forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbmap.c
1857 lines (1644 loc) · 49.2 KB
/
bmap.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
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/iomap.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "log.h"
#include "super.h"
#include "trans.h"
#include "dir.h"
#include "util.h"
#include "trace_gfs2.h"
/* This doesn't need to be that large as max 64 bit pointers in a 4k
* block is 512, so __u16 is fine for that. It saves stack space to
* keep it small.
*/
struct metapath {
struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
__u16 mp_list[GFS2_MAX_META_HEIGHT];
int mp_fheight; /* find_metapath height */
int mp_aheight; /* actual height (lookup height) */
};
/**
* gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
* @ip: the inode
* @dibh: the dinode buffer
* @block: the block number that was allocated
* @page: The (optional) page. This is looked up if @page is NULL
*
* Returns: errno
*/
static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
u64 block, struct page *page)
{
struct inode *inode = &ip->i_inode;
struct buffer_head *bh;
int release = 0;
if (!page || page->index) {
page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
if (!page)
return -ENOMEM;
release = 1;
}
if (!PageUptodate(page)) {
void *kaddr = kmap(page);
u64 dsize = i_size_read(inode);
if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
dsize = dibh->b_size - sizeof(struct gfs2_dinode);
memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
kunmap(page);
SetPageUptodate(page);
}
if (!page_has_buffers(page))
create_empty_buffers(page, BIT(inode->i_blkbits),
BIT(BH_Uptodate));
bh = page_buffers(page);
if (!buffer_mapped(bh))
map_bh(bh, inode->i_sb, block);
set_buffer_uptodate(bh);
if (!gfs2_is_jdata(ip))
mark_buffer_dirty(bh);
if (!gfs2_is_writeback(ip))
gfs2_trans_add_data(ip->i_gl, bh);
if (release) {
unlock_page(page);
put_page(page);
}
return 0;
}
/**
* gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
* @ip: The GFS2 inode to unstuff
* @page: The (optional) page. This is looked up if the @page is NULL
*
* This routine unstuffs a dinode and returns it to a "normal" state such
* that the height can be grown in the traditional way.
*
* Returns: errno
*/
int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
{
struct buffer_head *bh, *dibh;
struct gfs2_dinode *di;
u64 block = 0;
int isdir = gfs2_is_dir(ip);
int error;
down_write(&ip->i_rw_mutex);
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out;
if (i_size_read(&ip->i_inode)) {
/* Get a free block, fill it with the stuffed data,
and write it out to disk */
unsigned int n = 1;
error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL);
if (error)
goto out_brelse;
if (isdir) {
gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
error = gfs2_dir_get_new_buffer(ip, block, &bh);
if (error)
goto out_brelse;
gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
dibh, sizeof(struct gfs2_dinode));
brelse(bh);
} else {
error = gfs2_unstuffer_page(ip, dibh, block, page);
if (error)
goto out_brelse;
}
}
/* Set up the pointer to the new block */
gfs2_trans_add_meta(ip->i_gl, dibh);
di = (struct gfs2_dinode *)dibh->b_data;
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
if (i_size_read(&ip->i_inode)) {
*(__be64 *)(di + 1) = cpu_to_be64(block);
gfs2_add_inode_blocks(&ip->i_inode, 1);
di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
}
ip->i_height = 1;
di->di_height = cpu_to_be16(1);
out_brelse:
brelse(dibh);
out:
up_write(&ip->i_rw_mutex);
return error;
}
/**
* find_metapath - Find path through the metadata tree
* @sdp: The superblock
* @mp: The metapath to return the result in
* @block: The disk block to look up
* @height: The pre-calculated height of the metadata tree
*
* This routine returns a struct metapath structure that defines a path
* through the metadata of inode "ip" to get to block "block".
*
* Example:
* Given: "ip" is a height 3 file, "offset" is 101342453, and this is a
* filesystem with a blocksize of 4096.
*
* find_metapath() would return a struct metapath structure set to:
* mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
* and mp_list[2] = 165.
*
* That means that in order to get to the block containing the byte at
* offset 101342453, we would load the indirect block pointed to by pointer
* 0 in the dinode. We would then load the indirect block pointed to by
* pointer 48 in that indirect block. We would then load the data block
* pointed to by pointer 165 in that indirect block.
*
* ----------------------------------------
* | Dinode | |
* | | 4|
* | |0 1 2 3 4 5 9|
* | | 6|
* ----------------------------------------
* |
* |
* V
* ----------------------------------------
* | Indirect Block |
* | 5|
* | 4 4 4 4 4 5 5 1|
* |0 5 6 7 8 9 0 1 2|
* ----------------------------------------
* |
* |
* V
* ----------------------------------------
* | Indirect Block |
* | 1 1 1 1 1 5|
* | 6 6 6 6 6 1|
* |0 3 4 5 6 7 2|
* ----------------------------------------
* |
* |
* V
* ----------------------------------------
* | Data block containing offset |
* | 101342453 |
* | |
* | |
* ----------------------------------------
*
*/
static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
struct metapath *mp, unsigned int height)
{
unsigned int i;
mp->mp_fheight = height;
for (i = height; i--;)
mp->mp_list[i] = do_div(block, sdp->sd_inptrs);
}
static inline unsigned int metapath_branch_start(const struct metapath *mp)
{
if (mp->mp_list[0] == 0)
return 2;
return 1;
}
/**
* metaptr1 - Return the first possible metadata pointer in a metapath buffer
* @height: The metadata height (0 = dinode)
* @mp: The metapath
*/
static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp)
{
struct buffer_head *bh = mp->mp_bh[height];
if (height == 0)
return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)));
return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header)));
}
/**
* metapointer - Return pointer to start of metadata in a buffer
* @height: The metadata height (0 = dinode)
* @mp: The metapath
*
* Return a pointer to the block number of the next height of the metadata
* tree given a buffer containing the pointer to the current height of the
* metadata tree.
*/
static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
{
__be64 *p = metaptr1(height, mp);
return p + mp->mp_list[height];
}
static void gfs2_metapath_ra(struct gfs2_glock *gl,
const struct buffer_head *bh, const __be64 *pos)
{
struct buffer_head *rabh;
const __be64 *endp = (const __be64 *)(bh->b_data + bh->b_size);
const __be64 *t;
for (t = pos; t < endp; t++) {
if (!*t)
continue;
rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE);
if (trylock_buffer(rabh)) {
if (!buffer_uptodate(rabh)) {
rabh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ,
REQ_RAHEAD | REQ_META | REQ_PRIO,
rabh);
continue;
}
unlock_buffer(rabh);
}
brelse(rabh);
}
}
/**
* lookup_mp_height - helper function for lookup_metapath
* @ip: the inode
* @mp: the metapath
* @h: the height which needs looking up
*/
static int lookup_mp_height(struct gfs2_inode *ip, struct metapath *mp, int h)
{
__be64 *ptr = metapointer(h, mp);
u64 dblock = be64_to_cpu(*ptr);
if (!dblock)
return h + 1;
return gfs2_meta_indirect_buffer(ip, h + 1, dblock, &mp->mp_bh[h + 1]);
}
/**
* lookup_metapath - Walk the metadata tree to a specific point
* @ip: The inode
* @mp: The metapath
*
* Assumes that the inode's buffer has already been looked up and
* hooked onto mp->mp_bh[0] and that the metapath has been initialised
* by find_metapath().
*
* If this function encounters part of the tree which has not been
* allocated, it returns the current height of the tree at the point
* at which it found the unallocated block. Blocks which are found are
* added to the mp->mp_bh[] list.
*
* Returns: error or height of metadata tree
*/
static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
{
unsigned int end_of_metadata = ip->i_height - 1;
unsigned int x;
int ret;
for (x = 0; x < end_of_metadata; x++) {
ret = lookup_mp_height(ip, mp, x);
if (ret)
goto out;
}
ret = ip->i_height;
out:
mp->mp_aheight = ret;
return ret;
}
/**
* fillup_metapath - fill up buffers for the metadata path to a specific height
* @ip: The inode
* @mp: The metapath
* @h: The height to which it should be mapped
*
* Similar to lookup_metapath, but does lookups for a range of heights
*
* Returns: error or height of metadata tree
*/
static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
{
unsigned int start_h = h - 1;
int ret;
if (h) {
/* find the first buffer we need to look up. */
while (start_h > 0 && mp->mp_bh[start_h] == NULL)
start_h--;
for (; start_h < h; start_h++) {
ret = lookup_mp_height(ip, mp, start_h);
if (ret)
return ret;
}
}
return ip->i_height;
}
static inline void release_metapath(struct metapath *mp)
{
int i;
for (i = 0; i < GFS2_MAX_META_HEIGHT; i++) {
if (mp->mp_bh[i] == NULL)
break;
brelse(mp->mp_bh[i]);
}
}
/**
* gfs2_extent_length - Returns length of an extent of blocks
* @start: Start of the buffer
* @len: Length of the buffer in bytes
* @ptr: Current position in the buffer
* @limit: Max extent length to return (0 = unlimited)
* @eob: Set to 1 if we hit "end of block"
*
* If the first block is zero (unallocated) it will return the number of
* unallocated blocks in the extent, otherwise it will return the number
* of contiguous blocks in the extent.
*
* Returns: The length of the extent (minimum of one block)
*/
static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __be64 *ptr, size_t limit, int *eob)
{
const __be64 *end = (start + len);
const __be64 *first = ptr;
u64 d = be64_to_cpu(*ptr);
*eob = 0;
do {
ptr++;
if (ptr >= end)
break;
if (limit && --limit == 0)
break;
if (d)
d++;
} while(be64_to_cpu(*ptr) == d);
if (ptr >= end)
*eob = 1;
return (ptr - first);
}
static inline void bmap_lock(struct gfs2_inode *ip, int create)
{
if (create)
down_write(&ip->i_rw_mutex);
else
down_read(&ip->i_rw_mutex);
}
static inline void bmap_unlock(struct gfs2_inode *ip, int create)
{
if (create)
up_write(&ip->i_rw_mutex);
else
up_read(&ip->i_rw_mutex);
}
static inline __be64 *gfs2_indirect_init(struct metapath *mp,
struct gfs2_glock *gl, unsigned int i,
unsigned offset, u64 bn)
{
__be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data +
((i > 1) ? sizeof(struct gfs2_meta_header) :
sizeof(struct gfs2_dinode)));
BUG_ON(i < 1);
BUG_ON(mp->mp_bh[i] != NULL);
mp->mp_bh[i] = gfs2_meta_new(gl, bn);
gfs2_trans_add_meta(gl, mp->mp_bh[i]);
gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
ptr += offset;
*ptr = cpu_to_be64(bn);
return ptr;
}
enum alloc_state {
ALLOC_DATA = 0,
ALLOC_GROW_DEPTH = 1,
ALLOC_GROW_HEIGHT = 2,
/* ALLOC_UNSTUFF = 3, TBD and rather complicated */
};
static inline unsigned int hptrs(struct gfs2_sbd *sdp, const unsigned int hgt)
{
if (hgt)
return sdp->sd_inptrs;
return sdp->sd_diptrs;
}
/**
* gfs2_bmap_alloc - Build a metadata tree of the requested height
* @inode: The GFS2 inode
* @lblock: The logical starting block of the extent
* @bh_map: This is used to return the mapping details
* @zero_new: True if newly allocated blocks should be zeroed
* @mp: The metapath, with proper height information calculated
* @maxlen: The max number of data blocks to alloc
* @dblock: Pointer to return the resulting new block
* @dblks: Pointer to return the number of blocks allocated
*
* In this routine we may have to alloc:
* i) Indirect blocks to grow the metadata tree height
* ii) Indirect blocks to fill in lower part of the metadata tree
* iii) Data blocks
*
* The function is in two parts. The first part works out the total
* number of blocks which we need. The second part does the actual
* allocation asking for an extent at a time (if enough contiguous free
* blocks are available, there will only be one request per bmap call)
* and uses the state machine to initialise the blocks in order.
*
* Returns: errno on error
*/
static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
unsigned flags, struct metapath *mp)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct super_block *sb = sdp->sd_vfs;
struct buffer_head *dibh = mp->mp_bh[0];
u64 bn;
unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
unsigned dblks = 0;
unsigned ptrs_per_blk;
const unsigned end_of_metadata = mp->mp_fheight - 1;
int ret;
enum alloc_state state;
__be64 *ptr;
__be64 zero_bn = 0;
size_t maxlen = iomap->length >> inode->i_blkbits;
BUG_ON(mp->mp_aheight < 1);
BUG_ON(dibh == NULL);
gfs2_trans_add_meta(ip->i_gl, dibh);
if (mp->mp_fheight == mp->mp_aheight) {
struct buffer_head *bh;
int eob;
/* Bottom indirect block exists, find unalloced extent size */
ptr = metapointer(end_of_metadata, mp);
bh = mp->mp_bh[end_of_metadata];
dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr,
maxlen, &eob);
BUG_ON(dblks < 1);
state = ALLOC_DATA;
} else {
/* Need to allocate indirect blocks */
ptrs_per_blk = mp->mp_fheight > 1 ? sdp->sd_inptrs :
sdp->sd_diptrs;
dblks = min(maxlen, (size_t)(ptrs_per_blk -
mp->mp_list[end_of_metadata]));
if (mp->mp_fheight == ip->i_height) {
/* Writing into existing tree, extend tree down */
iblks = mp->mp_fheight - mp->mp_aheight;
state = ALLOC_GROW_DEPTH;
} else {
/* Building up tree height */
state = ALLOC_GROW_HEIGHT;
iblks = mp->mp_fheight - ip->i_height;
branch_start = metapath_branch_start(mp);
iblks += (mp->mp_fheight - branch_start);
}
}
/* start of the second part of the function (state machine) */
blks = dblks + iblks;
i = mp->mp_aheight;
do {
int error;
n = blks - alloced;
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
return error;
alloced += n;
if (state != ALLOC_DATA || gfs2_is_jdata(ip))
gfs2_trans_add_unrevoke(sdp, bn, n);
switch (state) {
/* Growing height of tree */
case ALLOC_GROW_HEIGHT:
if (i == 1) {
ptr = (__be64 *)(dibh->b_data +
sizeof(struct gfs2_dinode));
zero_bn = *ptr;
}
for (; i - 1 < mp->mp_fheight - ip->i_height && n > 0;
i++, n--)
gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
if (i - 1 == mp->mp_fheight - ip->i_height) {
i--;
gfs2_buffer_copy_tail(mp->mp_bh[i],
sizeof(struct gfs2_meta_header),
dibh, sizeof(struct gfs2_dinode));
gfs2_buffer_clear_tail(dibh,
sizeof(struct gfs2_dinode) +
sizeof(__be64));
ptr = (__be64 *)(mp->mp_bh[i]->b_data +
sizeof(struct gfs2_meta_header));
*ptr = zero_bn;
state = ALLOC_GROW_DEPTH;
for(i = branch_start; i < mp->mp_fheight; i++) {
if (mp->mp_bh[i] == NULL)
break;
brelse(mp->mp_bh[i]);
mp->mp_bh[i] = NULL;
}
i = branch_start;
}
if (n == 0)
break;
/* Branching from existing tree */
case ALLOC_GROW_DEPTH:
if (i > 1 && i < mp->mp_fheight)
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
for (; i < mp->mp_fheight && n > 0; i++, n--)
gfs2_indirect_init(mp, ip->i_gl, i,
mp->mp_list[i-1], bn++);
if (i == mp->mp_fheight)
state = ALLOC_DATA;
if (n == 0)
break;
/* Tree complete, adding data blocks */
case ALLOC_DATA:
BUG_ON(n > dblks);
BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
dblks = n;
ptr = metapointer(end_of_metadata, mp);
iomap->addr = bn << inode->i_blkbits;
iomap->flags |= IOMAP_F_NEW;
while (n-- > 0)
*ptr++ = cpu_to_be64(bn++);
if (flags & IOMAP_ZERO) {
ret = sb_issue_zeroout(sb, iomap->addr >> inode->i_blkbits,
dblks, GFP_NOFS);
if (ret) {
fs_err(sdp,
"Failed to zero data buffers\n");
flags &= ~IOMAP_ZERO;
}
}
break;
}
} while (iomap->addr == IOMAP_NULL_ADDR);
iomap->length = (u64)dblks << inode->i_blkbits;
ip->i_height = mp->mp_fheight;
gfs2_add_inode_blocks(&ip->i_inode, alloced);
gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
return 0;
}
/**
* hole_size - figure out the size of a hole
* @inode: The inode
* @lblock: The logical starting block number
* @mp: The metapath
*
* Returns: The hole size in bytes
*
*/
static u64 hole_size(struct inode *inode, sector_t lblock, struct metapath *mp)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct metapath mp_eof;
u64 factor = 1;
int hgt;
u64 holesz = 0;
const __be64 *first, *end, *ptr;
const struct buffer_head *bh;
u64 lblock_stop = (i_size_read(inode) - 1) >> inode->i_blkbits;
int zeroptrs;
bool done = false;
/* Get another metapath, to the very last byte */
find_metapath(sdp, lblock_stop, &mp_eof, ip->i_height);
for (hgt = ip->i_height - 1; hgt >= 0 && !done; hgt--) {
bh = mp->mp_bh[hgt];
if (bh) {
zeroptrs = 0;
first = metapointer(hgt, mp);
end = (const __be64 *)(bh->b_data + bh->b_size);
for (ptr = first; ptr < end; ptr++) {
if (*ptr) {
done = true;
break;
} else {
zeroptrs++;
}
}
} else {
zeroptrs = sdp->sd_inptrs;
}
if (factor * zeroptrs >= lblock_stop - lblock + 1) {
holesz = lblock_stop - lblock + 1;
break;
}
holesz += factor * zeroptrs;
factor *= sdp->sd_inptrs;
if (hgt && (mp->mp_list[hgt - 1] < mp_eof.mp_list[hgt - 1]))
(mp->mp_list[hgt - 1])++;
}
return holesz << inode->i_blkbits;
}
static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
{
struct gfs2_inode *ip = GFS2_I(inode);
iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
sizeof(struct gfs2_dinode);
iomap->offset = 0;
iomap->length = i_size_read(inode);
iomap->type = IOMAP_MAPPED;
iomap->flags = IOMAP_F_DATA_INLINE;
}
/**
* gfs2_iomap_begin - Map blocks from an inode to disk blocks
* @inode: The inode
* @pos: Starting position in bytes
* @length: Length to map, in bytes
* @flags: iomap flags
* @iomap: The iomap structure
*
* Returns: errno
*/
int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
unsigned flags, struct iomap *iomap)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct metapath mp = { .mp_aheight = 1, };
unsigned int factor = sdp->sd_sb.sb_bsize;
const u64 *arr = sdp->sd_heightsize;
__be64 *ptr;
sector_t lblock;
sector_t lend;
int ret;
int eob;
unsigned int len;
struct buffer_head *bh;
u8 height;
trace_gfs2_iomap_start(ip, pos, length, flags);
if (!length) {
ret = -EINVAL;
goto out;
}
if ((flags & IOMAP_REPORT) && gfs2_is_stuffed(ip)) {
gfs2_stuffed_iomap(inode, iomap);
if (pos >= iomap->length)
return -ENOENT;
ret = 0;
goto out;
}
lblock = pos >> inode->i_blkbits;
lend = (pos + length + sdp->sd_sb.sb_bsize - 1) >> inode->i_blkbits;
iomap->offset = lblock << inode->i_blkbits;
iomap->addr = IOMAP_NULL_ADDR;
iomap->type = IOMAP_HOLE;
iomap->length = (u64)(lend - lblock) << inode->i_blkbits;
iomap->flags = IOMAP_F_MERGED;
bmap_lock(ip, 0);
/*
* Directory data blocks have a struct gfs2_meta_header header, so the
* remaining size is smaller than the filesystem block size. Logical
* block numbers for directories are in units of this remaining size!
*/
if (gfs2_is_dir(ip)) {
factor = sdp->sd_jbsize;
arr = sdp->sd_jheightsize;
}
ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
if (ret)
goto out_release;
height = ip->i_height;
while ((lblock + 1) * factor > arr[height])
height++;
find_metapath(sdp, lblock, &mp, height);
if (height > ip->i_height || gfs2_is_stuffed(ip))
goto do_alloc;
ret = lookup_metapath(ip, &mp);
if (ret < 0)
goto out_release;
if (mp.mp_aheight != ip->i_height)
goto do_alloc;
ptr = metapointer(ip->i_height - 1, &mp);
if (*ptr == 0)
goto do_alloc;
iomap->type = IOMAP_MAPPED;
iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
bh = mp.mp_bh[ip->i_height - 1];
len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, lend - lblock, &eob);
if (eob)
iomap->flags |= IOMAP_F_BOUNDARY;
iomap->length = (u64)len << inode->i_blkbits;
ret = 0;
out_release:
release_metapath(&mp);
bmap_unlock(ip, 0);
out:
trace_gfs2_iomap_end(ip, iomap, ret);
return ret;
do_alloc:
if (!(flags & IOMAP_WRITE)) {
if (pos >= i_size_read(inode)) {
ret = -ENOENT;
goto out_release;
}
ret = 0;
iomap->length = hole_size(inode, lblock, &mp);
goto out_release;
}
ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
goto out_release;
}
/**
* gfs2_block_map - Map a block from an inode to a disk block
* @inode: The inode
* @lblock: The logical block number
* @bh_map: The bh to be mapped
* @create: True if its ok to alloc blocks to satify the request
*
* Sets buffer_mapped() if successful, sets buffer_boundary() if a
* read of metadata will be required before the next block can be
* mapped. Sets buffer_new() if new blocks were allocated.
*
* Returns: errno
*/
int gfs2_block_map(struct inode *inode, sector_t lblock,
struct buffer_head *bh_map, int create)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct iomap iomap;
int ret, flags = 0;
clear_buffer_mapped(bh_map);
clear_buffer_new(bh_map);
clear_buffer_boundary(bh_map);
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
if (create)
flags |= IOMAP_WRITE;
if (buffer_zeronew(bh_map))
flags |= IOMAP_ZERO;
ret = gfs2_iomap_begin(inode, (loff_t)lblock << inode->i_blkbits,
bh_map->b_size, flags, &iomap);
if (ret) {
if (!create && ret == -ENOENT) {
/* Return unmapped buffer beyond the end of file. */
ret = 0;
}
goto out;
}
if (iomap.length > bh_map->b_size) {
iomap.length = bh_map->b_size;
iomap.flags &= ~IOMAP_F_BOUNDARY;
}
if (iomap.addr != IOMAP_NULL_ADDR)
map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits);
bh_map->b_size = iomap.length;
if (iomap.flags & IOMAP_F_BOUNDARY)
set_buffer_boundary(bh_map);
if (iomap.flags & IOMAP_F_NEW)
set_buffer_new(bh_map);
out:
trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
return ret;
}
/*
* Deprecated: do not use in new code
*/
int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen)
{
struct buffer_head bh = { .b_state = 0, .b_blocknr = 0 };
int ret;
int create = *new;
BUG_ON(!extlen);
BUG_ON(!dblock);
BUG_ON(!new);
bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5));
ret = gfs2_block_map(inode, lblock, &bh, create);
*extlen = bh.b_size >> inode->i_blkbits;
*dblock = bh.b_blocknr;
if (buffer_new(&bh))
*new = 1;
else
*new = 0;
return ret;
}
/**
* gfs2_block_truncate_page - Deal with zeroing out data for truncate
*
* This is partly borrowed from ext3.
*/
static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
{
struct inode *inode = mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
unsigned long index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize, iblock, length, pos;
struct buffer_head *bh;
struct page *page;
int err;
page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page)
return 0;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
/* Find the buffer that contains "offset" */
bh = page_buffers(page);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
err = 0;
if (!buffer_mapped(bh)) {
gfs2_block_map(inode, iblock, bh, 0);
/* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh))
goto unlock;
}
/* Ok, it's mapped. Make sure it's up-to-date */
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
err = -EIO;
ll_rw_block(REQ_OP_READ, 0, 1, &bh);
wait_on_buffer(bh);
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
goto unlock;
err = 0;
}
if (!gfs2_is_writeback(ip))
gfs2_trans_add_data(ip->i_gl, bh);
zero_user(page, offset, length);
mark_buffer_dirty(bh);
unlock:
unlock_page(page);
put_page(page);
return err;
}
#define GFS2_JTRUNC_REVOKES 8192
/**
* gfs2_journaled_truncate - Wrapper for truncate_pagecache for jdata files
* @inode: The inode being truncated
* @oldsize: The original (larger) size
* @newsize: The new smaller size
*
* With jdata files, we have to journal a revoke for each block which is
* truncated. As a result, we need to split this into separate transactions
* if the number of pages being truncated gets too large.
*/
static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize)
{
struct gfs2_sbd *sdp = GFS2_SB(inode);