forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dax.c
1717 lines (1513 loc) · 47 KB
/
dax.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
/*
* fs/dax.c - Direct Access filesystem code
* Copyright (c) 2013-2014 Intel Corporation
* Author: Matthew Wilcox <[email protected]>
* Author: Ross Zwisler <[email protected]>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/fs_dax.h>
/* We choose 4096 entries - same as per-zone page wait tables */
#define DAX_WAIT_TABLE_BITS 12
#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
/* The 'colour' (ie low bits) within a PMD of a page offset. */
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
#define PG_PMD_NR (PMD_SIZE >> PAGE_SHIFT)
static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
static int __init init_dax_wait_table(void)
{
int i;
for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
init_waitqueue_head(wait_table + i);
return 0;
}
fs_initcall(init_dax_wait_table);
/*
* We use lowest available bit in exceptional entry for locking, one bit for
* the entry size (PMD) and two more to tell us if the entry is a zero page or
* an empty entry that is just used for locking. In total four special bits.
*
* If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
* and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
* block allocation.
*/
#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
static unsigned long dax_radix_pfn(void *entry)
{
return (unsigned long)entry >> RADIX_DAX_SHIFT;
}
static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
{
return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
}
static unsigned int dax_radix_order(void *entry)
{
if ((unsigned long)entry & RADIX_DAX_PMD)
return PMD_SHIFT - PAGE_SHIFT;
return 0;
}
static int dax_is_pmd_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_PMD;
}
static int dax_is_pte_entry(void *entry)
{
return !((unsigned long)entry & RADIX_DAX_PMD);
}
static int dax_is_zero_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
}
static int dax_is_empty_entry(void *entry)
{
return (unsigned long)entry & RADIX_DAX_EMPTY;
}
/*
* DAX radix tree locking
*/
struct exceptional_entry_key {
struct address_space *mapping;
pgoff_t entry_start;
};
struct wait_exceptional_entry_queue {
wait_queue_entry_t wait;
struct exceptional_entry_key key;
};
static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
pgoff_t index, void *entry, struct exceptional_entry_key *key)
{
unsigned long hash;
/*
* If 'entry' is a PMD, align the 'index' that we use for the wait
* queue to the start of that PMD. This ensures that all offsets in
* the range covered by the PMD map to the same bit lock.
*/
if (dax_is_pmd_entry(entry))
index &= ~PG_PMD_COLOUR;
key->mapping = mapping;
key->entry_start = index;
hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS);
return wait_table + hash;
}
static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode,
int sync, void *keyp)
{
struct exceptional_entry_key *key = keyp;
struct wait_exceptional_entry_queue *ewait =
container_of(wait, struct wait_exceptional_entry_queue, wait);
if (key->mapping != ewait->key.mapping ||
key->entry_start != ewait->key.entry_start)
return 0;
return autoremove_wake_function(wait, mode, sync, NULL);
}
/*
* @entry may no longer be the entry at the index in the mapping.
* The important information it's conveying is whether the entry at
* this index used to be a PMD entry.
*/
static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
pgoff_t index, void *entry, bool wake_all)
{
struct exceptional_entry_key key;
wait_queue_head_t *wq;
wq = dax_entry_waitqueue(mapping, index, entry, &key);
/*
* Checking for locked entry and prepare_to_wait_exclusive() happens
* under the i_pages lock, ditto for entry handling in our callers.
* So at this point all tasks that could have seen our entry locked
* must be in the waitqueue and the following check will see them.
*/
if (waitqueue_active(wq))
__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
}
/*
* Check whether the given slot is locked. Must be called with the i_pages
* lock held.
*/
static inline int slot_locked(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
return entry & RADIX_DAX_ENTRY_LOCK;
}
/*
* Mark the given slot as locked. Must be called with the i_pages lock held.
*/
static inline void *lock_slot(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
entry |= RADIX_DAX_ENTRY_LOCK;
radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
return (void *)entry;
}
/*
* Mark the given slot as unlocked. Must be called with the i_pages lock held.
*/
static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
unsigned long entry = (unsigned long)
radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
return (void *)entry;
}
/*
* Lookup entry in radix tree, wait for it to become unlocked if it is
* exceptional entry and return it. The caller must call
* put_unlocked_mapping_entry() when he decided not to lock the entry or
* put_locked_mapping_entry() when he locked the entry and now wants to
* unlock it.
*
* Must be called with the i_pages lock held.
*/
static void *get_unlocked_mapping_entry(struct address_space *mapping,
pgoff_t index, void ***slotp)
{
void *entry, **slot;
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
init_wait(&ewait.wait);
ewait.wait.func = wake_exceptional_entry_func;
for (;;) {
entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
&slot);
if (!entry ||
WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
!slot_locked(mapping, slot)) {
if (slotp)
*slotp = slot;
return entry;
}
wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
prepare_to_wait_exclusive(wq, &ewait.wait,
TASK_UNINTERRUPTIBLE);
xa_unlock_irq(&mapping->i_pages);
schedule();
finish_wait(wq, &ewait.wait);
xa_lock_irq(&mapping->i_pages);
}
}
static void dax_unlock_mapping_entry(struct address_space *mapping,
pgoff_t index)
{
void *entry, **slot;
xa_lock_irq(&mapping->i_pages);
entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
!slot_locked(mapping, slot))) {
xa_unlock_irq(&mapping->i_pages);
return;
}
unlock_slot(mapping, slot);
xa_unlock_irq(&mapping->i_pages);
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}
static void put_locked_mapping_entry(struct address_space *mapping,
pgoff_t index)
{
dax_unlock_mapping_entry(mapping, index);
}
/*
* Called when we are done with radix tree entry we looked up via
* get_unlocked_mapping_entry() and which we didn't lock in the end.
*/
static void put_unlocked_mapping_entry(struct address_space *mapping,
pgoff_t index, void *entry)
{
if (!entry)
return;
/* We have to wake up next waiter for the radix tree entry lock */
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}
static unsigned long dax_entry_size(void *entry)
{
if (dax_is_zero_entry(entry))
return 0;
else if (dax_is_empty_entry(entry))
return 0;
else if (dax_is_pmd_entry(entry))
return PMD_SIZE;
else
return PAGE_SIZE;
}
static unsigned long dax_radix_end_pfn(void *entry)
{
return dax_radix_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
}
/*
* Iterate through all mapped pfns represented by an entry, i.e. skip
* 'empty' and 'zero' entries.
*/
#define for_each_mapped_pfn(entry, pfn) \
for (pfn = dax_radix_pfn(entry); \
pfn < dax_radix_end_pfn(entry); pfn++)
static void dax_associate_entry(void *entry, struct address_space *mapping)
{
unsigned long pfn;
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return;
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
WARN_ON_ONCE(page->mapping);
page->mapping = mapping;
}
}
static void dax_disassociate_entry(void *entry, struct address_space *mapping,
bool trunc)
{
unsigned long pfn;
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return;
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
WARN_ON_ONCE(page->mapping && page->mapping != mapping);
page->mapping = NULL;
}
}
static struct page *dax_busy_page(void *entry)
{
unsigned long pfn;
for_each_mapped_pfn(entry, pfn) {
struct page *page = pfn_to_page(pfn);
if (page_ref_count(page) > 1)
return page;
}
return NULL;
}
/*
* Find radix tree entry at given index. If it points to an exceptional entry,
* return it with the radix tree entry locked. If the radix tree doesn't
* contain given index, create an empty exceptional entry for the index and
* return with it locked.
*
* When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
* either return that locked entry or will return an error. This error will
* happen if there are any 4k entries within the 2MiB range that we are
* requesting.
*
* We always favor 4k entries over 2MiB entries. There isn't a flow where we
* evict 4k entries in order to 'upgrade' them to a 2MiB entry. A 2MiB
* insertion will fail if it finds any 4k entries already in the tree, and a
* 4k insertion will cause an existing 2MiB entry to be unmapped and
* downgraded to 4k entries. This happens for both 2MiB huge zero pages as
* well as 2MiB empty entries.
*
* The exception to this downgrade path is for 2MiB DAX PMD entries that have
* real storage backing them. We will leave these real 2MiB DAX entries in
* the tree, and PTE writes will simply dirty the entire 2MiB DAX entry.
*
* Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
* persistent memory the benefit is doubtful. We can add that later if we can
* show it helps.
*/
static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
unsigned long size_flag)
{
bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
void *entry, **slot;
restart:
xa_lock_irq(&mapping->i_pages);
entry = get_unlocked_mapping_entry(mapping, index, &slot);
if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
entry = ERR_PTR(-EIO);
goto out_unlock;
}
if (entry) {
if (size_flag & RADIX_DAX_PMD) {
if (dax_is_pte_entry(entry)) {
put_unlocked_mapping_entry(mapping, index,
entry);
entry = ERR_PTR(-EEXIST);
goto out_unlock;
}
} else { /* trying to grab a PTE entry */
if (dax_is_pmd_entry(entry) &&
(dax_is_zero_entry(entry) ||
dax_is_empty_entry(entry))) {
pmd_downgrade = true;
}
}
}
/* No entry for given index? Make sure radix tree is big enough. */
if (!entry || pmd_downgrade) {
int err;
if (pmd_downgrade) {
/*
* Make sure 'entry' remains valid while we drop
* the i_pages lock.
*/
entry = lock_slot(mapping, slot);
}
xa_unlock_irq(&mapping->i_pages);
/*
* Besides huge zero pages the only other thing that gets
* downgraded are empty entries which don't need to be
* unmapped.
*/
if (pmd_downgrade && dax_is_zero_entry(entry))
unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
PG_PMD_NR, false);
err = radix_tree_preload(
mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
if (err) {
if (pmd_downgrade)
put_locked_mapping_entry(mapping, index);
return ERR_PTR(err);
}
xa_lock_irq(&mapping->i_pages);
if (!entry) {
/*
* We needed to drop the i_pages lock while calling
* radix_tree_preload() and we didn't have an entry to
* lock. See if another thread inserted an entry at
* our index during this time.
*/
entry = __radix_tree_lookup(&mapping->i_pages, index,
NULL, &slot);
if (entry) {
radix_tree_preload_end();
xa_unlock_irq(&mapping->i_pages);
goto restart;
}
}
if (pmd_downgrade) {
dax_disassociate_entry(entry, mapping, false);
radix_tree_delete(&mapping->i_pages, index);
mapping->nrexceptional--;
dax_wake_mapping_entry_waiter(mapping, index, entry,
true);
}
entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
err = __radix_tree_insert(&mapping->i_pages, index,
dax_radix_order(entry), entry);
radix_tree_preload_end();
if (err) {
xa_unlock_irq(&mapping->i_pages);
/*
* Our insertion of a DAX entry failed, most likely
* because we were inserting a PMD entry and it
* collided with a PTE sized entry at a different
* index in the PMD range. We haven't inserted
* anything into the radix tree and have no waiters to
* wake.
*/
return ERR_PTR(err);
}
/* Good, we have inserted empty locked entry into the tree. */
mapping->nrexceptional++;
xa_unlock_irq(&mapping->i_pages);
return entry;
}
entry = lock_slot(mapping, slot);
out_unlock:
xa_unlock_irq(&mapping->i_pages);
return entry;
}
/**
* dax_layout_busy_page - find first pinned page in @mapping
* @mapping: address space to scan for a page with ref count > 1
*
* DAX requires ZONE_DEVICE mapped pages. These pages are never
* 'onlined' to the page allocator so they are considered idle when
* page->count == 1. A filesystem uses this interface to determine if
* any page in the mapping is busy, i.e. for DMA, or other
* get_user_pages() usages.
*
* It is expected that the filesystem is holding locks to block the
* establishment of new mappings in this address_space. I.e. it expects
* to be able to run unmap_mapping_range() and subsequently not race
* mapping_mapped() becoming true.
*/
struct page *dax_layout_busy_page(struct address_space *mapping)
{
pgoff_t indices[PAGEVEC_SIZE];
struct page *page = NULL;
struct pagevec pvec;
pgoff_t index, end;
unsigned i;
/*
* In the 'limited' case get_user_pages() for dax is disabled.
*/
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
return NULL;
if (!dax_mapping(mapping) || !mapping_mapped(mapping))
return NULL;
pagevec_init(&pvec);
index = 0;
end = -1;
/*
* If we race get_user_pages_fast() here either we'll see the
* elevated page count in the pagevec_lookup and wait, or
* get_user_pages_fast() will see that the page it took a reference
* against is no longer mapped in the page tables and bail to the
* get_user_pages() slow path. The slow path is protected by
* pte_lock() and pmd_lock(). New references are not taken without
* holding those locks, and unmap_mapping_range() will not zero the
* pte or pmd without holding the respective lock, so we are
* guaranteed to either see new references or prevent new
* references from being established.
*/
unmap_mapping_range(mapping, 0, 0, 1);
while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *pvec_ent = pvec.pages[i];
void *entry;
index = indices[i];
if (index >= end)
break;
if (WARN_ON_ONCE(
!radix_tree_exceptional_entry(pvec_ent)))
continue;
xa_lock_irq(&mapping->i_pages);
entry = get_unlocked_mapping_entry(mapping, index, NULL);
if (entry)
page = dax_busy_page(entry);
put_unlocked_mapping_entry(mapping, index, entry);
xa_unlock_irq(&mapping->i_pages);
if (page)
break;
}
/*
* We don't expect normal struct page entries to exist in our
* tree, but we keep these pagevec calls so that this code is
* consistent with the common pattern for handling pagevecs
* throughout the kernel.
*/
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
index++;
if (page)
break;
}
return page;
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page);
static int __dax_invalidate_mapping_entry(struct address_space *mapping,
pgoff_t index, bool trunc)
{
int ret = 0;
void *entry;
struct radix_tree_root *pages = &mapping->i_pages;
xa_lock_irq(pages);
entry = get_unlocked_mapping_entry(mapping, index, NULL);
if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
goto out;
if (!trunc &&
(radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE)))
goto out;
dax_disassociate_entry(entry, mapping, trunc);
radix_tree_delete(pages, index);
mapping->nrexceptional--;
ret = 1;
out:
put_unlocked_mapping_entry(mapping, index, entry);
xa_unlock_irq(pages);
return ret;
}
/*
* Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
* entry to get unlocked before deleting it.
*/
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
int ret = __dax_invalidate_mapping_entry(mapping, index, true);
/*
* This gets called from truncate / punch_hole path. As such, the caller
* must hold locks protecting against concurrent modifications of the
* radix tree (usually fs-private i_mmap_sem for writing). Since the
* caller has seen exceptional entry for this index, we better find it
* at that index as well...
*/
WARN_ON_ONCE(!ret);
return ret;
}
/*
* Invalidate exceptional DAX entry if it is clean.
*/
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index)
{
return __dax_invalidate_mapping_entry(mapping, index, false);
}
static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
sector_t sector, size_t size, struct page *to,
unsigned long vaddr)
{
void *vto, *kaddr;
pgoff_t pgoff;
pfn_t pfn;
long rc;
int id;
rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
if (rc)
return rc;
id = dax_read_lock();
rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
if (rc < 0) {
dax_read_unlock(id);
return rc;
}
vto = kmap_atomic(to);
copy_user_page(vto, (void __force *)kaddr, vaddr, to);
kunmap_atomic(vto);
dax_read_unlock(id);
return 0;
}
/*
* By this point grab_mapping_entry() has ensured that we have a locked entry
* of the appropriate size so we don't have to worry about downgrading PMDs to
* PTEs. If we happen to be trying to insert a PTE and there is a PMD
* already in the tree, we will skip the insertion and just dirty the PMD as
* appropriate.
*/
static void *dax_insert_mapping_entry(struct address_space *mapping,
struct vm_fault *vmf,
void *entry, pfn_t pfn_t,
unsigned long flags, bool dirty)
{
struct radix_tree_root *pages = &mapping->i_pages;
unsigned long pfn = pfn_t_to_pfn(pfn_t);
pgoff_t index = vmf->pgoff;
void *new_entry;
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
/* we are replacing a zero page with block mapping */
if (dax_is_pmd_entry(entry))
unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
PG_PMD_NR, false);
else /* pte entry */
unmap_mapping_pages(mapping, vmf->pgoff, 1, false);
}
xa_lock_irq(pages);
new_entry = dax_radix_locked_entry(pfn, flags);
if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
dax_disassociate_entry(entry, mapping, false);
dax_associate_entry(new_entry, mapping);
}
if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
/*
* Only swap our new entry into the radix tree if the current
* entry is a zero page or an empty entry. If a normal PTE or
* PMD entry is already in the tree, we leave it alone. This
* means that if we are trying to insert a PTE and the
* existing entry is a PMD, we will just leave the PMD in the
* tree and dirty it if necessary.
*/
struct radix_tree_node *node;
void **slot;
void *ret;
ret = __radix_tree_lookup(pages, index, &node, &slot);
WARN_ON_ONCE(ret != entry);
__radix_tree_replace(pages, node, slot,
new_entry, NULL);
entry = new_entry;
}
if (dirty)
radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY);
xa_unlock_irq(pages);
return entry;
}
static inline unsigned long
pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
{
unsigned long address;
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
return address;
}
/* Walk all mappings of a given index of a file and writeprotect them */
static void dax_mapping_entry_mkclean(struct address_space *mapping,
pgoff_t index, unsigned long pfn)
{
struct vm_area_struct *vma;
pte_t pte, *ptep = NULL;
pmd_t *pmdp = NULL;
spinlock_t *ptl;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
unsigned long address, start, end;
cond_resched();
if (!(vma->vm_flags & VM_SHARED))
continue;
address = pgoff_address(index, vma);
/*
* Note because we provide start/end to follow_pte_pmd it will
* call mmu_notifier_invalidate_range_start() on our behalf
* before taking any lock.
*/
if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl))
continue;
/*
* No need to call mmu_notifier_invalidate_range() as we are
* downgrading page table protection not changing it to point
* to a new page.
*
* See Documentation/vm/mmu_notifier.rst
*/
if (pmdp) {
#ifdef CONFIG_FS_DAX_PMD
pmd_t pmd;
if (pfn != pmd_pfn(*pmdp))
goto unlock_pmd;
if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
goto unlock_pmd;
flush_cache_page(vma, address, pfn);
pmd = pmdp_huge_clear_flush(vma, address, pmdp);
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
unlock_pmd:
#endif
spin_unlock(ptl);
} else {
if (pfn != pte_pfn(*ptep))
goto unlock_pte;
if (!pte_dirty(*ptep) && !pte_write(*ptep))
goto unlock_pte;
flush_cache_page(vma, address, pfn);
pte = ptep_clear_flush(vma, address, ptep);
pte = pte_wrprotect(pte);
pte = pte_mkclean(pte);
set_pte_at(vma->vm_mm, address, ptep, pte);
unlock_pte:
pte_unmap_unlock(ptep, ptl);
}
mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
}
i_mmap_unlock_read(mapping);
}
static int dax_writeback_one(struct dax_device *dax_dev,
struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *pages = &mapping->i_pages;
void *entry2, **slot;
unsigned long pfn;
long ret = 0;
size_t size;
/*
* A page got tagged dirty in DAX mapping? Something is seriously
* wrong.
*/
if (WARN_ON(!radix_tree_exceptional_entry(entry)))
return -EIO;
xa_lock_irq(pages);
entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
/* Entry got punched out / reallocated? */
if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
goto put_unlocked;
/*
* Entry got reallocated elsewhere? No need to writeback. We have to
* compare pfns as we must not bail out due to difference in lockbit
* or entry type.
*/
if (dax_radix_pfn(entry2) != dax_radix_pfn(entry))
goto put_unlocked;
if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
dax_is_zero_entry(entry))) {
ret = -EIO;
goto put_unlocked;
}
/* Another fsync thread may have already written back this entry */
if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))
goto put_unlocked;
/* Lock the entry to serialize with page faults */
entry = lock_slot(mapping, slot);
/*
* We can clear the tag now but we have to be careful so that concurrent
* dax_writeback_one() calls for the same index cannot finish before we
* actually flush the caches. This is achieved as the calls will look
* at the entry only under the i_pages lock and once they do that
* they will see the entry locked and wait for it to unlock.
*/
radix_tree_tag_clear(pages, index, PAGECACHE_TAG_TOWRITE);
xa_unlock_irq(pages);
/*
* Even if dax_writeback_mapping_range() was given a wbc->range_start
* in the middle of a PMD, the 'index' we are given will be aligned to
* the start index of the PMD, as will the pfn we pull from 'entry'.
* This allows us to flush for PMD_SIZE and not have to worry about
* partial PMD writebacks.
*/
pfn = dax_radix_pfn(entry);
size = PAGE_SIZE << dax_radix_order(entry);
dax_mapping_entry_mkclean(mapping, index, pfn);
dax_flush(dax_dev, page_address(pfn_to_page(pfn)), size);
/*
* After we have flushed the cache, we can clear the dirty tag. There
* cannot be new dirty data in the pfn after the flush has completed as
* the pfn mappings are writeprotected and fault waits for mapping
* entry lock.
*/
xa_lock_irq(pages);
radix_tree_tag_clear(pages, index, PAGECACHE_TAG_DIRTY);
xa_unlock_irq(pages);
trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
put_locked_mapping_entry(mapping, index);
return ret;
put_unlocked:
put_unlocked_mapping_entry(mapping, index, entry2);
xa_unlock_irq(pages);
return ret;
}
/*
* Flush the mapping to the persistent domain within the byte range of [start,
* end]. This is required by data integrity operations to ensure file data is
* on persistent storage prior to completion of the operation.
*/
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
pgoff_t start_index, end_index;
pgoff_t indices[PAGEVEC_SIZE];
struct dax_device *dax_dev;
struct pagevec pvec;
bool done = false;
int i, ret = 0;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
if (!dax_dev)
return -EIO;
start_index = wbc->range_start >> PAGE_SHIFT;
end_index = wbc->range_end >> PAGE_SHIFT;
trace_dax_writeback_range(inode, start_index, end_index);
tag_pages_for_writeback(mapping, start_index, end_index);
pagevec_init(&pvec);
while (!done) {
pvec.nr = find_get_entries_tag(mapping, start_index,
PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
pvec.pages, indices);
if (pvec.nr == 0)
break;
for (i = 0; i < pvec.nr; i++) {
if (indices[i] > end_index) {
done = true;
break;
}
ret = dax_writeback_one(dax_dev, mapping, indices[i],
pvec.pages[i]);
if (ret < 0) {
mapping_set_error(mapping, ret);
goto out;
}
}
start_index = indices[pvec.nr - 1] + 1;
}
out:
put_dax(dax_dev);
trace_dax_writeback_range_done(inode, start_index, end_index);
return (ret < 0 ? ret : 0);
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
{
return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
}
static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
pfn_t *pfnp)
{
const sector_t sector = dax_iomap_sector(iomap, pos);
pgoff_t pgoff;
void *kaddr;
int id, rc;
long length;
rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
if (rc)
return rc;
id = dax_read_lock();
length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
&kaddr, pfnp);
if (length < 0) {
rc = length;
goto out;
}
rc = -EINVAL;
if (PFN_PHYS(length) < size)
goto out;
if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
goto out;
/* For larger pages we need devmap */
if (length > 1 && !pfn_t_devmap(*pfnp))
goto out;
rc = 0;