summaryrefslogtreecommitdiff
path: root/ipc/sem.c
blob: 1a8b9f0ac047be005635d0edefb24697d18d0ff6 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/ipc/sem.c
 * Copyright (C) 1992 Krishna Balasubramanian
 * Copyright (C) 1995 Eric Schenk, Bruno Haible
 *
 * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
 *
 * SMP-threaded, sysctl's added
 * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
 * Enforced range limit on SEM_UNDO
 * (c) 2001 Red Hat Inc
 * Lockless wakeup
 * (c) 2003 Manfred Spraul <manfred@colorfullife.com>
 * (c) 2016 Davidlohr Bueso <dave@stgolabs.net>
 * Further wakeup optimizations, documentation
 * (c) 2010 Manfred Spraul <manfred@colorfullife.com>
 *
 * support for audit of ipc object properties and permission changes
 * Dustin Kirkland <dustin.kirkland@us.ibm.com>
 *
 * namespaces support
 * OpenVZ, SWsoft Inc.
 * Pavel Emelianov <xemul@openvz.org>
 *
 * Implementation notes: (May 2010)
 * This file implements System V semaphores.
 *
 * User space visible behavior:
 * - FIFO ordering for semop() operations (just FIFO, not starvation
 *   protection)
 * - multiple semaphore operations that alter the same semaphore in
 *   one semop() are handled.
 * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and
 *   SETALL calls.
 * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO.
 * - undo adjustments at process exit are limited to 0..SEMVMX.
 * - namespace are supported.
 * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtime by writing
 *   to /proc/sys/kernel/sem.
 * - statistics about the usage are reported in /proc/sysvipc/sem.
 *
 * Internals:
 * - scalability:
 *   - all global variables are read-mostly.
 *   - semop() calls and semctl(RMID) are synchronized by RCU.
 *   - most operations do write operations (actually: spin_lock calls) to
 *     the per-semaphore array structure.
 *   Thus: Perfect SMP scaling between independent semaphore arrays.
 *         If multiple semaphores in one array are used, then cache line
 *         trashing on the semaphore array spinlock will limit the scaling.
 * - semncnt and semzcnt are calculated on demand in count_semcnt()
 * - the task that performs a successful semop() scans the list of all
 *   sleeping tasks and completes any pending operations that can be fulfilled.
 *   Semaphores are actively given to waiting tasks (necessary for FIFO).
 *   (see update_queue())
 * - To improve the scalability, the actual wake-up calls are performed after
 *   dropping all locks. (see wake_up_sem_queue_prepare())
 * - All work is done by the waker, the woken up task does not have to do
 *   anything - not even acquiring a lock or dropping a refcount.
 * - A woken up task may not even touch the semaphore array anymore, it may
 *   have been destroyed already by a semctl(RMID).
 * - UNDO values are stored in an array (one per process and per
 *   semaphore array, lazily allocated). For backwards compatibility, multiple
 *   modes for the UNDO variables are supported (per process, per thread)
 *   (see copy_semundo, CLONE_SYSVSEM)
 * - There are two lists of the pending operations: a per-array list
 *   and per-semaphore list (stored in the array). This allows to achieve FIFO
 *   ordering without always scanning all pending operations.
 *   The worst-case behavior is nevertheless O(N^2) for N wakeups.
 */

#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/time.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>
#include <linux/sched/wake_q.h>
#include <linux/nospec.h>
#include <linux/rhashtable.h>

#include <linux/uaccess.h>
#include "util.h"

/* One semaphore structure for each semaphore in the system. */
struct sem {
	int	semval;		/* current value */
	/*
	 * PID of the process that last modified the semaphore. For
	 * Linux, specifically these are:
	 *  - semop
	 *  - semctl, via SETVAL and SETALL.
	 *  - at task exit when performing undo adjustments (see exit_sem).
	 */
	struct pid *sempid;
	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
	struct list_head pending_alter; /* pending single-sop operations */
					/* that alter the semaphore */
	struct list_head pending_const; /* pending single-sop operations */
					/* that do not alter the semaphore*/
	time64_t	 sem_otime;	/* candidate for sem_otime */
} ____cacheline_aligned_in_smp;

/* One sem_array data structure for each set of semaphores in the system. */
struct sem_array {
	struct kern_ipc_perm	sem_perm;	/* permissions .. see ipc.h */
	time64_t		sem_ctime;	/* create/last semctl() time */
	struct list_head	pending_alter;	/* pending operations */
						/* that alter the array */
	struct list_head	pending_const;	/* pending complex operations */
						/* that do not alter semvals */
	struct list_head	list_id;	/* undo requests on this array */
	int			sem_nsems;	/* no. of semaphores in array */
	int			complex_count;	/* pending complex operations */
	unsigned int		use_global_lock;/* >0: global lock required */

	struct sem		sems[];
} __randomize_layout;

/* One queue for each sleeping process in the system. */
struct sem_queue {
	struct list_head	list;	 /* queue of pending operations */
	struct task_struct	*sleeper; /* this process */
	struct sem_undo		*undo;	 /* undo structure */
	struct pid		*pid;	 /* process id of requesting process */
	int			status;	 /* completion status of operation */
	struct sembuf		*sops;	 /* array of pending operations */
	struct sembuf		*blocking; /* the operation that blocked */
	int			nsops;	 /* number of operations */
	bool			alter;	 /* does *sops alter the array? */
	bool                    dupsop;	 /* sops on more than one sem_num */
};

/* Each task has a list of undo requests. They are executed automatically
 * when the process exits.
 */
struct sem_undo {
	struct list_head	list_proc;	/* per-process list: *
						 * all undos from one process
						 * rcu protected */
	struct rcu_head		rcu;		/* rcu struct for sem_undo */
	struct sem_undo_list	*ulp;		/* back ptr to sem_undo_list */
	struct list_head	list_id;	/* per semaphore array list:
						 * all undos for one array */
	int			semid;		/* semaphore set identifier */
	short			*semadj;	/* array of adjustments */
						/* one per semaphore */
};

/* sem_undo_list controls shared access to the list of sem_undo structures
 * that may be shared among all a CLONE_SYSVSEM task group.
 */
struct sem_undo_list {
	refcount_t		refcnt;
	spinlock_t		lock;
	struct list_head	list_proc;
};


#define sem_ids(ns)	((ns)->ids[IPC_SEM_IDS])

static int newary(struct ipc_namespace *, struct ipc_params *);
static void freeary(struct ipc_namespace *, struct kern_ipc_perm *);
#ifdef CONFIG_PROC_FS
static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
#endif

#define SEMMSL_FAST	256 /* 512 bytes on stack */
#define SEMOPM_FAST	64  /* ~ 372 bytes on stack */

/*
 * Switching from the mode suitable for simple ops
 * to the mode for complex ops is costly. Therefore:
 * use some hysteresis
 */
#define USE_GLOBAL_LOCK_HYSTERESIS	10

/*
 * Locking:
 * a) global sem_lock() for read/write
 *	sem_undo.id_next,
 *	sem_array.complex_count,
 *	sem_array.pending{_alter,_const},
 *	sem_array.sem_undo
 *
 * b) global or semaphore sem_lock() for read/write:
 *	sem_array.sems[i].pending_{const,alter}:
 *
 * c) special:
 *	sem_undo_list.list_proc:
 *	* undo_list->lock for write
 *	* rcu for read
 *	use_global_lock:
 *	* global sem_lock() for write
 *	* either local or global sem_lock() for read.
 *
 * Memory ordering:
 * Most ordering is enforced by using spin_lock() and spin_unlock().
 *
 * Exceptions:
 * 1) use_global_lock: (SEM_BARRIER_1)
 * Setting it from non-zero to 0 is a RELEASE, this is ensured by
 * using smp_store_release(): Immediately after setting it to 0,
 * a simple op can start.
 * Testing if it is non-zero is an ACQUIRE, this is ensured by using
 * smp_load_acquire().
 * Setting it from 0 to non-zero must be ordered with regards to
 * this smp_load_acquire(), this is guaranteed because the smp_load_acquire()
 * is inside a spin_lock() and after a write from 0 to non-zero a
 * spin_lock()+spin_unlock() is done.
 * To prevent the compiler/cpu temporarily writing 0 to use_global_lock,
 * READ_ONCE()/WRITE_ONCE() is used.
 *
 * 2) queue.status: (SEM_BARRIER_2)
 * Initialization is done while holding sem_lock(), so no further barrier is
 * required.
 * Setting it to a result code is a RELEASE, this is ensured by both a
 * smp_store_release() (for case a) and while holding sem_lock()
 * (for case b).
 * The ACQUIRE when reading the result code without holding sem_lock() is
 * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep().
 * (case a above).
 * Reading the result code while holding sem_lock() needs no further barriers,
 * the locks inside sem_lock() enforce ordering (case b above)
 *
 * 3) current->state:
 * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock().
 * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may
 * happen immediately after calling wake_q_add. As wake_q_add_safe() is called
 * when holding sem_lock(), no further barriers are required.
 *
 * See also ipc/mqueue.c for more details on the covered races.
 */

#define sc_semmsl	sem_ctls[0]
#define sc_semmns	sem_ctls[1]
#define sc_semopm	sem_ctls[2]
#define sc_semmni	sem_ctls[3]

void sem_init_ns(struct ipc_namespace *ns)
{
	ns->sc_semmsl = SEMMSL;
	ns->sc_semmns = SEMMNS;
	ns->sc_semopm = SEMOPM;
	ns->sc_semmni = SEMMNI;
	ns->used_sems = 0;
	ipc_init_ids(&ns->ids[IPC_SEM_IDS]);
}

#ifdef CONFIG_IPC_NS
void sem_exit_ns(struct ipc_namespace *ns)
{
	free_ipcs(ns, &sem_ids(ns), freeary);
	idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr);
	rhashtable_destroy(&ns->ids[IPC_SEM_IDS].key_ht);
}
#endif

void __init sem_init(void)
{
	sem_init_ns(&init_ipc_ns);
	ipc_init_proc_interface("sysvipc/sem",
				"       key      semid perms      nsems   uid   gid  cuid  cgid      otime      ctime\n",
				IPC_SEM_IDS, sysvipc_sem_proc_show);
}

/**
 * unmerge_queues - unmerge queues, if possible.
 * @sma: semaphore array
 *
 * The function unmerges the wait queues if complex_count is 0.
 * It must be called prior to dropping the global semaphore array lock.
 */
static void unmerge_queues(struct sem_array *sma)
{
	struct sem_queue *q, *tq;

	/* complex operations still around? */
	if (sma->complex_count)
		return;
	/*
	 * We will switch back to simple mode.
	 * Move all pending operation back into the per-semaphore
	 * queues.
	 */
	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
		struct sem *curr;
		curr = &sma->sems[q->sops[0].sem_num];

		list_add_tail(&q->list, &curr->pending_alter);
	}
	INIT_LIST_HEAD(&sma->pending_alter);
}

/**
 * merge_queues - merge single semop queues into global queue
 * @sma: semaphore array
 *
 * This function merges all per-semaphore queues into the global queue.
 * It is necessary to achieve FIFO ordering for the pending single-sop
 * operations when a multi-semop operation must sleep.
 * Only the alter operations must be moved, the const operations can stay.
 */
static void merge_queues(struct sem_array *sma)
{
	int i;
	for (i = 0; i < sma->sem_nsems; i++) {
		struct sem *sem = &sma->sems[i];

		list_splice_init(&sem->pending_alter, &sma->pending_alter);
	}
}

static void sem_rcu_free(struct rcu_head *head)
{
	struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu);
	struct sem_array *sma = container_of(p, struct sem_array, sem_perm);

	security_sem_free(&sma->sem_perm);
	kvfree(sma);
}

/*
 * Enter the mode suitable for non-simple operations:
 * Caller must own sem_perm.lock.
 */
static void complexmode_enter(struct sem_array *sma)
{
	int i;
	struct sem *sem;

	if (sma->use_global_lock > 0)  {
		/*
		 * We are already in global lock mode.
		 * Nothing to do, just reset the
		 * counter until we return to simple mode.
		 */
		WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);
		return;
	}
	WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);

	for (i = 0; i < sma->sem_nsems; i++) {
		sem = &sma->sems[i];
		spin_lock(&sem->lock);
		spin_unlock(&sem->lock);
	}
}

/*
 * Try to leave the mode that disallows simple operations:
 * Caller must own sem_perm.lock.
 */
static void complexmode_tryleave(struct sem_array *sma)
{
	if (sma->complex_count)  {
		/* Complex ops are sleeping.
		 * We must stay in complex mode
		 */
		return;
	}
	if (sma->use_global_lock == 1) {

		/* See SEM_BARRIER_1 for purpose/pairing */
		smp_store_release(&sma->use_global_lock, 0);
	} else {
		WRITE_ONCE(sma->use_global_lock,
				sma->use_global_lock-1);
	}
}

#define SEM_GLOBAL_LOCK	(-1)
/*
 * If the request contains only one semaphore operation, and there are
 * no complex transactions pending, lock only the semaphore involved.
 * Otherwise, lock the entire semaphore array, since we either have
 * multiple semaphores in our own semops, or we need to look at
 * semaphores from other pending complex operations.
 */
static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
			      int nsops)
{
	struct sem *sem;
	int idx;

	if (nsops != 1) {
		/* Complex operation - acquire a full lock */
		ipc_lock_object(&sma->sem_perm);

		/* Prevent parallel simple ops */
		complexmode_enter(sma);
		return SEM_GLOBAL_LOCK;
	}

	/*
	 * Only one semaphore affected - try to optimize locking.
	 * Optimized locking is possible if no complex operation
	 * is either enqueued or processed right now.
	 *
	 * Both facts are tracked by use_global_mode.
	 */
	idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
	sem = &sma->sems[idx];

	/*
	 * Initial check for use_global_lock. Just an optimization,
	 * no locking, no memory barrier.
	 */
	if (!READ_ONCE(sma->use_global_lock)) {
		/*
		 * It appears that no complex operation is around.
		 * Acquire the per-semaphore lock.
		 */
		spin_lock(&sem->lock);

		/* see SEM_BARRIER_1 for purpose/pairing */
		if (!smp_load_acquire(&sma->use_global_lock)) {
			/* fast path successful! */
			return sops->sem_num;
		}
		spin_unlock(&sem->lock);
	}

	/* slow path: acquire the full lock */
	ipc_lock_object(&sma->sem_perm);

	if (sma->use_global_lock == 0) {
		/*
		 * The use_global_lock mode ended while we waited for
		 * sma->sem_perm.lock. Thus we must switch to locking
		 * with sem->lock.
		 * Unlike in the fast path, there is no need to recheck
		 * sma->use_global_lock after we have acquired sem->lock:
		 * We own sma->sem_perm.lock, thus use_global_lock cannot
		 * change.
		 */
		spin_lock(&sem->lock);

		ipc_unlock_object(&sma->sem_perm);
		return sops->sem_num;
	} else {
		/*
		 * Not a false alarm, thus continue to use the global lock
		 * mode. No need for complexmode_enter(), this was done by
		 * the caller that has set use_global_mode to non-zero.
		 */
		return SEM_GLOBAL_LOCK;
	}
}

static inline void sem_unlock(struct sem_array *sma, int locknum)
{
	if (locknum == SEM_GLOBAL_LOCK) {
		unmerge_queues(sma);
		complexmode_tryleave(sma);
		ipc_unlock_object(&sma->sem_perm);
	} else {
		struct sem *sem = &sma->sems[locknum];
		spin_unlock(&sem->lock);
	}
}

/*
 * sem_lock_(check_) routines are called in the paths where the rwsem
 * is not held.
 *
 * The caller holds the RCU read lock.
 */
static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct sem_array, sem_perm);
}

static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns,
							int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct sem_array, sem_perm);
}

static inline void sem_lock_and_putref(struct sem_array *sma)
{
	sem_lock(sma, NULL, -1);
	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
}

static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
{
	ipc_rmid(&sem_ids(ns), &s->sem_perm);
}

static struct sem_array *sem_alloc(size_t nsems)
{
	struct sem_array *sma;

	if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0]))
		return NULL;

	sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT);
	if (unlikely(!sma))
		return NULL;

	return sma;
}

/**
 * newary - Create a new semaphore set
 * @ns: namespace
 * @params: ptr to the structure that contains key, semflg and nsems
 *
 * Called with sem_ids.rwsem held (as a writer)
 */
static int newary(struct ipc_namespace *ns, struct ipc_params *params)
{
	int retval;
	struct sem_array *sma;
	key_t key = params->key;
	int nsems = params->u.nsems;
	int semflg = params->flg;
	int i;

	if (!nsems)
		return -EINVAL;
	if (ns->used_sems + nsems > ns->sc_semmns)
		return -ENOSPC;

	sma = sem_alloc(nsems);
	if (!sma)
		return -ENOMEM;

	sma->sem_perm.mode = (semflg & S_IRWXUGO);
	sma->sem_perm.key = key;

	sma->sem_perm.security = NULL;
	retval = security_sem_alloc(&sma->sem_perm);
	if (retval) {
		kvfree(sma);
		return retval;
	}

	for (i = 0; i < nsems; i++) {
		INIT_LIST_HEAD(&sma->sems[i].pending_alter);
		INIT_LIST_HEAD(&sma->sems[i].pending_const);
		spin_lock_init(&sma->sems[i].lock);
	}

	sma->complex_count = 0;
	sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;
	INIT_LIST_HEAD(&sma->pending_alter);
	INIT_LIST_HEAD(&sma->pending_const);
	INIT_LIST_HEAD(&sma->list_id);
	sma->sem_nsems = nsems;
	sma->sem_ctime = ktime_get_real_seconds();

	/* ipc_addid() locks sma upon success. */
	retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
	if (retval < 0) {
		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
		return retval;
	}
	ns->used_sems += nsems;

	sem_unlock(sma, -1);
	rcu_read_unlock();

	return sma->sem_perm.id;
}


/*
 * Called with sem_ids.rwsem and ipcp locked.
 */
static int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params)
{
	struct sem_array *sma;

	sma = container_of(ipcp, struct sem_array, sem_perm);
	if (params->u.nsems > sma->sem_nsems)
		return -EINVAL;

	return 0;
}

long ksys_semget(key_t key, int nsems, int semflg)
{
	struct ipc_namespace *ns;
	static const struct ipc_ops sem_ops = {
		.getnew = newary,
		.associate = security_sem_associate,
		.more_checks = sem_more_checks,
	};
	struct ipc_params sem_params;

	ns = current->nsproxy->ipc_ns;

	if (nsems < 0 || nsems > ns->sc_semmsl)
		return -EINVAL;

	sem_params.key = key;
	sem_params.flg = semflg;
	sem_params.u.nsems = nsems;

	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
}

SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
{
	return ksys_semget(key, nsems, semflg);
}

/**
 * perform_atomic_semop[_slow] - Attempt to perform semaphore
 *                               operations on a given array.
 * @sma: semaphore array
 * @q: struct sem_queue that describes the operation
 *
 * Caller blocking are as follows, based the value
 * indicated by the semaphore operation (sem_op):
 *
 *  (1) >0 never blocks.
 *  (2)  0 (wait-for-zero operation): semval is non-zero.
 *  (3) <0 attempting to decrement semval to a value smaller than zero.
 *
 * Returns 0 if the operation was possible.
 * Returns 1 if the operation is impossible, the caller must sleep.
 * Returns <0 for error codes.
 */
static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
{
	int result, sem_op, nsops;
	struct pid *pid;
	struct sembuf *sop;
	struct sem *curr;
	struct sembuf *sops;
	struct sem_undo *un;

	sops = q->sops;
	nsops = q->nsops;
	un = q->undo;

	for (sop = sops; sop < sops + nsops; sop++) {
		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
		curr = &sma->sems[idx];
		sem_op = sop->sem_op;
		result = curr->semval;

		if (!sem_op && result)
			goto would_block;

		result += sem_op;
		if (result < 0)
			goto would_block;
		if (result > SEMVMX)
			goto out_of_range;

		if (sop->sem_flg & SEM_UNDO) {
			int undo = un->semadj[sop->sem_num] - sem_op;
			/* Exceeding the undo range is an error. */
			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
				goto out_of_range;
			un->semadj[sop->sem_num] = undo;
		}

		curr->semval = result;
	}

	sop--;
	pid = q->pid;
	while (sop >= sops) {
		ipc_update_pid(&sma->sems[sop->sem_num].sempid, pid);
		sop--;
	}

	return 0;

out_of_range:
	result = -ERANGE;
	goto undo;

would_block:
	q->blocking = sop;

	if (sop->sem_flg & IPC_NOWAIT)
		result = -EAGAIN;
	else
		result = 1;

undo:
	sop--;
	while (sop >= sops) {
		sem_op = sop->sem_op;
		sma->sems[sop->sem_num].semval -= sem_op;
		if (sop->sem_flg & SEM_UNDO)
			un->semadj[sop->sem_num] += sem_op;
		sop--;
	}

	return result;
}

static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
{
	int result, sem_op, nsops;
	struct sembuf *sop;
	struct sem *curr;
	struct sembuf *sops;
	struct sem_undo *un;

	sops = q->sops;
	nsops = q->nsops;
	un = q->undo;

	if (unlikely(q->dupsop))
		return perform_atomic_semop_slow(sma, q);

	/*
	 * We scan the semaphore set twice, first to ensure that the entire
	 * operation can succeed, therefore avoiding any pointless writes
	 * to shared memory and having to undo such changes in order to block
	 * until the operations can go through.
	 */
	for (sop = sops; sop < sops + nsops; sop++) {
		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);

		curr = &sma->sems[idx];
		sem_op = sop->sem_op;
		result = curr->semval;

		if (!sem_op && result)
			goto would_block; /* wait-for-zero */

		result += sem_op;
		if (result < 0)
			goto would_block;

		if (result > SEMVMX)
			return -ERANGE;

		if (sop->sem_flg & SEM_UNDO) {
			int undo = un->semadj[sop->sem_num] - sem_op;

			/* Exceeding the undo range is an error. */
			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
				return -ERANGE;
		}
	}

	for (sop = sops; sop < sops + nsops; sop++) {
		curr = &sma->sems[sop->sem_num];
		sem_op = sop->sem_op;
		result = curr->semval;

		if (sop->sem_flg & SEM_UNDO) {
			int undo = un->semadj[sop->sem_num] - sem_op;

			un->semadj[sop->sem_num] = undo;
		}
		curr->semval += sem_op;
		ipc_update_pid(&curr->sempid, q->pid);
	}

	return 0;

would_block:
	q->blocking = sop;
	return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1;
}

static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error,
					     struct wake_q_head *wake_q)
{
	struct task_struct *sleeper;

	sleeper = get_task_struct(q->sleeper);

	/* see SEM_BARRIER_2 for purpose/pairing */
	smp_store_release(&q->status, error);

	wake_q_add_safe(wake_q, sleeper);
}

static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
{
	list_del(&q->list);
	if (q->nsops > 1)
		sma->complex_count--;
}

/** check_restart(sma, q)
 * @sma: semaphore array
 * @q: the operation that just completed
 *
 * update_queue is O(N^2) when it restarts scanning the whole queue of
 * waiting operations. Therefore this function checks if the restart is
 * really necessary. It is called after a previously waiting operation
 * modified the array.
 * Note that wait-for-zero operations are handled without restart.
 */
static inline int check_restart(struct sem_array *sma, struct sem_queue *q)
{
	/* pending complex alter operations are too difficult to analyse */
	if (!list_empty(&sma->pending_alter))
		return 1;

	/* we were a sleeping complex operation. Too difficult */
	if (q->nsops > 1)
		return 1;

	/* It is impossible that someone waits for the new value:
	 * - complex operations always restart.
	 * - wait-for-zero are handled separately.
	 * - q is a previously sleeping simple operation that
	 *   altered the array. It must be a decrement, because
	 *   simple increments never sleep.
	 * - If there are older (higher priority) decrements
	 *   in the queue, then they have observed the original
	 *   semval value and couldn't proceed. The operation
	 *   decremented to value - thus they won't proceed either.
	 */
	return 0;
}

/**
 * wake_const_ops - wake up non-alter tasks
 * @sma: semaphore array.
 * @semnum: semaphore that was modified.
 * @wake_q: lockless wake-queue head.
 *
 * wake_const_ops must be called after a semaphore in a semaphore array
 * was set to 0. If complex const operations are pending, wake_const_ops must
 * be called with semnum = -1, as well as with the number of each modified
 * semaphore.
 * The tasks that must be woken up are added to @wake_q. The return code
 * is stored in q->pid.
 * The function returns 1 if at least one operation was completed successfully.
 */
static int wake_const_ops(struct sem_array *sma, int semnum,
			  struct wake_q_head *wake_q)
{
	struct sem_queue *q, *tmp;
	struct list_head *pending_list;
	int semop_completed = 0;

	if (semnum == -1)
		pending_list = &sma->pending_const;
	else
		pending_list = &sma->sems[semnum].pending_const;

	list_for_each_entry_safe(q, tmp, pending_list, list) {
		int error = perform_atomic_semop(sma, q);

		if (error > 0)
			continue;
		/* operation completed, remove from queue & wakeup */
		unlink_queue(sma, q);

		wake_up_sem_queue_prepare(q, error, wake_q);
		if (error == 0)
			semop_completed = 1;
	}

	return semop_completed;
}

/**
 * do_smart_wakeup_zero - wakeup all wait for zero tasks
 * @sma: semaphore array
 * @sops: operations that were performed
 * @nsops: number of operations
 * @wake_q: lockless wake-queue head
 *
 * Checks all required queue for wait-for-zero operations, based
 * on the actual changes that were performed on the semaphore array.
 * The function returns 1 if at least one operation was completed successfully.
 */
static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
				int nsops, struct wake_q_head *wake_q)
{
	int i;
	int semop_completed = 0;
	int got_zero = 0;

	/* first: the per-semaphore queues, if known */
	if (sops) {
		for (i = 0; i < nsops; i++) {
			int num = sops[i].sem_num;

			if (sma->sems[num].semval == 0) {
				got_zero = 1;
				semop_completed |= wake_const_ops(sma, num, wake_q);
			}
		}
	} else {
		/*
		 * No sops means modified semaphores not known.
		 * Assume all were changed.
		 */
		for (i = 0; i < sma->sem_nsems; i++) {
			if (sma->sems[i].semval == 0) {
				got_zero = 1;
				semop_completed |= wake_const_ops(sma, i, wake_q);
			}
		}
	}
	/*
	 * If one of the modified semaphores got 0,
	 * then check the global queue, too.
	 */
	if (got_zero)
		semop_completed |= wake_const_ops(sma, -1, wake_q);

	return semop_completed;
}


/**
 * update_queue - look for tasks that can be completed.
 * @sma: semaphore array.
 * @semnum: semaphore that was modified.
 * @wake_q: lockless wake-queue head.
 *
 * update_queue must be called after a semaphore in a semaphore array
 * was modified. If multiple semaphores were modified, update_queue must
 * be called with semnum = -1, as well as with the number of each modified
 * semaphore.
 * The tasks that must be woken up are added to @wake_q. The return code
 * is stored in q->pid.
 * The function internally checks if const operations can now succeed.
 *
 * The function return 1 if at least one semop was completed successfully.
 */
static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *wake_q)
{
	struct sem_queue *q, *tmp;
	struct list_head *pending_list;
	int semop_completed = 0;

	if (semnum == -1)
		pending_list = &sma->pending_alter;
	else
		pending_list = &sma->sems[semnum].pending_alter;

again:
	list_for_each_entry_safe(q, tmp, pending_list, list) {
		int error, restart;

		/* If we are scanning the single sop, per-semaphore list of
		 * one semaphore and that semaphore is 0, then it is not
		 * necessary to scan further: simple increments
		 * that affect only one entry succeed immediately and cannot
		 * be in the  per semaphore pending queue, and decrements
		 * cannot be successful if the value is already 0.
		 */
		if (semnum != -1 && sma->sems[semnum].semval == 0)
			break;

		error = perform_atomic_semop(sma, q);

		/* Does q->sleeper still need to sleep? */
		if (error > 0)
			continue;

		unlink_queue(sma, q);

		if (error) {
			restart = 0;
		} else {
			semop_completed = 1;
			do_smart_wakeup_zero(sma, q->sops, q->nsops, wake_q);
			restart = check_restart(sma, q);
		}

		wake_up_sem_queue_prepare(q, error, wake_q);
		if (restart)
			goto again;
	}
	return semop_completed;
}

/**
 * set_semotime - set sem_otime
 * @sma: semaphore array
 * @sops: operations that modified the array, may be NULL
 *
 * sem_otime is replicated to avoid cache line trashing.
 * This function sets one instance to the current time.
 */
static void set_semotime(struct sem_array *sma, struct sembuf *sops)
{
	if (sops == NULL) {
		sma->sems[0].sem_otime = ktime_get_real_seconds();
	} else {
		sma->sems[sops[0].sem_num].sem_otime =
						ktime_get_real_seconds();
	}
}

/**
 * do_smart_update - optimized update_queue
 * @sma: semaphore array
 * @sops: operations that were performed
 * @nsops: number of operations
 * @otime: force setting otime
 * @wake_q: lockless wake-queue head
 *
 * do_smart_update() does the required calls to update_queue and wakeup_zero,
 * based on the actual changes that were performed on the semaphore array.
 * Note that the function does not do the actual wake-up: the caller is
 * responsible for calling wake_up_q().
 * It is safe to perform this call after dropping all locks.
 */
static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops,
			    int otime, struct wake_q_head *wake_q)
{
	int i;

	otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q);

	if (!list_empty(&sma->pending_alter)) {
		/* semaphore array uses the global queue - just process it. */
		otime |= update_queue(sma, -1, wake_q);
	} else {
		if (!sops) {
			/*
			 * No sops, thus the modified semaphores are not
			 * known. Check all.
			 */
			for (i = 0; i < sma->sem_nsems; i++)
				otime |= update_queue(sma, i, wake_q);
		} else {
			/*
			 * Check the semaphores that were increased:
			 * - No complex ops, thus all sleeping ops are
			 *   decrease.
			 * - if we decreased the value, then any sleeping
			 *   semaphore ops won't be able to run: If the
			 *   previous value was too small, then the new
			 *   value will be too small, too.
			 */
			for (i = 0; i < nsops; i++) {
				if (sops[i].sem_op > 0) {
					otime |= update_queue(sma,
							      sops[i].sem_num, wake_q);
				}
			}
		}
	}
	if (otime)
		set_semotime(sma, sops);
}

/*
 * check_qop: Test if a queued operation sleeps on the semaphore semnum
 */
static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q,
			bool count_zero)
{
	struct sembuf *sop = q->blocking;

	/*
	 * Linux always (since 0.99.10) reported a task as sleeping on all
	 * semaphores. This violates SUS, therefore it was changed to the
	 * standard compliant behavior.
	 * Give the administrators a chance to notice that an application
	 * might misbehave because it relies on the Linux behavior.
	 */
	pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n"
			"The task %s (%d) triggered the difference, watch for misbehavior.\n",
			current->comm, task_pid_nr(current));

	if (sop->sem_num != semnum)
		return 0;

	if (count_zero && sop->sem_op == 0)
		return 1;
	if (!count_zero && sop->sem_op < 0)
		return 1;

	return 0;
}

/* The following counts are associated to each semaphore:
 *   semncnt        number of tasks waiting on semval being nonzero
 *   semzcnt        number of tasks waiting on semval being zero
 *
 * Per definition, a task waits only on the semaphore of the first semop
 * that cannot proceed, even if additional operation would block, too.
 */
static int count_semcnt(struct sem_array *sma, ushort semnum,
			bool count_zero)
{
	struct list_head *l;
	struct sem_queue *q;
	int semcnt;

	semcnt = 0;
	/* First: check the simple operations. They are easy to evaluate */
	if (count_zero)
		l = &sma->sems[semnum].pending_const;
	else
		l = &sma->sems[semnum].pending_alter;

	list_for_each_entry(q, l, list) {
		/* all task on a per-semaphore list sleep on exactly
		 * that semaphore
		 */
		semcnt++;
	}

	/* Then: check the complex operations. */
	list_for_each_entry(q, &sma->pending_alter, list) {
		semcnt += check_qop(sma, semnum, q, count_zero);
	}
	if (count_zero) {
		list_for_each_entry(q, &sma->pending_const, list) {
			semcnt += check_qop(sma, semnum, q, count_zero);
		}
	}
	return semcnt;
}

/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
 * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
 * remains locked on exit.
 */
static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
	struct sem_undo *un, *tu;
	struct sem_queue *q, *tq;
	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);
	int i;
	DEFINE_WAKE_Q(wake_q);

	/* Free the existing undo structures for this semaphore set.  */
	ipc_assert_locked_object(&sma->sem_perm);
	list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
		list_del(&un->list_id);
		spin_lock(&un->ulp->lock);
		un->semid = -1;
		list_del_rcu(&un->list_proc);
		spin_unlock(&un->ulp->lock);
		kvfree_rcu(un, rcu);
	}

	/* Wake up all pending processes and let them fail with EIDRM. */
	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
		unlink_queue(sma, q);
		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
	}

	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
		unlink_queue(sma, q);
		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
	}
	for (i = 0; i < sma->sem_nsems; i++) {
		struct sem *sem = &sma->sems[i];
		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
			unlink_queue(sma, q);
			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
		}
		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
			unlink_queue(sma, q);
			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
		}
		ipc_update_pid(&sem->sempid, NULL);
	}

	/* Remove the semaphore set from the IDR */
	sem_rmid(ns, sma);
	sem_unlock(sma, -1);
	rcu_read_unlock();

	wake_up_q(&wake_q);
	ns->used_sems -= sma->sem_nsems;
	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
}

static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
{
	switch (version) {
	case IPC_64:
		return copy_to_user(buf, in, sizeof(*in));
	case IPC_OLD:
	    {
		struct semid_ds out;

		memset(&out, 0, sizeof(out));

		ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm);

		out.sem_otime	= in->sem_otime;
		out.sem_ctime	= in->sem_ctime;
		out.sem_nsems	= in->sem_nsems;

		return copy_to_user(buf, &out, sizeof(out));
	    }
	default:
		return -EINVAL;
	}
}

static time64_t get_semotime(struct sem_array *sma)
{
	int i;
	time64_t res;

	res = sma->sems[0].sem_otime;
	for (i = 1; i < sma->sem_nsems; i++) {
		time64_t to = sma->sems[i].sem_otime;

		if (to > res)
			res = to;
	}
	return res;
}

static int semctl_stat(struct ipc_namespace *ns, int semid,
			 int cmd, struct semid64_ds *semid64)
{
	struct sem_array *sma;
	time64_t semotime;
	int err;

	memset(semid64, 0, sizeof(*semid64));

	rcu_read_lock();
	if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) {
		sma = sem_obtain_object(ns, semid);
		if (IS_ERR(sma)) {
			err = PTR_ERR(sma);
			goto out_unlock;
		}
	} else { /* IPC_STAT */
		sma = sem_obtain_object_check(ns, semid);
		if (IS_ERR(sma)) {
			err = PTR_ERR(sma);
			goto out_unlock;
		}
	}

	/* see comment for SHM_STAT_ANY */
	if (cmd == SEM_STAT_ANY)
		audit_ipc_obj(&sma->sem_perm);
	else {
		err = -EACCES;
		if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
			goto out_unlock;
	}

	err = security_sem_semctl(&sma->sem_perm, cmd);
	if (err)
		goto out_unlock;

	ipc_lock_object(&sma->sem_perm);

	if (!ipc_valid_object(&sma->sem_perm)) {
		ipc_unlock_object(&sma->sem_perm);
		err = -EIDRM;
		goto out_unlock;
	}

	kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm);
	semotime = get_semotime(sma);
	semid64->sem_otime = semotime;
	semid64->sem_ctime = sma->sem_ctime;
#ifndef CONFIG_64BIT
	semid64->sem_otime_high = semotime >> 32;
	semid64->sem_ctime_high = sma->sem_ctime >> 32;
#endif
	semid64->sem_nsems = sma->sem_nsems;

	if (cmd == IPC_STAT) {
		/*
		 * As defined in SUS:
		 * Return 0 on success
		 */
		err = 0;
	} else {
		/*
		 * SEM_STAT and SEM_STAT_ANY (both Linux specific)
		 * Return the full id, including the sequence number
		 */
		err = sma->sem_perm.id;
	}
	ipc_unlock_object(&sma->sem_perm);
out_unlock:
	rcu_read_unlock();
	return err;
}

static int semctl_info(struct ipc_namespace *ns, int semid,
			 int cmd, void __user *p)
{
	struct seminfo seminfo;
	int max_idx;
	int err;

	err = security_sem_semctl(NULL, cmd);
	if (err)
		return err;

	memset(&seminfo, 0, sizeof(seminfo));
	seminfo.semmni = ns->sc_semmni;
	seminfo.semmns = ns->sc_semmns;
	seminfo.semmsl = ns->sc_semmsl;
	seminfo.semopm = ns->sc_semopm;
	seminfo.semvmx = SEMVMX;
	seminfo.semmnu = SEMMNU;
	seminfo.semmap = SEMMAP;
	seminfo.semume = SEMUME;
	down_read(&sem_ids(ns).rwsem);
	if (cmd == SEM_INFO) {
		seminfo.semusz = sem_ids(ns).in_use;
		seminfo.semaem = ns->used_sems;
	} else {
		seminfo.semusz = SEMUSZ;
		seminfo.semaem = SEMAEM;
	}
	max_idx = ipc_get_maxidx(&sem_ids(ns));
	up_read(&sem_ids(ns).rwsem);
	if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
		return -EFAULT;
	return (max_idx < 0) ? 0 : max_idx;
}

static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
		int val)
{
	struct sem_undo *un;
	struct sem_array *sma;
	struct sem *curr;
	int err;
	DEFINE_WAKE_Q(wake_q);

	if (val > SEMVMX || val < 0)
		return -ERANGE;

	rcu_read_lock();
	sma = sem_obtain_object_check(ns, semid);
	if (IS_ERR(sma)) {
		rcu_read_unlock();
		return PTR_ERR(sma);
	}

	if (semnum < 0 || semnum >= sma->sem_nsems) {
		rcu_read_unlock();
		return -EINVAL;
	}


	if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) {
		rcu_read_unlock();
		return -EACCES;
	}

	err = security_sem_semctl(&sma->sem_perm, SETVAL);
	if (err) {
		rcu_read_unlock();
		return -EACCES;
	}

	sem_lock(sma, NULL, -1);

	if (!ipc_valid_object(&sma->sem_perm)) {
		sem_unlock(sma, -1);
		rcu_read_unlock();
		return -EIDRM;
	}

	semnum = array_index_nospec(semnum, sma->sem_nsems);
	curr = &sma->sems[semnum];

	ipc_assert_locked_object(&sma->sem_perm);
	list_for_each_entry(un, &sma->list_id, list_id)
		un->semadj[semnum] = 0;

	curr->semval = val;
	ipc_update_pid(&curr->sempid, task_tgid(current));
	sma->sem_ctime = ktime_get_real_seconds();
	/* maybe some queued-up processes were waiting for this */
	do_smart_update(sma, NULL, 0, 0, &wake_q);
	sem_unlock(sma, -1);
	rcu_read_unlock();
	wake_up_q(&wake_q);
	return 0;
}

static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
		int cmd, void __user *p)
{
	struct sem_array *sma;
	struct sem *curr;
	int err, nsems;
	ushort fast_sem_io[SEMMSL_FAST];
	ushort *sem_io = fast_sem_io;
	DEFINE_WAKE_Q(wake_q);

	rcu_read_lock();
	sma = sem_obtain_object_check(ns, semid);
	if (IS_ERR(sma)) {
		rcu_read_unlock();
		return PTR_ERR(sma);
	}

	nsems = sma->sem_nsems;

	err = -EACCES;
	if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO))
		goto out_rcu_wakeup;

	err = security_sem_semctl(&sma->sem_perm, cmd);
	if (err)
		goto out_rcu_wakeup;

	err = -EACCES;
	switch (cmd) {
	case GETALL:
	{
		ushort __user *array = p;
		int i;

		sem_lock(sma, NULL, -1);
		if (!ipc_valid_object(&sma->sem_perm)) {
			err = -EIDRM;
			goto out_unlock;
		}
		if (nsems > SEMMSL_FAST) {
			if (!ipc_rcu_getref(&sma->sem_perm)) {
				err = -EIDRM;
				goto out_unlock;
			}
			sem_unlock(sma, -1);
			rcu_read_unlock();
			sem_io = kvmalloc_array(nsems, sizeof(ushort),
						GFP_KERNEL);
			if (sem_io == NULL) {
				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
				return -ENOMEM;
			}

			rcu_read_lock();
			sem_lock_and_putref(sma);
			if (!ipc_valid_object(&sma->sem_perm)) {
				err = -EIDRM;
				goto out_unlock;
			}
		}
		for (i = 0; i < sma->sem_nsems; i++)
			sem_io[i] = sma->sems[i].semval;
		sem_unlock(sma, -1);
		rcu_read_unlock();
		err = 0;
		if (copy_to_user(array, sem_io, nsems*sizeof(ushort)))
			err = -EFAULT;
		goto out_free;
	}
	case SETALL:
	{
		int i;
		struct sem_undo *un;

		if (!ipc_rcu_getref(&sma->sem_perm)) {
			err = -EIDRM;
			goto out_rcu_wakeup;
		}
		rcu_read_unlock();

		if (nsems > SEMMSL_FAST) {
			sem_io = kvmalloc_array(nsems, sizeof(ushort),
						GFP_KERNEL);
			if (sem_io == NULL) {
				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
				return -ENOMEM;
			}
		}

		if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
			ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
			err = -EFAULT;
			goto out_free;
		}

		for (i = 0; i < nsems; i++) {
			if (sem_io[i] > SEMVMX) {
				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
				err = -ERANGE;
				goto out_free;
			}
		}
		rcu_read_lock();
		sem_lock_and_putref(sma);
		if (!ipc_valid_object(&sma->sem_perm)) {
			err = -EIDRM;
			goto out_unlock;
		}

		for (i = 0; i < nsems; i++) {
			sma->sems[i].semval = sem_io[i];
			ipc_update_pid(&sma->sems[i].sempid, task_tgid(current));
		}

		ipc_assert_locked_object(&sma->sem_perm);
		list_for_each_entry(un, &sma->list_id, list_id) {
			for (i = 0; i < nsems; i++)
				un->semadj[i] = 0;
		}
		sma->sem_ctime = ktime_get_real_seconds();
		/* maybe some queued-up processes were waiting for this */
		do_smart_update(sma, NULL, 0, 0, &wake_q);
		err = 0;
		goto out_unlock;
	}
	/* GETVAL, GETPID, GETNCTN, GETZCNT: fall-through */
	}
	err = -EINVAL;
	if (semnum < 0 || semnum >= nsems)
		goto out_rcu_wakeup;

	sem_lock(sma, NULL, -1);
	if (!ipc_valid_object(&sma->sem_perm)) {
		err = -EIDRM;
		goto out_unlock;
	}

	semnum = array_index_nospec(semnum, nsems);
	curr = &sma->sems[semnum];

	switch (cmd) {
	case GETVAL:
		err = curr->semval;
		goto out_unlock;
	case GETPID:
		err = pid_vnr(curr->sempid);
		goto out_unlock;
	case GETNCNT:
		err = count_semcnt(sma, semnum, 0);
		goto out_unlock;
	case GETZCNT:
		err = count_semcnt(sma, semnum, 1);
		goto out_unlock;
	}

out_unlock:
	sem_unlock(sma, -1);
out_rcu_wakeup:
	rcu_read_unlock();
	wake_up_q(&wake_q);
out_free:
	if (sem_io != fast_sem_io)
		kvfree(sem_io);
	return err;
}

static inline unsigned long
copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version)
{
	switch (version) {
	case IPC_64:
		if (copy_from_user(out, buf, sizeof(*out)))
			return -EFAULT;
		return 0;
	case IPC_OLD:
	    {
		struct semid_ds tbuf_old;

		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
			return -EFAULT;

		out->sem_perm.uid	= tbuf_old.sem_perm.uid;
		out->sem_perm.gid	= tbuf_old.sem_perm.gid;
		out->sem_perm.mode	= tbuf_old.sem_perm.mode;

		return 0;
	    }
	default:
		return -EINVAL;
	}
}

/*
 * This function handles some semctl commands which require the rwsem
 * to be held in write mode.
 * NOTE: no locks must be held, the rwsem is taken inside this function.
 */
static int semctl_down(struct ipc_namespace *ns, int semid,
		       int cmd, struct semid64_ds *semid64)
{
	struct sem_array *sma;
	int err;
	struct kern_ipc_perm *ipcp;

	down_write(&sem_ids(ns).rwsem);
	rcu_read_lock();

	ipcp = ipcctl_obtain_check(ns, &sem_ids(ns), semid, cmd,
				      &semid64->sem_perm, 0);
	if (IS_ERR(ipcp)) {
		err = PTR_ERR(ipcp);
		goto out_unlock1;
	}

	sma = container_of(ipcp, struct sem_array, sem_perm);

	err = security_sem_semctl(&sma->sem_perm, cmd);
	if (err)
		goto out_unlock1;

	switch (cmd) {
	case IPC_RMID:
		sem_lock(sma, NULL, -1);
		/* freeary unlocks the ipc object and rcu */
		freeary(ns, ipcp);
		goto out_up;
	case IPC_SET:
		sem_lock(sma, NULL, -1);
		err = ipc_update_perm(&semid64->sem_perm, ipcp);
		if (err)
			goto out_unlock0;
		sma->sem_ctime = ktime_get_real_seconds();
		break;
	default:
		err = -EINVAL;
		goto out_unlock1;
	}

out_unlock0:
	sem_unlock(sma, -1);
out_unlock1:
	rcu_read_unlock();
out_up:
	up_write(&sem_ids(ns).rwsem);
	return err;
}

static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int version)
{
	struct ipc_namespace *ns;
	void __user *p = (void __user *)arg;
	struct semid64_ds semid64;
	int err;

	if (semid < 0)
		return -EINVAL;

	ns = current->nsproxy->ipc_ns;

	switch (cmd) {
	case IPC_INFO:
	case SEM_INFO:
		return semctl_info(ns, semid, cmd, p);
	case IPC_STAT:
	case SEM_STAT:
	case SEM_STAT_ANY:
		err = semctl_stat(ns, semid, cmd, &semid64);
		if (err < 0)
			return err;
		if (copy_semid_to_user(p, &semid64, version))
			err = -EFAULT;
		return err;
	case GETALL:
	case GETVAL:
	case GETPID:
	case GETNCNT:
	case GETZCNT:
	case SETALL:
		return semctl_main(ns, semid, semnum, cmd, p);
	case SETVAL: {
		int val;
#if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN)
		/* big-endian 64bit */
		val = arg >> 32;
#else
		/* 32bit or little-endian 64bit */
		val = arg;
#endif
		return semctl_setval(ns, semid, semnum, val);
	}
	case IPC_SET:
		if (copy_semid_from_user(&semid64, p, version))
			return -EFAULT;
		fallthrough;
	case IPC_RMID:
		return semctl_down(ns, semid, cmd, &semid64);
	default:
		return -EINVAL;
	}
}

SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg)
{
	return ksys_semctl(semid, semnum, cmd, arg, IPC_64);
}

#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg)
{
	int version = ipc_parse_version(&cmd);

	return ksys_semctl(semid, semnum, cmd, arg, version);
}

SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, unsigned long, arg)
{
	return ksys_old_semctl(semid, semnum, cmd, arg);
}
#endif

#ifdef CONFIG_COMPAT

struct compat_semid_ds {
	struct compat_ipc_perm sem_perm;
	old_time32_t sem_otime;
	old_time32_t sem_ctime;
	compat_uptr_t sem_base;
	compat_uptr_t sem_pending;
	compat_uptr_t sem_pending_last;
	compat_uptr_t undo;
	unsigned short sem_nsems;
};

static int copy_compat_semid_from_user(struct semid64_ds *out, void __user *buf,
					int version)
{
	memset(out, 0, sizeof(*out));
	if (version == IPC_64) {
		struct compat_semid64_ds __user *p = buf;
		return get_compat_ipc64_perm(&out->sem_perm, &p->sem_perm);
	} else {
		struct compat_semid_ds __user *p = buf;
		return get_compat_ipc_perm(&out->sem_perm, &p->sem_perm);
	}
}

static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in,
					int version)
{
	if (version == IPC_64) {
		struct compat_semid64_ds v;
		memset(&v, 0, sizeof(v));
		to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm);
		v.sem_otime	 = lower_32_bits(in->sem_otime);
		v.sem_otime_high = upper_32_bits(in->sem_otime);
		v.sem_ctime	 = lower_32_bits(in->sem_ctime);
		v.sem_ctime_high = upper_32_bits(in->sem_ctime);
		v.sem_nsems = in->sem_nsems;
		return copy_to_user(buf, &v, sizeof(v));
	} else {
		struct compat_semid_ds v;
		memset(&v, 0, sizeof(v));
		to_compat_ipc_perm(&v.sem_perm, &in->sem_perm);
		v.sem_otime = in->sem_otime;
		v.sem_ctime = in->sem_ctime;
		v.sem_nsems = in->sem_nsems;
		return copy_to_user(buf, &v, sizeof(v));
	}
}

static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int version)
{
	void __user *p = compat_ptr(arg);
	struct ipc_namespace *ns;
	struct semid64_ds semid64;
	int err;

	ns = current->nsproxy->ipc_ns;

	if (semid < 0)
		return -EINVAL;

	switch (cmd & (~IPC_64)) {
	case IPC_INFO:
	case SEM_INFO:
		return semctl_info(ns, semid, cmd, p);
	case IPC_STAT:
	case SEM_STAT:
	case SEM_STAT_ANY:
		err = semctl_stat(ns, semid, cmd, &semid64);
		if (err < 0)
			return err;
		if (copy_compat_semid_to_user(p, &semid64, version))
			err = -EFAULT;
		return err;
	case GETVAL:
	case GETPID:
	case GETNCNT:
	case GETZCNT:
	case GETALL:
	case SETALL:
		return semctl_main(ns, semid, semnum, cmd, p);
	case SETVAL:
		return semctl_setval(ns, semid, semnum, arg);
	case IPC_SET:
		if (copy_compat_semid_from_user(&semid64, p, version))
			return -EFAULT;
		fallthrough;
	case IPC_RMID:
		return semctl_down(ns, semid, cmd, &semid64);
	default:
		return -EINVAL;
	}
}

COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg)
{
	return compat_ksys_semctl(semid, semnum, cmd, arg, IPC_64);
}

#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION
long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg)
{
	int version = compat_ipc_parse_version(&cmd);

	return compat_ksys_semctl(semid, semnum, cmd, arg, version);
}

COMPAT_SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, int, arg)
{
	return compat_ksys_old_semctl(semid, semnum, cmd, arg);
}
#endif
#endif

/* If the task doesn't already have a undo_list, then allocate one
 * here.  We guarantee there is only one thread using this undo list,
 * and current is THE ONE
 *
 * If this allocation and assignment succeeds, but later
 * portions of this code fail, there is no need to free the sem_undo_list.
 * Just let it stay associated with the task, and it'll be freed later
 * at exit time.
 *
 * This can block, so callers must hold no locks.
 */
static inline int get_undo_list(struct sem_undo_list **undo_listp)
{
	struct sem_undo_list *undo_list;

	undo_list = current->sysvsem.undo_list;
	if (!undo_list) {
		undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT);
		if (undo_list == NULL)
			return -ENOMEM;
		spin_lock_init(&undo_list->lock);
		refcount_set(&undo_list->refcnt, 1);
		INIT_LIST_HEAD(&undo_list->list_proc);

		current->sysvsem.undo_list = undo_list;
	}
	*undo_listp = undo_list;
	return 0;
}

static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid)
{
	struct sem_undo *un;

	list_for_each_entry_rcu(un, &ulp->list_proc, list_proc,
				spin_is_locked(&ulp->lock)) {
		if (un->semid == semid)
			return un;
	}
	return NULL;
}

static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid)
{
	struct sem_undo *un;

	assert_spin_locked(&ulp->lock);

	un = __lookup_undo(ulp, semid);
	if (un) {
		list_del_rcu(&un->list_proc);
		list_add_rcu(&un->list_proc, &ulp->list_proc);
	}
	return un;
}

/**
 * find_alloc_undo - lookup (and if not present create) undo array
 * @ns: namespace
 * @semid: semaphore array id
 *
 * The function looks up (and if not present creates) the undo structure.
 * The size of the undo structure depends on the size of the semaphore
 * array, thus the alloc path is not that straightforward.
 * Lifetime-rules: sem_undo is rcu-protected, on success, the function
 * performs a rcu_read_lock().
 */
static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
{
	struct sem_array *sma;
	struct sem_undo_list *ulp;
	struct sem_undo *un, *new;
	int nsems, error;

	error = get_undo_list(&ulp);
	if (error)
		return ERR_PTR(error);

	rcu_read_lock();
	spin_lock(&ulp->lock);
	un = lookup_undo(ulp, semid);
	spin_unlock(&ulp->lock);
	if (likely(un != NULL))
		goto out;

	/* no undo structure around - allocate one. */
	/* step 1: figure out the size of the semaphore array */
	sma = sem_obtain_object_check(ns, semid);
	if (IS_ERR(sma)) {
		rcu_read_unlock();
		return ERR_CAST(sma);
	}

	nsems = sma->sem_nsems;
	if (!ipc_rcu_getref(&sma->sem_perm)) {
		rcu_read_unlock();
		un = ERR_PTR(-EIDRM);
		goto out;
	}
	rcu_read_unlock();

	/* step 2: allocate new undo structure */
	new = kvzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems,
		       GFP_KERNEL_ACCOUNT);
	if (!new) {
		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
		return ERR_PTR(-ENOMEM);
	}

	/* step 3: Acquire the lock on semaphore array */
	rcu_read_lock();
	sem_lock_and_putref(sma);
	if (!ipc_valid_object(&sma->sem_perm)) {
		sem_unlock(sma, -1);
		rcu_read_unlock();
		kvfree(new);
		un = ERR_PTR(-EIDRM);
		goto out;
	}
	spin_lock(&ulp->lock);

	/*
	 * step 4: check for races: did someone else allocate the undo struct?
	 */
	un = lookup_undo(ulp, semid);
	if (un) {
		kvfree(new);
		goto success;
	}
	/* step 5: initialize & link new undo structure */
	new->semadj = (short *) &new[1];
	new->ulp = ulp;
	new->semid = semid;
	assert_spin_locked(&ulp->lock);
	list_add_rcu(&new->list_proc, &ulp->list_proc);
	ipc_assert_locked_object(&sma->sem_perm);
	list_add(&new->list_id, &sma->list_id);
	un = new;

success:
	spin_unlock(&ulp->lock);
	sem_unlock(sma, -1);
out:
	return un;
}

static long do_semtimedop(int semid, struct sembuf __user *tsops,
		unsigned nsops, const struct timespec64 *timeout)
{
	int error = -EINVAL;
	struct sem_array *sma;
	struct sembuf fast_sops[SEMOPM_FAST];
	struct sembuf *sops = fast_sops, *sop;
	struct sem_undo *un;
	int max, locknum;
	bool undos = false, alter = false, dupsop = false;
	struct sem_queue queue;
	unsigned long dup = 0, jiffies_left = 0;
	struct ipc_namespace *ns;

	ns = current->nsproxy->ipc_ns;

	if (nsops < 1 || semid < 0)
		return -EINVAL;
	if (nsops > ns->sc_semopm)
		return -E2BIG;
	if (nsops > SEMOPM_FAST) {
		sops = kvmalloc_array(nsops, sizeof(*sops),
				      GFP_KERNEL_ACCOUNT);
		if (sops == NULL)
			return -ENOMEM;
	}

	if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) {
		error =  -EFAULT;
		goto out_free;
	}

	if (timeout) {
		if (timeout->tv_sec < 0 || timeout->tv_nsec < 0 ||
			timeout->tv_nsec >= 1000000000L) {
			error = -EINVAL;
			goto out_free;
		}
		jiffies_left = timespec64_to_jiffies(timeout);
	}

	max = 0;
	for (sop = sops; sop < sops + nsops; sop++) {
		unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG);

		if (sop->sem_num >= max)
			max = sop->sem_num;
		if (sop->sem_flg & SEM_UNDO)
			undos = true;
		if (dup & mask) {
			/*
			 * There was a previous alter access that appears
			 * to have accessed the same semaphore, thus use
			 * the dupsop logic. "appears", because the detection
			 * can only check % BITS_PER_LONG.
			 */
			dupsop = true;
		}
		if (sop->sem_op != 0) {
			alter = true;
			dup |= mask;
		}
	}

	if (undos) {
		/* On success, find_alloc_undo takes the rcu_read_lock */
		un = find_alloc_undo(ns, semid);
		if (IS_ERR(un)) {
			error = PTR_ERR(un);
			goto out_free;
		}
	} else {
		un = NULL;
		rcu_read_lock();
	}

	sma = sem_obtain_object_check(ns, semid);
	if (IS_ERR(sma)) {
		rcu_read_unlock();
		error = PTR_ERR(sma);
		goto out_free;
	}

	error = -EFBIG;
	if (max >= sma->sem_nsems) {
		rcu_read_unlock();
		goto out_free;
	}

	error = -EACCES;
	if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) {
		rcu_read_unlock();
		goto out_free;
	}

	error = security_sem_semop(&sma->sem_perm, sops, nsops, alter);
	if (error) {
		rcu_read_unlock();
		goto out_free;
	}

	error = -EIDRM;
	locknum = sem_lock(sma, sops, nsops);
	/*
	 * We eventually might perform the following check in a lockless
	 * fashion, considering ipc_valid_object() locking constraints.
	 * If nsops == 1 and there is no contention for sem_perm.lock, then
	 * only a per-semaphore lock is held and it's OK to proceed with the
	 * check below. More details on the fine grained locking scheme
	 * entangled here and why it's RMID race safe on comments at sem_lock()
	 */
	if (!ipc_valid_object(&sma->sem_perm))
		goto out_unlock_free;
	/*
	 * semid identifiers are not unique - find_alloc_undo may have
	 * allocated an undo structure, it was invalidated by an RMID
	 * and now a new array with received the same id. Check and fail.
	 * This case can be detected checking un->semid. The existence of
	 * "un" itself is guaranteed by rcu.
	 */
	if (un && un->semid == -1)
		goto out_unlock_free;

	queue.sops = sops;
	queue.nsops = nsops;
	queue.undo = un;
	queue.pid = task_tgid(current);
	queue.alter = alter;
	queue.dupsop = dupsop;

	error = perform_atomic_semop(sma, &queue);
	if (error == 0) { /* non-blocking successful path */
		DEFINE_WAKE_Q(wake_q);

		/*
		 * If the operation was successful, then do
		 * the required updates.
		 */
		if (alter)
			do_smart_update(sma, sops, nsops, 1, &wake_q);
		else
			set_semotime(sma, sops);

		sem_unlock(sma, locknum);
		rcu_read_unlock();
		wake_up_q(&wake_q);

		goto out_free;
	}
	if (error < 0) /* non-blocking error path */
		goto out_unlock_free;

	/*
	 * We need to sleep on this operation, so we put the current
	 * task into the pending queue and go to sleep.
	 */
	if (nsops == 1) {
		struct sem *curr;
		int idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
		curr = &sma->sems[idx];

		if (alter) {
			if (sma->complex_count) {
				list_add_tail(&queue.list,
						&sma->pending_alter);
			} else {

				list_add_tail(&queue.list,
						&curr->pending_alter);
			}
		} else {
			list_add_tail(&queue.list, &curr->pending_const);
		}
	} else {
		if (!sma->complex_count)
			merge_queues(sma);

		if (alter)
			list_add_tail(&queue.list, &sma->pending_alter);
		else
			list_add_tail(&queue.list, &sma->pending_const);

		sma->complex_count++;
	}

	do {
		/* memory ordering ensured by the lock in sem_lock() */
		WRITE_ONCE(queue.status, -EINTR);
		queue.sleeper = current;

		/* memory ordering is ensured by the lock in sem_lock() */
		__set_current_state(TASK_INTERRUPTIBLE);
		sem_unlock(sma, locknum);
		rcu_read_unlock();

		if (timeout)
			jiffies_left = schedule_timeout(jiffies_left);
		else
			schedule();

		/*
		 * fastpath: the semop has completed, either successfully or
		 * not, from the syscall pov, is quite irrelevant to us at this
		 * point; we're done.
		 *
		 * We _do_ care, nonetheless, about being awoken by a signal or
		 * spuriously.  The queue.status is checked again in the
		 * slowpath (aka after taking sem_lock), such that we can detect
		 * scenarios where we were awakened externally, during the
		 * window between wake_q_add() and wake_up_q().
		 */
		error = READ_ONCE(queue.status);
		if (error != -EINTR) {
			/* see SEM_BARRIER_2 for purpose/pairing */
			smp_acquire__after_ctrl_dep();
			goto out_free;
		}

		rcu_read_lock();
		locknum = sem_lock(sma, sops, nsops);

		if (!ipc_valid_object(&sma->sem_perm))
			goto out_unlock_free;

		/*
		 * No necessity for any barrier: We are protect by sem_lock()
		 */
		error = READ_ONCE(queue.status);

		/*
		 * If queue.status != -EINTR we are woken up by another process.
		 * Leave without unlink_queue(), but with sem_unlock().
		 */
		if (error != -EINTR)
			goto out_unlock_free;

		/*
		 * If an interrupt occurred we have to clean up the queue.
		 */
		if (timeout && jiffies_left == 0)
			error = -EAGAIN;
	} while (error == -EINTR && !signal_pending(current)); /* spurious */

	unlink_queue(sma, &queue);

out_unlock_free:
	sem_unlock(sma, locknum);
	rcu_read_unlock();
out_free:
	if (sops != fast_sops)
		kvfree(sops);
	return error;
}

long ksys_semtimedop(int semid, struct sembuf __user *tsops,
		     unsigned int nsops, const struct __kernel_timespec __user *timeout)
{
	if (timeout) {
		struct timespec64 ts;
		if (get_timespec64(&ts, timeout))
			return -EFAULT;
		return do_semtimedop(semid, tsops, nsops, &ts);
	}
	return do_semtimedop(semid, tsops, nsops, NULL);
}

SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
		unsigned int, nsops, const struct __kernel_timespec __user *, timeout)
{
	return ksys_semtimedop(semid, tsops, nsops, timeout);
}

#ifdef CONFIG_COMPAT_32BIT_TIME
long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
			    unsigned int nsops,
			    const struct old_timespec32 __user *timeout)
{
	if (timeout) {
		struct timespec64 ts;
		if (get_old_timespec32(&ts, timeout))
			return -EFAULT;
		return do_semtimedop(semid, tsems, nsops, &ts);
	}
	return do_semtimedop(semid, tsems, nsops, NULL);
}

SYSCALL_DEFINE4(semtimedop_time32, int, semid, struct sembuf __user *, tsems,
		       unsigned int, nsops,
		       const struct old_timespec32 __user *, timeout)
{
	return compat_ksys_semtimedop(semid, tsems, nsops, timeout);
}
#endif

SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops,
		unsigned, nsops)
{
	return do_semtimedop(semid, tsops, nsops, NULL);
}

/* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between
 * parent and child tasks.
 */

int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
{
	struct sem_undo_list *undo_list;
	int error;

	if (clone_flags & CLONE_SYSVSEM) {
		error = get_undo_list(&undo_list);
		if (error)
			return error;
		refcount_inc(&undo_list->refcnt);
		tsk->sysvsem.undo_list = undo_list;
	} else
		tsk->sysvsem.undo_list = NULL;

	return 0;
}

/*
 * add semadj values to semaphores, free undo structures.
 * undo structures are not freed when semaphore arrays are destroyed
 * so some of them may be out of date.
 * IMPLEMENTATION NOTE: There is some confusion over whether the
 * set of adjustments that needs to be done should be done in an atomic
 * manner or not. That is, if we are attempting to decrement the semval
 * should we queue up and wait until we can do so legally?
 * The original implementation attempted to do this (queue and wait).
 * The current implementation does not do so. The POSIX standard
 * and SVID should be consulted to determine what behavior is mandated.
 */
void exit_sem(struct task_struct *tsk)
{
	struct sem_undo_list *ulp;

	ulp = tsk->sysvsem.undo_list;
	if (!ulp)
		return;
	tsk->sysvsem.undo_list = NULL;

	if (!refcount_dec_and_test(&ulp->refcnt))
		return;

	for (;;) {
		struct sem_array *sma;
		struct sem_undo *un;
		int semid, i;
		DEFINE_WAKE_Q(wake_q);

		cond_resched();

		rcu_read_lock();
		un = list_entry_rcu(ulp->list_proc.next,
				    struct sem_undo, list_proc);
		if (&un->list_proc == &ulp->list_proc) {
			/*
			 * We must wait for freeary() before freeing this ulp,
			 * in case we raced with last sem_undo. There is a small
			 * possibility where we exit while freeary() didn't
			 * finish unlocking sem_undo_list.
			 */
			spin_lock(&ulp->lock);
			spin_unlock(&ulp->lock);
			rcu_read_unlock();
			break;
		}
		spin_lock(&ulp->lock);
		semid = un->semid;
		spin_unlock(&ulp->lock);

		/* exit_sem raced with IPC_RMID, nothing to do */
		if (semid == -1) {
			rcu_read_unlock();
			continue;
		}

		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid);
		/* exit_sem raced with IPC_RMID, nothing to do */
		if (IS_ERR(sma)) {
			rcu_read_unlock();
			continue;
		}

		sem_lock(sma, NULL, -1);
		/* exit_sem raced with IPC_RMID, nothing to do */
		if (!ipc_valid_object(&sma->sem_perm)) {
			sem_unlock(sma, -1);
			rcu_read_unlock();
			continue;
		}
		un = __lookup_undo(ulp, semid);
		if (un == NULL) {
			/* exit_sem raced with IPC_RMID+semget() that created
			 * exactly the same semid. Nothing to do.
			 */
			sem_unlock(sma, -1);
			rcu_read_unlock();
			continue;
		}

		/* remove un from the linked lists */
		ipc_assert_locked_object(&sma->sem_perm);
		list_del(&un->list_id);

		spin_lock(&ulp->lock);
		list_del_rcu(&un->list_proc);
		spin_unlock(&ulp->lock);

		/* perform adjustments registered in un */
		for (i = 0; i < sma->sem_nsems; i++) {
			struct sem *semaphore = &sma->sems[i];
			if (un->semadj[i]) {
				semaphore->semval += un->semadj[i];
				/*
				 * Range checks of the new semaphore value,
				 * not defined by sus:
				 * - Some unices ignore the undo entirely
				 *   (e.g. HP UX 11i 11.22, Tru64 V5.1)
				 * - some cap the value (e.g. FreeBSD caps
				 *   at 0, but doesn't enforce SEMVMX)
				 *
				 * Linux caps the semaphore value, both at 0
				 * and at SEMVMX.
				 *
				 *	Manfred <manfred@colorfullife.com>
				 */
				if (semaphore->semval < 0)
					semaphore->semval = 0;
				if (semaphore->semval > SEMVMX)
					semaphore->semval = SEMVMX;
				ipc_update_pid(&semaphore->sempid, task_tgid(current));
			}
		}
		/* maybe some queued-up processes were waiting for this */
		do_smart_update(sma, NULL, 0, 1, &wake_q);
		sem_unlock(sma, -1);
		rcu_read_unlock();
		wake_up_q(&wake_q);

		kvfree_rcu(un, rcu);
	}
	kfree(ulp);
}

#ifdef CONFIG_PROC_FS
static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
{
	struct user_namespace *user_ns = seq_user_ns(s);
	struct kern_ipc_perm *ipcp = it;
	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);
	time64_t sem_otime;

	/*
	 * The proc interface isn't aware of sem_lock(), it calls
	 * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock).
	 * (in sysvipc_find_ipc)
	 * In order to stay compatible with sem_lock(), we must
	 * enter / leave complex_mode.
	 */
	complexmode_enter(sma);

	sem_otime = get_semotime(sma);

	seq_printf(s,
		   "%10d %10d  %4o %10u %5u %5u %5u %5u %10llu %10llu\n",
		   sma->sem_perm.key,
		   sma->sem_perm.id,
		   sma->sem_perm.mode,
		   sma->sem_nsems,
		   from_kuid_munged(user_ns, sma->sem_perm.uid),
		   from_kgid_munged(user_ns, sma->sem_perm.gid),
		   from_kuid_munged(user_ns, sma->sem_perm.cuid),
		   from_kgid_munged(user_ns, sma->sem_perm.cgid),
		   sem_otime,
		   sma->sem_ctime);

	complexmode_tryleave(sma);

	return 0;
}
#endif