pgtable.h 21.5 KB
Newer Older
H
H. Peter Anvin 已提交
1 2
#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H
3

4
#include <asm/page.h>
5
#include <asm/e820.h>
6

7
#include <asm/pgtable_types.h>
8

9 10 11 12 13 14 15 16
/*
 * 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))

17
#ifndef __ASSEMBLY__
18 19
#include <asm/x86_init.h>

20 21
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);

22 23 24 25
/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
26 27
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
	__visible;
28 29
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))

30 31
extern spinlock_t pgd_lock;
extern struct list_head pgd_list;
32

33 34
extern struct mm_struct *pgd_page_get_mm(struct page *page);

35 36 37 38 39
#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)
40
#define set_pmd_at(mm, addr, pmdp, pmd)	native_set_pmd_at(mm, addr, pmdp, pmd)
41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64

#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)
65 66
#define pmd_update(mm, addr, ptep)              do { } while (0)
#define pmd_update_defer(mm, addr, ptep)        do { } while (0)
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83

#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)

84 85
#define arch_end_context_switch(prev)	do {} while(0)

86 87
#endif	/* CONFIG_PARAVIRT */

88 89 90 91
/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
92 93
static inline int pte_dirty(pte_t pte)
{
94
	return pte_flags(pte) & _PAGE_DIRTY;
95 96 97 98
}

static inline int pte_young(pte_t pte)
{
99
	return pte_flags(pte) & _PAGE_ACCESSED;
100 101
}

J
Johannes Weiner 已提交
102 103 104 105 106
static inline int pmd_young(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_ACCESSED;
}

107 108
static inline int pte_write(pte_t pte)
{
109
	return pte_flags(pte) & _PAGE_RW;
110 111 112 113
}

static inline int pte_file(pte_t pte)
{
114
	return pte_flags(pte) & _PAGE_FILE;
115 116 117 118
}

static inline int pte_huge(pte_t pte)
{
119
	return pte_flags(pte) & _PAGE_PSE;
120 121
}

122 123
static inline int pte_global(pte_t pte)
{
124
	return pte_flags(pte) & _PAGE_GLOBAL;
125 126 127 128
}

static inline int pte_exec(pte_t pte)
{
129
	return !(pte_flags(pte) & _PAGE_NX);
130 131
}

N
Nick Piggin 已提交
132 133
static inline int pte_special(pte_t pte)
{
134 135 136 137 138 139 140
	/*
	 * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
	 * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
	 * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL.
	 */
	return (pte_flags(pte) & _PAGE_SPECIAL) &&
		(pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
N
Nick Piggin 已提交
141 142
}

H
Hugh Dickins 已提交
143 144 145 146 147
static inline unsigned long pte_pfn(pte_t pte)
{
	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

A
Akinobu Mita 已提交
148 149 150 151 152
static inline unsigned long pmd_pfn(pmd_t pmd)
{
	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

153 154 155 156 157
static inline unsigned long pud_pfn(pud_t pud)
{
	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

H
Hugh Dickins 已提交
158 159
#define pte_page(pte)	pfn_to_page(pte_pfn(pte))

160 161
static inline int pmd_large(pmd_t pte)
{
162
	return pmd_flags(pte) & _PAGE_PSE;
163 164
}

J
Johannes Weiner 已提交
165 166 167 168 169 170 171 172 173 174
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_splitting(pmd_t pmd)
{
	return pmd_val(pmd) & _PAGE_SPLITTING;
}

static inline int pmd_trans_huge(pmd_t pmd)
{
	return pmd_val(pmd) & _PAGE_PSE;
}
175 176 177 178 179

static inline int has_transparent_hugepage(void)
{
	return cpu_has_pse;
}
J
Johannes Weiner 已提交
180 181
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

182 183 184 185 186 187 188 189 190 191 192 193 194 195
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);
}

196 197
static inline pte_t pte_mkclean(pte_t pte)
{
198
	return pte_clear_flags(pte, _PAGE_DIRTY);
199 200 201 202
}

static inline pte_t pte_mkold(pte_t pte)
{
203
	return pte_clear_flags(pte, _PAGE_ACCESSED);
204 205 206 207
}

static inline pte_t pte_wrprotect(pte_t pte)
{
208
	return pte_clear_flags(pte, _PAGE_RW);
209 210 211 212
}

static inline pte_t pte_mkexec(pte_t pte)
{
213
	return pte_clear_flags(pte, _PAGE_NX);
214 215 216 217
}

static inline pte_t pte_mkdirty(pte_t pte)
{
218
	return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
219 220 221 222
}

static inline pte_t pte_mkyoung(pte_t pte)
{
223
	return pte_set_flags(pte, _PAGE_ACCESSED);
224 225 226 227
}

static inline pte_t pte_mkwrite(pte_t pte)
{
228
	return pte_set_flags(pte, _PAGE_RW);
229 230 231 232
}

static inline pte_t pte_mkhuge(pte_t pte)
{
233
	return pte_set_flags(pte, _PAGE_PSE);
234 235 236 237
}

static inline pte_t pte_clrhuge(pte_t pte)
{
238
	return pte_clear_flags(pte, _PAGE_PSE);
239 240 241 242
}

static inline pte_t pte_mkglobal(pte_t pte)
{
243
	return pte_set_flags(pte, _PAGE_GLOBAL);
244 245 246 247
}

static inline pte_t pte_clrglobal(pte_t pte)
{
248
	return pte_clear_flags(pte, _PAGE_GLOBAL);
249
}
250

N
Nick Piggin 已提交
251 252
static inline pte_t pte_mkspecial(pte_t pte)
{
253
	return pte_set_flags(pte, _PAGE_SPECIAL);
N
Nick Piggin 已提交
254 255
}

J
Johannes Weiner 已提交
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
static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
{
	pmdval_t v = native_pmd_val(pmd);

	return __pmd(v | set);
}

static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
{
	pmdval_t v = native_pmd_val(pmd);

	return __pmd(v & ~clear);
}

static inline pmd_t pmd_mkold(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
}

static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_RW);
}

static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
282
	return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
J
Johannes Weiner 已提交
283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
}

static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_PSE);
}

static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_ACCESSED);
}

static inline pmd_t pmd_mkwrite(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_RW);
}

static inline pmd_t pmd_mknotpresent(pmd_t pmd)
{
	return pmd_clear_flags(pmd, _PAGE_PRESENT);
}

305
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
static inline int pte_soft_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
}

static inline int pmd_soft_dirty(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
}

static inline pte_t pte_mksoft_dirty(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
}

static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}

326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
{
	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
}

static inline pte_t pte_file_mksoft_dirty(pte_t pte)
{
	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
}

static inline int pte_file_soft_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SOFT_DIRTY;
}

341 342
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */

343 344 345 346 347 348 349 350 351 352 353 354 355 356
/*
 * 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;
}

357 358
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
359 360
	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
		     massage_pgprot(pgprot));
361 362 363 364
}

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
365 366
	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
		     massage_pgprot(pgprot));
367 368
}

369 370 371 372 373 374 375 376
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):
	 */
377
	val &= _PAGE_CHG_MASK;
378
	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
379 380 381 382

	return __pte(val);
}

J
Johannes Weiner 已提交
383 384 385 386 387 388 389 390 391 392
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
	pmdval_t val = pmd_val(pmd);

	val &= _HPAGE_CHG_MASK;
	val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;

	return __pmd(val);
}

393 394 395 396 397 398 399 400 401
/* 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);
}

J
Jeremy Fitzhardinge 已提交
402
#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
A
Andi Kleen 已提交
403

404
#define canon_pgprot(p) __pgprot(massage_pgprot(p))
A
Andi Kleen 已提交
405

406 407 408
static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
					 unsigned long flags,
					 unsigned long new_flags)
409
{
410
	/*
411
	 * PAT type is always WB for untracked ranges, so no need to check.
412
	 */
413
	if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
414 415
		return 1;

416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
	/*
	 * 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;
}

432 433
pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);
434 435
#endif	/* __ASSEMBLY__ */

436
#ifdef CONFIG_X86_32
437
# include <asm/pgtable_32.h>
438
#else
439
# include <asm/pgtable_64.h>
440
#endif
441

442
#ifndef __ASSEMBLY__
J
Jeremy Fitzhardinge 已提交
443
#include <linux/mm_types.h>
444
#include <linux/mmdebug.h>
445
#include <linux/log2.h>
446

J
Jeremy Fitzhardinge 已提交
447 448 449 450 451
static inline int pte_none(pte_t pte)
{
	return !pte.pte;
}

J
Jeremy Fitzhardinge 已提交
452 453 454 455 456 457
#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
	return a.pte == b.pte;
}

J
Jeremy Fitzhardinge 已提交
458 459
static inline int pte_present(pte_t a)
{
460 461
	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
			       _PAGE_NUMA);
J
Jeremy Fitzhardinge 已提交
462 463
}

464 465 466 467 468 469
#define pte_present_nonuma pte_present_nonuma
static inline int pte_present_nonuma(pte_t a)
{
	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}

R
Rik van Riel 已提交
470
#define pte_accessible pte_accessible
471
static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
R
Rik van Riel 已提交
472
{
473 474 475 476 477 478 479 480
	if (pte_flags(a) & _PAGE_PRESENT)
		return true;

	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
			mm_tlb_flush_pending(mm))
		return true;

	return false;
R
Rik van Riel 已提交
481 482
}

J
Jeremy Fitzhardinge 已提交
483
static inline int pte_hidden(pte_t pte)
484
{
J
Jeremy Fitzhardinge 已提交
485
	return pte_flags(pte) & _PAGE_HIDDEN;
486 487
}

J
Jeremy Fitzhardinge 已提交
488 489
static inline int pmd_present(pmd_t pmd)
{
490 491 492 493 494 495
	/*
	 * Checking for _PAGE_PSE is needed too because
	 * split_huge_page will temporarily clear the present bit (but
	 * the _PAGE_PSE flag will remain set at all times while the
	 * _PAGE_PRESENT bit is clear).
	 */
496 497
	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE |
				 _PAGE_NUMA);
J
Jeremy Fitzhardinge 已提交
498 499
}

J
Jeremy Fitzhardinge 已提交
500 501 502 503
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. */
504
	return (unsigned long)native_pmd_val(pmd) == 0;
J
Jeremy Fitzhardinge 已提交
505 506
}

J
Jeremy Fitzhardinge 已提交
507 508 509 510 511
static inline unsigned long pmd_page_vaddr(pmd_t pmd)
{
	return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
}

512 513 514 515
/*
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
516
#define pmd_page(pmd)	pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
J
Jeremy Fitzhardinge 已提交
517

J
Jeremy Fitzhardinge 已提交
518 519 520 521 522 523
/*
 * 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
 */
F
Figo.zhang 已提交
524
static inline unsigned long pmd_index(unsigned long address)
J
Jeremy Fitzhardinge 已提交
525 526 527 528
{
	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}

J
Jeremy Fitzhardinge 已提交
529 530 531 532 533 534 535 536 537
/*
 * 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))

J
Jeremy Fitzhardinge 已提交
538 539 540 541 542 543
/*
 * 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
 */
F
Figo.zhang 已提交
544
static inline unsigned long pte_index(unsigned long address)
J
Jeremy Fitzhardinge 已提交
545 546 547 548
{
	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}

549 550 551 552 553
static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
	return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}

J
Jeremy Fitzhardinge 已提交
554 555
static inline int pmd_bad(pmd_t pmd)
{
556 557 558 559 560
#ifdef CONFIG_NUMA_BALANCING
	/* pmd_numa check */
	if ((pmd_flags(pmd) & (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA)
		return 0;
#endif
561
	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
J
Jeremy Fitzhardinge 已提交
562 563
}

J
Jeremy Fitzhardinge 已提交
564 565 566 567 568
static inline unsigned long pages_to_mb(unsigned long npg)
{
	return npg >> (20 - PAGE_SHIFT);
}

J
Jeremy Fitzhardinge 已提交
569
#if PAGETABLE_LEVELS > 2
J
Jeremy Fitzhardinge 已提交
570 571
static inline int pud_none(pud_t pud)
{
572
	return native_pud_val(pud) == 0;
J
Jeremy Fitzhardinge 已提交
573 574
}

J
Jeremy Fitzhardinge 已提交
575 576
static inline int pud_present(pud_t pud)
{
577
	return pud_flags(pud) & _PAGE_PRESENT;
J
Jeremy Fitzhardinge 已提交
578
}
J
Jeremy Fitzhardinge 已提交
579 580 581 582 583

static inline unsigned long pud_page_vaddr(pud_t pud)
{
	return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
}
J
Jeremy Fitzhardinge 已提交
584

585 586 587 588 589
/*
 * 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)
J
Jeremy Fitzhardinge 已提交
590 591 592 593 594 595

/* 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);
}
J
Jeremy Fitzhardinge 已提交
596

J
Jeremy Fitzhardinge 已提交
597 598
static inline int pud_large(pud_t pud)
{
599
	return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
J
Jeremy Fitzhardinge 已提交
600 601
		(_PAGE_PSE | _PAGE_PRESENT);
}
J
Jeremy Fitzhardinge 已提交
602 603 604

static inline int pud_bad(pud_t pud)
{
605
	return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
J
Jeremy Fitzhardinge 已提交
606
}
607 608 609 610 611
#else
static inline int pud_large(pud_t pud)
{
	return 0;
}
J
Jeremy Fitzhardinge 已提交
612 613
#endif	/* PAGETABLE_LEVELS > 2 */

J
Jeremy Fitzhardinge 已提交
614 615 616
#if PAGETABLE_LEVELS > 3
static inline int pgd_present(pgd_t pgd)
{
617
	return pgd_flags(pgd) & _PAGE_PRESENT;
J
Jeremy Fitzhardinge 已提交
618
}
J
Jeremy Fitzhardinge 已提交
619 620 621 622 623

static inline unsigned long pgd_page_vaddr(pgd_t pgd)
{
	return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
}
J
Jeremy Fitzhardinge 已提交
624

625 626 627 628 629
/*
 * 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)
J
Jeremy Fitzhardinge 已提交
630 631

/* to find an entry in a page-table-directory. */
F
Figo.zhang 已提交
632
static inline unsigned long pud_index(unsigned long address)
J
Jeremy Fitzhardinge 已提交
633 634 635
{
	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
J
Jeremy Fitzhardinge 已提交
636 637 638 639 640

static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
{
	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
}
J
Jeremy Fitzhardinge 已提交
641 642 643

static inline int pgd_bad(pgd_t pgd)
{
644
	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
J
Jeremy Fitzhardinge 已提交
645
}
J
Jeremy Fitzhardinge 已提交
646 647 648

static inline int pgd_none(pgd_t pgd)
{
649
	return !native_pgd_val(pgd);
J
Jeremy Fitzhardinge 已提交
650
}
J
Jeremy Fitzhardinge 已提交
651 652
#endif	/* PAGETABLE_LEVELS > 3 */

653 654
#endif	/* __ASSEMBLY__ */

J
Jeremy Fitzhardinge 已提交
655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
/*
 * 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))


J
Jeremy Fitzhardinge 已提交
675 676 677
#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)

678 679
#ifndef __ASSEMBLY__

680
extern int direct_gbpages;
681
void init_mem_mapping(void);
Y
Yinghai Lu 已提交
682
void early_alloc_pgt_buf(void);
683

684 685 686 687 688 689 690 691 692 693
/* 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;
}

J
Johannes Weiner 已提交
694 695 696 697 698 699 700 701
static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp)
{
	pmd_t res = *pmdp;

	native_pmd_clear(pmdp);
	return res;
}

702 703 704 705 706 707
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);
}

A
Andrea Arcangeli 已提交
708 709 710 711 712 713
static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
				     pmd_t *pmdp , pmd_t pmd)
{
	native_set_pmd(pmdp, pmd);
}

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
#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.
 */
739 740
struct vm_area_struct;

741
#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
742 743 744
extern int ptep_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pte_t *ptep,
				 pte_t entry, int dirty);
745 746

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
747 748
extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pte_t *ptep);
749 750

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
751 752
extern int ptep_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pte_t *ptep);
753 754

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
755 756
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
				       pte_t *ptep)
757 758 759 760 761 762 763
{
	pte_t pte = native_ptep_get_and_clear(ptep);
	pte_update(mm, addr, ptep);
	return pte;
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
764 765 766
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long addr, pte_t *ptep,
					    int full)
767 768 769 770 771 772 773 774 775 776 777 778 779 780 781
{
	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
782 783
static inline void ptep_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
784
{
J
Jeremy Fitzhardinge 已提交
785
	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
786 787 788
	pte_update(mm, addr, ptep);
}

789
#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
790

J
Johannes Weiner 已提交
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
#define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))

#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 addr, pmd_t *pmdp);

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


#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
extern void pmdp_splitting_flush(struct vm_area_struct *vma,
				 unsigned long addr, pmd_t *pmdp);

#define __HAVE_ARCH_PMD_WRITE
static inline int pmd_write(pmd_t pmd)
{
	return pmd_flags(pmd) & _PAGE_RW;
}

#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr,
				       pmd_t *pmdp)
{
	pmd_t pmd = native_pmdp_get_and_clear(pmdp);
	pmd_update(mm, addr, pmdp);
	return pmd;
}

#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pmd_t *pmdp)
{
	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
	pmd_update(mm, addr, pmdp);
}

J
Jeremy Fitzhardinge 已提交
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848
/*
 * 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));
}

849 850 851 852 853 854 855 856 857 858 859 860 861
#define PTE_SHIFT ilog2(PTRS_PER_PTE)
static inline int page_level_shift(enum pg_level level)
{
	return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT;
}
static inline unsigned long page_level_size(enum pg_level level)
{
	return 1UL << page_level_shift(level);
}
static inline unsigned long page_level_mask(enum pg_level level)
{
	return ~(page_level_size(level) - 1);
}
J
Jeremy Fitzhardinge 已提交
862

863 864 865 866 867 868 869 870 871 872 873 874
/*
 * The x86 doesn't have any external MMU info: the kernel page
 * tables contain all the necessary information.
 */
static inline void update_mmu_cache(struct vm_area_struct *vma,
		unsigned long addr, pte_t *ptep)
{
}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
		unsigned long addr, pmd_t *pmd)
{
}
J
Jeremy Fitzhardinge 已提交
875

876
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
877 878
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
879
	VM_BUG_ON(pte_present_nonuma(pte));
880 881 882 883 884
	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}

static inline int pte_swp_soft_dirty(pte_t pte)
{
885
	VM_BUG_ON(pte_present_nonuma(pte));
886 887 888 889 890
	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
}

static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
891
	VM_BUG_ON(pte_present_nonuma(pte));
892 893
	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}
894
#endif
895

896 897 898
#include <asm-generic/pgtable.h>
#endif	/* __ASSEMBLY__ */

H
H. Peter Anvin 已提交
899
#endif /* _ASM_X86_PGTABLE_H */