forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdax.c
1248 lines (1100 loc) · 34.7 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/pmem.h>
#include <linux/sched.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
/*
* We use lowest available bit in exceptional entry for locking, other two
* bits to determine entry type. In total 3 special bits.
*/
#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)
#define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD)
#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK)
#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \
RADIX_TREE_EXCEPTIONAL_ENTRY))
/* 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)
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);
static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
pgoff_t index)
{
unsigned long hash = hash_long((unsigned long)mapping ^ index,
DAX_WAIT_TABLE_BITS);
return wait_table + hash;
}
static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
{
struct request_queue *q = bdev->bd_queue;
long rc = -EIO;
dax->addr = (void __pmem *) ERR_PTR(-EIO);
if (blk_queue_enter(q, true) != 0)
return rc;
rc = bdev_direct_access(bdev, dax);
if (rc < 0) {
dax->addr = (void __pmem *) ERR_PTR(rc);
blk_queue_exit(q);
return rc;
}
return rc;
}
static void dax_unmap_atomic(struct block_device *bdev,
const struct blk_dax_ctl *dax)
{
if (IS_ERR(dax->addr))
return;
blk_queue_exit(bdev->bd_queue);
}
struct page *read_dax_sector(struct block_device *bdev, sector_t n)
{
struct page *page = alloc_pages(GFP_KERNEL, 0);
struct blk_dax_ctl dax = {
.size = PAGE_SIZE,
.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
};
long rc;
if (!page)
return ERR_PTR(-ENOMEM);
rc = dax_map_atomic(bdev, &dax);
if (rc < 0)
return ERR_PTR(rc);
memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
dax_unmap_atomic(bdev, &dax);
return page;
}
static bool buffer_written(struct buffer_head *bh)
{
return buffer_mapped(bh) && !buffer_unwritten(bh);
}
/*
* When ext4 encounters a hole, it returns without modifying the buffer_head
* which means that we can't trust b_size. To cope with this, we set b_state
* to 0 before calling get_block and, if any bit is set, we know we can trust
* b_size. Unfortunate, really, since ext4 knows precisely how long a hole is
* and would save us time calling get_block repeatedly.
*/
static bool buffer_size_valid(struct buffer_head *bh)
{
return bh->b_state != 0;
}
static sector_t to_sector(const struct buffer_head *bh,
const struct inode *inode)
{
sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
return sector;
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false, need_wmb = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
unsigned blkbits = inode->i_blkbits;
sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
>> blkbits;
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
if (!buffer_size_valid(bh))
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
/*
* We allow uninitialized buffers for writes
* beyond EOF as those cannot race with faults
*/
WARN_ON_ONCE(
(buffer_new(bh) && block < file_blks) ||
(rw == WRITE && buffer_unwritten(bh)));
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
dax.addr += first;
size = map_len - first;
}
/*
* pos + size is one past the last offset for IO,
* so pos + size can overflow loff_t at extreme offsets.
* Cast to u64 to catch this and get the true minimum.
*/
max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
if (need_wmb)
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
/**
* dax_do_io - Perform I/O to a DAX file
* @iocb: The control block for this I/O
* @inode: The file which the I/O is directed at
* @iter: The addresses to do I/O from or to
* @get_block: The filesystem method used to translate file offsets to blocks
* @end_io: A filesystem callback for I/O completion
* @flags: See below
*
* This function uses the same locking scheme as do_blockdev_direct_IO:
* If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
* caller for writes. For reads, we take and release the i_mutex ourselves.
* If DIO_LOCKING is not set, the filesystem takes care of its own locking.
* As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
* is in progress.
*/
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
struct iov_iter *iter, get_block_t get_block,
dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
loff_t pos = iocb->ki_pos;
loff_t end = pos + iov_iter_count(iter);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_lock(inode);
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_begin(inode);
retval = dax_io(inode, iter, pos, end, get_block, &bh);
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_unlock(inode);
if (end_io) {
int err;
err = end_io(iocb, pos, retval, bh.b_private);
if (err)
retval = err;
}
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
return retval;
}
EXPORT_SYMBOL_GPL(dax_do_io);
/*
* DAX radix tree locking
*/
struct exceptional_entry_key {
struct address_space *mapping;
unsigned long index;
};
struct wait_exceptional_entry_queue {
wait_queue_t wait;
struct exceptional_entry_key key;
};
static int wake_exceptional_entry_func(wait_queue_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->index != ewait->key.index)
return 0;
return autoremove_wake_function(wait, mode, sync, NULL);
}
/*
* Check whether the given slot is locked. The function must be called with
* mapping->tree_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->tree_lock);
return entry & RADIX_DAX_ENTRY_LOCK;
}
/*
* Mark the given slot is locked. The function must be called with
* mapping->tree_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->tree_lock);
entry |= RADIX_DAX_ENTRY_LOCK;
radix_tree_replace_slot(slot, (void *)entry);
return (void *)entry;
}
/*
* Mark the given slot is unlocked. The function must be called with
* mapping->tree_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->tree_lock);
entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
radix_tree_replace_slot(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.
*
* The function must be called with mapping->tree_lock held.
*/
static void *get_unlocked_mapping_entry(struct address_space *mapping,
pgoff_t index, void ***slotp)
{
void *ret, **slot;
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
init_wait(&ewait.wait);
ewait.wait.func = wake_exceptional_entry_func;
ewait.key.mapping = mapping;
ewait.key.index = index;
for (;;) {
ret = __radix_tree_lookup(&mapping->page_tree, index, NULL,
&slot);
if (!ret || !radix_tree_exceptional_entry(ret) ||
!slot_locked(mapping, slot)) {
if (slotp)
*slotp = slot;
return ret;
}
prepare_to_wait_exclusive(wq, &ewait.wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_irq(&mapping->tree_lock);
schedule();
finish_wait(wq, &ewait.wait);
spin_lock_irq(&mapping->tree_lock);
}
}
/*
* Find radix tree entry at given index. If it points to a page, return with
* the page locked. If it points to the exceptional entry, return with the
* radix tree entry locked. If the radix tree doesn't contain given index,
* create empty exceptional entry for the index and return with it locked.
*
* 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)
{
void *ret, **slot;
restart:
spin_lock_irq(&mapping->tree_lock);
ret = get_unlocked_mapping_entry(mapping, index, &slot);
/* No entry for given index? Make sure radix tree is big enough. */
if (!ret) {
int err;
spin_unlock_irq(&mapping->tree_lock);
err = radix_tree_preload(
mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
if (err)
return ERR_PTR(err);
ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
RADIX_DAX_ENTRY_LOCK);
spin_lock_irq(&mapping->tree_lock);
err = radix_tree_insert(&mapping->page_tree, index, ret);
radix_tree_preload_end();
if (err) {
spin_unlock_irq(&mapping->tree_lock);
/* Someone already created the entry? */
if (err == -EEXIST)
goto restart;
return ERR_PTR(err);
}
/* Good, we have inserted empty locked entry into the tree. */
mapping->nrexceptional++;
spin_unlock_irq(&mapping->tree_lock);
return ret;
}
/* Normal page in radix tree? */
if (!radix_tree_exceptional_entry(ret)) {
struct page *page = ret;
get_page(page);
spin_unlock_irq(&mapping->tree_lock);
lock_page(page);
/* Page got truncated? Retry... */
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto restart;
}
return page;
}
ret = lock_slot(mapping, slot);
spin_unlock_irq(&mapping->tree_lock);
return ret;
}
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
pgoff_t index, bool wake_all)
{
wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index);
/*
* Checking for locked entry and prepare_to_wait_exclusive() happens
* under mapping->tree_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)) {
struct exceptional_entry_key key;
key.mapping = mapping;
key.index = index;
__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
}
}
void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
{
void *ret, **slot;
spin_lock_irq(&mapping->tree_lock);
ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
if (WARN_ON_ONCE(!ret || !radix_tree_exceptional_entry(ret) ||
!slot_locked(mapping, slot))) {
spin_unlock_irq(&mapping->tree_lock);
return;
}
unlock_slot(mapping, slot);
spin_unlock_irq(&mapping->tree_lock);
dax_wake_mapping_entry_waiter(mapping, index, false);
}
static void put_locked_mapping_entry(struct address_space *mapping,
pgoff_t index, void *entry)
{
if (!radix_tree_exceptional_entry(entry)) {
unlock_page(entry);
put_page(entry);
} else {
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 (!radix_tree_exceptional_entry(entry))
return;
/* We have to wake up next waiter for the radix tree entry lock */
dax_wake_mapping_entry_waiter(mapping, index, false);
}
/*
* 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)
{
void *entry;
spin_lock_irq(&mapping->tree_lock);
entry = get_unlocked_mapping_entry(mapping, index, NULL);
/*
* 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...
*/
if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
spin_unlock_irq(&mapping->tree_lock);
return 0;
}
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
spin_unlock_irq(&mapping->tree_lock);
dax_wake_mapping_entry_waiter(mapping, index, true);
return 1;
}
/*
* The user has performed a load from a hole in the file. Allocating
* a new page in the file would cause excessive storage usage for
* workloads with sparse files. We allocate a page cache page instead.
* We'll kick it out of the page cache if it's ever written to,
* otherwise it will simply fall out of the page cache under memory
* pressure without ever having been dirtied.
*/
static int dax_load_hole(struct address_space *mapping, void *entry,
struct vm_fault *vmf)
{
struct page *page;
/* Hole page already exists? Return it... */
if (!radix_tree_exceptional_entry(entry)) {
vmf->page = entry;
return VM_FAULT_LOCKED;
}
/* This will replace locked radix tree entry with a hole page */
page = find_or_create_page(mapping, vmf->pgoff,
vmf->gfp_mask | __GFP_ZERO);
if (!page) {
put_locked_mapping_entry(mapping, vmf->pgoff, entry);
return VM_FAULT_OOM;
}
vmf->page = page;
return VM_FAULT_LOCKED;
}
static int copy_user_bh(struct page *to, struct inode *inode,
struct buffer_head *bh, unsigned long vaddr)
{
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
struct block_device *bdev = bh->b_bdev;
void *vto;
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
vto = kmap_atomic(to);
copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
kunmap_atomic(vto);
dax_unmap_atomic(bdev, &dax);
return 0;
}
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
static void *dax_insert_mapping_entry(struct address_space *mapping,
struct vm_fault *vmf,
void *entry, sector_t sector)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
int error = 0;
bool hole_fill = false;
void *new_entry;
pgoff_t index = vmf->pgoff;
if (vmf->flags & FAULT_FLAG_WRITE)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
/* Replacing hole page with block mapping? */
if (!radix_tree_exceptional_entry(entry)) {
hole_fill = true;
/*
* Unmap the page now before we remove it from page cache below.
* The page is locked so it cannot be faulted in again.
*/
unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
PAGE_SIZE, 0);
error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM);
if (error)
return ERR_PTR(error);
}
spin_lock_irq(&mapping->tree_lock);
new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) |
RADIX_DAX_ENTRY_LOCK);
if (hole_fill) {
__delete_from_page_cache(entry, NULL);
/* Drop pagecache reference */
put_page(entry);
error = radix_tree_insert(page_tree, index, new_entry);
if (error) {
new_entry = ERR_PTR(error);
goto unlock;
}
mapping->nrexceptional++;
} else {
void **slot;
void *ret;
ret = __radix_tree_lookup(page_tree, index, NULL, &slot);
WARN_ON_ONCE(ret != entry);
radix_tree_replace_slot(slot, new_entry);
}
if (vmf->flags & FAULT_FLAG_WRITE)
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
unlock:
spin_unlock_irq(&mapping->tree_lock);
if (hole_fill) {
radix_tree_preload_end();
/*
* We don't need hole page anymore, it has been replaced with
* locked radix tree entry now.
*/
if (mapping->a_ops->freepage)
mapping->a_ops->freepage(entry);
unlock_page(entry);
put_page(entry);
}
return new_entry;
}
static int dax_writeback_one(struct block_device *bdev,
struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
int type = RADIX_DAX_TYPE(entry);
struct radix_tree_node *node;
struct blk_dax_ctl dax;
void **slot;
int ret = 0;
spin_lock_irq(&mapping->tree_lock);
/*
* Regular page slots are stabilized by the page lock even
* without the tree itself locked. These unlocked entries
* need verification under the tree lock.
*/
if (!__radix_tree_lookup(page_tree, index, &node, &slot))
goto unlock;
if (*slot != entry)
goto unlock;
/* another fsync thread may have already written back this entry */
if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
goto unlock;
if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
ret = -EIO;
goto unlock;
}
dax.sector = RADIX_DAX_SECTOR(entry);
dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
spin_unlock_irq(&mapping->tree_lock);
/*
* We cannot hold tree_lock while calling dax_map_atomic() because it
* eventually calls cond_resched().
*/
ret = dax_map_atomic(bdev, &dax);
if (ret < 0)
return ret;
if (WARN_ON_ONCE(ret < dax.size)) {
ret = -EIO;
goto unmap;
}
wb_cache_pmem(dax.addr, dax.size);
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
spin_unlock_irq(&mapping->tree_lock);
unmap:
dax_unmap_atomic(bdev, &dax);
return ret;
unlock:
spin_unlock_irq(&mapping->tree_lock);
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, pmd_index;
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
bool done = false;
int i, ret = 0;
void *entry;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
start_index = wbc->range_start >> PAGE_SHIFT;
end_index = wbc->range_end >> PAGE_SHIFT;
pmd_index = DAX_PMD_INDEX(start_index);
rcu_read_lock();
entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
rcu_read_unlock();
/* see if the start of our range is covered by a PMD entry */
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
start_index = pmd_index;
tag_pages_for_writeback(mapping, start_index, end_index);
pagevec_init(&pvec, 0);
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(bdev, mapping, indices[i],
pvec.pages[i]);
if (ret < 0)
return ret;
}
}
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_insert_mapping(struct address_space *mapping,
struct buffer_head *bh, void **entryp,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
unsigned long vaddr = (unsigned long)vmf->virtual_address;
struct block_device *bdev = bh->b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(bh, mapping->host),
.size = bh->b_size,
};
void *ret;
void *entry = *entryp;
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
dax_unmap_atomic(bdev, &dax);
ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector);
if (IS_ERR(ret))
return PTR_ERR(ret);
*entryp = ret;
return vm_insert_mixed(vma, vaddr, dax.pfn);
}
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
void *entry;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
sector_t block;
pgoff_t size;
int error;
int major = 0;
/*
* Check whether offset isn't beyond end of file now. Caller is supposed
* to hold locks serializing us with truncate / punch hole so this is
* a reliable test.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
memset(&bh, 0, sizeof(bh));
block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
entry = grab_mapping_entry(mapping, vmf->pgoff);
if (IS_ERR(entry)) {
error = PTR_ERR(entry);
goto out;
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
goto unlock_entry;
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
if (buffer_written(&bh))
error = copy_user_bh(new_page, inode, &bh, vaddr);
else
clear_user_highpage(new_page, vaddr);
if (error)
goto unlock_entry;
if (!radix_tree_exceptional_entry(entry)) {
vmf->page = entry;
return VM_FAULT_LOCKED;
}
vmf->entry = entry;
return VM_FAULT_DAX_LOCKED;
}
if (!buffer_mapped(&bh)) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
goto unlock_entry;
} else {
return dax_load_hole(mapping, entry, vmf);
}
}
/* Filesystem should not return unwritten buffers to us! */
WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
error = dax_insert_mapping(mapping, &bh, &entry, vma, vmf);
unlock_entry:
put_locked_mapping_entry(mapping, vmf->pgoff, entry);
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
/* -EBUSY is fine, somebody else faulted on the same PTE */
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
}
EXPORT_SYMBOL_GPL(dax_fault);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
/*
* The 'colour' (ie low bits) within a PMD of a page offset. This comes up
* more often than one might expect in the below function.
*/
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
static void __dax_dbg(struct buffer_head *bh, unsigned long address,
const char *reason, const char *fn)
{
if (bh) {
char bname[BDEVNAME_SIZE];
bdevname(bh->b_bdev, bname);
pr_debug("%s: %s addr: %lx dev %s state %lx start %lld "
"length %zd fallback: %s\n", fn, current->comm,
address, bname, bh->b_state, (u64)bh->b_blocknr,
bh->b_size, reason);
} else {
pr_debug("%s: %s addr: %lx fallback: %s\n", fn,
current->comm, address, reason);
}
}
#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd")
/**
* dax_pmd_fault - handle a PMD fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* pmd_fault handler for DAX files.
*/
int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct buffer_head bh;
unsigned blkbits = inode->i_blkbits;
unsigned long pmd_addr = address & PMD_MASK;
bool write = flags & FAULT_FLAG_WRITE;
struct block_device *bdev;
pgoff_t size, pgoff;
sector_t block;
int result = 0;
bool alloc = false;
/* dax pmd mappings require pfn_t_devmap() */
if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
return VM_FAULT_FALLBACK;
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED)) {
split_huge_pmd(vma, pmd, address);
dax_pmd_dbg(NULL, address, "cow write");
return VM_FAULT_FALLBACK;
}
/* If the PMD would extend outside the VMA */
if (pmd_addr < vma->vm_start) {
dax_pmd_dbg(NULL, address, "vma start unaligned");
return VM_FAULT_FALLBACK;
}
if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
dax_pmd_dbg(NULL, address, "vma end unaligned");
return VM_FAULT_FALLBACK;
}
pgoff = linear_page_index(vma, pmd_addr);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size)
return VM_FAULT_SIGBUS;
/* If the PMD would cover blocks out of the file */
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(NULL, address,
"offset + huge page size > file size");
return VM_FAULT_FALLBACK;
}
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;