summaryrefslogtreecommitdiffstats
path: root/fs/afs/inode.c
blob: 9cedc3fc1b7744679010f4aae412c92925cd3b3a (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
/*
 * Copyright (c) 2002 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 Woodhouse <dwmw2@infradead.org>
 *          David Howells <dhowells@redhat.com>
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/iversion.h>
#include "internal.h"

static const struct inode_operations afs_symlink_inode_operations = {
	.get_link	= page_get_link,
	.listxattr	= afs_listxattr,
};

/*
 * Initialise an inode from the vnode status.
 */
static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key)
{
	struct inode *inode = AFS_VNODE_TO_I(vnode);

	_debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu",
	       vnode->status.type,
	       vnode->status.nlink,
	       (unsigned long long) vnode->status.size,
	       vnode->status.data_version,
	       vnode->status.mode);

	read_seqlock_excl(&vnode->cb_lock);

	afs_update_inode_from_status(vnode, &vnode->status, NULL,
				     AFS_VNODE_NOT_YET_SET);

	switch (vnode->status.type) {
	case AFS_FTYPE_FILE:
		inode->i_mode	= S_IFREG | vnode->status.mode;
		inode->i_op	= &afs_file_inode_operations;
		inode->i_fop	= &afs_file_operations;
		inode->i_mapping->a_ops	= &afs_fs_aops;
		break;
	case AFS_FTYPE_DIR:
		inode->i_mode	= S_IFDIR | vnode->status.mode;
		inode->i_op	= &afs_dir_inode_operations;
		inode->i_fop	= &afs_dir_file_operations;
		inode->i_mapping->a_ops	= &afs_dir_aops;
		break;
	case AFS_FTYPE_SYMLINK:
		/* Symlinks with a mode of 0644 are actually mountpoints. */
		if ((vnode->status.mode & 0777) == 0644) {
			inode->i_flags |= S_AUTOMOUNT;

			set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);

			inode->i_mode	= S_IFDIR | 0555;
			inode->i_op	= &afs_mntpt_inode_operations;
			inode->i_fop	= &afs_mntpt_file_operations;
			inode->i_mapping->a_ops	= &afs_fs_aops;
		} else {
			inode->i_mode	= S_IFLNK | vnode->status.mode;
			inode->i_op	= &afs_symlink_inode_operations;
			inode->i_mapping->a_ops	= &afs_fs_aops;
		}
		inode_nohighmem(inode);
		break;
	default:
		printk("kAFS: AFS vnode with undefined type\n");
		read_sequnlock_excl(&vnode->cb_lock);
		return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type);
	}

	inode->i_blocks		= 0;
	vnode->invalid_before	= vnode->status.data_version;

	read_sequnlock_excl(&vnode->cb_lock);
	return 0;
}

/*
 * Fetch file status from the volume.
 */
int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
{
	struct afs_fs_cursor fc;
	int ret;

	_enter("%s,{%llx:%llu.%u,S=%lx}",
	       vnode->volume->name,
	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique,
	       vnode->flags);

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, vnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = afs_calc_vnode_cb_break(vnode);
			afs_fs_fetch_file_status(&fc, NULL, new_inode);
		}

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

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

/*
 * iget5() comparator
 */
int afs_iget5_test(struct inode *inode, void *opaque)
{
	struct afs_iget_data *data = opaque;
	struct afs_vnode *vnode = AFS_FS_I(inode);

	return memcmp(&vnode->fid, &data->fid, sizeof(data->fid)) == 0;
}

/*
 * iget5() comparator for inode created by autocell operations
 *
 * These pseudo inodes don't match anything.
 */
static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque)
{
	return 0;
}

/*
 * iget5() inode initialiser
 */
static int afs_iget5_set(struct inode *inode, void *opaque)
{
	struct afs_iget_data *data = opaque;
	struct afs_vnode *vnode = AFS_FS_I(inode);

	vnode->fid = data->fid;
	vnode->volume = data->volume;

	/* YFS supports 96-bit vnode IDs, but Linux only supports
	 * 64-bit inode numbers.
	 */
	inode->i_ino = data->fid.vnode;
	inode->i_generation = data->fid.unique;
	return 0;
}

/*
 * Create an inode for a dynamic root directory or an autocell dynamic
 * automount dir.
 */
struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
{
	struct afs_iget_data data;
	struct afs_super_info *as;
	struct afs_vnode *vnode;
	struct inode *inode;
	static atomic_t afs_autocell_ino;

	_enter("");

	as = sb->s_fs_info;
	if (as->volume) {
		data.volume = as->volume;
		data.fid.vid = as->volume->vid;
	}
	if (root) {
		data.fid.vnode = 1;
		data.fid.unique = 1;
	} else {
		data.fid.vnode = atomic_inc_return(&afs_autocell_ino);
		data.fid.unique = 0;
	}

	inode = iget5_locked(sb, data.fid.vnode,
			     afs_iget5_pseudo_dir_test, afs_iget5_set,
			     &data);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	_debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }",
	       inode, inode->i_ino, data.fid.vid, data.fid.vnode,
	       data.fid.unique);

	vnode = AFS_FS_I(inode);

	/* there shouldn't be an existing inode */
	BUG_ON(!(inode->i_state & I_NEW));

	inode->i_size		= 0;
	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
	if (root) {
		inode->i_op	= &afs_dynroot_inode_operations;
		inode->i_fop	= &afs_dynroot_file_operations;
	} else {
		inode->i_op	= &afs_autocell_inode_operations;
	}
	set_nlink(inode, 2);
	inode->i_uid		= GLOBAL_ROOT_UID;
	inode->i_gid		= GLOBAL_ROOT_GID;
	inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode);
	inode->i_blocks		= 0;
	inode_set_iversion_raw(inode, 0);
	inode->i_generation	= 0;

	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
	if (!root) {
		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
		inode->i_flags |= S_AUTOMOUNT;
	}

	inode->i_flags |= S_NOATIME;
	unlock_new_inode(inode);
	_leave(" = %p", inode);
	return inode;
}

/*
 * Get a cache cookie for an inode.
 */
static void afs_get_inode_cache(struct afs_vnode *vnode)
{
#ifdef CONFIG_AFS_FSCACHE
	struct {
		u32 vnode_id;
		u32 unique;
		u32 vnode_id_ext[2];	/* Allow for a 96-bit key */
	} __packed key;
	struct afs_vnode_cache_aux aux;

	if (vnode->status.type == AFS_FTYPE_DIR) {
		vnode->cache = NULL;
		return;
	}

	key.vnode_id		= vnode->fid.vnode;
	key.unique		= vnode->fid.unique;
	key.vnode_id_ext[0]	= vnode->fid.vnode >> 32;
	key.vnode_id_ext[1]	= vnode->fid.vnode_hi;
	aux.data_version	= vnode->status.data_version;

	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
					      &afs_vnode_cache_index_def,
					      &key, sizeof(key),
					      &aux, sizeof(aux),
					      vnode, vnode->status.size, true);
#endif
}

/*
 * inode retrieval
 */
struct inode *afs_iget(struct super_block *sb, struct key *key,
		       struct afs_fid *fid, struct afs_file_status *status,
		       struct afs_callback *cb, struct afs_cb_interest *cbi)
{
	struct afs_iget_data data = { .fid = *fid };
	struct afs_super_info *as;
	struct afs_vnode *vnode;
	struct inode *inode;
	int ret;

	_enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique);

	as = sb->s_fs_info;
	data.volume = as->volume;

	inode = iget5_locked(sb, fid->vnode, afs_iget5_test, afs_iget5_set,
			     &data);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	_debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }",
	       inode, fid->vid, fid->vnode, fid->unique);

	vnode = AFS_FS_I(inode);

	/* deal with an existing inode */
	if (!(inode->i_state & I_NEW)) {
		_leave(" = %p", inode);
		return inode;
	}

	if (!status) {
		/* it's a remotely extant inode */
		ret = afs_fetch_status(vnode, key, true);
		if (ret < 0)
			goto bad_inode;
	} else {
		/* it's an inode we just created */
		memcpy(&vnode->status, status, sizeof(vnode->status));

		if (!cb) {
			/* it's a symlink we just created (the fileserver
			 * didn't give us a callback) */
			vnode->cb_version = 0;
			vnode->cb_type = 0;
			vnode->cb_expires_at = ktime_get();
		} else {
			vnode->cb_version = cb->version;
			vnode->cb_type = cb->type;
			vnode->cb_expires_at = cb->expires_at;
			vnode->cb_interest = afs_get_cb_interest(cbi);
			set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
		}

		vnode->cb_expires_at += ktime_get_real_seconds();
	}

	ret = afs_inode_init_from_status(vnode, key);
	if (ret < 0)
		goto bad_inode;

	afs_get_inode_cache(vnode);

	/* success */
	clear_bit(AFS_VNODE_UNSET, &vnode->flags);
	inode->i_flags |= S_NOATIME;
	unlock_new_inode(inode);
	_leave(" = %p [CB { v=%u t=%u }]", inode, vnode->cb_version, vnode->cb_type);
	return inode;

	/* failure */
bad_inode:
	iget_failed(inode);
	_leave(" = %d [bad]", ret);
	return ERR_PTR(ret);
}

/*
 * mark the data attached to an inode as obsolete due to a write on the server
 * - might also want to ditch all the outstanding writes and dirty pages
 */
void afs_zap_data(struct afs_vnode *vnode)
{
	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);

#ifdef CONFIG_AFS_FSCACHE
	fscache_invalidate(vnode->cache);
#endif

	/* nuke all the non-dirty pages that aren't locked, mapped or being
	 * written back in a regular file and completely discard the pages in a
	 * directory or symlink */
	if (S_ISREG(vnode->vfs_inode.i_mode))
		invalidate_remote_inode(&vnode->vfs_inode);
	else
		invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
}

/*
 * validate a vnode/inode
 * - there are several things we need to check
 *   - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
 *     symlink)
 *   - parent dir metadata changed (security changes)
 *   - dentry data changed (write, truncate)
 *   - dentry metadata changed (security changes)
 */
int afs_validate(struct afs_vnode *vnode, struct key *key)
{
	time64_t now = ktime_get_real_seconds();
	bool valid;
	int ret;

	_enter("{v={%llx:%llu} fl=%lx},%x",
	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
	       key_serial(key));

	/* Quickly check the callback state.  Ideally, we'd use read_seqbegin
	 * here, but we have no way to pass the net namespace to the RCU
	 * cleanup for the server record.
	 */
	read_seqlock_excl(&vnode->cb_lock);

	if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
		if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break ||
		    vnode->cb_v_break != vnode->volume->cb_v_break) {
			vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
			vnode->cb_v_break = vnode->volume->cb_v_break;
			valid = false;
		} else if (vnode->status.type == AFS_FTYPE_DIR &&
			   (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) ||
			    vnode->cb_expires_at - 10 <= now)) {
			valid = false;
		} else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) ||
			   vnode->cb_expires_at - 10 <= now) {
			valid = false;
		} else {
			valid = true;
		}
	} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		valid = true;
	} else {
		vnode->cb_v_break = vnode->volume->cb_v_break;
		valid = false;
	}

	read_sequnlock_excl(&vnode->cb_lock);

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		clear_nlink(&vnode->vfs_inode);

	if (valid)
		goto valid;

	down_write(&vnode->validate_lock);

	/* if the promise has expired, we need to check the server again to get
	 * a new promise - note that if the (parent) directory's metadata was
	 * changed then the security may be different and we may no longer have
	 * access */
	if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
		_debug("not promised");
		ret = afs_fetch_status(vnode, key, false);
		if (ret < 0) {
			if (ret == -ENOENT) {
				set_bit(AFS_VNODE_DELETED, &vnode->flags);
				ret = -ESTALE;
			}
			goto error_unlock;
		}
		_debug("new promise [fl=%lx]", vnode->flags);
	}

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		_debug("file already deleted");
		ret = -ESTALE;
		goto error_unlock;
	}

	/* if the vnode's data version number changed then its contents are
	 * different */
	if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
		afs_zap_data(vnode);
	up_write(&vnode->validate_lock);
valid:
	_leave(" = 0");
	return 0;

error_unlock:
	up_write(&vnode->validate_lock);
	_leave(" = %d", ret);
	return ret;
}

/*
 * read the attributes of an inode
 */
int afs_getattr(const struct path *path, struct kstat *stat,
		u32 request_mask, unsigned int query_flags)
{
	struct inode *inode = d_inode(path->dentry);
	struct afs_vnode *vnode = AFS_FS_I(inode);
	int seq = 0;

	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);

	do {
		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
		generic_fillattr(inode, stat);
	} while (need_seqretry(&vnode->cb_lock, seq));

	done_seqretry(&vnode->cb_lock, seq);
	return 0;
}

/*
 * discard an AFS inode
 */
int afs_drop_inode(struct inode *inode)
{
	_enter("");

	if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags))
		return generic_delete_inode(inode);
	else
		return generic_drop_inode(inode);
}

/*
 * clear an AFS inode
 */
void afs_evict_inode(struct inode *inode)
{
	struct afs_vnode *vnode;

	vnode = AFS_FS_I(inode);

	_enter("{%llx:%llu.%d}",
	       vnode->fid.vid,
	       vnode->fid.vnode,
	       vnode->fid.unique);

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

	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);

	truncate_inode_pages_final(&inode->i_data);
	clear_inode(inode);

	if (vnode->cb_interest) {
		afs_put_cb_interest(afs_i2net(inode), vnode->cb_interest);
		vnode->cb_interest = NULL;
	}

	while (!list_empty(&vnode->wb_keys)) {
		struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next,
						    struct afs_wb_key, vnode_link);
		list_del(&wbk->vnode_link);
		afs_put_wb_key(wbk);
	}

#ifdef CONFIG_AFS_FSCACHE
	{
		struct afs_vnode_cache_aux aux;

		aux.data_version = vnode->status.data_version;
		fscache_relinquish_cookie(vnode->cache, &aux,
					  test_bit(AFS_VNODE_DELETED, &vnode->flags));
		vnode->cache = NULL;
	}
#endif

	afs_put_permits(rcu_access_pointer(vnode->permit_cache));
	key_put(vnode->lock_key);
	vnode->lock_key = NULL;
	_leave("");
}

/*
 * set the attributes of an inode
 */
int afs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct afs_fs_cursor fc;
	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
	struct key *key;
	int ret;

	_enter("{%llx:%llu},{n=%pd},%x",
	       vnode->fid.vid, vnode->fid.vnode, dentry,
	       attr->ia_valid);

	if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
				ATTR_MTIME))) {
		_leave(" = 0 [unsupported]");
		return 0;
	}

	/* flush any dirty data outstanding on a regular file */
	if (S_ISREG(vnode->vfs_inode.i_mode))
		filemap_write_and_wait(vnode->vfs_inode.i_mapping);

	if (attr->ia_valid & ATTR_FILE) {
		key = afs_file_key(attr->ia_file);
	} else {
		key = afs_request_key(vnode->volume->cell);
		if (IS_ERR(key)) {
			ret = PTR_ERR(key);
			goto error;
		}
	}

	ret = -ERESTARTSYS;
	if (afs_begin_vnode_operation(&fc, vnode, key)) {
		while (afs_select_fileserver(&fc)) {
			fc.cb_break = afs_calc_vnode_cb_break(vnode);
			afs_fs_setattr(&fc, attr);
		}

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

	if (!(attr->ia_valid & ATTR_FILE))
		key_put(key);

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