summaryrefslogtreecommitdiff
path: root/arch/x86/xen/p2m.c
blob: 9bb3d82ffec8f8de8c0fb4f9db920ea260543171 (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
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
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
/*
 * Xen leaves the responsibility for maintaining p2m mappings to the
 * guests themselves, but it must also access and update the p2m array
 * during suspend/resume when all the pages are reallocated.
 *
 * The p2m table is logically a flat array, but we implement it as a
 * three-level tree to allow the address space to be sparse.
 *
 *                               Xen
 *                                |
 *     p2m_top              p2m_top_mfn
 *       /  \                   /   \
 * p2m_mid p2m_mid	p2m_mid_mfn p2m_mid_mfn
 *    / \      / \         /           /
 *  p2m p2m p2m p2m p2m p2m p2m ...
 *
 * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
 *
 * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
 * maximum representable pseudo-physical address space is:
 *  P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
 *
 * P2M_PER_PAGE depends on the architecture, as a mfn is always
 * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
 * 512 and 1024 entries respectively.
 *
 * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
 *
 * However not all entries are filled with MFNs. Specifically for all other
 * leaf entries, or for the top  root, or middle one, for which there is a void
 * entry, we assume it is  "missing". So (for example)
 *  pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY.
 *
 * We also have the possibility of setting 1-1 mappings on certain regions, so
 * that:
 *  pfn_to_mfn(0xc0000)=0xc0000
 *
 * The benefit of this is, that we can assume for non-RAM regions (think
 * PCI BARs, or ACPI spaces), we can create mappings easily because we
 * get the PFN value to match the MFN.
 *
 * For this to work efficiently we have one new page p2m_identity and
 * allocate (via reserved_brk) any other pages we need to cover the sides
 * (1GB or 4MB boundary violations). All entries in p2m_identity are set to
 * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs,
 * no other fancy value).
 *
 * On lookup we spot that the entry points to p2m_identity and return the
 * identity value instead of dereferencing and returning INVALID_P2M_ENTRY.
 * If the entry points to an allocated page, we just proceed as before and
 * return the PFN.  If the PFN has IDENTITY_FRAME_BIT set we unmask that in
 * appropriate functions (pfn_to_mfn).
 *
 * The reason for having the IDENTITY_FRAME_BIT instead of just returning the
 * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a
 * non-identity pfn. To protect ourselves against we elect to set (and get) the
 * IDENTITY_FRAME_BIT on all identity mapped PFNs.
 *
 * This simplistic diagram is used to explain the more subtle piece of code.
 * There is also a digram of the P2M at the end that can help.
 * Imagine your E820 looking as so:
 *
 *                    1GB                                           2GB    4GB
 * /-------------------+---------\/----\         /----------\    /---+-----\
 * | System RAM        | Sys RAM ||ACPI|         | reserved |    | Sys RAM |
 * \-------------------+---------/\----/         \----------/    \---+-----/
 *                               ^- 1029MB                       ^- 2001MB
 *
 * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100),
 *  2048MB = 524288 (0x80000)]
 *
 * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB
 * is actually not present (would have to kick the balloon driver to put it in).
 *
 * When we are told to set the PFNs for identity mapping (see patch: "xen/setup:
 * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start
 * of the PFN and the end PFN (263424 and 512256 respectively). The first step
 * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
 * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
 * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as
 * required to split any existing p2m_mid_missing middle pages.
 *
 * With the E820 example above, 263424 is not 1GB aligned so we allocate a
 * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
 * Each entry in the allocate page is "missing" (points to p2m_missing).
 *
 * Next stage is to determine if we need to do a more granular boundary check
 * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
 * We check if the start pfn and end pfn violate that boundary check, and if
 * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer
 * granularity of setting which PFNs are missing and which ones are identity.
 * In our example 263424 and 512256 both fail the check so we reserve_brk two
 * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
 * values) and assign them to p2m[1][2] and p2m[1][488] respectively.
 *
 * At this point we would at minimum reserve_brk one page, but could be up to
 * three. Each call to set_phys_range_identity has at maximum a three page
 * cost. If we were to query the P2M at this stage, all those entries from
 * start PFN through end PFN (so 1029MB -> 2001MB) would return
 * INVALID_P2M_ENTRY ("missing").
 *
 * The next step is to walk from the start pfn to the end pfn setting
 * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
 * If we find that the middle entry is pointing to p2m_missing we can swap it
 * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and
 * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions).
 * At this point we do not need to worry about boundary aligment (so no need to
 * reserve_brk a middle page, figure out which PFNs are "missing" and which
 * ones are identity), as that has been done earlier.  If we find that the
 * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
 * that page (which covers 512 PFNs) and set the appropriate PFN with
 * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we
 * set from p2m[1][2][256->511] and p2m[1][488][0->256] with
 * IDENTITY_FRAME_BIT set.
 *
 * All other regions that are void (or not filled) either point to p2m_missing
 * (considered missing) or have the default value of INVALID_P2M_ENTRY (also
 * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
 * contain the INVALID_P2M_ENTRY value and are considered "missing."
 *
 * Finally, the region beyond the end of of the E820 (4 GB in this example)
 * is set to be identity (in case there are MMIO regions placed here).
 *
 * This is what the p2m ends up looking (for the E820 above) with this
 * fabulous drawing:
 *
 *    p2m         /--------------\
 *  /-----\       | &mfn_list[0],|                           /-----------------\
 *  |  0  |------>| &mfn_list[1],|    /---------------\      | ~0, ~0, ..      |
 *  |-----|       |  ..., ~0, ~0 |    | ~0, ~0, [x]---+----->| IDENTITY [@256] |
 *  |  1  |---\   \--------------/    | [p2m_identity]+\     | IDENTITY [@257] |
 *  |-----|    \                      | [p2m_identity]+\\    | ....            |
 *  |  2  |--\  \-------------------->|  ...          | \\   \----------------/
 *  |-----|   \                       \---------------/  \\
 *  |  3  |-\  \                                          \\  p2m_identity [1]
 *  |-----|  \  \-------------------->/---------------\   /-----------------\
 *  | ..  |\  |                       | [p2m_identity]+-->| ~0, ~0, ~0, ... |
 *  \-----/ | |                       | [p2m_identity]+-->| ..., ~0         |
 *          | |                       | ....          |   \-----------------/
 *          | |                       +-[x], ~0, ~0.. +\
 *          | |                       \---------------/ \
 *          | |                                          \-> /---------------\
 *          | V  p2m_mid_missing       p2m_missing           | IDENTITY[@0]  |
 *          | /-----------------\     /------------\         | IDENTITY[@256]|
 *          | | [p2m_missing]   +---->| ~0, ~0, ...|         | ~0, ~0, ....  |
 *          | | [p2m_missing]   +---->| ..., ~0    |         \---------------/
 *          | | ...             |     \------------/
 *          | \-----------------/
 *          |
 *          |     p2m_mid_identity
 *          |   /-----------------\
 *          \-->| [p2m_identity]  +---->[1]
 *              | [p2m_identity]  +---->[1]
 *              | ...             |
 *              \-----------------/
 *
 * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/seq_file.h>

#include <asm/cache.h>
#include <asm/setup.h>

#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <xen/balloon.h>
#include <xen/grant_table.h>

#include "multicalls.h"
#include "xen-ops.h"

static void __init m2p_override_init(void);

unsigned long xen_max_p2m_pfn __read_mostly;

#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
#define P2M_MID_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long *))
#define P2M_TOP_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long **))

#define MAX_P2M_PFN		(P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)

/* Placeholders for holes in the address space */
static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);

static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);

static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE);

RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));

/* We might hit two boundary violations at the start and end, at max each
 * boundary violation will require three middle nodes. */
RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3);

/* When we populate back during bootup, the amount of pages can vary. The
 * max we have is seen is 395979, but that does not mean it can't be more.
 * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
 * it can re-use Xen provided mfn_list array, so we only need to allocate at
 * most three P2M top nodes. */
RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);

static inline unsigned p2m_top_index(unsigned long pfn)
{
	BUG_ON(pfn >= MAX_P2M_PFN);
	return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
}

static inline unsigned p2m_mid_index(unsigned long pfn)
{
	return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}

static inline unsigned p2m_index(unsigned long pfn)
{
	return pfn % P2M_PER_PAGE;
}

static void p2m_top_init(unsigned long ***top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = p2m_mid_missing;
}

static void p2m_top_mfn_init(unsigned long *top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = virt_to_mfn(p2m_mid_missing_mfn);
}

static void p2m_top_mfn_p_init(unsigned long **top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = p2m_mid_missing_mfn;
}

static void p2m_mid_init(unsigned long **mid, unsigned long *leaf)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		mid[i] = leaf;
}

static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		mid[i] = virt_to_mfn(leaf);
}

static void p2m_init(unsigned long *p2m)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		p2m[i] = INVALID_P2M_ENTRY;
}

/*
 * Build the parallel p2m_top_mfn and p2m_mid_mfn structures
 *
 * This is called both at boot time, and after resuming from suspend:
 * - At boot time we're called very early, and must use extend_brk()
 *   to allocate memory.
 *
 * - After resume we're called from within stop_machine, but the mfn
 *   tree should alreay be completely allocated.
 */
void __ref xen_build_mfn_list_list(void)
{
	unsigned long pfn;

	if (xen_feature(XENFEAT_auto_translated_physmap))
		return;

	/* Pre-initialize p2m_top_mfn to be completely missing */
	if (p2m_top_mfn == NULL) {
		p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
		p2m_mid_identity_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);

		p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_top_mfn_p_init(p2m_top_mfn_p);

		p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_top_mfn_init(p2m_top_mfn);
	} else {
		/* Reinitialise, mfn's all change after migration */
		p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
		p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);
	}

	for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);
		unsigned long **mid;
		unsigned long *mid_mfn_p;

		mid = p2m_top[topidx];
		mid_mfn_p = p2m_top_mfn_p[topidx];

		/* Don't bother allocating any mfn mid levels if
		 * they're just missing, just update the stored mfn,
		 * since all could have changed over a migrate.
		 */
		if (mid == p2m_mid_missing) {
			BUG_ON(mididx);
			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
			p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
			pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
			continue;
		}

		if (mid_mfn_p == p2m_mid_missing_mfn) {
			/*
			 * XXX boot-time only!  We should never find
			 * missing parts of the mfn tree after
			 * runtime.  extend_brk() will BUG if we call
			 * it too late.
			 */
			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
			p2m_mid_mfn_init(mid_mfn_p, p2m_missing);

			p2m_top_mfn_p[topidx] = mid_mfn_p;
		}

		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
		mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
	}
}

void xen_setup_mfn_list_list(void)
{
	if (xen_feature(XENFEAT_auto_translated_physmap))
		return;

	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);

	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
		virt_to_mfn(p2m_top_mfn);
	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
}

/* Set up p2m_top to point to the domain-builder provided p2m pages */
void __init xen_build_dynamic_phys_to_machine(void)
{
	unsigned long *mfn_list;
	unsigned long max_pfn;
	unsigned long pfn;

	 if (xen_feature(XENFEAT_auto_translated_physmap))
		return;

	mfn_list = (unsigned long *)xen_start_info->mfn_list;
	max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
	xen_max_p2m_pfn = max_pfn;

	p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_init(p2m_missing);
	p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_init(p2m_identity);

	p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_mid_init(p2m_mid_missing, p2m_missing);
	p2m_mid_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_mid_init(p2m_mid_identity, p2m_identity);

	p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_top_init(p2m_top);

	/*
	 * The domain builder gives us a pre-constructed p2m array in
	 * mfn_list for all the pages initially given to us, so we just
	 * need to graft that into our tree structure.
	 */
	for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);

		if (p2m_top[topidx] == p2m_mid_missing) {
			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
			p2m_mid_init(mid, p2m_missing);

			p2m_top[topidx] = mid;
		}

		/*
		 * As long as the mfn_list has enough entries to completely
		 * fill a p2m page, pointing into the array is ok. But if
		 * not the entries beyond the last pfn will be undefined.
		 */
		if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) {
			unsigned long p2midx;

			p2midx = max_pfn % P2M_PER_PAGE;
			for ( ; p2midx < P2M_PER_PAGE; p2midx++)
				mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY;
		}
		p2m_top[topidx][mididx] = &mfn_list[pfn];
	}

	m2p_override_init();
}
#ifdef CONFIG_X86_64
#include <linux/bootmem.h>
unsigned long __init xen_revector_p2m_tree(void)
{
	unsigned long va_start;
	unsigned long va_end;
	unsigned long pfn;
	unsigned long pfn_free = 0;
	unsigned long *mfn_list = NULL;
	unsigned long size;

	va_start = xen_start_info->mfn_list;
	/*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
	 * so make sure it is rounded up to that */
	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
	va_end = va_start + size;

	/* If we were revectored already, don't do it again. */
	if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
		return 0;

	mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
	if (!mfn_list) {
		pr_warn("Could not allocate space for a new P2M tree!\n");
		return xen_start_info->mfn_list;
	}
	/* Fill it out with INVALID_P2M_ENTRY value */
	memset(mfn_list, 0xFF, size);

	for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx;
		unsigned long *mid_p;

		if (!p2m_top[topidx])
			continue;

		if (p2m_top[topidx] == p2m_mid_missing)
			continue;

		mididx = p2m_mid_index(pfn);
		mid_p = p2m_top[topidx][mididx];
		if (!mid_p)
			continue;
		if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
			continue;

		if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
			continue;

		/* The old va. Rebase it on mfn_list */
		if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
			unsigned long *new;

			if (pfn_free  > (size / sizeof(unsigned long))) {
				WARN(1, "Only allocated for %ld pages, but we want %ld!\n",
				     size / sizeof(unsigned long), pfn_free);
				return 0;
			}
			new = &mfn_list[pfn_free];

			copy_page(new, mid_p);
			p2m_top[topidx][mididx] = &mfn_list[pfn_free];
			p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]);

			pfn_free += P2M_PER_PAGE;

		}
		/* This should be the leafs allocated for identity from _brk. */
	}
	return (unsigned long)mfn_list;

}
#else
unsigned long __init xen_revector_p2m_tree(void)
{
	return 0;
}
#endif
unsigned long get_phys_to_machine(unsigned long pfn)
{
	unsigned topidx, mididx, idx;

	if (unlikely(pfn >= MAX_P2M_PFN))
		return IDENTITY_FRAME(pfn);

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	/*
	 * The INVALID_P2M_ENTRY is filled in both p2m_*identity
	 * and in p2m_*missing, so returning the INVALID_P2M_ENTRY
	 * would be wrong.
	 */
	if (p2m_top[topidx][mididx] == p2m_identity)
		return IDENTITY_FRAME(pfn);

	return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);

static void *alloc_p2m_page(void)
{
	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
}

static void free_p2m_page(void *p)
{
	free_page((unsigned long)p);
}

/*
 * Fully allocate the p2m structure for a given pfn.  We need to check
 * that both the top and mid levels are allocated, and make sure the
 * parallel mfn tree is kept in sync.  We may race with other cpus, so
 * the new pages are installed with cmpxchg; if we lose the race then
 * simply free the page we allocated and use the one that's there.
 */
static bool alloc_p2m(unsigned long pfn)
{
	unsigned topidx, mididx;
	unsigned long ***top_p, **mid;
	unsigned long *top_mfn_p, *mid_mfn;

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);

	top_p = &p2m_top[topidx];
	mid = *top_p;

	if (mid == p2m_mid_missing) {
		/* Mid level is missing, allocate a new one */
		mid = alloc_p2m_page();
		if (!mid)
			return false;

		p2m_mid_init(mid, p2m_missing);

		if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
			free_p2m_page(mid);
	}

	top_mfn_p = &p2m_top_mfn[topidx];
	mid_mfn = p2m_top_mfn_p[topidx];

	BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);

	if (mid_mfn == p2m_mid_missing_mfn) {
		/* Separately check the mid mfn level */
		unsigned long missing_mfn;
		unsigned long mid_mfn_mfn;

		mid_mfn = alloc_p2m_page();
		if (!mid_mfn)
			return false;

		p2m_mid_mfn_init(mid_mfn, p2m_missing);

		missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
		mid_mfn_mfn = virt_to_mfn(mid_mfn);
		if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
			free_p2m_page(mid_mfn);
		else
			p2m_top_mfn_p[topidx] = mid_mfn;
	}

	if (p2m_top[topidx][mididx] == p2m_identity ||
	    p2m_top[topidx][mididx] == p2m_missing) {
		/* p2m leaf page is missing */
		unsigned long *p2m;
		unsigned long *p2m_orig = p2m_top[topidx][mididx];

		p2m = alloc_p2m_page();
		if (!p2m)
			return false;

		p2m_init(p2m);

		if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
			free_p2m_page(p2m);
		else
			mid_mfn[mididx] = virt_to_mfn(p2m);
	}

	return true;
}

static bool __init early_alloc_p2m(unsigned long pfn, bool check_boundary)
{
	unsigned topidx, mididx, idx;
	unsigned long *p2m;
	unsigned long *mid_mfn_p;

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	/* Pfff.. No boundary cross-over, lets get out. */
	if (!idx && check_boundary)
		return false;

	WARN(p2m_top[topidx][mididx] == p2m_identity,
		"P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
		topidx, mididx);

	/*
	 * Could be done by xen_build_dynamic_phys_to_machine..
	 */
	if (p2m_top[topidx][mididx] != p2m_missing)
		return false;

	/* Boundary cross-over for the edges: */
	p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);

	p2m_init(p2m);

	p2m_top[topidx][mididx] = p2m;

	/* For save/restore we need to MFN of the P2M saved */

	mid_mfn_p = p2m_top_mfn_p[topidx];
	WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
		"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
		topidx, mididx);
	mid_mfn_p[mididx] = virt_to_mfn(p2m);

	return true;
}

static bool __init early_alloc_p2m_middle(unsigned long pfn)
{
	unsigned topidx = p2m_top_index(pfn);
	unsigned long *mid_mfn_p;
	unsigned long **mid;

	mid = p2m_top[topidx];
	mid_mfn_p = p2m_top_mfn_p[topidx];
	if (mid == p2m_mid_missing) {
		mid = extend_brk(PAGE_SIZE, PAGE_SIZE);

		p2m_mid_init(mid, p2m_missing);

		p2m_top[topidx] = mid;

		BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
	}
	/* And the save/restore P2M tables.. */
	if (mid_mfn_p == p2m_mid_missing_mfn) {
		mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_mid_mfn_init(mid_mfn_p, p2m_missing);

		p2m_top_mfn_p[topidx] = mid_mfn_p;
		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
		/* Note: we don't set mid_mfn_p[midix] here,
		 * look in early_alloc_p2m() */
	}
	return true;
}

/*
 * Skim over the P2M tree looking at pages that are either filled with
 * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
 * replace the P2M leaf with a p2m_missing or p2m_identity.
 * Stick the old page in the new P2M tree location.
 */
bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
{
	unsigned topidx;
	unsigned mididx;
	unsigned ident_pfns;
	unsigned inv_pfns;
	unsigned long *p2m;
	unsigned long *mid_mfn_p;
	unsigned idx;
	unsigned long pfn;

	/* We only look when this entails a P2M middle layer */
	if (p2m_index(set_pfn))
		return false;

	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
		topidx = p2m_top_index(pfn);

		if (!p2m_top[topidx])
			continue;

		if (p2m_top[topidx] == p2m_mid_missing)
			continue;

		mididx = p2m_mid_index(pfn);
		p2m = p2m_top[topidx][mididx];
		if (!p2m)
			continue;

		if ((p2m == p2m_missing) || (p2m == p2m_identity))
			continue;

		if ((unsigned long)p2m == INVALID_P2M_ENTRY)
			continue;

		ident_pfns = 0;
		inv_pfns = 0;
		for (idx = 0; idx < P2M_PER_PAGE; idx++) {
			/* IDENTITY_PFNs are 1:1 */
			if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
				ident_pfns++;
			else if (p2m[idx] == INVALID_P2M_ENTRY)
				inv_pfns++;
			else
				break;
		}
		if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
			goto found;
	}
	return false;
found:
	/* Found one, replace old with p2m_identity or p2m_missing */
	p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
	/* And the other for save/restore.. */
	mid_mfn_p = p2m_top_mfn_p[topidx];
	/* NOTE: Even if it is a p2m_identity it should still be point to
	 * a page filled with INVALID_P2M_ENTRY entries. */
	mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);

	/* Reset where we want to stick the old page in. */
	topidx = p2m_top_index(set_pfn);
	mididx = p2m_mid_index(set_pfn);

	/* This shouldn't happen */
	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
		early_alloc_p2m_middle(set_pfn);

	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
		return false;

	p2m_init(p2m);
	p2m_top[topidx][mididx] = p2m;
	mid_mfn_p = p2m_top_mfn_p[topidx];
	mid_mfn_p[mididx] = virt_to_mfn(p2m);

	return true;
}
bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
		if (!early_alloc_p2m_middle(pfn))
			return false;

		if (early_can_reuse_p2m_middle(pfn, mfn))
			return __set_phys_to_machine(pfn, mfn);

		if (!early_alloc_p2m(pfn, false /* boundary crossover OK!*/))
			return false;

		if (!__set_phys_to_machine(pfn, mfn))
			return false;
	}

	return true;
}

static void __init early_split_p2m(unsigned long pfn)
{
	unsigned long mididx, idx;

	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	/*
	 * Allocate new middle and leaf pages if this pfn lies in the
	 * middle of one.
	 */
	if (mididx || idx)
		early_alloc_p2m_middle(pfn);
	if (idx)
		early_alloc_p2m(pfn, false);
}

unsigned long __init set_phys_range_identity(unsigned long pfn_s,
				      unsigned long pfn_e)
{
	unsigned long pfn;

	if (unlikely(pfn_s >= MAX_P2M_PFN))
		return 0;

	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
		return pfn_e - pfn_s;

	if (pfn_s > pfn_e)
		return 0;

	if (pfn_e > MAX_P2M_PFN)
		pfn_e = MAX_P2M_PFN;

	early_split_p2m(pfn_s);
	early_split_p2m(pfn_e);

	for (pfn = pfn_s; pfn < pfn_e;) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);

		if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
			break;
		pfn++;

		/*
		 * If the PFN was set to a middle or leaf identity
		 * page the remainder must also be identity, so skip
		 * ahead to the next middle or leaf entry.
		 */
		if (p2m_top[topidx] == p2m_mid_identity)
			pfn = ALIGN(pfn, P2M_MID_PER_PAGE * P2M_PER_PAGE);
		else if (p2m_top[topidx][mididx] == p2m_identity)
			pfn = ALIGN(pfn, P2M_PER_PAGE);
	}

	if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
		"Identity mapping failed. We are %ld short of 1-1 mappings!\n",
		(pfn_e - pfn_s) - (pfn - pfn_s)))
		printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);

	return pfn - pfn_s;
}

/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	unsigned topidx, mididx, idx;

	/* don't track P2M changes in autotranslate guests */
	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
		return true;

	if (unlikely(pfn >= MAX_P2M_PFN)) {
		BUG_ON(mfn != INVALID_P2M_ENTRY);
		return true;
	}

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	/* For sparse holes were the p2m leaf has real PFN along with
	 * PCI holes, stick in the PFN as the MFN value.
	 *
	 * set_phys_range_identity() will have allocated new middle
	 * and leaf pages as required so an existing p2m_mid_missing
	 * or p2m_missing mean that whole range will be identity so
	 * these can be switched to p2m_mid_identity or p2m_identity.
	 */
	if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
		if (p2m_top[topidx] == p2m_mid_identity)
			return true;

		if (p2m_top[topidx] == p2m_mid_missing) {
			WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing,
					p2m_mid_identity) != p2m_mid_missing);
			return true;
		}

		if (p2m_top[topidx][mididx] == p2m_identity)
			return true;

		/* Swap over from MISSING to IDENTITY if needed. */
		if (p2m_top[topidx][mididx] == p2m_missing) {
			WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing,
				p2m_identity) != p2m_missing);
			return true;
		}
	}

	if (p2m_top[topidx][mididx] == p2m_missing)
		return mfn == INVALID_P2M_ENTRY;

	p2m_top[topidx][mididx][idx] = mfn;

	return true;
}

bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
		if (!alloc_p2m(pfn))
			return false;

		if (!__set_phys_to_machine(pfn, mfn))
			return false;
	}

	return true;
}

#define M2P_OVERRIDE_HASH_SHIFT	10
#define M2P_OVERRIDE_HASH	(1 << M2P_OVERRIDE_HASH_SHIFT)

static RESERVE_BRK_ARRAY(struct list_head, m2p_overrides, M2P_OVERRIDE_HASH);
static DEFINE_SPINLOCK(m2p_override_lock);

static void __init m2p_override_init(void)
{
	unsigned i;

	m2p_overrides = extend_brk(sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
				   sizeof(unsigned long));

	for (i = 0; i < M2P_OVERRIDE_HASH; i++)
		INIT_LIST_HEAD(&m2p_overrides[i]);
}

static unsigned long mfn_hash(unsigned long mfn)
{
	return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT);
}

int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
			    struct gnttab_map_grant_ref *kmap_ops,
			    struct page **pages, unsigned int count)
{
	int i, ret = 0;
	bool lazy = false;
	pte_t *pte;

	if (xen_feature(XENFEAT_auto_translated_physmap))
		return 0;

	if (kmap_ops &&
	    !in_interrupt() &&
	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
		arch_enter_lazy_mmu_mode();
		lazy = true;
	}

	for (i = 0; i < count; i++) {
		unsigned long mfn, pfn;

		/* Do not add to override if the map failed. */
		if (map_ops[i].status)
			continue;

		if (map_ops[i].flags & GNTMAP_contains_pte) {
			pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
				(map_ops[i].host_addr & ~PAGE_MASK));
			mfn = pte_mfn(*pte);
		} else {
			mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
		}
		pfn = page_to_pfn(pages[i]);

		WARN_ON(PagePrivate(pages[i]));
		SetPagePrivate(pages[i]);
		set_page_private(pages[i], mfn);
		pages[i]->index = pfn_to_mfn(pfn);

		if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
			ret = -ENOMEM;
			goto out;
		}

		if (kmap_ops) {
			ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
			if (ret)
				goto out;
		}
	}

out:
	if (lazy)
		arch_leave_lazy_mmu_mode();

	return ret;
}
EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);

/* Add an MFN override for a particular page */
int m2p_add_override(unsigned long mfn, struct page *page,
		struct gnttab_map_grant_ref *kmap_op)
{
	unsigned long flags;
	unsigned long pfn;
	unsigned long uninitialized_var(address);
	unsigned level;
	pte_t *ptep = NULL;

	pfn = page_to_pfn(page);
	if (!PageHighMem(page)) {
		address = (unsigned long)__va(pfn << PAGE_SHIFT);
		ptep = lookup_address(address, &level);
		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
					"m2p_add_override: pfn %lx not mapped", pfn))
			return -EINVAL;
	}

	if (kmap_op != NULL) {
		if (!PageHighMem(page)) {
			struct multicall_space mcs =
				xen_mc_entry(sizeof(*kmap_op));

			MULTI_grant_table_op(mcs.mc,
					GNTTABOP_map_grant_ref, kmap_op, 1);

			xen_mc_issue(PARAVIRT_LAZY_MMU);
		}
	}
	spin_lock_irqsave(&m2p_override_lock, flags);
	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
	spin_unlock_irqrestore(&m2p_override_lock, flags);

	/* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
	 * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
	 * pfn so that the following mfn_to_pfn(mfn) calls will return the
	 * pfn from the m2p_override (the backend pfn) instead.
	 * We need to do this because the pages shared by the frontend
	 * (xen-blkfront) can be already locked (lock_page, called by
	 * do_read_cache_page); when the userspace backend tries to use them
	 * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
	 * do_blockdev_direct_IO is going to try to lock the same pages
	 * again resulting in a deadlock.
	 * As a side effect get_user_pages_fast might not be safe on the
	 * frontend pages while they are being shared with the backend,
	 * because mfn_to_pfn (that ends up being called by GUPF) will
	 * return the backend pfn rather than the frontend pfn. */
	pfn = mfn_to_pfn_no_overrides(mfn);
	if (get_phys_to_machine(pfn) == mfn)
		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));

	return 0;
}
EXPORT_SYMBOL_GPL(m2p_add_override);

int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
			      struct gnttab_map_grant_ref *kmap_ops,
			      struct page **pages, unsigned int count)
{
	int i, ret = 0;
	bool lazy = false;

	if (xen_feature(XENFEAT_auto_translated_physmap))
		return 0;

	if (kmap_ops &&
	    !in_interrupt() &&
	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
		arch_enter_lazy_mmu_mode();
		lazy = true;
	}

	for (i = 0; i < count; i++) {
		unsigned long mfn = get_phys_to_machine(page_to_pfn(pages[i]));
		unsigned long pfn = page_to_pfn(pages[i]);

		if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
			ret = -EINVAL;
			goto out;
		}

		set_page_private(pages[i], INVALID_P2M_ENTRY);
		WARN_ON(!PagePrivate(pages[i]));
		ClearPagePrivate(pages[i]);
		set_phys_to_machine(pfn, pages[i]->index);

		if (kmap_ops)
			ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
		if (ret)
			goto out;
	}

out:
	if (lazy)
		arch_leave_lazy_mmu_mode();
	return ret;
}
EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);

int m2p_remove_override(struct page *page,
			struct gnttab_map_grant_ref *kmap_op,
			unsigned long mfn)
{
	unsigned long flags;
	unsigned long pfn;
	unsigned long uninitialized_var(address);
	unsigned level;
	pte_t *ptep = NULL;

	pfn = page_to_pfn(page);

	if (!PageHighMem(page)) {
		address = (unsigned long)__va(pfn << PAGE_SHIFT);
		ptep = lookup_address(address, &level);

		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
					"m2p_remove_override: pfn %lx not mapped", pfn))
			return -EINVAL;
	}

	spin_lock_irqsave(&m2p_override_lock, flags);
	list_del(&page->lru);
	spin_unlock_irqrestore(&m2p_override_lock, flags);

	if (kmap_op != NULL) {
		if (!PageHighMem(page)) {
			struct multicall_space mcs;
			struct gnttab_unmap_and_replace *unmap_op;
			struct page *scratch_page = get_balloon_scratch_page();
			unsigned long scratch_page_address = (unsigned long)
				__va(page_to_pfn(scratch_page) << PAGE_SHIFT);

			/*
			 * It might be that we queued all the m2p grant table
			 * hypercalls in a multicall, then m2p_remove_override
			 * get called before the multicall has actually been
			 * issued. In this case handle is going to -1 because
			 * it hasn't been modified yet.
			 */
			if (kmap_op->handle == -1)
				xen_mc_flush();
			/*
			 * Now if kmap_op->handle is negative it means that the
			 * hypercall actually returned an error.
			 */
			if (kmap_op->handle == GNTST_general_error) {
				printk(KERN_WARNING "m2p_remove_override: "
						"pfn %lx mfn %lx, failed to modify kernel mappings",
						pfn, mfn);
				put_balloon_scratch_page();
				return -1;
			}

			xen_mc_batch();

			mcs = __xen_mc_entry(
					sizeof(struct gnttab_unmap_and_replace));
			unmap_op = mcs.args;
			unmap_op->host_addr = kmap_op->host_addr;
			unmap_op->new_addr = scratch_page_address;
			unmap_op->handle = kmap_op->handle;

			MULTI_grant_table_op(mcs.mc,
					GNTTABOP_unmap_and_replace, unmap_op, 1);

			mcs = __xen_mc_entry(0);
			MULTI_update_va_mapping(mcs.mc, scratch_page_address,
					pfn_pte(page_to_pfn(scratch_page),
					PAGE_KERNEL_RO), 0);

			xen_mc_issue(PARAVIRT_LAZY_MMU);

			kmap_op->host_addr = 0;
			put_balloon_scratch_page();
		}
	}

	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
	 * somewhere in this domain, even before being added to the
	 * m2p_override (see comment above in m2p_add_override).
	 * If there are no other entries in the m2p_override corresponding
	 * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
	 * the original pfn (the one shared by the frontend): the backend
	 * cannot do any IO on this page anymore because it has been
	 * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
	 * pfn again. */
	mfn &= ~FOREIGN_FRAME_BIT;
	pfn = mfn_to_pfn_no_overrides(mfn);
	if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
			m2p_find_override(mfn) == NULL)
		set_phys_to_machine(pfn, mfn);

	return 0;
}
EXPORT_SYMBOL_GPL(m2p_remove_override);

struct page *m2p_find_override(unsigned long mfn)
{
	unsigned long flags;
	struct list_head *bucket = &m2p_overrides[mfn_hash(mfn)];
	struct page *p, *ret;

	ret = NULL;

	spin_lock_irqsave(&m2p_override_lock, flags);

	list_for_each_entry(p, bucket, lru) {
		if (page_private(p) == mfn) {
			ret = p;
			break;
		}
	}

	spin_unlock_irqrestore(&m2p_override_lock, flags);

	return ret;
}

unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
{
	struct page *p = m2p_find_override(mfn);
	unsigned long ret = pfn;

	if (p)
		ret = page_to_pfn(p);

	return ret;
}
EXPORT_SYMBOL_GPL(m2p_find_override_pfn);

#ifdef CONFIG_XEN_DEBUG_FS
#include <linux/debugfs.h>
#include "debugfs.h"
static int p2m_dump_show(struct seq_file *m, void *v)
{
	static const char * const level_name[] = { "top", "middle",
						"entry", "abnormal", "error"};
#define TYPE_IDENTITY 0
#define TYPE_MISSING 1
#define TYPE_PFN 2
#define TYPE_UNKNOWN 3
	static const char * const type_name[] = {
				[TYPE_IDENTITY] = "identity",
				[TYPE_MISSING] = "missing",
				[TYPE_PFN] = "pfn",
				[TYPE_UNKNOWN] = "abnormal"};
	unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
	unsigned int uninitialized_var(prev_level);
	unsigned int uninitialized_var(prev_type);

	if (!p2m_top)
		return 0;

	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);
		unsigned idx = p2m_index(pfn);
		unsigned lvl, type;

		lvl = 4;
		type = TYPE_UNKNOWN;
		if (p2m_top[topidx] == p2m_mid_missing) {
			lvl = 0; type = TYPE_MISSING;
		} else if (p2m_top[topidx] == NULL) {
			lvl = 0; type = TYPE_UNKNOWN;
		} else if (p2m_top[topidx][mididx] == NULL) {
			lvl = 1; type = TYPE_UNKNOWN;
		} else if (p2m_top[topidx][mididx] == p2m_identity) {
			lvl = 1; type = TYPE_IDENTITY;
		} else if (p2m_top[topidx][mididx] == p2m_missing) {
			lvl = 1; type = TYPE_MISSING;
		} else if (p2m_top[topidx][mididx][idx] == 0) {
			lvl = 2; type = TYPE_UNKNOWN;
		} else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) {
			lvl = 2; type = TYPE_IDENTITY;
		} else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) {
			lvl = 2; type = TYPE_MISSING;
		} else if (p2m_top[topidx][mididx][idx] == pfn) {
			lvl = 2; type = TYPE_PFN;
		} else if (p2m_top[topidx][mididx][idx] != pfn) {
			lvl = 2; type = TYPE_PFN;
		}
		if (pfn == 0) {
			prev_level = lvl;
			prev_type = type;
		}
		if (pfn == MAX_DOMAIN_PAGES-1) {
			lvl = 3;
			type = TYPE_UNKNOWN;
		}
		if (prev_type != type) {
			seq_printf(m, " [0x%lx->0x%lx] %s\n",
				prev_pfn_type, pfn, type_name[prev_type]);
			prev_pfn_type = pfn;
			prev_type = type;
		}
		if (prev_level != lvl) {
			seq_printf(m, " [0x%lx->0x%lx] level %s\n",
				prev_pfn_level, pfn, level_name[prev_level]);
			prev_pfn_level = pfn;
			prev_level = lvl;
		}
	}
	return 0;
#undef TYPE_IDENTITY
#undef TYPE_MISSING
#undef TYPE_PFN
#undef TYPE_UNKNOWN
}

static int p2m_dump_open(struct inode *inode, struct file *filp)
{
	return single_open(filp, p2m_dump_show, NULL);
}

static const struct file_operations p2m_dump_fops = {
	.open		= p2m_dump_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static struct dentry *d_mmu_debug;

static int __init xen_p2m_debugfs(void)
{
	struct dentry *d_xen = xen_init_debugfs();

	if (d_xen == NULL)
		return -ENOMEM;

	d_mmu_debug = debugfs_create_dir("mmu", d_xen);

	debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
	return 0;
}
fs_initcall(xen_p2m_debugfs);
#endif /* CONFIG_XEN_DEBUG_FS */