warning */ \
(ssid) = 0; \
else \
for_each_set_bit(ssid, ss_maskp, CGROUP_SUBSYS_COUNT) \
if (((ss) = cgroup_subsys[ssid]) && false) \
break; \
else
/* iterate across the hierarchies */
#define for_each_root(root) \
list_for_each_entry((root), &cgroup_roots, root_list)
/* iterate over child cgrps, lock should be held throughout iteration */
#define cgroup_for_each_live_child(child, cgrp) \
list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
if (({ lockdep_assert_held(&cgroup_mutex); \
cgroup_is_dead(child); })) \
; \
else
static void cgroup_release_agent(struct work_struct *work);
static void check_for_release(struct cgroup *cgrp);
/*
* A cgroup can be associated with multiple css_sets as different tasks may
* belong to different cgroups on different hierarchies. In the other
* direction, a css_set is naturally associated with multiple cgroups.
* This M:N relationship is represented by the following link structure
* which exists for each association and allows traversing the associations
* from both sides.
*/
struct cgrp_cset_link {
/* the cgroup and css_set this link associates */
struct cgroup *cgrp;
struct css_set *cset;
/* list of cgrp_cset_links anchored at cgrp->cset_links */
struct list_head cset_link;
/* list of cgrp_cset_links anchored at css_set->cgrp_links */
struct list_head cgrp_link;
};
/*
* The default css_set - used by init and its children prior to any
* hierarchies being mounted. It contains a pointer to the root state
* for each subsystem. Also used to anchor the list of css_sets. Not
* reference-counted, to improve performance when child cgroups
* haven't been created.
*/
struct css_set init_css_set = {
.refcount = ATOMIC_INIT(1),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
.tasks = LIST_HEAD_INIT(init_css_set.tasks),
.mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
.mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
};
static int css_set_count = 1; /* 1 for init_css_set */
/**
* cgroup_update_populated - updated populated count of a cgroup
* @cgrp: the target cgroup
* @populated: inc or dec populated count
*
* @cgrp is either getting the first task (css_set) or losing the last.
* Update @cgrp->populated_cnt accordingly. The count is propagated
* towards root so that a given cgroup's populated_cnt is zero iff the
* cgroup and all its descendants are empty.
*
* @cgrp's interface file "cgroup.populated" is zero if
* @cgrp->populated_cnt is zero and 1 otherwise. When @cgrp->populated_cnt
* changes from or to zero, userland is notified that the content of the
* interface file has changed. This can be used to detect when @cgrp and
* its descendants become populated or empty.
*/
static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
{
lockdep_assert_held(&css_set_rwsem);
do {
bool trigger;
if (populated)
trigger = !cgrp->populated_cnt++;
else
trigger = !--cgrp->populated_cnt;
if (!trigger)
break;
cgroup_file_notify(&cgrp->events_file);
cgrp = cgroup_parent(cgrp);
} while (cgrp);
}
/*
* hash table for cgroup groups. This improves the performance to find
* an existing css_set. This hash doesn't (currently) take into
* account cgroups in empty hierarchies.
*/
#define CSS_SET_HASH_BITS 7
static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
{
unsigned long key = 0UL;
struct cgroup_subsys *ss;
int i;
for_each_subsys(ss, i)
key += (unsigned long)css[i];
key = (key >> 16) ^ key;
return key;
}
static void put_css_set_locked(struct css_set *cset)
{
struct cgrp_cset_link *link, *tmp_link;
struct cgroup_subsys *ss;
int ssid;
lockdep_assert_held(&css_set_rwsem);
if (!atomic_dec_and_test(&cset->refcount))
return;
/* This css_set is dead. unlink it and release cgroup refcounts */
for_each_subsys(ss, ssid)
list_del(&cset->e_cset_node[ssid]);
hash_del(&cset->hlist);
css_set_count--;
list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) {
struct cgroup *cgrp = link->cgrp;
list_del(&link->cset_link);
list_del(&link->cgrp_link);
/* @cgrp can't go away while we're holding css_set_rwsem */
if (list_empty(&cgrp->cset_links)) {
cgroup_update_populated(cgrp, false);
check_for_release(cgrp);
}
kfree(link);
}
kfree_rcu(cset, rcu_head);
}
static void put_css_set(struct css_set *cset)
{
/*
* Ensure that the refcount doesn't hit zero while any readers
* can see it. Similar to atomic_dec_and_lock(), but for an
* rwlock
*/
if (atomic_add_unless(&cset->refcount, -1, 1))
return;
down_write(&css_set_rwsem);
put_css_set_locked(cset);
up_write(&css_set_rwsem);
}
/*
* refcounted get/put for css_set objects
*/
static inline void get_css_set(struct css_set *cset)
{
atomic_inc(&cset->refcount);
}
/**
* compare_css_sets - helper function for find_existing_css_set().
* @cset: candidate css_set being tested
* @old_cset: existing css_set for a task
* @new_cgrp: cgroup that's being entered by the task
* @template: desired set of css pointers in css_set (pre-calculated)
*
* Returns true if "cset" matches "old_cset" except for the hierarchy
* which "new_cgrp" belongs to, for which it should match "new_cgrp".
*/
static bool compare_css_sets(struct css_set *cset,
struct css_set *old_cset,
struct cgroup *new_cgrp,
struct cgroup_subsys_state *template[])
{
struct list_head *l1, *l2;
/*
* On the default hierarchy, there can be csets which are
* associated with the same set of cgroups but different csses.
* Let's first ensure that csses match.
*/
if (memcmp(template, cset->subsys, sizeof(cset->subsys)))
return false;
/*
* Compare cgroup pointers in order to distinguish between
* different cgroups in hierarchies. As different cgroups may
* share the same effective css, this comparison is always
* necessary.
*/
l1 = &cset->cgrp_links;
l2 = &old_cset->cgrp_links;
while (1) {
struct cgrp_cset_link *link1, *link2;
struct cgroup *cgrp1, *cgrp2;
l1 = l1->next;
l2 = l2->next;
/* See if we reached the end - both lists are equal length. */
if (l1 == &cset->cgrp_links) {
BUG_ON(l2 != &old_cset->cgrp_links);
break;
} else {
BUG_ON(l2 == &old_cset->cgrp_links);
}
/* Locate the cgroups associated with these links. */
link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link);
link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link);
cgrp1 = link1->cgrp;
cgrp2 = link2->cgrp;
/* Hierarchies should be linked in the same order. */
BUG_ON(cgrp1->root != cgrp2->root);
/*
* If this hierarchy is the hierarchy of the cgroup
* that's changing, then we need to check that this
* css_set points to the new cgroup; if it's any other
* hierarchy, then this css_set should point to the
* same cgroup as the old css_set.
*/
if (cgrp1->root == new_cgrp->root) {
if (cgrp1 != new_cgrp)
return false;
} else {
if (cgrp1 != cgrp2)
return false;
}
}
return true;
}
/**
* find_existing_css_set - init css array and find the matching css_set
* @old_cset: the css_set that we're using before the cgroup transition
* @cgrp: the cgroup that we're moving into
* @template: out param for the new set of csses, should be clear on entry
*/
static struct css_set *find_existing_css_set(struct css_set *old_cset,
struct cgroup *cgrp,
struct cgroup_subsys_state *template[])
{
struct cgroup_root *root = cgrp->root;
struct cgroup_subsys *ss;
struct css_set *cset;
unsigned long key;
int i;
/*
* Build the set of subsystem state objects that we want to see in the
* new css_set. while subsystems can change globally, the entries here
* won't change, so no need for locking.
*/
for_each_subsys(ss, i) {
if (root->subsys_mask & (1UL << i)) {
/*
* @ss is in this hierarchy, so we want the
* effective css from @cgrp.
*/
template[i] = cgroup_e_css(cgrp, ss);
} else {
/*
* @ss is not in this hierarchy, so we don't want
* to change the css.
*/
template[i] = old_cset->subsys[i];
}
}
key = css_set_hash(template);
hash_for_each_possible(css_set_table, cset, hlist, key) {
if (!compare_css_sets(cset, old_cset, cgrp, template))
continue;
/* This css_set matches what we need */
return cset;
}
/* No existing cgroup group matched */
return NULL;
}
static void free_cgrp_cset_links(struct list_head *links_to_free)
{
struct cgrp_cset_link *link, *tmp_link;
list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) {
list_del(&link->cset_link);
kfree(link);
}
}
/**
* allocate_cgrp_cset_links - allocate cgrp_cset_links
* @count: the number of links to allocate
* @tmp_links: list_head the allocated links are put on
*
* Allocate @count cgrp_cset_link structures and chain them on @tmp_links
* through ->cset_link. Returns 0 on success or -errno.
*/
static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links)
{
struct cgrp_cset_link *link;
int i;
INIT_LIST_HEAD(tmp_links);
for (i = 0; i < count; i++) {
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
free_cgrp_cset_links(tmp_links);
return -ENOMEM;
}
list_add(&link->cset_link, tmp_links);
}
return 0;
}
/**
* link_css_set - a helper function to link a css_set to a cgroup
* @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links()
* @cset: the css_set to be linked
* @cgrp: the destination cgroup
*/
static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
struct cgroup *cgrp)
{
struct cgrp_cset_link *link;
BUG_ON(list_empty(tmp_links));
if (cgroup_on_dfl(cgrp))
cset->dfl_cgrp = cgrp;
link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link);
link->cset = cset;
link->cgrp = cgrp;
if (list_empty(&cgrp->cset_links))
cgroup_update_populated(cgrp, true);
list_move(&link->cset_link, &cgrp->cset_links);
/*
* Always add links to the tail of the list so that the list
* is sorted by order of hierarchy creation
*/
list_add_tail(&link->cgrp_link, &cset->cgrp_links);
}
/**
* find_css_set - return a new css_set with one cgroup updated
* @old_cset: the baseline css_set
* @cgrp: the cgroup to be updated
*
* Return a new css_set that's equivalent to @old_cset, but with @cgrp
* substituted into the appropriate hierarchy.
*/
static struct css_set *find_css_set(struct css_set *old_cset,
struct cgroup *cgrp)
{
struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { };
struct css_set *cset;
struct list_head tmp_links;
struct cgrp_cset_link *link;
struct cgroup_subsys *ss;
unsigned long key;
int ssid;
lockdep_assert_held(&cgroup_mutex);
/* First see if we already have a cgroup group that matches
* the desired set */
down_read(&css_set_rwsem);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
up_read(&css_set_rwsem);
if (cset)
return cset;
cset = kzalloc(sizeof(*cset), GFP_KERNEL);
if (!cset)
return NULL;
/* Allocate all the cgrp_cset_link objects that we'll need */
if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) {
kfree(cset);
return NULL;
}
atomic_set(&cset->refcount, 1);
INIT_LIST_HEAD(&cset->cgrp_links);
INIT_LIST_HEAD(&cset->tasks);
INIT_LIST_HEAD(&cset->mg_tasks);
INIT_LIST_HEAD(&cset->mg_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
INIT_HLIST_NODE(&cset->hlist);
/* Copy the set of subsystem state objects generated in
* find_existing_css_set() */
memcpy(cset->subsys, template, sizeof(cset->subsys));
down_write(&css_set_rwsem);
/* Add reference counts and links from the new css_set. */
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
if (c->root == cgrp->root)
c = cgrp;
link_css_set(&tmp_links, cset, c);
}
BUG_ON(!list_empty(&tmp_links));
css_set_count++;
/* Add @cset to the hash table */
key = css_set_hash(cset->subsys);
hash_add(css_set_table, &cset->hlist, key);
for_each_subsys(ss, ssid)
list_add_tail(&cset->e_cset_node[ssid],
&cset->subsys[ssid]->cgroup->e_csets[ssid]);
up_write(&css_set_rwsem);
return cset;
}
static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
{
struct cgroup *root_cgrp = kf_root->kn->priv;
return root_cgrp->root;
}
static int cgroup_init_root_id(struct cgroup_root *root)
{
int id;
lockdep_assert_held(&cgroup_mutex);
id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL);
if (id < 0)
return id;
root->hierarchy_id = id;
return 0;
}
static void cgroup_exit_root_id(struct cgroup_root *root)
{
lockdep_assert_held(&cgroup_mutex);
if (root->hierarchy_id) {
idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
root->hierarchy_id = 0;
}
}
static void cgroup_free_root(struct cgroup_root *root)
{
if (root) {
/* hierarchy ID should already have been released */
WARN_ON_ONCE(root->hierarchy_id);
idr_destroy(&root->cgroup_idr);
kfree(root);
}
}
static void cgroup_destroy_root(struct cgroup_root *root)
{
struct cgroup *cgrp = &root->cgrp;
struct cgrp_cset_link *link, *tmp_link;
mutex_lock(&cgroup_mutex);
BUG_ON(atomic_read(&root->nr_cgrps));
BUG_ON(!list_empty(&cgrp->self.children));
/* Rebind all subsystems back to the default hierarchy */
rebind_subsystems(&cgrp_dfl_root, root->subsys_mask);
/*
* Release all the links from cset_links to this hierarchy's
* root cgroup
*/
down_write(&css_set_rwsem);
list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
list_del(&link->cset_link);
list_del(&link->cgrp_link);
kfree(link);
}
up_write(&css_set_rwsem);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
cgroup_root_count--;
}
cgroup_exit_root_id(root);
mutex_unlock(&cgroup_mutex);
kernfs_destroy_root(root->kf_root);
cgroup_free_root(root);
}
/* look up cgroup associated with given css_set on the specified hierarchy */
static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
{
struct cgroup *res = NULL;
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_rwsem);
if (cset == &init_css_set) {
res = &root->cgrp;
} else {
struct cgrp_cset_link *link;
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
if (c->root == root) {
res = c;
break;
}
}
}
BUG_ON(!res);
return res;
}
/*
* Return the cgroup for "task" from the given hierarchy. Must be
* called with cgroup_mutex and css_set_rwsem held.
*/
static struct cgroup *task_cgroup_from_root(struct task_struct *task,
struct cgroup_root *root)
{
/*
* No need to lock the task - since we hold cgroup_mutex the
* task can't change groups, so the only thing that can happen
* is that it exits and its css is set back to init_css_set.
*/
return cset_cgroup_from_root(task_css_set(task), root);
}
/*
* A task must hold cgroup_mutex to modify cgroups.
*
* Any task can increment and decrement the count field without lock.
* So in general, code holding cgroup_mutex can't rely on the count
* field not changing. However, if the count goes to zero, then only
* cgroup_attach_task() can increment it again. Because a count of zero
* means that no tasks are currently attached, therefore there is no
* way a task attached to that cgroup can fork (the other way to
* increment the count). So code holding cgroup_mutex can safely
* assume that if the count is zero, it will stay zero. Similarly, if
* a task holds cgroup_mutex on a cgroup with zero count, it
* knows that the cgroup won't be removed, as cgroup_rmdir()
* needs that mutex.
*
* A cgroup can only be deleted if both its 'count' of using tasks
* is zero, and its list of 'children' cgroups is empty. Since all
* tasks in the system use _some_ cgroup, and since there is always at
* least one task in the system (init, pid == 1), therefore, root cgroup
* always has either children cgroups and/or using tasks. So we don't
* need a special hack to ensure that root cgroup cannot be deleted.
*
* P.S. One more locking exception. RCU is used to guard the
* update of a tasks cgroup pointer by cgroup_attach_task()
*/
static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
static const struct file_operations proc_cgroupstats_operations;
static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
char *buf)
{
struct cgroup_subsys *ss = cft->ss;
if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
!(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
cft->name);
else
strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
return buf;
}
/**
* cgroup_file_mode - deduce file mode of a control file
* @cft: the control file in question
*
* S_IRUGO for read, S_IWUSR for write.
*/
static umode_t cgroup_file_mode(const struct cftype *cft)
{
umode_t mode = 0;
if (cft->read_u64 || cft->read_s64 || cft->seq_show)
mode |= S_IRUGO;
if (cft->write_u64 || cft->write_s64 || cft->write) {
if (cft->flags & CFTYPE_WORLD_WRITABLE)
mode |= S_IWUGO;
else
mode |= S_IWUSR;
}
return mode;
}
static void cgroup_get(struct cgroup *cgrp)
{
WARN_ON_ONCE(cgroup_is_dead(cgrp));
css_get(&cgrp->self);
}
static bool cgroup_tryget(struct cgroup *cgrp)
{
return css_tryget(&cgrp->self);
}
static void cgroup_put(struct cgroup *cgrp)
{
css_put(&cgrp->self);
}
/**
* cgroup_calc_child_subsys_mask - calculate child_subsys_mask
* @cgrp: the target cgroup
* @subtree_control: the new subtree_control mask to consider
*
* On the default hierarchy, a subsystem may request other subsystems to be
* enabled together through its ->depends_on mask. In such cases, more
* subsystems than specified in "cgroup.subtree_control" may be enabled.
*
* This function calculates which subsystems need to be enabled if
* @subtree_control is to be applied to @cgrp. The returned mask is always
* a superset of @subtree_control and follows the usual hierarchy rules.
*/
static unsigned long cgroup_calc_child_subsys_mask(struct cgroup *cgrp,
unsigned long subtree_control)
{
struct cgroup *parent = cgroup_parent(cgrp);
unsigned long cur_ss_mask = subtree_control;
struct cgroup_subsys *ss;
int ssid;
lockdep_assert_held(&cgroup_mutex);
if (!cgroup_on_dfl(cgrp))
return cur_ss_mask;
while (true) {
unsigned long new_ss_mask = cur_ss_mask;
for_each_subsys_which(ss, ssid, &cur_ss_mask)
new_ss_mask |= ss->depends_on;
/*
* Mask out subsystems which aren't available. This can
* happen only if some depended-upon subsystems were bound
* to non-default hierarchies.
*/
if (parent)
new_ss_mask &= parent->child_subsys_mask;
else
new_ss_mask &= cgrp->root->subsys_mask;
if (new_ss_mask == cur_ss_mask)
break;
cur_ss_mask = new_ss_mask;
}
return cur_ss_mask;
}
/**
* cgroup_refresh_child_subsys_mask - update child_subsys_mask
* @cgrp: the target cgroup
*
* Update @cgrp->child_subsys_mask according to the current
* @cgrp->subtree_control using cgroup_calc_child_subsys_mask().
*/
static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
{
cgrp->child_subsys_mask =
cgroup_calc_child_subsys_mask(cgrp, cgrp->subtree_control);
}
/**
* cgroup_kn_unlock - unlocking helper for cgroup kernfs methods
* @kn: the kernfs_node being serviced
*
* This helper undoes cgroup_kn_lock_live() and should be invoked before
* the method finishes if locking succeeded. Note that once this function
* returns the cgroup returned by cgroup_kn_lock_live() may become
* inaccessible any time. If the caller intends to continue to access the
* cgroup, it should pin it before invoking this function.
*/
static void cgroup_kn_unlock(struct kernfs_node *kn)
{
struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR)
cgrp = kn->priv;
else
cgrp = kn->parent->priv;
mutex_unlock(&cgroup_mutex);
kernfs_unbreak_active_protection(kn);
cgroup_put(cgrp);
}
/**
* cgroup_kn_lock_live - locking helper for cgroup kernfs methods
* @kn: the kernfs_node being serviced
*
* This helper is to be used by a cgroup kernfs method currently servicing
* @kn. It breaks the active protection, performs cgroup locking and
* verifies that the associated cgroup is alive. Returns the cgroup if
* alive; otherwise, %NULL. A successful return should be undone by a
* matching cgroup_kn_unlock() invocation.
*
* Any cgroup kernfs method implementation which requires locking the
* associated cgroup should use this helper. It avoids nesting cgroup
* locking under kernfs active protection and allows all kernfs operations
* including self-removal.
*/
static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
{
struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR)
cgrp = kn->priv;
else
cgrp = kn->parent->priv;
/*
* We're gonna grab cgroup_mutex which nests outside kernfs
* active_ref. cgroup liveliness check alone provides enough
* protection against removal. Ensure @cgrp stays accessible and
* break the active_ref protection.
*/
if (!cgroup_tryget(cgrp))
return NULL;
kernfs_break_active_protection(kn);
mutex_lock(&cgroup_mutex);
if (!cgroup_is_dead(cgrp))
return cgrp;
cgroup_kn_unlock(kn);
return NULL;
}
static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
{
char name[CGROUP_FILE_NAME_MAX];
lockdep_assert_held(&cgroup_mutex);
kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
}
/**
* css_clear_dir - remove subsys files in a cgroup directory
* @css: taget css
* @cgrp_override: specify if target cgroup is different from css->cgroup
*/
static void css_clear_dir(struct cgroup_subsys_state *css,
struct cgroup *cgrp_override)
{
struct cgroup *cgrp = cgrp_override ?: css->cgroup;
struct cftype *cfts;
list_for_each_entry(cfts, &css->ss->cfts, node)
cgroup_addrm_files(css, cgrp, cfts, false);
}
/**
* css_populate_dir - create subsys files in a cgroup directory
* @css: target css
* @cgrp_overried: specify if target cgroup is different from css->cgroup
*
* On failure, no file is added.
*/
static int css_populate_dir(struct cgroup_subsys_state *css,
struct cgroup *cgrp_override)
{
struct cgroup *cgrp = cgrp_override ?: css->cgroup;
struct cftype *cfts, *failed_cfts;
int ret;
if (!css->ss) {
if (cgroup_on_dfl(cgrp))
cfts = cgroup_dfl_base_files;
else
cfts = cgroup_legacy_base_files;
return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
}
list_for_each_entry(cfts, &css->ss->cfts, node) {
ret = cgroup_addrm_files(css, cgrp, cfts, true);
if (ret < 0) {
failed_cfts = cfts;
goto err;
}
}
return 0;
err:
list_for_each_entry(cfts, &css->ss->cfts, node) {
if (cfts == failed_cfts)
break;
cgroup_addrm_files(css, cgrp, cfts, false);
}
return ret;
}
static int rebind_subsystems(struct cgroup_root *dst_root,
unsigned long ss_mask)
{
struct cgroup *dcgrp = &dst_root->cgrp;
struct cgroup_subsys *ss;
unsigned long tmp_ss_mask;
int ssid, i, ret;
lockdep_assert_held(&cgroup_mutex);
for_each_subsys_which(ss, ssid, &ss_mask) {
/* if @ss has non-root csses attached to it, can't move */
if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)))
return -EBUSY;
/* can't move between two non-dummy roots either */
if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root)
return -EBUSY;
}
/* skip creating root files on dfl_root for inhibited subsystems */
tmp_ss_mask = ss_mask;
if (dst_root == &cgrp_dfl_root)
tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask;
for_each_subsys_which(ss, ssid, &tmp_ss_mask) {
struct cgroup *scgrp = &ss->root->cgrp;
int tssid;
ret = css_populate_dir(cgroup_css(scgrp, ss), dcgrp);
if (!ret)
continue;
/*
* Rebinding back to the default root is not allowed to
* fail. Using both default and non-default roots should
* be rare. Moving subsystems back and forth even more so.
* Just warn about it and continue.
*/
if (dst_root == &cgrp_dfl_root) {
if (cgrp_dfl_root_visible) {
pr_warn("failed to create files (%d) while rebinding 0x%lx to default root\n",
ret, ss_mask);
pr_warn("you may retry by moving them to a different hierarchy and unbinding\n");
}
continue;
}
for_each_subsys_which(ss, tssid, &tmp_ss_mask) {
if (tssid == ssid)
break;
css_clear_dir(cgroup_css(scgrp, ss), dcgrp);
}
return ret;
}
/*
* Nothing can fail from this point on. Remove files for the
* removed subsystems and rebind each subsystem.
*/
for_each_subsys_which(ss, ssid, &ss_mask) {
struct cgroup_root *src_root = ss->root;
struct cgroup *scgrp = &src_root->cgrp;
struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
struct css_set *cset;
WARN_ON(!css || cgroup_css(dcgrp, ss));
css_clear_dir(css, NULL);
RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
rcu_assign_pointer(dcgrp->subsys[ssid], css);
ss->root = dst_root;
css->cgroup = dcgrp;
down_write(&css_set_rwsem);
hash_for_each(css_set_table, i, cset, hlist)
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
up_write(&css_set_rwsem);
src_root->subsys_mask &= ~(1 << ssid);
scgrp->subtree_control &= ~(1 << ssid);
cgroup_refresh_child_subsys_mask(scgrp);
/* default hierarchy doesn't enable controllers by default */
dst_root->subsys_mask |= 1 << ssid;
if (dst_root == &cgrp_dfl_root) {
static_branch_enable(cgroup_subsys_on_dfl_key[ssid]);
} else {
dcgrp->subtree_control |= 1 << ssid;
cgroup_refresh_child_subsys_mask(dcgrp);
static_branch_disable(cgroup_subsys_on_dfl_key[ssid]);
}
if (ss->bind)
ss->bind(css);
}
kernfs_activate(dcgrp->kn);
return 0;
}
static int cgroup_show_options(struct seq_file *seq,
struct kernfs_root *kf_root)
{
struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_subsys *ss;
int ssid;
if (root != &cgrp_dfl_root)
for_each_subsys(ss, ssid)
if (root->subsys_mask & (1 << ssid))
seq_show_option(seq, ss->legacy_name, NULL);
if (root->flags & CGRP_ROOT_NOPREFIX)
seq_puts(seq, ",noprefix");
if (root->flags & CGRP_ROOT_XATTR)
seq_puts(seq, ",xattr");
spin_lock(&release_agent_path_lock);
if (strlen(root->release_agent_path))
seq_show_option(seq, "release_agent",
root->release_agent_path);
spin_unlock(&release_agent_path_lock);
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_show_option(seq, "name", root->name);
return 0;
}
struct cgroup_sb_opts {
unsigned long subsys_mask;
unsigned int flags;
char *release_agent;
bool cpuset_clone_children;
char *name;
/* User explicitly requested empty subsystem */
bool none;
};
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
char *token, *o = data;
bool all_ss = false, one_ss = false;
unsigned long mask = -1UL;
struct cgroup_subsys *ss;
int nr_opts = 0;
int i;
#ifdef CONFIG_CPUSETS
mask = ~(1U << cpuset_cgrp_id);
#endif
memset(opts, 0, sizeof(*opts));
while ((token = strsep(&o, ",")) != NULL) {
nr_opts++;
if (!*token)
return -EINVAL;
if (!strcmp(token, "none")) {
/* Explicitly have no subsystems */
opts->none = true;
continue;
}
if (!strcmp(token, "all")) {
/* Mutually exclusive option 'all' + subsystem name */
if (one_ss)
return -EINVAL;
all_ss = true;
continue;
}
if (!strcmp(token, "__DEVEL__sane_behavior")) {
opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
continue;
}
if (!strcmp(token, "noprefix")) {
opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
}
if (!strcmp(token, "clone_children")) {
opts->cpuset_clone_children = true;
continue;
}
if (!strcmp(token, "xattr")) {
opts->flags |= CGRP_ROOT_XATTR;
continue;
}
if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
opts->release_agent =
kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
continue;
}
if (!strncmp(token, "name=", 5)) {
const char *name = token + 5;
/* Can't specify an empty name */
if (!strlen(name))
return -EINVAL;
/* Must match [\w.-]+ */
for (i = 0; i < strlen(name); i++) {
char c = name[i];
if (isalnum(c))
continue;
if ((c == '.') || (c == '-') || (c == '_'))
continue;
return -EINVAL;
}
/* Specifying two names is forbidden */
if (opts->name)
return -EINVAL;
opts->name = kstrndup(name,
MAX_CGROUP_ROOT_NAMELEN - 1,
GFP_KERNEL);
if (!opts->name)
return -ENOMEM;
continue;
}
for_each_subsys(ss, i) {
if (strcmp(token, ss->legacy_name))
continue;
if (!cgroup_ssid_enabled(i))
continue;
/* Mutually exclusive option 'all' + subsystem name */
if (all_ss)
return -EINVAL;
opts->subsys_mask |= (1 << i);
one_ss = true;
break;
}
if (i == CGROUP_SUBSYS_COUNT)
return -ENOENT;
}
if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
if (nr_opts != 1) {
pr_err("sane_behavior: no other mount options allowed\n");
return -EINVAL;
}
return 0;
}
/*
* If the 'all' option was specified select all the subsystems,
* otherwise if 'none', 'name=' and a subsystem name options were
* not specified, let's default to 'all'
*/
if (all_ss || (!one_ss && !opts->none && !opts->name))
for_each_subsys(ss, i)
if (cgroup_ssid_enabled(i))
opts->subsys_mask |= (1 << i);
/*
* We either have to specify by name or by subsystems. (So all
* empty hierarchies must have a name).
*/
if (!opts->subsys_mask && !opts->name)
return -EINVAL;
/*
* Option noprefix was introduced just for backward compatibility
* with the old cpuset, so we allow noprefix only if mounting just
* the cpuset subsystem.
*/
if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
return -EINVAL;
/* Can't specify "none" and some subsystems */
if (opts->subsys_mask && opts->none)
return -EINVAL;
return 0;
}
static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
int ret = 0;
struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_sb_opts opts;
unsigned long added_mask, removed_mask;
if (root == &cgrp_dfl_root) {
pr_err("remount is not allowed\n");
return -EINVAL;
}
mutex_lock(&cgroup_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
if (ret)
goto out_unlock;
if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n",
task_tgid_nr(current), current->comm);
added_mask = opts.subsys_mask & ~root->subsys_mask;
removed_mask = root->subsys_mask & ~opts.subsys_mask;
/* Don't allow flags or name to change at remount */
if ((opts.flags ^ root->flags) ||
(opts.name && strcmp(opts.name, root->name))) {
pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n",
opts.flags, opts.name ?: "", root->flags, root->name);
ret = -EINVAL;
goto out_unlock;
}
/* remounting is not allowed for populated hierarchies */
if (!list_empty(&root->cgrp.self.children)) {
ret = -EBUSY;
goto out_unlock;
}
ret = rebind_subsystems(root, added_mask);
if (ret)
goto out_unlock;
rebind_subsystems(&cgrp_dfl_root, removed_mask);
if (opts.release_agent) {
spin_lock(&release_agent_path_lock);
strcpy(root->release_agent_path, opts.release_agent);
spin_unlock(&release_agent_path_lock);
}
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
mutex_unlock(&cgroup_mutex);
return ret;
}
/*
* To reduce the fork() overhead for systems that are not actually using
* their cgroups capability, we don't maintain the lists running through
* each css_set to its tasks until we see the list actually used - in other
* words after the first mount.
*/
static bool use_task_css_set_links __read_mostly;
static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
down_write(&css_set_rwsem);
if (use_task_css_set_links)
goto out_unlock;
use_task_css_set_links = true;
/*
* We need tasklist_lock because RCU is not safe against
* while_each_thread(). Besides, a forking task that has passed
* cgroup_post_fork() without seeing use_task_css_set_links = 1
* is not guaranteed to have its child immediately visible in the
* tasklist if we walk through it with RCU.
*/
read_lock(&tasklist_lock);
do_each_thread(g, p) {
WARN_ON_ONCE(!list_empty(&p->cg_list) ||
task_css_set(p) != &init_css_set);
/*
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
* Do it while holding siglock so that we don't end up
* racing against cgroup_exit().
*/
spin_lock_irq(&p->sighand->siglock);
if (!(p->flags & PF_EXITING)) {
struct css_set *cset = task_css_set(p);
list_add(&p->cg_list, &cset->tasks);
get_css_set(cset);
}
spin_unlock_irq(&p->sighand->siglock);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
out_unlock:
up_write(&css_set_rwsem);
}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
struct cgroup_subsys *ss;
int ssid;
INIT_LIST_HEAD(&cgrp->self.sibling);
INIT_LIST_HEAD(&cgrp->self.children);
INIT_LIST_HEAD(&cgrp->self.files);
INIT_LIST_HEAD(&cgrp->cset_links);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
cgrp->self.cgroup = cgrp;
cgrp->self.flags |= CSS_ONLINE;
for_each_subsys(ss, ssid)
INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
init_waitqueue_head(&cgrp->offline_waitq);
INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
}
static void init_cgroup_root(struct cgroup_root *root,
struct cgroup_sb_opts *opts)
{
struct cgroup *cgrp = &root->cgrp;
INIT_LIST_HEAD(&root->root_list);
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
init_cgroup_housekeeping(cgrp);
idr_init(&root->cgroup_idr);
root->flags = opts->flags;
if (opts->release_agent)
strcpy(root->release_agent_path, opts->release_agent);
if (opts->name)
strcpy(root->name, opts->name);
if (opts->cpuset_clone_children)
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
{
LIST_HEAD(tmp_links);
struct cgroup *root_cgrp = &root->cgrp;
struct css_set *cset;
int i, ret;
lockdep_assert_held(&cgroup_mutex);
ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL);
if (ret < 0)
goto out;
root_cgrp->id = ret;
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
GFP_KERNEL);
if (ret)
goto out;
/*
* We're accessing css_set_count without locking css_set_rwsem here,
* but that's OK - it can only be increased by someone holding
* cgroup_lock, and that's us. The worst that can happen is that we
* have some link structures left over
*/
ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
if (ret)
goto cancel_ref;
ret = cgroup_init_root_id(root);
if (ret)
goto cancel_ref;
root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
KERNFS_ROOT_CREATE_DEACTIVATED,
root_cgrp);
if (IS_ERR(root->kf_root)) {
ret = PTR_ERR(root->kf_root);
goto exit_root_id;
}
root_cgrp->kn = root->kf_root->kn;
ret = css_populate_dir(&root_cgrp->self, NULL);
if (ret)
goto destroy_root;
ret = rebind_subsystems(root, ss_mask);
if (ret)
goto destroy_root;
/*
* There must be no failure case after here, since rebinding takes
* care of subsystems' refcounts, which are explicitly dropped in
* the failure exit path.
*/
list_add(&root->root_list, &cgroup_roots);
cgroup_root_count++;
/*
* Link the root cgroup in this hierarchy into all the css_set
* objects.
*/
down_write(&css_set_rwsem);
hash_for_each(css_set_table, i, cset, hlist)
link_css_set(&tmp_links, cset, root_cgrp);
up_write(&css_set_rwsem);
BUG_ON(!list_empty(&root_cgrp->self.children));
BUG_ON(atomic_read(&root->nr_cgrps) != 1);
kernfs_activate(root_cgrp->kn);
ret = 0;
goto out;
destroy_root:
kernfs_destroy_root(root->kf_root);
root->kf_root = NULL;
exit_root_id:
cgroup_exit_root_id(root);
cancel_ref:
percpu_ref_exit(&root_cgrp->self.refcnt);
out:
free_cgrp_cset_links(&tmp_links);
return ret;
}
static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
struct cgroup_root *root;
struct cgroup_sb_opts opts;
struct dentry *dentry;
int ret;
int i;
bool new_sb;
/*
* The first time anyone tries to mount a cgroup, enable the list
* linking each css_set to its tasks and fix up all existing tasks.
*/
if (!use_task_css_set_links)
cgroup_enable_task_cg_lists();
mutex_lock(&cgroup_mutex);
/* First find the desired set of subsystems */
ret = parse_cgroupfs_options(data, &opts);
if (ret)
goto out_unlock;
/* look for a matching existing root */
if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
cgrp_dfl_root_visible = true;
root = &cgrp_dfl_root;
cgroup_get(&root->cgrp);
ret = 0;
goto out_unlock;
}
/*
* Destruction of cgroup root is asynchronous, so subsystems may
* still be dying after the previous unmount. Let's drain the
* dying subsystems. We just need to ensure that the ones
* unmounted previously finish dying and don't care about new ones
* starting. Testing ref liveliness is good enough.
*/
for_each_subsys(ss, i) {
if (!(opts.subsys_mask & (1 << i)) ||
ss->root == &cgrp_dfl_root)
continue;
if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
mutex_unlock(&cgroup_mutex);
msleep(10);
ret = restart_syscall();
goto out_free;
}
cgroup_put(&ss->root->cgrp);
}
for_each_root(root) {
bool name_match = false;
if (root == &cgrp_dfl_root)
continue;
/*
* If we asked for a name then it must match. Also, if
* name matches but sybsys_mask doesn't, we should fail.
* Remember whether name matched.
*/
if (opts.name) {
if (strcmp(opts.name, root->name))
continue;
name_match = true;
}
/*
* If we asked for subsystems (or explicitly for no
* subsystems) then they must match.
*/
if ((opts.subsys_mask || opts.none) &&
(opts.subsys_mask != root->subsys_mask)) {
if (!name_match)
continue;
ret = -EBUSY;
goto out_unlock;
}
if (root->flags ^ opts.flags)
pr_warn("new mount options do not match the existing superblock, will be ignored\n");
/*
* We want to reuse @root whose lifetime is governed by its
* ->cgrp. Let's check whether @root is alive and keep it
* that way. As cgroup_kill_sb() can happen anytime, we
* want to block it by pinning the sb so that @root doesn't
* get killed before mount is complete.
*
* With the sb pinned, tryget_live can reliably indicate
* whether @root can be reused. If it's being killed,
* drain it. We can use wait_queue for the wait but this
* path is super cold. Let's just sleep a bit and retry.
*/
pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
if (IS_ERR(pinned_sb) ||
!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
mutex_unlock(&cgroup_mutex);
if (!IS_ERR_OR_NULL(pinned_sb))
deactivate_super(pinned_sb);
msleep(10);
ret = restart_syscall();
goto out_free;
}
ret = 0;
goto out_unlock;
}
/*
* No such thing, create a new one. name= matching without subsys
* specification is allowed for already existing hierarchies but we
* can't create new one without subsys specification.
*/
if (!opts.subsys_mask && !opts.none) {
ret = -EINVAL;
goto out_unlock;
}
root = kzalloc(sizeof(*root), GFP_KERNEL);
if (!root) {
ret = -ENOMEM;
goto out_unlock;
}
init_cgroup_root(root, &opts);
ret = cgroup_setup_root(root, opts.subsys_mask);
if (ret)
cgroup_free_root(root);
out_unlock:
mutex_unlock(&cgroup_mutex);
out_free:
kfree(opts.release_agent);
kfree(opts.name);
if (ret)
return ERR_PTR(ret);
dentry = kernfs_mount(fs_type, flags, root->kf_root,
CGROUP_SUPER_MAGIC, &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
/*
* If @pinned_sb, we're reusing an existing root and holding an
* extra ref on its sb. Mount is complete. Put the extra ref.
*/
if (pinned_sb) {
WARN_ON(new_sb);
deactivate_super(pinned_sb);
}
return dentry;
}
static void cgroup_kill_sb(struct super_block *sb)
{
struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
struct cgroup_root *root = cgroup_root_from_kf(kf_root);
/*
* If @root doesn't have any mounts or children, start killing it.
* This prevents new mounts by disabling percpu_ref_tryget_live().
* cgroup_mount() may wait for @root's release.
*
* And don't kill the default root.
*/
if (!list_empty(&root->cgrp.self.children) ||
root == &cgrp_dfl_root)
cgroup_put(&root->cgrp);
else
percpu_ref_kill(&root->cgrp.self.refcnt);
kernfs_kill_sb(sb);
}
static struct file_system_type cgroup_fs_type = {
.name = "cgroup",
.mount = cgroup_mount,
.kill_sb = cgroup_kill_sb,
};
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
* @buf: the buffer to write the path into
* @buflen: the length of the buffer
*
* Determine @task's cgroup on the first (the one with the lowest non-zero
* hierarchy_id) cgroup hierarchy and copy its path into @buf. This
* function grabs cgroup_mutex and shouldn't be used inside locks used by
* cgroup controller callbacks.
*
* Return value is the same as kernfs_path().
*/
char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
struct cgroup_root *root;
struct cgroup *cgrp;
int hierarchy_id = 1;
char *path = NULL;
mutex_lock(&cgroup_mutex);
down_read(&css_set_rwsem);
root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
if (root) {
cgrp = task_cgroup_from_root(task, root);
path = cgroup_path(cgrp, buf, buflen);
} else {
/* if no hierarchy exists, everyone is in "/" */
if (strlcpy(buf, "/", buflen) < buflen)
path = buf;
}
up_read(&css_set_rwsem);
mutex_unlock(&cgroup_mutex);
return path;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
/* used to track tasks and other necessary states during migration */
struct cgroup_taskset {
/* the src and dst cset list running through cset->mg_node */
struct list_head src_csets;
struct list_head dst_csets;
/*
* Fields for cgroup_taskset_*() iteration.
*
* Before migration is committed, the target migration tasks are on
* ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of
* the csets on ->dst_csets. ->csets point to either ->src_csets
* or ->dst_csets depending on whether migration is committed.
*
* ->cur_csets and ->cur_task point to the current task position
* during iteration.
*/
struct list_head *csets;
struct css_set *cur_cset;
struct task_struct *cur_task;
};
/**
* cgroup_taskset_first - reset taskset and return the first task
* @tset: taskset of interest
*
* @tset iteration is initialized and the first task is returned.
*/
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
{
tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
tset->cur_task = NULL;
return cgroup_taskset_next(tset);
}
/**
* cgroup_taskset_next - iterate to the next task in taskset
* @tset: taskset of interest
*
* Return the next task in @tset. Iteration must have been initialized
* with cgroup_taskset_first().
*/
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
{
struct css_set *cset = tset->cur_cset;
struct task_struct *task = tset->cur_task;
while (&cset->mg_node != tset->csets) {
if (!task)
task = list_first_entry(&cset->mg_tasks,
struct task_struct, cg_list);
else
task = list_next_entry(task, cg_list);
if (&task->cg_list != &cset->mg_tasks) {
tset->cur_cset = cset;
tset->cur_task = task;
return task;
}
cset = list_next_entry(cset, mg_node);
task = NULL;
}
return NULL;
}
/**
* cgroup_task_migrate - move a task from one cgroup to another.
* @old_cgrp: the cgroup @tsk is being migrated from
* @tsk: the task being migrated
* @new_cset: the new css_set @tsk is being attached to
*
* Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked.
*/
static void cgroup_task_migrate(struct cgroup *old_cgrp,
struct task_struct *tsk,
struct css_set *new_cset)
{
struct css_set *old_cset;
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_rwsem);
/*
* We are synchronized through cgroup_threadgroup_rwsem against
* PF_EXITING setting such that we can't race against cgroup_exit()
* changing the css_set to init_css_set and dropping the old one.
*/
WARN_ON_ONCE(tsk->flags & PF_EXITING);
old_cset = task_css_set(tsk);
get_css_set(new_cset);
rcu_assign_pointer(tsk->cgroups, new_cset);
list_move_tail(&tsk->cg_list, &new_cset->mg_tasks);
/*
* We just gained a reference on old_cset by taking it from the
* task. As trading it for new_cset is protected by cgroup_mutex,
* we're safe to drop it here; it will be freed under RCU.
*/
put_css_set_locked(old_cset);
}
/**
* cgroup_migrate_finish - cleanup after attach
* @preloaded_csets: list of preloaded css_sets
*
* Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See
* those functions for details.
*/
static void cgroup_migrate_finish(struct list_head *preloaded_csets)
{
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
down_write(&css_set_rwsem);
list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cset = NULL;
list_del_init(&cset->mg_preload_node);
put_css_set_locked(cset);
}
up_write(&css_set_rwsem);
}
/**
* cgroup_migrate_add_src - add a migration source css_set
* @src_cset: the source css_set to add
* @dst_cgrp: the destination cgroup
* @preloaded_csets: list of preloaded css_sets
*
* Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin
* @src_cset and add it to @preloaded_csets, which should later be cleaned
* up by cgroup_migrate_finish().
*
* This function may be called without holding cgroup_threadgroup_rwsem
* even if the target is a process. Threads may be created and destroyed
* but as long as cgroup_mutex is not dropped, no new css_set can be put
* into play and the preloaded css_sets are guaranteed to cover all
* migrations.
*/
static void cgroup_migrate_add_src(struct css_set *src_cset,
struct cgroup *dst_cgrp,
struct list_head *preloaded_csets)
{
struct cgroup *src_cgrp;
lockdep_assert_held(&cgroup_mutex);
lockdep_assert_held(&css_set_rwsem);
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
if (!list_empty(&src_cset->mg_preload_node))
return;
WARN_ON(src_cset->mg_src_cgrp);
WARN_ON(!list_empty(&src_cset->mg_tasks));
WARN_ON(!list_empty(&src_cset->mg_node));
src_cset->mg_src_cgrp = src_cgrp;
get_css_set(src_cset);
list_add(&src_cset->mg_preload_node, preloaded_csets);
}
/**
* cgroup_migrate_prepare_dst - prepare destination css_sets for migration
* @dst_cgrp: the destination cgroup (may be %NULL)
* @preloaded_csets: list of preloaded source css_sets
*
* Tasks are about to be moved to @dst_cgrp and all the source css_sets
* have been preloaded to @preloaded_csets. This function looks up and
* pins all destination css_sets, links each to its source, and append them
* to @preloaded_csets. If @dst_cgrp is %NULL, the destination of each
* source css_set is assumed to be its cgroup on the default hierarchy.
*
* This function must be called after cgroup_migrate_add_src() has been
* called on each migration source css_set. After migration is performed
* using cgroup_migrate(), cgroup_migrate_finish() must be called on
* @preloaded_csets.
*/
static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
struct list_head *preloaded_csets)
{
LIST_HEAD(csets);
struct css_set *src_cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
/*
* Except for the root, child_subsys_mask must be zero for a cgroup
* with tasks so that child cgroups don't compete against tasks.
*/
if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) &&
dst_cgrp->child_subsys_mask)
return -EBUSY;
/* look up the dst cset for each src cset and link it to src */
list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) {
struct css_set *dst_cset;
dst_cset = find_css_set(src_cset,
dst_cgrp ?: src_cset->dfl_cgrp);
if (!dst_cset)
goto err;
WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
/*
* If src cset equals dst, it's noop. Drop the src.
* cgroup_migrate() will skip the cset too. Note that we
* can't handle src == dst as some nodes are used by both.
*/
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
list_del_init(&src_cset->mg_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
}
src_cset->mg_dst_cset = dst_cset;
if (list_empty(&dst_cset->mg_preload_node))
list_add(&dst_cset->mg_preload_node, &csets);
else
put_css_set(dst_cset);
}
list_splice_tail(&csets, preloaded_csets);
return 0;
err:
cgroup_migrate_finish(&csets);
return -ENOMEM;
}
/**
* cgroup_migrate - migrate a process or task to a cgroup
* @cgrp: the destination cgroup
* @leader: the leader of the process or the task to migrate
* @threadgroup: whether @leader points to the whole process or a single task
*
* Migrate a process or task denoted by @leader to @cgrp. If migrating a
* process, the caller must be holding cgroup_threadgroup_rwsem. The
* caller is also responsible for invoking cgroup_migrate_add_src() and
* cgroup_migrate_prepare_dst() on the targets before invoking this
* function and following up with cgroup_migrate_finish().
*
* As long as a controller's ->can_attach() doesn't fail, this function is
* guaranteed to succeed. This means that, excluding ->can_attach()
* failure, when migrating multiple targets, the success or failure can be
* decided for all targets by invoking group_migrate_prepare_dst() before
* actually starting migrating.
*/
static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
bool threadgroup)
{
struct cgroup_taskset tset = {
.src_csets = LIST_HEAD_INIT(tset.src_csets),
.dst_csets = LIST_HEAD_INIT(tset.dst_csets),
.csets = &tset.src_csets,
};
struct cgroup_subsys_state *css, *failed_css = NULL;
struct css_set *cset, *tmp_cset;
struct task_struct *task, *tmp_task;
int i, ret;
/*
* Prevent freeing of tasks while we take a snapshot. Tasks that are
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
down_write(&css_set_rwsem);
rcu_read_lock();
task = leader;
do {
/* @task either already exited or can't exit until the end */
if (task->flags & PF_EXITING)
goto next;
/* leave @task alone if post_fork() hasn't linked it yet */
if (list_empty(&task->cg_list))
goto next;
cset = task_css_set(task);
if (!cset->mg_src_cgrp)
goto next;
list_move_tail(&task->cg_list, &cset->mg_tasks);
if (list_empty(&cset->mg_node))
list_add_tail(&cset->mg_node, &tset.src_csets);
if (list_empty(&cset->mg_dst_cset->mg_node))
list_move_tail(&cset->mg_dst_cset->mg_node,
&tset.dst_csets);
next:
if (!threadgroup)
break;
} while_each_thread(leader, task);
rcu_read_unlock();
up_write(&css_set_rwsem);
/* methods shouldn't be called if no task is actually migrating */
if (list_empty(&tset.src_csets))
return 0;
/* check that we can legitimately attach to the cgroup */
for_each_e_css(css, i, cgrp) {
if (css->ss->can_attach) {
ret = css->ss->can_attach(css, &tset);
if (ret) {
failed_css = css;
goto out_cancel_attach;
}
}
}
/*
* Now that we're guaranteed success, proceed to move all tasks to
* the new cgroup. There are no failure cases after here, so this
* is the commit point.
*/
down_write(&css_set_rwsem);
list_for_each_entry(cset, &tset.src_csets, mg_node) {
list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list)
cgroup_task_migrate(cset->mg_src_cgrp, task,
cset->mg_dst_cset);
}
up_write(&css_set_rwsem);
/*
* Migration is committed, all target tasks are now on dst_csets.
* Nothing is sensitive to fork() after this point. Notify
* controllers that migration is complete.
*/
tset.csets = &tset.dst_csets;
for_each_e_css(css, i, cgrp)
if (css->ss->attach)
css->ss->attach(css, &tset);
ret = 0;
goto out_release_tset;
out_cancel_attach:
for_each_e_css(css, i, cgrp) {
if (css == failed_css)
break;
if (css->ss->cancel_attach)
css->ss->cancel_attach(css, &tset);
}
out_release_tset:
down_write(&css_set_rwsem);
list_splice_init(&tset.dst_csets, &tset.src_csets);
list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) {
list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
list_del_init(&cset->mg_node);
}
up_write(&css_set_rwsem);
return ret;
}
/**
* cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
* @dst_cgrp: the cgroup to attach to
* @leader: the task or the leader of the threadgroup to be attached
* @threadgroup: attach the whole threadgroup?
*
* Call holding cgroup_mutex and cgroup_threadgroup_rwsem.
*/
static int cgroup_attach_task(struct cgroup *dst_cgrp,
struct task_struct *leader, bool threadgroup)
{
LIST_HEAD(preloaded_csets);
struct task_struct *task;
int ret;
/* look up all src csets */
down_read(&css_set_rwsem);
rcu_read_lock();
task = leader;
do {
cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
&preloaded_csets);
if (!threadgroup)
break;
} while_each_thread(leader, task);
rcu_read_unlock();
up_read(&css_set_rwsem);
/* prepare dst csets and commit */
ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
if (!ret)
ret = cgroup_migrate(dst_cgrp, leader, threadgroup);
cgroup_migrate_finish(&preloaded_csets);
return ret;
}
static int cgroup_procs_write_permission(struct task_struct *task,
struct cgroup *dst_cgrp,
struct kernfs_open_file *of)
{
const struct cred *cred = current_cred();
const struct cred *tcred = get_task_cred(task);
int ret = 0;
/*
* even if we're attaching all tasks in the thread group, we only
* need to check permissions on one of them.
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
!uid_eq(cred->euid, tcred->suid))
ret = -EACCES;
if (!ret && cgroup_on_dfl(dst_cgrp)) {
struct super_block *sb = of->file->f_path.dentry->d_sb;
struct cgroup *cgrp;
struct inode *inode;
down_read(&css_set_rwsem);
cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
up_read(&css_set_rwsem);
while (!cgroup_is_descendant(dst_cgrp, cgrp))
cgrp = cgroup_parent(cgrp);
ret = -ENOMEM;
inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
if (inode) {
ret = inode_permission(inode, MAY_WRITE);
iput(inode);
}
}
put_cred(tcred);
return ret;
}
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
* function to attach either it or all tasks in its threadgroup. Will lock
* cgroup_mutex and threadgroup.
*/
static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off, bool threadgroup)
{
struct task_struct *tsk;
struct cgroup *cgrp;
pid_t pid;
int ret;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
cgrp = cgroup_kn_lock_live(of->kn);
if (!cgrp)
return -ENODEV;
percpu_down_write(&cgroup_threadgroup_rwsem);
rcu_read_lock();
if (pid) {
tsk = find_task_by_vpid(pid);
if (!tsk) {
ret = -ESRCH;
goto out_unlock_rcu;
}
} else {
tsk = current;
}
if (threadgroup)
tsk = tsk->group_leader;
/*
* Workqueue threads may acquire PF_NO_SETAFFINITY and become
* trapped in a cpuset, or RT worker may be born in a cgroup
* with no rt_runtime allocated. Just say no.
*/
if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out_unlock_rcu;
}
get_task_struct(tsk);
rcu_read_unlock();
ret = cgroup_procs_write_permission(tsk, cgrp, of);
if (!ret)
ret = cgroup_attach_task(cgrp, tsk, threadgroup);
put_task_struct(tsk);
goto out_unlock_threadgroup;
out_unlock_rcu:
rcu_read_unlock();
out_unlock_threadgroup:
percpu_up_write(&cgroup_threadgroup_rwsem);
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
/**
* cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
* @from: attach to all cgroups of a given task
* @tsk: the task to be attached
*/
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
{
struct cgroup_root *root;
int retval = 0;
mutex_lock(&cgroup_mutex);
for_each_root(root) {
struct cgroup *from_cgrp;
if (root == &cgrp_dfl_root)
continue;
down_read(&css_set_rwsem);
from_cgrp = task_cgroup_from_root(from, root);
up_read(&css_set_rwsem);
retval = cgroup_attach_task(from_cgrp, tsk, false);
if (retval)
break;
}
mutex_unlock(&cgroup_mutex);
return retval;
}
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
static ssize_t cgroup_tasks_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
return __cgroup_procs_write(of, buf, nbytes, off, false);
}
static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
return __cgroup_procs_write(of, buf, nbytes, off, true);
}
static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cgroup *cgrp;
BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
cgrp = cgroup_kn_lock_live(of->kn);
if (!cgrp)
return -ENODEV;
spin_lock(&release_agent_path_lock);
strlcpy(cgrp->root->release_agent_path, strstrip(buf),
sizeof(cgrp->root->release_agent_path));
spin_unlock(&release_agent_path_lock);
cgroup_kn_unlock(of->kn);
return nbytes;
}
static int cgroup_release_agent_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
spin_lock(&release_agent_path_lock);
seq_puts(seq, cgrp->root->release_agent_path);
spin_unlock(&release_agent_path_lock);
seq_putc(seq, '\n');
return 0;
}
static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
{
seq_puts(seq, "0\n");
return 0;
}
static void cgroup_print_ss_mask(struct seq_file *seq, unsigned long ss_mask)
{
struct cgroup_subsys *ss;
bool printed = false;
int ssid;
for_each_subsys_which(ss, ssid, &ss_mask) {
if (printed)
seq_putc(seq, ' ');
seq_printf(seq, "%s", ss->name);
printed = true;
}
if (printed)
seq_putc(seq, '\n');
}
/* show controllers which are currently attached to the default hierarchy */
static int cgroup_root_controllers_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgrp->root->subsys_mask &
~cgrp_dfl_root_inhibit_ss_mask);
return 0;
}
/* show controllers which are enabled from the parent */
static int cgroup_controllers_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgroup_parent(cgrp)->subtree_control);
return 0;
}
/* show controllers which are enabled for a given cgroup's children */
static int cgroup_subtree_control_show(struct seq_file *seq, void *v)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgrp->subtree_control);
return 0;
}
/**
* cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy
* @cgrp: root of the subtree to update csses for
*
* @cgrp's child_subsys_mask has changed and its subtree's (self excluded)
* css associations need to be updated accordingly. This function looks up
* all css_sets which are attached to the subtree, creates the matching
* updated css_sets and migrates the tasks to the new ones.
*/
static int cgroup_update_dfl_csses(struct cgroup *cgrp)
{
LIST_HEAD(preloaded_csets);
struct cgroup_subsys_state *css;
struct css_set *src_cset;
int ret;
lockdep_assert_held(&cgroup_mutex);
percpu_down_write(&cgroup_threadgroup_rwsem);
/* look up all csses currently attached to @cgrp's subtree */
down_read(&css_set_rwsem);
css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
struct cgrp_cset_link *link;
/* self is not affected by child_subsys_mask change */
if (css->cgroup == cgrp)
continue;
list_for_each_entry(link, &css->cgroup->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, cgrp,
&preloaded_csets);
}
up_read(&css_set_rwsem);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets);
if (ret)
goto out_finish;
list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
struct task_struct *last_task = NULL, *task;
/* src_csets precede dst_csets, break on the first dst_cset */
if (!src_cset->mg_src_cgrp)
break;
/*
* All tasks in src_cset need to be migrated to the
* matching dst_cset. Empty it process by process. We
* walk tasks but migrate processes. The leader might even
* belong to a different cset but such src_cset would also
* be among the target src_csets because the default
* hierarchy enforces per-process membership.
*/
while (true) {
down_read(&css_set_rwsem);
task = list_first_entry_or_null(&src_cset->tasks,
struct task_struct, cg_list);
if (task) {
task = task->group_leader;
WARN_ON_ONCE(!task_css_set(task)->mg_src_cgrp);
get_task_struct(task);
}
up_read(&css_set_rwsem);
if (!task)
break;
/* guard against possible infinite loop */
if (WARN(last_task == task,
"cgroup: update_dfl_csses failed to make progress, aborting in inconsistent state\n"))
goto out_finish;
last_task = task;
ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
put_task_struct(task);
if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
goto out_finish;
}
}
out_finish:
cgroup_migrate_finish(&preloaded_csets);
percpu_up_write(&cgroup_threadgroup_rwsem);
return ret;
}
/* change the enabled child controllers for a cgroup in the default hierarchy */
static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
unsigned long enable = 0, disable = 0;
unsigned long css_enable, css_disable, old_sc, new_sc, old_ss, new_ss;
struct cgroup *cgrp, *child;
struct cgroup_subsys *ss;
char *tok;
int ssid, ret;
/*
* Parse input - space separated list of subsystem names prefixed
* with either + or -.
*/
buf = strstrip(buf);
while ((tok = strsep(&buf, " "))) {
unsigned long tmp_ss_mask = ~cgrp_dfl_root_inhibit_ss_mask;
if (tok[0] == '\0')
continue;
for_each_subsys_which(ss, ssid, &tmp_ss_mask) {
if (!cgroup_ssid_enabled(ssid) ||
strcmp(tok + 1, ss->name))
continue;
if (*tok == '+') {
enable |= 1 << ssid;
disable &= ~(1 << ssid);
} else if (*tok == '-') {
disable |= 1 << ssid;
enable &= ~(1 << ssid);
} else {
return -EINVAL;
}
break;
}
if (ssid == CGROUP_SUBSYS_COUNT)
return -EINVAL;
}
cgrp = cgroup_kn_lock_live(of->kn);
if (!cgrp)
return -ENODEV;
for_each_subsys(ss, ssid) {
if (enable & (1 << ssid)) {
if (cgrp->subtree_control & (1 << ssid)) {
enable &= ~(1 << ssid);
continue;
}
/* unavailable or not enabled on the parent? */
if (!(cgrp_dfl_root.subsys_mask & (1 << ssid)) ||
(cgroup_parent(cgrp) &&
!(cgroup_parent(cgrp)->subtree_control & (1 << ssid)))) {
ret = -ENOENT;
goto out_unlock;
}
} else if (disable & (1 << ssid)) {
if (!(cgrp->subtree_control & (1 << ssid))) {
disable &= ~(1 << ssid);
continue;
}
/* a child has it enabled? */
cgroup_for_each_live_child(child, cgrp) {
if (child->subtree_control & (1 << ssid)) {
ret = -EBUSY;
goto out_unlock;
}
}
}
}
if (!enable && !disable) {
ret = 0;
goto out_unlock;
}
/*
* Except for the root, subtree_control must be zero for a cgroup
* with tasks so that child cgroups don't compete against tasks.
*/
if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
ret = -EBUSY;
goto out_unlock;
}
/*
* Update subsys masks and calculate what needs to be done. More
* subsystems than specified may need to be enabled or disabled
* depending on subsystem dependencies.
*/
old_sc = cgrp->subtree_control;
old_ss = cgrp->child_subsys_mask;
new_sc = (old_sc | enable) & ~disable;
new_ss = cgroup_calc_child_subsys_mask(cgrp, new_sc);
css_enable = ~old_ss & new_ss;
css_disable = old_ss & ~new_ss;
enable |= css_enable;
disable |= css_disable;
/*
* Because css offlining is asynchronous, userland might try to
* re-enable the same controller while the previous instance is
* still around. In such cases, wait till it's gone using
* offline_waitq.
*/
for_each_subsys_which(ss, ssid, &css_enable) {
cgroup_for_each_live_child(child, cgrp) {
DEFINE_WAIT(wait);
if (!cgroup_css(child, ss))
continue;
cgroup_get(child);
prepare_to_wait(&child->offline_waitq, &wait,
TASK_UNINTERRUPTIBLE);
cgroup_kn_unlock(of->kn);
schedule();
finish_wait(&child->offline_waitq, &wait);
cgroup_put(child);
return restart_syscall();
}
}
cgrp->subtree_control = new_sc;
cgrp->child_subsys_mask = new_ss;
/*
* Create new csses or make the existing ones visible. A css is
* created invisible if it's being implicitly enabled through
* dependency. An invisible css is made visible when the userland
* explicitly enables it.
*/
for_each_subsys(ss, ssid) {
if (!(enable & (1 << ssid)))
continue;
cgroup_for_each_live_child(child, cgrp) {
if (css_enable & (1 << ssid))
ret = create_css(child, ss,
cgrp->subtree_control & (1 << ssid));
else
ret = css_populate_dir(cgroup_css(child, ss),
NULL);
if (ret)
goto err_undo_css;
}
}
/*
* At this point, cgroup_e_css() results reflect the new csses
* making the following cgroup_update_dfl_csses() properly update
* css associations of all tasks in the subtree.
*/
ret = cgroup_update_dfl_csses(cgrp);
if (ret)
goto err_undo_css;
/*
* All tasks are migrated out of disabled csses. Kill or hide
* them. A css is hidden when the userland requests it to be
* disabled while other subsystems are still depending on it. The
* css must not actively control resources and be in the vanilla
* state if it's made visible again later. Controllers which may
* be depended upon should provide ->css_reset() for this purpose.
*/
for_each_subsys(ss, ssid) {
if (!(disable & (1 << ssid)))
continue;
cgroup_for_each_live_child(child, cgrp) {
struct cgroup_subsys_state *css = cgroup_css(child, ss);
if (css_disable & (1 << ssid)) {
kill_css(css);
} else {
css_clear_dir(css, NULL);
if (ss->css_reset)
ss->css_reset(css);
}
}
}
/*
* The effective csses of all the descendants (excluding @cgrp) may
* have changed. Subsystems can optionally subscribe to this event
* by implementing ->css_e_css_changed() which is invoked if any of
* the effective csses seen from the css's cgroup may have changed.
*/
for_each_subsys(ss, ssid) {
struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss);
struct cgroup_subsys_state *css;
if (!ss->css_e_css_changed || !this_css)
continue;
css_for_each_descendant_pre(css, this_css)
if (css != this_css)
ss->css_e_css_changed(css);
}
kernfs_activate(cgrp->kn);
ret = 0;
out_unlock:
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;
err_undo_css:
cgrp->subtree_control = old_sc;
cgrp->child_subsys_mask = old_ss;
for_each_subsys(ss, ssid) {
if (!(enable & (1 << ssid)))
continue;
cgroup_for_each_live_child(child, cgrp) {
struct cgroup_subsys_state *css = cgroup_css(child, ss);
if (!css)
continue;
if (css_enable & (1 << ssid))
kill_css(css);
else
css_clear_dir(css, NULL);
}
}
goto out_unlock;
}
static int cgroup_events_show(struct seq_file *seq, void *v)
{
seq_printf(seq, "populated %d\n",
(bool)seq_css(seq)->cgroup->populated_cnt);
return 0;
}
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of->kn->priv;
struct cgroup_subsys_state *css;
int ret;
if (cft->write)
return cft->write(of, buf, nbytes, off);
/*
* kernfs guarantees that a file isn't deleted with operations in
* flight, which means that the matching css is and stays alive and
* doesn't need to be pinned. The RCU locking is not necessary
* either. It's just for the convenience of using cgroup_css().
*/
rcu_read_lock();
css = cgroup_css(cgrp, cft->ss);
rcu_read_unlock();
if (cft->write_u64) {
unsigned long long v;
ret = kstrtoull(buf, 0, &v);
if (!ret)
ret = cft->write_u64(css, cft, v);
} else if (cft->write_s64) {
long long v;
ret = kstrtoll(buf, 0, &v);
if (!ret)
ret = cft->write_s64(css, cft, v);
} else {
ret = -EINVAL;
}
return ret ?: nbytes;
}
static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
return seq_cft(seq)->seq_start(seq, ppos);
}
static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
return seq_cft(seq)->seq_next(seq, v, ppos);
}
static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
seq_cft(seq)->seq_stop(seq, v);
}
static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
struct cftype *cft = seq_cft(m);
struct cgroup_subsys_state *css = seq_css(m);
if (cft->seq_show)
return cft->seq_show(m, arg);
if (cft->read_u64)
seq_printf(m, "%llu\n", cft->read_u64(css, cft));
else if (cft->read_s64)
seq_printf(m, "%lld\n", cft->read_s64(css, cft));
else
return -EINVAL;
return 0;
}
static struct kernfs_ops cgroup_kf_single_ops = {
.atomic_write_len = PAGE_SIZE,
.write = cgroup_file_write,
.seq_show = cgroup_seqfile_show,
};
static struct kernfs_ops cgroup_kf_ops = {
.atomic_write_len = PAGE_SIZE,
.write = cgroup_file_write,
.seq_start = cgroup_seqfile_start,
.seq_next = cgroup_seqfile_next,
.seq_stop = cgroup_seqfile_stop,
.seq_show = cgroup_seqfile_show,
};
/*
* cgroup_rename - Only allow simple rename of directories in place.
*/
static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
const char *new_name_str)
{
struct cgroup *cgrp = kn->priv;
int ret;
if (kernfs_type(kn) != KERNFS_DIR)
return -ENOTDIR;
if (kn->parent != new_parent)
return -EIO;
/*
* This isn't a proper migration and its usefulness is very
* limited. Disallow on the default hierarchy.
*/
if (cgroup_on_dfl(cgrp))
return -EPERM;
/*
* We're gonna grab cgroup_mutex which nests outside kernfs
* active_ref. kernfs_rename() doesn't require active_ref
* protection. Break them before grabbing cgroup_mutex.
*/
kernfs_break_active_protection(new_parent);
kernfs_break_active_protection(kn);
mutex_lock(&cgroup_mutex);
ret = kernfs_rename(kn, new_parent, new_name_str);
mutex_unlock(&cgroup_mutex);
kernfs_unbreak_active_protection(kn);
kernfs_unbreak_active_protection(new_parent);
return ret;
}
/* set uid and gid of cgroup dirs and files to that of the creator */
static int cgroup_kn_set_ugid(struct kernfs_node *kn)
{
struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
.ia_uid = current_fsuid(),
.ia_gid = current_fsgid(), };
if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
return 0;
return kernfs_setattr(kn, &iattr);
}
static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
struct cftype *cft)
{
char name[CGROUP_FILE_NAME_MAX];
struct kernfs_node *kn;
struct lock_class_key *key = NULL;
int ret;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
key = &cft->lockdep_key;
#endif
kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
cgroup_file_mode(cft), 0, cft->kf_ops, cft,
NULL, key);
if (IS_ERR(kn))
return PTR_ERR(kn);
ret = cgroup_kn_set_ugid(kn);
if (ret) {
kernfs_remove(kn);
return ret;
}
if (cft->file_offset) {
struct cgroup_file *cfile = (void *)css + cft->file_offset;
kernfs_get(kn);
cfile->kn = kn;
list_add(&cfile->node, &css->files);
}
return 0;
}
/**
* cgroup_addrm_files - add or remove files to a cgroup directory
* @css: the target css
* @cgrp: the target cgroup (usually css->cgroup)
* @cfts: array of cftypes to be added
* @is_add: whether to add or remove
*
* Depending on @is_add, add or remove files defined by @cfts on @cgrp.
* For removals, this function never fails.
*/
static int cgroup_addrm_files(struct cgroup_subsys_state *css,
struct cgroup *cgrp, struct cftype cfts[],
bool is_add)
{
struct cftype *cft, *cft_end = NULL;
int ret;
lockdep_assert_held(&cgroup_mutex);
restart:
for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) {
/* does cft->flags tell us to skip this file on @cgrp? */
if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
continue;
if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
continue;
if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp))
continue;
if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
continue;
if (is_add) {
ret = cgroup_add_file(css, cgrp, cft);
if (ret) {
pr_warn("%s: failed to add %s, err=%d\n",
__func__, cft->name, ret);
cft_end = cft;
is_add = false;
goto restart;
}
} else {
cgroup_rm_file(cgrp, cft);
}
}
return 0;
}
static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
{
LIST_HEAD(pending);
struct cgroup_subsys *ss = cfts[0].ss;
struct cgroup *root = &ss->root->cgrp;
struct cgroup_subsys_state *css;
int ret = 0;
lockdep_assert_held(&cgroup_mutex);
/* add/rm files for all cgroups created before */
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
if (cgroup_is_dead(cgrp))
continue;
ret = cgroup_addrm_files(css, cgrp, cfts, is_add);
if (ret)
break;
}
if (is_add && !ret)
kernfs_activate(root->kn);
return ret;
}
static void cgroup_exit_cftypes(struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft->name[0] != '\0'; cft++) {
/* free copy for custom atomic_write_len, see init_cftypes() */
if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
kfree(cft->kf_ops);
cft->kf_ops = NULL;
cft->ss = NULL;
/* revert flags set by cgroup core while adding @cfts */
cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
}
}
static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft->name[0] != '\0'; cft++) {
struct kernfs_ops *kf_ops;
WARN_ON(cft->ss || cft->kf_ops);
if (cft->seq_start)
kf_ops = &cgroup_kf_ops;
else
kf_ops = &cgroup_kf_single_ops;
/*
* Ugh... if @cft wants a custom max_write_len, we need to
* make a copy of kf_ops to set its atomic_write_len.
*/
if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
if (!kf_ops) {
cgroup_exit_cftypes(cfts);
return -ENOMEM;
}
kf_ops->atomic_write_len = cft->max_write_len;
}
cft->kf_ops = kf_ops;
cft->ss = ss;
}
return 0;
}
static int cgroup_rm_cftypes_locked(struct cftype *cfts)
{
lockdep_assert_held(&cgroup_mutex);
if (!cfts || !cfts[0].ss)
return -ENOENT;
list_del(&cfts->node);
cgroup_apply_cftypes(cfts, false);
cgroup_exit_cftypes(cfts);
return 0;
}
/**
* cgroup_rm_cftypes - remove an array of cftypes from a subsystem
* @cfts: zero-length name terminated array of cftypes
*
* Unregister @cfts. Files described by @cfts are removed from all
* existing cgroups and all future cgroups won't have them either. This
* function can be called anytime whether @cfts' subsys is attached or not.
*
* Returns 0 on successful unregistration, -ENOENT if @cfts is not
* registered.
*/
int cgroup_rm_cftypes(struct cftype *cfts)
{
int ret;
mutex_lock(&cgroup_mutex);
ret = cgroup_rm_cftypes_locked(cfts);
mutex_unlock(&cgroup_mutex);
return ret;
}
/**
* cgroup_add_cftypes - add an array of cftypes to a subsystem
* @ss: target cgroup subsystem
* @cfts: zero-length name terminated array of cftypes
*
* Register @cfts to @ss. Files described by @cfts are created for all
* existing cgroups to which @ss is attached and all future cgroups will
* have them too. This function can be called anytime whether @ss is
* attached or not.
*
* Returns 0 on successful registration, -errno on failure. Note that this
* function currently returns 0 as long as @cfts registration is successful
* even if some file creation attempts on existing cgroups fail.
*/
static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
int ret;
if (!cgroup_ssid_enabled(ss->id))
return 0;
if (!cfts || cfts[0].name[0] == '\0')
return 0;
ret = cgroup_init_cftypes(ss, cfts);
if (ret)
return ret;
mutex_lock(&cgroup_mutex);
list_add_tail(&cfts->node, &ss->cfts);
ret = cgroup_apply_cftypes(cfts, true);
if (ret)
cgroup_rm_cftypes_locked(cfts);
mutex_unlock(&cgroup_mutex);
return ret;
}
/**
* cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy
* @ss: target cgroup subsystem
* @cfts: zero-length name terminated array of cftypes
*
* Similar to cgroup_add_cftypes() but the added files are only used for
* the default hierarchy.
*/
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
cft->flags |= __CFTYPE_ONLY_ON_DFL;
return cgroup_add_cftypes(ss, cfts);
}
/**
* cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies
* @ss: target cgroup subsystem
* @cfts: zero-length name terminated array of cftypes
*
* Similar to cgroup_add_cftypes() but the added files are only used for
* the legacy hierarchies.
*/
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
struct cftype *cft;
/*
* If legacy_flies_on_dfl, we want to show the legacy files on the
* dfl hierarchy but iff the target subsystem hasn't been updated
* for the dfl hierarchy yet.
*/
if (!cgroup_legacy_files_on_dfl ||
ss->dfl_cftypes != ss->legacy_cftypes) {
for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
cft->flags |= __CFTYPE_NOT_ON_DFL;
}
return cgroup_add_cftypes(ss, cfts);
}
/**
* cgroup_task_count - count the number of tasks in a cgroup.
* @cgrp: the cgroup in question
*
* Return the number of tasks in the cgroup.
*/
static int cgroup_task_count(const struct cgroup *cgrp)
{
int count = 0;
struct cgrp_cset_link *link;
down_read(&css_set_rwsem);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += atomic_read(&link->cset->refcount);
up_read(&css_set_rwsem);
return count;
}
/**
* css_next_child - find the next child of a given css
* @pos: the current position (%NULL to initiate traversal)
* @parent: css whose children to walk
*
* This function returns the next child of @parent and should be called
* under either cgroup_mutex or RCU read lock. The only requirement is
* that @parent and @pos are accessible. The next sibling is guaranteed to
* be returned regardless of their states.
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*/
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *parent)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/*
* @pos could already have been unlinked from the sibling list.
* Once a cgroup is removed, its ->sibling.next is no longer
* updated when its next sibling changes. CSS_RELEASED is set when
* @pos is taken off list, at which time its next pointer is valid,
* and, as releases are serialized, the one pointed to by the next
* pointer is guaranteed to not have started release yet. This
* implies that if we observe !CSS_RELEASED on @pos in this RCU
* critical section, the one pointed to by its next pointer is
* guaranteed to not have finished its RCU grace period even if we
* have dropped rcu_read_lock() inbetween iterations.
*
* If @pos has CSS_RELEASED set, its next pointer can't be
* dereferenced; however, as each css is given a monotonically
* increasing unique serial number and always appended to the
* sibling list, the next one can be found by walking the parent's
* children until the first css with higher serial number than
* @pos's. While this path can be slower, it happens iff iteration
* races against release and the race window is very small.
*/
if (!pos) {
next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling);
} else if (likely(!(pos->flags & CSS_RELEASED))) {
next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
} else {
list_for_each_entry_rcu(next, &parent->children, sibling)
if (next->serial_nr > pos->serial_nr)
break;
}
/*
* @next, if not pointing to the head, can be dereferenced and is
* the next sibling.
*/
if (&next->sibling != &parent->children)
return next;
return NULL;
}
/**
* css_next_descendant_pre - find the next descendant for pre-order walk
* @pos: the current position (%NULL to initiate traversal)
* @root: css whose descendants to walk
*
* To be used by css_for_each_descendant_pre(). Find the next descendant
* to visit for pre-order traversal of @root's descendants. @root is
* included in the iteration and the first node to be visited.
*
* While this function requires cgroup_mutex or RCU read locking, it
* doesn't require the whole traversal to be contained in a single critical
* section. This function will return the correct next descendant as long
* as both @pos and @root are accessible and @pos is a descendant of @root.
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*/
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *root)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit @root */
if (!pos)
return root;
/* visit the first child if exists */
next = css_next_child(NULL, pos);
if (next)
return next;
/* no child, visit my or the closest ancestor's next sibling */
while (pos != root) {
next = css_next_child(pos, pos->parent);
if (next)
return next;
pos = pos->parent;
}
return NULL;
}
/**
* css_rightmost_descendant - return the rightmost descendant of a css
* @pos: css of interest
*
* Return the rightmost descendant of @pos. If there's no descendant, @pos
* is returned. This can be used during pre-order traversal to skip
* subtree of @pos.
*
* While this function requires cgroup_mutex or RCU read locking, it
* doesn't require the whole traversal to be contained in a single critical
* section. This function will return the correct rightmost descendant as
* long as @pos is accessible.
*/
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last, *tmp;
cgroup_assert_mutex_or_rcu_locked();
do {
last = pos;
/* ->prev isn't RCU safe, walk ->next till the end */
pos = NULL;
css_for_each_child(tmp, last)
pos = tmp;
} while (pos);
return last;
}
static struct cgroup_subsys_state *
css_leftmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last;
do {
last = pos;
pos = css_next_child(NULL, pos);
} while (pos);
return last;
}
/**
* css_next_descendant_post - find the next descendant for post-order walk
* @pos: the current position (%NULL to initiate traversal)
* @root: css whose descendants to walk
*
* To be used by css_for_each_descendant_post(). Find the next descendant
* to visit for post-order traversal of @root's descendants. @root is
* included in the iteration and the last node to be visited.
*
* While this function requires cgroup_mutex or RCU read locking, it
* doesn't require the whole traversal to be contained in a single critical
* section. This function will return the correct next descendant as long
* as both @pos and @cgroup are accessible and @pos is a descendant of
* @cgroup.
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*/
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *root)
{
struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit leftmost descendant which may be @root */
if (!pos)
return css_leftmost_descendant(root);
/* if we visited @root, we're done */
if (pos == root)
return NULL;
/* if there's an unvisited sibling, visit its leftmost descendant */
next = css_next_child(pos, pos->parent);
if (next)
return css_leftmost_descendant(next);
/* no sibling left, visit parent */
return pos->parent;
}
/**
* css_has_online_children - does a css have online children
* @css: the target css
*
* Returns %true if @css has any online children; otherwise, %false. This
* function can be called from any context but the caller is responsible
* for synchronizing against on/offlining as necessary.
*/
bool css_has_online_children(struct cgroup_subsys_state *css)
{
struct cgroup_subsys_state *child;
bool ret = false;
rcu_read_lock();
css_for_each_child(child, css) {
if (child->flags & CSS_ONLINE) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
/**
* css_advance_task_iter - advance a task itererator to the next css_set
* @it: the iterator to advance
*
* Advance @it to the next css_set to walk.
*/
static void css_advance_task_iter(struct css_task_iter *it)
{
struct list_head *l = it->cset_pos;
struct cgrp_cset_link *link;
struct css_set *cset;
/* Advance to the next non-empty css_set */
do {
l = l->next;
if (l == it->cset_head) {
it->cset_pos = NULL;
return;
}
if (it->ss) {
cset = container_of(l, struct css_set,
e_cset_node[it->ss->id]);
} else {
link = list_entry(l, struct cgrp_cset_link, cset_link);
cset = link->cset;
}
} while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
it->cset_pos = l;
if (!list_empty(&cset->tasks))
it->task_pos = cset->tasks.next;
else
it->task_pos = cset->mg_tasks.next;
it->tasks_head = &cset->tasks;
it->mg_tasks_head = &cset->mg_tasks;
}
/**
* css_task_iter_start - initiate task iteration
* @css: the css to walk tasks of
* @it: the task iterator to use
*
* Initiate iteration through the tasks of @css. The caller can call
* css_task_iter_next() to walk through the tasks until the function
* returns NULL. On completion of iteration, css_task_iter_end() must be
* called.
*
* Note that this function acquires a lock which is released when the
* iteration finishes. The caller can't sleep while iteration is in
* progress.
*/
void css_task_iter_start(struct cgroup_subsys_state *css,
struct css_task_iter *it)
__acquires(css_set_rwsem)
{
/* no one should try to iterate before mounting cgroups */
WARN_ON_ONCE(!use_task_css_set_links);
down_read(&css_set_rwsem);
it->ss = css->ss;
if (it->ss)
it->cset_pos = &css->cgroup->e_csets[css->ss->id];
else
it->cset_pos = &css->cgroup->cset_links;
it->cset_head = it->cset_pos;
css_advance_task_iter(it);
}
/**
* css_task_iter_next - return the next task for the iterator
* @it: the task iterator being iterated
*
* The "next" function for task iteration. @it should have been
* initialized via css_task_iter_start(). Returns NULL when the iteration
* reaches the end.
*/
struct task_struct *css_task_iter_next(struct css_task_iter *it)
{
struct task_struct *res;
struct list_head *l = it->task_pos;
/* If the iterator cg is NULL, we have no tasks */
if (!it->cset_pos)
return NULL;
res = list_entry(l, struct task_struct, cg_list);
/*
* Advance iterator to find next entry. cset->tasks is consumed
* first and then ->mg_tasks. After ->mg_tasks, we move onto the
* next cset.
*/
l = l->next;
if (l == it->tasks_head)
l = it->mg_tasks_head->next;
if (l == it->mg_tasks_head)
css_advance_task_iter(it);
else
it->task_pos = l;
return res;
}
/**
* css_task_iter_end - finish task iteration
* @it: the task iterator to finish
*
* Finish task iteration started by css_task_iter_start().
*/
void css_task_iter_end(struct css_task_iter *it)
__releases(css_set_rwsem)
{
up_read(&css_set_rwsem);
}
/**
* cgroup_trasnsfer_tasks - move tasks from one cgroup to another
* @to: cgroup to which the tasks will be moved
* @from: cgroup in which the tasks currently reside
*
* Locking rules between cgroup_post_fork() and the migration path
* guarantee that, if a task is forking while being migrated, the new child
* is guaranteed to be either visible in the source cgroup after the
* parent's migration is complete or put into the target cgroup. No task
* can slip out of migration through forking.
*/
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
{
LIST_HEAD(preloaded_csets);
struct cgrp_cset_link *link;
struct css_task_iter it;
struct task_struct *task;
int ret;
mutex_lock(&cgroup_mutex);
/* all tasks in @from are being moved, all csets are source */
down_read(&css_set_rwsem);
list_for_each_entry(link, &from->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
up_read(&css_set_rwsem);
ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
if (ret)
goto out_err;
/*
* Migrate tasks one-by-one until @form is empty. This fails iff
* ->can_attach() fails.
*/
do {
css_task_iter_start(&from->self, &it);
task = css_task_iter_next(&it);
if (task)
get_task_struct(task);
css_task_iter_end(&it);
if (task) {
ret = cgroup_migrate(to, task, false);
put_task_struct(task);
}
} while (task && !ret);
out_err:
cgroup_migrate_finish(&preloaded_csets);
mutex_unlock(&cgroup_mutex);
return ret;
}
/*
* Stuff for reading the 'tasks'/'procs' files.
*
* Reading this file can return large amounts of data if a cgroup has
* *lots* of attached tasks. So it may need several calls to read(),
* but we cannot guarantee that the information we produce is correct
* unless we produce it entirely atomically.
*
*/
/* which pidlist file are we talking about? */
enum cgroup_filetype {
CGROUP_FILE_PROCS,
CGROUP_FILE_TASKS,
};
/*
* A pidlist is a list of pids that virtually represents the contents of one
* of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
* a pair (one each for procs, tasks) for each pid namespace that's relevant
* to the cgroup.
*/
struct cgroup_pidlist {
/*
* used to find which pidlist is wanted. doesn't change as long as
* this particular list stays in the list.
*/
struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
/* array of xids */
pid_t *list;
/* how many elements the above list has */
int length;
/* each of these stored in a list by its cgroup */
struct list_head links;
/* pointer to the cgroup we belong to, for list removal purposes */
struct cgroup *owner;
/* for delayed destruction */
struct delayed_work destroy_dwork;
};
/*
* The following two functions "fix" the issue where there are more pids
* than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
* TODO: replace with a kernel-wide solution to this problem
*/
#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count)
{
if (PIDLIST_TOO_LARGE(count))
return vmalloc(count * sizeof(pid_t));
else
return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
static void pidlist_free(void *p)
{
kvfree(p);
}
/*
* Used to destroy all pidlists lingering waiting for destroy timer. None
* should be left afterwards.
*/
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
{
struct cgroup_pidlist *l, *tmp_l;
mutex_lock(&cgrp->pidlist_mutex);
list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
mutex_unlock(&cgrp->pidlist_mutex);
flush_workqueue(cgroup_pidlist_destroy_wq);
BUG_ON(!list_empty(&cgrp->pidlists));
}
static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
{
struct delayed_work *dwork = to_delayed_work(work);
struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
destroy_dwork);
struct cgroup_pidlist *tofree = NULL;
mutex_lock(&l->owner->pidlist_mutex);
/*
* Destroy iff we didn't get queued again. The state won't change
* as destroy_dwork can only be queued while locked.
*/
if (!delayed_work_pending(dwork)) {
list_del(&l->links);
pidlist_free(l->list);
put_pid_ns(l->key.ns);
tofree = l;
}
mutex_unlock(&l->owner->pidlist_mutex);
kfree(tofree);
}
/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
* Returns the number of unique elements.
*/
static int pidlist_uniq(pid_t *list, int length)
{
int src, dest = 1;
/*
* we presume the 0th element is unique, so i starts at 1. trivial
* edge cases first; no work needs to be done for either
*/
if (length == 0 || length == 1)
return length;
/* src and dest walk down the list; dest counts unique elements */
for (src = 1; src < length; src++) {
/* find next unique element */
while (list[src] == list[src-1]) {
src++;
if (src == length)
goto after;
}
/* dest always points to where the next unique element goes */
list[dest] = list[src];
dest++;
}
after:
return dest;
}
/*
* The two pid files - task and cgroup.procs - guaranteed that the result
* is sorted, which forced this whole pidlist fiasco. As pid order is
* different per namespace, each namespace needs differently sorted list,
* making it impossible to use, for example, single rbtree of member tasks
* sorted by task pointer. As pidlists can be fairly large, allocating one
* per open file is dangerous, so cgroup had to implement shared pool of
* pidlists keyed by cgroup and namespace.
*
* All this extra complexity was caused by the original implementation
* committing to an entirely unnecessary property. In the long term, we
* want to do away with it. Explicitly scramble sort order if on the
* default hierarchy so that no such expectation exists in the new
* interface.
*
* Scrambling is done by swapping every two consecutive bits, which is
* non-identity one-to-one mapping which disturbs sort order sufficiently.
*/
static pid_t pid_fry(pid_t pid)
{
unsigned a = pid & 0x55555555;
unsigned b = pid & 0xAAAAAAAA;
return (a << 1) | (b >> 1);
}
static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
{
if (cgroup_on_dfl(cgrp))
return pid_fry(pid);
else
return pid;
}
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
static int fried_cmppid(const void *a, const void *b)
{
return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
}
static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
enum cgroup_filetype type)
{
struct cgroup_pidlist *l;
/* don't need task_nsproxy() if we're looking at ourself */
struct pid_namespace *ns = task_active_pid_ns(current);
lockdep_assert_held(&cgrp->pidlist_mutex);
list_for_each_entry(l, &cgrp->pidlists, links)
if (l->key.type == type && l->key.ns == ns)
return l;
return NULL;
}
/*
* find the appropriate pidlist for our purpose (given procs vs tasks)
* returns with the lock on that pidlist already held, and takes care
* of the use count, or returns NULL with no locks held if we're out of
* memory.
*/
static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
enum cgroup_filetype type)
{
struct cgroup_pidlist *l;
lockdep_assert_held(&cgrp->pidlist_mutex);
l = cgroup_pidlist_find(cgrp, type);
if (l)
return l;
/* entry not found; create a new one */
l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
if (!l)
return l;
INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
l->key.type = type;
/* don't need task_nsproxy() if we're looking at ourself */
l->key.ns = get_pid_ns(task_active_pid_ns(current));
l->owner = cgrp;
list_add(&l->links, &cgrp->pidlists);
return l;
}
/*
* Load a cgroup's pidarray with either procs' tgids or tasks' pids
*/
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
struct cgroup_pidlist **lp)
{
pid_t *array;
int length;
int pid, n = 0; /* used for populating the array */
struct css_task_iter it;
struct task_struct *tsk;
struct cgroup_pidlist *l;
lockdep_assert_held(&cgrp->pidlist_mutex);
/*
* If cgroup gets more users after we read count, we won't have
* enough space - tough. This race is indistinguishable to the
* caller from the case that the additional cgroup users didn't
* show up until sometime later on.
*/
length = cgroup_task_count(cgrp);
array = pidlist_allocate(length);
if (!array)
return -ENOMEM;
/* now, populate the array */
css_task_iter_start(&cgrp->self, &it);
while ((tsk = css_task_iter_next(&it))) {
if (unlikely(n == length))
break;
/* get tgid or pid for procs or tasks file respectively */
if (type == CGROUP_FILE_PROCS)
pid = task_tgid_vnr(tsk);
else
pid = task_pid_vnr(tsk);
if (pid > 0) /* make sure to only use valid results */
array[n++] = pid;
}
css_task_iter_end(&it);
length = n;
/* now sort & (if procs) strip out duplicates */
if (cgroup_on_dfl(cgrp))
sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
else
sort(array, length, sizeof(pid_t), cmppid, NULL);
if (type == CGROUP_FILE_PROCS)
length = pidlist_uniq(array, length);
l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
pidlist_free(array);
return -ENOMEM;
}
/* store array, freeing old if necessary */
pidlist_free(l->list);
l->list = array;
l->length = length;
*lp = l;
return 0;
}
/**
* cgroupstats_build - build and fill cgroupstats
* @stats: cgroupstats to fill information into
* @dentry: A dentry entry belonging to the cgroup for which stats have
* been requested.
*
* Build and fill cgroupstats so that taskstats can export it to user
* space.
*/
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct cgroup *cgrp;
struct css_task_iter it;
struct task_struct *tsk;
/* it should be kernfs_node belonging to cgroupfs and is a directory */
if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
kernfs_type(kn) != KERNFS_DIR)
return -EINVAL;
mutex_lock(&cgroup_mutex);
/*
* We aren't being called from kernfs and there's no guarantee on
* @kn->priv's validity. For this and css_tryget_online_from_dir(),
* @kn->priv is RCU safe. Let's do the RCU dancing.
*/
rcu_read_lock();
cgrp = rcu_dereference(kn->priv);
if (!cgrp || cgroup_is_dead(cgrp)) {
rcu_read_unlock();
mutex_unlock(&cgroup_mutex);
return -ENOENT;
}
rcu_read_unlock();
css_task_iter_start(&cgrp->self, &it);
while ((tsk = css_task_iter_next(&it))) {
switch (tsk->state) {
case TASK_RUNNING:
stats->nr_running++;
break;
case TASK_INTERRUPTIBLE:
stats->nr_sleeping++;
break;
case TASK_UNINTERRUPTIBLE:
stats->nr_uninterruptible++;
break;
case TASK_STOPPED:
stats->nr_stopped++;
break;
default:
if (delayacct_is_task_waiting_on_io(tsk))
stats->nr_io_wait++;
break;
}
}
css_task_iter_end(&it);
mutex_unlock(&cgroup_mutex);
return 0;
}
/*
* seq_file methods for the tasks/procs files. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
* in the cgroup->l->list array.
*/
static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
/*
* Initially we receive a position value that corresponds to
* one more than the last pid shown (or 0 on the first call or
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
struct kernfs_open_file *of = s->private;
struct cgroup *cgrp = seq_css(s)->cgroup;
struct cgroup_pidlist *l;
enum cgroup_filetype type = seq_cft(s)->private;
int index = 0, pid = *pos;
int *iter, ret;
mutex_lock(&cgrp->pidlist_mutex);
/*
* !NULL @of->priv indicates that this isn't the first start()
* after open. If the matching pidlist is around, we can use that.
* Look for it. Note that @of->priv can't be used directly. It
* could already have been destroyed.
*/
if (of->priv)
of->priv = cgroup_pidlist_find(cgrp, type);
/*
* Either this is the first start() after open or the matching
* pidlist has been destroyed inbetween. Create a new one.
*/
if (!of->priv) {
ret = pidlist_array_load(cgrp, type,
(struct cgroup_pidlist **)&of->priv);
if (ret)
return ERR_PTR(ret);
}
l = of->priv;
if (pid) {
int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
index = mid;
break;
} else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
if (index >= l->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
iter = l->list + index;
*pos = cgroup_pid_fry(cgrp, *iter);
return iter;
}
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
if (l)
mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
CGROUP_PIDLIST_DESTROY_DELAY);
mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
struct kernfs_open_file *of = s->private;
struct cgroup_pidlist *l = of->priv;
pid_t *p = v;
pid_t *end = l->list + l->length;
/*
* Advance to the next pid in the array. If this goes off the
* end, we're done
*/
p++;
if (p >= end) {
return NULL;
} else {
*pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
return p;
}
}
static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
seq_printf(s, "%d\n", *(int *)v);
return 0;
}
static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return notify_on_release(css->cgroup);
}
static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
if (val)
set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
else
clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
return 0;
}
static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
}
static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
if (val)
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
else
clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
return 0;
}
/* cgroup core interface files for the default hierarchy */
static struct cftype cgroup_dfl_base_files[] = {
{
.name = "cgroup.procs",
.file_offset = offsetof(struct cgroup, procs_file),
.seq_start = cgroup_pidlist_start,
.seq_next = cgroup_pidlist_next,
.seq_stop = cgroup_pidlist_stop,
.seq_show = cgroup_pidlist_show,
.private = CGROUP_FILE_PROCS,
.write = cgroup_procs_write,
},
{
.name = "cgroup.controllers",
.flags = CFTYPE_ONLY_ON_ROOT,
.seq_show = cgroup_root_controllers_show,
},
{
.name = "cgroup.controllers",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cgroup_controllers_show,
},
{
.name = "cgroup.subtree_control",
.seq_show = cgroup_subtree_control_show,
.write = cgroup_subtree_control_write,
},
{
.name = "cgroup.events",
.flags = CFTYPE_NOT_ON_ROOT,
.file_offset = offsetof(struct cgroup, events_file),
.seq_show = cgroup_events_show,
},
{ } /* terminate */
};
/* cgroup core interface files for the legacy hierarchies */
static struct cftype cgroup_legacy_base_files[] = {
{
.name = "cgroup.procs",
.seq_start = cgroup_pidlist_start,
.seq_next = cgroup_pidlist_next,
.seq_stop = cgroup_pidlist_stop,
.seq_show = cgroup_pidlist_show,
.private = CGROUP_FILE_PROCS,
.write = cgroup_procs_write,
},
{
.name = "cgroup.clone_children",
.read_u64 = cgroup_clone_children_read,
.write_u64 = cgroup_clone_children_write,
},
{
.name = "cgroup.sane_behavior",
.flags = CFTYPE_ONLY_ON_ROOT,
.seq_show = cgroup_sane_behavior_show,
},
{
.name = "tasks",
.seq_start = cgroup_pidlist_start,
.seq_next = cgroup_pidlist_next,
.seq_stop = cgroup_pidlist_stop,
.seq_show = cgroup_pidlist_show,
.private = CGROUP_FILE_TASKS,
.write = cgroup_tasks_write,
},
{
.name = "notify_on_release",
.read_u64 = cgroup_read_notify_on_release,
.write_u64 = cgroup_write_notify_on_release,
},
{
.name = "release_agent",
.flags = CFTYPE_ONLY_ON_ROOT,
.seq_show = cgroup_release_agent_show,
.write = cgroup_release_agent_write,
.max_write_len = PATH_MAX - 1,
},
{ } /* terminate */
};
/*
* css destruction is four-stage process.
*
* 1. Destruction starts. Killing of the percpu_ref is initiated.
* Implemented in kill_css().
*
* 2. When the percpu_ref is confirmed to be visible as killed on all CPUs
* and thus css_tryget_online() is guaranteed to fail, the css can be
* offlined by invoking offline_css(). After offlining, the base ref is
* put. Implemented in css_killed_work_fn().
*
* 3. When the percpu_ref reaches zero, the only possible remaining
* accessors are inside RCU read sections. css_release() schedules the
* RCU callback.
*
* 4. After the grace period, the css can be freed. Implemented in
* css_free_work_fn().
*
* It is actually hairier because both step 2 and 4 require process context
* and thus involve punting to css->destroy_work adding two additional
* steps to the already complex sequence.
*/
static void css_free_work_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
struct cgroup_file *cfile;
percpu_ref_exit(&css->refcnt);
list_for_each_entry(cfile, &css->files, node)
kernfs_put(cfile->kn);
if (ss) {
/* css free path */
int id = css->id;
if (css->parent)
css_put(css->parent);
ss->css_free(css);
cgroup_idr_remove(&ss->css_idr, id);
cgroup_put(cgrp);
} else {
/* cgroup free path */
atomic_dec(&cgrp->root->nr_cgrps);
cgroup_pidlist_destroy_all(cgrp);
cancel_work_sync(&cgrp->release_agent_work);
if (cgroup_parent(cgrp)) {
/*
* We get a ref to the parent, and put the ref when
* this cgroup is being freed, so it's guaranteed
* that the parent won't be destroyed before its
* children.
*/
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
kfree(cgrp);
} else {
/*
* This is root cgroup's refcnt reaching zero,
* which indicates that the root should be
* released.
*/
cgroup_destroy_root(cgrp->root);
}
}
}
static void css_free_rcu_fn(struct rcu_head *rcu_head)
{
struct cgroup_subsys_state *css =
container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
INIT_WORK(&css->destroy_work, css_free_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
static void css_release_work_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup_subsys *ss = css->ss;
struct cgroup *cgrp = css->cgroup;
mutex_lock(&cgroup_mutex);
css->flags |= CSS_RELEASED;
list_del_rcu(&css->sibling);
if (ss) {
/* css release path */
cgroup_idr_replace(&ss->css_idr, NULL, css->id);
if (ss->css_released)
ss->css_released(css);
} else {
/* cgroup release path */
cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
cgrp->id = -1;
/*
* There are two control paths which try to determine
* cgroup from dentry without going through kernfs -
* cgroupstats_build() and css_tryget_online_from_dir().
* Those are supported by RCU protecting clearing of
* cgrp->kn->priv backpointer.
*/
RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
}
mutex_unlock(&cgroup_mutex);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
static void css_release(struct percpu_ref *ref)
{
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_release_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
static void init_and_link_css(struct cgroup_subsys_state *css,
struct cgroup_subsys *ss, struct cgroup *cgrp)
{
lockdep_assert_held(&cgroup_mutex);
cgroup_get(cgrp);
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
css->ss = ss;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
INIT_LIST_HEAD(&css->files);
css->serial_nr = css_serial_nr_next++;
if (cgroup_parent(cgrp)) {
css->parent = cgroup_css(cgroup_parent(cgrp), ss);
css_get(css->parent);
}
BUG_ON(cgroup_css(cgrp, ss));
}
/* invoke ->css_online() on a new CSS and mark it online if successful */
static int online_css(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
int ret = 0;
lockdep_assert_held(&cgroup_mutex);
if (ss->css_online)
ret = ss->css_online(css);
if (!ret) {
css->flags |= CSS_ONLINE;
rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
}
return ret;
}
/* if the CSS is online, invoke ->css_offline() on it and mark it offline */
static void offline_css(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
lockdep_assert_held(&cgroup_mutex);
if (!(css->flags & CSS_ONLINE))
return;
if (ss->css_offline)
ss->css_offline(css);
css->flags &= ~CSS_ONLINE;
RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
wake_up_all(&css->cgroup->offline_waitq);
}
/**
* create_css - create a cgroup_subsys_state
* @cgrp: the cgroup new css will be associated with
* @ss: the subsys of new css
* @visible: whether to create control knobs for the new css or not
*
* Create a new css associated with @cgrp - @ss pair. On success, the new
* css is online and installed in @cgrp with all interface files created if
* @visible. Returns 0 on success, -errno on failure.
*/
static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
bool visible)
{
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss);
struct cgroup_subsys_state *css;
int err;
lockdep_assert_held(&cgroup_mutex);
css = ss->css_alloc(parent_css);
if (IS_ERR(css))
return PTR_ERR(css);
init_and_link_css(css, ss, cgrp);
err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL);
if (err)
goto err_free_css;
err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
if (err < 0)
goto err_free_percpu_ref;
css->id = err;
if (visible) {
err = css_populate_dir(css, NULL);
if (err)
goto err_free_id;
}
/* @css is ready to be brought online now, make it visible */
list_add_tail_rcu(&css->sibling, &parent_css->children);
cgroup_idr_replace(&ss->css_idr, css, css->id);
err = online_css(css);
if (err)
goto err_list_del;
if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
cgroup_parent(parent)) {
pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
current->comm, current->pid, ss->name);
if (!strcmp(ss->name, "memory"))
pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
ss->warned_broken_hierarchy = true;
}
return 0;
err_list_del:
list_del_rcu(&css->sibling);
css_clear_dir(css, NULL);
err_free_id:
cgroup_idr_remove(&ss->css_idr, css->id);
err_free_percpu_ref:
percpu_ref_exit(&css->refcnt);
err_free_css:
call_rcu(&css->rcu_head, css_free_rcu_fn);
return err;
}
static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
umode_t mode)
{
struct cgroup *parent, *cgrp;
struct cgroup_root *root;
struct cgroup_subsys *ss;
struct kernfs_node *kn;
int ssid, ret;
/* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
*/
if (strchr(name, '\n'))
return -EINVAL;
parent = cgroup_kn_lock_live(parent_kn);
if (!parent)
return -ENODEV;
root = parent->root;
/* allocate the cgroup and its ID, 0 is reserved for the root */
cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
if (!cgrp) {
ret = -ENOMEM;
goto out_unlock;
}
ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
if (ret)
goto out_free_cgrp;
/*
* Temporarily set the pointer to NULL, so idr_find() won't return
* a half-baked cgroup.
*/
cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
if (cgrp->id < 0) {
ret = -ENOMEM;
goto out_cancel_ref;
}
init_cgroup_housekeeping(cgrp);
cgrp->self.parent = &parent->self;
cgrp->root = root;
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
/* create the directory */
kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
if (IS_ERR(kn)) {
ret = PTR_ERR(kn);
goto out_free_id;
}
cgrp->kn = kn;
/*
* This extra ref will be put in cgroup_free_fn() and guarantees
* that @cgrp->kn is always accessible.
*/
kernfs_get(kn);
cgrp->self.serial_nr = css_serial_nr_next++;
/* allocation complete, commit to creation */
list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
atomic_inc(&root->nr_cgrps);
cgroup_get(parent);
/*
* @cgrp is now fully operational. If something fails after this
* point, it'll be released via the normal destruction path.
*/
cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
ret = cgroup_kn_set_ugid(kn);
if (ret)
goto out_destroy;
ret = css_populate_dir(&cgrp->self, NULL);
if (ret)
goto out_destroy;
/* let's create and online css's */
for_each_subsys(ss, ssid) {
if (parent->child_subsys_mask & (1 << ssid)) {
ret = create_css(cgrp, ss,
parent->subtree_control & (1 << ssid));
if (ret)
goto out_destroy;
}
}
/*
* On the default hierarchy, a child doesn't automatically inherit
* subtree_control from the parent. Each is configured manually.
*/
if (!cgroup_on_dfl(cgrp)) {
cgrp->subtree_control = parent->subtree_control;
cgroup_refresh_child_subsys_mask(cgrp);
}
kernfs_activate(kn);
ret = 0;
goto out_unlock;
out_free_id:
cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_cancel_ref:
percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
kfree(cgrp);
out_unlock:
cgroup_kn_unlock(parent_kn);
return ret;
out_destroy:
cgroup_destroy_locked(cgrp);
goto out_unlock;
}
/*
* This is called when the refcnt of a css is confirmed to be killed.
* css_tryget_online() is now guaranteed to fail. Tell the subsystem to
* initate destruction and put the css ref from kill_css().
*/
static void css_killed_work_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, destroy_work);
mutex_lock(&cgroup_mutex);
offline_css(css);
mutex_unlock(&cgroup_mutex);
css_put(css);
}
/* css kill confirmation processing requires process context, bounce */
static void css_killed_ref_fn(struct percpu_ref *ref)
{
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_killed_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
/**
* kill_css - destroy a css
* @css: css to destroy
*
* This function initiates destruction of @css by removing cgroup interface
* files and putting its base reference. ->css_offline() will be invoked
* asynchronously once css_tryget_online() is guaranteed to fail and when
* the reference count reaches zero, @css will be released.
*/
static void kill_css(struct cgroup_subsys_state *css)
{
lockdep_assert_held(&cgroup_mutex);
/*
* This must happen before css is disassociated with its cgroup.
* See seq_css() for details.
*/
css_clear_dir(css, NULL);
/*
* Killing would put the base ref, but we need to keep it alive
* until after ->css_offline().
*/
css_get(css);
/*
* cgroup core guarantees that, by the time ->css_offline() is
* invoked, no new css reference will be given out via
* css_tryget_online(). We can't simply call percpu_ref_kill() and
* proceed to offlining css's because percpu_ref_kill() doesn't
* guarantee that the ref is seen as killed on all CPUs on return.
*
* Use percpu_ref_kill_and_confirm() to get notifications as each
* css is confirmed to be seen as killed on all CPUs.
*/
percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
}
/**
* cgroup_destroy_locked - the first stage of cgroup destruction
* @cgrp: cgroup to be destroyed
*
* css's make use of percpu refcnts whose killing latency shouldn't be
* exposed to userland and are RCU protected. Also, cgroup core needs to
* guarantee that css_tryget_online() won't succeed by the time
* ->css_offline() is invoked. To satisfy all the requirements,
* destruction is implemented in the following two steps.
*
* s1. Verify @cgrp can be destroyed and mark it dying. Remove all
* userland visible parts and start killing the percpu refcnts of
* css's. Set up so that the next stage will be kicked off once all
* the percpu refcnts are confirmed to be killed.
*
* s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the
* rest of destruction. Once all cgroup references are gone, the
* cgroup is RCU-freed.
*
* This function implements s1. After this step, @cgrp is gone as far as
* the userland is concerned and a new cgroup with the same name may be
* created. As cgroup doesn't care about the names internally, this
* doesn't cause any problem.
*/
static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
struct cgroup_subsys_state *css;
bool empty;
int ssid;
lockdep_assert_held(&cgroup_mutex);
/*
* css_set_rwsem synchronizes access to ->cset_links and prevents
* @cgrp from being removed while put_css_set() is in progress.
*/
down_read(&css_set_rwsem);
empty = list_empty(&cgrp->cset_links);
up_read(&css_set_rwsem);
if (!empty)
return -EBUSY;
/*
* Make sure there's no live children. We can't test emptiness of
* ->self.children as dead children linger on it while being
* drained; otherwise, "rmdir parent/child parent" may fail.
*/
if (css_has_online_children(&cgrp->self))
return -EBUSY;
/*
* Mark @cgrp dead. This prevents further task migration and child
* creation by disabling cgroup_lock_live_group().
*/
cgrp->self.flags &= ~CSS_ONLINE;
/* initiate massacre of all css's */
for_each_css(css, ssid, cgrp)
kill_css(css);
/*
* Remove @cgrp directory along with the base files. @cgrp has an
* extra ref on its kn.
*/
kernfs_remove(cgrp->kn);
check_for_release(cgroup_parent(cgrp));
/* put the base reference */
percpu_ref_kill(&cgrp->self.refcnt);
return 0;
};
static int cgroup_rmdir(struct kernfs_node *kn)
{
struct cgroup *cgrp;
int ret = 0;
cgrp = cgroup_kn_lock_live(kn);
if (!cgrp)
return 0;
ret = cgroup_destroy_locked(cgrp);
cgroup_kn_unlock(kn);
return ret;
}
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
.remount_fs = cgroup_remount,
.show_options = cgroup_show_options,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.rename = cgroup_rename,
};
static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
{
struct cgroup_subsys_state *css;
printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
mutex_lock(&cgroup_mutex);
idr_init(&ss->css_idr);
INIT_LIST_HEAD(&ss->cfts);
/* Create the root cgroup state for this subsystem */
ss->root = &cgrp_dfl_root;
css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
/* We don't handle early failures gracefully */
BUG_ON(IS_ERR(css));
init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
/*
* Root csses are never destroyed and we can't initialize
* percpu_ref during early init. Disable refcnting.
*/
css->flags |= CSS_NO_REF;
if (early) {
/* allocation can't be done safely during early init */
css->id = 1;
} else {
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
BUG_ON(css->id < 0);
}
/* Update the init_css_set to contain a subsys
* pointer to this state - since the subsystem is
* newly registered, all tasks and hence the
* init_css_set is in the subsystem's root cgroup. */
init_css_set.subsys[ss->id] = css;
have_fork_callback |= (bool)ss->fork << ss->id;
have_exit_callback |= (bool)ss->exit << ss->id;
have_canfork_callback |= (bool)ss->can_fork << ss->id;
/* At system boot, before all subsystems have been
* registered, no tasks have been forked, so we don't
* need to invoke fork callbacks here. */
BUG_ON(!list_empty(&init_task.tasks));
BUG_ON(online_css(css));
mutex_unlock(&cgroup_mutex);
}
/**
* cgroup_init_early - cgroup initialization at system boot
*
* Initialize cgroups at system boot, and initialize any
* subsystems that request early init.
*/
int __init cgroup_init_early(void)
{
static struct cgroup_sb_opts __initdata opts;
struct cgroup_subsys *ss;
int i;
init_cgroup_root(&cgrp_dfl_root, &opts);
cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
for_each_subsys(ss, i) {
WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
"invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
ss->id, ss->name);
WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
"cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
ss->id = i;
ss->name = cgroup_subsys_name[i];
if (!ss->legacy_name)
ss->legacy_name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss, true);
}
return 0;
}
/**
* cgroup_init - cgroup initialization
*
* Register cgroup filesystem and /proc file, and initialize
* any subsystems that didn't request early init.
*/
int __init cgroup_init(void)
{
struct cgroup_subsys *ss;
unsigned long key;
int ssid, err;
BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
mutex_lock(&cgroup_mutex);
/* Add init_css_set to the hash table */
key = css_set_hash(init_css_set.subsys);
hash_add(css_set_table, &init_css_set.hlist, key);
BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
mutex_unlock(&cgroup_mutex);
for_each_subsys(ss, ssid) {
if (ss->early_init) {
struct cgroup_subsys_state *css =
init_css_set.subsys[ss->id];
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
GFP_KERNEL);
BUG_ON(css->id < 0);
} else {
cgroup_init_subsys(ss, false);
}
list_add_tail(&init_css_set.e_cset_node[ssid],
&cgrp_dfl_root.cgrp.e_csets[ssid]);
/*
* Setting dfl_root subsys_mask needs to consider the
* disabled flag and cftype registration needs kmalloc,
* both of which aren't available during early_init.
*/
if (!cgroup_ssid_enabled(ssid))
continue;
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
if (cgroup_legacy_files_on_dfl && !ss->dfl_cftypes)
ss->dfl_cftypes = ss->legacy_cftypes;
if (!ss->dfl_cftypes)
cgrp_dfl_root_inhibit_ss_mask |= 1 << ss->id;
if (ss->dfl_cftypes == ss->legacy_cftypes) {
WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes));
} else {
WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
}
if (ss->bind)
ss->bind(init_css_set.subsys[ssid]);
}
err = sysfs_create_mount_point(fs_kobj, "cgroup");
if (err)
return err;
err = register_filesystem(&cgroup_fs_type);
if (err < 0) {
sysfs_remove_mount_point(fs_kobj, "cgroup");
return err;
}
proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
return 0;
}
static int __init cgroup_wq_init(void)
{
/*
* There isn't much point in executing destruction path in
* parallel. Good chunk is serialized with cgroup_mutex anyway.
* Use 1 for @max_active.
*
* We would prefer to do this in cgroup_init() above, but that
* is called before init_workqueues(): so leave this until after.
*/
cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
BUG_ON(!cgroup_destroy_wq);
/*
* Used to destroy pidlists and separate to serve as flush domain.
* Cap @max_active to 1 too.
*/
cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
0, 1);
BUG_ON(!cgroup_pidlist_destroy_wq);
return 0;
}
core_initcall(cgroup_wq_init);
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
* - Used for /proc/<pid>/cgroup.
*/
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk)
{
char *buf, *path;
int retval;
struct cgroup_root *root;
retval = -ENOMEM;
buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
goto out;
mutex_lock(&cgroup_mutex);
down_read(&css_set_rwsem);
for_each_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
int ssid, count = 0;
if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible)
continue;
seq_printf(m, "%d:", root->hierarchy_id);
if (root != &cgrp_dfl_root)
for_each_subsys(ss, ssid)
if (root->subsys_mask & (1 << ssid))
seq_printf(m, "%s%s", count++ ? "," : "",
ss->legacy_name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
seq_putc(m, ':');
cgrp = task_cgroup_from_root(tsk, root);
path = cgroup_path(cgrp, buf, PATH_MAX);
if (!path) {
retval = -ENAMETOOLONG;
goto out_unlock;
}
seq_puts(m, path);
seq_putc(m, '\n');
}
retval = 0;
out_unlock:
up_read(&css_set_rwsem);
mutex_unlock(&cgroup_mutex);
kfree(buf);
out:
return retval;
}
/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v)
{
struct cgroup_subsys *ss;
int i;
seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
/*
* ideally we don't want subsystems moving around while we do this.
* cgroup_mutex is also necessary to guarantee an atomic snapshot of
* subsys/hierarchy state.
*/
mutex_lock(&cgroup_mutex);
for_each_subsys(ss, i)
seq_printf(m, "%s\t%d\t%d\t%d\n",
ss->legacy_name, ss->root->hierarchy_id,
atomic_read(&ss->root->nr_cgrps),
cgroup_ssid_enabled(i));
mutex_unlock(&cgroup_mutex);
return 0;
}
static int cgroupstats_open(struct inode *inode, struct file *file)
{
return single_open(file, proc_cgroupstats_show, NULL);
}
static const struct file_operations proc_cgroupstats_operations = {
.open = cgroupstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void **subsys_canfork_priv_p(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
{
if (CGROUP_CANFORK_START <= i && i < CGROUP_CANFORK_END)
return &ss_priv[i - CGROUP_CANFORK_START];
return NULL;
}
static void *subsys_canfork_priv(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
{
void **private = subsys_canfork_priv_p(ss_priv, i);
return private ? *private : NULL;
}
/**
* cgroup_fork - initialize cgroup related fields during copy_process()
* @child: pointer to task_struct of forking parent process.
*
* A task is associated with the init_css_set until cgroup_post_fork()
* attaches it to the parent's css_set. Empty cg_list indicates that
* @child isn't holding reference to its css_set.
*/
void cgroup_fork(struct task_struct *child)
{
RCU_INIT_POINTER(child->cgroups, &init_css_set);
INIT_LIST_HEAD(&child->cg_list);
}
/**
* cgroup_can_fork - called on a new task before the process is exposed
* @child: the task in question.
*
* This calls the subsystem can_fork() callbacks. If the can_fork() callback
* returns an error, the fork aborts with that error code. This allows for
* a cgroup subsystem to conditionally allow or deny new forks.
*/
int cgroup_can_fork(struct task_struct *child,
void *ss_priv[CGROUP_CANFORK_COUNT])
{
struct cgroup_subsys *ss;
int i, j, ret;
for_each_subsys_which(ss, i, &have_canfork_callback) {
ret = ss->can_fork(child, subsys_canfork_priv_p(ss_priv, i));
if (ret)
goto out_revert;
}
return 0;
out_revert:
for_each_subsys(ss, j) {
if (j >= i)
break;
if (ss->cancel_fork)
ss->cancel_fork(child, subsys_canfork_priv(ss_priv, j));
}
return ret;
}
/**
* cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
* @child: the task in question
*
* This calls the cancel_fork() callbacks if a fork failed *after*
* cgroup_can_fork() succeded.
*/
void cgroup_cancel_fork(struct task_struct *child,
void *ss_priv[CGROUP_CANFORK_COUNT])
{
struct cgroup_subsys *ss;
int i;
for_each_subsys(ss, i)
if (ss->cancel_fork)
ss->cancel_fork(child, subsys_canfork_priv(ss_priv, i));
}
/**
* cgroup_post_fork - called on a new task after adding it to the task list
* @child: the task in question
*
* Adds the task to the list running through its css_set if necessary and
* call the subsystem fork() callbacks. Has to be after the task is
* visible on the task list in case we race with the first call to
* cgroup_task_iter_start() - to guarantee that the new task ends up on its
* list.
*/
void cgroup_post_fork(struct task_struct *child,
void *old_ss_priv[CGROUP_CANFORK_COUNT])
{
struct cgroup_subsys *ss;
int i;
/*
* This may race against cgroup_enable_task_cg_lists(). As that
* function sets use_task_css_set_links before grabbing
* tasklist_lock and we just went through tasklist_lock to add
* @child, it's guaranteed that either we see the set
* use_task_css_set_links or cgroup_enable_task_cg_lists() sees
* @child during its iteration.
*
* If we won the race, @child is associated with %current's
* css_set. Grabbing css_set_rwsem guarantees both that the
* association is stable, and, on completion of the parent's
* migration, @child is visible in the source of migration or
* already in the destination cgroup. This guarantee is necessary
* when implementing operations which need to migrate all tasks of
* a cgroup to another.
*
* Note that if we lose to cgroup_enable_task_cg_lists(), @child
* will remain in init_css_set. This is safe because all tasks are
* in the init_css_set before cg_links is enabled and there's no
* operation which transfers all tasks out of init_css_set.
*/
if (use_task_css_set_links) {
struct css_set *cset;
down_write(&css_set_rwsem);
cset = task_css_set(current);
if (list_empty(&child->cg_list)) {
rcu_assign_pointer(child->cgroups, cset);
list_add(&child->cg_list, &cset->tasks);
get_css_set(cset);
}
up_write(&css_set_rwsem);
}
/*
* Call ss->fork(). This must happen after @child is linked on
* css_set; otherwise, @child might change state between ->fork()
* and addition to css_set.
*/
for_each_subsys_which(ss, i, &have_fork_callback)
ss->fork(child, subsys_canfork_priv(old_ss_priv, i));
}
/**
* cgroup_exit - detach cgroup from exiting task
* @tsk: pointer to task_struct of exiting process
*
* Description: Detach cgroup from @tsk and release it.
*
* Note that cgroups marked notify_on_release force every task in
* them to take the global cgroup_mutex mutex when exiting.
* This could impact scaling on very large systems. Be reluctant to
* use notify_on_release cgroups where very high task exit scaling
* is required on large systems.
*
* We set the exiting tasks cgroup to the root cgroup (top_cgroup). We
* call cgroup_exit() while the task is still competent to handle
* notify_on_release(), then leave the task attached to the root cgroup in
* each hierarchy for the remainder of its exit. No need to bother with
* init_css_set refcnting. init_css_set never goes away and we can't race
* with migration path - PF_EXITING is visible to migration path.
*/
void cgroup_exit(struct task_struct *tsk)
{
struct cgroup_subsys *ss;
struct css_set *cset;
bool put_cset = false;
int i;
/*
* Unlink from @tsk from its css_set. As migration path can't race
* with us, we can check cg_list without grabbing css_set_rwsem.
*/
if (!list_empty(&tsk->cg_list)) {
down_write(&css_set_rwsem);
list_del_init(&tsk->cg_list);
up_write(&css_set_rwsem);
put_cset = true;
}
/* Reassign the task to the init_css_set. */
cset = task_css_set(tsk);
RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
/* see cgroup_post_fork() for details */
for_each_subsys_which(ss, i, &have_exit_callback) {
struct cgroup_subsys_state *old_css = cset->subsys[i];
struct cgroup_subsys_state *css = task_css(tsk, i);
ss->exit(css, old_css, tsk);
}
if (put_cset)
put_css_set(cset);
}
static void check_for_release(struct cgroup *cgrp)
{
if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) &&
!css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
schedule_work(&cgrp->release_agent_work);
}
/*
* Notify userspace when a cgroup is released, by running the
* configured release agent with the name of the cgroup (path
* relative to the root of cgroup file system) as the argument.
*
* Most likely, this user command will try to rmdir this cgroup.
*
* This races with the possibility that some other task will be
* attached to this cgroup before it is removed, or that some other
* user task will 'mkdir' a child cgroup of this cgroup. That's ok.
* The presumed 'rmdir' will fail quietly if this cgroup is no longer
* unused, and this cgroup will be reprieved from its death sentence,
* to continue to serve a useful existence. Next time it's released,
* we will get notified again, if it still has 'notify_on_release' set.
*
* The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
* means only wait until the task is successfully execve()'d. The
* separate release agent task is forked by call_usermodehelper(),
* then control in this thread returns here, without waiting for the
* release agent task. We don't bother to wait because the caller of
* this routine has no use for the exit status of the release agent
* task, so no sense holding our caller up for that.
*/
static void cgroup_release_agent(struct work_struct *work)
{
struct cgroup *cgrp =
container_of(work, struct cgroup, release_agent_work);
char *pathbuf = NULL, *agentbuf = NULL, *path;
char *argv[3], *envp[3];
mutex_lock(&cgroup_mutex);
pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
if (!pathbuf || !agentbuf)
goto out;
path = cgroup_path(cgrp, pathbuf, PATH_MAX);
if (!path)
goto out;
argv[0] = agentbuf;
argv[1] = path;
argv[2] = NULL;
/* minimal command environment */
envp[0] = "HOME=/";
envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
envp[2] = NULL;
mutex_unlock(&cgroup_mutex);
call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
goto out_free;
out:
mutex_unlock(&cgroup_mutex);
out_free:
kfree(agentbuf);
kfree(pathbuf);
}
static int __init cgroup_disable(char *str)
{
struct cgroup_subsys *ss;
char *token;
int i;
while ((token = strsep(&str, ",")) != NULL) {
if (!*token)
continue;
for_each_subsys(ss, i) {
if (strcmp(token, ss->name) &&
strcmp(token, ss->legacy_name))
continue;
static_branch_disable(cgroup_subsys_enabled_key[i]);
printk(KERN_INFO "Disabling %s control group subsystem\n",
ss->name);
break;
}
}
return 1;
}
__setup("cgroup_disable=", cgroup_disable);
static int __init cgroup_set_legacy_files_on_dfl(char *str)
{
printk("cgroup: using legacy files on the default hierarchy\n");
cgroup_legacy_files_on_dfl = true;
return 0;
}
__setup("cgroup__DEVEL__legacy_files_on_dfl", cgroup_set_legacy_files_on_dfl);
/**
* css_tryget_online_from_dir - get corresponding css from a cgroup dentry
* @dentry: directory dentry of interest
* @ss: subsystem of interest
*
* If @dentry is a directory for a cgroup which has @ss enabled on it, try
* to get the corresponding css and return it. If such css doesn't exist
* or can't be pinned, an ERR_PTR value is returned.
*/
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss)
{
struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct cgroup_subsys_state *css = NULL;
struct cgroup *cgrp;
/* is @dentry a cgroup dir? */
if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
kernfs_type(kn) != KERNFS_DIR)
return ERR_PTR(-EBADF);
rcu_read_lock();
/*
* This path doesn't originate from kernfs and @kn could already
* have been or be removed at any point. @kn->priv is RCU
* protected for this access. See css_release_work_fn() for details.
*/
cgrp = rcu_dereference(kn->priv);
if (cgrp)
css = cgroup_css(cgrp, ss);
if (!css || !css_tryget_online(css))
css = ERR_PTR(-ENOENT);
rcu_read_unlock();
return css;
}
/**
* css_from_id - lookup css by id
* @id: the cgroup id
* @ss: cgroup subsys to be looked into
*
* Returns the css if there's valid one with @id, otherwise returns NULL.
* Should be called under rcu_read_lock().
*/
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
{
WARN_ON_ONCE(!rcu_read_lock_held());
return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
}
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *
debug_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
if (!css)
return ERR_PTR(-ENOMEM);
return css;
}
static void debug_css_free(struct cgroup_subsys_state *css)
{
kfree(css);
}
static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return cgroup_task_count(css->cgroup);
}
static u64 current_css_set_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return (u64)(unsigned long)current->cgroups;
}
static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
u64 count;
rcu_read_lock();
count = atomic_read(&task_css_set(current)->refcount);
rcu_read_unlock();
return count;
}
static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
{
struct cgrp_cset_link *link;
struct css_set *cset;
char *name_buf;
name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
if (!name_buf)
return -ENOMEM;
down_read(&css_set_rwsem);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
cgroup_name(c, name_buf, NAME_MAX + 1);
seq_printf(seq, "Root %d group %s\n",
c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
up_read(&css_set_rwsem);
kfree(name_buf);
return 0;
}
#define MAX_TASKS_SHOWN_PER_CSS 25
static int cgroup_css_links_read(struct seq_file *seq, void *v)
{
struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
down_read(&css_set_rwsem);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
int count = 0;
seq_printf(seq, "css_set %p\n", cset);
list_for_each_entry(task, &cset->tasks, cg_list) {
if (count++ > MAX_TASKS_SHOWN_PER_CSS)
goto overflow;
seq_printf(seq, " task %d\n", task_pid_vnr(task));
}
list_for_each_entry(task, &cset->mg_tasks, cg_list) {
if (count++ > MAX_TASKS_SHOWN_PER_CSS)
goto overflow;
seq_printf(seq, " task %d\n", task_pid_vnr(task));
}
continue;
overflow:
seq_puts(seq, " ...\n");
}
up_read(&css_set_rwsem);
return 0;
}
static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
return (!cgroup_has_tasks(css->cgroup) &&
!css_has_online_children(&css->cgroup->self));
}
static struct cftype debug_files[] = {
{
.name = "taskcount",
.read_u64 = debug_taskcount_read,
},
{
.name = "current_css_set",
.read_u64 = current_css_set_read,
},
{
.name = "current_css_set_refcount",
.read_u64 = current_css_set_refcount_read,
},
{
.name = "current_css_set_cg_links",
.seq_show = current_css_set_cg_links_read,
},
{
.name = "cgroup_css_links",
.seq_show = cgroup_css_links_read,
},
{
.name = "releasable",
.read_u64 = releasable_read,
},
{ } /* terminate */
};
struct cgroup_subsys debug_cgrp_subsys = {
.css_alloc = debug_css_alloc,
.css_free = debug_css_free,
.legacy_cftypes = debug_files,
};
#endif /* CONFIG_CGROUP_DEBUG */
|