forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathinode.c
1671 lines (1510 loc) · 47.4 KB
/
inode.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
/*
* linux/fs/ext2/inode.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Goal-directed block allocation by Stephen Tweedie
* (sct@dcs.ed.ac.uk), 1993, 1998
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
* 64-bit file support on 64-bit platforms by Jakub Jelinek
* (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext2_get_block() by Al Viro, 2000
*/
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/fiemap.h>
#include <linux/iomap.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include "ext2.h"
#include "acl.h"
#include "xattr.h"
static int __ext2_write_inode(struct inode *inode, int do_sync);
/*
* Test whether an inode is a fast symlink.
*/
static inline int ext2_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT2_I(inode)->i_file_acl ?
(inode->i_sb->s_blocksize >> 9) : 0;
return (S_ISLNK(inode->i_mode) &&
inode->i_blocks - ea_blocks == 0);
}
static void ext2_truncate_blocks(struct inode *inode, loff_t offset);
void ext2_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
if (to > inode->i_size) {
truncate_pagecache(inode, inode->i_size);
ext2_truncate_blocks(inode, inode->i_size);
}
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext2_evict_inode(struct inode * inode)
{
struct ext2_block_alloc_info *rsv;
int want_delete = 0;
if (!inode->i_nlink && !is_bad_inode(inode)) {
want_delete = 1;
dquot_initialize(inode);
} else {
dquot_drop(inode);
}
truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
sb_start_intwrite(inode->i_sb);
/* set dtime */
EXT2_I(inode)->i_dtime = ktime_get_real_seconds();
mark_inode_dirty(inode);
__ext2_write_inode(inode, inode_needs_sync(inode));
/* truncate to 0 */
inode->i_size = 0;
if (inode->i_blocks)
ext2_truncate_blocks(inode, 0);
ext2_xattr_delete_inode(inode);
}
invalidate_inode_buffers(inode);
clear_inode(inode);
ext2_discard_reservation(inode);
rsv = EXT2_I(inode)->i_block_alloc_info;
EXT2_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
if (want_delete) {
ext2_free_inode(inode);
sb_end_intwrite(inode->i_sb);
}
}
typedef struct {
__le32 *p;
__le32 key;
struct buffer_head *bh;
} Indirect;
static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
p->key = *(p->p = v);
p->bh = bh;
}
static inline int verify_chain(Indirect *from, Indirect *to)
{
while (from <= to && from->key == *from->p)
from++;
return (from > to);
}
/**
* ext2_block_to_path - parse the block number into array of offsets
* @inode: inode in question (we are only interested in its superblock)
* @i_block: block number to be parsed
* @offsets: array to store the offsets in
* @boundary: set this non-zero if the referred-to block is likely to be
* followed (on disk) by an indirect block.
* To store the locations of file's data ext2 uses a data structure common
* for UNIX filesystems - tree of pointers anchored in the inode, with
* data blocks at leaves and indirect blocks in intermediate nodes.
* This function translates the block number into path in that tree -
* return value is the path length and @offsets[n] is the offset of
* pointer to (n+1)th node in the nth one. If @block is out of range
* (negative or too large) warning is printed and zero returned.
*
* Note: function doesn't find node addresses, so no IO is needed. All
* we need to know is the capacity of indirect blocks (taken from the
* inode->i_sb).
*/
/*
* Portability note: the last comparison (check that we fit into triple
* indirect block) is spelled differently, because otherwise on an
* architecture with 32-bit longs and 8Kb pages we might get into trouble
* if our filesystem had 8Kb blocks. We might use long long, but that would
* kill us on x86. Oh, well, at least the sign propagation does not matter -
* i_block would have to be negative in the very beginning, so we would not
* get there at all.
*/
static int ext2_block_to_path(struct inode *inode,
long i_block, int offsets[4], int *boundary)
{
int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb);
int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb);
const long direct_blocks = EXT2_NDIR_BLOCKS,
indirect_blocks = ptrs,
double_blocks = (1 << (ptrs_bits * 2));
int n = 0;
int final = 0;
if (i_block < 0) {
ext2_msg(inode->i_sb, KERN_WARNING,
"warning: %s: block < 0", __func__);
} else if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
} else if ( (i_block -= direct_blocks) < indirect_blocks) {
offsets[n++] = EXT2_IND_BLOCK;
offsets[n++] = i_block;
final = ptrs;
} else if ((i_block -= indirect_blocks) < double_blocks) {
offsets[n++] = EXT2_DIND_BLOCK;
offsets[n++] = i_block >> ptrs_bits;
offsets[n++] = i_block & (ptrs - 1);
final = ptrs;
} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
offsets[n++] = EXT2_TIND_BLOCK;
offsets[n++] = i_block >> (ptrs_bits * 2);
offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
offsets[n++] = i_block & (ptrs - 1);
final = ptrs;
} else {
ext2_msg(inode->i_sb, KERN_WARNING,
"warning: %s: block is too big", __func__);
}
if (boundary)
*boundary = final - 1 - (i_block & (ptrs - 1));
return n;
}
/**
* ext2_get_branch - read the chain of indirect blocks leading to data
* @inode: inode in question
* @depth: depth of the chain (1 - direct pointer, etc.)
* @offsets: offsets of pointers in inode/indirect blocks
* @chain: place to store the result
* @err: here we store the error value
*
* Function fills the array of triples <key, p, bh> and returns %NULL
* if everything went OK or the pointer to the last filled triple
* (incomplete one) otherwise. Upon the return chain[i].key contains
* the number of (i+1)-th block in the chain (as it is stored in memory,
* i.e. little-endian 32-bit), chain[i].p contains the address of that
* number (it points into struct inode for i==0 and into the bh->b_data
* for i>0) and chain[i].bh points to the buffer_head of i-th indirect
* block for i>0 and NULL for i==0. In other words, it holds the block
* numbers of the chain, addresses they were taken from (and where we can
* verify that chain did not change) and buffer_heads hosting these
* numbers.
*
* Function stops when it stumbles upon zero pointer (absent block)
* (pointer to last triple returned, *@err == 0)
* or when it gets an IO error reading an indirect block
* (ditto, *@err == -EIO)
* or when it notices that chain had been changed while it was reading
* (ditto, *@err == -EAGAIN)
* or when it reads all @depth-1 indirect blocks successfully and finds
* the whole chain, all way to the data (returns %NULL, *err == 0).
*/
static Indirect *ext2_get_branch(struct inode *inode,
int depth,
int *offsets,
Indirect chain[4],
int *err)
{
struct super_block *sb = inode->i_sb;
Indirect *p = chain;
struct buffer_head *bh;
*err = 0;
/* i_data is not going away, no lock needed */
add_chain (chain, NULL, EXT2_I(inode)->i_data + *offsets);
if (!p->key)
goto no_block;
while (--depth) {
bh = sb_bread(sb, le32_to_cpu(p->key));
if (!bh)
goto failure;
read_lock(&EXT2_I(inode)->i_meta_lock);
if (!verify_chain(chain, p))
goto changed;
add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
read_unlock(&EXT2_I(inode)->i_meta_lock);
if (!p->key)
goto no_block;
}
return NULL;
changed:
read_unlock(&EXT2_I(inode)->i_meta_lock);
brelse(bh);
*err = -EAGAIN;
goto no_block;
failure:
*err = -EIO;
no_block:
return p;
}
/**
* ext2_find_near - find a place for allocation with sufficient locality
* @inode: owner
* @ind: descriptor of indirect block.
*
* This function returns the preferred place for block allocation.
* It is used when heuristic for sequential allocation fails.
* Rules are:
* + if there is a block to the left of our position - allocate near it.
* + if pointer will live in indirect block - allocate near that block.
* + if pointer will live in inode - allocate in the same cylinder group.
*
* In the latter case we colour the starting block by the callers PID to
* prevent it from clashing with concurrent allocations for a different inode
* in the same block group. The PID is used here so that functionally related
* files will be close-by on-disk.
*
* Caller must make sure that @ind is valid and will stay that way.
*/
static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind)
{
struct ext2_inode_info *ei = EXT2_I(inode);
__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
__le32 *p;
ext2_fsblk_t bg_start;
ext2_fsblk_t colour;
/* Try to find previous block */
for (p = ind->p - 1; p >= start; p--)
if (*p)
return le32_to_cpu(*p);
/* No such thing, so let's try location of indirect block */
if (ind->bh)
return ind->bh->b_blocknr;
/*
* It is going to be referred from inode itself? OK, just put it into
* the same cylinder group then.
*/
bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group);
colour = (current->pid % 16) *
(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
return bg_start + colour;
}
/**
* ext2_find_goal - find a preferred place for allocation.
* @inode: owner
* @block: block we want
* @partial: pointer to the last triple within a chain
*
* Returns preferred place for a block (the goal).
*/
static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
Indirect *partial)
{
struct ext2_block_alloc_info *block_i;
block_i = EXT2_I(inode)->i_block_alloc_info;
/*
* try the heuristic for sequential allocation,
* failing that at least try to get decent locality.
*/
if (block_i && (block == block_i->last_alloc_logical_block + 1)
&& (block_i->last_alloc_physical_block != 0)) {
return block_i->last_alloc_physical_block + 1;
}
return ext2_find_near(inode, partial);
}
/**
* ext2_blks_to_allocate: Look up the block map and count the number
* of direct blocks need to be allocated for the given branch.
*
* @branch: chain of indirect blocks
* @k: number of blocks need for indirect blocks
* @blks: number of data blocks to be mapped.
* @blocks_to_boundary: the offset in the indirect block
*
* return the number of direct blocks to allocate.
*/
static int
ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
int blocks_to_boundary)
{
unsigned long count = 0;
/*
* Simple case, [t,d]Indirect block(s) has not allocated yet
* then it's clear blocks on that path have not allocated
*/
if (k > 0) {
/* right now don't hanel cross boundary allocation */
if (blks < blocks_to_boundary + 1)
count += blks;
else
count += blocks_to_boundary + 1;
return count;
}
count++;
while (count < blks && count <= blocks_to_boundary
&& le32_to_cpu(*(branch[0].p + count)) == 0) {
count++;
}
return count;
}
/**
* ext2_alloc_blocks: Allocate multiple blocks needed for a branch.
* @inode: Owner.
* @goal: Preferred place for allocation.
* @indirect_blks: The number of blocks needed to allocate for indirect blocks.
* @blks: The number of blocks need to allocate for direct blocks.
* @new_blocks: On return it will store the new block numbers for
* the indirect blocks(if needed) and the first direct block.
* @err: Error pointer.
*
* Return: Number of blocks allocated.
*/
static int ext2_alloc_blocks(struct inode *inode,
ext2_fsblk_t goal, int indirect_blks, int blks,
ext2_fsblk_t new_blocks[4], int *err)
{
int target, i;
unsigned long count = 0;
int index = 0;
ext2_fsblk_t current_block = 0;
int ret = 0;
/*
* Here we try to allocate the requested multiple blocks at once,
* on a best-effort basis.
* To build a branch, we should allocate blocks for
* the indirect blocks(if not allocated yet), and at least
* the first direct block of this branch. That's the
* minimum number of blocks need to allocate(required)
*/
target = blks + indirect_blks;
while (1) {
count = target;
/* allocating blocks for indirect blocks and direct blocks */
current_block = ext2_new_blocks(inode, goal, &count, err, 0);
if (*err)
goto failed_out;
target -= count;
/* allocate blocks for indirect blocks */
while (index < indirect_blks && count) {
new_blocks[index++] = current_block++;
count--;
}
if (count > 0)
break;
}
/* save the new block number for the first direct block */
new_blocks[index] = current_block;
/* total number of blocks allocated for direct blocks */
ret = count;
*err = 0;
return ret;
failed_out:
for (i = 0; i <index; i++)
ext2_free_blocks(inode, new_blocks[i], 1);
if (index)
mark_inode_dirty(inode);
return ret;
}
/**
* ext2_alloc_branch - allocate and set up a chain of blocks.
* @inode: owner
* @indirect_blks: depth of the chain (number of blocks to allocate)
* @blks: number of allocated direct blocks
* @goal: preferred place for allocation
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
* This function allocates @num blocks, zeroes out all but the last one,
* links them into chain and (if we are synchronous) writes them to disk.
* In other words, it prepares a branch that can be spliced onto the
* inode. It stores the information about that chain in the branch[], in
* the same format as ext2_get_branch() would do. We are calling it after
* we had read the existing part of chain and partial points to the last
* triple of that (one with zero ->key). Upon the exit we have the same
* picture as after the successful ext2_get_block(), except that in one
* place chain is disconnected - *branch->p is still zero (we did not
* set the last link), but branch->key contains the number that should
* be placed into *branch->p to fill that gap.
*
* If allocation fails we free all blocks we've allocated (and forget
* their buffer_heads) and return the error value the from failed
* ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain
* as described above and return 0.
*/
static int ext2_alloc_branch(struct inode *inode,
int indirect_blks, int *blks, ext2_fsblk_t goal,
int *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
int i, n = 0;
int err = 0;
struct buffer_head *bh;
int num;
ext2_fsblk_t new_blocks[4];
ext2_fsblk_t current_block;
num = ext2_alloc_blocks(inode, goal, indirect_blks,
*blks, new_blocks, &err);
if (err)
return err;
branch[0].key = cpu_to_le32(new_blocks[0]);
/*
* metadata blocks and data blocks are allocated.
*/
for (n = 1; n <= indirect_blks; n++) {
/*
* Get buffer_head for parent block, zero it out
* and set the pointer to new one, then send
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
if (unlikely(!bh)) {
err = -ENOMEM;
goto failed;
}
branch[n].bh = bh;
lock_buffer(bh);
memset(bh->b_data, 0, blocksize);
branch[n].p = (__le32 *) bh->b_data + offsets[n];
branch[n].key = cpu_to_le32(new_blocks[n]);
*branch[n].p = branch[n].key;
if ( n == indirect_blks) {
current_block = new_blocks[n];
/*
* End of chain, update the last new metablock of
* the chain to point to the new allocated
* data blocks numbers
*/
for (i=1; i < num; i++)
*(branch[n].p + i) = cpu_to_le32(++current_block);
}
set_buffer_uptodate(bh);
unlock_buffer(bh);
mark_buffer_dirty_inode(bh, inode);
/* We used to sync bh here if IS_SYNC(inode).
* But we now rely upon generic_write_sync()
* and b_inode_buffers. But not for directories.
*/
if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
sync_dirty_buffer(bh);
}
*blks = num;
return err;
failed:
for (i = 1; i < n; i++)
bforget(branch[i].bh);
for (i = 0; i < indirect_blks; i++)
ext2_free_blocks(inode, new_blocks[i], 1);
ext2_free_blocks(inode, new_blocks[i], num);
return err;
}
/**
* ext2_splice_branch - splice the allocated branch onto inode.
* @inode: owner
* @block: (logical) number of block we are adding
* @where: location of missing link
* @num: number of indirect blocks we are adding
* @blks: number of direct blocks we are adding
*
* This function fills the missing link and does all housekeeping needed in
* inode (->i_blocks, etc.). In case of success we end up with the full
* chain to new block and return 0.
*/
static void ext2_splice_branch(struct inode *inode,
long block, Indirect *where, int num, int blks)
{
int i;
struct ext2_block_alloc_info *block_i;
ext2_fsblk_t current_block;
block_i = EXT2_I(inode)->i_block_alloc_info;
/* XXX LOCKING probably should have i_meta_lock ?*/
/* That's it */
*where->p = where->key;
/*
* Update the host buffer_head or inode to point to more just allocated
* direct blocks blocks
*/
if (num == 0 && blks > 1) {
current_block = le32_to_cpu(where->key) + 1;
for (i = 1; i < blks; i++)
*(where->p + i ) = cpu_to_le32(current_block++);
}
/*
* update the most recently allocated logical & physical block
* in i_block_alloc_info, to assist find the proper goal block for next
* allocation
*/
if (block_i) {
block_i->last_alloc_logical_block = block + blks - 1;
block_i->last_alloc_physical_block =
le32_to_cpu(where[num].key) + blks - 1;
}
/* We are done with atomic stuff, now do the rest of housekeeping */
/* had we spliced it onto indirect block? */
if (where->bh)
mark_buffer_dirty_inode(where->bh, inode);
inode_set_ctime_current(inode);
mark_inode_dirty(inode);
}
/*
* Allocation strategy is simple: if we have to allocate something, we will
* have to go the whole way to leaf. So let's do it before attaching anything
* to tree, set linkage between the newborn blocks, write them if sync is
* required, recheck the path, free and repeat if check fails, otherwise
* set the last missing link (that will protect us from any truncate-generated
* removals - all blocks on the path are immune now) and possibly force the
* write on the parent block.
* That has a nice additional property: no special recovery from the failed
* allocations is needed - we simply release blocks and do not touch anything
* reachable from inode.
*
* `handle' can be NULL if create == 0.
*
* return > 0, # of blocks mapped or allocated.
* return = 0, if plain lookup failed.
* return < 0, error case.
*/
static int ext2_get_blocks(struct inode *inode,
sector_t iblock, unsigned long maxblocks,
u32 *bno, bool *new, bool *boundary,
int create)
{
int err;
int offsets[4];
Indirect chain[4];
Indirect *partial;
ext2_fsblk_t goal;
int indirect_blks;
int blocks_to_boundary = 0;
int depth;
struct ext2_inode_info *ei = EXT2_I(inode);
int count = 0;
ext2_fsblk_t first_block = 0;
BUG_ON(maxblocks == 0);
depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
if (depth == 0)
return -EIO;
partial = ext2_get_branch(inode, depth, offsets, chain, &err);
/* Simplest case - block found, no allocation needed */
if (!partial) {
first_block = le32_to_cpu(chain[depth - 1].key);
count++;
/*map more blocks*/
while (count < maxblocks && count <= blocks_to_boundary) {
ext2_fsblk_t blk;
if (!verify_chain(chain, chain + depth - 1)) {
/*
* Indirect block might be removed by
* truncate while we were reading it.
* Handling of that case: forget what we've
* got now, go to reread.
*/
err = -EAGAIN;
count = 0;
partial = chain + depth - 1;
break;
}
blk = le32_to_cpu(*(chain[depth-1].p + count));
if (blk == first_block + count)
count++;
else
break;
}
if (err != -EAGAIN)
goto got_it;
}
/* Next simple case - plain lookup or failed read of indirect block */
if (!create || err == -EIO)
goto cleanup;
mutex_lock(&ei->truncate_mutex);
/*
* If the indirect block is missing while we are reading
* the chain(ext2_get_branch() returns -EAGAIN err), or
* if the chain has been changed after we grab the semaphore,
* (either because another process truncated this branch, or
* another get_block allocated this branch) re-grab the chain to see if
* the request block has been allocated or not.
*
* Since we already block the truncate/other get_block
* at this point, we will have the current copy of the chain when we
* splice the branch into the tree.
*/
if (err == -EAGAIN || !verify_chain(chain, partial)) {
while (partial > chain) {
brelse(partial->bh);
partial--;
}
partial = ext2_get_branch(inode, depth, offsets, chain, &err);
if (!partial) {
count++;
mutex_unlock(&ei->truncate_mutex);
goto got_it;
}
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
}
/*
* Okay, we need to do block allocation. Lazily initialize the block
* allocation info here if necessary
*/
if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
ext2_init_block_alloc_info(inode);
goal = ext2_find_goal(inode, iblock, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) - partial - 1;
/*
* Next look up the indirect map to count the total number of
* direct blocks to allocate for this branch.
*/
count = ext2_blks_to_allocate(partial, indirect_blks,
maxblocks, blocks_to_boundary);
/*
* XXX ???? Block out ext2_truncate while we alter the tree
*/
err = ext2_alloc_branch(inode, indirect_blks, &count, goal,
offsets + (partial - chain), partial);
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
if (IS_DAX(inode)) {
/*
* We must unmap blocks before zeroing so that writeback cannot
* overwrite zeros with stale data from block device page cache.
*/
clean_bdev_aliases(inode->i_sb->s_bdev,
le32_to_cpu(chain[depth-1].key),
count);
/*
* block must be initialised before we put it in the tree
* so that it's not found by another thread before it's
* initialised
*/
err = sb_issue_zeroout(inode->i_sb,
le32_to_cpu(chain[depth-1].key), count,
GFP_NOFS);
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
}
*new = true;
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
got_it:
if (count > blocks_to_boundary)
*boundary = true;
err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
cleanup:
while (partial > chain) {
brelse(partial->bh);
partial--;
}
if (err > 0)
*bno = le32_to_cpu(chain[depth-1].key);
return err;
}
int ext2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
bool new = false, boundary = false;
u32 bno;
int ret;
ret = ext2_get_blocks(inode, iblock, max_blocks, &bno, &new, &boundary,
create);
if (ret <= 0)
return ret;
map_bh(bh_result, inode->i_sb, bno);
bh_result->b_size = (ret << inode->i_blkbits);
if (new)
set_buffer_new(bh_result);
if (boundary)
set_buffer_boundary(bh_result);
return 0;
}
static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
unsigned int blkbits = inode->i_blkbits;
unsigned long first_block = offset >> blkbits;
unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
bool new = false, boundary = false;
u32 bno;
int ret;
bool create = flags & IOMAP_WRITE;
/*
* For writes that could fill holes inside i_size on a
* DIO_SKIP_HOLES filesystem we forbid block creations: only
* overwrites are permitted.
*/
if ((flags & IOMAP_DIRECT) &&
(first_block << blkbits) < i_size_read(inode))
create = 0;
/*
* Writes that span EOF might trigger an IO size update on completion,
* so consider them to be dirty for the purposes of O_DSYNC even if
* there is no other metadata changes pending or have been made here.
*/
if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
ret = ext2_get_blocks(inode, first_block, max_blocks,
&bno, &new, &boundary, create);
if (ret < 0)
return ret;
iomap->flags = 0;
iomap->offset = (u64)first_block << blkbits;
if (flags & IOMAP_DAX)
iomap->dax_dev = sbi->s_daxdev;
else
iomap->bdev = inode->i_sb->s_bdev;
if (ret == 0) {
/*
* Switch to buffered-io for writing to holes in a non-extent
* based filesystem to avoid stale data exposure problem.
*/
if (!create && (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))
return -ENOTBLK;
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
iomap->length = 1 << blkbits;
} else {
iomap->type = IOMAP_MAPPED;
iomap->addr = (u64)bno << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += sbi->s_dax_part_off;
iomap->length = (u64)ret << blkbits;
iomap->flags |= IOMAP_F_MERGED;
}
if (new)
iomap->flags |= IOMAP_F_NEW;
return 0;
}
static int
ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
/*
* Switch to buffered-io in case of any error.
* Blocks allocated can be used by the buffered-io path.
*/
if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE) && written == 0)
return -ENOTBLK;
if (iomap->type == IOMAP_MAPPED &&
written < length &&
(flags & IOMAP_WRITE))
ext2_write_failed(inode->i_mapping, offset + length);
return 0;
}
const struct iomap_ops ext2_iomap_ops = {
.iomap_begin = ext2_iomap_begin,
.iomap_end = ext2_iomap_end,
};
int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
int ret;
inode_lock(inode);
len = min_t(u64, len, i_size_read(inode));
ret = iomap_fiemap(inode, fieinfo, start, len, &ext2_iomap_ops);
inode_unlock(inode);
return ret;
}
static int ext2_read_folio(struct file *file, struct folio *folio)
{
return mpage_read_folio(folio, ext2_get_block);
}
static void ext2_readahead(struct readahead_control *rac)
{
mpage_readahead(rac, ext2_get_block);
}
static int
ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, struct page **pagep, void **fsdata)
{
int ret;
ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block);
if (ret < 0)
ext2_write_failed(mapping, pos + len);
return ret;
}
static int ext2_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
int ret;
ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
if (ret < len)
ext2_write_failed(mapping, pos + len);
return ret;
}
static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,ext2_get_block);
}
static int
ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
return mpage_writepages(mapping, wbc, ext2_get_block);
}
static int
ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct ext2_sb_info *sbi = EXT2_SB(mapping->host->i_sb);
return dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
}
const struct address_space_operations ext2_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
.read_folio = ext2_read_folio,
.readahead = ext2_readahead,
.write_begin = ext2_write_begin,
.write_end = ext2_write_end,
.bmap = ext2_bmap,
.direct_IO = noop_direct_IO,
.writepages = ext2_writepages,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext2_dax_aops = {
.writepages = ext2_dax_writepages,
.direct_IO = noop_direct_IO,
.dirty_folio = noop_dirty_folio,
};
/*
* Probably it should be a library function... search for first non-zero word
* or memcmp with zero_page, whatever is better for particular architecture.
* Linus?
*/
static inline int all_zeroes(__le32 *p, __le32 *q)
{
while (p < q)
if (*p++)
return 0;
return 1;
}
/**
* ext2_find_shared - find the indirect blocks for partial truncation.
* @inode: inode in question
* @depth: depth of the affected branch
* @offsets: offsets of pointers in that branch (see ext2_block_to_path)
* @chain: place to store the pointers to partial indirect blocks
* @top: place to the (detached) top of branch