forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
file.c
1596 lines (1390 loc) · 39.7 KB
/
file.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-only
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
*/
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/compat.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/crc32.h>
#include <linux/writeback.h>
#include <linux/uaccess.h>
#include <linux/dlm.h>
#include <linux/dlm_plock.h>
#include <linux/delay.h>
#include <linux/backing-dev.h>
#include <linux/fileattr.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "aops.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
/**
* gfs2_llseek - seek to a location in a file
* @file: the file
* @offset: the offset
* @whence: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
*
* SEEK_END requires the glock for the file because it references the
* file's size.
*
* Returns: The new offset, or errno
*/
static loff_t gfs2_llseek(struct file *file, loff_t offset, int whence)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_holder i_gh;
loff_t error;
switch (whence) {
case SEEK_END:
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (!error) {
error = generic_file_llseek(file, offset, whence);
gfs2_glock_dq_uninit(&i_gh);
}
break;
case SEEK_DATA:
error = gfs2_seek_data(file, offset);
break;
case SEEK_HOLE:
error = gfs2_seek_hole(file, offset);
break;
case SEEK_CUR:
case SEEK_SET:
/*
* These don't reference inode->i_size and don't depend on the
* block mapping, so we don't need the glock.
*/
error = generic_file_llseek(file, offset, whence);
break;
default:
error = -EINVAL;
}
return error;
}
/**
* gfs2_readdir - Iterator for a directory
* @file: The directory to read from
* @ctx: What to feed directory entries to
*
* Returns: errno
*/
static int gfs2_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *dir = file->f_mapping->host;
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_holder d_gh;
int error;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
return error;
error = gfs2_dir_read(dir, ctx, &file->f_ra);
gfs2_glock_dq_uninit(&d_gh);
return error;
}
/*
* struct fsflag_gfs2flag
*
* The FS_JOURNAL_DATA_FL flag maps to GFS2_DIF_INHERIT_JDATA for directories,
* and to GFS2_DIF_JDATA for non-directories.
*/
static struct {
u32 fsflag;
u32 gfsflag;
} fsflag_gfs2flag[] = {
{FS_SYNC_FL, GFS2_DIF_SYNC},
{FS_IMMUTABLE_FL, GFS2_DIF_IMMUTABLE},
{FS_APPEND_FL, GFS2_DIF_APPENDONLY},
{FS_NOATIME_FL, GFS2_DIF_NOATIME},
{FS_INDEX_FL, GFS2_DIF_EXHASH},
{FS_TOPDIR_FL, GFS2_DIF_TOPDIR},
{FS_JOURNAL_DATA_FL, GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA},
};
static inline u32 gfs2_gfsflags_to_fsflags(struct inode *inode, u32 gfsflags)
{
int i;
u32 fsflags = 0;
if (S_ISDIR(inode->i_mode))
gfsflags &= ~GFS2_DIF_JDATA;
else
gfsflags &= ~GFS2_DIF_INHERIT_JDATA;
for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++)
if (gfsflags & fsflag_gfs2flag[i].gfsflag)
fsflags |= fsflag_gfs2flag[i].fsflag;
return fsflags;
}
int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
u32 fsflags;
if (d_is_special(dentry))
return -ENOTTY;
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
error = gfs2_glock_nq(&gh);
if (error)
goto out_uninit;
fsflags = gfs2_gfsflags_to_fsflags(inode, ip->i_diskflags);
fileattr_fill_flags(fa, fsflags);
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return error;
}
void gfs2_set_inode_flags(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
unsigned int flags = inode->i_flags;
flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_NOSEC);
if ((ip->i_eattr == 0) && !is_sxid(inode->i_mode))
flags |= S_NOSEC;
if (ip->i_diskflags & GFS2_DIF_IMMUTABLE)
flags |= S_IMMUTABLE;
if (ip->i_diskflags & GFS2_DIF_APPENDONLY)
flags |= S_APPEND;
if (ip->i_diskflags & GFS2_DIF_NOATIME)
flags |= S_NOATIME;
if (ip->i_diskflags & GFS2_DIF_SYNC)
flags |= S_SYNC;
inode->i_flags = flags;
}
/* Flags that can be set by user space */
#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA| \
GFS2_DIF_IMMUTABLE| \
GFS2_DIF_APPENDONLY| \
GFS2_DIF_NOATIME| \
GFS2_DIF_SYNC| \
GFS2_DIF_TOPDIR| \
GFS2_DIF_INHERIT_JDATA)
/**
* do_gfs2_set_flags - set flags on an inode
* @inode: The inode
* @reqflags: The flags to set
* @mask: Indicates which flags are valid
*
*/
static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_holder gh;
int error;
u32 new_flags, flags;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (error)
return error;
error = 0;
flags = ip->i_diskflags;
new_flags = (flags & ~mask) | (reqflags & mask);
if ((new_flags ^ flags) == 0)
goto out;
if (!IS_IMMUTABLE(inode)) {
error = gfs2_permission(&init_user_ns, inode, MAY_WRITE);
if (error)
goto out;
}
if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
if (new_flags & GFS2_DIF_JDATA)
gfs2_log_flush(sdp, ip->i_gl,
GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_SET_FLAGS);
error = filemap_fdatawrite(inode->i_mapping);
if (error)
goto out;
error = filemap_fdatawait(inode->i_mapping);
if (error)
goto out;
if (new_flags & GFS2_DIF_JDATA)
gfs2_ordered_del_inode(ip);
}
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (error)
goto out;
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
goto out_trans_end;
inode->i_ctime = current_time(inode);
gfs2_trans_add_meta(ip->i_gl, bh);
ip->i_diskflags = new_flags;
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
gfs2_set_inode_flags(inode);
gfs2_set_aops(inode);
out_trans_end:
gfs2_trans_end(sdp);
out:
gfs2_glock_dq_uninit(&gh);
return error;
}
int gfs2_fileattr_set(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
u32 fsflags = fa->flags, gfsflags = 0;
u32 mask;
int i;
if (d_is_special(dentry))
return -ENOTTY;
if (fileattr_has_fsx(fa))
return -EOPNOTSUPP;
for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++) {
if (fsflags & fsflag_gfs2flag[i].fsflag) {
fsflags &= ~fsflag_gfs2flag[i].fsflag;
gfsflags |= fsflag_gfs2flag[i].gfsflag;
}
}
if (fsflags || gfsflags & ~GFS2_FLAGS_USER_SET)
return -EINVAL;
mask = GFS2_FLAGS_USER_SET;
if (S_ISDIR(inode->i_mode)) {
mask &= ~GFS2_DIF_JDATA;
} else {
/* The GFS2_DIF_TOPDIR flag is only valid for directories. */
if (gfsflags & GFS2_DIF_TOPDIR)
return -EINVAL;
mask &= ~(GFS2_DIF_TOPDIR | GFS2_DIF_INHERIT_JDATA);
}
return do_gfs2_set_flags(inode, gfsflags, mask);
}
static int gfs2_getlabel(struct file *filp, char __user *label)
{
struct inode *inode = file_inode(filp);
struct gfs2_sbd *sdp = GFS2_SB(inode);
if (copy_to_user(label, sdp->sd_sb.sb_locktable, GFS2_LOCKNAME_LEN))
return -EFAULT;
return 0;
}
static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch(cmd) {
case FITRIM:
return gfs2_fitrim(filp, (void __user *)arg);
case FS_IOC_GETFSLABEL:
return gfs2_getlabel(filp, (char __user *)arg);
}
return -ENOTTY;
}
#ifdef CONFIG_COMPAT
static long gfs2_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch(cmd) {
/* Keep this list in sync with gfs2_ioctl */
case FITRIM:
case FS_IOC_GETFSLABEL:
break;
default:
return -ENOIOCTLCMD;
}
return gfs2_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
}
#else
#define gfs2_compat_ioctl NULL
#endif
/**
* gfs2_size_hint - Give a hint to the size of a write request
* @filep: The struct file
* @offset: The file offset of the write
* @size: The length of the write
*
* When we are about to do a write, this function records the total
* write size in order to provide a suitable hint to the lower layers
* about how many blocks will be required.
*
*/
static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size)
{
struct inode *inode = file_inode(filep);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift;
int hint = min_t(size_t, INT_MAX, blks);
if (hint > atomic_read(&ip->i_sizehint))
atomic_set(&ip->i_sizehint, hint);
}
/**
* gfs2_allocate_page_backing - Allocate blocks for a write fault
* @page: The (locked) page to allocate backing for
* @length: Size of the allocation
*
* We try to allocate all the blocks required for the page in one go. This
* might fail for various reasons, so we keep trying until all the blocks to
* back this page are allocated. If some of the blocks are already allocated,
* that is ok too.
*/
static int gfs2_allocate_page_backing(struct page *page, unsigned int length)
{
u64 pos = page_offset(page);
do {
struct iomap iomap = { };
if (gfs2_iomap_alloc(page->mapping->host, pos, length, &iomap))
return -EIO;
if (length < iomap.length)
iomap.length = length;
length -= iomap.length;
pos += iomap.length;
} while (length > 0);
return 0;
}
/**
* gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
* @vmf: The virtual memory fault containing the page to become writable
*
* When the page becomes writable, we need to ensure that we have
* blocks allocated on disk to back that page.
*/
static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
u64 offset = page_offset(page);
unsigned int data_blocks, ind_blocks, rblocks;
vm_fault_t ret = VM_FAULT_LOCKED;
struct gfs2_holder gh;
unsigned int length;
loff_t size;
int err;
sb_start_pagefault(inode->i_sb);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
err = gfs2_glock_nq(&gh);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_uninit;
}
/* Check page index against inode size */
size = i_size_read(inode);
if (offset >= size) {
ret = VM_FAULT_SIGBUS;
goto out_unlock;
}
/* Update file times before taking page lock */
file_update_time(vmf->vma->vm_file);
/* page is wholly or partially inside EOF */
if (size - offset < PAGE_SIZE)
length = size - offset;
else
length = PAGE_SIZE;
gfs2_size_hint(vmf->vma->vm_file, offset, length);
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
/*
* iomap_writepage / iomap_writepages currently don't support inline
* files, so always unstuff here.
*/
if (!gfs2_is_stuffed(ip) &&
!gfs2_write_alloc_required(ip, offset, length)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = VM_FAULT_NOPAGE;
unlock_page(page);
}
goto out_unlock;
}
err = gfs2_rindex_update(sdp);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_unlock;
}
gfs2_write_calc_reserv(ip, length, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
err = gfs2_quota_lock_check(ip, &ap);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_unlock;
}
err = gfs2_inplace_reserve(ip, &ap);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_quota_unlock;
}
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
err = gfs2_trans_begin(sdp, rblocks, 0);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_trans_fail;
}
/* Unstuff, if required, and allocate backing blocks for page */
if (gfs2_is_stuffed(ip)) {
err = gfs2_unstuff_dinode(ip);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_trans_end;
}
}
lock_page(page);
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = VM_FAULT_NOPAGE;
goto out_page_locked;
}
err = gfs2_allocate_page_backing(page, length);
if (err)
ret = block_page_mkwrite_return(err);
out_page_locked:
if (ret != VM_FAULT_LOCKED)
unlock_page(page);
out_trans_end:
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == VM_FAULT_LOCKED) {
set_page_dirty(page);
wait_for_stable_page(page);
}
sb_end_pagefault(inode->i_sb);
return ret;
}
static vm_fault_t gfs2_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
vm_fault_t ret;
int err;
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
err = gfs2_glock_nq(&gh);
if (err) {
ret = block_page_mkwrite_return(err);
goto out_uninit;
}
ret = filemap_fault(vmf);
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return ret;
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = gfs2_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = gfs2_page_mkwrite,
};
/**
* gfs2_mmap
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
return 0;
}
/**
* gfs2_open_common - This is common to open and atomic_open
* @inode: The inode being opened
* @file: The file being opened
*
* This maybe called under a glock or not depending upon how it has
* been called. We must always be called under a glock for regular
* files, however. For other file types, it does not matter whether
* we hold the glock or not.
*
* Returns: Error code or 0 for success
*/
int gfs2_open_common(struct inode *inode, struct file *file)
{
struct gfs2_file *fp;
int ret;
if (S_ISREG(inode->i_mode)) {
ret = generic_file_open(inode, file);
if (ret)
return ret;
}
fp = kzalloc(sizeof(struct gfs2_file), GFP_NOFS);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
if (file->f_mode & FMODE_WRITE) {
ret = gfs2_qa_get(GFS2_I(inode));
if (ret)
goto fail;
}
return 0;
fail:
kfree(file->private_data);
file->private_data = NULL;
return ret;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* After atomic_open, this function is only used for opening files
* which are already cached. We must still get the glock for regular
* files to ensure that we have the file size uptodate for the large
* file check which is in the common code. That is only an issue for
* regular files though.
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
int error;
bool need_unlock = false;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
need_unlock = true;
}
error = gfs2_open_common(inode, file);
if (need_unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (file->f_mode & FMODE_WRITE) {
if (gfs2_rs_active(&ip->i_res))
gfs2_rs_delete(ip);
gfs2_qa_put(ip);
}
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* We split the data flushing here so that we don't wait for the data
* until after we've also sent the metadata to disk. Note that for
* data=ordered, we will write & wait for the data at the log flush
* stage anyway, so this is unlikely to make much of a difference
* except in the data=writeback case.
*
* If the fdatawrite fails due to any reason except -EIO, we will
* continue the remainder of the fsync, although we'll still report
* the error at the end. This is to match filemap_write_and_wait_range()
* behaviour.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret = 0, ret1 = 0;
if (mapping->nrpages) {
ret1 = filemap_fdatawrite_range(mapping, start, end);
if (ret1 == -EIO)
return ret1;
}
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
ret = file_write_and_wait(file);
if (ret)
return ret;
gfs2_ail_flush(ip->i_gl, 1);
}
if (mapping->nrpages)
ret = file_fdatawait_range(file, start, end);
return ret ? ret : ret1;
}
static inline bool should_fault_in_pages(struct iov_iter *i,
struct kiocb *iocb,
size_t *prev_count,
size_t *window_size)
{
size_t count = iov_iter_count(i);
size_t size, offs;
if (!count)
return false;
if (!user_backed_iter(i))
return false;
size = PAGE_SIZE;
offs = offset_in_page(iocb->ki_pos);
if (*prev_count != count || !*window_size) {
size_t nr_dirtied;
nr_dirtied = max(current->nr_dirtied_pause -
current->nr_dirtied, 8);
size = min_t(size_t, SZ_1M, nr_dirtied << PAGE_SHIFT);
}
*prev_count = count;
*window_size = size - offs;
return true;
}
static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to,
struct gfs2_holder *gh)
{
struct file *file = iocb->ki_filp;
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
size_t prev_count = 0, window_size = 0;
size_t read = 0;
ssize_t ret;
/*
* In this function, we disable page faults when we're holding the
* inode glock while doing I/O. If a page fault occurs, we indicate
* that the inode glock may be dropped, fault in the pages manually,
* and retry.
*
* Unlike generic_file_read_iter, for reads, iomap_dio_rw can trigger
* physical as well as manual page faults, and we need to disable both
* kinds.
*
* For direct I/O, gfs2 takes the inode glock in deferred mode. This
* locking mode is compatible with other deferred holders, so multiple
* processes and nodes can do direct I/O to a file at the same time.
* There's no guarantee that reads or writes will be atomic. Any
* coordination among readers and writers needs to happen externally.
*/
if (!iov_iter_count(to))
return 0; /* skip atime */
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh);
retry:
ret = gfs2_glock_nq(gh);
if (ret)
goto out_uninit;
pagefault_disable();
to->nofault = true;
ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL,
IOMAP_DIO_PARTIAL, NULL, read);
to->nofault = false;
pagefault_enable();
if (ret <= 0 && ret != -EFAULT)
goto out_unlock;
/* No increment (+=) because iomap_dio_rw returns a cumulative value. */
if (ret > 0)
read = ret;
if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) {
gfs2_glock_dq(gh);
window_size -= fault_in_iov_iter_writeable(to, window_size);
if (window_size)
goto retry;
}
out_unlock:
if (gfs2_holder_queued(gh))
gfs2_glock_dq(gh);
out_uninit:
gfs2_holder_uninit(gh);
/* User space doesn't expect partial success. */
if (ret < 0)
return ret;
return read;
}
static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
struct gfs2_holder *gh)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
size_t prev_count = 0, window_size = 0;
size_t written = 0;
ssize_t ret;
/*
* In this function, we disable page faults when we're holding the
* inode glock while doing I/O. If a page fault occurs, we indicate
* that the inode glock may be dropped, fault in the pages manually,
* and retry.
*
* For writes, iomap_dio_rw only triggers manual page faults, so we
* don't need to disable physical ones.
*/
/*
* Deferred lock, even if its a write, since we do no allocation on
* this path. All we need to change is the atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately, have the option of only flushing a range like the
* VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh);
retry:
ret = gfs2_glock_nq(gh);
if (ret)
goto out_uninit;
/* Silently fall back to buffered I/O when writing beyond EOF */
if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode))
goto out_unlock;
from->nofault = true;
ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL,
IOMAP_DIO_PARTIAL, NULL, written);
from->nofault = false;
if (ret <= 0) {
if (ret == -ENOTBLK)
ret = 0;
if (ret != -EFAULT)
goto out_unlock;
}
/* No increment (+=) because iomap_dio_rw returns a cumulative value. */
if (ret > 0)
written = ret;
if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) {
gfs2_glock_dq(gh);
window_size -= fault_in_iov_iter_readable(from, window_size);
if (window_size)
goto retry;
}
out_unlock:
if (gfs2_holder_queued(gh))
gfs2_glock_dq(gh);
out_uninit:
gfs2_holder_uninit(gh);
/* User space doesn't expect partial success. */
if (ret < 0)
return ret;
return written;
}
static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct gfs2_inode *ip;
struct gfs2_holder gh;
size_t prev_count = 0, window_size = 0;
size_t read = 0;
ssize_t ret;
/*
* In this function, we disable page faults when we're holding the
* inode glock while doing I/O. If a page fault occurs, we indicate
* that the inode glock may be dropped, fault in the pages manually,
* and retry.
*/
if (iocb->ki_flags & IOCB_DIRECT)
return gfs2_file_direct_read(iocb, to, &gh);
pagefault_disable();
iocb->ki_flags |= IOCB_NOIO;
ret = generic_file_read_iter(iocb, to);
iocb->ki_flags &= ~IOCB_NOIO;
pagefault_enable();
if (ret >= 0) {
if (!iov_iter_count(to))
return ret;
read = ret;
} else if (ret != -EFAULT) {
if (ret != -EAGAIN)
return ret;
if (iocb->ki_flags & IOCB_NOWAIT)
return ret;
}
ip = GFS2_I(iocb->ki_filp->f_mapping->host);
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
retry:
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
pagefault_disable();
ret = generic_file_read_iter(iocb, to);
pagefault_enable();
if (ret <= 0 && ret != -EFAULT)
goto out_unlock;
if (ret > 0)
read += ret;
if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) {
gfs2_glock_dq(&gh);
window_size -= fault_in_iov_iter_writeable(to, window_size);
if (window_size)
goto retry;
}
out_unlock:
if (gfs2_holder_queued(&gh))
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return read ? read : ret;
}
static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
struct iov_iter *from,
struct gfs2_holder *gh)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);