summaryrefslogtreecommitdiffstats
path: root/include/asm-i386/pgtable.h
blob: cfa011108cb02fd2cf0515c689eeab6b62325875 (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
#ifndef _I386_PGTABLE_H
#define _I386_PGTABLE_H

#include <linux/config.h>

/*
 * The Linux memory management assumes a three-level page table setup. On
 * the i386, we use that, but "fold" the mid level into the top-level page
 * table, so that we physically have the same two-level page table as the
 * i386 mmu expects.
 *
 * This file contains the functions and defines necessary to modify and use
 * the i386 page table tree.
 */
#ifndef __ASSEMBLY__
#include <asm/processor.h>
#include <asm/fixmap.h>
#include <linux/threads.h>

extern pgd_t swapper_pg_dir[1024];
extern void paging_init(void);

/* Caches aren't brain-dead on the intel. */
#define flush_cache_all()			do { } while (0)
#define flush_cache_mm(mm)			do { } while (0)
#define flush_cache_range(mm, start, end)	do { } while (0)
#define flush_cache_page(vma, vmaddr)		do { } while (0)
#define flush_page_to_ram(page)			do { } while (0)
#define flush_icache_range(start, end)		do { } while (0)
#define flush_icache_page(vma,pg)		do { } while (0)

#define __flush_tlb()							\
	do {								\
		unsigned int tmpreg;					\
									\
		__asm__ __volatile__(					\
			"movl %%cr3, %0;  # flush TLB \n"		\
			"movl %0, %%cr3;              \n"		\
			: "=r" (tmpreg)					\
			:: "memory");					\
	} while (0)

/*
 * Global pages have to be flushed a bit differently. Not a real
 * performance problem because this does not happen often.
 */
#define __flush_tlb_global()						\
	do {								\
		unsigned int tmpreg;					\
									\
		__asm__ __volatile__(					\
			"movl %1, %%cr4;  # turn off PGE     \n"	\
			"movl %%cr3, %0;  # flush TLB        \n"	\
			"movl %0, %%cr3;                     \n"	\
			"movl %2, %%cr4;  # turn PGE back on \n"	\
			: "=&r" (tmpreg)				\
			: "r" (mmu_cr4_features & ~X86_CR4_PGE),	\
			  "r" (mmu_cr4_features)			\
			: "memory");					\
	} while (0)

extern unsigned long pgkern_mask;

/*
 * Do not check the PGE bit unnecesserily if this is a PPro+ kernel.
 */
#ifdef CONFIG_X86_PGE
# define __flush_tlb_all() __flush_tlb_global()
#else
# define __flush_tlb_all()						\
	do {								\
		if (cpu_has_pge)					\
			__flush_tlb_global();				\
		else							\
			__flush_tlb();					\
	} while (0)
#endif

#ifndef CONFIG_X86_INVLPG
#define __flush_tlb_one(addr) __flush_tlb()
#else
#define __flush_tlb_one(addr) \
__asm__ __volatile__("invlpg %0": :"m" (*(char *) addr))
#endif

/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
extern unsigned long empty_zero_page[1024];
#define ZERO_PAGE(vaddr) (mem_map + MAP_NR(empty_zero_page))

#endif /* !__ASSEMBLY__ */

/*
 * The Linux x86 paging architecture is 'compile-time dual-mode', it
 * implements both the traditional 2-level x86 page tables and the
 * newer 3-level PAE-mode page tables.
 */
#ifndef __ASSEMBLY__
#if CONFIG_X86_PAE
# include <asm/pgtable-3level.h>
#else
# include <asm/pgtable-2level.h>
#endif
#endif

#define __beep() asm("movb $0x3,%al; outb %al,$0x61")

#define PMD_SIZE	(1UL << PMD_SHIFT)
#define PMD_MASK	(~(PMD_SIZE-1))
#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
#define PGDIR_MASK	(~(PGDIR_SIZE-1))

#define USER_PTRS_PER_PGD	(TASK_SIZE/PGDIR_SIZE)
#define FIRST_USER_PGD_NR	0

#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)

#define TWOLEVEL_PGDIR_SHIFT	22
#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)


#ifndef __ASSEMBLY__
/* 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. ;)
 */
#define VMALLOC_OFFSET	(8*1024*1024)
#define VMALLOC_START	(((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
						~(VMALLOC_OFFSET-1))
#define VMALLOC_VMADDR(x) ((unsigned long)(x))
#define VMALLOC_END	(FIXADDR_START)

/*
 * The 4MB page is guessing..  Detailed in the infamous "Chapter H"
 * of the Pentium details, but assuming intel did the straightforward
 * thing, this bit set in the page directory entry just means that
 * the page directory entry points directly to a 4MB-aligned block of
 * memory. 
 */
#define _PAGE_PRESENT	0x001
#define _PAGE_RW	0x002
#define _PAGE_USER	0x004
#define _PAGE_PWT	0x008
#define _PAGE_PCD	0x010
#define _PAGE_ACCESSED	0x020
#define _PAGE_DIRTY	0x040
#define _PAGE_PSE	0x080	/* 4 MB (or 2MB) page, Pentium+, if present.. */
#define _PAGE_GLOBAL	0x100	/* Global TLB entry PPro+ */

#define _PAGE_PROTNONE	0x080	/* If not present */

#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	(PTE_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 \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
#define __PAGE_KERNEL_NOCACHE \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED)
#define __PAGE_KERNEL_RO \
	(_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED)

#ifdef CONFIG_X86_PGE
# define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
#else
# define MAKE_GLOBAL(x)						\
	({							\
		pgprot_t __ret;					\
								\
		if (cpu_has_pge)				\
			__ret = __pgprot((x) | _PAGE_GLOBAL);	\
		else						\
			__ret = __pgprot(x);			\
		__ret;						\
	})
#endif

#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)

/*
 * 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..
 */
#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

/*
 * Define this if things work differently on an i386 and an i486:
 * it will (on an i486) warn about kernel memory accesses that are
 * done without a 'verify_area(VERIFY_WRITE,..)'
 */
#undef TEST_VERIFY_AREA

/* page table for 0-4MB for everybody */
extern unsigned long pg0[1024];

/*
 * Handling allocation failures during page table setup.
 */
extern void __handle_bad_pmd(pmd_t * pmd);
extern void __handle_bad_pmd_kernel(pmd_t * pmd);

#define pte_none(x)	(!pte_val(x))
#define pte_present(x)	(pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
#define pte_clear(xp)	do { set_pte(xp, __pte(0)); } while (0)
#define pte_pagenr(x)	((unsigned long)((pte_val(x) >> PAGE_SHIFT)))

#define pmd_none(x)	(!pmd_val(x))
#define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
#define pmd_clear(xp)	do { set_pmd(xp, __pmd(0)); } while (0)
#define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)

/*
 * Permanent address of a page. Obviously must never be
 * called on a highmem page.
 */
#define page_address(page) ((page)->virtual)
#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
#define pte_page(x) (mem_map+pte_pagenr(x))

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
extern inline int pte_read(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
extern inline int pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
extern inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }

extern inline pte_t pte_rdprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
extern inline pte_t pte_exprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
extern inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
extern inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
extern inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
extern inline pte_t pte_mkread(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
extern inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
extern inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
extern inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
extern inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }

/*
 * 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,pgprot) \
({									\
	pte_t __pte;							\
									\
	set_pte(&__pte, __pte(((page)-mem_map) * 			\
		(unsigned long long)PAGE_SIZE + pgprot_val(pgprot)));	\
	__pte;								\
})

/* This takes a physical page address that is used by the remapping functions */
#define mk_pte_phys(physpage, pgprot) \
({ pte_t __pte; set_pte(&__pte, __pte(physpage + pgprot_val(pgprot))); __pte; })

extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{ set_pte(&pte, __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot))); return pte; }

#define page_pte(page) page_pte_prot(page, __pgprot(0))

#define pmd_page(pmd) \
((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))

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

#define __pgd_offset(address) pgd_index(address)

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

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

#define __pmd_offset(address) \
		(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))

/* Find an entry in the third-level page table.. */
#define __pte_offset(address) \
		((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset(dir, address) ((pte_t *) pmd_page(*(dir)) + \
			__pte_offset(address))

/*
 * The i386 doesn't have any external MMU info: the kernel page
 * tables contain all the necessary information.
 */
#define update_mmu_cache(vma,address,pte) do { } while (0)

/* Encode and de-code a swap entry */
#define SWP_TYPE(x)			(((x).val >> 1) & 0x3f)
#define SWP_OFFSET(x)			((x).val >> 8)
#define SWP_ENTRY(type, offset)		((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
#define pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
#define swp_entry_to_pte(x)		((pte_t) { (x).val })

#define module_map      vmalloc
#define module_unmap    vfree

#endif /* !__ASSEMBLY__ */

/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
#define PageSkip(page)		(0)
#define kern_addr_valid(addr)	(1)

#define io_remap_page_range remap_page_range

#endif /* _I386_PGTABLE_H */