forked from Sricharanti/sricharan
-
Notifications
You must be signed in to change notification settings - Fork 0
/
inode.c
1444 lines (1202 loc) · 33.9 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
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2008 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/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/posix_acl.h>
#include <linux/sort.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/lm_interface.h>
#include <linux/security.h>
#include "gfs2.h"
#include "incore.h"
#include "acl.h"
#include "bmap.h"
#include "dir.h"
#include "eattr.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "ops_address.h"
#include "ops_inode.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
struct gfs2_inum_range_host {
u64 ir_start;
u64 ir_length;
};
static int iget_test(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
u64 *no_addr = opaque;
if (ip->i_no_addr == *no_addr && test_bit(GIF_USER, &ip->i_flags))
return 1;
return 0;
}
static int iget_set(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
u64 *no_addr = opaque;
inode->i_ino = (unsigned long)*no_addr;
ip->i_no_addr = *no_addr;
set_bit(GIF_USER, &ip->i_flags);
return 0;
}
struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
{
unsigned long hash = (unsigned long)no_addr;
return ilookup5(sb, hash, iget_test, &no_addr);
}
static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
{
unsigned long hash = (unsigned long)no_addr;
return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
}
struct gfs2_skip_data {
u64 no_addr;
int skipped;
};
static int iget_skip_test(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_skip_data *data = opaque;
if (ip->i_no_addr == data->no_addr && test_bit(GIF_USER, &ip->i_flags)){
if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){
data->skipped = 1;
return 0;
}
return 1;
}
return 0;
}
static int iget_skip_set(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_skip_data *data = opaque;
if (data->skipped)
return 1;
inode->i_ino = (unsigned long)(data->no_addr);
ip->i_no_addr = data->no_addr;
set_bit(GIF_USER, &ip->i_flags);
return 0;
}
static struct inode *gfs2_iget_skip(struct super_block *sb,
u64 no_addr)
{
struct gfs2_skip_data data;
unsigned long hash = (unsigned long)no_addr;
data.no_addr = no_addr;
data.skipped = 0;
return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data);
}
/**
* GFS2 lookup code fills in vfs inode contents based on info obtained
* from directory entry inside gfs2_inode_lookup(). This has caused issues
* with NFS code path since its get_dentry routine doesn't have the relevant
* directory entry when gfs2_inode_lookup() is invoked. Part of the code
* segment inside gfs2_inode_lookup code needs to get moved around.
*
* Clean up I_LOCK and I_NEW as well.
**/
void gfs2_set_iop(struct inode *inode)
{
struct gfs2_sbd *sdp = GFS2_SB(inode);
umode_t mode = inode->i_mode;
if (S_ISREG(mode)) {
inode->i_op = &gfs2_file_iops;
if (sdp->sd_args.ar_localflocks)
inode->i_fop = &gfs2_file_fops_nolock;
else
inode->i_fop = &gfs2_file_fops;
} else if (S_ISDIR(mode)) {
inode->i_op = &gfs2_dir_iops;
if (sdp->sd_args.ar_localflocks)
inode->i_fop = &gfs2_dir_fops_nolock;
else
inode->i_fop = &gfs2_dir_fops;
} else if (S_ISLNK(mode)) {
inode->i_op = &gfs2_symlink_iops;
} else {
inode->i_op = &gfs2_file_iops;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
}
unlock_new_inode(inode);
}
/**
* gfs2_inode_lookup - Lookup an inode
* @sb: The super block
* @no_addr: The inode number
* @type: The type of the inode
* @skip_freeing: set this not return an inode if it is currently being freed.
*
* Returns: A VFS inode, or an error
*/
struct inode *gfs2_inode_lookup(struct super_block *sb,
unsigned int type,
u64 no_addr,
u64 no_formal_ino, int skip_freeing)
{
struct inode *inode;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl;
int error;
if (skip_freeing)
inode = gfs2_iget_skip(sb, no_addr);
else
inode = gfs2_iget(sb, no_addr);
ip = GFS2_I(inode);
if (!inode)
return ERR_PTR(-ENOBUFS);
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
ip->i_no_formal_ino = no_formal_ino;
error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (unlikely(error))
goto fail;
ip->i_gl->gl_object = ip;
error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (unlikely(error))
goto fail_put;
set_bit(GIF_INVALID, &ip->i_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail_iopen;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
goto gfs2_nfsbypass;
inode->i_mode = DT2IF(type);
/*
* We must read the inode in order to work out its type in
* this case. Note that this doesn't happen often as we normally
* know the type beforehand. This code path only occurs during
* unlinked inode recovery (where it is safe to do this glock,
* which is not true in the general case).
*/
if (type == DT_UNKNOWN) {
struct gfs2_holder gh;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (unlikely(error))
goto fail_glock;
/* Inode is now uptodate */
gfs2_glock_dq_uninit(&gh);
}
gfs2_set_iop(inode);
}
gfs2_nfsbypass:
return inode;
fail_glock:
gfs2_glock_dq(&ip->i_iopen_gh);
fail_iopen:
gfs2_glock_put(io_gl);
fail_put:
ip->i_gl->gl_object = NULL;
gfs2_glock_put(ip->i_gl);
fail:
iget_failed(inode);
return ERR_PTR(error);
}
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
struct gfs2_dinode_host *di = &ip->i_di;
const struct gfs2_dinode *str = buf;
u16 height, depth;
if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
goto corrupt;
ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
ip->i_inode.i_rdev = 0;
switch (ip->i_inode.i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
be32_to_cpu(str->di_minor));
break;
};
ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
/*
* We will need to review setting the nlink count here in the
* light of the forthcoming ro bind mount work. This is a reminder
* to do that.
*/
ip->i_inode.i_nlink = be32_to_cpu(str->di_nlink);
di->di_size = be64_to_cpu(str->di_size);
i_size_write(&ip->i_inode, di->di_size);
gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime);
ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
ip->i_goal = be64_to_cpu(str->di_goal_meta);
di->di_generation = be64_to_cpu(str->di_generation);
di->di_flags = be32_to_cpu(str->di_flags);
gfs2_set_inode_flags(&ip->i_inode);
height = be16_to_cpu(str->di_height);
if (unlikely(height > GFS2_MAX_META_HEIGHT))
goto corrupt;
ip->i_height = (u8)height;
depth = be16_to_cpu(str->di_depth);
if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
goto corrupt;
ip->i_depth = (u8)depth;
di->di_entries = be32_to_cpu(str->di_entries);
di->di_eattr = be64_to_cpu(str->di_eattr);
if (S_ISREG(ip->i_inode.i_mode))
gfs2_set_aops(&ip->i_inode);
return 0;
corrupt:
if (gfs2_consist_inode(ip))
gfs2_dinode_print(ip);
return -EIO;
}
/**
* gfs2_inode_refresh - Refresh the incore copy of the dinode
* @ip: The GFS2 inode
*
* Returns: errno
*/
int gfs2_inode_refresh(struct gfs2_inode *ip)
{
struct buffer_head *dibh;
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
return error;
if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
brelse(dibh);
return -EIO;
}
error = gfs2_dinode_in(ip, dibh->b_data);
brelse(dibh);
clear_bit(GIF_INVALID, &ip->i_flags);
return error;
}
int gfs2_dinode_dealloc(struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_alloc *al;
struct gfs2_rgrpd *rgd;
int error;
if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
if (gfs2_consist_inode(ip))
gfs2_dinode_print(ip);
return -EIO;
}
al = gfs2_alloc_get(ip);
if (!al)
return -ENOMEM;
error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
if (error)
goto out;
error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
if (error)
goto out_qs;
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
if (!rgd) {
gfs2_consist_inode(ip);
error = -EIO;
goto out_rindex_relse;
}
error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
&al->al_rgd_gh);
if (error)
goto out_rindex_relse;
error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 1);
if (error)
goto out_rg_gunlock;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GLF_LFLUSH, &ip->i_gl->gl_flags);
gfs2_free_di(rgd, ip);
gfs2_trans_end(sdp);
clear_bit(GLF_STICKY, &ip->i_gl->gl_flags);
out_rg_gunlock:
gfs2_glock_dq_uninit(&al->al_rgd_gh);
out_rindex_relse:
gfs2_glock_dq_uninit(&al->al_ri_gh);
out_qs:
gfs2_quota_unhold(ip);
out:
gfs2_alloc_put(ip);
return error;
}
/**
* gfs2_change_nlink - Change nlink count on inode
* @ip: The GFS2 inode
* @diff: The change in the nlink count required
*
* Returns: errno
*/
int gfs2_change_nlink(struct gfs2_inode *ip, int diff)
{
struct buffer_head *dibh;
u32 nlink;
int error;
BUG_ON(diff != 1 && diff != -1);
nlink = ip->i_inode.i_nlink + diff;
/* If we are reducing the nlink count, but the new value ends up being
bigger than the old one, we must have underflowed. */
if (diff < 0 && nlink > ip->i_inode.i_nlink) {
if (gfs2_consist_inode(ip))
gfs2_dinode_print(ip);
return -EIO;
}
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
return error;
if (diff > 0)
inc_nlink(&ip->i_inode);
else
drop_nlink(&ip->i_inode);
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
mark_inode_dirty(&ip->i_inode);
if (ip->i_inode.i_nlink == 0)
gfs2_unlink_di(&ip->i_inode); /* mark inode unlinked */
return error;
}
struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
{
struct qstr qstr;
struct inode *inode;
gfs2_str2qstr(&qstr, name);
inode = gfs2_lookupi(dip, &qstr, 1);
/* gfs2_lookupi has inconsistent callers: vfs
* related routines expect NULL for no entry found,
* gfs2_lookup_simple callers expect ENOENT
* and do not check for NULL.
*/
if (inode == NULL)
return ERR_PTR(-ENOENT);
else
return inode;
}
/**
* gfs2_lookupi - Look up a filename in a directory and return its inode
* @d_gh: An initialized holder for the directory glock
* @name: The name of the inode to look for
* @is_root: If 1, ignore the caller's permissions
* @i_gh: An uninitialized holder for the new inode glock
*
* This can be called via the VFS filldir function when NFS is doing
* a readdirplus and the inode which its intending to stat isn't
* already in cache. In this case we must not take the directory glock
* again, since the readdir call will have already taken that lock.
*
* Returns: errno
*/
struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
int is_root)
{
struct super_block *sb = dir->i_sb;
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_holder d_gh;
int error = 0;
struct inode *inode = NULL;
int unlock = 0;
if (!name->len || name->len > GFS2_FNAMESIZE)
return ERR_PTR(-ENAMETOOLONG);
if ((name->len == 1 && memcmp(name->name, ".", 1) == 0) ||
(name->len == 2 && memcmp(name->name, "..", 2) == 0 &&
dir == sb->s_root->d_inode)) {
igrab(dir);
return dir;
}
if (gfs2_glock_is_locked_by_me(dip->i_gl) == NULL) {
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
return ERR_PTR(error);
unlock = 1;
}
if (!is_root) {
error = gfs2_permission(dir, MAY_EXEC);
if (error)
goto out;
}
inode = gfs2_dir_search(dir, name);
if (IS_ERR(inode))
error = PTR_ERR(inode);
out:
if (unlock)
gfs2_glock_dq_uninit(&d_gh);
if (error == -ENOENT)
return NULL;
return inode ? inode : ERR_PTR(error);
}
static void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf)
{
const struct gfs2_inum_range *str = buf;
ir->ir_start = be64_to_cpu(str->ir_start);
ir->ir_length = be64_to_cpu(str->ir_length);
}
static void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf)
{
struct gfs2_inum_range *str = buf;
str->ir_start = cpu_to_be64(ir->ir_start);
str->ir_length = cpu_to_be64(ir->ir_length);
}
static int pick_formal_ino_1(struct gfs2_sbd *sdp, u64 *formal_ino)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_ir_inode);
struct buffer_head *bh;
struct gfs2_inum_range_host ir;
int error;
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (error)
return error;
mutex_lock(&sdp->sd_inum_mutex);
error = gfs2_meta_inode_buffer(ip, &bh);
if (error) {
mutex_unlock(&sdp->sd_inum_mutex);
gfs2_trans_end(sdp);
return error;
}
gfs2_inum_range_in(&ir, bh->b_data + sizeof(struct gfs2_dinode));
if (ir.ir_length) {
*formal_ino = ir.ir_start++;
ir.ir_length--;
gfs2_trans_add_bh(ip->i_gl, bh, 1);
gfs2_inum_range_out(&ir,
bh->b_data + sizeof(struct gfs2_dinode));
brelse(bh);
mutex_unlock(&sdp->sd_inum_mutex);
gfs2_trans_end(sdp);
return 0;
}
brelse(bh);
mutex_unlock(&sdp->sd_inum_mutex);
gfs2_trans_end(sdp);
return 1;
}
static int pick_formal_ino_2(struct gfs2_sbd *sdp, u64 *formal_ino)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_ir_inode);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_inum_inode);
struct gfs2_holder gh;
struct buffer_head *bh;
struct gfs2_inum_range_host ir;
int error;
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (error)
return error;
error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
if (error)
goto out;
mutex_lock(&sdp->sd_inum_mutex);
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
goto out_end_trans;
gfs2_inum_range_in(&ir, bh->b_data + sizeof(struct gfs2_dinode));
if (!ir.ir_length) {
struct buffer_head *m_bh;
u64 x, y;
__be64 z;
error = gfs2_meta_inode_buffer(m_ip, &m_bh);
if (error)
goto out_brelse;
z = *(__be64 *)(m_bh->b_data + sizeof(struct gfs2_dinode));
x = y = be64_to_cpu(z);
ir.ir_start = x;
ir.ir_length = GFS2_INUM_QUANTUM;
x += GFS2_INUM_QUANTUM;
if (x < y)
gfs2_consist_inode(m_ip);
z = cpu_to_be64(x);
gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
*(__be64 *)(m_bh->b_data + sizeof(struct gfs2_dinode)) = z;
brelse(m_bh);
}
*formal_ino = ir.ir_start++;
ir.ir_length--;
gfs2_trans_add_bh(ip->i_gl, bh, 1);
gfs2_inum_range_out(&ir, bh->b_data + sizeof(struct gfs2_dinode));
out_brelse:
brelse(bh);
out_end_trans:
mutex_unlock(&sdp->sd_inum_mutex);
gfs2_trans_end(sdp);
out:
gfs2_glock_dq_uninit(&gh);
return error;
}
static int pick_formal_ino(struct gfs2_sbd *sdp, u64 *inum)
{
int error;
error = pick_formal_ino_1(sdp, inum);
if (error <= 0)
return error;
error = pick_formal_ino_2(sdp, inum);
return error;
}
/**
* create_ok - OK to create a new on-disk inode here?
* @dip: Directory in which dinode is to be created
* @name: Name of new dinode
* @mode:
*
* Returns: errno
*/
static int create_ok(struct gfs2_inode *dip, const struct qstr *name,
unsigned int mode)
{
int error;
error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
/* Don't create entries in an unlinked directory */
if (!dip->i_inode.i_nlink)
return -EPERM;
error = gfs2_dir_check(&dip->i_inode, name, NULL);
switch (error) {
case -ENOENT:
error = 0;
break;
case 0:
return -EEXIST;
default:
return error;
}
if (dip->i_di.di_entries == (u32)-1)
return -EFBIG;
if (S_ISDIR(mode) && dip->i_inode.i_nlink == (u32)-1)
return -EMLINK;
return 0;
}
static void munge_mode_uid_gid(struct gfs2_inode *dip, unsigned int *mode,
unsigned int *uid, unsigned int *gid)
{
if (GFS2_SB(&dip->i_inode)->sd_args.ar_suiddir &&
(dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) {
if (S_ISDIR(*mode))
*mode |= S_ISUID;
else if (dip->i_inode.i_uid != current->fsuid)
*mode &= ~07111;
*uid = dip->i_inode.i_uid;
} else
*uid = current->fsuid;
if (dip->i_inode.i_mode & S_ISGID) {
if (S_ISDIR(*mode))
*mode |= S_ISGID;
*gid = dip->i_inode.i_gid;
} else
*gid = current->fsgid;
}
static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
int error;
if (gfs2_alloc_get(dip) == NULL)
return -ENOMEM;
dip->i_alloc->al_requested = RES_DINODE;
error = gfs2_inplace_reserve(dip);
if (error)
goto out;
error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS, 0);
if (error)
goto out_ipreserv;
*no_addr = gfs2_alloc_di(dip, generation);
gfs2_trans_end(sdp);
out_ipreserv:
gfs2_inplace_release(dip);
out:
gfs2_alloc_put(dip);
return error;
}
/**
* init_dinode - Fill in a new dinode structure
* @dip: the directory this inode is being created in
* @gl: The glock covering the new inode
* @inum: the inode number
* @mode: the file permissions
* @uid:
* @gid:
*
*/
static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
const struct gfs2_inum_host *inum, unsigned int mode,
unsigned int uid, unsigned int gid,
const u64 *generation, dev_t dev, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_dinode *di;
struct buffer_head *dibh;
struct timespec tv = CURRENT_TIME;
dibh = gfs2_meta_new(gl, inum->no_addr);
gfs2_trans_add_bh(gl, dibh, 1);
gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
di = (struct gfs2_dinode *)dibh->b_data;
di->di_num.no_formal_ino = cpu_to_be64(inum->no_formal_ino);
di->di_num.no_addr = cpu_to_be64(inum->no_addr);
di->di_mode = cpu_to_be32(mode);
di->di_uid = cpu_to_be32(uid);
di->di_gid = cpu_to_be32(gid);
di->di_nlink = 0;
di->di_size = 0;
di->di_blocks = cpu_to_be64(1);
di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
di->di_major = cpu_to_be32(MAJOR(dev));
di->di_minor = cpu_to_be32(MINOR(dev));
di->di_goal_meta = di->di_goal_data = cpu_to_be64(inum->no_addr);
di->di_generation = cpu_to_be64(*generation);
di->di_flags = 0;
if (S_ISREG(mode)) {
if ((dip->i_di.di_flags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
} else if (S_ISDIR(mode)) {
di->di_flags |= cpu_to_be32(dip->i_di.di_flags &
GFS2_DIF_INHERIT_JDATA);
}
di->__pad1 = 0;
di->di_payload_format = cpu_to_be32(S_ISDIR(mode) ? GFS2_FORMAT_DE : 0);
di->di_height = 0;
di->__pad2 = 0;
di->__pad3 = 0;
di->di_depth = 0;
di->di_entries = 0;
memset(&di->__pad4, 0, sizeof(di->__pad4));
di->di_eattr = 0;
di->di_atime_nsec = cpu_to_be32(tv.tv_nsec);
di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
memset(&di->di_reserved, 0, sizeof(di->di_reserved));
set_buffer_uptodate(dibh);
*bhp = dibh;
}
static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
unsigned int mode, const struct gfs2_inum_host *inum,
const u64 *generation, dev_t dev, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
unsigned int uid, gid;
int error;
munge_mode_uid_gid(dip, &mode, &uid, &gid);
if (!gfs2_alloc_get(dip))
return -ENOMEM;
error = gfs2_quota_lock(dip, uid, gid);
if (error)
goto out;
error = gfs2_quota_check(dip, uid, gid);
if (error)
goto out_quota;
error = gfs2_trans_begin(sdp, RES_DINODE + RES_QUOTA, 0);
if (error)
goto out_quota;
init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp);
gfs2_quota_change(dip, +1, uid, gid);
gfs2_trans_end(sdp);
out_quota:
gfs2_quota_unlock(dip);
out:
gfs2_alloc_put(dip);
return error;
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc *al;
int alloc_required;
struct buffer_head *dibh;
int error;
al = gfs2_alloc_get(dip);
if (!al)
return -ENOMEM;
error = gfs2_quota_lock(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
if (error)
goto fail;
error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
if (alloc_required < 0)
goto fail_quota_locks;
if (alloc_required) {
error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
if (error)
goto fail_quota_locks;
al->al_requested = sdp->sd_max_dirres;
error = gfs2_inplace_reserve(dip);
if (error)
goto fail_quota_locks;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
al->al_rgd->rd_length +
2 * RES_DINODE +
RES_STATFS + RES_QUOTA, 0);
if (error)
goto fail_ipreserv;
} else {
error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
if (error)
goto fail_quota_locks;
}
error = gfs2_dir_add(&dip->i_inode, name, ip, IF2DT(ip->i_inode.i_mode));
if (error)
goto fail_end_trans;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto fail_end_trans;
ip->i_inode.i_nlink = 1;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
return 0;
fail_end_trans:
gfs2_trans_end(sdp);
fail_ipreserv:
if (dip->i_alloc->al_rgd)
gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
fail:
gfs2_alloc_put(dip);
return error;
}
static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
{
int err;
size_t len;
void *value;
char *name;
struct gfs2_ea_request er;
err = security_inode_init_security(&ip->i_inode, &dip->i_inode,
&name, &value, &len);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
memset(&er, 0, sizeof(struct gfs2_ea_request));
er.er_type = GFS2_EATYPE_SECURITY;
er.er_name = name;
er.er_data = value;
er.er_name_len = strlen(name);
er.er_data_len = len;
err = gfs2_ea_set_i(ip, &er);
kfree(value);
kfree(name);
return err;
}
/**
* gfs2_createi - Create a new inode
* @ghs: An array of two holders
* @name: The name of the new file
* @mode: the permissions on the new inode
*
* @ghs[0] is an initialized holder for the directory
* @ghs[1] is the holder for the inode lock
*
* If the return value is not NULL, the glocks on both the directory and the new
* file are held. A transaction has been started and an inplace reservation
* is held, as well.
*
* Returns: An inode
*/
struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
unsigned int mode, dev_t dev)
{
struct inode *inode = NULL;
struct gfs2_inode *dip = ghs->gh_gl->gl_object;
struct inode *dir = &dip->i_inode;
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
int error;
u64 generation;
struct buffer_head *bh = NULL;
if (!name->len || name->len > GFS2_FNAMESIZE)
return ERR_PTR(-ENAMETOOLONG);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, ghs);
error = gfs2_glock_nq(ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
if (error)
goto fail_gunlock;
error = pick_formal_ino(sdp, &inum.no_formal_ino);
if (error)
goto fail_gunlock;
error = alloc_dinode(dip, &inum.no_addr, &generation);
if (error)