summaryrefslogtreecommitdiff
path: root/arch/powerpc/include/asm/book3s/64/pgtable.h
blob: 7ec176674b7800f7794741b627dc715a827da2c4 (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
#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_

/*
 * Common bits between hash and Radix page table
 */
#define _PAGE_BIT_SWAP_TYPE	0

#define _PAGE_EXEC		0x00001 /* execute permission */
#define _PAGE_WRITE		0x00002 /* write access allowed */
#define _PAGE_READ		0x00004	/* read access allowed */
#define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
#define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
#define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
#define _PAGE_SAO		0x00010 /* Strong access order */
#define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
#define _PAGE_TOLERANT		0x00030 /* tolerant memory, cache inhibited */
#define _PAGE_DIRTY		0x00080 /* C: page changed */
#define _PAGE_ACCESSED		0x00100 /* R: page referenced */
/*
 * Software bits
 */
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SOFT_DIRTY	0x00200 /* software: software dirty tracking */
#else
#define _PAGE_SOFT_DIRTY	0x00000
#endif
#define _PAGE_SPECIAL		0x00400 /* software: special page */


#define _PAGE_PTE		(1ul << 62)	/* distinguishes PTEs from pointers */
#define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
/*
 * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
 * Instead of fixing all of them, add an alternate define which
 * maps CI pte mapping.
 */
#define _PAGE_NO_CACHE		_PAGE_TOLERANT
/*
 * We support 57 bit real address in pte. Clear everything above 57, and
 * every thing below PAGE_SHIFT;
 */
#define PTE_RPN_MASK	(((1UL << 57) - 1) & (PAGE_MASK))
/*
 * set of bits not changed in pmd_modify. Even though we have hash specific bits
 * in here, on radix we expect them to be zero.
 */
#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
			 _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \
			 _PAGE_SOFT_DIRTY)
/*
 * user access blocked by key
 */
#define _PAGE_KERNEL_RW		(_PAGE_PRIVILEGED | _PAGE_RW | _PAGE_DIRTY)
#define _PAGE_KERNEL_RO		 (_PAGE_PRIVILEGED | _PAGE_READ)
#define _PAGE_KERNEL_RWX	(_PAGE_PRIVILEGED | _PAGE_DIRTY |	\
				 _PAGE_RW | _PAGE_EXEC)
/*
 * No page size encoding in the linux PTE
 */
#define _PAGE_PSIZE		0
/*
 * _PAGE_CHG_MASK masks of bits that are to be preserved across
 * pgprot changes
 */
#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE |	\
			 _PAGE_SOFT_DIRTY)
/*
 * Mask of bits returned by pte_pgprot()
 */
#define PAGE_PROT_BITS  (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT | \
			 H_PAGE_4K_PFN | _PAGE_PRIVILEGED | _PAGE_ACCESSED | \
			 _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_EXEC | \
			 _PAGE_SOFT_DIRTY)
/*
 * We define 2 sets of base prot bits, one for basic pages (ie,
 * cacheable kernel and user pages) and one for non cacheable
 * pages. We always set _PAGE_COHERENT when SMP is enabled or
 * the processor might need it for DMA coherency.
 */
#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
#define _PAGE_BASE	(_PAGE_BASE_NC)

/* Permission masks used to generate the __P and __S table,
 *
 * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
 *
 * Write permissions imply read permissions for now (we could make write-only
 * pages on BookE but we don't bother for now). Execute permission control is
 * possible on platforms that define _PAGE_EXEC
 *
 * Note due to the way vm flags are laid out, the bits are XWR
 */
#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_PRIVILEGED)
#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW)
#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC)
#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_READ)
#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_READ)
#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)

#define __P000	PAGE_NONE
#define __P001	PAGE_READONLY
#define __P010	PAGE_COPY
#define __P011	PAGE_COPY
#define __P100	PAGE_READONLY_X
#define __P101	PAGE_READONLY_X
#define __P110	PAGE_COPY_X
#define __P111	PAGE_COPY_X

#define __S000	PAGE_NONE
#define __S001	PAGE_READONLY
#define __S010	PAGE_SHARED
#define __S011	PAGE_SHARED
#define __S100	PAGE_READONLY_X
#define __S101	PAGE_READONLY_X
#define __S110	PAGE_SHARED_X
#define __S111	PAGE_SHARED_X

/* Permission masks used for kernel mappings */
#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
#define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
				 _PAGE_TOLERANT)
#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
				 _PAGE_NON_IDEMPOTENT)
#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)

/*
 * Protection used for kernel text. We want the debuggers to be able to
 * set breakpoints anywhere, so don't write protect the kernel text
 * on platforms where such control is possible.
 */
#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \
	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
#define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
#else
#define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
#endif

/* Make modules code happy. We don't set RO yet */
#define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
#define PAGE_AGP		(PAGE_KERNEL_NC)

#include <asm/book3s/64/hash.h>
#include <asm/barrier.h>

/*
 * The second half of the kernel virtual space is used for IO mappings,
 * it's itself carved into the PIO region (ISA and PHB IO space) and
 * the ioremap space
 *
 *  ISA_IO_BASE = KERN_IO_START, 64K reserved area
 *  PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
 * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
 */
#define KERN_IO_START	(KERN_VIRT_START + (KERN_VIRT_SIZE >> 1))
#define FULL_IO_SIZE	0x80000000ul
#define  ISA_IO_BASE	(KERN_IO_START)
#define  ISA_IO_END	(KERN_IO_START + 0x10000ul)
#define  PHB_IO_BASE	(ISA_IO_END)
#define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
#define IOREMAP_BASE	(PHB_IO_END)
#define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)

#define vmemmap			((struct page *)VMEMMAP_BASE)

/* Advertise special mapping type for AGP */
#define HAVE_PAGE_AGP

/* Advertise support for _PAGE_SPECIAL */
#define __HAVE_ARCH_PTE_SPECIAL

#ifndef __ASSEMBLY__

/*
 * This is the default implementation of various PTE accessors, it's
 * used in all cases except Book3S with 64K pages where we have a
 * concept of sub-pages
 */
#ifndef __real_pte

#define __real_pte(e,p)		((real_pte_t){(e)})
#define __rpte_to_pte(r)	((r).pte)
#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)

#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
	do {							         \
		index = 0;					         \
		shift = mmu_psize_defs[psize].shift;		         \

#define pte_iterate_hashed_end() } while(0)

/*
 * We expect this to be called only for user addresses or kernel virtual
 * addresses other than the linear mapping.
 */
#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K

#endif /* __real_pte */

/*
 * For hash even if we have _PAGE_ACCESSED = 0, we do a pte_update.
 * We currently remove entries from the hashtable regardless of whether
 * the entry was young or dirty.
 *
 * We should be more intelligent about this but for the moment we override
 * these functions and force a tlb flush unconditionally
 * For radix: H_PAGE_HASHPTE should be zero. Hence we can use the same
 * function for both hash and radix.
 */
static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
					      unsigned long addr, pte_t *ptep)
{
	unsigned long old;

	if ((pte_val(*ptep) & (_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
		return 0;
	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
	return (old & _PAGE_ACCESSED) != 0;
}

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define ptep_test_and_clear_young(__vma, __addr, __ptep)	\
({								\
	int __r;						\
	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
	__r;							\
})

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
				      pte_t *ptep)
{

	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
		return;

	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
}

static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
					   unsigned long addr, pte_t *ptep)
{
	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
		return;

	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long addr, pte_t *ptep)
{
	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
	return __pte(old);
}

static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
			     pte_t * ptep)
{
	pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_WRITE);}
static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline bool pte_soft_dirty(pte_t pte)
{
	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
}

static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY);
}
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */

#ifdef CONFIG_NUMA_BALANCING
/*
 * These work without NUMA balancing but the kernel does not care. See the
 * comment in include/asm-generic/pgtable.h . On powerpc, this will only
 * work for user pages and always return true for kernel pages.
 */
static inline int pte_protnone(pte_t pte)
{
	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
		(_PAGE_PRESENT | _PAGE_PRIVILEGED);
}
#endif /* CONFIG_NUMA_BALANCING */

static inline int pte_present(pte_t pte)
{
	return !!(pte_val(pte) & _PAGE_PRESENT);
}
/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 *
 * Even if PTEs can be unsigned long long, a PFN is always an unsigned
 * long for now.
 */
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
{
	return __pte((((pte_basic_t)(pfn) << PAGE_SHIFT) & PTE_RPN_MASK) |
		     pgprot_val(pgprot));
}

static inline unsigned long pte_pfn(pte_t pte)
{
	return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT;
}

/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_WRITE);
}

static inline pte_t pte_mkclean(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	/*
	 * write implies read, hence set both
	 */
	return __pte(pte_val(pte) | _PAGE_RW);
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_ACCESSED);
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SPECIAL);
}

static inline pte_t pte_mkhuge(pte_t pte)
{
	return pte;
}

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	/* FIXME!! check whether this need to be a conditional */
	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
}

#define _PAGE_CACHE_CTL	(_PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)

#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_NON_IDEMPOTENT);
}

#define pgprot_noncached_wc pgprot_noncached_wc
static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
			_PAGE_TOLERANT);
}

#define pgprot_cached pgprot_cached
static inline pgprot_t pgprot_cached(pgprot_t prot)
{
	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL));
}

#define pgprot_writecombine pgprot_writecombine
static inline pgprot_t pgprot_writecombine(pgprot_t prot)
{
	return pgprot_noncached_wc(prot);
}
/*
 * check a pte mapping have cache inhibited property
 */
static inline bool pte_ci(pte_t pte)
{
	unsigned long pte_v = pte_val(pte);

	if (((pte_v & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) ||
	    ((pte_v & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT))
		return true;
	return false;
}

static inline void pmd_set(pmd_t *pmdp, unsigned long val)
{
	*pmdp = __pmd(val);
}

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

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

static inline void pud_set(pud_t *pudp, unsigned long val)
{
	*pudp = __pud(val);
}

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

#define pud_none(pud)		(!pud_val(pud))
#define pud_present(pud)	(pud_val(pud) != 0)

extern struct page *pud_page(pud_t pud);
extern struct page *pmd_page(pmd_t pmd);
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));
}
#define pud_write(pud)		pte_write(pud_pte(pud))
#define pgd_write(pgd)		pte_write(pgd_pte(pgd))
static inline void pgd_set(pgd_t *pgdp, unsigned long val)
{
	*pgdp = __pgd(val);
}

static inline void pgd_clear(pgd_t *pgdp)
{
	*pgdp = __pgd(0);
}

#define pgd_none(pgd)		(!pgd_val(pgd))
#define pgd_present(pgd)	(!pgd_none(pgd))

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

static inline pgd_t pte_pgd(pte_t pte)
{
	return __pgd(pte_val(pte));
}

extern struct page *pgd_page(pgd_t pgd);

/*
 * Find an entry in a page-table-directory.  We combine the address region
 * (the high order N bits) and the pgd portion of the address.
 */

#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))

#define pud_offset(pgdp, addr)	\
	(((pud_t *) pgd_page_vaddr(*(pgdp))) + pud_index(addr))
#define pmd_offset(pudp,addr) \
	(((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr))
#define pte_offset_kernel(dir,addr) \
	(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))

#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
#define pte_unmap(pte)			do { } while(0)

/* to find an entry in a kernel page-table-directory */
/* This now only contains the vmalloc pages */
#define pgd_offset_k(address) pgd_offset(&init_mm, address)

#define pte_ERROR(e) \
	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
#define pud_ERROR(e) \
	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
#define pgd_ERROR(e) \
	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))

/* Encode and de-code a swap entry */
#define MAX_SWAPFILES_CHECK() do { \
	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
	/*							\
	 * Don't have overlapping bits with _PAGE_HPTEFLAGS	\
	 * We filter HPTEFLAGS on set_pte.			\
	 */							\
	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
	} while (0)
/*
 * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
 */
#define SWP_TYPE_BITS 5
#define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
				& ((1UL << SWP_TYPE_BITS) - 1))
#define __swp_offset(x)		(((x).val & PTE_RPN_MASK) >> PAGE_SHIFT)
#define __swp_entry(type, offset)	((swp_entry_t) { \
				((type) << _PAGE_BIT_SWAP_TYPE) \
				| (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)})
/*
 * swp_entry_t must be independent of pte bits. We build a swp_entry_t from
 * swap type and offset we get from swap and convert that to pte to find a
 * matching pte in linux page table.
 * Clear bits not found in swap entries here.
 */
#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })
#define __swp_entry_to_pte(x)	__pte((x).val | _PAGE_PTE)

static inline bool pte_user(pte_t pte)
{
	return !(pte_val(pte) & _PAGE_PRIVILEGED);
}

#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
#else
#define _PAGE_SWP_SOFT_DIRTY	0UL
#endif /* CONFIG_MEM_SOFT_DIRTY */

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
}
static inline bool pte_swp_soft_dirty(pte_t pte)
{
	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
}
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */

static inline bool check_pte_access(unsigned long access, unsigned long ptev)
{
	/*
	 * This check for _PAGE_RWX and _PAGE_PRESENT bits
	 */
	if (access & ~ptev)
		return false;
	/*
	 * This check for access to privilege space
	 */
	if ((access & _PAGE_PRIVILEGED) != (ptev & _PAGE_PRIVILEGED))
		return false;

	return true;
}

void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
void pgtable_cache_init(void);

struct page *realmode_pfn_to_page(unsigned long pfn);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
		       pmd_t *pmdp, pmd_t pmd);
extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
				 pmd_t *pmd);
extern int has_transparent_hugepage(void);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */


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 pte_t *pmdp_ptep(pmd_t *pmd)
{
	return (pte_t *)pmd;
}

#define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))

#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
#define pmd_mksoft_dirty(pmd)  pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */

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

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

static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE));
}

#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pmd_t *pmdp,
				 pmd_t entry, int dirty);

#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long address, pmd_t *pmdp);

#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
				     unsigned long addr, pmd_t *pmdp);

extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
				 unsigned long address, pmd_t *pmdp);
#define pmdp_collapse_flush pmdp_collapse_flush

#define __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				       pgtable_t pgtable);
#define __HAVE_ARCH_PGTABLE_WITHDRAW
extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);

#define __HAVE_ARCH_PMDP_INVALIDATE
extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
			    pmd_t *pmdp);

#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
extern void pmdp_huge_split_prepare(struct vm_area_struct *vma,
				    unsigned long address, pmd_t *pmdp);

#define pmd_move_must_withdraw pmd_move_must_withdraw
struct spinlock;
static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
					 struct spinlock *old_pmd_ptl)
{
	/*
	 * Archs like ppc64 use pgtable to store per pmd
	 * specific information. So when we switch the pmd,
	 * we should also withdraw and deposit the pgtable
	 */
	return true;
}
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */