forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpage-types.c
1299 lines (1085 loc) · 28.4 KB
/
page-types.c
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
/*
* page-types: Tool for querying page flags
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; version 2.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should find a copy of v2 of the GNU General Public License somewhere on
* your Linux system; if not, write to the Free Software Foundation, Inc., 59
* Temple Place, Suite 330, Boston, MA 02111-1307 USA.
*
* Copyright (C) 2009 Intel corporation
*
* Authors: Wu Fengguang <[email protected]>
*/
#define _FILE_OFFSET_BITS 64
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdint.h>
#include <stdarg.h>
#include <string.h>
#include <getopt.h>
#include <limits.h>
#include <assert.h>
#include <ftw.h>
#include <time.h>
#include <setjmp.h>
#include <signal.h>
#include <sys/types.h>
#include <sys/errno.h>
#include <sys/fcntl.h>
#include <sys/mount.h>
#include <sys/statfs.h>
#include <sys/mman.h>
#include "../../include/uapi/linux/magic.h"
#include "../../include/uapi/linux/kernel-page-flags.h"
#include <api/fs/fs.h>
#ifndef MAX_PATH
# define MAX_PATH 256
#endif
#ifndef STR
# define _STR(x) #x
# define STR(x) _STR(x)
#endif
/*
* pagemap kernel ABI bits
*/
#define PM_ENTRY_BYTES 8
#define PM_PFRAME_BITS 55
#define PM_PFRAME_MASK ((1LL << PM_PFRAME_BITS) - 1)
#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
#define MAX_SWAPFILES_SHIFT 5
#define PM_SWAP_OFFSET(x) (((x) & PM_PFRAME_MASK) >> MAX_SWAPFILES_SHIFT)
#define PM_SOFT_DIRTY (1ULL << 55)
#define PM_MMAP_EXCLUSIVE (1ULL << 56)
#define PM_FILE (1ULL << 61)
#define PM_SWAP (1ULL << 62)
#define PM_PRESENT (1ULL << 63)
/*
* kernel page flags
*/
#define KPF_BYTES 8
#define PROC_KPAGEFLAGS "/proc/kpageflags"
#define PROC_KPAGECGROUP "/proc/kpagecgroup"
/* [32-] kernel hacking assistances */
#define KPF_RESERVED 32
#define KPF_MLOCKED 33
#define KPF_MAPPEDTODISK 34
#define KPF_PRIVATE 35
#define KPF_PRIVATE_2 36
#define KPF_OWNER_PRIVATE 37
#define KPF_ARCH 38
#define KPF_UNCACHED 39
#define KPF_SOFTDIRTY 40
/* [48-] take some arbitrary free slots for expanding overloaded flags
* not part of kernel API
*/
#define KPF_READAHEAD 48
#define KPF_SLOB_FREE 49
#define KPF_SLUB_FROZEN 50
#define KPF_SLUB_DEBUG 51
#define KPF_FILE 61
#define KPF_SWAP 62
#define KPF_MMAP_EXCLUSIVE 63
#define KPF_ALL_BITS ((uint64_t)~0ULL)
#define KPF_HACKERS_BITS (0xffffULL << 32)
#define KPF_OVERLOADED_BITS (0xffffULL << 48)
#define BIT(name) (1ULL << KPF_##name)
#define BITS_COMPOUND (BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
static const char * const page_flag_names[] = {
[KPF_LOCKED] = "L:locked",
[KPF_ERROR] = "E:error",
[KPF_REFERENCED] = "R:referenced",
[KPF_UPTODATE] = "U:uptodate",
[KPF_DIRTY] = "D:dirty",
[KPF_LRU] = "l:lru",
[KPF_ACTIVE] = "A:active",
[KPF_SLAB] = "S:slab",
[KPF_WRITEBACK] = "W:writeback",
[KPF_RECLAIM] = "I:reclaim",
[KPF_BUDDY] = "B:buddy",
[KPF_MMAP] = "M:mmap",
[KPF_ANON] = "a:anonymous",
[KPF_SWAPCACHE] = "s:swapcache",
[KPF_SWAPBACKED] = "b:swapbacked",
[KPF_COMPOUND_HEAD] = "H:compound_head",
[KPF_COMPOUND_TAIL] = "T:compound_tail",
[KPF_HUGE] = "G:huge",
[KPF_UNEVICTABLE] = "u:unevictable",
[KPF_HWPOISON] = "X:hwpoison",
[KPF_NOPAGE] = "n:nopage",
[KPF_KSM] = "x:ksm",
[KPF_THP] = "t:thp",
[KPF_BALLOON] = "o:balloon",
[KPF_ZERO_PAGE] = "z:zero_page",
[KPF_IDLE] = "i:idle_page",
[KPF_RESERVED] = "r:reserved",
[KPF_MLOCKED] = "m:mlocked",
[KPF_MAPPEDTODISK] = "d:mappedtodisk",
[KPF_PRIVATE] = "P:private",
[KPF_PRIVATE_2] = "p:private_2",
[KPF_OWNER_PRIVATE] = "O:owner_private",
[KPF_ARCH] = "h:arch",
[KPF_UNCACHED] = "c:uncached",
[KPF_SOFTDIRTY] = "f:softdirty",
[KPF_READAHEAD] = "I:readahead",
[KPF_SLOB_FREE] = "P:slob_free",
[KPF_SLUB_FROZEN] = "A:slub_frozen",
[KPF_SLUB_DEBUG] = "E:slub_debug",
[KPF_FILE] = "F:file",
[KPF_SWAP] = "w:swap",
[KPF_MMAP_EXCLUSIVE] = "1:mmap_exclusive",
};
static const char * const debugfs_known_mountpoints[] = {
"/sys/kernel/debug",
"/debug",
0,
};
/*
* data structures
*/
static int opt_raw; /* for kernel developers */
static int opt_list; /* list pages (in ranges) */
static int opt_no_summary; /* don't show summary */
static pid_t opt_pid; /* process to walk */
const char *opt_file; /* file or directory path */
static uint64_t opt_cgroup; /* cgroup inode */
static int opt_list_cgroup;/* list page cgroup */
static const char *opt_kpageflags;/* kpageflags file to parse */
#define MAX_ADDR_RANGES 1024
static int nr_addr_ranges;
static unsigned long opt_offset[MAX_ADDR_RANGES];
static unsigned long opt_size[MAX_ADDR_RANGES];
#define MAX_VMAS 10240
static int nr_vmas;
static unsigned long pg_start[MAX_VMAS];
static unsigned long pg_end[MAX_VMAS];
#define MAX_BIT_FILTERS 64
static int nr_bit_filters;
static uint64_t opt_mask[MAX_BIT_FILTERS];
static uint64_t opt_bits[MAX_BIT_FILTERS];
static int page_size;
static int pagemap_fd;
static int kpageflags_fd;
static int kpagecgroup_fd = -1;
static int opt_hwpoison;
static int opt_unpoison;
static const char *hwpoison_debug_fs;
static int hwpoison_inject_fd;
static int hwpoison_forget_fd;
#define HASH_SHIFT 13
#define HASH_SIZE (1 << HASH_SHIFT)
#define HASH_MASK (HASH_SIZE - 1)
#define HASH_KEY(flags) (flags & HASH_MASK)
static unsigned long total_pages;
static unsigned long nr_pages[HASH_SIZE];
static uint64_t page_flags[HASH_SIZE];
/*
* helper functions
*/
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#define min_t(type, x, y) ({ \
type __min1 = (x); \
type __min2 = (y); \
__min1 < __min2 ? __min1 : __min2; })
#define max_t(type, x, y) ({ \
type __max1 = (x); \
type __max2 = (y); \
__max1 > __max2 ? __max1 : __max2; })
static unsigned long pages2mb(unsigned long pages)
{
return (pages * page_size) >> 20;
}
static void fatal(const char *x, ...)
{
va_list ap;
va_start(ap, x);
vfprintf(stderr, x, ap);
va_end(ap);
exit(EXIT_FAILURE);
}
static int checked_open(const char *pathname, int flags)
{
int fd = open(pathname, flags);
if (fd < 0) {
perror(pathname);
exit(EXIT_FAILURE);
}
return fd;
}
/*
* pagemap/kpageflags routines
*/
static unsigned long do_u64_read(int fd, const char *name,
uint64_t *buf,
unsigned long index,
unsigned long count)
{
long bytes;
if (index > ULONG_MAX / 8)
fatal("index overflow: %lu\n", index);
bytes = pread(fd, buf, count * 8, (off_t)index * 8);
if (bytes < 0) {
perror(name);
exit(EXIT_FAILURE);
}
if (bytes % 8)
fatal("partial read: %lu bytes\n", bytes);
return bytes / 8;
}
static unsigned long kpageflags_read(uint64_t *buf,
unsigned long index,
unsigned long pages)
{
return do_u64_read(kpageflags_fd, opt_kpageflags, buf, index, pages);
}
static unsigned long kpagecgroup_read(uint64_t *buf,
unsigned long index,
unsigned long pages)
{
if (kpagecgroup_fd < 0)
return pages;
return do_u64_read(kpagecgroup_fd, opt_kpageflags, buf, index, pages);
}
static unsigned long pagemap_read(uint64_t *buf,
unsigned long index,
unsigned long pages)
{
return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
}
static unsigned long pagemap_pfn(uint64_t val)
{
unsigned long pfn;
if (val & PM_PRESENT)
pfn = PM_PFRAME(val);
else
pfn = 0;
return pfn;
}
static unsigned long pagemap_swap_offset(uint64_t val)
{
return val & PM_SWAP ? PM_SWAP_OFFSET(val) : 0;
}
/*
* page flag names
*/
static char *page_flag_name(uint64_t flags)
{
static char buf[65];
int present;
size_t i, j;
for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
present = (flags >> i) & 1;
if (!page_flag_names[i]) {
if (present)
fatal("unknown flag bit %d\n", i);
continue;
}
buf[j++] = present ? page_flag_names[i][0] : '_';
}
return buf;
}
static char *page_flag_longname(uint64_t flags)
{
static char buf[1024];
size_t i, n;
for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
if (!page_flag_names[i])
continue;
if ((flags >> i) & 1)
n += snprintf(buf + n, sizeof(buf) - n, "%s,",
page_flag_names[i] + 2);
}
if (n)
n--;
buf[n] = '\0';
return buf;
}
/*
* page list and summary
*/
static void show_page_range(unsigned long voffset, unsigned long offset,
unsigned long size, uint64_t flags, uint64_t cgroup)
{
static uint64_t flags0;
static uint64_t cgroup0;
static unsigned long voff;
static unsigned long index;
static unsigned long count;
if (flags == flags0 && cgroup == cgroup0 && offset == index + count &&
size && voffset == voff + count) {
count += size;
return;
}
if (count) {
if (opt_pid)
printf("%lx\t", voff);
if (opt_file)
printf("%lu\t", voff);
if (opt_list_cgroup)
printf("@%llu\t", (unsigned long long)cgroup0);
printf("%lx\t%lx\t%s\n",
index, count, page_flag_name(flags0));
}
flags0 = flags;
cgroup0= cgroup;
index = offset;
voff = voffset;
count = size;
}
static void flush_page_range(void)
{
show_page_range(0, 0, 0, 0, 0);
}
static void show_page(unsigned long voffset, unsigned long offset,
uint64_t flags, uint64_t cgroup)
{
if (opt_pid)
printf("%lx\t", voffset);
if (opt_file)
printf("%lu\t", voffset);
if (opt_list_cgroup)
printf("@%llu\t", (unsigned long long)cgroup);
printf("%lx\t%s\n", offset, page_flag_name(flags));
}
static void show_summary(void)
{
size_t i;
printf(" flags\tpage-count MB"
" symbolic-flags\t\t\tlong-symbolic-flags\n");
for (i = 0; i < ARRAY_SIZE(nr_pages); i++) {
if (nr_pages[i])
printf("0x%016llx\t%10lu %8lu %s\t%s\n",
(unsigned long long)page_flags[i],
nr_pages[i],
pages2mb(nr_pages[i]),
page_flag_name(page_flags[i]),
page_flag_longname(page_flags[i]));
}
printf(" total\t%10lu %8lu\n",
total_pages, pages2mb(total_pages));
}
/*
* page flag filters
*/
static int bit_mask_ok(uint64_t flags)
{
int i;
for (i = 0; i < nr_bit_filters; i++) {
if (opt_bits[i] == KPF_ALL_BITS) {
if ((flags & opt_mask[i]) == 0)
return 0;
} else {
if ((flags & opt_mask[i]) != opt_bits[i])
return 0;
}
}
return 1;
}
static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
{
/* SLOB/SLUB overload several page flags */
if (flags & BIT(SLAB)) {
if (flags & BIT(PRIVATE))
flags ^= BIT(PRIVATE) | BIT(SLOB_FREE);
if (flags & BIT(ACTIVE))
flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN);
if (flags & BIT(ERROR))
flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
}
/* PG_reclaim is overloaded as PG_readahead in the read path */
if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
flags ^= BIT(RECLAIM) | BIT(READAHEAD);
if (pme & PM_SOFT_DIRTY)
flags |= BIT(SOFTDIRTY);
if (pme & PM_FILE)
flags |= BIT(FILE);
if (pme & PM_SWAP)
flags |= BIT(SWAP);
if (pme & PM_MMAP_EXCLUSIVE)
flags |= BIT(MMAP_EXCLUSIVE);
return flags;
}
static uint64_t well_known_flags(uint64_t flags)
{
/* hide flags intended only for kernel hacker */
flags &= ~KPF_HACKERS_BITS;
/* hide non-hugeTLB compound pages */
if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE)))
flags &= ~BITS_COMPOUND;
return flags;
}
static uint64_t kpageflags_flags(uint64_t flags, uint64_t pme)
{
if (opt_raw)
flags = expand_overloaded_flags(flags, pme);
else
flags = well_known_flags(flags);
return flags;
}
/*
* page actions
*/
static void prepare_hwpoison_fd(void)
{
char buf[MAX_PATH + 1];
hwpoison_debug_fs = debugfs__mount();
if (!hwpoison_debug_fs) {
perror("mount debugfs");
exit(EXIT_FAILURE);
}
if (opt_hwpoison && !hwpoison_inject_fd) {
snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",
hwpoison_debug_fs);
hwpoison_inject_fd = checked_open(buf, O_WRONLY);
}
if (opt_unpoison && !hwpoison_forget_fd) {
snprintf(buf, MAX_PATH, "%s/hwpoison/unpoison-pfn",
hwpoison_debug_fs);
hwpoison_forget_fd = checked_open(buf, O_WRONLY);
}
}
static int hwpoison_page(unsigned long offset)
{
char buf[100];
int len;
len = sprintf(buf, "0x%lx\n", offset);
len = write(hwpoison_inject_fd, buf, len);
if (len < 0) {
perror("hwpoison inject");
return len;
}
return 0;
}
static int unpoison_page(unsigned long offset)
{
char buf[100];
int len;
len = sprintf(buf, "0x%lx\n", offset);
len = write(hwpoison_forget_fd, buf, len);
if (len < 0) {
perror("hwpoison forget");
return len;
}
return 0;
}
/*
* page frame walker
*/
static size_t hash_slot(uint64_t flags)
{
size_t k = HASH_KEY(flags);
size_t i;
/* Explicitly reserve slot 0 for flags 0: the following logic
* cannot distinguish an unoccupied slot from slot (flags==0).
*/
if (flags == 0)
return 0;
/* search through the remaining (HASH_SIZE-1) slots */
for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) {
if (!k || k >= ARRAY_SIZE(page_flags))
k = 1;
if (page_flags[k] == 0) {
page_flags[k] = flags;
return k;
}
if (page_flags[k] == flags)
return k;
}
fatal("hash table full: bump up HASH_SHIFT?\n");
exit(EXIT_FAILURE);
}
static void add_page(unsigned long voffset, unsigned long offset,
uint64_t flags, uint64_t cgroup, uint64_t pme)
{
flags = kpageflags_flags(flags, pme);
if (!bit_mask_ok(flags))
return;
if (opt_cgroup && cgroup != (uint64_t)opt_cgroup)
return;
if (opt_hwpoison)
hwpoison_page(offset);
if (opt_unpoison)
unpoison_page(offset);
if (opt_list == 1)
show_page_range(voffset, offset, 1, flags, cgroup);
else if (opt_list == 2)
show_page(voffset, offset, flags, cgroup);
nr_pages[hash_slot(flags)]++;
total_pages++;
}
#define KPAGEFLAGS_BATCH (64 << 10) /* 64k pages */
static void walk_pfn(unsigned long voffset,
unsigned long index,
unsigned long count,
uint64_t pme)
{
uint64_t buf[KPAGEFLAGS_BATCH];
uint64_t cgi[KPAGEFLAGS_BATCH];
unsigned long batch;
unsigned long pages;
unsigned long i;
/*
* kpagecgroup_read() reads only if kpagecgroup were opened, but
* /proc/kpagecgroup might even not exist, so it's better to fill
* them with zeros here.
*/
if (count == 1)
cgi[0] = 0;
else
memset(cgi, 0, sizeof cgi);
while (count) {
batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
pages = kpageflags_read(buf, index, batch);
if (pages == 0)
break;
if (kpagecgroup_read(cgi, index, pages) != pages)
fatal("kpagecgroup returned fewer pages than expected");
for (i = 0; i < pages; i++)
add_page(voffset + i, index + i, buf[i], cgi[i], pme);
index += pages;
count -= pages;
}
}
static void walk_swap(unsigned long voffset, uint64_t pme)
{
uint64_t flags = kpageflags_flags(0, pme);
if (!bit_mask_ok(flags))
return;
if (opt_cgroup)
return;
if (opt_list == 1)
show_page_range(voffset, pagemap_swap_offset(pme), 1, flags, 0);
else if (opt_list == 2)
show_page(voffset, pagemap_swap_offset(pme), flags, 0);
nr_pages[hash_slot(flags)]++;
total_pages++;
}
#define PAGEMAP_BATCH (64 << 10)
static void walk_vma(unsigned long index, unsigned long count)
{
uint64_t buf[PAGEMAP_BATCH];
unsigned long batch;
unsigned long pages;
unsigned long pfn;
unsigned long i;
while (count) {
batch = min_t(unsigned long, count, PAGEMAP_BATCH);
pages = pagemap_read(buf, index, batch);
if (pages == 0)
break;
for (i = 0; i < pages; i++) {
pfn = pagemap_pfn(buf[i]);
if (pfn)
walk_pfn(index + i, pfn, 1, buf[i]);
if (buf[i] & PM_SWAP)
walk_swap(index + i, buf[i]);
}
index += pages;
count -= pages;
}
}
static void walk_task(unsigned long index, unsigned long count)
{
const unsigned long end = index + count;
unsigned long start;
int i = 0;
while (index < end) {
while (pg_end[i] <= index)
if (++i >= nr_vmas)
return;
if (pg_start[i] >= end)
return;
start = max_t(unsigned long, pg_start[i], index);
index = min_t(unsigned long, pg_end[i], end);
assert(start < index);
walk_vma(start, index - start);
}
}
static void add_addr_range(unsigned long offset, unsigned long size)
{
if (nr_addr_ranges >= MAX_ADDR_RANGES)
fatal("too many addr ranges\n");
opt_offset[nr_addr_ranges] = offset;
opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset);
nr_addr_ranges++;
}
static void walk_addr_ranges(void)
{
int i;
kpageflags_fd = checked_open(opt_kpageflags, O_RDONLY);
if (!nr_addr_ranges)
add_addr_range(0, ULONG_MAX);
for (i = 0; i < nr_addr_ranges; i++)
if (!opt_pid)
walk_pfn(opt_offset[i], opt_offset[i], opt_size[i], 0);
else
walk_task(opt_offset[i], opt_size[i]);
close(kpageflags_fd);
}
/*
* user interface
*/
static const char *page_flag_type(uint64_t flag)
{
if (flag & KPF_HACKERS_BITS)
return "(r)";
if (flag & KPF_OVERLOADED_BITS)
return "(o)";
return " ";
}
static void usage(void)
{
size_t i, j;
printf(
"page-types [options]\n"
" -r|--raw Raw mode, for kernel developers\n"
" -d|--describe flags Describe flags\n"
" -a|--addr addr-spec Walk a range of pages\n"
" -b|--bits bits-spec Walk pages with specified bits\n"
" -c|--cgroup path|@inode Walk pages within memory cgroup\n"
" -p|--pid pid Walk process address space\n"
" -f|--file filename Walk file address space\n"
" -l|--list Show page details in ranges\n"
" -L|--list-each Show page details one by one\n"
" -C|--list-cgroup Show cgroup inode for pages\n"
" -N|--no-summary Don't show summary info\n"
" -X|--hwpoison hwpoison pages\n"
" -x|--unpoison unpoison pages\n"
" -F|--kpageflags filename kpageflags file to parse\n"
" -h|--help Show this usage message\n"
"flags:\n"
" 0x10 bitfield format, e.g.\n"
" anon bit-name, e.g.\n"
" 0x10,anon comma-separated list, e.g.\n"
"addr-spec:\n"
" N one page at offset N (unit: pages)\n"
" N+M pages range from N to N+M-1\n"
" N,M pages range from N to M-1\n"
" N, pages range from N to end\n"
" ,M pages range from 0 to M-1\n"
"bits-spec:\n"
" bit1,bit2 (flags & (bit1|bit2)) != 0\n"
" bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1\n"
" bit1,~bit2 (flags & (bit1|bit2)) == bit1\n"
" =bit1,bit2 flags == (bit1|bit2)\n"
"bit-names:\n"
);
for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
if (!page_flag_names[i])
continue;
printf("%16s%s", page_flag_names[i] + 2,
page_flag_type(1ULL << i));
if (++j > 3) {
j = 0;
putchar('\n');
}
}
printf("\n "
"(r) raw mode bits (o) overloaded bits\n");
}
static unsigned long long parse_number(const char *str)
{
unsigned long long n;
n = strtoll(str, NULL, 0);
if (n == 0 && str[0] != '0')
fatal("invalid name or number: %s\n", str);
return n;
}
static void parse_pid(const char *str)
{
FILE *file;
char buf[5000];
opt_pid = parse_number(str);
sprintf(buf, "/proc/%d/pagemap", opt_pid);
pagemap_fd = checked_open(buf, O_RDONLY);
sprintf(buf, "/proc/%d/maps", opt_pid);
file = fopen(buf, "r");
if (!file) {
perror(buf);
exit(EXIT_FAILURE);
}
while (fgets(buf, sizeof(buf), file) != NULL) {
unsigned long vm_start;
unsigned long vm_end;
unsigned long long pgoff;
int major, minor;
char r, w, x, s;
unsigned long ino;
int n;
n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu",
&vm_start,
&vm_end,
&r, &w, &x, &s,
&pgoff,
&major, &minor,
&ino);
if (n < 10) {
fprintf(stderr, "unexpected line: %s\n", buf);
continue;
}
pg_start[nr_vmas] = vm_start / page_size;
pg_end[nr_vmas] = vm_end / page_size;
if (++nr_vmas >= MAX_VMAS) {
fprintf(stderr, "too many VMAs\n");
break;
}
}
fclose(file);
}
static void show_file(const char *name, const struct stat *st)
{
unsigned long long size = st->st_size;
char atime[64], mtime[64];
long now = time(NULL);
printf("%s\tInode: %u\tSize: %llu (%llu pages)\n",
name, (unsigned)st->st_ino,
size, (size + page_size - 1) / page_size);
strftime(atime, sizeof(atime), "%c", localtime(&st->st_atime));
strftime(mtime, sizeof(mtime), "%c", localtime(&st->st_mtime));
printf("Modify: %s (%ld seconds ago)\nAccess: %s (%ld seconds ago)\n",
mtime, now - st->st_mtime,
atime, now - st->st_atime);
}
static sigjmp_buf sigbus_jmp;
static void * volatile sigbus_addr;
static void sigbus_handler(int sig, siginfo_t *info, void *ucontex)
{
(void)sig;
(void)ucontex;
sigbus_addr = info ? info->si_addr : NULL;
siglongjmp(sigbus_jmp, 1);
}
static struct sigaction sigbus_action = {
.sa_sigaction = sigbus_handler,
.sa_flags = SA_SIGINFO,
};
static void walk_file(const char *name, const struct stat *st)
{
uint8_t vec[PAGEMAP_BATCH];
uint64_t buf[PAGEMAP_BATCH], flags;
uint64_t cgroup = 0;
unsigned long nr_pages, pfn, i;
off_t off, end = st->st_size;
int fd;
ssize_t len;
void *ptr;
int first = 1;
fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW);
for (off = 0; off < end; off += len) {
nr_pages = (end - off + page_size - 1) / page_size;
if (nr_pages > PAGEMAP_BATCH)
nr_pages = PAGEMAP_BATCH;
len = nr_pages * page_size;
ptr = mmap(NULL, len, PROT_READ, MAP_SHARED, fd, off);
if (ptr == MAP_FAILED)
fatal("mmap failed: %s", name);
/* determine cached pages */
if (mincore(ptr, len, vec))
fatal("mincore failed: %s", name);
/* turn off readahead */
if (madvise(ptr, len, MADV_RANDOM))
fatal("madvice failed: %s", name);
if (sigsetjmp(sigbus_jmp, 1)) {
end = off + sigbus_addr ? sigbus_addr - ptr : 0;
fprintf(stderr, "got sigbus at offset %lld: %s\n",
(long long)end, name);
goto got_sigbus;
}
/* populate ptes */
for (i = 0; i < nr_pages ; i++) {
if (vec[i] & 1)
(void)*(volatile int *)(ptr + i * page_size);
}
got_sigbus:
/* turn off harvesting reference bits */
if (madvise(ptr, len, MADV_SEQUENTIAL))
fatal("madvice failed: %s", name);
if (pagemap_read(buf, (unsigned long)ptr / page_size,
nr_pages) != nr_pages)
fatal("cannot read pagemap");
munmap(ptr, len);
for (i = 0; i < nr_pages; i++) {
pfn = pagemap_pfn(buf[i]);
if (!pfn)
continue;
if (!kpageflags_read(&flags, pfn, 1))
continue;
if (!kpagecgroup_read(&cgroup, pfn, 1))
fatal("kpagecgroup_read failed");
if (first && opt_list) {
first = 0;
flush_page_range();
show_file(name, st);
}
add_page(off / page_size + i, pfn,
flags, cgroup, buf[i]);
}
}
close(fd);
}
int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f)
{