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
|
#ifndef _I386_PGTABLE_H
#define _I386_PGTABLE_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>
#include <asm/paravirt.h>
#ifndef _I386_BITOPS_H
#include <asm/bitops.h>
#endif
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
struct mm_struct;
struct vm_area_struct;
/*
* 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))
extern unsigned long empty_zero_page[1024];
extern pgd_t swapper_pg_dir[1024];
extern struct kmem_cache *pmd_cache;
extern spinlock_t pgd_lock;
extern struct page *pgd_list;
void check_pgt_cache(void);
void pmd_ctor(void *, struct kmem_cache *, unsigned long);
void pgtable_cache_init(void);
void paging_init(void);
/*
* 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.
*/
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level-defs.h>
# define PMD_SIZE (1UL << PMD_SHIFT)
# define PMD_MASK (~(PMD_SIZE-1))
#else
# include <asm/pgtable-2level-defs.h>
#endif
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
#define FIRST_USER_ADDRESS 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)
/* 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))
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
#else
# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
#endif
/*
* _PAGE_PSE set in the page directory entry just means that
* the page directory entry points directly to a 4MB-aligned block of
* memory.
*/
#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, Pentium+, if present.. */
#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
#define _PAGE_BIT_UNUSED2 10
#define _PAGE_BIT_UNUSED3 11
#define _PAGE_BIT_NX 63
#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_UNUSED1 0x200 /* available for programmer */
#define _PAGE_UNUSED2 0x400
#define _PAGE_UNUSED3 0x800
/* If _PAGE_PRESENT is clear, we use these: */
#define _PAGE_FILE 0x040 /* nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_PROTNONE 0x080 /* if the user mapped it with PROT_NONE;
pte_present gives true */
#ifdef CONFIG_X86_PAE
#define _PAGE_NX (1ULL<<_PAGE_BIT_NX)
#else
#define _PAGE_NX 0
#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 (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_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_EXEC \
__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY \
PAGE_COPY_NOEXEC
#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)
extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
/*
* 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_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
/*
* 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 'access_ok(VERIFY_WRITE,..)'
*/
#undef TEST_ACCESS_OK
/* The boot page tables (all created as a single array) */
extern unsigned long pg0[];
#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
#define pmd_none(x) (!(unsigned long)pmd_val(x))
#define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT)
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
static inline int pte_huge(pte_t pte) { return (pte).pte_low & _PAGE_PSE; }
/*
* The following only works if pte_present() is not true.
*/
static inline int pte_file(pte_t pte) { return (pte).pte_low & _PAGE_FILE; }
static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return pte; }
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level.h>
#else
# include <asm/pgtable-2level.h>
#endif
#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
/* 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;
}
/*
* 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) { \
(ptep)->pte_low = (entry).pte_low; \
pte_update_defer((vma)->vm_mm, (address), (ptep)); \
flush_tlb_page(vma, address); \
} \
__changed; \
})
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define ptep_test_and_clear_young(vma, addr, ptep) ({ \
int __ret = 0; \
if (pte_young(*(ptep))) \
__ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, \
&(ptep)->pte_low); \
if (__ret) \
pte_update((vma)->vm_mm, addr, ptep); \
__ret; \
})
#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
#define ptep_clear_flush_young(vma, address, ptep) \
({ \
int __young; \
__young = ptep_test_and_clear_young((vma), (address), (ptep)); \
if (__young) \
flush_tlb_page(vma, address); \
__young; \
})
#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, &ptep->pte_low);
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));
}
/*
* Macro to mark a page protection value as "uncacheable". On processors which do not support
* it, this is a no-op.
*/
#define pgprot_noncached(prot) ((boot_cpu_data.x86 > 3) \
? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) : (prot))
/*
* 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) pfn_pte(page_to_pfn(page), (pgprot))
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pte.pte_low &= _PAGE_CHG_MASK;
pte.pte_low |= pgprot_val(newprot);
#ifdef CONFIG_X86_PAE
/*
* Chop off the NX bit (if present), and add the NX portion of
* the newprot (if present):
*/
pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
pte.pte_high |= (pgprot_val(newprot
|