pgtable.h 9.7 KB
Newer Older
L
Linus Torvalds 已提交
1
/* 
J
Jeff Dike 已提交
2
 * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
L
Linus Torvalds 已提交
3 4 5 6 7 8 9 10
 * Copyright 2003 PathScale, Inc.
 * Derived from include/asm-i386/pgtable.h
 * Licensed under the GPL
 */

#ifndef __UM_PGTABLE_H
#define __UM_PGTABLE_H

J
Jeff Dike 已提交
11
#include <asm/fixmap.h>
L
Linus Torvalds 已提交
12 13 14

#define _PAGE_PRESENT	0x001
#define _PAGE_NEWPAGE	0x002
15
#define _PAGE_NEWPROT	0x004
L
Linus Torvalds 已提交
16 17 18 19
#define _PAGE_RW	0x020
#define _PAGE_USER	0x040
#define _PAGE_ACCESSED	0x080
#define _PAGE_DIRTY	0x100
20 21 22 23
/* If _PAGE_PRESENT is clear, we use these: */
#define _PAGE_FILE	0x008	/* nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_PROTNONE	0x010	/* if the user mapped it with PROT_NONE;
				   pte_present gives true */
L
Linus Torvalds 已提交
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

#ifdef CONFIG_3_LEVEL_PGTABLES
#include "asm/pgtable-3level.h"
#else
#include "asm/pgtable-2level.h"
#endif

extern pgd_t swapper_pg_dir[PTRS_PER_PGD];

/* zero page used for uninitialized stuff */
extern unsigned long *empty_zero_page;

#define pgtable_cache_init() do ; while (0)

/* Just any arbitrary offset to the start of the vmalloc VM area: the
 * current 8MB value just means that there will be a 8MB "hole" after the
 * physical memory until the kernel virtual memory starts.  That means that
 * any out-of-bounds memory accesses will hopefully be caught.
 * The vmalloc() routines leaves a hole of 4kB between each vmalloced
 * area for the same reason. ;)
 */

extern unsigned long end_iomem;

#define VMALLOC_OFFSET	(__va_space)
#define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
A
Al Viro 已提交
50
#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK)
L
Linus Torvalds 已提交
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END	(PKMAP_BASE-2*PAGE_SIZE)
#else
# define VMALLOC_END	(FIXADDR_START-2*PAGE_SIZE)
#endif

#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)

#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)

/*
J
Jeff Dike 已提交
68 69 70 71
 * The i386 can't do page protection for execute, and considers that the same
 * are read.
 * Also, write permissions imply read permissions. This is the closest we can
 * get..
L
Linus Torvalds 已提交
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
 */
#define __P000	PAGE_NONE
#define __P001	PAGE_READONLY
#define __P010	PAGE_COPY
#define __P011	PAGE_COPY
#define __P100	PAGE_READONLY
#define __P101	PAGE_READONLY
#define __P110	PAGE_COPY
#define __P111	PAGE_COPY

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

/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page)

#define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE))

99
#define pmd_none(x)	(!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE))
L
Linus Torvalds 已提交
100
#define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
J
Jeff Dike 已提交
101

L
Linus Torvalds 已提交
102 103 104 105 106 107 108 109 110 111 112
#define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
#define pmd_clear(xp)	do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0)

#define pmd_newpage(x)  (pmd_val(x) & _PAGE_NEWPAGE)
#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEWPAGE)

#define pud_newpage(x)  (pud_val(x) & _PAGE_NEWPAGE)
#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE)

#define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK)

113
#define pte_page(x) pfn_to_page(pte_pfn(x))
L
Linus Torvalds 已提交
114

115 116 117 118 119 120 121 122 123 124 125 126 127
#define pte_present(x)	pte_get_bits(x, (_PAGE_PRESENT | _PAGE_PROTNONE))

/*
 * =================================
 * Flags checking section.
 * =================================
 */

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

L
Linus Torvalds 已提交
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
/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
static inline int pte_read(pte_t pte)
{ 
	return((pte_get_bits(pte, _PAGE_USER)) &&
	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
}

static inline int pte_exec(pte_t pte){
	return((pte_get_bits(pte, _PAGE_USER)) &&
	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
}

static inline int pte_write(pte_t pte)
{
	return((pte_get_bits(pte, _PAGE_RW)) &&
	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
}

/*
 * The following only works if pte_present() is not true.
 */
static inline int pte_file(pte_t pte)
{
	return pte_get_bits(pte, _PAGE_FILE);
}

static inline int pte_dirty(pte_t pte)
{
	return pte_get_bits(pte, _PAGE_DIRTY);
}

static inline int pte_young(pte_t pte)
{
	return pte_get_bits(pte, _PAGE_ACCESSED);
}

static inline int pte_newpage(pte_t pte)
{
	return pte_get_bits(pte, _PAGE_NEWPAGE);
}

static inline int pte_newprot(pte_t pte)
{ 
	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
}

N
Nick Piggin 已提交
177 178 179 180 181
static inline int pte_special(pte_t pte)
{
	return 0;
}

182 183 184 185 186 187 188 189 190 191 192 193
/*
 * =================================
 * Flags setting section.
 * =================================
 */

static inline pte_t pte_mknewprot(pte_t pte)
{
	pte_set_bits(pte, _PAGE_NEWPROT);
	return(pte);
}

L
Linus Torvalds 已提交
194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213
static inline pte_t pte_mkclean(pte_t pte)
{
	pte_clear_bits(pte, _PAGE_DIRTY);
	return(pte);
}

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

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

static inline pte_t pte_mkread(pte_t pte)
{ 
J
Jeff Dike 已提交
214
	pte_set_bits(pte, _PAGE_USER);
L
Linus Torvalds 已提交
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
	return(pte_mknewprot(pte)); 
}

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

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

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

static inline pte_t pte_mkuptodate(pte_t pte)	
{
	pte_clear_bits(pte, _PAGE_NEWPAGE);
	if(pte_present(pte))
		pte_clear_bits(pte, _PAGE_NEWPROT);
	return(pte); 
}

244 245 246 247 248 249
static inline pte_t pte_mknewpage(pte_t pte)
{
	pte_set_bits(pte, _PAGE_NEWPAGE);
	return(pte);
}

N
Nick Piggin 已提交
250 251 252 253 254
static inline pte_t pte_mkspecial(pte_t pte)
{
	return(pte);
}

255 256 257 258 259 260 261 262 263 264 265 266 267 268
static inline void set_pte(pte_t *pteptr, pte_t pteval)
{
	pte_copy(*pteptr, pteval);

	/* If it's a swap entry, it needs to be marked _PAGE_NEWPAGE so
	 * fix_range knows to unmap it.  _PAGE_NEWPROT is specific to
	 * mapped pages.
	 */

	*pteptr = pte_mknewpage(*pteptr);
	if(pte_present(*pteptr)) *pteptr = pte_mknewprot(*pteptr);
}
#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)

L
Linus Torvalds 已提交
269 270 271 272 273
/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */

274 275
#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys))
#define __virt_to_page(virt) phys_to_page(__pa(virt))
J
Jeff Dike 已提交
276
#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page))
J
Jeff Dike 已提交
277
#define virt_to_page(addr) __virt_to_page((const unsigned long) addr)
278 279 280 281 282 283 284 285

#define mk_pte(page, pgprot) \
	({ pte_t pte;					\
							\
	pte_set_val(pte, page_to_phys(page), (pgprot));	\
	if (pte_present(pte))				\
		pte_mknewprot(pte_mknewpage(pte));	\
	pte;})
L
Linus Torvalds 已提交
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

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	pte_set_val(pte, (pte_val(pte) & _PAGE_CHG_MASK), newprot);
	return pte; 
}

/*
 * 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)

/*
 * 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
 */
J
Jeff Dike 已提交
319
#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
L
Linus Torvalds 已提交
320 321
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))

J
Jeff Dike 已提交
322 323 324
#define pmd_page_vaddr(pmd) \
	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))

L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332
/*
 * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
 *
 * this macro returns the index of the entry in the pte page which would
 * control the given virtual address
 */
#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset_kernel(dir, address) \
333
	((pte_t *) pmd_page_vaddr(*(dir)) +  pte_index(address))
L
Linus Torvalds 已提交
334 335 336 337 338 339
#define pte_offset_map(dir, address) \
	((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
#define pte_unmap(pte) do { } while (0)
#define pte_unmap_nested(pte) do { } while (0)

J
Jeff Dike 已提交
340 341 342
struct mm_struct;
extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);

L
Linus Torvalds 已提交
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
#define update_mmu_cache(vma,address,pte) do ; while (0)

/* Encode and de-code a swap entry */
#define __swp_type(x)			(((x).val >> 4) & 0x3f)
#define __swp_offset(x)			((x).val >> 11)

#define __swp_entry(type, offset) \
	((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
#define __pte_to_swp_entry(pte) \
	((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
#define __swp_entry_to_pte(x)		((pte_t) { (x).val })

#define kern_addr_valid(addr) (1)

#include <asm-generic/pgtable.h>

A
Al Viro 已提交
359 360 361 362 363 364 365
/* Clear a kernel PTE and flush it from the TLB */
#define kpte_clear_flush(ptep, vaddr)		\
do {						\
	pte_clear(&init_mm, (vaddr), (ptep));	\
	__flush_tlb_one((vaddr));		\
} while (0)

366
#endif