aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-x86_64/pgtable.h
blob: 60cff1e4f7a34b9797dcb8eb4b6e39e6ff839867 (plain) (blame)
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
#ifndef _X86_64_PGTABLE_H
#define _X86_64_PGTABLE_H

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

/*
 * This file contains the functions and defines necessary to modify and use
 * the x86-64 page table tree.
 */
#include <asm/processor.h>
#include <asm/bitops.h>
#include <linux/threads.h>
#include <asm/pda.h>

extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pgd_t init_level4_pgt[];
extern unsigned long __supported_pte_mask;

#define swapper_pg_dir init_level4_pgt

extern void paging_init(void);
extern void clear_kernel_mapping(unsigned long addr, unsigned long size);

/*
 * 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))

#endif /* !__ASSEMBLY__ */

/*
 * PGDIR_SHIFT determines what a top-level page table entry can map
 */
#define PGDIR_SHIFT	39
#define PTRS_PER_PGD	512

/*
 * 3rd level page
 */
#define PUD_SHIFT	30
#define PTRS_PER_PUD	512

/*
 * PMD_SHIFT determines the size of the area a middle-level
 * page table can map
 */
#define PMD_SHIFT	21
#define PTRS_PER_PMD	512

/*
 * entries per page directory level
 */
#define PTRS_PER_PTE	512

#ifndef __ASSEMBLY__

#define pte_ERROR(e) \
	printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
#define pmd_ERROR(e) \
	printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
#define pud_ERROR(e) \
	printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e))
#define pgd_ERROR(e) \
	printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))

#define pgd_none(x)	(!pgd_val(x))
#define pud_none(x)	(!pud_val(x))

static inline void set_pte(pte_t *dst, pte_t val)
{
	pte_val(*dst) = pte_val(val);
} 
#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)

static inline void set_pmd(pmd_t *dst, pmd_t val)
{
        pmd_val(*dst) = pmd_val(val); 
} 

static inline void set_pud(pud_t *dst, pud_t val)
{
	pud_val(*dst) = pud_val(val);
}

static inline void pud_clear (pud_t *pud)
{
	set_pud(pud, __pud(0));
}

static inline void set_pgd(pgd_t *dst, pgd_t val)
{
	pgd_val(*dst) = pgd_val(val); 
} 

static inline void pgd_clear (pgd_t * pgd)
{
	set_pgd(pgd, __pgd(0));
}

#define ptep_get_and_clear(mm,addr,xp)	__pte(xchg(&(xp)->pte, 0))

struct mm_struct;

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) {
		pte = *ptep;
		*ptep = __pte(0);
	} else {
		pte = ptep_get_and_clear(mm, addr, ptep);
	}
	return pte;
}

#define pte_same(a, b)		((a).pte == (b).pte)

#define pte_pgprot(a)	(__pgprot((a).pte & ~PHYSICAL_PAGE_MASK))

#endif /* !__ASSEMBLY__ */

#define PMD_SIZE	(_AC(1,UL) << PMD_SHIFT)
#define PMD_MASK	(~(PMD_SIZE-1))
#define PUD_SIZE	(_AC(1,UL) << PUD_SHIFT)
#define PUD_MASK	(~(PUD_SIZE-1))
#define PGDIR_SIZE	(_AC(1,UL) << PGDIR_SHIFT)
#define PGDIR_MASK	(~(PGDIR_SIZE-1))

#define USER_PTRS_PER_PGD	((TASK_SIZE-1)/PGDIR_SIZE+1)
#define FIRST_USER_ADDRESS	0

#define MAXMEM		 _AC(0x3fffffffffff, UL)
#define VMALLOC_START    _AC(0xffffc20000000000, UL)
#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
#define MODULES_VADDR    _AC(0xffffffff88000000, UL)
#define MODULES_END      _AC(0xfffffffffff00000, UL)
#define MODULES_LEN   (MODULES_END - MODULES_VADDR)

#define _PAGE_BIT_PRESENT	0
#define _PAGE_BIT_RW		1
#define _PAGE_BIT_USER		2
#define _PAGE_BIT_PWT		3
#define _PAGE_BIT_PCD		4
#define _PAGE_BIT_ACCESSED	5
#define _PAGE_BIT_DIRTY		6
#define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
#define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */

#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	/* 2MB page */
#define _PAGE_FILE	0x040	/* nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_GLOBAL	0x100	/* Global TLB entry */

#define _PAGE_PROTNONE	0x080	/* If not present */
#define _PAGE_NX        (_AC(1,UL)<<_PAGE_BIT_NX)

#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 | _PAGE_NX)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
#define PAGE_COPY PAGE_COPY_NOEXEC
#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define __PAGE_KERNEL \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
#define __PAGE_KERNEL_EXEC \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
#define __PAGE_KERNEL_NOCACHE \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED | _PAGE_NX)
#define __PAGE_KERNEL_RO \
	(_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
#define __PAGE_KERNEL_VSYSCALL \
	(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define __PAGE_KERNEL_VSYSCALL_NOCACHE \
	(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD)
#define __PAGE_KERNEL_LARGE \
	(__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC \
	(__PAGE_KERNEL_EXEC | _PAGE_PSE)

#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)

#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)

/*         xwr */
#define __P000	PAGE_NONE
#define __P001	PAGE_READONLY
#define __P010	PAGE_COPY
#define __P011	PAGE_COPY
#define __P100	PAGE_READONLY_EXEC
#define __P101	PAGE_READONLY_EXEC
#define __P110	PAGE_COPY_EXEC
#define __P111	PAGE_COPY_EXEC

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

#ifndef __ASSEMBLY__

static inline unsigned long pgd_bad(pgd_t pgd)
{
	return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
}

static inline unsigned long pud_bad(pud_t pud)
{
	return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
}

static inline unsigned long pmd_bad(pmd_t pmd)
{
	return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
}

#define pte_none(x)	(!pte_val(x))
#define pte_present(x)	(pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
#define pte_clear(mm,addr,xp)	do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)

#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))	/* FIXME: is this
						   right? */
#define pte_page(x)	pfn_to_page(pte_pfn(x))
#define pte_pfn(x)  ((pte_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
	pte_t pte;
	pte_val(pte) = (page_nr << PAGE_SHIFT);
	pte_val(pte) |= pgprot_val(pgprot);
	pte_val(pte) &= __supported_pte_mask;
	return pte;
}

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
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_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
static inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_PSE; }

static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
static inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
static inline pte_t pte_clrhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }

struct vm_area_struct;

static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
{
	if (!pte_young(*ptep))
		return 0;
	return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
}

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

/*
 * Macro to mark a page protection value as "uncacheable".
 */
#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))

static inline int pmd_large(pmd_t pte) { 
	return (pmd_val(pte) & __LARGE_PTE) == __LARGE_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.
 */

/*
 * Level 4 access.
 */
#define pgd_page_vaddr(pgd) ((unsigned long) __va((unsigned long)pgd_val(pgd) & PTE_MASK))
#define pgd_page(pgd)		(pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT))
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr))
#define pgd_offset_k(address) (init_level4_pgt + pgd_index(address))
#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })

/* PUD - Level3 access */
/* to find an entry in a page-table-directory. */
#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
#define pud_page(pud)		(pfn_to_page(pud_val(pud) >> PAGE_SHIFT))
#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
#define pud_offset(pgd, address) ((pud_t *) pgd_page_vaddr(*(pgd)) + pud_index(address))
#define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)

/* PMD  - Level 2 access */
#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
#define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))

#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
#define pmd_offset(dir, address) ((pmd_t *) pud_page_vaddr(*(dir)) + \
			pmd_index(address))
#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 pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
#define pmd_pfn(x)  ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)

#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT

/* PTE - Level 1 access. */

/* page, protection -> pte */
#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE)
 
/* Change flags of a PTE */
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{ 
	pte_val(pte) &= _PAGE_CHG_MASK;
	pte_val(pte) |= pgprot_val(newprot);
	pte_val(pte) &= __supported_pte_mask;
       return pte; 
}

#define pte_index(address) \
		(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
			pte_index(address))

/* x86-64 always has all page tables mapped. */
#define pte_offset_map(dir,address) pte_offset_kernel(dir,address)
#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address)
#define pte_unmap(pte) /* NOP */
#define pte_unmap_nested(pte) /* NOP */ 

#define update_mmu_cache(vma,address,pte) do { } while (0)

/* 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. */
#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
({									  \
	int __changed = !pte_same(*(__ptep), __entry);			  \
	if (__changed && __dirty) {					  \
		set_pte(__ptep, __entry);			  	  \
		flush_tlb_page(__vma, __address);		  	  \
	}								  \
	__changed;							  \
})

/* 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 })

extern spinlock_t pgd_lock;
extern struct list_head pgd_list;

extern int kern_addr_valid(unsigned long addr); 

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

#define HAVE_ARCH_UNMAPPED_AREA

#define pgtable_cache_init()   do { } while (0)

#define PAGE_AGP    PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1

/* fs/proc/kcore.c */
#define	kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
#define	kc_offset_to_vaddr(o) \
   (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o))

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
#define __HAVE_ARCH_PTE_SAME
#include <asm-generic/pgtable.h>
#endif /* !__ASSEMBLY__ */

#endif /* _X86_64_PGTABLE_H */