aboutsummaryrefslogtreecommitdiff
path: root/target/i386/tcg/excp_helper.c
blob: 1e71e44510ec5282809563bc72ecaac65d837b85 (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
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
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
/*
 *  x86 exception helpers
 *
 *  Copyright (c) 2003 Fabrice Bellard
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */

#include "qemu/osdep.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "qemu/log.h"
#include "sysemu/runstate.h"
#include "exec/helper-proto.h"
#include "helper-tcg.h"

void helper_raise_interrupt(CPUX86State *env, int intno, int next_eip_addend)
{
    raise_interrupt(env, intno, 1, 0, next_eip_addend);
}

void helper_raise_exception(CPUX86State *env, int exception_index)
{
    raise_exception(env, exception_index);
}

/*
 * Check nested exceptions and change to double or triple fault if
 * needed. It should only be called, if this is not an interrupt.
 * Returns the new exception number.
 */
static int check_exception(CPUX86State *env, int intno, int *error_code,
                           uintptr_t retaddr)
{
    int first_contributory = env->old_exception == 0 ||
                              (env->old_exception >= 10 &&
                               env->old_exception <= 13);
    int second_contributory = intno == 0 ||
                               (intno >= 10 && intno <= 13);

    qemu_log_mask(CPU_LOG_INT, "check_exception old: 0x%x new 0x%x\n",
                env->old_exception, intno);

#if !defined(CONFIG_USER_ONLY)
    if (env->old_exception == EXCP08_DBLE) {
        if (env->hflags & HF_GUEST_MASK) {
            cpu_vmexit(env, SVM_EXIT_SHUTDOWN, 0, retaddr); /* does not return */
        }

        qemu_log_mask(CPU_LOG_RESET, "Triple fault\n");

        qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
        return EXCP_HLT;
    }
#endif

    if ((first_contributory && second_contributory)
        || (env->old_exception == EXCP0E_PAGE &&
            (second_contributory || (intno == EXCP0E_PAGE)))) {
        intno = EXCP08_DBLE;
        *error_code = 0;
    }

    if (second_contributory || (intno == EXCP0E_PAGE) ||
        (intno == EXCP08_DBLE)) {
        env->old_exception = intno;
    }

    return intno;
}

/*
 * Signal an interruption. It is executed in the main CPU loop.
 * is_int is TRUE if coming from the int instruction. next_eip is the
 * env->eip value AFTER the interrupt instruction. It is only relevant if
 * is_int is TRUE.
 */
static void QEMU_NORETURN raise_interrupt2(CPUX86State *env, int intno,
                                           int is_int, int error_code,
                                           int next_eip_addend,
                                           uintptr_t retaddr)
{
    CPUState *cs = env_cpu(env);

    if (!is_int) {
        cpu_svm_check_intercept_param(env, SVM_EXIT_EXCP_BASE + intno,
                                      error_code, retaddr);
        intno = check_exception(env, intno, &error_code, retaddr);
    } else {
        cpu_svm_check_intercept_param(env, SVM_EXIT_SWINT, 0, retaddr);
    }

    cs->exception_index = intno;
    env->error_code = error_code;
    env->exception_is_int = is_int;
    env->exception_next_eip = env->eip + next_eip_addend;
    cpu_loop_exit_restore(cs, retaddr);
}

/* shortcuts to generate exceptions */

void QEMU_NORETURN raise_interrupt(CPUX86State *env, int intno, int is_int,
                                   int error_code, int next_eip_addend)
{
    raise_interrupt2(env, intno, is_int, error_code, next_eip_addend, 0);
}

void raise_exception_err(CPUX86State *env, int exception_index,
                         int error_code)
{
    raise_interrupt2(env, exception_index, 0, error_code, 0, 0);
}

void raise_exception_err_ra(CPUX86State *env, int exception_index,
                            int error_code, uintptr_t retaddr)
{
    raise_interrupt2(env, exception_index, 0, error_code, 0, retaddr);
}

void raise_exception(CPUX86State *env, int exception_index)
{
    raise_interrupt2(env, exception_index, 0, 0, 0, 0);
}

void raise_exception_ra(CPUX86State *env, int exception_index, uintptr_t retaddr)
{
    raise_interrupt2(env, exception_index, 0, 0, 0, retaddr);
}

#if !defined(CONFIG_USER_ONLY)
static hwaddr get_hphys(CPUState *cs, hwaddr gphys, MMUAccessType access_type,
                        int *prot)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;
    uint64_t rsvd_mask = PG_ADDRESS_MASK & ~MAKE_64BIT_MASK(0, cpu->phys_bits);
    uint64_t ptep, pte;
    uint64_t exit_info_1 = 0;
    target_ulong pde_addr, pte_addr;
    uint32_t page_offset;
    int page_size;

    if (likely(!(env->hflags2 & HF2_NPT_MASK))) {
        return gphys;
    }

    if (!(env->nested_pg_mode & SVM_NPT_NXE)) {
        rsvd_mask |= PG_NX_MASK;
    }

    if (env->nested_pg_mode & SVM_NPT_PAE) {
        uint64_t pde, pdpe;
        target_ulong pdpe_addr;

#ifdef TARGET_X86_64
        if (env->nested_pg_mode & SVM_NPT_LMA) {
            uint64_t pml5e;
            uint64_t pml4e_addr, pml4e;

            pml5e = env->nested_cr3;
            ptep = PG_NX_MASK | PG_USER_MASK | PG_RW_MASK;

            pml4e_addr = (pml5e & PG_ADDRESS_MASK) +
                    (((gphys >> 39) & 0x1ff) << 3);
            pml4e = x86_ldq_phys(cs, pml4e_addr);
            if (!(pml4e & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            if (pml4e & (rsvd_mask | PG_PSE_MASK)) {
                goto do_fault_rsvd;
            }
            if (!(pml4e & PG_ACCESSED_MASK)) {
                pml4e |= PG_ACCESSED_MASK;
                x86_stl_phys_notdirty(cs, pml4e_addr, pml4e);
            }
            ptep &= pml4e ^ PG_NX_MASK;
            pdpe_addr = (pml4e & PG_ADDRESS_MASK) +
                    (((gphys >> 30) & 0x1ff) << 3);
            pdpe = x86_ldq_phys(cs, pdpe_addr);
            if (!(pdpe & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            if (pdpe & rsvd_mask) {
                goto do_fault_rsvd;
            }
            ptep &= pdpe ^ PG_NX_MASK;
            if (!(pdpe & PG_ACCESSED_MASK)) {
                pdpe |= PG_ACCESSED_MASK;
                x86_stl_phys_notdirty(cs, pdpe_addr, pdpe);
            }
            if (pdpe & PG_PSE_MASK) {
                /* 1 GB page */
                page_size = 1024 * 1024 * 1024;
                pte_addr = pdpe_addr;
                pte = pdpe;
                goto do_check_protect;
            }
        } else
#endif
        {
            pdpe_addr = (env->nested_cr3 & ~0x1f) + ((gphys >> 27) & 0x18);
            pdpe = x86_ldq_phys(cs, pdpe_addr);
            if (!(pdpe & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            rsvd_mask |= PG_HI_USER_MASK;
            if (pdpe & (rsvd_mask | PG_NX_MASK)) {
                goto do_fault_rsvd;
            }
            ptep = PG_NX_MASK | PG_USER_MASK | PG_RW_MASK;
        }

        pde_addr = (pdpe & PG_ADDRESS_MASK) + (((gphys >> 21) & 0x1ff) << 3);
        pde = x86_ldq_phys(cs, pde_addr);
        if (!(pde & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        if (pde & rsvd_mask) {
            goto do_fault_rsvd;
        }
        ptep &= pde ^ PG_NX_MASK;
        if (pde & PG_PSE_MASK) {
            /* 2 MB page */
            page_size = 2048 * 1024;
            pte_addr = pde_addr;
            pte = pde;
            goto do_check_protect;
        }
        /* 4 KB page */
        if (!(pde & PG_ACCESSED_MASK)) {
            pde |= PG_ACCESSED_MASK;
            x86_stl_phys_notdirty(cs, pde_addr, pde);
        }
        pte_addr = (pde & PG_ADDRESS_MASK) + (((gphys >> 12) & 0x1ff) << 3);
        pte = x86_ldq_phys(cs, pte_addr);
        if (!(pte & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        if (pte & rsvd_mask) {
            goto do_fault_rsvd;
        }
        /* combine pde and pte nx, user and rw protections */
        ptep &= pte ^ PG_NX_MASK;
        page_size = 4096;
    } else {
        uint32_t pde;

        /* page directory entry */
        pde_addr = (env->nested_cr3 & ~0xfff) + ((gphys >> 20) & 0xffc);
        pde = x86_ldl_phys(cs, pde_addr);
        if (!(pde & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        ptep = pde | PG_NX_MASK;

        /* if host cr4 PSE bit is set, then we use a 4MB page */
        if ((pde & PG_PSE_MASK) && (env->nested_pg_mode & SVM_NPT_PSE)) {
            page_size = 4096 * 1024;
            pte_addr = pde_addr;

            /* Bits 20-13 provide bits 39-32 of the address, bit 21 is reserved.
             * Leave bits 20-13 in place for setting accessed/dirty bits below.
             */
            pte = pde | ((pde & 0x1fe000LL) << (32 - 13));
            rsvd_mask = 0x200000;
            goto do_check_protect_pse36;
        }

        if (!(pde & PG_ACCESSED_MASK)) {
            pde |= PG_ACCESSED_MASK;
            x86_stl_phys_notdirty(cs, pde_addr, pde);
        }

        /* page directory entry */
        pte_addr = (pde & ~0xfff) + ((gphys >> 10) & 0xffc);
        pte = x86_ldl_phys(cs, pte_addr);
        if (!(pte & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        /* combine pde and pte user and rw protections */
        ptep &= pte | PG_NX_MASK;
        page_size = 4096;
        rsvd_mask = 0;
    }

 do_check_protect:
    rsvd_mask |= (page_size - 1) & PG_ADDRESS_MASK & ~PG_PSE_PAT_MASK;
 do_check_protect_pse36:
    if (pte & rsvd_mask) {
        goto do_fault_rsvd;
    }
    ptep ^= PG_NX_MASK;

    if (!(ptep & PG_USER_MASK)) {
        goto do_fault_protect;
    }
    if (ptep & PG_NX_MASK) {
        if (access_type == MMU_INST_FETCH) {
            goto do_fault_protect;
        }
        *prot &= ~PAGE_EXEC;
    }
    if (!(ptep & PG_RW_MASK)) {
        if (access_type == MMU_DATA_STORE) {
            goto do_fault_protect;
        }
        *prot &= ~PAGE_WRITE;
    }

    pte &= PG_ADDRESS_MASK & ~(page_size - 1);
    page_offset = gphys & (page_size - 1);
    return pte + page_offset;

 do_fault_rsvd:
    exit_info_1 |= SVM_NPTEXIT_RSVD;
 do_fault_protect:
    exit_info_1 |= SVM_NPTEXIT_P;
 do_fault:
    x86_stq_phys(cs, env->vm_vmcb + offsetof(struct vmcb, control.exit_info_2),
                 gphys);
    exit_info_1 |= SVM_NPTEXIT_US;
    if (access_type == MMU_DATA_STORE) {
        exit_info_1 |= SVM_NPTEXIT_RW;
    } else if (access_type == MMU_INST_FETCH) {
        exit_info_1 |= SVM_NPTEXIT_ID;
    }
    if (prot) {
        exit_info_1 |= SVM_NPTEXIT_GPA;
    } else { /* page table access */
        exit_info_1 |= SVM_NPTEXIT_GPT;
    }
    cpu_vmexit(env, SVM_EXIT_NPF, exit_info_1, env->retaddr);
}

/* return value:
 * -1 = cannot handle fault
 * 0  = nothing more to do
 * 1  = generate PF fault
 */
static int handle_mmu_fault(CPUState *cs, vaddr addr, int size,
                            int is_write1, int mmu_idx)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;
    uint64_t ptep, pte;
    int32_t a20_mask;
    target_ulong pde_addr, pte_addr;
    int error_code = 0;
    int is_dirty, prot, page_size, is_write, is_user;
    hwaddr paddr;
    uint64_t rsvd_mask = PG_ADDRESS_MASK & ~MAKE_64BIT_MASK(0, cpu->phys_bits);
    uint32_t page_offset;
    target_ulong vaddr;
    uint32_t pkr;

    is_user = mmu_idx == MMU_USER_IDX;
#if defined(DEBUG_MMU)
    printf("MMU fault: addr=%" VADDR_PRIx " w=%d u=%d eip=" TARGET_FMT_lx "\n",
           addr, is_write1, is_user, env->eip);
#endif
    is_write = is_write1 & 1;

    a20_mask = x86_get_a20_mask(env);
    if (!(env->cr[0] & CR0_PG_MASK)) {
        pte = addr;
#ifdef TARGET_X86_64
        if (!(env->hflags & HF_LMA_MASK)) {
            /* Without long mode we can only address 32bits in real mode */
            pte = (uint32_t)pte;
        }
#endif
        prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
        page_size = 4096;
        goto do_mapping;
    }

    if (!(env->efer & MSR_EFER_NXE)) {
        rsvd_mask |= PG_NX_MASK;
    }

    if (env->cr[4] & CR4_PAE_MASK) {
        uint64_t pde, pdpe;
        target_ulong pdpe_addr;

#ifdef TARGET_X86_64
        if (env->hflags & HF_LMA_MASK) {
            bool la57 = env->cr[4] & CR4_LA57_MASK;
            uint64_t pml5e_addr, pml5e;
            uint64_t pml4e_addr, pml4e;
            int32_t sext;

            /* test virtual address sign extension */
            sext = la57 ? (int64_t)addr >> 56 : (int64_t)addr >> 47;
            if (sext != 0 && sext != -1) {
                env->error_code = 0;
                cs->exception_index = EXCP0D_GPF;
                return 1;
            }

            if (la57) {
                pml5e_addr = ((env->cr[3] & ~0xfff) +
                        (((addr >> 48) & 0x1ff) << 3)) & a20_mask;
                pml5e_addr = get_hphys(cs, pml5e_addr, MMU_DATA_STORE, NULL);
                pml5e = x86_ldq_phys(cs, pml5e_addr);
                if (!(pml5e & PG_PRESENT_MASK)) {
                    goto do_fault;
                }
                if (pml5e & (rsvd_mask | PG_PSE_MASK)) {
                    goto do_fault_rsvd;
                }
                if (!(pml5e & PG_ACCESSED_MASK)) {
                    pml5e |= PG_ACCESSED_MASK;
                    x86_stl_phys_notdirty(cs, pml5e_addr, pml5e);
                }
                ptep = pml5e ^ PG_NX_MASK;
            } else {
                pml5e = env->cr[3];
                ptep = PG_NX_MASK | PG_USER_MASK | PG_RW_MASK;
            }

            pml4e_addr = ((pml5e & PG_ADDRESS_MASK) +
                    (((addr >> 39) & 0x1ff) << 3)) & a20_mask;
            pml4e_addr = get_hphys(cs, pml4e_addr, MMU_DATA_STORE, false);
            pml4e = x86_ldq_phys(cs, pml4e_addr);
            if (!(pml4e & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            if (pml4e & (rsvd_mask | PG_PSE_MASK)) {
                goto do_fault_rsvd;
            }
            if (!(pml4e & PG_ACCESSED_MASK)) {
                pml4e |= PG_ACCESSED_MASK;
                x86_stl_phys_notdirty(cs, pml4e_addr, pml4e);
            }
            ptep &= pml4e ^ PG_NX_MASK;
            pdpe_addr = ((pml4e & PG_ADDRESS_MASK) + (((addr >> 30) & 0x1ff) << 3)) &
                a20_mask;
            pdpe_addr = get_hphys(cs, pdpe_addr, MMU_DATA_STORE, NULL);
            pdpe = x86_ldq_phys(cs, pdpe_addr);
            if (!(pdpe & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            if (pdpe & rsvd_mask) {
                goto do_fault_rsvd;
            }
            ptep &= pdpe ^ PG_NX_MASK;
            if (!(pdpe & PG_ACCESSED_MASK)) {
                pdpe |= PG_ACCESSED_MASK;
                x86_stl_phys_notdirty(cs, pdpe_addr, pdpe);
            }
            if (pdpe & PG_PSE_MASK) {
                /* 1 GB page */
                page_size = 1024 * 1024 * 1024;
                pte_addr = pdpe_addr;
                pte = pdpe;
                goto do_check_protect;
            }
        } else
#endif
        {
            /* XXX: load them when cr3 is loaded ? */
            pdpe_addr = ((env->cr[3] & ~0x1f) + ((addr >> 27) & 0x18)) &
                a20_mask;
            pdpe_addr = get_hphys(cs, pdpe_addr, MMU_DATA_STORE, false);
            pdpe = x86_ldq_phys(cs, pdpe_addr);
            if (!(pdpe & PG_PRESENT_MASK)) {
                goto do_fault;
            }
            rsvd_mask |= PG_HI_USER_MASK;
            if (pdpe & (rsvd_mask | PG_NX_MASK)) {
                goto do_fault_rsvd;
            }
            ptep = PG_NX_MASK | PG_USER_MASK | PG_RW_MASK;
        }

        pde_addr = ((pdpe & PG_ADDRESS_MASK) + (((addr >> 21) & 0x1ff) << 3)) &
            a20_mask;
        pde_addr = get_hphys(cs, pde_addr, MMU_DATA_STORE, NULL);
        pde = x86_ldq_phys(cs, pde_addr);
        if (!(pde & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        if (pde & rsvd_mask) {
            goto do_fault_rsvd;
        }
        ptep &= pde ^ PG_NX_MASK;
        if (pde & PG_PSE_MASK) {
            /* 2 MB page */
            page_size = 2048 * 1024;
            pte_addr = pde_addr;
            pte = pde;
            goto do_check_protect;
        }
        /* 4 KB page */
        if (!(pde & PG_ACCESSED_MASK)) {
            pde |= PG_ACCESSED_MASK;
            x86_stl_phys_notdirty(cs, pde_addr, pde);
        }
        pte_addr = ((pde & PG_ADDRESS_MASK) + (((addr >> 12) & 0x1ff) << 3)) &
            a20_mask;
        pte_addr = get_hphys(cs, pte_addr, MMU_DATA_STORE, NULL);
        pte = x86_ldq_phys(cs, pte_addr);
        if (!(pte & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        if (pte & rsvd_mask) {
            goto do_fault_rsvd;
        }
        /* combine pde and pte nx, user and rw protections */
        ptep &= pte ^ PG_NX_MASK;
        page_size = 4096;
    } else {
        uint32_t pde;

        /* page directory entry */
        pde_addr = ((env->cr[3] & ~0xfff) + ((addr >> 20) & 0xffc)) &
            a20_mask;
        pde_addr = get_hphys(cs, pde_addr, MMU_DATA_STORE, NULL);
        pde = x86_ldl_phys(cs, pde_addr);
        if (!(pde & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        ptep = pde | PG_NX_MASK;

        /* if PSE bit is set, then we use a 4MB page */
        if ((pde & PG_PSE_MASK) && (env->cr[4] & CR4_PSE_MASK)) {
            page_size = 4096 * 1024;
            pte_addr = pde_addr;

            /* Bits 20-13 provide bits 39-32 of the address, bit 21 is reserved.
             * Leave bits 20-13 in place for setting accessed/dirty bits below.
             */
            pte = pde | ((pde & 0x1fe000LL) << (32 - 13));
            rsvd_mask = 0x200000;
            goto do_check_protect_pse36;
        }

        if (!(pde & PG_ACCESSED_MASK)) {
            pde |= PG_ACCESSED_MASK;
            x86_stl_phys_notdirty(cs, pde_addr, pde);
        }

        /* page directory entry */
        pte_addr = ((pde & ~0xfff) + ((addr >> 10) & 0xffc)) &
            a20_mask;
        pte_addr = get_hphys(cs, pte_addr, MMU_DATA_STORE, NULL);
        pte = x86_ldl_phys(cs, pte_addr);
        if (!(pte & PG_PRESENT_MASK)) {
            goto do_fault;
        }
        /* combine pde and pte user and rw protections */
        ptep &= pte | PG_NX_MASK;
        page_size = 4096;
        rsvd_mask = 0;
    }

do_check_protect:
    rsvd_mask |= (page_size - 1) & PG_ADDRESS_MASK & ~PG_PSE_PAT_MASK;
do_check_protect_pse36:
    if (pte & rsvd_mask) {
        goto do_fault_rsvd;
    }
    ptep ^= PG_NX_MASK;

    /* can the page can be put in the TLB?  prot will tell us */
    if (is_user && !(ptep & PG_USER_MASK)) {
        goto do_fault_protect;
    }

    prot = 0;
    if (mmu_idx != MMU_KSMAP_IDX || !(ptep & PG_USER_MASK)) {
        prot |= PAGE_READ;
        if ((ptep & PG_RW_MASK) || (!is_user && !(env->cr[0] & CR0_WP_MASK))) {
            prot |= PAGE_WRITE;
        }
    }
    if (!(ptep & PG_NX_MASK) &&
        (mmu_idx == MMU_USER_IDX ||
         !((env->cr[4] & CR4_SMEP_MASK) && (ptep & PG_USER_MASK)))) {
        prot |= PAGE_EXEC;
    }

    if (!(env->hflags & HF_LMA_MASK)) {
        pkr = 0;
    } else if (ptep & PG_USER_MASK) {
        pkr = env->cr[4] & CR4_PKE_MASK ? env->pkru : 0;
    } else {
        pkr = env->cr[4] & CR4_PKS_MASK ? env->pkrs : 0;
    }
    if (pkr) {
        uint32_t pk = (pte & PG_PKRU_MASK) >> PG_PKRU_BIT;
        uint32_t pkr_ad = (pkr >> pk * 2) & 1;
        uint32_t pkr_wd = (pkr >> pk * 2) & 2;
        uint32_t pkr_prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;

        if (pkr_ad) {
            pkr_prot &= ~(PAGE_READ | PAGE_WRITE);
        } else if (pkr_wd && (is_user || env->cr[0] & CR0_WP_MASK)) {
            pkr_prot &= ~PAGE_WRITE;
        }

        prot &= pkr_prot;
        if ((pkr_prot & (1 << is_write1)) == 0) {
            assert(is_write1 != 2);
            error_code |= PG_ERROR_PK_MASK;
            goto do_fault_protect;
        }
    }

    if ((prot & (1 << is_write1)) == 0) {
        goto do_fault_protect;
    }

    /* yes, it can! */
    is_dirty = is_write && !(pte & PG_DIRTY_MASK);
    if (!(pte & PG_ACCESSED_MASK) || is_dirty) {
        pte |= PG_ACCESSED_MASK;
        if (is_dirty) {
            pte |= PG_DIRTY_MASK;
        }
        x86_stl_phys_notdirty(cs, pte_addr, pte);
    }

    if (!(pte & PG_DIRTY_MASK)) {
        /* only set write access if already dirty... otherwise wait
           for dirty access */
        assert(!is_write);
        prot &= ~PAGE_WRITE;
    }

 do_mapping:
    pte = pte & a20_mask;

    /* align to page_size */
    pte &= PG_ADDRESS_MASK & ~(page_size - 1);
    page_offset = addr & (page_size - 1);
    paddr = get_hphys(cs, pte + page_offset, is_write1, &prot);

    /* Even if 4MB pages, we map only one 4KB page in the cache to
       avoid filling it too fast */
    vaddr = addr & TARGET_PAGE_MASK;
    paddr &= TARGET_PAGE_MASK;

    assert(prot & (1 << is_write1));
    tlb_set_page_with_attrs(cs, vaddr, paddr, cpu_get_mem_attrs(env),
                            prot, mmu_idx, page_size);
    return 0;
 do_fault_rsvd:
    error_code |= PG_ERROR_RSVD_MASK;
 do_fault_protect:
    error_code |= PG_ERROR_P_MASK;
 do_fault:
    error_code |= (is_write << PG_ERROR_W_BIT);
    if (is_user)
        error_code |= PG_ERROR_U_MASK;
    if (is_write1 == 2 &&
        (((env->efer & MSR_EFER_NXE) &&
          (env->cr[4] & CR4_PAE_MASK)) ||
         (env->cr[4] & CR4_SMEP_MASK)))
        error_code |= PG_ERROR_I_D_MASK;
    if (env->intercept_exceptions & (1 << EXCP0E_PAGE)) {
        /* cr2 is not modified in case of exceptions */
        x86_stq_phys(cs,
                 env->vm_vmcb + offsetof(struct vmcb, control.exit_info_2),
                 addr);
    } else {
        env->cr[2] = addr;
    }
    env->error_code = error_code;
    cs->exception_index = EXCP0E_PAGE;
    return 1;
}
#endif

bool x86_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
                      MMUAccessType access_type, int mmu_idx,
                      bool probe, uintptr_t retaddr)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;

#ifdef CONFIG_USER_ONLY
    /* user mode only emulation */
    env->cr[2] = addr;
    env->error_code = (access_type == MMU_DATA_STORE) << PG_ERROR_W_BIT;
    env->error_code |= PG_ERROR_U_MASK;
    cs->exception_index = EXCP0E_PAGE;
    env->exception_is_int = 0;
    env->exception_next_eip = -1;
    cpu_loop_exit_restore(cs, retaddr);
#else
    env->retaddr = retaddr;
    if (handle_mmu_fault(cs, addr, size, access_type, mmu_idx)) {
        /* FIXME: On error in get_hphys we have already jumped out.  */
        g_assert(!probe);
        raise_exception_err_ra(env, cs->exception_index,
                               env->error_code, retaddr);
    }
    return true;
#endif
}