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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* COW (Copy On Write) tests for anonymous memory.
*
* Copyright 2022, Red Hat, Inc.
*
* Author(s): David Hildenbrand <david@redhat.com>
*/
#define _GNU_SOURCE
#include <stdlib.h>
#include <string.h>
#include <stdbool.h>
#include <stdint.h>
#include <unistd.h>
#include <errno.h>
#include <fcntl.h>
#include <dirent.h>
#include <assert.h>
#include <sys/mman.h>
#include <sys/ioctl.h>
#include <sys/wait.h>
#include "local_config.h"
#ifdef LOCAL_CONFIG_HAVE_LIBURING
#include <liburing.h>
#endif /* LOCAL_CONFIG_HAVE_LIBURING */
#include "../../../../mm/gup_test.h"
#include "../kselftest.h"
#include "vm_util.h"
static size_t pagesize;
static int pagemap_fd;
static size_t thpsize;
static int nr_hugetlbsizes;
static size_t hugetlbsizes[10];
static int gup_fd;
static void detect_thpsize(void)
{
int fd = open("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size",
O_RDONLY);
size_t size = 0;
char buf[15];
int ret;
if (fd < 0)
return;
ret = pread(fd, buf, sizeof(buf), 0);
if (ret > 0 && ret < sizeof(buf)) {
buf[ret] = 0;
size = strtoul(buf, NULL, 10);
if (size < pagesize)
size = 0;
if (size > 0) {
thpsize = size;
ksft_print_msg("[INFO] detected THP size: %zu KiB\n",
thpsize / 1024);
}
}
close(fd);
}
static void detect_hugetlbsizes(void)
{
DIR *dir = opendir("/sys/kernel/mm/hugepages/");
if (!dir)
return;
while (nr_hugetlbsizes < ARRAY_SIZE(hugetlbsizes)) {
struct dirent *entry = readdir(dir);
size_t kb;
if (!entry)
break;
if (entry->d_type != DT_DIR)
continue;
if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1)
continue;
hugetlbsizes[nr_hugetlbsizes] = kb * 1024;
nr_hugetlbsizes++;
ksft_print_msg("[INFO] detected hugetlb size: %zu KiB\n",
kb);
}
closedir(dir);
}
static bool range_is_swapped(void *addr, size_t size)
{
for (; size; addr += pagesize, size -= pagesize)
if (!pagemap_is_swapped(pagemap_fd, addr))
return false;
return true;
}
struct comm_pipes {
int child_ready[2];
int parent_ready[2];
};
static int setup_comm_pipes(struct comm_pipes *comm_pipes)
{
if (pipe(comm_pipes->child_ready) < 0)
return -errno;
if (pipe(comm_pipes->parent_ready) < 0) {
close(comm_pipes->child_ready[0]);
close(comm_pipes->child_ready[1]);
return -errno;
}
return 0;
}
static void close_comm_pipes(struct comm_pipes *comm_pipes)
{
close(comm_pipes->child_ready[0]);
close(comm_pipes->child_ready[1]);
close(comm_pipes->parent_ready[0]);
close(comm_pipes->parent_ready[1]);
}
static int child_memcmp_fn(char *mem, size_t size,
struct comm_pipes *comm_pipes)
{
char *old = malloc(size);
char buf;
/* Backup the original content. */
memcpy(old, mem, size);
/* Wait until the parent modified the page. */
write(comm_pipes->child_ready[1], "0", 1);
while (read(comm_pipes->parent_ready[0], &buf, 1) != 1)
;
/* See if we still read the old values. */
return memcmp(old, mem, size);
}
static int child_vmsplice_memcmp_fn(char *mem, size_t size,
struct comm_pipes *comm_pipes)
{
struct iovec iov = {
.iov_base = mem,
.iov_len = size,
};
ssize_t cur, total, transferred;
char *old, *new;
int fds[2];
char buf;
old = malloc(size);
new = malloc(size);
/* Backup the original content. */
memcpy(old, mem, size);
if (pipe(fds) < 0)
return -errno;
/* Trigger a read-only pin. */
transferred = vmsplice(fds[1], &iov, 1, 0);
if (transferred < 0)
return -errno;
if (transferred == 0)
return -EINVAL;
/* Unmap it from our page tables. */
if (munmap(mem, size) < 0)
return -errno;
/* Wait until the parent modified it. */
write(comm_pipes->child_ready[1], "0", 1);
while (read(comm_pipes->parent_ready[0], &buf, 1) != 1)
;
/* See if we still read the old values via the pipe. */
for (total = 0; total < transferred; total += cur) {
cur = read(fds[0], new + total, transferred - total);
if (cur < 0)
return -errno;
}
return memcmp(old, new, transferred);
}
typedef int (*child_fn)(char *mem, size_t size, struct comm_pipes *comm_pipes);
static void do_test_cow_in_parent(char *mem, size_t size, child_fn fn)
{
struct comm_pipes comm_pipes;
char buf;
int ret;
ret = setup_comm_pipes(&comm_pipes);
if (ret) {
ksft_test_result_fail("pipe() failed\n");
return;
}
ret = fork();
if (ret < 0) {
ksft_test_result_fail("fork() failed\n");
goto close_comm_pipes;
} else if (!ret) {
exit(fn(mem, size, &comm_pipes));
}
while (read(comm_pipes.child_ready[0], &buf, 1) != 1)
;
/* Modify the page. */
memset(mem, 0xff, size);
write(comm_pipes.parent_ready[1], "0", 1);
wait(&ret);
if (WIFEXITED(ret))
ret = WEXITSTATUS(ret);
else
ret = -EINVAL;
ksft_test_result(!ret, "No leak from parent into child\n");
close_comm_pipes:
close_comm_pipes(&comm_pipes);
}
static void test_cow_in_parent(char *mem, size_t size)
{
do_test_cow_in_parent(mem, size, child_memcmp_fn);
}
static void test_vmsplice_in_child(char *mem, size_t size)
{
do_test_cow_in_parent(mem, size, child_vmsplice_memcmp_fn);
}
static void do_test_vmsplice_in_parent(char *mem, size_t size,
bool before_fork)
{
struct iovec iov = {
.iov_base = mem,
.iov_len = size,
};
ssize_t cur, total, transferred;
struct comm_pipes comm_pipes;
char *old, *new;
int ret, fds[2];
char buf;
old = malloc(size);
new = malloc(size);
memcpy(old, mem, size);
ret = setup_comm_pipes(&comm_pipes);
if (ret) {
ksft_test_result_fail("pipe() failed\n");
goto free;
}
if (pipe(fds) < 0) {
ksft_test_result_fail("pipe() failed\n");
goto close_comm_pipes;
}
if (before_fork) {
transferred = vmsplice(fds[1], &iov, 1, 0);
if (transferred <= 0) {
ksft_test_result_fail("vmsplice() failed\n");
goto close_pipe;
}
}
ret = fork();
if (ret < 0) {
ksft_test_result_fail("fork() failed\n");
goto close_pipe;
} else if (!ret) {
write(comm_pipes.child_ready[1], "0", 1);
while (read(comm_pipes.parent_ready[0], &buf, 1) != 1)
;
/* Modify page content in the child. */
memset(mem, 0xff, size);
exit(0);
}
if (!before_fork) {
transferred = vmsplice(fds[1], &iov, 1, 0);
if (transferred <= 0) {
ksft_test_result_fail("vmsplice() failed\n");
wait(&ret);
goto close_pipe;
}
}
while (read(comm_pipes.child_ready[0], &buf, 1) != 1)
;
if (munmap(mem, size) < 0) {
ksft_test_result_fail("munmap() failed\n");
goto close_pipe;
}
write(comm_pipes.parent_ready[1], "0", 1);
/* Wait until the child is done writing. */
wait(&ret);
if (!WIFEXITED(ret)) {
ksft_test_result_fail("wait() failed\n");
goto close_pipe;
}
/* See if we still read the old values. */
for (total = 0; total < transferred; total += cur) {
cur = read(fds[0], new + total, transferred - total);
if (cur < 0) {
ksft_test_result_fail("read() failed\n");
goto close_pipe;
}
}
ksft_test_result(!memcmp(old, new, transferred),
"No leak from child into parent\n");
close_pipe:
close(fds[0]);
close(fds[1]);
close_comm_pipes:
close_comm_pipes(&comm_pipes);
free:
free(old);
free(new);
}
static void test_vmsplice_before_fork(char *mem, size_t size)
{
do_test_vmsplice_in_parent(mem, size, true);
}
static void test_vmsplice_after_fork(char *mem, size_t size)
{
do_test_vmsplice_in_parent(mem, size, false);
}
#ifdef LOCAL_CONFIG_HAVE_LIBURING
static void do_test_iouring(char *mem, size_t size, bool use_fork)
{
struct comm_pipes comm_pipes;
struct io_uring_cqe *cqe;
struct io_uring_sqe *sqe;
struct io_uring ring;
ssize_t cur, total;
struct iovec iov;
char *buf, *tmp;
int ret, fd;
FILE *file;
ret = setup_comm_pipes(&comm_pipes);
if (ret) {
ksft_test_result_fail("pipe() failed\n");
return;
}
file = tmpfile();
if (!file) {
ksft_test_result_fail("tmpfile() failed\n");
goto close_comm_pipes;
}
fd = fileno(file);
assert(fd);
tmp = malloc(size);
if (!tmp) {
ksft_test_result_fail("malloc() failed\n");
goto close_file;
}
/* Skip on errors, as we might just lack kernel support. */
ret = io_uring_queue_init(1, &ring, 0);
if (ret < 0) {
ksft_test_result_skip("io_uring_queue_init() failed\n");
goto free_tmp;
}
/*
* Register the range as a fixed buffer. This will FOLL_WRITE | FOLL_PIN
* | FOLL_LONGTERM the range.
*
* Skip on errors, as we might just lack kernel support or might not
* have sufficient MEMLOCK permissions.
*/
iov.iov_base = mem;
iov.iov_len = size;
ret = io_uring_register_buffers(&ring, &iov, 1);
if (ret) {
ksft_test_result_skip("io_uring_register_buffers() failed\n");
goto queue_exit;
}
if (use_fork) {
/*
* fork() and keep the child alive until we're done. Note that
* we expect the pinned page to not get shared with the child.
*/
ret = fork();
if (ret < 0) {
ksft_test_result_fail("fork() failed\n");
goto unregister_buffers;
} else if (!ret) {
write(comm_pipes.child_ready[1], "0", 1);
while (read(comm_pipes.parent_ready[0], &buf, 1) != 1)
;
exit(0);
}
while (read(comm_pipes.child_ready[0], &buf, 1) != 1)
;
} else {
/*
* Map the page R/O into the page table. Enable softdirty
* tracking to stop the page from getting mapped R/W immediately
* again by mprotect() optimizations. Note that we don't have an
* easy way to test if that worked (the pagemap does not export
* if the page is mapped R/O vs. R/W).
*/
ret = mprotect(mem, size, PROT_READ);
clear_softdirty();
ret |= mprotect(mem, size, PROT_READ | PROT_WRITE);
if (ret) {
ksft_test_result_fail("mprotect() failed\n");
goto unregister_buffers;
}
}
/*
* Modify the page and write page content as observed by the fixed
* buffer pin to the file so we can verify it.
*/
memset(mem, 0xff, size);
sqe = io_uring_get_sqe(&ring);
if (!sqe) {
ksft_test_result_fail("io_uring_get_sqe() failed\n");
goto quit_child;
}
io_uring_prep_write_fixed(sqe, fd, mem, size, 0, 0);
ret = io_uring_submit(&ring);
if (ret < 0) {
ksft_test_result_fail("io_uring_submit() failed\n");
goto quit_child;
}
ret = io_uring_wait_cqe(&ring, &cqe);
if (ret < 0) {
ksft_test_result_fail("io_uring_wait_cqe() failed\n");
goto quit_child;
}
if (cqe->res != size) {
ksft_test_result_fail("write_fixed failed\n");
goto quit_child;
}
io_uring_cqe_seen(&ring, cqe);
/* Read back the file content to the temporary buffer. */
total = 0;
while (total < size) {
cur = pread(fd, tmp + total, size - total, total);
if (cur < 0) {
ksft_test_result_fail("pread() failed\n");
goto quit_child;
}
total += cur;
}
/* Finally, check if we read what we expected. */
ksft_test_result(!memcmp(mem, tmp, size),
"Longterm R/W pin is reliable\n");
quit_child:
if (use_fork) {
write(comm_pipes.parent_ready[1], "0", 1);
wait(&ret);
}
unregister_buffers:
io_uring_unregister_buffers(&ring);
queue_exit:
io_uring_queue_exit(&ring);
free_tmp:
free(tmp);
close_file:
fclose(file);
close_comm_pipes:
close_comm_pipes(&comm_pipes);
}
static void test_iouring_ro(char *mem, size_t size)
{
do_test_iouring(mem, size, false);
}
static void test_iouring_fork(char *mem, size_t size)
{
do_test_iouring(mem, size, true);
}
#endif /* LOCAL_CONFIG_HAVE_LIBURING */
enum ro_pin_test {
RO_PIN_TEST_SHARED,
RO_PIN_TEST_PREVIOUSLY_SHARED,
RO_PIN_TEST_RO_EXCLUSIVE,
};
static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
bool fast)
{
struct pin_longterm_test args;
struct comm_pipes comm_pipes;
char *tmp, buf;
__u64 tmp_val;
int ret;
if (gup_fd < 0) {
ksft_test_result_skip("gup_test not available\n");
return;
}
tmp = malloc(size);
if (!tmp) {
ksft_test_result_fail("malloc() failed\n");
return;
}
ret = setup_comm_pipes(&comm_pipes);
if (ret) {
ksft_test_result_fail("pipe() failed\n");
goto free_tmp;
}
switch (test) {
case RO_PIN_TEST_SHARED:
case RO_PIN_TEST_PREVIOUSLY_SHARED:
/*
* Share the pages with our child. As the pages are not pinned,
* this should just work.
*/
ret = fork();
if (ret < 0) {
ksft_test_result_fail("fork() failed\n");
goto close_comm_pipes;
} else if (!ret) {
write(comm_pipes.child_ready[1], "0", 1);
while (read(comm_pipes.parent_ready[0], &buf, 1) != 1)
;
exit(0);
}
/* Wait until our child is ready. */
while (read(comm_pipes.child_ready[0], &buf, 1) != 1)
;
if (test == RO_PIN_TEST_PREVIOUSLY_SHARED) {
/*
* Tell the child to quit now and wait until it quit.
* The pages should now be mapped R/O into our page
* tables, but they are no longer shared.
*/
write(comm_pipes.parent_ready[1], "0", 1);
wait(&ret);
if (!WIFEXITED(ret))
ksft_print_msg("[INFO] wait() failed\n");
}
break;
case RO_PIN_TEST_RO_EXCLUSIVE:
/*
* Map the page R/O into the page table. Enable softdirty
* tracking to stop the page from getting mapped R/W immediately
* again by mprotect() optimizations. Note that we don't have an
* easy way to test if that worked (the pagemap does not export
* if the page is mapped R/O vs. R/W).
*/
ret = mprotect(mem, size, PROT_READ);
clear_softdirty();
ret |= mprotect(mem, size, PROT_READ | PROT_WRITE);
if (ret) {
ksft_test_result_fail("mprotect() failed\n");
goto close_comm_pipes;
}
break;
default:
assert(false);
}
/* Take a R/O pin. This should trigger unsharing. */
args.addr = (__u64)mem;
args.size = size;
args.flags = fast ? PIN_LONGTERM_TEST_FLAG_USE_FAST : 0;
ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args);
if (ret) {
if (errno == EINVAL)
ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n");
else
ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n");
goto wait;
}
/* Modify the page. */
memset(mem, 0xff, size);
/*
* Read back the content via the pin to the temporary buffer and
* test if we observed the modification.
*/
tmp_val = (__u64)tmp;
ret = ioctl(gup_fd, PIN_LONGTERM_TEST_READ, &tmp_val);
if (ret)
ksft_test_result_fail("PIN_LONGTERM_TEST_READ failed\n");
else
ksft_test_result(!memcmp(mem, tmp, size),
"Longterm R/O pin is reliable\n");
ret = ioctl(gup_fd, PIN_LONGTERM_TEST_STOP);
if (ret)
ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n");
wait:
switch (test) {
case RO_PIN_TEST_SHARED:
write(comm_pipes.parent_ready[1], "0", 1);
wait(&ret);
if (!WIFEXITED(ret))
ksft_print_msg("[INFO] wait() failed\n");
break;
default:
break;
}
close_comm_pipes:
close_comm_pipes(&comm_pipes);
free_tmp:
free(tmp);
}
static void test_ro_pin_on_shared(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_SHARED, false);
}
static void test_ro_fast_pin_on_shared(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_SHARED, true);
}
static void test_ro_pin_on_ro_previously_shared(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_PREVIOUSLY_SHARED, false);
}
static void test_ro_fast_pin_on_ro_previously_shared(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_PREVIOUSLY_SHARED, true);
}
static void test_ro_pin_on_ro_exclusive(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_RO_EXCLUSIVE, false);
}
static void test_ro_fast_pin_on_ro_exclusive(char *mem, size_t size)
{
do_test_ro_pin(mem, size, RO_PIN_TEST_RO_EXCLUSIVE, true);
}
typedef void (*test_fn)(char *mem, size_t size);
static void do_run_with_base_page(test_fn fn, bool swapout)
{
char *mem;
int ret;
mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (mem == MAP_FAILED) {
ksft_test_result_fail("mmap() failed\n");
return;
}
ret = madvise(mem, pagesize, MADV_NOHUGEPAGE);
/* Ignore if not around on a kernel. */
if (ret && errno != EINVAL) {
ksft_test_result_fail("MADV_NOHUGEPAGE failed\n");
goto munmap;
}
/* Populate a base page. */
memset(mem, 0, pagesize);
if (swapout) {
madvise(mem, pagesize, MADV_PAGEOUT);
if (!pagemap_is_swapped(pagemap_fd, mem)) {
ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n");
goto munmap;
}
}
fn(mem, pagesize);
munmap:
munmap(mem, pagesize);
}
static void run_with_base_page(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with base page\n", desc);
do_run_with_base_page(fn, false);
}
static void run_with_base_page_swap(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with swapped out base page\n", desc);
do_run_with_base_page(fn, true);
}
enum thp_run {
THP_RUN_PMD,
THP_RUN_PMD_SWAPOUT,
THP_RUN_PTE,
THP_RUN_PTE_SWAPOUT,
THP_RUN_SINGLE_PTE,
THP_RUN_SINGLE_PTE_SWAPOUT,
THP_RUN_PARTIAL_MREMAP,
THP_RUN_PARTIAL_SHARED,
};
static void do_run_with_thp(test_fn fn, enum thp_run thp_run)
{
char *mem, *mmap_mem, *tmp, *mremap_mem = MAP_FAILED;
size_t size, mmap_size, mremap_size;
int ret;
/* For alignment purposes, we need twice the thp size. */
mmap_size = 2 * thpsize;
mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (mmap_mem == MAP_FAILED) {
ksft_test_result_fail("mmap() failed\n");
return;
}
/* We need a THP-aligned memory area. */
mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1));
ret = madvise(mem, thpsize, MADV_HUGEPAGE);
if (ret) {
ksft_test_result_fail("MADV_HUGEPAGE failed\n");
goto munmap;
}
/*
* Try to populate a THP. Touch the first sub-page and test if we get
* another sub-page populated automatically.
*/
mem[0] = 0;
if (!pagemap_is_populated(pagemap_fd, mem + pagesize)) {
ksft_test_result_skip("Did not get a THP populated\n");
goto munmap;
}
memset(mem, 0, thpsize);
size = thpsize;
switch (thp_run) {
case THP_RUN_PMD:
case THP_RUN_PMD_SWAPOUT:
break;
case THP_RUN_PTE:
case THP_RUN_PTE_SWAPOUT:
/*
* Trigger PTE-mapping the THP by temporarily mapping a single
* subpage R/O.
*/
ret = mprotect(mem + pagesize, pagesize, PROT_READ);
if (ret) {
ksft_test_result_fail("mprotect() failed\n");
goto munmap;
}
ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE);
if (ret) {
ksft_test_result_fail("mprotect() failed\n");
goto munmap;
}
break;
case THP_RUN_SINGLE_PTE:
case THP_RUN_SINGLE_PTE_SWAPOUT:
/*
* Discard all but a single subpage of that PTE-mapped THP. What
* remains is a single PTE mapping a single subpage.
*/
ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTNEED);
if (ret) {
ksft_test_result_fail("MADV_DONTNEED failed\n");
goto munmap;
}
size = pagesize;
break;
case THP_RUN_PARTIAL_MREMAP:
/*
* Remap half of the THP. We need some new memory location
* for that.
*/
mremap_size = thpsize / 2;
mremap_mem = mmap(NULL, mremap_size, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (mem == MAP_FAILED) {
ksft_test_result_fail("mmap() failed\n");
goto munmap;
}
tmp = mremap(mem + mremap_size, mremap_size, mremap_size,
MREMAP_MAYMOVE | MREMAP_FIXED, mremap_mem);
if (tmp != mremap_mem) {
ksft_test_result_fail("mremap() failed\n");
goto munmap;
}
size = mremap_size;
break;
case THP_RUN_PARTIAL_SHARED:
/*
* Share the first page of the THP with a child and quit the
* child. This will result in some parts of the THP never
* have been shared.
*/
ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTFORK);
if (ret) {
ksft_test_result_fail("MADV_DONTFORK failed\n");
goto munmap;
}
ret = fork();
if (ret < 0) {
ksft_test_result_fail("fork() failed\n");
goto munmap;
} else if (!ret) {
exit(0);
}
wait(&ret);
/* Allow for sharing all pages again. */
ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DOFORK);
if (ret) {
ksft_test_result_fail("MADV_DOFORK failed\n");
goto munmap;
}
break;
default:
assert(false);
}
switch (thp_run) {
case THP_RUN_PMD_SWAPOUT:
case THP_RUN_PTE_SWAPOUT:
case THP_RUN_SINGLE_PTE_SWAPOUT:
madvise(mem, size, MADV_PAGEOUT);
if (!range_is_swapped(mem, size)) {
ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n");
goto munmap;
}
break;
default:
break;
}
fn(mem, size);
munmap:
munmap(mmap_mem, mmap_size);
if (mremap_mem != MAP_FAILED)
munmap(mremap_mem, mremap_size);
}
static void run_with_thp(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with THP\n", desc);
do_run_with_thp(fn, THP_RUN_PMD);
}
static void run_with_thp_swap(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with swapped-out THP\n", desc);
do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT);
}
static void run_with_pte_mapped_thp(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with PTE-mapped THP\n", desc);
do_run_with_thp(fn, THP_RUN_PTE);
}
static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP\n", desc);
do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT);
}
static void run_with_single_pte_of_thp(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with single PTE of THP\n", desc);
do_run_with_thp(fn, THP_RUN_SINGLE_PTE);
}
static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP\n", desc);
do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT);
}
static void run_with_partial_mremap_thp(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP\n", desc);
do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP);
}
static void run_with_partial_shared_thp(test_fn fn, const char *desc)
{
ksft_print_msg("[RUN] %s ... with partially shared THP\n", desc);
do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED);
}
static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize)
{
int flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB;
char *mem, *dummy;
ksft_print_msg("[RUN] %s ... with hugetlb (%zu kB)\n", desc,
hugetlbsize / 1024);
flags |= __builtin_ctzll(hugetlbsize) << MAP_HUGE_SHIFT;
mem = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0);
if (mem == MAP_FAILED) {
ksft_test_result_skip("need more free huge pages\n");
return;
}
/* Populate an huge page. */
memset(mem, 0, hugetlbsize);
/*
* We need a total of two hugetlb pages to handle COW/unsharing
* properly, otherwise we might get zapped by a SIGBUS.
*/
dummy = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0);
if (dummy == MAP_FAILED) {
ksft_test_result_skip("need more free huge pages\n");
goto munmap;
}
munmap(dummy, hugetlbsize);
fn(mem, hugetlbsize);
munmap:
munmap(mem, hugetlbsize);
}
struct test_case {
const char *desc;
test_fn fn;
};
static const struct test_case test_cases[] = {
/*
* Basic COW tests for fork() without any GUP. If we miss to break COW,
* either the child can observe modifications by the parent or the
* other way around.
*/
{
"Basic COW after fork()",
test_cow_in_parent,
},
/*
* vmsplice() [R/O GUP] + unmap in the child; modify in the parent. If
* we miss to break COW, the child observes modifications by the parent.
* This is CVE-2020-29374 reported by Jann Horn.
*/
{
"vmsplice() + unmap in child",
test_vmsplice_in_child
},
/*
* vmsplice() [R/O GUP] in parent before fork(), unmap in parent after
* fork(); modify in the child. If we miss to break COW, the parent
* observes modifications by the child.
*/
{
"vmsplice() before fork(), unmap in parent after fork()",
test_vmsplice_before_fork,
},
/*
* vmsplice() [R/O GUP] + unmap in parent after fork(); modify in the
* child. If we miss to break COW, the parent observes modifications by
* the child.
*/
{
"vmsplice() + unmap in parent after fork()",
test_vmsplice_after_fork,
},
#ifdef LOCAL_CONFIG_HAVE_LIBURING
/*
* Take a R/W longterm pin and then map the page R/O into the page
* table to trigger a write fault on next access. When modifying the
* page, the page content must be visible via the pin.
*/
{
"R/O-mapping a page registered as iouring fixed buffer",
test_iouring_ro,
},
/*
* Take a R/W longterm pin and then fork() a child. When modifying the
* page, the page content must be visible via the pin. We expect the
* pinned page to not get shared with the child.
*/
{
"fork() with an iouring fixed buffer",
test_iouring_fork,
},
#endif /* LOCAL_CONFIG_HAVE_LIBURING */
/*
* Take a R/O longterm pin on a R/O-mapped shared anonymous page.
* When modifying the page via the page table, the page content change
* must be visible via the pin.
*/
{
"R/O GUP pin on R/O-mapped shared page",
test_ro_pin_on_shared,
},
/* Same as above, but using GUP-fast. */
{
"R/O GUP-fast pin on R/O-mapped shared page",
test_ro_fast_pin_on_shared,
},
/*
* Take a R/O longterm pin on a R/O-mapped exclusive anonymous page that
* was previously shared. When modifying the page via the page table,
* the page content change must be visible via the pin.
*/
{
"R/O GUP pin on R/O-mapped previously-shared page",
test_ro_pin_on_ro_previously_shared,
},
/* Same as above, but using GUP-fast. */
{
"R/O GUP-fast pin on R/O-mapped previously-shared page",
test_ro_fast_pin_on_ro_previously_shared,
},
/*
* Take a R/O longterm pin on a R/O-mapped exclusive anonymous page.
* When modifying the page via the page table, the page content change
* must be visible via the pin.
*/
{
"R/O GUP pin on R/O-mapped exclusive page",
test_ro_pin_on_ro_exclusive,
},
/* Same as above, but using GUP-fast. */
{
"R/O GUP-fast pin on R/O-mapped exclusive page",
test_ro_fast_pin_on_ro_exclusive,
},
};
static void run_test_case(struct test_case const *test_case)
{
int i;
run_with_base_page(test_case->fn, test_case->desc);
run_with_base_page_swap(test_case->fn, test_case->desc);
if (thpsize) {
run_with_thp(test_case->fn, test_case->desc);
run_with_thp_swap(test_case->fn, test_case->desc);
run_with_pte_mapped_thp(test_case->fn, test_case->desc);
run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc);
run_with_single_pte_of_thp(test_case->fn, test_case->desc);
run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc);
run_with_partial_mremap_thp(test_case->fn, test_case->desc);
run_with_partial_shared_thp(test_case->fn, test_case->desc);
}
for (i = 0; i < nr_hugetlbsizes; i++)
run_with_hugetlb(test_case->fn, test_case->desc,
hugetlbsizes[i]);
}
static void run_test_cases(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(test_cases); i++)
run_test_case(&test_cases[i]);
}
static int tests_per_test_case(void)
{
int tests = 2 + nr_hugetlbsizes;
if (thpsize)
tests += 8;
return tests;
}
int main(int argc, char **argv)
{
int nr_test_cases = ARRAY_SIZE(test_cases);
int err;
pagesize = getpagesize();
detect_thpsize();
detect_hugetlbsizes();
ksft_print_header();
ksft_set_plan(nr_test_cases * tests_per_test_case());
gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR);
pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
if (pagemap_fd < 0)
ksft_exit_fail_msg("opening pagemap failed\n");
run_test_cases();
err = ksft_get_fail_cnt();
if (err)
ksft_exit_fail_msg("%d out of %d tests failed\n",
err, ksft_test_num());
return ksft_exit_pass();
}
|