summaryrefslogtreecommitdiff
blob: 00cecf6d7de894c3de5bb74e25927e6f08578b48 (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
/*
 * QEMU KVM support
 *
 * Copyright IBM, Corp. 2008
 *           Red Hat, Inc. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *  Glauber Costa     <gcosta@redhat.com>
 *
 * 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 <sys/types.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <stdarg.h>

#include <linux/kvm.h>

#include "qemu-common.h"
#include "qemu-barrier.h"
#include "sysemu.h"
#include "hw/hw.h"
#include "gdbstub.h"
#include "kvm.h"
#include "bswap.h"

/* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
#define PAGE_SIZE TARGET_PAGE_SIZE

//#define DEBUG_KVM

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

#ifdef KVM_UPSTREAM

typedef struct KVMSlot
{
    target_phys_addr_t start_addr;
    ram_addr_t memory_size;
    ram_addr_t phys_offset;
    int slot;
    int flags;
} KVMSlot;

typedef struct kvm_dirty_log KVMDirtyLog;

struct KVMState
{
    KVMSlot slots[32];
    int fd;
    int vmfd;
    int coalesced_mmio;
#ifdef KVM_CAP_COALESCED_MMIO
    struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
#endif
    int broken_set_mem_region;
    int migration_log;
    int vcpu_events;
    int robust_singlestep;
    int debugregs;
#ifdef KVM_CAP_SET_GUEST_DEBUG
    struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
#endif
    int irqchip_in_kernel;
    int pit_in_kernel;
    int xsave, xcrs;
};

static KVMState *kvm_state;

#endif

static KVMSlot *kvm_alloc_slot(KVMState *s)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        /* KVM private memory slots */
        if (i >= 8 && i < 12)
            continue;
        if (s->slots[i].memory_size == 0)
            return &s->slots[i];
    }

    fprintf(stderr, "%s: no free slot available\n", __func__);
    abort();
}

static KVMSlot *kvm_lookup_matching_slot(KVMState *s,
                                         target_phys_addr_t start_addr,
                                         target_phys_addr_t end_addr)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        KVMSlot *mem = &s->slots[i];

        if (start_addr == mem->start_addr &&
            end_addr == mem->start_addr + mem->memory_size) {
            return mem;
        }
    }

    return NULL;
}

/*
 * Find overlapping slot with lowest start address
 */
static KVMSlot *kvm_lookup_overlapping_slot(KVMState *s,
                                            target_phys_addr_t start_addr,
                                            target_phys_addr_t end_addr)
{
    KVMSlot *found = NULL;
    int i;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        KVMSlot *mem = &s->slots[i];

        if (mem->memory_size == 0 ||
            (found && found->start_addr < mem->start_addr)) {
            continue;
        }

        if (end_addr > mem->start_addr &&
            start_addr < mem->start_addr + mem->memory_size) {
            found = mem;
        }
    }

    return found;
}

static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
{
    struct kvm_userspace_memory_region mem;

    mem.slot = slot->slot;
    mem.guest_phys_addr = slot->start_addr;
    mem.memory_size = slot->memory_size;
    mem.userspace_addr = (unsigned long)qemu_get_ram_ptr(slot->phys_offset);
    mem.flags = slot->flags;
    if (s->migration_log) {
        mem.flags |= KVM_MEM_LOG_DIRTY_PAGES;
    }
    return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
}

#ifdef KVM_UPSTREAM
static void kvm_reset_vcpu(void *opaque)
{
    CPUState *env = opaque;

    kvm_arch_reset_vcpu(env);
}
#endif

int kvm_irqchip_in_kernel(void)
{
    return kvm_state->irqchip_in_kernel;
}

int kvm_pit_in_kernel(void)
{
    return kvm_state->pit_in_kernel;
}


#ifdef KVM_UPSTREAM
int kvm_init_vcpu(CPUState *env)
{
    KVMState *s = kvm_state;
    long mmap_size;
    int ret;

    DPRINTF("kvm_init_vcpu\n");

    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
    if (ret < 0) {
        DPRINTF("kvm_create_vcpu failed\n");
        goto err;
    }

    env->kvm_fd = ret;
    env->kvm_state = s;

    mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
    if (mmap_size < 0) {
        DPRINTF("KVM_GET_VCPU_MMAP_SIZE failed\n");
        goto err;
    }

    env->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
                        env->kvm_fd, 0);
    if (env->kvm_run == MAP_FAILED) {
        ret = -errno;
        DPRINTF("mmap'ing vcpu state failed\n");
        goto err;
    }

#ifdef KVM_CAP_COALESCED_MMIO
    if (s->coalesced_mmio && !s->coalesced_mmio_ring)
        s->coalesced_mmio_ring = (void *) env->kvm_run +
		s->coalesced_mmio * PAGE_SIZE;
#endif

    ret = kvm_arch_init_vcpu(env);
    if (ret == 0) {
        qemu_register_reset(kvm_reset_vcpu, env);
        kvm_arch_reset_vcpu(env);
    }
err:
    return ret;
}
#endif

/*
 * dirty pages logging control
 */
static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
                                      ram_addr_t size, int flags, int mask)
{
    KVMState *s = kvm_state;
    KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
    int old_flags;

    if (mem == NULL)  {
            fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
                    TARGET_FMT_plx "\n", __func__, phys_addr,
                    (target_phys_addr_t)(phys_addr + size - 1));
            return -EINVAL;
    }

    old_flags = mem->flags;

    flags = (mem->flags & ~mask) | flags;
    mem->flags = flags;

    /* If nothing changed effectively, no need to issue ioctl */
    if (s->migration_log) {
        flags |= KVM_MEM_LOG_DIRTY_PAGES;
    }
    if (flags == old_flags) {
            return 0;
    }

    return kvm_set_user_memory_region(s, mem);
}

int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size)
{
        return kvm_dirty_pages_log_change(phys_addr, size,
                                          KVM_MEM_LOG_DIRTY_PAGES,
                                          KVM_MEM_LOG_DIRTY_PAGES);
}

int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
{
        return kvm_dirty_pages_log_change(phys_addr, size,
                                          0,
                                          KVM_MEM_LOG_DIRTY_PAGES);
}

static int kvm_set_migration_log(int enable)
{
    KVMState *s = kvm_state;
    KVMSlot *mem;
    int i, err;

    s->migration_log = enable;

    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
        mem = &s->slots[i];

        if (!!(mem->flags & KVM_MEM_LOG_DIRTY_PAGES) == enable) {
            continue;
        }
        err = kvm_set_user_memory_region(s, mem);
        if (err) {
            return err;
        }
    }
    return 0;
}

/* get kvm's dirty pages bitmap and update qemu's */
static int kvm_get_dirty_pages_log_range(unsigned long start_addr,
                                         unsigned long *bitmap,
                                         unsigned long offset,
                                         unsigned long mem_size)
{
    unsigned int i, j;
    unsigned long page_number, addr, addr1, c;
    ram_addr_t ram_addr;
    unsigned int len = ((mem_size / TARGET_PAGE_SIZE) + HOST_LONG_BITS - 1) /
        HOST_LONG_BITS;

    /*
     * bitmap-traveling is faster than memory-traveling (for addr...)
     * especially when most of the memory is not dirty.
     */
    for (i = 0; i < len; i++) {
        if (bitmap[i] != 0) {
            c = leul_to_cpu(bitmap[i]);
            do {
                j = ffsl(c) - 1;
                c &= ~(1ul << j);
                page_number = i * HOST_LONG_BITS + j;
                addr1 = page_number * TARGET_PAGE_SIZE;
                addr = offset + addr1;
                ram_addr = cpu_get_physical_page_desc(addr);
                cpu_physical_memory_set_dirty(ram_addr);
            } while (c != 0);
        }
    }
    return 0;
}

#define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))

/**
 * kvm_physical_sync_dirty_bitmap - Grab dirty bitmap from kernel space
 * This function updates qemu's dirty bitmap using cpu_physical_memory_set_dirty().
 * This means all bits are set to dirty.
 *
 * @start_add: start of logged region.
 * @end_addr: end of logged region.
 */
static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
					  target_phys_addr_t end_addr)
{
    KVMState *s = kvm_state;
    unsigned long size, allocated_size = 0;
    KVMDirtyLog d;
    KVMSlot *mem;
    int ret = 0;

    d.dirty_bitmap = NULL;
    while (start_addr < end_addr) {
        mem = kvm_lookup_overlapping_slot(s, start_addr, end_addr);
        if (mem == NULL) {
            break;
        }

        size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS), HOST_LONG_BITS) / 8;
        if (!d.dirty_bitmap) {
            d.dirty_bitmap = qemu_malloc(size);
        } else if (size > allocated_size) {
            d.dirty_bitmap = qemu_realloc(d.dirty_bitmap, size);
        }
        allocated_size = size;
        memset(d.dirty_bitmap, 0, allocated_size);

        d.slot = mem->slot;

        if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
            DPRINTF("ioctl failed %d\n", errno);
            ret = -1;
            break;
        }

        kvm_get_dirty_pages_log_range(mem->start_addr, d.dirty_bitmap,
                                      mem->start_addr, mem->memory_size);
        start_addr = mem->start_addr + mem->memory_size;
    }
    qemu_free(d.dirty_bitmap);

    return ret;
}

int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
    int ret = -ENOSYS;
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;

        ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
    }
#endif

    return ret;
}

int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
{
    int ret = -ENOSYS;
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;

        ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
    }
#endif

    return ret;
}

int kvm_check_extension(KVMState *s, unsigned int extension)
{
    int ret;

    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, extension);
    if (ret < 0) {
        ret = 0;
    }

    return ret;
}

static void kvm_set_phys_mem(target_phys_addr_t start_addr,
			     ram_addr_t size,
			     ram_addr_t phys_offset)
{
    KVMState *s = kvm_state;
    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
    KVMSlot *mem, old;
    int err;

    if (start_addr & ~TARGET_PAGE_MASK) {
        if (flags >= IO_MEM_UNASSIGNED) {
            if (!kvm_lookup_overlapping_slot(s, start_addr,
                                             start_addr + size)) {
                return;
            }
            fprintf(stderr, "Unaligned split of a KVM memory slot\n");
        } else {
            fprintf(stderr, "Only page-aligned memory slots supported\n");
        }
        abort();
    }

    /* KVM does not support read-only slots */
    phys_offset &= ~IO_MEM_ROM;

    while (1) {
        mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
        if (!mem) {
            break;
        }

        if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
            (start_addr + size <= mem->start_addr + mem->memory_size) &&
            (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
            /* The new slot fits into the existing one and comes with
             * identical parameters - nothing to be done. */
            return;
        }

        old = *mem;

        /* unregister the overlapping slot */
        mem->memory_size = 0;
        err = kvm_set_user_memory_region(s, mem);
        if (err) {
            fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
                    __func__, strerror(-err));
            abort();
        }

        /* Workaround for older KVM versions: we can't join slots, even not by
         * unregistering the previous ones and then registering the larger
         * slot. We have to maintain the existing fragmentation. Sigh.
         *
         * This workaround assumes that the new slot starts at the same
         * address as the first existing one. If not or if some overlapping
         * slot comes around later, we will fail (not seen in practice so far)
         * - and actually require a recent KVM version. */
        if (s->broken_set_mem_region &&
            old.start_addr == start_addr && old.memory_size < size &&
            flags < IO_MEM_UNASSIGNED) {
            mem = kvm_alloc_slot(s);
            mem->memory_size = old.memory_size;
            mem->start_addr = old.start_addr;
            mem->phys_offset = old.phys_offset;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
                        strerror(-err));
                abort();
            }

            start_addr += old.memory_size;
            phys_offset += old.memory_size;
            size -= old.memory_size;
            continue;
        }

        /* register prefix slot */
        if (old.start_addr < start_addr) {
            mem = kvm_alloc_slot(s);
            mem->memory_size = start_addr - old.start_addr;
            mem->start_addr = old.start_addr;
            mem->phys_offset = old.phys_offset;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error registering prefix slot: %s\n",
                        __func__, strerror(-err));
                abort();
            }
        }

        /* register suffix slot */
        if (old.start_addr + old.memory_size > start_addr + size) {
            ram_addr_t size_delta;

            mem = kvm_alloc_slot(s);
            mem->start_addr = start_addr + size;
            size_delta = mem->start_addr - old.start_addr;
            mem->memory_size = old.memory_size - size_delta;
            mem->phys_offset = old.phys_offset + size_delta;
            mem->flags = 0;

            err = kvm_set_user_memory_region(s, mem);
            if (err) {
                fprintf(stderr, "%s: error registering suffix slot: %s\n",
                        __func__, strerror(-err));
                abort();
            }
        }
    }

    /* in case the KVM bug workaround already "consumed" the new slot */
    if (!size)
        return;

    /* KVM does not need to know about this memory */
    if (flags >= IO_MEM_UNASSIGNED)
        return;

    mem = kvm_alloc_slot(s);
    mem->memory_size = size;
    mem->start_addr = start_addr;
    mem->phys_offset = phys_offset;
    mem->flags = 0;

    err = kvm_set_user_memory_region(s, mem);
    if (err) {
        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
                strerror(-err));
        abort();
    }
}

static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
				  target_phys_addr_t start_addr,
				  ram_addr_t size,
				  ram_addr_t phys_offset)
{
	kvm_set_phys_mem(start_addr, size, phys_offset);
}

static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
					target_phys_addr_t start_addr,
					target_phys_addr_t end_addr)
{
	return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
}

static int kvm_client_migration_log(struct CPUPhysMemoryClient *client,
				    int enable)
{
	return kvm_set_migration_log(enable);
}

static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
	.set_memory = kvm_client_set_memory,
	.sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
	.migration_log = kvm_client_migration_log,
};


void kvm_cpu_register_phys_memory_client(void)
{
    cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
}

#ifdef KVM_UPSTREAM

int kvm_init(int smp_cpus)
{
    static const char upgrade_note[] =
        "Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
        "(see http://sourceforge.net/projects/kvm).\n";
    KVMState *s;
    int ret;
    int i;

    s = qemu_mallocz(sizeof(KVMState));

#ifdef KVM_CAP_SET_GUEST_DEBUG
    QTAILQ_INIT(&s->kvm_sw_breakpoints);
#endif
    for (i = 0; i < ARRAY_SIZE(s->slots); i++)
        s->slots[i].slot = i;

    s->vmfd = -1;
    s->fd = qemu_open("/dev/kvm", O_RDWR);
    if (s->fd == -1) {
        fprintf(stderr, "Could not access KVM kernel module: %m\n");
        ret = -errno;
        goto err;
    }

    ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0);
    if (ret < KVM_API_VERSION) {
        if (ret > 0)
            ret = -EINVAL;
        fprintf(stderr, "kvm version too old\n");
        goto err;
    }

    if (ret > KVM_API_VERSION) {
        ret = -EINVAL;
        fprintf(stderr, "kvm version not supported\n");
        goto err;
    }

    s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0);
    if (s->vmfd < 0) {
#ifdef TARGET_S390X
        fprintf(stderr, "Please add the 'switch_amode' kernel parameter to "
                        "your host kernel command line\n");
#endif
        goto err;
    }

    /* initially, KVM allocated its own memory and we had to jump through
     * hooks to make phys_ram_base point to this.  Modern versions of KVM
     * just use a user allocated buffer so we can use regular pages
     * unmodified.  Make sure we have a sufficiently modern version of KVM.
     */
    if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
        ret = -EINVAL;
        fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n%s",
                upgrade_note);
        goto err;
    }

    /* There was a nasty bug in < kvm-80 that prevents memory slots from being
     * destroyed properly.  Since we rely on this capability, refuse to work
     * with any kernel without this capability. */
    if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
        ret = -EINVAL;

        fprintf(stderr,
                "KVM kernel module broken (DESTROY_MEMORY_REGION).\n%s",
                upgrade_note);
        goto err;
    }

    s->coalesced_mmio = 0;
#ifdef KVM_CAP_COALESCED_MMIO
    s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
    s->coalesced_mmio_ring = NULL;
#endif

    s->broken_set_mem_region = 1;
#ifdef KVM_CAP_JOIN_MEMORY_REGIONS_WORKS
    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
    if (ret > 0) {
        s->broken_set_mem_region = 0;
    }
#endif

    s->vcpu_events = 0;
#ifdef KVM_CAP_VCPU_EVENTS
    s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS);
#endif

    s->robust_singlestep = 0;
#ifdef KVM_CAP_X86_ROBUST_SINGLESTEP
    s->robust_singlestep =
        kvm_check_extension(s, KVM_CAP_X86_ROBUST_SINGLESTEP);
#endif

    s->debugregs = 0;
#ifdef KVM_CAP_DEBUGREGS
    s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS);
#endif

    s->xsave = 0;
#ifdef KVM_CAP_XSAVE
    s->xsave = kvm_check_extension(s, KVM_CAP_XSAVE);
#endif

    s->xcrs = 0;
#ifdef KVM_CAP_XCRS
    s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
#endif

    ret = kvm_arch_init(s, smp_cpus);
    if (ret < 0)
        goto err;

    kvm_state = s;
    cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);

    return 0;

err:
    if (s) {
        if (s->vmfd != -1)
            close(s->vmfd);
        if (s->fd != -1)
            close(s->fd);
    }
    qemu_free(s);

    return ret;
}
#endif

static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
                         uint32_t count)
{
    int i;
    uint8_t *ptr = data;

    for (i = 0; i < count; i++) {
        if (direction == KVM_EXIT_IO_IN) {
            switch (size) {
            case 1:
                stb_p(ptr, cpu_inb(port));
                break;
            case 2:
                stw_p(ptr, cpu_inw(port));
                break;
            case 4:
                stl_p(ptr, cpu_inl(port));
                break;
            }
        } else {
            switch (size) {
            case 1:
                cpu_outb(port, ldub_p(ptr));
                break;
            case 2:
                cpu_outw(port, lduw_p(ptr));
                break;
            case 4:
                cpu_outl(port, ldl_p(ptr));
                break;
            }
        }

        ptr += size;
    }

    return 1;
}

#ifdef KVM_CAP_INTERNAL_ERROR_DATA
static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
{

    if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
        int i;

        fprintf(stderr, "KVM internal error. Suberror: %d\n",
                run->internal.suberror);

        for (i = 0; i < run->internal.ndata; ++i) {
            fprintf(stderr, "extra data[%d]: %"PRIx64"\n",
                    i, (uint64_t)run->internal.data[i]);
        }
    }
    cpu_dump_state(env, stderr, fprintf, 0);
    if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
        fprintf(stderr, "emulation failure\n");
        if (!kvm_arch_stop_on_emulation_error(env))
		return;
    }
    /* FIXME: Should trigger a qmp message to let management know
     * something went wrong.
     */
    vm_stop(0);
}
#endif

void kvm_flush_coalesced_mmio_buffer(void)
{
#ifdef KVM_CAP_COALESCED_MMIO
    KVMState *s = kvm_state;
    if (s->coalesced_mmio_ring) {
        struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring;
        while (ring->first != ring->last) {
            struct kvm_coalesced_mmio *ent;

            ent = &ring->coalesced_mmio[ring->first];

            cpu_physical_memory_write(ent->phys_addr, ent->data, ent->len);
            smp_wmb();
            ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
        }
    }
#endif
}

#ifdef KVM_UPSTREAM

static void do_kvm_cpu_synchronize_state(void *_env)
{
    CPUState *env = _env;

    if (!env->kvm_vcpu_dirty) {
        kvm_arch_get_registers(env);
        env->kvm_vcpu_dirty = 1;
    }
}

void kvm_cpu_synchronize_state(CPUState *env)
{
    if (!env->kvm_vcpu_dirty)
        run_on_cpu(env, do_kvm_cpu_synchronize_state, env);
}

void kvm_cpu_synchronize_post_reset(CPUState *env)
{
    kvm_arch_put_registers(env, KVM_PUT_RESET_STATE);
    env->kvm_vcpu_dirty = 0;
}

void kvm_cpu_synchronize_post_init(CPUState *env)
{
    kvm_arch_put_registers(env, KVM_PUT_FULL_STATE);
    env->kvm_vcpu_dirty = 0;
}

int kvm_cpu_exec(CPUState *env)
{
    struct kvm_run *run = env->kvm_run;
    int ret;

    DPRINTF("kvm_cpu_exec()\n");

    do {
#ifndef CONFIG_IOTHREAD
        if (env->exit_request) {
            DPRINTF("interrupt exit requested\n");
            ret = 0;
            break;
        }
#endif

        if (kvm_arch_process_irqchip_events(env)) {
            ret = 0;
            break;
        }

        if (env->kvm_vcpu_dirty) {
            kvm_arch_put_registers(env, KVM_PUT_RUNTIME_STATE);
            env->kvm_vcpu_dirty = 0;
        }

        kvm_arch_pre_run(env, run);
        cpu_single_env = NULL;
        qemu_mutex_unlock_iothread();
        ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
        qemu_mutex_lock_iothread();
        cpu_single_env = env;
        kvm_arch_post_run(env, run);

        if (ret == -EINTR || ret == -EAGAIN) {
            cpu_exit(env);
            DPRINTF("io window exit\n");
            ret = 0;
            break;
        }

        if (ret < 0) {
            DPRINTF("kvm run failed %s\n", strerror(-ret));
            abort();
        }

        kvm_flush_coalesced_mmio_buffer();

        ret = 0; /* exit loop */
        switch (run->exit_reason) {
        case KVM_EXIT_IO:
            DPRINTF("handle_io\n");
            ret = kvm_handle_io(run->io.port,
                                (uint8_t *)run + run->io.data_offset,
                                run->io.direction,
                                run->io.size,
                                run->io.count);
            break;
        case KVM_EXIT_MMIO:
            DPRINTF("handle_mmio\n");
            cpu_physical_memory_rw(run->mmio.phys_addr,
                                   run->mmio.data,
                                   run->mmio.len,
                                   run->mmio.is_write);
            ret = 1;
            break;
        case KVM_EXIT_IRQ_WINDOW_OPEN:
            DPRINTF("irq_window_open\n");
            break;
        case KVM_EXIT_SHUTDOWN:
            DPRINTF("shutdown\n");
            qemu_system_reset_request();
            ret = 1;
            break;
        case KVM_EXIT_UNKNOWN:
            DPRINTF("kvm_exit_unknown\n");
            break;
        case KVM_EXIT_FAIL_ENTRY:
            DPRINTF("kvm_exit_fail_entry\n");
            break;
        case KVM_EXIT_EXCEPTION:
            DPRINTF("kvm_exit_exception\n");
            break;
#ifdef KVM_CAP_INTERNAL_ERROR_DATA
        case KVM_EXIT_INTERNAL_ERROR:
            kvm_handle_internal_error(env, run);
            break;
#endif
        case KVM_EXIT_DEBUG:
            DPRINTF("kvm_exit_debug\n");
#ifdef KVM_CAP_SET_GUEST_DEBUG
            if (kvm_arch_debug(&run->debug.arch)) {
                env->exception_index = EXCP_DEBUG;
                return 0;
            }
            /* re-enter, this exception was guest-internal */
            ret = 1;
#endif /* KVM_CAP_SET_GUEST_DEBUG */
            break;
        default:
            DPRINTF("kvm_arch_handle_exit\n");
            ret = kvm_arch_handle_exit(env, run);
            break;
        }
    } while (ret > 0);

    if (env->exit_request) {
        env->exit_request = 0;
        env->exception_index = EXCP_INTERRUPT;
    }

    return ret;
}

#endif
int kvm_ioctl(KVMState *s, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(s->fd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_vm_ioctl(KVMState *s, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(s->vmfd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_vcpu_ioctl(CPUState *env, int type, ...)
{
    int ret;
    void *arg;
    va_list ap;

    va_start(ap, type);
    arg = va_arg(ap, void *);
    va_end(ap);

    ret = ioctl(env->kvm_fd, type, arg);
    if (ret == -1)
        ret = -errno;

    return ret;
}

int kvm_has_sync_mmu(void)
{
#ifdef KVM_CAP_SYNC_MMU
    KVMState *s = kvm_state;

    return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
#else
    return 0;
#endif
}

int kvm_has_vcpu_events(void)
{
    return kvm_state->vcpu_events;
}

int kvm_has_robust_singlestep(void)
{
    return kvm_state->robust_singlestep;
}

int kvm_has_debugregs(void)
{
    return kvm_state->debugregs;
}

#ifdef KVM_UPSTREAM
int kvm_has_xsave(void)
{
    return kvm_state->xsave;
}

int kvm_has_xcrs(void)
{
    return kvm_state->xcrs;
}
#endif

void kvm_setup_guest_memory(void *start, size_t size)
{
    if (!kvm_has_sync_mmu()) {
#ifdef MADV_DONTFORK
        int ret = madvise(start, size, MADV_DONTFORK);

        if (ret) {
            perror("madvice");
            exit(1);
        }
#else
        fprintf(stderr,
                "Need MADV_DONTFORK in absence of synchronous KVM MMU\n");
        exit(1);
#endif
    }
}

#ifdef KVM_CAP_SET_GUEST_DEBUG
#ifndef KVM_UPSTREAM
#define run_on_cpu on_vcpu
static void on_vcpu(CPUState *env, void (*func)(void *data), void *data);
#endif /* !KVM_UPSTREAM */

struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
                                                 target_ulong pc)
{
    struct kvm_sw_breakpoint *bp;

    QTAILQ_FOREACH(bp, &env->kvm_state->kvm_sw_breakpoints, entry) {
        if (bp->pc == pc)
            return bp;
    }
    return NULL;
}

int kvm_sw_breakpoints_active(CPUState *env)
{
    return !QTAILQ_EMPTY(&env->kvm_state->kvm_sw_breakpoints);
}

struct kvm_set_guest_debug_data {
    struct kvm_guest_debug dbg;
    CPUState *env;
    int err;
};

static void kvm_invoke_set_guest_debug(void *data)
{
    struct kvm_set_guest_debug_data *dbg_data = data;
    CPUState *env = dbg_data->env;

    dbg_data->err = kvm_vcpu_ioctl(env, KVM_SET_GUEST_DEBUG, &dbg_data->dbg);
}

int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
{
    struct kvm_set_guest_debug_data data;

    data.dbg.control = reinject_trap;

    if (env->singlestep_enabled) {
        data.dbg.control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
    }
    kvm_arch_update_guest_debug(env, &data.dbg);
    data.env = env;

    run_on_cpu(env, kvm_invoke_set_guest_debug, &data);
    return data.err;
}

int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    struct kvm_sw_breakpoint *bp;
    CPUState *env;
    int err;

    if (type == GDB_BREAKPOINT_SW) {
        bp = kvm_find_sw_breakpoint(current_env, addr);
        if (bp) {
            bp->use_count++;
            return 0;
        }

        bp = qemu_malloc(sizeof(struct kvm_sw_breakpoint));
        if (!bp)
            return -ENOMEM;

        bp->pc = addr;
        bp->use_count = 1;
        err = kvm_arch_insert_sw_breakpoint(current_env, bp);
        if (err) {
            free(bp);
            return err;
        }

        QTAILQ_INSERT_HEAD(&current_env->kvm_state->kvm_sw_breakpoints,
                          bp, entry);
    } else {
        err = kvm_arch_insert_hw_breakpoint(addr, len, type);
        if (err)
            return err;
    }

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        err = kvm_update_guest_debug(env, 0);
        if (err)
            return err;
    }
    return 0;
}

int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    struct kvm_sw_breakpoint *bp;
    CPUState *env;
    int err;

    if (type == GDB_BREAKPOINT_SW) {
        bp = kvm_find_sw_breakpoint(current_env, addr);
        if (!bp)
            return -ENOENT;

        if (bp->use_count > 1) {
            bp->use_count--;
            return 0;
        }

        err = kvm_arch_remove_sw_breakpoint(current_env, bp);
        if (err)
            return err;

        QTAILQ_REMOVE(&current_env->kvm_state->kvm_sw_breakpoints, bp, entry);
        qemu_free(bp);
    } else {
        err = kvm_arch_remove_hw_breakpoint(addr, len, type);
        if (err)
            return err;
    }

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        err = kvm_update_guest_debug(env, 0);
        if (err)
            return err;
    }
    return 0;
}

void kvm_remove_all_breakpoints(CPUState *current_env)
{
    struct kvm_sw_breakpoint *bp, *next;
    KVMState *s = current_env->kvm_state;
    CPUState *env;

    QTAILQ_FOREACH_SAFE(bp, &s->kvm_sw_breakpoints, entry, next) {
        if (kvm_arch_remove_sw_breakpoint(current_env, bp) != 0) {
            /* Try harder to find a CPU that currently sees the breakpoint. */
            for (env = first_cpu; env != NULL; env = env->next_cpu) {
                if (kvm_arch_remove_sw_breakpoint(env, bp) == 0)
                    break;
            }
        }
    }
    kvm_arch_remove_all_hw_breakpoints();

    for (env = first_cpu; env != NULL; env = env->next_cpu)
        kvm_update_guest_debug(env, 0);
}

#else /* !KVM_CAP_SET_GUEST_DEBUG */

int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
{
    return -EINVAL;
}

int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    return -EINVAL;
}

int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
                          target_ulong len, int type)
{
    return -EINVAL;
}

void kvm_remove_all_breakpoints(CPUState *current_env)
{
}
#endif /* !KVM_CAP_SET_GUEST_DEBUG */

int kvm_set_signal_mask(CPUState *env, const sigset_t *sigset)
{
    struct kvm_signal_mask *sigmask;
    int r;

    if (!sigset)
        return kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, NULL);

    sigmask = qemu_malloc(sizeof(*sigmask) + sizeof(*sigset));

    sigmask->len = 8;
    memcpy(sigmask->sigset, sigset, sizeof(*sigset));
    r = kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, sigmask);
    free(sigmask);

    return r;
}

int kvm_set_ioeventfd_mmio_long(int fd, uint32_t addr, uint32_t val, bool assign)
{
#ifdef KVM_IOEVENTFD
    int ret;
    struct kvm_ioeventfd iofd;

    iofd.datamatch = val;
    iofd.addr = addr;
    iofd.len = 4;
    iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
    iofd.fd = fd;

    if (!kvm_enabled()) {
        return -ENOSYS;
    }

    if (!assign) {
        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
    }

    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);

    if (ret < 0) {
        return -errno;
    }

    return 0;
#else
    return -ENOSYS;
#endif
}

int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
{
#ifdef KVM_IOEVENTFD
    struct kvm_ioeventfd kick = {
        .datamatch = val,
        .addr = addr,
        .len = 2,
        .flags = KVM_IOEVENTFD_FLAG_DATAMATCH | KVM_IOEVENTFD_FLAG_PIO,
        .fd = fd,
    };
    int r;
    if (!kvm_enabled())
        return -ENOSYS;
    if (!assign)
        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
    if (r < 0)
        return r;
    return 0;
#else
    return -ENOSYS;
#endif
}

#if defined(KVM_IRQFD)
int kvm_set_irqfd(int gsi, int fd, bool assigned)
{
    struct kvm_irqfd irqfd = {
        .fd = fd,
        .gsi = gsi,
        .flags = assigned ? 0 : KVM_IRQFD_FLAG_DEASSIGN,
    };
    int r;
    if (!kvm_enabled() || !kvm_irqchip_in_kernel())
        return -ENOSYS;

    r = kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd);
    if (r < 0)
        return r;
    return 0;
}
#endif

#undef PAGE_SIZE
#include "qemu-kvm.c"