forked from analogdevicesinc/linux
-
Notifications
You must be signed in to change notification settings - Fork 3
/
ops_fstype.c
1297 lines (1100 loc) · 31.6 KB
/
ops_fstype.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/blkdev.h>
#include <linux/kthread.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "mount.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "sys.h"
#include "util.h"
#include "log.h"
#include "quota.h"
#include "dir.h"
#define DO 0
#define UNDO 1
static const u32 gfs2_old_fs_formats[] = {
0
};
static const u32 gfs2_old_multihost_formats[] = {
0
};
/**
* gfs2_tune_init - Fill a gfs2_tune structure with default values
* @gt: tune
*
*/
static void gfs2_tune_init(struct gfs2_tune *gt)
{
spin_lock_init(>->gt_spin);
gt->gt_incore_log_blocks = 1024;
gt->gt_log_flush_secs = 60;
gt->gt_recoverd_secs = 60;
gt->gt_logd_secs = 1;
gt->gt_quota_simul_sync = 64;
gt->gt_quota_warn_period = 10;
gt->gt_quota_scale_num = 1;
gt->gt_quota_scale_den = 1;
gt->gt_quota_cache_secs = 300;
gt->gt_quota_quantum = 60;
gt->gt_new_files_jdata = 0;
gt->gt_max_readahead = 1 << 18;
gt->gt_stall_secs = 600;
gt->gt_complain_secs = 10;
gt->gt_statfs_quantum = 30;
gt->gt_statfs_slow = 0;
}
static struct gfs2_sbd *init_sbd(struct super_block *sb)
{
struct gfs2_sbd *sdp;
sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
if (!sdp)
return NULL;
sb->s_fs_info = sdp;
sdp->sd_vfs = sb;
gfs2_tune_init(&sdp->sd_tune);
mutex_init(&sdp->sd_inum_mutex);
spin_lock_init(&sdp->sd_statfs_spin);
spin_lock_init(&sdp->sd_rindex_spin);
mutex_init(&sdp->sd_rindex_mutex);
INIT_LIST_HEAD(&sdp->sd_rindex_list);
INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
INIT_LIST_HEAD(&sdp->sd_jindex_list);
spin_lock_init(&sdp->sd_jindex_spin);
mutex_init(&sdp->sd_jindex_mutex);
INIT_LIST_HEAD(&sdp->sd_quota_list);
spin_lock_init(&sdp->sd_quota_spin);
mutex_init(&sdp->sd_quota_mutex);
init_waitqueue_head(&sdp->sd_quota_wait);
INIT_LIST_HEAD(&sdp->sd_trunc_list);
spin_lock_init(&sdp->sd_trunc_lock);
spin_lock_init(&sdp->sd_log_lock);
INIT_LIST_HEAD(&sdp->sd_log_le_buf);
INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
INIT_LIST_HEAD(&sdp->sd_log_le_rg);
INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
mutex_init(&sdp->sd_log_reserve_mutex);
INIT_LIST_HEAD(&sdp->sd_ail1_list);
INIT_LIST_HEAD(&sdp->sd_ail2_list);
init_rwsem(&sdp->sd_log_flush_lock);
atomic_set(&sdp->sd_log_in_flight, 0);
init_waitqueue_head(&sdp->sd_log_flush_wait);
INIT_LIST_HEAD(&sdp->sd_revoke_list);
mutex_init(&sdp->sd_freeze_lock);
return sdp;
}
/**
* gfs2_check_sb - Check superblock
* @sdp: the filesystem
* @sb: The superblock
* @silent: Don't print a message if the check fails
*
* Checks the version code of the FS is one that we understand how to
* read and that the sizes of the various on-disk structures have not
* changed.
*/
static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
{
unsigned int x;
if (sb->sb_magic != GFS2_MAGIC ||
sb->sb_type != GFS2_METATYPE_SB) {
if (!silent)
printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
return -EINVAL;
}
/* If format numbers match exactly, we're done. */
if (sb->sb_fs_format == GFS2_FORMAT_FS &&
sb->sb_multihost_format == GFS2_FORMAT_MULTI)
return 0;
if (sb->sb_fs_format != GFS2_FORMAT_FS) {
for (x = 0; gfs2_old_fs_formats[x]; x++)
if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
break;
if (!gfs2_old_fs_formats[x]) {
printk(KERN_WARNING
"GFS2: code version (%u, %u) is incompatible "
"with ondisk format (%u, %u)\n",
GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
sb->sb_fs_format, sb->sb_multihost_format);
printk(KERN_WARNING
"GFS2: I don't know how to upgrade this FS\n");
return -EINVAL;
}
}
if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
for (x = 0; gfs2_old_multihost_formats[x]; x++)
if (gfs2_old_multihost_formats[x] ==
sb->sb_multihost_format)
break;
if (!gfs2_old_multihost_formats[x]) {
printk(KERN_WARNING
"GFS2: code version (%u, %u) is incompatible "
"with ondisk format (%u, %u)\n",
GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
sb->sb_fs_format, sb->sb_multihost_format);
printk(KERN_WARNING
"GFS2: I don't know how to upgrade this FS\n");
return -EINVAL;
}
}
if (!sdp->sd_args.ar_upgrade) {
printk(KERN_WARNING
"GFS2: code version (%u, %u) is incompatible "
"with ondisk format (%u, %u)\n",
GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
sb->sb_fs_format, sb->sb_multihost_format);
printk(KERN_INFO
"GFS2: Use the \"upgrade\" mount option to upgrade "
"the FS\n");
printk(KERN_INFO "GFS2: See the manual for more details\n");
return -EINVAL;
}
return 0;
}
static void end_bio_io_page(struct bio *bio, int error)
{
struct page *page = bio->bi_private;
if (!error)
SetPageUptodate(page);
else
printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
unlock_page(page);
}
static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
{
const struct gfs2_sb *str = buf;
sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
sb->sb_bsize = be32_to_cpu(str->sb_bsize);
sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
}
/**
* gfs2_read_super - Read the gfs2 super block from disk
* @sdp: The GFS2 super block
* @sector: The location of the super block
* @error: The error code to return
*
* This uses the bio functions to read the super block from disk
* because we want to be 100% sure that we never read cached data.
* A super block is read twice only during each GFS2 mount and is
* never written to by the filesystem. The first time its read no
* locks are held, and the only details which are looked at are those
* relating to the locking protocol. Once locking is up and working,
* the sb is read again under the lock to establish the location of
* the master directory (contains pointers to journals etc) and the
* root directory.
*
* Returns: 0 on success or error
*/
static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_sb *p;
struct page *page;
struct bio *bio;
page = alloc_page(GFP_NOFS);
if (unlikely(!page))
return -ENOBUFS;
ClearPageUptodate(page);
ClearPageDirty(page);
lock_page(page);
bio = bio_alloc(GFP_NOFS, 1);
if (unlikely(!bio)) {
__free_page(page);
return -ENOBUFS;
}
bio->bi_sector = sector * (sb->s_blocksize >> 9);
bio->bi_bdev = sb->s_bdev;
bio_add_page(bio, page, PAGE_SIZE, 0);
bio->bi_end_io = end_bio_io_page;
bio->bi_private = page;
submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
wait_on_page_locked(page);
bio_put(bio);
if (!PageUptodate(page)) {
__free_page(page);
return -EIO;
}
p = kmap(page);
gfs2_sb_in(&sdp->sd_sb, p);
kunmap(page);
__free_page(page);
return 0;
}
/**
* gfs2_read_sb - Read super block
* @sdp: The GFS2 superblock
* @gl: the glock for the superblock (assumed to be held)
* @silent: Don't print message if mount fails
*
*/
static int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
{
u32 hash_blocks, ind_blocks, leaf_blocks;
u32 tmp_blocks;
unsigned int x;
int error;
error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
if (error) {
if (!silent)
fs_err(sdp, "can't read superblock\n");
return error;
}
error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
if (error)
return error;
sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
GFS2_BASIC_BLOCK_SHIFT;
sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_dinode)) / sizeof(u64);
sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_meta_header)) / sizeof(u64);
sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_meta_header)) /
sizeof(struct gfs2_quota_change);
/* Compute maximum reservation required to add a entry to a directory */
hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
sdp->sd_jbsize);
ind_blocks = 0;
for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
ind_blocks += tmp_blocks;
}
leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_dinode);
sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
for (x = 2;; x++) {
u64 space, d;
u32 m;
space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
d = space;
m = do_div(d, sdp->sd_inptrs);
if (d != sdp->sd_heightsize[x - 1] || m)
break;
sdp->sd_heightsize[x] = space;
}
sdp->sd_max_height = x;
sdp->sd_heightsize[x] = ~0;
gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_dinode);
sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
for (x = 2;; x++) {
u64 space, d;
u32 m;
space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
d = space;
m = do_div(d, sdp->sd_inptrs);
if (d != sdp->sd_jheightsize[x - 1] || m)
break;
sdp->sd_jheightsize[x] = space;
}
sdp->sd_max_jheight = x;
sdp->sd_jheightsize[x] = ~0;
gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
return 0;
}
static int init_names(struct gfs2_sbd *sdp, int silent)
{
char *proto, *table;
int error = 0;
proto = sdp->sd_args.ar_lockproto;
table = sdp->sd_args.ar_locktable;
/* Try to autodetect */
if (!proto[0] || !table[0]) {
error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
if (error)
return error;
error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
if (error)
goto out;
if (!proto[0])
proto = sdp->sd_sb.sb_lockproto;
if (!table[0])
table = sdp->sd_sb.sb_locktable;
}
if (!table[0])
table = sdp->sd_vfs->s_id;
strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN);
strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN);
table = sdp->sd_table_name;
while ((table = strchr(table, '/')))
*table = '_';
out:
return error;
}
static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
int undo)
{
int error = 0;
if (undo)
goto fail_trans;
error = gfs2_glock_nq_num(sdp,
GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
mount_gh);
if (error) {
fs_err(sdp, "can't acquire mount glock: %d\n", error);
goto fail;
}
error = gfs2_glock_nq_num(sdp,
GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
LM_ST_SHARED,
LM_FLAG_NOEXP | GL_EXACT,
&sdp->sd_live_gh);
if (error) {
fs_err(sdp, "can't acquire live glock: %d\n", error);
goto fail_mount;
}
error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
CREATE, &sdp->sd_rename_gl);
if (error) {
fs_err(sdp, "can't create rename glock: %d\n", error);
goto fail_live;
}
error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
CREATE, &sdp->sd_trans_gl);
if (error) {
fs_err(sdp, "can't create transaction glock: %d\n", error);
goto fail_rename;
}
return 0;
fail_trans:
gfs2_glock_put(sdp->sd_trans_gl);
fail_rename:
gfs2_glock_put(sdp->sd_rename_gl);
fail_live:
gfs2_glock_dq_uninit(&sdp->sd_live_gh);
fail_mount:
gfs2_glock_dq_uninit(mount_gh);
fail:
return error;
}
static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
u64 no_addr, const char *name)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct dentry *dentry;
struct inode *inode;
inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
if (IS_ERR(inode)) {
fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
return PTR_ERR(inode);
}
dentry = d_alloc_root(inode);
if (!dentry) {
fs_err(sdp, "can't alloc %s dentry\n", name);
iput(inode);
return -ENOMEM;
}
dentry->d_op = &gfs2_dops;
*dptr = dentry;
return 0;
}
static int init_sb(struct gfs2_sbd *sdp, int silent)
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_holder sb_gh;
u64 no_addr;
int ret;
ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
LM_ST_SHARED, 0, &sb_gh);
if (ret) {
fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
return ret;
}
ret = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
if (ret) {
fs_err(sdp, "can't read superblock: %d\n", ret);
goto out;
}
/* Set up the buffer cache and SB for real */
if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
ret = -EINVAL;
fs_err(sdp, "FS block size (%u) is too small for device "
"block size (%u)\n",
sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
goto out;
}
if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
ret = -EINVAL;
fs_err(sdp, "FS block size (%u) is too big for machine "
"page size (%u)\n",
sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
goto out;
}
sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);
/* Get the root inode */
no_addr = sdp->sd_sb.sb_root_dir.no_addr;
ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
if (ret)
goto out;
/* Get the master inode */
no_addr = sdp->sd_sb.sb_master_dir.no_addr;
ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
if (ret) {
dput(sdp->sd_root_dir);
goto out;
}
sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
out:
gfs2_glock_dq_uninit(&sb_gh);
return ret;
}
/**
* map_journal_extents - create a reusable "extent" mapping from all logical
* blocks to all physical blocks for the given journal. This will save
* us time when writing journal blocks. Most journals will have only one
* extent that maps all their logical blocks. That's because gfs2.mkfs
* arranges the journal blocks sequentially to maximize performance.
* So the extent would map the first block for the entire file length.
* However, gfs2_jadd can happen while file activity is happening, so
* those journals may not be sequential. Less likely is the case where
* the users created their own journals by mounting the metafs and
* laying it out. But it's still possible. These journals might have
* several extents.
*
* TODO: This should be done in bigger chunks rather than one block at a time,
* but since it's only done at mount time, I'm not worried about the
* time it takes.
*/
static int map_journal_extents(struct gfs2_sbd *sdp)
{
struct gfs2_jdesc *jd = sdp->sd_jdesc;
unsigned int lb;
u64 db, prev_db; /* logical block, disk block, prev disk block */
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_journal_extent *jext = NULL;
struct buffer_head bh;
int rc = 0;
prev_db = 0;
for (lb = 0; lb < ip->i_disksize >> sdp->sd_sb.sb_bsize_shift; lb++) {
bh.b_state = 0;
bh.b_blocknr = 0;
bh.b_size = 1 << ip->i_inode.i_blkbits;
rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
db = bh.b_blocknr;
if (rc || !db) {
printk(KERN_INFO "GFS2 journal mapping error %d: lb="
"%u db=%llu\n", rc, lb, (unsigned long long)db);
break;
}
if (!prev_db || db != prev_db + 1) {
jext = kzalloc(sizeof(struct gfs2_journal_extent),
GFP_KERNEL);
if (!jext) {
printk(KERN_INFO "GFS2 error: out of memory "
"mapping journal extents.\n");
rc = -ENOMEM;
break;
}
jext->dblock = db;
jext->lblock = lb;
jext->blocks = 1;
list_add_tail(&jext->extent_list, &jd->extent_list);
} else {
jext->blocks++;
}
prev_db = db;
}
return rc;
}
static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
{
if (!sdp->sd_lockstruct.ls_ops->lm_others_may_mount)
return;
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
sdp->sd_lockstruct.ls_ops->lm_others_may_mount(
sdp->sd_lockstruct.ls_lockspace);
}
/**
* gfs2_jindex_hold - Grab a lock on the jindex
* @sdp: The GFS2 superblock
* @ji_gh: the holder for the jindex glock
*
* Returns: errno
*/
static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
{
struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
struct qstr name;
char buf[20];
struct gfs2_jdesc *jd;
int error;
name.name = buf;
mutex_lock(&sdp->sd_jindex_mutex);
for (;;) {
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
if (error)
break;
name.len = sprintf(buf, "journal%u", sdp->sd_journals);
name.hash = gfs2_disk_hash(name.name, name.len);
error = gfs2_dir_check(sdp->sd_jindex, &name, NULL);
if (error == -ENOENT) {
error = 0;
break;
}
gfs2_glock_dq_uninit(ji_gh);
if (error)
break;
error = -ENOMEM;
jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
if (!jd)
break;
INIT_LIST_HEAD(&jd->extent_list);
jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
if (!jd->jd_inode)
error = -ENOENT;
else
error = PTR_ERR(jd->jd_inode);
kfree(jd);
break;
}
spin_lock(&sdp->sd_jindex_spin);
jd->jd_jid = sdp->sd_journals++;
list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
spin_unlock(&sdp->sd_jindex_spin);
}
mutex_unlock(&sdp->sd_jindex_mutex);
return error;
}
static int init_journal(struct gfs2_sbd *sdp, int undo)
{
struct inode *master = sdp->sd_master_dir->d_inode;
struct gfs2_holder ji_gh;
struct task_struct *p;
struct gfs2_inode *ip;
int jindex = 1;
int error = 0;
if (undo) {
jindex = 0;
goto fail_recoverd;
}
sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
if (IS_ERR(sdp->sd_jindex)) {
fs_err(sdp, "can't lookup journal index: %d\n", error);
return PTR_ERR(sdp->sd_jindex);
}
ip = GFS2_I(sdp->sd_jindex);
/* Load in the journal index special file */
error = gfs2_jindex_hold(sdp, &ji_gh);
if (error) {
fs_err(sdp, "can't read journal index: %d\n", error);
goto fail;
}
error = -EINVAL;
if (!gfs2_jindex_size(sdp)) {
fs_err(sdp, "no journals!\n");
goto fail_jindex;
}
if (sdp->sd_args.ar_spectator) {
sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
} else {
if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
fs_err(sdp, "can't mount journal #%u\n",
sdp->sd_lockstruct.ls_jid);
fs_err(sdp, "there are only %u journals (0 - %u)\n",
gfs2_jindex_size(sdp),
gfs2_jindex_size(sdp) - 1);
goto fail_jindex;
}
sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);
error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
&gfs2_journal_glops,
LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
&sdp->sd_journal_gh);
if (error) {
fs_err(sdp, "can't acquire journal glock: %d\n", error);
goto fail_jindex;
}
ip = GFS2_I(sdp->sd_jdesc->jd_inode);
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
&sdp->sd_jinode_gh);
if (error) {
fs_err(sdp, "can't acquire journal inode glock: %d\n",
error);
goto fail_journal_gh;
}
error = gfs2_jdesc_check(sdp->sd_jdesc);
if (error) {
fs_err(sdp, "my journal (%u) is bad: %d\n",
sdp->sd_jdesc->jd_jid, error);
goto fail_jinode_gh;
}
atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
/* Map the extents for this journal's blocks */
map_journal_extents(sdp);
}
if (sdp->sd_lockstruct.ls_first) {
unsigned int x;
for (x = 0; x < sdp->sd_journals; x++) {
error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
if (error) {
fs_err(sdp, "error recovering journal %u: %d\n",
x, error);
goto fail_jinode_gh;
}
}
gfs2_lm_others_may_mount(sdp);
} else if (!sdp->sd_args.ar_spectator) {
error = gfs2_recover_journal(sdp->sd_jdesc);
if (error) {
fs_err(sdp, "error recovering my journal: %d\n", error);
goto fail_jinode_gh;
}
}
set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
gfs2_glock_dq_uninit(&ji_gh);
jindex = 0;
p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
error = IS_ERR(p);
if (error) {
fs_err(sdp, "can't start recoverd thread: %d\n", error);
goto fail_jinode_gh;
}
sdp->sd_recoverd_process = p;
return 0;
fail_recoverd:
kthread_stop(sdp->sd_recoverd_process);
fail_jinode_gh:
if (!sdp->sd_args.ar_spectator)
gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
fail_journal_gh:
if (!sdp->sd_args.ar_spectator)
gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
fail_jindex:
gfs2_jindex_free(sdp);
if (jindex)
gfs2_glock_dq_uninit(&ji_gh);
fail:
iput(sdp->sd_jindex);
return error;
}
static int init_inodes(struct gfs2_sbd *sdp, int undo)
{
int error = 0;
struct gfs2_inode *ip;
struct inode *master = sdp->sd_master_dir->d_inode;
if (undo)
goto fail_qinode;
error = init_journal(sdp, undo);
if (error)
goto fail;
/* Read in the master inode number inode */
sdp->sd_inum_inode = gfs2_lookup_simple(master, "inum");
if (IS_ERR(sdp->sd_inum_inode)) {
error = PTR_ERR(sdp->sd_inum_inode);
fs_err(sdp, "can't read in inum inode: %d\n", error);
goto fail_journal;
}
/* Read in the master statfs inode */
sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
if (IS_ERR(sdp->sd_statfs_inode)) {
error = PTR_ERR(sdp->sd_statfs_inode);
fs_err(sdp, "can't read in statfs inode: %d\n", error);
goto fail_inum;
}
/* Read in the resource index inode */
sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
if (IS_ERR(sdp->sd_rindex)) {
error = PTR_ERR(sdp->sd_rindex);
fs_err(sdp, "can't get resource index inode: %d\n", error);
goto fail_statfs;
}
ip = GFS2_I(sdp->sd_rindex);
sdp->sd_rindex_uptodate = 0;
/* Read in the quota inode */
sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
if (IS_ERR(sdp->sd_quota_inode)) {
error = PTR_ERR(sdp->sd_quota_inode);
fs_err(sdp, "can't get quota file inode: %d\n", error);
goto fail_rindex;
}
return 0;
fail_qinode:
iput(sdp->sd_quota_inode);
fail_rindex:
gfs2_clear_rgrpd(sdp);
iput(sdp->sd_rindex);
fail_statfs:
iput(sdp->sd_statfs_inode);
fail_inum:
iput(sdp->sd_inum_inode);
fail_journal:
init_journal(sdp, UNDO);
fail:
return error;
}
static int init_per_node(struct gfs2_sbd *sdp, int undo)
{
struct inode *pn = NULL;
char buf[30];
int error = 0;
struct gfs2_inode *ip;
struct inode *master = sdp->sd_master_dir->d_inode;
if (sdp->sd_args.ar_spectator)
return 0;
if (undo)
goto fail_qc_gh;
pn = gfs2_lookup_simple(master, "per_node");
if (IS_ERR(pn)) {
error = PTR_ERR(pn);
fs_err(sdp, "can't find per_node directory: %d\n", error);
return error;
}
sprintf(buf, "inum_range%u", sdp->sd_jdesc->jd_jid);
sdp->sd_ir_inode = gfs2_lookup_simple(pn, buf);
if (IS_ERR(sdp->sd_ir_inode)) {
error = PTR_ERR(sdp->sd_ir_inode);
fs_err(sdp, "can't find local \"ir\" file: %d\n", error);
goto fail;
}
sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
if (IS_ERR(sdp->sd_sc_inode)) {
error = PTR_ERR(sdp->sd_sc_inode);
fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
goto fail_ir_i;
}
sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
sdp->sd_qc_inode = gfs2_lookup_simple(pn, buf);
if (IS_ERR(sdp->sd_qc_inode)) {
error = PTR_ERR(sdp->sd_qc_inode);
fs_err(sdp, "can't find local \"qc\" file: %d\n", error);
goto fail_ut_i;
}
iput(pn);
pn = NULL;
ip = GFS2_I(sdp->sd_ir_inode);
error = gfs2_glock_nq_init(ip->i_gl,
LM_ST_EXCLUSIVE, 0,
&sdp->sd_ir_gh);
if (error) {
fs_err(sdp, "can't lock local \"ir\" file: %d\n", error);
goto fail_qc_i;
}
ip = GFS2_I(sdp->sd_sc_inode);
error = gfs2_glock_nq_init(ip->i_gl,
LM_ST_EXCLUSIVE, 0,
&sdp->sd_sc_gh);
if (error) {
fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
goto fail_ir_gh;
}
ip = GFS2_I(sdp->sd_qc_inode);
error = gfs2_glock_nq_init(ip->i_gl,
LM_ST_EXCLUSIVE, 0,
&sdp->sd_qc_gh);
if (error) {
fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
goto fail_ut_gh;
}
return 0;
fail_qc_gh:
gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
fail_ut_gh:
gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
fail_ir_gh:
gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
fail_qc_i:
iput(sdp->sd_qc_inode);
fail_ut_i:
iput(sdp->sd_sc_inode);
fail_ir_i:
iput(sdp->sd_ir_inode);
fail:
if (pn)
iput(pn);
return error;
}
static int init_threads(struct gfs2_sbd *sdp, int undo)
{