summaryrefslogtreecommitdiff
path: root/fs/userfaultfd.c
blob: 894cc28142e7c2c33ca26d41c7e291cc4f816047 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  fs/userfaultfd.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *  Copyright (C) 2008-2009 Red Hat, Inc.
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 *  Some part derived from fs/eventfd.c (anon inode setup) and
 *  mm/ksm.c (mm hashing).
 */

#include <linux/list.h>
#include <linux/hashtable.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/mm.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/file.h>
#include <linux/bug.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/userfaultfd_k.h>
#include <linux/mempolicy.h>
#include <linux/ioctl.h>
#include <linux/security.h>
#include <linux/hugetlb.h>

int sysctl_unprivileged_userfaultfd __read_mostly;

static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;

enum userfaultfd_state {
	UFFD_STATE_WAIT_API,
	UFFD_STATE_RUNNING,
};

/*
 * Start with fault_pending_wqh and fault_wqh so they're more likely
 * to be in the same cacheline.
 *
 * Locking order:
 *	fd_wqh.lock
 *		fault_pending_wqh.lock
 *			fault_wqh.lock
 *		event_wqh.lock
 *
 * To avoid deadlocks, IRQs must be disabled when taking any of the above locks,
 * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's
 * also taken in IRQ context.
 */
struct userfaultfd_ctx {
	/* waitqueue head for the pending (i.e. not read) userfaults */
	wait_queue_head_t fault_pending_wqh;
	/* waitqueue head for the userfaults */
	wait_queue_head_t fault_wqh;
	/* waitqueue head for the pseudo fd to wakeup poll/read */
	wait_queue_head_t fd_wqh;
	/* waitqueue head for events */
	wait_queue_head_t event_wqh;
	/* a refile sequence protected by fault_pending_wqh lock */
	seqcount_spinlock_t refile_seq;
	/* pseudo fd refcounting */
	refcount_t refcount;
	/* userfaultfd syscall flags */
	unsigned int flags;
	/* features requested from the userspace */
	unsigned int features;
	/* state machine */
	enum userfaultfd_state state;
	/* released */
	bool released;
	/* memory mappings are changing because of non-cooperative event */
	bool mmap_changing;
	/* mm with one ore more vmas attached to this userfaultfd_ctx */
	struct mm_struct *mm;
};

struct userfaultfd_fork_ctx {
	struct userfaultfd_ctx *orig;
	struct userfaultfd_ctx *new;
	struct list_head list;
};

struct userfaultfd_unmap_ctx {
	struct userfaultfd_ctx *ctx;
	unsigned long start;
	unsigned long end;
	struct list_head list;
};

struct userfaultfd_wait_queue {
	struct uffd_msg msg;
	wait_queue_entry_t wq;
	struct userfaultfd_ctx *ctx;
	bool waken;
};

struct userfaultfd_wake_range {
	unsigned long start;
	unsigned long len;
};

static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
				     int wake_flags, void *key)
{
	struct userfaultfd_wake_range *range = key;
	int ret;
	struct userfaultfd_wait_queue *uwq;
	unsigned long start, len;

	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
	ret = 0;
	/* len == 0 means wake all */
	start = range->start;
	len = range->len;
	if (len && (start > uwq->msg.arg.pagefault.address ||
		    start + len <= uwq->msg.arg.pagefault.address))
		goto out;
	WRITE_ONCE(uwq->waken, true);
	/*
	 * The Program-Order guarantees provided by the scheduler
	 * ensure uwq->waken is visible before the task is woken.
	 */
	ret = wake_up_state(wq->private, mode);
	if (ret) {
		/*
		 * Wake only once, autoremove behavior.
		 *
		 * After the effect of list_del_init is visible to the other
		 * CPUs, the waitqueue may disappear from under us, see the
		 * !list_empty_careful() in handle_userfault().
		 *
		 * try_to_wake_up() has an implicit smp_mb(), and the
		 * wq->private is read before calling the extern function
		 * "wake_up_state" (which in turns calls try_to_wake_up).
		 */
		list_del_init(&wq->entry);
	}
out:
	return ret;
}

/**
 * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
 * context.
 * @ctx: [in] Pointer to the userfaultfd context.
 */
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
	refcount_inc(&ctx->refcount);
}

/**
 * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
 * context.
 * @ctx: [in] Pointer to userfaultfd context.
 *
 * The userfaultfd context reference must have been previously acquired either
 * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
 */
static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
{
	if (refcount_dec_and_test(&ctx->refcount)) {
		VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
		VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
		VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
		VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
		mmdrop(ctx->mm);
		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
	}
}

static inline void msg_init(struct uffd_msg *msg)
{
	BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
	/*
	 * Must use memset to zero out the paddings or kernel data is
	 * leaked to userland.
	 */
	memset(msg, 0, sizeof(struct uffd_msg));
}

static inline struct uffd_msg userfault_msg(unsigned long address,
					    unsigned int flags,
					    unsigned long reason,
					    unsigned int features)
{
	struct uffd_msg msg;
	msg_init(&msg);
	msg.event = UFFD_EVENT_PAGEFAULT;
	msg.arg.pagefault.address = address;
	if (flags & FAULT_FLAG_WRITE)
		/*
		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
		 * was not set in a UFFD_EVENT_PAGEFAULT, it means it
		 * was a read fault, otherwise if set it means it's
		 * a write fault.
		 */
		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
	if (reason & VM_UFFD_WP)
		/*
		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
		 * not set in a UFFD_EVENT_PAGEFAULT, it means it was
		 * a missing fault, otherwise if set it means it's a
		 * write protect fault.
		 */
		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
	if (features & UFFD_FEATURE_THREAD_ID)
		msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
	return msg;
}

#ifdef CONFIG_HUGETLB_PAGE
/*
 * Same functionality as userfaultfd_must_wait below with modifications for
 * hugepmd ranges.
 */
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
					 struct vm_area_struct *vma,
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	struct mm_struct *mm = ctx->mm;
	pte_t *ptep, pte;
	bool ret = true;

	mmap_assert_locked(mm);

	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));

	if (!ptep)
		goto out;

	ret = false;
	pte = huge_ptep_get(ptep);

	/*
	 * Lockless access: we're in a wait_event so it's ok if it
	 * changes under us.
	 */
	if (huge_pte_none(pte))
		ret = true;
	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
		ret = true;
out:
	return ret;
}
#else
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
					 struct vm_area_struct *vma,
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	return false;	/* should never get here */
}
#endif /* CONFIG_HUGETLB_PAGE */

/*
 * Verify the pagetables are still not ok after having reigstered into
 * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
 * userfault that has already been resolved, if userfaultfd_read and
 * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
 * threads.
 */
static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	struct mm_struct *mm = ctx->mm;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd, _pmd;
	pte_t *pte;
	bool ret = true;

	mmap_assert_locked(mm);

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;
	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		goto out;
	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		goto out;
	pmd = pmd_offset(pud, address);
	/*
	 * READ_ONCE must function as a barrier with narrower scope
	 * and it must be equivalent to:
	 *	_pmd = *pmd; barrier();
	 *
	 * This is to deal with the instability (as in
	 * pmd_trans_unstable) of the pmd.
	 */
	_pmd = READ_ONCE(*pmd);
	if (pmd_none(_pmd))
		goto out;

	ret = false;
	if (!pmd_present(_pmd))
		goto out;

	if (pmd_trans_huge(_pmd)) {
		if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
			ret = true;
		goto out;
	}

	/*
	 * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
	 * and use the standard pte_offset_map() instead of parsing _pmd.
	 */
	pte = pte_offset_map(pmd, address);
	/*
	 * Lockless access: we're in a wait_event so it's ok if it
	 * changes under us.
	 */
	if (pte_none(*pte))
		ret = true;
	if (!pte_write(*pte) && (reason & VM_UFFD_WP))
		ret = true;
	pte_unmap(pte);

out:
	return ret;
}

static inline long userfaultfd_get_blocking_state(unsigned int flags)
{
	if (flags & FAULT_FLAG_INTERRUPTIBLE)
		return TASK_INTERRUPTIBLE;

	if (flags & FAULT_FLAG_KILLABLE)
		return TASK_KILLABLE;

	return TASK_UNINTERRUPTIBLE;
}

/*
 * The locking rules involved in returning VM_FAULT_RETRY depending on
 * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
 * FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
 * recommendation in __lock_page_or_retry is not an understatement.
 *
 * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released
 * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
 * not set.
 *
 * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
 * set, VM_FAULT_RETRY can still be returned if and only if there are
 * fatal_signal_pending()s, and the mmap_lock must be released before
 * returning it.
 */
vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
{
	struct mm_struct *mm = vmf->vma->vm_mm;
	struct userfaultfd_ctx *ctx;
	struct userfaultfd_wait_queue uwq;
	vm_fault_t ret = VM_FAULT_SIGBUS;
	bool must_wait;
	long blocking_state;

	/*
	 * We don't do userfault handling for the final child pid update.
	 *
	 * We also don't do userfault handling during
	 * coredumping. hugetlbfs has the special
	 * follow_hugetlb_page() to skip missing pages in the
	 * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
	 * the no_page_table() helper in follow_page_mask(), but the
	 * shmem_vm_ops->fault method is invoked even during
	 * coredumping without mmap_lock and it ends up here.
	 */
	if (current->flags & (PF_EXITING|PF_DUMPCORE))
		goto out;

	/*
	 * Coredumping runs without mmap_lock so we can only check that
	 * the mmap_lock is held, if PF_DUMPCORE was not set.
	 */
	mmap_assert_locked(mm);

	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
	if (!ctx)
		goto out;

	BUG_ON(ctx->mm != mm);

	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));

	if (ctx->features & UFFD_FEATURE_SIGBUS)
		goto out;
	if ((vmf->flags & FAULT_FLAG_USER) == 0 &&
	    ctx->flags & UFFD_USER_MODE_ONLY) {
		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
			"sysctl knob to 1 if kernel faults must be handled "
			"without obtaining CAP_SYS_PTRACE capability\n");
		goto out;
	}

	/*
	 * If it's already released don't get it. This avoids to loop
	 * in __get_user_pages if userfaultfd_release waits on the
	 * caller of handle_userfault to release the mmap_lock.
	 */
	if (unlikely(READ_ONCE(ctx->released))) {
		/*
		 * Don't return VM_FAULT_SIGBUS in this case, so a non
		 * cooperative manager can close the uffd after the
		 * last UFFDIO_COPY, without risking to trigger an
		 * involuntary SIGBUS if the process was starting the
		 * userfaultfd while the userfaultfd was still armed
		 * (but after the last UFFDIO_COPY). If the uffd
		 * wasn't already closed when the userfault reached
		 * this point, that would normally be solved by
		 * userfaultfd_must_wait returning 'false'.
		 *
		 * If we were to return VM_FAULT_SIGBUS here, the non
		 * cooperative manager would be instead forced to
		 * always call UFFDIO_UNREGISTER before it can safely
		 * close the uffd.
		 */
		ret = VM_FAULT_NOPAGE;
		goto out;
	}

	/*
	 * Check that we can return VM_FAULT_RETRY.
	 *
	 * NOTE: it should become possible to return VM_FAULT_RETRY
	 * even if FAULT_FLAG_TRIED is set without leading to gup()
	 * -EBUSY failures, if the userfaultfd is to be extended for
	 * VM_UFFD_WP tracking and we intend to arm the userfault
	 * without first stopping userland access to the memory. For
	 * VM_UFFD_MISSING userfaults this is enough for now.
	 */
	if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
		/*
		 * Validate the invariant that nowait must allow retry
		 * to be sure not to return SIGBUS erroneously on
		 * nowait invocations.
		 */
		BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
#ifdef CONFIG_DEBUG_VM
		if (printk_ratelimit()) {
			printk(KERN_WARNING
			       "FAULT_FLAG_ALLOW_RETRY missing %x\n",
			       vmf->flags);
			dump_stack();
		}
#endif
		goto out;
	}

	/*
	 * Handle nowait, not much to do other than tell it to retry
	 * and wait.
	 */
	ret = VM_FAULT_RETRY;
	if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
		goto out;

	/* take the reference before dropping the mmap_lock */
	userfaultfd_ctx_get(ctx);

	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
	uwq.wq.private = current;
	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
			ctx->features);
	uwq.ctx = ctx;
	uwq.waken = false;

	blocking_state = userfaultfd_get_blocking_state(vmf->flags);

	spin_lock_irq(&ctx->fault_pending_wqh.lock);
	/*
	 * After the __add_wait_queue the uwq is visible to userland
	 * through poll/read().
	 */
	__add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
	/*
	 * The smp_mb() after __set_current_state prevents the reads
	 * following the spin_unlock to happen before the list_add in
	 * __add_wait_queue.
	 */
	set_current_state(blocking_state);
	spin_unlock_irq(&ctx->fault_pending_wqh.lock);

	if (!is_vm_hugetlb_page(vmf->vma))
		must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
						  reason);
	else
		must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
						       vmf->address,
						       vmf->flags, reason);
	mmap_read_unlock(mm);

	if (likely(must_wait && !READ_ONCE(ctx->released))) {
		wake_up_poll(&ctx->fd_wqh, EPOLLIN);
		schedule();
	}

	__set_current_state(TASK_RUNNING);

	/*
	 * Here we race with the list_del; list_add in
	 * userfaultfd_ctx_read(), however because we don't ever run
	 * list_del_init() to refile across the two lists, the prev
	 * and next pointers will never point to self. list_add also
	 * would never let any of the two pointers to point to
	 * self. So list_empty_careful won't risk to see both pointers
	 * pointing to self at any time during the list refile. The
	 * only case where list_del_init() is called is the full
	 * removal in the wake function and there we don't re-list_add
	 * and it's fine not to block on the spinlock. The uwq on this
	 * kernel stack can be released after the list_del_init.
	 */
	if (!list_empty_careful(&uwq.wq.entry)) {
		spin_lock_irq(&ctx->fault_pending_wqh.lock);
		/*
		 * No need of list_del_init(), the uwq on the stack
		 * will be freed shortly anyway.
		 */
		list_del(&uwq.wq.entry);
		spin_unlock_irq(&ctx->fault_pending_wqh.lock);
	}

	/*
	 * ctx may go away after this if the userfault pseudo fd is
	 * already released.
	 */
	userfaultfd_ctx_put(ctx);

out:
	return ret;
}

static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
					      struct userfaultfd_wait_queue *ewq)
{
	struct userfaultfd_ctx *release_new_ctx;

	if (WARN_ON_ONCE(current->flags & PF_EXITING))
		goto out;

	ewq->ctx = ctx;
	init_waitqueue_entry(&ewq->wq, current);
	release_new_ctx = NULL;

	spin_lock_irq(&ctx->event_wqh.lock);
	/*
	 * After the __add_wait_queue the uwq is visible to userland
	 * through poll/read().
	 */
	__add_wait_queue(&ctx->event_wqh, &ewq->wq);
	for (;;) {
		set_current_state(TASK_KILLABLE);
		if (ewq->msg.event == 0)
			break;
		if (READ_ONCE(ctx->released) ||
		    fatal_signal_pending(current)) {
			/*
			 * &ewq->wq may be queued in fork_event, but
			 * __remove_wait_queue ignores the head
			 * parameter. It would be a problem if it
			 * didn't.
			 */
			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
			if (ewq->msg.event == UFFD_EVENT_FORK) {
				struct userfaultfd_ctx *new;

				new = (struct userfaultfd_ctx *)
					(unsigned long)
					ewq->msg.arg.reserved.reserved1;
				release_new_ctx = new;
			}
			break;
		}

		spin_unlock_irq(&ctx->event_wqh.lock);

		wake_up_poll(&ctx->fd_wqh, EPOLLIN);
		schedule();

		spin_lock_irq(&ctx->event_wqh.lock);
	}
	__set_current_state(TASK_RUNNING);
	spin_unlock_irq(&ctx->event_wqh.lock);

	if (release_new_ctx) {
		struct vm_area_struct *vma;
		struct mm_struct *mm = release_new_ctx->mm;

		/* the various vma->vm_userfaultfd_ctx still points to it */
		mmap_write_lock(mm);
		for (vma = mm->mmap; vma; vma = vma->vm_next)
			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
			}
		mmap_write_unlock(mm);

		userfaultfd_ctx_put(release_new_ctx);
	}

	/*
	 * ctx may go away after this if the userfault pseudo fd is
	 * already released.
	 */
out:
	WRITE_ONCE(ctx->mmap_changing, false);
	userfaultfd_ctx_put(ctx);
}

static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
				       struct userfaultfd_wait_queue *ewq)
{
	ewq->msg.event = 0;
	wake_up_locked(&ctx->event_wqh);
	__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
}

int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
{
	struct userfaultfd_ctx *ctx = NULL, *octx;
	struct userfaultfd_fork_ctx *fctx;

	octx = vma->vm_userfaultfd_ctx.ctx;
	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
		return 0;
	}

	list_for_each_entry(fctx, fcs, list)
		if (fctx->orig == octx) {
			ctx = fctx->new;
			break;
		}

	if (!ctx) {
		fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
		if (!fctx)
			return -ENOMEM;

		ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
		if (!ctx) {
			kfree(fctx);
			return -ENOMEM;
		}

		refcount_set(&ctx->refcount, 1);
		ctx->flags = octx->flags;
		ctx->state = UFFD_STATE_RUNNING;
		ctx->features = octx->features;
		ctx->released = false;
		ctx->mmap_changing = false;
		ctx->mm = vma->vm_mm;
		mmgrab(ctx->mm);

		userfaultfd_ctx_get(octx);
		WRITE_ONCE(octx->mmap_changing, true);
		fctx->orig = octx;
		fctx->new = ctx;
		list_add_tail(&fctx->list, fcs);
	}

	vma->vm_userfaultfd_ctx.ctx = ctx;
	return 0;
}

static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
{
	struct userfaultfd_ctx *ctx = fctx->orig;
	struct userfaultfd_wait_queue ewq;

	msg_init(&ewq.msg);

	ewq.msg.event = UFFD_EVENT_FORK;
	ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;

	userfaultfd_event_wait_completion(ctx, &ewq);
}

void dup_userfaultfd_complete(struct list_head *fcs)
{
	struct userfaultfd_fork_ctx *fctx, *n;

	list_for_each_entry_safe(fctx, n, fcs, list) {
		dup_fctx(fctx);
		list_del(&fctx->list);
		kfree(fctx);
	}
}

void mremap_userfaultfd_prep(struct vm_area_struct *vma,
			     struct vm_userfaultfd_ctx *vm_ctx)
{
	struct userfaultfd_ctx *ctx;

	ctx = vma->vm_userfaultfd_ctx.ctx;

	if (!ctx)
		return;

	if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
		vm_ctx->ctx = ctx;
		userfaultfd_ctx_get(ctx);
		WRITE_ONCE(ctx->mmap_changing, true);
	} else {
		/* Drop uffd context if remap feature not enabled */
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
	}
}

void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
				 unsigned long from, unsigned long to,
				 unsigned long len)
{
	struct userfaultfd_ctx *ctx = vm_ctx->ctx;
	struct userfaultfd_wait_queue ewq;

	if (!ctx)
		return;

	if (to & ~PAGE_MASK) {
		userfaultfd_ctx_put(ctx);
		return;
	}

	msg_init(&ewq.msg);

	ewq.msg.event = UFFD_EVENT_REMAP;
	ewq.msg.arg.remap.from = from;
	ewq.msg.arg.remap.to = to;
	ewq.msg.arg.remap.len = len;

	userfaultfd_event_wait_completion(ctx, &ewq);
}

bool userfaultfd_remove(struct vm_area_struct *vma,
			unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;
	struct userfaultfd_ctx *ctx;
	struct userfaultfd_wait_queue ewq;

	ctx = vma->vm_userfaultfd_ctx.ctx;
	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
		return true;

	userfaultfd_ctx_get(ctx);
	WRITE_ONCE(ctx->mmap_changing, true);
	mmap_read_unlock(mm);

	msg_init(&ewq.msg);

	ewq.msg.event = UFFD_EVENT_REMOVE;
	ewq.msg.arg.remove.start = start;
	ewq.msg.arg.remove.end = end;

	userfaultfd_event_wait_completion(ctx, &ewq);

	return false;
}

static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
			  unsigned long start, unsigned long end)
{
	struct userfaultfd_unmap_ctx *unmap_ctx;

	list_for_each_entry(unmap_ctx, unmaps, list)
		if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
		    unmap_ctx->end == end)
			return true;

	return false;
}

int userfaultfd_unmap_prep(struct vm_area_struct *vma,
			   unsigned long start, unsigned long end,
			   struct list_head *unmaps)
{
	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
		struct userfaultfd_unmap_ctx *unmap_ctx;
		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;

		if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
		    has_unmap_ctx(ctx, unmaps, start, end))
			continue;

		unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
		if (!unmap_ctx)
			return -ENOMEM;

		userfaultfd_ctx_get(ctx);
		WRITE_ONCE(ctx->mmap_changing, true);
		unmap_ctx->ctx = ctx;
		unmap_ctx->start = start;
		unmap_ctx->end = end;
		list_add_tail(&unmap_ctx->list, unmaps);
	}

	return 0;
}

void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
{
	struct userfaultfd_unmap_ctx *ctx, *n;
	struct userfaultfd_wait_queue ewq;

	list_for_each_entry_safe(ctx, n, uf, list) {
		msg_init(&ewq.msg);

		ewq.msg.event = UFFD_EVENT_UNMAP;
		ewq.msg.arg.remove.start = ctx->start;
		ewq.msg.arg.remove.end = ctx->end;

		userfaultfd_event_wait_completion(ctx->ctx, &ewq);

		list_del(&ctx->list);
		kfree(ctx);
	}
}

static int userfaultfd_release(struct inode *inode, struct file *file)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev;
	/* len == 0 means wake all */
	struct userfaultfd_wake_range range = { .len = 0, };
	unsigned long new_flags;

	WRITE_ONCE(ctx->released, true);

	if (!mmget_not_zero(mm))
		goto wakeup;

	/*
	 * Flush page faults out of all CPUs. NOTE: all page faults
	 * must be retried without returning VM_FAULT_SIGBUS if
	 * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
	 * changes while handle_userfault released the mmap_lock. So
	 * it's critical that released is set to true (above), before
	 * taking the mmap_lock for writing.
	 */
	mmap_write_lock(mm);
	prev = NULL;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		cond_resched();
		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
		       !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
		if (vma->vm_userfaultfd_ctx.ctx != ctx) {
			prev = vma;
			continue;
		}
		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
				 new_flags, vma->anon_vma,
				 vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 NULL_VM_UFFD_CTX);
		if (prev)
			vma = prev;
		else
			prev = vma;
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
	}
	mmap_write_unlock(mm);
	mmput(mm);
wakeup:
	/*
	 * After no new page faults can wait on this fault_*wqh, flush
	 * the last page faults that may have been already waiting on
	 * the fault_*wqh.
	 */
	spin_lock_irq(&ctx->fault_pending_wqh.lock);
	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
	__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range);
	spin_unlock_irq(&ctx->fault_pending_wqh.lock);

	/* Flush pending events that may still wait on event_wqh */
	wake_up_all(&ctx->event_wqh);

	wake_up_poll(&ctx->fd_wqh, EPOLLHUP);
	userfaultfd_ctx_put(ctx);
	return 0;
}

/* fault_pending_wqh.lock must be hold by the caller */
static inline struct userfaultfd_wait_queue *find_userfault_in(
		wait_queue_head_t *wqh)
{
	wait_queue_entry_t *wq;
	struct userfaultfd_wait_queue *uwq;

	lockdep_assert_held(&wqh->lock);

	uwq = NULL;
	if (!waitqueue_active(wqh))
		goto out;
	/* walk in reverse to provide FIFO behavior to read userfaults */
	wq = list_last_entry(&wqh->head, typeof(*wq), entry);
	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
out:
	return uwq;
}

static inline struct userfaultfd_wait_queue *find_userfault(
		struct userfaultfd_ctx *ctx)
{
	return find_userfault_in(&ctx->fault_pending_wqh);
}

static inline struct userfaultfd_wait_queue *find_userfault_evt(
		struct userfaultfd_ctx *ctx)
{
	return find_userfault_in(&ctx->event_wqh);
}

static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	__poll_t ret;

	poll_wait(file, &ctx->fd_wqh, wait);

	switch (ctx->state) {
	case UFFD_STATE_WAIT_API:
		return EPOLLERR;
	case UFFD_STATE_RUNNING:
		/*
		 * poll() never guarantees that read won't block.
		 * userfaults can be waken before they're read().
		 */
		if (unlikely(!(file->f_flags & O_NONBLOCK)))
			return EPOLLERR;
		/*
		 * lockless access to see if there are pending faults
		 * __pollwait last action is the add_wait_queue but
		 * the spin_unlock would allow the waitqueue_active to
		 * pass above the actual list_add inside
		 * add_wait_queue critical section. So use a full
		 * memory barrier to serialize the list_add write of
		 * add_wait_queue() with the waitqueue_active read
		 * below.
		 */
		ret = 0;
		smp_mb();
		if (waitqueue_active(&ctx->fault_pending_wqh))
			ret = EPOLLIN;
		else if (waitqueue_active(&ctx->event_wqh))
			ret = EPOLLIN;

		return ret;
	default:
		WARN_ON_ONCE(1);
		return EPOLLERR;
	}
}

static const struct file_operations userfaultfd_fops;

static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
				  struct userfaultfd_ctx *new,
				  struct uffd_msg *msg)
{
	int fd;

	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, new,
			      O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS));
	if (fd < 0)
		return fd;

	msg->arg.reserved.reserved1 = 0;
	msg->arg.fork.ufd = fd;
	return 0;
}

static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
				    struct uffd_msg *msg)
{
	ssize_t ret;
	DECLARE_WAITQUEUE(wait, current);
	struct userfaultfd_wait_queue *uwq;
	/*
	 * Handling fork event requires sleeping operations, so
	 * we drop the event_wqh lock, then do these ops, then
	 * lock it back and wake up the waiter. While the lock is
	 * dropped the ewq may go away so we keep track of it
	 * carefully.
	 */
	LIST_HEAD(fork_event);
	struct userfaultfd_ctx *fork_nctx = NULL;

	/* always take the fd_wqh lock before the fault_pending_wqh lock */
	spin_lock_irq(&ctx->fd_wqh.lock);
	__add_wait_queue(&ctx->fd_wqh, &wait);
	for (;;) {
		set_current_state(TASK_INTERRUPTIBLE);
		spin_lock(&ctx->fault_pending_wqh.lock);
		uwq = find_userfault(ctx);
		if (uwq) {
			/*
			 * Use a seqcount to repeat the lockless check
			 * in wake_userfault() to avoid missing
			 * wakeups because during the refile both
			 * waitqueue could become empty if this is the
			 * only userfault.
			 */
			write_seqcount_begin(&ctx->refile_seq);

			/*
			 * The fault_pending_wqh.lock prevents the uwq
			 * to disappear from under us.
			 *
			 * Refile this userfault from
			 * fault_pending_wqh to fault_wqh, it's not
			 * pending anymore after we read it.
			 *
			 * Use list_del() by hand (as
			 * userfaultfd_wake_function also uses
			 * list_del_init() by hand) to be sure nobody
			 * changes __remove_wait_queue() to use
			 * list_del_init() in turn breaking the
			 * !list_empty_careful() check in
			 * handle_userfault(). The uwq->wq.head list
			 * must never be empty at any time during the
			 * refile, or the waitqueue could disappear
			 * from under us. The "wait_queue_head_t"
			 * parameter of __remove_wait_queue() is unused
			 * anyway.
			 */
			list_del(&uwq->wq.entry);
			add_wait_queue(&ctx->fault_wqh, &uwq->wq);

			write_seqcount_end(&ctx->refile_seq);

			/* careful to always initialize msg if ret == 0 */
			*msg = uwq->msg;
			spin_unlock(&ctx->fault_pending_wqh.lock);
			ret = 0;
			break;
		}
		spin_unlock(&ctx->fault_pending_wqh.lock);

		spin_lock(&ctx->event_wqh.lock);
		uwq = find_userfault_evt(ctx);
		if (uwq) {
			*msg = uwq->msg;

			if (uwq->msg.event == UFFD_EVENT_FORK) {
				fork_nctx = (struct userfaultfd_ctx *)
					(unsigned long)
					uwq->msg.arg.reserved.reserved1;
				list_move(&uwq->wq.entry, &fork_event);
				/*
				 * fork_nctx can be freed as soon as
				 * we drop the lock, unless we take a
				 * reference on it.
				 */
				userfaultfd_ctx_get(fork_nctx);
				spin_unlock(&ctx->event_wqh.lock);
				ret = 0;
				break;
			}

			userfaultfd_event_complete(ctx, uwq);
			spin_unlock(&ctx->event_wqh.lock);
			ret = 0;
			break;
		}
		spin_unlock(&ctx->event_wqh.lock);

		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		if (no_wait) {
			ret = -EAGAIN;
			break;
		}
		spin_unlock_irq(&ctx->fd_wqh.lock);
		schedule();
		spin_lock_irq(&ctx->fd_wqh.lock);
	}
	__remove_wait_queue(&ctx->fd_wqh, &wait);
	__set_current_state(TASK_RUNNING);
	spin_unlock_irq(&ctx->fd_wqh.lock);

	if (!ret && msg->event == UFFD_EVENT_FORK) {
		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
		spin_lock_irq(&ctx->event_wqh.lock);
		if (!list_empty(&fork_event)) {
			/*
			 * The fork thread didn't abort, so we can
			 * drop the temporary refcount.
			 */
			userfaultfd_ctx_put(fork_nctx);

			uwq = list_first_entry(&fork_event,
					       typeof(*uwq),
					       wq.entry);
			/*
			 * If fork_event list wasn't empty and in turn
			 * the event wasn't already released by fork
			 * (the event is allocated on fork kernel
			 * stack), put the event back to its place in
			 * the event_wq. fork_event head will be freed
			 * as soon as we return so the event cannot
			 * stay queued there no matter the current
			 * "ret" value.
			 */
			list_del(&uwq->wq.entry);
			__add_wait_queue(&ctx->event_wqh, &uwq->wq);

			/*
			 * Leave the event in the waitqueue and report
			 * error to userland if we failed to resolve
			 * the userfault fork.
			 */
			if (likely(!ret))
				userfaultfd_event_complete(ctx, uwq);
		} else {
			/*
			 * Here the fork thread aborted and the
			 * refcount from the fork thread on fork_nctx
			 * has already been released. We still hold
			 * the reference we took before releasing the
			 * lock above. If resolve_userfault_fork
			 * failed we've to drop it because the
			 * fork_nctx has to be freed in such case. If
			 * it succeeded we'll hold it because the new
			 * uffd references it.
			 */
			if (ret)
				userfaultfd_ctx_put(fork_nctx);
		}
		spin_unlock_irq(&ctx->event_wqh.lock);
	}

	return ret;
}

static ssize_t userfaultfd_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	ssize_t _ret, ret = 0;
	struct uffd_msg msg;
	int no_wait = file->f_flags & O_NONBLOCK;

	if (ctx->state == UFFD_STATE_WAIT_API)
		return -EINVAL;

	for (;;) {
		if (count < sizeof(msg))
			return ret ? ret : -EINVAL;
		_ret = userfaultfd_ctx_read(ctx, no_wait, &msg);
		if (_ret < 0)
			return ret ? ret : _ret;
		if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
			return ret ? ret : -EFAULT;
		ret += sizeof(msg);
		buf += sizeof(msg);
		count -= sizeof(msg);
		/*
		 * Allow to read more than one fault at time but only
		 * block if waiting for the very first one.
		 */
		no_wait = O_NONBLOCK;
	}
}

static void __wake_userfault(struct userfaultfd_ctx *ctx,
			     struct userfaultfd_wake_range *range)
{
	spin_lock_irq(&ctx->fault_pending_wqh.lock);
	/* wake all in the range and autoremove */
	if (waitqueue_active(&ctx->fault_pending_wqh))
		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
				     range);
	if (waitqueue_active(&ctx->fault_wqh))
		__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range);
	spin_unlock_irq(&ctx->fault_pending_wqh.lock);
}

static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
					   struct userfaultfd_wake_range *range)
{
	unsigned seq;
	bool need_wakeup;

	/*
	 * To be sure waitqueue_active() is not reordered by the CPU
	 * before the pagetable update, use an explicit SMP memory
	 * barrier here. PT lock release or mmap_read_unlock(mm) still
	 * have release semantics that can allow the
	 * waitqueue_active() to be reordered before the pte update.
	 */
	smp_mb();

	/*
	 * Use waitqueue_active because it's very frequent to
	 * change the address space atomically even if there are no
	 * userfaults yet. So we take the spinlock only when we're
	 * sure we've userfaults to wake.
	 */
	do {
		seq = read_seqcount_begin(&ctx->refile_seq);
		need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
			waitqueue_active(&ctx->fault_wqh);
		cond_resched();
	} while (read_seqcount_retry(&ctx->refile_seq, seq));
	if (need_wakeup)
		__wake_userfault(ctx, range);
}

static __always_inline int validate_range(struct mm_struct *mm,
					  __u64 *start, __u64 len)
{
	__u64 task_size = mm->task_size;

	*start = untagged_addr(*start);

	if (*start & ~PAGE_MASK)
		return -EINVAL;
	if (len & ~PAGE_MASK)
		return -EINVAL;
	if (!len)
		return -EINVAL;
	if (*start < mmap_min_addr)
		return -EINVAL;
	if (*start >= task_size)
		return -EINVAL;
	if (len > task_size - *start)
		return -EINVAL;
	return 0;
}

static inline bool vma_can_userfault(struct vm_area_struct *vma,
				     unsigned long vm_flags)
{
	/* FIXME: add WP support to hugetlbfs and shmem */
	return vma_is_anonymous(vma) ||
		((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
		 !(vm_flags & VM_UFFD_WP));
}

static int userfaultfd_register(struct userfaultfd_ctx *ctx,
				unsigned long arg)
{
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev, *cur;
	int ret;
	struct uffdio_register uffdio_register;
	struct uffdio_register __user *user_uffdio_register;
	unsigned long vm_flags, new_flags;
	bool found;
	bool basic_ioctls;
	unsigned long start, end, vma_end;

	user_uffdio_register = (struct uffdio_register __user *) arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_register, user_uffdio_register,
			   sizeof(uffdio_register)-sizeof(__u64)))
		goto out;

	ret = -EINVAL;
	if (!uffdio_register.mode)
		goto out;
	if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
				     UFFDIO_REGISTER_MODE_WP))
		goto out;
	vm_flags = 0;
	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
		vm_flags |= VM_UFFD_MISSING;
	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
		vm_flags |= VM_UFFD_WP;

	ret = validate_range(mm, &uffdio_register.range.start,
			     uffdio_register.range.len);
	if (ret)
		goto out;

	start = uffdio_register.range.start;
	end = start + uffdio_register.range.len;

	ret = -ENOMEM;
	if (!mmget_not_zero(mm))
		goto out;

	mmap_write_lock(mm);
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
		goto out_unlock;

	/* check that there's at least one vma in the range */
	ret = -EINVAL;
	if (vma->vm_start >= end)
		goto out_unlock;

	/*
	 * If the first vma contains huge pages, make sure start address
	 * is aligned to huge page size.
	 */
	if (is_vm_hugetlb_page(vma)) {
		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);

		if (start & (vma_hpagesize - 1))
			goto out_unlock;
	}

	/*
	 * Search for not compatible vmas.
	 */
	found = false;
	basic_ioctls = false;
	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
		cond_resched();

		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));

		/* check not compatible vmas */
		ret = -EINVAL;
		if (!vma_can_userfault(cur, vm_flags))
			goto out_unlock;

		/*
		 * UFFDIO_COPY will fill file holes even without
		 * PROT_WRITE. This check enforces that if this is a
		 * MAP_SHARED, the process has write permission to the backing
		 * file. If VM_MAYWRITE is set it also enforces that on a
		 * MAP_SHARED vma: there is no F_WRITE_SEAL and no further
		 * F_WRITE_SEAL can be taken until the vma is destroyed.
		 */
		ret = -EPERM;
		if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
			goto out_unlock;

		/*
		 * If this vma contains ending address, and huge pages
		 * check alignment.
		 */
		if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
		    end > cur->vm_start) {
			unsigned long vma_hpagesize = vma_kernel_pagesize(cur);

			ret = -EINVAL;

			if (end & (vma_hpagesize - 1))
				goto out_unlock;
		}
		if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
			goto out_unlock;

		/*
		 * Check that this vma isn't already owned by a
		 * different userfaultfd. We can't allow more than one
		 * userfaultfd to own a single vma simultaneously or we
		 * wouldn't know which one to deliver the userfaults to.
		 */
		ret = -EBUSY;
		if (cur->vm_userfaultfd_ctx.ctx &&
		    cur->vm_userfaultfd_ctx.ctx != ctx)
			goto out_unlock;

		/*
		 * Note vmas containing huge pages
		 */
		if (is_vm_hugetlb_page(cur))
			basic_ioctls = true;

		found = true;
	}
	BUG_ON(!found);

	if (vma->vm_start < start)
		prev = vma;

	ret = 0;
	do {
		cond_resched();

		BUG_ON(!vma_can_userfault(vma, vm_flags));
		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
		       vma->vm_userfaultfd_ctx.ctx != ctx);
		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));

		/*
		 * Nothing to do: this vma is already registered into this
		 * userfaultfd and with the right tracking mode too.
		 */
		if (vma->vm_userfaultfd_ctx.ctx == ctx &&
		    (vma->vm_flags & vm_flags) == vm_flags)
			goto skip;

		if (vma->vm_start > start)
			start = vma->vm_start;
		vma_end = min(end, vma->vm_end);

		new_flags = (vma->vm_flags &
			     ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
		prev = vma_merge(mm, prev, start, vma_end, new_flags,
				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 ((struct vm_userfaultfd_ctx){ ctx }));
		if (prev) {
			vma = prev;
			goto next;
		}
		if (vma->vm_start < start) {
			ret = split_vma(mm, vma, start, 1);
			if (ret)
				break;
		}
		if (vma->vm_end > end) {
			ret = split_vma(mm, vma, end, 0);
			if (ret)
				break;
		}
	next:
		/*
		 * In the vma_merge() successful mprotect-like case 8:
		 * the next vma was merged into the current one and
		 * the current one has not been updated yet.
		 */
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx.ctx = ctx;

	skip:
		prev = vma;
		start = vma->vm_end;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
out_unlock:
	mmap_write_unlock(mm);
	mmput(mm);
	if (!ret) {
		__u64 ioctls_out;

		ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
		    UFFD_API_RANGE_IOCTLS;

		/*
		 * Declare the WP ioctl only if the WP mode is
		 * specified and all checks passed with the range
		 */
		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
			ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);

		/*
		 * Now that we scanned all vmas we can already tell
		 * userland which ioctls methods are guaranteed to
		 * succeed on this range.
		 */
		if (put_user(ioctls_out, &user_uffdio_register->ioctls))
			ret = -EFAULT;
	}
out:
	return ret;
}

static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
				  unsigned long arg)
{
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev, *cur;
	int ret;
	struct uffdio_range uffdio_unregister;
	unsigned long new_flags;
	bool found;
	unsigned long start, end, vma_end;
	const void __user *buf = (void __user *)arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
		goto out;

	ret = validate_range(mm, &uffdio_unregister.start,
			     uffdio_unregister.len);
	if (ret)
		goto out;

	start = uffdio_unregister.start;
	end = start + uffdio_unregister.len;

	ret = -ENOMEM;
	if (!mmget_not_zero(mm))
		goto out;

	mmap_write_lock(mm);
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
		goto out_unlock;

	/* check that there's at least one vma in the range */
	ret = -EINVAL;
	if (vma->vm_start >= end)
		goto out_unlock;

	/*
	 * If the first vma contains huge pages, make sure start address
	 * is aligned to huge page size.
	 */
	if (is_vm_hugetlb_page(vma)) {
		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);

		if (start & (vma_hpagesize - 1))
			goto out_unlock;
	}

	/*
	 * Search for not compatible vmas.
	 */
	found = false;
	ret = -EINVAL;
	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
		cond_resched();

		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));

		/*
		 * Check not compatible vmas, not strictly required
		 * here as not compatible vmas cannot have an
		 * userfaultfd_ctx registered on them, but this
		 * provides for more strict behavior to notice
		 * unregistration errors.
		 */
		if (!vma_can_userfault(cur, cur->vm_flags))
			goto out_unlock;

		found = true;
	}
	BUG_ON(!found);

	if (vma->vm_start < start)
		prev = vma;

	ret = 0;
	do {
		cond_resched();

		BUG_ON(!vma_can_userfault(vma, vma->vm_flags));

		/*
		 * Nothing to do: this vma is already registered into this
		 * userfaultfd and with the right tracking mode too.
		 */
		if (!vma->vm_userfaultfd_ctx.ctx)
			goto skip;

		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));

		if (vma->vm_start > start)
			start = vma->vm_start;
		vma_end = min(end, vma->vm_end);

		if (userfaultfd_missing(vma)) {
			/*
			 * Wake any concurrent pending userfault while
			 * we unregister, so they will not hang
			 * permanently and it avoids userland to call
			 * UFFDIO_WAKE explicitly.
			 */
			struct userfaultfd_wake_range range;
			range.start = start;
			range.len = vma_end - start;
			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
		}

		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
		prev = vma_merge(mm, prev, start, vma_end, new_flags,
				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 NULL_VM_UFFD_CTX);
		if (prev) {
			vma = prev;
			goto next;
		}
		if (vma->vm_start < start) {
			ret = split_vma(mm, vma, start, 1);
			if (ret)
				break;
		}
		if (vma->vm_end > end) {
			ret = split_vma(mm, vma, end, 0);
			if (ret)
				break;
		}
	next:
		/*
		 * In the vma_merge() successful mprotect-like case 8:
		 * the next vma was merged into the current one and
		 * the current one has not been updated yet.
		 */
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;

	skip:
		prev = vma;
		start = vma->vm_end;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
out_unlock:
	mmap_write_unlock(mm);
	mmput(mm);
out:
	return ret;
}

/*
 * userfaultfd_wake may be used in combination with the
 * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
 */
static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
			    unsigned long arg)
{
	int ret;
	struct uffdio_range uffdio_wake;
	struct userfaultfd_wake_range range;
	const void __user *buf = (void __user *)arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
		goto out;

	ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
	if (ret)
		goto out;

	range.start = uffdio_wake.start;
	range.len = uffdio_wake.len;

	/*
	 * len == 0 means wake all and we don't want to wake all here,
	 * so check it again to be sure.
	 */
	VM_BUG_ON(!range.len);

	wake_userfault(ctx, &range);
	ret = 0;

out:
	return ret;
}

static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
			    unsigned long arg)
{
	__s64 ret;
	struct uffdio_copy uffdio_copy;
	struct uffdio_copy __user *user_uffdio_copy;
	struct userfaultfd_wake_range range;

	user_uffdio_copy = (struct uffdio_copy __user *) arg;

	ret = -EAGAIN;
	if (READ_ONCE(ctx->mmap_changing))
		goto out;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
			   /* don't copy "copy" last field */
			   sizeof(uffdio_copy)-sizeof(__s64)))
		goto out;

	ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
	if (ret)
		goto out;
	/*
	 * double check for wraparound just in case. copy_from_user()
	 * will later check uffdio_copy.src + uffdio_copy.len to fit
	 * in the userland range.
	 */
	ret = -EINVAL;
	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
		goto out;
	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
		goto out;
	if (mmget_not_zero(ctx->mm)) {
		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
				   uffdio_copy.len, &ctx->mmap_changing,
				   uffdio_copy.mode);
		mmput(ctx->mm);
	} else {
		return -ESRCH;
	}
	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
		return -EFAULT;
	if (ret < 0)
		goto out;
	BUG_ON(!ret);
	/* len == 0 would wake all */
	range.len = ret;
	if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
		range.start = uffdio_copy.dst;
		wake_userfault(ctx, &range);
	}
	ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
out:
	return ret;
}

static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
				unsigned long arg)
{
	__s64 ret;
	struct uffdio_zeropage uffdio_zeropage;
	struct uffdio_zeropage __user *user_uffdio_zeropage;
	struct userfaultfd_wake_range range;

	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;

	ret = -EAGAIN;
	if (READ_ONCE(ctx->mmap_changing))
		goto out;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
			   /* don't copy "zeropage" last field */
			   sizeof(uffdio_zeropage)-sizeof(__s64)))
		goto out;

	ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
			     uffdio_zeropage.range.len);
	if (ret)
		goto out;
	ret = -EINVAL;
	if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
		goto out;

	if (mmget_not_zero(ctx->mm)) {
		ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
				     uffdio_zeropage.range.len,
				     &ctx->mmap_changing);
		mmput(ctx->mm);
	} else {
		return -ESRCH;
	}
	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
		return -EFAULT;
	if (ret < 0)
		goto out;
	/* len == 0 would wake all */
	BUG_ON(!ret);
	range.len = ret;
	if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
		range.start = uffdio_zeropage.range.start;
		wake_userfault(ctx, &range);
	}
	ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
out:
	return ret;
}

static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
				    unsigned long arg)
{
	int ret;
	struct uffdio_writeprotect uffdio_wp;
	struct uffdio_writeprotect __user *user_uffdio_wp;
	struct userfaultfd_wake_range range;
	bool mode_wp, mode_dontwake;

	if (READ_ONCE(ctx->mmap_changing))
		return -EAGAIN;

	user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;

	if (copy_from_user(&uffdio_wp, user_uffdio_wp,
			   sizeof(struct uffdio_writeprotect)))
		return -EFAULT;

	ret = validate_range(ctx->mm, &uffdio_wp.range.start,
			     uffdio_wp.range.len);
	if (ret)
		return ret;

	if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
			       UFFDIO_WRITEPROTECT_MODE_WP))
		return -EINVAL;

	mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
	mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;

	if (mode_wp && mode_dontwake)
		return -EINVAL;

	ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
				  uffdio_wp.range.len, mode_wp,
				  &ctx->mmap_changing);
	if (ret)
		return ret;

	if (!mode_wp && !mode_dontwake) {
		range.start = uffdio_wp.range.start;
		range.len = uffdio_wp.range.len;
		wake_userfault(ctx, &range);
	}
	return ret;
}

static inline unsigned int uffd_ctx_features(__u64 user_features)
{
	/*
	 * For the current set of features the bits just coincide
	 */
	return (unsigned int)user_features;
}

/*
 * userland asks for a certain API version and we return which bits
 * and ioctl commands are implemented in this kernel for such API
 * version or -EINVAL if unknown.
 */
static int userfaultfd_api(struct userfaultfd_ctx *ctx,
			   unsigned long arg)
{
	struct uffdio_api uffdio_api;
	void __user *buf = (void __user *)arg;
	int ret;
	__u64 features;

	ret = -EINVAL;
	if (ctx->state != UFFD_STATE_WAIT_API)
		goto out;
	ret = -EFAULT;
	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
		goto out;
	features = uffdio_api.features;
	ret = -EINVAL;
	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
		goto err_out;
	ret = -EPERM;
	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
		goto err_out;
	/* report all available features and ioctls to userland */
	uffdio_api.features = UFFD_API_FEATURES;
	uffdio_api.ioctls = UFFD_API_IOCTLS;
	ret = -EFAULT;
	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
		goto out;
	ctx->state = UFFD_STATE_RUNNING;
	/* only enable the requested features for this uffd context */
	ctx->features = uffd_ctx_features(features);
	ret = 0;
out:
	return ret;
err_out:
	memset(&uffdio_api, 0, sizeof(uffdio_api));
	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
		ret = -EFAULT;
	goto out;
}

static long userfaultfd_ioctl(struct file *file, unsigned cmd,
			      unsigned long arg)
{
	int ret = -EINVAL;
	struct userfaultfd_ctx *ctx = file->private_data;

	if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API)
		return -EINVAL;

	switch(cmd) {
	case UFFDIO_API:
		ret = userfaultfd_api(ctx, arg);
		break;
	case UFFDIO_REGISTER:
		ret = userfaultfd_register(ctx, arg);
		break;
	case UFFDIO_UNREGISTER:
		ret = userfaultfd_unregister(ctx, arg);
		break;
	case UFFDIO_WAKE:
		ret = userfaultfd_wake(ctx, arg);
		break;
	case UFFDIO_COPY:
		ret = userfaultfd_copy(ctx, arg);
		break;
	case UFFDIO_ZEROPAGE:
		ret = userfaultfd_zeropage(ctx, arg);
		break;
	case UFFDIO_WRITEPROTECT:
		ret = userfaultfd_writeprotect(ctx, arg);
		break;
	}
	return ret;
}

#ifdef CONFIG_PROC_FS
static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct userfaultfd_ctx *ctx = f->private_data;
	wait_queue_entry_t *wq;
	unsigned long pending = 0, total = 0;

	spin_lock_irq(&ctx->fault_pending_wqh.lock);
	list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
		pending++;
		total++;
	}
	list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
		total++;
	}
	spin_unlock_irq(&ctx->fault_pending_wqh.lock);

	/*
	 * If more protocols will be added, there will be all shown
	 * separated by a space. Like this:
	 *	protocols: aa:... bb:...
	 */
	seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
		   pending, total, UFFD_API, ctx->features,
		   UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif

static const struct file_operations userfaultfd_fops = {
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= userfaultfd_show_fdinfo,
#endif
	.release	= userfaultfd_release,
	.poll		= userfaultfd_poll,
	.read		= userfaultfd_read,
	.unlocked_ioctl = userfaultfd_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.llseek		= noop_llseek,
};

static void init_once_userfaultfd_ctx(void *mem)
{
	struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;

	init_waitqueue_head(&ctx->fault_pending_wqh);
	init_waitqueue_head(&ctx->fault_wqh);
	init_waitqueue_head(&ctx->event_wqh);
	init_waitqueue_head(&ctx->fd_wqh);
	seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
}

SYSCALL_DEFINE1(userfaultfd, int, flags)
{
	struct userfaultfd_ctx *ctx;
	int fd;

	if (!sysctl_unprivileged_userfaultfd &&
	    (flags & UFFD_USER_MODE_ONLY) == 0 &&
	    !capable(CAP_SYS_PTRACE)) {
		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
			"sysctl knob to 1 if kernel faults must be handled "
			"without obtaining CAP_SYS_PTRACE capability\n");
		return -EPERM;
	}

	BUG_ON(!current->mm);

	/* Check the UFFD_* constants for consistency.  */
	BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
	BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
	BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);

	if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
		return -EINVAL;

	ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	refcount_set(&ctx->refcount, 1);
	ctx->flags = flags;
	ctx->features = 0;
	ctx->state = UFFD_STATE_WAIT_API;
	ctx->released = false;
	ctx->mmap_changing = false;
	ctx->mm = current->mm;
	/* prevent the mm struct to be freed */
	mmgrab(ctx->mm);

	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
			      O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
	if (fd < 0) {
		mmdrop(ctx->mm);
		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
	}
	return fd;
}

static int __init userfaultfd_init(void)
{
	userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
						sizeof(struct userfaultfd_ctx),
						0,
						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
						init_once_userfaultfd_ctx);
	return 0;
}
__initcall(userfaultfd_init);