forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ioctl.c
1654 lines (1415 loc) · 40.9 KB
/
ioctl.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/ext4/ioctl.c
*
* Copyright (C) 1993, 1994, 1995
* Remy Card ([email protected])
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*/
#include <linux/fs.h>
#include <linux/capability.h>
#include <linux/time.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/random.h>
#include <linux/uuid.h>
#include <linux/uaccess.h>
#include <linux/delay.h>
#include <linux/iversion.h>
#include <linux/fileattr.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include <linux/fsmap.h>
#include "fsmap.h"
#include <trace/events/ext4.h>
typedef void ext4_update_sb_callback(struct ext4_super_block *es,
const void *arg);
/*
* Superblock modification callback function for changing file system
* label
*/
static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg)
{
/* Sanity check, this should never happen */
BUILD_BUG_ON(sizeof(es->s_volume_name) < EXT4_LABEL_MAX);
memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX);
}
static
int ext4_update_primary_sb(struct super_block *sb, handle_t *handle,
ext4_update_sb_callback func,
const void *arg)
{
int err = 0;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct buffer_head *bh = sbi->s_sbh;
struct ext4_super_block *es = sbi->s_es;
trace_ext4_update_sb(sb, bh->b_blocknr, 1);
BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, sb,
bh,
EXT4_JTR_NONE);
if (err)
goto out_err;
lock_buffer(bh);
func(es, arg);
ext4_superblock_csum_set(sb);
unlock_buffer(bh);
if (buffer_write_io_error(bh) || !buffer_uptodate(bh)) {
ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
}
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out_err;
err = sync_dirty_buffer(bh);
out_err:
ext4_std_error(sb, err);
return err;
}
/*
* Update one backup superblock in the group 'grp' using the callback
* function 'func' and argument 'arg'. If the handle is NULL the
* modification is not journalled.
*
* Returns: 0 when no modification was done (no superblock in the group)
* 1 when the modification was successful
* <0 on error
*/
static int ext4_update_backup_sb(struct super_block *sb,
handle_t *handle, ext4_group_t grp,
ext4_update_sb_callback func, const void *arg)
{
int err = 0;
ext4_fsblk_t sb_block;
struct buffer_head *bh;
unsigned long offset = 0;
struct ext4_super_block *es;
if (!ext4_bg_has_super(sb, grp))
return 0;
/*
* For the group 0 there is always 1k padding, so we have
* either adjust offset, or sb_block depending on blocksize
*/
if (grp == 0) {
sb_block = 1 * EXT4_MIN_BLOCK_SIZE;
offset = do_div(sb_block, sb->s_blocksize);
} else {
sb_block = ext4_group_first_block_no(sb, grp);
offset = 0;
}
trace_ext4_update_sb(sb, sb_block, handle ? 1 : 0);
bh = ext4_sb_bread(sb, sb_block, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
if (handle) {
BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, sb,
bh,
EXT4_JTR_NONE);
if (err)
goto out_bh;
}
es = (struct ext4_super_block *) (bh->b_data + offset);
lock_buffer(bh);
if (ext4_has_metadata_csum(sb) &&
es->s_checksum != ext4_superblock_csum(sb, es)) {
ext4_msg(sb, KERN_ERR, "Invalid checksum for backup "
"superblock %llu\n", sb_block);
unlock_buffer(bh);
err = -EFSBADCRC;
goto out_bh;
}
func(es, arg);
if (ext4_has_metadata_csum(sb))
es->s_checksum = ext4_superblock_csum(sb, es);
set_buffer_uptodate(bh);
unlock_buffer(bh);
if (err)
goto out_bh;
if (handle) {
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out_bh;
} else {
BUFFER_TRACE(bh, "marking dirty");
mark_buffer_dirty(bh);
}
err = sync_dirty_buffer(bh);
out_bh:
brelse(bh);
ext4_std_error(sb, err);
return (err) ? err : 1;
}
/*
* Update primary and backup superblocks using the provided function
* func and argument arg.
*
* Only the primary superblock and at most two backup superblock
* modifications are journalled; the rest is modified without journal.
* This is safe because e2fsck will re-write them if there is a problem,
* and we're very unlikely to ever need more than two backups.
*/
static
int ext4_update_superblocks_fn(struct super_block *sb,
ext4_update_sb_callback func,
const void *arg)
{
handle_t *handle;
ext4_group_t ngroups;
unsigned int three = 1;
unsigned int five = 5;
unsigned int seven = 7;
int err = 0, ret, i;
ext4_group_t grp, primary_grp;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
* We can't update superblocks while the online resize is running
*/
if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
&sbi->s_ext4_flags)) {
ext4_msg(sb, KERN_ERR, "Can't modify superblock while"
"performing online resize");
return -EBUSY;
}
/*
* We're only going to update primary superblock and two
* backup superblocks in this transaction.
*/
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out;
}
/* Update primary superblock */
err = ext4_update_primary_sb(sb, handle, func, arg);
if (err) {
ext4_msg(sb, KERN_ERR, "Failed to update primary "
"superblock");
goto out_journal;
}
primary_grp = ext4_get_group_number(sb, sbi->s_sbh->b_blocknr);
ngroups = ext4_get_groups_count(sb);
/*
* Update backup superblocks. We have to start from group 0
* because it might not be where the primary superblock is
* if the fs is mounted with -o sb=<backup_sb_block>
*/
i = 0;
grp = 0;
while (grp < ngroups) {
/* Skip primary superblock */
if (grp == primary_grp)
goto next_grp;
ret = ext4_update_backup_sb(sb, handle, grp, func, arg);
if (ret < 0) {
/* Ignore bad checksum; try to update next sb */
if (ret == -EFSBADCRC)
goto next_grp;
err = ret;
goto out_journal;
}
i += ret;
if (handle && i > 1) {
/*
* We're only journalling primary superblock and
* two backup superblocks; the rest is not
* journalled.
*/
err = ext4_journal_stop(handle);
if (err)
goto out;
handle = NULL;
}
next_grp:
grp = ext4_list_backups(sb, &three, &five, &seven);
}
out_journal:
if (handle) {
ret = ext4_journal_stop(handle);
if (ret && !err)
err = ret;
}
out:
clear_bit_unlock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags);
smp_mb__after_atomic();
return err ? err : 0;
}
/**
* Swap memory between @a and @b for @len bytes.
*
* @a: pointer to first memory area
* @b: pointer to second memory area
* @len: number of bytes to swap
*
*/
static void memswap(void *a, void *b, size_t len)
{
unsigned char *ap, *bp;
ap = (unsigned char *)a;
bp = (unsigned char *)b;
while (len-- > 0) {
swap(*ap, *bp);
ap++;
bp++;
}
}
/**
* Swap i_data and associated attributes between @inode1 and @inode2.
* This function is used for the primary swap between inode1 and inode2
* and also to revert this primary swap in case of errors.
*
* Therefore you have to make sure, that calling this method twice
* will revert all changes.
*
* @inode1: pointer to first inode
* @inode2: pointer to second inode
*/
static void swap_inode_data(struct inode *inode1, struct inode *inode2)
{
loff_t isize;
struct ext4_inode_info *ei1;
struct ext4_inode_info *ei2;
unsigned long tmp;
ei1 = EXT4_I(inode1);
ei2 = EXT4_I(inode2);
swap(inode1->i_version, inode2->i_version);
swap(inode1->i_atime, inode2->i_atime);
swap(inode1->i_mtime, inode2->i_mtime);
memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP;
ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) |
(ei1->i_flags & ~EXT4_FL_SHOULD_SWAP);
ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP);
swap(ei1->i_disksize, ei2->i_disksize);
ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
isize = i_size_read(inode1);
i_size_write(inode1, i_size_read(inode2));
i_size_write(inode2, isize);
}
void ext4_reset_inode_seed(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__le32 inum = cpu_to_le32(inode->i_ino);
__le32 gen = cpu_to_le32(inode->i_generation);
__u32 csum;
if (!ext4_has_metadata_csum(inode->i_sb))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum));
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen));
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct user_namespace *mnt_userns,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
qsize_t size, size_bl, diff;
blkcnt_t blocks;
unsigned short bytes;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
if (IS_ERR(inode_bl))
return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
(EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) ||
ext4_has_inline_data(inode)) {
err = -EINVAL;
goto journal_err_out;
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
!inode_owner_or_capable(mnt_userns, inode) ||
!capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
}
filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto err_out;
err = filemap_write_and_wait(inode_bl->i_mapping);
if (err)
goto err_out;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto err_out;
}
ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
err = dquot_initialize(inode);
if (err)
goto err_out1;
size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
diff = size - size_bl;
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
inode_bl->i_generation = prandom_u32();
ext4_reset_inode_seed(inode);
ext4_reset_inode_seed(inode_bl);
ext4_discard_preallocations(inode, 0);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
goto err_out1;
}
blocks = inode_bl->i_blocks;
bytes = inode_bl->i_bytes;
inode_bl->i_blocks = inode->i_blocks;
inode_bl->i_bytes = inode->i_bytes;
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
goto revert;
}
/* Bootloader inode should not be counted into quota information. */
if (diff > 0)
dquot_free_space(inode, diff);
else
err = dquot_alloc_space(inode, -1 * diff);
if (err < 0) {
revert:
/* Revert all changes: */
inode_bl->i_blocks = blocks;
inode_bl->i_bytes = bytes;
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
ext4_mark_inode_dirty(handle, inode_bl);
}
err_out1:
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
err_out:
filemap_invalidate_unlock(inode->i_mapping);
journal_err_out:
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
return err;
}
#ifdef CONFIG_FS_ENCRYPTION
static int uuid_is_zero(__u8 u[16])
{
int i;
for (i = 0; i < 16; i++)
if (u[i])
return 0;
return 1;
}
#endif
/*
* If immutable is set and we are not clearing it, we're not allowed to change
* anything else in the inode. Don't error out if we're only trying to set
* immutable on an immutable file.
*/
static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid,
unsigned int flags)
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int oldflags = ei->i_flags;
if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL))
return 0;
if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL))
return -EPERM;
if (ext4_has_feature_project(inode->i_sb) &&
__kprojid_val(ei->i_projid) != new_projid)
return -EPERM;
return 0;
}
static void ext4_dax_dontcache(struct inode *inode, unsigned int flags)
{
struct ext4_inode_info *ei = EXT4_I(inode);
if (S_ISDIR(inode->i_mode))
return;
if (test_opt2(inode->i_sb, DAX_NEVER) ||
test_opt(inode->i_sb, DAX_ALWAYS))
return;
if ((ei->i_flags ^ flags) & EXT4_DAX_FL)
d_mark_dontcache(inode);
}
static bool dax_compatible(struct inode *inode, unsigned int oldflags,
unsigned int flags)
{
/* Allow the DAX flag to be changed on inline directories */
if (S_ISDIR(inode->i_mode)) {
flags &= ~EXT4_INLINE_DATA_FL;
oldflags &= ~EXT4_INLINE_DATA_FL;
}
if (flags & EXT4_DAX_FL) {
if ((oldflags & EXT4_DAX_MUT_EXCL) ||
ext4_test_inode_state(inode,
EXT4_STATE_VERITY_IN_PROGRESS)) {
return false;
}
}
if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL))
return false;
return true;
}
static int ext4_ioctl_setflags(struct inode *inode,
unsigned int flags)
{
struct ext4_inode_info *ei = EXT4_I(inode);
handle_t *handle = NULL;
int err = -EPERM, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
struct super_block *sb = inode->i_sb;
/* Is it quota file? Do not allow user to mess with it */
if (ext4_is_quota_file(inode))
goto flags_out;
oldflags = ei->i_flags;
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if (!dax_compatible(inode, oldflags, flags)) {
err = -EOPNOTSUPP;
goto flags_out;
}
if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) {
if (!ext4_has_feature_casefold(sb)) {
err = -EOPNOTSUPP;
goto flags_out;
}
if (!S_ISDIR(inode->i_mode)) {
err = -ENOTDIR;
goto flags_out;
}
if (!ext4_empty_dir(inode)) {
err = -ENOTEMPTY;
goto flags_out;
}
}
/*
* Wait for all pending directio and then flush all the dirty pages
* for this file. The flush marks all the pages readonly, so any
* subsequent attempt to write to the file (particularly mmap pages)
* will come through the filesystem and fail.
*/
if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) &&
(flags & EXT4_IMMUTABLE_FL)) {
inode_dio_wait(inode);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto flags_out;
}
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
ext4_dax_dontcache(inode, flags);
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
/* These flags get special treatment later */
if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL)
continue;
if (mask & flags)
ext4_set_inode_flag(inode, i);
else
ext4_clear_inode_flag(inode, i);
}
ext4_set_inode_flags(inode, false);
inode->i_ctime = current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
/*
* Changes to the journaling mode can cause unsafe changes to
* S_DAX if the inode is DAX
*/
if (IS_DAX(inode)) {
err = -EBUSY;
goto flags_out;
}
err = ext4_change_inode_journal_flag(inode,
flags & EXT4_JOURNAL_DATA_FL);
if (err)
goto flags_out;
}
if (migrate) {
if (flags & EXT4_EXTENTS_FL)
err = ext4_ext_migrate(inode);
else
err = ext4_ind_migrate(inode);
}
flags_out:
return err;
}
#ifdef CONFIG_QUOTA
static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
{
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
int err, rc;
handle_t *handle;
kprojid_t kprojid;
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct dquot *transfer_to[MAXQUOTAS] = { };
if (!ext4_has_feature_project(sb)) {
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
else
return 0;
}
if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE)
return -EOPNOTSUPP;
kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
if (projid_eq(kprojid, EXT4_I(inode)->i_projid))
return 0;
err = -EPERM;
/* Is it quota file? Do not allow user to mess with it */
if (ext4_is_quota_file(inode))
return err;
err = ext4_get_inode_loc(inode, &iloc);
if (err)
return err;
raw_inode = ext4_raw_inode(&iloc);
if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
err = ext4_expand_extra_isize(inode,
EXT4_SB(sb)->s_want_extra_isize,
&iloc);
if (err)
return err;
} else {
brelse(iloc.bh);
}
err = dquot_initialize(inode);
if (err)
return err;
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(sb) +
EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
if (IS_ERR(handle))
return PTR_ERR(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_stop;
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
/* __dquot_transfer() calls back ext4_get_inode_usage() which
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
err = __dquot_transfer(inode, transfer_to);
up_read(&EXT4_I(inode)->xattr_sem);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
}
EXT4_I(inode)->i_projid = kprojid;
inode->i_ctime = current_time(inode);
out_dirty:
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
out_stop:
ext4_journal_stop(handle);
return err;
}
#else
static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
{
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
return 0;
}
#endif
static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
__u32 flags;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(flags, (__u32 __user *)arg))
return -EFAULT;
if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
return -EINVAL;
if (ext4_forced_shutdown(sbi))
return 0;
ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
trace_ext4_shutdown(sb, flags);
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
freeze_bdev(sb->s_bdev);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
thaw_bdev(sb->s_bdev);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
(void) ext4_force_commit(sb);
jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN);
}
break;
case EXT4_GOING_FLAGS_NOLOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal))
jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN);
break;
default:
return -EINVAL;
}
clear_opt(sb, DISCARD);
return 0;
}
struct getfsmap_info {
struct super_block *gi_sb;
struct fsmap_head __user *gi_data;
unsigned int gi_idx;
__u32 gi_last_flags;
};
static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv)
{
struct getfsmap_info *info = priv;
struct fsmap fm;
trace_ext4_getfsmap_mapping(info->gi_sb, xfm);
info->gi_last_flags = xfm->fmr_flags;
ext4_fsmap_from_internal(info->gi_sb, &fm, xfm);
if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm,
sizeof(struct fsmap)))
return -EFAULT;
return 0;
}
static int ext4_ioc_getfsmap(struct super_block *sb,
struct fsmap_head __user *arg)
{
struct getfsmap_info info = { NULL };
struct ext4_fsmap_head xhead = {0};
struct fsmap_head head;
bool aborted = false;
int error;
if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
return -EFAULT;
if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
sizeof(head.fmh_keys[0].fmr_reserved)) ||
memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
sizeof(head.fmh_keys[1].fmr_reserved)))
return -EINVAL;
/*
* ext4 doesn't report file extents at all, so the only valid
* file offsets are the magic ones (all zeroes or all ones).
*/
if (head.fmh_keys[0].fmr_offset ||
(head.fmh_keys[1].fmr_offset != 0 &&
head.fmh_keys[1].fmr_offset != -1ULL))
return -EINVAL;
xhead.fmh_iflags = head.fmh_iflags;
xhead.fmh_count = head.fmh_count;
ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]);
ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]);
trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]);
trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]);
info.gi_sb = sb;
info.gi_data = arg;
error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info);
if (error == EXT4_QUERY_RANGE_ABORT)
aborted = true;
else if (error)
return error;
/* If we didn't abort, set the "last" flag in the last fmx */
if (!aborted && info.gi_idx) {
info.gi_last_flags |= FMR_OF_LAST;
if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags,
&info.gi_last_flags,
sizeof(info.gi_last_flags)))
return -EFAULT;
}
/* copy back header */
head.fmh_entries = xhead.fmh_entries;
head.fmh_oflags = xhead.fmh_oflags;
if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
return -EFAULT;
return 0;
}
static long ext4_ioctl_group_add(struct file *file,
struct ext4_new_group_data *input)
{
struct super_block *sb = file_inode(file)->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(file);
if (err)
goto group_add_out;
err = ext4_group_add(sb, input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(file);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input->group);
group_add_out:
ext4_resize_end(sb);
return err;
}
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
struct ext4_inode_info *ei = EXT4_I(inode);
u32 flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
if (S_ISREG(inode->i_mode))
flags &= ~FS_PROJINHERIT_FL;
fileattr_fill_flags(fa, flags);
if (ext4_has_feature_project(inode->i_sb))
fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid);
return 0;
}
int ext4_fileattr_set(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
u32 flags = fa->flags;
int err = -EOPNOTSUPP;
if (flags & ~EXT4_FL_USER_VISIBLE)
goto out;
/*
* chattr(1) grabs flags via GETFLAGS, modifies the result and
* passes that to SETFLAGS. So we cannot easily make SETFLAGS
* more restrictive than just silently masking off visible but
* not settable flags as we always did.
*/
flags &= EXT4_FL_USER_MODIFIABLE;
if (ext4_mask_flags(inode->i_mode, flags) != flags)
goto out;
err = ext4_ioctl_check_immutable(inode, fa->fsx_projid, flags);
if (err)