summaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm/pgtable.h
blob: 1f3218fc52fc2bcea5ea0f48cfbf7781ced58711 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2012 ARM Ltd.
 */
#ifndef __ASM_PGTABLE_H
#define __ASM_PGTABLE_H

#include <asm/bug.h>
#include <asm/proc-fns.h>

#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable-prot.h>
#include <asm/tlbflush.h>

/*
 * VMALLOC range.
 *
 * VMALLOC_START: beginning of the kernel vmalloc space
 * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space
 *	and fixed mappings
 */
#define VMALLOC_START		(MODULES_END)
#define VMALLOC_END		(- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)

#define FIRST_USER_ADDRESS	0UL

#ifndef __ASSEMBLY__

#include <asm/cmpxchg.h>
#include <asm/fixmap.h>
#include <linux/mmdebug.h>
#include <linux/mm_types.h>
#include <linux/sched.h>

extern struct page *vmemmap;

extern void __pte_error(const char *file, int line, unsigned long val);
extern void __pmd_error(const char *file, int line, unsigned long val);
extern void __pud_error(const char *file, int line, unsigned long val);
extern void __pgd_error(const char *file, int line, unsigned long val);

/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))

#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))

/*
 * Macros to convert between a physical address and its placement in a
 * page table entry, taking care of 52-bit addresses.
 */
#ifdef CONFIG_ARM64_PA_BITS_52
#define __pte_to_phys(pte)	\
	((pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << 36))
#define __phys_to_pte_val(phys)	(((phys) | ((phys) >> 36)) & PTE_ADDR_MASK)
#else
#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_MASK)
#define __phys_to_pte_val(phys)	(phys)
#endif

#define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
#define pfn_pte(pfn,prot)	\
	__pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))

#define pte_none(pte)		(!pte_val(pte))
#define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
#define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))

/*
 * The following only work if pte_present(). Undefined behaviour otherwise.
 */
#define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
#define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
#define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
#define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
#define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
#define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
#define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))

#define pte_cont_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK;	\
	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
})

#define pmd_cont_addr_end(addr, end)						\
({	unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK;	\
	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
})

#define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
#define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
#define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))

#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
#define pte_valid_not_user(pte) \
	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
#define pte_valid_young(pte) \
	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
#define pte_valid_user(pte) \
	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))

/*
 * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
 * so that we don't erroneously return false for pages that have been
 * remapped as PROT_NONE but are yet to be flushed from the TLB.
 */
#define pte_accessible(mm, pte)	\
	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))

/*
 * p??_access_permitted() is true for valid user mappings (subject to the
 * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
 * set.
 */
#define pte_access_permitted(pte, write) \
	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
#define pmd_access_permitted(pmd, write) \
	(pte_access_permitted(pmd_pte(pmd), (write)))
#define pud_access_permitted(pud, write) \
	(pte_access_permitted(pud_pte(pud), (write)))

static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
{
	pte_val(pte) &= ~pgprot_val(prot);
	return pte;
}

static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
{
	pte_val(pte) |= pgprot_val(prot);
	return pte;
}

static inline pte_t pte_wrprotect(pte_t pte)
{
	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
	return pte;
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
	pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
	return pte;
}

static inline pte_t pte_mkclean(pte_t pte)
{
	pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY));
	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));

	return pte;
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));

	if (pte_write(pte))
		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));

	return pte;
}

static inline pte_t pte_mkold(pte_t pte)
{
	return clear_pte_bit(pte, __pgprot(PTE_AF));
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return set_pte_bit(pte, __pgprot(PTE_AF));
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
}

static inline pte_t pte_mkcont(pte_t pte)
{
	pte = set_pte_bit(pte, __pgprot(PTE_CONT));
	return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
}

static inline pte_t pte_mknoncont(pte_t pte)
{
	return clear_pte_bit(pte, __pgprot(PTE_CONT));
}

static inline pte_t pte_mkpresent(pte_t pte)
{
	return set_pte_bit(pte, __pgprot(PTE_VALID));
}

static inline pmd_t pmd_mkcont(pmd_t pmd)
{
	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
}

static inline pte_t pte_mkdevmap(pte_t pte)
{
	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
}

static inline void set_pte(pte_t *ptep, pte_t pte)
{
	WRITE_ONCE(*ptep, pte);

	/*
	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
	 * or update_mmu_cache() have the necessary barriers.
	 */
	if (pte_valid_not_user(pte)) {
		dsb(ishst);
		isb();
	}
}

extern void __sync_icache_dcache(pte_t pteval);

/*
 * PTE bits configuration in the presence of hardware Dirty Bit Management
 * (PTE_WRITE == PTE_DBM):
 *
 * Dirty  Writable | PTE_RDONLY  PTE_WRITE  PTE_DIRTY (sw)
 *   0      0      |   1           0          0
 *   0      1      |   1           1          0
 *   1      0      |   1           0          1
 *   1      1      |   0           1          x
 *
 * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
 * the page fault mechanism. Checking the dirty status of a pte becomes:
 *
 *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
 */

static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
					   pte_t pte)
{
	pte_t old_pte;

	if (!IS_ENABLED(CONFIG_DEBUG_VM))
		return;

	old_pte = READ_ONCE(*ptep);

	if (!pte_valid(old_pte) || !pte_valid(pte))
		return;
	if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1)
		return;

	/*
	 * Check for potential race with hardware updates of the pte
	 * (ptep_set_access_flags safely changes valid ptes without going
	 * through an invalid entry).
	 */
	VM_WARN_ONCE(!pte_young(pte),
		     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
		     __func__, pte_val(old_pte), pte_val(pte));
	VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
		     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
		     __func__, pte_val(old_pte), pte_val(pte));
}

static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep, pte_t pte)
{
	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
		__sync_icache_dcache(pte);

	__check_racy_pte_update(mm, ptep, pte);

	set_pte(ptep, pte);
}

/*
 * Huge pte definitions.
 */
#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))

/*
 * Hugetlb definitions.
 */
#define HUGE_MAX_HSTATE		4
#define HPAGE_SHIFT		PMD_SHIFT
#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)

static inline pte_t pgd_pte(pgd_t pgd)
{
	return __pte(pgd_val(pgd));
}

static inline pte_t p4d_pte(p4d_t p4d)
{
	return __pte(p4d_val(p4d));
}

static inline pte_t pud_pte(pud_t pud)
{
	return __pte(pud_val(pud));
}

static inline pud_t pte_pud(pte_t pte)
{
	return __pud(pte_val(pte));
}

static inline pmd_t pud_pmd(pud_t pud)
{
	return __pmd(pud_val(pud));
}

static inline pte_t pmd_pte(pmd_t pmd)
{
	return __pte(pmd_val(pmd));
}

static inline pmd_t pte_pmd(pte_t pte)
{
	return __pmd(pte_val(pte));
}

static inline pgprot_t mk_pud_sect_prot(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT);
}

static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * See the comment in include/asm-generic/pgtable.h
 */
static inline int pte_protnone(pte_t pte)
{
	return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE;
}

static inline int pmd_protnone(pmd_t pmd)
{
	return pte_protnone(pmd_pte(pmd));
}
#endif

/*
 * THP definitions.
 */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
#define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
#define pmd_mkinvalid(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))

#define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))

#define pmd_write(pmd)		pte_write(pmd_pte(pmd))

#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
#endif
static inline pmd_t pmd_mkdevmap(pmd_t pmd)
{
	return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
}

#define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
#define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
#define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
#define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)

#define pud_young(pud)		pte_young(pud_pte(pud))
#define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
#define pud_write(pud)		pte_write(pud_pte(pud))

#define pud_mkhuge(pud)		(__pud(pud_val(pud) & ~PUD_TABLE_BIT))

#define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
#define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
#define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
#define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))

#define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))

#define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
#define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)

#define __pgd_to_phys(pgd)	__pte_to_phys(pgd_pte(pgd))
#define __phys_to_pgd_val(phys)	__phys_to_pte_val(phys)

#define __pgprot_modify(prot,mask,bits) \
	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))

#define pgprot_nx(prot) \
	__pgprot_modify(prot, 0, PTE_PXN)

/*
 * Mark the prot value as uncacheable and unbufferable.
 */
#define pgprot_noncached(prot) \
	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
#define pgprot_writecombine(prot) \
	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
#define pgprot_device(prot) \
	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
/*
 * DMA allocations for non-coherent devices use what the Arm architecture calls
 * "Normal non-cacheable" memory, which permits speculation, unaligned accesses
 * and merging of writes.  This is different from "Device-nGnR[nE]" memory which
 * is intended for MMIO and thus forbids speculation, preserves access size,
 * requires strict alignment and can also force write responses to come from the
 * endpoint.
 */
#define pgprot_dmacoherent(prot) \
	__pgprot_modify(prot, PTE_ATTRINDX_MASK, \
			PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)

#define __HAVE_PHYS_MEM_ACCESS_PROT
struct file;
extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
				     unsigned long size, pgprot_t vma_prot);

#define pmd_none(pmd)		(!pmd_val(pmd))

#define pmd_bad(pmd)		(!(pmd_val(pmd) & PMD_TABLE_BIT))

#define pmd_table(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
				 PMD_TYPE_TABLE)
#define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
				 PMD_TYPE_SECT)
#define pmd_leaf(pmd)		pmd_sect(pmd)

#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
static inline bool pud_sect(pud_t pud) { return false; }
static inline bool pud_table(pud_t pud) { return true; }
#else
#define pud_sect(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
				 PUD_TYPE_SECT)
#define pud_table(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
				 PUD_TYPE_TABLE)
#endif

extern pgd_t init_pg_dir[PTRS_PER_PGD];
extern pgd_t init_pg_end[];
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_end[];
extern pgd_t tramp_pg_dir[PTRS_PER_PGD];

extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);

static inline bool in_swapper_pgdir(void *addr)
{
	return ((unsigned long)addr & PAGE_MASK) ==
	        ((unsigned long)swapper_pg_dir & PAGE_MASK);
}

static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
#ifdef __PAGETABLE_PMD_FOLDED
	if (in_swapper_pgdir(pmdp)) {
		set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd)));
		return;
	}
#endif /* __PAGETABLE_PMD_FOLDED */

	WRITE_ONCE(*pmdp, pmd);

	if (pmd_valid(pmd)) {
		dsb(ishst);
		isb();
	}
}

static inline void pmd_clear(pmd_t *pmdp)
{
	set_pmd(pmdp, __pmd(0));
}

static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
{
	return __pmd_to_phys(pmd);
}

static inline void pte_unmap(pte_t *pte) { }

/* Find an entry in the third-level page table. */
#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))

#define pte_offset_phys(dir,addr)	(pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
#define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))

#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))

#define pte_set_fixmap(addr)		((pte_t *)set_fixmap_offset(FIX_PTE, addr))
#define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
#define pte_clear_fixmap()		clear_fixmap(FIX_PTE)

#define pmd_page(pmd)			phys_to_page(__pmd_to_phys(pmd))

/* use ONLY for statically allocated translation tables */
#define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)

#if CONFIG_PGTABLE_LEVELS > 2

#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))

#define pud_none(pud)		(!pud_val(pud))
#define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
#define pud_present(pud)	pte_present(pud_pte(pud))
#define pud_leaf(pud)		pud_sect(pud)
#define pud_valid(pud)		pte_valid(pud_pte(pud))

static inline void set_pud(pud_t *pudp, pud_t pud)
{
#ifdef __PAGETABLE_PUD_FOLDED
	if (in_swapper_pgdir(pudp)) {
		set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud)));
		return;
	}
#endif /* __PAGETABLE_PUD_FOLDED */

	WRITE_ONCE(*pudp, pud);

	if (pud_valid(pud)) {
		dsb(ishst);
		isb();
	}
}

static inline void pud_clear(pud_t *pudp)
{
	set_pud(pudp, __pud(0));
}

static inline phys_addr_t pud_page_paddr(pud_t pud)
{
	return __pud_to_phys(pud);
}

/* Find an entry in the second-level page table. */
#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))

#define pmd_offset_phys(dir, addr)	(pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t))
#define pmd_offset(dir, addr)		((pmd_t *)__va(pmd_offset_phys((dir), (addr))))

#define pmd_set_fixmap(addr)		((pmd_t *)set_fixmap_offset(FIX_PMD, addr))
#define pmd_set_fixmap_offset(pud, addr)	pmd_set_fixmap(pmd_offset_phys(pud, addr))
#define pmd_clear_fixmap()		clear_fixmap(FIX_PMD)

#define pud_page(pud)			phys_to_page(__pud_to_phys(pud))

/* use ONLY for statically allocated translation tables */
#define pmd_offset_kimg(dir,addr)	((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))

#else

#define pud_page_paddr(pud)	({ BUILD_BUG(); 0; })

/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
#define pmd_set_fixmap(addr)		NULL
#define pmd_set_fixmap_offset(pudp, addr)	((pmd_t *)pudp)
#define pmd_clear_fixmap()

#define pmd_offset_kimg(dir,addr)	((pmd_t *)dir)

#endif	/* CONFIG_PGTABLE_LEVELS > 2 */

#if CONFIG_PGTABLE_LEVELS > 3

#define pud_ERROR(pud)		__pud_error(__FILE__, __LINE__, pud_val(pud))

#define p4d_none(p4d)		(!p4d_val(p4d))
#define p4d_bad(p4d)		(!(p4d_val(p4d) & 2))
#define p4d_present(p4d)	(p4d_val(p4d))

static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
{
	if (in_swapper_pgdir(p4dp)) {
		set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d)));
		return;
	}

	WRITE_ONCE(*p4dp, p4d);
	dsb(ishst);
	isb();
}

static inline void p4d_clear(p4d_t *p4dp)
{
	set_p4d(p4dp, __p4d(0));
}

static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
{
	return __p4d_to_phys(p4d);
}

/* Find an entry in the frst-level page table. */
#define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))

#define pud_offset_phys(dir, addr)	(p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
#define pud_offset(dir, addr)		((pud_t *)__va(pud_offset_phys((dir), (addr))))

#define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))
#define pud_set_fixmap_offset(p4d, addr)	pud_set_fixmap(pud_offset_phys(p4d, addr))
#define pud_clear_fixmap()		clear_fixmap(FIX_PUD)

#define p4d_page(p4d)		pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d)))

/* use ONLY for statically allocated translation tables */
#define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))

#else

#define p4d_page_paddr(p4d)	({ BUILD_BUG(); 0;})
#define pgd_page_paddr(pgd)	({ BUILD_BUG(); 0;})

/* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */
#define pud_set_fixmap(addr)		NULL
#define pud_set_fixmap_offset(pgdp, addr)	((pud_t *)pgdp)
#define pud_clear_fixmap()

#define pud_offset_kimg(dir,addr)	((pud_t *)dir)

#endif  /* CONFIG_PGTABLE_LEVELS > 3 */

#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))

/* to find an entry in a page-table-directory */
#define pgd_index(addr)		(((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))

#define pgd_offset_raw(pgd, addr)	((pgd) + pgd_index(addr))

#define pgd_offset(mm, addr)	(pgd_offset_raw((mm)->pgd, (addr)))

/* to find an entry in a kernel page-table-directory */
#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)

#define pgd_set_fixmap(addr)	((pgd_t *)set_fixmap_offset(FIX_PGD, addr))
#define pgd_clear_fixmap()	clear_fixmap(FIX_PGD)

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
	/* preserve the hardware dirty information */
	if (pte_hw_dirty(pte))
		pte = pte_mkdirty(pte);
	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
	return pte;
}

static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
}

#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pte_t *ptep,
				 pte_t entry, int dirty);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
					unsigned long address, pmd_t *pmdp,
					pmd_t entry, int dirty)
{
	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
}

static inline int pud_devmap(pud_t pud)
{
	return 0;
}

static inline int pgd_devmap(pgd_t pgd)
{
	return 0;
}
#endif

/*
 * Atomic pte/pmd modifications.
 */
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int __ptep_test_and_clear_young(pte_t *ptep)
{
	pte_t old_pte, pte;

	pte = READ_ONCE(*ptep);
	do {
		old_pte = pte;
		pte = pte_mkold(pte);
		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
					       pte_val(old_pte), pte_val(pte));
	} while (pte_val(pte) != pte_val(old_pte));

	return pte_young(pte);
}

static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pte_t *ptep)
{
	return __ptep_test_and_clear_young(ptep);
}

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
					 unsigned long address, pte_t *ptep)
{
	int young = ptep_test_and_clear_young(vma, address, ptep);

	if (young) {
		/*
		 * We can elide the trailing DSB here since the worst that can
		 * happen is that a CPU continues to use the young entry in its
		 * TLB and we mistakenly reclaim the associated page. The
		 * window for such an event is bounded by the next
		 * context-switch, which provides a DSB to complete the TLB
		 * invalidation.
		 */
		flush_tlb_page_nosync(vma, address);
	}

	return young;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pmd_t *pmdp)
{
	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long address, pte_t *ptep)
{
	return __pte(xchg_relaxed(&pte_val(*ptep), 0));
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
					    unsigned long address, pmd_t *pmdp)
{
	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/*
 * ptep_set_wrprotect - mark read-only while trasferring potential hardware
 * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
 */
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
	pte_t old_pte, pte;

	pte = READ_ONCE(*ptep);
	do {
		old_pte = pte;
		/*
		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
		 * clear), set the PTE_DIRTY bit.
		 */
		if (pte_hw_dirty(pte))
			pte = pte_mkdirty(pte);
		pte = pte_wrprotect(pte);
		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
					       pte_val(old_pte), pte_val(pte));
	} while (pte_val(pte) != pte_val(old_pte));
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pmd_t *pmdp)
{
	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
}

#define pmdp_establish pmdp_establish
static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
}
#endif

/*
 * Encode and decode a swap entry:
 *	bits 0-1:	present (must be zero)
 *	bits 2-7:	swap type
 *	bits 8-57:	swap offset
 *	bit  58:	PTE_PROT_NONE (must be zero)
 */
#define __SWP_TYPE_SHIFT	2
#define __SWP_TYPE_BITS		6
#define __SWP_OFFSET_BITS	50
#define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
#define __SWP_OFFSET_MASK	((1UL << __SWP_OFFSET_BITS) - 1)

#define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
#define __swp_offset(x)		(((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK)
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })

#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })

/*
 * Ensure that there are not more swap files than can be encoded in the kernel
 * PTEs.
 */
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)

extern int kern_addr_valid(unsigned long addr);

#include <asm-generic/pgtable.h>

/*
 * On AArch64, the cache coherency is handled via the set_pte_at() function.
 */
static inline void update_mmu_cache(struct vm_area_struct *vma,
				    unsigned long addr, pte_t *ptep)
{
	/*
	 * We don't do anything here, so there's a very small chance of
	 * us retaking a user fault which we just fixed up. The alternative
	 * is doing a dsb(ishst), but that penalises the fastpath.
	 */
}

#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)

#ifdef CONFIG_ARM64_PA_BITS_52
#define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
#else
#define phys_to_ttbr(addr)	(addr)
#endif

/*
 * On arm64 without hardware Access Flag, copying from user will fail because
 * the pte is old and cannot be marked young. So we always end up with zeroed
 * page after fork() + CoW for pfn mappings. We don't always have a
 * hardware-managed access flag on arm64.
 */
static inline bool arch_faults_on_old_pte(void)
{
	WARN_ON(preemptible());

	return !cpu_has_hw_af();
}
#define arch_faults_on_old_pte arch_faults_on_old_pte

#endif /* !__ASSEMBLY__ */

#endif /* __ASM_PGTABLE_H */