aboutsummaryrefslogtreecommitdiff
path: root/target/arm/kvm64.c
blob: 37ceadd9a9dd92714fd4b7cbfe95678061bcb505 (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
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
/*
 * ARM implementation of KVM hooks, 64 bit specific code
 *
 * Copyright Mian-M. Hamayun 2013, Virtual Open Systems
 * Copyright Alex Bennée 2014, Linaro
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include <sys/ioctl.h>
#include <sys/ptrace.h>

#include <linux/elf.h>
#include <linux/kvm.h>

#include "qemu-common.h"
#include "qapi/error.h"
#include "cpu.h"
#include "qemu/timer.h"
#include "qemu/error-report.h"
#include "qemu/host-utils.h"
#include "qemu/main-loop.h"
#include "exec/gdbstub.h"
#include "sysemu/runstate.h"
#include "sysemu/kvm.h"
#include "sysemu/kvm_int.h"
#include "kvm_arm.h"
#include "internals.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/ghes.h"
#include "hw/arm/virt.h"

static bool have_guest_debug;

/*
 * Although the ARM implementation of hardware assisted debugging
 * allows for different breakpoints per-core, the current GDB
 * interface treats them as a global pool of registers (which seems to
 * be the case for x86, ppc and s390). As a result we store one copy
 * of registers which is used for all active cores.
 *
 * Write access is serialised by virtue of the GDB protocol which
 * updates things. Read access (i.e. when the values are copied to the
 * vCPU) is also gated by GDB's run control.
 *
 * This is not unreasonable as most of the time debugging kernels you
 * never know which core will eventually execute your function.
 */

typedef struct {
    uint64_t bcr;
    uint64_t bvr;
} HWBreakpoint;

/* The watchpoint registers can cover more area than the requested
 * watchpoint so we need to store the additional information
 * somewhere. We also need to supply a CPUWatchpoint to the GDB stub
 * when the watchpoint is hit.
 */
typedef struct {
    uint64_t wcr;
    uint64_t wvr;
    CPUWatchpoint details;
} HWWatchpoint;

/* Maximum and current break/watch point counts */
int max_hw_bps, max_hw_wps;
GArray *hw_breakpoints, *hw_watchpoints;

#define cur_hw_wps      (hw_watchpoints->len)
#define cur_hw_bps      (hw_breakpoints->len)
#define get_hw_bp(i)    (&g_array_index(hw_breakpoints, HWBreakpoint, i))
#define get_hw_wp(i)    (&g_array_index(hw_watchpoints, HWWatchpoint, i))

/**
 * kvm_arm_init_debug() - check for guest debug capabilities
 * @cs: CPUState
 *
 * kvm_check_extension returns the number of debug registers we have
 * or 0 if we have none.
 *
 */
static void kvm_arm_init_debug(CPUState *cs)
{
    have_guest_debug = kvm_check_extension(cs->kvm_state,
                                           KVM_CAP_SET_GUEST_DEBUG);

    max_hw_wps = kvm_check_extension(cs->kvm_state, KVM_CAP_GUEST_DEBUG_HW_WPS);
    hw_watchpoints = g_array_sized_new(true, true,
                                       sizeof(HWWatchpoint), max_hw_wps);

    max_hw_bps = kvm_check_extension(cs->kvm_state, KVM_CAP_GUEST_DEBUG_HW_BPS);
    hw_breakpoints = g_array_sized_new(true, true,
                                       sizeof(HWBreakpoint), max_hw_bps);
    return;
}

/**
 * insert_hw_breakpoint()
 * @addr: address of breakpoint
 *
 * See ARM ARM D2.9.1 for details but here we are only going to create
 * simple un-linked breakpoints (i.e. we don't chain breakpoints
 * together to match address and context or vmid). The hardware is
 * capable of fancier matching but that will require exposing that
 * fanciness to GDB's interface
 *
 * DBGBCR<n>_EL1, Debug Breakpoint Control Registers
 *
 *  31  24 23  20 19   16 15 14  13  12   9 8   5 4    3 2   1  0
 * +------+------+-------+-----+----+------+-----+------+-----+---+
 * | RES0 |  BT  |  LBN  | SSC | HMC| RES0 | BAS | RES0 | PMC | E |
 * +------+------+-------+-----+----+------+-----+------+-----+---+
 *
 * BT: Breakpoint type (0 = unlinked address match)
 * LBN: Linked BP number (0 = unused)
 * SSC/HMC/PMC: Security, Higher and Priv access control (Table D-12)
 * BAS: Byte Address Select (RES1 for AArch64)
 * E: Enable bit
 *
 * DBGBVR<n>_EL1, Debug Breakpoint Value Registers
 *
 *  63  53 52       49 48       2  1 0
 * +------+-----------+----------+-----+
 * | RESS | VA[52:49] | VA[48:2] | 0 0 |
 * +------+-----------+----------+-----+
 *
 * Depending on the addressing mode bits the top bits of the register
 * are a sign extension of the highest applicable VA bit. Some
 * versions of GDB don't do it correctly so we ensure they are correct
 * here so future PC comparisons will work properly.
 */

static int insert_hw_breakpoint(target_ulong addr)
{
    HWBreakpoint brk = {
        .bcr = 0x1,                             /* BCR E=1, enable */
        .bvr = sextract64(addr, 0, 53)
    };

    if (cur_hw_bps >= max_hw_bps) {
        return -ENOBUFS;
    }

    brk.bcr = deposit32(brk.bcr, 1, 2, 0x3);   /* PMC = 11 */
    brk.bcr = deposit32(brk.bcr, 5, 4, 0xf);   /* BAS = RES1 */

    g_array_append_val(hw_breakpoints, brk);

    return 0;
}

/**
 * delete_hw_breakpoint()
 * @pc: address of breakpoint
 *
 * Delete a breakpoint and shuffle any above down
 */

static int delete_hw_breakpoint(target_ulong pc)
{
    int i;
    for (i = 0; i < hw_breakpoints->len; i++) {
        HWBreakpoint *brk = get_hw_bp(i);
        if (brk->bvr == pc) {
            g_array_remove_index(hw_breakpoints, i);
            return 0;
        }
    }
    return -ENOENT;
}

/**
 * insert_hw_watchpoint()
 * @addr: address of watch point
 * @len: size of area
 * @type: type of watch point
 *
 * See ARM ARM D2.10. As with the breakpoints we can do some advanced
 * stuff if we want to. The watch points can be linked with the break
 * points above to make them context aware. However for simplicity
 * currently we only deal with simple read/write watch points.
 *
 * D7.3.11 DBGWCR<n>_EL1, Debug Watchpoint Control Registers
 *
 *  31  29 28   24 23  21  20  19 16 15 14  13   12  5 4   3 2   1  0
 * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+
 * | RES0 |  MASK | RES0 | WT | LBN | SSC | HMC | BAS | LSC | PAC | E |
 * +------+-------+------+----+-----+-----+-----+-----+-----+-----+---+
 *
 * MASK: num bits addr mask (0=none,01/10=res,11=3 bits (8 bytes))
 * WT: 0 - unlinked, 1 - linked (not currently used)
 * LBN: Linked BP number (not currently used)
 * SSC/HMC/PAC: Security, Higher and Priv access control (Table D2-11)
 * BAS: Byte Address Select
 * LSC: Load/Store control (01: load, 10: store, 11: both)
 * E: Enable
 *
 * The bottom 2 bits of the value register are masked. Therefore to
 * break on any sizes smaller than an unaligned word you need to set
 * MASK=0, BAS=bit per byte in question. For larger regions (^2) you
 * need to ensure you mask the address as required and set BAS=0xff
 */

static int insert_hw_watchpoint(target_ulong addr,
                                target_ulong len, int type)
{
    HWWatchpoint wp = {
        .wcr = 1, /* E=1, enable */
        .wvr = addr & (~0x7ULL),
        .details = { .vaddr = addr, .len = len }
    };

    if (cur_hw_wps >= max_hw_wps) {
        return -ENOBUFS;
    }

    /*
     * HMC=0 SSC=0 PAC=3 will hit EL0 or EL1, any security state,
     * valid whether EL3 is implemented or not
     */
    wp.wcr = deposit32(wp.wcr, 1, 2, 3);

    switch (type) {
    case GDB_WATCHPOINT_READ:
        wp.wcr = deposit32(wp.wcr, 3, 2, 1);
        wp.details.flags = BP_MEM_READ;
        break;
    case GDB_WATCHPOINT_WRITE:
        wp.wcr = deposit32(wp.wcr, 3, 2, 2);
        wp.details.flags = BP_MEM_WRITE;
        break;
    case GDB_WATCHPOINT_ACCESS:
        wp.wcr = deposit32(wp.wcr, 3, 2, 3);
        wp.details.flags = BP_MEM_ACCESS;
        break;
    default:
        g_assert_not_reached();
        break;
    }
    if (len <= 8) {
        /* we align the address and set the bits in BAS */
        int off = addr & 0x7;
        int bas = (1 << len) - 1;

        wp.wcr = deposit32(wp.wcr, 5 + off, 8 - off, bas);
    } else {
        /* For ranges above 8 bytes we need to be a power of 2 */
        if (is_power_of_2(len)) {
            int bits = ctz64(len);

            wp.wvr &= ~((1 << bits) - 1);
            wp.wcr = deposit32(wp.wcr, 24, 4, bits);
            wp.wcr = deposit32(wp.wcr, 5, 8, 0xff);
        } else {
            return -ENOBUFS;
        }
    }

    g_array_append_val(hw_watchpoints, wp);
    return 0;
}


static bool check_watchpoint_in_range(int i, target_ulong addr)
{
    HWWatchpoint *wp = get_hw_wp(i);
    uint64_t addr_top, addr_bottom = wp->wvr;
    int bas = extract32(wp->wcr, 5, 8);
    int mask = extract32(wp->wcr, 24, 4);

    if (mask) {
        addr_top = addr_bottom + (1 << mask);
    } else {
        /* BAS must be contiguous but can offset against the base
         * address in DBGWVR */
        addr_bottom = addr_bottom + ctz32(bas);
        addr_top = addr_bottom + clo32(bas);
    }

    if (addr >= addr_bottom && addr <= addr_top) {
        return true;
    }

    return false;
}

/**
 * delete_hw_watchpoint()
 * @addr: address of breakpoint
 *
 * Delete a breakpoint and shuffle any above down
 */

static int delete_hw_watchpoint(target_ulong addr,
                                target_ulong len, int type)
{
    int i;
    for (i = 0; i < cur_hw_wps; i++) {
        if (check_watchpoint_in_range(i, addr)) {
            g_array_remove_index(hw_watchpoints, i);
            return 0;
        }
    }
    return -ENOENT;
}


int kvm_arch_insert_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    switch (type) {
    case GDB_BREAKPOINT_HW:
        return insert_hw_breakpoint(addr);
        break;
    case GDB_WATCHPOINT_READ:
    case GDB_WATCHPOINT_WRITE:
    case GDB_WATCHPOINT_ACCESS:
        return insert_hw_watchpoint(addr, len, type);
    default:
        return -ENOSYS;
    }
}

int kvm_arch_remove_hw_breakpoint(target_ulong addr,
                                  target_ulong len, int type)
{
    switch (type) {
    case GDB_BREAKPOINT_HW:
        return delete_hw_breakpoint(addr);
    case GDB_WATCHPOINT_READ:
    case GDB_WATCHPOINT_WRITE:
    case GDB_WATCHPOINT_ACCESS:
        return delete_hw_watchpoint(addr, len, type);
    default:
        return -ENOSYS;
    }
}


void kvm_arch_remove_all_hw_breakpoints(void)
{
    if (cur_hw_wps > 0) {
        g_array_remove_range(hw_watchpoints, 0, cur_hw_wps);
    }
    if (cur_hw_bps > 0) {
        g_array_remove_range(hw_breakpoints, 0, cur_hw_bps);
    }
}

void kvm_arm_copy_hw_debug_data(struct kvm_guest_debug_arch *ptr)
{
    int i;
    memset(ptr, 0, sizeof(struct kvm_guest_debug_arch));

    for (i = 0; i < max_hw_wps; i++) {
        HWWatchpoint *wp = get_hw_wp(i);
        ptr->dbg_wcr[i] = wp->wcr;
        ptr->dbg_wvr[i] = wp->wvr;
    }
    for (i = 0; i < max_hw_bps; i++) {
        HWBreakpoint *bp = get_hw_bp(i);
        ptr->dbg_bcr[i] = bp->bcr;
        ptr->dbg_bvr[i] = bp->bvr;
    }
}

bool kvm_arm_hw_debug_active(CPUState *cs)
{
    return ((cur_hw_wps > 0) || (cur_hw_bps > 0));
}

static bool find_hw_breakpoint(CPUState *cpu, target_ulong pc)
{
    int i;

    for (i = 0; i < cur_hw_bps; i++) {
        HWBreakpoint *bp = get_hw_bp(i);
        if (bp->bvr == pc) {
            return true;
        }
    }
    return false;
}

static CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr)
{
    int i;

    for (i = 0; i < cur_hw_wps; i++) {
        if (check_watchpoint_in_range(i, addr)) {
            return &get_hw_wp(i)->details;
        }
    }
    return NULL;
}

static bool kvm_arm_set_device_attr(CPUState *cs, struct kvm_device_attr *attr,
                                    const char *name)
{
    int err;

    err = kvm_vcpu_ioctl(cs, KVM_HAS_DEVICE_ATTR, attr);
    if (err != 0) {
        error_report("%s: KVM_HAS_DEVICE_ATTR: %s", name, strerror(-err));
        return false;
    }

    err = kvm_vcpu_ioctl(cs, KVM_SET_DEVICE_ATTR, attr);
    if (err != 0) {
        error_report("%s: KVM_SET_DEVICE_ATTR: %s", name, strerror(-err));
        return false;
    }

    return true;
}

void kvm_arm_pmu_init(CPUState *cs)
{
    struct kvm_device_attr attr = {
        .group = KVM_ARM_VCPU_PMU_V3_CTRL,
        .attr = KVM_ARM_VCPU_PMU_V3_INIT,
    };

    if (!ARM_CPU(cs)->has_pmu) {
        return;
    }
    if (!kvm_arm_set_device_attr(cs, &attr, "PMU")) {
        error_report("failed to init PMU");
        abort();
    }
}

void kvm_arm_pmu_set_irq(CPUState *cs, int irq)
{
    struct kvm_device_attr attr = {
        .group = KVM_ARM_VCPU_PMU_V3_CTRL,
        .addr = (intptr_t)&irq,
        .attr = KVM_ARM_VCPU_PMU_V3_IRQ,
    };

    if (!ARM_CPU(cs)->has_pmu) {
        return;
    }
    if (!kvm_arm_set_device_attr(cs, &attr, "PMU")) {
        error_report("failed to set irq for PMU");
        abort();
    }
}

void kvm_arm_pvtime_init(CPUState *cs, uint64_t ipa)
{
    struct kvm_device_attr attr = {
        .group = KVM_ARM_VCPU_PVTIME_CTRL,
        .attr = KVM_ARM_VCPU_PVTIME_IPA,
        .addr = (uint64_t)&ipa,
    };

    if (ARM_CPU(cs)->kvm_steal_time == ON_OFF_AUTO_OFF) {
        return;
    }
    if (!kvm_arm_set_device_attr(cs, &attr, "PVTIME IPA")) {
        error_report("failed to init PVTIME IPA");
        abort();
    }
}

static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id)
{
    uint64_t ret;
    struct kvm_one_reg idreg = { .id = id, .addr = (uintptr_t)&ret };
    int err;

    assert((id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64);
    err = ioctl(fd, KVM_GET_ONE_REG, &idreg);
    if (err < 0) {
        return -1;
    }
    *pret = ret;
    return 0;
}

static int read_sys_reg64(int fd, uint64_t *pret, uint64_t id)
{
    struct kvm_one_reg idreg = { .id = id, .addr = (uintptr_t)pret };

    assert((id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64);
    return ioctl(fd, KVM_GET_ONE_REG, &idreg);
}

bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
{
    /* Identify the feature bits corresponding to the host CPU, and
     * fill out the ARMHostCPUClass fields accordingly. To do this
     * we have to create a scratch VM, create a single CPU inside it,
     * and then query that CPU for the relevant ID registers.
     */
    int fdarray[3];
    bool sve_supported;
    uint64_t features = 0;
    uint64_t t;
    int err;

    /* Old kernels may not know about the PREFERRED_TARGET ioctl: however
     * we know these will only support creating one kind of guest CPU,
     * which is its preferred CPU type. Fortunately these old kernels
     * support only a very limited number of CPUs.
     */
    static const uint32_t cpus_to_try[] = {
        KVM_ARM_TARGET_AEM_V8,
        KVM_ARM_TARGET_FOUNDATION_V8,
        KVM_ARM_TARGET_CORTEX_A57,
        QEMU_KVM_ARM_TARGET_NONE
    };
    /*
     * target = -1 informs kvm_arm_create_scratch_host_vcpu()
     * to use the preferred target
     */
    struct kvm_vcpu_init init = { .target = -1, };

    if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) {
        return false;
    }

    ahcf->target = init.target;
    ahcf->dtb_compatible = "arm,arm-v8";

    err = read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64pfr0,
                         ARM64_SYS_REG(3, 0, 0, 4, 0));
    if (unlikely(err < 0)) {
        /*
         * Before v4.15, the kernel only exposed a limited number of system
         * registers, not including any of the interesting AArch64 ID regs.
         * For the most part we could leave these fields as zero with minimal
         * effect, since this does not affect the values seen by the guest.
         *
         * However, it could cause problems down the line for QEMU,
         * so provide a minimal v8.0 default.
         *
         * ??? Could read MIDR and use knowledge from cpu64.c.
         * ??? Could map a page of memory into our temp guest and
         *     run the tiniest of hand-crafted kernels to extract
         *     the values seen by the guest.
         * ??? Either of these sounds like too much effort just
         *     to work around running a modern host kernel.
         */
        ahcf->isar.id_aa64pfr0 = 0x00000011; /* EL1&0, AArch64 only */
        err = 0;
    } else {
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64pfr1,
                              ARM64_SYS_REG(3, 0, 0, 4, 1));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64dfr0,
                              ARM64_SYS_REG(3, 0, 0, 5, 0));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64dfr1,
                              ARM64_SYS_REG(3, 0, 0, 5, 1));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar0,
                              ARM64_SYS_REG(3, 0, 0, 6, 0));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar1,
                              ARM64_SYS_REG(3, 0, 0, 6, 1));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr0,
                              ARM64_SYS_REG(3, 0, 0, 7, 0));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr1,
                              ARM64_SYS_REG(3, 0, 0, 7, 1));
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr2,
                              ARM64_SYS_REG(3, 0, 0, 7, 2));

        /*
         * Note that if AArch32 support is not present in the host,
         * the AArch32 sysregs are present to be read, but will
         * return UNKNOWN values.  This is neither better nor worse
         * than skipping the reads and leaving 0, as we must avoid
         * considering the values in every case.
         */
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_pfr0,
                              ARM64_SYS_REG(3, 0, 0, 1, 0));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_pfr1,
                              ARM64_SYS_REG(3, 0, 0, 1, 1));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_pfr2,
                              ARM64_SYS_REG(3, 0, 0, 3, 4));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_dfr0,
                              ARM64_SYS_REG(3, 0, 0, 1, 2));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr0,
                              ARM64_SYS_REG(3, 0, 0, 1, 4));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr1,
                              ARM64_SYS_REG(3, 0, 0, 1, 5));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr2,
                              ARM64_SYS_REG(3, 0, 0, 1, 6));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr3,
                              ARM64_SYS_REG(3, 0, 0, 1, 7));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar0,
                              ARM64_SYS_REG(3, 0, 0, 2, 0));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar1,
                              ARM64_SYS_REG(3, 0, 0, 2, 1));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar2,
                              ARM64_SYS_REG(3, 0, 0, 2, 2));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar3,
                              ARM64_SYS_REG(3, 0, 0, 2, 3));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar4,
                              ARM64_SYS_REG(3, 0, 0, 2, 4));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar5,
                              ARM64_SYS_REG(3, 0, 0, 2, 5));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr4,
                              ARM64_SYS_REG(3, 0, 0, 2, 6));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar6,
                              ARM64_SYS_REG(3, 0, 0, 2, 7));

        err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr0,
                              ARM64_SYS_REG(3, 0, 0, 3, 0));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr1,
                              ARM64_SYS_REG(3, 0, 0, 3, 1));
        err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr2,
                              ARM64_SYS_REG(3, 0, 0, 3, 2));

        /*
         * DBGDIDR is a bit complicated because the kernel doesn't
         * provide an accessor for it in 64-bit mode, which is what this
         * scratch VM is in, and there's no architected "64-bit sysreg
         * which reads the same as the 32-bit register" the way there is
         * for other ID registers. Instead we synthesize a value from the
         * AArch64 ID_AA64DFR0, the same way the kernel code in
         * arch/arm64/kvm/sys_regs.c:trap_dbgidr() does.
         * We only do this if the CPU supports AArch32 at EL1.
         */
        if (FIELD_EX32(ahcf->isar.id_aa64pfr0, ID_AA64PFR0, EL1) >= 2) {
            int wrps = FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, WRPS);
            int brps = FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, BRPS);
            int ctx_cmps =
                FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, CTX_CMPS);
            int version = 6; /* ARMv8 debug architecture */
            bool has_el3 =
                !!FIELD_EX32(ahcf->isar.id_aa64pfr0, ID_AA64PFR0, EL3);
            uint32_t dbgdidr = 0;

            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, WRPS, wrps);
            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, BRPS, brps);
            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, CTX_CMPS, ctx_cmps);
            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, VERSION, version);
            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, NSUHD_IMP, has_el3);
            dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, SE_IMP, has_el3);
            dbgdidr |= (1 << 15); /* RES1 bit */
            ahcf->isar.dbgdidr = dbgdidr;
        }
    }

    sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0;

    /* Add feature bits that can't appear until after VCPU init. */
    if (sve_supported) {
        t = ahcf->isar.id_aa64pfr0;
        t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1);
        ahcf->isar.id_aa64pfr0 = t;

        /*
         * Before v5.1, KVM did not support SVE and did not expose
         * ID_AA64ZFR0_EL1 even as RAZ.  After v5.1, KVM still does
         * not expose the register to "user" requests like this
         * unless the host supports SVE.
         */
        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64zfr0,
                              ARM64_SYS_REG(3, 0, 0, 4, 4));
    }

    kvm_arm_destroy_scratch_host_vcpu(fdarray);

    if (err < 0) {
        return false;
    }

    /*
     * We can assume any KVM supporting CPU is at least a v8
     * with VFPv4+Neon; this in turn implies most of the other
     * feature bits.
     */
    features |= 1ULL << ARM_FEATURE_V8;
    features |= 1ULL << ARM_FEATURE_NEON;
    features |= 1ULL << ARM_FEATURE_AARCH64;
    features |= 1ULL << ARM_FEATURE_PMU;
    features |= 1ULL << ARM_FEATURE_GENERIC_TIMER;

    ahcf->features = features;

    return true;
}

void kvm_arm_steal_time_finalize(ARMCPU *cpu, Error **errp)
{
    bool has_steal_time = kvm_arm_steal_time_supported();

    if (cpu->kvm_steal_time == ON_OFF_AUTO_AUTO) {
        if (!has_steal_time || !arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
            cpu->kvm_steal_time = ON_OFF_AUTO_OFF;
        } else {
            cpu->kvm_steal_time = ON_OFF_AUTO_ON;
        }
    } else if (cpu->kvm_steal_time == ON_OFF_AUTO_ON) {
        if (!has_steal_time) {
            error_setg(errp, "'kvm-steal-time' cannot be enabled "
                             "on this host");
            return;
        } else if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
            /*
             * DEN0057A chapter 2 says "This specification only covers
             * systems in which the Execution state of the hypervisor
             * as well as EL1 of virtual machines is AArch64.". And,
             * to ensure that, the smc/hvc calls are only specified as
             * smc64/hvc64.
             */
            error_setg(errp, "'kvm-steal-time' cannot be enabled "
                             "for AArch32 guests");
            return;
        }
    }
}

bool kvm_arm_aarch32_supported(void)
{
    return kvm_check_extension(kvm_state, KVM_CAP_ARM_EL1_32BIT);
}

bool kvm_arm_sve_supported(void)
{
    return kvm_check_extension(kvm_state, KVM_CAP_ARM_SVE);
}

bool kvm_arm_steal_time_supported(void)
{
    return kvm_check_extension(kvm_state, KVM_CAP_STEAL_TIME);
}

QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1);

void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map)
{
    /* Only call this function if kvm_arm_sve_supported() returns true. */
    static uint64_t vls[KVM_ARM64_SVE_VLS_WORDS];
    static bool probed;
    uint32_t vq = 0;
    int i, j;

    bitmap_clear(map, 0, ARM_MAX_VQ);

    /*
     * KVM ensures all host CPUs support the same set of vector lengths.
     * So we only need to create the scratch VCPUs once and then cache
     * the results.
     */
    if (!probed) {
        struct kvm_vcpu_init init = {
            .target = -1,
            .features[0] = (1 << KVM_ARM_VCPU_SVE),
        };
        struct kvm_one_reg reg = {
            .id = KVM_REG_ARM64_SVE_VLS,
            .addr = (uint64_t)&vls[0],
        };
        int fdarray[3], ret;

        probed = true;

        if (!kvm_arm_create_scratch_host_vcpu(NULL, fdarray, &init)) {
            error_report("failed to create scratch VCPU with SVE enabled");
            abort();
        }
        ret = ioctl(fdarray[2], KVM_GET_ONE_REG, &reg);
        kvm_arm_destroy_scratch_host_vcpu(fdarray);
        if (ret) {
            error_report("failed to get KVM_REG_ARM64_SVE_VLS: %s",
                         strerror(errno));
            abort();
        }

        for (i = KVM_ARM64_SVE_VLS_WORDS - 1; i >= 0; --i) {
            if (vls[i]) {
                vq = 64 - clz64(vls[i]) + i * 64;
                break;
            }
        }
        if (vq > ARM_MAX_VQ) {
            warn_report("KVM supports vector lengths larger than "
                        "QEMU can enable");
        }
    }

    for (i = 0; i < KVM_ARM64_SVE_VLS_WORDS; ++i) {
        if (!vls[i]) {
            continue;
        }
        for (j = 1; j <= 64; ++j) {
            vq = j + i * 64;
            if (vq > ARM_MAX_VQ) {
                return;
            }
            if (vls[i] & (1UL << (j - 1))) {
                set_bit(vq - 1, map);
            }
        }
    }
}

static int kvm_arm_sve_set_vls(CPUState *cs)
{
    uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = {0};
    struct kvm_one_reg reg = {
        .id = KVM_REG_ARM64_SVE_VLS,
        .addr = (uint64_t)&vls[0],
    };
    ARMCPU *cpu = ARM_CPU(cs);
    uint32_t vq;
    int i, j;

    assert(cpu->sve_max_vq <= KVM_ARM64_SVE_VQ_MAX);

    for (vq = 1; vq <= cpu->sve_max_vq; ++vq) {
        if (test_bit(vq - 1, cpu->sve_vq_map)) {
            i = (vq - 1) / 64;
            j = (vq - 1) % 64;
            vls[i] |= 1UL << j;
        }
    }

    return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
}

#define ARM_CPU_ID_MPIDR       3, 0, 0, 0, 5

int kvm_arch_init_vcpu(CPUState *cs)
{
    int ret;
    uint64_t mpidr;
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;

    if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE ||
        !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) {
        error_report("KVM is not supported for this guest CPU type");
        return -EINVAL;
    }

    qemu_add_vm_change_state_handler(kvm_arm_vm_state_change, cs);

    /* Determine init features for this CPU */
    memset(cpu->kvm_init_features, 0, sizeof(cpu->kvm_init_features));
    if (cs->start_powered_off) {
        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_POWER_OFF;
    }
    if (kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PSCI_0_2)) {
        cpu->psci_version = 2;
        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2;
    }
    if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_EL1_32BIT;
    }
    if (!kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PMU_V3)) {
        cpu->has_pmu = false;
    }
    if (cpu->has_pmu) {
        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PMU_V3;
    } else {
        env->features &= ~(1ULL << ARM_FEATURE_PMU);
    }
    if (cpu_isar_feature(aa64_sve, cpu)) {
        assert(kvm_arm_sve_supported());
        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE;
    }

    /* Do KVM_ARM_VCPU_INIT ioctl */
    ret = kvm_arm_vcpu_init(cs);
    if (ret) {
        return ret;
    }

    if (cpu_isar_feature(aa64_sve, cpu)) {
        ret = kvm_arm_sve_set_vls(cs);
        if (ret) {
            return ret;
        }
        ret = kvm_arm_vcpu_finalize(cs, KVM_ARM_VCPU_SVE);
        if (ret) {
            return ret;
        }
    }

    /*
     * When KVM is in use, PSCI is emulated in-kernel and not by qemu.
     * Currently KVM has its own idea about MPIDR assignment, so we
     * override our defaults with what we get from KVM.
     */
    ret = kvm_get_one_reg(cs, ARM64_SYS_REG(ARM_CPU_ID_MPIDR), &mpidr);
    if (ret) {
        return ret;
    }
    cpu->mp_affinity = mpidr & ARM64_AFFINITY_MASK;

    kvm_arm_init_debug(cs);

    /* Check whether user space can specify guest syndrome value */
    kvm_arm_init_serror_injection(cs);

    return kvm_arm_init_cpreg_list(cpu);
}

int kvm_arch_destroy_vcpu(CPUState *cs)
{
    return 0;
}

bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx)
{
    /* Return true if the regidx is a register we should synchronize
     * via the cpreg_tuples array (ie is not a core or sve reg that
     * we sync by hand in kvm_arch_get/put_registers())
     */
    switch (regidx & KVM_REG_ARM_COPROC_MASK) {
    case KVM_REG_ARM_CORE:
    case KVM_REG_ARM64_SVE:
        return false;
    default:
        return true;
    }
}

typedef struct CPRegStateLevel {
    uint64_t regidx;
    int level;
} CPRegStateLevel;

/* All system registers not listed in the following table are assumed to be
 * of the level KVM_PUT_RUNTIME_STATE. If a register should be written less
 * often, you must add it to this table with a state of either
 * KVM_PUT_RESET_STATE or KVM_PUT_FULL_STATE.
 */
static const CPRegStateLevel non_runtime_cpregs[] = {
    { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE },
};

int kvm_arm_cpreg_level(uint64_t regidx)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(non_runtime_cpregs); i++) {
        const CPRegStateLevel *l = &non_runtime_cpregs[i];
        if (l->regidx == regidx) {
            return l->level;
        }
    }

    return KVM_PUT_RUNTIME_STATE;
}

/* Callers must hold the iothread mutex lock */
static void kvm_inject_arm_sea(CPUState *c)
{
    ARMCPU *cpu = ARM_CPU(c);
    CPUARMState *env = &cpu->env;
    uint32_t esr;
    bool same_el;

    c->exception_index = EXCP_DATA_ABORT;
    env->exception.target_el = 1;

    /*
     * Set the DFSC to synchronous external abort and set FnV to not valid,
     * this will tell guest the FAR_ELx is UNKNOWN for this abort.
     */
    same_el = arm_current_el(env) == env->exception.target_el;
    esr = syn_data_abort_no_iss(same_el, 1, 0, 0, 0, 0, 0x10);

    env->exception.syndrome = esr;

    arm_cpu_do_interrupt(c);
}

#define AARCH64_CORE_REG(x)   (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
                 KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))

#define AARCH64_SIMD_CORE_REG(x)   (KVM_REG_ARM64 | KVM_REG_SIZE_U128 | \
                 KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))

#define AARCH64_SIMD_CTRL_REG(x)   (KVM_REG_ARM64 | KVM_REG_SIZE_U32 | \
                 KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))

static int kvm_arch_put_fpsimd(CPUState *cs)
{
    CPUARMState *env = &ARM_CPU(cs)->env;
    struct kvm_one_reg reg;
    int i, ret;

    for (i = 0; i < 32; i++) {
        uint64_t *q = aa64_vfp_qreg(env, i);
#ifdef HOST_WORDS_BIGENDIAN
        uint64_t fp_val[2] = { q[1], q[0] };
        reg.addr = (uintptr_t)fp_val;
#else
        reg.addr = (uintptr_t)q;
#endif
        reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]);
        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    return 0;
}

/*
 * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits
 * and PREGS and the FFR have a slice size of 256 bits. However we simply hard
 * code the slice index to zero for now as it's unlikely we'll need more than
 * one slice for quite some time.
 */
static int kvm_arch_put_sve(CPUState *cs)
{
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;
    uint64_t tmp[ARM_MAX_VQ * 2];
    uint64_t *r;
    struct kvm_one_reg reg;
    int n, ret;

    for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
        r = sve_bswap64(tmp, &env->vfp.zregs[n].d[0], cpu->sve_max_vq * 2);
        reg.addr = (uintptr_t)r;
        reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
        r = sve_bswap64(tmp, r = &env->vfp.pregs[n].p[0],
                        DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
        reg.addr = (uintptr_t)r;
        reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    r = sve_bswap64(tmp, &env->vfp.pregs[FFR_PRED_NUM].p[0],
                    DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
    reg.addr = (uintptr_t)r;
    reg.id = KVM_REG_ARM64_SVE_FFR(0);
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    return 0;
}

int kvm_arch_put_registers(CPUState *cs, int level)
{
    struct kvm_one_reg reg;
    uint64_t val;
    uint32_t fpr;
    int i, ret;
    unsigned int el;

    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;

    /* If we are in AArch32 mode then we need to copy the AArch32 regs to the
     * AArch64 registers before pushing them out to 64-bit KVM.
     */
    if (!is_a64(env)) {
        aarch64_sync_32_to_64(env);
    }

    for (i = 0; i < 31; i++) {
        reg.id = AARCH64_CORE_REG(regs.regs[i]);
        reg.addr = (uintptr_t) &env->xregs[i];
        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    /* KVM puts SP_EL0 in regs.sp and SP_EL1 in regs.sp_el1. On the
     * QEMU side we keep the current SP in xregs[31] as well.
     */
    aarch64_save_sp(env, 1);

    reg.id = AARCH64_CORE_REG(regs.sp);
    reg.addr = (uintptr_t) &env->sp_el[0];
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.id = AARCH64_CORE_REG(sp_el1);
    reg.addr = (uintptr_t) &env->sp_el[1];
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    /* Note that KVM thinks pstate is 64 bit but we use a uint32_t */
    if (is_a64(env)) {
        val = pstate_read(env);
    } else {
        val = cpsr_read(env);
    }
    reg.id = AARCH64_CORE_REG(regs.pstate);
    reg.addr = (uintptr_t) &val;
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.id = AARCH64_CORE_REG(regs.pc);
    reg.addr = (uintptr_t) &env->pc;
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.id = AARCH64_CORE_REG(elr_el1);
    reg.addr = (uintptr_t) &env->elr_el[1];
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    /* Saved Program State Registers
     *
     * Before we restore from the banked_spsr[] array we need to
     * ensure that any modifications to env->spsr are correctly
     * reflected in the banks.
     */
    el = arm_current_el(env);
    if (el > 0 && !is_a64(env)) {
        i = bank_number(env->uncached_cpsr & CPSR_M);
        env->banked_spsr[i] = env->spsr;
    }

    /* KVM 0-4 map to QEMU banks 1-5 */
    for (i = 0; i < KVM_NR_SPSR; i++) {
        reg.id = AARCH64_CORE_REG(spsr[i]);
        reg.addr = (uintptr_t) &env->banked_spsr[i + 1];
        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    if (cpu_isar_feature(aa64_sve, cpu)) {
        ret = kvm_arch_put_sve(cs);
    } else {
        ret = kvm_arch_put_fpsimd(cs);
    }
    if (ret) {
        return ret;
    }

    reg.addr = (uintptr_t)(&fpr);
    fpr = vfp_get_fpsr(env);
    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.addr = (uintptr_t)(&fpr);
    fpr = vfp_get_fpcr(env);
    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    write_cpustate_to_list(cpu, true);

    if (!write_list_to_kvmstate(cpu, level)) {
        return -EINVAL;
    }

   /*
    * Setting VCPU events should be triggered after syncing the registers
    * to avoid overwriting potential changes made by KVM upon calling
    * KVM_SET_VCPU_EVENTS ioctl
    */
    ret = kvm_put_vcpu_events(cpu);
    if (ret) {
        return ret;
    }

    kvm_arm_sync_mpstate_to_kvm(cpu);

    return ret;
}

static int kvm_arch_get_fpsimd(CPUState *cs)
{
    CPUARMState *env = &ARM_CPU(cs)->env;
    struct kvm_one_reg reg;
    int i, ret;

    for (i = 0; i < 32; i++) {
        uint64_t *q = aa64_vfp_qreg(env, i);
        reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]);
        reg.addr = (uintptr_t)q;
        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
        if (ret) {
            return ret;
        } else {
#ifdef HOST_WORDS_BIGENDIAN
            uint64_t t;
            t = q[0], q[0] = q[1], q[1] = t;
#endif
        }
    }

    return 0;
}

/*
 * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits
 * and PREGS and the FFR have a slice size of 256 bits. However we simply hard
 * code the slice index to zero for now as it's unlikely we'll need more than
 * one slice for quite some time.
 */
static int kvm_arch_get_sve(CPUState *cs)
{
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;
    struct kvm_one_reg reg;
    uint64_t *r;
    int n, ret;

    for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
        r = &env->vfp.zregs[n].d[0];
        reg.addr = (uintptr_t)r;
        reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
        sve_bswap64(r, r, cpu->sve_max_vq * 2);
    }

    for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
        r = &env->vfp.pregs[n].p[0];
        reg.addr = (uintptr_t)r;
        reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
        sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
    }

    r = &env->vfp.pregs[FFR_PRED_NUM].p[0];
    reg.addr = (uintptr_t)r;
    reg.id = KVM_REG_ARM64_SVE_FFR(0);
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }
    sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));

    return 0;
}

int kvm_arch_get_registers(CPUState *cs)
{
    struct kvm_one_reg reg;
    uint64_t val;
    unsigned int el;
    uint32_t fpr;
    int i, ret;

    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;

    for (i = 0; i < 31; i++) {
        reg.id = AARCH64_CORE_REG(regs.regs[i]);
        reg.addr = (uintptr_t) &env->xregs[i];
        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    reg.id = AARCH64_CORE_REG(regs.sp);
    reg.addr = (uintptr_t) &env->sp_el[0];
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.id = AARCH64_CORE_REG(sp_el1);
    reg.addr = (uintptr_t) &env->sp_el[1];
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    reg.id = AARCH64_CORE_REG(regs.pstate);
    reg.addr = (uintptr_t) &val;
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    env->aarch64 = ((val & PSTATE_nRW) == 0);
    if (is_a64(env)) {
        pstate_write(env, val);
    } else {
        cpsr_write(env, val, 0xffffffff, CPSRWriteRaw);
    }

    /* KVM puts SP_EL0 in regs.sp and SP_EL1 in regs.sp_el1. On the
     * QEMU side we keep the current SP in xregs[31] as well.
     */
    aarch64_restore_sp(env, 1);

    reg.id = AARCH64_CORE_REG(regs.pc);
    reg.addr = (uintptr_t) &env->pc;
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    /* If we are in AArch32 mode then we need to sync the AArch32 regs with the
     * incoming AArch64 regs received from 64-bit KVM.
     * We must perform this after all of the registers have been acquired from
     * the kernel.
     */
    if (!is_a64(env)) {
        aarch64_sync_64_to_32(env);
    }

    reg.id = AARCH64_CORE_REG(elr_el1);
    reg.addr = (uintptr_t) &env->elr_el[1];
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }

    /* Fetch the SPSR registers
     *
     * KVM SPSRs 0-4 map to QEMU banks 1-5
     */
    for (i = 0; i < KVM_NR_SPSR; i++) {
        reg.id = AARCH64_CORE_REG(spsr[i]);
        reg.addr = (uintptr_t) &env->banked_spsr[i + 1];
        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
        if (ret) {
            return ret;
        }
    }

    el = arm_current_el(env);
    if (el > 0 && !is_a64(env)) {
        i = bank_number(env->uncached_cpsr & CPSR_M);
        env->spsr = env->banked_spsr[i];
    }

    if (cpu_isar_feature(aa64_sve, cpu)) {
        ret = kvm_arch_get_sve(cs);
    } else {
        ret = kvm_arch_get_fpsimd(cs);
    }
    if (ret) {
        return ret;
    }

    reg.addr = (uintptr_t)(&fpr);
    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }
    vfp_set_fpsr(env, fpr);

    reg.addr = (uintptr_t)(&fpr);
    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
    if (ret) {
        return ret;
    }
    vfp_set_fpcr(env, fpr);

    ret = kvm_get_vcpu_events(cpu);
    if (ret) {
        return ret;
    }

    if (!write_kvmstate_to_list(cpu)) {
        return -EINVAL;
    }
    /* Note that it's OK to have registers which aren't in CPUState,
     * so we can ignore a failure return here.
     */
    write_list_to_cpustate(cpu);

    kvm_arm_sync_mpstate_to_qemu(cpu);

    /* TODO: other registers */
    return ret;
}

void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
{
    ram_addr_t ram_addr;
    hwaddr paddr;
    Object *obj = qdev_get_machine();
    VirtMachineState *vms = VIRT_MACHINE(obj);
    bool acpi_enabled = virt_is_acpi_enabled(vms);

    assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);

    if (acpi_enabled && addr &&
            object_property_get_bool(obj, "ras", NULL)) {
        ram_addr = qemu_ram_addr_from_host(addr);
        if (ram_addr != RAM_ADDR_INVALID &&
            kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
            kvm_hwpoison_page_add(ram_addr);
            /*
             * If this is a BUS_MCEERR_AR, we know we have been called
             * synchronously from the vCPU thread, so we can easily
             * synchronize the state and inject an error.
             *
             * TODO: we currently don't tell the guest at all about
             * BUS_MCEERR_AO. In that case we might either be being
             * called synchronously from the vCPU thread, or a bit
             * later from the main thread, so doing the injection of
             * the error would be more complicated.
             */
            if (code == BUS_MCEERR_AR) {
                kvm_cpu_synchronize_state(c);
                if (!acpi_ghes_record_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
                    kvm_inject_arm_sea(c);
                } else {
                    error_report("failed to record the error");
                    abort();
                }
            }
            return;
        }
        if (code == BUS_MCEERR_AO) {
            error_report("Hardware memory error at addr %p for memory used by "
                "QEMU itself instead of guest system!", addr);
        }
    }

    if (code == BUS_MCEERR_AR) {
        error_report("Hardware memory error!");
        exit(1);
    }
}

/* C6.6.29 BRK instruction */
static const uint32_t brk_insn = 0xd4200000;

int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{
    if (have_guest_debug) {
        if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, 4, 0) ||
            cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&brk_insn, 4, 1)) {
            return -EINVAL;
        }
        return 0;
    } else {
        error_report("guest debug not supported on this kernel");
        return -EINVAL;
    }
}

int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{
    static uint32_t brk;

    if (have_guest_debug) {
        if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&brk, 4, 0) ||
            brk != brk_insn ||
            cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, 4, 1)) {
            return -EINVAL;
        }
        return 0;
    } else {
        error_report("guest debug not supported on this kernel");
        return -EINVAL;
    }
}

/* See v8 ARM ARM D7.2.27 ESR_ELx, Exception Syndrome Register
 *
 * To minimise translating between kernel and user-space the kernel
 * ABI just provides user-space with the full exception syndrome
 * register value to be decoded in QEMU.
 */

bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit)
{
    int hsr_ec = syn_get_ec(debug_exit->hsr);
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;

    /* Ensure PC is synchronised */
    kvm_cpu_synchronize_state(cs);

    switch (hsr_ec) {
    case EC_SOFTWARESTEP:
        if (cs->singlestep_enabled) {
            return true;
        } else {
            /*
             * The kernel should have suppressed the guest's ability to
             * single step at this point so something has gone wrong.
             */
            error_report("%s: guest single-step while debugging unsupported"
                         " (%"PRIx64", %"PRIx32")",
                         __func__, env->pc, debug_exit->hsr);
            return false;
        }
        break;
    case EC_AA64_BKPT:
        if (kvm_find_sw_breakpoint(cs, env->pc)) {
            return true;
        }
        break;
    case EC_BREAKPOINT:
        if (find_hw_breakpoint(cs, env->pc)) {
            return true;
        }
        break;
    case EC_WATCHPOINT:
    {
        CPUWatchpoint *wp = find_hw_watchpoint(cs, debug_exit->far);
        if (wp) {
            cs->watchpoint_hit = wp;
            return true;
        }
        break;
    }
    default:
        error_report("%s: unhandled debug exit (%"PRIx32", %"PRIx64")",
                     __func__, debug_exit->hsr, env->pc);
    }

    /* If we are not handling the debug exception it must belong to
     * the guest. Let's re-use the existing TCG interrupt code to set
     * everything up properly.
     */
    cs->exception_index = EXCP_BKPT;
    env->exception.syndrome = debug_exit->hsr;
    env->exception.vaddress = debug_exit->far;
    env->exception.target_el = 1;
    qemu_mutex_lock_iothread();
    arm_cpu_do_interrupt(cs);
    qemu_mutex_unlock_iothread();

    return false;
}

#define ARM64_REG_ESR_EL1 ARM64_SYS_REG(3, 0, 5, 2, 0)
#define ARM64_REG_TCR_EL1 ARM64_SYS_REG(3, 0, 2, 0, 2)

/*
 * ESR_EL1
 * ISS encoding
 * AARCH64: DFSC,   bits [5:0]
 * AARCH32:
 *      TTBCR.EAE == 0
 *          FS[4]   - DFSR[10]
 *          FS[3:0] - DFSR[3:0]
 *      TTBCR.EAE == 1
 *          FS, bits [5:0]
 */
#define ESR_DFSC(aarch64, lpae, v)        \
    ((aarch64 || (lpae)) ? ((v) & 0x3F)   \
               : (((v) >> 6) | ((v) & 0x1F)))

#define ESR_DFSC_EXTABT(aarch64, lpae) \
    ((aarch64) ? 0x10 : (lpae) ? 0x10 : 0x8)

bool kvm_arm_verify_ext_dabt_pending(CPUState *cs)
{
    uint64_t dfsr_val;

    if (!kvm_get_one_reg(cs, ARM64_REG_ESR_EL1, &dfsr_val)) {
        ARMCPU *cpu = ARM_CPU(cs);
        CPUARMState *env = &cpu->env;
        int aarch64_mode = arm_feature(env, ARM_FEATURE_AARCH64);
        int lpae = 0;

        if (!aarch64_mode) {
            uint64_t ttbcr;

            if (!kvm_get_one_reg(cs, ARM64_REG_TCR_EL1, &ttbcr)) {
                lpae = arm_feature(env, ARM_FEATURE_LPAE)
                        && (ttbcr & TTBCR_EAE);
            }
        }
        /*
         * The verification here is based on the DFSC bits
         * of the ESR_EL1 reg only
         */
         return (ESR_DFSC(aarch64_mode, lpae, dfsr_val) ==
                ESR_DFSC_EXTABT(aarch64_mode, lpae));
    }
    return false;
}