summaryrefslogtreecommitdiff
path: root/kernel/workqueue.c
blob: e697d6c72daacfd1f0e7ecca67f5d5640a52966d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
/*
 * linux/kernel/workqueue.c
 *
 * Generic mechanism for defining kernel helper threads for running
 * arbitrary tasks in process context.
 *
 * Started by Ingo Molnar, Copyright (C) 2002
 *
 * Derived from the taskqueue/keventd code by:
 *
 *   David Woodhouse <dwmw2@infradead.org>
 *   Andrew Morton
 *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
 *   Theodore Ts'o <tytso@mit.edu>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
#include <linux/delay.h>

enum {
	/* global_cwq flags */
	GCWQ_FREEZING		= 1 << 3,	/* freeze in progress */

	/* worker flags */
	WORKER_STARTED		= 1 << 0,	/* started */
	WORKER_DIE		= 1 << 1,	/* die die die */
	WORKER_IDLE		= 1 << 2,	/* is idle */
	WORKER_ROGUE		= 1 << 4,	/* not bound to any cpu */

	/* gcwq->trustee_state */
	TRUSTEE_START		= 0,		/* start */
	TRUSTEE_IN_CHARGE	= 1,		/* trustee in charge of gcwq */
	TRUSTEE_BUTCHER		= 2,		/* butcher workers */
	TRUSTEE_RELEASE		= 3,		/* release workers */
	TRUSTEE_DONE		= 4,		/* trustee is done */

	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */
	BUSY_WORKER_HASH_SIZE	= 1 << BUSY_WORKER_HASH_ORDER,
	BUSY_WORKER_HASH_MASK	= BUSY_WORKER_HASH_SIZE - 1,

	TRUSTEE_COOLDOWN	= HZ / 10,	/* for trustee draining */
};

/*
 * Structure fields follow one of the following exclusion rules.
 *
 * I: Set during initialization and read-only afterwards.
 *
 * L: gcwq->lock protected.  Access with gcwq->lock held.
 *
 * F: wq->flush_mutex protected.
 *
 * W: workqueue_lock protected.
 */

struct global_cwq;

struct worker {
	/* on idle list while idle, on busy hash table while busy */
	union {
		struct list_head	entry;	/* L: while idle */
		struct hlist_node	hentry;	/* L: while busy */
	};

	struct work_struct	*current_work;	/* L: work being processed */
	struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */
	struct list_head	scheduled;	/* L: scheduled works */
	struct task_struct	*task;		/* I: worker task */
	struct global_cwq	*gcwq;		/* I: the associated gcwq */
	unsigned int		flags;		/* L: flags */
	int			id;		/* I: worker id */
};

/*
 * Global per-cpu workqueue.
 */
struct global_cwq {
	spinlock_t		lock;		/* the gcwq lock */
	struct list_head	worklist;	/* L: list of pending works */
	unsigned int		cpu;		/* I: the associated cpu */
	unsigned int		flags;		/* L: GCWQ_* flags */

	int			nr_workers;	/* L: total number of workers */
	int			nr_idle;	/* L: currently idle ones */

	/* workers are chained either in the idle_list or busy_hash */
	struct list_head	idle_list;	/* L: list of idle workers */
	struct hlist_head	busy_hash[BUSY_WORKER_HASH_SIZE];
						/* L: hash of busy workers */

	struct ida		worker_ida;	/* L: for worker IDs */

	struct task_struct	*trustee;	/* L: for gcwq shutdown */
	unsigned int		trustee_state;	/* L: trustee state */
	wait_queue_head_t	trustee_wait;	/* trustee wait */
} ____cacheline_aligned_in_smp;

/*
 * The per-CPU workqueue.  The lower WORK_STRUCT_FLAG_BITS of
 * work_struct->data are used for flags and thus cwqs need to be
 * aligned at two's power of the number of flag bits.
 */
struct cpu_workqueue_struct {
	struct global_cwq	*gcwq;		/* I: the associated gcwq */
	struct worker		*worker;
	struct workqueue_struct *wq;		/* I: the owning workqueue */
	int			work_color;	/* L: current color */
	int			flush_color;	/* L: flushing color */
	int			nr_in_flight[WORK_NR_COLORS];
						/* L: nr of in_flight works */
	int			nr_active;	/* L: nr of active works */
	int			max_active;	/* L: max active works */
	struct list_head	delayed_works;	/* L: delayed works */
};

/*
 * Structure used to wait for workqueue flush.
 */
struct wq_flusher {
	struct list_head	list;		/* F: list of flushers */
	int			flush_color;	/* F: flush color waiting for */
	struct completion	done;		/* flush completion */
};

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	unsigned int		flags;		/* I: WQ_* flags */
	struct cpu_workqueue_struct *cpu_wq;	/* I: cwq's */
	struct list_head	list;		/* W: list of all workqueues */

	struct mutex		flush_mutex;	/* protects wq flushing */
	int			work_color;	/* F: current work color */
	int			flush_color;	/* F: current flush color */
	atomic_t		nr_cwqs_to_flush; /* flush in progress */
	struct wq_flusher	*first_flusher;	/* F: first flusher */
	struct list_head	flusher_queue;	/* F: flush waiters */
	struct list_head	flusher_overflow; /* F: flush overflow list */

	unsigned long		single_cpu;	/* cpu for single cpu wq */

	int			saved_max_active; /* I: saved cwq max_active */
	const char		*name;		/* I: workqueue name */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map	lockdep_map;
#endif
};

#define for_each_busy_worker(worker, i, pos, gcwq)			\
	for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)			\
		hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)

#ifdef CONFIG_DEBUG_OBJECTS_WORK

static struct debug_obj_descr work_debug_descr;

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static int work_fixup_init(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_init(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int work_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. The work struct was
		 * statically initialized. We just make sure that it
		 * is tracked in the object tracker.
		 */
		if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) {
			debug_object_init(work, &work_debug_descr);
			debug_object_activate(work, &work_debug_descr);
			return 0;
		}
		WARN_ON_ONCE(1);
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int work_fixup_free(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_free(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr work_debug_descr = {
	.name		= "work_struct",
	.fixup_init	= work_fixup_init,
	.fixup_activate	= work_fixup_activate,
	.fixup_free	= work_fixup_free,
};

static inline void debug_work_activate(struct work_struct *work)
{
	debug_object_activate(work, &work_debug_descr);
}

static inline void debug_work_deactivate(struct work_struct *work)
{
	debug_object_deactivate(work, &work_debug_descr);
}

void __init_work(struct work_struct *work, int onstack)
{
	if (onstack)
		debug_object_init_on_stack(work, &work_debug_descr);
	else
		debug_object_init(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(__init_work);

void destroy_work_on_stack(struct work_struct *work)
{
	debug_object_free(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);

#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif

/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
static bool workqueue_freezing;		/* W: have wqs started freezing? */

static DEFINE_PER_CPU(struct global_cwq, global_cwq);

static int worker_thread(void *__worker);

static struct global_cwq *get_gcwq(unsigned int cpu)
{
	return &per_cpu(global_cwq, cpu);
}

static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
					    struct workqueue_struct *wq)
{
	return per_cpu_ptr(wq->cpu_wq, cpu);
}

static unsigned int work_color_to_flags(int color)
{
	return color << WORK_STRUCT_COLOR_SHIFT;
}

static int get_work_color(struct work_struct *work)
{
	return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) &
		((1 << WORK_STRUCT_COLOR_BITS) - 1);
}

static int work_next_color(int color)
{
	return (color + 1) % WORK_NR_COLORS;
}

/*
 * Work data points to the cwq while a work is on queue.  Once
 * execution starts, it points to the cpu the work was last on.  This
 * can be distinguished by comparing the data value against
 * PAGE_OFFSET.
 *
 * set_work_{cwq|cpu}() and clear_work_data() can be used to set the
 * cwq, cpu or clear work->data.  These functions should only be
 * called while the work is owned - ie. while the PENDING bit is set.
 *
 * get_work_[g]cwq() can be used to obtain the gcwq or cwq
 * corresponding to a work.  gcwq is available once the work has been
 * queued anywhere after initialization.  cwq is available only from
 * queueing until execution starts.
 */
static inline void set_work_data(struct work_struct *work, unsigned long data,
				 unsigned long flags)
{
	BUG_ON(!work_pending(work));
	atomic_long_set(&work->data, data | flags | work_static(work));
}

static void set_work_cwq(struct work_struct *work,
			 struct cpu_workqueue_struct *cwq,
			 unsigned long extra_flags)
{
	set_work_data(work, (unsigned long)cwq,
		      WORK_STRUCT_PENDING | extra_flags);
}

static void set_work_cpu(struct work_struct *work, unsigned int cpu)
{
	set_work_data(work, cpu << WORK_STRUCT_FLAG_BITS, WORK_STRUCT_PENDING);
}

static void clear_work_data(struct work_struct *work)
{
	set_work_data(work, WORK_STRUCT_NO_CPU, 0);
}

static inline unsigned long get_work_data(struct work_struct *work)
{
	return atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK;
}

static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work)
{
	unsigned long data = get_work_data(work);

	return data >= PAGE_OFFSET ? (void *)data : NULL;
}

static struct global_cwq *get_work_gcwq(struct work_struct *work)
{
	unsigned long data = get_work_data(work);
	unsigned int cpu;

	if (data >= PAGE_OFFSET)
		return ((struct cpu_workqueue_struct *)data)->gcwq;

	cpu = data >> WORK_STRUCT_FLAG_BITS;
	if (cpu == NR_CPUS)
		return NULL;

	BUG_ON(cpu >= num_possible_cpus());
	return get_gcwq(cpu);
}

/* Return the first worker.  Safe with preemption disabled */
static struct worker *first_worker(struct global_cwq *gcwq)
{
	if (unlikely(list_empty(&gcwq->idle_list)))
		return NULL;

	return list_first_entry(&gcwq->idle_list, struct worker, entry);
}

/**
 * wake_up_worker - wake up an idle worker
 * @gcwq: gcwq to wake worker for
 *
 * Wake up the first idle worker of @gcwq.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void wake_up_worker(struct global_cwq *gcwq)
{
	struct worker *worker = first_worker(gcwq);

	if (likely(worker))
		wake_up_process(worker->task);
}

/**
 * busy_worker_head - return the busy hash head for a work
 * @gcwq: gcwq of interest
 * @work: work to be hashed
 *
 * Return hash head of @gcwq for @work.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 *
 * RETURNS:
 * Pointer to the hash head.
 */
static struct hlist_head *busy_worker_head(struct global_cwq *gcwq,
					   struct work_struct *work)
{
	const int base_shift = ilog2(sizeof(struct work_struct));
	unsigned long v = (unsigned long)work;

	/* simple shift and fold hash, do we need something better? */
	v >>= base_shift;
	v += v >> BUSY_WORKER_HASH_ORDER;
	v &= BUSY_WORKER_HASH_MASK;

	return &gcwq->busy_hash[v];
}

/**
 * __find_worker_executing_work - find worker which is executing a work
 * @gcwq: gcwq of interest
 * @bwh: hash head as returned by busy_worker_head()
 * @work: work to find worker for
 *
 * Find a worker which is executing @work on @gcwq.  @bwh should be
 * the hash head obtained by calling busy_worker_head() with the same
 * work.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 *
 * RETURNS:
 * Pointer to worker which is executing @work if found, NULL
 * otherwise.
 */
static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
						   struct hlist_head *bwh,
						   struct work_struct *work)
{
	struct worker *worker;
	struct hlist_node *tmp;

	hlist_for_each_entry(worker, tmp, bwh, hentry)
		if (worker->current_work == work)
			return worker;
	return NULL;
}

/**
 * find_worker_executing_work - find worker which is executing a work
 * @gcwq: gcwq of interest
 * @work: work to find worker for
 *
 * Find a worker which is executing @work on @gcwq.  This function is
 * identical to __find_worker_executing_work() except that this
 * function calculates @bwh itself.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 *
 * RETURNS:
 * Pointer to worker which is executing @work if found, NULL
 * otherwise.
 */
static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
						 struct work_struct *work)
{
	return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work),
					    work);
}

/**
 * insert_work - insert a work into gcwq
 * @cwq: cwq @work belongs to
 * @work: work to insert
 * @head: insertion point
 * @extra_flags: extra WORK_STRUCT_* flags to set
 *
 * Insert @work which belongs to @cwq into @gcwq after @head.
 * @extra_flags is or'd to work_struct flags.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void insert_work(struct cpu_workqueue_struct *cwq,
			struct work_struct *work, struct list_head *head,
			unsigned int extra_flags)
{
	/* we own @work, set data and link */
	set_work_cwq(work, cwq, extra_flags);

	/*
	 * Ensure that we get the right work->data if we see the
	 * result of list_add() below, see try_to_grab_pending().
	 */
	smp_wmb();

	list_add_tail(&work->entry, head);
	wake_up_worker(cwq->gcwq);
}

/**
 * cwq_unbind_single_cpu - unbind cwq from single cpu workqueue processing
 * @cwq: cwq to unbind
 *
 * Try to unbind @cwq from single cpu workqueue processing.  If
 * @cwq->wq is frozen, unbind is delayed till the workqueue is thawed.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void cwq_unbind_single_cpu(struct cpu_workqueue_struct *cwq)
{
	struct workqueue_struct *wq = cwq->wq;
	struct global_cwq *gcwq = cwq->gcwq;

	BUG_ON(wq->single_cpu != gcwq->cpu);
	/*
	 * Unbind from workqueue if @cwq is not frozen.  If frozen,
	 * thaw_workqueues() will either restart processing on this
	 * cpu or unbind if empty.  This keeps works queued while
	 * frozen fully ordered and flushable.
	 */
	if (likely(!(gcwq->flags & GCWQ_FREEZING))) {
		smp_wmb();	/* paired with cmpxchg() in __queue_work() */
		wq->single_cpu = NR_CPUS;
	}
}

static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
			 struct work_struct *work)
{
	struct global_cwq *gcwq;
	struct cpu_workqueue_struct *cwq;
	struct list_head *worklist;
	unsigned long flags;
	bool arbitrate;

	debug_work_activate(work);

	/*
	 * Determine gcwq to use.  SINGLE_CPU is inherently
	 * NON_REENTRANT, so test it first.
	 */
	if (!(wq->flags & WQ_SINGLE_CPU)) {
		struct global_cwq *last_gcwq;

		/*
		 * It's multi cpu.  If @wq is non-reentrant and @work
		 * was previously on a different cpu, it might still
		 * be running there, in which case the work needs to
		 * be queued on that cpu to guarantee non-reentrance.
		 */
		gcwq = get_gcwq(cpu);
		if (wq->flags & WQ_NON_REENTRANT &&
		    (last_gcwq = get_work_gcwq(work)) && last_gcwq != gcwq) {
			struct worker *worker;

			spin_lock_irqsave(&last_gcwq->lock, flags);

			worker = find_worker_executing_work(last_gcwq, work);

			if (worker && worker->current_cwq->wq == wq)
				gcwq = last_gcwq;
			else {
				/* meh... not running there, queue here */
				spin_unlock_irqrestore(&last_gcwq->lock, flags);
				spin_lock_irqsave(&gcwq->lock, flags);
			}
		} else
			spin_lock_irqsave(&gcwq->lock, flags);
	} else {
		unsigned int req_cpu = cpu;

		/*
		 * It's a bit more complex for single cpu workqueues.
		 * We first need to determine which cpu is going to be
		 * used.  If no cpu is currently serving this
		 * workqueue, arbitrate using atomic accesses to
		 * wq->single_cpu; otherwise, use the current one.
		 */
	retry:
		cpu = wq->single_cpu;
		arbitrate = cpu == NR_CPUS;
		if (arbitrate)
			cpu = req_cpu;

		gcwq = get_gcwq(cpu);
		spin_lock_irqsave(&gcwq->lock, flags);

		/*
		 * The following cmpxchg() is a full barrier paired
		 * with smp_wmb() in cwq_unbind_single_cpu() and
		 * guarantees that all changes to wq->st_* fields are
		 * visible on the new cpu after this point.
		 */
		if (arbitrate)
			cmpxchg(&wq->single_cpu, NR_CPUS, cpu);

		if (unlikely(wq->single_cpu != cpu)) {
			spin_unlock_irqrestore(&gcwq->lock, flags);
			goto retry;
		}
	}

	/* gcwq determined, get cwq and queue */
	cwq = get_cwq(gcwq->cpu, wq);

	BUG_ON(!list_empty(&work->entry));

	cwq->nr_in_flight[cwq->work_color]++;

	if (likely(cwq->nr_active < cwq->max_active)) {
		cwq->nr_active++;
		worklist = &gcwq->worklist;
	} else
		worklist = &cwq->delayed_works;

	insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color));

	spin_unlock_irqrestore(&gcwq->lock, flags);
}

/**
 * queue_work - queue work on a workqueue
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 *
 * We queue the work to the CPU on which it was submitted, but if the CPU dies
 * it can be processed by another CPU.
 */
int queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
	int ret;

	ret = queue_work_on(get_cpu(), wq, work);
	put_cpu();

	return ret;
}
EXPORT_SYMBOL_GPL(queue_work);

/**
 * queue_work_on - queue work on specific cpu
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 *
 * We queue the work to a specific CPU, the caller must ensure it
 * can't go away.
 */
int
queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
{
	int ret = 0;

	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
		__queue_work(cpu, wq, work);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_work_on);

static void delayed_work_timer_fn(unsigned long __data)
{
	struct delayed_work *dwork = (struct delayed_work *)__data;
	struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work);

	__queue_work(smp_processor_id(), cwq->wq, &dwork->work);
}

/**
 * queue_delayed_work - queue work on a workqueue after delay
 * @wq: workqueue to use
 * @dwork: delayable work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work(struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	if (delay == 0)
		return queue_work(wq, &dwork->work);

	return queue_delayed_work_on(-1, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);

/**
 * queue_delayed_work_on - queue work on specific CPU after delay
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	int ret = 0;
	struct timer_list *timer = &dwork->timer;
	struct work_struct *work = &dwork->work;

	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
		struct global_cwq *gcwq = get_work_gcwq(work);
		unsigned int lcpu = gcwq ? gcwq->cpu : raw_smp_processor_id();

		BUG_ON(timer_pending(timer));
		BUG_ON(!list_empty(&work->entry));

		timer_stats_timer_set_start_info(&dwork->timer);
		/*
		 * This stores cwq for the moment, for the timer_fn.
		 * Note that the work's gcwq is preserved to allow
		 * reentrance detection for delayed works.
		 */
		set_work_cwq(work, get_cwq(lcpu, wq), 0);
		timer->expires = jiffies + delay;
		timer->data = (unsigned long)dwork;
		timer->function = delayed_work_timer_fn;

		if (unlikely(cpu >= 0))
			add_timer_on(timer, cpu);
		else
			add_timer(timer);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);

/**
 * worker_enter_idle - enter idle state
 * @worker: worker which is entering idle state
 *
 * @worker is entering idle state.  Update stats and idle timer if
 * necessary.
 *
 * LOCKING:
 * spin_lock_irq(gcwq->lock).
 */
static void worker_enter_idle(struct worker *worker)
{
	struct global_cwq *gcwq = worker->gcwq;

	BUG_ON(worker->flags & WORKER_IDLE);
	BUG_ON(!list_empty(&worker->entry) &&
	       (worker->hentry.next || worker->hentry.pprev));

	worker->flags |= WORKER_IDLE;
	gcwq->nr_idle++;

	/* idle_list is LIFO */
	list_add(&worker->entry, &gcwq->idle_list);

	if (unlikely(worker->flags & WORKER_ROGUE))
		wake_up_all(&gcwq->trustee_wait);
}

/**
 * worker_leave_idle - leave idle state
 * @worker: worker which is leaving idle state
 *
 * @worker is leaving idle state.  Update stats.
 *
 * LOCKING:
 * spin_lock_irq(gcwq->lock).
 */
static void worker_leave_idle(struct worker *worker)
{
	struct global_cwq *gcwq = worker->gcwq;

	BUG_ON(!(worker->flags & WORKER_IDLE));
	worker->flags &= ~WORKER_IDLE;
	gcwq->nr_idle--;
	list_del_init(&worker->entry);
}

static struct worker *alloc_worker(void)
{
	struct worker *worker;

	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
	if (worker) {
		INIT_LIST_HEAD(&worker->entry);
		INIT_LIST_HEAD(&worker->scheduled);
	}
	return worker;
}

/**
 * create_worker - create a new workqueue worker
 * @gcwq: gcwq the new worker will belong to
 * @bind: whether to set affinity to @cpu or not
 *
 * Create a new worker which is bound to @gcwq.  The returned worker
 * can be started by calling start_worker() or destroyed using
 * destroy_worker().
 *
 * CONTEXT:
 * Might sleep.  Does GFP_KERNEL allocations.
 *
 * RETURNS:
 * Pointer to the newly created worker.
 */
static struct worker *create_worker(struct global_cwq *gcwq, bool bind)
{
	int id = -1;
	struct worker *worker = NULL;

	spin_lock_irq(&gcwq->lock);
	while (ida_get_new(&gcwq->worker_ida, &id)) {
		spin_unlock_irq(&gcwq->lock);
		if (!ida_pre_get(&gcwq->worker_ida, GFP_KERNEL))
			goto fail;
		spin_lock_irq(&gcwq->lock);
	}
	spin_unlock_irq(&gcwq->lock);

	worker = alloc_worker();
	if (!worker)
		goto fail;

	worker->gcwq = gcwq;
	worker->id = id;

	worker->task = kthread_create(worker_thread, worker, "kworker/%u:%d",
				      gcwq->cpu, id);
	if (IS_ERR(worker->task))
		goto fail;

	/*
	 * A rogue worker will become a regular one if CPU comes
	 * online later on.  Make sure every worker has
	 * PF_THREAD_BOUND set.
	 */
	if (bind)
		kthread_bind(worker->task, gcwq->cpu);
	else
		worker->task->flags |= PF_THREAD_BOUND;

	return worker;
fail:
	if (id >= 0) {
		spin_lock_irq(&gcwq->lock);
		ida_remove(&gcwq->worker_ida, id);
		spin_unlock_irq(&gcwq->lock);
	}
	kfree(worker);
	return NULL;
}

/**
 * start_worker - start a newly created worker
 * @worker: worker to start
 *
 * Make the gcwq aware of @worker and start it.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void start_worker(struct worker *worker)
{
	worker->flags |= WORKER_STARTED;
	worker->gcwq->nr_workers++;
	worker_enter_idle(worker);
	wake_up_process(worker->task);
}

/**
 * destroy_worker - destroy a workqueue worker
 * @worker: worker to be destroyed
 *
 * Destroy @worker and adjust @gcwq stats accordingly.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which is released and regrabbed.
 */
static void destroy_worker(struct worker *worker)
{
	struct global_cwq *gcwq = worker->gcwq;
	int id = worker->id;

	/* sanity check frenzy */
	BUG_ON(worker->current_work);
	BUG_ON(!list_empty(&worker->scheduled));

	if (worker->flags & WORKER_STARTED)
		gcwq->nr_workers--;
	if (worker->flags & WORKER_IDLE)
		gcwq->nr_idle--;

	list_del_init(&worker->entry);
	worker->flags |= WORKER_DIE;

	spin_unlock_irq(&gcwq->lock);

	kthread_stop(worker->task);
	kfree(worker);

	spin_lock_irq(&gcwq->lock);
	ida_remove(&gcwq->worker_ida, id);
}

/**
 * move_linked_works - move linked works to a list
 * @work: start of series of works to be scheduled
 * @head: target list to append @work to
 * @nextp: out paramter for nested worklist walking
 *
 * Schedule linked works starting from @work to @head.  Work series to
 * be scheduled starts at @work and includes any consecutive work with
 * WORK_STRUCT_LINKED set in its predecessor.
 *
 * If @nextp is not NULL, it's updated to point to the next work of
 * the last scheduled work.  This allows move_linked_works() to be
 * nested inside outer list_for_each_entry_safe().
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void move_linked_works(struct work_struct *work, struct list_head *head,
			      struct work_struct **nextp)
{
	struct work_struct *n;

	/*
	 * Linked worklist will always end before the end of the list,
	 * use NULL for list head.
	 */
	list_for_each_entry_safe_from(work, n, NULL, entry) {
		list_move_tail(&work->entry, head);
		if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
			break;
	}

	/*
	 * If we're already inside safe list traversal and have moved
	 * multiple works to the scheduled queue, the next position
	 * needs to be updated.
	 */
	if (nextp)
		*nextp = n;
}

static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
{
	struct work_struct *work = list_first_entry(&cwq->delayed_works,
						    struct work_struct, entry);

	move_linked_works(work, &cwq->gcwq->worklist, NULL);
	cwq->nr_active++;
}

/**
 * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
 * @cwq: cwq of interest
 * @color: color of work which left the queue
 *
 * A work either has completed or is removed from pending queue,
 * decrement nr_in_flight of its cwq and handle workqueue flushing.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
{
	/* ignore uncolored works */
	if (color == WORK_NO_COLOR)
		return;

	cwq->nr_in_flight[color]--;
	cwq->nr_active--;

	if (!list_empty(&cwq->delayed_works)) {
		/* one down, submit a delayed one */
		if (cwq->nr_active < cwq->max_active)
			cwq_activate_first_delayed(cwq);
	} else if (!cwq->nr_active && cwq->wq->flags & WQ_SINGLE_CPU) {
		/* this was the last work, unbind from single cpu */
		cwq_unbind_single_cpu(cwq);
	}

	/* is flush in progress and are we at the flushing tip? */
	if (likely(cwq->flush_color != color))
		return;

	/* are there still in-flight works? */
	if (cwq->nr_in_flight[color])
		return;

	/* this cwq is done, clear flush_color */
	cwq->flush_color = -1;

	/*
	 * If this was the last cwq, wake up the first flusher.  It
	 * will handle the rest.
	 */
	if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush))
		complete(&cwq->wq->first_flusher->done);
}

/**
 * process_one_work - process single work
 * @worker: self
 * @work: work to process
 *
 * Process @work.  This function contains all the logics necessary to
 * process a single work including synchronization against and
 * interaction with other workers on the same cpu, queueing and
 * flushing.  As long as context requirement is met, any worker can
 * call this function to process a work.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which is released and regrabbed.
 */
static void process_one_work(struct worker *worker, struct work_struct *work)
{
	struct cpu_workqueue_struct *cwq = get_work_cwq(work);
	struct global_cwq *gcwq = cwq->gcwq;
	struct hlist_head *bwh = busy_worker_head(gcwq, work);
	work_func_t f = work->func;
	int work_color;
	struct worker *collision;
#ifdef CONFIG_LOCKDEP
	/*
	 * It is permissible to free the struct work_struct from
	 * inside the function that is called from it, this we need to
	 * take into account for lockdep too.  To avoid bogus "held
	 * lock freed" warnings as well as problems when looking into
	 * work->lockdep_map, make a copy and use that here.
	 */
	struct lockdep_map lockdep_map = work->lockdep_map;
#endif
	/*
	 * A single work shouldn't be executed concurrently by
	 * multiple workers on a single cpu.  Check whether anyone is
	 * already processing the work.  If so, defer the work to the
	 * currently executing one.
	 */
	collision = __find_worker_executing_work(gcwq, bwh, work);
	if (unlikely(collision)) {
		move_linked_works(work, &collision->scheduled, NULL);
		return;
	}

	/* claim and process */
	debug_work_deactivate(work);
	hlist_add_head(&worker->hentry, bwh);
	worker->current_work = work;
	worker->current_cwq = cwq;
	work_color = get_work_color(work);

	/* record the current cpu number in the work data and dequeue */
	set_work_cpu(work, gcwq->cpu);
	list_del_init(&work->entry);

	spin_unlock_irq(&gcwq->lock);

	work_clear_pending(work);
	lock_map_acquire(&cwq->wq->lockdep_map);
	lock_map_acquire(&lockdep_map);
	f(work);
	lock_map_release(&lockdep_map);
	lock_map_release(&cwq->wq->lockdep_map);

	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
		printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
		       "%s/0x%08x/%d\n",
		       current->comm, preempt_count(), task_pid_nr(current));
		printk(KERN_ERR "    last function: ");
		print_symbol("%s\n", (unsigned long)f);
		debug_show_held_locks(current);
		dump_stack();
	}

	spin_lock_irq(&gcwq->lock);

	/* we're done with it, release */
	hlist_del_init(&worker->hentry);
	worker->current_work = NULL;
	worker->current_cwq = NULL;
	cwq_dec_nr_in_flight(cwq, work_color);
}

/**
 * process_scheduled_works - process scheduled works
 * @worker: self
 *
 * Process all scheduled works.  Please note that the scheduled list
 * may change while processing a work, so this function repeatedly
 * fetches a work from the top and executes it.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which may be released and regrabbed
 * multiple times.
 */
static void process_scheduled_works(struct worker *worker)
{
	while (!list_empty(&worker->scheduled)) {
		struct work_struct *work = list_first_entry(&worker->scheduled,
						struct work_struct, entry);
		process_one_work(worker, work);
	}
}

/**
 * worker_thread - the worker thread function
 * @__worker: self
 *
 * The cwq worker thread function.
 */
static int worker_thread(void *__worker)
{
	struct worker *worker = __worker;
	struct global_cwq *gcwq = worker->gcwq;

woke_up:
	spin_lock_irq(&gcwq->lock);

	/* DIE can be set only while we're idle, checking here is enough */
	if (worker->flags & WORKER_DIE) {
		spin_unlock_irq(&gcwq->lock);
		return 0;
	}

	worker_leave_idle(worker);
recheck:
	/*
	 * ->scheduled list can only be filled while a worker is
	 * preparing to process a work or actually processing it.
	 * Make sure nobody diddled with it while I was sleeping.
	 */
	BUG_ON(!list_empty(&worker->scheduled));

	while (!list_empty(&gcwq->worklist)) {
		struct work_struct *work =
			list_first_entry(&gcwq->worklist,
					 struct work_struct, entry);

		/*
		 * The following is a rather inefficient way to close
		 * race window against cpu hotplug operations.  Will
		 * be replaced soon.
		 */
		if (unlikely(!(worker->flags & WORKER_ROGUE) &&
			     !cpumask_equal(&worker->task->cpus_allowed,
					    get_cpu_mask(gcwq->cpu)))) {
			spin_unlock_irq(&gcwq->lock);
			set_cpus_allowed_ptr(worker->task,
					     get_cpu_mask(gcwq->cpu));
			cpu_relax();
			spin_lock_irq(&gcwq->lock);
			goto recheck;
		}

		if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
			/* optimization path, not strictly necessary */
			process_one_work(worker, work);
			if (unlikely(!list_empty(&worker->scheduled)))
				process_scheduled_works(worker);
		} else {
			move_linked_works(work, &worker->scheduled, NULL);
			process_scheduled_works(worker);
		}
	}

	/*
	 * gcwq->lock is held and there's no work to process, sleep.
	 * Workers are woken up only while holding gcwq->lock, so
	 * setting the current state before releasing gcwq->lock is
	 * enough to prevent losing any event.
	 */
	worker_enter_idle(worker);
	__set_current_state(TASK_INTERRUPTIBLE);
	spin_unlock_irq(&gcwq->lock);
	schedule();
	goto woke_up;
}

struct wq_barrier {
	struct work_struct	work;
	struct completion	done;
};

static void wq_barrier_func(struct work_struct *work)
{
	struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
	complete(&barr->done);
}

/**
 * insert_wq_barrier - insert a barrier work
 * @cwq: cwq to insert barrier into
 * @barr: wq_barrier to insert
 * @target: target work to attach @barr to
 * @worker: worker currently executing @target, NULL if @target is not executing
 *
 * @barr is linked to @target such that @barr is completed only after
 * @target finishes execution.  Please note that the ordering
 * guarantee is observed only with respect to @target and on the local
 * cpu.
 *
 * Currently, a queued barrier can't be canceled.  This is because
 * try_to_grab_pending() can't determine whether the work to be
 * grabbed is at the head of the queue and thus can't clear LINKED
 * flag of the previous work while there must be a valid next work
 * after a work with LINKED flag set.
 *
 * Note that when @worker is non-NULL, @target may be modified
 * underneath us, so we can't reliably determine cwq from @target.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock).
 */
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
			      struct wq_barrier *barr,
			      struct work_struct *target, struct worker *worker)
{
	struct list_head *head;
	unsigned int linked = 0;

	/*
	 * debugobject calls are safe here even with gcwq->lock locked
	 * as we know for sure that this will not trigger any of the
	 * checks and call back into the fixup functions where we
	 * might deadlock.
	 */
	INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
	init_completion(&barr->done);

	/*
	 * If @target is currently being executed, schedule the
	 * barrier to the worker; otherwise, put it after @target.
	 */
	if (worker)
		head = worker->scheduled.next;
	else {
		unsigned long *bits = work_data_bits(target);

		head = target->entry.next;
		/* there can already be other linked works, inherit and set */
		linked = *bits & WORK_STRUCT_LINKED;
		__set_bit(WORK_STRUCT_LINKED_BIT, bits);
	}

	debug_work_activate(&barr->work);
	insert_work(cwq, &barr->work, head,
		    work_color_to_flags(WORK_NO_COLOR) | linked);
}

/**
 * flush_workqueue_prep_cwqs - prepare cwqs for workqueue flushing
 * @wq: workqueue being flushed
 * @flush_color: new flush color, < 0 for no-op
 * @work_color: new work color, < 0 for no-op
 *
 * Prepare cwqs for workqueue flushing.
 *
 * If @flush_color is non-negative, flush_color on all cwqs should be
 * -1.  If no cwq has in-flight commands at the specified color, all
 * cwq->flush_color's stay at -1 and %false is returned.  If any cwq
 * has in flight commands, its cwq->flush_color is set to
 * @flush_color, @wq->nr_cwqs_to_flush is updated accordingly, cwq
 * wakeup logic is armed and %true is returned.
 *
 * The caller should have initialized @wq->first_flusher prior to
 * calling this function with non-negative @flush_color.  If
 * @flush_color is negative, no flush color update is done and %false
 * is returned.
 *
 * If @work_color is non-negative, all cwqs should have the same
 * work_color which is previous to @work_color and all will be
 * advanced to @work_color.
 *
 * CONTEXT:
 * mutex_lock(wq->flush_mutex).
 *
 * RETURNS:
 * %true if @flush_color >= 0 and there's something to flush.  %false
 * otherwise.
 */
static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq,
				      int flush_color, int work_color)
{
	bool wait = false;
	unsigned int cpu;

	if (flush_color >= 0) {
		BUG_ON(atomic_read(&wq->nr_cwqs_to_flush));
		atomic_set(&wq->nr_cwqs_to_flush, 1);
	}

	for_each_possible_cpu(cpu) {
		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
		struct global_cwq *gcwq = cwq->gcwq;

		spin_lock_irq(&gcwq->lock);

		if (flush_color >= 0) {
			BUG_ON(cwq->flush_color != -1);

			if (cwq->nr_in_flight[flush_color]) {
				cwq->flush_color = flush_color;
				atomic_inc(&wq->nr_cwqs_to_flush);
				wait = true;
			}
		}

		if (work_color >= 0) {
			BUG_ON(work_color != work_next_color(cwq->work_color));
			cwq->work_color = work_color;
		}

		spin_unlock_irq(&gcwq->lock);
	}

	if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_cwqs_to_flush))
		complete(&wq->first_flusher->done);

	return wait;
}

/**
 * flush_workqueue - ensure that any scheduled work has run to completion.
 * @wq: workqueue to flush
 *
 * Forces execution of the workqueue and blocks until its completion.
 * This is typically used in driver shutdown handlers.
 *
 * We sleep until all works which were queued on entry have been handled,
 * but we are not livelocked by new incoming ones.
 */
void flush_workqueue(struct workqueue_struct *wq)
{
	struct wq_flusher this_flusher = {
		.list = LIST_HEAD_INIT(this_flusher.list),
		.flush_color = -1,
		.done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done),
	};
	int next_color;

	lock_map_acquire(&wq->lockdep_map);
	lock_map_release(&wq->lockdep_map);

	mutex_lock(&wq->flush_mutex);

	/*
	 * Start-to-wait phase
	 */
	next_color = work_next_color(wq->work_color);

	if (next_color != wq->flush_color) {
		/*
		 * Color space is not full.  The current work_color
		 * becomes our flush_color and work_color is advanced
		 * by one.
		 */
		BUG_ON(!list_empty(&wq->flusher_overflow));
		this_flusher.flush_color = wq->work_color;
		wq->work_color = next_color;

		if (!wq->first_flusher) {
			/* no flush in progress, become the first flusher */
			BUG_ON(wq->flush_color != this_flusher.flush_color);

			wq->first_flusher = &this_flusher;

			if (!flush_workqueue_prep_cwqs(wq, wq->flush_color,
						       wq->work_color)) {
				/* nothing to flush, done */
				wq->flush_color = next_color;
				wq->first_flusher = NULL;
				goto out_unlock;
			}
		} else {
			/* wait in queue */
			BUG_ON(wq->flush_color == this_flusher.flush_color);
			list_add_tail(&this_flusher.list, &wq->flusher_queue);
			flush_workqueue_prep_cwqs(wq, -1, wq->work_color);
		}
	} else {
		/*
		 * Oops, color space is full, wait on overflow queue.
		 * The next flush completion will assign us
		 * flush_color and transfer to flusher_queue.
		 */
		list_add_tail(&this_flusher.list, &wq->flusher_overflow);
	}

	mutex_unlock(&wq->flush_mutex);

	wait_for_completion(&this_flusher.done);

	/*
	 * Wake-up-and-cascade phase
	 *
	 * First flushers are responsible for cascading flushes and
	 * handling overflow.  Non-first flushers can simply return.
	 */
	if (wq->first_flusher != &this_flusher)
		return;

	mutex_lock(&wq->flush_mutex);

	wq->first_flusher = NULL;

	BUG_ON(!list_empty(&this_flusher.list));
	BUG_ON(wq->flush_color != this_flusher.flush_color);

	while (true) {
		struct wq_flusher *next, *tmp;

		/* complete all the flushers sharing the current flush color */
		list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) {
			if (next->flush_color != wq->flush_color)
				break;
			list_del_init(&next->list);
			complete(&next->done);
		}

		BUG_ON(!list_empty(&wq->flusher_overflow) &&
		       wq->flush_color != work_next_color(wq->work_color));

		/* this flush_color is finished, advance by one */
		wq->flush_color = work_next_color(wq->flush_color);

		/* one color has been freed, handle overflow queue */
		if (!list_empty(&wq->flusher_overflow)) {
			/*
			 * Assign the same color to all overflowed
			 * flushers, advance work_color and append to
			 * flusher_queue.  This is the start-to-wait
			 * phase for these overflowed flushers.
			 */
			list_for_each_entry(tmp, &wq->flusher_overflow, list)
				tmp->flush_color = wq->work_color;

			wq->work_color = work_next_color(wq->work_color);

			list_splice_tail_init(&wq->flusher_overflow,
					      &wq->flusher_queue);
			flush_workqueue_prep_cwqs(wq, -1, wq->work_color);
		}

		if (list_empty(&wq->flusher_queue)) {
			BUG_ON(wq->flush_color != wq->work_color);
			break;
		}

		/*
		 * Need to flush more colors.  Make the next flusher
		 * the new first flusher and arm cwqs.
		 */
		BUG_ON(wq->flush_color == wq->work_color);
		BUG_ON(wq->flush_color != next->flush_color);

		list_del_init(&next->list);
		wq->first_flusher = next;

		if (flush_workqueue_prep_cwqs(wq, wq->flush_color, -1))
			break;

		/*
		 * Meh... this color is already done, clear first
		 * flusher and repeat cascading.
		 */
		wq->first_flusher = NULL;
	}

out_unlock:
	mutex_unlock(&wq->flush_mutex);
}
EXPORT_SYMBOL_GPL(flush_workqueue);

/**
 * flush_work - block until a work_struct's callback has terminated
 * @work: the work which is to be flushed
 *
 * Returns false if @work has already terminated.
 *
 * It is expected that, prior to calling flush_work(), the caller has
 * arranged for the work to not be requeued, otherwise it doesn't make
 * sense to use this function.
 */
int flush_work(struct work_struct *work)
{
	struct worker *worker = NULL;
	struct global_cwq *gcwq;
	struct cpu_workqueue_struct *cwq;
	struct wq_barrier barr;

	might_sleep();
	gcwq = get_work_gcwq(work);
	if (!gcwq)
		return 0;

	spin_lock_irq(&gcwq->lock);
	if (!list_empty(&work->entry)) {
		/*
		 * See the comment near try_to_grab_pending()->smp_rmb().
		 * If it was re-queued to a different gcwq under us, we
		 * are not going to wait.
		 */
		smp_rmb();
		cwq = get_work_cwq(work);
		if (unlikely(!cwq || gcwq != cwq->gcwq))
			goto already_gone;
	} else {
		worker = find_worker_executing_work(gcwq, work);
		if (!worker)
			goto already_gone;
		cwq = worker->current_cwq;
	}

	insert_wq_barrier(cwq, &barr, work, worker);
	spin_unlock_irq(&gcwq->lock);

	lock_map_acquire(&cwq->wq->lockdep_map);
	lock_map_release(&cwq->wq->lockdep_map);

	wait_for_completion(&barr.done);
	destroy_work_on_stack(&barr.work);
	return 1;
already_gone:
	spin_unlock_irq(&gcwq->lock);
	return 0;
}
EXPORT_SYMBOL_GPL(flush_work);

/*
 * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
 * so this work can't be re-armed in any way.
 */
static int try_to_grab_pending(struct work_struct *work)
{
	struct global_cwq *gcwq;
	int ret = -1;

	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
		return 0;

	/*
	 * The queueing is in progress, or it is already queued. Try to
	 * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
	 */
	gcwq = get_work_gcwq(work);
	if (!gcwq)
		return ret;

	spin_lock_irq(&gcwq->lock);
	if (!list_empty(&work->entry)) {
		/*
		 * This work is queued, but perhaps we locked the wrong gcwq.
		 * In that case we must see the new value after rmb(), see
		 * insert_work()->wmb().
		 */
		smp_rmb();
		if (gcwq == get_work_gcwq(work)) {
			debug_work_deactivate(work);
			list_del_init(&work->entry);
			cwq_dec_nr_in_flight(get_work_cwq(work),
					     get_work_color(work));
			ret = 1;
		}
	}
	spin_unlock_irq(&gcwq->lock);

	return ret;
}

static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
{
	struct wq_barrier barr;
	struct worker *worker;

	spin_lock_irq(&gcwq->lock);

	worker = find_worker_executing_work(gcwq, work);
	if (unlikely(worker))
		insert_wq_barrier(worker->current_cwq, &barr, work, worker);

	spin_unlock_irq(&gcwq->lock);

	if (unlikely(worker)) {
		wait_for_completion(&barr.done);
		destroy_work_on_stack(&barr.work);
	}
}

static void wait_on_work(struct work_struct *work)
{
	int cpu;

	might_sleep();

	lock_map_acquire(&work->lockdep_map);
	lock_map_release(&work->lockdep_map);

	for_each_possible_cpu(cpu)
		wait_on_cpu_work(get_gcwq(cpu), work);
}

static int __cancel_work_timer(struct work_struct *work,
				struct timer_list* timer)
{
	int ret;

	do {
		ret = (timer && likely(del_timer(timer)));
		if (!ret)
			ret = try_to_grab_pending(work);
		wait_on_work(work);
	} while (unlikely(ret < 0));

	clear_work_data(work);
	return ret;
}

/**
 * cancel_work_sync - block until a work_struct's callback has terminated
 * @work: the work which is to be flushed
 *
 * Returns true if @work was pending.
 *
 * cancel_work_sync() will cancel the work if it is queued. If the work's
 * callback appears to be running, cancel_work_sync() will block until it
 * has completed.
 *
 * It is possible to use this function if the work re-queues itself. It can
 * cancel the work even if it migrates to another workqueue, however in that
 * case it only guarantees that work->func() has completed on the last queued
 * workqueue.
 *
 * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
 * pending, otherwise it goes into a busy-wait loop until the timer expires.
 *
 * The caller must ensure that workqueue_struct on which this work was last
 * queued can't be destroyed before this function returns.
 */
int cancel_work_sync(struct work_struct *work)
{
	return __cancel_work_timer(work, NULL);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);

/**
 * cancel_delayed_work_sync - reliably kill off a delayed work.
 * @dwork: the delayed work struct
 *
 * Returns true if @dwork was pending.
 *
 * It is possible to use this function if @dwork rearms itself via queue_work()
 * or queue_delayed_work(). See also the comment for cancel_work_sync().
 */
int cancel_delayed_work_sync(struct delayed_work *dwork)
{
	return __cancel_work_timer(&dwork->work, &dwork->timer);
}
EXPORT_SYMBOL(cancel_delayed_work_sync);

static struct workqueue_struct *keventd_wq __read_mostly;

/**
 * schedule_work - put work task in global workqueue
 * @work: job to be done
 *
 * Returns zero if @work was already on the kernel-global workqueue and
 * non-zero otherwise.
 *
 * This puts a job in the kernel-global workqueue if it was not already
 * queued and leaves it in the same position on the kernel-global
 * workqueue otherwise.
 */
int schedule_work(struct work_struct *work)
{
	return queue_work(keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work);

/*
 * schedule_work_on - put work task on a specific cpu
 * @cpu: cpu to put the work task on
 * @work: job to be done
 *
 * This puts a job on a specific cpu
 */
int schedule_work_on(int cpu, struct work_struct *work)
{
	return queue_work_on(cpu, keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work_on);

/**
 * schedule_delayed_work - put work task in global workqueue after delay
 * @dwork: job to be done
 * @delay: number of jiffies to wait or 0 for immediate execution
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue.
 */
int schedule_delayed_work(struct delayed_work *dwork,
					unsigned long delay)
{
	return queue_delayed_work(keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work);

/**
 * flush_delayed_work - block until a dwork_struct's callback has terminated
 * @dwork: the delayed work which is to be flushed
 *
 * Any timeout is cancelled, and any pending work is run immediately.
 */
void flush_delayed_work(struct delayed_work *dwork)
{
	if (del_timer_sync(&dwork->timer)) {
		__queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
			     &dwork->work);
		put_cpu();
	}
	flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);

/**
 * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
 * @cpu: cpu to use
 * @dwork: job to be done
 * @delay: number of jiffies to wait
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue on the specified CPU.
 */
int schedule_delayed_work_on(int cpu,
			struct delayed_work *dwork, unsigned long delay)
{
	return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);

/**
 * schedule_on_each_cpu - call a function on each online CPU from keventd
 * @func: the function to call
 *
 * Returns zero on success.
 * Returns -ve errno on failure.
 *
 * schedule_on_each_cpu() is very slow.
 */
int schedule_on_each_cpu(work_func_t func)
{
	int cpu;
	int orig = -1;
	struct work_struct *works;

	works = alloc_percpu(struct work_struct);
	if (!works)
		return -ENOMEM;

	get_online_cpus();

	/*
	 * When running in keventd don't schedule a work item on
	 * itself.  Can just call directly because the work queue is
	 * already bound.  This also is faster.
	 */
	if (current_is_keventd())
		orig = raw_smp_processor_id();

	for_each_online_cpu(cpu) {
		struct work_struct *work = per_cpu_ptr(works, cpu);

		INIT_WORK(work, func);
		if (cpu != orig)
			schedule_work_on(cpu, work);
	}
	if (orig >= 0)
		func(per_cpu_ptr(works, orig));

	for_each_online_cpu(cpu)
		flush_work(per_cpu_ptr(works, cpu));

	put_online_cpus();
	free_percpu(works);
	return 0;
}

/**
 * flush_scheduled_work - ensure that any scheduled work has run to completion.
 *
 * Forces execution of the kernel-global workqueue and blocks until its
 * completion.
 *
 * Think twice before calling this function!  It's very easy to get into
 * trouble if you don't take great care.  Either of the following situations
 * will lead to deadlock:
 *
 *	One of the work items currently on the workqueue needs to acquire
 *	a lock held by your code or its caller.
 *
 *	Your code is running in the context of a work routine.
 *
 * They will be detected by lockdep when they occur, but the first might not
 * occur very often.  It depends on what work items are on the workqueue and
 * what locks they need, which you have no control over.
 *
 * In most situations flushing the entire workqueue is overkill; you merely
 * need to know that a particular work item isn't queued and isn't running.
 * In such cases you should use cancel_delayed_work_sync() or
 * cancel_work_sync() instead.
 */
void flush_scheduled_work(void)
{
	flush_workqueue(keventd_wq);
}
EXPORT_SYMBOL(flush_scheduled_work);

/**
 * execute_in_process_context - reliably execute the routine with user context
 * @fn:		the function to execute
 * @ew:		guaranteed storage for the execute work structure (must
 *		be available when the work executes)
 *
 * Executes the function immediately if process context is available,
 * otherwise schedules the function for delayed execution.
 *
 * Returns:	0 - function was executed
 *		1 - function was scheduled for execution
 */
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{
	if (!in_interrupt()) {
		fn(&ew->work);
		return 0;
	}

	INIT_WORK(&ew->work, fn);
	schedule_work(&ew->work);

	return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);

int keventd_up(void)
{
	return keventd_wq != NULL;
}

int current_is_keventd(void)
{
	bool found = false;
	unsigned int cpu;

	/*
	 * There no longer is one-to-one relation between worker and
	 * work queue and a worker task might be unbound from its cpu
	 * if the cpu was offlined.  Match all busy workers.  This
	 * function will go away once dynamic pool is implemented.
	 */
	for_each_possible_cpu(cpu) {
		struct global_cwq *gcwq = get_gcwq(cpu);
		struct worker *worker;
		struct hlist_node *pos;
		unsigned long flags;
		int i;

		spin_lock_irqsave(&gcwq->lock, flags);

		for_each_busy_worker(worker, i, pos, gcwq) {
			if (worker->task == current) {
				found = true;
				break;
			}
		}

		spin_unlock_irqrestore(&gcwq->lock, flags);
		if (found)
			break;
	}

	return found;
}

static struct cpu_workqueue_struct *alloc_cwqs(void)
{
	/*
	 * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
	 * Make sure that the alignment isn't lower than that of
	 * unsigned long long.
	 */
	const size_t size = sizeof(struct cpu_workqueue_struct);
	const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS,
				   __alignof__(unsigned long long));
	struct cpu_workqueue_struct *cwqs;
#ifndef CONFIG_SMP
	void *ptr;

	/*
	 * On UP, percpu allocator doesn't honor alignment parameter
	 * and simply uses arch-dependent default.  Allocate enough
	 * room to align cwq and put an extra pointer at the end
	 * pointing back to the originally allocated pointer which
	 * will be used for free.
	 *
	 * FIXME: This really belongs to UP percpu code.  Update UP
	 * percpu code to honor alignment and remove this ugliness.
	 */
	ptr = __alloc_percpu(size + align + sizeof(void *), 1);
	cwqs = PTR_ALIGN(ptr, align);
	*(void **)per_cpu_ptr(cwqs + 1, 0) = ptr;
#else
	/* On SMP, percpu allocator can do it itself */
	cwqs = __alloc_percpu(size, align);
#endif
	/* just in case, make sure it's actually aligned */
	BUG_ON(!IS_ALIGNED((unsigned long)cwqs, align));
	return cwqs;
}

static void free_cwqs(struct cpu_workqueue_struct *cwqs)
{
#ifndef CONFIG_SMP
	/* on UP, the pointer to free is stored right after the cwq */
	if (cwqs)
		free_percpu(*(void **)per_cpu_ptr(cwqs + 1, 0));
#else
	free_percpu(cwqs);
#endif
}

struct workqueue_struct *__create_workqueue_key(const char *name,
						unsigned int flags,
						int max_active,
						struct lock_class_key *key,
						const char *lock_name)
{
	struct workqueue_struct *wq;
	bool failed = false;
	unsigned int cpu;

	max_active = clamp_val(max_active, 1, INT_MAX);

	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
	if (!wq)
		goto err;

	wq->cpu_wq = alloc_cwqs();
	if (!wq->cpu_wq)
		goto err;

	wq->flags = flags;
	wq->saved_max_active = max_active;
	mutex_init(&wq->flush_mutex);
	atomic_set(&wq->nr_cwqs_to_flush, 0);
	INIT_LIST_HEAD(&wq->flusher_queue);
	INIT_LIST_HEAD(&wq->flusher_overflow);
	wq->single_cpu = NR_CPUS;

	wq->name = name;
	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
	INIT_LIST_HEAD(&wq->list);

	cpu_maps_update_begin();
	/*
	 * We must initialize cwqs for each possible cpu even if we
	 * are going to call destroy_workqueue() finally. Otherwise
	 * cpu_up() can hit the uninitialized cwq once we drop the
	 * lock.
	 */
	for_each_possible_cpu(cpu) {
		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
		struct global_cwq *gcwq = get_gcwq(cpu);

		BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK);
		cwq->gcwq = gcwq;
		cwq->wq = wq;
		cwq->flush_color = -1;
		cwq->max_active = max_active;
		INIT_LIST_HEAD(&cwq->delayed_works);

		if (failed)
			continue;
		cwq->worker = create_worker(gcwq, cpu_online(cpu));
		if (cwq->worker)
			start_worker(cwq->worker);
		else
			failed = true;
	}

	/*
	 * workqueue_lock protects global freeze state and workqueues
	 * list.  Grab it, set max_active accordingly and add the new
	 * workqueue to workqueues list.
	 */
	spin_lock(&workqueue_lock);

	if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
		for_each_possible_cpu(cpu)
			get_cwq(cpu, wq)->max_active = 0;

	list_add(&wq->list, &workqueues);

	spin_unlock(&workqueue_lock);

	cpu_maps_update_done();

	if (failed) {
		destroy_workqueue(wq);
		wq = NULL;
	}
	return wq;
err:
	if (wq) {
		free_cwqs(wq->cpu_wq);
		kfree(wq);
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(__create_workqueue_key);

/**
 * destroy_workqueue - safely terminate a workqueue
 * @wq: target workqueue
 *
 * Safely destroy a workqueue. All work currently pending will be done first.
 */
void destroy_workqueue(struct workqueue_struct *wq)
{
	unsigned int cpu;

	flush_workqueue(wq);

	/*
	 * wq list is used to freeze wq, remove from list after
	 * flushing is complete in case freeze races us.
	 */
	cpu_maps_update_begin();
	spin_lock(&workqueue_lock);
	list_del(&wq->list);
	spin_unlock(&workqueue_lock);
	cpu_maps_update_done();

	for_each_possible_cpu(cpu) {
		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
		struct global_cwq *gcwq = cwq->gcwq;
		int i;

		if (cwq->worker) {
		retry:
			spin_lock_irq(&gcwq->lock);
			/*
			 * Worker can only be destroyed while idle.
			 * Wait till it becomes idle.  This is ugly
			 * and prone to starvation.  It will go away
			 * once dynamic worker pool is implemented.
			 */
			if (!(cwq->worker->flags & WORKER_IDLE)) {
				spin_unlock_irq(&gcwq->lock);
				msleep(100);
				goto retry;
			}
			destroy_worker(cwq->worker);
			cwq->worker = NULL;
			spin_unlock_irq(&gcwq->lock);
		}

		for (i = 0; i < WORK_NR_COLORS; i++)
			BUG_ON(cwq->nr_in_flight[i]);
		BUG_ON(cwq->nr_active);
		BUG_ON(!list_empty(&cwq->delayed_works));
	}

	free_cwqs(wq->cpu_wq);
	kfree(wq);
}
EXPORT_SYMBOL_GPL(destroy_workqueue);

/*
 * CPU hotplug.
 *
 * CPU hotplug is implemented by allowing cwqs to be detached from
 * CPU, running with unbound workers and allowing them to be
 * reattached later if the cpu comes back online.  A separate thread
 * is created to govern cwqs in such state and is called the trustee.
 *
 * Trustee states and their descriptions.
 *
 * START	Command state used on startup.  On CPU_DOWN_PREPARE, a
 *		new trustee is started with this state.
 *
 * IN_CHARGE	Once started, trustee will enter this state after
 *		making all existing workers rogue.  DOWN_PREPARE waits
 *		for trustee to enter this state.  After reaching
 *		IN_CHARGE, trustee tries to execute the pending
 *		worklist until it's empty and the state is set to
 *		BUTCHER, or the state is set to RELEASE.
 *
 * BUTCHER	Command state which is set by the cpu callback after
 *		the cpu has went down.  Once this state is set trustee
 *		knows that there will be no new works on the worklist
 *		and once the worklist is empty it can proceed to
 *		killing idle workers.
 *
 * RELEASE	Command state which is set by the cpu callback if the
 *		cpu down has been canceled or it has come online
 *		again.  After recognizing this state, trustee stops
 *		trying to drain or butcher and transits to DONE.
 *
 * DONE		Trustee will enter this state after BUTCHER or RELEASE
 *		is complete.
 *
 *          trustee                 CPU                draining
 *         took over                down               complete
 * START -----------> IN_CHARGE -----------> BUTCHER -----------> DONE
 *                        |                     |                  ^
 *                        | CPU is back online  v   return workers |
 *                         ----------------> RELEASE --------------
 */

/**
 * trustee_wait_event_timeout - timed event wait for trustee
 * @cond: condition to wait for
 * @timeout: timeout in jiffies
 *
 * wait_event_timeout() for trustee to use.  Handles locking and
 * checks for RELEASE request.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which may be released and regrabbed
 * multiple times.  To be used by trustee.
 *
 * RETURNS:
 * Positive indicating left time if @cond is satisfied, 0 if timed
 * out, -1 if canceled.
 */
#define trustee_wait_event_timeout(cond, timeout) ({			\
	long __ret = (timeout);						\
	while (!((cond) || (gcwq->trustee_state == TRUSTEE_RELEASE)) &&	\
	       __ret) {							\
		spin_unlock_irq(&gcwq->lock);				\
		__wait_event_timeout(gcwq->trustee_wait, (cond) ||	\
			(gcwq->trustee_state == TRUSTEE_RELEASE),	\
			__ret);						\
		spin_lock_irq(&gcwq->lock);				\
	}								\
	gcwq->trustee_state == TRUSTEE_RELEASE ? -1 : (__ret);		\
})

/**
 * trustee_wait_event - event wait for trustee
 * @cond: condition to wait for
 *
 * wait_event() for trustee to use.  Automatically handles locking and
 * checks for CANCEL request.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which may be released and regrabbed
 * multiple times.  To be used by trustee.
 *
 * RETURNS:
 * 0 if @cond is satisfied, -1 if canceled.
 */
#define trustee_wait_event(cond) ({					\
	long __ret1;							\
	__ret1 = trustee_wait_event_timeout(cond, MAX_SCHEDULE_TIMEOUT);\
	__ret1 < 0 ? -1 : 0;						\
})

static int __cpuinit trustee_thread(void *__gcwq)
{
	struct global_cwq *gcwq = __gcwq;
	struct worker *worker;
	struct hlist_node *pos;
	int i;

	BUG_ON(gcwq->cpu != smp_processor_id());

	spin_lock_irq(&gcwq->lock);
	/*
	 * Make all workers rogue.  Trustee must be bound to the
	 * target cpu and can't be cancelled.
	 */
	BUG_ON(gcwq->cpu != smp_processor_id());

	list_for_each_entry(worker, &gcwq->idle_list, entry)
		worker->flags |= WORKER_ROGUE;

	for_each_busy_worker(worker, i, pos, gcwq)
		worker->flags |= WORKER_ROGUE;

	/*
	 * We're now in charge.  Notify and proceed to drain.  We need
	 * to keep the gcwq running during the whole CPU down
	 * procedure as other cpu hotunplug callbacks may need to
	 * flush currently running tasks.
	 */
	gcwq->trustee_state = TRUSTEE_IN_CHARGE;
	wake_up_all(&gcwq->trustee_wait);

	/*
	 * The original cpu is in the process of dying and may go away
	 * anytime now.  When that happens, we and all workers would
	 * be migrated to other cpus.  Try draining any left work.
	 * Note that if the gcwq is frozen, there may be frozen works
	 * in freezeable cwqs.  Don't declare completion while frozen.
	 */
	while (gcwq->nr_workers != gcwq->nr_idle ||
	       gcwq->flags & GCWQ_FREEZING ||
	       gcwq->trustee_state == TRUSTEE_IN_CHARGE) {
		/* give a breather */
		if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0)
			break;
	}

	/* notify completion */
	gcwq->trustee = NULL;
	gcwq->trustee_state = TRUSTEE_DONE;
	wake_up_all(&gcwq->trustee_wait);
	spin_unlock_irq(&gcwq->lock);
	return 0;
}

/**
 * wait_trustee_state - wait for trustee to enter the specified state
 * @gcwq: gcwq the trustee of interest belongs to
 * @state: target state to wait for
 *
 * Wait for the trustee to reach @state.  DONE is already matched.
 *
 * CONTEXT:
 * spin_lock_irq(gcwq->lock) which may be released and regrabbed
 * multiple times.  To be used by cpu_callback.
 */
static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state)
{
	if (!(gcwq->trustee_state == state ||
	      gcwq->trustee_state == TRUSTEE_DONE)) {
		spin_unlock_irq(&gcwq->lock);
		__wait_event(gcwq->trustee_wait,
			     gcwq->trustee_state == state ||
			     gcwq->trustee_state == TRUSTEE_DONE);
		spin_lock_irq(&gcwq->lock);
	}
}

static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
						unsigned long action,
						void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct global_cwq *gcwq = get_gcwq(cpu);
	struct task_struct *new_trustee = NULL;
	struct worker *worker;
	struct hlist_node *pos;
	unsigned long flags;
	int i;

	action &= ~CPU_TASKS_FROZEN;

	switch (action) {
	case CPU_DOWN_PREPARE:
		new_trustee = kthread_create(trustee_thread, gcwq,
					     "workqueue_trustee/%d\n", cpu);
		if (IS_ERR(new_trustee))
			return notifier_from_errno(PTR_ERR(new_trustee));
		kthread_bind(new_trustee, cpu);
	}

	/* some are called w/ irq disabled, don't disturb irq status */
	spin_lock_irqsave(&gcwq->lock, flags);

	switch (action) {
	case CPU_DOWN_PREPARE:
		/* initialize trustee and tell it to acquire the gcwq */
		BUG_ON(gcwq->trustee || gcwq->trustee_state != TRUSTEE_DONE);
		gcwq->trustee = new_trustee;
		gcwq->trustee_state = TRUSTEE_START;
		wake_up_process(gcwq->trustee);
		wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE);
		break;

	case CPU_POST_DEAD:
		gcwq->trustee_state = TRUSTEE_BUTCHER;
		break;

	case CPU_DOWN_FAILED:
	case CPU_ONLINE:
		if (gcwq->trustee_state != TRUSTEE_DONE) {
			gcwq->trustee_state = TRUSTEE_RELEASE;
			wake_up_process(gcwq->trustee);
			wait_trustee_state(gcwq, TRUSTEE_DONE);
		}

		/* clear ROGUE from all workers */
		list_for_each_entry(worker, &gcwq->idle_list, entry)
			worker->flags &= ~WORKER_ROGUE;

		for_each_busy_worker(worker, i, pos, gcwq)
			worker->flags &= ~WORKER_ROGUE;
		break;
	}

	spin_unlock_irqrestore(&gcwq->lock, flags);

	return notifier_from_errno(0);
}

#ifdef CONFIG_SMP

struct work_for_cpu {
	struct completion completion;
	long (*fn)(void *);
	void *arg;
	long ret;
};

static int do_work_for_cpu(void *_wfc)
{
	struct work_for_cpu *wfc = _wfc;
	wfc->ret = wfc->fn(wfc->arg);
	complete(&wfc->completion);
	return 0;
}

/**
 * work_on_cpu - run a function in user context on a particular cpu
 * @cpu: the cpu to run on
 * @fn: the function to run
 * @arg: the function arg
 *
 * This will return the value @fn returns.
 * It is up to the caller to ensure that the cpu doesn't go offline.
 * The caller must not hold any locks which would prevent @fn from completing.
 */
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
	struct task_struct *sub_thread;
	struct work_for_cpu wfc = {
		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
		.fn = fn,
		.arg = arg,
	};

	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
	if (IS_ERR(sub_thread))
		return PTR_ERR(sub_thread);
	kthread_bind(sub_thread, cpu);
	wake_up_process(sub_thread);
	wait_for_completion(&wfc.completion);
	return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
#endif /* CONFIG_SMP */

#ifdef CONFIG_FREEZER

/**
 * freeze_workqueues_begin - begin freezing workqueues
 *
 * Start freezing workqueues.  After this function returns, all
 * freezeable workqueues will queue new works to their frozen_works
 * list instead of gcwq->worklist.
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock and gcwq->lock's.
 */
void freeze_workqueues_begin(void)
{
	struct workqueue_struct *wq;
	unsigned int cpu;

	spin_lock(&workqueue_lock);

	BUG_ON(workqueue_freezing);
	workqueue_freezing = true;

	for_each_possible_cpu(cpu) {
		struct global_cwq *gcwq = get_gcwq(cpu);

		spin_lock_irq(&gcwq->lock);

		BUG_ON(gcwq->flags & GCWQ_FREEZING);
		gcwq->flags |= GCWQ_FREEZING;

		list_for_each_entry(wq, &workqueues, list) {
			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);

			if (wq->flags & WQ_FREEZEABLE)
				cwq->max_active = 0;
		}

		spin_unlock_irq(&gcwq->lock);
	}

	spin_unlock(&workqueue_lock);
}

/**
 * freeze_workqueues_busy - are freezeable workqueues still busy?
 *
 * Check whether freezing is complete.  This function must be called
 * between freeze_workqueues_begin() and thaw_workqueues().
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock.
 *
 * RETURNS:
 * %true if some freezeable workqueues are still busy.  %false if
 * freezing is complete.
 */
bool freeze_workqueues_busy(void)
{
	struct workqueue_struct *wq;
	unsigned int cpu;
	bool busy = false;

	spin_lock(&workqueue_lock);

	BUG_ON(!workqueue_freezing);

	for_each_possible_cpu(cpu) {
		/*
		 * nr_active is monotonically decreasing.  It's safe
		 * to peek without lock.
		 */
		list_for_each_entry(wq, &workqueues, list) {
			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);

			if (!(wq->flags & WQ_FREEZEABLE))
				continue;

			BUG_ON(cwq->nr_active < 0);
			if (cwq->nr_active) {
				busy = true;
				goto out_unlock;
			}
		}
	}
out_unlock:
	spin_unlock(&workqueue_lock);
	return busy;
}

/**
 * thaw_workqueues - thaw workqueues
 *
 * Thaw workqueues.  Normal queueing is restored and all collected
 * frozen works are transferred to their respective gcwq worklists.
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock and gcwq->lock's.
 */
void thaw_workqueues(void)
{
	struct workqueue_struct *wq;
	unsigned int cpu;

	spin_lock(&workqueue_lock);

	if (!workqueue_freezing)
		goto out_unlock;

	for_each_possible_cpu(cpu) {
		struct global_cwq *gcwq = get_gcwq(cpu);

		spin_lock_irq(&gcwq->lock);

		BUG_ON(!(gcwq->flags & GCWQ_FREEZING));
		gcwq->flags &= ~GCWQ_FREEZING;

		list_for_each_entry(wq, &workqueues, list) {
			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);

			if (!(wq->flags & WQ_FREEZEABLE))
				continue;

			/* restore max_active and repopulate worklist */
			cwq->max_active = wq->saved_max_active;

			while (!list_empty(&cwq->delayed_works) &&
			       cwq->nr_active < cwq->max_active)
				cwq_activate_first_delayed(cwq);

			/* perform delayed unbind from single cpu if empty */
			if (wq->single_cpu == gcwq->cpu &&
			    !cwq->nr_active && list_empty(&cwq->delayed_works))
				cwq_unbind_single_cpu(cwq);

			wake_up_process(cwq->worker->task);
		}

		spin_unlock_irq(&gcwq->lock);
	}

	workqueue_freezing = false;
out_unlock:
	spin_unlock(&workqueue_lock);
}
#endif /* CONFIG_FREEZER */

void __init init_workqueues(void)
{
	unsigned int cpu;
	int i;

	/*
	 * The pointer part of work->data is either pointing to the
	 * cwq or contains the cpu number the work ran last on.  Make
	 * sure cpu number won't overflow into kernel pointer area so
	 * that they can be distinguished.
	 */
	BUILD_BUG_ON(NR_CPUS << WORK_STRUCT_FLAG_BITS >= PAGE_OFFSET);

	hotcpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE);

	/* initialize gcwqs */
	for_each_possible_cpu(cpu) {
		struct global_cwq *gcwq = get_gcwq(cpu);

		spin_lock_init(&gcwq->lock);
		INIT_LIST_HEAD(&gcwq->worklist);
		gcwq->cpu = cpu;

		INIT_LIST_HEAD(&gcwq->idle_list);
		for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)
			INIT_HLIST_HEAD(&gcwq->busy_hash[i]);

		ida_init(&gcwq->worker_ida);

		gcwq->trustee_state = TRUSTEE_DONE;
		init_waitqueue_head(&gcwq->trustee_wait);
	}

	keventd_wq = create_workqueue("events");
	BUG_ON(!keventd_wq);
}