aboutsummaryrefslogtreecommitdiff
path: root/cpus.c
blob: 3de2e27f41c3f7fc86fc0df9fcbca7aa40b49390 (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
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/* Needed early for CONFIG_BSD etc. */
#include "config-host.h"

#include "monitor.h"
#include "sysemu.h"
#include "gdbstub.h"
#include "dma.h"
#include "kvm.h"
#include "qmp-commands.h"

#include "qemu-thread.h"
#include "cpus.h"
#include "qtest.h"
#include "main-loop.h"
#include "bitmap.h"

#ifndef _WIN32
#include "compatfd.h"
#endif

#ifdef CONFIG_LINUX

#include <sys/prctl.h>

#ifndef PR_MCE_KILL
#define PR_MCE_KILL 33
#endif

#ifndef PR_MCE_KILL_SET
#define PR_MCE_KILL_SET 1
#endif

#ifndef PR_MCE_KILL_EARLY
#define PR_MCE_KILL_EARLY 1
#endif

#endif /* CONFIG_LINUX */

static CPUArchState *next_cpu;

static bool cpu_thread_is_idle(CPUArchState *env)
{
    if (env->stop || env->queued_work_first) {
        return false;
    }
    if (env->stopped || !runstate_is_running()) {
        return true;
    }
    if (!env->halted || qemu_cpu_has_work(env) || kvm_irqchip_in_kernel()) {
        return false;
    }
    return true;
}

static bool all_cpu_threads_idle(void)
{
    CPUArchState *env;

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        if (!cpu_thread_is_idle(env)) {
            return false;
        }
    }
    return true;
}

/***********************************************************/
/* guest cycle counter */

/* Conversion factor from emulated instructions to virtual clock ticks.  */
static int icount_time_shift;
/* Arbitrarily pick 1MIPS as the minimum allowable speed.  */
#define MAX_ICOUNT_SHIFT 10
/* Compensate for varying guest execution speed.  */
static int64_t qemu_icount_bias;
static QEMUTimer *icount_rt_timer;
static QEMUTimer *icount_vm_timer;
static QEMUTimer *icount_warp_timer;
static int64_t vm_clock_warp_start;
static int64_t qemu_icount;

typedef struct TimersState {
    int64_t cpu_ticks_prev;
    int64_t cpu_ticks_offset;
    int64_t cpu_clock_offset;
    int32_t cpu_ticks_enabled;
    int64_t dummy;
} TimersState;

TimersState timers_state;

/* Return the virtual CPU time, based on the instruction counter.  */
int64_t cpu_get_icount(void)
{
    int64_t icount;
    CPUArchState *env = cpu_single_env;

    icount = qemu_icount;
    if (env) {
        if (!can_do_io(env)) {
            fprintf(stderr, "Bad clock read\n");
        }
        icount -= (env->icount_decr.u16.low + env->icount_extra);
    }
    return qemu_icount_bias + (icount << icount_time_shift);
}

/* return the host CPU cycle counter and handle stop/restart */
int64_t cpu_get_ticks(void)
{
    if (use_icount) {
        return cpu_get_icount();
    }
    if (!timers_state.cpu_ticks_enabled) {
        return timers_state.cpu_ticks_offset;
    } else {
        int64_t ticks;
        ticks = cpu_get_real_ticks();
        if (timers_state.cpu_ticks_prev > ticks) {
            /* Note: non increasing ticks may happen if the host uses
               software suspend */
            timers_state.cpu_ticks_offset += timers_state.cpu_ticks_prev - ticks;
        }
        timers_state.cpu_ticks_prev = ticks;
        return ticks + timers_state.cpu_ticks_offset;
    }
}

/* return the host CPU monotonic timer and handle stop/restart */
int64_t cpu_get_clock(void)
{
    int64_t ti;
    if (!timers_state.cpu_ticks_enabled) {
        return timers_state.cpu_clock_offset;
    } else {
        ti = get_clock();
        return ti + timers_state.cpu_clock_offset;
    }
}

/* enable cpu_get_ticks() */
void cpu_enable_ticks(void)
{
    if (!timers_state.cpu_ticks_enabled) {
        timers_state.cpu_ticks_offset -= cpu_get_real_ticks();
        timers_state.cpu_clock_offset -= get_clock();
        timers_state.cpu_ticks_enabled = 1;
    }
}

/* disable cpu_get_ticks() : the clock is stopped. You must not call
   cpu_get_ticks() after that.  */
void cpu_disable_ticks(void)
{
    if (timers_state.cpu_ticks_enabled) {
        timers_state.cpu_ticks_offset = cpu_get_ticks();
        timers_state.cpu_clock_offset = cpu_get_clock();
        timers_state.cpu_ticks_enabled = 0;
    }
}

/* Correlation between real and virtual time is always going to be
   fairly approximate, so ignore small variation.
   When the guest is idle real and virtual time will be aligned in
   the IO wait loop.  */
#define ICOUNT_WOBBLE (get_ticks_per_sec() / 10)

static void icount_adjust(void)
{
    int64_t cur_time;
    int64_t cur_icount;
    int64_t delta;
    static int64_t last_delta;
    /* If the VM is not running, then do nothing.  */
    if (!runstate_is_running()) {
        return;
    }
    cur_time = cpu_get_clock();
    cur_icount = qemu_get_clock_ns(vm_clock);
    delta = cur_icount - cur_time;
    /* FIXME: This is a very crude algorithm, somewhat prone to oscillation.  */
    if (delta > 0
        && last_delta + ICOUNT_WOBBLE < delta * 2
        && icount_time_shift > 0) {
        /* The guest is getting too far ahead.  Slow time down.  */
        icount_time_shift--;
    }
    if (delta < 0
        && last_delta - ICOUNT_WOBBLE > delta * 2
        && icount_time_shift < MAX_ICOUNT_SHIFT) {
        /* The guest is getting too far behind.  Speed time up.  */
        icount_time_shift++;
    }
    last_delta = delta;
    qemu_icount_bias = cur_icount - (qemu_icount << icount_time_shift);
}

static void icount_adjust_rt(void *opaque)
{
    qemu_mod_timer(icount_rt_timer,
                   qemu_get_clock_ms(rt_clock) + 1000);
    icount_adjust();
}

static void icount_adjust_vm(void *opaque)
{
    qemu_mod_timer(icount_vm_timer,
                   qemu_get_clock_ns(vm_clock) + get_ticks_per_sec() / 10);
    icount_adjust();
}

static int64_t qemu_icount_round(int64_t count)
{
    return (count + (1 << icount_time_shift) - 1) >> icount_time_shift;
}

static void icount_warp_rt(void *opaque)
{
    if (vm_clock_warp_start == -1) {
        return;
    }

    if (runstate_is_running()) {
        int64_t clock = qemu_get_clock_ns(rt_clock);
        int64_t warp_delta = clock - vm_clock_warp_start;
        if (use_icount == 1) {
            qemu_icount_bias += warp_delta;
        } else {
            /*
             * In adaptive mode, do not let the vm_clock run too
             * far ahead of real time.
             */
            int64_t cur_time = cpu_get_clock();
            int64_t cur_icount = qemu_get_clock_ns(vm_clock);
            int64_t delta = cur_time - cur_icount;
            qemu_icount_bias += MIN(warp_delta, delta);
        }
        if (qemu_clock_expired(vm_clock)) {
            qemu_notify_event();
        }
    }
    vm_clock_warp_start = -1;
}

void qtest_clock_warp(int64_t dest)
{
    int64_t clock = qemu_get_clock_ns(vm_clock);
    assert(qtest_enabled());
    while (clock < dest) {
        int64_t deadline = qemu_clock_deadline(vm_clock);
        int64_t warp = MIN(dest - clock, deadline);
        qemu_icount_bias += warp;
        qemu_run_timers(vm_clock);
        clock = qemu_get_clock_ns(vm_clock);
    }
    qemu_notify_event();
}

void qemu_clock_warp(QEMUClock *clock)
{
    int64_t deadline;

    /*
     * There are too many global variables to make the "warp" behavior
     * applicable to other clocks.  But a clock argument removes the
     * need for if statements all over the place.
     */
    if (clock != vm_clock || !use_icount) {
        return;
    }

    /*
     * If the CPUs have been sleeping, advance the vm_clock timer now.  This
     * ensures that the deadline for the timer is computed correctly below.
     * This also makes sure that the insn counter is synchronized before the
     * CPU starts running, in case the CPU is woken by an event other than
     * the earliest vm_clock timer.
     */
    icount_warp_rt(NULL);
    if (!all_cpu_threads_idle() || !qemu_clock_has_timers(vm_clock)) {
        qemu_del_timer(icount_warp_timer);
        return;
    }

    if (qtest_enabled()) {
        /* When testing, qtest commands advance icount.  */
	return;
    }

    vm_clock_warp_start = qemu_get_clock_ns(rt_clock);
    deadline = qemu_clock_deadline(vm_clock);
    if (deadline > 0) {
        /*
         * Ensure the vm_clock proceeds even when the virtual CPU goes to
         * sleep.  Otherwise, the CPU might be waiting for a future timer
         * interrupt to wake it up, but the interrupt never comes because
         * the vCPU isn't running any insns and thus doesn't advance the
         * vm_clock.
         *
         * An extreme solution for this problem would be to never let VCPUs
         * sleep in icount mode if there is a pending vm_clock timer; rather
         * time could just advance to the next vm_clock event.  Instead, we
         * do stop VCPUs and only advance vm_clock after some "real" time,
         * (related to the time left until the next event) has passed.  This
         * rt_clock timer will do this.  This avoids that the warps are too
         * visible externally---for example, you will not be sending network
         * packets continuously instead of every 100ms.
         */
        qemu_mod_timer(icount_warp_timer, vm_clock_warp_start + deadline);
    } else {
        qemu_notify_event();
    }
}

static const VMStateDescription vmstate_timers = {
    .name = "timer",
    .version_id = 2,
    .minimum_version_id = 1,
    .minimum_version_id_old = 1,
    .fields      = (VMStateField[]) {
        VMSTATE_INT64(cpu_ticks_offset, TimersState),
        VMSTATE_INT64(dummy, TimersState),
        VMSTATE_INT64_V(cpu_clock_offset, TimersState, 2),
        VMSTATE_END_OF_LIST()
    }
};

void configure_icount(const char *option)
{
    vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
    if (!option) {
        return;
    }

    icount_warp_timer = qemu_new_timer_ns(rt_clock, icount_warp_rt, NULL);
    if (strcmp(option, "auto") != 0) {
        icount_time_shift = strtol(option, NULL, 0);
        use_icount = 1;
        return;
    }

    use_icount = 2;

    /* 125MIPS seems a reasonable initial guess at the guest speed.
       It will be corrected fairly quickly anyway.  */
    icount_time_shift = 3;

    /* Have both realtime and virtual time triggers for speed adjustment.
       The realtime trigger catches emulated time passing too slowly,
       the virtual time trigger catches emulated time passing too fast.
       Realtime triggers occur even when idle, so use them less frequently
       than VM triggers.  */
    icount_rt_timer = qemu_new_timer_ms(rt_clock, icount_adjust_rt, NULL);
    qemu_mod_timer(icount_rt_timer,
                   qemu_get_clock_ms(rt_clock) + 1000);
    icount_vm_timer = qemu_new_timer_ns(vm_clock, icount_adjust_vm, NULL);
    qemu_mod_timer(icount_vm_timer,
                   qemu_get_clock_ns(vm_clock) + get_ticks_per_sec() / 10);
}

/***********************************************************/
void hw_error(const char *fmt, ...)
{
    va_list ap;
    CPUArchState *env;

    va_start(ap, fmt);
    fprintf(stderr, "qemu: hardware error: ");
    vfprintf(stderr, fmt, ap);
    fprintf(stderr, "\n");
    for(env = first_cpu; env != NULL; env = env->next_cpu) {
        fprintf(stderr, "CPU #%d:\n", env->cpu_index);
#ifdef TARGET_I386
        cpu_dump_state(env, stderr, fprintf, X86_DUMP_FPU);
#else
        cpu_dump_state(env, stderr, fprintf, 0);
#endif
    }
    va_end(ap);
    abort();
}

void cpu_synchronize_all_states(void)
{
    CPUArchState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
        cpu_synchronize_state(cpu);
    }
}

void cpu_synchronize_all_post_reset(void)
{
    CPUArchState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
        cpu_synchronize_post_reset(cpu);
    }
}

void cpu_synchronize_all_post_init(void)
{
    CPUArchState *cpu;

    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
        cpu_synchronize_post_init(cpu);
    }
}

int cpu_is_stopped(CPUArchState *env)
{
    return !runstate_is_running() || env->stopped;
}

static void do_vm_stop(RunState state)
{
    if (runstate_is_running()) {
        cpu_disable_ticks();
        pause_all_vcpus();
        runstate_set(state);
        vm_state_notify(0, state);
        bdrv_drain_all();
        bdrv_flush_all();
        monitor_protocol_event(QEVENT_STOP, NULL);
    }
}

static int cpu_can_run(CPUArchState *env)
{
    if (env->stop) {
        return 0;
    }
    if (env->stopped || !runstate_is_running()) {
        return 0;
    }
    return 1;
}

static void cpu_handle_guest_debug(CPUArchState *env)
{
    gdb_set_stop_cpu(env);
    qemu_system_debug_request();
    env->stopped = 1;
}

static void cpu_signal(int sig)
{
    if (cpu_single_env) {
        cpu_exit(cpu_single_env);
    }
    exit_request = 1;
}

#ifdef CONFIG_LINUX
static void sigbus_reraise(void)
{
    sigset_t set;
    struct sigaction action;

    memset(&action, 0, sizeof(action));
    action.sa_handler = SIG_DFL;
    if (!sigaction(SIGBUS, &action, NULL)) {
        raise(SIGBUS);
        sigemptyset(&set);
        sigaddset(&set, SIGBUS);
        sigprocmask(SIG_UNBLOCK, &set, NULL);
    }
    perror("Failed to re-raise SIGBUS!\n");
    abort();
}

static void sigbus_handler(int n, struct qemu_signalfd_siginfo *siginfo,
                           void *ctx)
{
    if (kvm_on_sigbus(siginfo->ssi_code,
                      (void *)(intptr_t)siginfo->ssi_addr)) {
        sigbus_reraise();
    }
}

static void qemu_init_sigbus(void)
{
    struct sigaction action;

    memset(&action, 0, sizeof(action));
    action.sa_flags = SA_SIGINFO;
    action.sa_sigaction = (void (*)(int, siginfo_t*, void*))sigbus_handler;
    sigaction(SIGBUS, &action, NULL);

    prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
}

static void qemu_kvm_eat_signals(CPUArchState *env)
{
    struct timespec ts = { 0, 0 };
    siginfo_t siginfo;
    sigset_t waitset;
    sigset_t chkset;
    int r;

    sigemptyset(&waitset);
    sigaddset(&waitset, SIG_IPI);
    sigaddset(&waitset, SIGBUS);

    do {
        r = sigtimedwait(&waitset, &siginfo, &ts);
        if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {
            perror("sigtimedwait");
            exit(1);
        }

        switch (r) {
        case SIGBUS:
            if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {
                sigbus_reraise();
            }
            break;
        default:
            break;
        }

        r = sigpending(&chkset);
        if (r == -1) {
            perror("sigpending");
            exit(1);
        }
    } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));
}

#else /* !CONFIG_LINUX */

static void qemu_init_sigbus(void)
{
}

static void qemu_kvm_eat_signals(CPUArchState *env)
{
}
#endif /* !CONFIG_LINUX */

#ifndef _WIN32
static void dummy_signal(int sig)
{
}

static void qemu_kvm_init_cpu_signals(CPUArchState *env)
{
    int r;
    sigset_t set;
    struct sigaction sigact;

    memset(&sigact, 0, sizeof(sigact));
    sigact.sa_handler = dummy_signal;
    sigaction(SIG_IPI, &sigact, NULL);

    pthread_sigmask(SIG_BLOCK, NULL, &set);
    sigdelset(&set, SIG_IPI);
    sigdelset(&set, SIGBUS);
    r = kvm_set_signal_mask(env, &set);
    if (r) {
        fprintf(stderr, "kvm_set_signal_mask: %s\n", strerror(-r));
        exit(1);
    }
}

static void qemu_tcg_init_cpu_signals(void)
{
    sigset_t set;
    struct sigaction sigact;

    memset(&sigact, 0, sizeof(sigact));
    sigact.sa_handler = cpu_signal;
    sigaction(SIG_IPI, &sigact, NULL);

    sigemptyset(&set);
    sigaddset(&set, SIG_IPI);
    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
}

#else /* _WIN32 */
static void qemu_kvm_init_cpu_signals(CPUArchState *env)
{
    abort();
}

static void qemu_tcg_init_cpu_signals(void)
{
}
#endif /* _WIN32 */

QemuMutex qemu_global_mutex;
static QemuCond qemu_io_proceeded_cond;
static bool iothread_requesting_mutex;

static QemuThread io_thread;

static QemuThread *tcg_cpu_thread;
static QemuCond *tcg_halt_cond;

/* cpu creation */
static QemuCond qemu_cpu_cond;
/* system init */
static QemuCond qemu_pause_cond;
static QemuCond qemu_work_cond;

void qemu_init_cpu_loop(void)
{
    qemu_init_sigbus();
    qemu_cond_init(&qemu_cpu_cond);
    qemu_cond_init(&qemu_pause_cond);
    qemu_cond_init(&qemu_work_cond);
    qemu_cond_init(&qemu_io_proceeded_cond);
    qemu_mutex_init(&qemu_global_mutex);

    qemu_thread_get_self(&io_thread);
}

void run_on_cpu(CPUArchState *env, void (*func)(void *data), void *data)
{
    struct qemu_work_item wi;

    if (qemu_cpu_is_self(env)) {
        func(data);
        return;
    }

    wi.func = func;
    wi.data = data;
    if (!env->queued_work_first) {
        env->queued_work_first = &wi;
    } else {
        env->queued_work_last->next = &wi;
    }
    env->queued_work_last = &wi;
    wi.next = NULL;
    wi.done = false;

    qemu_cpu_kick(env);
    while (!wi.done) {
        CPUArchState *self_env = cpu_single_env;

        qemu_cond_wait(&qemu_work_cond, &qemu_global_mutex);
        cpu_single_env = self_env;
    }
}

static void flush_queued_work(CPUArchState *env)
{
    struct qemu_work_item *wi;

    if (!env->queued_work_first) {
        return;
    }

    while ((wi = env->queued_work_first)) {
        env->queued_work_first = wi->next;
        wi->func(wi->data);
        wi->done = true;
    }
    env->queued_work_last = NULL;
    qemu_cond_broadcast(&qemu_work_cond);
}

static void qemu_wait_io_event_common(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);

    if (env->stop) {
        env->stop = 0;
        env->stopped = 1;
        qemu_cond_signal(&qemu_pause_cond);
    }
    flush_queued_work(env);
    cpu->thread_kicked = false;
}

static void qemu_tcg_wait_io_event(void)
{
    CPUArchState *env;

    while (all_cpu_threads_idle()) {
       /* Start accounting real time to the virtual clock if the CPUs
          are idle.  */
        qemu_clock_warp(vm_clock);
        qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
    }

    while (iothread_requesting_mutex) {
        qemu_cond_wait(&qemu_io_proceeded_cond, &qemu_global_mutex);
    }

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        qemu_wait_io_event_common(env);
    }
}

static void qemu_kvm_wait_io_event(CPUArchState *env)
{
    while (cpu_thread_is_idle(env)) {
        qemu_cond_wait(env->halt_cond, &qemu_global_mutex);
    }

    qemu_kvm_eat_signals(env);
    qemu_wait_io_event_common(env);
}

static void *qemu_kvm_cpu_thread_fn(void *arg)
{
    CPUArchState *env = arg;
    CPUState *cpu = ENV_GET_CPU(env);
    int r;

    qemu_mutex_lock(&qemu_global_mutex);
    qemu_thread_get_self(cpu->thread);
    env->thread_id = qemu_get_thread_id();
    cpu_single_env = env;

    r = kvm_init_vcpu(env);
    if (r < 0) {
        fprintf(stderr, "kvm_init_vcpu failed: %s\n", strerror(-r));
        exit(1);
    }

    qemu_kvm_init_cpu_signals(env);

    /* signal CPU creation */
    env->created = 1;
    qemu_cond_signal(&qemu_cpu_cond);

    while (1) {
        if (cpu_can_run(env)) {
            r = kvm_cpu_exec(env);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(env);
            }
        }
        qemu_kvm_wait_io_event(env);
    }

    return NULL;
}

static void *qemu_dummy_cpu_thread_fn(void *arg)
{
#ifdef _WIN32
    fprintf(stderr, "qtest is not supported under Windows\n");
    exit(1);
#else
    CPUArchState *env = arg;
    CPUState *cpu = ENV_GET_CPU(env);
    sigset_t waitset;
    int r;

    qemu_mutex_lock_iothread();
    qemu_thread_get_self(cpu->thread);
    env->thread_id = qemu_get_thread_id();

    sigemptyset(&waitset);
    sigaddset(&waitset, SIG_IPI);

    /* signal CPU creation */
    env->created = 1;
    qemu_cond_signal(&qemu_cpu_cond);

    cpu_single_env = env;
    while (1) {
        cpu_single_env = NULL;
        qemu_mutex_unlock_iothread();
        do {
            int sig;
            r = sigwait(&waitset, &sig);
        } while (r == -1 && (errno == EAGAIN || errno == EINTR));
        if (r == -1) {
            perror("sigwait");
            exit(1);
        }
        qemu_mutex_lock_iothread();
        cpu_single_env = env;
        qemu_wait_io_event_common(env);
    }

    return NULL;
#endif
}

static void tcg_exec_all(void);

static void *qemu_tcg_cpu_thread_fn(void *arg)
{
    CPUArchState *env = arg;
    CPUState *cpu = ENV_GET_CPU(env);

    qemu_tcg_init_cpu_signals();
    qemu_thread_get_self(cpu->thread);

    /* signal CPU creation */
    qemu_mutex_lock(&qemu_global_mutex);
    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        env->thread_id = qemu_get_thread_id();
        env->created = 1;
    }
    qemu_cond_signal(&qemu_cpu_cond);

    /* wait for initial kick-off after machine start */
    while (first_cpu->stopped) {
        qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);

        /* process any pending work */
        for (env = first_cpu; env != NULL; env = env->next_cpu) {
            qemu_wait_io_event_common(env);
        }
    }

    while (1) {
        tcg_exec_all();
        if (use_icount && qemu_clock_deadline(vm_clock) <= 0) {
            qemu_notify_event();
        }
        qemu_tcg_wait_io_event();
    }

    return NULL;
}

static void qemu_cpu_kick_thread(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);
#ifndef _WIN32
    int err;

    err = pthread_kill(cpu->thread->thread, SIG_IPI);
    if (err) {
        fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
        exit(1);
    }
#else /* _WIN32 */
    if (!qemu_cpu_is_self(env)) {
        SuspendThread(cpu->hThread);
        cpu_signal(0);
        ResumeThread(cpu->hThread);
    }
#endif
}

void qemu_cpu_kick(void *_env)
{
    CPUArchState *env = _env;
    CPUState *cpu = ENV_GET_CPU(env);

    qemu_cond_broadcast(env->halt_cond);
    if (!tcg_enabled() && !cpu->thread_kicked) {
        qemu_cpu_kick_thread(env);
        cpu->thread_kicked = true;
    }
}

void qemu_cpu_kick_self(void)
{
#ifndef _WIN32
    assert(cpu_single_env);
    CPUState *cpu_single_cpu = ENV_GET_CPU(cpu_single_env);

    if (!cpu_single_cpu->thread_kicked) {
        qemu_cpu_kick_thread(cpu_single_env);
        cpu_single_cpu->thread_kicked = true;
    }
#else
    abort();
#endif
}

int qemu_cpu_is_self(void *_env)
{
    CPUArchState *env = _env;
    CPUState *cpu = ENV_GET_CPU(env);

    return qemu_thread_is_self(cpu->thread);
}

void qemu_mutex_lock_iothread(void)
{
    if (!tcg_enabled()) {
        qemu_mutex_lock(&qemu_global_mutex);
    } else {
        iothread_requesting_mutex = true;
        if (qemu_mutex_trylock(&qemu_global_mutex)) {
            qemu_cpu_kick_thread(first_cpu);
            qemu_mutex_lock(&qemu_global_mutex);
        }
        iothread_requesting_mutex = false;
        qemu_cond_broadcast(&qemu_io_proceeded_cond);
    }
}

void qemu_mutex_unlock_iothread(void)
{
    qemu_mutex_unlock(&qemu_global_mutex);
}

static int all_vcpus_paused(void)
{
    CPUArchState *penv = first_cpu;

    while (penv) {
        if (!penv->stopped) {
            return 0;
        }
        penv = penv->next_cpu;
    }

    return 1;
}

void pause_all_vcpus(void)
{
    CPUArchState *penv = first_cpu;

    qemu_clock_enable(vm_clock, false);
    while (penv) {
        penv->stop = 1;
        qemu_cpu_kick(penv);
        penv = penv->next_cpu;
    }

    if (!qemu_thread_is_self(&io_thread)) {
        cpu_stop_current();
        if (!kvm_enabled()) {
            while (penv) {
                penv->stop = 0;
                penv->stopped = 1;
                penv = penv->next_cpu;
            }
            return;
        }
    }

    while (!all_vcpus_paused()) {
        qemu_cond_wait(&qemu_pause_cond, &qemu_global_mutex);
        penv = first_cpu;
        while (penv) {
            qemu_cpu_kick(penv);
            penv = penv->next_cpu;
        }
    }
}

void resume_all_vcpus(void)
{
    CPUArchState *penv = first_cpu;

    qemu_clock_enable(vm_clock, true);
    while (penv) {
        penv->stop = 0;
        penv->stopped = 0;
        qemu_cpu_kick(penv);
        penv = penv->next_cpu;
    }
}

static void qemu_tcg_init_vcpu(void *_env)
{
    CPUArchState *env = _env;
    CPUState *cpu = ENV_GET_CPU(env);

    /* share a single thread for all cpus with TCG */
    if (!tcg_cpu_thread) {
        cpu->thread = g_malloc0(sizeof(QemuThread));
        env->halt_cond = g_malloc0(sizeof(QemuCond));
        qemu_cond_init(env->halt_cond);
        tcg_halt_cond = env->halt_cond;
        qemu_thread_create(cpu->thread, qemu_tcg_cpu_thread_fn, env,
                           QEMU_THREAD_JOINABLE);
#ifdef _WIN32
        cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
        while (env->created == 0) {
            qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
        }
        tcg_cpu_thread = cpu->thread;
    } else {
        cpu->thread = tcg_cpu_thread;
        env->halt_cond = tcg_halt_cond;
    }
}

static void qemu_kvm_start_vcpu(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);

    cpu->thread = g_malloc0(sizeof(QemuThread));
    env->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(env->halt_cond);
    qemu_thread_create(cpu->thread, qemu_kvm_cpu_thread_fn, env,
                       QEMU_THREAD_JOINABLE);
    while (env->created == 0) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

static void qemu_dummy_start_vcpu(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);

    cpu->thread = g_malloc0(sizeof(QemuThread));
    env->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(env->halt_cond);
    qemu_thread_create(cpu->thread, qemu_dummy_cpu_thread_fn, env,
                       QEMU_THREAD_JOINABLE);
    while (env->created == 0) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
}

void qemu_init_vcpu(void *_env)
{
    CPUArchState *env = _env;

    env->nr_cores = smp_cores;
    env->nr_threads = smp_threads;
    env->stopped = 1;
    if (kvm_enabled()) {
        qemu_kvm_start_vcpu(env);
    } else if (tcg_enabled()) {
        qemu_tcg_init_vcpu(env);
    } else {
        qemu_dummy_start_vcpu(env);
    }
}

void cpu_stop_current(void)
{
    if (cpu_single_env) {
        cpu_single_env->stop = 0;
        cpu_single_env->stopped = 1;
        cpu_exit(cpu_single_env);
        qemu_cond_signal(&qemu_pause_cond);
    }
}

void vm_stop(RunState state)
{
    if (!qemu_thread_is_self(&io_thread)) {
        qemu_system_vmstop_request(state);
        /*
         * FIXME: should not return to device code in case
         * vm_stop() has been requested.
         */
        cpu_stop_current();
        return;
    }
    do_vm_stop(state);
}

/* does a state transition even if the VM is already stopped,
   current state is forgotten forever */
void vm_stop_force_state(RunState state)
{
    if (runstate_is_running()) {
        vm_stop(state);
    } else {
        runstate_set(state);
    }
}

static int tcg_cpu_exec(CPUArchState *env)
{
    int ret;
#ifdef CONFIG_PROFILER
    int64_t ti;
#endif

#ifdef CONFIG_PROFILER
    ti = profile_getclock();
#endif
    if (use_icount) {
        int64_t count;
        int decr;
        qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
        env->icount_decr.u16.low = 0;
        env->icount_extra = 0;
        count = qemu_icount_round(qemu_clock_deadline(vm_clock));
        qemu_icount += count;
        decr = (count > 0xffff) ? 0xffff : count;
        count -= decr;
        env->icount_decr.u16.low = decr;
        env->icount_extra = count;
    }
    ret = cpu_exec(env);
#ifdef CONFIG_PROFILER
    qemu_time += profile_getclock() - ti;
#endif
    if (use_icount) {
        /* Fold pending instructions back into the
           instruction counter, and clear the interrupt flag.  */
        qemu_icount -= (env->icount_decr.u16.low
                        + env->icount_extra);
        env->icount_decr.u32 = 0;
        env->icount_extra = 0;
    }
    return ret;
}

static void tcg_exec_all(void)
{
    int r;

    /* Account partial waits to the vm_clock.  */
    qemu_clock_warp(vm_clock);

    if (next_cpu == NULL) {
        next_cpu = first_cpu;
    }
    for (; next_cpu != NULL && !exit_request; next_cpu = next_cpu->next_cpu) {
        CPUArchState *env = next_cpu;

        qemu_clock_enable(vm_clock,
                          (env->singlestep_enabled & SSTEP_NOTIMER) == 0);

        if (cpu_can_run(env)) {
            r = tcg_cpu_exec(env);
            if (r == EXCP_DEBUG) {
                cpu_handle_guest_debug(env);
                break;
            }
        } else if (env->stop || env->stopped) {
            break;
        }
    }
    exit_request = 0;
}

void set_numa_modes(void)
{
    CPUArchState *env;
    int i;

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        for (i = 0; i < nb_numa_nodes; i++) {
            if (test_bit(env->cpu_index, node_cpumask[i])) {
                env->numa_node = i;
            }
        }
    }
}

void set_cpu_log(const char *optarg)
{
    int mask;
    const CPULogItem *item;

    mask = cpu_str_to_log_mask(optarg);
    if (!mask) {
        printf("Log items (comma separated):\n");
        for (item = cpu_log_items; item->mask != 0; item++) {
            printf("%-10s %s\n", item->name, item->help);
        }
        exit(1);
    }
    cpu_set_log(mask);
}

void set_cpu_log_filename(const char *optarg)
{
    cpu_set_log_filename(optarg);
}

void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
{
    /* XXX: implement xxx_cpu_list for targets that still miss it */
#if defined(cpu_list_id)
    cpu_list_id(f, cpu_fprintf, optarg);
#elif defined(cpu_list)
    cpu_list(f, cpu_fprintf); /* deprecated */
#endif
}

CpuInfoList *qmp_query_cpus(Error **errp)
{
    CpuInfoList *head = NULL, *cur_item = NULL;
    CPUArchState *env;

    for(env = first_cpu; env != NULL; env = env->next_cpu) {
        CpuInfoList *info;

        cpu_synchronize_state(env);

        info = g_malloc0(sizeof(*info));
        info->value = g_malloc0(sizeof(*info->value));
        info->value->CPU = env->cpu_index;
        info->value->current = (env == first_cpu);
        info->value->halted = env->halted;
        info->value->thread_id = env->thread_id;
#if defined(TARGET_I386)
        info->value->has_pc = true;
        info->value->pc = env->eip + env->segs[R_CS].base;
#elif defined(TARGET_PPC)
        info->value->has_nip = true;
        info->value->nip = env->nip;
#elif defined(TARGET_SPARC)
        info->value->has_pc = true;
        info->value->pc = env->pc;
        info->value->has_npc = true;
        info->value->npc = env->npc;
#elif defined(TARGET_MIPS)
        info->value->has_PC = true;
        info->value->PC = env->active_tc.PC;
#endif

        /* XXX: waiting for the qapi to support GSList */
        if (!cur_item) {
            head = cur_item = info;
        } else {
            cur_item->next = info;
            cur_item = info;
        }
    }

    return head;
}

void qmp_memsave(int64_t addr, int64_t size, const char *filename,
                 bool has_cpu, int64_t cpu_index, Error **errp)
{
    FILE *f;
    uint32_t l;
    CPUArchState *env;
    uint8_t buf[1024];

    if (!has_cpu) {
        cpu_index = 0;
    }

    for (env = first_cpu; env; env = env->next_cpu) {
        if (cpu_index == env->cpu_index) {
            break;
        }
    }

    if (env == NULL) {
        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cpu-index",
                  "a CPU number");
        return;
    }

    f = fopen(filename, "wb");
    if (!f) {
        error_set(errp, QERR_OPEN_FILE_FAILED, filename);
        return;
    }

    while (size != 0) {
        l = sizeof(buf);
        if (l > size)
            l = size;
        cpu_memory_rw_debug(env, addr, buf, l, 0);
        if (fwrite(buf, 1, l, f) != l) {
            error_set(errp, QERR_IO_ERROR);
            goto exit;
        }
        addr += l;
        size -= l;
    }

exit:
    fclose(f);
}

void qmp_pmemsave(int64_t addr, int64_t size, const char *filename,
                  Error **errp)
{
    FILE *f;
    uint32_t l;
    uint8_t buf[1024];

    f = fopen(filename, "wb");
    if (!f) {
        error_set(errp, QERR_OPEN_FILE_FAILED, filename);
        return;
    }

    while (size != 0) {
        l = sizeof(buf);
        if (l > size)
            l = size;
        cpu_physical_memory_rw(addr, buf, l, 0);
        if (fwrite(buf, 1, l, f) != l) {
            error_set(errp, QERR_IO_ERROR);
            goto exit;
        }
        addr += l;
        size -= l;
    }

exit:
    fclose(f);
}

void qmp_inject_nmi(Error **errp)
{
#if defined(TARGET_I386)
    CPUArchState *env;

    for (env = first_cpu; env != NULL; env = env->next_cpu) {
        if (!env->apic_state) {
            cpu_interrupt(env, CPU_INTERRUPT_NMI);
        } else {
            apic_deliver_nmi(env->apic_state);
        }
    }
#else
    error_set(errp, QERR_UNSUPPORTED);
#endif
}