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
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
|
/*
* Kernel-based Virtual Machine driver for Linux
*
* This module enables machines with Intel VT-x extensions to run virtual
* machines without emulation or binary translation.
*
* MMU support
*
* Copyright (C) 2006 Qumranet, Inc.
*
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
/*
* We need the mmu code to access both 32-bit and 64-bit guest ptes,
* so the code in this file is compiled twice, once per pte size.
*/
#if PTTYPE == 64
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
#define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
#define PT_LEVEL_BITS PT64_LEVEL_BITS
#ifdef CONFIG_X86_64
#define PT_MAX_FULL_LEVELS 4
#else
#define PT_MAX_FULL_LEVELS 2
#endif
#elif PTTYPE == 32
#define pt_element_t u32
#define guest_walker guest_walker32
#define FNAME(name) paging##32_##name
#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
#define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
#define PT_LEVEL_BITS PT32_LEVEL_BITS
#define PT_MAX_FULL_LEVELS 2
#else
#error Invalid PTTYPE value
#endif
/*
* The guest_walker structure emulates the behavior of the hardware page
* table walker.
*/
struct guest_walker {
int level;
gfn_t table_gfn[PT_MAX_FULL_LEVELS];
pt_element_t *table;
pt_element_t pte;
pt_element_t *ptep;
struct page *page;
int index;
pt_element_t inherited_ar;
gfn_t gfn;
u32 error_code;
};
/*
* Fetch a guest pte for a guest virtual address
*/
static int FNAME(walk_addr)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr,
int write_fault, int user_fault, int fetch_fault)
{
hpa_t hpa;
struct kvm_memory_slot *slot;
pt_element_t *ptep;
pt_element_t root;
gfn_t table_gfn;
pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
walker->level = vcpu->mmu.root_level;
walker->table = NULL;
walker->page = NULL;
walker->ptep = NULL;
root = vcpu->cr3;
#if PTTYPE == 64
if (!is_long_mode(vcpu)) {
walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
root = *walker->ptep;
walker->pte = root;
if (!(root & PT_PRESENT_MASK))
goto not_present;
--walker->level;
}
#endif
table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
walker->table_gfn[walker->level - 1] = table_gfn;
pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
walker->level - 1, table_gfn);
slot = gfn_to_memslot(vcpu->kvm, table_gfn);
hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK);
walker->page = pfn_to_page(hpa >> PAGE_SHIFT);
walker->table = kmap_atomic(walker->page, KM_USER0);
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
(vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0);
walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
for (;;) {
int index = PT_INDEX(addr, walker->level);
hpa_t paddr;
ptep = &walker->table[index];
walker->index = index;
ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
((unsigned long)ptep & PAGE_MASK));
if (!is_present_pte(*ptep))
goto not_present;
if (write_fault && !is_writeble_pte(*ptep))
if (user_fault || is_write_protection(vcpu))
goto access_error;
if (user_fault && !(*ptep & PT_USER_MASK))
goto access_error;
#if PTTYPE == 64
if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK))
goto access_error;
#endif
if (!(*ptep & PT_ACCESSED_MASK)) {
mark_page_dirty(vcpu->kvm, table_gfn);
*ptep |= PT_ACCESSED_MASK;
}
if (walker->level == PT_PAGE_TABLE_LEVEL) {
walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
>> PAGE_SHIFT;
break;
}
if (walker->level == PT_DIRECTORY_LEVEL
&& (*ptep & PT_PAGE_SIZE_MASK)
&& (PTTYPE == 64 || is_pse(vcpu))) {
walker->gfn = (*ptep & PT_DIR_BASE_ADDR_MASK)
>> PAGE_SHIFT;
walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
break;
}
walker->inherited_ar &= walker->table[index];
table_gfn = (*ptep & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
kunmap_atomic(walker->table, KM_USER0);
paddr = safe_gpa_to_hpa(vcpu, table_gfn << PAGE_SHIFT);
walker->page = pfn_to_page(paddr >> PAGE_SHIFT);
walker->table = kmap_atomic(walker->page, KM_USER0);
--walker->level;
walker->table_gfn[walker->level - 1 ] = table_gfn;
pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
walker->level - 1, table_gfn);
}
walker->pte = *ptep;
if (walker->page)
walker->ptep = NULL;
if (walker->table)
kunmap_atomic(walker->table, KM_USER0);
pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
return 1;
not_present:
walker->error_code = 0;
goto err;
access_error:
walker->error_code = PFERR_PRESENT_MASK;
err:
if (write_fault)
walker->error_code |= PFERR_WRITE_MASK;
if (user_fault)
walker->error_code |= PFERR_USER_MASK;
if (fetch_fault)
walker->error_code |= PFERR_FETCH_MASK;
if (walker->table)
kunmap_atomic(walker->table, KM_USER0);
return 0;
}
static void FNAME(mark_pagetable_dirty)(struct kvm *kvm,
struct guest_walker *walker)
{
mark_page_dirty(kvm, walker->table_gfn[walker->level - 1]);
}
static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
u64 *shadow_pte,
gpa_t gaddr,
pt_element_t gpte,
u64 access_bits,
int user_fault,
int write_fault,
int *ptwrite,
struct guest_walker *walker,
gfn_t gfn)
{
hpa_t paddr;
int dirty = gpte & PT_DIRTY_MASK;
u64 spte;
int was_rmapped = is_rmap_pte(*shadow_pte);
pgprintk("%s: spte %llx gpte %llx access %llx write_fault %d"
" user_fault %d gfn %lx\n",
__FUNCTION__, *shadow_pte, (u64)gpte, access_bits,
write_fault, user_fault, gfn);
if (write_fault && !dirty) {
pt_element_t *guest_ent, *tmp = NULL;
if (walker->ptep)
guest_ent = walker->ptep;
else {
tmp = kmap_atomic(walker->page, KM_USER0);
guest_ent = &tmp[walker->index];
}
*guest_ent |= PT_DIRTY_MASK;
if (!walker->ptep)
kunmap_atomic(tmp, KM_USER0);
dirty = 1;
FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
}
/*
* We don't set the accessed bit, since we sometimes want to see
* whether the guest actually used the pte (in order to detect
* demand paging).
*/
spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
spte |= gpte & PT64_NX_MASK;
if (!dirty)
access_bits &= ~PT_WRITABLE_MASK;
paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
spte |= PT_PRESENT_MASK;
if (access_bits & PT_USER_MASK)
spte |= PT_USER_MASK;
if (is_error_hpa(paddr)) {
set_shadow_pte(shadow_pte,
shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK);
return;
}
spte |= paddr;
if ((access_bits & PT_WRITABLE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
struct kvm_mmu_page *shadow;
spte |= PT_WRITABLE_MASK;
if (user_fault) {
mmu_unshadow(vcpu, gfn);
goto unshadowed;
}
shadow = kvm_mmu_lookup_page(vcpu, gfn);
if (shadow) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__FUNCTION__, gfn);
access_bits &= ~PT_WRITABLE_MASK;
if (is_writeble_pte(spte)) {
spte &= ~PT_WRITABLE_MASK;
kvm_x86_ops->tlb_flush(vcpu);
}
if (write_fault)
*ptwrite = 1;
}
}
unshadowed:
if (access_bits & PT_WRITABLE_MASK)
mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
set_shadow_pte(shadow_pte, spte);
page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
if (!was_rmapped)
rmap_add(vcpu, shadow_pte, (gaddr & PT64_BASE_ADDR_MASK)
>> PAGE_SHIFT);
if (!ptwrite || !*ptwrite)
vcpu->last_pte_updated = shadow_pte;
}
static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t gpte,
u64 *shadow_pte, u64 access_bits,
int user_fault, int write_fault, int *ptwrite,
struct guest_walker *walker, gfn_t gfn)
{
access_bits &= gpte;
FNAME(set_pte_common)(vcpu, shadow_pte, gpte & PT_BASE_ADDR_MASK,
gpte, access_bits, user_fault, write_fault,
ptwrite, walker, gfn);
}
static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
u64 *spte, const void *pte, int bytes,
int offset_in_pte)
{
pt_element_t gpte;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
if (!offset_in_pte && !is_present_pte(gpte))
set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
return;
}
if (bytes < sizeof(pt_element_t))
return;
pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
FNAME(set_pte)(vcpu, gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0,
0, NULL, NULL,
(gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT);
}
static void FNAME(set_pde)(struct kvm_vcpu *vcpu, pt_element_t gpde,
u64 *shadow_pte, u64 access_bits,
int user_fault, int write_fault, int *ptwrite,
struct guest_walker *walker, gfn_t gfn)
{
gpa_t gaddr;
access_bits &= gpde;
gaddr = (gpa_t)gfn << PAGE_SHIFT;
if (PTTYPE == 32 && is_cpuid_PSE36())
gaddr |= (gpde & PT32_DIR_PSE36_MASK) <<
(32 - PT32_DIR_PSE36_SHIFT);
FNAME(set_pte_common)(vcpu, shadow_pte, gaddr,
gpde, access_bits, user_fault, write_fault,
ptwrite, walker, gfn);
}
/*
* Fetch a shadow pte for a specific level in the paging hierarchy.
*/
static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *walker,
int user_fault, int write_fault, int *ptwrite)
{
hpa_t shadow_addr;
int level;
u64 *shadow_ent;
u64 *prev_shadow_ent = NULL;
if (!is_present_pte(walker->pte))
return NULL;
shadow_addr = vcpu->mmu.root_hpa;
level = vcpu->mmu.shadow_root_level;
if (level == PT32E_ROOT_LEVEL) {
shadow_addr = vcpu->mmu.pae_root[(addr >> 30) & 3];
shadow_addr &= PT64_BASE_ADDR_MASK;
--level;
}
for (; ; level--) {
u32 index = SHADOW_PT_INDEX(addr, level);
struct kvm_mmu_page *shadow_page;
u64 shadow_pte;
int metaphysical;
gfn_t table_gfn;
unsigned hugepage_access = 0;
shadow_ent = ((u64 *)__va(shadow_addr)) + index;
if (is_shadow_present_pte(*shadow_ent)) {
if (level == PT_PAGE_TABLE_LEVEL)
break;
shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
prev_shadow_ent = shadow_ent;
continue;
}
if (level == PT_PAGE_TABLE_LEVEL)
break;
if (level - 1 == PT_PAGE_TABLE_LEVEL
&& walker->level == PT_DIRECTORY_LEVEL) {
metaphysical = 1;
hugepage_access = walker->pte;
hugepage_access &= PT_USER_MASK | PT_WRITABLE_MASK;
if (walker->pte & PT64_NX_MASK)
hugepage_access |= (1 << 2);
hugepage_access >>= PT_WRITABLE_SHIFT;
table_gfn = (walker->pte & PT_BASE_ADDR_MASK)
>> PAGE_SHIFT;
} else {
metaphysical = 0;
table_gfn = walker->table_gfn[level - 2];
}
shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
metaphysical, hugepage_access,
shadow_ent);
shadow_addr = __pa(shadow_page->spt);
shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
| PT_WRITABLE_MASK | PT_USER_MASK;
*shadow_ent = shadow_pte;
prev_shadow_ent = shadow_ent;
}
if (walker->level == PT_DIRECTORY_LEVEL) {
FNAME(set_pde)(vcpu, walker->pte, shadow_ent,
walker->inherited_ar, user_fault, write_fault,
ptwrite, walker, walker->gfn);
} else {
ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
FNAME(set_pte)(vcpu, walker->pte, shadow_ent,
walker->inherited_ar, user_fault, write_fault,
ptwrite, walker, walker->gfn);
}
return shadow_ent;
}
/*
* Page fault handler. There are several causes for a page fault:
* - there is no shadow pte for the guest pte
* - write access through a shadow pte marked read only so that we can set
* the dirty bit
* - write access to a shadow pte marked read only so we can update the page
* dirty bitmap, when userspace requests it
* - mmio access; in this case we will never install a present shadow pte
* - normal guest page fault due to the guest pte marked not present, not
* writable, or not executable
*
* Returns: 1 if we need to emulate the instruction, 0 otherwise, or
* a negative value on error.
*/
static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
u32 error_code)
{
int write_fault = error_code & PFERR_WRITE_MASK;
int user_fault = error_code & PFERR_USER_MASK;
int fetch_fault = error_code & PFERR_FETCH_MASK;
struct guest_walker walker;
u64 *shadow_pte;
int write_pt = 0;
int r;
pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code);
kvm_mmu_audit(vcpu, "pre page fault");
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
/*
* Look up the shadow pte for the faulting address.
*/
r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault,
fetch_fault);
/*
* The page is not mapped by the guest. Let the guest handle it.
*/
if (!r) {
pgprintk("%s: guest page fault\n", __FUNCTION__);
inject_page_fault(vcpu, addr, walker.error_code);
vcpu->last_pt_write_count = 0; /* reset fork detector */
return 0;
}
shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
&write_pt);
pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__,
shadow_pte, *shadow_pte, write_pt);
if (!write_pt)
vcpu->last_pt_write_count = 0; /* reset fork detector */
/*
* mmio: emulate if accessible, otherwise its a guest fault.
*/
if (is_io_pte(*shadow_pte))
return 1;
++vcpu->stat.pf_fixed;
kvm_mmu_audit(vcpu, "post page fault (fixed)");
return write_pt;
}
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
{
struct guest_walker walker;
gpa_t gpa = UNMAPPED_GVA;
int r;
r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
if (r) {
gpa = (gpa_t)walker.gfn << PAGE_SHIFT;
gpa |= vaddr & ~PAGE_MASK;
}
return gpa;
}
static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp)
{
int i;
pt_element_t *gpt;
if (sp->role.metaphysical || PTTYPE == 32) {
nonpaging_prefetch_page(vcpu, sp);
return;
}
gpt = kmap_atomic(gfn_to_page(vcpu->kvm, sp->gfn), KM_USER0);
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
if (is_present_pte(gpt[i]))
sp->spt[i] = shadow_trap_nonpresent_pte;
else
sp->spt[i] = shadow_notrap_nonpresent_pte;
kunmap_atomic(gpt, KM_USER0);
}
#undef pt_element_t
#undef guest_walker
#undef FNAME
#undef PT_BASE_ADDR_MASK
#undef PT_INDEX
#undef SHADOW_PT_INDEX
#undef PT_LEVEL_MASK
#undef PT_DIR_BASE_ADDR_MASK
#undef PT_LEVEL_BITS
#undef PT_MAX_FULL_LEVELS
|