forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
migrate.c
2212 lines (1926 loc) · 57.4 KB
/
migrate.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
// SPDX-License-Identifier: GPL-2.0
/*
* Memory Migration functionality - linux/mm/migrate.c
*
* Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
*
* Page migration was first developed in the context of the memory hotplug
* project. The main authors of the migration code are:
*
* IWAMOTO Toshihiro <[email protected]>
* Hirokazu Takahashi <[email protected]>
* Dave Hansen <[email protected]>
* Christoph Lameter
*/
#include <linux/migrate.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/mm_inline.h>
#include <linux/nsproxy.h>
#include <linux/pagevec.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/writeback.h>
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/compaction.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/balloon_compaction.h>
#include <linux/page_idle.h>
#include <linux/page_owner.h>
#include <linux/sched/mm.h>
#include <linux/ptrace.h>
#include <linux/oom.h>
#include <linux/memory.h>
#include <linux/random.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>
#include <asm/tlbflush.h>
#include <trace/events/migrate.h>
#include "internal.h"
int isolate_movable_page(struct page *page, isolate_mode_t mode)
{
const struct movable_operations *mops;
/*
* Avoid burning cycles with pages that are yet under __free_pages(),
* or just got freed under us.
*
* In case we 'win' a race for a movable page being freed under us and
* raise its refcount preventing __free_pages() from doing its job
* the put_page() at the end of this block will take care of
* release this page, thus avoiding a nasty leakage.
*/
if (unlikely(!get_page_unless_zero(page)))
goto out;
/*
* Check PageMovable before holding a PG_lock because page's owner
* assumes anybody doesn't touch PG_lock of newly allocated page
* so unconditionally grabbing the lock ruins page's owner side.
*/
if (unlikely(!__PageMovable(page)))
goto out_putpage;
/*
* As movable pages are not isolated from LRU lists, concurrent
* compaction threads can race against page migration functions
* as well as race against the releasing a page.
*
* In order to avoid having an already isolated movable page
* being (wrongly) re-isolated while it is under migration,
* or to avoid attempting to isolate pages being released,
* lets be sure we have the page lock
* before proceeding with the movable page isolation steps.
*/
if (unlikely(!trylock_page(page)))
goto out_putpage;
if (!PageMovable(page) || PageIsolated(page))
goto out_no_isolated;
mops = page_movable_ops(page);
VM_BUG_ON_PAGE(!mops, page);
if (!mops->isolate_page(page, mode))
goto out_no_isolated;
/* Driver shouldn't use PG_isolated bit of page->flags */
WARN_ON_ONCE(PageIsolated(page));
SetPageIsolated(page);
unlock_page(page);
return 0;
out_no_isolated:
unlock_page(page);
out_putpage:
put_page(page);
out:
return -EBUSY;
}
static void putback_movable_page(struct page *page)
{
const struct movable_operations *mops = page_movable_ops(page);
mops->putback_page(page);
ClearPageIsolated(page);
}
/*
* Put previously isolated pages back onto the appropriate lists
* from where they were once taken off for compaction/migration.
*
* This function shall be used whenever the isolated pageset has been
* built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
* and isolate_hugetlb().
*/
void putback_movable_pages(struct list_head *l)
{
struct page *page;
struct page *page2;
list_for_each_entry_safe(page, page2, l, lru) {
if (unlikely(PageHuge(page))) {
putback_active_hugepage(page);
continue;
}
list_del(&page->lru);
/*
* We isolated non-lru movable page so here we can use
* __PageMovable because LRU page's mapping cannot have
* PAGE_MAPPING_MOVABLE.
*/
if (unlikely(__PageMovable(page))) {
VM_BUG_ON_PAGE(!PageIsolated(page), page);
lock_page(page);
if (PageMovable(page))
putback_movable_page(page);
else
ClearPageIsolated(page);
unlock_page(page);
put_page(page);
} else {
mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
page_is_file_lru(page), -thp_nr_pages(page));
putback_lru_page(page);
}
}
}
/*
* Restore a potential migration pte to a working pte entry
*/
static bool remove_migration_pte(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr, void *old)
{
DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
while (page_vma_mapped_walk(&pvmw)) {
rmap_t rmap_flags = RMAP_NONE;
pte_t pte;
swp_entry_t entry;
struct page *new;
unsigned long idx = 0;
/* pgoff is invalid for ksm pages, but they are never large */
if (folio_test_large(folio) && !folio_test_hugetlb(folio))
idx = linear_page_index(vma, pvmw.address) - pvmw.pgoff;
new = folio_page(folio, idx);
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
/* PMD-mapped THP migration entry */
if (!pvmw.pte) {
VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
!folio_test_pmd_mappable(folio), folio);
remove_migration_pmd(&pvmw, new);
continue;
}
#endif
folio_get(folio);
pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
if (pte_swp_soft_dirty(*pvmw.pte))
pte = pte_mksoft_dirty(pte);
/*
* Recheck VMA as permissions can change since migration started
*/
entry = pte_to_swp_entry(*pvmw.pte);
if (!is_migration_entry_young(entry))
pte = pte_mkold(pte);
if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
pte = pte_mkdirty(pte);
if (is_writable_migration_entry(entry))
pte = maybe_mkwrite(pte, vma);
else if (pte_swp_uffd_wp(*pvmw.pte))
pte = pte_mkuffd_wp(pte);
if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
rmap_flags |= RMAP_EXCLUSIVE;
if (unlikely(is_device_private_page(new))) {
if (pte_write(pte))
entry = make_writable_device_private_entry(
page_to_pfn(new));
else
entry = make_readable_device_private_entry(
page_to_pfn(new));
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(*pvmw.pte))
pte = pte_swp_mksoft_dirty(pte);
if (pte_swp_uffd_wp(*pvmw.pte))
pte = pte_swp_mkuffd_wp(pte);
}
#ifdef CONFIG_HUGETLB_PAGE
if (folio_test_hugetlb(folio)) {
unsigned int shift = huge_page_shift(hstate_vma(vma));
pte = pte_mkhuge(pte);
pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
if (folio_test_anon(folio))
hugepage_add_anon_rmap(new, vma, pvmw.address,
rmap_flags);
else
page_dup_file_rmap(new, true);
set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
} else
#endif
{
if (folio_test_anon(folio))
page_add_anon_rmap(new, vma, pvmw.address,
rmap_flags);
else
page_add_file_rmap(new, vma, false);
set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
}
if (vma->vm_flags & VM_LOCKED)
mlock_page_drain_local();
trace_remove_migration_pte(pvmw.address, pte_val(pte),
compound_order(new));
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, pvmw.address, pvmw.pte);
}
return true;
}
/*
* Get rid of all migration entries and replace them by
* references to the indicated page.
*/
void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked)
{
struct rmap_walk_control rwc = {
.rmap_one = remove_migration_pte,
.arg = src,
};
if (locked)
rmap_walk_locked(dst, &rwc);
else
rmap_walk(dst, &rwc);
}
/*
* Something used the pte of a page under migration. We need to
* get to the page and wait until migration is finished.
* When we return from this function the fault will be retried.
*/
void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
spinlock_t *ptl)
{
pte_t pte;
swp_entry_t entry;
spin_lock(ptl);
pte = *ptep;
if (!is_swap_pte(pte))
goto out;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
goto out;
migration_entry_wait_on_locked(entry, ptep, ptl);
return;
out:
pte_unmap_unlock(ptep, ptl);
}
void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address)
{
spinlock_t *ptl = pte_lockptr(mm, pmd);
pte_t *ptep = pte_offset_map(pmd, address);
__migration_entry_wait(mm, ptep, ptl);
}
#ifdef CONFIG_HUGETLB_PAGE
void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl)
{
pte_t pte;
spin_lock(ptl);
pte = huge_ptep_get(ptep);
if (unlikely(!is_hugetlb_entry_migration(pte)))
spin_unlock(ptl);
else
migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl);
}
void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte)
{
spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte);
__migration_entry_wait_huge(pte, ptl);
}
#endif
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
{
spinlock_t *ptl;
ptl = pmd_lock(mm, pmd);
if (!is_pmd_migration_entry(*pmd))
goto unlock;
migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl);
return;
unlock:
spin_unlock(ptl);
}
#endif
static int folio_expected_refs(struct address_space *mapping,
struct folio *folio)
{
int refs = 1;
if (!mapping)
return refs;
refs += folio_nr_pages(folio);
if (folio_test_private(folio))
refs++;
return refs;
}
/*
* Replace the page in the mapping.
*
* The number of remaining references must be:
* 1 for anonymous pages without a mapping
* 2 for pages with a mapping
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
int folio_migrate_mapping(struct address_space *mapping,
struct folio *newfolio, struct folio *folio, int extra_count)
{
XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct zone *oldzone, *newzone;
int dirty;
int expected_count = folio_expected_refs(mapping, folio) + extra_count;
long nr = folio_nr_pages(folio);
if (!mapping) {
/* Anonymous page without mapping */
if (folio_ref_count(folio) != expected_count)
return -EAGAIN;
/* No turning back from here */
newfolio->index = folio->index;
newfolio->mapping = folio->mapping;
if (folio_test_swapbacked(folio))
__folio_set_swapbacked(newfolio);
return MIGRATEPAGE_SUCCESS;
}
oldzone = folio_zone(folio);
newzone = folio_zone(newfolio);
xas_lock_irq(&xas);
if (!folio_ref_freeze(folio, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
/*
* Now we know that no one else is looking at the folio:
* no turning back from here.
*/
newfolio->index = folio->index;
newfolio->mapping = folio->mapping;
folio_ref_add(newfolio, nr); /* add cache reference */
if (folio_test_swapbacked(folio)) {
__folio_set_swapbacked(newfolio);
if (folio_test_swapcache(folio)) {
folio_set_swapcache(newfolio);
newfolio->private = folio_get_private(folio);
}
} else {
VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
}
/* Move dirty while page refs frozen and newpage not yet exposed */
dirty = folio_test_dirty(folio);
if (dirty) {
folio_clear_dirty(folio);
folio_set_dirty(newfolio);
}
xas_store(&xas, newfolio);
/*
* Drop cache reference from old page by unfreezing
* to one less reference.
* We know this isn't the last reference.
*/
folio_ref_unfreeze(folio, expected_count - nr);
xas_unlock(&xas);
/* Leave irq disabled to prevent preemption while updating stats */
/*
* If moved to a different zone then also account
* the page for that zone. Other VM counters will be
* taken care of when we establish references to the
* new page and drop references to the old page.
*
* Note that anonymous pages are accounted for
* via NR_FILE_PAGES and NR_ANON_MAPPED if they
* are mapped to swap space.
*/
if (newzone != oldzone) {
struct lruvec *old_lruvec, *new_lruvec;
struct mem_cgroup *memcg;
memcg = folio_memcg(folio);
old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
__mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
__mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
}
#ifdef CONFIG_SWAP
if (folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
}
#endif
if (dirty && mapping_can_writeback(mapping)) {
__mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
__mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
__mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr);
__mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr);
}
}
local_irq_enable();
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(folio_migrate_mapping);
/*
* The expected number of remaining references is the same as that
* of folio_migrate_mapping().
*/
int migrate_huge_page_move_mapping(struct address_space *mapping,
struct folio *dst, struct folio *src)
{
XA_STATE(xas, &mapping->i_pages, folio_index(src));
int expected_count;
xas_lock_irq(&xas);
expected_count = 2 + folio_has_private(src);
if (!folio_ref_freeze(src, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
dst->index = src->index;
dst->mapping = src->mapping;
folio_get(dst);
xas_store(&xas, dst);
folio_ref_unfreeze(src, expected_count - 1);
xas_unlock_irq(&xas);
return MIGRATEPAGE_SUCCESS;
}
/*
* Copy the flags and some other ancillary information
*/
void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
{
int cpupid;
if (folio_test_error(folio))
folio_set_error(newfolio);
if (folio_test_referenced(folio))
folio_set_referenced(newfolio);
if (folio_test_uptodate(folio))
folio_mark_uptodate(newfolio);
if (folio_test_clear_active(folio)) {
VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio);
folio_set_active(newfolio);
} else if (folio_test_clear_unevictable(folio))
folio_set_unevictable(newfolio);
if (folio_test_workingset(folio))
folio_set_workingset(newfolio);
if (folio_test_checked(folio))
folio_set_checked(newfolio);
/*
* PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via
* migration entries. We can still have PG_anon_exclusive set on an
* effectively unmapped and unreferenced first sub-pages of an
* anonymous THP: we can simply copy it here via PG_mappedtodisk.
*/
if (folio_test_mappedtodisk(folio))
folio_set_mappedtodisk(newfolio);
/* Move dirty on pages not done by folio_migrate_mapping() */
if (folio_test_dirty(folio))
folio_set_dirty(newfolio);
if (folio_test_young(folio))
folio_set_young(newfolio);
if (folio_test_idle(folio))
folio_set_idle(newfolio);
/*
* Copy NUMA information to the new page, to prevent over-eager
* future migrations of this same page.
*/
cpupid = page_cpupid_xchg_last(&folio->page, -1);
/*
* For memory tiering mode, when migrate between slow and fast
* memory node, reset cpupid, because that is used to record
* page access time in slow memory node.
*/
if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) {
bool f_toptier = node_is_toptier(page_to_nid(&folio->page));
bool t_toptier = node_is_toptier(page_to_nid(&newfolio->page));
if (f_toptier != t_toptier)
cpupid = -1;
}
page_cpupid_xchg_last(&newfolio->page, cpupid);
folio_migrate_ksm(newfolio, folio);
/*
* Please do not reorder this without considering how mm/ksm.c's
* get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
*/
if (folio_test_swapcache(folio))
folio_clear_swapcache(folio);
folio_clear_private(folio);
/* page->private contains hugetlb specific flags */
if (!folio_test_hugetlb(folio))
folio->private = NULL;
/*
* If any waiters have accumulated on the new page then
* wake them up.
*/
if (folio_test_writeback(newfolio))
folio_end_writeback(newfolio);
/*
* PG_readahead shares the same bit with PG_reclaim. The above
* end_page_writeback() may clear PG_readahead mistakenly, so set the
* bit after that.
*/
if (folio_test_readahead(folio))
folio_set_readahead(newfolio);
folio_copy_owner(newfolio, folio);
if (!folio_test_hugetlb(folio))
mem_cgroup_migrate(folio, newfolio);
}
EXPORT_SYMBOL(folio_migrate_flags);
void folio_migrate_copy(struct folio *newfolio, struct folio *folio)
{
folio_copy(newfolio, folio);
folio_migrate_flags(newfolio, folio);
}
EXPORT_SYMBOL(folio_migrate_copy);
/************************************************************
* Migration functions
***********************************************************/
int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
struct folio *src, enum migrate_mode mode, int extra_count)
{
int rc;
BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */
rc = folio_migrate_mapping(mapping, dst, src, extra_count);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
if (mode != MIGRATE_SYNC_NO_COPY)
folio_migrate_copy(dst, src);
else
folio_migrate_flags(dst, src);
return MIGRATEPAGE_SUCCESS;
}
/**
* migrate_folio() - Simple folio migration.
* @mapping: The address_space containing the folio.
* @dst: The folio to migrate the data to.
* @src: The folio containing the current data.
* @mode: How to migrate the page.
*
* Common logic to directly migrate a single LRU folio suitable for
* folios that do not use PagePrivate/PagePrivate2.
*
* Folios are locked upon entry and exit.
*/
int migrate_folio(struct address_space *mapping, struct folio *dst,
struct folio *src, enum migrate_mode mode)
{
return migrate_folio_extra(mapping, dst, src, mode, 0);
}
EXPORT_SYMBOL(migrate_folio);
#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
static bool buffer_migrate_lock_buffers(struct buffer_head *head,
enum migrate_mode mode)
{
struct buffer_head *bh = head;
/* Simple case, sync compaction */
if (mode != MIGRATE_ASYNC) {
do {
lock_buffer(bh);
bh = bh->b_this_page;
} while (bh != head);
return true;
}
/* async case, we cannot block on lock_buffer so use trylock_buffer */
do {
if (!trylock_buffer(bh)) {
/*
* We failed to lock the buffer and cannot stall in
* async migration. Release the taken locks
*/
struct buffer_head *failed_bh = bh;
bh = head;
while (bh != failed_bh) {
unlock_buffer(bh);
bh = bh->b_this_page;
}
return false;
}
bh = bh->b_this_page;
} while (bh != head);
return true;
}
static int __buffer_migrate_folio(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode,
bool check_refs)
{
struct buffer_head *bh, *head;
int rc;
int expected_count;
head = folio_buffers(src);
if (!head)
return migrate_folio(mapping, dst, src, mode);
/* Check whether page does not have extra refs before we do more work */
expected_count = folio_expected_refs(mapping, src);
if (folio_ref_count(src) != expected_count)
return -EAGAIN;
if (!buffer_migrate_lock_buffers(head, mode))
return -EAGAIN;
if (check_refs) {
bool busy;
bool invalidated = false;
recheck_buffers:
busy = false;
spin_lock(&mapping->private_lock);
bh = head;
do {
if (atomic_read(&bh->b_count)) {
busy = true;
break;
}
bh = bh->b_this_page;
} while (bh != head);
if (busy) {
if (invalidated) {
rc = -EAGAIN;
goto unlock_buffers;
}
spin_unlock(&mapping->private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
}
}
rc = folio_migrate_mapping(mapping, dst, src, 0);
if (rc != MIGRATEPAGE_SUCCESS)
goto unlock_buffers;
folio_attach_private(dst, folio_detach_private(src));
bh = head;
do {
set_bh_page(bh, &dst->page, bh_offset(bh));
bh = bh->b_this_page;
} while (bh != head);
if (mode != MIGRATE_SYNC_NO_COPY)
folio_migrate_copy(dst, src);
else
folio_migrate_flags(dst, src);
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
if (check_refs)
spin_unlock(&mapping->private_lock);
bh = head;
do {
unlock_buffer(bh);
bh = bh->b_this_page;
} while (bh != head);
return rc;
}
/**
* buffer_migrate_folio() - Migration function for folios with buffers.
* @mapping: The address space containing @src.
* @dst: The folio to migrate to.
* @src: The folio to migrate from.
* @mode: How to migrate the folio.
*
* This function can only be used if the underlying filesystem guarantees
* that no other references to @src exist. For example attached buffer
* heads are accessed only under the folio lock. If your filesystem cannot
* provide this guarantee, buffer_migrate_folio_norefs() may be more
* appropriate.
*
* Return: 0 on success or a negative errno on failure.
*/
int buffer_migrate_folio(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode)
{
return __buffer_migrate_folio(mapping, dst, src, mode, false);
}
EXPORT_SYMBOL(buffer_migrate_folio);
/**
* buffer_migrate_folio_norefs() - Migration function for folios with buffers.
* @mapping: The address space containing @src.
* @dst: The folio to migrate to.
* @src: The folio to migrate from.
* @mode: How to migrate the folio.
*
* Like buffer_migrate_folio() except that this variant is more careful
* and checks that there are also no buffer head references. This function
* is the right one for mappings where buffer heads are directly looked
* up and referenced (such as block device mappings).
*
* Return: 0 on success or a negative errno on failure.
*/
int buffer_migrate_folio_norefs(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode)
{
return __buffer_migrate_folio(mapping, dst, src, mode, true);
}
#endif
int filemap_migrate_folio(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode)
{
int ret;
ret = folio_migrate_mapping(mapping, dst, src, 0);
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
if (folio_get_private(src))
folio_attach_private(dst, folio_detach_private(src));
if (mode != MIGRATE_SYNC_NO_COPY)
folio_migrate_copy(dst, src);
else
folio_migrate_flags(dst, src);
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL_GPL(filemap_migrate_folio);
/*
* Writeback a folio to clean the dirty state
*/
static int writeout(struct address_space *mapping, struct folio *folio)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = 1,
.range_start = 0,
.range_end = LLONG_MAX,
.for_reclaim = 1
};
int rc;
if (!mapping->a_ops->writepage)
/* No write method for the address space */
return -EINVAL;
if (!folio_clear_dirty_for_io(folio))
/* Someone else already triggered a write */
return -EAGAIN;
/*
* A dirty folio may imply that the underlying filesystem has
* the folio on some queue. So the folio must be clean for
* migration. Writeout may mean we lose the lock and the
* folio state is no longer what we checked for earlier.
* At this point we know that the migration attempt cannot
* be successful.
*/
remove_migration_ptes(folio, folio, false);
rc = mapping->a_ops->writepage(&folio->page, &wbc);
if (rc != AOP_WRITEPAGE_ACTIVATE)
/* unlocked. Relock */
folio_lock(folio);
return (rc < 0) ? -EIO : -EAGAIN;
}
/*
* Default handling if a filesystem does not provide a migration function.
*/
static int fallback_migrate_folio(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode)
{
if (folio_test_dirty(src)) {
/* Only writeback folios in full synchronous migration */
switch (mode) {
case MIGRATE_SYNC:
case MIGRATE_SYNC_NO_COPY:
break;
default:
return -EBUSY;
}
return writeout(mapping, src);
}
/*
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
if (folio_test_private(src) &&
!filemap_release_folio(src, GFP_KERNEL))
return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;
return migrate_folio(mapping, dst, src, mode);
}
/*
* Move a page to a newly allocated page
* The page is locked and all ptes have been successfully removed.
*
* The new page will have replaced the old page if this function
* is successful.
*
* Return value:
* < 0 - error code
* MIGRATEPAGE_SUCCESS - success
*/
static int move_to_new_folio(struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
int rc = -EAGAIN;
bool is_lru = !__PageMovable(&src->page);
VM_BUG_ON_FOLIO(!folio_test_locked(src), src);
VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst);
if (likely(is_lru)) {
struct address_space *mapping = folio_mapping(src);
if (!mapping)
rc = migrate_folio(mapping, dst, src, mode);
else if (mapping->a_ops->migrate_folio)
/*
* Most folios have a mapping and most filesystems
* provide a migrate_folio callback. Anonymous folios
* are part of swap space which also has its own
* migrate_folio callback. This is the most common path
* for page migration.
*/
rc = mapping->a_ops->migrate_folio(mapping, dst, src,
mode);
else
rc = fallback_migrate_folio(mapping, dst, src, mode);
} else {
const struct movable_operations *mops;
/*
* In case of non-lru page, it could be released after
* isolation step. In that case, we shouldn't try migration.
*/
VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
if (!folio_test_movable(src)) {
rc = MIGRATEPAGE_SUCCESS;
folio_clear_isolated(src);
goto out;
}
mops = page_movable_ops(&src->page);
rc = mops->migrate_page(&dst->page, &src->page, mode);
WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
!folio_test_isolated(src));
}
/*
* When successful, old pagecache src->mapping must be cleared before
* src is freed; but stats require that PageAnon be left as PageAnon.
*/
if (rc == MIGRATEPAGE_SUCCESS) {
if (__PageMovable(&src->page)) {
VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
/*
* We clear PG_movable under page_lock so any compactor
* cannot try to migrate this page.
*/
folio_clear_isolated(src);
}
/*
* Anonymous and movable src->mapping will be cleared by
* free_pages_prepare so don't reset it here for keeping
* the type to work PageAnon, for example.
*/
if (!folio_mapping_flags(src))
src->mapping = NULL;
if (likely(!folio_is_zone_device(dst)))
flush_dcache_folio(dst);
}
out:
return rc;
}