summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/mm/khugepaged.c
blob: 829320a519e723127ad6c0f0928486d95a581024 (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
#define _GNU_SOURCE
#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
#include <limits.h>
#include <dirent.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
#include <unistd.h>

#include <linux/mman.h>
#include <sys/mman.h>
#include <sys/wait.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/sysmacros.h>
#include <sys/vfs.h>

#include "linux/magic.h"

#include "vm_util.h"
#include "thp_settings.h"

#define BASE_ADDR ((void *)(1UL << 30))
static unsigned long hpage_pmd_size;
static unsigned long page_size;
static int hpage_pmd_nr;
static int anon_order;

#define PID_SMAPS "/proc/self/smaps"
#define TEST_FILE "collapse_test_file"

#define MAX_LINE_LENGTH 500

enum vma_type {
	VMA_ANON,
	VMA_FILE,
	VMA_SHMEM,
};

struct mem_ops {
	void *(*setup_area)(int nr_hpages);
	void (*cleanup_area)(void *p, unsigned long size);
	void (*fault)(void *p, unsigned long start, unsigned long end);
	bool (*check_huge)(void *addr, int nr_hpages);
	const char *name;
};

static struct mem_ops *file_ops;
static struct mem_ops *anon_ops;
static struct mem_ops *shmem_ops;

struct collapse_context {
	void (*collapse)(const char *msg, char *p, int nr_hpages,
			 struct mem_ops *ops, bool expect);
	bool enforce_pte_scan_limits;
	const char *name;
};

static struct collapse_context *khugepaged_context;
static struct collapse_context *madvise_context;

struct file_info {
	const char *dir;
	char path[PATH_MAX];
	enum vma_type type;
	int fd;
	char dev_queue_read_ahead_path[PATH_MAX];
};

static struct file_info finfo;
static bool skip_settings_restore;
static int exit_status;

static void success(const char *msg)
{
	printf(" \e[32m%s\e[0m\n", msg);
}

static void fail(const char *msg)
{
	printf(" \e[31m%s\e[0m\n", msg);
	exit_status++;
}

static void skip(const char *msg)
{
	printf(" \e[33m%s\e[0m\n", msg);
}

static void restore_settings_atexit(void)
{
	if (skip_settings_restore)
		return;

	printf("Restore THP and khugepaged settings...");
	thp_restore_settings();
	success("OK");

	skip_settings_restore = true;
}

static void restore_settings(int sig)
{
	/* exit() will invoke the restore_settings_atexit handler. */
	exit(sig ? EXIT_FAILURE : exit_status);
}

static void save_settings(void)
{
	printf("Save THP and khugepaged settings...");
	if (file_ops && finfo.type == VMA_FILE)
		thp_set_read_ahead_path(finfo.dev_queue_read_ahead_path);
	thp_save_settings();

	success("OK");

	atexit(restore_settings_atexit);
	signal(SIGTERM, restore_settings);
	signal(SIGINT, restore_settings);
	signal(SIGHUP, restore_settings);
	signal(SIGQUIT, restore_settings);
}

static void get_finfo(const char *dir)
{
	struct stat path_stat;
	struct statfs fs;
	char buf[1 << 10];
	char path[PATH_MAX];
	char *str, *end;

	finfo.dir = dir;
	stat(finfo.dir, &path_stat);
	if (!S_ISDIR(path_stat.st_mode)) {
		printf("%s: Not a directory (%s)\n", __func__, finfo.dir);
		exit(EXIT_FAILURE);
	}
	if (snprintf(finfo.path, sizeof(finfo.path), "%s/" TEST_FILE,
		     finfo.dir) >= sizeof(finfo.path)) {
		printf("%s: Pathname is too long\n", __func__);
		exit(EXIT_FAILURE);
	}
	if (statfs(finfo.dir, &fs)) {
		perror("statfs()");
		exit(EXIT_FAILURE);
	}
	finfo.type = fs.f_type == TMPFS_MAGIC ? VMA_SHMEM : VMA_FILE;
	if (finfo.type == VMA_SHMEM)
		return;

	/* Find owning device's queue/read_ahead_kb control */
	if (snprintf(path, sizeof(path), "/sys/dev/block/%d:%d/uevent",
		     major(path_stat.st_dev), minor(path_stat.st_dev))
	    >= sizeof(path)) {
		printf("%s: Pathname is too long\n", __func__);
		exit(EXIT_FAILURE);
	}
	if (read_file(path, buf, sizeof(buf)) < 0) {
		perror("read_file(read_num)");
		exit(EXIT_FAILURE);
	}
	if (strstr(buf, "DEVTYPE=disk")) {
		/* Found it */
		if (snprintf(finfo.dev_queue_read_ahead_path,
			     sizeof(finfo.dev_queue_read_ahead_path),
			     "/sys/dev/block/%d:%d/queue/read_ahead_kb",
			     major(path_stat.st_dev), minor(path_stat.st_dev))
		    >= sizeof(finfo.dev_queue_read_ahead_path)) {
			printf("%s: Pathname is too long\n", __func__);
			exit(EXIT_FAILURE);
		}
		return;
	}
	if (!strstr(buf, "DEVTYPE=partition")) {
		printf("%s: Unknown device type: %s\n", __func__, path);
		exit(EXIT_FAILURE);
	}
	/*
	 * Partition of block device - need to find actual device.
	 * Using naming convention that devnameN is partition of
	 * device devname.
	 */
	str = strstr(buf, "DEVNAME=");
	if (!str) {
		printf("%s: Could not read: %s", __func__, path);
		exit(EXIT_FAILURE);
	}
	str += 8;
	end = str;
	while (*end) {
		if (isdigit(*end)) {
			*end = '\0';
			if (snprintf(finfo.dev_queue_read_ahead_path,
				     sizeof(finfo.dev_queue_read_ahead_path),
				     "/sys/block/%s/queue/read_ahead_kb",
				     str) >= sizeof(finfo.dev_queue_read_ahead_path)) {
				printf("%s: Pathname is too long\n", __func__);
				exit(EXIT_FAILURE);
			}
			return;
		}
		++end;
	}
	printf("%s: Could not read: %s\n", __func__, path);
	exit(EXIT_FAILURE);
}

static bool check_swap(void *addr, unsigned long size)
{
	bool swap = false;
	int ret;
	FILE *fp;
	char buffer[MAX_LINE_LENGTH];
	char addr_pattern[MAX_LINE_LENGTH];

	ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
		       (unsigned long) addr);
	if (ret >= MAX_LINE_LENGTH) {
		printf("%s: Pattern is too long\n", __func__);
		exit(EXIT_FAILURE);
	}


	fp = fopen(PID_SMAPS, "r");
	if (!fp) {
		printf("%s: Failed to open file %s\n", __func__, PID_SMAPS);
		exit(EXIT_FAILURE);
	}
	if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer)))
		goto err_out;

	ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "Swap:%19ld kB",
		       size >> 10);
	if (ret >= MAX_LINE_LENGTH) {
		printf("%s: Pattern is too long\n", __func__);
		exit(EXIT_FAILURE);
	}
	/*
	 * Fetch the Swap: in the same block and check whether it got
	 * the expected number of hugeepages next.
	 */
	if (!check_for_pattern(fp, "Swap:", buffer, sizeof(buffer)))
		goto err_out;

	if (strncmp(buffer, addr_pattern, strlen(addr_pattern)))
		goto err_out;

	swap = true;
err_out:
	fclose(fp);
	return swap;
}

static void *alloc_mapping(int nr)
{
	void *p;

	p = mmap(BASE_ADDR, nr * hpage_pmd_size, PROT_READ | PROT_WRITE,
		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
	if (p != BASE_ADDR) {
		printf("Failed to allocate VMA at %p\n", BASE_ADDR);
		exit(EXIT_FAILURE);
	}

	return p;
}

static void fill_memory(int *p, unsigned long start, unsigned long end)
{
	int i;

	for (i = start / page_size; i < end / page_size; i++)
		p[i * page_size / sizeof(*p)] = i + 0xdead0000;
}

/*
 * MADV_COLLAPSE is a best-effort request and may fail if an internal
 * resource is temporarily unavailable, in which case it will set errno to
 * EAGAIN.  In such a case, immediately reattempt the operation one more
 * time.
 */
static int madvise_collapse_retry(void *p, unsigned long size)
{
	bool retry = true;
	int ret;

retry:
	ret = madvise(p, size, MADV_COLLAPSE);
	if (ret && errno == EAGAIN && retry) {
		retry = false;
		goto retry;
	}
	return ret;
}

/*
 * Returns pmd-mapped hugepage in VMA marked VM_HUGEPAGE, filled with
 * validate_memory()'able contents.
 */
static void *alloc_hpage(struct mem_ops *ops)
{
	void *p = ops->setup_area(1);

	ops->fault(p, 0, hpage_pmd_size);

	/*
	 * VMA should be neither VM_HUGEPAGE nor VM_NOHUGEPAGE.
	 * The latter is ineligible for collapse by MADV_COLLAPSE
	 * while the former might cause MADV_COLLAPSE to race with
	 * khugepaged on low-load system (like a test machine), which
	 * would cause MADV_COLLAPSE to fail with EAGAIN.
	 */
	printf("Allocate huge page...");
	if (madvise_collapse_retry(p, hpage_pmd_size)) {
		perror("madvise(MADV_COLLAPSE)");
		exit(EXIT_FAILURE);
	}
	if (!ops->check_huge(p, 1)) {
		perror("madvise(MADV_COLLAPSE)");
		exit(EXIT_FAILURE);
	}
	if (madvise(p, hpage_pmd_size, MADV_HUGEPAGE)) {
		perror("madvise(MADV_HUGEPAGE)");
		exit(EXIT_FAILURE);
	}
	success("OK");
	return p;
}

static void validate_memory(int *p, unsigned long start, unsigned long end)
{
	int i;

	for (i = start / page_size; i < end / page_size; i++) {
		if (p[i * page_size / sizeof(*p)] != i + 0xdead0000) {
			printf("Page %d is corrupted: %#x\n",
					i, p[i * page_size / sizeof(*p)]);
			exit(EXIT_FAILURE);
		}
	}
}

static void *anon_setup_area(int nr_hpages)
{
	return alloc_mapping(nr_hpages);
}

static void anon_cleanup_area(void *p, unsigned long size)
{
	munmap(p, size);
}

static void anon_fault(void *p, unsigned long start, unsigned long end)
{
	fill_memory(p, start, end);
}

static bool anon_check_huge(void *addr, int nr_hpages)
{
	return check_huge_anon(addr, nr_hpages, hpage_pmd_size);
}

static void *file_setup_area(int nr_hpages)
{
	int fd;
	void *p;
	unsigned long size;

	unlink(finfo.path);  /* Cleanup from previous failed tests */
	printf("Creating %s for collapse%s...", finfo.path,
	       finfo.type == VMA_SHMEM ? " (tmpfs)" : "");
	fd = open(finfo.path, O_DSYNC | O_CREAT | O_RDWR | O_TRUNC | O_EXCL,
		  777);
	if (fd < 0) {
		perror("open()");
		exit(EXIT_FAILURE);
	}

	size = nr_hpages * hpage_pmd_size;
	p = alloc_mapping(nr_hpages);
	fill_memory(p, 0, size);
	write(fd, p, size);
	close(fd);
	munmap(p, size);
	success("OK");

	printf("Opening %s read only for collapse...", finfo.path);
	finfo.fd = open(finfo.path, O_RDONLY, 777);
	if (finfo.fd < 0) {
		perror("open()");
		exit(EXIT_FAILURE);
	}
	p = mmap(BASE_ADDR, size, PROT_READ | PROT_EXEC,
		 MAP_PRIVATE, finfo.fd, 0);
	if (p == MAP_FAILED || p != BASE_ADDR) {
		perror("mmap()");
		exit(EXIT_FAILURE);
	}

	/* Drop page cache */
	write_file("/proc/sys/vm/drop_caches", "3", 2);
	success("OK");
	return p;
}

static void file_cleanup_area(void *p, unsigned long size)
{
	munmap(p, size);
	close(finfo.fd);
	unlink(finfo.path);
}

static void file_fault(void *p, unsigned long start, unsigned long end)
{
	if (madvise(((char *)p) + start, end - start, MADV_POPULATE_READ)) {
		perror("madvise(MADV_POPULATE_READ");
		exit(EXIT_FAILURE);
	}
}

static bool file_check_huge(void *addr, int nr_hpages)
{
	switch (finfo.type) {
	case VMA_FILE:
		return check_huge_file(addr, nr_hpages, hpage_pmd_size);
	case VMA_SHMEM:
		return check_huge_shmem(addr, nr_hpages, hpage_pmd_size);
	default:
		exit(EXIT_FAILURE);
		return false;
	}
}

static void *shmem_setup_area(int nr_hpages)
{
	void *p;
	unsigned long size = nr_hpages * hpage_pmd_size;

	finfo.fd = memfd_create("khugepaged-selftest-collapse-shmem", 0);
	if (finfo.fd < 0)  {
		perror("memfd_create()");
		exit(EXIT_FAILURE);
	}
	if (ftruncate(finfo.fd, size)) {
		perror("ftruncate()");
		exit(EXIT_FAILURE);
	}
	p = mmap(BASE_ADDR, size, PROT_READ | PROT_WRITE, MAP_SHARED, finfo.fd,
		 0);
	if (p != BASE_ADDR) {
		perror("mmap()");
		exit(EXIT_FAILURE);
	}
	return p;
}

static void shmem_cleanup_area(void *p, unsigned long size)
{
	munmap(p, size);
	close(finfo.fd);
}

static bool shmem_check_huge(void *addr, int nr_hpages)
{
	return check_huge_shmem(addr, nr_hpages, hpage_pmd_size);
}

static struct mem_ops __anon_ops = {
	.setup_area = &anon_setup_area,
	.cleanup_area = &anon_cleanup_area,
	.fault = &anon_fault,
	.check_huge = &anon_check_huge,
	.name = "anon",
};

static struct mem_ops __file_ops = {
	.setup_area = &file_setup_area,
	.cleanup_area = &file_cleanup_area,
	.fault = &file_fault,
	.check_huge = &file_check_huge,
	.name = "file",
};

static struct mem_ops __shmem_ops = {
	.setup_area = &shmem_setup_area,
	.cleanup_area = &shmem_cleanup_area,
	.fault = &anon_fault,
	.check_huge = &shmem_check_huge,
	.name = "shmem",
};

static void __madvise_collapse(const char *msg, char *p, int nr_hpages,
			       struct mem_ops *ops, bool expect)
{
	int ret;
	struct thp_settings settings = *thp_current_settings();

	printf("%s...", msg);

	/*
	 * Prevent khugepaged interference and tests that MADV_COLLAPSE
	 * ignores /sys/kernel/mm/transparent_hugepage/enabled
	 */
	settings.thp_enabled = THP_NEVER;
	settings.shmem_enabled = SHMEM_NEVER;
	thp_push_settings(&settings);

	/* Clear VM_NOHUGEPAGE */
	madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE);
	ret = madvise_collapse_retry(p, nr_hpages * hpage_pmd_size);
	if (((bool)ret) == expect)
		fail("Fail: Bad return value");
	else if (!ops->check_huge(p, expect ? nr_hpages : 0))
		fail("Fail: check_huge()");
	else
		success("OK");

	thp_pop_settings();
}

static void madvise_collapse(const char *msg, char *p, int nr_hpages,
			     struct mem_ops *ops, bool expect)
{
	/* Sanity check */
	if (!ops->check_huge(p, 0)) {
		printf("Unexpected huge page\n");
		exit(EXIT_FAILURE);
	}
	__madvise_collapse(msg, p, nr_hpages, ops, expect);
}

#define TICK 500000
static bool wait_for_scan(const char *msg, char *p, int nr_hpages,
			  struct mem_ops *ops)
{
	int full_scans;
	int timeout = 6; /* 3 seconds */

	/* Sanity check */
	if (!ops->check_huge(p, 0)) {
		printf("Unexpected huge page\n");
		exit(EXIT_FAILURE);
	}

	madvise(p, nr_hpages * hpage_pmd_size, MADV_HUGEPAGE);

	/* Wait until the second full_scan completed */
	full_scans = thp_read_num("khugepaged/full_scans") + 2;

	printf("%s...", msg);
	while (timeout--) {
		if (ops->check_huge(p, nr_hpages))
			break;
		if (thp_read_num("khugepaged/full_scans") >= full_scans)
			break;
		printf(".");
		usleep(TICK);
	}

	madvise(p, nr_hpages * hpage_pmd_size, MADV_NOHUGEPAGE);

	return timeout == -1;
}

static void khugepaged_collapse(const char *msg, char *p, int nr_hpages,
				struct mem_ops *ops, bool expect)
{
	if (wait_for_scan(msg, p, nr_hpages, ops)) {
		if (expect)
			fail("Timeout");
		else
			success("OK");
		return;
	}

	/*
	 * For file and shmem memory, khugepaged only retracts pte entries after
	 * putting the new hugepage in the page cache. The hugepage must be
	 * subsequently refaulted to install the pmd mapping for the mm.
	 */
	if (ops != &__anon_ops)
		ops->fault(p, 0, nr_hpages * hpage_pmd_size);

	if (ops->check_huge(p, expect ? nr_hpages : 0))
		success("OK");
	else
		fail("Fail");
}

static struct collapse_context __khugepaged_context = {
	.collapse = &khugepaged_collapse,
	.enforce_pte_scan_limits = true,
	.name = "khugepaged",
};

static struct collapse_context __madvise_context = {
	.collapse = &madvise_collapse,
	.enforce_pte_scan_limits = false,
	.name = "madvise",
};

static bool is_tmpfs(struct mem_ops *ops)
{
	return ops == &__file_ops && finfo.type == VMA_SHMEM;
}

static bool is_anon(struct mem_ops *ops)
{
	return ops == &__anon_ops;
}

static void alloc_at_fault(void)
{
	struct thp_settings settings = *thp_current_settings();
	char *p;

	settings.thp_enabled = THP_ALWAYS;
	thp_push_settings(&settings);

	p = alloc_mapping(1);
	*p = 1;
	printf("Allocate huge page on fault...");
	if (check_huge_anon(p, 1, hpage_pmd_size))
		success("OK");
	else
		fail("Fail");

	thp_pop_settings();

	madvise(p, page_size, MADV_DONTNEED);
	printf("Split huge PMD on MADV_DONTNEED...");
	if (check_huge_anon(p, 0, hpage_pmd_size))
		success("OK");
	else
		fail("Fail");
	munmap(p, hpage_pmd_size);
}

static void collapse_full(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;
	int nr_hpages = 4;
	unsigned long size = nr_hpages * hpage_pmd_size;

	p = ops->setup_area(nr_hpages);
	ops->fault(p, 0, size);
	c->collapse("Collapse multiple fully populated PTE table", p, nr_hpages,
		    ops, true);
	validate_memory(p, 0, size);
	ops->cleanup_area(p, size);
}

static void collapse_empty(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;

	p = ops->setup_area(1);
	c->collapse("Do not collapse empty PTE table", p, 1, ops, false);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_single_pte_entry(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;

	p = ops->setup_area(1);
	ops->fault(p, 0, page_size);
	c->collapse("Collapse PTE table with single PTE entry present", p,
		    1, ops, true);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *ops)
{
	int max_ptes_none = hpage_pmd_nr / 2;
	struct thp_settings settings = *thp_current_settings();
	void *p;
	int fault_nr_pages = is_anon(ops) ? 1 << anon_order : 1;

	settings.khugepaged.max_ptes_none = max_ptes_none;
	thp_push_settings(&settings);

	p = ops->setup_area(1);

	if (is_tmpfs(ops)) {
		/* shmem pages always in the page cache */
		printf("tmpfs...");
		skip("Skip");
		goto skip;
	}

	ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);
	c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1,
		    ops, !c->enforce_pte_scan_limits);
	validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);

	if (c->enforce_pte_scan_limits) {
		ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size);
		c->collapse("Collapse with max_ptes_none PTEs empty", p, 1, ops,
			    true);
		validate_memory(p, 0,
				(hpage_pmd_nr - max_ptes_none) * page_size);
	}
skip:
	ops->cleanup_area(p, hpage_pmd_size);
	thp_pop_settings();
}

static void collapse_swapin_single_pte(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;

	p = ops->setup_area(1);
	ops->fault(p, 0, hpage_pmd_size);

	printf("Swapout one page...");
	if (madvise(p, page_size, MADV_PAGEOUT)) {
		perror("madvise(MADV_PAGEOUT)");
		exit(EXIT_FAILURE);
	}
	if (check_swap(p, page_size)) {
		success("OK");
	} else {
		fail("Fail");
		goto out;
	}

	c->collapse("Collapse with swapping in single PTE entry", p, 1, ops,
		    true);
	validate_memory(p, 0, hpage_pmd_size);
out:
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_max_ptes_swap(struct collapse_context *c, struct mem_ops *ops)
{
	int max_ptes_swap = thp_read_num("khugepaged/max_ptes_swap");
	void *p;

	p = ops->setup_area(1);
	ops->fault(p, 0, hpage_pmd_size);

	printf("Swapout %d of %d pages...", max_ptes_swap + 1, hpage_pmd_nr);
	if (madvise(p, (max_ptes_swap + 1) * page_size, MADV_PAGEOUT)) {
		perror("madvise(MADV_PAGEOUT)");
		exit(EXIT_FAILURE);
	}
	if (check_swap(p, (max_ptes_swap + 1) * page_size)) {
		success("OK");
	} else {
		fail("Fail");
		goto out;
	}

	c->collapse("Maybe collapse with max_ptes_swap exceeded", p, 1, ops,
		    !c->enforce_pte_scan_limits);
	validate_memory(p, 0, hpage_pmd_size);

	if (c->enforce_pte_scan_limits) {
		ops->fault(p, 0, hpage_pmd_size);
		printf("Swapout %d of %d pages...", max_ptes_swap,
		       hpage_pmd_nr);
		if (madvise(p, max_ptes_swap * page_size, MADV_PAGEOUT)) {
			perror("madvise(MADV_PAGEOUT)");
			exit(EXIT_FAILURE);
		}
		if (check_swap(p, max_ptes_swap * page_size)) {
			success("OK");
		} else {
			fail("Fail");
			goto out;
		}

		c->collapse("Collapse with max_ptes_swap pages swapped out", p,
			    1, ops, true);
		validate_memory(p, 0, hpage_pmd_size);
	}
out:
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_single_pte_entry_compound(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;

	p = alloc_hpage(ops);

	if (is_tmpfs(ops)) {
		/* MADV_DONTNEED won't evict tmpfs pages */
		printf("tmpfs...");
		skip("Skip");
		goto skip;
	}

	madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
	printf("Split huge page leaving single PTE mapping compound page...");
	madvise(p + page_size, hpage_pmd_size - page_size, MADV_DONTNEED);
	if (ops->check_huge(p, 0))
		success("OK");
	else
		fail("Fail");

	c->collapse("Collapse PTE table with single PTE mapping compound page",
		    p, 1, ops, true);
	validate_memory(p, 0, page_size);
skip:
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_full_of_compound(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;

	p = alloc_hpage(ops);
	printf("Split huge page leaving single PTE page table full of compound pages...");
	madvise(p, page_size, MADV_NOHUGEPAGE);
	madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
	if (ops->check_huge(p, 0))
		success("OK");
	else
		fail("Fail");

	c->collapse("Collapse PTE table full of compound pages", p, 1, ops,
		    true);
	validate_memory(p, 0, hpage_pmd_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_compound_extreme(struct collapse_context *c, struct mem_ops *ops)
{
	void *p;
	int i;

	p = ops->setup_area(1);
	for (i = 0; i < hpage_pmd_nr; i++) {
		printf("\rConstruct PTE page table full of different PTE-mapped compound pages %3d/%d...",
				i + 1, hpage_pmd_nr);

		madvise(BASE_ADDR, hpage_pmd_size, MADV_HUGEPAGE);
		ops->fault(BASE_ADDR, 0, hpage_pmd_size);
		if (!ops->check_huge(BASE_ADDR, 1)) {
			printf("Failed to allocate huge page\n");
			exit(EXIT_FAILURE);
		}
		madvise(BASE_ADDR, hpage_pmd_size, MADV_NOHUGEPAGE);

		p = mremap(BASE_ADDR - i * page_size,
				i * page_size + hpage_pmd_size,
				(i + 1) * page_size,
				MREMAP_MAYMOVE | MREMAP_FIXED,
				BASE_ADDR + 2 * hpage_pmd_size);
		if (p == MAP_FAILED) {
			perror("mremap+unmap");
			exit(EXIT_FAILURE);
		}

		p = mremap(BASE_ADDR + 2 * hpage_pmd_size,
				(i + 1) * page_size,
				(i + 1) * page_size + hpage_pmd_size,
				MREMAP_MAYMOVE | MREMAP_FIXED,
				BASE_ADDR - (i + 1) * page_size);
		if (p == MAP_FAILED) {
			perror("mremap+alloc");
			exit(EXIT_FAILURE);
		}
	}

	ops->cleanup_area(BASE_ADDR, hpage_pmd_size);
	ops->fault(p, 0, hpage_pmd_size);
	if (!ops->check_huge(p, 1))
		success("OK");
	else
		fail("Fail");

	c->collapse("Collapse PTE table full of different compound pages", p, 1,
		    ops, true);

	validate_memory(p, 0, hpage_pmd_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_fork(struct collapse_context *c, struct mem_ops *ops)
{
	int wstatus;
	void *p;

	p = ops->setup_area(1);

	printf("Allocate small page...");
	ops->fault(p, 0, page_size);
	if (ops->check_huge(p, 0))
		success("OK");
	else
		fail("Fail");

	printf("Share small page over fork()...");
	if (!fork()) {
		/* Do not touch settings on child exit */
		skip_settings_restore = true;
		exit_status = 0;

		if (ops->check_huge(p, 0))
			success("OK");
		else
			fail("Fail");

		ops->fault(p, page_size, 2 * page_size);
		c->collapse("Collapse PTE table with single page shared with parent process",
			    p, 1, ops, true);

		validate_memory(p, 0, page_size);
		ops->cleanup_area(p, hpage_pmd_size);
		exit(exit_status);
	}

	wait(&wstatus);
	exit_status += WEXITSTATUS(wstatus);

	printf("Check if parent still has small page...");
	if (ops->check_huge(p, 0))
		success("OK");
	else
		fail("Fail");
	validate_memory(p, 0, page_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *ops)
{
	int wstatus;
	void *p;

	p = alloc_hpage(ops);
	printf("Share huge page over fork()...");
	if (!fork()) {
		/* Do not touch settings on child exit */
		skip_settings_restore = true;
		exit_status = 0;

		if (ops->check_huge(p, 1))
			success("OK");
		else
			fail("Fail");

		printf("Split huge page PMD in child process...");
		madvise(p, page_size, MADV_NOHUGEPAGE);
		madvise(p, hpage_pmd_size, MADV_NOHUGEPAGE);
		if (ops->check_huge(p, 0))
			success("OK");
		else
			fail("Fail");
		ops->fault(p, 0, page_size);

		thp_write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1);
		c->collapse("Collapse PTE table full of compound pages in child",
			    p, 1, ops, true);
		thp_write_num("khugepaged/max_ptes_shared",
			  thp_current_settings()->khugepaged.max_ptes_shared);

		validate_memory(p, 0, hpage_pmd_size);
		ops->cleanup_area(p, hpage_pmd_size);
		exit(exit_status);
	}

	wait(&wstatus);
	exit_status += WEXITSTATUS(wstatus);

	printf("Check if parent still has huge page...");
	if (ops->check_huge(p, 1))
		success("OK");
	else
		fail("Fail");
	validate_memory(p, 0, hpage_pmd_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops *ops)
{
	int max_ptes_shared = thp_read_num("khugepaged/max_ptes_shared");
	int wstatus;
	void *p;

	p = alloc_hpage(ops);
	printf("Share huge page over fork()...");
	if (!fork()) {
		/* Do not touch settings on child exit */
		skip_settings_restore = true;
		exit_status = 0;

		if (ops->check_huge(p, 1))
			success("OK");
		else
			fail("Fail");

		printf("Trigger CoW on page %d of %d...",
				hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr);
		ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size);
		if (ops->check_huge(p, 0))
			success("OK");
		else
			fail("Fail");

		c->collapse("Maybe collapse with max_ptes_shared exceeded", p,
			    1, ops, !c->enforce_pte_scan_limits);

		if (c->enforce_pte_scan_limits) {
			printf("Trigger CoW on page %d of %d...",
			       hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr);
			ops->fault(p, 0, (hpage_pmd_nr - max_ptes_shared) *
				    page_size);
			if (ops->check_huge(p, 0))
				success("OK");
			else
				fail("Fail");

			c->collapse("Collapse with max_ptes_shared PTEs shared",
				    p, 1, ops, true);
		}

		validate_memory(p, 0, hpage_pmd_size);
		ops->cleanup_area(p, hpage_pmd_size);
		exit(exit_status);
	}

	wait(&wstatus);
	exit_status += WEXITSTATUS(wstatus);

	printf("Check if parent still has huge page...");
	if (ops->check_huge(p, 1))
		success("OK");
	else
		fail("Fail");
	validate_memory(p, 0, hpage_pmd_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

static void madvise_collapse_existing_thps(struct collapse_context *c,
					   struct mem_ops *ops)
{
	void *p;

	p = ops->setup_area(1);
	ops->fault(p, 0, hpage_pmd_size);
	c->collapse("Collapse fully populated PTE table...", p, 1, ops, true);
	validate_memory(p, 0, hpage_pmd_size);

	/* c->collapse() will find a hugepage and complain - call directly. */
	__madvise_collapse("Re-collapse PMD-mapped hugepage", p, 1, ops, true);
	validate_memory(p, 0, hpage_pmd_size);
	ops->cleanup_area(p, hpage_pmd_size);
}

/*
 * Test race with khugepaged where page tables have been retracted and
 * pmd cleared.
 */
static void madvise_retracted_page_tables(struct collapse_context *c,
					  struct mem_ops *ops)
{
	void *p;
	int nr_hpages = 1;
	unsigned long size = nr_hpages * hpage_pmd_size;

	p = ops->setup_area(nr_hpages);
	ops->fault(p, 0, size);

	/* Let khugepaged collapse and leave pmd cleared */
	if (wait_for_scan("Collapse and leave PMD cleared", p, nr_hpages,
			  ops)) {
		fail("Timeout");
		return;
	}
	success("OK");
	c->collapse("Install huge PMD from page cache", p, nr_hpages, ops,
		    true);
	validate_memory(p, 0, size);
	ops->cleanup_area(p, size);
}

static void usage(void)
{
	fprintf(stderr, "\nUsage: ./khugepaged [OPTIONS] <test type> [dir]\n\n");
	fprintf(stderr, "\t<test type>\t: <context>:<mem_type>\n");
	fprintf(stderr, "\t<context>\t: [all|khugepaged|madvise]\n");
	fprintf(stderr, "\t<mem_type>\t: [all|anon|file|shmem]\n");
	fprintf(stderr, "\n\t\"file,all\" mem_type requires [dir] argument\n");
	fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n");
	fprintf(stderr,	"\tCONFIG_READ_ONLY_THP_FOR_FS=y\n");
	fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n");
	fprintf(stderr,	"\tmounted with huge=madvise option for khugepaged tests to work\n");
	fprintf(stderr,	"\n\tSupported Options:\n");
	fprintf(stderr,	"\t\t-h: This help message.\n");
	fprintf(stderr,	"\t\t-s: mTHP size, expressed as page order.\n");
	fprintf(stderr,	"\t\t    Defaults to 0. Use this size for anon allocations.\n");
	exit(1);
}

static void parse_test_type(int argc, char **argv)
{
	int opt;
	char *buf;
	const char *token;

	while ((opt = getopt(argc, argv, "s:h")) != -1) {
		switch (opt) {
		case 's':
			anon_order = atoi(optarg);
			break;
		case 'h':
		default:
			usage();
		}
	}

	argv += optind;
	argc -= optind;

	if (argc == 0) {
		/* Backwards compatibility */
		khugepaged_context =  &__khugepaged_context;
		madvise_context =  &__madvise_context;
		anon_ops = &__anon_ops;
		return;
	}

	buf = strdup(argv[0]);
	token = strsep(&buf, ":");

	if (!strcmp(token, "all")) {
		khugepaged_context =  &__khugepaged_context;
		madvise_context =  &__madvise_context;
	} else if (!strcmp(token, "khugepaged")) {
		khugepaged_context =  &__khugepaged_context;
	} else if (!strcmp(token, "madvise")) {
		madvise_context =  &__madvise_context;
	} else {
		usage();
	}

	if (!buf)
		usage();

	if (!strcmp(buf, "all")) {
		file_ops =  &__file_ops;
		anon_ops = &__anon_ops;
		shmem_ops = &__shmem_ops;
	} else if (!strcmp(buf, "anon")) {
		anon_ops = &__anon_ops;
	} else if (!strcmp(buf, "file")) {
		file_ops =  &__file_ops;
	} else if (!strcmp(buf, "shmem")) {
		shmem_ops = &__shmem_ops;
	} else {
		usage();
	}

	if (!file_ops)
		return;

	if (argc != 2)
		usage();

	get_finfo(argv[1]);
}

int main(int argc, char **argv)
{
	int hpage_pmd_order;
	struct thp_settings default_settings = {
		.thp_enabled = THP_MADVISE,
		.thp_defrag = THP_DEFRAG_ALWAYS,
		.shmem_enabled = SHMEM_ADVISE,
		.use_zero_page = 0,
		.khugepaged = {
			.defrag = 1,
			.alloc_sleep_millisecs = 10,
			.scan_sleep_millisecs = 10,
		},
		/*
		 * When testing file-backed memory, the collapse path
		 * looks at how many pages are found in the page cache, not
		 * what pages are mapped. Disable read ahead optimization so
		 * pages don't find their way into the page cache unless
		 * we mem_ops->fault() them in.
		 */
		.read_ahead_kb = 0,
	};

	parse_test_type(argc, argv);

	setbuf(stdout, NULL);

	page_size = getpagesize();
	hpage_pmd_size = read_pmd_pagesize();
	if (!hpage_pmd_size) {
		printf("Reading PMD pagesize failed");
		exit(EXIT_FAILURE);
	}
	hpage_pmd_nr = hpage_pmd_size / page_size;
	hpage_pmd_order = __builtin_ctz(hpage_pmd_nr);

	default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1;
	default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8;
	default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2;
	default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8;
	default_settings.hugepages[hpage_pmd_order].enabled = THP_INHERIT;
	default_settings.hugepages[anon_order].enabled = THP_ALWAYS;

	save_settings();
	thp_push_settings(&default_settings);

	alloc_at_fault();

#define TEST(t, c, o) do { \
	if (c && o) { \
		printf("\nRun test: " #t " (%s:%s)\n", c->name, o->name); \
		t(c, o); \
	} \
	} while (0)

	TEST(collapse_full, khugepaged_context, anon_ops);
	TEST(collapse_full, khugepaged_context, file_ops);
	TEST(collapse_full, khugepaged_context, shmem_ops);
	TEST(collapse_full, madvise_context, anon_ops);
	TEST(collapse_full, madvise_context, file_ops);
	TEST(collapse_full, madvise_context, shmem_ops);

	TEST(collapse_empty, khugepaged_context, anon_ops);
	TEST(collapse_empty, madvise_context, anon_ops);

	TEST(collapse_single_pte_entry, khugepaged_context, anon_ops);
	TEST(collapse_single_pte_entry, khugepaged_context, file_ops);
	TEST(collapse_single_pte_entry, khugepaged_context, shmem_ops);
	TEST(collapse_single_pte_entry, madvise_context, anon_ops);
	TEST(collapse_single_pte_entry, madvise_context, file_ops);
	TEST(collapse_single_pte_entry, madvise_context, shmem_ops);

	TEST(collapse_max_ptes_none, khugepaged_context, anon_ops);
	TEST(collapse_max_ptes_none, khugepaged_context, file_ops);
	TEST(collapse_max_ptes_none, madvise_context, anon_ops);
	TEST(collapse_max_ptes_none, madvise_context, file_ops);

	TEST(collapse_single_pte_entry_compound, khugepaged_context, anon_ops);
	TEST(collapse_single_pte_entry_compound, khugepaged_context, file_ops);
	TEST(collapse_single_pte_entry_compound, madvise_context, anon_ops);
	TEST(collapse_single_pte_entry_compound, madvise_context, file_ops);

	TEST(collapse_full_of_compound, khugepaged_context, anon_ops);
	TEST(collapse_full_of_compound, khugepaged_context, file_ops);
	TEST(collapse_full_of_compound, khugepaged_context, shmem_ops);
	TEST(collapse_full_of_compound, madvise_context, anon_ops);
	TEST(collapse_full_of_compound, madvise_context, file_ops);
	TEST(collapse_full_of_compound, madvise_context, shmem_ops);

	TEST(collapse_compound_extreme, khugepaged_context, anon_ops);
	TEST(collapse_compound_extreme, madvise_context, anon_ops);

	TEST(collapse_swapin_single_pte, khugepaged_context, anon_ops);
	TEST(collapse_swapin_single_pte, madvise_context, anon_ops);

	TEST(collapse_max_ptes_swap, khugepaged_context, anon_ops);
	TEST(collapse_max_ptes_swap, madvise_context, anon_ops);

	TEST(collapse_fork, khugepaged_context, anon_ops);
	TEST(collapse_fork, madvise_context, anon_ops);

	TEST(collapse_fork_compound, khugepaged_context, anon_ops);
	TEST(collapse_fork_compound, madvise_context, anon_ops);

	TEST(collapse_max_ptes_shared, khugepaged_context, anon_ops);
	TEST(collapse_max_ptes_shared, madvise_context, anon_ops);

	TEST(madvise_collapse_existing_thps, madvise_context, anon_ops);
	TEST(madvise_collapse_existing_thps, madvise_context, file_ops);
	TEST(madvise_collapse_existing_thps, madvise_context, shmem_ops);

	TEST(madvise_retracted_page_tables, madvise_context, file_ops);
	TEST(madvise_retracted_page_tables, madvise_context, shmem_ops);

	restore_settings(0);
}