summaryrefslogtreecommitdiff
path: root/fs/aufs/i_op_del.c
blob: 3cd4c7b198fca31ddb359763e3a2b1192b4fb61a (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
/*
 * Copyright (C) 2005-2015 Junjiro R. Okajima
 */

/*
 * inode operations (del entry)
 */

#include "aufs.h"

/*
 * decide if a new whiteout for @dentry is necessary or not.
 * when it is necessary, prepare the parent dir for the upper branch whose
 * branch index is @bcpup for creation. the actual creation of the whiteout will
 * be done by caller.
 * return value:
 * 0: wh is unnecessary
 * plus: wh is necessary
 * minus: error
 */
int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
{
	int need_wh, err;
	aufs_bindex_t bstart;
	struct super_block *sb;

	sb = dentry->d_sb;
	bstart = au_dbstart(dentry);
	if (*bcpup < 0) {
		*bcpup = bstart;
		if (au_test_ro(sb, bstart, d_inode(dentry))) {
			err = AuWbrCopyup(au_sbi(sb), dentry);
			*bcpup = err;
			if (unlikely(err < 0))
				goto out;
		}
	} else
		AuDebugOn(bstart < *bcpup
			  || au_test_ro(sb, *bcpup, d_inode(dentry)));
	AuDbg("bcpup %d, bstart %d\n", *bcpup, bstart);

	if (*bcpup != bstart) {
		err = au_cpup_dirs(dentry, *bcpup);
		if (unlikely(err))
			goto out;
		need_wh = 1;
	} else {
		struct au_dinfo *dinfo, *tmp;

		need_wh = -ENOMEM;
		dinfo = au_di(dentry);
		tmp = au_di_alloc(sb, AuLsc_DI_TMP);
		if (tmp) {
			au_di_cp(tmp, dinfo);
			au_di_swap(tmp, dinfo);
			/* returns the number of positive dentries */
			need_wh = au_lkup_dentry(dentry, bstart + 1, /*type*/0);
			au_di_swap(tmp, dinfo);
			au_rw_write_unlock(&tmp->di_rwsem);
			au_di_free(tmp);
		}
	}
	AuDbg("need_wh %d\n", need_wh);
	err = need_wh;

out:
	return err;
}

/*
 * simple tests for the del-entry operations.
 * following the checks in vfs, plus the parent-child relationship.
 */
int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
	       struct dentry *h_parent, int isdir)
{
	int err;
	umode_t h_mode;
	struct dentry *h_dentry, *h_latest;
	struct inode *h_inode;

	h_dentry = au_h_dptr(dentry, bindex);
	if (d_really_is_positive(dentry)) {
		err = -ENOENT;
		if (unlikely(d_is_negative(h_dentry)))
			goto out;
		h_inode = d_inode(h_dentry);
		if (unlikely(!h_inode->i_nlink))
			goto out;

		h_mode = h_inode->i_mode;
		if (!isdir) {
			err = -EISDIR;
			if (unlikely(S_ISDIR(h_mode)))
				goto out;
		} else if (unlikely(!S_ISDIR(h_mode))) {
			err = -ENOTDIR;
			goto out;
		}
	} else {
		/* rename(2) case */
		err = -EIO;
		if (unlikely(d_is_positive(h_dentry)))
			goto out;
	}

	err = -ENOENT;
	/* expected parent dir is locked */
	if (unlikely(h_parent != h_dentry->d_parent))
		goto out;
	err = 0;

	/*
	 * rmdir a dir may break the consistency on some filesystem.
	 * let's try heavy test.
	 */
	err = -EACCES;
	if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)
		     && au_test_h_perm(d_inode(h_parent),
				       MAY_EXEC | MAY_WRITE)))
		goto out;

	h_latest = au_sio_lkup_one(&dentry->d_name, h_parent);
	err = -EIO;
	if (IS_ERR(h_latest))
		goto out;
	if (h_latest == h_dentry)
		err = 0;
	dput(h_latest);

out:
	return err;
}

/*
 * decide the branch where we operate for @dentry. the branch index will be set
 * @rbcpup. after diciding it, 'pin' it and store the timestamps of the parent
 * dir for reverting.
 * when a new whiteout is necessary, create it.
 */
static struct dentry*
lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
		    struct au_dtime *dt, struct au_pin *pin)
{
	struct dentry *wh_dentry;
	struct super_block *sb;
	struct path h_path;
	int err, need_wh;
	unsigned int udba;
	aufs_bindex_t bcpup;

	need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
	wh_dentry = ERR_PTR(need_wh);
	if (unlikely(need_wh < 0))
		goto out;

	sb = dentry->d_sb;
	udba = au_opt_udba(sb);
	bcpup = *rbcpup;
	err = au_pin(pin, dentry, bcpup, udba,
		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
	wh_dentry = ERR_PTR(err);
	if (unlikely(err))
		goto out;

	h_path.dentry = au_pinned_h_parent(pin);
	if (udba != AuOpt_UDBA_NONE
	    && au_dbstart(dentry) == bcpup) {
		err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
		wh_dentry = ERR_PTR(err);
		if (unlikely(err))
			goto out_unpin;
	}

	h_path.mnt = au_sbr_mnt(sb, bcpup);
	au_dtime_store(dt, au_pinned_parent(pin), &h_path);
	wh_dentry = NULL;
	if (!need_wh)
		goto out; /* success, no need to create whiteout */

	wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
	if (IS_ERR(wh_dentry))
		goto out_unpin;

	/* returns with the parent is locked and wh_dentry is dget-ed */
	goto out; /* success */

out_unpin:
	au_unpin(pin);
out:
	return wh_dentry;
}

/*
 * when removing a dir, rename it to a unique temporary whiteout-ed name first
 * in order to be revertible and save time for removing many child whiteouts
 * under the dir.
 * returns 1 when there are too many child whiteout and caller should remove
 * them asynchronously. returns 0 when the number of children is enough small to
 * remove now or the branch fs is a remote fs.
 * otherwise return an error.
 */
static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
			   struct au_nhash *whlist, struct inode *dir)
{
	int rmdir_later, err, dirwh;
	struct dentry *h_dentry;
	struct super_block *sb;
	struct inode *inode;

	sb = dentry->d_sb;
	SiMustAnyLock(sb);
	h_dentry = au_h_dptr(dentry, bindex);
	err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
	if (unlikely(err))
		goto out;

	/* stop monitoring */
	inode = d_inode(dentry);
	au_hn_free(au_hi(inode, bindex));

	if (!au_test_fs_remote(h_dentry->d_sb)) {
		dirwh = au_sbi(sb)->si_dirwh;
		rmdir_later = (dirwh <= 1);
		if (!rmdir_later)
			rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
							      dirwh);
		if (rmdir_later)
			return rmdir_later;
	}

	err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
	if (unlikely(err)) {
		AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
			h_dentry, bindex, err);
		err = 0;
	}

out:
	AuTraceErr(err);
	return err;
}

/*
 * final procedure for deleting a entry.
 * maintain dentry and iattr.
 */
static void epilog(struct inode *dir, struct dentry *dentry,
		   aufs_bindex_t bindex)
{
	struct inode *inode;

	inode = d_inode(dentry);
	d_drop(dentry);
	inode->i_ctime = dir->i_ctime;

	au_dir_ts(dir, bindex);
	dir->i_version++;
}

/*
 * when an error happened, remove the created whiteout and revert everything.
 */
static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
		     aufs_bindex_t bwh, struct dentry *wh_dentry,
		     struct dentry *dentry, struct au_dtime *dt)
{
	int rerr;
	struct path h_path = {
		.dentry	= wh_dentry,
		.mnt	= au_sbr_mnt(dir->i_sb, bindex)
	};

	rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
	if (!rerr) {
		au_set_dbwh(dentry, bwh);
		au_dtime_revert(dt);
		return 0;
	}

	AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
	return -EIO;
}

/* ---------------------------------------------------------------------- */

int aufs_unlink(struct inode *dir, struct dentry *dentry)
{
	int err;
	aufs_bindex_t bwh, bindex, bstart;
	struct inode *inode, *h_dir, *delegated;
	struct dentry *parent, *wh_dentry;
	/* to reuduce stack size */
	struct {
		struct au_dtime dt;
		struct au_pin pin;
		struct path h_path;
	} *a;

	IMustLock(dir);

	err = -ENOMEM;
	a = kmalloc(sizeof(*a), GFP_NOFS);
	if (unlikely(!a))
		goto out;

	err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
	if (unlikely(err))
		goto out_free;
	err = au_d_hashed_positive(dentry);
	if (unlikely(err))
		goto out_unlock;
	inode = d_inode(dentry);
	IMustLock(inode);
	err = -EISDIR;
	if (unlikely(d_is_dir(dentry)))
		goto out_unlock; /* possible? */

	bstart = au_dbstart(dentry);
	bwh = au_dbwh(dentry);
	bindex = -1;
	parent = dentry->d_parent; /* dir inode is locked */
	di_write_lock_parent(parent);
	wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
					&a->pin);
	err = PTR_ERR(wh_dentry);
	if (IS_ERR(wh_dentry))
		goto out_parent;

	a->h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
	a->h_path.dentry = au_h_dptr(dentry, bstart);
	dget(a->h_path.dentry);
	if (bindex == bstart) {
		h_dir = au_pinned_h_dir(&a->pin);
		delegated = NULL;
		err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
		if (unlikely(err == -EWOULDBLOCK)) {
			pr_warn("cannot retry for NFSv4 delegation"
				" for an internal unlink\n");
			iput(delegated);
		}
	} else {
		/* dir inode is locked */
		h_dir = d_inode(wh_dentry->d_parent);
		IMustLock(h_dir);
		err = 0;
	}

	if (!err) {
		vfsub_drop_nlink(inode);
		epilog(dir, dentry, bindex);

		/* update target timestamps */
		if (bindex == bstart) {
			vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
			/*ignore*/
			inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime;
		} else
			/* todo: this timestamp may be reverted later */
			inode->i_ctime = h_dir->i_ctime;
		goto out_unpin; /* success */
	}

	/* revert */
	if (wh_dentry) {
		int rerr;

		rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
				 &a->dt);
		if (rerr)
			err = rerr;
	}

out_unpin:
	au_unpin(&a->pin);
	dput(wh_dentry);
	dput(a->h_path.dentry);
out_parent:
	di_write_unlock(parent);
out_unlock:
	aufs_read_unlock(dentry, AuLock_DW);
out_free:
	kfree(a);
out:
	return err;
}

int aufs_rmdir(struct inode *dir, struct dentry *dentry)
{
	int err, rmdir_later;
	aufs_bindex_t bwh, bindex, bstart;
	struct inode *inode;
	struct dentry *parent, *wh_dentry, *h_dentry;
	struct au_whtmp_rmdir *args;
	/* to reuduce stack size */
	struct {
		struct au_dtime dt;
		struct au_pin pin;
	} *a;

	IMustLock(dir);

	err = -ENOMEM;
	a = kmalloc(sizeof(*a), GFP_NOFS);
	if (unlikely(!a))
		goto out;

	err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
	if (unlikely(err))
		goto out_free;
	err = au_alive_dir(dentry);
	if (unlikely(err))
		goto out_unlock;
	inode = d_inode(dentry);
	IMustLock(inode);
	err = -ENOTDIR;
	if (unlikely(!d_is_dir(dentry)))
		goto out_unlock; /* possible? */

	err = -ENOMEM;
	args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
	if (unlikely(!args))
		goto out_unlock;

	parent = dentry->d_parent; /* dir inode is locked */
	di_write_lock_parent(parent);
	err = au_test_empty(dentry, &args->whlist);
	if (unlikely(err))
		goto out_parent;

	bstart = au_dbstart(dentry);
	bwh = au_dbwh(dentry);
	bindex = -1;
	wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
					&a->pin);
	err = PTR_ERR(wh_dentry);
	if (IS_ERR(wh_dentry))
		goto out_parent;

	h_dentry = au_h_dptr(dentry, bstart);
	dget(h_dentry);
	rmdir_later = 0;
	if (bindex == bstart) {
		err = renwh_and_rmdir(dentry, bstart, &args->whlist, dir);
		if (err > 0) {
			rmdir_later = err;
			err = 0;
		}
	} else {
		/* stop monitoring */
		au_hn_free(au_hi(inode, bstart));

		/* dir inode is locked */
		IMustLock(d_inode(wh_dentry->d_parent));
		err = 0;
	}

	if (!err) {
		vfsub_dead_dir(inode);
		au_set_dbdiropq(dentry, -1);
		epilog(dir, dentry, bindex);

		if (rmdir_later) {
			au_whtmp_kick_rmdir(dir, bstart, h_dentry, args);
			args = NULL;
		}

		goto out_unpin; /* success */
	}

	/* revert */
	AuLabel(revert);
	if (wh_dentry) {
		int rerr;

		rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
				 &a->dt);
		if (rerr)
			err = rerr;
	}

out_unpin:
	au_unpin(&a->pin);
	dput(wh_dentry);
	dput(h_dentry);
out_parent:
	di_write_unlock(parent);
	if (args)
		au_whtmp_rmdir_free(args);
out_unlock:
	aufs_read_unlock(dentry, AuLock_DW);
out_free:
	kfree(a);
out:
	AuTraceErr(err);
	return err;
}