aboutsummaryrefslogtreecommitdiff
path: root/xen-hvm.c
blob: 5043beb98f9785d450366a89415c8149a0d33de9 (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
/*
 * Copyright (C) 2010       Citrix Ltd.
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "qemu/osdep.h"

#include "cpu.h"
#include "hw/pci/pci.h"
#include "hw/i386/pc.h"
#include "hw/i386/apic-msidef.h"
#include "hw/xen/xen_common.h"
#include "hw/xen/xen_backend.h"
#include "qmp-commands.h"

#include "sysemu/char.h"
#include "qemu/error-report.h"
#include "qemu/range.h"
#include "sysemu/xen-mapcache.h"
#include "trace-root.h"
#include "exec/address-spaces.h"

#include <xen/hvm/ioreq.h>
#include <xen/hvm/params.h>
#include <xen/hvm/e820.h>

//#define DEBUG_XEN_HVM

#ifdef DEBUG_XEN_HVM
#define DPRINTF(fmt, ...) \
    do { fprintf(stderr, "xen: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

static MemoryRegion ram_memory, ram_640k, ram_lo, ram_hi;
static MemoryRegion *framebuffer;
static bool xen_in_migration;

/* Compatibility with older version */

/* This allows QEMU to build on a system that has Xen 4.5 or earlier
 * installed.  This here (not in hw/xen/xen_common.h) because xen/hvm/ioreq.h
 * needs to be included before this block and hw/xen/xen_common.h needs to
 * be included before xen/hvm/ioreq.h
 */
#ifndef IOREQ_TYPE_VMWARE_PORT
#define IOREQ_TYPE_VMWARE_PORT  3
struct vmware_regs {
    uint32_t esi;
    uint32_t edi;
    uint32_t ebx;
    uint32_t ecx;
    uint32_t edx;
};
typedef struct vmware_regs vmware_regs_t;

struct shared_vmport_iopage {
    struct vmware_regs vcpu_vmport_regs[1];
};
typedef struct shared_vmport_iopage shared_vmport_iopage_t;
#endif

static inline uint32_t xen_vcpu_eport(shared_iopage_t *shared_page, int i)
{
    return shared_page->vcpu_ioreq[i].vp_eport;
}
static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu)
{
    return &shared_page->vcpu_ioreq[vcpu];
}

#define BUFFER_IO_MAX_DELAY  100

typedef struct XenPhysmap {
    hwaddr start_addr;
    ram_addr_t size;
    const char *name;
    hwaddr phys_offset;

    QLIST_ENTRY(XenPhysmap) list;
} XenPhysmap;

typedef struct XenIOState {
    ioservid_t ioservid;
    shared_iopage_t *shared_page;
    shared_vmport_iopage_t *shared_vmport_page;
    buffered_iopage_t *buffered_io_page;
    QEMUTimer *buffered_io_timer;
    CPUState **cpu_by_vcpu_id;
    /* the evtchn port for polling the notification, */
    evtchn_port_t *ioreq_local_port;
    /* evtchn local port for buffered io */
    evtchn_port_t bufioreq_local_port;
    /* the evtchn fd for polling */
    xenevtchn_handle *xce_handle;
    /* which vcpu we are serving */
    int send_vcpu;

    struct xs_handle *xenstore;
    MemoryListener memory_listener;
    MemoryListener io_listener;
    DeviceListener device_listener;
    QLIST_HEAD(, XenPhysmap) physmap;
    hwaddr free_phys_offset;
    const XenPhysmap *log_for_dirtybit;

    Notifier exit;
    Notifier suspend;
    Notifier wakeup;
} XenIOState;

/* Xen specific function for piix pci */

int xen_pci_slot_get_pirq(PCIDevice *pci_dev, int irq_num)
{
    return irq_num + ((pci_dev->devfn >> 3) << 2);
}

void xen_piix3_set_irq(void *opaque, int irq_num, int level)
{
    xc_hvm_set_pci_intx_level(xen_xc, xen_domid, 0, 0, irq_num >> 2,
                              irq_num & 3, level);
}

void xen_piix_pci_write_config_client(uint32_t address, uint32_t val, int len)
{
    int i;

    /* Scan for updates to PCI link routes (0x60-0x63). */
    for (i = 0; i < len; i++) {
        uint8_t v = (val >> (8 * i)) & 0xff;
        if (v & 0x80) {
            v = 0;
        }
        v &= 0xf;
        if (((address + i) >= 0x60) && ((address + i) <= 0x63)) {
            xc_hvm_set_pci_link_route(xen_xc, xen_domid, address + i - 0x60, v);
        }
    }
}

int xen_is_pirq_msi(uint32_t msi_data)
{
    /* If vector is 0, the msi is remapped into a pirq, passed as
     * dest_id.
     */
    return ((msi_data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT) == 0;
}

void xen_hvm_inject_msi(uint64_t addr, uint32_t data)
{
    xc_hvm_inject_msi(xen_xc, xen_domid, addr, data);
}

static void xen_suspend_notifier(Notifier *notifier, void *data)
{
    xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 3);
}

/* Xen Interrupt Controller */

static void xen_set_irq(void *opaque, int irq, int level)
{
    xc_hvm_set_isa_irq_level(xen_xc, xen_domid, irq, level);
}

qemu_irq *xen_interrupt_controller_init(void)
{
    return qemu_allocate_irqs(xen_set_irq, NULL, 16);
}

/* Memory Ops */

static void xen_ram_init(PCMachineState *pcms,
                         ram_addr_t ram_size, MemoryRegion **ram_memory_p)
{
    MemoryRegion *sysmem = get_system_memory();
    ram_addr_t block_len;
    uint64_t user_lowmem = object_property_get_int(qdev_get_machine(),
                                                   PC_MACHINE_MAX_RAM_BELOW_4G,
                                                   &error_abort);

    /* Handle the machine opt max-ram-below-4g.  It is basically doing
     * min(xen limit, user limit).
     */
    if (!user_lowmem) {
        user_lowmem = HVM_BELOW_4G_RAM_END; /* default */
    }
    if (HVM_BELOW_4G_RAM_END <= user_lowmem) {
        user_lowmem = HVM_BELOW_4G_RAM_END;
    }

    if (ram_size >= user_lowmem) {
        pcms->above_4g_mem_size = ram_size - user_lowmem;
        pcms->below_4g_mem_size = user_lowmem;
    } else {
        pcms->above_4g_mem_size = 0;
        pcms->below_4g_mem_size = ram_size;
    }
    if (!pcms->above_4g_mem_size) {
        block_len = ram_size;
    } else {
        /*
         * Xen does not allocate the memory continuously, it keeps a
         * hole of the size computed above or passed in.
         */
        block_len = (1ULL << 32) + pcms->above_4g_mem_size;
    }
    memory_region_init_ram(&ram_memory, NULL, "xen.ram", block_len,
                           &error_fatal);
    *ram_memory_p = &ram_memory;
    vmstate_register_ram_global(&ram_memory);

    memory_region_init_alias(&ram_640k, NULL, "xen.ram.640k",
                             &ram_memory, 0, 0xa0000);
    memory_region_add_subregion(sysmem, 0, &ram_640k);
    /* Skip of the VGA IO memory space, it will be registered later by the VGA
     * emulated device.
     *
     * The area between 0xc0000 and 0x100000 will be used by SeaBIOS to load
     * the Options ROM, so it is registered here as RAM.
     */
    memory_region_init_alias(&ram_lo, NULL, "xen.ram.lo",
                             &ram_memory, 0xc0000,
                             pcms->below_4g_mem_size - 0xc0000);
    memory_region_add_subregion(sysmem, 0xc0000, &ram_lo);
    if (pcms->above_4g_mem_size > 0) {
        memory_region_init_alias(&ram_hi, NULL, "xen.ram.hi",
                                 &ram_memory, 0x100000000ULL,
                                 pcms->above_4g_mem_size);
        memory_region_add_subregion(sysmem, 0x100000000ULL, &ram_hi);
    }
}

void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, MemoryRegion *mr,
                   Error **errp)
{
    unsigned long nr_pfn;
    xen_pfn_t *pfn_list;
    int i;

    if (runstate_check(RUN_STATE_INMIGRATE)) {
        /* RAM already populated in Xen */
        fprintf(stderr, "%s: do not alloc "RAM_ADDR_FMT
                " bytes of ram at "RAM_ADDR_FMT" when runstate is INMIGRATE\n",
                __func__, size, ram_addr); 
        return;
    }

    if (mr == &ram_memory) {
        return;
    }

    trace_xen_ram_alloc(ram_addr, size);

    nr_pfn = size >> TARGET_PAGE_BITS;
    pfn_list = g_malloc(sizeof (*pfn_list) * nr_pfn);

    for (i = 0; i < nr_pfn; i++) {
        pfn_list[i] = (ram_addr >> TARGET_PAGE_BITS) + i;
    }

    if (xc_domain_populate_physmap_exact(xen_xc, xen_domid, nr_pfn, 0, 0, pfn_list)) {
        error_setg(errp, "xen: failed to populate ram at " RAM_ADDR_FMT,
                   ram_addr);
    }

    g_free(pfn_list);
}

static XenPhysmap *get_physmapping(XenIOState *state,
                                   hwaddr start_addr, ram_addr_t size)
{
    XenPhysmap *physmap = NULL;

    start_addr &= TARGET_PAGE_MASK;

    QLIST_FOREACH(physmap, &state->physmap, list) {
        if (range_covers_byte(physmap->start_addr, physmap->size, start_addr)) {
            return physmap;
        }
    }
    return NULL;
}

static hwaddr xen_phys_offset_to_gaddr(hwaddr start_addr,
                                                   ram_addr_t size, void *opaque)
{
    hwaddr addr = start_addr & TARGET_PAGE_MASK;
    XenIOState *xen_io_state = opaque;
    XenPhysmap *physmap = NULL;

    QLIST_FOREACH(physmap, &xen_io_state->physmap, list) {
        if (range_covers_byte(physmap->phys_offset, physmap->size, addr)) {
            return physmap->start_addr;
        }
    }

    return start_addr;
}

static int xen_add_to_physmap(XenIOState *state,
                              hwaddr start_addr,
                              ram_addr_t size,
                              MemoryRegion *mr,
                              hwaddr offset_within_region)
{
    unsigned long i = 0;
    int rc = 0;
    XenPhysmap *physmap = NULL;
    hwaddr pfn, start_gpfn;
    hwaddr phys_offset = memory_region_get_ram_addr(mr);
    char path[80], value[17];
    const char *mr_name;

    if (get_physmapping(state, start_addr, size)) {
        return 0;
    }
    if (size <= 0) {
        return -1;
    }

    /* Xen can only handle a single dirty log region for now and we want
     * the linear framebuffer to be that region.
     * Avoid tracking any regions that is not videoram and avoid tracking
     * the legacy vga region. */
    if (mr == framebuffer && start_addr > 0xbffff) {
        goto go_physmap;
    }
    return -1;

go_physmap:
    DPRINTF("mapping vram to %"HWADDR_PRIx" - %"HWADDR_PRIx"\n",
            start_addr, start_addr + size);

    pfn = phys_offset >> TARGET_PAGE_BITS;
    start_gpfn = start_addr >> TARGET_PAGE_BITS;
    for (i = 0; i < size >> TARGET_PAGE_BITS; i++) {
        unsigned long idx = pfn + i;
        xen_pfn_t gpfn = start_gpfn + i;

        rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
        if (rc) {
            DPRINTF("add_to_physmap MFN %"PRI_xen_pfn" to PFN %"
                    PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno);
            return -rc;
        }
    }

    mr_name = memory_region_name(mr);

    physmap = g_malloc(sizeof (XenPhysmap));

    physmap->start_addr = start_addr;
    physmap->size = size;
    physmap->name = mr_name;
    physmap->phys_offset = phys_offset;

    QLIST_INSERT_HEAD(&state->physmap, physmap, list);

    xc_domain_pin_memory_cacheattr(xen_xc, xen_domid,
                                   start_addr >> TARGET_PAGE_BITS,
                                   (start_addr + size - 1) >> TARGET_PAGE_BITS,
                                   XEN_DOMCTL_MEM_CACHEATTR_WB);

    snprintf(path, sizeof(path),
            "/local/domain/0/device-model/%d/physmap/%"PRIx64"/start_addr",
            xen_domid, (uint64_t)phys_offset);
    snprintf(value, sizeof(value), "%"PRIx64, (uint64_t)start_addr);
    if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
        return -1;
    }
    snprintf(path, sizeof(path),
            "/local/domain/0/device-model/%d/physmap/%"PRIx64"/size",
            xen_domid, (uint64_t)phys_offset);
    snprintf(value, sizeof(value), "%"PRIx64, (uint64_t)size);
    if (!xs_write(state->xenstore, 0, path, value, strlen(value))) {
        return -1;
    }
    if (mr_name) {
        snprintf(path, sizeof(path),
                "/local/domain/0/device-model/%d/physmap/%"PRIx64"/name",
                xen_domid, (uint64_t)phys_offset);
        if (!xs_write(state->xenstore, 0, path, mr_name, strlen(mr_name))) {
            return -1;
        }
    }

    return 0;
}

static int xen_remove_from_physmap(XenIOState *state,
                                   hwaddr start_addr,
                                   ram_addr_t size)
{
    unsigned long i = 0;
    int rc = 0;
    XenPhysmap *physmap = NULL;
    hwaddr phys_offset = 0;

    physmap = get_physmapping(state, start_addr, size);
    if (physmap == NULL) {
        return -1;
    }

    phys_offset = physmap->phys_offset;
    size = physmap->size;

    DPRINTF("unmapping vram to %"HWADDR_PRIx" - %"HWADDR_PRIx", at "
            "%"HWADDR_PRIx"\n", start_addr, start_addr + size, phys_offset);

    size >>= TARGET_PAGE_BITS;
    start_addr >>= TARGET_PAGE_BITS;
    phys_offset >>= TARGET_PAGE_BITS;
    for (i = 0; i < size; i++) {
        xen_pfn_t idx = start_addr + i;
        xen_pfn_t gpfn = phys_offset + i;

        rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
        if (rc) {
            fprintf(stderr, "add_to_physmap MFN %"PRI_xen_pfn" to PFN %"
                    PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno);
            return -rc;
        }
    }

    QLIST_REMOVE(physmap, list);
    if (state->log_for_dirtybit == physmap) {
        state->log_for_dirtybit = NULL;
    }
    g_free(physmap);

    return 0;
}

static void xen_set_memory(struct MemoryListener *listener,
                           MemoryRegionSection *section,
                           bool add)
{
    XenIOState *state = container_of(listener, XenIOState, memory_listener);
    hwaddr start_addr = section->offset_within_address_space;
    ram_addr_t size = int128_get64(section->size);
    bool log_dirty = memory_region_is_logging(section->mr, DIRTY_MEMORY_VGA);
    hvmmem_type_t mem_type;

    if (section->mr == &ram_memory) {
        return;
    } else {
        if (add) {
            xen_map_memory_section(xen_xc, xen_domid, state->ioservid,
                                   section);
        } else {
            xen_unmap_memory_section(xen_xc, xen_domid, state->ioservid,
                                     section);
        }
    }

    if (!memory_region_is_ram(section->mr)) {
        return;
    }

    if (log_dirty != add) {
        return;
    }

    trace_xen_client_set_memory(start_addr, size, log_dirty);

    start_addr &= TARGET_PAGE_MASK;
    size = TARGET_PAGE_ALIGN(size);

    if (add) {
        if (!memory_region_is_rom(section->mr)) {
            xen_add_to_physmap(state, start_addr, size,
                               section->mr, section->offset_within_region);
        } else {
            mem_type = HVMMEM_ram_ro;
            if (xc_hvm_set_mem_type(xen_xc, xen_domid, mem_type,
                                    start_addr >> TARGET_PAGE_BITS,
                                    size >> TARGET_PAGE_BITS)) {
                DPRINTF("xc_hvm_set_mem_type error, addr: "TARGET_FMT_plx"\n",
                        start_addr);
            }
        }
    } else {
        if (xen_remove_from_physmap(state, start_addr, size) < 0) {
            DPRINTF("physmapping does not exist at "TARGET_FMT_plx"\n", start_addr);
        }
    }
}

static void xen_region_add(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    memory_region_ref(section->mr);
    xen_set_memory(listener, section, true);
}

static void xen_region_del(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    xen_set_memory(listener, section, false);
    memory_region_unref(section->mr);
}

static void xen_io_add(MemoryListener *listener,
                       MemoryRegionSection *section)
{
    XenIOState *state = container_of(listener, XenIOState, io_listener);
    MemoryRegion *mr = section->mr;

    if (mr->ops == &unassigned_io_ops) {
        return;
    }

    memory_region_ref(mr);

    xen_map_io_section(xen_xc, xen_domid, state->ioservid, section);
}

static void xen_io_del(MemoryListener *listener,
                       MemoryRegionSection *section)
{
    XenIOState *state = container_of(listener, XenIOState, io_listener);
    MemoryRegion *mr = section->mr;

    if (mr->ops == &unassigned_io_ops) {
        return;
    }

    xen_unmap_io_section(xen_xc, xen_domid, state->ioservid, section);

    memory_region_unref(mr);
}

static void xen_device_realize(DeviceListener *listener,
			       DeviceState *dev)
{
    XenIOState *state = container_of(listener, XenIOState, device_listener);

    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
        PCIDevice *pci_dev = PCI_DEVICE(dev);

        xen_map_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev);
    }
}

static void xen_device_unrealize(DeviceListener *listener,
				 DeviceState *dev)
{
    XenIOState *state = container_of(listener, XenIOState, device_listener);

    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
        PCIDevice *pci_dev = PCI_DEVICE(dev);

        xen_unmap_pcidev(xen_xc, xen_domid, state->ioservid, pci_dev);
    }
}

static void xen_sync_dirty_bitmap(XenIOState *state,
                                  hwaddr start_addr,
                                  ram_addr_t size)
{
    hwaddr npages = size >> TARGET_PAGE_BITS;
    const int width = sizeof(unsigned long) * 8;
    unsigned long bitmap[DIV_ROUND_UP(npages, width)];
    int rc, i, j;
    const XenPhysmap *physmap = NULL;

    physmap = get_physmapping(state, start_addr, size);
    if (physmap == NULL) {
        /* not handled */
        return;
    }

    if (state->log_for_dirtybit == NULL) {
        state->log_for_dirtybit = physmap;
    } else if (state->log_for_dirtybit != physmap) {
        /* Only one range for dirty bitmap can be tracked. */
        return;
    }

    rc = xc_hvm_track_dirty_vram(xen_xc, xen_domid,
                                 start_addr >> TARGET_PAGE_BITS, npages,
                                 bitmap);
    if (rc < 0) {
#ifndef ENODATA
#define ENODATA  ENOENT
#endif
        if (errno == ENODATA) {
            memory_region_set_dirty(framebuffer, 0, size);
            DPRINTF("xen: track_dirty_vram failed (0x" TARGET_FMT_plx
                    ", 0x" TARGET_FMT_plx "): %s\n",
                    start_addr, start_addr + size, strerror(errno));
        }
        return;
    }

    for (i = 0; i < ARRAY_SIZE(bitmap); i++) {
        unsigned long map = bitmap[i];
        while (map != 0) {
            j = ctzl(map);
            map &= ~(1ul << j);
            memory_region_set_dirty(framebuffer,
                                    (i * width + j) * TARGET_PAGE_SIZE,
                                    TARGET_PAGE_SIZE);
        };
    }
}

static void xen_log_start(MemoryListener *listener,
                          MemoryRegionSection *section,
                          int old, int new)
{
    XenIOState *state = container_of(listener, XenIOState, memory_listener);

    if (new & ~old & (1 << DIRTY_MEMORY_VGA)) {
        xen_sync_dirty_bitmap(state, section->offset_within_address_space,
                              int128_get64(section->size));
    }
}

static void xen_log_stop(MemoryListener *listener, MemoryRegionSection *section,
                         int old, int new)
{
    XenIOState *state = container_of(listener, XenIOState, memory_listener);

    if (old & ~new & (1 << DIRTY_MEMORY_VGA)) {
        state->log_for_dirtybit = NULL;
        /* Disable dirty bit tracking */
        xc_hvm_track_dirty_vram(xen_xc, xen_domid, 0, 0, NULL);
    }
}

static void xen_log_sync(MemoryListener *listener, MemoryRegionSection *section)
{
    XenIOState *state = container_of(listener, XenIOState, memory_listener);

    xen_sync_dirty_bitmap(state, section->offset_within_address_space,
                          int128_get64(section->size));
}

static void xen_log_global_start(MemoryListener *listener)
{
    if (xen_enabled()) {
        xen_in_migration = true;
    }
}

static void xen_log_global_stop(MemoryListener *listener)
{
    xen_in_migration = false;
}

static MemoryListener xen_memory_listener = {
    .region_add = xen_region_add,
    .region_del = xen_region_del,
    .log_start = xen_log_start,
    .log_stop = xen_log_stop,
    .log_sync = xen_log_sync,
    .log_global_start = xen_log_global_start,
    .log_global_stop = xen_log_global_stop,
    .priority = 10,
};

static MemoryListener xen_io_listener = {
    .region_add = xen_io_add,
    .region_del = xen_io_del,
    .priority = 10,
};

static DeviceListener xen_device_listener = {
    .realize = xen_device_realize,
    .unrealize = xen_device_unrealize,
};

/* get the ioreq packets from share mem */
static ioreq_t *cpu_get_ioreq_from_shared_memory(XenIOState *state, int vcpu)
{
    ioreq_t *req = xen_vcpu_ioreq(state->shared_page, vcpu);

    if (req->state != STATE_IOREQ_READY) {
        DPRINTF("I/O request not ready: "
                "%x, ptr: %x, port: %"PRIx64", "
                "data: %"PRIx64", count: %u, size: %u\n",
                req->state, req->data_is_ptr, req->addr,
                req->data, req->count, req->size);
        return NULL;
    }

    xen_rmb(); /* see IOREQ_READY /then/ read contents of ioreq */

    req->state = STATE_IOREQ_INPROCESS;
    return req;
}

/* use poll to get the port notification */
/* ioreq_vec--out,the */
/* retval--the number of ioreq packet */
static ioreq_t *cpu_get_ioreq(XenIOState *state)
{
    int i;
    evtchn_port_t port;

    port = xenevtchn_pending(state->xce_handle);
    if (port == state->bufioreq_local_port) {
        timer_mod(state->buffered_io_timer,
                BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME));
        return NULL;
    }

    if (port != -1) {
        for (i = 0; i < max_cpus; i++) {
            if (state->ioreq_local_port[i] == port) {
                break;
            }
        }

        if (i == max_cpus) {
            hw_error("Fatal error while trying to get io event!\n");
        }

        /* unmask the wanted port again */
        xenevtchn_unmask(state->xce_handle, port);

        /* get the io packet from shared memory */
        state->send_vcpu = i;
        return cpu_get_ioreq_from_shared_memory(state, i);
    }

    /* read error or read nothing */
    return NULL;
}

static uint32_t do_inp(uint32_t addr, unsigned long size)
{
    switch (size) {
        case 1:
            return cpu_inb(addr);
        case 2:
            return cpu_inw(addr);
        case 4:
            return cpu_inl(addr);
        default:
            hw_error("inp: bad size: %04x %lx", addr, size);
    }
}

static void do_outp(uint32_t addr,
        unsigned long size, uint32_t val)
{
    switch (size) {
        case 1:
            return cpu_outb(addr, val);
        case 2:
            return cpu_outw(addr, val);
        case 4:
            return cpu_outl(addr, val);
        default:
            hw_error("outp: bad size: %04x %lx", addr, size);
    }
}

/*
 * Helper functions which read/write an object from/to physical guest
 * memory, as part of the implementation of an ioreq.
 *
 * Equivalent to
 *   cpu_physical_memory_rw(addr + (req->df ? -1 : +1) * req->size * i,
 *                          val, req->size, 0/1)
 * except without the integer overflow problems.
 */
static void rw_phys_req_item(hwaddr addr,
                             ioreq_t *req, uint32_t i, void *val, int rw)
{
    /* Do everything unsigned so overflow just results in a truncated result
     * and accesses to undesired parts of guest memory, which is up
     * to the guest */
    hwaddr offset = (hwaddr)req->size * i;
    if (req->df) {
        addr -= offset;
    } else {
        addr += offset;
    }
    cpu_physical_memory_rw(addr, val, req->size, rw);
}

static inline void read_phys_req_item(hwaddr addr,
                                      ioreq_t *req, uint32_t i, void *val)
{
    rw_phys_req_item(addr, req, i, val, 0);
}
static inline void write_phys_req_item(hwaddr addr,
                                       ioreq_t *req, uint32_t i, void *val)
{
    rw_phys_req_item(addr, req, i, val, 1);
}


static void cpu_ioreq_pio(ioreq_t *req)
{
    uint32_t i;

    trace_cpu_ioreq_pio(req, req->dir, req->df, req->data_is_ptr, req->addr,
                         req->data, req->count, req->size);

    if (req->size > sizeof(uint32_t)) {
        hw_error("PIO: bad size (%u)", req->size);
    }

    if (req->dir == IOREQ_READ) {
        if (!req->data_is_ptr) {
            req->data = do_inp(req->addr, req->size);
            trace_cpu_ioreq_pio_read_reg(req, req->data, req->addr,
                                         req->size);
        } else {
            uint32_t tmp;

            for (i = 0; i < req->count; i++) {
                tmp = do_inp(req->addr, req->size);
                write_phys_req_item(req->data, req, i, &tmp);
            }
        }
    } else if (req->dir == IOREQ_WRITE) {
        if (!req->data_is_ptr) {
            trace_cpu_ioreq_pio_write_reg(req, req->data, req->addr,
                                          req->size);
            do_outp(req->addr, req->size, req->data);
        } else {
            for (i = 0; i < req->count; i++) {
                uint32_t tmp = 0;

                read_phys_req_item(req->data, req, i, &tmp);
                do_outp(req->addr, req->size, tmp);
            }
        }
    }
}

static void cpu_ioreq_move(ioreq_t *req)
{
    uint32_t i;

    trace_cpu_ioreq_move(req, req->dir, req->df, req->data_is_ptr, req->addr,
                         req->data, req->count, req->size);

    if (req->size > sizeof(req->data)) {
        hw_error("MMIO: bad size (%u)", req->size);
    }

    if (!req->data_is_ptr) {
        if (req->dir == IOREQ_READ) {
            for (i = 0; i < req->count; i++) {
                read_phys_req_item(req->addr, req, i, &req->data);
            }
        } else if (req->dir == IOREQ_WRITE) {
            for (i = 0; i < req->count; i++) {
                write_phys_req_item(req->addr, req, i, &req->data);
            }
        }
    } else {
        uint64_t tmp;

        if (req->dir == IOREQ_READ) {
            for (i = 0; i < req->count; i++) {
                read_phys_req_item(req->addr, req, i, &tmp);
                write_phys_req_item(req->data, req, i, &tmp);
            }
        } else if (req->dir == IOREQ_WRITE) {
            for (i = 0; i < req->count; i++) {
                read_phys_req_item(req->data, req, i, &tmp);
                write_phys_req_item(req->addr, req, i, &tmp);
            }
        }
    }
}

static void regs_to_cpu(vmware_regs_t *vmport_regs, ioreq_t *req)
{
    X86CPU *cpu;
    CPUX86State *env;

    cpu = X86_CPU(current_cpu);
    env = &cpu->env;
    env->regs[R_EAX] = req->data;
    env->regs[R_EBX] = vmport_regs->ebx;
    env->regs[R_ECX] = vmport_regs->ecx;
    env->regs[R_EDX] = vmport_regs->edx;
    env->regs[R_ESI] = vmport_regs->esi;
    env->regs[R_EDI] = vmport_regs->edi;
}

static void regs_from_cpu(vmware_regs_t *vmport_regs)
{
    X86CPU *cpu = X86_CPU(current_cpu);
    CPUX86State *env = &cpu->env;

    vmport_regs->ebx = env->regs[R_EBX];
    vmport_regs->ecx = env->regs[R_ECX];
    vmport_regs->edx = env->regs[R_EDX];
    vmport_regs->esi = env->regs[R_ESI];
    vmport_regs->edi = env->regs[R_EDI];
}

static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req)
{
    vmware_regs_t *vmport_regs;

    assert(state->shared_vmport_page);
    vmport_regs =
        &state->shared_vmport_page->vcpu_vmport_regs[state->send_vcpu];
    QEMU_BUILD_BUG_ON(sizeof(*req) < sizeof(*vmport_regs));

    current_cpu = state->cpu_by_vcpu_id[state->send_vcpu];
    regs_to_cpu(vmport_regs, req);
    cpu_ioreq_pio(req);
    regs_from_cpu(vmport_regs);
    current_cpu = NULL;
}

static void handle_ioreq(XenIOState *state, ioreq_t *req)
{
    trace_handle_ioreq(req, req->type, req->dir, req->df, req->data_is_ptr,
                       req->addr, req->data, req->count, req->size);

    if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) &&
            (req->size < sizeof (target_ulong))) {
        req->data &= ((target_ulong) 1 << (8 * req->size)) - 1;
    }

    if (req->dir == IOREQ_WRITE)
        trace_handle_ioreq_write(req, req->type, req->df, req->data_is_ptr,
                                 req->addr, req->data, req->count, req->size);

    switch (req->type) {
        case IOREQ_TYPE_PIO:
            cpu_ioreq_pio(req);
            break;
        case IOREQ_TYPE_COPY:
            cpu_ioreq_move(req);
            break;
        case IOREQ_TYPE_VMWARE_PORT:
            handle_vmport_ioreq(state, req);
            break;
        case IOREQ_TYPE_TIMEOFFSET:
            break;
        case IOREQ_TYPE_INVALIDATE:
            xen_invalidate_map_cache();
            break;
        case IOREQ_TYPE_PCI_CONFIG: {
            uint32_t sbdf = req->addr >> 32;
            uint32_t val;

            /* Fake a write to port 0xCF8 so that
             * the config space access will target the
             * correct device model.
             */
            val = (1u << 31) |
                  ((req->addr & 0x0f00) << 16) |
                  ((sbdf & 0xffff) << 8) |
                  (req->addr & 0xfc);
            do_outp(0xcf8, 4, val);

            /* Now issue the config space access via
             * port 0xCFC
             */
            req->addr = 0xcfc | (req->addr & 0x03);
            cpu_ioreq_pio(req);
            break;
        }
        default:
            hw_error("Invalid ioreq type 0x%x\n", req->type);
    }
    if (req->dir == IOREQ_READ) {
        trace_handle_ioreq_read(req, req->type, req->df, req->data_is_ptr,
                                req->addr, req->data, req->count, req->size);
    }
}

static int handle_buffered_iopage(XenIOState *state)
{
    buffered_iopage_t *buf_page = state->buffered_io_page;
    buf_ioreq_t *buf_req = NULL;
    ioreq_t req;
    int qw;

    if (!buf_page) {
        return 0;
    }

    memset(&req, 0x00, sizeof(req));
    req.state = STATE_IOREQ_READY;
    req.count = 1;
    req.dir = IOREQ_WRITE;

    for (;;) {
        uint32_t rdptr = buf_page->read_pointer, wrptr;

        xen_rmb();
        wrptr = buf_page->write_pointer;
        xen_rmb();
        if (rdptr != buf_page->read_pointer) {
            continue;
        }
        if (rdptr == wrptr) {
            break;
        }
        buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM];
        req.size = 1U << buf_req->size;
        req.addr = buf_req->addr;
        req.data = buf_req->data;
        req.type = buf_req->type;
        xen_rmb();
        qw = (req.size == 8);
        if (qw) {
            if (rdptr + 1 == wrptr) {
                hw_error("Incomplete quad word buffered ioreq");
            }
            buf_req = &buf_page->buf_ioreq[(rdptr + 1) %
                                           IOREQ_BUFFER_SLOT_NUM];
            req.data |= ((uint64_t)buf_req->data) << 32;
            xen_rmb();
        }

        handle_ioreq(state, &req);

        /* Only req.data may get updated by handle_ioreq(), albeit even that
         * should not happen as such data would never make it to the guest (we
         * can only usefully see writes here after all).
         */
        assert(req.state == STATE_IOREQ_READY);
        assert(req.count == 1);
        assert(req.dir == IOREQ_WRITE);
        assert(!req.data_is_ptr);

        atomic_add(&buf_page->read_pointer, qw + 1);
    }

    return req.count;
}

static void handle_buffered_io(void *opaque)
{
    XenIOState *state = opaque;

    if (handle_buffered_iopage(state)) {
        timer_mod(state->buffered_io_timer,
                BUFFER_IO_MAX_DELAY + qemu_clock_get_ms(QEMU_CLOCK_REALTIME));
    } else {
        timer_del(state->buffered_io_timer);
        xenevtchn_unmask(state->xce_handle, state->bufioreq_local_port);
    }
}

static void cpu_handle_ioreq(void *opaque)
{
    XenIOState *state = opaque;
    ioreq_t *req = cpu_get_ioreq(state);

    handle_buffered_iopage(state);
    if (req) {
        ioreq_t copy = *req;

        xen_rmb();
        handle_ioreq(state, &copy);
        req->data = copy.data;

        if (req->state != STATE_IOREQ_INPROCESS) {
            fprintf(stderr, "Badness in I/O request ... not in service?!: "
                    "%x, ptr: %x, port: %"PRIx64", "
                    "data: %"PRIx64", count: %u, size: %u, type: %u\n",
                    req->state, req->data_is_ptr, req->addr,
                    req->data, req->count, req->size, req->type);
            destroy_hvm_domain(false);
            return;
        }

        xen_wmb(); /* Update ioreq contents /then/ update state. */

        /*
         * We do this before we send the response so that the tools
         * have the opportunity to pick up on the reset before the
         * guest resumes and does a hlt with interrupts disabled which
         * causes Xen to powerdown the domain.
         */
        if (runstate_is_running()) {
            if (qemu_shutdown_requested_get()) {
                destroy_hvm_domain(false);
            }
            if (qemu_reset_requested_get()) {
                qemu_system_reset(VMRESET_REPORT);
                destroy_hvm_domain(true);
            }
        }

        req->state = STATE_IORESP_READY;
        xenevtchn_notify(state->xce_handle,
                         state->ioreq_local_port[state->send_vcpu]);
    }
}

static void xen_main_loop_prepare(XenIOState *state)
{
    int evtchn_fd = -1;

    if (state->xce_handle != NULL) {
        evtchn_fd = xenevtchn_fd(state->xce_handle);
    }

    state->buffered_io_timer = timer_new_ms(QEMU_CLOCK_REALTIME, handle_buffered_io,
                                                 state);

    if (evtchn_fd != -1) {
        CPUState *cpu_state;

        DPRINTF("%s: Init cpu_by_vcpu_id\n", __func__);
        CPU_FOREACH(cpu_state) {
            DPRINTF("%s: cpu_by_vcpu_id[%d]=%p\n",
                    __func__, cpu_state->cpu_index, cpu_state);
            state->cpu_by_vcpu_id[cpu_state->cpu_index] = cpu_state;
        }
        qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state);
    }
}


static void xen_hvm_change_state_handler(void *opaque, int running,
                                         RunState rstate)
{
    XenIOState *state = opaque;

    if (running) {
        xen_main_loop_prepare(state);
    }

    xen_set_ioreq_server_state(xen_xc, xen_domid,
                               state->ioservid,
                               (rstate == RUN_STATE_RUNNING));
}

static void xen_exit_notifier(Notifier *n, void *data)
{
    XenIOState *state = container_of(n, XenIOState, exit);

    xenevtchn_close(state->xce_handle);
    xs_daemon_close(state->xenstore);
}

static void xen_read_physmap(XenIOState *state)
{
    XenPhysmap *physmap = NULL;
    unsigned int len, num, i;
    char path[80], *value = NULL;
    char **entries = NULL;

    snprintf(path, sizeof(path),
            "/local/domain/0/device-model/%d/physmap", xen_domid);
    entries = xs_directory(state->xenstore, 0, path, &num);
    if (entries == NULL)
        return;

    for (i = 0; i < num; i++) {
        physmap = g_malloc(sizeof (XenPhysmap));
        physmap->phys_offset = strtoull(entries[i], NULL, 16);
        snprintf(path, sizeof(path),
                "/local/domain/0/device-model/%d/physmap/%s/start_addr",
                xen_domid, entries[i]);
        value = xs_read(state->xenstore, 0, path, &len);
        if (value == NULL) {
            g_free(physmap);
            continue;
        }
        physmap->start_addr = strtoull(value, NULL, 16);
        free(value);

        snprintf(path, sizeof(path),
                "/local/domain/0/device-model/%d/physmap/%s/size",
                xen_domid, entries[i]);
        value = xs_read(state->xenstore, 0, path, &len);
        if (value == NULL) {
            g_free(physmap);
            continue;
        }
        physmap->size = strtoull(value, NULL, 16);
        free(value);

        snprintf(path, sizeof(path),
                "/local/domain/0/device-model/%d/physmap/%s/name",
                xen_domid, entries[i]);
        physmap->name = xs_read(state->xenstore, 0, path, &len);

        QLIST_INSERT_HEAD(&state->physmap, physmap, list);
    }
    free(entries);
}

static void xen_wakeup_notifier(Notifier *notifier, void *data)
{
    xc_set_hvm_param(xen_xc, xen_domid, HVM_PARAM_ACPI_S_STATE, 0);
}

void xen_hvm_init(PCMachineState *pcms, MemoryRegion **ram_memory)
{
    int i, rc;
    xen_pfn_t ioreq_pfn;
    xen_pfn_t bufioreq_pfn;
    evtchn_port_t bufioreq_evtchn;
    XenIOState *state;

    state = g_malloc0(sizeof (XenIOState));

    state->xce_handle = xenevtchn_open(NULL, 0);
    if (state->xce_handle == NULL) {
        perror("xen: event channel open");
        goto err;
    }

    state->xenstore = xs_daemon_open();
    if (state->xenstore == NULL) {
        perror("xen: xenstore open");
        goto err;
    }

    xen_create_ioreq_server(xen_xc, xen_domid, &state->ioservid);

    state->exit.notify = xen_exit_notifier;
    qemu_add_exit_notifier(&state->exit);

    state->suspend.notify = xen_suspend_notifier;
    qemu_register_suspend_notifier(&state->suspend);

    state->wakeup.notify = xen_wakeup_notifier;
    qemu_register_wakeup_notifier(&state->wakeup);

    rc = xen_get_ioreq_server_info(xen_xc, xen_domid, state->ioservid,
                                   &ioreq_pfn, &bufioreq_pfn,
                                   &bufioreq_evtchn);
    if (rc < 0) {
        error_report("failed to get ioreq server info: error %d handle=%p",
                     errno, xen_xc);
        goto err;
    }

    DPRINTF("shared page at pfn %lx\n", ioreq_pfn);
    DPRINTF("buffered io page at pfn %lx\n", bufioreq_pfn);
    DPRINTF("buffered io evtchn is %x\n", bufioreq_evtchn);

    state->shared_page = xenforeignmemory_map(xen_fmem, xen_domid,
                                              PROT_READ|PROT_WRITE,
                                              1, &ioreq_pfn, NULL);
    if (state->shared_page == NULL) {
        error_report("map shared IO page returned error %d handle=%p",
                     errno, xen_xc);
        goto err;
    }

    rc = xen_get_vmport_regs_pfn(xen_xc, xen_domid, &ioreq_pfn);
    if (!rc) {
        DPRINTF("shared vmport page at pfn %lx\n", ioreq_pfn);
        state->shared_vmport_page =
            xenforeignmemory_map(xen_fmem, xen_domid, PROT_READ|PROT_WRITE,
                                 1, &ioreq_pfn, NULL);
        if (state->shared_vmport_page == NULL) {
            error_report("map shared vmport IO page returned error %d handle=%p",
                         errno, xen_xc);
            goto err;
        }
    } else if (rc != -ENOSYS) {
        error_report("get vmport regs pfn returned error %d, rc=%d",
                     errno, rc);
        goto err;
    }

    state->buffered_io_page = xenforeignmemory_map(xen_fmem, xen_domid,
                                                   PROT_READ|PROT_WRITE,
                                                   1, &bufioreq_pfn, NULL);
    if (state->buffered_io_page == NULL) {
        error_report("map buffered IO page returned error %d", errno);
        goto err;
    }

    /* Note: cpus is empty at this point in init */
    state->cpu_by_vcpu_id = g_malloc0(max_cpus * sizeof(CPUState *));

    rc = xen_set_ioreq_server_state(xen_xc, xen_domid, state->ioservid, true);
    if (rc < 0) {
        error_report("failed to enable ioreq server info: error %d handle=%p",
                     errno, xen_xc);
        goto err;
    }

    state->ioreq_local_port = g_malloc0(max_cpus * sizeof (evtchn_port_t));

    /* FIXME: how about if we overflow the page here? */
    for (i = 0; i < max_cpus; i++) {
        rc = xenevtchn_bind_interdomain(state->xce_handle, xen_domid,
                                        xen_vcpu_eport(state->shared_page, i));
        if (rc == -1) {
            error_report("shared evtchn %d bind error %d", i, errno);
            goto err;
        }
        state->ioreq_local_port[i] = rc;
    }

    rc = xenevtchn_bind_interdomain(state->xce_handle, xen_domid,
                                    bufioreq_evtchn);
    if (rc == -1) {
        error_report("buffered evtchn bind error %d", errno);
        goto err;
    }
    state->bufioreq_local_port = rc;

    /* Init RAM management */
    xen_map_cache_init(xen_phys_offset_to_gaddr, state);
    xen_ram_init(pcms, ram_size, ram_memory);

    qemu_add_vm_change_state_handler(xen_hvm_change_state_handler, state);

    state->memory_listener = xen_memory_listener;
    QLIST_INIT(&state->physmap);
    memory_listener_register(&state->memory_listener, &address_space_memory);
    state->log_for_dirtybit = NULL;

    state->io_listener = xen_io_listener;
    memory_listener_register(&state->io_listener, &address_space_io);

    state->device_listener = xen_device_listener;
    device_listener_register(&state->device_listener);

    /* Initialize backend core & drivers */
    if (xen_be_init() != 0) {
        error_report("xen backend core setup failed");
        goto err;
    }
    xen_be_register_common();
    xen_read_physmap(state);

    /* Disable ACPI build because Xen handles it */
    pcms->acpi_build_enabled = false;

    return;

err:
    error_report("xen hardware virtual machine initialisation failed");
    exit(1);
}

void destroy_hvm_domain(bool reboot)
{
    xc_interface *xc_handle;
    int sts;

    xc_handle = xc_interface_open(0, 0, 0);
    if (xc_handle == NULL) {
        fprintf(stderr, "Cannot acquire xenctrl handle\n");
    } else {
        sts = xc_domain_shutdown(xc_handle, xen_domid,
                                 reboot ? SHUTDOWN_reboot : SHUTDOWN_poweroff);
        if (sts != 0) {
            fprintf(stderr, "xc_domain_shutdown failed to issue %s, "
                    "sts %d, %s\n", reboot ? "reboot" : "poweroff",
                    sts, strerror(errno));
        } else {
            fprintf(stderr, "Issued domain %d %s\n", xen_domid,
                    reboot ? "reboot" : "poweroff");
        }
        xc_interface_close(xc_handle);
    }
}

void xen_register_framebuffer(MemoryRegion *mr)
{
    framebuffer = mr;
}

void xen_shutdown_fatal_error(const char *fmt, ...)
{
    va_list ap;

    va_start(ap, fmt);
    vfprintf(stderr, fmt, ap);
    va_end(ap);
    fprintf(stderr, "Will destroy the domain.\n");
    /* destroy the domain */
    qemu_system_shutdown_request();
}

void xen_modified_memory(ram_addr_t start, ram_addr_t length)
{
    if (unlikely(xen_in_migration)) {
        int rc;
        ram_addr_t start_pfn, nb_pages;

        if (length == 0) {
            length = TARGET_PAGE_SIZE;
        }
        start_pfn = start >> TARGET_PAGE_BITS;
        nb_pages = ((start + length + TARGET_PAGE_SIZE - 1) >> TARGET_PAGE_BITS)
            - start_pfn;
        rc = xc_hvm_modified_memory(xen_xc, xen_domid, start_pfn, nb_pages);
        if (rc) {
            fprintf(stderr,
                    "%s failed for "RAM_ADDR_FMT" ("RAM_ADDR_FMT"): %i, %s\n",
                    __func__, start, nb_pages, rc, strerror(-rc));
        }
    }
}

void qmp_xen_set_global_dirty_log(bool enable, Error **errp)
{
    if (enable) {
        memory_global_dirty_log_start();
    } else {
        memory_global_dirty_log_stop();
    }
}