-
Notifications
You must be signed in to change notification settings - Fork 0
/
cpus.c
2321 lines (1982 loc) · 62.9 KB
/
cpus.c
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
/*
* 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 "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/config-file.h"
#include "migration/vmstate.h"
#include "monitor/monitor.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-misc.h"
#include "qapi/qapi-events-run-state.h"
#include "qapi/qmp/qerror.h"
#include "qemu/error-report.h"
#include "qemu/qemu-print.h"
#include "sysemu/tcg.h"
#include "sysemu/block-backend.h"
#include "exec/gdbstub.h"
#include "sysemu/dma.h"
#include "sysemu/hw_accel.h"
#include "sysemu/kvm.h"
#include "sysemu/hax.h"
#include "sysemu/hvf.h"
#include "sysemu/whpx.h"
#include "exec/exec-all.h"
#include "qemu/thread.h"
#include "sysemu/cpus.h"
#include "sysemu/qtest.h"
#include "qemu/main-loop.h"
#include "qemu/option.h"
#include "qemu/bitmap.h"
#include "qemu/seqlock.h"
#include "qemu/guest-random.h"
#include "tcg.h"
#include "hw/nmi.h"
#include "sysemu/replay.h"
#include "sysemu/runstate.h"
#include "hw/boards.h"
#include "hw/hw.h"
#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 QemuMutex qemu_global_mutex;
int64_t max_delay;
int64_t max_advance;
/* vcpu throttling controls */
static QEMUTimer *throttle_timer;
static unsigned int throttle_percentage;
#define CPU_THROTTLE_PCT_MIN 1
#define CPU_THROTTLE_PCT_MAX 99
#define CPU_THROTTLE_TIMESLICE_NS 10000000
bool cpu_is_stopped(CPUState *cpu)
{
return cpu->stopped || !runstate_is_running();
}
static bool cpu_thread_is_idle(CPUState *cpu)
{
if (cpu->stop || cpu->queued_work_first) {
return false;
}
if (cpu_is_stopped(cpu)) {
return true;
}
if (!cpu->halted || cpu_has_work(cpu) ||
kvm_halt_in_kernel()) {
return false;
}
return true;
}
static bool all_cpu_threads_idle(void)
{
CPUState *cpu;
CPU_FOREACH(cpu) {
if (!cpu_thread_is_idle(cpu)) {
return false;
}
}
return true;
}
/***********************************************************/
/* guest cycle counter */
/* Protected by TimersState seqlock */
static bool icount_sleep = true;
/* Arbitrarily pick 1MIPS as the minimum allowable speed. */
#define MAX_ICOUNT_SHIFT 10
typedef struct TimersState {
/* Protected by BQL. */
int64_t cpu_ticks_prev;
int64_t cpu_ticks_offset;
/* Protect fields that can be respectively read outside the
* BQL, and written from multiple threads.
*/
QemuSeqLock vm_clock_seqlock;
QemuSpin vm_clock_lock;
int16_t cpu_ticks_enabled;
/* Conversion factor from emulated instructions to virtual clock ticks. */
int16_t icount_time_shift;
/* Compensate for varying guest execution speed. */
int64_t qemu_icount_bias;
int64_t vm_clock_warp_start;
int64_t cpu_clock_offset;
/* Only written by TCG thread */
int64_t qemu_icount;
/* for adjusting icount */
QEMUTimer *icount_rt_timer;
QEMUTimer *icount_vm_timer;
QEMUTimer *icount_warp_timer;
} TimersState;
static TimersState timers_state;
bool mttcg_enabled;
/*
* We default to false if we know other options have been enabled
* which are currently incompatible with MTTCG. Otherwise when each
* guest (target) has been updated to support:
* - atomic instructions
* - memory ordering primitives (barriers)
* they can set the appropriate CONFIG flags in ${target}-softmmu.mak
*
* Once a guest architecture has been converted to the new primitives
* there are two remaining limitations to check.
*
* - The guest can't be oversized (e.g. 64 bit guest on 32 bit host)
* - The host must have a stronger memory order than the guest
*
* It may be possible in future to support strong guests on weak hosts
* but that will require tagging all load/stores in a guest with their
* implicit memory order requirements which would likely slow things
* down a lot.
*/
static bool check_tcg_memory_orders_compatible(void)
{
#if defined(TCG_GUEST_DEFAULT_MO) && defined(TCG_TARGET_DEFAULT_MO)
return (TCG_GUEST_DEFAULT_MO & ~TCG_TARGET_DEFAULT_MO) == 0;
#else
return false;
#endif
}
static bool default_mttcg_enabled(void)
{
if (use_icount || TCG_OVERSIZED_GUEST) {
return false;
} else {
#ifdef TARGET_SUPPORTS_MTTCG
return check_tcg_memory_orders_compatible();
#else
return false;
#endif
}
}
void qemu_tcg_configure(QemuOpts *opts, Error **errp)
{
const char *t = qemu_opt_get(opts, "thread");
if (t) {
if (strcmp(t, "multi") == 0) {
if (TCG_OVERSIZED_GUEST) {
error_setg(errp, "No MTTCG when guest word size > hosts");
} else if (use_icount) {
error_setg(errp, "No MTTCG when icount is enabled");
} else {
#ifndef TARGET_SUPPORTS_MTTCG
warn_report("Guest not yet converted to MTTCG - "
"you may get unexpected results");
#endif
if (!check_tcg_memory_orders_compatible()) {
warn_report("Guest expects a stronger memory ordering "
"than the host provides");
error_printf("This may cause strange/hard to debug errors\n");
}
mttcg_enabled = true;
}
} else if (strcmp(t, "single") == 0) {
mttcg_enabled = false;
} else {
error_setg(errp, "Invalid 'thread' setting %s", t);
}
} else {
mttcg_enabled = default_mttcg_enabled();
}
}
/* The current number of executed instructions is based on what we
* originally budgeted minus the current state of the decrementing
* icount counters in extra/u16.low.
*/
static int64_t cpu_get_icount_executed(CPUState *cpu)
{
return (cpu->icount_budget -
(cpu_neg(cpu)->icount_decr.u16.low + cpu->icount_extra));
}
/*
* Update the global shared timer_state.qemu_icount to take into
* account executed instructions. This is done by the TCG vCPU
* thread so the main-loop can see time has moved forward.
*/
static void cpu_update_icount_locked(CPUState *cpu)
{
int64_t executed = cpu_get_icount_executed(cpu);
cpu->icount_budget -= executed;
atomic_set_i64(&timers_state.qemu_icount,
timers_state.qemu_icount + executed);
}
/*
* Update the global shared timer_state.qemu_icount to take into
* account executed instructions. This is done by the TCG vCPU
* thread so the main-loop can see time has moved forward.
*/
void cpu_update_icount(CPUState *cpu)
{
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
cpu_update_icount_locked(cpu);
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
}
static int64_t cpu_get_icount_raw_locked(void)
{
CPUState *cpu = current_cpu;
if (cpu && cpu->running) {
if (!cpu->can_do_io) {
error_report("Bad icount read");
exit(1);
}
/* Take into account what has run */
cpu_update_icount_locked(cpu);
}
/* The read is protected by the seqlock, but needs atomic64 to avoid UB */
return atomic_read_i64(&timers_state.qemu_icount);
}
static int64_t cpu_get_icount_locked(void)
{
int64_t icount = cpu_get_icount_raw_locked();
return atomic_read_i64(&timers_state.qemu_icount_bias) +
cpu_icount_to_ns(icount);
}
int64_t cpu_get_icount_raw(void)
{
int64_t icount;
unsigned start;
do {
start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
icount = cpu_get_icount_raw_locked();
} while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));
return icount;
}
/* Return the virtual CPU time, based on the instruction counter. */
int64_t cpu_get_icount(void)
{
int64_t icount;
unsigned start;
do {
start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
icount = cpu_get_icount_locked();
} while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));
return icount;
}
int64_t cpu_icount_to_ns(int64_t icount)
{
return icount << atomic_read(&timers_state.icount_time_shift);
}
static int64_t cpu_get_ticks_locked(void)
{
int64_t ticks = timers_state.cpu_ticks_offset;
if (timers_state.cpu_ticks_enabled) {
ticks += cpu_get_host_ticks();
}
if (timers_state.cpu_ticks_prev > ticks) {
/* Non increasing ticks may happen if the host uses software suspend. */
timers_state.cpu_ticks_offset += timers_state.cpu_ticks_prev - ticks;
ticks = timers_state.cpu_ticks_prev;
}
timers_state.cpu_ticks_prev = ticks;
return ticks;
}
/* return the time elapsed in VM between vm_start and vm_stop. Unless
* icount is active, cpu_get_ticks() uses units of the host CPU cycle
* counter.
*/
int64_t cpu_get_ticks(void)
{
int64_t ticks;
if (use_icount) {
return cpu_get_icount();
}
qemu_spin_lock(&timers_state.vm_clock_lock);
ticks = cpu_get_ticks_locked();
qemu_spin_unlock(&timers_state.vm_clock_lock);
return ticks;
}
static int64_t cpu_get_clock_locked(void)
{
int64_t time;
time = timers_state.cpu_clock_offset;
if (timers_state.cpu_ticks_enabled) {
time += get_clock();
}
return time;
}
/* Return the monotonic time elapsed in VM, i.e.,
* the time between vm_start and vm_stop
*/
int64_t cpu_get_clock(void)
{
int64_t ti;
unsigned start;
do {
start = seqlock_read_begin(&timers_state.vm_clock_seqlock);
ti = cpu_get_clock_locked();
} while (seqlock_read_retry(&timers_state.vm_clock_seqlock, start));
return ti;
}
/* enable cpu_get_ticks()
* Caller must hold BQL which serves as mutex for vm_clock_seqlock.
*/
void cpu_enable_ticks(void)
{
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
if (!timers_state.cpu_ticks_enabled) {
timers_state.cpu_ticks_offset -= cpu_get_host_ticks();
timers_state.cpu_clock_offset -= get_clock();
timers_state.cpu_ticks_enabled = 1;
}
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
}
/* disable cpu_get_ticks() : the clock is stopped. You must not call
* cpu_get_ticks() after that.
* Caller must hold BQL which serves as mutex for vm_clock_seqlock.
*/
void cpu_disable_ticks(void)
{
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
if (timers_state.cpu_ticks_enabled) {
timers_state.cpu_ticks_offset += cpu_get_host_ticks();
timers_state.cpu_clock_offset = cpu_get_clock_locked();
timers_state.cpu_ticks_enabled = 0;
}
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
}
/* 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 (NANOSECONDS_PER_SECOND / 10)
static void icount_adjust(void)
{
int64_t cur_time;
int64_t cur_icount;
int64_t delta;
/* Protected by TimersState mutex. */
static int64_t last_delta;
/* If the VM is not running, then do nothing. */
if (!runstate_is_running()) {
return;
}
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
cur_time = cpu_get_clock_locked();
cur_icount = cpu_get_icount_locked();
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
&& timers_state.icount_time_shift > 0) {
/* The guest is getting too far ahead. Slow time down. */
atomic_set(&timers_state.icount_time_shift,
timers_state.icount_time_shift - 1);
}
if (delta < 0
&& last_delta - ICOUNT_WOBBLE > delta * 2
&& timers_state.icount_time_shift < MAX_ICOUNT_SHIFT) {
/* The guest is getting too far behind. Speed time up. */
atomic_set(&timers_state.icount_time_shift,
timers_state.icount_time_shift + 1);
}
last_delta = delta;
atomic_set_i64(&timers_state.qemu_icount_bias,
cur_icount - (timers_state.qemu_icount
<< timers_state.icount_time_shift));
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
}
static void icount_adjust_rt(void *opaque)
{
timer_mod(timers_state.icount_rt_timer,
qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + 1000);
icount_adjust();
}
static void icount_adjust_vm(void *opaque)
{
timer_mod(timers_state.icount_vm_timer,
qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
NANOSECONDS_PER_SECOND / 10);
icount_adjust();
}
static int64_t qemu_icount_round(int64_t count)
{
int shift = atomic_read(&timers_state.icount_time_shift);
return (count + (1 << shift) - 1) >> shift;
}
static void icount_warp_rt(void)
{
unsigned seq;
int64_t warp_start;
/* The icount_warp_timer is rescheduled soon after vm_clock_warp_start
* changes from -1 to another value, so the race here is okay.
*/
do {
seq = seqlock_read_begin(&timers_state.vm_clock_seqlock);
warp_start = timers_state.vm_clock_warp_start;
} while (seqlock_read_retry(&timers_state.vm_clock_seqlock, seq));
if (warp_start == -1) {
return;
}
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
if (runstate_is_running()) {
int64_t clock = REPLAY_CLOCK_LOCKED(REPLAY_CLOCK_VIRTUAL_RT,
cpu_get_clock_locked());
int64_t warp_delta;
warp_delta = clock - timers_state.vm_clock_warp_start;
if (use_icount == 2) {
/*
* In adaptive mode, do not let QEMU_CLOCK_VIRTUAL run too
* far ahead of real time.
*/
int64_t cur_icount = cpu_get_icount_locked();
int64_t delta = clock - cur_icount;
warp_delta = MIN(warp_delta, delta);
}
atomic_set_i64(&timers_state.qemu_icount_bias,
timers_state.qemu_icount_bias + warp_delta);
}
timers_state.vm_clock_warp_start = -1;
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
if (qemu_clock_expired(QEMU_CLOCK_VIRTUAL)) {
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
}
static void icount_timer_cb(void *opaque)
{
/* No need for a checkpoint because the timer already synchronizes
* with CHECKPOINT_CLOCK_VIRTUAL_RT.
*/
icount_warp_rt();
}
void qtest_clock_warp(int64_t dest)
{
int64_t clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
AioContext *aio_context;
assert(qtest_enabled());
aio_context = qemu_get_aio_context();
while (clock < dest) {
int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
QEMU_TIMER_ATTR_ALL);
int64_t warp = qemu_soonest_timeout(dest - clock, deadline);
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
atomic_set_i64(&timers_state.qemu_icount_bias,
timers_state.qemu_icount_bias + warp);
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
timerlist_run_timers(aio_context->tlg.tl[QEMU_CLOCK_VIRTUAL]);
clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
}
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
void qemu_start_warp_timer(void)
{
int64_t clock;
int64_t deadline;
if (!use_icount) {
return;
}
/* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
* do not fire, so computing the deadline does not make sense.
*/
if (!runstate_is_running()) {
return;
}
if (replay_mode != REPLAY_MODE_PLAY) {
if (!all_cpu_threads_idle()) {
return;
}
if (qtest_enabled()) {
/* When testing, qtest commands advance icount. */
return;
}
replay_checkpoint(CHECKPOINT_CLOCK_WARP_START);
} else {
/* warp clock deterministically in record/replay mode */
if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_START)) {
/* vCPU is sleeping and warp can't be started.
It is probably a race condition: notification sent
to vCPU was processed in advance and vCPU went to sleep.
Therefore we have to wake it up for doing someting. */
if (replay_has_checkpoint()) {
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
return;
}
}
/* We want to use the earliest deadline from ALL vm_clocks */
clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
~QEMU_TIMER_ATTR_EXTERNAL);
if (deadline < 0) {
static bool notified;
if (!icount_sleep && !notified) {
warn_report("icount sleep disabled and no active timers");
notified = true;
}
return;
}
if (deadline > 0) {
/*
* Ensure QEMU_CLOCK_VIRTUAL 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
* QEMU_CLOCK_VIRTUAL.
*/
if (!icount_sleep) {
/*
* We never let VCPUs sleep in no sleep icount mode.
* If there is a pending QEMU_CLOCK_VIRTUAL timer we just advance
* to the next QEMU_CLOCK_VIRTUAL event and notify it.
* It is useful when we want a deterministic execution time,
* isolated from host latencies.
*/
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
atomic_set_i64(&timers_state.qemu_icount_bias,
timers_state.qemu_icount_bias + deadline);
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
} else {
/*
* We do stop VCPUs and only advance QEMU_CLOCK_VIRTUAL after some
* "real" time, (related to the time left until the next event) has
* passed. The QEMU_CLOCK_VIRTUAL_RT clock will do this.
* This avoids that the warps are visible externally; for example,
* you will not be sending network packets continuously instead of
* every 100ms.
*/
seqlock_write_lock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
if (timers_state.vm_clock_warp_start == -1
|| timers_state.vm_clock_warp_start > clock) {
timers_state.vm_clock_warp_start = clock;
}
seqlock_write_unlock(&timers_state.vm_clock_seqlock,
&timers_state.vm_clock_lock);
timer_mod_anticipate(timers_state.icount_warp_timer,
clock + deadline);
}
} else if (deadline == 0) {
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
}
static void qemu_account_warp_timer(void)
{
if (!use_icount || !icount_sleep) {
return;
}
/* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
* do not fire, so computing the deadline does not make sense.
*/
if (!runstate_is_running()) {
return;
}
/* warp clock deterministically in record/replay mode */
if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_ACCOUNT)) {
return;
}
timer_del(timers_state.icount_warp_timer);
icount_warp_rt();
}
static bool icount_state_needed(void *opaque)
{
return use_icount;
}
static bool warp_timer_state_needed(void *opaque)
{
TimersState *s = opaque;
return s->icount_warp_timer != NULL;
}
static bool adjust_timers_state_needed(void *opaque)
{
TimersState *s = opaque;
return s->icount_rt_timer != NULL;
}
/*
* Subsection for warp timer migration is optional, because may not be created
*/
static const VMStateDescription icount_vmstate_warp_timer = {
.name = "timer/icount/warp_timer",
.version_id = 1,
.minimum_version_id = 1,
.needed = warp_timer_state_needed,
.fields = (VMStateField[]) {
VMSTATE_INT64(vm_clock_warp_start, TimersState),
VMSTATE_TIMER_PTR(icount_warp_timer, TimersState),
VMSTATE_END_OF_LIST()
}
};
static const VMStateDescription icount_vmstate_adjust_timers = {
.name = "timer/icount/timers",
.version_id = 1,
.minimum_version_id = 1,
.needed = adjust_timers_state_needed,
.fields = (VMStateField[]) {
VMSTATE_TIMER_PTR(icount_rt_timer, TimersState),
VMSTATE_TIMER_PTR(icount_vm_timer, TimersState),
VMSTATE_END_OF_LIST()
}
};
/*
* This is a subsection for icount migration.
*/
static const VMStateDescription icount_vmstate_timers = {
.name = "timer/icount",
.version_id = 1,
.minimum_version_id = 1,
.needed = icount_state_needed,
.fields = (VMStateField[]) {
VMSTATE_INT64(qemu_icount_bias, TimersState),
VMSTATE_INT64(qemu_icount, TimersState),
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription*[]) {
&icount_vmstate_warp_timer,
&icount_vmstate_adjust_timers,
NULL
}
};
static const VMStateDescription vmstate_timers = {
.name = "timer",
.version_id = 2,
.minimum_version_id = 1,
.fields = (VMStateField[]) {
VMSTATE_INT64(cpu_ticks_offset, TimersState),
VMSTATE_UNUSED(8),
VMSTATE_INT64_V(cpu_clock_offset, TimersState, 2),
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription*[]) {
&icount_vmstate_timers,
NULL
}
};
static void cpu_throttle_thread(CPUState *cpu, run_on_cpu_data opaque)
{
double pct;
double throttle_ratio;
int64_t sleeptime_ns, endtime_ns;
if (!cpu_throttle_get_percentage()) {
return;
}
pct = (double)cpu_throttle_get_percentage()/100;
throttle_ratio = pct / (1 - pct);
/* Add 1ns to fix double's rounding error (like 0.9999999...) */
sleeptime_ns = (int64_t)(throttle_ratio * CPU_THROTTLE_TIMESLICE_NS + 1);
endtime_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + sleeptime_ns;
while (sleeptime_ns > 0 && !cpu->stop) {
if (sleeptime_ns > SCALE_MS) {
qemu_cond_timedwait(cpu->halt_cond, &qemu_global_mutex,
sleeptime_ns / SCALE_MS);
} else {
qemu_mutex_unlock_iothread();
g_usleep(sleeptime_ns / SCALE_US);
qemu_mutex_lock_iothread();
}
sleeptime_ns = endtime_ns - qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
}
atomic_set(&cpu->throttle_thread_scheduled, 0);
}
static void cpu_throttle_timer_tick(void *opaque)
{
CPUState *cpu;
double pct;
/* Stop the timer if needed */
if (!cpu_throttle_get_percentage()) {
return;
}
CPU_FOREACH(cpu) {
if (!atomic_xchg(&cpu->throttle_thread_scheduled, 1)) {
async_run_on_cpu(cpu, cpu_throttle_thread,
RUN_ON_CPU_NULL);
}
}
pct = (double)cpu_throttle_get_percentage()/100;
timer_mod(throttle_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT) +
CPU_THROTTLE_TIMESLICE_NS / (1-pct));
}
void cpu_throttle_set(int new_throttle_pct)
{
/* Ensure throttle percentage is within valid range */
new_throttle_pct = MIN(new_throttle_pct, CPU_THROTTLE_PCT_MAX);
new_throttle_pct = MAX(new_throttle_pct, CPU_THROTTLE_PCT_MIN);
atomic_set(&throttle_percentage, new_throttle_pct);
timer_mod(throttle_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT) +
CPU_THROTTLE_TIMESLICE_NS);
}
void cpu_throttle_stop(void)
{
atomic_set(&throttle_percentage, 0);
}
bool cpu_throttle_active(void)
{
return (cpu_throttle_get_percentage() != 0);
}
int cpu_throttle_get_percentage(void)
{
return atomic_read(&throttle_percentage);
}
void cpu_ticks_init(void)
{
seqlock_init(&timers_state.vm_clock_seqlock);
qemu_spin_init(&timers_state.vm_clock_lock);
vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
throttle_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
cpu_throttle_timer_tick, NULL);
}
void configure_icount(QemuOpts *opts, Error **errp)
{
const char *option;
char *rem_str = NULL;
option = qemu_opt_get(opts, "shift");
if (!option) {
if (qemu_opt_get(opts, "align") != NULL) {
error_setg(errp, "Please specify shift option when using align");
}
return;
}
icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
if (icount_sleep) {
timers_state.icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
icount_timer_cb, NULL);
}
icount_align_option = qemu_opt_get_bool(opts, "align", false);
if (icount_align_option && !icount_sleep) {
error_setg(errp, "align=on and sleep=off are incompatible");
}
if (strcmp(option, "auto") != 0) {
errno = 0;
timers_state.icount_time_shift = strtol(option, &rem_str, 0);
if (errno != 0 || *rem_str != '\0' || !strlen(option)) {
error_setg(errp, "icount: Invalid shift value");
}
use_icount = 1;
return;
} else if (icount_align_option) {
error_setg(errp, "shift=auto and align=on are incompatible");
} else if (!icount_sleep) {
error_setg(errp, "shift=auto and sleep=off are incompatible");
}
use_icount = 2;
/* 125MIPS seems a reasonable initial guess at the guest speed.
It will be corrected fairly quickly anyway. */
timers_state.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. */
timers_state.vm_clock_warp_start = -1;
timers_state.icount_rt_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL_RT,
icount_adjust_rt, NULL);
timer_mod(timers_state.icount_rt_timer,
qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + 1000);
timers_state.icount_vm_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
icount_adjust_vm, NULL);
timer_mod(timers_state.icount_vm_timer,
qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
NANOSECONDS_PER_SECOND / 10);
}
/***********************************************************/
/* TCG vCPU kick timer
*
* The kick timer is responsible for moving single threaded vCPU
* emulation on to the next vCPU. If more than one vCPU is running a
* timer event with force a cpu->exit so the next vCPU can get
* scheduled.
*
* The timer is removed if all vCPUs are idle and restarted again once
* idleness is complete.
*/
static QEMUTimer *tcg_kick_vcpu_timer;
static CPUState *tcg_current_rr_cpu;
#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
static inline int64_t qemu_tcg_next_kick(void)
{
return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
}
/* Kick the currently round-robin scheduled vCPU */
static void qemu_cpu_kick_rr_cpu(void)
{
CPUState *cpu;
do {
cpu = atomic_mb_read(&tcg_current_rr_cpu);
if (cpu) {
cpu_exit(cpu);
}
} while (cpu != atomic_mb_read(&tcg_current_rr_cpu));
}
static void do_nothing(CPUState *cpu, run_on_cpu_data unused)
{
}
void qemu_timer_notify_cb(void *opaque, QEMUClockType type)
{
if (!use_icount || type != QEMU_CLOCK_VIRTUAL) {
qemu_notify_event();
return;
}
if (qemu_in_vcpu_thread()) {
/* A CPU is currently running; kick it back out to the
* tcg_cpu_exec() loop so it will recalculate its
* icount deadline immediately.
*/
qemu_cpu_kick(current_cpu);
} else if (first_cpu) {
/* qemu_cpu_kick is not enough to kick a halted CPU out of
* qemu_tcg_wait_io_event. async_run_on_cpu, instead,
* causes cpu_thread_is_idle to return false. This way,
* handle_icount_deadline can run.
* If we have no CPUs at all for some reason, we don't
* need to do anything.
*/
async_run_on_cpu(first_cpu, do_nothing, RUN_ON_CPU_NULL);
}
}
static void kick_tcg_thread(void *opaque)
{
timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
qemu_cpu_kick_rr_cpu();
}
static void start_tcg_kick_timer(void)
{