aboutsummaryrefslogtreecommitdiff
path: root/migration/multifd.c
blob: e362b1bb89c004b24a452dff458abc66e7a8de9e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
/*
 * Multifd common code
 *
 * Copyright (c) 2019-2020 Red Hat Inc
 *
 * Authors:
 *  Juan Quintela <quintela@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "qemu/rcu.h"
#include "exec/target_page.h"
#include "sysemu/sysemu.h"
#include "exec/ramblock.h"
#include "qemu/error-report.h"
#include "qapi/error.h"
#include "ram.h"
#include "migration.h"
#include "socket.h"
#include "tls.h"
#include "qemu-file.h"
#include "trace.h"
#include "multifd.h"

#include "qemu/yank.h"
#include "io/channel-socket.h"
#include "yank_functions.h"

/* Multiple fd's */

#define MULTIFD_MAGIC 0x11223344U
#define MULTIFD_VERSION 1

typedef struct {
    uint32_t magic;
    uint32_t version;
    unsigned char uuid[16]; /* QemuUUID */
    uint8_t id;
    uint8_t unused1[7];     /* Reserved for future use */
    uint64_t unused2[4];    /* Reserved for future use */
} __attribute__((packed)) MultiFDInit_t;

/* Multifd without compression */

/**
 * nocomp_send_setup: setup send side
 *
 * For no compression this function does nothing.
 *
 * Returns 0 for success or -1 for error
 *
 * @p: Params for the channel that we are using
 * @errp: pointer to an error
 */
static int nocomp_send_setup(MultiFDSendParams *p, Error **errp)
{
    return 0;
}

/**
 * nocomp_send_cleanup: cleanup send side
 *
 * For no compression this function does nothing.
 *
 * @p: Params for the channel that we are using
 * @errp: pointer to an error
 */
static void nocomp_send_cleanup(MultiFDSendParams *p, Error **errp)
{
    return;
}

/**
 * nocomp_send_prepare: prepare date to be able to send
 *
 * For no compression we just have to calculate the size of the
 * packet.
 *
 * Returns 0 for success or -1 for error
 *
 * @p: Params for the channel that we are using
 * @errp: pointer to an error
 */
static int nocomp_send_prepare(MultiFDSendParams *p, Error **errp)
{
    MultiFDPages_t *pages = p->pages;
    size_t page_size = qemu_target_page_size();

    for (int i = 0; i < p->normal_num; i++) {
        p->iov[p->iovs_num].iov_base = pages->block->host + p->normal[i];
        p->iov[p->iovs_num].iov_len = page_size;
        p->iovs_num++;
    }

    p->next_packet_size = p->normal_num * page_size;
    p->flags |= MULTIFD_FLAG_NOCOMP;
    return 0;
}

/**
 * nocomp_recv_setup: setup receive side
 *
 * For no compression this function does nothing.
 *
 * Returns 0 for success or -1 for error
 *
 * @p: Params for the channel that we are using
 * @errp: pointer to an error
 */
static int nocomp_recv_setup(MultiFDRecvParams *p, Error **errp)
{
    return 0;
}

/**
 * nocomp_recv_cleanup: setup receive side
 *
 * For no compression this function does nothing.
 *
 * @p: Params for the channel that we are using
 */
static void nocomp_recv_cleanup(MultiFDRecvParams *p)
{
}

/**
 * nocomp_recv_pages: read the data from the channel into actual pages
 *
 * For no compression we just need to read things into the correct place.
 *
 * Returns 0 for success or -1 for error
 *
 * @p: Params for the channel that we are using
 * @errp: pointer to an error
 */
static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
{
    uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
    size_t page_size = qemu_target_page_size();

    if (flags != MULTIFD_FLAG_NOCOMP) {
        error_setg(errp, "multifd %u: flags received %x flags expected %x",
                   p->id, flags, MULTIFD_FLAG_NOCOMP);
        return -1;
    }
    for (int i = 0; i < p->normal_num; i++) {
        p->iov[i].iov_base = p->pages->block->host + p->normal[i];
        p->iov[i].iov_len = page_size;
    }
    return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
}

static MultiFDMethods multifd_nocomp_ops = {
    .send_setup = nocomp_send_setup,
    .send_cleanup = nocomp_send_cleanup,
    .send_prepare = nocomp_send_prepare,
    .recv_setup = nocomp_recv_setup,
    .recv_cleanup = nocomp_recv_cleanup,
    .recv_pages = nocomp_recv_pages
};

static MultiFDMethods *multifd_ops[MULTIFD_COMPRESSION__MAX] = {
    [MULTIFD_COMPRESSION_NONE] = &multifd_nocomp_ops,
};

void multifd_register_ops(int method, MultiFDMethods *ops)
{
    assert(0 < method && method < MULTIFD_COMPRESSION__MAX);
    multifd_ops[method] = ops;
}

static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp)
{
    MultiFDInit_t msg = {};
    int ret;

    msg.magic = cpu_to_be32(MULTIFD_MAGIC);
    msg.version = cpu_to_be32(MULTIFD_VERSION);
    msg.id = p->id;
    memcpy(msg.uuid, &qemu_uuid.data, sizeof(msg.uuid));

    ret = qio_channel_write_all(p->c, (char *)&msg, sizeof(msg), errp);
    if (ret != 0) {
        return -1;
    }
    return 0;
}

static int multifd_recv_initial_packet(QIOChannel *c, Error **errp)
{
    MultiFDInit_t msg;
    int ret;

    ret = qio_channel_read_all(c, (char *)&msg, sizeof(msg), errp);
    if (ret != 0) {
        return -1;
    }

    msg.magic = be32_to_cpu(msg.magic);
    msg.version = be32_to_cpu(msg.version);

    if (msg.magic != MULTIFD_MAGIC) {
        error_setg(errp, "multifd: received packet magic %x "
                   "expected %x", msg.magic, MULTIFD_MAGIC);
        return -1;
    }

    if (msg.version != MULTIFD_VERSION) {
        error_setg(errp, "multifd: received packet version %u "
                   "expected %u", msg.version, MULTIFD_VERSION);
        return -1;
    }

    if (memcmp(msg.uuid, &qemu_uuid, sizeof(qemu_uuid))) {
        char *uuid = qemu_uuid_unparse_strdup(&qemu_uuid);
        char *msg_uuid = qemu_uuid_unparse_strdup((const QemuUUID *)msg.uuid);

        error_setg(errp, "multifd: received uuid '%s' and expected "
                   "uuid '%s' for channel %hhd", msg_uuid, uuid, msg.id);
        g_free(uuid);
        g_free(msg_uuid);
        return -1;
    }

    if (msg.id > migrate_multifd_channels()) {
        error_setg(errp, "multifd: received channel version %u "
                   "expected %u", msg.version, MULTIFD_VERSION);
        return -1;
    }

    return msg.id;
}

static MultiFDPages_t *multifd_pages_init(size_t size)
{
    MultiFDPages_t *pages = g_new0(MultiFDPages_t, 1);

    pages->allocated = size;
    pages->offset = g_new0(ram_addr_t, size);

    return pages;
}

static void multifd_pages_clear(MultiFDPages_t *pages)
{
    pages->num = 0;
    pages->allocated = 0;
    pages->packet_num = 0;
    pages->block = NULL;
    g_free(pages->offset);
    pages->offset = NULL;
    g_free(pages);
}

static void multifd_send_fill_packet(MultiFDSendParams *p)
{
    MultiFDPacket_t *packet = p->packet;
    int i;

    packet->flags = cpu_to_be32(p->flags);
    packet->pages_alloc = cpu_to_be32(p->pages->allocated);
    packet->pages_used = cpu_to_be32(p->normal_num);
    packet->next_packet_size = cpu_to_be32(p->next_packet_size);
    packet->packet_num = cpu_to_be64(p->packet_num);

    if (p->pages->block) {
        strncpy(packet->ramblock, p->pages->block->idstr, 256);
    }

    for (i = 0; i < p->normal_num; i++) {
        /* there are architectures where ram_addr_t is 32 bit */
        uint64_t temp = p->normal[i];

        packet->offset[i] = cpu_to_be64(temp);
    }
}

static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
{
    MultiFDPacket_t *packet = p->packet;
    size_t page_size = qemu_target_page_size();
    uint32_t page_count = MULTIFD_PACKET_SIZE / page_size;
    RAMBlock *block;
    int i;

    packet->magic = be32_to_cpu(packet->magic);
    if (packet->magic != MULTIFD_MAGIC) {
        error_setg(errp, "multifd: received packet "
                   "magic %x and expected magic %x",
                   packet->magic, MULTIFD_MAGIC);
        return -1;
    }

    packet->version = be32_to_cpu(packet->version);
    if (packet->version != MULTIFD_VERSION) {
        error_setg(errp, "multifd: received packet "
                   "version %u and expected version %u",
                   packet->version, MULTIFD_VERSION);
        return -1;
    }

    p->flags = be32_to_cpu(packet->flags);

    packet->pages_alloc = be32_to_cpu(packet->pages_alloc);
    /*
     * If we received a packet that is 100 times bigger than expected
     * just stop migration.  It is a magic number.
     */
    if (packet->pages_alloc > page_count) {
        error_setg(errp, "multifd: received packet "
                   "with size %u and expected a size of %u",
                   packet->pages_alloc, page_count) ;
        return -1;
    }

    p->normal_num = be32_to_cpu(packet->pages_used);
    if (p->normal_num > packet->pages_alloc) {
        error_setg(errp, "multifd: received packet "
                   "with %u pages and expected maximum pages are %u",
                   p->normal_num, packet->pages_alloc) ;
        return -1;
    }

    p->next_packet_size = be32_to_cpu(packet->next_packet_size);
    p->packet_num = be64_to_cpu(packet->packet_num);

    if (p->normal_num == 0) {
        return 0;
    }

    /* make sure that ramblock is 0 terminated */
    packet->ramblock[255] = 0;
    block = qemu_ram_block_by_name(packet->ramblock);
    if (!block) {
        error_setg(errp, "multifd: unknown ram block %s",
                   packet->ramblock);
        return -1;
    }

    p->pages->block = block;
    for (i = 0; i < p->normal_num; i++) {
        uint64_t offset = be64_to_cpu(packet->offset[i]);

        if (offset > (block->used_length - page_size)) {
            error_setg(errp, "multifd: offset too long %" PRIu64
                       " (max " RAM_ADDR_FMT ")",
                       offset, block->used_length);
            return -1;
        }
        p->normal[i] = offset;
    }

    return 0;
}

struct {
    MultiFDSendParams *params;
    /* array of pages to sent */
    MultiFDPages_t *pages;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* send channels ready */
    QemuSemaphore channels_ready;
    /*
     * Have we already run terminate threads.  There is a race when it
     * happens that we got one error while we are exiting.
     * We will use atomic operations.  Only valid values are 0 and 1.
     */
    int exiting;
    /* multifd ops */
    MultiFDMethods *ops;
} *multifd_send_state;

/*
 * How we use multifd_send_state->pages and channel->pages?
 *
 * We create a pages for each channel, and a main one.  Each time that
 * we need to send a batch of pages we interchange the ones between
 * multifd_send_state and the channel that is sending it.  There are
 * two reasons for that:
 *    - to not have to do so many mallocs during migration
 *    - to make easier to know what to free at the end of migration
 *
 * This way we always know who is the owner of each "pages" struct,
 * and we don't need any locking.  It belongs to the migration thread
 * or to the channel thread.  Switching is safe because the migration
 * thread is using the channel mutex when changing it, and the channel
 * have to had finish with its own, otherwise pending_job can't be
 * false.
 */

static int multifd_send_pages(QEMUFile *f)
{
    int i;
    static int next_channel;
    MultiFDSendParams *p = NULL; /* make happy gcc */
    MultiFDPages_t *pages = multifd_send_state->pages;
    uint64_t transferred;

    if (qatomic_read(&multifd_send_state->exiting)) {
        return -1;
    }

    qemu_sem_wait(&multifd_send_state->channels_ready);
    /*
     * next_channel can remain from a previous migration that was
     * using more channels, so ensure it doesn't overflow if the
     * limit is lower now.
     */
    next_channel %= migrate_multifd_channels();
    for (i = next_channel;; i = (i + 1) % migrate_multifd_channels()) {
        p = &multifd_send_state->params[i];

        qemu_mutex_lock(&p->mutex);
        if (p->quit) {
            error_report("%s: channel %d has already quit!", __func__, i);
            qemu_mutex_unlock(&p->mutex);
            return -1;
        }
        if (!p->pending_job) {
            p->pending_job++;
            next_channel = (i + 1) % migrate_multifd_channels();
            break;
        }
        qemu_mutex_unlock(&p->mutex);
    }
    assert(!p->pages->num);
    assert(!p->pages->block);

    p->packet_num = multifd_send_state->packet_num++;
    multifd_send_state->pages = p->pages;
    p->pages = pages;
    transferred = ((uint64_t) pages->num) * qemu_target_page_size()
                + p->packet_len;
    qemu_file_update_transfer(f, transferred);
    ram_counters.multifd_bytes += transferred;
    ram_counters.transferred += transferred;
    qemu_mutex_unlock(&p->mutex);
    qemu_sem_post(&p->sem);

    return 1;
}

int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
{
    MultiFDPages_t *pages = multifd_send_state->pages;

    if (!pages->block) {
        pages->block = block;
    }

    if (pages->block == block) {
        pages->offset[pages->num] = offset;
        pages->num++;

        if (pages->num < pages->allocated) {
            return 1;
        }
    }

    if (multifd_send_pages(f) < 0) {
        return -1;
    }

    if (pages->block != block) {
        return  multifd_queue_page(f, block, offset);
    }

    return 1;
}

static void multifd_send_terminate_threads(Error *err)
{
    int i;

    trace_multifd_send_terminate_threads(err != NULL);

    if (err) {
        MigrationState *s = migrate_get_current();
        migrate_set_error(s, err);
        if (s->state == MIGRATION_STATUS_SETUP ||
            s->state == MIGRATION_STATUS_PRE_SWITCHOVER ||
            s->state == MIGRATION_STATUS_DEVICE ||
            s->state == MIGRATION_STATUS_ACTIVE) {
            migrate_set_state(&s->state, s->state,
                              MIGRATION_STATUS_FAILED);
        }
    }

    /*
     * We don't want to exit each threads twice.  Depending on where
     * we get the error, or if there are two independent errors in two
     * threads at the same time, we can end calling this function
     * twice.
     */
    if (qatomic_xchg(&multifd_send_state->exiting, 1)) {
        return;
    }

    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        qemu_mutex_lock(&p->mutex);
        p->quit = true;
        qemu_sem_post(&p->sem);
        if (p->c) {
            qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
        }
        qemu_mutex_unlock(&p->mutex);
    }
}

void multifd_save_cleanup(void)
{
    int i;

    if (!migrate_use_multifd() || !migrate_multifd_is_allowed()) {
        return;
    }
    multifd_send_terminate_threads(NULL);
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        if (p->running) {
            qemu_thread_join(&p->thread);
        }
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];
        Error *local_err = NULL;

        if (p->registered_yank) {
            migration_ioc_unregister_yank(p->c);
        }
        socket_send_channel_destroy(p->c);
        p->c = NULL;
        qemu_mutex_destroy(&p->mutex);
        qemu_sem_destroy(&p->sem);
        qemu_sem_destroy(&p->sem_sync);
        g_free(p->name);
        p->name = NULL;
        g_free(p->tls_hostname);
        p->tls_hostname = NULL;
        multifd_pages_clear(p->pages);
        p->pages = NULL;
        p->packet_len = 0;
        g_free(p->packet);
        p->packet = NULL;
        g_free(p->iov);
        p->iov = NULL;
        g_free(p->normal);
        p->normal = NULL;
        multifd_send_state->ops->send_cleanup(p, &local_err);
        if (local_err) {
            migrate_set_error(migrate_get_current(), local_err);
            error_free(local_err);
        }
    }
    qemu_sem_destroy(&multifd_send_state->channels_ready);
    g_free(multifd_send_state->params);
    multifd_send_state->params = NULL;
    multifd_pages_clear(multifd_send_state->pages);
    multifd_send_state->pages = NULL;
    g_free(multifd_send_state);
    multifd_send_state = NULL;
}

void multifd_send_sync_main(QEMUFile *f)
{
    int i;

    if (!migrate_use_multifd()) {
        return;
    }
    if (multifd_send_state->pages->num) {
        if (multifd_send_pages(f) < 0) {
            error_report("%s: multifd_send_pages fail", __func__);
            return;
        }
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        trace_multifd_send_sync_main_signal(p->id);

        qemu_mutex_lock(&p->mutex);

        if (p->quit) {
            error_report("%s: channel %d has already quit", __func__, i);
            qemu_mutex_unlock(&p->mutex);
            return;
        }

        p->packet_num = multifd_send_state->packet_num++;
        p->flags |= MULTIFD_FLAG_SYNC;
        p->pending_job++;
        qemu_file_update_transfer(f, p->packet_len);
        ram_counters.multifd_bytes += p->packet_len;
        ram_counters.transferred += p->packet_len;
        qemu_mutex_unlock(&p->mutex);
        qemu_sem_post(&p->sem);
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        trace_multifd_send_sync_main_wait(p->id);
        qemu_sem_wait(&p->sem_sync);
    }
    trace_multifd_send_sync_main(multifd_send_state->packet_num);
}

static void *multifd_send_thread(void *opaque)
{
    MultiFDSendParams *p = opaque;
    Error *local_err = NULL;
    int ret = 0;

    trace_multifd_send_thread_start(p->id);
    rcu_register_thread();

    if (multifd_send_initial_packet(p, &local_err) < 0) {
        ret = -1;
        goto out;
    }
    /* initial packet */
    p->num_packets = 1;

    while (true) {
        qemu_sem_wait(&p->sem);

        if (qatomic_read(&multifd_send_state->exiting)) {
            break;
        }
        qemu_mutex_lock(&p->mutex);

        if (p->pending_job) {
            uint64_t packet_num = p->packet_num;
            uint32_t flags = p->flags;
            p->iovs_num = 1;
            p->normal_num = 0;

            for (int i = 0; i < p->pages->num; i++) {
                p->normal[p->normal_num] = p->pages->offset[i];
                p->normal_num++;
            }

            if (p->normal_num) {
                ret = multifd_send_state->ops->send_prepare(p, &local_err);
                if (ret != 0) {
                    qemu_mutex_unlock(&p->mutex);
                    break;
                }
            }
            multifd_send_fill_packet(p);
            p->flags = 0;
            p->num_packets++;
            p->total_normal_pages += p->normal_num;
            p->pages->num = 0;
            p->pages->block = NULL;
            qemu_mutex_unlock(&p->mutex);

            trace_multifd_send(p->id, packet_num, p->normal_num, flags,
                               p->next_packet_size);

            p->iov[0].iov_len = p->packet_len;
            p->iov[0].iov_base = p->packet;

            ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num,
                                         &local_err);
            if (ret != 0) {
                break;
            }

            qemu_mutex_lock(&p->mutex);
            p->pending_job--;
            qemu_mutex_unlock(&p->mutex);

            if (flags & MULTIFD_FLAG_SYNC) {
                qemu_sem_post(&p->sem_sync);
            }
            qemu_sem_post(&multifd_send_state->channels_ready);
        } else if (p->quit) {
            qemu_mutex_unlock(&p->mutex);
            break;
        } else {
            qemu_mutex_unlock(&p->mutex);
            /* sometimes there are spurious wakeups */
        }
    }

out:
    if (local_err) {
        trace_multifd_send_error(p->id);
        multifd_send_terminate_threads(local_err);
        error_free(local_err);
    }

    /*
     * Error happen, I will exit, but I can't just leave, tell
     * who pay attention to me.
     */
    if (ret != 0) {
        qemu_sem_post(&p->sem_sync);
        qemu_sem_post(&multifd_send_state->channels_ready);
    }

    qemu_mutex_lock(&p->mutex);
    p->running = false;
    qemu_mutex_unlock(&p->mutex);

    rcu_unregister_thread();
    trace_multifd_send_thread_end(p->id, p->num_packets, p->total_normal_pages);

    return NULL;
}

static bool multifd_channel_connect(MultiFDSendParams *p,
                                    QIOChannel *ioc,
                                    Error *error);

static void multifd_tls_outgoing_handshake(QIOTask *task,
                                           gpointer opaque)
{
    MultiFDSendParams *p = opaque;
    QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task));
    Error *err = NULL;

    if (qio_task_propagate_error(task, &err)) {
        trace_multifd_tls_outgoing_handshake_error(ioc, error_get_pretty(err));
    } else {
        trace_multifd_tls_outgoing_handshake_complete(ioc);
    }

    if (!multifd_channel_connect(p, ioc, err)) {
        /*
         * Error happen, mark multifd_send_thread status as 'quit' although it
         * is not created, and then tell who pay attention to me.
         */
        p->quit = true;
        qemu_sem_post(&multifd_send_state->channels_ready);
        qemu_sem_post(&p->sem_sync);
    }
}

static void *multifd_tls_handshake_thread(void *opaque)
{
    MultiFDSendParams *p = opaque;
    QIOChannelTLS *tioc = QIO_CHANNEL_TLS(p->c);

    qio_channel_tls_handshake(tioc,
                              multifd_tls_outgoing_handshake,
                              p,
                              NULL,
                              NULL);
    return NULL;
}

static void multifd_tls_channel_connect(MultiFDSendParams *p,
                                        QIOChannel *ioc,
                                        Error **errp)
{
    MigrationState *s = migrate_get_current();
    const char *hostname = p->tls_hostname;
    QIOChannelTLS *tioc;

    tioc = migration_tls_client_create(s, ioc, hostname, errp);
    if (!tioc) {
        return;
    }

    object_unref(OBJECT(ioc));
    trace_multifd_tls_outgoing_handshake_start(ioc, tioc, hostname);
    qio_channel_set_name(QIO_CHANNEL(tioc), "multifd-tls-outgoing");
    p->c = QIO_CHANNEL(tioc);
    qemu_thread_create(&p->thread, "multifd-tls-handshake-worker",
                       multifd_tls_handshake_thread, p,
                       QEMU_THREAD_JOINABLE);
}

static bool multifd_channel_connect(MultiFDSendParams *p,
                                    QIOChannel *ioc,
                                    Error *error)
{
    MigrationState *s = migrate_get_current();

    trace_multifd_set_outgoing_channel(
        ioc, object_get_typename(OBJECT(ioc)), p->tls_hostname, error);

    if (!error) {
        if (s->parameters.tls_creds &&
            *s->parameters.tls_creds &&
            !object_dynamic_cast(OBJECT(ioc),
                                 TYPE_QIO_CHANNEL_TLS)) {
            multifd_tls_channel_connect(p, ioc, &error);
            if (!error) {
                /*
                 * tls_channel_connect will call back to this
                 * function after the TLS handshake,
                 * so we mustn't call multifd_send_thread until then
                 */
                return true;
            } else {
                return false;
            }
        } else {
            migration_ioc_register_yank(ioc);
            p->registered_yank = true;
            p->c = ioc;
            qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
                                   QEMU_THREAD_JOINABLE);
       }
       return true;
    }

    return false;
}

static void multifd_new_send_channel_cleanup(MultiFDSendParams *p,
                                             QIOChannel *ioc, Error *err)
{
     migrate_set_error(migrate_get_current(), err);
     /* Error happen, we need to tell who pay attention to me */
     qemu_sem_post(&multifd_send_state->channels_ready);
     qemu_sem_post(&p->sem_sync);
     /*
      * Although multifd_send_thread is not created, but main migration
      * thread neet to judge whether it is running, so we need to mark
      * its status.
      */
     p->quit = true;
     object_unref(OBJECT(ioc));
     error_free(err);
}

static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
{
    MultiFDSendParams *p = opaque;
    QIOChannel *sioc = QIO_CHANNEL(qio_task_get_source(task));
    Error *local_err = NULL;

    trace_multifd_new_send_channel_async(p->id);
    if (qio_task_propagate_error(task, &local_err)) {
        goto cleanup;
    } else {
        p->c = QIO_CHANNEL(sioc);
        qio_channel_set_delay(p->c, false);
        p->running = true;
        if (!multifd_channel_connect(p, sioc, local_err)) {
            goto cleanup;
        }
        return;
    }

cleanup:
    multifd_new_send_channel_cleanup(p, sioc, local_err);
}

static bool migrate_allow_multifd = true;
void migrate_protocol_allow_multifd(bool allow)
{
    migrate_allow_multifd = allow;
}

bool migrate_multifd_is_allowed(void)
{
    return migrate_allow_multifd;
}

int multifd_save_setup(Error **errp)
{
    int thread_count;
    uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
    uint8_t i;
    MigrationState *s;

    if (!migrate_use_multifd()) {
        return 0;
    }
    if (!migrate_multifd_is_allowed()) {
        error_setg(errp, "multifd is not supported by current protocol");
        return -1;
    }

    s = migrate_get_current();
    thread_count = migrate_multifd_channels();
    multifd_send_state = g_malloc0(sizeof(*multifd_send_state));
    multifd_send_state->params = g_new0(MultiFDSendParams, thread_count);
    multifd_send_state->pages = multifd_pages_init(page_count);
    qemu_sem_init(&multifd_send_state->channels_ready, 0);
    qatomic_set(&multifd_send_state->exiting, 0);
    multifd_send_state->ops = multifd_ops[migrate_multifd_compression()];

    for (i = 0; i < thread_count; i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        qemu_mutex_init(&p->mutex);
        qemu_sem_init(&p->sem, 0);
        qemu_sem_init(&p->sem_sync, 0);
        p->quit = false;
        p->pending_job = 0;
        p->id = i;
        p->pages = multifd_pages_init(page_count);
        p->packet_len = sizeof(MultiFDPacket_t)
                      + sizeof(uint64_t) * page_count;
        p->packet = g_malloc0(p->packet_len);
        p->packet->magic = cpu_to_be32(MULTIFD_MAGIC);
        p->packet->version = cpu_to_be32(MULTIFD_VERSION);
        p->name = g_strdup_printf("multifdsend_%d", i);
        p->tls_hostname = g_strdup(s->hostname);
        /* We need one extra place for the packet header */
        p->iov = g_new0(struct iovec, page_count + 1);
        p->normal = g_new0(ram_addr_t, page_count);
        socket_send_channel_create(multifd_new_send_channel_async, p);
    }

    for (i = 0; i < thread_count; i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];
        Error *local_err = NULL;
        int ret;

        ret = multifd_send_state->ops->send_setup(p, &local_err);
        if (ret) {
            error_propagate(errp, local_err);
            return ret;
        }
    }
    return 0;
}

struct {
    MultiFDRecvParams *params;
    /* number of created threads */
    int count;
    /* syncs main thread and channels */
    QemuSemaphore sem_sync;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* multifd ops */
    MultiFDMethods *ops;
} *multifd_recv_state;

static void multifd_recv_terminate_threads(Error *err)
{
    int i;

    trace_multifd_recv_terminate_threads(err != NULL);

    if (err) {
        MigrationState *s = migrate_get_current();
        migrate_set_error(s, err);
        if (s->state == MIGRATION_STATUS_SETUP ||
            s->state == MIGRATION_STATUS_ACTIVE) {
            migrate_set_state(&s->state, s->state,
                              MIGRATION_STATUS_FAILED);
        }
    }

    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        qemu_mutex_lock(&p->mutex);
        p->quit = true;
        /*
         * We could arrive here for two reasons:
         *  - normal quit, i.e. everything went fine, just finished
         *  - error quit: We close the channels so the channel threads
         *    finish the qio_channel_read_all_eof()
         */
        if (p->c) {
            qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
        }
        qemu_mutex_unlock(&p->mutex);
    }
}

int multifd_load_cleanup(Error **errp)
{
    int i;

    if (!migrate_use_multifd() || !migrate_multifd_is_allowed()) {
        return 0;
    }
    multifd_recv_terminate_threads(NULL);
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        if (p->running) {
            p->quit = true;
            /*
             * multifd_recv_thread may hung at MULTIFD_FLAG_SYNC handle code,
             * however try to wakeup it without harm in cleanup phase.
             */
            qemu_sem_post(&p->sem_sync);
            qemu_thread_join(&p->thread);
        }
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        migration_ioc_unregister_yank(p->c);
        object_unref(OBJECT(p->c));
        p->c = NULL;
        qemu_mutex_destroy(&p->mutex);
        qemu_sem_destroy(&p->sem_sync);
        g_free(p->name);
        p->name = NULL;
        multifd_pages_clear(p->pages);
        p->pages = NULL;
        p->packet_len = 0;
        g_free(p->packet);
        p->packet = NULL;
        g_free(p->iov);
        p->iov = NULL;
        g_free(p->normal);
        p->normal = NULL;
        multifd_recv_state->ops->recv_cleanup(p);
    }
    qemu_sem_destroy(&multifd_recv_state->sem_sync);
    g_free(multifd_recv_state->params);
    multifd_recv_state->params = NULL;
    g_free(multifd_recv_state);
    multifd_recv_state = NULL;

    return 0;
}

void multifd_recv_sync_main(void)
{
    int i;

    if (!migrate_use_multifd()) {
        return;
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        trace_multifd_recv_sync_main_wait(p->id);
        qemu_sem_wait(&multifd_recv_state->sem_sync);
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        WITH_QEMU_LOCK_GUARD(&p->mutex) {
            if (multifd_recv_state->packet_num < p->packet_num) {
                multifd_recv_state->packet_num = p->packet_num;
            }
        }
        trace_multifd_recv_sync_main_signal(p->id);
        qemu_sem_post(&p->sem_sync);
    }
    trace_multifd_recv_sync_main(multifd_recv_state->packet_num);
}

static void *multifd_recv_thread(void *opaque)
{
    MultiFDRecvParams *p = opaque;
    Error *local_err = NULL;
    int ret;

    trace_multifd_recv_thread_start(p->id);
    rcu_register_thread();

    while (true) {
        uint32_t flags;

        if (p->quit) {
            break;
        }

        ret = qio_channel_read_all_eof(p->c, (void *)p->packet,
                                       p->packet_len, &local_err);
        if (ret == 0) {   /* EOF */
            break;
        }
        if (ret == -1) {   /* Error */
            break;
        }

        qemu_mutex_lock(&p->mutex);
        ret = multifd_recv_unfill_packet(p, &local_err);
        if (ret) {
            qemu_mutex_unlock(&p->mutex);
            break;
        }

        flags = p->flags;
        /* recv methods don't know how to handle the SYNC flag */
        p->flags &= ~MULTIFD_FLAG_SYNC;
        trace_multifd_recv(p->id, p->packet_num, p->normal_num, flags,
                           p->next_packet_size);
        p->num_packets++;
        p->total_normal_pages += p->normal_num;
        qemu_mutex_unlock(&p->mutex);

        if (p->normal_num) {
            ret = multifd_recv_state->ops->recv_pages(p, &local_err);
            if (ret != 0) {
                break;
            }
        }

        if (flags & MULTIFD_FLAG_SYNC) {
            qemu_sem_post(&multifd_recv_state->sem_sync);
            qemu_sem_wait(&p->sem_sync);
        }
    }

    if (local_err) {
        multifd_recv_terminate_threads(local_err);
        error_free(local_err);
    }
    qemu_mutex_lock(&p->mutex);
    p->running = false;
    qemu_mutex_unlock(&p->mutex);

    rcu_unregister_thread();
    trace_multifd_recv_thread_end(p->id, p->num_packets, p->total_normal_pages);

    return NULL;
}

int multifd_load_setup(Error **errp)
{
    int thread_count;
    uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
    uint8_t i;

    if (!migrate_use_multifd()) {
        return 0;
    }
    if (!migrate_multifd_is_allowed()) {
        error_setg(errp, "multifd is not supported by current protocol");
        return -1;
    }
    thread_count = migrate_multifd_channels();
    multifd_recv_state = g_malloc0(sizeof(*multifd_recv_state));
    multifd_recv_state->params = g_new0(MultiFDRecvParams, thread_count);
    qatomic_set(&multifd_recv_state->count, 0);
    qemu_sem_init(&multifd_recv_state->sem_sync, 0);
    multifd_recv_state->ops = multifd_ops[migrate_multifd_compression()];

    for (i = 0; i < thread_count; i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        qemu_mutex_init(&p->mutex);
        qemu_sem_init(&p->sem_sync, 0);
        p->quit = false;
        p->id = i;
        p->pages = multifd_pages_init(page_count);
        p->packet_len = sizeof(MultiFDPacket_t)
                      + sizeof(uint64_t) * page_count;
        p->packet = g_malloc0(p->packet_len);
        p->name = g_strdup_printf("multifdrecv_%d", i);
        p->iov = g_new0(struct iovec, page_count);
        p->normal = g_new0(ram_addr_t, page_count);
    }

    for (i = 0; i < thread_count; i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];
        Error *local_err = NULL;
        int ret;

        ret = multifd_recv_state->ops->recv_setup(p, &local_err);
        if (ret) {
            error_propagate(errp, local_err);
            return ret;
        }
    }
    return 0;
}

bool multifd_recv_all_channels_created(void)
{
    int thread_count = migrate_multifd_channels();

    if (!migrate_use_multifd()) {
        return true;
    }

    if (!multifd_recv_state) {
        /* Called before any connections created */
        return false;
    }

    return thread_count == qatomic_read(&multifd_recv_state->count);
}

/*
 * Try to receive all multifd channels to get ready for the migration.
 * - Return true and do not set @errp when correctly receiving all channels;
 * - Return false and do not set @errp when correctly receiving the current one;
 * - Return false and set @errp when failing to receive the current channel.
 */
bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
{
    MultiFDRecvParams *p;
    Error *local_err = NULL;
    int id;

    id = multifd_recv_initial_packet(ioc, &local_err);
    if (id < 0) {
        multifd_recv_terminate_threads(local_err);
        error_propagate_prepend(errp, local_err,
                                "failed to receive packet"
                                " via multifd channel %d: ",
                                qatomic_read(&multifd_recv_state->count));
        return false;
    }
    trace_multifd_recv_new_channel(id);

    p = &multifd_recv_state->params[id];
    if (p->c != NULL) {
        error_setg(&local_err, "multifd: received id '%d' already setup'",
                   id);
        multifd_recv_terminate_threads(local_err);
        error_propagate(errp, local_err);
        return false;
    }
    p->c = ioc;
    object_ref(OBJECT(ioc));
    /* initial packet */
    p->num_packets = 1;

    p->running = true;
    qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
                       QEMU_THREAD_JOINABLE);
    qatomic_inc(&multifd_recv_state->count);
    return qatomic_read(&multifd_recv_state->count) ==
           migrate_multifd_channels();
}