-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathmigration.c
3383 lines (2903 loc) · 102 KB
/
migration.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 live migration
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu/cutils.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "migration/blocker.h"
#include "exec.h"
#include "fd.h"
#include "socket.h"
#include "sysemu/runstate.h"
#include "sysemu/sysemu.h"
#include "sysemu/cpu-throttle.h"
#include "rdma.h"
#include "ram.h"
#include "ram-compress.h"
#include "migration/global_state.h"
#include "migration/misc.h"
#include "migration.h"
#include "migration-stats.h"
#include "savevm.h"
#include "qemu-file.h"
#include "channel.h"
#include "migration/vmstate.h"
#include "block/block.h"
#include "qapi/error.h"
#include "qapi/clone-visitor.h"
#include "qapi/qapi-visit-migration.h"
#include "qapi/qapi-visit-sockets.h"
#include "qapi/qapi-commands-migration.h"
#include "qapi/qapi-events-migration.h"
#include "qapi/qmp/qerror.h"
#include "qapi/qmp/qnull.h"
#include "qemu/rcu.h"
#include "block.h"
#include "postcopy-ram.h"
#include "qemu/thread.h"
#include "trace.h"
#include "exec/target_page.h"
#include "io/channel-buffer.h"
#include "io/channel-tls.h"
#include "migration/colo.h"
#include "hw/boards.h"
#include "monitor/monitor.h"
#include "net/announce.h"
#include "qemu/queue.h"
#include "multifd.h"
#include "threadinfo.h"
#include "qemu/yank.h"
#include "sysemu/cpus.h"
#include "yank_functions.h"
#include "sysemu/qtest.h"
#include "options.h"
static NotifierList migration_state_notifiers =
NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
/* Messages sent on the return path from destination to source */
enum mig_rp_message_type {
MIG_RP_MSG_INVALID = 0, /* Must be 0 */
MIG_RP_MSG_SHUT, /* sibling will not send any more RP messages */
MIG_RP_MSG_PONG, /* Response to a PING; data (seq: be32 ) */
MIG_RP_MSG_REQ_PAGES_ID, /* data (start: be64, len: be32, id: string) */
MIG_RP_MSG_REQ_PAGES, /* data (start: be64, len: be32) */
MIG_RP_MSG_RECV_BITMAP, /* send recved_bitmap back to source */
MIG_RP_MSG_RESUME_ACK, /* tell source that we are ready to resume */
MIG_RP_MSG_SWITCHOVER_ACK, /* Tell source it's OK to do switchover */
MIG_RP_MSG_MAX
};
/* When we add fault tolerance, we could have several
migrations at once. For now we don't need to add
dynamic creation of migration */
static MigrationState *current_migration;
static MigrationIncomingState *current_incoming;
static GSList *migration_blockers;
static bool migration_object_check(MigrationState *ms, Error **errp);
static int migration_maybe_pause(MigrationState *s,
int *current_active_state,
int new_state);
static void migrate_fd_cancel(MigrationState *s);
static bool migration_needs_multiple_sockets(void)
{
return migrate_multifd() || migrate_postcopy_preempt();
}
static bool uri_supports_multi_channels(const char *uri)
{
return strstart(uri, "tcp:", NULL) || strstart(uri, "unix:", NULL) ||
strstart(uri, "vsock:", NULL);
}
static bool
migration_channels_and_uri_compatible(const char *uri, Error **errp)
{
if (migration_needs_multiple_sockets() &&
!uri_supports_multi_channels(uri)) {
error_setg(errp, "Migration requires multi-channel URIs (e.g. tcp)");
return false;
}
return true;
}
static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
{
uintptr_t a = (uintptr_t) ap, b = (uintptr_t) bp;
return (a > b) - (a < b);
}
void migration_object_init(void)
{
/* This can only be called once. */
assert(!current_migration);
current_migration = MIGRATION_OBJ(object_new(TYPE_MIGRATION));
/*
* Init the migrate incoming object as well no matter whether
* we'll use it or not.
*/
assert(!current_incoming);
current_incoming = g_new0(MigrationIncomingState, 1);
current_incoming->state = MIGRATION_STATUS_NONE;
current_incoming->postcopy_remote_fds =
g_array_new(FALSE, TRUE, sizeof(struct PostCopyFD));
qemu_mutex_init(¤t_incoming->rp_mutex);
qemu_mutex_init(¤t_incoming->postcopy_prio_thread_mutex);
qemu_event_init(¤t_incoming->main_thread_load_event, false);
qemu_sem_init(¤t_incoming->postcopy_pause_sem_dst, 0);
qemu_sem_init(¤t_incoming->postcopy_pause_sem_fault, 0);
qemu_sem_init(¤t_incoming->postcopy_pause_sem_fast_load, 0);
qemu_sem_init(¤t_incoming->postcopy_qemufile_dst_done, 0);
qemu_mutex_init(¤t_incoming->page_request_mutex);
current_incoming->page_requested = g_tree_new(page_request_addr_cmp);
migration_object_check(current_migration, &error_fatal);
blk_mig_init();
ram_mig_init();
dirty_bitmap_mig_init();
}
void migration_cancel(const Error *error)
{
if (error) {
migrate_set_error(current_migration, error);
}
migrate_fd_cancel(current_migration);
}
void migration_shutdown(void)
{
/*
* When the QEMU main thread exit, the COLO thread
* may wait a semaphore. So, we should wakeup the
* COLO thread before migration shutdown.
*/
colo_shutdown();
/*
* Cancel the current migration - that will (eventually)
* stop the migration using this structure
*/
migration_cancel(NULL);
object_unref(OBJECT(current_migration));
/*
* Cancel outgoing migration of dirty bitmaps. It should
* at least unref used block nodes.
*/
dirty_bitmap_mig_cancel_outgoing();
/*
* Cancel incoming migration of dirty bitmaps. Dirty bitmaps
* are non-critical data, and their loss never considered as
* something serious.
*/
dirty_bitmap_mig_cancel_incoming();
}
/* For outgoing */
MigrationState *migrate_get_current(void)
{
/* This can only be called after the object created. */
assert(current_migration);
return current_migration;
}
MigrationIncomingState *migration_incoming_get_current(void)
{
assert(current_incoming);
return current_incoming;
}
void migration_incoming_transport_cleanup(MigrationIncomingState *mis)
{
if (mis->socket_address_list) {
qapi_free_SocketAddressList(mis->socket_address_list);
mis->socket_address_list = NULL;
}
if (mis->transport_cleanup) {
mis->transport_cleanup(mis->transport_data);
mis->transport_data = mis->transport_cleanup = NULL;
}
}
void migration_incoming_state_destroy(void)
{
struct MigrationIncomingState *mis = migration_incoming_get_current();
multifd_load_cleanup();
compress_threads_load_cleanup();
if (mis->to_src_file) {
/* Tell source that we are done */
migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
qemu_fclose(mis->to_src_file);
mis->to_src_file = NULL;
}
if (mis->from_src_file) {
migration_ioc_unregister_yank_from_file(mis->from_src_file);
qemu_fclose(mis->from_src_file);
mis->from_src_file = NULL;
}
if (mis->postcopy_remote_fds) {
g_array_free(mis->postcopy_remote_fds, TRUE);
mis->postcopy_remote_fds = NULL;
}
migration_incoming_transport_cleanup(mis);
qemu_event_reset(&mis->main_thread_load_event);
if (mis->page_requested) {
g_tree_destroy(mis->page_requested);
mis->page_requested = NULL;
}
if (mis->postcopy_qemufile_dst) {
migration_ioc_unregister_yank_from_file(mis->postcopy_qemufile_dst);
qemu_fclose(mis->postcopy_qemufile_dst);
mis->postcopy_qemufile_dst = NULL;
}
yank_unregister_instance(MIGRATION_YANK_INSTANCE);
}
static void migrate_generate_event(int new_state)
{
if (migrate_events()) {
qapi_event_send_migration(new_state);
}
}
/*
* Send a message on the return channel back to the source
* of the migration.
*/
static int migrate_send_rp_message(MigrationIncomingState *mis,
enum mig_rp_message_type message_type,
uint16_t len, void *data)
{
int ret = 0;
trace_migrate_send_rp_message((int)message_type, len);
QEMU_LOCK_GUARD(&mis->rp_mutex);
/*
* It's possible that the file handle got lost due to network
* failures.
*/
if (!mis->to_src_file) {
ret = -EIO;
return ret;
}
qemu_put_be16(mis->to_src_file, (unsigned int)message_type);
qemu_put_be16(mis->to_src_file, len);
qemu_put_buffer(mis->to_src_file, data, len);
qemu_fflush(mis->to_src_file);
/* It's possible that qemu file got error during sending */
ret = qemu_file_get_error(mis->to_src_file);
return ret;
}
/* Request one page from the source VM at the given start address.
* rb: the RAMBlock to request the page in
* Start: Address offset within the RB
* Len: Length in bytes required - must be a multiple of pagesize
*/
int migrate_send_rp_message_req_pages(MigrationIncomingState *mis,
RAMBlock *rb, ram_addr_t start)
{
uint8_t bufc[12 + 1 + 255]; /* start (8), len (4), rbname up to 256 */
size_t msglen = 12; /* start + len */
size_t len = qemu_ram_pagesize(rb);
enum mig_rp_message_type msg_type;
const char *rbname;
int rbname_len;
*(uint64_t *)bufc = cpu_to_be64((uint64_t)start);
*(uint32_t *)(bufc + 8) = cpu_to_be32((uint32_t)len);
/*
* We maintain the last ramblock that we requested for page. Note that we
* don't need locking because this function will only be called within the
* postcopy ram fault thread.
*/
if (rb != mis->last_rb) {
mis->last_rb = rb;
rbname = qemu_ram_get_idstr(rb);
rbname_len = strlen(rbname);
assert(rbname_len < 256);
bufc[msglen++] = rbname_len;
memcpy(bufc + msglen, rbname, rbname_len);
msglen += rbname_len;
msg_type = MIG_RP_MSG_REQ_PAGES_ID;
} else {
msg_type = MIG_RP_MSG_REQ_PAGES;
}
return migrate_send_rp_message(mis, msg_type, msglen, bufc);
}
int migrate_send_rp_req_pages(MigrationIncomingState *mis,
RAMBlock *rb, ram_addr_t start, uint64_t haddr)
{
void *aligned = (void *)(uintptr_t)ROUND_DOWN(haddr, qemu_ram_pagesize(rb));
bool received = false;
WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) {
received = ramblock_recv_bitmap_test_byte_offset(rb, start);
if (!received && !g_tree_lookup(mis->page_requested, aligned)) {
/*
* The page has not been received, and it's not yet in the page
* request list. Queue it. Set the value of element to 1, so that
* things like g_tree_lookup() will return TRUE (1) when found.
*/
g_tree_insert(mis->page_requested, aligned, (gpointer)1);
mis->page_requested_count++;
trace_postcopy_page_req_add(aligned, mis->page_requested_count);
}
}
/*
* If the page is there, skip sending the message. We don't even need the
* lock because as long as the page arrived, it'll be there forever.
*/
if (received) {
return 0;
}
return migrate_send_rp_message_req_pages(mis, rb, start);
}
static bool migration_colo_enabled;
bool migration_incoming_colo_enabled(void)
{
return migration_colo_enabled;
}
void migration_incoming_disable_colo(void)
{
ram_block_discard_disable(false);
migration_colo_enabled = false;
}
int migration_incoming_enable_colo(void)
{
#ifndef CONFIG_REPLICATION
error_report("ENABLE_COLO command come in migration stream, but COLO "
"module is not built in");
return -ENOTSUP;
#endif
if (!migrate_colo()) {
error_report("ENABLE_COLO command come in migration stream, but c-colo "
"capability is not set");
return -EINVAL;
}
if (ram_block_discard_disable(true)) {
error_report("COLO: cannot disable RAM discard");
return -EBUSY;
}
migration_colo_enabled = true;
return 0;
}
void migrate_add_address(SocketAddress *address)
{
MigrationIncomingState *mis = migration_incoming_get_current();
QAPI_LIST_PREPEND(mis->socket_address_list,
QAPI_CLONE(SocketAddress, address));
}
static void qemu_start_incoming_migration(const char *uri, Error **errp)
{
const char *p = NULL;
/* URI is not suitable for migration? */
if (!migration_channels_and_uri_compatible(uri, errp)) {
return;
}
qapi_event_send_migration(MIGRATION_STATUS_SETUP);
if (strstart(uri, "tcp:", &p) ||
strstart(uri, "unix:", NULL) ||
strstart(uri, "vsock:", NULL)) {
socket_start_incoming_migration(p ? p : uri, errp);
#ifdef CONFIG_RDMA
} else if (strstart(uri, "rdma:", &p)) {
rdma_start_incoming_migration(p, errp);
#endif
} else if (strstart(uri, "exec:", &p)) {
exec_start_incoming_migration(p, errp);
} else if (strstart(uri, "fd:", &p)) {
fd_start_incoming_migration(p, errp);
} else {
error_setg(errp, "unknown migration protocol: %s", uri);
}
}
static void process_incoming_migration_bh(void *opaque)
{
Error *local_err = NULL;
MigrationIncomingState *mis = opaque;
/* If capability late_block_activate is set:
* Only fire up the block code now if we're going to restart the
* VM, else 'cont' will do it.
* This causes file locking to happen; so we don't want it to happen
* unless we really are starting the VM.
*/
if (!migrate_late_block_activate() ||
(autostart && (!global_state_received() ||
global_state_get_runstate() == RUN_STATE_RUNNING))) {
/* Make sure all file formats throw away their mutable metadata.
* If we get an error here, just don't restart the VM yet. */
bdrv_activate_all(&local_err);
if (local_err) {
error_report_err(local_err);
local_err = NULL;
autostart = false;
}
}
/*
* This must happen after all error conditions are dealt with and
* we're sure the VM is going to be running on this host.
*/
qemu_announce_self(&mis->announce_timer, migrate_announce_params());
multifd_load_shutdown();
dirty_bitmap_mig_before_vm_start();
if (!global_state_received() ||
global_state_get_runstate() == RUN_STATE_RUNNING) {
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PAUSED);
}
} else if (migration_incoming_colo_enabled()) {
migration_incoming_disable_colo();
vm_start();
} else {
runstate_set(global_state_get_runstate());
}
/*
* This must happen after any state changes since as soon as an external
* observer sees this event they might start to prod at the VM assuming
* it's ready to use.
*/
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COMPLETED);
qemu_bh_delete(mis->bh);
migration_incoming_state_destroy();
}
static void coroutine_fn
process_incoming_migration_co(void *opaque)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyState ps;
int ret;
assert(mis->from_src_file);
if (compress_threads_load_setup(mis->from_src_file)) {
error_report("Failed to setup decompress threads");
goto fail;
}
mis->largest_page_size = qemu_ram_pagesize_largest();
postcopy_state_set(POSTCOPY_INCOMING_NONE);
migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
MIGRATION_STATUS_ACTIVE);
mis->loadvm_co = qemu_coroutine_self();
ret = qemu_loadvm_state(mis->from_src_file);
mis->loadvm_co = NULL;
ps = postcopy_state_get();
trace_process_incoming_migration_co_end(ret, ps);
if (ps != POSTCOPY_INCOMING_NONE) {
if (ps == POSTCOPY_INCOMING_ADVISE) {
/*
* Where a migration had postcopy enabled (and thus went to advise)
* but managed to complete within the precopy period, we can use
* the normal exit.
*/
postcopy_ram_incoming_cleanup(mis);
} else if (ret >= 0) {
/*
* Postcopy was started, cleanup should happen at the end of the
* postcopy thread.
*/
trace_process_incoming_migration_co_postcopy_end_main();
return;
}
/* Else if something went wrong then just fall out of the normal exit */
}
if (ret < 0) {
error_report("load of migration failed: %s", strerror(-ret));
goto fail;
}
if (colo_incoming_co() < 0) {
goto fail;
}
mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
qemu_bh_schedule(mis->bh);
return;
fail:
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
qemu_fclose(mis->from_src_file);
multifd_load_cleanup();
compress_threads_load_cleanup();
exit(EXIT_FAILURE);
}
/**
* migration_incoming_setup: Setup incoming migration
* @f: file for main migration channel
* @errp: where to put errors
*
* Returns: %true on success, %false on error.
*/
static bool migration_incoming_setup(QEMUFile *f, Error **errp)
{
MigrationIncomingState *mis = migration_incoming_get_current();
if (!mis->from_src_file) {
mis->from_src_file = f;
}
qemu_file_set_blocking(f, false);
return true;
}
void migration_incoming_process(void)
{
Coroutine *co = qemu_coroutine_create(process_incoming_migration_co, NULL);
qemu_coroutine_enter(co);
}
/* Returns true if recovered from a paused migration, otherwise false */
static bool postcopy_try_recover(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
if (mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) {
/* Resumed from a paused postcopy migration */
/* This should be set already in migration_incoming_setup() */
assert(mis->from_src_file);
/* Postcopy has standalone thread to do vm load */
qemu_file_set_blocking(mis->from_src_file, true);
/* Re-configure the return path */
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_PAUSED,
MIGRATION_STATUS_POSTCOPY_RECOVER);
/*
* Here, we only wake up the main loading thread (while the
* rest threads will still be waiting), so that we can receive
* commands from source now, and answer it if needed. The
* rest threads will be woken up afterwards until we are sure
* that source is ready to reply to page requests.
*/
qemu_sem_post(&mis->postcopy_pause_sem_dst);
return true;
}
return false;
}
void migration_fd_process_incoming(QEMUFile *f, Error **errp)
{
if (!migration_incoming_setup(f, errp)) {
return;
}
if (postcopy_try_recover()) {
return;
}
migration_incoming_process();
}
/*
* Returns true when we want to start a new incoming migration process,
* false otherwise.
*/
static bool migration_should_start_incoming(bool main_channel)
{
/* Multifd doesn't start unless all channels are established */
if (migrate_multifd()) {
return migration_has_all_channels();
}
/* Preempt channel only starts when the main channel is created */
if (migrate_postcopy_preempt()) {
return main_channel;
}
/*
* For all the rest types of migration, we should only reach here when
* it's the main channel that's being created, and we should always
* proceed with this channel.
*/
assert(main_channel);
return true;
}
void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
{
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
QEMUFile *f;
bool default_channel = true;
uint32_t channel_magic = 0;
int ret = 0;
if (migrate_multifd() && !migrate_postcopy_ram() &&
qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
/*
* With multiple channels, it is possible that we receive channels
* out of order on destination side, causing incorrect mapping of
* source channels on destination side. Check channel MAGIC to
* decide type of channel. Please note this is best effort, postcopy
* preempt channel does not send any magic number so avoid it for
* postcopy live migration. Also tls live migration already does
* tls handshake while initializing main channel so with tls this
* issue is not possible.
*/
ret = migration_channel_read_peek(ioc, (void *)&channel_magic,
sizeof(channel_magic), &local_err);
if (ret != 0) {
error_propagate(errp, local_err);
return;
}
default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC));
} else {
default_channel = !mis->from_src_file;
}
if (multifd_load_setup(errp) != 0) {
error_setg(errp, "Failed to setup multifd channels");
return;
}
if (default_channel) {
f = qemu_file_new_input(ioc);
if (!migration_incoming_setup(f, errp)) {
return;
}
} else {
/* Multiple connections */
assert(migration_needs_multiple_sockets());
if (migrate_multifd()) {
multifd_recv_new_channel(ioc, &local_err);
} else {
assert(migrate_postcopy_preempt());
f = qemu_file_new_input(ioc);
postcopy_preempt_new_channel(mis, f);
}
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
if (migration_should_start_incoming(default_channel)) {
/* If it's a recovery, we're done */
if (postcopy_try_recover()) {
return;
}
migration_incoming_process();
}
}
/**
* @migration_has_all_channels: We have received all channels that we need
*
* Returns true when we have got connections to all the channels that
* we need for migration.
*/
bool migration_has_all_channels(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
if (!mis->from_src_file) {
return false;
}
if (migrate_multifd()) {
return multifd_recv_all_channels_created();
}
if (migrate_postcopy_preempt()) {
return mis->postcopy_qemufile_dst != NULL;
}
return true;
}
int migrate_send_rp_switchover_ack(MigrationIncomingState *mis)
{
return migrate_send_rp_message(mis, MIG_RP_MSG_SWITCHOVER_ACK, 0, NULL);
}
/*
* Send a 'SHUT' message on the return channel with the given value
* to indicate that we've finished with the RP. Non-0 value indicates
* error.
*/
void migrate_send_rp_shut(MigrationIncomingState *mis,
uint32_t value)
{
uint32_t buf;
buf = cpu_to_be32(value);
migrate_send_rp_message(mis, MIG_RP_MSG_SHUT, sizeof(buf), &buf);
}
/*
* Send a 'PONG' message on the return channel with the given value
* (normally in response to a 'PING')
*/
void migrate_send_rp_pong(MigrationIncomingState *mis,
uint32_t value)
{
uint32_t buf;
buf = cpu_to_be32(value);
migrate_send_rp_message(mis, MIG_RP_MSG_PONG, sizeof(buf), &buf);
}
void migrate_send_rp_recv_bitmap(MigrationIncomingState *mis,
char *block_name)
{
char buf[512];
int len;
int64_t res;
/*
* First, we send the header part. It contains only the len of
* idstr, and the idstr itself.
*/
len = strlen(block_name);
buf[0] = len;
memcpy(buf + 1, block_name, len);
if (mis->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
error_report("%s: MSG_RP_RECV_BITMAP only used for recovery",
__func__);
return;
}
migrate_send_rp_message(mis, MIG_RP_MSG_RECV_BITMAP, len + 1, buf);
/*
* Next, we dump the received bitmap to the stream.
*
* TODO: currently we are safe since we are the only one that is
* using the to_src_file handle (fault thread is still paused),
* and it's ok even not taking the mutex. However the best way is
* to take the lock before sending the message header, and release
* the lock after sending the bitmap.
*/
qemu_mutex_lock(&mis->rp_mutex);
res = ramblock_recv_bitmap_send(mis->to_src_file, block_name);
qemu_mutex_unlock(&mis->rp_mutex);
trace_migrate_send_rp_recv_bitmap(block_name, res);
}
void migrate_send_rp_resume_ack(MigrationIncomingState *mis, uint32_t value)
{
uint32_t buf;
buf = cpu_to_be32(value);
migrate_send_rp_message(mis, MIG_RP_MSG_RESUME_ACK, sizeof(buf), &buf);
}
/*
* Return true if we're already in the middle of a migration
* (i.e. any of the active or setup states)
*/
bool migration_is_setup_or_active(int state)
{
switch (state) {
case MIGRATION_STATUS_ACTIVE:
case MIGRATION_STATUS_POSTCOPY_ACTIVE:
case MIGRATION_STATUS_POSTCOPY_PAUSED:
case MIGRATION_STATUS_POSTCOPY_RECOVER:
case MIGRATION_STATUS_SETUP:
case MIGRATION_STATUS_PRE_SWITCHOVER:
case MIGRATION_STATUS_DEVICE:
case MIGRATION_STATUS_WAIT_UNPLUG:
case MIGRATION_STATUS_COLO:
return true;
default:
return false;
}
}
bool migration_is_running(int state)
{
switch (state) {
case MIGRATION_STATUS_ACTIVE:
case MIGRATION_STATUS_POSTCOPY_ACTIVE:
case MIGRATION_STATUS_POSTCOPY_PAUSED:
case MIGRATION_STATUS_POSTCOPY_RECOVER:
case MIGRATION_STATUS_SETUP:
case MIGRATION_STATUS_PRE_SWITCHOVER:
case MIGRATION_STATUS_DEVICE:
case MIGRATION_STATUS_WAIT_UNPLUG:
case MIGRATION_STATUS_CANCELLING:
return true;
default:
return false;
}
}
static bool migrate_show_downtime(MigrationState *s)
{
return (s->state == MIGRATION_STATUS_COMPLETED) || migration_in_postcopy();
}
static void populate_time_info(MigrationInfo *info, MigrationState *s)
{
info->has_status = true;
info->has_setup_time = true;
info->setup_time = s->setup_time;
if (s->state == MIGRATION_STATUS_COMPLETED) {
info->has_total_time = true;
info->total_time = s->total_time;
} else {
info->has_total_time = true;
info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) -
s->start_time;
}
if (migrate_show_downtime(s)) {
info->has_downtime = true;
info->downtime = s->downtime;
} else {
info->has_expected_downtime = true;
info->expected_downtime = s->expected_downtime;
}
}
static void populate_ram_info(MigrationInfo *info, MigrationState *s)
{
size_t page_size = qemu_target_page_size();
info->ram = g_malloc0(sizeof(*info->ram));
info->ram->transferred = stat64_get(&mig_stats.transferred);
info->ram->total = ram_bytes_total();
info->ram->duplicate = stat64_get(&mig_stats.zero_pages);
/* legacy value. It is not used anymore */
info->ram->skipped = 0;
info->ram->normal = stat64_get(&mig_stats.normal_pages);
info->ram->normal_bytes = info->ram->normal * page_size;
info->ram->mbps = s->mbps;
info->ram->dirty_sync_count =
stat64_get(&mig_stats.dirty_sync_count);
info->ram->dirty_sync_missed_zero_copy =
stat64_get(&mig_stats.dirty_sync_missed_zero_copy);
info->ram->postcopy_requests =
stat64_get(&mig_stats.postcopy_requests);
info->ram->page_size = page_size;
info->ram->multifd_bytes = stat64_get(&mig_stats.multifd_bytes);
info->ram->pages_per_second = s->pages_per_second;
info->ram->precopy_bytes = stat64_get(&mig_stats.precopy_bytes);
info->ram->downtime_bytes = stat64_get(&mig_stats.downtime_bytes);
info->ram->postcopy_bytes = stat64_get(&mig_stats.postcopy_bytes);
if (migrate_xbzrle()) {
info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
info->xbzrle_cache->cache_size = migrate_xbzrle_cache_size();
info->xbzrle_cache->bytes = xbzrle_counters.bytes;
info->xbzrle_cache->pages = xbzrle_counters.pages;
info->xbzrle_cache->cache_miss = xbzrle_counters.cache_miss;
info->xbzrle_cache->cache_miss_rate = xbzrle_counters.cache_miss_rate;
info->xbzrle_cache->encoding_rate = xbzrle_counters.encoding_rate;
info->xbzrle_cache->overflow = xbzrle_counters.overflow;
}
if (migrate_compress()) {
info->compression = g_malloc0(sizeof(*info->compression));
info->compression->pages = compression_counters.pages;
info->compression->busy = compression_counters.busy;
info->compression->busy_rate = compression_counters.busy_rate;
info->compression->compressed_size =
compression_counters.compressed_size;
info->compression->compression_rate =
compression_counters.compression_rate;
}
if (cpu_throttle_active()) {
info->has_cpu_throttle_percentage = true;
info->cpu_throttle_percentage = cpu_throttle_get_percentage();
}
if (s->state != MIGRATION_STATUS_COMPLETED) {
info->ram->remaining = ram_bytes_remaining();
info->ram->dirty_pages_rate =
stat64_get(&mig_stats.dirty_pages_rate);
}
}
static void populate_disk_info(MigrationInfo *info)
{
if (blk_mig_active()) {
info->disk = g_malloc0(sizeof(*info->disk));
info->disk->transferred = blk_mig_bytes_transferred();
info->disk->remaining = blk_mig_bytes_remaining();
info->disk->total = blk_mig_bytes_total();
}
}
static void fill_source_migration_info(MigrationInfo *info)
{
MigrationState *s = migrate_get_current();
int state = qatomic_read(&s->state);
GSList *cur_blocker = migration_blockers;
info->blocked_reasons = NULL;
/*
* There are two types of reasons a migration might be blocked;
* a) devices marked in VMState as non-migratable, and
* b) Explicit migration blockers
* We need to add both of them here.
*/
qemu_savevm_non_migratable_list(&info->blocked_reasons);