forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 4
/
debug_vm_pgtable.c
1335 lines (1123 loc) · 38.1 KB
/
debug_vm_pgtable.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
// SPDX-License-Identifier: GPL-2.0-only
/*
* This kernel test validates architecture page table helpers and
* accessors and helps in verifying their continued compliance with
* expected generic MM semantics.
*
* Copyright (C) 2019 ARM Ltd.
*
* Author: Anshuman Khandual <[email protected]>
*/
#define pr_fmt(fmt) "debug_vm_pgtable: [%-25s]: " fmt, __func__
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/kconfig.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mm_types.h>
#include <linux/module.h>
#include <linux/pfn_t.h>
#include <linux/printk.h>
#include <linux/pgtable.h>
#include <linux/random.h>
#include <linux/spinlock.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/start_kernel.h>
#include <linux/sched/mm.h>
#include <linux/io.h>
#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
/*
* Please refer Documentation/vm/arch_pgtable_helpers.rst for the semantics
* expectations that are being validated here. All future changes in here
* or the documentation need to be in sync.
*/
#define VMFLAGS (VM_READ|VM_WRITE|VM_EXEC)
/*
* On s390 platform, the lower 4 bits are used to identify given page table
* entry type. But these bits might affect the ability to clear entries with
* pxx_clear() because of how dynamic page table folding works on s390. So
* while loading up the entries do not change the lower 4 bits. It does not
* have affect any other platform. Also avoid the 62nd bit on ppc64 that is
* used to mark a pte entry.
*/
#define S390_SKIP_MASK GENMASK(3, 0)
#if __BITS_PER_LONG == 64
#define PPC64_SKIP_MASK GENMASK(62, 62)
#else
#define PPC64_SKIP_MASK 0x0
#endif
#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK)
#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK)
#define RANDOM_NZVALUE GENMASK(7, 0)
struct pgtable_debug_args {
struct mm_struct *mm;
struct vm_area_struct *vma;
pgd_t *pgdp;
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
p4d_t *start_p4dp;
pud_t *start_pudp;
pmd_t *start_pmdp;
pgtable_t start_ptep;
unsigned long vaddr;
pgprot_t page_prot;
pgprot_t page_prot_none;
bool is_contiguous_page;
unsigned long pud_pfn;
unsigned long pmd_pfn;
unsigned long pte_pfn;
unsigned long fixed_pgd_pfn;
unsigned long fixed_p4d_pfn;
unsigned long fixed_pud_pfn;
unsigned long fixed_pmd_pfn;
unsigned long fixed_pte_pfn;
};
static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx)
{
pgprot_t prot = protection_map[idx];
pte_t pte = pfn_pte(args->fixed_pte_pfn, prot);
unsigned long val = idx, *ptr = &val;
pr_debug("Validating PTE basic (%pGv)\n", ptr);
/*
* This test needs to be executed after the given page table entry
* is created with pfn_pte() to make sure that protection_map[idx]
* does not have the dirty bit enabled from the beginning. This is
* important for platforms like arm64 where (!PTE_RDONLY) indicate
* dirty bit being set.
*/
WARN_ON(pte_dirty(pte_wrprotect(pte)));
WARN_ON(!pte_same(pte, pte));
WARN_ON(!pte_young(pte_mkyoung(pte_mkold(pte))));
WARN_ON(!pte_dirty(pte_mkdirty(pte_mkclean(pte))));
WARN_ON(!pte_write(pte_mkwrite(pte_wrprotect(pte))));
WARN_ON(pte_young(pte_mkold(pte_mkyoung(pte))));
WARN_ON(pte_dirty(pte_mkclean(pte_mkdirty(pte))));
WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte))));
WARN_ON(pte_dirty(pte_wrprotect(pte_mkclean(pte))));
WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte))));
}
static void __init pte_advanced_tests(struct pgtable_debug_args *args)
{
struct page *page;
pte_t pte;
/*
* Architectures optimize set_pte_at by avoiding TLB flush.
* This requires set_pte_at to be not used to update an
* existing pte entry. Clear pte before we do set_pte_at
*
* flush_dcache_page() is called after set_pte_at() to clear
* PG_arch_1 for the page on ARM64. The page flag isn't cleared
* when it's released and page allocation check will fail when
* the page is allocated again. For architectures other than ARM64,
* the unexpected overhead of cache flushing is acceptable.
*/
page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
if (!page)
return;
pr_debug("Validating PTE advanced\n");
pte = pfn_pte(args->pte_pfn, args->page_prot);
set_pte_at(args->mm, args->vaddr, args->ptep, pte);
flush_dcache_page(page);
ptep_set_wrprotect(args->mm, args->vaddr, args->ptep);
pte = ptep_get(args->ptep);
WARN_ON(pte_write(pte));
ptep_get_and_clear(args->mm, args->vaddr, args->ptep);
pte = ptep_get(args->ptep);
WARN_ON(!pte_none(pte));
pte = pfn_pte(args->pte_pfn, args->page_prot);
pte = pte_wrprotect(pte);
pte = pte_mkclean(pte);
set_pte_at(args->mm, args->vaddr, args->ptep, pte);
flush_dcache_page(page);
pte = pte_mkwrite(pte);
pte = pte_mkdirty(pte);
ptep_set_access_flags(args->vma, args->vaddr, args->ptep, pte, 1);
pte = ptep_get(args->ptep);
WARN_ON(!(pte_write(pte) && pte_dirty(pte)));
ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1);
pte = ptep_get(args->ptep);
WARN_ON(!pte_none(pte));
pte = pfn_pte(args->pte_pfn, args->page_prot);
pte = pte_mkyoung(pte);
set_pte_at(args->mm, args->vaddr, args->ptep, pte);
flush_dcache_page(page);
ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep);
pte = ptep_get(args->ptep);
WARN_ON(pte_young(pte));
ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1);
}
static void __init pte_savedwrite_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none);
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
return;
pr_debug("Validating PTE saved write\n");
WARN_ON(!pte_savedwrite(pte_mk_savedwrite(pte_clear_savedwrite(pte))));
WARN_ON(pte_savedwrite(pte_clear_savedwrite(pte_mk_savedwrite(pte))));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx)
{
pgprot_t prot = protection_map[idx];
unsigned long val = idx, *ptr = &val;
pmd_t pmd;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD basic (%pGv)\n", ptr);
pmd = pfn_pmd(args->fixed_pmd_pfn, prot);
/*
* This test needs to be executed after the given page table entry
* is created with pfn_pmd() to make sure that protection_map[idx]
* does not have the dirty bit enabled from the beginning. This is
* important for platforms like arm64 where (!PTE_RDONLY) indicate
* dirty bit being set.
*/
WARN_ON(pmd_dirty(pmd_wrprotect(pmd)));
WARN_ON(!pmd_same(pmd, pmd));
WARN_ON(!pmd_young(pmd_mkyoung(pmd_mkold(pmd))));
WARN_ON(!pmd_dirty(pmd_mkdirty(pmd_mkclean(pmd))));
WARN_ON(!pmd_write(pmd_mkwrite(pmd_wrprotect(pmd))));
WARN_ON(pmd_young(pmd_mkold(pmd_mkyoung(pmd))));
WARN_ON(pmd_dirty(pmd_mkclean(pmd_mkdirty(pmd))));
WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd))));
WARN_ON(pmd_dirty(pmd_wrprotect(pmd_mkclean(pmd))));
WARN_ON(!pmd_dirty(pmd_wrprotect(pmd_mkdirty(pmd))));
/*
* A huge page does not point to next level page table
* entry. Hence this must qualify as pmd_bad().
*/
WARN_ON(!pmd_bad(pmd_mkhuge(pmd)));
}
static void __init pmd_advanced_tests(struct pgtable_debug_args *args)
{
struct page *page;
pmd_t pmd;
unsigned long vaddr = args->vaddr;
if (!has_transparent_hugepage())
return;
page = (args->pmd_pfn != ULONG_MAX) ? pfn_to_page(args->pmd_pfn) : NULL;
if (!page)
return;
/*
* flush_dcache_page() is called after set_pmd_at() to clear
* PG_arch_1 for the page on ARM64. The page flag isn't cleared
* when it's released and page allocation check will fail when
* the page is allocated again. For architectures other than ARM64,
* the unexpected overhead of cache flushing is acceptable.
*/
pr_debug("Validating PMD advanced\n");
/* Align the address wrt HPAGE_PMD_SIZE */
vaddr &= HPAGE_PMD_MASK;
pgtable_trans_huge_deposit(args->mm, args->pmdp, args->start_ptep);
pmd = pfn_pmd(args->pmd_pfn, args->page_prot);
set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
flush_dcache_page(page);
pmdp_set_wrprotect(args->mm, vaddr, args->pmdp);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(pmd_write(pmd));
pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(!pmd_none(pmd));
pmd = pfn_pmd(args->pmd_pfn, args->page_prot);
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
flush_dcache_page(page);
pmd = pmd_mkwrite(pmd);
pmd = pmd_mkdirty(pmd);
pmdp_set_access_flags(args->vma, vaddr, args->pmdp, pmd, 1);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(!(pmd_write(pmd) && pmd_dirty(pmd)));
pmdp_huge_get_and_clear_full(args->vma, vaddr, args->pmdp, 1);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(!pmd_none(pmd));
pmd = pmd_mkhuge(pfn_pmd(args->pmd_pfn, args->page_prot));
pmd = pmd_mkyoung(pmd);
set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
flush_dcache_page(page);
pmdp_test_and_clear_young(args->vma, vaddr, args->pmdp);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(pmd_young(pmd));
/* Clear the pte entries */
pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp);
pgtable_trans_huge_withdraw(args->mm, args->pmdp);
}
static void __init pmd_leaf_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD leaf\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
/*
* PMD based THP is a leaf entry.
*/
pmd = pmd_mkhuge(pmd);
WARN_ON(!pmd_leaf(pmd));
}
static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
return;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD saved write\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none);
WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd))));
WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd))));
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx)
{
pgprot_t prot = protection_map[idx];
unsigned long val = idx, *ptr = &val;
pud_t pud;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PUD basic (%pGv)\n", ptr);
pud = pfn_pud(args->fixed_pud_pfn, prot);
/*
* This test needs to be executed after the given page table entry
* is created with pfn_pud() to make sure that protection_map[idx]
* does not have the dirty bit enabled from the beginning. This is
* important for platforms like arm64 where (!PTE_RDONLY) indicate
* dirty bit being set.
*/
WARN_ON(pud_dirty(pud_wrprotect(pud)));
WARN_ON(!pud_same(pud, pud));
WARN_ON(!pud_young(pud_mkyoung(pud_mkold(pud))));
WARN_ON(!pud_dirty(pud_mkdirty(pud_mkclean(pud))));
WARN_ON(pud_dirty(pud_mkclean(pud_mkdirty(pud))));
WARN_ON(!pud_write(pud_mkwrite(pud_wrprotect(pud))));
WARN_ON(pud_write(pud_wrprotect(pud_mkwrite(pud))));
WARN_ON(pud_young(pud_mkold(pud_mkyoung(pud))));
WARN_ON(pud_dirty(pud_wrprotect(pud_mkclean(pud))));
WARN_ON(!pud_dirty(pud_wrprotect(pud_mkdirty(pud))));
if (mm_pmd_folded(args->mm))
return;
/*
* A huge page does not point to next level page table
* entry. Hence this must qualify as pud_bad().
*/
WARN_ON(!pud_bad(pud_mkhuge(pud)));
}
static void __init pud_advanced_tests(struct pgtable_debug_args *args)
{
struct page *page;
unsigned long vaddr = args->vaddr;
pud_t pud;
if (!has_transparent_hugepage())
return;
page = (args->pud_pfn != ULONG_MAX) ? pfn_to_page(args->pud_pfn) : NULL;
if (!page)
return;
/*
* flush_dcache_page() is called after set_pud_at() to clear
* PG_arch_1 for the page on ARM64. The page flag isn't cleared
* when it's released and page allocation check will fail when
* the page is allocated again. For architectures other than ARM64,
* the unexpected overhead of cache flushing is acceptable.
*/
pr_debug("Validating PUD advanced\n");
/* Align the address wrt HPAGE_PUD_SIZE */
vaddr &= HPAGE_PUD_MASK;
pud = pfn_pud(args->pud_pfn, args->page_prot);
set_pud_at(args->mm, vaddr, args->pudp, pud);
flush_dcache_page(page);
pudp_set_wrprotect(args->mm, vaddr, args->pudp);
pud = READ_ONCE(*args->pudp);
WARN_ON(pud_write(pud));
#ifndef __PAGETABLE_PMD_FOLDED
pudp_huge_get_and_clear(args->mm, vaddr, args->pudp);
pud = READ_ONCE(*args->pudp);
WARN_ON(!pud_none(pud));
#endif /* __PAGETABLE_PMD_FOLDED */
pud = pfn_pud(args->pud_pfn, args->page_prot);
pud = pud_wrprotect(pud);
pud = pud_mkclean(pud);
set_pud_at(args->mm, vaddr, args->pudp, pud);
flush_dcache_page(page);
pud = pud_mkwrite(pud);
pud = pud_mkdirty(pud);
pudp_set_access_flags(args->vma, vaddr, args->pudp, pud, 1);
pud = READ_ONCE(*args->pudp);
WARN_ON(!(pud_write(pud) && pud_dirty(pud)));
#ifndef __PAGETABLE_PMD_FOLDED
pudp_huge_get_and_clear_full(args->mm, vaddr, args->pudp, 1);
pud = READ_ONCE(*args->pudp);
WARN_ON(!pud_none(pud));
#endif /* __PAGETABLE_PMD_FOLDED */
pud = pfn_pud(args->pud_pfn, args->page_prot);
pud = pud_mkyoung(pud);
set_pud_at(args->mm, vaddr, args->pudp, pud);
flush_dcache_page(page);
pudp_test_and_clear_young(args->vma, vaddr, args->pudp);
pud = READ_ONCE(*args->pudp);
WARN_ON(pud_young(pud));
pudp_huge_get_and_clear(args->mm, vaddr, args->pudp);
}
static void __init pud_leaf_tests(struct pgtable_debug_args *args)
{
pud_t pud;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PUD leaf\n");
pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
/*
* PUD based THP is a leaf entry.
*/
pud = pud_mkhuge(pud);
WARN_ON(!pud_leaf(pud));
}
#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { }
static void __init pud_advanced_tests(struct pgtable_debug_args *args) { }
static void __init pud_leaf_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) { }
static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { }
static void __init pmd_advanced_tests(struct pgtable_debug_args *args) { }
static void __init pud_advanced_tests(struct pgtable_debug_args *args) { }
static void __init pmd_leaf_tests(struct pgtable_debug_args *args) { }
static void __init pud_leaf_tests(struct pgtable_debug_args *args) { }
static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static void __init pmd_huge_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!arch_vmap_pmd_supported(args->page_prot))
return;
pr_debug("Validating PMD huge\n");
/*
* X86 defined pmd_set_huge() verifies that the given
* PMD is not a populated non-leaf entry.
*/
WRITE_ONCE(*args->pmdp, __pmd(0));
WARN_ON(!pmd_set_huge(args->pmdp, __pfn_to_phys(args->fixed_pmd_pfn), args->page_prot));
WARN_ON(!pmd_clear_huge(args->pmdp));
pmd = READ_ONCE(*args->pmdp);
WARN_ON(!pmd_none(pmd));
}
static void __init pud_huge_tests(struct pgtable_debug_args *args)
{
pud_t pud;
if (!arch_vmap_pud_supported(args->page_prot))
return;
pr_debug("Validating PUD huge\n");
/*
* X86 defined pud_set_huge() verifies that the given
* PUD is not a populated non-leaf entry.
*/
WRITE_ONCE(*args->pudp, __pud(0));
WARN_ON(!pud_set_huge(args->pudp, __pfn_to_phys(args->fixed_pud_pfn), args->page_prot));
WARN_ON(!pud_clear_huge(args->pudp));
pud = READ_ONCE(*args->pudp);
WARN_ON(!pud_none(pud));
}
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static void __init pmd_huge_tests(struct pgtable_debug_args *args) { }
static void __init pud_huge_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static void __init p4d_basic_tests(struct pgtable_debug_args *args)
{
p4d_t p4d;
pr_debug("Validating P4D basic\n");
memset(&p4d, RANDOM_NZVALUE, sizeof(p4d_t));
WARN_ON(!p4d_same(p4d, p4d));
}
static void __init pgd_basic_tests(struct pgtable_debug_args *args)
{
pgd_t pgd;
pr_debug("Validating PGD basic\n");
memset(&pgd, RANDOM_NZVALUE, sizeof(pgd_t));
WARN_ON(!pgd_same(pgd, pgd));
}
#ifndef __PAGETABLE_PUD_FOLDED
static void __init pud_clear_tests(struct pgtable_debug_args *args)
{
pud_t pud = READ_ONCE(*args->pudp);
if (mm_pmd_folded(args->mm))
return;
pr_debug("Validating PUD clear\n");
pud = __pud(pud_val(pud) | RANDOM_ORVALUE);
WRITE_ONCE(*args->pudp, pud);
pud_clear(args->pudp);
pud = READ_ONCE(*args->pudp);
WARN_ON(!pud_none(pud));
}
static void __init pud_populate_tests(struct pgtable_debug_args *args)
{
pud_t pud;
if (mm_pmd_folded(args->mm))
return;
pr_debug("Validating PUD populate\n");
/*
* This entry points to next level page table page.
* Hence this must not qualify as pud_bad().
*/
pud_populate(args->mm, args->pudp, args->start_pmdp);
pud = READ_ONCE(*args->pudp);
WARN_ON(pud_bad(pud));
}
#else /* !__PAGETABLE_PUD_FOLDED */
static void __init pud_clear_tests(struct pgtable_debug_args *args) { }
static void __init pud_populate_tests(struct pgtable_debug_args *args) { }
#endif /* PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_P4D_FOLDED
static void __init p4d_clear_tests(struct pgtable_debug_args *args)
{
p4d_t p4d = READ_ONCE(*args->p4dp);
if (mm_pud_folded(args->mm))
return;
pr_debug("Validating P4D clear\n");
p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE);
WRITE_ONCE(*args->p4dp, p4d);
p4d_clear(args->p4dp);
p4d = READ_ONCE(*args->p4dp);
WARN_ON(!p4d_none(p4d));
}
static void __init p4d_populate_tests(struct pgtable_debug_args *args)
{
p4d_t p4d;
if (mm_pud_folded(args->mm))
return;
pr_debug("Validating P4D populate\n");
/*
* This entry points to next level page table page.
* Hence this must not qualify as p4d_bad().
*/
pud_clear(args->pudp);
p4d_clear(args->p4dp);
p4d_populate(args->mm, args->p4dp, args->start_pudp);
p4d = READ_ONCE(*args->p4dp);
WARN_ON(p4d_bad(p4d));
}
static void __init pgd_clear_tests(struct pgtable_debug_args *args)
{
pgd_t pgd = READ_ONCE(*(args->pgdp));
if (mm_p4d_folded(args->mm))
return;
pr_debug("Validating PGD clear\n");
pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE);
WRITE_ONCE(*args->pgdp, pgd);
pgd_clear(args->pgdp);
pgd = READ_ONCE(*args->pgdp);
WARN_ON(!pgd_none(pgd));
}
static void __init pgd_populate_tests(struct pgtable_debug_args *args)
{
pgd_t pgd;
if (mm_p4d_folded(args->mm))
return;
pr_debug("Validating PGD populate\n");
/*
* This entry points to next level page table page.
* Hence this must not qualify as pgd_bad().
*/
p4d_clear(args->p4dp);
pgd_clear(args->pgdp);
pgd_populate(args->mm, args->pgdp, args->start_p4dp);
pgd = READ_ONCE(*args->pgdp);
WARN_ON(pgd_bad(pgd));
}
#else /* !__PAGETABLE_P4D_FOLDED */
static void __init p4d_clear_tests(struct pgtable_debug_args *args) { }
static void __init pgd_clear_tests(struct pgtable_debug_args *args) { }
static void __init p4d_populate_tests(struct pgtable_debug_args *args) { }
static void __init pgd_populate_tests(struct pgtable_debug_args *args) { }
#endif /* PAGETABLE_P4D_FOLDED */
static void __init pte_clear_tests(struct pgtable_debug_args *args)
{
struct page *page;
pte_t pte = pfn_pte(args->pte_pfn, args->page_prot);
page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
if (!page)
return;
/*
* flush_dcache_page() is called after set_pte_at() to clear
* PG_arch_1 for the page on ARM64. The page flag isn't cleared
* when it's released and page allocation check will fail when
* the page is allocated again. For architectures other than ARM64,
* the unexpected overhead of cache flushing is acceptable.
*/
pr_debug("Validating PTE clear\n");
#ifndef CONFIG_RISCV
pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
#endif
set_pte_at(args->mm, args->vaddr, args->ptep, pte);
flush_dcache_page(page);
barrier();
ptep_clear(args->mm, args->vaddr, args->ptep);
pte = ptep_get(args->ptep);
WARN_ON(!pte_none(pte));
}
static void __init pmd_clear_tests(struct pgtable_debug_args *args)
{
pmd_t pmd = READ_ONCE(*args->pmdp);
pr_debug("Validating PMD clear\n");
pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE);
WRITE_ONCE(*args->pmdp, pmd);
pmd_clear(args->pmdp);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(!pmd_none(pmd));
}
static void __init pmd_populate_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
pr_debug("Validating PMD populate\n");
/*
* This entry points to next level page table page.
* Hence this must not qualify as pmd_bad().
*/
pmd_populate(args->mm, args->pmdp, args->start_ptep);
pmd = READ_ONCE(*args->pmdp);
WARN_ON(pmd_bad(pmd));
}
static void __init pte_special_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL))
return;
pr_debug("Validating PTE special\n");
WARN_ON(!pte_special(pte_mkspecial(pte)));
}
static void __init pte_protnone_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none);
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
return;
pr_debug("Validating PTE protnone\n");
WARN_ON(!pte_protnone(pte));
WARN_ON(!pte_present(pte));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_protnone_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
return;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD protnone\n");
pmd = pmd_mkhuge(pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none));
WARN_ON(!pmd_protnone(pmd));
WARN_ON(!pmd_present(pmd));
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_protnone_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
static void __init pte_devmap_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
pr_debug("Validating PTE devmap\n");
WARN_ON(!pte_devmap(pte_mkdevmap(pte)));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_devmap_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD devmap\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd)));
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void __init pud_devmap_tests(struct pgtable_debug_args *args)
{
pud_t pud;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PUD devmap\n");
pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
WARN_ON(!pud_devmap(pud_mkdevmap(pud)));
}
#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#else
static void __init pte_devmap_tests(struct pgtable_debug_args *args) { }
static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
return;
pr_debug("Validating PTE soft dirty\n");
WARN_ON(!pte_soft_dirty(pte_mksoft_dirty(pte)));
WARN_ON(pte_soft_dirty(pte_clear_soft_dirty(pte)));
}
static void __init pte_swap_soft_dirty_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
return;
pr_debug("Validating PTE swap soft dirty\n");
WARN_ON(!pte_swp_soft_dirty(pte_swp_mksoft_dirty(pte)));
WARN_ON(pte_swp_soft_dirty(pte_swp_clear_soft_dirty(pte)));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
return;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD soft dirty\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd)));
WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd)));
}
static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) ||
!IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION))
return;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD swap soft dirty\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd)));
WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd)));
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { }
static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pte_swap_tests(struct pgtable_debug_args *args)
{
swp_entry_t swp;
pte_t pte;
pr_debug("Validating PTE swap\n");
pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
swp = __pte_to_swp_entry(pte);
pte = __swp_entry_to_pte(swp);
WARN_ON(args->fixed_pte_pfn != pte_pfn(pte));
}
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
static void __init pmd_swap_tests(struct pgtable_debug_args *args)
{
swp_entry_t swp;
pmd_t pmd;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD swap\n");
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
swp = __pmd_to_swp_entry(pmd);
pmd = __swp_entry_to_pmd(swp);
WARN_ON(args->fixed_pmd_pfn != pmd_pfn(pmd));
}
#else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */
static void __init pmd_swap_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
static void __init swap_migration_tests(struct pgtable_debug_args *args)
{
struct page *page;
swp_entry_t swp;
if (!IS_ENABLED(CONFIG_MIGRATION))
return;
/*
* swap_migration_tests() requires a dedicated page as it needs to
* be locked before creating a migration entry from it. Locking the
* page that actually maps kernel text ('start_kernel') can be real
* problematic. Lets use the allocated page explicitly for this
* purpose.
*/
page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
if (!page)
return;
pr_debug("Validating swap migration\n");
/*
* make_[readable|writable]_migration_entry() expects given page to
* be locked, otherwise it stumbles upon a BUG_ON().
*/
__SetPageLocked(page);
swp = make_writable_migration_entry(page_to_pfn(page));
WARN_ON(!is_migration_entry(swp));
WARN_ON(!is_writable_migration_entry(swp));
swp = make_readable_migration_entry(swp_offset(swp));
WARN_ON(!is_migration_entry(swp));
WARN_ON(is_writable_migration_entry(swp));
swp = make_readable_migration_entry(page_to_pfn(page));
WARN_ON(!is_migration_entry(swp));
WARN_ON(is_writable_migration_entry(swp));
__ClearPageLocked(page);
}
#ifdef CONFIG_HUGETLB_PAGE
static void __init hugetlb_basic_tests(struct pgtable_debug_args *args)
{
struct page *page;
pte_t pte;
pr_debug("Validating HugeTLB basic\n");
/*
* Accessing the page associated with the pfn is safe here,
* as it was previously derived from a real kernel symbol.
*/
page = pfn_to_page(args->fixed_pmd_pfn);
pte = mk_huge_pte(page, args->page_prot);
WARN_ON(!huge_pte_dirty(huge_pte_mkdirty(pte)));
WARN_ON(!huge_pte_write(huge_pte_mkwrite(huge_pte_wrprotect(pte))));
WARN_ON(huge_pte_write(huge_pte_wrprotect(huge_pte_mkwrite(pte))));
#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
pte = pfn_pte(args->fixed_pmd_pfn, args->page_prot);
WARN_ON(!pte_huge(pte_mkhuge(pte)));
#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
}
#else /* !CONFIG_HUGETLB_PAGE */
static void __init hugetlb_basic_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_HUGETLB_PAGE */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_thp_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PMD based THP\n");
/*
* pmd_trans_huge() and pmd_present() must return positive after
* MMU invalidation with pmd_mkinvalid(). This behavior is an
* optimization for transparent huge page. pmd_trans_huge() must
* be true if pmd_page() returns a valid THP to avoid taking the
* pmd_lock when others walk over non transhuge pmds (i.e. there
* are no THP allocated). Especially when splitting a THP and
* removing the present bit from the pmd, pmd_trans_huge() still
* needs to return true. pmd_present() should be true whenever
* pmd_trans_huge() returns true.
*/
pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
WARN_ON(!pmd_trans_huge(pmd_mkhuge(pmd)));
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
WARN_ON(!pmd_trans_huge(pmd_mkinvalid(pmd_mkhuge(pmd))));
WARN_ON(!pmd_present(pmd_mkinvalid(pmd_mkhuge(pmd))));
#endif /* __HAVE_ARCH_PMDP_INVALIDATE */
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void __init pud_thp_tests(struct pgtable_debug_args *args)
{
pud_t pud;
if (!has_transparent_hugepage())
return;
pr_debug("Validating PUD based THP\n");
pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
WARN_ON(!pud_trans_huge(pud_mkhuge(pud)));
/*
* pud_mkinvalid() has been dropped for now. Enable back
* these tests when it comes back with a modified pud_present().
*
* WARN_ON(!pud_trans_huge(pud_mkinvalid(pud_mkhuge(pud))));
* WARN_ON(!pud_present(pud_mkinvalid(pud_mkhuge(pud))));
*/
}
#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __init pud_thp_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_thp_tests(struct pgtable_debug_args *args) { }
static void __init pud_thp_tests(struct pgtable_debug_args *args) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static unsigned long __init get_random_vaddr(void)
{
unsigned long random_vaddr, random_pages, total_user_pages;
total_user_pages = (TASK_SIZE - FIRST_USER_ADDRESS) / PAGE_SIZE;