aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/pgtable.h
blob: a34c785c5a63b88ecd9fb3f07ee26c8fd3b4a7df (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
#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H

#include <asm/page.h>
#include <asm/e820.h>

#include <asm/pgtable_types.h>

/*
 * Macro to mark a page protection value as UC-
 */
#define pgprot_noncached(prot)					\
	((boot_cpu_data.x86 > 3)				\
	 ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))	\
	 : (prot))

#ifndef __ASSEMBLY__

#include <asm/x86_init.h>

/*
 * 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) (virt_to_page(empty_zero_page))

extern spinlock_t pgd_lock;
extern struct list_head pgd_list;

#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else  /* !CONFIG_PARAVIRT */
#define set_pte(ptep, pte)		native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)

#define set_pte_atomic(ptep, pte)					\
	native_set_pte_atomic(ptep, pte)

#define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)

#ifndef __PAGETABLE_PUD_FOLDED
#define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
#define pgd_clear(pgd)			native_pgd_clear(pgd)
#endif

#ifndef set_pud
# define set_pud(pudp, pud)		native_set_pud(pudp, pud)
#endif

#ifndef __PAGETABLE_PMD_FOLDED
#define pud_clear(pud)			native_pud_clear(pud)
#endif

#define pte_clear(mm, addr, ptep)	native_pte_clear(mm, addr, ptep)
#define pmd_clear(pmd)			native_pmd_clear(pmd)

#define pte_update(mm, addr, ptep)              do { } while (0)
#define pte_update_defer(mm, addr, ptep)        do { } while (0)

#define pgd_val(x)	native_pgd_val(x)
#define __pgd(x)	native_make_pgd(x)

#ifndef __PAGETABLE_PUD_FOLDED
#define pud_val(x)	native_pud_val(x)
#define __pud(x)	native_make_pud(x)
#endif

#ifndef __PAGETABLE_PMD_FOLDED
#define pmd_val(x)	native_pmd_val(x)
#define __pmd(x)	native_make_pmd(x)
#endif

#define pte_val(x)	native_pte_val(x)
#define __pte(x)	native_make_pte(x)

#define arch_end_context_switch(prev)	do {} while(0)

#endif	/* CONFIG_PARAVIRT */

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
static inline int pte_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_DIRTY;
}

static inline int pte_young(pte_t pte)
{
	return pte_flags(pte) & _PAGE_ACCESSED;
}

static inline int pte_write(pte_t pte)
{
	return pte_flags(pte) & _PAGE_RW;
}

static inline int pte_file(pte_t pte)
{
	return pte_flags(pte) & _PAGE_FILE;
}

static inline int pte_huge(pte_t pte)
{
	return pte_flags(pte) & _PAGE_PSE;
}

static inline int pte_global(pte_t pte)
{
	return pte_flags(pte) & _PAGE_GLOBAL;
}

static inline int pte_exec(pte_t pte)
{
	return !(pte_flags(pte) & _PAGE_NX);
}

static inline int pte_special(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SPECIAL;
}

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

static inline unsigned long pmd_pfn(pmd_t pmd)
{
	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

#define pte_page(pte)	pfn_to_page(pte_pfn(pte))

static inline int pmd_large(pmd_t pte)
{
	return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
		(_PAGE_PSE | _PAGE_PRESENT);
}

static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
{
	pteval_t v = native_pte_val(pte);

	return native_make_pte(v | set);
}

static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
{
	pteval_t v = native_pte_val(pte);

	return native_make_pte(v & ~clear);
}

static inline pte_t pte_mkclean(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_DIRTY);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_ACCESSED);
}

static inline pte_t pte_wrprotect(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_RW);
}

static inline pte_t pte_mkexec(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_NX);
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_DIRTY);
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_ACCESSED);
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_RW);
}

static inline pte_t pte_mkhuge(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_PSE);
}

static inline pte_t pte_clrhuge(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_PSE);
}

static inline pte_t pte_mkglobal(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_GLOBAL);
}

static inline pte_t pte_clrglobal(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_GLOBAL);
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SPECIAL);
}

/*
 * Mask out unsupported bits in a present pgprot.  Non-present pgprots
 * can use those bits for other purposes, so leave them be.
 */
static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
{
	pgprotval_t protval = pgprot_val(pgprot);

	if (protval & _PAGE_PRESENT)
		protval &= __supported_pte_mask;

	return protval;
}

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
		     massage_pgprot(pgprot));
}

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
		     massage_pgprot(pgprot));
}

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	pteval_t val = pte_val(pte);

	/*
	 * Chop off the NX bit (if present), and add the NX portion of
	 * the newprot (if present):
	 */
	val &= _PAGE_CHG_MASK;
	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;

	return __pte(val);
}

/* mprotect needs to preserve PAT bits when updating vm_page_prot */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	pgprotval_t addbits = pgprot_val(newprot);
	return __pgprot(preservebits | addbits);
}

#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)

#define canon_pgprot(p) __pgprot(massage_pgprot(p))

static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
					 unsigned long flags,
					 unsigned long new_flags)
{
	/*
	 * PAT type is always WB for untracked ranges, so no need to check.
	 */
	if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
		return 1;

	/*
	 * Certain new memtypes are not allowed with certain
	 * requested memtype:
	 * - request is uncached, return cannot be write-back
	 * - request is write-combine, return cannot be write-back
	 */
	if ((flags == _PAGE_CACHE_UC_MINUS &&
	     new_flags == _PAGE_CACHE_WB) ||
	    (flags == _PAGE_CACHE_WC &&
	     new_flags == _PAGE_CACHE_WB)) {
		return 0;
	}

	return 1;
}

pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);
#endif	/* __ASSEMBLY__ */

#ifdef CONFIG_X86_32
# include "pgtable_32.h"
#else
# include "pgtable_64.h"
#endif

#ifndef __ASSEMBLY__
#include <linux/mm_types.h>

static inline int pte_none(pte_t pte)
{
	return !pte.pte;
}

#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
	return a.pte == b.pte;
}

static inline int pte_present(pte_t a)
{
	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}

static inline int pte_hidden(pte_t pte)
{
	return pte_flags(pte) & _PAGE_HIDDEN;
}

static inline int pmd_present(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_PRESENT;
}

static inline int pmd_none(pmd_t pmd)
{
	/* Only check low word on 32-bit platforms, since it might be
	   out of sync with upper half. */
	return (unsigned long)native_pmd_val(pmd) == 0;
}

static inline unsigned long pmd_page_vaddr(pmd_t pmd)
{
	return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pmd_page(pmd)	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)

/*
 * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
 *
 * this macro returns the index of the entry in the pmd page which would
 * control the given virtual address
 */
static inline unsigned long pmd_index(unsigned long address)
{
	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 *
 * (Currently stuck as a macro because of indirect forward reference
 * to linux/mm.h:page_to_nid())
 */
#define mk_pte(page, pgprot)   pfn_pte(page_to_pfn(page), (pgprot))

/*
 * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
 *
 * this function returns the index of the entry in the pte page which would
 * control the given virtual address
 */
static inline unsigned long pte_index(unsigned long address)
{
	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}

static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
	return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}

static inline int pmd_bad(pmd_t pmd)
{
	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
}

static inline unsigned long pages_to_mb(unsigned long npg)
{
	return npg >> (20 - PAGE_SHIFT);
}

#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
	remap_pfn_range(vma, vaddr, pfn, size, prot)

#if PAGETABLE_LEVELS > 2
static inline int pud_none(pud_t pud)
{
	return native_pud_val(pud) == 0;
}

static inline int pud_present(pud_t pud)
{
	return pud_flags(pud) & _PAGE_PRESENT;
}

static inline unsigned long pud_page_vaddr(pud_t pud)
{
	return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pud_page(pud)		pfn_to_page(pud_val(pud) >> PAGE_SHIFT)

/* Find an entry in the second-level page table.. */
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
}

static inline int pud_large(pud_t pud)
{
	return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
		(_PAGE_PSE | _PAGE_PRESENT);
}

static inline int pud_bad(pud_t pud)
{
	return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
}
#else
static inline int pud_large(pud_t pud)
{
	return 0;
}
#endif	/* PAGETABLE_LEVELS > 2 */

#if PAGETABLE_LEVELS > 3
static inline int pgd_present(pgd_t pgd)
{
	return pgd_flags(pgd) & _PAGE_PRESENT;
}

static inline unsigned long pgd_page_vaddr(pgd_t pgd)
{
	return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
}

/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
#define pgd_page(pgd)		pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)

/* to find an entry in a page-table-directory. */
static inline unsigned long pud_index(unsigned long address)
{
	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}

static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
{
	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
}

static inline int pgd_bad(pgd_t pgd)
{
	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
}

static inline int pgd_none(pgd_t pgd)
{
	return !native_pgd_val(pgd);
}
#endif	/* PAGETABLE_LEVELS > 3 */

#endif	/* __ASSEMBLY__ */

/*
 * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
 *
 * this macro returns the index of the entry in the pgd page which would
 * control the given virtual address
 */
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))

/*
 * pgd_offset() returns a (pgd_t *)
 * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
 */
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
/*
 * a shortcut which implies the use of the kernel's pgd, instead
 * of a process's
 */
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))


#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)

#ifndef __ASSEMBLY__

extern int direct_gbpages;

/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
	pte_t res = *ptep;

	/* Pure native function needs no input for mm, addr */
	native_pte_clear(NULL, 0, ptep);
	return res;
}

static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
				     pte_t *ptep , pte_t pte)
{
	native_set_pte(ptep, pte);
}

#ifndef CONFIG_PARAVIRT
/*
 * Rules for using pte_update - it must be called after any PTE update which
 * has not been done using the set_pte / clear_pte interfaces.  It is used by
 * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
 * updates should either be sets, clears, or set_pte_atomic for P->P
 * transitions, which means this hook should only be called for user PTEs.
 * This hook implies a P->P protection or access change has taken place, which
 * requires a subsequent TLB flush.  The notification can optionally be delayed
 * until the TLB flush event by using the pte_update_defer form of the
 * interface, but care must be taken to assure that the flush happens while
 * still holding the same page table lock so that the shadow and primary pages
 * do not become out of sync on SMP.
 */
#define pte_update(mm, addr, ptep)		do { } while (0)
#define pte_update_defer(mm, addr, ptep)	do { } while (0)
#endif

/*
 * We only update the dirty/accessed state if we set
 * the dirty bit by hand in the kernel, since the hardware
 * will do the accessed bit for us, and we don't want to
 * race with other CPU's that might be updating the dirty
 * bit at the same time.
 */
struct vm_area_struct;

#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);

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pte_t *ptep);

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
extern int ptep_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pte_t *ptep);

#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)
{
	pte_t pte = native_ptep_get_and_clear(ptep);
	pte_update(mm, addr, ptep);
	return pte;
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long addr, pte_t *ptep,
					    int full)
{
	pte_t pte;
	if (full) {
		/*
		 * Full address destruction in progress; paravirt does not
		 * care about updates and native needs no locking
		 */
		pte = native_local_ptep_get_and_clear(ptep);
	} else {
		pte = ptep_get_and_clear(mm, addr, ptep);
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
{
	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
	pte_update(mm, addr, ptep);
}

/*
 * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
 *
 *  dst - pointer to pgd range anwhere on a pgd page
 *  src - ""
 *  count - the number of pgds to copy.
 *
 * dst and src can be on the same page, but the range must not overlap,
 * and must not cross a page boundary.
 */
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
       memcpy(dst, src, count * sizeof(pgd_t));
}


#include <asm-generic/pgtable.h>
#endif	/* __ASSEMBLY__ */

#endif /* _ASM_X86_PGTABLE_H */