forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsuper.c
1630 lines (1395 loc) · 40.4 KB
/
super.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) 2004-2007 Red Hat, Inc. All rights reserved.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/bio.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/time.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/kernel.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "util.h"
#include "sys.h"
#include "xattr.h"
#include "lops.h"
enum dinode_demise {
SHOULD_DELETE_DINODE,
SHOULD_NOT_DELETE_DINODE,
SHOULD_DEFER_EVICTION,
};
/**
* gfs2_jindex_free - Clear all the journal index information
* @sdp: The GFS2 superblock
*
*/
void gfs2_jindex_free(struct gfs2_sbd *sdp)
{
struct list_head list;
struct gfs2_jdesc *jd;
spin_lock(&sdp->sd_jindex_spin);
list_add(&list, &sdp->sd_jindex_list);
list_del_init(&sdp->sd_jindex_list);
sdp->sd_journals = 0;
spin_unlock(&sdp->sd_jindex_spin);
sdp->sd_jdesc = NULL;
while (!list_empty(&list)) {
jd = list_first_entry(&list, struct gfs2_jdesc, jd_list);
gfs2_free_journal_extents(jd);
list_del(&jd->jd_list);
iput(jd->jd_inode);
jd->jd_inode = NULL;
kfree(jd);
}
}
static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
{
struct gfs2_jdesc *jd;
list_for_each_entry(jd, head, jd_list) {
if (jd->jd_jid == jid)
return jd;
}
return NULL;
}
struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
{
struct gfs2_jdesc *jd;
spin_lock(&sdp->sd_jindex_spin);
jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
spin_unlock(&sdp->sd_jindex_spin);
return jd;
}
int gfs2_jdesc_check(struct gfs2_jdesc *jd)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
u64 size = i_size_read(jd->jd_inode);
if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, BIT(30)))
return -EIO;
jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
if (gfs2_write_alloc_required(ip, 0, size)) {
gfs2_consist_inode(ip);
return -EIO;
}
return 0;
}
/**
* gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
* @sdp: the filesystem
*
* Returns: errno
*/
int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
struct gfs2_glock *j_gl = ip->i_gl;
struct gfs2_log_header_host head;
int error;
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
if (gfs2_withdrawn(sdp))
return -EIO;
error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
if (error) {
gfs2_consist(sdp);
return error;
}
if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
gfs2_consist(sdp);
return -EIO;
}
/* Initialize some head of the log stuff */
sdp->sd_log_sequence = head.lh_sequence + 1;
gfs2_log_pointers_init(sdp, head.lh_blkno);
error = gfs2_quota_init(sdp);
if (!error && gfs2_withdrawn(sdp))
error = -EIO;
if (!error)
set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
return error;
}
void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
{
const struct gfs2_statfs_change *str = buf;
sc->sc_total = be64_to_cpu(str->sc_total);
sc->sc_free = be64_to_cpu(str->sc_free);
sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
}
void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
{
struct gfs2_statfs_change *str = buf;
str->sc_total = cpu_to_be64(sc->sc_total);
str->sc_free = cpu_to_be64(sc->sc_free);
str->sc_dinodes = cpu_to_be64(sc->sc_dinodes);
}
int gfs2_statfs_init(struct gfs2_sbd *sdp)
{
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct buffer_head *m_bh;
struct gfs2_holder gh;
int error;
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
&gh);
if (error)
return error;
error = gfs2_meta_inode_buffer(m_ip, &m_bh);
if (error)
goto out;
if (sdp->sd_args.ar_spectator) {
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
spin_unlock(&sdp->sd_statfs_spin);
} else {
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
gfs2_statfs_change_in(l_sc, sdp->sd_sc_bh->b_data +
sizeof(struct gfs2_dinode));
spin_unlock(&sdp->sd_statfs_spin);
}
brelse(m_bh);
out:
gfs2_glock_dq_uninit(&gh);
return 0;
}
void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
s64 dinodes)
{
struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
s64 x, y;
int need_sync = 0;
gfs2_trans_add_meta(l_ip->i_gl, sdp->sd_sc_bh);
spin_lock(&sdp->sd_statfs_spin);
l_sc->sc_total += total;
l_sc->sc_free += free;
l_sc->sc_dinodes += dinodes;
gfs2_statfs_change_out(l_sc, sdp->sd_sc_bh->b_data +
sizeof(struct gfs2_dinode));
if (sdp->sd_args.ar_statfs_percent) {
x = 100 * l_sc->sc_free;
y = m_sc->sc_free * sdp->sd_args.ar_statfs_percent;
if (x >= y || x <= -y)
need_sync = 1;
}
spin_unlock(&sdp->sd_statfs_spin);
if (need_sync)
gfs2_wake_up_statfs(sdp);
}
void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh)
{
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
gfs2_trans_add_meta(l_ip->i_gl, sdp->sd_sc_bh);
gfs2_trans_add_meta(m_ip->i_gl, m_bh);
spin_lock(&sdp->sd_statfs_spin);
m_sc->sc_total += l_sc->sc_total;
m_sc->sc_free += l_sc->sc_free;
m_sc->sc_dinodes += l_sc->sc_dinodes;
memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
memset(sdp->sd_sc_bh->b_data + sizeof(struct gfs2_dinode),
0, sizeof(struct gfs2_statfs_change));
gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
spin_unlock(&sdp->sd_statfs_spin);
}
int gfs2_statfs_sync(struct super_block *sb, int type)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct gfs2_holder gh;
struct buffer_head *m_bh;
int error;
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
&gh);
if (error)
goto out;
error = gfs2_meta_inode_buffer(m_ip, &m_bh);
if (error)
goto out_unlock;
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
if (!l_sc->sc_total && !l_sc->sc_free && !l_sc->sc_dinodes) {
spin_unlock(&sdp->sd_statfs_spin);
goto out_bh;
}
spin_unlock(&sdp->sd_statfs_spin);
error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
if (error)
goto out_bh;
update_statfs(sdp, m_bh);
sdp->sd_statfs_force_sync = 0;
gfs2_trans_end(sdp);
out_bh:
brelse(m_bh);
out_unlock:
gfs2_glock_dq_uninit(&gh);
out:
return error;
}
struct lfcc {
struct list_head list;
struct gfs2_holder gh;
};
/**
* gfs2_lock_fs_check_clean - Stop all writes to the FS and check that all
* journals are clean
* @sdp: the file system
*
* Returns: errno
*/
static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
struct gfs2_jdesc *jd;
struct lfcc *lfcc;
LIST_HEAD(list);
struct gfs2_log_header_host lh;
int error, error2;
/*
* Grab all the journal glocks in SH mode. We are *probably* doing
* that to prevent recovery.
*/
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
if (!lfcc) {
error = -ENOMEM;
goto out;
}
ip = GFS2_I(jd->jd_inode);
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &lfcc->gh);
if (error) {
kfree(lfcc);
goto out;
}
list_add(&lfcc->list, &list);
}
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
LM_FLAG_NOEXP | GL_NOPID,
&sdp->sd_freeze_gh);
if (error)
goto relock_shared;
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
error = gfs2_jdesc_check(jd);
if (error)
break;
error = gfs2_find_jhead(jd, &lh, false);
if (error)
break;
if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
error = -EBUSY;
break;
}
}
if (!error)
goto out; /* success */
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
relock_shared:
error2 = gfs2_freeze_lock_shared(sdp);
gfs2_assert_withdraw(sdp, !error2);
out:
while (!list_empty(&list)) {
lfcc = list_first_entry(&list, struct lfcc, list);
list_del(&lfcc->list);
gfs2_glock_dq_uninit(&lfcc->gh);
kfree(lfcc);
}
return error;
}
void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
{
const struct inode *inode = &ip->i_inode;
struct gfs2_dinode *str = buf;
str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
str->di_mode = cpu_to_be32(inode->i_mode);
str->di_uid = cpu_to_be32(i_uid_read(inode));
str->di_gid = cpu_to_be32(i_gid_read(inode));
str->di_nlink = cpu_to_be32(inode->i_nlink);
str->di_size = cpu_to_be64(i_size_read(inode));
str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(inode));
str->di_atime = cpu_to_be64(inode->i_atime.tv_sec);
str->di_mtime = cpu_to_be64(inode->i_mtime.tv_sec);
str->di_ctime = cpu_to_be64(inode->i_ctime.tv_sec);
str->di_goal_meta = cpu_to_be64(ip->i_goal);
str->di_goal_data = cpu_to_be64(ip->i_goal);
str->di_generation = cpu_to_be64(ip->i_generation);
str->di_flags = cpu_to_be32(ip->i_diskflags);
str->di_height = cpu_to_be16(ip->i_height);
str->di_payload_format = cpu_to_be32(S_ISDIR(inode->i_mode) &&
!(ip->i_diskflags & GFS2_DIF_EXHASH) ?
GFS2_FORMAT_DE : 0);
str->di_depth = cpu_to_be16(ip->i_depth);
str->di_entries = cpu_to_be32(ip->i_entries);
str->di_eattr = cpu_to_be64(ip->i_eattr);
str->di_atime_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
str->di_mtime_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
str->di_ctime_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
}
/**
* gfs2_write_inode - Make sure the inode is stable on the disk
* @inode: The inode
* @wbc: The writeback control structure
*
* Returns: errno
*/
static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
int ret = 0;
bool flush_all = (wbc->sync_mode == WB_SYNC_ALL || gfs2_is_jdata(ip));
if (flush_all)
gfs2_log_flush(GFS2_SB(inode), ip->i_gl,
GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_WRITE_INODE);
if (bdi->wb.dirty_exceeded)
gfs2_ail1_flush(sdp, wbc);
else
filemap_fdatawrite(metamapping);
if (flush_all)
ret = filemap_fdatawait(metamapping);
if (ret)
mark_inode_dirty_sync(inode);
else {
spin_lock(&inode->i_lock);
if (!(inode->i_flags & I_DIRTY))
gfs2_ordered_del_inode(ip);
spin_unlock(&inode->i_lock);
}
return ret;
}
/**
* gfs2_dirty_inode - check for atime updates
* @inode: The inode in question
* @flags: The type of dirty
*
* Unfortunately it can be called under any combination of inode
* glock and freeze glock, so we have to check carefully.
*
* At the moment this deals only with atime - it should be possible
* to expand that role in future, once a review of the locking has
* been carried out.
*/
static void gfs2_dirty_inode(struct inode *inode, int flags)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_holder gh;
int need_unlock = 0;
int need_endtrans = 0;
int ret;
if (unlikely(!ip->i_gl)) {
/* This can only happen during incomplete inode creation. */
BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
return;
}
if (unlikely(gfs2_withdrawn(sdp)))
return;
if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (ret) {
fs_err(sdp, "dirty_inode: glock %d\n", ret);
gfs2_dump_glock(NULL, ip->i_gl, true);
return;
}
need_unlock = 1;
} else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE))
return;
if (current->journal_info == NULL) {
ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (ret) {
fs_err(sdp, "dirty_inode: gfs2_trans_begin %d\n", ret);
goto out;
}
need_endtrans = 1;
}
ret = gfs2_meta_inode_buffer(ip, &bh);
if (ret == 0) {
gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
}
if (need_endtrans)
gfs2_trans_end(sdp);
out:
if (need_unlock)
gfs2_glock_dq_uninit(&gh);
}
/**
* gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
* @sdp: the filesystem
*
* Returns: errno
*/
void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
{
int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
if (!test_bit(SDF_DEACTIVATING, &sdp->sd_flags))
gfs2_flush_delete_work(sdp);
if (!log_write_allowed && current == sdp->sd_quotad_process)
fs_warn(sdp, "The quotad daemon is withdrawing.\n");
else if (sdp->sd_quotad_process)
kthread_stop(sdp->sd_quotad_process);
sdp->sd_quotad_process = NULL;
if (!log_write_allowed && current == sdp->sd_logd_process)
fs_warn(sdp, "The logd daemon is withdrawing.\n");
else if (sdp->sd_logd_process)
kthread_stop(sdp->sd_logd_process);
sdp->sd_logd_process = NULL;
if (log_write_allowed) {
gfs2_quota_sync(sdp->sd_vfs, 0);
gfs2_statfs_sync(sdp->sd_vfs, 0);
/* We do two log flushes here. The first one commits dirty inodes
* and rgrps to the journal, but queues up revokes to the ail list.
* The second flush writes out and removes the revokes.
*
* The first must be done before the FLUSH_SHUTDOWN code
* clears the LIVE flag, otherwise it will not be able to start
* a transaction to write its revokes, and the error will cause
* a withdraw of the file system. */
gfs2_log_flush(sdp, NULL, GFS2_LFC_MAKE_FS_RO);
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
GFS2_LFC_MAKE_FS_RO);
wait_event_timeout(sdp->sd_log_waitq,
gfs2_log_is_empty(sdp),
HZ * 5);
gfs2_assert_warn(sdp, gfs2_log_is_empty(sdp));
} else {
wait_event_timeout(sdp->sd_log_waitq,
gfs2_log_is_empty(sdp),
HZ * 5);
}
gfs2_quota_cleanup(sdp);
if (!log_write_allowed)
sdp->sd_vfs->s_flags |= SB_RDONLY;
}
/**
* gfs2_put_super - Unmount the filesystem
* @sb: The VFS superblock
*
*/
static void gfs2_put_super(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_jdesc *jd;
/* No more recovery requests */
set_bit(SDF_NORECOVERY, &sdp->sd_flags);
smp_mb();
/* Wait on outstanding recovery */
restart:
spin_lock(&sdp->sd_jindex_spin);
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
continue;
spin_unlock(&sdp->sd_jindex_spin);
wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
TASK_UNINTERRUPTIBLE);
goto restart;
}
spin_unlock(&sdp->sd_jindex_spin);
if (!sb_rdonly(sb)) {
gfs2_make_fs_ro(sdp);
}
WARN_ON(gfs2_withdrawing(sdp));
/* At this point, we're through modifying the disk */
/* Release stuff */
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
iput(sdp->sd_jindex);
iput(sdp->sd_statfs_inode);
iput(sdp->sd_rindex);
iput(sdp->sd_quota_inode);
gfs2_glock_put(sdp->sd_rename_gl);
gfs2_glock_put(sdp->sd_freeze_gl);
if (!sdp->sd_args.ar_spectator) {
if (gfs2_holder_initialized(&sdp->sd_journal_gh))
gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
if (gfs2_holder_initialized(&sdp->sd_jinode_gh))
gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
brelse(sdp->sd_sc_bh);
gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
free_local_statfs_inodes(sdp);
iput(sdp->sd_qc_inode);
}
gfs2_glock_dq_uninit(&sdp->sd_live_gh);
gfs2_clear_rgrpd(sdp);
gfs2_jindex_free(sdp);
/* Take apart glock structures and buffer lists */
gfs2_gl_hash_clear(sdp);
truncate_inode_pages_final(&sdp->sd_aspace);
gfs2_delete_debugfs_file(sdp);
/* Unmount the locking protocol */
gfs2_lm_unmount(sdp);
/* At this point, we're through participating in the lockspace */
gfs2_sys_fs_del(sdp);
free_sbd(sdp);
}
/**
* gfs2_sync_fs - sync the filesystem
* @sb: the superblock
* @wait: true to wait for completion
*
* Flushes the log to disk.
*/
static int gfs2_sync_fs(struct super_block *sb, int wait)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
gfs2_quota_sync(sb, -1);
if (wait)
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_SYNC_FS);
return sdp->sd_log_error;
}
static int gfs2_freeze_locally(struct gfs2_sbd *sdp)
{
struct super_block *sb = sdp->sd_vfs;
int error;
error = freeze_super(sb);
if (error)
return error;
if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
GFS2_LFC_FREEZE_GO_SYNC);
if (gfs2_withdrawn(sdp)) {
thaw_super(sb);
return -EIO;
}
}
return 0;
}
static int gfs2_do_thaw(struct gfs2_sbd *sdp)
{
struct super_block *sb = sdp->sd_vfs;
int error;
error = gfs2_freeze_lock_shared(sdp);
if (error)
goto fail;
error = thaw_super(sb);
if (!error)
return 0;
fail:
fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n", error);
gfs2_assert_withdraw(sdp, 0);
return error;
}
void gfs2_freeze_func(struct work_struct *work)
{
struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_freeze_work);
struct super_block *sb = sdp->sd_vfs;
int error;
mutex_lock(&sdp->sd_freeze_mutex);
error = -EBUSY;
if (test_bit(SDF_FROZEN, &sdp->sd_flags))
goto freeze_failed;
error = gfs2_freeze_locally(sdp);
if (error)
goto freeze_failed;
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
set_bit(SDF_FROZEN, &sdp->sd_flags);
error = gfs2_do_thaw(sdp);
if (error)
goto out;
clear_bit(SDF_FROZEN, &sdp->sd_flags);
goto out;
freeze_failed:
fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", error);
out:
mutex_unlock(&sdp->sd_freeze_mutex);
deactivate_super(sb);
}
/**
* gfs2_freeze_super - prevent further writes to the filesystem
* @sb: the VFS structure for the filesystem
*
*/
static int gfs2_freeze_super(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
int error;
if (!mutex_trylock(&sdp->sd_freeze_mutex))
return -EBUSY;
error = -EBUSY;
if (test_bit(SDF_FROZEN, &sdp->sd_flags))
goto out;
for (;;) {
error = gfs2_freeze_locally(sdp);
if (error) {
fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
error);
goto out;
}
error = gfs2_lock_fs_check_clean(sdp);
if (!error)
break; /* success */
error = gfs2_do_thaw(sdp);
if (error)
goto out;
if (error == -EBUSY)
fs_err(sdp, "waiting for recovery before freeze\n");
else if (error == -EIO) {
fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
"to recovery error.\n");
goto out;
} else {
fs_err(sdp, "error freezing FS: %d\n", error);
}
fs_err(sdp, "retrying...\n");
msleep(1000);
}
out:
if (!error) {
set_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
set_bit(SDF_FROZEN, &sdp->sd_flags);
}
mutex_unlock(&sdp->sd_freeze_mutex);
return error;
}
/**
* gfs2_thaw_super - reallow writes to the filesystem
* @sb: the VFS structure for the filesystem
*
*/
static int gfs2_thaw_super(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
int error;
if (!mutex_trylock(&sdp->sd_freeze_mutex))
return -EBUSY;
error = -EINVAL;
if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags))
goto out;
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
error = gfs2_do_thaw(sdp);
if (!error) {
clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
clear_bit(SDF_FROZEN, &sdp->sd_flags);
}
out:
mutex_unlock(&sdp->sd_freeze_mutex);
return error;
}
void gfs2_thaw_freeze_initiator(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
mutex_lock(&sdp->sd_freeze_mutex);
if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags))
goto out;
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
out:
mutex_unlock(&sdp->sd_freeze_mutex);
}
/**
* statfs_slow_fill - fill in the sg for a given RG
* @rgd: the RG
* @sc: the sc structure
*
* Returns: 0 on success, -ESTALE if the LVB is invalid
*/
static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
struct gfs2_statfs_change_host *sc)
{
gfs2_rgrp_verify(rgd);
sc->sc_total += rgd->rd_data;
sc->sc_free += rgd->rd_free;
sc->sc_dinodes += rgd->rd_dinodes;
return 0;
}
/**
* gfs2_statfs_slow - Stat a filesystem using asynchronous locking
* @sdp: the filesystem
* @sc: the sc info that will be returned
*
* Any error (other than a signal) will cause this routine to fall back
* to the synchronous version.
*
* FIXME: This really shouldn't busy wait like this.
*
* Returns: errno
*/
static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
struct gfs2_rgrpd *rgd_next;
struct gfs2_holder *gha, *gh;
unsigned int slots = 64;
unsigned int x;
int done;
int error = 0, err;
memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
gha = kmalloc_array(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
if (!gha)
return -ENOMEM;
for (x = 0; x < slots; x++)
gfs2_holder_mark_uninitialized(gha + x);
rgd_next = gfs2_rgrpd_get_first(sdp);
for (;;) {
done = 1;
for (x = 0; x < slots; x++) {
gh = gha + x;
if (gfs2_holder_initialized(gh) && gfs2_glock_poll(gh)) {
err = gfs2_glock_wait(gh);
if (err) {
gfs2_holder_uninit(gh);
error = err;
} else {
if (!error) {
struct gfs2_rgrpd *rgd =
gfs2_glock2rgrp(gh->gh_gl);
error = statfs_slow_fill(rgd, sc);
}
gfs2_glock_dq_uninit(gh);
}
}
if (gfs2_holder_initialized(gh))
done = 0;
else if (rgd_next && !error) {
error = gfs2_glock_nq_init(rgd_next->rd_gl,
LM_ST_SHARED,
GL_ASYNC,
gh);
rgd_next = gfs2_rgrpd_get_next(rgd_next);
done = 0;
}
if (signal_pending(current))
error = -ERESTARTSYS;
}
if (done)
break;
yield();
}
kfree(gha);
return error;
}
/**
* gfs2_statfs_i - Do a statfs
* @sdp: the filesystem
* @sc: the sc structure
*
* Returns: errno
*/
static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
spin_lock(&sdp->sd_statfs_spin);
*sc = *m_sc;
sc->sc_total += l_sc->sc_total;
sc->sc_free += l_sc->sc_free;
sc->sc_dinodes += l_sc->sc_dinodes;
spin_unlock(&sdp->sd_statfs_spin);
if (sc->sc_free < 0)
sc->sc_free = 0;
if (sc->sc_free > sc->sc_total)
sc->sc_free = sc->sc_total;
if (sc->sc_dinodes < 0)
sc->sc_dinodes = 0;
return 0;
}
/**
* gfs2_statfs - Gather and return stats about the filesystem
* @dentry: The name of the link
* @buf: The buffer
*
* Returns: 0 on success or error code
*/
static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_statfs_change_host sc;
int error;
error = gfs2_rindex_update(sdp);