
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
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197

/******************************************************************************
 * arch/x86/mm/p2m.c
 *
 * physical-to-machine mappings for automatically-translated domains.
 *
 * Parts of this code are Copyright (c) 2007 by Advanced Micro Devices.
 * Parts of this code are Copyright (c) 2006-2007 by XenSource Inc.
 * Parts of this code are Copyright (c) 2006 by Michael A Fetterman
 * Parts based on earlier work by Michael A Fetterman, Ian Pratt et al.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <asm/domain.h>
#include <asm/page.h>
#include <asm/paging.h>
#include <asm/p2m.h>
#include <asm/hvm/vmx/vmx.h> /* ept_p2m_init() */
#include <xen/iommu.h>

/* Debugging and auditing of the P2M code? */
#define P2M_AUDIT     0
#define P2M_DEBUGGING 0

/*
 * The P2M lock.  This protects all updates to the p2m table.
 * Updates are expected to be safe against concurrent reads,
 * which do *not* require the lock.
 *
 * Locking discipline: always acquire this lock before the shadow or HAP one
 */

#define p2m_lock_init(_p2m)                     \
    do {                                        \
        spin_lock_init(&(_p2m)->lock);          \
        (_p2m)->locker = -1;                    \
        (_p2m)->locker_function = "nobody";     \
    } while (0)

#define p2m_lock(_p2m)                                          \
    do {                                                        \
        if ( unlikely((_p2m)->locker == current->processor) )   \
        {                                                       \
            printk("Error: p2m lock held by %s\n",              \
                   (_p2m)->locker_function);                    \
            BUG();                                              \
        }                                                       \
        spin_lock(&(_p2m)->lock);                               \
        ASSERT((_p2m)->locker == -1);                           \
        (_p2m)->locker = current->processor;                    \
        (_p2m)->locker_function = __func__;                     \
    } while (0)

#define p2m_unlock(_p2m)                                \
    do {                                                \
        ASSERT((_p2m)->locker == current->processor);   \
        (_p2m)->locker = -1;                            \
        (_p2m)->locker_function = "nobody";             \
        spin_unlock(&(_p2m)->lock);                     \
    } while (0)

#define p2m_locked_by_me(_p2m)                            \
    (current->processor == (_p2m)->locker)

/* Printouts */
#define P2M_PRINTK(_f, _a...)                                \
    debugtrace_printk("p2m: %s(): " _f, __func__, ##_a)
#define P2M_ERROR(_f, _a...)                                 \
    printk("pg error: %s(): " _f, __func__, ##_a)
#if P2M_DEBUGGING
#define P2M_DEBUG(_f, _a...)                                 \
    debugtrace_printk("p2mdebug: %s(): " _f, __func__, ##_a)
#else
#define P2M_DEBUG(_f, _a...) do { (void)(_f); } while(0)
#endif


/* Override macros from asm/page.h to make them work with mfn_t */
#undef mfn_to_page
#define mfn_to_page(_m) (frame_table + mfn_x(_m))
#undef mfn_valid
#define mfn_valid(_mfn) (mfn_x(_mfn) < max_page)
#undef page_to_mfn
#define page_to_mfn(_pg) (_mfn((_pg) - frame_table))


/* PTE flags for the various types of p2m entry */
#define P2M_BASE_FLAGS \
        (_PAGE_PRESENT | _PAGE_USER | _PAGE_DIRTY | _PAGE_ACCESSED)

static unsigned long p2m_type_to_flags(p2m_type_t t) 
{
    unsigned long flags = (t & 0x7UL) << 9;
    switch(t)
    {
    case p2m_invalid:
    default:
        return flags;
    case p2m_ram_rw:
        return flags | P2M_BASE_FLAGS | _PAGE_RW;
    case p2m_ram_logdirty:
        return flags | P2M_BASE_FLAGS;
    case p2m_ram_ro:
        return flags | P2M_BASE_FLAGS;
    case p2m_mmio_dm:
        return flags;
    case p2m_mmio_direct:
        return flags | P2M_BASE_FLAGS | _PAGE_RW | _PAGE_PCD;
    }
}


// Find the next level's P2M entry, checking for out-of-range gfn's...
// Returns NULL on error.
//
static l1_pgentry_t *
p2m_find_entry(void *table, unsigned long *gfn_remainder,
                   unsigned long gfn, u32 shift, u32 max)
{
    u32 index;

    index = *gfn_remainder >> shift;
    if ( index >= max )
    {
        P2M_DEBUG("gfn=0x%lx out of range "
                  "(gfn_remainder=0x%lx shift=%d index=0x%x max=0x%x)\n",
                  gfn, *gfn_remainder, shift, index, max);
        return NULL;
    }
    *gfn_remainder &= (1 << shift) - 1;
    return (l1_pgentry_t *)table + index;
}

// Walk one level of the P2M table, allocating a new table if required.
// Returns 0 on error.
//
static int
p2m_next_level(struct domain *d, mfn_t *table_mfn, void **table,
               unsigned long *gfn_remainder, unsigned long gfn, u32 shift,
               u32 max, unsigned long type)
{
    l1_pgentry_t *l1_entry;
    l1_pgentry_t *p2m_entry;
    l1_pgentry_t new_entry;
    void *next;
    int i;
    ASSERT(d->arch.p2m->alloc_page);

    if ( !(p2m_entry = p2m_find_entry(*table, gfn_remainder, gfn,
                                      shift, max)) )
        return 0;

    if ( !(l1e_get_flags(*p2m_entry) & _PAGE_PRESENT) )
    {
        struct page_info *pg = d->arch.p2m->alloc_page(d);
        if ( pg == NULL )
            return 0;
        list_add_tail(&pg->list, &d->arch.p2m->pages);
        pg->u.inuse.type_info = type | 1 | PGT_validated;
        pg->count_info = 1;

        new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
                                 __PAGE_HYPERVISOR|_PAGE_USER);

        switch ( type ) {
        case PGT_l3_page_table:
            paging_write_p2m_entry(d, gfn,
                                   p2m_entry, *table_mfn, new_entry, 4);
            break;
        case PGT_l2_page_table:
#if CONFIG_PAGING_LEVELS == 3
            /* for PAE mode, PDPE only has PCD/PWT/P bits available */
            new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)), _PAGE_PRESENT);
#endif
            paging_write_p2m_entry(d, gfn,
                                   p2m_entry, *table_mfn, new_entry, 3);
            break;
        case PGT_l1_page_table:
            paging_write_p2m_entry(d, gfn,
                                   p2m_entry, *table_mfn, new_entry, 2);
            break;
        default:
            BUG();
            break;
        }
    }

    ASSERT(l1e_get_flags(*p2m_entry) & _PAGE_PRESENT);

    /* split single large page into 4KB page in P2M table */
    if ( type == PGT_l1_page_table && (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
    {
        unsigned long flags, pfn;
        struct page_info *pg = d->arch.p2m->alloc_page(d);
        if ( pg == NULL )
            return 0;
        list_add_tail(&pg->list, &d->arch.p2m->pages);
        pg->u.inuse.type_info = PGT_l1_page_table | 1 | PGT_validated;
        pg->count_info = 1;
        
        /* New splintered mappings inherit the flags of the old superpage, 
         * with a little reorganisation for the _PAGE_PSE_PAT bit. */
        flags = l1e_get_flags(*p2m_entry);
        pfn = l1e_get_pfn(*p2m_entry);
        if ( pfn & 1 )           /* ==> _PAGE_PSE_PAT was set */
            pfn -= 1;            /* Clear it; _PAGE_PSE becomes _PAGE_PAT */
        else
            flags &= ~_PAGE_PSE; /* Clear _PAGE_PSE (== _PAGE_PAT) */
        
        l1_entry = map_domain_page(mfn_x(page_to_mfn(pg)));
        for ( i = 0; i < L1_PAGETABLE_ENTRIES; i++ )
        {
            new_entry = l1e_from_pfn(pfn + i, flags);
            paging_write_p2m_entry(d, gfn,
                                   l1_entry+i, *table_mfn, new_entry, 1);
        }
        unmap_domain_page(l1_entry);
        
        new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
                                 __PAGE_HYPERVISOR|_PAGE_USER);
        paging_write_p2m_entry(d, gfn,
                               p2m_entry, *table_mfn, new_entry, 2);
    }

    *table_mfn = _mfn(l1e_get_pfn(*p2m_entry));
    next = map_domain_page(mfn_x(*table_mfn));
    unmap_domain_page(*table);
    *table = next;

    return 1;
}

// Returns 0 on error (out of memory)
static int
p2m_set_entry(struct domain *d, unsigned long gfn, mfn_t mfn, 
              unsigned int page_order, p2m_type_t p2mt)
{
    // XXX -- this might be able to be faster iff current->domain == d
    mfn_t table_mfn = pagetable_get_mfn(d->arch.phys_table);
    void *table =map_domain_page(mfn_x(table_mfn));
    unsigned long i, gfn_remainder = gfn;
    l1_pgentry_t *p2m_entry;
    l1_pgentry_t entry_content;
    l2_pgentry_t l2e_content;
    int rv=0;

#if CONFIG_PAGING_LEVELS >= 4
    if ( !p2m_next_level(d, &table_mfn, &table, &gfn_remainder, gfn,
                         L4_PAGETABLE_SHIFT - PAGE_SHIFT,
                         L4_PAGETABLE_ENTRIES, PGT_l3_page_table) )
        goto out;
#endif
    /*
     * When using PAE Xen, we only allow 33 bits of pseudo-physical
     * address in translated guests (i.e. 8 GBytes).  This restriction
     * comes from wanting to map the P2M table into the 16MB RO_MPT hole
     * in Xen's address space for translated PV guests.
     * When using AMD's NPT on PAE Xen, we are restricted to 4GB.
     */
    if ( !p2m_next_level(d, &table_mfn, &table, &gfn_remainder, gfn,
                         L3_PAGETABLE_SHIFT - PAGE_SHIFT,
                         ((CONFIG_PAGING_LEVELS == 3)
                          ? (d->arch.hvm_domain.hap_enabled ? 4 : 8)
                          : L3_PAGETABLE_ENTRIES),
                         PGT_l2_page_table) )
        goto out;

    if ( page_order == 0 )
    {
        if ( !p2m_next_level(d, &table_mfn, &table, &gfn_remainder, gfn,
                             L2_PAGETABLE_SHIFT - PAGE_SHIFT,
                             L2_PAGETABLE_ENTRIES, PGT_l1_page_table) )
            goto out;

        p2m_entry = p2m_find_entry(table, &gfn_remainder, gfn,
                                   0, L1_PAGETABLE_ENTRIES);
        ASSERT(p2m_entry);
        
        if ( mfn_valid(mfn) || (p2mt == p2m_mmio_direct) )
            entry_content = l1e_from_pfn(mfn_x(mfn), p2m_type_to_flags(p2mt));
        else
            entry_content = l1e_empty();
        
        /* level 1 entry */
        paging_write_p2m_entry(d, gfn, p2m_entry, table_mfn, entry_content, 1);
    }
    else 
    {
        p2m_entry = p2m_find_entry(table, &gfn_remainder, gfn,
                                   L2_PAGETABLE_SHIFT - PAGE_SHIFT,
                                   L2_PAGETABLE_ENTRIES);
        ASSERT(p2m_entry);
        
        if ( (l1e_get_flags(*p2m_entry) & _PAGE_PRESENT) &&
             !(l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
        {
            P2M_ERROR("configure P2M table 4KB L2 entry with large page\n");
            domain_crash(d);
            goto out;
        }
        
        if ( mfn_valid(mfn) )
            l2e_content = l2e_from_pfn(mfn_x(mfn),
                                       p2m_type_to_flags(p2mt) | _PAGE_PSE);
        else
            l2e_content = l2e_empty();
        
        entry_content.l1 = l2e_content.l2;
        paging_write_p2m_entry(d, gfn, p2m_entry, table_mfn, entry_content, 2);
    }

    /* Track the highest gfn for which we have ever had a valid mapping */
    if ( mfn_valid(mfn) 
         && (gfn + (1UL << page_order) - 1 > d->arch.p2m->max_mapped_pfn) )
        d->arch.p2m->max_mapped_pfn = gfn + (1UL << page_order) - 1;

    if ( iommu_enabled && (is_hvm_domain(d) || need_iommu(d)) )
    {
        if ( p2mt == p2m_ram_rw )
            for ( i = 0; i < (1UL << page_order); i++ )
                iommu_map_page(d, gfn+i, mfn_x(mfn)+i );
        else
            for ( int i = 0; i < (1UL << page_order); i++ )
                iommu_unmap_page(d, gfn+i);
    }

    /* Success */
    rv = 1;

 out:
    unmap_domain_page(table);
    return rv;
}

static mfn_t
p2m_gfn_to_mfn(struct domain *d, unsigned long gfn, p2m_type_t *t)
{
    mfn_t mfn;
    paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
    l2_pgentry_t *l2e;
    l1_pgentry_t *l1e;

    ASSERT(paging_mode_translate(d));

    /* XXX This is for compatibility with the old model, where anything not 
     * XXX marked as RAM was considered to be emulated MMIO space.
     * XXX Once we start explicitly registering MMIO regions in the p2m 
     * XXX we will return p2m_invalid for unmapped gfns */
    *t = p2m_mmio_dm;

    mfn = pagetable_get_mfn(d->arch.phys_table);

    if ( gfn > d->arch.p2m->max_mapped_pfn )
        /* This pfn is higher than the highest the p2m map currently holds */
        return _mfn(INVALID_MFN);

#if CONFIG_PAGING_LEVELS >= 4
    {
        l4_pgentry_t *l4e = map_domain_page(mfn_x(mfn));
        l4e += l4_table_offset(addr);
        if ( (l4e_get_flags(*l4e) & _PAGE_PRESENT) == 0 )
        {
            unmap_domain_page(l4e);
            return _mfn(INVALID_MFN);
        }
        mfn = _mfn(l4e_get_pfn(*l4e));
        unmap_domain_page(l4e);
    }
#endif
    {
        l3_pgentry_t *l3e = map_domain_page(mfn_x(mfn));
#if CONFIG_PAGING_LEVELS == 3
        /* On PAE hosts the p2m has eight l3 entries, not four (see
         * shadow_set_p2m_entry()) so we can't use l3_table_offset.
         * Instead, just count the number of l3es from zero.  It's safe
         * to do this because we already checked that the gfn is within
         * the bounds of the p2m. */
        l3e += (addr >> L3_PAGETABLE_SHIFT);
#else
        l3e += l3_table_offset(addr);
#endif
        if ( (l3e_get_flags(*l3e) & _PAGE_PRESENT) == 0 )
        {
            unmap_domain_page(l3e);
            return _mfn(INVALID_MFN);
        }
        mfn = _mfn(l3e_get_pfn(*l3e));
        unmap_domain_page(l3e);
    }

    l2e = map_domain_page(mfn_x(mfn));
    l2e += l2_table_offset(addr);
    if ( (l2e_get_flags(*l2e) & _PAGE_PRESENT) == 0 )
    {
        unmap_domain_page(l2e);
        return _mfn(INVALID_MFN);
    }
    else if ( (l2e_get_flags(*l2e) & _PAGE_PSE) )
    {
        mfn = _mfn(l2e_get_pfn(*l2e) + l1_table_offset(addr));
        *t = p2m_flags_to_type(l2e_get_flags(*l2e));
        unmap_domain_page(l2e);
        
        ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
        return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
    }

    mfn = _mfn(l2e_get_pfn(*l2e));
    unmap_domain_page(l2e);

    l1e = map_domain_page(mfn_x(mfn));
    l1e += l1_table_offset(addr);
    if ( (l1e_get_flags(*l1e) & _PAGE_PRESENT) == 0 )
    {
        unmap_domain_page(l1e);
        return _mfn(INVALID_MFN);
    }
    mfn = _mfn(l1e_get_pfn(*l1e));
    *t = p2m_flags_to_type(l1e_get_flags(*l1e));
    unmap_domain_page(l1e);

    ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
    return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
}

/* Read the current domain's p2m table (through the linear mapping). */
static mfn_t p2m_gfn_to_mfn_current(unsigned long gfn, p2m_type_t *t)
{
    mfn_t mfn = _mfn(INVALID_MFN);
    p2m_type_t p2mt = p2m_mmio_dm;
    paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
    /* XXX This is for compatibility with the old model, where anything not 
     * XXX marked as RAM was considered to be emulated MMIO space.
     * XXX Once we start explicitly registering MMIO regions in the p2m 
     * XXX we will return p2m_invalid for unmapped gfns */

    if ( gfn <= current->domain->arch.p2m->max_mapped_pfn )
    {
        l1_pgentry_t l1e = l1e_empty();
        l2_pgentry_t l2e = l2e_empty();
        int ret;

        ASSERT(gfn < (RO_MPT_VIRT_END - RO_MPT_VIRT_START) 
               / sizeof(l1_pgentry_t));

        ret = __copy_from_user(&l2e,
                               &__linear_l1_table[l1_linear_offset(RO_MPT_VIRT_START) + l2_linear_offset(addr)],
                               sizeof(l2e));
        
        if ( (ret == 0) && (l2e_get_flags(l2e) & _PAGE_PRESENT) && 
             (l2e_get_flags(l2e) & _PAGE_PSE) ) 
        {
            p2mt = p2m_flags_to_type(l2e_get_flags(l2e));
            ASSERT(l2e_get_pfn(l2e) != INVALID_MFN || !p2m_is_ram(p2mt));
            if ( p2m_is_valid(p2mt) )
                mfn = _mfn(l2e_get_pfn(l2e) + l1_table_offset(addr));
            else
                p2mt = p2m_mmio_dm;
        }
        else
        {
        
            /* Need to __copy_from_user because the p2m is sparse and this
             * part might not exist */
            ret = __copy_from_user(&l1e,
                                   &phys_to_machine_mapping[gfn],
                                   sizeof(l1e));
            
            if ( ret == 0 ) {
                p2mt = p2m_flags_to_type(l1e_get_flags(l1e));
                ASSERT(l1e_get_pfn(l1e) != INVALID_MFN || !p2m_is_ram(p2mt));
                if ( p2m_is_valid(p2mt) )
                    mfn = _mfn(l1e_get_pfn(l1e));
                else 
                    /* XXX see above */
                    p2mt = p2m_mmio_dm;
            }
        }
    }

    *t = p2mt;
    return mfn;
}

/* Init the datastructures for later use by the p2m code */
int p2m_init(struct domain *d)
{
    struct p2m_domain *p2m;

    p2m = xmalloc(struct p2m_domain);
    if ( p2m == NULL )
        return -ENOMEM;

    d->arch.p2m = p2m;

    memset(p2m, 0, sizeof(*p2m));
    p2m_lock_init(p2m);
    INIT_LIST_HEAD(&p2m->pages);

    p2m->set_entry = p2m_set_entry;
    p2m->get_entry = p2m_gfn_to_mfn;
    p2m->get_entry_current = p2m_gfn_to_mfn_current;
    p2m->change_entry_type_global = p2m_change_type_global;

    if ( is_hvm_domain(d) && d->arch.hvm_domain.hap_enabled &&
         (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) )
        ept_p2m_init(d);

    return 0;
}

void p2m_change_entry_type_global(struct domain *d,
                                  p2m_type_t ot, p2m_type_t nt)
{
    struct p2m_domain *p2m = d->arch.p2m;

    p2m_lock(p2m);
    p2m->change_entry_type_global(d, ot, nt);
    p2m_unlock(p2m);
}

static
int set_p2m_entry(struct domain *d, unsigned long gfn, mfn_t mfn, 
                    unsigned int page_order, p2m_type_t p2mt)
{
    unsigned long todo = 1ul << page_order;
    unsigned int order;
    int rc = 0;

    while ( todo )
    {
        order = (((gfn | mfn_x(mfn) | todo) & ((1ul << 9) - 1)) == 0) ? 9 : 0;
        rc = d->arch.p2m->set_entry(d, gfn, mfn, order, p2mt);
        gfn += 1ul << order;
        if ( mfn_x(mfn) != INVALID_MFN )
            mfn = _mfn(mfn_x(mfn) + (1ul << order));
        todo -= 1ul << order;
    }

    return rc;
}

// Allocate a new p2m table for a domain.
//
// The structure of the p2m table is that of a pagetable for xen (i.e. it is
// controlled by CONFIG_PAGING_LEVELS).
//
// The alloc_page and free_page functions will be used to get memory to
// build the p2m, and to release it again at the end of day.
//
// Returns 0 for success or -errno.
//
int p2m_alloc_table(struct domain *d,
                    struct page_info * (*alloc_page)(struct domain *d),
                    void (*free_page)(struct domain *d, struct page_info *pg))

{
    mfn_t mfn = _mfn(INVALID_MFN);
    struct list_head *entry;
    struct page_info *page, *p2m_top;
    unsigned int page_count = 0;
    unsigned long gfn = -1UL;
    struct p2m_domain *p2m = d->arch.p2m;

    p2m_lock(p2m);

    if ( pagetable_get_pfn(d->arch.phys_table) != 0 )
    {
        P2M_ERROR("p2m already allocated for this domain\n");
        p2m_unlock(p2m);
        return -EINVAL;
    }

    P2M_PRINTK("allocating p2m table\n");

    p2m->alloc_page = alloc_page;
    p2m->free_page = free_page;

    p2m_top = p2m->alloc_page(d);
    if ( p2m_top == NULL )
    {
        p2m_unlock(p2m);
        return -ENOMEM;
    }
    list_add_tail(&p2m_top->list, &p2m->pages);

    p2m_top->count_info = 1;
    p2m_top->u.inuse.type_info =
#if CONFIG_PAGING_LEVELS == 4
        PGT_l4_page_table
#else
        PGT_l3_page_table
#endif
        | 1 | PGT_validated;

    d->arch.phys_table = pagetable_from_mfn(page_to_mfn(p2m_top));

    P2M_PRINTK("populating p2m table\n");

    /* Initialise physmap tables for slot zero. Other code assumes this. */
    if ( !set_p2m_entry(d, 0, _mfn(INVALID_MFN), 0,
                        p2m_invalid) )
        goto error;

    /* Copy all existing mappings from the page list and m2p */
    for ( entry = d->page_list.next;
          entry != &d->page_list;
          entry = entry->next )
    {
        page = list_entry(entry, struct page_info, list);
        mfn = page_to_mfn(page);
        gfn = get_gpfn_from_mfn(mfn_x(mfn));
        page_count++;
        if (
#ifdef __x86_64__
            (gfn != 0x5555555555555555L)
#else
            (gfn != 0x55555555L)
#endif
             && gfn != INVALID_M2P_ENTRY
            && !set_p2m_entry(d, gfn, mfn, 0, p2m_ram_rw) )
            goto error;
    }

    P2M_PRINTK("p2m table initialised (%u pages)\n", page_count);
    p2m_unlock(p2m);
    return 0;

 error:
    P2M_PRINTK("failed to initialize p2m table, gfn=%05lx, mfn=%"
               PRI_mfn "\n", gfn, mfn_x(mfn));
    p2m_unlock(p2m);
    return -ENOMEM;
}

void p2m_teardown(struct domain *d)
/* Return all the p2m pages to Xen.
 * We know we don't have any extra mappings to these pages */
{
    struct list_head *entry, *n;
    struct page_info *pg;
    struct p2m_domain *p2m = d->arch.p2m;

    p2m_lock(p2m);
    d->arch.phys_table = pagetable_null();

    list_for_each_safe(entry, n, &p2m->pages)
    {
        pg = list_entry(entry, struct page_info, list);
        list_del(entry);
        p2m->free_page(d, pg);
    }
    p2m_unlock(p2m);
}

void p2m_final_teardown(struct domain *d)
{
    xfree(d->arch.p2m);
    d->arch.p2m = NULL;
}

#if P2M_AUDIT
static void audit_p2m(struct domain *d)
{
    struct list_head *entry;
    struct page_info *page;
    struct domain *od;
    unsigned long mfn, gfn, m2pfn, lp2mfn = 0;
    mfn_t p2mfn;
    unsigned long orphans_d = 0, orphans_i = 0, mpbad = 0, pmbad = 0;
    int test_linear;
    p2m_type_t type;

    if ( !paging_mode_translate(d) )
        return;

    //P2M_PRINTK("p2m audit starts\n");

    test_linear = ( (d == current->domain)
                    && !pagetable_is_null(current->arch.monitor_table) );
    if ( test_linear )
        flush_tlb_local();

    /* Audit part one: walk the domain's page allocation list, checking
     * the m2p entries. */
    for ( entry = d->page_list.next;
          entry != &d->page_list;
          entry = entry->next )
    {
        page = list_entry(entry, struct page_info, list);
        mfn = mfn_x(page_to_mfn(page));

        // P2M_PRINTK("auditing guest page, mfn=%#lx\n", mfn);

        od = page_get_owner(page);

        if ( od != d )
        {
            P2M_PRINTK("wrong owner %#lx -> %p(%u) != %p(%u)\n",
                       mfn, od, (od?od->domain_id:-1), d, d->domain_id);
            continue;
        }

        gfn = get_gpfn_from_mfn(mfn);
        if ( gfn == INVALID_M2P_ENTRY )
        {
            orphans_i++;
            //P2M_PRINTK("orphaned guest page: mfn=%#lx has invalid gfn\n",
            //               mfn);
            continue;
        }

        if ( gfn == 0x55555555 )
        {
            orphans_d++;
            //P2M_PRINTK("orphaned guest page: mfn=%#lx has debug gfn\n",
            //               mfn);
            continue;
        }

        p2mfn = gfn_to_mfn_foreign(d, gfn, &type);
        if ( mfn_x(p2mfn) != mfn )
        {
            mpbad++;
            P2M_PRINTK("map mismatch mfn %#lx -> gfn %#lx -> mfn %#lx"
                       " (-> gfn %#lx)\n",
                       mfn, gfn, mfn_x(p2mfn),
                       (mfn_valid(p2mfn)
                        ? get_gpfn_from_mfn(mfn_x(p2mfn))
                        : -1u));
            /* This m2p entry is stale: the domain has another frame in
             * this physical slot.  No great disaster, but for neatness,
             * blow away the m2p entry. */
            set_gpfn_from_mfn(mfn, INVALID_M2P_ENTRY);
        }

        if ( test_linear && (gfn <= d->arch.p2m->max_mapped_pfn) )
        {
            lp2mfn = mfn_x(gfn_to_mfn(d, gfn, &type));
            if ( lp2mfn != mfn_x(p2mfn) )
            {
                P2M_PRINTK("linear mismatch gfn %#lx -> mfn %#lx "
                           "(!= mfn %#lx)\n", gfn, lp2mfn, mfn_x(p2mfn));
            }
        }

        // P2M_PRINTK("OK: mfn=%#lx, gfn=%#lx, p2mfn=%#lx, lp2mfn=%#lx\n",
        //                mfn, gfn, p2mfn, lp2mfn);
    }

    /* Audit part two: walk the domain's p2m table, checking the entries. */
    if ( pagetable_get_pfn(d->arch.phys_table) != 0 )
    {
        l2_pgentry_t *l2e;
        l1_pgentry_t *l1e;
        int i1, i2;

#if CONFIG_PAGING_LEVELS == 4
        l4_pgentry_t *l4e;
        l3_pgentry_t *l3e;
        int i3, i4;
        l4e = map_domain_page(mfn_x(pagetable_get_mfn(d->arch.phys_table)));
#else /* CONFIG_PAGING_LEVELS == 3 */
        l3_pgentry_t *l3e;
        int i3;
        l3e = map_domain_page(mfn_x(pagetable_get_mfn(d->arch.phys_table)));
#endif

        gfn = 0;
#if CONFIG_PAGING_LEVELS >= 4
        for ( i4 = 0; i4 < L4_PAGETABLE_ENTRIES; i4++ )
        {
            if ( !(l4e_get_flags(l4e[i4]) & _PAGE_PRESENT) )
            {
                gfn += 1 << (L4_PAGETABLE_SHIFT - PAGE_SHIFT);
                continue;
            }
            l3e = map_domain_page(mfn_x(_mfn(l4e_get_pfn(l4e[i4]))));
#endif
            for ( i3 = 0;
                  i3 < ((CONFIG_PAGING_LEVELS==4) ? L3_PAGETABLE_ENTRIES : 8);