summaryrefslogtreecommitdiff
path: root/qemu-timer.c
blob: b8c0c8870debc6de47b675075599da1b0575617b (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
/*
 * 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.
 */

#include "sysemu.h"
#include "net.h"
#include "monitor.h"
#include "console.h"

#include "hw/hw.h"

#include <unistd.h>
#include <fcntl.h>
#include <time.h>
#include <errno.h>
#include <sys/time.h>
#include <signal.h>
#ifdef __FreeBSD__
#include <sys/param.h>
#endif

#ifdef __linux__
#include <sys/ioctl.h>
#include <linux/rtc.h>
/* For the benefit of older linux systems which don't supply it,
   we use a local copy of hpet.h. */
/* #include <linux/hpet.h> */
#include "hpet.h"
#endif

#ifdef _WIN32
#include <windows.h>
#include <mmsystem.h>
#endif

#include "qemu-timer.h"

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

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

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 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 */
static 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;
    }
}

#ifndef CONFIG_IOTHREAD
static int64_t qemu_icount_delta(void)
{
    if (!use_icount) {
        return 5000 * (int64_t) 1000000;
    } else if (use_icount == 1) {
        /* When not using an adaptive execution frequency
           we tend to get badly out of sync with real time,
           so just delay for a reasonable amount of time.  */
        return 0;
    } else {
        return cpu_get_icount() - cpu_get_clock();
    }
}
#endif

/* 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;
    }
}

/***********************************************************/
/* timers */

#define QEMU_CLOCK_REALTIME 0
#define QEMU_CLOCK_VIRTUAL  1
#define QEMU_CLOCK_HOST     2

struct QEMUClock {
    int type;
    int enabled;

    QEMUTimer *warp_timer;
};

struct QEMUTimer {
    QEMUClock *clock;
    int64_t expire_time;	/* in nanoseconds */
    int scale;
    QEMUTimerCB *cb;
    void *opaque;
    struct QEMUTimer *next;
};

struct qemu_alarm_timer {
    char const *name;
    int (*start)(struct qemu_alarm_timer *t);
    void (*stop)(struct qemu_alarm_timer *t);
    void (*rearm)(struct qemu_alarm_timer *t);
    void *priv;

    char expired;
    char pending;
};

static struct qemu_alarm_timer *alarm_timer;

int qemu_alarm_pending(void)
{
    return alarm_timer->pending;
}

static inline int alarm_has_dynticks(struct qemu_alarm_timer *t)
{
    return !!t->rearm;
}

static void qemu_rearm_alarm_timer(struct qemu_alarm_timer *t)
{
    if (!alarm_has_dynticks(t))
        return;

    t->rearm(t);
}

/* TODO: MIN_TIMER_REARM_NS should be optimized */
#define MIN_TIMER_REARM_NS 250000

#ifdef _WIN32

static int win32_start_timer(struct qemu_alarm_timer *t);
static void win32_stop_timer(struct qemu_alarm_timer *t);
static void win32_rearm_timer(struct qemu_alarm_timer *t);

#else

static int unix_start_timer(struct qemu_alarm_timer *t);
static void unix_stop_timer(struct qemu_alarm_timer *t);

#ifdef __linux__

static int dynticks_start_timer(struct qemu_alarm_timer *t);
static void dynticks_stop_timer(struct qemu_alarm_timer *t);
static void dynticks_rearm_timer(struct qemu_alarm_timer *t);

static int hpet_start_timer(struct qemu_alarm_timer *t);
static void hpet_stop_timer(struct qemu_alarm_timer *t);

static int rtc_start_timer(struct qemu_alarm_timer *t);
static void rtc_stop_timer(struct qemu_alarm_timer *t);

#endif /* __linux__ */

#endif /* _WIN32 */

/* 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 (!vm_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();
}

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

static struct qemu_alarm_timer alarm_timers[] = {
#ifndef _WIN32
#ifdef __linux__
    {"dynticks", dynticks_start_timer,
     dynticks_stop_timer, dynticks_rearm_timer, NULL},
    /* HPET - if available - is preferred */
    {"hpet", hpet_start_timer, hpet_stop_timer, NULL, NULL},
    /* ...otherwise try RTC */
    {"rtc", rtc_start_timer, rtc_stop_timer, NULL, NULL},
#endif
    {"unix", unix_start_timer, unix_stop_timer, NULL, NULL},
#else
    {"dynticks", win32_start_timer,
     win32_stop_timer, win32_rearm_timer, NULL},
    {"win32", win32_start_timer,
     win32_stop_timer, NULL, NULL},
#endif
    {NULL, }
};

static void show_available_alarms(void)
{
    int i;

    printf("Available alarm timers, in order of precedence:\n");
    for (i = 0; alarm_timers[i].name; i++)
        printf("%s\n", alarm_timers[i].name);
}

void configure_alarms(char const *opt)
{
    int i;
    int cur = 0;
    int count = ARRAY_SIZE(alarm_timers) - 1;
    char *arg;
    char *name;
    struct qemu_alarm_timer tmp;

    if (!strcmp(opt, "?")) {
        show_available_alarms();
        exit(0);
    }

    arg = qemu_strdup(opt);

    /* Reorder the array */
    name = strtok(arg, ",");
    while (name) {
        for (i = 0; i < count && alarm_timers[i].name; i++) {
            if (!strcmp(alarm_timers[i].name, name))
                break;
        }

        if (i == count) {
            fprintf(stderr, "Unknown clock %s\n", name);
            goto next;
        }

        if (i < cur)
            /* Ignore */
            goto next;

	/* Swap */
        tmp = alarm_timers[i];
        alarm_timers[i] = alarm_timers[cur];
        alarm_timers[cur] = tmp;

        cur++;
next:
        name = strtok(NULL, ",");
    }

    qemu_free(arg);

    if (cur) {
        /* Disable remaining timers */
        for (i = cur; i < count; i++)
            alarm_timers[i].name = NULL;
    } else {
        show_available_alarms();
        exit(1);
    }
}

#define QEMU_NUM_CLOCKS 3

QEMUClock *rt_clock;
QEMUClock *vm_clock;
QEMUClock *host_clock;

static QEMUTimer *active_timers[QEMU_NUM_CLOCKS];

static QEMUClock *qemu_new_clock(int type)
{
    QEMUClock *clock;
    clock = qemu_mallocz(sizeof(QEMUClock));
    clock->type = type;
    clock->enabled = 1;
    return clock;
}

void qemu_clock_enable(QEMUClock *clock, int enabled)
{
    clock->enabled = enabled;
}

static int64_t vm_clock_warp_start;

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

    if (vm_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_timer_expired(active_timers[QEMU_CLOCK_VIRTUAL],
                               qemu_get_clock_ns(vm_clock))) {
            qemu_notify_event();
        }
    }
    vm_clock_warp_start = -1;
}

void qemu_clock_warp(QEMUClock *clock)
{
    int64_t deadline;

    if (!clock->warp_timer) {
        return;
    }

    /*
     * 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.
     */
    assert(clock == vm_clock);

    /*
     * 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() || !active_timers[clock->type]) {
        qemu_del_timer(clock->warp_timer);
        return;
    }

    vm_clock_warp_start = qemu_get_clock_ns(rt_clock);
    deadline = qemu_next_icount_deadline();
    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 continously instead of every 100ms.
         */
        qemu_mod_timer(clock->warp_timer, vm_clock_warp_start + deadline);
    } else {
        qemu_notify_event();
    }
}

QEMUTimer *qemu_new_timer(QEMUClock *clock, int scale,
                          QEMUTimerCB *cb, void *opaque)
{
    QEMUTimer *ts;

    ts = qemu_mallocz(sizeof(QEMUTimer));
    ts->clock = clock;
    ts->cb = cb;
    ts->opaque = opaque;
    ts->scale = scale;
    return ts;
}

void qemu_free_timer(QEMUTimer *ts)
{
    qemu_free(ts);
}

/* stop a timer, but do not dealloc it */
void qemu_del_timer(QEMUTimer *ts)
{
    QEMUTimer **pt, *t;

    /* NOTE: this code must be signal safe because
       qemu_timer_expired() can be called from a signal. */
    pt = &active_timers[ts->clock->type];
    for(;;) {
        t = *pt;
        if (!t)
            break;
        if (t == ts) {
            *pt = t->next;
            break;
        }
        pt = &t->next;
    }
}

/* modify the current timer so that it will be fired when current_time
   >= expire_time. The corresponding callback will be called. */
static void qemu_mod_timer_ns(QEMUTimer *ts, int64_t expire_time)
{
    QEMUTimer **pt, *t;

    qemu_del_timer(ts);

    /* add the timer in the sorted list */
    /* NOTE: this code must be signal safe because
       qemu_timer_expired() can be called from a signal. */
    pt = &active_timers[ts->clock->type];
    for(;;) {
        t = *pt;
        if (!t)
            break;
        if (t->expire_time > expire_time)
            break;
        pt = &t->next;
    }
    ts->expire_time = expire_time;
    ts->next = *pt;
    *pt = ts;

    /* Rearm if necessary  */
    if (pt == &active_timers[ts->clock->type]) {
        if (!alarm_timer->pending) {
            qemu_rearm_alarm_timer(alarm_timer);
        }
        /* Interrupt execution to force deadline recalculation.  */
        qemu_clock_warp(ts->clock);
        if (use_icount) {
            qemu_notify_event();
        }
    }
}

/* modify the current timer so that it will be fired when current_time
   >= expire_time. The corresponding callback will be called. */
void qemu_mod_timer(QEMUTimer *ts, int64_t expire_time)
{
    qemu_mod_timer_ns(ts, expire_time * ts->scale);
}

int qemu_timer_pending(QEMUTimer *ts)
{
    QEMUTimer *t;
    for(t = active_timers[ts->clock->type]; t != NULL; t = t->next) {
        if (t == ts)
            return 1;
    }
    return 0;
}

int qemu_timer_expired(QEMUTimer *timer_head, int64_t current_time)
{
    if (!timer_head)
        return 0;
    return (timer_head->expire_time <= current_time * timer_head->scale);
}

static void qemu_run_timers(QEMUClock *clock)
{
    QEMUTimer **ptimer_head, *ts;
    int64_t current_time;
   
    if (!clock->enabled)
        return;

    current_time = qemu_get_clock_ns(clock);
    ptimer_head = &active_timers[clock->type];
    for(;;) {
        ts = *ptimer_head;
        if (!ts || ts->expire_time > current_time)
            break;
        /* remove timer from the list before calling the callback */
        *ptimer_head = ts->next;
        ts->next = NULL;

        /* run the callback (the timer list can be modified) */
        ts->cb(ts->opaque);
    }
}

int64_t qemu_get_clock_ns(QEMUClock *clock)
{
    switch(clock->type) {
    case QEMU_CLOCK_REALTIME:
        return get_clock();
    default:
    case QEMU_CLOCK_VIRTUAL:
        if (use_icount) {
            return cpu_get_icount();
        } else {
            return cpu_get_clock();
        }
    case QEMU_CLOCK_HOST:
        return get_clock_realtime();
    }
}

void init_clocks(void)
{
    rt_clock = qemu_new_clock(QEMU_CLOCK_REALTIME);
    vm_clock = qemu_new_clock(QEMU_CLOCK_VIRTUAL);
    host_clock = qemu_new_clock(QEMU_CLOCK_HOST);

    rtc_clock = host_clock;
}

/* save a timer */
void qemu_put_timer(QEMUFile *f, QEMUTimer *ts)
{
    uint64_t expire_time;

    if (qemu_timer_pending(ts)) {
        expire_time = ts->expire_time;
    } else {
        expire_time = -1;
    }
    qemu_put_be64(f, expire_time);
}

void qemu_get_timer(QEMUFile *f, QEMUTimer *ts)
{
    uint64_t expire_time;

    expire_time = qemu_get_be64(f);
    if (expire_time != -1) {
        qemu_mod_timer_ns(ts, expire_time);
    } else {
        qemu_del_timer(ts);
    }
}

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;

#ifdef CONFIG_IOTHREAD
    vm_clock->warp_timer = qemu_new_timer_ns(rt_clock, icount_warp_rt, NULL);
#endif

    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 qemu_run_all_timers(void)
{
    alarm_timer->pending = 0;

    /* rearm timer, if not periodic */
    if (alarm_timer->expired) {
        alarm_timer->expired = 0;
        qemu_rearm_alarm_timer(alarm_timer);
    }

    /* vm time timers */
    if (vm_running) {
        qemu_run_timers(vm_clock);
    }

    qemu_run_timers(rt_clock);
    qemu_run_timers(host_clock);
}

static int64_t qemu_next_alarm_deadline(void);

#ifdef _WIN32
static void CALLBACK host_alarm_handler(PVOID lpParam, BOOLEAN unused)
#else
static void host_alarm_handler(int host_signum)
#endif
{
    struct qemu_alarm_timer *t = alarm_timer;
    if (!t)
	return;

#if 0
#define DISP_FREQ 1000
    {
        static int64_t delta_min = INT64_MAX;
        static int64_t delta_max, delta_cum, last_clock, delta, ti;
        static int count;
        ti = qemu_get_clock_ns(vm_clock);
        if (last_clock != 0) {
            delta = ti - last_clock;
            if (delta < delta_min)
                delta_min = delta;
            if (delta > delta_max)
                delta_max = delta;
            delta_cum += delta;
            if (++count == DISP_FREQ) {
                printf("timer: min=%" PRId64 " us max=%" PRId64 " us avg=%" PRId64 " us avg_freq=%0.3f Hz\n",
                       muldiv64(delta_min, 1000000, get_ticks_per_sec()),
                       muldiv64(delta_max, 1000000, get_ticks_per_sec()),
                       muldiv64(delta_cum, 1000000 / DISP_FREQ, get_ticks_per_sec()),
                       (double)get_ticks_per_sec() / ((double)delta_cum / DISP_FREQ));
                count = 0;
                delta_min = INT64_MAX;
                delta_max = 0;
                delta_cum = 0;
            }
        }
        last_clock = ti;
    }
#endif
    if (alarm_has_dynticks(t) ||
        qemu_next_alarm_deadline () <= 0) {
        t->expired = alarm_has_dynticks(t);
        t->pending = 1;
        qemu_notify_event();
    }
}

int64_t qemu_next_icount_deadline(void)
{
    /* To avoid problems with overflow limit this to 2^32.  */
    int64_t delta = INT32_MAX;

    assert(use_icount);
    if (active_timers[QEMU_CLOCK_VIRTUAL]) {
        delta = active_timers[QEMU_CLOCK_VIRTUAL]->expire_time -
                     qemu_get_clock_ns(vm_clock);
    }

    if (delta < 0)
        delta = 0;

    return delta;
}

static int64_t qemu_next_alarm_deadline(void)
{
    int64_t delta;
    int64_t rtdelta;

    if (!use_icount && active_timers[QEMU_CLOCK_VIRTUAL]) {
        delta = active_timers[QEMU_CLOCK_VIRTUAL]->expire_time -
                     qemu_get_clock_ns(vm_clock);
    } else {
        delta = INT32_MAX;
    }
    if (active_timers[QEMU_CLOCK_HOST]) {
        int64_t hdelta = active_timers[QEMU_CLOCK_HOST]->expire_time -
                 qemu_get_clock_ns(host_clock);
        if (hdelta < delta)
            delta = hdelta;
    }
    if (active_timers[QEMU_CLOCK_REALTIME]) {
        rtdelta = (active_timers[QEMU_CLOCK_REALTIME]->expire_time -
                 qemu_get_clock_ns(rt_clock));
        if (rtdelta < delta)
            delta = rtdelta;
    }

    return delta;
}

#if defined(__linux__)

#define RTC_FREQ 1024

static void enable_sigio_timer(int fd)
{
    struct sigaction act;

    /* timer signal */
    sigfillset(&act.sa_mask);
    act.sa_flags = 0;
    act.sa_handler = host_alarm_handler;

    sigaction(SIGIO, &act, NULL);
    fcntl_setfl(fd, O_ASYNC);
    fcntl(fd, F_SETOWN, getpid());
}

static int hpet_start_timer(struct qemu_alarm_timer *t)
{
    struct hpet_info info;
    int r, fd;

    fd = qemu_open("/dev/hpet", O_RDONLY);
    if (fd < 0)
        return -1;

    /* Set frequency */
    r = ioctl(fd, HPET_IRQFREQ, RTC_FREQ);
    if (r < 0) {
        fprintf(stderr, "Could not configure '/dev/hpet' to have a 1024Hz timer. This is not a fatal\n"
                "error, but for better emulation accuracy type:\n"
                "'echo 1024 > /proc/sys/dev/hpet/max-user-freq' as root.\n");
        goto fail;
    }

    /* Check capabilities */
    r = ioctl(fd, HPET_INFO, &info);
    if (r < 0)
        goto fail;

    /* Enable periodic mode */
    r = ioctl(fd, HPET_EPI, 0);
    if (info.hi_flags && (r < 0))
        goto fail;

    /* Enable interrupt */
    r = ioctl(fd, HPET_IE_ON, 0);
    if (r < 0)
        goto fail;

    enable_sigio_timer(fd);
    t->priv = (void *)(long)fd;

    return 0;
fail:
    close(fd);
    return -1;
}

static void hpet_stop_timer(struct qemu_alarm_timer *t)
{
    int fd = (long)t->priv;

    close(fd);
}

static int rtc_start_timer(struct qemu_alarm_timer *t)
{
    int rtc_fd;
    unsigned long current_rtc_freq = 0;

    TFR(rtc_fd = qemu_open("/dev/rtc", O_RDONLY));
    if (rtc_fd < 0)
        return -1;
    ioctl(rtc_fd, RTC_IRQP_READ, &current_rtc_freq);
    if (current_rtc_freq != RTC_FREQ &&
        ioctl(rtc_fd, RTC_IRQP_SET, RTC_FREQ) < 0) {
        fprintf(stderr, "Could not configure '/dev/rtc' to have a 1024 Hz timer. This is not a fatal\n"
                "error, but for better emulation accuracy either use a 2.6 host Linux kernel or\n"
                "type 'echo 1024 > /proc/sys/dev/rtc/max-user-freq' as root.\n");
        goto fail;
    }
    if (ioctl(rtc_fd, RTC_PIE_ON, 0) < 0) {
    fail:
        close(rtc_fd);
        return -1;
    }

    enable_sigio_timer(rtc_fd);

    t->priv = (void *)(long)rtc_fd;

    return 0;
}

static void rtc_stop_timer(struct qemu_alarm_timer *t)
{
    int rtc_fd = (long)t->priv;

    close(rtc_fd);
}

static int dynticks_start_timer(struct qemu_alarm_timer *t)
{
    struct sigevent ev;
    timer_t host_timer;
    struct sigaction act;

    sigfillset(&act.sa_mask);
    act.sa_flags = 0;
    act.sa_handler = host_alarm_handler;

    sigaction(SIGALRM, &act, NULL);

    /* 
     * Initialize ev struct to 0 to avoid valgrind complaining
     * about uninitialized data in timer_create call
     */
    memset(&ev, 0, sizeof(ev));
    ev.sigev_value.sival_int = 0;
    ev.sigev_notify = SIGEV_SIGNAL;
    ev.sigev_signo = SIGALRM;

    if (timer_create(CLOCK_REALTIME, &ev, &host_timer)) {
        perror("timer_create");

        /* disable dynticks */
        fprintf(stderr, "Dynamic Ticks disabled\n");

        return -1;
    }

    t->priv = (void *)(long)host_timer;

    return 0;
}

static void dynticks_stop_timer(struct qemu_alarm_timer *t)
{
    timer_t host_timer = (timer_t)(long)t->priv;

    timer_delete(host_timer);
}

static void dynticks_rearm_timer(struct qemu_alarm_timer *t)
{
    timer_t host_timer = (timer_t)(long)t->priv;
    struct itimerspec timeout;
    int64_t nearest_delta_ns = INT64_MAX;
    int64_t current_ns;

    assert(alarm_has_dynticks(t));
    if (!active_timers[QEMU_CLOCK_REALTIME] &&
        !active_timers[QEMU_CLOCK_VIRTUAL] &&
        !active_timers[QEMU_CLOCK_HOST])
        return;

    nearest_delta_ns = qemu_next_alarm_deadline();
    if (nearest_delta_ns < MIN_TIMER_REARM_NS)
        nearest_delta_ns = MIN_TIMER_REARM_NS;

    /* check whether a timer is already running */
    if (timer_gettime(host_timer, &timeout)) {
        perror("gettime");
        fprintf(stderr, "Internal timer error: aborting\n");
        exit(1);
    }
    current_ns = timeout.it_value.tv_sec * 1000000000LL + timeout.it_value.tv_nsec;
    if (current_ns && current_ns <= nearest_delta_ns)
        return;

    timeout.it_interval.tv_sec = 0;
    timeout.it_interval.tv_nsec = 0; /* 0 for one-shot timer */
    timeout.it_value.tv_sec =  nearest_delta_ns / 1000000000;
    timeout.it_value.tv_nsec = nearest_delta_ns % 1000000000;
    if (timer_settime(host_timer, 0 /* RELATIVE */, &timeout, NULL)) {
        perror("settime");
        fprintf(stderr, "Internal timer error: aborting\n");
        exit(1);
    }
}

#endif /* defined(__linux__) */

#if !defined(_WIN32)

static int unix_start_timer(struct qemu_alarm_timer *t)
{
    struct sigaction act;
    struct itimerval itv;
    int err;

    /* timer signal */
    sigfillset(&act.sa_mask);
    act.sa_flags = 0;
    act.sa_handler = host_alarm_handler;

    sigaction(SIGALRM, &act, NULL);

    itv.it_interval.tv_sec = 0;
    /* for i386 kernel 2.6 to get 1 ms */
    itv.it_interval.tv_usec = 999;
    itv.it_value.tv_sec = 0;
    itv.it_value.tv_usec = 10 * 1000;

    err = setitimer(ITIMER_REAL, &itv, NULL);
    if (err)
        return -1;

    return 0;
}

static void unix_stop_timer(struct qemu_alarm_timer *t)
{
    struct itimerval itv;

    memset(&itv, 0, sizeof(itv));
    setitimer(ITIMER_REAL, &itv, NULL);
}

#endif /* !defined(_WIN32) */


#ifdef _WIN32

static int win32_start_timer(struct qemu_alarm_timer *t)
{
    HANDLE hTimer;
    BOOLEAN success;

    /* If you call ChangeTimerQueueTimer on a one-shot timer (its period
       is zero) that has already expired, the timer is not updated.  Since
       creating a new timer is relatively expensive, set a bogus one-hour
       interval in the dynticks case.  */
    success = CreateTimerQueueTimer(&hTimer,
                          NULL,
                          host_alarm_handler,
                          t,
                          1,
                          alarm_has_dynticks(t) ? 3600000 : 1,
                          WT_EXECUTEINTIMERTHREAD);

    if (!success) {
        fprintf(stderr, "Failed to initialize win32 alarm timer: %ld\n",
                GetLastError());
        return -1;
    }

    t->priv = (PVOID) hTimer;
    return 0;
}

static void win32_stop_timer(struct qemu_alarm_timer *t)
{
    HANDLE hTimer = t->priv;

    if (hTimer) {
        DeleteTimerQueueTimer(NULL, hTimer, NULL);
    }
}

static void win32_rearm_timer(struct qemu_alarm_timer *t)
{
    HANDLE hTimer = t->priv;
    int nearest_delta_ms;
    BOOLEAN success;

    assert(alarm_has_dynticks(t));
    if (!active_timers[QEMU_CLOCK_REALTIME] &&
        !active_timers[QEMU_CLOCK_VIRTUAL] &&
        !active_timers[QEMU_CLOCK_HOST])
        return;

    nearest_delta_ms = (qemu_next_alarm_deadline() + 999999) / 1000000;
    if (nearest_delta_ms < 1) {
        nearest_delta_ms = 1;
    }
    success = ChangeTimerQueueTimer(NULL,
                                    hTimer,
                                    nearest_delta_ms,
                                    3600000);

    if (!success) {
        fprintf(stderr, "Failed to rearm win32 alarm timer: %ld\n",
                GetLastError());
        exit(-1);
    }

}

#endif /* _WIN32 */

static void alarm_timer_on_change_state_rearm(void *opaque, int running, int reason)
{
    if (running)
        qemu_rearm_alarm_timer((struct qemu_alarm_timer *) opaque);
}

int init_timer_alarm(void)
{
    struct qemu_alarm_timer *t = NULL;
    int i, err = -1;

    for (i = 0; alarm_timers[i].name; i++) {
        t = &alarm_timers[i];

        err = t->start(t);
        if (!err)
            break;
    }

    if (err) {
        err = -ENOENT;
        goto fail;
    }

    /* first event is at time 0 */
    t->pending = 1;
    alarm_timer = t;
    qemu_add_vm_change_state_handler(alarm_timer_on_change_state_rearm, t);

    return 0;

fail:
    return err;
}

void quit_timers(void)
{
    struct qemu_alarm_timer *t = alarm_timer;
    alarm_timer = NULL;
    t->stop(t);
}

int qemu_calculate_timeout(void)
{
#ifndef CONFIG_IOTHREAD
    int timeout;

    if (!vm_running)
        timeout = 5000;
    else {
     /* XXX: use timeout computed from timers */
        int64_t add;
        int64_t delta;
        /* Advance virtual time to the next event.  */
	delta = qemu_icount_delta();
        if (delta > 0) {
            /* If virtual time is ahead of real time then just
               wait for IO.  */
            timeout = (delta + 999999) / 1000000;
        } else {
            /* Wait for either IO to occur or the next
               timer event.  */
            add = qemu_next_icount_deadline();
            /* We advance the timer before checking for IO.
               Limit the amount we advance so that early IO
               activity won't get the guest too far ahead.  */
            if (add > 10000000)
                add = 10000000;
            delta += add;
            qemu_icount += qemu_icount_round (add);
            timeout = delta / 1000000;
            if (timeout < 0)
                timeout = 0;
        }
    }

    return timeout;
#else /* CONFIG_IOTHREAD */
    return 1000;
#endif
}