-
Notifications
You must be signed in to change notification settings - Fork 0
/
postcopy-ram.c
1448 lines (1275 loc) · 45.6 KB
/
postcopy-ram.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
/*
* Postcopy migration for RAM
*
* Copyright 2013-2015 Red Hat, Inc. and/or its affiliates
*
* Authors:
* Dave Gilbert <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
/*
* Postcopy is a migration technique where the execution flips from the
* source to the destination before all the data has been copied.
*/
#include "qemu/osdep.h"
#include "exec/target_page.h"
#include "migration.h"
#include "qemu-file.h"
#include "savevm.h"
#include "postcopy-ram.h"
#include "ram.h"
#include "qapi/error.h"
#include "qemu/notify.h"
#include "qemu/rcu.h"
#include "sysemu/sysemu.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/boards.h"
/* Arbitrary limit on size of each discard command,
* keeps them around ~200 bytes
*/
#define MAX_DISCARDS_PER_COMMAND 12
struct PostcopyDiscardState {
const char *ramblock_name;
uint16_t cur_entry;
/*
* Start and length of a discard range (bytes)
*/
uint64_t start_list[MAX_DISCARDS_PER_COMMAND];
uint64_t length_list[MAX_DISCARDS_PER_COMMAND];
unsigned int nsentwords;
unsigned int nsentcmds;
};
static NotifierWithReturnList postcopy_notifier_list;
void postcopy_infrastructure_init(void)
{
notifier_with_return_list_init(&postcopy_notifier_list);
}
void postcopy_add_notifier(NotifierWithReturn *nn)
{
notifier_with_return_list_add(&postcopy_notifier_list, nn);
}
void postcopy_remove_notifier(NotifierWithReturn *n)
{
notifier_with_return_remove(n);
}
int postcopy_notify(enum PostcopyNotifyReason reason, Error **errp)
{
struct PostcopyNotifyData pnd;
pnd.reason = reason;
pnd.errp = errp;
return notifier_with_return_list_notify(&postcopy_notifier_list,
&pnd);
}
/* Postcopy needs to detect accesses to pages that haven't yet been copied
* across, and efficiently map new pages in, the techniques for doing this
* are target OS specific.
*/
#if defined(__linux__)
#include <poll.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <asm/types.h> /* for __u64 */
#endif
#if defined(__linux__) && defined(__NR_userfaultfd) && defined(CONFIG_EVENTFD)
#include <sys/eventfd.h>
#include <linux/userfaultfd.h>
typedef struct PostcopyBlocktimeContext {
/* time when page fault initiated per vCPU */
uint32_t *page_fault_vcpu_time;
/* page address per vCPU */
uintptr_t *vcpu_addr;
uint32_t total_blocktime;
/* blocktime per vCPU */
uint32_t *vcpu_blocktime;
/* point in time when last page fault was initiated */
uint32_t last_begin;
/* number of vCPU are suspended */
int smp_cpus_down;
uint64_t start_time;
/*
* Handler for exit event, necessary for
* releasing whole blocktime_ctx
*/
Notifier exit_notifier;
} PostcopyBlocktimeContext;
static void destroy_blocktime_context(struct PostcopyBlocktimeContext *ctx)
{
g_free(ctx->page_fault_vcpu_time);
g_free(ctx->vcpu_addr);
g_free(ctx->vcpu_blocktime);
g_free(ctx);
}
static void migration_exit_cb(Notifier *n, void *data)
{
PostcopyBlocktimeContext *ctx = container_of(n, PostcopyBlocktimeContext,
exit_notifier);
destroy_blocktime_context(ctx);
}
static struct PostcopyBlocktimeContext *blocktime_context_new(void)
{
MachineState *ms = MACHINE(qdev_get_machine());
unsigned int smp_cpus = ms->smp.cpus;
PostcopyBlocktimeContext *ctx = g_new0(PostcopyBlocktimeContext, 1);
ctx->page_fault_vcpu_time = g_new0(uint32_t, smp_cpus);
ctx->vcpu_addr = g_new0(uintptr_t, smp_cpus);
ctx->vcpu_blocktime = g_new0(uint32_t, smp_cpus);
ctx->exit_notifier.notify = migration_exit_cb;
ctx->start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
qemu_add_exit_notifier(&ctx->exit_notifier);
return ctx;
}
static uint32List *get_vcpu_blocktime_list(PostcopyBlocktimeContext *ctx)
{
MachineState *ms = MACHINE(qdev_get_machine());
uint32List *list = NULL, *entry = NULL;
int i;
for (i = ms->smp.cpus - 1; i >= 0; i--) {
entry = g_new0(uint32List, 1);
entry->value = ctx->vcpu_blocktime[i];
entry->next = list;
list = entry;
}
return list;
}
/*
* This function just populates MigrationInfo from postcopy's
* blocktime context. It will not populate MigrationInfo,
* unless postcopy-blocktime capability was set.
*
* @info: pointer to MigrationInfo to populate
*/
void fill_destination_postcopy_migration_info(MigrationInfo *info)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
if (!bc) {
return;
}
info->has_postcopy_blocktime = true;
info->postcopy_blocktime = bc->total_blocktime;
info->has_postcopy_vcpu_blocktime = true;
info->postcopy_vcpu_blocktime = get_vcpu_blocktime_list(bc);
}
static uint32_t get_postcopy_total_blocktime(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
if (!bc) {
return 0;
}
return bc->total_blocktime;
}
/**
* receive_ufd_features: check userfault fd features, to request only supported
* features in the future.
*
* Returns: true on success
*
* __NR_userfaultfd - should be checked before
* @features: out parameter will contain uffdio_api.features provided by kernel
* in case of success
*/
static bool receive_ufd_features(uint64_t *features)
{
struct uffdio_api api_struct = {0};
int ufd;
bool ret = true;
/* if we are here __NR_userfaultfd should exists */
ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
if (ufd == -1) {
error_report("%s: syscall __NR_userfaultfd failed: %s", __func__,
strerror(errno));
return false;
}
/* ask features */
api_struct.api = UFFD_API;
api_struct.features = 0;
if (ioctl(ufd, UFFDIO_API, &api_struct)) {
error_report("%s: UFFDIO_API failed: %s", __func__,
strerror(errno));
ret = false;
goto release_ufd;
}
*features = api_struct.features;
release_ufd:
close(ufd);
return ret;
}
/**
* request_ufd_features: this function should be called only once on a newly
* opened ufd, subsequent calls will lead to error.
*
* Returns: true on succes
*
* @ufd: fd obtained from userfaultfd syscall
* @features: bit mask see UFFD_API_FEATURES
*/
static bool request_ufd_features(int ufd, uint64_t features)
{
struct uffdio_api api_struct = {0};
uint64_t ioctl_mask;
api_struct.api = UFFD_API;
api_struct.features = features;
if (ioctl(ufd, UFFDIO_API, &api_struct)) {
error_report("%s failed: UFFDIO_API failed: %s", __func__,
strerror(errno));
return false;
}
ioctl_mask = (__u64)1 << _UFFDIO_REGISTER |
(__u64)1 << _UFFDIO_UNREGISTER;
if ((api_struct.ioctls & ioctl_mask) != ioctl_mask) {
error_report("Missing userfault features: %" PRIx64,
(uint64_t)(~api_struct.ioctls & ioctl_mask));
return false;
}
return true;
}
static bool ufd_check_and_apply(int ufd, MigrationIncomingState *mis)
{
uint64_t asked_features = 0;
static uint64_t supported_features;
/*
* it's not possible to
* request UFFD_API twice per one fd
* userfault fd features is persistent
*/
if (!supported_features) {
if (!receive_ufd_features(&supported_features)) {
error_report("%s failed", __func__);
return false;
}
}
#ifdef UFFD_FEATURE_THREAD_ID
if (migrate_postcopy_blocktime() && mis &&
UFFD_FEATURE_THREAD_ID & supported_features) {
/* kernel supports that feature */
/* don't create blocktime_context if it exists */
if (!mis->blocktime_ctx) {
mis->blocktime_ctx = blocktime_context_new();
}
asked_features |= UFFD_FEATURE_THREAD_ID;
}
#endif
/*
* request features, even if asked_features is 0, due to
* kernel expects UFFD_API before UFFDIO_REGISTER, per
* userfault file descriptor
*/
if (!request_ufd_features(ufd, asked_features)) {
error_report("%s failed: features %" PRIu64, __func__,
asked_features);
return false;
}
if (qemu_real_host_page_size != ram_pagesize_summary()) {
bool have_hp = false;
/* We've got a huge page */
#ifdef UFFD_FEATURE_MISSING_HUGETLBFS
have_hp = supported_features & UFFD_FEATURE_MISSING_HUGETLBFS;
#endif
if (!have_hp) {
error_report("Userfault on this host does not support huge pages");
return false;
}
}
return true;
}
/* Callback from postcopy_ram_supported_by_host block iterator.
*/
static int test_ramblock_postcopiable(RAMBlock *rb, void *opaque)
{
const char *block_name = qemu_ram_get_idstr(rb);
ram_addr_t length = qemu_ram_get_used_length(rb);
size_t pagesize = qemu_ram_pagesize(rb);
if (length % pagesize) {
error_report("Postcopy requires RAM blocks to be a page size multiple,"
" block %s is 0x" RAM_ADDR_FMT " bytes with a "
"page size of 0x%zx", block_name, length, pagesize);
return 1;
}
return 0;
}
/*
* Note: This has the side effect of munlock'ing all of RAM, that's
* normally fine since if the postcopy succeeds it gets turned back on at the
* end.
*/
bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
{
long pagesize = qemu_real_host_page_size;
int ufd = -1;
bool ret = false; /* Error unless we change it */
void *testarea = NULL;
struct uffdio_register reg_struct;
struct uffdio_range range_struct;
uint64_t feature_mask;
Error *local_err = NULL;
if (qemu_target_page_size() > pagesize) {
error_report("Target page size bigger than host page size");
goto out;
}
ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
if (ufd == -1) {
error_report("%s: userfaultfd not available: %s", __func__,
strerror(errno));
goto out;
}
/* Give devices a chance to object */
if (postcopy_notify(POSTCOPY_NOTIFY_PROBE, &local_err)) {
error_report_err(local_err);
goto out;
}
/* Version and features check */
if (!ufd_check_and_apply(ufd, mis)) {
goto out;
}
/* We don't support postcopy with shared RAM yet */
if (foreach_not_ignored_block(test_ramblock_postcopiable, NULL)) {
goto out;
}
/*
* userfault and mlock don't go together; we'll put it back later if
* it was enabled.
*/
if (munlockall()) {
error_report("%s: munlockall: %s", __func__, strerror(errno));
return -1;
}
/*
* We need to check that the ops we need are supported on anon memory
* To do that we need to register a chunk and see the flags that
* are returned.
*/
testarea = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS, -1, 0);
if (testarea == MAP_FAILED) {
error_report("%s: Failed to map test area: %s", __func__,
strerror(errno));
goto out;
}
g_assert(((size_t)testarea & (pagesize-1)) == 0);
reg_struct.range.start = (uintptr_t)testarea;
reg_struct.range.len = pagesize;
reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
if (ioctl(ufd, UFFDIO_REGISTER, ®_struct)) {
error_report("%s userfault register: %s", __func__, strerror(errno));
goto out;
}
range_struct.start = (uintptr_t)testarea;
range_struct.len = pagesize;
if (ioctl(ufd, UFFDIO_UNREGISTER, &range_struct)) {
error_report("%s userfault unregister: %s", __func__, strerror(errno));
goto out;
}
feature_mask = (__u64)1 << _UFFDIO_WAKE |
(__u64)1 << _UFFDIO_COPY |
(__u64)1 << _UFFDIO_ZEROPAGE;
if ((reg_struct.ioctls & feature_mask) != feature_mask) {
error_report("Missing userfault map features: %" PRIx64,
(uint64_t)(~reg_struct.ioctls & feature_mask));
goto out;
}
/* Success! */
ret = true;
out:
if (testarea) {
munmap(testarea, pagesize);
}
if (ufd != -1) {
close(ufd);
}
return ret;
}
/*
* Setup an area of RAM so that it *can* be used for postcopy later; this
* must be done right at the start prior to pre-copy.
* opaque should be the MIS.
*/
static int init_range(RAMBlock *rb, void *opaque)
{
const char *block_name = qemu_ram_get_idstr(rb);
void *host_addr = qemu_ram_get_host_addr(rb);
ram_addr_t offset = qemu_ram_get_offset(rb);
ram_addr_t length = qemu_ram_get_used_length(rb);
trace_postcopy_init_range(block_name, host_addr, offset, length);
/*
* We need the whole of RAM to be truly empty for postcopy, so things
* like ROMs and any data tables built during init must be zero'd
* - we're going to get the copy from the source anyway.
* (Precopy will just overwrite this data, so doesn't need the discard)
*/
if (ram_discard_range(block_name, 0, length)) {
return -1;
}
return 0;
}
/*
* At the end of migration, undo the effects of init_range
* opaque should be the MIS.
*/
static int cleanup_range(RAMBlock *rb, void *opaque)
{
const char *block_name = qemu_ram_get_idstr(rb);
void *host_addr = qemu_ram_get_host_addr(rb);
ram_addr_t offset = qemu_ram_get_offset(rb);
ram_addr_t length = qemu_ram_get_used_length(rb);
MigrationIncomingState *mis = opaque;
struct uffdio_range range_struct;
trace_postcopy_cleanup_range(block_name, host_addr, offset, length);
/*
* We turned off hugepage for the precopy stage with postcopy enabled
* we can turn it back on now.
*/
qemu_madvise(host_addr, length, QEMU_MADV_HUGEPAGE);
/*
* We can also turn off userfault now since we should have all the
* pages. It can be useful to leave it on to debug postcopy
* if you're not sure it's always getting every page.
*/
range_struct.start = (uintptr_t)host_addr;
range_struct.len = length;
if (ioctl(mis->userfault_fd, UFFDIO_UNREGISTER, &range_struct)) {
error_report("%s: userfault unregister %s", __func__, strerror(errno));
return -1;
}
return 0;
}
/*
* Initialise postcopy-ram, setting the RAM to a state where we can go into
* postcopy later; must be called prior to any precopy.
* called from arch_init's similarly named ram_postcopy_incoming_init
*/
int postcopy_ram_incoming_init(MigrationIncomingState *mis)
{
if (foreach_not_ignored_block(init_range, NULL)) {
return -1;
}
return 0;
}
/*
* At the end of a migration where postcopy_ram_incoming_init was called.
*/
int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
{
trace_postcopy_ram_incoming_cleanup_entry();
if (mis->have_fault_thread) {
Error *local_err = NULL;
/* Let the fault thread quit */
atomic_set(&mis->fault_thread_quit, 1);
postcopy_fault_thread_notify(mis);
trace_postcopy_ram_incoming_cleanup_join();
qemu_thread_join(&mis->fault_thread);
if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_END, &local_err)) {
error_report_err(local_err);
return -1;
}
if (foreach_not_ignored_block(cleanup_range, mis)) {
return -1;
}
trace_postcopy_ram_incoming_cleanup_closeuf();
close(mis->userfault_fd);
close(mis->userfault_event_fd);
mis->have_fault_thread = false;
}
if (enable_mlock) {
if (os_mlock() < 0) {
error_report("mlock: %s", strerror(errno));
/*
* It doesn't feel right to fail at this point, we have a valid
* VM state.
*/
}
}
if (mis->postcopy_tmp_page) {
munmap(mis->postcopy_tmp_page, mis->largest_page_size);
mis->postcopy_tmp_page = NULL;
}
if (mis->postcopy_tmp_zero_page) {
munmap(mis->postcopy_tmp_zero_page, mis->largest_page_size);
mis->postcopy_tmp_zero_page = NULL;
}
trace_postcopy_ram_incoming_cleanup_blocktime(
get_postcopy_total_blocktime());
trace_postcopy_ram_incoming_cleanup_exit();
return 0;
}
/*
* Disable huge pages on an area
*/
static int nhp_range(RAMBlock *rb, void *opaque)
{
const char *block_name = qemu_ram_get_idstr(rb);
void *host_addr = qemu_ram_get_host_addr(rb);
ram_addr_t offset = qemu_ram_get_offset(rb);
ram_addr_t length = qemu_ram_get_used_length(rb);
trace_postcopy_nhp_range(block_name, host_addr, offset, length);
/*
* Before we do discards we need to ensure those discards really
* do delete areas of the page, even if THP thinks a hugepage would
* be a good idea, so force hugepages off.
*/
qemu_madvise(host_addr, length, QEMU_MADV_NOHUGEPAGE);
return 0;
}
/*
* Userfault requires us to mark RAM as NOHUGEPAGE prior to discard
* however leaving it until after precopy means that most of the precopy
* data is still THPd
*/
int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
{
if (foreach_not_ignored_block(nhp_range, mis)) {
return -1;
}
postcopy_state_set(POSTCOPY_INCOMING_DISCARD);
return 0;
}
/*
* Mark the given area of RAM as requiring notification to unwritten areas
* Used as a callback on foreach_not_ignored_block.
* host_addr: Base of area to mark
* offset: Offset in the whole ram arena
* length: Length of the section
* opaque: MigrationIncomingState pointer
* Returns 0 on success
*/
static int ram_block_enable_notify(RAMBlock *rb, void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffdio_register reg_struct;
reg_struct.range.start = (uintptr_t)qemu_ram_get_host_addr(rb);
reg_struct.range.len = qemu_ram_get_used_length(rb);
reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
/* Now tell our userfault_fd that it's responsible for this area */
if (ioctl(mis->userfault_fd, UFFDIO_REGISTER, ®_struct)) {
error_report("%s userfault register: %s", __func__, strerror(errno));
return -1;
}
if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
error_report("%s userfault: Region doesn't support COPY", __func__);
return -1;
}
if (reg_struct.ioctls & ((__u64)1 << _UFFDIO_ZEROPAGE)) {
qemu_ram_set_uf_zeroable(rb);
}
return 0;
}
int postcopy_wake_shared(struct PostCopyFD *pcfd,
uint64_t client_addr,
RAMBlock *rb)
{
size_t pagesize = qemu_ram_pagesize(rb);
struct uffdio_range range;
int ret;
trace_postcopy_wake_shared(client_addr, qemu_ram_get_idstr(rb));
range.start = client_addr & ~(pagesize - 1);
range.len = pagesize;
ret = ioctl(pcfd->fd, UFFDIO_WAKE, &range);
if (ret) {
error_report("%s: Failed to wake: %zx in %s (%s)",
__func__, (size_t)client_addr, qemu_ram_get_idstr(rb),
strerror(errno));
}
return ret;
}
/*
* Callback from shared fault handlers to ask for a page,
* the page must be specified by a RAMBlock and an offset in that rb
* Note: Only for use by shared fault handlers (in fault thread)
*/
int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
uint64_t client_addr, uint64_t rb_offset)
{
size_t pagesize = qemu_ram_pagesize(rb);
uint64_t aligned_rbo = rb_offset & ~(pagesize - 1);
MigrationIncomingState *mis = migration_incoming_get_current();
trace_postcopy_request_shared_page(pcfd->idstr, qemu_ram_get_idstr(rb),
rb_offset);
if (ramblock_recv_bitmap_test_byte_offset(rb, aligned_rbo)) {
trace_postcopy_request_shared_page_present(pcfd->idstr,
qemu_ram_get_idstr(rb), rb_offset);
return postcopy_wake_shared(pcfd, client_addr, rb);
}
if (rb != mis->last_rb) {
mis->last_rb = rb;
migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
aligned_rbo, pagesize);
} else {
/* Save some space */
migrate_send_rp_req_pages(mis, NULL, aligned_rbo, pagesize);
}
return 0;
}
static int get_mem_fault_cpu_index(uint32_t pid)
{
CPUState *cpu_iter;
CPU_FOREACH(cpu_iter) {
if (cpu_iter->thread_id == pid) {
trace_get_mem_fault_cpu_index(cpu_iter->cpu_index, pid);
return cpu_iter->cpu_index;
}
}
trace_get_mem_fault_cpu_index(-1, pid);
return -1;
}
static uint32_t get_low_time_offset(PostcopyBlocktimeContext *dc)
{
int64_t start_time_offset = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) -
dc->start_time;
return start_time_offset < 1 ? 1 : start_time_offset & UINT32_MAX;
}
/*
* This function is being called when pagefault occurs. It
* tracks down vCPU blocking time.
*
* @addr: faulted host virtual address
* @ptid: faulted process thread id
* @rb: ramblock appropriate to addr
*/
static void mark_postcopy_blocktime_begin(uintptr_t addr, uint32_t ptid,
RAMBlock *rb)
{
int cpu, already_received;
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *dc = mis->blocktime_ctx;
uint32_t low_time_offset;
if (!dc || ptid == 0) {
return;
}
cpu = get_mem_fault_cpu_index(ptid);
if (cpu < 0) {
return;
}
low_time_offset = get_low_time_offset(dc);
if (dc->vcpu_addr[cpu] == 0) {
atomic_inc(&dc->smp_cpus_down);
}
atomic_xchg(&dc->last_begin, low_time_offset);
atomic_xchg(&dc->page_fault_vcpu_time[cpu], low_time_offset);
atomic_xchg(&dc->vcpu_addr[cpu], addr);
/*
* check it here, not at the beginning of the function,
* due to, check could occur early than bitmap_set in
* qemu_ufd_copy_ioctl
*/
already_received = ramblock_recv_bitmap_test(rb, (void *)addr);
if (already_received) {
atomic_xchg(&dc->vcpu_addr[cpu], 0);
atomic_xchg(&dc->page_fault_vcpu_time[cpu], 0);
atomic_dec(&dc->smp_cpus_down);
}
trace_mark_postcopy_blocktime_begin(addr, dc, dc->page_fault_vcpu_time[cpu],
cpu, already_received);
}
/*
* This function just provide calculated blocktime per cpu and trace it.
* Total blocktime is calculated in mark_postcopy_blocktime_end.
*
*
* Assume we have 3 CPU
*
* S1 E1 S1 E1
* -----***********------------xxx***************------------------------> CPU1
*
* S2 E2
* ------------****************xxx---------------------------------------> CPU2
*
* S3 E3
* ------------------------****xxx********-------------------------------> CPU3
*
* We have sequence S1,S2,E1,S3,S1,E2,E3,E1
* S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include CPU3
* S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
* it's a part of total blocktime.
* S1 - here is last_begin
* Legend of the picture is following:
* * - means blocktime per vCPU
* x - means overlapped blocktime (total blocktime)
*
* @addr: host virtual address
*/
static void mark_postcopy_blocktime_end(uintptr_t addr)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *dc = mis->blocktime_ctx;
MachineState *ms = MACHINE(qdev_get_machine());
unsigned int smp_cpus = ms->smp.cpus;
int i, affected_cpu = 0;
bool vcpu_total_blocktime = false;
uint32_t read_vcpu_time, low_time_offset;
if (!dc) {
return;
}
low_time_offset = get_low_time_offset(dc);
/* lookup cpu, to clear it,
* that algorithm looks straighforward, but it's not
* optimal, more optimal algorithm is keeping tree or hash
* where key is address value is a list of */
for (i = 0; i < smp_cpus; i++) {
uint32_t vcpu_blocktime = 0;
read_vcpu_time = atomic_fetch_add(&dc->page_fault_vcpu_time[i], 0);
if (atomic_fetch_add(&dc->vcpu_addr[i], 0) != addr ||
read_vcpu_time == 0) {
continue;
}
atomic_xchg(&dc->vcpu_addr[i], 0);
vcpu_blocktime = low_time_offset - read_vcpu_time;
affected_cpu += 1;
/* we need to know is that mark_postcopy_end was due to
* faulted page, another possible case it's prefetched
* page and in that case we shouldn't be here */
if (!vcpu_total_blocktime &&
atomic_fetch_add(&dc->smp_cpus_down, 0) == smp_cpus) {
vcpu_total_blocktime = true;
}
/* continue cycle, due to one page could affect several vCPUs */
dc->vcpu_blocktime[i] += vcpu_blocktime;
}
atomic_sub(&dc->smp_cpus_down, affected_cpu);
if (vcpu_total_blocktime) {
dc->total_blocktime += low_time_offset - atomic_fetch_add(
&dc->last_begin, 0);
}
trace_mark_postcopy_blocktime_end(addr, dc, dc->total_blocktime,
affected_cpu);
}
static bool postcopy_pause_fault_thread(MigrationIncomingState *mis)
{
trace_postcopy_pause_fault_thread();
qemu_sem_wait(&mis->postcopy_pause_sem_fault);
trace_postcopy_pause_fault_thread_continued();
return true;
}
/*
* Handle faults detected by the USERFAULT markings
*/
static void *postcopy_ram_fault_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffd_msg msg;
int ret;
size_t index;
RAMBlock *rb = NULL;
trace_postcopy_ram_fault_thread_entry();
rcu_register_thread();
mis->last_rb = NULL; /* last RAMBlock we sent part of */
qemu_sem_post(&mis->fault_thread_sem);
struct pollfd *pfd;
size_t pfd_len = 2 + mis->postcopy_remote_fds->len;
pfd = g_new0(struct pollfd, pfd_len);
pfd[0].fd = mis->userfault_fd;
pfd[0].events = POLLIN;
pfd[1].fd = mis->userfault_event_fd;
pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */
trace_postcopy_ram_fault_thread_fds_core(pfd[0].fd, pfd[1].fd);
for (index = 0; index < mis->postcopy_remote_fds->len; index++) {
struct PostCopyFD *pcfd = &g_array_index(mis->postcopy_remote_fds,
struct PostCopyFD, index);
pfd[2 + index].fd = pcfd->fd;
pfd[2 + index].events = POLLIN;
trace_postcopy_ram_fault_thread_fds_extra(2 + index, pcfd->idstr,
pcfd->fd);
}
while (true) {
ram_addr_t rb_offset;
int poll_result;
/*
* We're mainly waiting for the kernel to give us a faulting HVA,
* however we can be told to quit via userfault_quit_fd which is
* an eventfd
*/
poll_result = poll(pfd, pfd_len, -1 /* Wait forever */);
if (poll_result == -1) {
error_report("%s: userfault poll: %s", __func__, strerror(errno));
break;
}
if (!mis->to_src_file) {
/*
* Possibly someone tells us that the return path is
* broken already using the event. We should hold until
* the channel is rebuilt.
*/
if (postcopy_pause_fault_thread(mis)) {
mis->last_rb = NULL;
/* Continue to read the userfaultfd */
} else {
error_report("%s: paused but don't allow to continue",
__func__);
break;
}
}
if (pfd[1].revents) {
uint64_t tmp64 = 0;
/* Consume the signal */
if (read(mis->userfault_event_fd, &tmp64, 8) != 8) {
/* Nothing obviously nicer than posting this error. */
error_report("%s: read() failed", __func__);
}
if (atomic_read(&mis->fault_thread_quit)) {
trace_postcopy_ram_fault_thread_quit();
break;
}
}
if (pfd[0].revents) {
poll_result--;
ret = read(mis->userfault_fd, &msg, sizeof(msg));
if (ret != sizeof(msg)) {
if (errno == EAGAIN) {
/*
* if a wake up happens on the other thread just after
* the poll, there is nothing to read.
*/
continue;
}
if (ret < 0) {
error_report("%s: Failed to read full userfault "
"message: %s",
__func__, strerror(errno));
break;
} else {
error_report("%s: Read %d bytes from userfaultfd "
"expected %zd",
__func__, ret, sizeof(msg));
break; /* Lost alignment, don't know what we'd read next */
}
}
if (msg.event != UFFD_EVENT_PAGEFAULT) {
error_report("%s: Read unexpected event %ud from userfaultfd",
__func__, msg.event);
continue; /* It's not a page fault, shouldn't happen */
}
rb = qemu_ram_block_from_host(
(void *)(uintptr_t)msg.arg.pagefault.address,
true, &rb_offset);
if (!rb) {
error_report("postcopy_ram_fault_thread: Fault outside guest: %"
PRIx64, (uint64_t)msg.arg.pagefault.address);
break;
}
rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
qemu_ram_get_idstr(rb),
rb_offset,
msg.arg.pagefault.feat.ptid);
mark_postcopy_blocktime_begin(
(uintptr_t)(msg.arg.pagefault.address),
msg.arg.pagefault.feat.ptid, rb);
retry:
/*
* Send the request to the source - we want to request one
* of our host page sizes (which is >= TPS)
*/
if (rb != mis->last_rb) {
mis->last_rb = rb;
ret = migrate_send_rp_req_pages(mis,
qemu_ram_get_idstr(rb),
rb_offset,
qemu_ram_pagesize(rb));
} else {
/* Save some space */
ret = migrate_send_rp_req_pages(mis,
NULL,
rb_offset,
qemu_ram_pagesize(rb));