summaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
blob: 81fc6791a2966f1e0aa31f97263b771f8571b102 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
/*
 *  kernel/cpuset.c
 *
 *  Processor and Memory placement constraints for sets of tasks.
 *
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2007 Silicon Graphics, Inc.
 *  Copyright (C) 2006 Google, 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.
 *  2006 Rework by Paul Menage to use generic cgroups
 *  2008 Rework of the scheduler domains and CPU hotplug handling
 *       by Max Krasnyansky
 *
 *  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.
 */

#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>

/*
 * Tracks how many cpusets are currently defined in system.
 * When there is only one cpuset (the root cpuset) we can
 * short circuit some hooks.
 */
int number_of_cpusets __read_mostly;

/* Forward declare cgroup structures */
struct cgroup_subsys cpuset_subsys;
struct cpuset;

/* See "Frequency meter" comments, below. */

struct fmeter {
	int cnt;		/* unprocessed events count */
	int val;		/* most recent output value */
	time_t time;		/* clock (secs) when val computed */
	spinlock_t lock;	/* guards read or write of above */
};

struct cpuset {
	struct cgroup_subsys_state css;

	unsigned long flags;		/* "unsigned long" so bitops work */
	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

	struct cpuset *parent;		/* my parent */

	/*
	 * Copy of global cpuset_mems_generation as of the most
	 * recent time this cpuset changed its mems_allowed.
	 */
	int mems_generation;

	struct fmeter fmeter;		/* memory_pressure filter */

	/* partition number for rebuild_sched_domains() */
	int pn;

	/* for custom sched domain */
	int relax_domain_level;

	/* used for walking a cpuset heirarchy */
	struct list_head stack_list;
};

/* Retrieve the cpuset for a cgroup */
static inline struct cpuset *cgroup_cs(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont, cpuset_subsys_id),
			    struct cpuset, css);
}

/* Retrieve the cpuset for a task */
static inline struct cpuset *task_cs(struct task_struct *task)
{
	return container_of(task_subsys_state(task, cpuset_subsys_id),
			    struct cpuset, css);
}
struct cpuset_hotplug_scanner {
	struct cgroup_scanner scan;
	struct cgroup *to;
};

/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
	CS_MEM_HARDWALL,
	CS_MEMORY_MIGRATE,
	CS_SCHED_LOAD_BALANCE,
	CS_SPREAD_PAGE,
	CS_SPREAD_SLAB,
} cpuset_flagbits_t;

/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
}

static inline int is_mem_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
}

static inline int is_mem_hardwall(const struct cpuset *cs)
{
	return test_bit(CS_MEM_HARDWALL, &cs->flags);
}

static inline int is_sched_load_balance(const struct cpuset *cs)
{
	return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
}

static inline int is_memory_migrate(const struct cpuset *cs)
{
	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}

static inline int is_spread_page(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_PAGE, &cs->flags);
}

static inline int is_spread_slab(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_SLAB, &cs->flags);
}

/*
 * Increment this integer everytime any cpuset changes its
 * mems_allowed value.  Users of cpusets can track this generation
 * number, and avoid having to lock and reload mems_allowed unless
 * the cpuset they're using changes generation.
 *
 * A single, global generation is needed because cpuset_attach_task() could
 * reattach a task to a different cpuset, which must not have its
 * generation numbers aliased with those of that tasks previous cpuset.
 *
 * Generations are needed for mems_allowed because one task cannot
 * modify another's memory placement.  So we must enable every task,
 * on every visit to __alloc_pages(), to efficiently check whether
 * its current->cpuset->mems_allowed has changed, requiring an update
 * of its current->mems_allowed.
 *
 * Since writes to cpuset_mems_generation are guarded by the cgroup lock
 * there is no need to mark it atomic.
 */
static int cpuset_mems_generation;

static struct cpuset top_cpuset = {
	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
	.cpus_allowed = CPU_MASK_ALL,
	.mems_allowed = NODE_MASK_ALL,
};

/*
 * There are two global mutexes guarding cpuset structures.  The first
 * is the main control groups cgroup_mutex, accessed via
 * cgroup_lock()/cgroup_unlock().  The second is the cpuset-specific
 * callback_mutex, below. They can nest.  It is ok to first take
 * cgroup_mutex, then nest callback_mutex.  We also require taking
 * task_lock() when dereferencing a task's cpuset pointer.  See "The
 * task_lock() exception", at the end of this comment.
 *
 * A task must hold both mutexes to modify cpusets.  If a task
 * holds cgroup_mutex, then it blocks others wanting that mutex,
 * ensuring that it is the only task able to also acquire callback_mutex
 * and be able to modify cpusets.  It can perform various checks on
 * the cpuset structure first, knowing nothing will change.  It can
 * also allocate memory while just holding cgroup_mutex.  While it is
 * performing these checks, various callback routines can briefly
 * acquire callback_mutex to query cpusets.  Once it is ready to make
 * the changes, it takes callback_mutex, blocking everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_mutex, as that would risk double tripping on callback_mutex
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_mutex, then it has read-only
 * access to cpusets.
 *
 * The task_struct fields mems_allowed and mems_generation may only
 * be accessed in the context of that task, so require no locks.
 *
 * The cpuset_common_file_read() handlers only hold callback_mutex across
 * small pieces of code, such as when reading out possibly multi-word
 * cpumasks and nodemasks.
 *
 * Accessing a task's cpuset should be done in accordance with the
 * guidelines for accessing subsystem state in kernel/cgroup.c
 */

static DEFINE_MUTEX(callback_mutex);

/*
 * This is ugly, but preserves the userspace API for existing cpuset
 * users. If someone tries to mount the "cpuset" filesystem, we
 * silently switch it to mount "cgroup" instead
 */
static int cpuset_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
	int ret = -ENODEV;
	if (cgroup_fs) {
		char mountopts[] =
			"cpuset,noprefix,"
			"release_agent=/sbin/cpuset_release_agent";
		ret = cgroup_fs->get_sb(cgroup_fs, flags,
					   unused_dev_name, mountopts, mnt);
		put_filesystem(cgroup_fs);
	}
	return ret;
}

static struct file_system_type cpuset_fs_type = {
	.name = "cpuset",
	.get_sb = cpuset_get_sb,
};

/*
 * Return in *pmask the portion of a cpusets's cpus_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online cpus.  If we get
 * all the way to the top and still haven't found any online cpus,
 * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
 * task, return cpu_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of cpu_online_map.
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
{
	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
		cs = cs->parent;
	if (cs)
		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
	else
		*pmask = cpu_online_map;
	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
}

/*
 * Return in *pmask the portion of a cpusets's mems_allowed that
 * are online, with memory.  If none are online with memory, walk
 * up the cpuset hierarchy until we find one that does have some
 * online mems.  If we get all the way to the top and still haven't
 * found any online mems, return node_states[N_HIGH_MEMORY].
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_states[N_HIGH_MEMORY].
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
{
	while (cs && !nodes_intersects(cs->mems_allowed,
					node_states[N_HIGH_MEMORY]))
		cs = cs->parent;
	if (cs)
		nodes_and(*pmask, cs->mems_allowed,
					node_states[N_HIGH_MEMORY]);
	else
		*pmask = node_states[N_HIGH_MEMORY];
	BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
}

/**
 * cpuset_update_task_memory_state - update task memory placement
 *
 * If the current tasks cpusets mems_allowed changed behind our
 * backs, update current->mems_allowed, mems_generation and task NUMA
 * mempolicy to the new value.
 *
 * Task mempolicy is updated by rebinding it relative to the
 * current->cpuset if a task has its memory placement changed.
 * Do not call this routine if in_interrupt().
 *
 * Call without callback_mutex or task_lock() held.  May be
 * called with or without cgroup_mutex held.  Thanks in part to
 * 'the_top_cpuset_hack', the task's cpuset pointer will never
 * be NULL.  This routine also might acquire callback_mutex during
 * call.
 *
 * Reading current->cpuset->mems_generation doesn't need task_lock
 * to guard the current->cpuset derefence, because it is guarded
 * from concurrent freeing of current->cpuset using RCU.
 *
 * The rcu_dereference() is technically probably not needed,
 * as I don't actually mind if I see a new cpuset pointer but
 * an old value of mems_generation.  However this really only
 * matters on alpha systems using cpusets heavily.  If I dropped
 * that rcu_dereference(), it would save them a memory barrier.
 * For all other arch's, rcu_dereference is a no-op anyway, and for
 * alpha systems not using cpusets, another planned optimization,
 * avoiding the rcu critical section for tasks in the root cpuset
 * which is statically allocated, so can't vanish, will make this
 * irrelevant.  Better to use RCU as intended, than to engage in
 * some cute trick to save a memory barrier that is impossible to
 * test, for alpha systems using cpusets heavily, which might not
 * even exist.
 *
 * This routine is needed to update the per-task mems_allowed data,
 * within the tasks context, when it is trying to allocate memory
 * (in various mm/mempolicy.c routines) and notices that some other
 * task has been modifying its cpuset.
 */

void cpuset_update_task_memory_state(void)
{
	int my_cpusets_mem_gen;
	struct task_struct *tsk = current;
	struct cpuset *cs;

	if (task_cs(tsk) == &top_cpuset) {
		/* Don't need rcu for top_cpuset.  It's never freed. */
		my_cpusets_mem_gen = top_cpuset.mems_generation;
	} else {
		rcu_read_lock();
		my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
		rcu_read_unlock();
	}

	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
		mutex_lock(&callback_mutex);
		task_lock(tsk);
		cs = task_cs(tsk); /* Maybe changed when task not locked */
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		if (is_spread_page(cs))
			tsk->flags |= PF_SPREAD_PAGE;
		else
			tsk->flags &= ~PF_SPREAD_PAGE;
		if (is_spread_slab(cs))
			tsk->flags |= PF_SPREAD_SLAB;
		else
			tsk->flags &= ~PF_SPREAD_SLAB;
		task_unlock(tsk);
		mutex_unlock(&callback_mutex);
		mpol_rebind_task(tsk, &tsk->mems_allowed);
	}
}

/*
 * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
 *
 * One cpuset is a subset of another if all its allowed CPUs and
 * Memory Nodes are a subset of the other, and its exclusive flags
 * are only set if the other's are set.  Call holding cgroup_mutex.
 */

static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
		nodes_subset(p->mems_allowed, q->mems_allowed) &&
		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
		is_mem_exclusive(p) <= is_mem_exclusive(q);
}

/*
 * validate_change() - Used to validate that any proposed cpuset change
 *		       follows the structural rules for cpusets.
 *
 * If we replaced the flag and mask values of the current cpuset
 * (cur) with those values in the trial cpuset (trial), would
 * our various subset and exclusive rules still be valid?  Presumes
 * cgroup_mutex held.
 *
 * 'cur' is the address of an actual, in-use cpuset.  Operations
 * such as list traversal that depend on the actual address of the
 * cpuset in the list must use cur below, not trial.
 *
 * 'trial' is the address of bulk structure copy of cur, with
 * perhaps one or more of the fields cpus_allowed, mems_allowed,
 * or flags changed to new, trial values.
 *
 * Return 0 if valid, -errno if not.
 */

static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
	struct cgroup *cont;
	struct cpuset *c, *par;

	/* Each of our child cpusets must be a subset of us */
	list_for_each_entry(cont, &cur->css.cgroup->children, sibling) {
		if (!is_cpuset_subset(cgroup_cs(cont), trial))
			return -EBUSY;
	}

	/* Remaining checks don't apply to root cpuset */
	if (cur == &top_cpuset)
		return 0;

	par = cur->parent;

	/* We must be a subset of our parent cpuset */
	if (!is_cpuset_subset(trial, par))
		return -EACCES;

	/*
	 * If either I or some sibling (!= me) is exclusive, we can't
	 * overlap
	 */
	list_for_each_entry(cont, &par->css.cgroup->children, sibling) {
		c = cgroup_cs(cont);
		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
		    c != cur &&
		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
			return -EINVAL;
		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
		    c != cur &&
		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
			return -EINVAL;
	}

	/* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */
	if (cgroup_task_count(cur->css.cgroup)) {
		if (cpus_empty(trial->cpus_allowed) ||
		    nodes_empty(trial->mems_allowed)) {
			return -ENOSPC;
		}
	}

	return 0;
}

/*
 * Helper routine for generate_sched_domains().
 * Do cpusets a, b have overlapping cpus_allowed masks?
 */
static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
{
	return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
}

static void
update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
{
	if (dattr->relax_domain_level < c->relax_domain_level)
		dattr->relax_domain_level = c->relax_domain_level;
	return;
}

static void
update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
{
	LIST_HEAD(q);

	list_add(&c->stack_list, &q);
	while (!list_empty(&q)) {
		struct cpuset *cp;
		struct cgroup *cont;
		struct cpuset *child;

		cp = list_first_entry(&q, struct cpuset, stack_list);
		list_del(q.next);

		if (cpus_empty(cp->cpus_allowed))
			continue;

		if (is_sched_load_balance(cp))
			update_domain_attr(dattr, cp);

		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
			child = cgroup_cs(cont);
			list_add_tail(&child->stack_list, &q);
		}
	}
}

/*
 * generate_sched_domains()
 *
 * This function builds a partial partition of the systems CPUs
 * A 'partial partition' is a set of non-overlapping subsets whose
 * union is a subset of that set.
 * The output of this function needs to be passed to kernel/sched.c
 * partition_sched_domains() routine, which will rebuild the scheduler's
 * load balancing domains (sched domains) as specified by that partial
 * partition.
 *
 * See "What is sched_load_balance" in Documentation/cpusets.txt
 * for a background explanation of this.
 *
 * Does not return errors, on the theory that the callers of this
 * routine would rather not worry about failures to rebuild sched
 * domains when operating in the severe memory shortage situations
 * that could cause allocation failures below.
 *
 * Must be called with cgroup_lock held.
 *
 * The three key local variables below are:
 *    q  - a linked-list queue of cpuset pointers, used to implement a
 *	   top-down scan of all cpusets.  This scan loads a pointer
 *	   to each cpuset marked is_sched_load_balance into the
 *	   array 'csa'.  For our purposes, rebuilding the schedulers
 *	   sched domains, we can ignore !is_sched_load_balance cpusets.
 *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
 *	   that need to be load balanced, for convenient iterative
 *	   access by the subsequent code that finds the best partition,
 *	   i.e the set of domains (subsets) of CPUs such that the
 *	   cpus_allowed of every cpuset marked is_sched_load_balance
 *	   is a subset of one of these domains, while there are as
 *	   many such domains as possible, each as small as possible.
 * doms  - Conversion of 'csa' to an array of cpumasks, for passing to
 *	   the kernel/sched.c routine partition_sched_domains() in a
 *	   convenient format, that can be easily compared to the prior
 *	   value to determine what partition elements (sched domains)
 *	   were changed (added or removed.)
 *
 * Finding the best partition (set of domains):
 *	The triple nested loops below over i, j, k scan over the
 *	load balanced cpusets (using the array of cpuset pointers in
 *	csa[]) looking for pairs of cpusets that have overlapping
 *	cpus_allowed, but which don't have the same 'pn' partition
 *	number and gives them in the same partition number.  It keeps
 *	looping on the 'restart' label until it can no longer find
 *	any such pairs.
 *
 *	The union of the cpus_allowed masks from the set of
 *	all cpusets having the same 'pn' value then form the one
 *	element of the partition (one sched domain) to be passed to
 *	partition_sched_domains().
 */
static int generate_sched_domains(cpumask_t **domains,
			struct sched_domain_attr **attributes)
{
	LIST_HEAD(q);		/* queue of cpusets to be scanned */
	struct cpuset *cp;	/* scans q */
	struct cpuset **csa;	/* array of all cpuset ptrs */
	int csn;		/* how many cpuset ptrs in csa so far */
	int i, j, k;		/* indices for partition finding loops */
	cpumask_t *doms;	/* resulting partition; i.e. sched domains */
	struct sched_domain_attr *dattr;  /* attributes for custom domains */
	int ndoms;		/* number of sched domains in result */
	int nslot;		/* next empty doms[] cpumask_t slot */

	doms = NULL;
	dattr = NULL;
	csa = NULL;

	/* Special case for the 99% of systems with one, full, sched domain */
	if (is_sched_load_balance(&top_cpuset)) {
		doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
		if (!doms)
			goto done;

		dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
		if (dattr) {
			*dattr = SD_ATTR_INIT;
			update_domain_attr_tree(dattr, &top_cpuset);
		}
		*doms = top_cpuset.cpus_allowed;

		ndoms = 1;
		goto done;
	}

	csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
	if (!csa)
		goto done;
	csn = 0;

	list_add(&top_cpuset.stack_list, &q);
	while (!list_empty(&q)) {
		struct cgroup *cont;
		struct cpuset *child;   /* scans child cpusets of cp */

		cp = list_first_entry(&q, struct cpuset, stack_list);
		list_del(q.next);

		if (cpus_empty(cp->cpus_allowed))
			continue;

		/*
		 * All child cpusets contain a subset of the parent's cpus, so
		 * just skip them, and then we call update_domain_attr_tree()
		 * to calc relax_domain_level of the corresponding sched
		 * domain.
		 */
		if (is_sched_load_balance(cp)) {
			csa[csn++] = cp;
			continue;
		}

		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
			child = cgroup_cs(cont);
			list_add_tail(&child->stack_list, &q);
		}
  	}

	for (i = 0; i < csn; i++)
		csa[i]->pn = i;
	ndoms = csn;

restart:
	/* Find the best partition (set of sched domains) */
	for (i = 0; i < csn; i++) {
		struct cpuset *a = csa[i];
		int apn = a->pn;

		for (j = 0; j < csn; j++) {
			struct cpuset *b = csa[j];
			int bpn = b->pn;

			if (apn != bpn && cpusets_overlap(a, b)) {
				for (k = 0; k < csn; k++) {
					struct cpuset *c = csa[k];

					if (c->pn == bpn)
						c->pn = apn;
				}
				ndoms--;	/* one less element */
				goto restart;
			}
		}
	}

	/*
	 * Now we know how many domains to create.
	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
	 */
	doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
	if (!doms)
		goto done;

	/*
	 * The rest of the code, including the scheduler, can deal with
	 * dattr==NULL case. No need to abort if alloc fails.
	 */
	dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);

	for (nslot = 0, i = 0; i < csn; i++) {
		struct cpuset *a = csa[i];
		cpumask_t *dp;
		int apn = a->pn;

		if (apn < 0) {
			/* Skip completed partitions */
			continue;
		}

		dp = doms + nslot;

		if (nslot == ndoms) {
			static int warnings = 10;
			if (warnings) {
				printk(KERN_WARNING
				 "rebuild_sched_domains confused:"
				  " nslot %d, ndoms %d, csn %d, i %d,"
				  " apn %d\n",
				  nslot, ndoms, csn, i, apn);
				warnings--;
			}
			continue;
		}

		cpus_clear(*dp);
		if (dattr)
			*(dattr + nslot) = SD_ATTR_INIT;
		for (j = i; j < csn; j++) {
			struct cpuset *b = csa[j];

			if (apn == b->pn) {
				cpus_or(*dp, *dp, b->cpus_allowed);
				if (dattr)
					update_domain_attr_tree(dattr + nslot, b);

				/* Done with this partition */
				b->pn = -1;
			}
		}
		nslot++;
	}
	BUG_ON(nslot != ndoms);

done:
	kfree(csa);

	/*
	 * Fallback to the default domain if kmalloc() failed.
	 * See comments in partition_sched_domains().
	 */
	if (doms == NULL)
		ndoms = 1;

	*domains    = doms;
	*attributes = dattr;
	return ndoms;
}

/*
 * Rebuild scheduler domains.
 *
 * Call with neither cgroup_mutex held nor within get_online_cpus().
 * Takes both cgroup_mutex and get_online_cpus().
 *
 * Cannot be directly called from cpuset code handling changes
 * to the cpuset pseudo-filesystem, because it cannot be called
 * from code that already holds cgroup_mutex.
 */
static void do_rebuild_sched_domains(struct work_struct *unused)
{
	struct sched_domain_attr *attr;
	cpumask_t *doms;
	int ndoms;

	get_online_cpus();

	/* Generate domain masks and attrs */
	cgroup_lock();
	ndoms = generate_sched_domains(&doms, &attr);
	cgroup_unlock();

	/* Have scheduler rebuild the domains */
	partition_sched_domains(ndoms, doms, attr);

	put_online_cpus();
}

static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);

/*
 * Rebuild scheduler domains, asynchronously via workqueue.
 *
 * If the flag 'sched_load_balance' of any cpuset with non-empty
 * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
 * which has that flag enabled, or if any cpuset with a non-empty
 * 'cpus' is removed, then call this routine to rebuild the
 * scheduler's dynamic sched domains.
 *
 * The rebuild_sched_domains() and partition_sched_domains()
 * routines must nest cgroup_lock() inside get_online_cpus(),
 * but such cpuset changes as these must nest that locking the
 * other way, holding cgroup_lock() for much of the code.
 *
 * So in order to avoid an ABBA deadlock, the cpuset code handling
 * these user changes delegates the actual sched domain rebuilding
 * to a separate workqueue thread, which ends up processing the
 * above do_rebuild_sched_domains() function.
 */
static void async_rebuild_sched_domains(void)
{
	schedule_work(&rebuild_sched_domains_work);
}

/*
 * Accomplishes the same scheduler domain rebuild as the above
 * async_rebuild_sched_domains(), however it directly calls the
 * rebuild routine synchronously rather than calling it via an
 * asynchronous work thread.
 *
 * This can only be called from code that is not holding
 * cgroup_mutex (not nested in a cgroup_lock() call.)
 */
void rebuild_sched_domains(void)
{
	do_rebuild_sched_domains(NULL);
}

/**
 * cpuset_test_cpumask - test a task's cpus_allowed versus its cpuset's
 * @tsk: task to test
 * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner
 *
 * Call with cgroup_mutex held.  May take callback_mutex during call.
 * Called for each task in a cgroup by cgroup_scan_tasks().
 * Return nonzero if this tasks's cpus_allowed mask should be changed (in other
 * words, if its mask is not equal to its cpuset's mask).
 */
static int cpuset_test_cpumask(struct task_struct *tsk,
			       struct cgroup_scanner *scan)
{
	return !cpus_equal(tsk->cpus_allowed,
			(cgroup_cs(scan->cg))->cpus_allowed);
}

/**
 * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's
 * @tsk: task to test
 * @scan: struct cgroup_scanner containing the cgroup of the task
 *
 * Called by cgroup_scan_tasks() for each task in a cgroup whose
 * cpus_allowed mask needs to be changed.
 *
 * We don't need to re-check for the cgroup/cpuset membership, since we're
 * holding cgroup_lock() at this point.
 */
static void cpuset_change_cpumask(struct task_struct *tsk,
				  struct cgroup_scanner *scan)
{
	set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed));
}

/**
 * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
 * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
 * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
 *
 * Called with cgroup_mutex held
 *
 * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
 * calling callback functions for each.
 *
 * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
 * if @heap != NULL.
 */
static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
{
	struct cgroup_scanner scan;

	scan.cg = cs->css.cgroup;
	scan.test_task = cpuset_test_cpumask;
	scan.process_task = cpuset_change_cpumask;
	scan.heap = heap;
	cgroup_scan_tasks(&scan);
}

/**
 * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
 * @cs: the cpuset to consider
 * @buf: buffer of cpu numbers written to this cpuset
 */
static int update_cpumask(struct cpuset *cs, const char *buf)
{
	struct ptr_heap heap;
	struct cpuset trialcs;
	int retval;
	int is_load_balanced;

	/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
	if (cs == &top_cpuset)
		return -EACCES;

	trialcs = *cs;

	/*
	 * An empty cpus_allowed is ok only if the cpuset has no tasks.
	 * Since cpulist_parse() fails on an empty mask, we special case
	 * that parsing.  The validate_change() call ensures that cpusets
	 * with tasks have cpus.
	 */
	if (!*buf) {
		cpus_clear(trialcs.cpus_allowed);
	} else {
		retval = cpulist_parse(buf, trialcs.cpus_allowed);
		if (retval < 0)
			return retval;

		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
			return -EINVAL;
	}
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		return retval;

	/* Nothing to do if the cpus didn't change */
	if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
		return 0;

	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
	if (retval)
		return retval;

	is_load_balanced = is_sched_load_balance(&trialcs);

	mutex_lock(&callback_mutex);
	cs->cpus_allowed = trialcs.cpus_allowed;
	mutex_unlock(&callback_mutex);

	/*
	 * Scan tasks in the cpuset, and update the cpumasks of any
	 * that need an update.
	 */
	update_tasks_cpumask(cs, &heap);

	heap_free(&heap);

	if (is_load_balanced)
		async_rebuild_sched_domains();
	return 0;
}

/*
 * cpuset_migrate_mm
 *
 *    Migrate memory region from one set of nodes to another.
 *
 *    Temporarilly set tasks mems_allowed to target nodes of migration,
 *    so that the migration code can allocate pages on these nodes.
 *
 *    Call holding cgroup_mutex, so current's cpuset won't change
 *    during this call, as manage_mutex holds off any cpuset_attach()
 *    calls.  Therefore we don't need to take task_lock around the
 *    call to guarantee_online_mems(), as we know no one is changing
 *    our task's cpuset.
 *
 *    Hold callback_mutex around the two modifications of our tasks
 *    mems_allowed to synchronize with cpuset_mems_allowed().
 *
 *    While the mm_struct we are migrating is typically from some
 *    other task, the task_struct mems_allowed that we are hacking
 *    is for our current task, which must allocate new pages for that
 *    migrating memory region.
 *
 *    We call cpuset_update_task_memory_state() before hacking
 *    our tasks mems_allowed, so that we are assured of being in
 *    sync with our tasks cpuset, and in particular, callbacks to
 *    cpuset_update_task_memory_state() from nested page allocations
 *    won't see any mismatch of our cpuset and task mems_generation
 *    values, so won't overwrite our hacked tasks mems_allowed
 *    nodemask.
 */

static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
							const nodemask_t *to)
{
	struct task_struct *tsk = current;

	cpuset_update_task_memory_state();

	mutex_lock(&callback_mutex);
	tsk->mems_allowed = *to;
	mutex_unlock(&callback_mutex);

	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);

	mutex_lock(&callback_mutex);
	guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
	mutex_unlock(&callback_mutex);
}

static void *cpuset_being_rebound;

/**
 * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
 * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
 * @oldmem: old mems_allowed of cpuset cs
 *
 * Called with cgroup_mutex held
 * Return 0 if successful, -errno if not.
 */
static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
{
	struct task_struct *p;
	struct mm_struct **mmarray;
	int i, n, ntasks;
	int migrate;
	int fudge;
	struct cgroup_iter it;
	int retval;

	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */

	fudge = 10;				/* spare mmarray[] slots */
	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
	retval = -ENOMEM;

	/*
	 * Allocate mmarray[] to hold mm reference for each task
	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
	 * few more lines of code, we can retry until we get a big
	 * enough mmarray[] w/o using GFP_ATOMIC.
	 */
	while (1) {
		ntasks = cgroup_task_count(cs->css.cgroup);  /* guess */
		ntasks += fudge;
		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
		if (!mmarray)
			goto done;
		read_lock(&tasklist_lock);		/* block fork */
		if (cgroup_task_count(cs->css.cgroup) <= ntasks)
			break;				/* got enough */
		read_unlock(&tasklist_lock);		/* try again */
		kfree(mmarray);
	}

	n = 0;

	/* Load up mmarray[] with mm reference for each task in cpuset. */
	cgroup_iter_start(cs->css.cgroup, &it);
	while ((p = cgroup_iter_next(cs->css.cgroup, &it))) {
		struct mm_struct *mm;

		if (n >= ntasks) {
			printk(KERN_WARNING
				"Cpuset mempolicy rebind incomplete.\n");
			break;
		}
		mm = get_task_mm(p);
		if (!mm)
			continue;
		mmarray[n++] = mm;
	}
	cgroup_iter_end(cs->css.cgroup, &it);
	read_unlock(&tasklist_lock);

	/*
	 * Now that we've dropped the tasklist spinlock, we can
	 * rebind the vma mempolicies of each mm in mmarray[] to their
	 * new cpuset, and release that mm.  The mpol_rebind_mm()
	 * call takes mmap_sem, which we couldn't take while holding
	 * tasklist_lock.  Forks can happen again now - the mpol_dup()
	 * cpuset_being_rebound check will catch such forks, and rebind
	 * their vma mempolicies too.  Because we still hold the global
	 * cgroup_mutex, we know that no other rebind effort will
	 * be contending for the global variable cpuset_being_rebound.
	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
	 * is idempotent.  Also migrate pages in each mm to new nodes.
	 */
	migrate = is_memory_migrate(cs);
	for (i = 0; i < n; i++) {
		struct mm_struct *mm = mmarray[i];

		mpol_rebind_mm(mm, &cs->mems_allowed);
		if (migrate)
			cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
		mmput(mm);
	}

	/* We're done rebinding vmas to this cpuset's new mems_allowed. */
	kfree(mmarray);
	cpuset_being_rebound = NULL;
	retval = 0;
done:
	return retval;
}

/*
 * Handle user request to change the 'mems' memory placement
 * of a cpuset.  Needs to validate the request, update the
 * cpusets mems_allowed and mems_generation, and for each
 * task in the cpuset, rebind any vma mempolicies and if
 * the cpuset is marked 'memory_migrate', migrate the tasks
 * pages to the new memory.
 *
 * Call with cgroup_mutex held.  May take callback_mutex during call.
 * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
 * lock each such tasks mm->mmap_sem, scan its vma's and rebind
 * their mempolicies to the cpusets new mems_allowed.
 */
static int update_nodemask(struct cpuset *cs, const char *buf)
{
	struct cpuset trialcs;
	nodemask_t oldmem;
	int retval;

	/*
	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
	 * it's read-only
	 */
	if (cs == &top_cpuset)
		return -EACCES;

	trialcs = *cs;

	/*
	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
	 * Since nodelist_parse() fails on an empty mask, we special case
	 * that parsing.  The validate_change() call ensures that cpusets
	 * with tasks have memory.
	 */
	if (!*buf) {
		nodes_clear(trialcs.mems_allowed);
	} else {
		retval = nodelist_parse(buf, trialcs.mems_allowed);
		if (retval < 0)
			goto done;

		if (!nodes_subset(trialcs.mems_allowed,
				node_states[N_HIGH_MEMORY]))
			return -EINVAL;
	}
	oldmem = cs->mems_allowed;
	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
		retval = 0;		/* Too easy - nothing to do */
		goto done;
	}
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		goto done;

	mutex_lock(&callback_mutex);
	cs->mems_allowed = trialcs.mems_allowed;
	cs->mems_generation = cpuset_mems_generation++;
	mutex_unlock(&callback_mutex);

	retval = update_tasks_nodemask(cs, &oldmem);
done:
	return retval;
}

int current_cpuset_is_being_rebound(void)
{
	return task_cs(current) == cpuset_being_rebound;
}

static int update_relax_domain_level(struct cpuset *cs, s64 val)
{
	if (val < -1 || val >= SD_LV_MAX)
		return -EINVAL;

	if (val != cs->relax_domain_level) {
		cs->relax_domain_level = val;
		if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs))
			async_rebuild_sched_domains();
	}

	return 0;
}

/*
 * update_flag - read a 0 or a 1 in a file and update associated flag
 * bit:		the bit to update (see cpuset_flagbits_t)
 * cs:		the cpuset to update
 * turning_on: 	whether the flag is being set or cleared
 *
 * Call with cgroup_mutex held.
 */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
		       int turning_on)
{
	struct cpuset trialcs;
	int err;
	int balance_flag_changed;

	trialcs = *cs;
	if (turning_on)
		set_bit(bit, &trialcs.flags);
	else
		clear_bit(bit, &trialcs.flags);

	err = validate_change(cs, &trialcs);
	if (err < 0)
		return err;

	balance_flag_changed = (is_sched_load_balance(cs) !=
		 			is_sched_load_balance(&trialcs));

	mutex_lock(&callback_mutex);
	cs->flags = trialcs.flags;
	mutex_unlock(&callback_mutex);

	if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
		async_rebuild_sched_domains();

	return 0;
}

/*
 * Frequency meter - How fast is some event occurring?
 *
 * These routines manage a digitally filtered, constant time based,
 * event frequency meter.  There are four routines:
 *   fmeter_init() - initialize a frequency meter.
 *   fmeter_markevent() - called each time the event happens.
 *   fmeter_getrate() - returns the recent rate of such events.
 *   fmeter_update() - internal routine used to update fmeter.
 *
 * A common data structure is passed to each of these routines,
 * which is used to keep track of the state required to manage the
 * frequency meter and its digital filter.
 *
 * The filter works on the number of events marked per unit time.
 * The filter is single-pole low-pass recursive (IIR).  The time unit
 * is 1 second.  Arithmetic is done using 32-bit integers scaled to
 * simulate 3 decimal digits of precision (multiplied by 1000).
 *
 * With an FM_COEF of 933, and a time base of 1 second, the filter
 * has a half-life of 10 seconds, meaning that if the events quit
 * happening, then the rate returned from the fmeter_getrate()
 * will be cut in half each 10 seconds, until it converges to zero.
 *
 * It is not worth doing a real infinitely recursive filter.  If more
 * than FM_MAXTICKS ticks have elapsed since the last filter event,
 * just compute FM_MAXTICKS ticks worth, by which point the level
 * will be stable.
 *
 * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
 * arithmetic overflow in the fmeter_update() routine.
 *
 * Given the simple 32 bit integer arithmetic used, this meter works
 * best for reporting rates between one per millisecond (msec) and
 * one per 32 (approx) seconds.  At constant rates faster than one
 * per msec it maxes out at values just under 1,000,000.  At constant
 * rates between one per msec, and one per second it will stabilize
 * to a value N*1000, where N is the rate of events per second.
 * At constant rates between one per second and one per 32 seconds,
 * it will be choppy, moving up on the seconds that have an event,
 * and then decaying until the next event.  At rates slower than
 * about one in 32 seconds, it decays all the way back to zero between
 * each event.
 */

#define FM_COEF 933		/* coefficient for half-life of 10 secs */
#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
#define FM_SCALE 1000		/* faux fixed point scale */

/* Initialize a frequency meter */
static void fmeter_init(struct fmeter *fmp)
{
	fmp->cnt = 0;
	fmp->val = 0;
	fmp->time = 0;
	spin_lock_init(&fmp->lock);
}

/* Internal meter update - process cnt events and update value */
static void fmeter_update(struct fmeter *fmp)
{
	time_t now = get_seconds();
	time_t ticks = now - fmp->time;

	if (ticks == 0)
		return;

	ticks = min(FM_MAXTICKS, ticks);
	while (ticks-- > 0)
		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
	fmp->time = now;

	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
	fmp->cnt = 0;
}

/* Process any previous ticks, then bump cnt by one (times scale). */
static void fmeter_markevent(struct fmeter *fmp)
{
	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
	spin_unlock(&fmp->lock);
}

/* Process any previous ticks, then return current value. */
static int fmeter_getrate(struct fmeter *fmp)
{
	int val;

	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	val = fmp->val;
	spin_unlock(&fmp->lock);
	return val;
}

/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
static int cpuset_can_attach(struct cgroup_subsys *ss,
			     struct cgroup *cont, struct task_struct *tsk)
{
	struct cpuset *cs = cgroup_cs(cont);

	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
		return -ENOSPC;
	if (tsk->flags & PF_THREAD_BOUND) {
		cpumask_t mask;

		mutex_lock(&callback_mutex);
		mask = cs->cpus_allowed;
		mutex_unlock(&callback_mutex);
		if (!cpus_equal(tsk->cpus_allowed, mask))
			return -EINVAL;
	}

	return security_task_setscheduler(tsk, 0, NULL);
}

static void cpuset_attach(struct cgroup_subsys *ss,
			  struct cgroup *cont, struct cgroup *oldcont,
			  struct task_struct *tsk)
{
	cpumask_t cpus;
	nodemask_t from, to;
	struct mm_struct *mm;
	struct cpuset *cs = cgroup_cs(cont);
	struct cpuset *oldcs = cgroup_cs(oldcont);
	int err;

	mutex_lock(&callback_mutex);
	guarantee_online_cpus(cs, &cpus);
	err = set_cpus_allowed_ptr(tsk, &cpus);
	mutex_unlock(&callback_mutex);
	if (err)
		return;

	from = oldcs->mems_allowed;
	to = cs->mems_allowed;
	mm = get_task_mm(tsk);
	if (mm) {
		mpol_rebind_mm(mm, &to);
		if (is_memory_migrate(cs))
			cpuset_migrate_mm(mm, &from, &to);
		mmput(mm);
	}

}

/* The various types of files and directories in a cpuset file system */

typedef enum {
	FILE_MEMORY_MIGRATE,
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_MEM_HARDWALL,
	FILE_SCHED_LOAD_BALANCE,
	FILE_SCHED_RELAX_DOMAIN_LEVEL,
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
	FILE_SPREAD_PAGE,
	FILE_SPREAD_SLAB,
} cpuset_filetype_t;

static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
{
	int retval = 0;
	struct cpuset *cs = cgroup_cs(cgrp);
	cpuset_filetype_t type = cft->private;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (type) {
	case FILE_CPU_EXCLUSIVE:
		retval = update_flag(CS_CPU_EXCLUSIVE, cs, val);
		break;
	case FILE_MEM_EXCLUSIVE:
		retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);
		break;
	case FILE_MEM_HARDWALL:
		retval = update_flag(CS_MEM_HARDWALL, cs, val);
		break;
	case FILE_SCHED_LOAD_BALANCE:
		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
		break;
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, val);
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		cpuset_memory_pressure_enabled = !!val;
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
	case FILE_SPREAD_PAGE:
		retval = update_flag(CS_SPREAD_PAGE, cs, val);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	case FILE_SPREAD_SLAB:
		retval = update_flag(CS_SPREAD_SLAB, cs, val);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
{
	int retval = 0;
	struct cpuset *cs = cgroup_cs(cgrp);
	cpuset_filetype_t type = cft->private;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (type) {
	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
		retval = update_relax_domain_level(cs, val);
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

/*
 * Common handling for a write to a "cpus" or "mems" file.
 */
static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
				const char *buf)
{
	int retval = 0;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (cft->private) {
	case FILE_CPULIST:
		retval = update_cpumask(cgroup_cs(cgrp), buf);
		break;
	case FILE_MEMLIST:
		retval = update_nodemask(cgroup_cs(cgrp), buf);
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

/*
 * These ascii lists should be read in a single call, by using a user
 * buffer large enough to hold the entire map.  If read in smaller
 * chunks, there is no guarantee of atomicity.  Since the display format
 * used, list of ranges of sequential numbers, is variable length,
 * and since these maps can change value dynamically, one could read
 * gibberish by doing partial reads while a list was changing.
 * A single large read to a buffer that crosses a page boundary is
 * ok, because the result being copied to user land is not recomputed
 * across a page fault.
 */

static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
	cpumask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->cpus_allowed;
	mutex_unlock(&callback_mutex);

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->mems_allowed;
	mutex_unlock(&callback_mutex);

	return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

static ssize_t cpuset_common_file_read(struct cgroup *cont,
				       struct cftype *cft,
				       struct file *file,
				       char __user *buf,
				       size_t nbytes, loff_t *ppos)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	char *page;
	ssize_t retval = 0;
	char *s;

	if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
		return -ENOMEM;

	s = page;

	switch (type) {
	case FILE_CPULIST:
		s += cpuset_sprintf_cpulist(s, cs);
		break;
	case FILE_MEMLIST:
		s += cpuset_sprintf_memlist(s, cs);
		break;
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
out:
	free_page((unsigned long)page);
	return retval;
}

static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	switch (type) {
	case FILE_CPU_EXCLUSIVE:
		return is_cpu_exclusive(cs);
	case FILE_MEM_EXCLUSIVE:
		return is_mem_exclusive(cs);
	case FILE_MEM_HARDWALL:
		return is_mem_hardwall(cs);
	case FILE_SCHED_LOAD_BALANCE:
		return is_sched_load_balance(cs);
	case FILE_MEMORY_MIGRATE:
		return is_memory_migrate(cs);
	case FILE_MEMORY_PRESSURE_ENABLED:
		return cpuset_memory_pressure_enabled;
	case FILE_MEMORY_PRESSURE:
		return fmeter_getrate(&cs->fmeter);
	case FILE_SPREAD_PAGE:
		return is_spread_page(cs);
	case FILE_SPREAD_SLAB:
		return is_spread_slab(cs);
	default:
		BUG();
	}

	/* Unreachable but makes gcc happy */
	return 0;
}

static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	switch (type) {
	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
		return cs->relax_domain_level;
	default:
		BUG();
	}

	/* Unrechable but makes gcc happy */
	return 0;
}


/*
 * for the common functions, 'private' gives the type of file
 */

static struct cftype files[] = {
	{
		.name = "cpus",
		.read = cpuset_common_file_read,
		.write_string = cpuset_write_resmask,
		.max_write_len = (100U + 6 * NR_CPUS),
		.private = FILE_CPULIST,
	},

	{
		.name = "mems",
		.read = cpuset_common_file_read,
		.write_string = cpuset_write_resmask,
		.max_write_len = (100U + 6 * MAX_NUMNODES),
		.private = FILE_MEMLIST,
	},

	{
		.name = "cpu_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_CPU_EXCLUSIVE,
	},

	{
		.name = "mem_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_EXCLUSIVE,
	},

	{
		.name = "mem_hardwall",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_HARDWALL,
	},

	{
		.name = "sched_load_balance",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SCHED_LOAD_BALANCE,
	},

	{
		.name = "sched_relax_domain_level",
		.read_s64 = cpuset_read_s64,
		.write_s64 = cpuset_write_s64,
		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
	},

	{
		.name = "memory_migrate",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_MIGRATE,
	},

	{
		.name = "memory_pressure",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_PRESSURE,
	},

	{
		.name = "memory_spread_page",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_PAGE,
	},

	{
		.name = "memory_spread_slab",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_SLAB,
	},
};

static struct cftype cft_memory_pressure_enabled = {
	.name = "memory_pressure_enabled",
	.read_u64 = cpuset_read_u64,
	.write_u64 = cpuset_write_u64,
	.private = FILE_MEMORY_PRESSURE_ENABLED,
};

static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
	int err;

	err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
	if (err)
		return err;
	/* memory_pressure_enabled is in root cpuset only */
	if (!cont->parent)
		err = cgroup_add_file(cont, ss,
				      &cft_memory_pressure_enabled);
	return err;
}

/*
 * post_clone() is called at the end of cgroup_clone().
 * 'cgroup' was just created automatically as a result of
 * a cgroup_clone(), and the current task is about to
 * be moved into 'cgroup'.
 *
 * Currently we refuse to set up the cgroup - thereby
 * refusing the task to be entered, and as a result refusing
 * the sys_unshare() or clone() which initiated it - if any
 * sibling cpusets have exclusive cpus or mem.
 *
 * If this becomes a problem for some users who wish to
 * allow that scenario, then cpuset_post_clone() could be
 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
 * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
 * held.
 */
static void cpuset_post_clone(struct cgroup_subsys *ss,
			      struct cgroup *cgroup)
{
	struct cgroup *parent, *child;
	struct cpuset *cs, *parent_cs;

	parent = cgroup->parent;
	list_for_each_entry(child, &parent->children, sibling) {
		cs = cgroup_cs(child);
		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
			return;
	}
	cs = cgroup_cs(cgroup);
	parent_cs = cgroup_cs(parent);

	cs->mems_allowed = parent_cs->mems_allowed;
	cs->cpus_allowed = parent_cs->cpus_allowed;
	return;
}

/*
 *	cpuset_create - create a cpuset
 *	ss:	cpuset cgroup subsystem
 *	cont:	control group that the new cpuset will be part of
 */

static struct cgroup_subsys_state *cpuset_create(
	struct cgroup_subsys *ss,
	struct cgroup *cont)
{
	struct cpuset *cs;
	struct cpuset *parent;

	if (!cont->parent) {
		/* This is early initialization for the top cgroup */
		top_cpuset.mems_generation = cpuset_mems_generation++;
		return &top_cpuset.css;
	}
	parent = cgroup_cs(cont->parent);
	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
	if (!cs)
		return ERR_PTR(-ENOMEM);

	cpuset_update_task_memory_state();
	cs->flags = 0;
	if (is_spread_page(parent))
		set_bit(CS_SPREAD_PAGE, &cs->flags);
	if (is_spread_slab(parent))
		set_bit(CS_SPREAD_SLAB, &cs->flags);
	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
	cpus_clear(cs->cpus_allowed);
	nodes_clear(cs->mems_allowed);
	cs->mems_generation = cpuset_mems_generation++;
	fmeter_init(&cs->fmeter);
	cs->relax_domain_level = -1;

	cs->parent = parent;
	number_of_cpusets++;
	return &cs->css ;
}

/*
 * If the cpuset being removed has its flag 'sched_load_balance'
 * enabled, then simulate turning sched_load_balance off, which
 * will call async_rebuild_sched_domains().
 */

static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct cpuset *cs = cgroup_cs(cont);

	cpuset_update_task_memory_state();

	if (is_sched_load_balance(cs))
		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);

	number_of_cpusets--;
	kfree(cs);
}

struct cgroup_subsys cpuset_subsys = {
	.name = "cpuset",
	.create = cpuset_create,
	.destroy = cpuset_destroy,
	.can_attach = cpuset_can_attach,
	.attach = cpuset_attach,
	.populate = cpuset_populate,
	.post_clone = cpuset_post_clone,
	.subsys_id = cpuset_subsys_id,
	.early_init = 1,
};

/*
 * cpuset_init_early - just enough so that the calls to
 * cpuset_update_task_memory_state() in early init code
 * are harmless.
 */

int __init cpuset_init_early(void)
{
	top_cpuset.mems_generation = cpuset_mems_generation++;
	return 0;
}


/**
 * cpuset_init - initialize cpusets at system boot
 *
 * Description: Initialize top_cpuset and the cpuset internal file system,
 **/

int __init cpuset_init(void)
{
	int err = 0;

	cpus_setall(top_cpuset.cpus_allowed);
	nodes_setall(top_cpuset.mems_allowed);

	fmeter_init(&top_cpuset.fmeter);
	top_cpuset.mems_generation = cpuset_mems_generation++;
	set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
	top_cpuset.relax_domain_level = -1;

	err = register_filesystem(&cpuset_fs_type);
	if (err < 0)
		return err;

	number_of_cpusets = 1;
	return 0;
}

/**
 * cpuset_do_move_task - move a given task to another cpuset
 * @tsk: pointer to task_struct the task to move
 * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner
 *
 * Called by cgroup_scan_tasks() for each task in a cgroup.
 * Return nonzero to stop the walk through the tasks.
 */
static void cpuset_do_move_task(struct task_struct *tsk,
				struct cgroup_scanner *scan)
{
	struct cpuset_hotplug_scanner *chsp;

	chsp = container_of(scan, struct cpuset_hotplug_scanner, scan);
	cgroup_attach_task(chsp->to, tsk);
}

/**
 * move_member_tasks_to_cpuset - move tasks from one cpuset to another
 * @from: cpuset in which the tasks currently reside
 * @to: cpuset to which the tasks will be moved
 *
 * Called with cgroup_mutex held
 * callback_mutex must not be held, as cpuset_attach() will take it.
 *
 * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
 * calling callback functions for each.
 */
static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
{
	struct cpuset_hotplug_scanner scan;

	scan.scan.cg = from->css.cgroup;
	scan.scan.test_task = NULL; /* select all tasks in cgroup */
	scan.scan.process_task = cpuset_do_move_task;
	scan.scan.heap = NULL;
	scan.to = to->css.cgroup;

	if (cgroup_scan_tasks(&scan.scan))
		printk(KERN_ERR "move_member_tasks_to_cpuset: "
				"cgroup_scan_tasks failed\n");
}

/*
 * If CPU and/or memory hotplug handlers, below, unplug any CPUs
 * or memory nodes, we need to walk over the cpuset hierarchy,
 * removing that CPU or node from all cpusets.  If this removes the
 * last CPU or node from a cpuset, then move the tasks in the empty
 * cpuset to its next-highest non-empty parent.
 *
 * Called with cgroup_mutex held
 * callback_mutex must not be held, as cpuset_attach() will take it.
 */
static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
{
	struct cpuset *parent;

	/*
	 * The cgroup's css_sets list is in use if there are tasks
	 * in the cpuset; the list is empty if there are none;
	 * the cs->css.refcnt seems always 0.
	 */
	if (list_empty(&cs->css.cgroup->css_sets))
		return;

	/*
	 * Find its next-highest non-empty parent, (top cpuset
	 * has online cpus, so can't be empty).
	 */
	parent = cs->parent;
	while (cpus_empty(parent->cpus_allowed) ||
			nodes_empty(parent->mems_allowed))
		parent = parent->parent;

	move_member_tasks_to_cpuset(cs, parent);
}

/*
 * Walk the specified cpuset subtree and look for empty cpusets.
 * The tasks of such cpuset must be moved to a parent cpuset.
 *
 * Called with cgroup_mutex held.  We take callback_mutex to modify
 * cpus_allowed and mems_allowed.
 *
 * This walk processes the tree from top to bottom, completing one layer
 * before dropping down to the next.  It always processes a node before
 * any of its children.
 *
 * For now, since we lack memory hot unplug, we'll never see a cpuset
 * that has tasks along with an empty 'mems'.  But if we did see such
 * a cpuset, we'd handle it just like we do if its 'cpus' was empty.
 */
static void scan_for_empty_cpusets(struct cpuset *root)
{
	LIST_HEAD(queue);
	struct cpuset *cp;	/* scans cpusets being updated */
	struct cpuset *child;	/* scans child cpusets of cp */
	struct cgroup *cont;
	nodemask_t oldmems;

	list_add_tail((struct list_head *)&root->stack_list, &queue);

	while (!list_empty(&queue)) {
		cp = list_first_entry(&queue, struct cpuset, stack_list);
		list_del(queue.next);
		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
			child = cgroup_cs(cont);
			list_add_tail(&child->stack_list, &queue);
		}

		/* Continue past cpusets with all cpus, mems online */
		if (cpus_subset(cp->cpus_allowed, cpu_online_map) &&
		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
			continue;

		oldmems = cp->mems_allowed;

		/* Remove offline cpus and mems from this cpuset. */
		mutex_lock(&callback_mutex);
		cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map);
		nodes_and(cp->mems_allowed, cp->mems_allowed,
						node_states[N_HIGH_MEMORY]);
		mutex_unlock(&callback_mutex);

		/* Move tasks from the empty cpuset to a parent */
		if (cpus_empty(cp->cpus_allowed) ||
		     nodes_empty(cp->mems_allowed))
			remove_tasks_in_empty_cpuset(cp);
		else {
			update_tasks_cpumask(cp, NULL);
			update_tasks_nodemask(cp, &oldmems);
		}
	}
}

/*
 * The top_cpuset tracks what CPUs and Memory Nodes are online,
 * period.  This is necessary in order to make cpusets transparent
 * (of no affect) on systems that are actively using CPU hotplug
 * but making no active use of cpusets.
 *
 * This routine ensures that top_cpuset.cpus_allowed tracks
 * cpu_online_map on each CPU hotplug (cpuhp) event.
 *
 * Called within get_online_cpus().  Needs to call cgroup_lock()
 * before calling generate_sched_domains().
 */
static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
				unsigned long phase, void *unused_cpu)
{
	struct sched_domain_attr *attr;
	cpumask_t *doms;
	int ndoms;

	switch (phase) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		break;

	default:
		return NOTIFY_DONE;
	}

	cgroup_lock();
	top_cpuset.cpus_allowed = cpu_online_map;
	scan_for_empty_cpusets(&top_cpuset);
	ndoms = generate_sched_domains(&doms, &attr);
	cgroup_unlock();

	/* Have scheduler rebuild the domains */
	partition_sched_domains(ndoms, doms, attr);

	return NOTIFY_OK;
}

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
 * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
 * See also the previous routine cpuset_track_online_cpus().
 */
void cpuset_track_online_nodes(void)
{
	cgroup_lock();
	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
	scan_for_empty_cpusets(&top_cpuset);
	cgroup_unlock();
}
#endif

/**
 * cpuset_init_smp - initialize cpus_allowed
 *
 * Description: Finish top cpuset after cpu, node maps are initialized
 **/

void __init cpuset_init_smp(void)
{
	top_cpuset.cpus_allowed = cpu_online_map;
	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];

	hotcpu_notifier(cpuset_track_online_cpus, 0);
}

/**
 * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
 * @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
 *
 * Description: Returns the cpumask_t cpus_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of cpu_online_map, even if this means going outside the
 * tasks cpuset.
 **/

void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
{
	mutex_lock(&callback_mutex);
	cpuset_cpus_allowed_locked(tsk, pmask);
	mutex_unlock(&callback_mutex);
}

/**
 * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
 * Must be called with callback_mutex held.
 **/
void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask)
{
	task_lock(tsk);
	guarantee_online_cpus(task_cs(tsk), pmask);
	task_unlock(tsk);
}

void cpuset_init_current_mems_allowed(void)
{
	nodes_setall(current->mems_allowed);
}

/**
 * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
 *
 * Description: Returns the nodemask_t mems_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of node_states[N_HIGH_MEMORY], even if this means going outside the
 * tasks cpuset.
 **/

nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	task_lock(tsk);
	guarantee_online_mems(task_cs(tsk), &mask);
	task_unlock(tsk);
	mutex_unlock(&callback_mutex);

	return mask;
}

/**
 * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed
 * @nodemask: the nodemask to be checked
 *
 * Are any of the nodes in the nodemask allowed in current->mems_allowed?
 */
int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
{
	return nodes_intersects(*nodemask, current->mems_allowed);
}

/*
 * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or
 * mem_hardwall ancestor to the specified cpuset.  Call holding
 * callback_mutex.  If no ancestor is mem_exclusive or mem_hardwall
 * (an unusual configuration), then returns the root cpuset.
 */
static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
{
	while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && cs->parent)
		cs = cs->parent;
	return cs;
}

/**
 * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node?
 * @z: is this zone on an allowed node?
 * @gfp_mask: memory allocation flags
 *
 * If we're in interrupt, yes, we can always allocate.  If
 * __GFP_THISNODE is set, yes, we can always allocate.  If zone
 * z's node is in our tasks mems_allowed, yes.  If it's not a
 * __GFP_HARDWALL request and this zone's nodes is in the nearest
 * hardwalled cpuset ancestor to this tasks cpuset, yes.
 * If the task has been OOM killed and has access to memory reserves
 * as specified by the TIF_MEMDIE flag, yes.
 * Otherwise, no.
 *
 * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall()
 * reduces to cpuset_zone_allowed_hardwall().  Otherwise,
 * cpuset_zone_allowed_softwall() might sleep, and might allow a zone
 * from an enclosing cpuset.
 *
 * cpuset_zone_allowed_hardwall() only handles the simpler case of
 * hardwall cpusets, and never sleeps.
 *
 * The __GFP_THISNODE placement logic is really handled elsewhere,
 * by forcibly using a zonelist starting at a specified node, and by
 * (in get_page_from_freelist()) refusing to consider the zones for
 * any node on the zonelist except the first.  By the time any such
 * calls get to this routine, we should just shut up and say 'yes'.
 *
 * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
 * and do not allow allocations outside the current tasks cpuset
 * unless the task has been OOM killed as is marked TIF_MEMDIE.
 * GFP_KERNEL allocations are not so marked, so can escape to the
 * nearest enclosing hardwalled ancestor cpuset.
 *
 * Scanning up parent cpusets requires callback_mutex.  The
 * __alloc_pages() routine only calls here with __GFP_HARDWALL bit
 * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the
 * current tasks mems_allowed came up empty on the first pass over
 * the zonelist.  So only GFP_KERNEL allocations, if all nodes in the
 * cpuset are short of memory, might require taking the callback_mutex
 * mutex.
 *
 * The first call here from mm/page_alloc:get_page_from_freelist()
 * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets,
 * so no allocation on a node outside the cpuset is allowed (unless
 * in interrupt, of course).
 *
 * The second pass through get_page_from_freelist() doesn't even call
 * here for GFP_ATOMIC calls.  For those calls, the __alloc_pages()
 * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set
 * in alloc_flags.  That logic and the checks below have the combined
 * affect that:
 *	in_interrupt - any node ok (current task context irrelevant)
 *	GFP_ATOMIC   - any node ok
 *	TIF_MEMDIE   - any node ok
 *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
 *	GFP_USER     - only nodes in current tasks mems allowed ok.
 *
 * Rule:
 *    Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you
 *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
 *    the code that might scan up ancestor cpusets and sleep.
 */

int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
{
	int node;			/* node that zone z is on */
	const struct cpuset *cs;	/* current cpuset ancestors */
	int allowed;			/* is allocation in zone z allowed? */

	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
		return 1;
	node = zone_to_nid(z);
	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
	if (node_isset(node, current->mems_allowed))
		return 1;
	/*
	 * Allow tasks that have access to memory reserves because they have
	 * been OOM killed to get memory anywhere.
	 */
	if (unlikely(test_thread_flag(TIF_MEMDIE)))
		return 1;
	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
		return 0;

	if (current->flags & PF_EXITING) /* Let dying task have memory */
		return 1;

	/* Not hardwall and node outside mems_allowed: scan up cpusets */
	mutex_lock(&callback_mutex);

	task_lock(current);
	cs = nearest_hardwall_ancestor(task_cs(current));
	task_unlock(current);

	allowed = node_isset(node, cs->mems_allowed);
	mutex_unlock(&callback_mutex);
	return allowed;
}

/*
 * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node?
 * @z: is this zone on an allowed node?
 * @gfp_mask: memory allocation flags
 *
 * If we're in interrupt, yes, we can always allocate.
 * If __GFP_THISNODE is set, yes, we can always allocate.  If zone
 * z's node is in our tasks mems_allowed, yes.   If the task has been
 * OOM killed and has access to memory reserves as specified by the
 * TIF_MEMDIE flag, yes.  Otherwise, no.
 *
 * The __GFP_THISNODE placement logic is really handled elsewhere,
 * by forcibly using a zonelist starting at a specified node, and by
 * (in get_page_from_freelist()) refusing to consider the zones for
 * any node on the zonelist except the first.  By the time any such
 * calls get to this routine, we should just shut up and say 'yes'.
 *
 * Unlike the cpuset_zone_allowed_softwall() variant, above,
 * this variant requires that the zone be in the current tasks
 * mems_allowed or that we're in interrupt.  It does not scan up the
 * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
 * It never sleeps.
 */

int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
{
	int node;			/* node that zone z is on */

	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
		return 1;
	node = zone_to_nid(z);
	if (node_isset(node, current->mems_allowed))
		return 1;
	/*
	 * Allow tasks that have access to memory reserves because they have
	 * been OOM killed to get memory anywhere.
	 */
	if (unlikely(test_thread_flag(TIF_MEMDIE)))
		return 1;
	return 0;
}

/**
 * cpuset_lock - lock out any changes to cpuset structures
 *
 * The out of memory (oom) code needs to mutex_lock cpusets
 * from being changed while it scans the tasklist looking for a
 * task in an overlapping cpuset.  Expose callback_mutex via this
 * cpuset_lock() routine, so the oom code can lock it, before
 * locking the task list.  The tasklist_lock is a spinlock, so
 * must be taken inside callback_mutex.
 */

void cpuset_lock(void)
{
	mutex_lock(&callback_mutex);
}

/**
 * cpuset_unlock - release lock on cpuset changes
 *
 * Undo the lock taken in a previous cpuset_lock() call.
 */

void cpuset_unlock(void)
{
	mutex_unlock(&callback_mutex);
}

/**
 * cpuset_mem_spread_node() - On which node to begin search for a page
 *
 * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
 * tasks in a cpuset with is_spread_page or is_spread_slab set),
 * and if the memory allocation used cpuset_mem_spread_node()
 * to determine on which node to start looking, as it will for
 * certain page cache or slab cache pages such as used for file
 * system buffers and inode caches, then instead of starting on the
 * local node to look for a free page, rather spread the starting
 * node around the tasks mems_allowed nodes.
 *
 * We don't have to worry about the returned node being offline
 * because "it can't happen", and even if it did, it would be ok.
 *
 * The routines calling guarantee_online_mems() are careful to
 * only set nodes in task->mems_allowed that are online.  So it
 * should not be possible for the following code to return an
 * offline node.  But if it did, that would be ok, as this routine
 * is not returning the node where the allocation must be, only
 * the node where the search should start.  The zonelist passed to
 * __alloc_pages() will include all nodes.  If the slab allocator
 * is passed an offline node, it will fall back to the local node.
 * See kmem_cache_alloc_node().
 */

int cpuset_mem_spread_node(void)
{
	int node;

	node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
	if (node == MAX_NUMNODES)
		node = first_node(current->mems_allowed);
	current->cpuset_mem_spread_rotor = node;
	return node;
}
EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);

/**
 * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's?
 * @tsk1: pointer to task_struct of some task.
 * @tsk2: pointer to task_struct of some other task.
 *
 * Description: Return true if @tsk1's mems_allowed intersects the
 * mems_allowed of @tsk2.  Used by the OOM killer to determine if
 * one of the task's memory usage might impact the memory available
 * to the other.
 **/

int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
				   const struct task_struct *tsk2)
{
	return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed);
}

/*
 * Collection of memory_pressure is suppressed unless
 * this flag is enabled by writing "1" to the special
 * cpuset file 'memory_pressure_enabled' in the root cpuset.
 */

int cpuset_memory_pressure_enabled __read_mostly;

/**
 * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
 *
 * Keep a running average of the rate of synchronous (direct)
 * page reclaim efforts initiated by tasks in each cpuset.
 *
 * This represents the rate at which some task in the cpuset
 * ran low on memory on all nodes it was allowed to use, and
 * had to enter the kernels page reclaim code in an effort to
 * create more free memory by tossing clean pages or swapping
 * or writing dirty pages.
 *
 * Display to user space in the per-cpuset read-only file
 * "memory_pressure".  Value displayed is an integer
 * representing the recent rate of entry into the synchronous
 * (direct) page reclaim by any task attached to the cpuset.
 **/

void __cpuset_memory_pressure_bump(void)
{
	task_lock(current);
	fmeter_markevent(&task_cs(current)->fmeter);
	task_unlock(current);
}

#ifdef CONFIG_PROC_PID_CPUSET
/*
 * proc_cpuset_show()
 *  - Print tasks cpuset path into seq_file.
 *  - Used for /proc/<pid>/cpuset.
 *  - No need to task_lock(tsk) on this tsk->cpuset reference, as it
 *    doesn't really matter if tsk->cpuset changes after we read it,
 *    and we take cgroup_mutex, keeping cpuset_attach() from changing it
 *    anyway.
 */
static int proc_cpuset_show(struct seq_file *m, void *unused_v)
{
	struct pid *pid;
	struct task_struct *tsk;
	char *buf;
	struct cgroup_subsys_state *css;
	int retval;

	retval = -ENOMEM;
	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!buf)
		goto out;

	retval = -ESRCH;
	pid = m->private;
	tsk = get_pid_task(pid, PIDTYPE_PID);
	if (!tsk)
		goto out_free;

	retval = -EINVAL;
	cgroup_lock();
	css = task_subsys_state(tsk, cpuset_subsys_id);
	retval = cgroup_path(css->cgroup, buf, PAGE_SIZE);
	if (retval < 0)
		goto out_unlock;
	seq_puts(m, buf);
	seq_putc(m, '\n');
out_unlock:
	cgroup_unlock();
	put_task_struct(tsk);
out_free:
	kfree(buf);
out:
	return retval;
}

static int cpuset_open(struct inode *inode, struct file *file)
{
	struct pid *pid = PROC_I(inode)->pid;
	return single_open(file, proc_cpuset_show, pid);
}

const struct file_operations proc_cpuset_operations = {
	.open		= cpuset_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};
#endif /* CONFIG_PROC_PID_CPUSET */

/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
{
	seq_printf(m, "Cpus_allowed:\t");
	seq_cpumask(m, &task->cpus_allowed);
	seq_printf(m, "\n");
	seq_printf(m, "Cpus_allowed_list:\t");
	seq_cpumask_list(m, &task->cpus_allowed);
	seq_printf(m, "\n");
	seq_printf(m, "Mems_allowed:\t");
	seq_nodemask(m, &task->mems_allowed);
	seq_printf(m, "\n");
	seq_printf(m, "Mems_allowed_list:\t");
	seq_nodemask_list(m, &task->mems_allowed);
	seq_printf(m, "\n");
}