-
Notifications
You must be signed in to change notification settings - Fork 3
/
arch_init.c
1418 lines (1207 loc) · 38.2 KB
/
arch_init.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 <stdint.h>
#include <stdarg.h>
#include <stdlib.h>
#ifndef _WIN32
#include <sys/types.h>
#include <sys/mman.h>
#endif
#include "config.h"
#include "monitor/monitor.h"
#include "sysemu/sysemu.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "sysemu/arch_init.h"
#include "audio/audio.h"
#include "hw/i386/pc.h"
#include "hw/pci/pci.h"
#include "hw/audio/audio.h"
#include "sysemu/kvm.h"
#include "migration/migration.h"
#include "hw/i386/smbios.h"
#include "exec/address-spaces.h"
#include "hw/audio/pcspk.h"
#include "migration/page_cache.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qmp-commands.h"
#include "trace.h"
#include "exec/cpu-all.h"
#include "exec/ram_addr.h"
#include "hw/acpi/acpi.h"
#include "qemu/host-utils.h"
#ifdef DEBUG_ARCH_INIT
#define DPRINTF(fmt, ...) \
do { fprintf(stdout, "arch_init: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
#ifdef TARGET_SPARC
int graphic_width = 1024;
int graphic_height = 768;
int graphic_depth = 8;
#else
int graphic_width = 800;
int graphic_height = 600;
int graphic_depth = 32;
#endif
#if defined(TARGET_ALPHA)
#define QEMU_ARCH QEMU_ARCH_ALPHA
#elif defined(TARGET_ARM)
#define QEMU_ARCH QEMU_ARCH_ARM
#elif defined(TARGET_CRIS)
#define QEMU_ARCH QEMU_ARCH_CRIS
#elif defined(TARGET_I386)
#define QEMU_ARCH QEMU_ARCH_I386
#elif defined(TARGET_M68K)
#define QEMU_ARCH QEMU_ARCH_M68K
#elif defined(TARGET_LM32)
#define QEMU_ARCH QEMU_ARCH_LM32
#elif defined(TARGET_MICROBLAZE)
#define QEMU_ARCH QEMU_ARCH_MICROBLAZE
#elif defined(TARGET_MIPS)
#define QEMU_ARCH QEMU_ARCH_MIPS
#elif defined(TARGET_MOXIE)
#define QEMU_ARCH QEMU_ARCH_MOXIE
#elif defined(TARGET_OPENRISC)
#define QEMU_ARCH QEMU_ARCH_OPENRISC
#elif defined(TARGET_PPC)
#define QEMU_ARCH QEMU_ARCH_PPC
#elif defined(TARGET_S390X)
#define QEMU_ARCH QEMU_ARCH_S390X
#elif defined(TARGET_SH4)
#define QEMU_ARCH QEMU_ARCH_SH4
#elif defined(TARGET_SPARC)
#define QEMU_ARCH QEMU_ARCH_SPARC
#elif defined(TARGET_XTENSA)
#define QEMU_ARCH QEMU_ARCH_XTENSA
#elif defined(TARGET_UNICORE32)
#define QEMU_ARCH QEMU_ARCH_UNICORE32
#endif
const uint32_t arch_type = QEMU_ARCH;
static bool mig_throttle_on;
static int dirty_rate_high_cnt;
static void check_guest_throttling(void);
static uint64_t bitmap_sync_count;
/***********************************************************/
/* ram save/restore */
#define RAM_SAVE_FLAG_FULL 0x01 /* Obsolete, not used anymore */
#define RAM_SAVE_FLAG_COMPRESS 0x02
#define RAM_SAVE_FLAG_MEM_SIZE 0x04
#define RAM_SAVE_FLAG_PAGE 0x08
#define RAM_SAVE_FLAG_EOS 0x10
#define RAM_SAVE_FLAG_CONTINUE 0x20
#define RAM_SAVE_FLAG_XBZRLE 0x40
/* 0x80 is reserved in migration.h start with 0x100 next */
static struct defconfig_file {
const char *filename;
/* Indicates it is an user config file (disabled by -no-user-config) */
bool userconfig;
} default_config_files[] = {
{ CONFIG_QEMU_CONFDIR "/qemu.conf", true },
{ CONFIG_QEMU_CONFDIR "/target-" TARGET_NAME ".conf", true },
{ NULL }, /* end of list */
};
static const uint8_t ZERO_TARGET_PAGE[TARGET_PAGE_SIZE];
int qemu_read_default_config_files(bool userconfig)
{
int ret;
struct defconfig_file *f;
for (f = default_config_files; f->filename; f++) {
if (!userconfig && f->userconfig) {
continue;
}
ret = qemu_read_config_file(f->filename);
if (ret < 0 && ret != -ENOENT) {
return ret;
}
}
return 0;
}
static inline bool is_zero_range(uint8_t *p, uint64_t size)
{
return buffer_find_nonzero_offset(p, size) == size;
}
/* struct contains XBZRLE cache and a static page
used by the compression */
static struct {
/* buffer used for XBZRLE encoding */
uint8_t *encoded_buf;
/* buffer for storing page content */
uint8_t *current_buf;
/* Cache for XBZRLE, Protected by lock. */
PageCache *cache;
QemuMutex lock;
} XBZRLE;
/* buffer used for XBZRLE decoding */
static uint8_t *xbzrle_decoded_buf;
static void XBZRLE_cache_lock(void)
{
if (migrate_use_xbzrle())
qemu_mutex_lock(&XBZRLE.lock);
}
static void XBZRLE_cache_unlock(void)
{
if (migrate_use_xbzrle())
qemu_mutex_unlock(&XBZRLE.lock);
}
/*
* called from qmp_migrate_set_cache_size in main thread, possibly while
* a migration is in progress.
* A running migration maybe using the cache and might finish during this
* call, hence changes to the cache are protected by XBZRLE.lock().
*/
int64_t xbzrle_cache_resize(int64_t new_size)
{
PageCache *new_cache;
int64_t ret;
if (new_size < TARGET_PAGE_SIZE) {
return -1;
}
XBZRLE_cache_lock();
if (XBZRLE.cache != NULL) {
if (pow2floor(new_size) == migrate_xbzrle_cache_size()) {
goto out_new_size;
}
new_cache = cache_init(new_size / TARGET_PAGE_SIZE,
TARGET_PAGE_SIZE);
if (!new_cache) {
error_report("Error creating cache");
ret = -1;
goto out;
}
cache_fini(XBZRLE.cache);
XBZRLE.cache = new_cache;
}
out_new_size:
ret = pow2floor(new_size);
out:
XBZRLE_cache_unlock();
return ret;
}
/* accounting for migration statistics */
typedef struct AccountingInfo {
uint64_t dup_pages;
uint64_t skipped_pages;
uint64_t norm_pages;
uint64_t iterations;
uint64_t xbzrle_bytes;
uint64_t xbzrle_pages;
uint64_t xbzrle_cache_miss;
double xbzrle_cache_miss_rate;
uint64_t xbzrle_overflows;
} AccountingInfo;
static AccountingInfo acct_info;
static void acct_clear(void)
{
memset(&acct_info, 0, sizeof(acct_info));
}
uint64_t dup_mig_bytes_transferred(void)
{
return acct_info.dup_pages * TARGET_PAGE_SIZE;
}
uint64_t dup_mig_pages_transferred(void)
{
return acct_info.dup_pages;
}
uint64_t skipped_mig_bytes_transferred(void)
{
return acct_info.skipped_pages * TARGET_PAGE_SIZE;
}
uint64_t skipped_mig_pages_transferred(void)
{
return acct_info.skipped_pages;
}
uint64_t norm_mig_bytes_transferred(void)
{
return acct_info.norm_pages * TARGET_PAGE_SIZE;
}
uint64_t norm_mig_pages_transferred(void)
{
return acct_info.norm_pages;
}
uint64_t xbzrle_mig_bytes_transferred(void)
{
return acct_info.xbzrle_bytes;
}
uint64_t xbzrle_mig_pages_transferred(void)
{
return acct_info.xbzrle_pages;
}
uint64_t xbzrle_mig_pages_cache_miss(void)
{
return acct_info.xbzrle_cache_miss;
}
double xbzrle_mig_cache_miss_rate(void)
{
return acct_info.xbzrle_cache_miss_rate;
}
uint64_t xbzrle_mig_pages_overflow(void)
{
return acct_info.xbzrle_overflows;
}
static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
int cont, int flag)
{
size_t size;
qemu_put_be64(f, offset | cont | flag);
size = 8;
if (!cont) {
qemu_put_byte(f, strlen(block->idstr));
qemu_put_buffer(f, (uint8_t *)block->idstr,
strlen(block->idstr));
size += 1 + strlen(block->idstr);
}
return size;
}
/* This is the last block that we have visited serching for dirty pages
*/
static RAMBlock *last_seen_block;
/* This is the last block from where we have sent data */
static RAMBlock *last_sent_block;
static ram_addr_t last_offset;
static unsigned long *migration_bitmap;
static uint64_t migration_dirty_pages;
static uint32_t last_version;
static bool ram_bulk_stage;
/* Update the xbzrle cache to reflect a page that's been sent as all 0.
* The important thing is that a stale (not-yet-0'd) page be replaced
* by the new data.
* As a bonus, if the page wasn't in the cache it gets added so that
* when a small write is made into the 0'd page it gets XBZRLE sent
*/
static void xbzrle_cache_zero_page(ram_addr_t current_addr)
{
if (ram_bulk_stage || !migrate_use_xbzrle()) {
return;
}
/* We don't care if this fails to allocate a new cache page
* as long as it updated an old one */
cache_insert(XBZRLE.cache, current_addr, ZERO_TARGET_PAGE);
}
#define ENCODING_FLAG_XBZRLE 0x1
static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
ram_addr_t current_addr, RAMBlock *block,
ram_addr_t offset, int cont, bool last_stage)
{
int encoded_len = 0, bytes_sent = -1;
uint8_t *prev_cached_page;
if (!cache_is_cached(XBZRLE.cache, current_addr)) {
acct_info.xbzrle_cache_miss++;
if (!last_stage) {
if (cache_insert(XBZRLE.cache, current_addr, *current_data) == -1) {
return -1;
} else {
/* update *current_data when the page has been
inserted into cache */
*current_data = get_cached_data(XBZRLE.cache, current_addr);
}
}
return -1;
}
prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
/* save current buffer into memory */
memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
/* XBZRLE encoding (if there is no overflow) */
encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
TARGET_PAGE_SIZE);
if (encoded_len == 0) {
DPRINTF("Skipping unmodified page\n");
return 0;
} else if (encoded_len == -1) {
DPRINTF("Overflow\n");
acct_info.xbzrle_overflows++;
/* update data in the cache */
if (!last_stage) {
memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE);
*current_data = prev_cached_page;
}
return -1;
}
/* we need to update the data in the cache, in order to get the same data */
if (!last_stage) {
memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
}
/* Send XBZRLE based compressed page */
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
qemu_put_be16(f, encoded_len);
qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
bytes_sent += encoded_len + 1 + 2;
acct_info.xbzrle_pages++;
acct_info.xbzrle_bytes += bytes_sent;
return bytes_sent;
}
static inline
ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
ram_addr_t start)
{
unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
unsigned long nr = base + (start >> TARGET_PAGE_BITS);
uint64_t mr_size = TARGET_PAGE_ALIGN(memory_region_size(mr));
unsigned long size = base + (mr_size >> TARGET_PAGE_BITS);
unsigned long next;
if (ram_bulk_stage && nr > base) {
next = nr + 1;
} else {
next = find_next_bit(migration_bitmap, size, nr);
}
if (next < size) {
clear_bit(next, migration_bitmap);
migration_dirty_pages--;
}
return (next - base) << TARGET_PAGE_BITS;
}
static inline bool migration_bitmap_set_dirty(ram_addr_t addr)
{
bool ret;
int nr = addr >> TARGET_PAGE_BITS;
ret = test_and_set_bit(nr, migration_bitmap);
if (!ret) {
migration_dirty_pages++;
}
return ret;
}
static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
{
ram_addr_t addr;
unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
/* start address is aligned at the start of a word? */
if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) {
int k;
int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
unsigned long *src = ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION];
for (k = page; k < page + nr; k++) {
if (src[k]) {
unsigned long new_dirty;
new_dirty = ~migration_bitmap[k];
migration_bitmap[k] |= src[k];
new_dirty &= src[k];
migration_dirty_pages += ctpopl(new_dirty);
src[k] = 0;
}
}
} else {
for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
if (cpu_physical_memory_get_dirty(start + addr,
TARGET_PAGE_SIZE,
DIRTY_MEMORY_MIGRATION)) {
cpu_physical_memory_reset_dirty(start + addr,
TARGET_PAGE_SIZE,
DIRTY_MEMORY_MIGRATION);
migration_bitmap_set_dirty(start + addr);
}
}
}
}
/* Needs iothread lock! */
static void migration_bitmap_sync(void)
{
RAMBlock *block;
uint64_t num_dirty_pages_init = migration_dirty_pages;
MigrationState *s = migrate_get_current();
static int64_t start_time;
static int64_t bytes_xfer_prev;
static int64_t num_dirty_pages_period;
int64_t end_time;
int64_t bytes_xfer_now;
static uint64_t xbzrle_cache_miss_prev;
static uint64_t iterations_prev;
bitmap_sync_count++;
if (!bytes_xfer_prev) {
bytes_xfer_prev = ram_bytes_transferred();
}
if (!start_time) {
start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
}
trace_migration_bitmap_sync_start();
address_space_sync_dirty_bitmap(&address_space_memory);
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
migration_bitmap_sync_range(block->mr->ram_addr, block->length);
}
trace_migration_bitmap_sync_end(migration_dirty_pages
- num_dirty_pages_init);
num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
/* more than 1 second = 1000 millisecons */
if (end_time > start_time + 1000) {
if (migrate_auto_converge()) {
/* The following detection logic can be refined later. For now:
Check to see if the dirtied bytes is 50% more than the approx.
amount of bytes that just got transferred since the last time we
were in this routine. If that happens >N times (for now N==4)
we turn on the throttle down logic */
bytes_xfer_now = ram_bytes_transferred();
if (s->dirty_pages_rate &&
(num_dirty_pages_period * TARGET_PAGE_SIZE >
(bytes_xfer_now - bytes_xfer_prev)/2) &&
(dirty_rate_high_cnt++ > 4)) {
trace_migration_throttle();
mig_throttle_on = true;
dirty_rate_high_cnt = 0;
}
bytes_xfer_prev = bytes_xfer_now;
} else {
mig_throttle_on = false;
}
if (migrate_use_xbzrle()) {
if (iterations_prev != 0) {
acct_info.xbzrle_cache_miss_rate =
(double)(acct_info.xbzrle_cache_miss -
xbzrle_cache_miss_prev) /
(acct_info.iterations - iterations_prev);
}
iterations_prev = acct_info.iterations;
xbzrle_cache_miss_prev = acct_info.xbzrle_cache_miss;
}
s->dirty_pages_rate = num_dirty_pages_period * 1000
/ (end_time - start_time);
s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
start_time = end_time;
num_dirty_pages_period = 0;
s->dirty_sync_count = bitmap_sync_count;
}
}
/*
* ram_save_page: Send the given page to the stream
*
* Returns: Number of bytes written.
*/
static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
bool last_stage)
{
int bytes_sent;
int cont;
ram_addr_t current_addr;
MemoryRegion *mr = block->mr;
uint8_t *p;
int ret;
bool send_async = true;
cont = (block == last_sent_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
p = memory_region_get_ram_ptr(mr) + offset;
/* In doubt sent page as normal */
bytes_sent = -1;
ret = ram_control_save_page(f, block->offset,
offset, TARGET_PAGE_SIZE, &bytes_sent);
XBZRLE_cache_lock();
current_addr = block->offset + offset;
if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret != RAM_SAVE_CONTROL_DELAYED) {
if (bytes_sent > 0) {
acct_info.norm_pages++;
} else if (bytes_sent == 0) {
acct_info.dup_pages++;
}
}
} else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
acct_info.dup_pages++;
bytes_sent = save_block_hdr(f, block, offset, cont,
RAM_SAVE_FLAG_COMPRESS);
qemu_put_byte(f, 0);
bytes_sent++;
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
*/
xbzrle_cache_zero_page(current_addr);
} else if (!ram_bulk_stage && migrate_use_xbzrle()) {
bytes_sent = save_xbzrle_page(f, &p, current_addr, block,
offset, cont, last_stage);
if (!last_stage) {
/* Can't send this cached data async, since the cache page
* might get updated before it gets to the wire
*/
send_async = false;
}
}
/* XBZRLE overflow or normal page */
if (bytes_sent == -1) {
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
if (send_async) {
qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
} else {
qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
}
bytes_sent += TARGET_PAGE_SIZE;
acct_info.norm_pages++;
}
XBZRLE_cache_unlock();
return bytes_sent;
}
/*
* ram_find_and_save_block: Finds a page to send and sends it to f
*
* Returns: The number of bytes written.
* 0 means no dirty pages
*/
static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
{
RAMBlock *block = last_seen_block;
ram_addr_t offset = last_offset;
bool complete_round = false;
int bytes_sent = 0;
MemoryRegion *mr;
if (!block)
block = QTAILQ_FIRST(&ram_list.blocks);
while (true) {
mr = block->mr;
offset = migration_bitmap_find_and_reset_dirty(mr, offset);
if (complete_round && block == last_seen_block &&
offset >= last_offset) {
break;
}
if (offset >= block->length) {
offset = 0;
block = QTAILQ_NEXT(block, next);
if (!block) {
block = QTAILQ_FIRST(&ram_list.blocks);
complete_round = true;
ram_bulk_stage = false;
}
} else {
bytes_sent = ram_save_page(f, block, offset, last_stage);
/* if page is unmodified, continue to the next */
if (bytes_sent > 0) {
last_sent_block = block;
break;
}
}
}
last_seen_block = block;
last_offset = offset;
return bytes_sent;
}
static uint64_t bytes_transferred;
void acct_update_position(QEMUFile *f, size_t size, bool zero)
{
uint64_t pages = size / TARGET_PAGE_SIZE;
if (zero) {
acct_info.dup_pages += pages;
} else {
acct_info.norm_pages += pages;
bytes_transferred += size;
qemu_update_position(f, size);
}
}
static ram_addr_t ram_save_remaining(void)
{
return migration_dirty_pages;
}
uint64_t ram_bytes_remaining(void)
{
return ram_save_remaining() * TARGET_PAGE_SIZE;
}
uint64_t ram_bytes_transferred(void)
{
return bytes_transferred;
}
uint64_t ram_bytes_total(void)
{
RAMBlock *block;
uint64_t total = 0;
QTAILQ_FOREACH(block, &ram_list.blocks, next)
total += block->length;
return total;
}
void free_xbzrle_decoded_buf(void)
{
g_free(xbzrle_decoded_buf);
xbzrle_decoded_buf = NULL;
}
static void migration_end(void)
{
if (migration_bitmap) {
memory_global_dirty_log_stop();
g_free(migration_bitmap);
migration_bitmap = NULL;
}
XBZRLE_cache_lock();
if (XBZRLE.cache) {
cache_fini(XBZRLE.cache);
g_free(XBZRLE.encoded_buf);
g_free(XBZRLE.current_buf);
XBZRLE.cache = NULL;
XBZRLE.encoded_buf = NULL;
XBZRLE.current_buf = NULL;
}
XBZRLE_cache_unlock();
}
static void ram_migration_cancel(void *opaque)
{
migration_end();
}
static void reset_ram_globals(void)
{
last_seen_block = NULL;
last_sent_block = NULL;
last_offset = 0;
last_version = ram_list.version;
ram_bulk_stage = true;
}
#define MAX_WAIT 50 /* ms, half buffered_file limit */
static int ram_save_setup(QEMUFile *f, void *opaque)
{
RAMBlock *block;
int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
mig_throttle_on = false;
dirty_rate_high_cnt = 0;
bitmap_sync_count = 0;
if (migrate_use_xbzrle()) {
XBZRLE_cache_lock();
XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
TARGET_PAGE_SIZE,
TARGET_PAGE_SIZE);
if (!XBZRLE.cache) {
XBZRLE_cache_unlock();
error_report("Error creating cache");
return -1;
}
XBZRLE_cache_unlock();
/* We prefer not to abort if there is no memory */
XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
if (!XBZRLE.encoded_buf) {
error_report("Error allocating encoded_buf");
return -1;
}
XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
if (!XBZRLE.current_buf) {
error_report("Error allocating current_buf");
g_free(XBZRLE.encoded_buf);
XBZRLE.encoded_buf = NULL;
return -1;
}
acct_clear();
}
qemu_mutex_lock_iothread();
qemu_mutex_lock_ramlist();
bytes_transferred = 0;
reset_ram_globals();
ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
migration_bitmap = bitmap_new(ram_bitmap_pages);
bitmap_set(migration_bitmap, 0, ram_bitmap_pages);
/*
* Count the total number of pages used by ram blocks not including any
* gaps due to alignment or unplugs.
*/
migration_dirty_pages = 0;
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
uint64_t block_pages;
block_pages = block->length >> TARGET_PAGE_BITS;
migration_dirty_pages += block_pages;
}
memory_global_dirty_log_start();
migration_bitmap_sync();
qemu_mutex_unlock_iothread();
qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
qemu_put_byte(f, strlen(block->idstr));
qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
qemu_put_be64(f, block->length);
}
qemu_mutex_unlock_ramlist();
ram_control_before_iterate(f, RAM_CONTROL_SETUP);
ram_control_after_iterate(f, RAM_CONTROL_SETUP);
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
}
static int ram_save_iterate(QEMUFile *f, void *opaque)
{
int ret;
int i;
int64_t t0;
int total_sent = 0;
qemu_mutex_lock_ramlist();
if (ram_list.version != last_version) {
reset_ram_globals();
}
ram_control_before_iterate(f, RAM_CONTROL_ROUND);
t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
i = 0;
while ((ret = qemu_file_rate_limit(f)) == 0) {
int bytes_sent;
bytes_sent = ram_find_and_save_block(f, false);
/* no more blocks to sent */
if (bytes_sent == 0) {
break;
}
total_sent += bytes_sent;
acct_info.iterations++;
check_guest_throttling();
/* we want to check in the 1st loop, just in case it was the 1st time
and we had to sync the dirty bitmap.
qemu_get_clock_ns() is a bit expensive, so we only check each some
iterations
*/
if ((i & 63) == 0) {
uint64_t t1 = (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - t0) / 1000000;
if (t1 > MAX_WAIT) {
DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
t1, i);
break;
}
}
i++;
}
qemu_mutex_unlock_ramlist();
/*
* Must occur before EOS (or any QEMUFile operation)
* because of RDMA protocol.
*/
ram_control_after_iterate(f, RAM_CONTROL_ROUND);
bytes_transferred += total_sent;
/*
* Do not count these 8 bytes into total_sent, so that we can
* return 0 if no page had been dirtied.
*/
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
bytes_transferred += 8;
ret = qemu_file_get_error(f);
if (ret < 0) {
return ret;
}
return total_sent;
}
static int ram_save_complete(QEMUFile *f, void *opaque)
{
qemu_mutex_lock_ramlist();
migration_bitmap_sync();
ram_control_before_iterate(f, RAM_CONTROL_FINISH);
/* try transferring iterative blocks of memory */
/* flush all remaining blocks regardless of rate limiting */
while (true) {
int bytes_sent;
bytes_sent = ram_find_and_save_block(f, true);
/* no more blocks to sent */
if (bytes_sent == 0) {
break;
}
bytes_transferred += bytes_sent;
}
ram_control_after_iterate(f, RAM_CONTROL_FINISH);
migration_end();
qemu_mutex_unlock_ramlist();
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
}
static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
{
uint64_t remaining_size;
remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
if (remaining_size < max_size) {
qemu_mutex_lock_iothread();
migration_bitmap_sync();
qemu_mutex_unlock_iothread();
remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
}
return remaining_size;
}
static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
unsigned int xh_len;
int xh_flags;
if (!xbzrle_decoded_buf) {
xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE);
}
/* extract RLE header */
xh_flags = qemu_get_byte(f);
xh_len = qemu_get_be16(f);
if (xh_flags != ENCODING_FLAG_XBZRLE) {
error_report("Failed to load XBZRLE page - wrong compression!");
return -1;
}
if (xh_len > TARGET_PAGE_SIZE) {
error_report("Failed to load XBZRLE page - len overflow!");
return -1;
}
/* load data and decode */
qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);
/* decode RLE */
if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
TARGET_PAGE_SIZE) == -1) {
error_report("Failed to load XBZRLE page - decode error!");
return -1;
}
return 0;
}
static inline void *host_from_stream_offset(QEMUFile *f,
ram_addr_t offset,
int flags)