summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/vm/userfaultfd.c
blob: 2f49c9af1b582449b5e06d250ae2a9b69c0a461e (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Stress userfaultfd syscall.
 *
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 * This test allocates two virtual areas and bounces the physical
 * memory across the two virtual areas (from area_src to area_dst)
 * using userfaultfd.
 *
 * There are three threads running per CPU:
 *
 * 1) one per-CPU thread takes a per-page pthread_mutex in a random
 *    page of the area_dst (while the physical page may still be in
 *    area_src), and increments a per-page counter in the same page,
 *    and checks its value against a verification region.
 *
 * 2) another per-CPU thread handles the userfaults generated by
 *    thread 1 above. userfaultfd blocking reads or poll() modes are
 *    exercised interleaved.
 *
 * 3) one last per-CPU thread transfers the memory in the background
 *    at maximum bandwidth (if not already transferred by thread
 *    2). Each cpu thread takes cares of transferring a portion of the
 *    area.
 *
 * When all threads of type 3 completed the transfer, one bounce is
 * complete. area_src and area_dst are then swapped. All threads are
 * respawned and so the bounce is immediately restarted in the
 * opposite direction.
 *
 * per-CPU threads 1 by triggering userfaults inside
 * pthread_mutex_lock will also verify the atomicity of the memory
 * transfer (UFFDIO_COPY).
 */

#define _GNU_SOURCE
#include <stdio.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <time.h>
#include <signal.h>
#include <poll.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/wait.h>
#include <pthread.h>
#include <linux/userfaultfd.h>
#include <setjmp.h>
#include <stdbool.h>
#include <assert.h>
#include <inttypes.h>
#include <stdint.h>
#include <sys/random.h>

#include "../kselftest.h"

#ifdef __NR_userfaultfd

static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;

#define BOUNCE_RANDOM		(1<<0)
#define BOUNCE_RACINGFAULTS	(1<<1)
#define BOUNCE_VERIFY		(1<<2)
#define BOUNCE_POLL		(1<<3)
static int bounces;

#define TEST_ANON	1
#define TEST_HUGETLB	2
#define TEST_SHMEM	3
static int test_type;

/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */
#define ALARM_INTERVAL_SECS 10
static volatile bool test_uffdio_copy_eexist = true;
static volatile bool test_uffdio_zeropage_eexist = true;
/* Whether to test uffd write-protection */
static bool test_uffdio_wp = false;
/* Whether to test uffd minor faults */
static bool test_uffdio_minor = false;

static bool map_shared;
static int shm_fd;
static int huge_fd;
static char *huge_fd_off0;
static unsigned long long *count_verify;
static int uffd = -1;
static int uffd_flags, finished, *pipefd;
static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
static char *zeropage;
pthread_attr_t attr;

/* Userfaultfd test statistics */
struct uffd_stats {
	int cpu;
	unsigned long missing_faults;
	unsigned long wp_faults;
	unsigned long minor_faults;
};

/* pthread_mutex_t starts at page offset 0 */
#define area_mutex(___area, ___nr)					\
	((pthread_mutex_t *) ((___area) + (___nr)*page_size))
/*
 * count is placed in the page after pthread_mutex_t naturally aligned
 * to avoid non alignment faults on non-x86 archs.
 */
#define area_count(___area, ___nr)					\
	((volatile unsigned long long *) ((unsigned long)		\
				 ((___area) + (___nr)*page_size +	\
				  sizeof(pthread_mutex_t) +		\
				  sizeof(unsigned long long) - 1) &	\
				 ~(unsigned long)(sizeof(unsigned long long) \
						  -  1)))

const char *examples =
    "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
    "./userfaultfd anon 100 99999\n\n"
    "# Run share memory test on 1GiB region with 99 bounces:\n"
    "./userfaultfd shmem 1000 99\n\n"
    "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n"
    "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n"
    "# Run the same hugetlb test but using shmem:\n"
    "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n"
    "# 10MiB-~6GiB 999 bounces anonymous test, "
    "continue forever unless an error triggers\n"
    "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n";

static void usage(void)
{
	fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces> "
		"[hugetlbfs_file]\n\n");
	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
		"hugetlb_shared, shmem\n\n");
	fprintf(stderr, "Examples:\n\n");
	fprintf(stderr, "%s", examples);
	exit(1);
}

#define _err(fmt, ...)						\
	do {							\
		int ret = errno;				\
		fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__);	\
		fprintf(stderr, " (errno=%d, line=%d)\n",	\
			ret, __LINE__);				\
	} while (0)

#define err(fmt, ...)				\
	do {					\
		_err(fmt, ##__VA_ARGS__);	\
		exit(1);			\
	} while (0)

static void uffd_stats_reset(struct uffd_stats *uffd_stats,
			     unsigned long n_cpus)
{
	int i;

	for (i = 0; i < n_cpus; i++) {
		uffd_stats[i].cpu = i;
		uffd_stats[i].missing_faults = 0;
		uffd_stats[i].wp_faults = 0;
		uffd_stats[i].minor_faults = 0;
	}
}

static void uffd_stats_report(struct uffd_stats *stats, int n_cpus)
{
	int i;
	unsigned long long miss_total = 0, wp_total = 0, minor_total = 0;

	for (i = 0; i < n_cpus; i++) {
		miss_total += stats[i].missing_faults;
		wp_total += stats[i].wp_faults;
		minor_total += stats[i].minor_faults;
	}

	printf("userfaults: ");
	if (miss_total) {
		printf("%llu missing (", miss_total);
		for (i = 0; i < n_cpus; i++)
			printf("%lu+", stats[i].missing_faults);
		printf("\b) ");
	}
	if (wp_total) {
		printf("%llu wp (", wp_total);
		for (i = 0; i < n_cpus; i++)
			printf("%lu+", stats[i].wp_faults);
		printf("\b) ");
	}
	if (minor_total) {
		printf("%llu minor (", minor_total);
		for (i = 0; i < n_cpus; i++)
			printf("%lu+", stats[i].minor_faults);
		printf("\b)");
	}
	printf("\n");
}

static void anon_release_pages(char *rel_area)
{
	if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED))
		err("madvise(MADV_DONTNEED) failed");
}

static void anon_allocate_area(void **alloc_area)
{
	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
			   MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
	if (*alloc_area == MAP_FAILED)
		err("mmap of anonymous memory failed");
}

static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
{
}

static void hugetlb_release_pages(char *rel_area)
{
	if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
		      rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
		      nr_pages * page_size))
		err("fallocate() failed");
}

static void hugetlb_allocate_area(void **alloc_area)
{
	void *area_alias = NULL;
	char **alloc_area_alias;

	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
			   (map_shared ? MAP_SHARED : MAP_PRIVATE) |
			   MAP_HUGETLB |
			   (*alloc_area == area_src ? 0 : MAP_NORESERVE),
			   huge_fd, *alloc_area == area_src ? 0 :
			   nr_pages * page_size);
	if (*alloc_area == MAP_FAILED)
		err("mmap of hugetlbfs file failed");

	if (map_shared) {
		area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
				  MAP_SHARED | MAP_HUGETLB,
				  huge_fd, *alloc_area == area_src ? 0 :
				  nr_pages * page_size);
		if (area_alias == MAP_FAILED)
			err("mmap of hugetlb file alias failed");
	}

	if (*alloc_area == area_src) {
		huge_fd_off0 = *alloc_area;
		alloc_area_alias = &area_src_alias;
	} else {
		alloc_area_alias = &area_dst_alias;
	}
	if (area_alias)
		*alloc_area_alias = area_alias;
}

static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
{
	if (!map_shared)
		return;
	/*
	 * We can't zap just the pagetable with hugetlbfs because
	 * MADV_DONTEED won't work. So exercise -EEXIST on a alias
	 * mapping where the pagetables are not established initially,
	 * this way we'll exercise the -EEXEC at the fs level.
	 */
	*start = (unsigned long) area_dst_alias + offset;
}

static void shmem_release_pages(char *rel_area)
{
	if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE))
		err("madvise(MADV_REMOVE) failed");
}

static void shmem_allocate_area(void **alloc_area)
{
	void *area_alias = NULL;
	bool is_src = alloc_area == (void **)&area_src;
	unsigned long offset = is_src ? 0 : nr_pages * page_size;

	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
			   MAP_SHARED, shm_fd, offset);
	if (*alloc_area == MAP_FAILED)
		err("mmap of memfd failed");

	area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
			  MAP_SHARED, shm_fd, offset);
	if (area_alias == MAP_FAILED)
		err("mmap of memfd alias failed");

	if (is_src)
		area_src_alias = area_alias;
	else
		area_dst_alias = area_alias;
}

static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset)
{
	*start = (unsigned long)area_dst_alias + offset;
}

struct uffd_test_ops {
	void (*allocate_area)(void **alloc_area);
	void (*release_pages)(char *rel_area);
	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
};

static struct uffd_test_ops anon_uffd_test_ops = {
	.allocate_area	= anon_allocate_area,
	.release_pages	= anon_release_pages,
	.alias_mapping = noop_alias_mapping,
};

static struct uffd_test_ops shmem_uffd_test_ops = {
	.allocate_area	= shmem_allocate_area,
	.release_pages	= shmem_release_pages,
	.alias_mapping = shmem_alias_mapping,
};

static struct uffd_test_ops hugetlb_uffd_test_ops = {
	.allocate_area	= hugetlb_allocate_area,
	.release_pages	= hugetlb_release_pages,
	.alias_mapping = hugetlb_alias_mapping,
};

static struct uffd_test_ops *uffd_test_ops;

static inline uint64_t uffd_minor_feature(void)
{
	if (test_type == TEST_HUGETLB && map_shared)
		return UFFD_FEATURE_MINOR_HUGETLBFS;
	else if (test_type == TEST_SHMEM)
		return UFFD_FEATURE_MINOR_SHMEM;
	else
		return 0;
}

static uint64_t get_expected_ioctls(uint64_t mode)
{
	uint64_t ioctls = UFFD_API_RANGE_IOCTLS;

	if (test_type == TEST_HUGETLB)
		ioctls &= ~(1 << _UFFDIO_ZEROPAGE);

	if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp))
		ioctls &= ~(1 << _UFFDIO_WRITEPROTECT);

	if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor))
		ioctls &= ~(1 << _UFFDIO_CONTINUE);

	return ioctls;
}

static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls)
{
	uint64_t expected = get_expected_ioctls(mode);
	uint64_t actual = ioctls & expected;

	if (actual != expected) {
		err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64,
		    expected, actual);
	}
}

static void userfaultfd_open(uint64_t *features)
{
	struct uffdio_api uffdio_api;

	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
	if (uffd < 0)
		err("userfaultfd syscall not available in this kernel");
	uffd_flags = fcntl(uffd, F_GETFD, NULL);

	uffdio_api.api = UFFD_API;
	uffdio_api.features = *features;
	if (ioctl(uffd, UFFDIO_API, &uffdio_api))
		err("UFFDIO_API failed.\nPlease make sure to "
		    "run with either root or ptrace capability.");
	if (uffdio_api.api != UFFD_API)
		err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api);

	*features = uffdio_api.features;
}

static inline void munmap_area(void **area)
{
	if (*area)
		if (munmap(*area, nr_pages * page_size))
			err("munmap");

	*area = NULL;
}

static void uffd_test_ctx_clear(void)
{
	size_t i;

	if (pipefd) {
		for (i = 0; i < nr_cpus * 2; ++i) {
			if (close(pipefd[i]))
				err("close pipefd");
		}
		free(pipefd);
		pipefd = NULL;
	}

	if (count_verify) {
		free(count_verify);
		count_verify = NULL;
	}

	if (uffd != -1) {
		if (close(uffd))
			err("close uffd");
		uffd = -1;
	}

	huge_fd_off0 = NULL;
	munmap_area((void **)&area_src);
	munmap_area((void **)&area_src_alias);
	munmap_area((void **)&area_dst);
	munmap_area((void **)&area_dst_alias);
}

static void uffd_test_ctx_init(uint64_t features)
{
	unsigned long nr, cpu;

	uffd_test_ctx_clear();

	uffd_test_ops->allocate_area((void **)&area_src);
	uffd_test_ops->allocate_area((void **)&area_dst);

	userfaultfd_open(&features);

	count_verify = malloc(nr_pages * sizeof(unsigned long long));
	if (!count_verify)
		err("count_verify");

	for (nr = 0; nr < nr_pages; nr++) {
		*area_mutex(area_src, nr) =
			(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER;
		count_verify[nr] = *area_count(area_src, nr) = 1;
		/*
		 * In the transition between 255 to 256, powerpc will
		 * read out of order in my_bcmp and see both bytes as
		 * zero, so leave a placeholder below always non-zero
		 * after the count, to avoid my_bcmp to trigger false
		 * positives.
		 */
		*(area_count(area_src, nr) + 1) = 1;
	}

	/*
	 * After initialization of area_src, we must explicitly release pages
	 * for area_dst to make sure it's fully empty.  Otherwise we could have
	 * some area_dst pages be errornously initialized with zero pages,
	 * hence we could hit memory corruption later in the test.
	 *
	 * One example is when THP is globally enabled, above allocate_area()
	 * calls could have the two areas merged into a single VMA (as they
	 * will have the same VMA flags so they're mergeable).  When we
	 * initialize the area_src above, it's possible that some part of
	 * area_dst could have been faulted in via one huge THP that will be
	 * shared between area_src and area_dst.  It could cause some of the
	 * area_dst won't be trapped by missing userfaults.
	 *
	 * This release_pages() will guarantee even if that happened, we'll
	 * proactively split the thp and drop any accidentally initialized
	 * pages within area_dst.
	 */
	uffd_test_ops->release_pages(area_dst);

	pipefd = malloc(sizeof(int) * nr_cpus * 2);
	if (!pipefd)
		err("pipefd");
	for (cpu = 0; cpu < nr_cpus; cpu++)
		if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
			err("pipe");
}

static int my_bcmp(char *str1, char *str2, size_t n)
{
	unsigned long i;
	for (i = 0; i < n; i++)
		if (str1[i] != str2[i])
			return 1;
	return 0;
}

static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
{
	struct uffdio_writeprotect prms;

	/* Write protection page faults */
	prms.range.start = start;
	prms.range.len = len;
	/* Undo write-protect, do wakeup after that */
	prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;

	if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms))
		err("clear WP failed: address=0x%"PRIx64, (uint64_t)start);
}

static void continue_range(int ufd, __u64 start, __u64 len)
{
	struct uffdio_continue req;
	int ret;

	req.range.start = start;
	req.range.len = len;
	req.mode = 0;

	if (ioctl(ufd, UFFDIO_CONTINUE, &req))
		err("UFFDIO_CONTINUE failed for address 0x%" PRIx64,
		    (uint64_t)start);

	/*
	 * Error handling within the kernel for continue is subtly different
	 * from copy or zeropage, so it may be a source of bugs. Trigger an
	 * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG.
	 */
	req.mapped = 0;
	ret = ioctl(ufd, UFFDIO_CONTINUE, &req);
	if (ret >= 0 || req.mapped != -EEXIST)
		err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64,
		    ret, (int64_t) req.mapped);
}

static void *locking_thread(void *arg)
{
	unsigned long cpu = (unsigned long) arg;
	unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
	unsigned long long count;

	if (!(bounces & BOUNCE_RANDOM)) {
		page_nr = -bounces;
		if (!(bounces & BOUNCE_RACINGFAULTS))
			page_nr += cpu * nr_pages_per_cpu;
	}

	while (!finished) {
		if (bounces & BOUNCE_RANDOM) {
			if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr))
				err("getrandom failed");
		} else
			page_nr += 1;
		page_nr %= nr_pages;
		pthread_mutex_lock(area_mutex(area_dst, page_nr));
		count = *area_count(area_dst, page_nr);
		if (count != count_verify[page_nr])
			err("page_nr %lu memory corruption %llu %llu",
			    page_nr, count, count_verify[page_nr]);
		count++;
		*area_count(area_dst, page_nr) = count_verify[page_nr] = count;
		pthread_mutex_unlock(area_mutex(area_dst, page_nr));
	}

	return NULL;
}

static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
			    unsigned long offset)
{
	uffd_test_ops->alias_mapping(&uffdio_copy->dst,
				     uffdio_copy->len,
				     offset);
	if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
		/* real retval in ufdio_copy.copy */
		if (uffdio_copy->copy != -EEXIST)
			err("UFFDIO_COPY retry error: %"PRId64,
			    (int64_t)uffdio_copy->copy);
	} else {
		err("UFFDIO_COPY retry unexpected: %"PRId64,
		    (int64_t)uffdio_copy->copy);
	}
}

static void wake_range(int ufd, unsigned long addr, unsigned long len)
{
	struct uffdio_range uffdio_wake;

	uffdio_wake.start = addr;
	uffdio_wake.len = len;

	if (ioctl(ufd, UFFDIO_WAKE, &uffdio_wake))
		fprintf(stderr, "error waking %lu\n",
			addr), exit(1);
}

static int __copy_page(int ufd, unsigned long offset, bool retry)
{
	struct uffdio_copy uffdio_copy;

	if (offset >= nr_pages * page_size)
		err("unexpected offset %lu\n", offset);
	uffdio_copy.dst = (unsigned long) area_dst + offset;
	uffdio_copy.src = (unsigned long) area_src + offset;
	uffdio_copy.len = page_size;
	if (test_uffdio_wp)
		uffdio_copy.mode = UFFDIO_COPY_MODE_WP;
	else
		uffdio_copy.mode = 0;
	uffdio_copy.copy = 0;
	if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
		/* real retval in ufdio_copy.copy */
		if (uffdio_copy.copy != -EEXIST)
			err("UFFDIO_COPY error: %"PRId64,
			    (int64_t)uffdio_copy.copy);
		wake_range(ufd, uffdio_copy.dst, page_size);
	} else if (uffdio_copy.copy != page_size) {
		err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy);
	} else {
		if (test_uffdio_copy_eexist && retry) {
			test_uffdio_copy_eexist = false;
			retry_copy_page(ufd, &uffdio_copy, offset);
		}
		return 1;
	}
	return 0;
}

static int copy_page_retry(int ufd, unsigned long offset)
{
	return __copy_page(ufd, offset, true);
}

static int copy_page(int ufd, unsigned long offset)
{
	return __copy_page(ufd, offset, false);
}

static int uffd_read_msg(int ufd, struct uffd_msg *msg)
{
	int ret = read(uffd, msg, sizeof(*msg));

	if (ret != sizeof(*msg)) {
		if (ret < 0) {
			if (errno == EAGAIN || errno == EINTR)
				return 1;
			err("blocking read error");
		} else {
			err("short read");
		}
	}

	return 0;
}

static void uffd_handle_page_fault(struct uffd_msg *msg,
				   struct uffd_stats *stats)
{
	unsigned long offset;

	if (msg->event != UFFD_EVENT_PAGEFAULT)
		err("unexpected msg event %u", msg->event);

	if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) {
		/* Write protect page faults */
		wp_range(uffd, msg->arg.pagefault.address, page_size, false);
		stats->wp_faults++;
	} else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) {
		uint8_t *area;
		int b;

		/*
		 * Minor page faults
		 *
		 * To prove we can modify the original range for testing
		 * purposes, we're going to bit flip this range before
		 * continuing.
		 *
		 * Note that this requires all minor page fault tests operate on
		 * area_dst (non-UFFD-registered) and area_dst_alias
		 * (UFFD-registered).
		 */

		area = (uint8_t *)(area_dst +
				   ((char *)msg->arg.pagefault.address -
				    area_dst_alias));
		for (b = 0; b < page_size; ++b)
			area[b] = ~area[b];
		continue_range(uffd, msg->arg.pagefault.address, page_size);
		stats->minor_faults++;
	} else {
		/* Missing page faults */
		if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
			err("unexpected write fault");

		offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
		offset &= ~(page_size-1);

		if (copy_page(uffd, offset))
			stats->missing_faults++;
	}
}

static void *uffd_poll_thread(void *arg)
{
	struct uffd_stats *stats = (struct uffd_stats *)arg;
	unsigned long cpu = stats->cpu;
	struct pollfd pollfd[2];
	struct uffd_msg msg;
	struct uffdio_register uffd_reg;
	int ret;
	char tmp_chr;

	pollfd[0].fd = uffd;
	pollfd[0].events = POLLIN;
	pollfd[1].fd = pipefd[cpu*2];
	pollfd[1].events = POLLIN;

	for (;;) {
		ret = poll(pollfd, 2, -1);
		if (ret <= 0) {
			if (errno == EINTR || errno == EAGAIN)
				continue;
			err("poll error: %d", ret);
		}
		if (pollfd[1].revents & POLLIN) {
			if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
				err("read pipefd error");
			break;
		}
		if (!(pollfd[0].revents & POLLIN))
			err("pollfd[0].revents %d", pollfd[0].revents);
		if (uffd_read_msg(uffd, &msg))
			continue;
		switch (msg.event) {
		default:
			err("unexpected msg event %u\n", msg.event);
			break;
		case UFFD_EVENT_PAGEFAULT:
			uffd_handle_page_fault(&msg, stats);
			break;
		case UFFD_EVENT_FORK:
			close(uffd);
			uffd = msg.arg.fork.ufd;
			pollfd[0].fd = uffd;
			break;
		case UFFD_EVENT_REMOVE:
			uffd_reg.range.start = msg.arg.remove.start;
			uffd_reg.range.len = msg.arg.remove.end -
				msg.arg.remove.start;
			if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
				err("remove failure");
			break;
		case UFFD_EVENT_REMAP:
			area_dst = (char *)(unsigned long)msg.arg.remap.to;
			break;
		}
	}

	return NULL;
}

pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;

static void *uffd_read_thread(void *arg)
{
	struct uffd_stats *stats = (struct uffd_stats *)arg;
	struct uffd_msg msg;

	pthread_mutex_unlock(&uffd_read_mutex);
	/* from here cancellation is ok */

	for (;;) {
		if (uffd_read_msg(uffd, &msg))
			continue;
		uffd_handle_page_fault(&msg, stats);
	}

	return NULL;
}

static void *background_thread(void *arg)
{
	unsigned long cpu = (unsigned long) arg;
	unsigned long page_nr, start_nr, mid_nr, end_nr;

	start_nr = cpu * nr_pages_per_cpu;
	end_nr = (cpu+1) * nr_pages_per_cpu;
	mid_nr = (start_nr + end_nr) / 2;

	/* Copy the first half of the pages */
	for (page_nr = start_nr; page_nr < mid_nr; page_nr++)
		copy_page_retry(uffd, page_nr * page_size);

	/*
	 * If we need to test uffd-wp, set it up now.  Then we'll have
	 * at least the first half of the pages mapped already which
	 * can be write-protected for testing
	 */
	if (test_uffdio_wp)
		wp_range(uffd, (unsigned long)area_dst + start_nr * page_size,
			nr_pages_per_cpu * page_size, true);

	/*
	 * Continue the 2nd half of the page copying, handling write
	 * protection faults if any
	 */
	for (page_nr = mid_nr; page_nr < end_nr; page_nr++)
		copy_page_retry(uffd, page_nr * page_size);

	return NULL;
}

static int stress(struct uffd_stats *uffd_stats)
{
	unsigned long cpu;
	pthread_t locking_threads[nr_cpus];
	pthread_t uffd_threads[nr_cpus];
	pthread_t background_threads[nr_cpus];

	finished = 0;
	for (cpu = 0; cpu < nr_cpus; cpu++) {
		if (pthread_create(&locking_threads[cpu], &attr,
				   locking_thread, (void *)cpu))
			return 1;
		if (bounces & BOUNCE_POLL) {
			if (pthread_create(&uffd_threads[cpu], &attr,
					   uffd_poll_thread,
					   (void *)&uffd_stats[cpu]))
				return 1;
		} else {
			if (pthread_create(&uffd_threads[cpu], &attr,
					   uffd_read_thread,
					   (void *)&uffd_stats[cpu]))
				return 1;
			pthread_mutex_lock(&uffd_read_mutex);
		}
		if (pthread_create(&background_threads[cpu], &attr,
				   background_thread, (void *)cpu))
			return 1;
	}
	for (cpu = 0; cpu < nr_cpus; cpu++)
		if (pthread_join(background_threads[cpu], NULL))
			return 1;

	/*
	 * Be strict and immediately zap area_src, the whole area has
	 * been transferred already by the background treads. The
	 * area_src could then be faulted in in a racy way by still
	 * running uffdio_threads reading zeropages after we zapped
	 * area_src (but they're guaranteed to get -EEXIST from
	 * UFFDIO_COPY without writing zero pages into area_dst
	 * because the background threads already completed).
	 */
	uffd_test_ops->release_pages(area_src);

	finished = 1;
	for (cpu = 0; cpu < nr_cpus; cpu++)
		if (pthread_join(locking_threads[cpu], NULL))
			return 1;

	for (cpu = 0; cpu < nr_cpus; cpu++) {
		char c;
		if (bounces & BOUNCE_POLL) {
			if (write(pipefd[cpu*2+1], &c, 1) != 1)
				err("pipefd write error");
			if (pthread_join(uffd_threads[cpu],
					 (void *)&uffd_stats[cpu]))
				return 1;
		} else {
			if (pthread_cancel(uffd_threads[cpu]))
				return 1;
			if (pthread_join(uffd_threads[cpu], NULL))
				return 1;
		}
	}

	return 0;
}

sigjmp_buf jbuf, *sigbuf;

static void sighndl(int sig, siginfo_t *siginfo, void *ptr)
{
	if (sig == SIGBUS) {
		if (sigbuf)
			siglongjmp(*sigbuf, 1);
		abort();
	}
}

/*
 * For non-cooperative userfaultfd test we fork() a process that will
 * generate pagefaults, will mremap the area monitored by the
 * userfaultfd and at last this process will release the monitored
 * area.
 * For the anonymous and shared memory the area is divided into two
 * parts, the first part is accessed before mremap, and the second
 * part is accessed after mremap. Since hugetlbfs does not support
 * mremap, the entire monitored area is accessed in a single pass for
 * HUGETLB_TEST.
 * The release of the pages currently generates event for shmem and
 * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked
 * for hugetlb.
 * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register
 * monitored area, generate pagefaults and test that signal is delivered.
 * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2
 * test robustness use case - we release monitored area, fork a process
 * that will generate pagefaults and verify signal is generated.
 * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal
 * feature. Using monitor thread, verify no userfault events are generated.
 */
static int faulting_process(int signal_test)
{
	unsigned long nr;
	unsigned long long count;
	unsigned long split_nr_pages;
	unsigned long lastnr;
	struct sigaction act;
	unsigned long signalled = 0;

	if (test_type != TEST_HUGETLB)
		split_nr_pages = (nr_pages + 1) / 2;
	else
		split_nr_pages = nr_pages;

	if (signal_test) {
		sigbuf = &jbuf;
		memset(&act, 0, sizeof(act));
		act.sa_sigaction = sighndl;
		act.sa_flags = SA_SIGINFO;
		if (sigaction(SIGBUS, &act, 0))
			err("sigaction");
		lastnr = (unsigned long)-1;
	}

	for (nr = 0; nr < split_nr_pages; nr++) {
		int steps = 1;
		unsigned long offset = nr * page_size;

		if (signal_test) {
			if (sigsetjmp(*sigbuf, 1) != 0) {
				if (steps == 1 && nr == lastnr)
					err("Signal repeated");

				lastnr = nr;
				if (signal_test == 1) {
					if (steps == 1) {
						/* This is a MISSING request */
						steps++;
						if (copy_page(uffd, offset))
							signalled++;
					} else {
						/* This is a WP request */
						assert(steps == 2);
						wp_range(uffd,
							 (__u64)area_dst +
							 offset,
							 page_size, false);
					}
				} else {
					signalled++;
					continue;
				}
			}
		}

		count = *area_count(area_dst, nr);
		if (count != count_verify[nr])
			err("nr %lu memory corruption %llu %llu\n",
			    nr, count, count_verify[nr]);
		/*
		 * Trigger write protection if there is by writing
		 * the same value back.
		 */
		*area_count(area_dst, nr) = count;
	}

	if (signal_test)
		return signalled != split_nr_pages;

	if (test_type == TEST_HUGETLB)
		return 0;

	area_dst = mremap(area_dst, nr_pages * page_size,  nr_pages * page_size,
			  MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
	if (area_dst == MAP_FAILED)
		err("mremap");
	/* Reset area_src since we just clobbered it */
	area_src = NULL;

	for (; nr < nr_pages; nr++) {
		count = *area_count(area_dst, nr);
		if (count != count_verify[nr]) {
			err("nr %lu memory corruption %llu %llu\n",
			    nr, count, count_verify[nr]);
		}
		/*
		 * Trigger write protection if there is by writing
		 * the same value back.
		 */
		*area_count(area_dst, nr) = count;
	}

	uffd_test_ops->release_pages(area_dst);

	for (nr = 0; nr < nr_pages; nr++)
		if (my_bcmp(area_dst + nr * page_size, zeropage, page_size))
			err("nr %lu is not zero", nr);

	return 0;
}

static void retry_uffdio_zeropage(int ufd,
				  struct uffdio_zeropage *uffdio_zeropage,
				  unsigned long offset)
{
	uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start,
				     uffdio_zeropage->range.len,
				     offset);
	if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
		if (uffdio_zeropage->zeropage != -EEXIST)
			err("UFFDIO_ZEROPAGE error: %"PRId64,
			    (int64_t)uffdio_zeropage->zeropage);
	} else {
		err("UFFDIO_ZEROPAGE error: %"PRId64,
		    (int64_t)uffdio_zeropage->zeropage);
	}
}

static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
{
	struct uffdio_zeropage uffdio_zeropage;
	int ret;
	bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE);
	__s64 res;

	if (offset >= nr_pages * page_size)
		err("unexpected offset %lu", offset);
	uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
	uffdio_zeropage.range.len = page_size;
	uffdio_zeropage.mode = 0;
	ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
	res = uffdio_zeropage.zeropage;
	if (ret) {
		/* real retval in ufdio_zeropage.zeropage */
		if (has_zeropage)
			err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res);
		else if (res != -EINVAL)
			err("UFFDIO_ZEROPAGE not -EINVAL");
	} else if (has_zeropage) {
		if (res != page_size) {
			err("UFFDIO_ZEROPAGE unexpected size");
		} else {
			if (test_uffdio_zeropage_eexist && retry) {
				test_uffdio_zeropage_eexist = false;
				retry_uffdio_zeropage(ufd, &uffdio_zeropage,
						      offset);
			}
			return 1;
		}
	} else
		err("UFFDIO_ZEROPAGE succeeded");

	return 0;
}

static int uffdio_zeropage(int ufd, unsigned long offset)
{
	return __uffdio_zeropage(ufd, offset, false);
}

/* exercise UFFDIO_ZEROPAGE */
static int userfaultfd_zeropage_test(void)
{
	struct uffdio_register uffdio_register;

	printf("testing UFFDIO_ZEROPAGE: ");
	fflush(stdout);

	uffd_test_ctx_init(0);

	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
	if (test_uffdio_wp)
		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		err("register failure");

	assert_expected_ioctls_present(
		uffdio_register.mode, uffdio_register.ioctls);

	if (uffdio_zeropage(uffd, 0))
		if (my_bcmp(area_dst, zeropage, page_size))
			err("zeropage is not zero");

	printf("done.\n");
	return 0;
}

static int userfaultfd_events_test(void)
{
	struct uffdio_register uffdio_register;
	pthread_t uffd_mon;
	int err, features;
	pid_t pid;
	char c;
	struct uffd_stats stats = { 0 };

	printf("testing events (fork, remap, remove): ");
	fflush(stdout);

	features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
		UFFD_FEATURE_EVENT_REMOVE;
	uffd_test_ctx_init(features);

	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);

	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
	if (test_uffdio_wp)
		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		err("register failure");

	assert_expected_ioctls_present(
		uffdio_register.mode, uffdio_register.ioctls);

	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
		err("uffd_poll_thread create");

	pid = fork();
	if (pid < 0)
		err("fork");

	if (!pid)
		exit(faulting_process(0));

	waitpid(pid, &err, 0);
	if (err)
		err("faulting process failed");
	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
		err("pipe write");
	if (pthread_join(uffd_mon, NULL))
		return 1;

	uffd_stats_report(&stats, 1);

	return stats.missing_faults != nr_pages;
}

static int userfaultfd_sig_test(void)
{
	struct uffdio_register uffdio_register;
	unsigned long userfaults;
	pthread_t uffd_mon;
	int err, features;
	pid_t pid;
	char c;
	struct uffd_stats stats = { 0 };

	printf("testing signal delivery: ");
	fflush(stdout);

	features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
	uffd_test_ctx_init(features);

	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);

	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
	if (test_uffdio_wp)
		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		err("register failure");

	assert_expected_ioctls_present(
		uffdio_register.mode, uffdio_register.ioctls);

	if (faulting_process(1))
		err("faulting process failed");

	uffd_test_ops->release_pages(area_dst);

	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
		err("uffd_poll_thread create");

	pid = fork();
	if (pid < 0)
		err("fork");

	if (!pid)
		exit(faulting_process(2));

	waitpid(pid, &err, 0);
	if (err)
		err("faulting process failed");
	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
		err("pipe write");
	if (pthread_join(uffd_mon, (void **)&userfaults))
		return 1;

	printf("done.\n");
	if (userfaults)
		err("Signal test failed, userfaults: %ld", userfaults);

	return userfaults != 0;
}

static int userfaultfd_minor_test(void)
{
	struct uffdio_register uffdio_register;
	unsigned long p;
	pthread_t uffd_mon;
	uint8_t expected_byte;
	void *expected_page;
	char c;
	struct uffd_stats stats = { 0 };

	if (!test_uffdio_minor)
		return 0;

	printf("testing minor faults: ");
	fflush(stdout);

	uffd_test_ctx_init(uffd_minor_feature());

	uffdio_register.range.start = (unsigned long)area_dst_alias;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		err("register failure");

	assert_expected_ioctls_present(
		uffdio_register.mode, uffdio_register.ioctls);

	/*
	 * After registering with UFFD, populate the non-UFFD-registered side of
	 * the shared mapping. This should *not* trigger any UFFD minor faults.
	 */
	for (p = 0; p < nr_pages; ++p) {
		memset(area_dst + (p * page_size), p % ((uint8_t)-1),
		       page_size);
	}

	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
		err("uffd_poll_thread create");

	/*
	 * Read each of the pages back using the UFFD-registered mapping. We
	 * expect that the first time we touch a page, it will result in a minor
	 * fault. uffd_poll_thread will resolve the fault by bit-flipping the
	 * page's contents, and then issuing a CONTINUE ioctl.
	 */

	if (posix_memalign(&expected_page, page_size, page_size))
		err("out of memory");

	for (p = 0; p < nr_pages; ++p) {
		expected_byte = ~((uint8_t)(p % ((uint8_t)-1)));
		memset(expected_page, expected_byte, page_size);
		if (my_bcmp(expected_page, area_dst_alias + (p * page_size),
			    page_size))
			err("unexpected page contents after minor fault");
	}

	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
		err("pipe write");
	if (pthread_join(uffd_mon, NULL))
		return 1;

	uffd_stats_report(&stats, 1);

	return stats.missing_faults != 0 || stats.minor_faults != nr_pages;
}

#define BIT_ULL(nr)                   (1ULL << (nr))
#define PM_SOFT_DIRTY                 BIT_ULL(55)
#define PM_MMAP_EXCLUSIVE             BIT_ULL(56)
#define PM_UFFD_WP                    BIT_ULL(57)
#define PM_FILE                       BIT_ULL(61)
#define PM_SWAP                       BIT_ULL(62)
#define PM_PRESENT                    BIT_ULL(63)

static int pagemap_open(void)
{
	int fd = open("/proc/self/pagemap", O_RDONLY);

	if (fd < 0)
		err("open pagemap");

	return fd;
}

static uint64_t pagemap_read_vaddr(int fd, void *vaddr)
{
	uint64_t value;
	int ret;

	ret = pread(fd, &value, sizeof(uint64_t),
		    ((uint64_t)vaddr >> 12) * sizeof(uint64_t));
	if (ret != sizeof(uint64_t))
		err("pread() on pagemap failed");

	return value;
}

/* This macro let __LINE__ works in err() */
#define  pagemap_check_wp(value, wp) do {				\
		if (!!(value & PM_UFFD_WP) != wp)			\
			err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \
	} while (0)

static int pagemap_test_fork(bool present)
{
	pid_t child = fork();
	uint64_t value;
	int fd, result;

	if (!child) {
		/* Open the pagemap fd of the child itself */
		fd = pagemap_open();
		value = pagemap_read_vaddr(fd, area_dst);
		/*
		 * After fork() uffd-wp bit should be gone as long as we're
		 * without UFFD_FEATURE_EVENT_FORK
		 */
		pagemap_check_wp(value, false);
		/* Succeed */
		exit(0);
	}
	waitpid(child, &result, 0);
	return result;
}

static void userfaultfd_pagemap_test(unsigned int test_pgsize)
{
	struct uffdio_register uffdio_register;
	int pagemap_fd;
	uint64_t value;

	/* Pagemap tests uffd-wp only */
	if (!test_uffdio_wp)
		return;

	/* Not enough memory to test this page size */
	if (test_pgsize > nr_pages * page_size)
		return;

	printf("testing uffd-wp with pagemap (pgsize=%u): ", test_pgsize);
	/* Flush so it doesn't flush twice in parent/child later */
	fflush(stdout);

	uffd_test_ctx_init(0);

	if (test_pgsize > page_size) {
		/* This is a thp test */
		if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE))
			err("madvise(MADV_HUGEPAGE) failed");
	} else if (test_pgsize == page_size) {
		/* This is normal page test; force no thp */
		if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE))
			err("madvise(MADV_NOHUGEPAGE) failed");
	}

	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		err("register failed");

	pagemap_fd = pagemap_open();

	/* Touch the page */
	*area_dst = 1;
	wp_range(uffd, (uint64_t)area_dst, test_pgsize, true);
	value = pagemap_read_vaddr(pagemap_fd, area_dst);
	pagemap_check_wp(value, true);
	/* Make sure uffd-wp bit dropped when fork */
	if (pagemap_test_fork(true))
		err("Detected stall uffd-wp bit in child");

	/* Exclusive required or PAGEOUT won't work */
	if (!(value & PM_MMAP_EXCLUSIVE))
		err("multiple mapping detected: 0x%"PRIx64, value);

	if (madvise(area_dst, test_pgsize, MADV_PAGEOUT))
		err("madvise(MADV_PAGEOUT) failed");

	/* Uffd-wp should persist even swapped out */
	value = pagemap_read_vaddr(pagemap_fd, area_dst);
	pagemap_check_wp(value, true);
	/* Make sure uffd-wp bit dropped when fork */
	if (pagemap_test_fork(false))
		err("Detected stall uffd-wp bit in child");

	/* Unprotect; this tests swap pte modifications */
	wp_range(uffd, (uint64_t)area_dst, page_size, false);
	value = pagemap_read_vaddr(pagemap_fd, area_dst);
	pagemap_check_wp(value, false);

	/* Fault in the page from disk */
	*area_dst = 2;
	value = pagemap_read_vaddr(pagemap_fd, area_dst);
	pagemap_check_wp(value, false);

	close(pagemap_fd);
	printf("done\n");
}

static int userfaultfd_stress(void)
{
	void *area;
	char *tmp_area;
	unsigned long nr;
	struct uffdio_register uffdio_register;
	struct uffd_stats uffd_stats[nr_cpus];

	uffd_test_ctx_init(0);

	if (posix_memalign(&area, page_size, page_size))
		err("out of memory");
	zeropage = area;
	bzero(zeropage, page_size);

	pthread_mutex_lock(&uffd_read_mutex);

	pthread_attr_init(&attr);
	pthread_attr_setstacksize(&attr, 16*1024*1024);

	while (bounces--) {
		printf("bounces: %d, mode:", bounces);
		if (bounces & BOUNCE_RANDOM)
			printf(" rnd");
		if (bounces & BOUNCE_RACINGFAULTS)
			printf(" racing");
		if (bounces & BOUNCE_VERIFY)
			printf(" ver");
		if (bounces & BOUNCE_POLL)
			printf(" poll");
		else
			printf(" read");
		printf(", ");
		fflush(stdout);

		if (bounces & BOUNCE_POLL)
			fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
		else
			fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK);

		/* register */
		uffdio_register.range.start = (unsigned long) area_dst;
		uffdio_register.range.len = nr_pages * page_size;
		uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
		if (test_uffdio_wp)
			uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
			err("register failure");
		assert_expected_ioctls_present(
			uffdio_register.mode, uffdio_register.ioctls);

		if (area_dst_alias) {
			uffdio_register.range.start = (unsigned long)
				area_dst_alias;
			if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
				err("register failure alias");
		}

		/*
		 * The madvise done previously isn't enough: some
		 * uffd_thread could have read userfaults (one of
		 * those already resolved by the background thread)
		 * and it may be in the process of calling
		 * UFFDIO_COPY. UFFDIO_COPY will read the zapped
		 * area_src and it would map a zero page in it (of
		 * course such a UFFDIO_COPY is perfectly safe as it'd
		 * return -EEXIST). The problem comes at the next
		 * bounce though: that racing UFFDIO_COPY would
		 * generate zeropages in the area_src, so invalidating
		 * the previous MADV_DONTNEED. Without this additional
		 * MADV_DONTNEED those zeropages leftovers in the
		 * area_src would lead to -EEXIST failure during the
		 * next bounce, effectively leaving a zeropage in the
		 * area_dst.
		 *
		 * Try to comment this out madvise to see the memory
		 * corruption being caught pretty quick.
		 *
		 * khugepaged is also inhibited to collapse THP after
		 * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's
		 * required to MADV_DONTNEED here.
		 */
		uffd_test_ops->release_pages(area_dst);

		uffd_stats_reset(uffd_stats, nr_cpus);

		/* bounce pass */
		if (stress(uffd_stats))
			return 1;

		/* Clear all the write protections if there is any */
		if (test_uffdio_wp)
			wp_range(uffd, (unsigned long)area_dst,
				 nr_pages * page_size, false);

		/* unregister */
		if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range))
			err("unregister failure");
		if (area_dst_alias) {
			uffdio_register.range.start = (unsigned long) area_dst;
			if (ioctl(uffd, UFFDIO_UNREGISTER,
				  &uffdio_register.range))
				err("unregister failure alias");
		}

		/* verification */
		if (bounces & BOUNCE_VERIFY)
			for (nr = 0; nr < nr_pages; nr++)
				if (*area_count(area_dst, nr) != count_verify[nr])
					err("error area_count %llu %llu %lu\n",
					    *area_count(area_src, nr),
					    count_verify[nr], nr);

		/* prepare next bounce */
		tmp_area = area_src;
		area_src = area_dst;
		area_dst = tmp_area;

		tmp_area = area_src_alias;
		area_src_alias = area_dst_alias;
		area_dst_alias = tmp_area;

		uffd_stats_report(uffd_stats, nr_cpus);
	}

	if (test_type == TEST_ANON) {
		/*
		 * shmem/hugetlb won't be able to run since they have different
		 * behavior on fork() (file-backed memory normally drops ptes
		 * directly when fork), meanwhile the pagemap test will verify
		 * pgtable entry of fork()ed child.
		 */
		userfaultfd_pagemap_test(page_size);
		/*
		 * Hard-code for x86_64 for now for 2M THP, as x86_64 is
		 * currently the only one that supports uffd-wp
		 */
		userfaultfd_pagemap_test(page_size * 512);
	}

	return userfaultfd_zeropage_test() || userfaultfd_sig_test()
		|| userfaultfd_events_test() || userfaultfd_minor_test();
}

/*
 * Copied from mlock2-tests.c
 */
unsigned long default_huge_page_size(void)
{
	unsigned long hps = 0;
	char *line = NULL;
	size_t linelen = 0;
	FILE *f = fopen("/proc/meminfo", "r");

	if (!f)
		return 0;
	while (getline(&line, &linelen, f) > 0) {
		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
			hps <<= 10;
			break;
		}
	}

	free(line);
	fclose(f);
	return hps;
}

static void set_test_type(const char *type)
{
	uint64_t features = UFFD_API_FEATURES;

	if (!strcmp(type, "anon")) {
		test_type = TEST_ANON;
		uffd_test_ops = &anon_uffd_test_ops;
		/* Only enable write-protect test for anonymous test */
		test_uffdio_wp = true;
	} else if (!strcmp(type, "hugetlb")) {
		test_type = TEST_HUGETLB;
		uffd_test_ops = &hugetlb_uffd_test_ops;
	} else if (!strcmp(type, "hugetlb_shared")) {
		map_shared = true;
		test_type = TEST_HUGETLB;
		uffd_test_ops = &hugetlb_uffd_test_ops;
		/* Minor faults require shared hugetlb; only enable here. */
		test_uffdio_minor = true;
	} else if (!strcmp(type, "shmem")) {
		map_shared = true;
		test_type = TEST_SHMEM;
		uffd_test_ops = &shmem_uffd_test_ops;
		test_uffdio_minor = true;
	} else {
		err("Unknown test type: %s", type);
	}

	if (test_type == TEST_HUGETLB)
		page_size = default_huge_page_size();
	else
		page_size = sysconf(_SC_PAGE_SIZE);

	if (!page_size)
		err("Unable to determine page size");
	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
	    > page_size)
		err("Impossible to run this test");

	/*
	 * Whether we can test certain features depends not just on test type,
	 * but also on whether or not this particular kernel supports the
	 * feature.
	 */

	userfaultfd_open(&features);

	test_uffdio_wp = test_uffdio_wp &&
		(features & UFFD_FEATURE_PAGEFAULT_FLAG_WP);
	test_uffdio_minor = test_uffdio_minor &&
		(features & uffd_minor_feature());

	close(uffd);
	uffd = -1;
}

static void sigalrm(int sig)
{
	if (sig != SIGALRM)
		abort();
	test_uffdio_copy_eexist = true;
	test_uffdio_zeropage_eexist = true;
	alarm(ALARM_INTERVAL_SECS);
}

int main(int argc, char **argv)
{
	if (argc < 4)
		usage();

	if (signal(SIGALRM, sigalrm) == SIG_ERR)
		err("failed to arm SIGALRM");
	alarm(ALARM_INTERVAL_SECS);

	set_test_type(argv[1]);

	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
	nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size /
		nr_cpus;
	if (!nr_pages_per_cpu) {
		_err("invalid MiB");
		usage();
	}

	bounces = atoi(argv[3]);
	if (bounces <= 0) {
		_err("invalid bounces");
		usage();
	}
	nr_pages = nr_pages_per_cpu * nr_cpus;

	if (test_type == TEST_HUGETLB) {
		if (argc < 5)
			usage();
		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
		if (huge_fd < 0)
			err("Open of %s failed", argv[4]);
		if (ftruncate(huge_fd, 0))
			err("ftruncate %s to size 0 failed", argv[4]);
	} else if (test_type == TEST_SHMEM) {
		shm_fd = memfd_create(argv[0], 0);
		if (shm_fd < 0)
			err("memfd_create");
		if (ftruncate(shm_fd, nr_pages * page_size * 2))
			err("ftruncate");
		if (fallocate(shm_fd,
			      FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
			      nr_pages * page_size * 2))
			err("fallocate");
	}
	printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
	       nr_pages, nr_pages_per_cpu);
	return userfaultfd_stress();
}

#else /* __NR_userfaultfd */

#warning "missing __NR_userfaultfd definition"

int main(void)
{
	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
	return KSFT_SKIP;
}

#endif /* __NR_userfaultfd */