-
Notifications
You must be signed in to change notification settings - Fork 0
/
super.c
1808 lines (1618 loc) · 44.3 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
/*
* linux/fs/super.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* super.c contains code to handle: - mount structures
* - super-block tables
* - filesystem drivers list
* - mount system call
* - umount system call
* - ustat system call
*
* GK 2/5/95 - Changed to support mounting the root fs via NFS
*
* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
* Added options to /proc/mounts:
* Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
#include <linux/config.h>
#include <linux/string.h>
#include <linux/malloc.h>
#include <linux/locks.h>
#include <linux/smp_lock.h>
#include <linux/devfs_fs_kernel.h>
#include <linux/fd.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/acct.h>
#include <asm/uaccess.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
#include <linux/nfs_mount.h>
#include <linux/kmod.h>
#define __NO_VERSION__
#include <linux/module.h>
/*
* We use a semaphore to synchronize all mount/umount
* activity - imagine the mess if we have a race between
* unmounting a filesystem and re-mounting it (or something
* else).
*/
static DECLARE_MUTEX(mount_sem);
extern void wait_for_keypress(void);
extern int root_mountflags;
static int do_remount_sb(struct super_block *sb, int flags, char * data);
/* this is initialized in init/main.c */
kdev_t ROOT_DEV;
int nr_super_blocks;
int max_super_blocks = NR_SUPER;
LIST_HEAD(super_blocks);
/*
* Handling of filesystem drivers list.
* Rules:
* Inclusion to/removals from/scanning of list are protected by spinlock.
* During the unload module must call unregister_filesystem().
* We can access the fields of list element if:
* 1) spinlock is held or
* 2) we hold the reference to the module.
* The latter can be guaranteed by call of try_inc_mod_count(); if it
* returned 0 we must skip the element, otherwise we got the reference.
* Once the reference is obtained we can drop the spinlock.
*/
static struct file_system_type *file_systems;
static rwlock_t file_systems_lock = RW_LOCK_UNLOCKED;
/* WARNING: This can be used only if we _already_ own a reference */
static void get_filesystem(struct file_system_type *fs)
{
if (fs->owner)
__MOD_INC_USE_COUNT(fs->owner);
}
static void put_filesystem(struct file_system_type *fs)
{
if (fs->owner)
__MOD_DEC_USE_COUNT(fs->owner);
}
static struct file_system_type **find_filesystem(const char *name)
{
struct file_system_type **p;
for (p=&file_systems; *p; p=&(*p)->next)
if (strcmp((*p)->name,name) == 0)
break;
return p;
}
/**
* register_filesystem - register a new filesystem
* @fs: the file system structure
*
* Adds the file system passed to the list of file systems the kernel
* is aware of for mount and other syscalls. Returns 0 on success,
* or a negative errno code on an error.
*
* The &struct file_system_type that is passed is linked into the kernel
* structures and must not be freed until the file system has been
* unregistered.
*/
int register_filesystem(struct file_system_type * fs)
{
int res = 0;
struct file_system_type ** p;
if (!fs)
return -EINVAL;
if (fs->next)
return -EBUSY;
write_lock(&file_systems_lock);
p = find_filesystem(fs->name);
if (*p)
res = -EBUSY;
else
*p = fs;
write_unlock(&file_systems_lock);
return res;
}
/**
* unregister_filesystem - unregister a file system
* @fs: filesystem to unregister
*
* Remove a file system that was previously successfully registered
* with the kernel. An error is returned if the file system is not found.
* Zero is returned on a success.
*
* Once this function has returned the &struct file_system_type structure
* may be freed or reused.
*/
int unregister_filesystem(struct file_system_type * fs)
{
struct file_system_type ** tmp;
write_lock(&file_systems_lock);
tmp = &file_systems;
while (*tmp) {
if (fs == *tmp) {
*tmp = fs->next;
fs->next = NULL;
write_unlock(&file_systems_lock);
return 0;
}
tmp = &(*tmp)->next;
}
write_unlock(&file_systems_lock);
return -EINVAL;
}
static int fs_index(const char * __name)
{
struct file_system_type * tmp;
char * name;
int err, index;
name = getname(__name);
err = PTR_ERR(name);
if (IS_ERR(name))
return err;
err = -EINVAL;
read_lock(&file_systems_lock);
for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) {
if (strcmp(tmp->name,name) == 0) {
err = index;
break;
}
}
read_unlock(&file_systems_lock);
putname(name);
return err;
}
static int fs_name(unsigned int index, char * buf)
{
struct file_system_type * tmp;
int len, res;
read_lock(&file_systems_lock);
for (tmp = file_systems; tmp; tmp = tmp->next, index--)
if (index <= 0 && try_inc_mod_count(tmp->owner))
break;
read_unlock(&file_systems_lock);
if (!tmp)
return -EINVAL;
/* OK, we got the reference, so we can safely block */
len = strlen(tmp->name) + 1;
res = copy_to_user(buf, tmp->name, len) ? -EFAULT : 0;
put_filesystem(tmp);
return res;
}
static int fs_maxindex(void)
{
struct file_system_type * tmp;
int index;
read_lock(&file_systems_lock);
for (tmp = file_systems, index = 0 ; tmp ; tmp = tmp->next, index++)
;
read_unlock(&file_systems_lock);
return index;
}
/*
* Whee.. Weird sysv syscall.
*/
asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2)
{
int retval = -EINVAL;
switch (option) {
case 1:
retval = fs_index((const char *) arg1);
break;
case 2:
retval = fs_name(arg1, (char *) arg2);
break;
case 3:
retval = fs_maxindex();
break;
}
return retval;
}
int get_filesystem_list(char * buf)
{
int len = 0;
struct file_system_type * tmp;
read_lock(&file_systems_lock);
tmp = file_systems;
while (tmp && len < PAGE_SIZE - 80) {
len += sprintf(buf+len, "%s\t%s\n",
(tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev",
tmp->name);
tmp = tmp->next;
}
read_unlock(&file_systems_lock);
return len;
}
struct file_system_type *get_fs_type(const char *name)
{
struct file_system_type *fs;
read_lock(&file_systems_lock);
fs = *(find_filesystem(name));
if (fs && !try_inc_mod_count(fs->owner))
fs = NULL;
read_unlock(&file_systems_lock);
if (!fs && (request_module(name) == 0)) {
read_lock(&file_systems_lock);
fs = *(find_filesystem(name));
if (fs && !try_inc_mod_count(fs->owner))
fs = NULL;
read_unlock(&file_systems_lock);
}
return fs;
}
static LIST_HEAD(vfsmntlist);
/**
* add_vfsmnt - add a new mount node
* @nd: location of mountpoint or %NULL if we want a root node
* @root: root of (sub)tree to be mounted
* @dev_name: device name to show in /proc/mounts or %NULL (for "none").
*
* This is VFS idea of mount. New node is allocated, bound to a tree
* we are mounting and optionally (OK, usually) registered as mounted
* on a given mountpoint. Returns a pointer to new node or %NULL in
* case of failure.
*
* Potential reason for failure (aside of trivial lack of memory) is a
* deleted mountpoint. Caller must hold ->i_zombie on mountpoint
* dentry (if any).
*
* Node is marked as MNT_VISIBLE (visible in /proc/mounts) unless both
* @nd and @devname are %NULL. It works since we pass non-%NULL @devname
* when we are mounting root and kern_mount() filesystems are deviceless.
* If we will get a kern_mount() filesystem with nontrivial @devname we
* will have to pass the visibility flag explicitly, so if we will add
* support for such beasts we'll have to change prototype.
*/
static struct vfsmount *add_vfsmnt(struct nameidata *nd,
struct dentry *root,
const char *dev_name)
{
struct vfsmount *mnt;
struct super_block *sb = root->d_inode->i_sb;
char *name;
mnt = kmalloc(sizeof(struct vfsmount), GFP_KERNEL);
if (!mnt)
goto out;
memset(mnt, 0, sizeof(struct vfsmount));
if (nd || dev_name)
mnt->mnt_flags = MNT_VISIBLE;
/* It may be NULL, but who cares? */
if (dev_name) {
name = kmalloc(strlen(dev_name)+1, GFP_KERNEL);
if (name) {
strcpy(name, dev_name);
mnt->mnt_devname = name;
}
}
mnt->mnt_owner = current->uid;
atomic_set(&mnt->mnt_count,1);
mnt->mnt_sb = sb;
spin_lock(&dcache_lock);
if (nd && !IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))
goto fail;
mnt->mnt_root = dget(root);
mnt->mnt_mountpoint = nd ? dget(nd->dentry) : dget(root);
mnt->mnt_parent = nd ? mntget(nd->mnt) : mnt;
if (nd) {
list_add(&mnt->mnt_child, &nd->mnt->mnt_mounts);
list_add(&mnt->mnt_clash, &nd->dentry->d_vfsmnt);
} else {
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_clash);
}
INIT_LIST_HEAD(&mnt->mnt_mounts);
list_add(&mnt->mnt_instances, &sb->s_mounts);
list_add(&mnt->mnt_list, vfsmntlist.prev);
spin_unlock(&dcache_lock);
out:
return mnt;
fail:
spin_unlock(&dcache_lock);
if (mnt->mnt_devname)
kfree(mnt->mnt_devname);
kfree(mnt);
return NULL;
}
static void move_vfsmnt(struct vfsmount *mnt,
struct dentry *mountpoint,
struct vfsmount *parent,
const char *dev_name)
{
struct dentry *old_mountpoint;
struct vfsmount *old_parent;
char *new_devname = NULL;
if (dev_name) {
new_devname = kmalloc(strlen(dev_name)+1, GFP_KERNEL);
if (new_devname)
strcpy(new_devname, dev_name);
}
spin_lock(&dcache_lock);
old_mountpoint = mnt->mnt_mountpoint;
old_parent = mnt->mnt_parent;
/* flip names */
if (new_devname) {
if (mnt->mnt_devname)
kfree(mnt->mnt_devname);
mnt->mnt_devname = new_devname;
}
/* flip the linkage */
mnt->mnt_mountpoint = dget(mountpoint);
mnt->mnt_parent = parent ? mntget(parent) : mnt;
list_del(&mnt->mnt_clash);
list_del(&mnt->mnt_child);
if (parent) {
list_add(&mnt->mnt_child, &parent->mnt_mounts);
list_add(&mnt->mnt_clash, &mountpoint->d_vfsmnt);
} else {
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_clash);
}
spin_unlock(&dcache_lock);
/* put the old stuff */
dput(old_mountpoint);
if (old_parent != mnt)
mntput(old_parent);
}
/*
* Called with spinlock held, releases it.
*/
static void remove_vfsmnt(struct vfsmount *mnt)
{
/* First of all, remove it from all lists */
list_del(&mnt->mnt_instances);
list_del(&mnt->mnt_clash);
list_del(&mnt->mnt_list);
list_del(&mnt->mnt_child);
spin_unlock(&dcache_lock);
/* Now we can work safely */
if (mnt->mnt_parent != mnt)
mntput(mnt->mnt_parent);
dput(mnt->mnt_mountpoint);
dput(mnt->mnt_root);
if (mnt->mnt_devname)
kfree(mnt->mnt_devname);
kfree(mnt);
}
/* Use octal escapes, like mount does, for embedded spaces etc. */
static unsigned char need_escaping[] = { ' ', '\t', '\n', '\\' };
static int
mangle(const unsigned char *s, char *buf, int len) {
char *sp;
int n;
sp = buf;
while(*s && sp-buf < len-3) {
for (n = 0; n < sizeof(need_escaping); n++) {
if (*s == need_escaping[n]) {
*sp++ = '\\';
*sp++ = '0' + ((*s & 0300) >> 6);
*sp++ = '0' + ((*s & 070) >> 3);
*sp++ = '0' + (*s & 07);
goto next;
}
}
*sp++ = *s;
next:
s++;
}
return sp - buf; /* no trailing NUL */
}
static struct proc_fs_info {
int flag;
char *str;
} fs_info[] = {
{ MS_NOEXEC, ",noexec" },
{ MS_NOSUID, ",nosuid" },
{ MS_NODEV, ",nodev" },
{ MS_SYNCHRONOUS, ",sync" },
{ MS_MANDLOCK, ",mand" },
{ MS_NOATIME, ",noatime" },
{ MS_NODIRATIME, ",nodiratime" },
#ifdef MS_NOSUB /* Can't find this except in mount.c */
{ MS_NOSUB, ",nosub" },
#endif
{ 0, NULL }
};
static struct proc_nfs_info {
int flag;
char *str;
char *nostr;
} nfs_info[] = {
{ NFS_MOUNT_SOFT, ",soft", ",hard" },
{ NFS_MOUNT_INTR, ",intr", "" },
{ NFS_MOUNT_POSIX, ",posix", "" },
{ NFS_MOUNT_TCP, ",tcp", ",udp" },
{ NFS_MOUNT_NOCTO, ",nocto", "" },
{ NFS_MOUNT_NOAC, ",noac", "" },
{ NFS_MOUNT_NONLM, ",nolock", ",lock" },
{ NFS_MOUNT_BROKEN_SUID, ",broken_suid", "" },
{ 0, NULL, NULL }
};
int get_filesystem_info( char *buf )
{
struct list_head *p;
struct proc_fs_info *fs_infop;
struct proc_nfs_info *nfs_infop;
struct nfs_server *nfss;
int len, prevlen;
char *path, *buffer = (char *) __get_free_page(GFP_KERNEL);
if (!buffer) return 0;
len = prevlen = 0;
#define FREEROOM ((int)PAGE_SIZE-200-len)
#define MANGLE(s) len += mangle((s), buf+len, FREEROOM);
for (p = vfsmntlist.next; p != &vfsmntlist; p = p->next) {
struct vfsmount *tmp = list_entry(p, struct vfsmount, mnt_list);
if (!(tmp->mnt_flags & MNT_VISIBLE))
continue;
path = d_path(tmp->mnt_root, tmp, buffer, PAGE_SIZE);
if (!path)
continue;
MANGLE(tmp->mnt_devname ? tmp->mnt_devname : "none");
buf[len++] = ' ';
MANGLE(path);
buf[len++] = ' ';
MANGLE(tmp->mnt_sb->s_type->name);
len += sprintf(buf+len, " %s",
tmp->mnt_sb->s_flags & MS_RDONLY ? "ro" : "rw");
for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
if (tmp->mnt_sb->s_flags & fs_infop->flag)
MANGLE(fs_infop->str);
}
if (!strcmp("nfs", tmp->mnt_sb->s_type->name)) {
nfss = &tmp->mnt_sb->u.nfs_sb.s_server;
len += sprintf(buf+len, ",v%d", nfss->rpc_ops->version);
len += sprintf(buf+len, ",rsize=%d", nfss->rsize);
len += sprintf(buf+len, ",wsize=%d", nfss->wsize);
#if 0
if (nfss->timeo != 7*HZ/10) {
len += sprintf(buf+len, ",timeo=%d",
nfss->timeo*10/HZ);
}
if (nfss->retrans != 3) {
len += sprintf(buf+len, ",retrans=%d",
nfss->retrans);
}
#endif
if (nfss->acregmin != 3*HZ) {
len += sprintf(buf+len, ",acregmin=%d",
nfss->acregmin/HZ);
}
if (nfss->acregmax != 60*HZ) {
len += sprintf(buf+len, ",acregmax=%d",
nfss->acregmax/HZ);
}
if (nfss->acdirmin != 30*HZ) {
len += sprintf(buf+len, ",acdirmin=%d",
nfss->acdirmin/HZ);
}
if (nfss->acdirmax != 60*HZ) {
len += sprintf(buf+len, ",acdirmax=%d",
nfss->acdirmax/HZ);
}
for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
char *str;
if (nfss->flags & nfs_infop->flag)
str = nfs_infop->str;
else
str = nfs_infop->nostr;
MANGLE(str);
}
len += sprintf(buf+len, ",addr=");
MANGLE(nfss->hostname);
}
len += sprintf(buf + len, " 0 0\n");
if (FREEROOM <= 3) {
len = prevlen;
len += sprintf(buf+len, "# truncated\n");
break;
}
prevlen = len;
}
free_page((unsigned long) buffer);
return len;
#undef MANGLE
#undef FREEROOM
}
/**
* __wait_on_super - wait on a superblock
* @sb: superblock to wait on
*
* Waits for a superblock to become unlocked and then returns. It does
* not take the lock. This is an internal function. See wait_on_super().
*/
void __wait_on_super(struct super_block * sb)
{
DECLARE_WAITQUEUE(wait, current);
add_wait_queue(&sb->s_wait, &wait);
repeat:
set_current_state(TASK_UNINTERRUPTIBLE);
if (sb->s_lock) {
schedule();
goto repeat;
}
remove_wait_queue(&sb->s_wait, &wait);
current->state = TASK_RUNNING;
}
/*
* Note: check the dirty flag before waiting, so we don't
* hold up the sync while mounting a device. (The newly
* mounted device won't need syncing.)
*/
void sync_supers(kdev_t dev)
{
struct super_block * sb;
for (sb = sb_entry(super_blocks.next);
sb != sb_entry(&super_blocks);
sb = sb_entry(sb->s_list.next)) {
if (!sb->s_dev)
continue;
if (dev && sb->s_dev != dev)
continue;
if (!sb->s_dirt)
continue;
lock_super(sb);
if (sb->s_dev && sb->s_dirt && (!dev || dev == sb->s_dev))
if (sb->s_op && sb->s_op->write_super)
sb->s_op->write_super(sb);
unlock_super(sb);
}
}
/**
* get_super - get the superblock of a device
* @dev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device given. %NULL is returned if no match is found.
*/
struct super_block * get_super(kdev_t dev)
{
struct super_block * s;
if (!dev)
return NULL;
restart:
s = sb_entry(super_blocks.next);
while (s != sb_entry(&super_blocks))
if (s->s_dev == dev) {
wait_on_super(s);
if (s->s_dev == dev)
return s;
goto restart;
} else
s = sb_entry(s->s_list.next);
return NULL;
}
asmlinkage long sys_ustat(dev_t dev, struct ustat * ubuf)
{
struct super_block *s;
struct ustat tmp;
struct statfs sbuf;
int err = -EINVAL;
lock_kernel();
s = get_super(to_kdev_t(dev));
unlock_kernel();
if (s == NULL)
goto out;
err = vfs_statfs(s, &sbuf);
if (err)
goto out;
memset(&tmp,0,sizeof(struct ustat));
tmp.f_tfree = sbuf.f_bfree;
tmp.f_tinode = sbuf.f_ffree;
err = copy_to_user(ubuf,&tmp,sizeof(struct ustat)) ? -EFAULT : 0;
out:
return err;
}
/**
* get_empty_super - find empty superblocks
*
* Find a superblock with no device assigned. A free superblock is
* found and returned. If neccessary new superblocks are allocated.
* %NULL is returned if there are insufficient resources to complete
* the request.
*/
struct super_block *get_empty_super(void)
{
struct super_block *s;
for (s = sb_entry(super_blocks.next);
s != sb_entry(&super_blocks);
s = sb_entry(s->s_list.next)) {
if (s->s_dev)
continue;
if (!s->s_lock)
return s;
printk("VFS: empty superblock %p locked!\n", s);
}
/* Need a new one... */
if (nr_super_blocks >= max_super_blocks)
return NULL;
s = kmalloc(sizeof(struct super_block), GFP_USER);
if (s) {
nr_super_blocks++;
memset(s, 0, sizeof(struct super_block));
INIT_LIST_HEAD(&s->s_dirty);
list_add (&s->s_list, super_blocks.prev);
init_waitqueue_head(&s->s_wait);
INIT_LIST_HEAD(&s->s_files);
INIT_LIST_HEAD(&s->s_mounts);
}
return s;
}
static struct super_block * read_super(kdev_t dev, struct block_device *bdev,
struct file_system_type *type, int flags,
void *data, int silent)
{
struct super_block * s;
s = get_empty_super();
if (!s)
goto out;
s->s_dev = dev;
s->s_bdev = bdev;
s->s_flags = flags;
s->s_dirt = 0;
sema_init(&s->s_vfs_rename_sem,1);
sema_init(&s->s_nfsd_free_path_sem,1);
s->s_type = type;
sema_init(&s->s_dquot.dqio_sem, 1);
sema_init(&s->s_dquot.dqoff_sem, 1);
s->s_dquot.flags = 0;
lock_super(s);
if (!type->read_super(s, data, silent))
goto out_fail;
unlock_super(s);
/* tell bdcache that we are going to keep this one */
if (bdev)
atomic_inc(&bdev->bd_count);
out:
return s;
out_fail:
s->s_dev = 0;
s->s_bdev = 0;
s->s_type = NULL;
unlock_super(s);
return NULL;
}
/*
* Unnamed block devices are dummy devices used by virtual
* filesystems which don't use real block-devices. -- jrs
*/
static unsigned int unnamed_dev_in_use[256/(8*sizeof(unsigned int))];
kdev_t get_unnamed_dev(void)
{
int i;
for (i = 1; i < 256; i++) {
if (!test_and_set_bit(i,unnamed_dev_in_use))
return MKDEV(UNNAMED_MAJOR, i);
}
return 0;
}
void put_unnamed_dev(kdev_t dev)
{
if (!dev || MAJOR(dev) != UNNAMED_MAJOR)
return;
if (test_and_clear_bit(MINOR(dev), unnamed_dev_in_use))
return;
printk("VFS: put_unnamed_dev: freeing unused device %s\n",
kdevname(dev));
}
static struct super_block *get_sb_bdev(struct file_system_type *fs_type,
char *dev_name, int flags, void * data)
{
struct inode *inode;
struct block_device *bdev;
struct block_device_operations *bdops;
struct super_block * sb;
struct nameidata nd;
kdev_t dev;
int error = 0;
/* What device it is? */
if (!dev_name || !*dev_name)
return ERR_PTR(-EINVAL);
if (path_init(dev_name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, &nd))
error = path_walk(dev_name, &nd);
if (error)
return ERR_PTR(error);
inode = nd.dentry->d_inode;
error = -ENOTBLK;
if (!S_ISBLK(inode->i_mode))
goto out;
error = -EACCES;
if (IS_NODEV(inode))
goto out;
bdev = inode->i_bdev;
bdops = devfs_get_ops ( devfs_get_handle_from_inode (inode) );
if (bdops) bdev->bd_op = bdops;
/* Done with lookups, semaphore down */
down(&mount_sem);
dev = to_kdev_t(bdev->bd_dev);
sb = get_super(dev);
if (sb) {
if (fs_type == sb->s_type &&
((flags ^ sb->s_flags) & MS_RDONLY) == 0) {
path_release(&nd);
return sb;
}
} else {
mode_t mode = FMODE_READ; /* we always need it ;-) */
if (!(flags & MS_RDONLY))
mode |= FMODE_WRITE;
error = blkdev_get(bdev, mode, 0, BDEV_FS);
if (error)
goto out;
check_disk_change(dev);
error = -EACCES;
if (!(flags & MS_RDONLY) && is_read_only(dev))
goto out1;
error = -EINVAL;
sb = read_super(dev, bdev, fs_type, flags, data, 0);
if (sb) {
get_filesystem(fs_type);
path_release(&nd);
return sb;
}
out1:
blkdev_put(bdev, BDEV_FS);
}
out:
path_release(&nd);
up(&mount_sem);
return ERR_PTR(error);
}
static struct super_block *get_sb_nodev(struct file_system_type *fs_type,
int flags, void * data)
{
kdev_t dev;
int error = -EMFILE;
down(&mount_sem);
dev = get_unnamed_dev();
if (dev) {
struct super_block * sb;
error = -EINVAL;
sb = read_super(dev, NULL, fs_type, flags, data, 0);
if (sb) {
get_filesystem(fs_type);
return sb;
}
put_unnamed_dev(dev);
}
up(&mount_sem);
return ERR_PTR(error);
}
static struct super_block *get_sb_single(struct file_system_type *fs_type,
int flags, void *data)
{
struct super_block * sb;
/*
* Get the superblock of kernel-wide instance, but
* keep the reference to fs_type.
*/
down(&mount_sem);
sb = fs_type->kern_mnt->mnt_sb;
if (!sb)
BUG();
get_filesystem(fs_type);
do_remount_sb(sb, flags, data);
return sb;
}
static void kill_super(struct super_block *sb, int umount_root)
{
struct block_device *bdev;
kdev_t dev;
struct dentry *root = sb->s_root;
struct file_system_type *fs = sb->s_type;
struct super_operations *sop = sb->s_op;
sb->s_root = NULL;
/* Need to clean after the sucker */
if (fs->fs_flags & FS_LITTER)
d_genocide(root);
if (fs->fs_flags & (FS_SINGLE|FS_LITTER))
shrink_dcache_parent(root);
dput(root);
lock_super(sb);
if (sop) {
if (sop->write_super && sb->s_dirt)
sop->write_super(sb);
if (sop->put_super)
sop->put_super(sb);
}
/* Forget any remaining inodes */
if (invalidate_inodes(sb)) {
printk("VFS: Busy inodes after unmount. "
"Self-destruct in 5 seconds. Have a nice day...\n");
}
dev = sb->s_dev;
sb->s_dev = 0; /* Free the superblock */
bdev = sb->s_bdev;
sb->s_bdev = NULL;
put_filesystem(fs);
sb->s_type = NULL;
unlock_super(sb);
if (umount_root) {
/* special: the old device driver is going to be
a ramdisk and the point of this call is to free its
protected memory (even if dirty). */
destroy_buffers(dev);
}
if (bdev) {
blkdev_put(bdev, BDEV_FS);
bdput(bdev);
} else
put_unnamed_dev(dev);
}
/*
* Alters the mount flags of a mounted file system. Only the mount point
* is used as a reference - file system type and the device are ignored.
*/
static int do_remount_sb(struct super_block *sb, int flags, char *data)
{
int retval;
if (!(flags & MS_RDONLY) && sb->s_dev && is_read_only(sb->s_dev))
return -EACCES;
/*flags |= MS_RDONLY;*/
/* If we are remounting RDONLY, make sure there are no rw files open */
if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY))
if (!fs_may_remount_ro(sb))
return -EBUSY;
if (sb->s_op && sb->s_op->remount_fs) {
lock_super(sb);
retval = sb->s_op->remount_fs(sb, &flags, data);
unlock_super(sb);
if (retval)
return retval;
}
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
/*
* We can't invalidate inodes as we can loose data when remounting
* (someone might manage to alter data while we are waiting in lock_super()
* or in foo_remount_fs()))
*/
return 0;
}
struct vfsmount *kern_mount(struct file_system_type *type)
{
kdev_t dev = get_unnamed_dev();
struct super_block *sb;
struct vfsmount *mnt;
if (!dev)
return ERR_PTR(-EMFILE);
sb = read_super(dev, NULL, type, 0, NULL, 0);
if (!sb) {
put_unnamed_dev(dev);
return ERR_PTR(-EINVAL);
}
mnt = add_vfsmnt(NULL, sb->s_root, NULL);
if (!mnt) {
kill_super(sb, 0);
return ERR_PTR(-ENOMEM);
}
type->kern_mnt = mnt;
return mnt;
}
/* Call only after unregister_filesystem() - it's a final cleanup */
void kern_umount(struct vfsmount *mnt)
{
struct super_block *sb = mnt->mnt_sb;
spin_lock(&dcache_lock);
remove_vfsmnt(mnt);
kill_super(sb, 0);
}