summaryrefslogtreecommitdiffstats
path: root/fs/afs/super.c
blob: 59382037284810e856d724cd38a2062d768b7bbc (plain)
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
/* AFS superblock handling
 *
 * Copyright (c) 2002, 2007 Red Hat, Inc. All rights reserved.
 *
 * This software may be freely redistributed under the terms of the
 * GNU General Public License.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * Authors: David Howells <dhowells@redhat.com>
 *          David Woodhouse <dwmw2@infradead.org>
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/parser.h>
#include <linux/statfs.h>
#include <linux/sched.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
#include <net/net_namespace.h>
#include "internal.h"

static void afs_i_init_once(void *foo);
static struct dentry *afs_mount(struct file_system_type *fs_type,
		      int flags, const char *dev_name, void *data);
static void afs_kill_super(struct super_block *sb);
static struct inode *afs_alloc_inode(struct super_block *sb);
static void afs_destroy_inode(struct inode *inode);
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
static int afs_show_devname(struct seq_file *m, struct dentry *root);
static int afs_show_options(struct seq_file *m, struct dentry *root);

struct file_system_type afs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "afs",
	.mount		= afs_mount,
	.kill_sb	= afs_kill_super,
	.fs_flags	= 0,
};
MODULE_ALIAS_FS("afs");

int afs_net_id;

static const struct super_operations afs_super_ops = {
	.statfs		= afs_statfs,
	.alloc_inode	= afs_alloc_inode,
	.drop_inode	= afs_drop_inode,
	.destroy_inode	= afs_destroy_inode,
	.evict_inode	= afs_evict_inode,
	.show_devname	= afs_show_devname,
	.show_options	= afs_show_options,
};

static struct kmem_cache *afs_inode_cachep;
static atomic_t afs_count_active_inodes;

enum {
	afs_no_opt,
	afs_opt_cell,
	afs_opt_dyn,
	afs_opt_rwpath,
	afs_opt_vol,
	afs_opt_autocell,
};

static const match_table_t afs_options_list = {
	{ afs_opt_cell,		"cell=%s"	},
	{ afs_opt_dyn,		"dyn"		},
	{ afs_opt_rwpath,	"rwpath"	},
	{ afs_opt_vol,		"vol=%s"	},
	{ afs_opt_autocell,	"autocell"	},
	{ afs_no_opt,		NULL		},
};

/*
 * initialise the filesystem
 */
int __init afs_fs_init(void)
{
	int ret;

	_enter("");

	/* create ourselves an inode cache */
	atomic_set(&afs_count_active_inodes, 0);

	ret = -ENOMEM;
	afs_inode_cachep = kmem_cache_create("afs_inode_cache",
					     sizeof(struct afs_vnode),
					     0,
					     SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
					     afs_i_init_once);
	if (!afs_inode_cachep) {
		printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n");
		return ret;
	}

	/* now export our filesystem to lesser mortals */
	ret = register_filesystem(&afs_fs_type);
	if (ret < 0) {
		kmem_cache_destroy(afs_inode_cachep);
		_leave(" = %d", ret);
		return ret;
	}

	_leave(" = 0");
	return 0;
}

/*
 * clean up the filesystem
 */
void afs_fs_exit(void)
{
	_enter("");

	afs_mntpt_kill_timer();
	unregister_filesystem(&afs_fs_type);

	if (atomic_read(&afs_count_active_inodes) != 0) {
		printk("kAFS: %d active inode objects still present\n",
		       atomic_read(&afs_count_active_inodes));
		BUG();
	}

	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(afs_inode_cachep);
	_leave("");
}

/*
 * Display the mount device name in /proc/mounts.
 */
static int afs_show_devname(struct seq_file *m, struct dentry *root)
{
	struct afs_super_info *as = AFS_FS_S(root->d_sb);
	struct afs_volume *volume = as->volume;
	struct afs_cell *cell = as->cell;
	const char *suf = "";
	char pref = '%';

	if (as->dyn_root) {
		seq_puts(m, "none");
		return 0;
	}

	switch (volume->type) {
	case AFSVL_RWVOL:
		break;
	case AFSVL_ROVOL:
		pref = '#';
		if (volume->type_force)
			suf = ".readonly";
		break;
	case AFSVL_BACKVOL:
		pref = '#';
		suf = ".backup";
		break;
	}

	seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->name, suf);
	return 0;
}

/*
 * Display the mount options in /proc/mounts.
 */
static int afs_show_options(struct seq_file *m, struct dentry *root)
{
	struct afs_super_info *as = AFS_FS_S(root->d_sb);

	if (as->dyn_root)
		seq_puts(m, ",dyn");
	if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags))
		seq_puts(m, ",autocell");
	return 0;
}

/*
 * parse the mount options
 * - this function has been shamelessly adapted from the ext3 fs which
 *   shamelessly adapted it from the msdos fs
 */
static int afs_parse_options(struct afs_mount_params *params,
			     char *options, const char **devname)
{
	struct afs_cell *cell;
	substring_t args[MAX_OPT_ARGS];
	char *p;
	int token;

	_enter("%s", options);

	options[PAGE_SIZE - 1] = 0;

	while ((p = strsep(&options, ","))) {
		if (!*p)
			continue;

		token = match_token(p, afs_options_list, args);
		switch (token) {
		case afs_opt_cell:
			rcu_read_lock();
			cell = afs_lookup_cell_rcu(params->net,
						   args[0].from,
						   args[0].to - args[0].from);
			rcu_read_unlock();
			if (IS_ERR(cell))
				return PTR_ERR(cell);
			afs_put_cell(params->net, params->cell);
			params->cell = cell;
			break;

		case afs_opt_rwpath:
			params->rwpath = true;
			break;

		case afs_opt_vol:
			*devname = args[0].from;
			break;

		case afs_opt_autocell:
			params->autocell = true;
			break;

		case afs_opt_dyn:
			params->dyn_root = true;
			break;

		default:
			printk(KERN_ERR "kAFS:"
			       " Unknown or invalid mount option: '%s'\n", p);
			return -EINVAL;
		}
	}

	_leave(" = 0");
	return 0;
}

/*
 * parse a device name to get cell name, volume name, volume type and R/W
 * selector
 * - this can be one of the following:
 *	"%[cell:]volume[.]"		R/W volume
 *	"#[cell:]volume[.]"		R/O or R/W volume (rwpath=0),
 *					 or R/W (rwpath=1) volume
 *	"%[cell:]volume.readonly"	R/O volume
 *	"#[cell:]volume.readonly"	R/O volume
 *	"%[cell:]volume.backup"		Backup volume
 *	"#[cell:]volume.backup"		Backup volume
 */
static int afs_parse_device_name(struct afs_mount_params *params,
				 const char *name)
{
	struct afs_cell *cell;
	const char *cellname, *suffix;
	int cellnamesz;

	_enter(",%s", name);

	if (!name) {
		printk(KERN_ERR "kAFS: no volume name specified\n");
		return -EINVAL;
	}

	if ((name[0] != '%' && name[0] != '#') || !name[1]) {
		printk(KERN_ERR "kAFS: unparsable volume name\n");
		return -EINVAL;
	}

	/* determine the type of volume we're looking for */
	params->type = AFSVL_ROVOL;
	params->force = false;
	if (params->rwpath || name[0] == '%') {
		params->type = AFSVL_RWVOL;
		params->force = true;
	}
	name++;

	/* split the cell name out if there is one */
	params->volname = strchr(name, ':');
	if (params->volname) {
		cellname = name;
		cellnamesz = params->volname - name;
		params->volname++;
	} else {
		params->volname = name;
		cellname = NULL;
		cellnamesz = 0;
	}

	/* the volume type is further affected by a possible suffix */
	suffix = strrchr(params->volname, '.');
	if (suffix) {
		if (strcmp(suffix, ".readonly") == 0) {
			params->type = AFSVL_ROVOL;
			params->force = true;
		} else if (strcmp(suffix, ".backup") == 0) {
			params->type = AFSVL_BACKVOL;
			params->force = true;
		} else if (suffix[1] == 0) {
		} else {
			suffix = NULL;
		}
	}

	params->volnamesz = suffix ?
		suffix - params->volname : strlen(params->volname);

	_debug("cell %*.*s [%p]",
	       cellnamesz, cellnamesz, cellname ?: "", params->cell);

	/* lookup the cell record */
	if (cellname || !params->cell) {
		cell = afs_lookup_cell(params->net, cellname, cellnamesz,
				       NULL, false);
		if (IS_ERR(cell)) {
			printk(KERN_ERR "kAFS: unable to lookup cell '%*.*s'\n",
			       cellnamesz, cellnamesz, cellname ?: "");
			return PTR_ERR(cell);
		}
		afs_put_cell(params->net, params->cell);
		params->cell = cell;
	}

	_debug("CELL:%s [%p] VOLUME:%*.*s SUFFIX:%s TYPE:%d%s",
	       params->cell->name, params->cell,
	       params->volnamesz, params->volnamesz, params->volname,
	       suffix ?: "-", params->type, params->force ? " FORCE" : "");

	return 0;
}

/*
 * check a superblock to see if it's the one we're looking for
 */
static int afs_test_super(struct super_block *sb, void *data)
{
	struct afs_super_info *as1 = data;
	struct afs_super_info *as = AFS_FS_S(sb);

	return (as->net_ns == as1->net_ns &&
		as->volume &&
		as->volume->vid == as1->volume->vid);
}

static int afs_dynroot_test_super(struct super_block *sb, void *data)
{
	return false;
}

static int afs_set_super(struct super_block *sb, void *data)
{
	struct afs_super_info *as = data;

	sb->s_fs_info = as;
	return set_anon_super(sb, NULL);
}

/*
 * fill in the superblock
 */
static int afs_fill_super(struct super_block *sb,
			  struct afs_mount_params *params)
{
	struct afs_super_info *as = AFS_FS_S(sb);
	struct afs_fid fid;
	struct inode *inode = NULL;
	int ret;

	_enter("");

	/* fill in the superblock */
	sb->s_blocksize		= PAGE_SIZE;
	sb->s_blocksize_bits	= PAGE_SHIFT;
	sb->s_magic		= AFS_FS_MAGIC;
	sb->s_op		= &afs_super_ops;
	if (!as->dyn_root)
		sb->s_xattr	= afs_xattr_handlers;
	ret = super_setup_bdi(sb);
	if (ret)
		return ret;
	sb->s_bdi->ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_SIZE;

	/* allocate the root inode and dentry */
	if (as->dyn_root) {
		inode = afs_iget_pseudo_dir(sb, true);
		sb->s_flags	|= SB_RDONLY;
	} else {
		sprintf(sb->s_id, "%u", as->volume->vid);
		afs_activate_volume(as->volume);
		fid.vid		= as->volume->vid;
		fid.vnode	= 1;
		fid.unique	= 1;
		inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
	}

	if (IS_ERR(inode))
		return PTR_ERR(inode);

	if (params->autocell || params->dyn_root)
		set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);

	ret = -ENOMEM;
	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		goto error;

	if (params->dyn_root)
		sb->s_d_op = &afs_dynroot_dentry_operations;
	else
		sb->s_d_op = &afs_fs_dentry_operations;

	_leave(" = 0");
	return 0;

error:
	_leave(" = %d", ret);
	return ret;
}

static struct afs_super_info *afs_alloc_sbi(struct afs_mount_params *params)
{
	struct afs_super_info *as;

	as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
	if (as) {
		as->net_ns = get_net(params->net_ns);
		if (params->dyn_root)
			as->dyn_root = true;
		else
			as->cell = afs_get_cell(params->cell);
	}
	return as;
}

static void afs_destroy_sbi(struct afs_super_info *as)
{
	if (as) {
		afs_put_volume(as->cell, as->volume);
		afs_put_cell(afs_net(as->net_ns), as->cell);
		put_net(as->net_ns);
		kfree(as);
	}
}

/*
 * get an AFS superblock
 */
static struct dentry *afs_mount(struct file_system_type *fs_type,
				int flags, const char *dev_name, void *options)
{
	struct afs_mount_params params;
	struct super_block *sb;
	struct afs_volume *candidate;
	struct key *key;
	struct afs_super_info *as;
	int ret;

	_enter(",,%s,%p", dev_name, options);

	memset(&params, 0, sizeof(params));

	ret = -EINVAL;
	if (current->nsproxy->net_ns != &init_net)
		goto error;
	params.net_ns = current->nsproxy->net_ns;
	params.net = afs_net(params.net_ns);
	
	/* parse the options and device name */
	if (options) {
		ret = afs_parse_options(&params, options, &dev_name);
		if (ret < 0)
			goto error;
	}

	if (!params.dyn_root) {
		ret = afs_parse_device_name(&params, dev_name);
		if (ret < 0)
			goto error;

		/* try and do the mount securely */
		key = afs_request_key(params.cell);
		if (IS_ERR(key)) {
			_leave(" = %ld [key]", PTR_ERR(key));
			ret = PTR_ERR(key);
			goto error;
		}
		params.key = key;
	}

	/* allocate a superblock info record */
	ret = -ENOMEM;
	as = afs_alloc_sbi(&params);
	if (!as)
		goto error_key;

	if (!params.dyn_root) {
		/* Assume we're going to need a volume record; at the very
		 * least we can use it to update the volume record if we have
		 * one already.  This checks that the volume exists within the
		 * cell.
		 */
		candidate = afs_create_volume(&params);
		if (IS_ERR(candidate)) {
			ret = PTR_ERR(candidate);
			goto error_as;
		}

		as->volume = candidate;
	}

	/* allocate a deviceless superblock */
	sb = sget(fs_type,
		  as->dyn_root ? afs_dynroot_test_super : afs_test_super,
		  afs_set_super, flags, as);
	if (IS_ERR(sb)) {
		ret = PTR_ERR(sb);
		goto error_as;
	}

	if (!sb->s_root) {
		/* initial superblock/root creation */
		_debug("create");
		ret = afs_fill_super(sb, &params);
		if (ret < 0)
			goto error_sb;
		as = NULL;
		sb->s_flags |= SB_ACTIVE;
	} else {
		_debug("reuse");
		ASSERTCMP(sb->s_flags, &, SB_ACTIVE);
		afs_destroy_sbi(as);
		as = NULL;
	}

	afs_put_cell(params.net, params.cell);
	key_put(params.key);
	_leave(" = 0 [%p]", sb);
	return dget(sb->s_root);

error_sb:
	deactivate_locked_super(sb);
	goto error_key;
error_as:
	afs_destroy_sbi(as);
error_key:
	key_put(params.key);
error:
	afs_put_cell(params.net, params.cell);
	_leave(" = %d", ret);
	return ERR_PTR(ret);
}

static void afs_kill_super(struct super_block *sb)
{
	struct afs_super_info *as = AFS_FS_S(sb);

	/* Clear the callback interests (which will do ilookup5) before
	 * deactivating the superblock.
	 */
	if (as->volume)
		afs_clear_callback_interests(afs_net(as->net_ns),
					     as->volume->servers);
	kill_anon_super(sb);
	if (as->volume)
		afs_deactivate_volume(as->volume);
	afs_destroy_sbi(as);
}

/*
 * Initialise an inode cache slab element prior to any use.  Note that
 * afs_alloc_inode() *must* reset anything that could incorrectly leak from one
 * inode to another.
 */
static void afs_i_init_once(void *_vnode)
{
	struct afs_vnode *vnode = _vnode;

	memset(vnode, 0, sizeof(*vnode));
	inode_init_once(&vnode->vfs_inode);
	mutex_init(&vnode->io_lock);
	mutex_init(&vnode->validate_lock);
	spin_lock_init(&vnode->wb_lock);
	spin_lock_init(&vnode->lock);
	INIT_LIST_HEAD(&vnode->wb_keys);
	INIT_LIST_HEAD(&vnode->pending_locks);
	INIT_LIST_HEAD(&vnode->granted_locks);
	INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work);
	seqlock_init(&vnode->cb_lock);
}

/*
 * allocate an AFS inode struct from our slab cache
 */
static struct inode *afs_alloc_inode(struct super_block *sb)
{
	struct afs_vnode *vnode;

	vnode = kmem_cache_alloc(afs_inode_cachep, GFP_KERNEL);
	if (!vnode)
		return NULL;

	atomic_inc(&afs_count_active_inodes);

	/* Reset anything that shouldn't leak from one inode to the next. */
	memset(&vnode->fid, 0, sizeof(vnode->fid));
	memset(&vnode->status, 0, sizeof(vnode->status));

	vnode->volume		= NULL;
	vnode->lock_key		= NULL;
	vnode->permit_cache	= NULL;
	vnode->cb_interest	= NULL;
#ifdef CONFIG_AFS_FSCACHE
	vnode->cache		= NULL;
#endif

	vnode->flags		= 1 << AFS_VNODE_UNSET;
	vnode->cb_type		= 0;
	vnode->lock_state	= AFS_VNODE_LOCK_NONE;

	_leave(" = %p", &vnode->vfs_inode);
	return &vnode->vfs_inode;
}

static void afs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct afs_vnode *vnode = AFS_FS_I(inode);
	kmem_cache_free(afs_inode_cachep, vnode);
}

/*
 * destroy an AFS inode struct
 */
static void afs_destroy_inode(struct inode *inode)
{
	struct afs_vnode *vnode = AFS_FS_I(inode);

	_enter("%p{%x:%u}", inode, vnode->fid.vid, vnode->fid.vnode);

	_debug("DESTROY INODE %p", inode);

	ASSERTCMP(vnode->cb_interest, ==, NULL);

	call_rcu(&inode->i_rcu, afs_i_callback);
	atomic_dec(&afs_count_active_inodes);
}

/*
 * return information about an AFS volume
 */
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct afs_super_info *as = AFS_FS_S(dentry->d_sb);
	struct afs_fs_cursor fc;
	struct afs_volume_status vs;
	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
	struct key *key;
	int ret;

	buf->f_type	= dentry->d_sb->s_magic;
	buf->f_bsize	= AFS_BLOCK_SIZE;
	buf->f_namelen	= AFSNAMEMAX - 1;

	if (as->dyn_root) {
		buf->f_blocks	= 1;
		buf->f_bavail	= 0;
		buf->f_bfree	= 0;
		return 0;
	}

	key = afs_request_key(vnode->volume->cell);
	if (IS_ERR(key))
		return PTR_ERR(key);

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, vnode, key)) {
		fc.flags |= AFS_FS_CURSOR_NO_VSLEEP;
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = vnode->cb_break + vnode->cb_s_break;
			afs_fs_get_volume_status(&fc, &vs);
		}

		afs_check_for_remote_deletion(&fc, fc.vnode);
		afs_vnode_commit_status(&fc, vnode, fc.cb_break);
		ret = afs_end_vnode_operation(&fc);
	}

	key_put(key);

	if (ret == 0) {
		if (vs.max_quota == 0)
			buf->f_blocks = vs.part_max_blocks;
		else
			buf->f_blocks = vs.max_quota;
		buf->f_bavail = buf->f_bfree = buf->f_blocks - vs.blocks_in_use;
	}

	return ret;
}