super.c 18.6 KB
Newer Older
J. R. Okajima's avatar
J. R. Okajima committed
1
2
3
4
5
6
7
8
9
10
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2005-2019 Junjiro R. Okajima
 */

/*
 * mount and super_block operations
 */

#include <linux/iversion.h>
11
#include <linux/mm.h>
J. R. Okajima's avatar
J. R. Okajima committed
12
#include <linux/seq_file.h>
J. R. Okajima's avatar
J. R. Okajima committed
13
#include <linux/statfs.h>
14
#include <linux/vmalloc.h>
J. R. Okajima's avatar
J. R. Okajima committed
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
#include "aufs.h"

/*
 * super_operations
 */
static struct inode *aufs_alloc_inode(struct super_block *sb __maybe_unused)
{
	struct au_icntnr *c;

	c = au_cache_alloc_icntnr();
	if (c) {
		au_icntnr_init(c);
		inode_set_iversion(&c->vfs_inode, 1); /* sigen(sb); */
		c->iinfo.ii_hinode = NULL;
		return &c->vfs_inode;
	}
	return NULL;
}

static void aufs_destroy_inode_cb(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);

	au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode));
}

static void aufs_destroy_inode(struct inode *inode)
{
	if (!au_is_bad_inode(inode))
		au_iinfo_fin(inode);
	call_rcu(&inode->i_rcu, aufs_destroy_inode_cb);
}

struct inode *au_iget_locked(struct super_block *sb, ino_t ino)
{
	struct inode *inode;
	int err;

	inode = iget_locked(sb, ino);
	if (unlikely(!inode)) {
		inode = ERR_PTR(-ENOMEM);
		goto out;
	}
	if (!(inode->i_state & I_NEW))
		goto out;

J. R. Okajima's avatar
J. R. Okajima committed
61
62
63
	err = au_xigen_new(inode);
	if (!err)
		err = au_iinfo_init(inode);
J. R. Okajima's avatar
J. R. Okajima committed
64
65
66
67
68
69
70
71
72
73
	if (!err)
		inode_inc_iversion(inode);
	else {
		iget_failed(inode);
		inode = ERR_PTR(err);
	}

out:
	/* never return NULL */
	AuDebugOn(!inode);
J. R. Okajima's avatar
J. R. Okajima committed
74
	AuTraceErrPtr(inode);
J. R. Okajima's avatar
J. R. Okajima committed
75
76
77
	return inode;
}

J. R. Okajima's avatar
J. R. Okajima committed
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
/* lock free root dinfo */
static int au_show_brs(struct seq_file *seq, struct super_block *sb)
{
	int err;
	aufs_bindex_t bindex, bbot;
	struct path path;
	struct au_hdentry *hdp;
	struct au_branch *br;
	au_br_perm_str_t perm;

	err = 0;
	bbot = au_sbbot(sb);
	bindex = 0;
	hdp = au_hdentry(au_di(sb->s_root), bindex);
	for (; !err && bindex <= bbot; bindex++, hdp++) {
		br = au_sbr(sb, bindex);
		path.mnt = au_br_mnt(br);
		path.dentry = hdp->hd_dentry;
		err = au_seq_path(seq, &path);
		if (!err) {
			au_optstr_br_perm(&perm, br->br_perm);
			seq_printf(seq, "=%s", perm.a);
			if (bindex != bbot)
				seq_putc(seq, ':');
		}
	}
	if (unlikely(err || seq_has_overflowed(seq)))
		err = -E2BIG;

	return err;
}

110
111
112
113
114
115
116
117
118
119
120
121
122
static void au_gen_fmt(char *fmt, int len __maybe_unused, const char *pat,
		       const char *append)
{
	char *p;

	p = fmt;
	while (*pat != ':')
		*p++ = *pat++;
	*p++ = *pat++;
	strcpy(p, append);
	AuDebugOn(strlen(fmt) >= len);
}

123
124
125
126
static void au_show_wbr_create(struct seq_file *m, int v,
			       struct au_sbinfo *sbinfo)
{
	const char *pat;
127
128
	char fmt[32];
	struct au_wbr_mfs *mfs;
129
130
131
132
133

	AuRwMustAnyLock(&sbinfo->si_rwsem);

	seq_puts(m, ",create=");
	pat = au_optstr_wbr_create(v);
134
	mfs = &sbinfo->si_wbr_mfs;
135
136
	switch (v) {
	case AuWbrCreate_TDP:
137
138
139
	case AuWbrCreate_RR:
	case AuWbrCreate_MFS:
	case AuWbrCreate_PMFS:
140
141
		seq_puts(m, pat);
		break;
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
	case AuWbrCreate_MFSRR:
	case AuWbrCreate_TDMFS:
	case AuWbrCreate_PMFSRR:
		au_gen_fmt(fmt, sizeof(fmt), pat, "%llu");
		seq_printf(m, fmt, mfs->mfsrr_watermark);
		break;
	case AuWbrCreate_MFSV:
	case AuWbrCreate_PMFSV:
		au_gen_fmt(fmt, sizeof(fmt), pat, "%lu");
		seq_printf(m, fmt,
			   jiffies_to_msecs(mfs->mfs_expire)
			   / MSEC_PER_SEC);
		break;
	case AuWbrCreate_MFSRRV:
	case AuWbrCreate_TDMFSV:
	case AuWbrCreate_PMFSRRV:
		au_gen_fmt(fmt, sizeof(fmt), pat, "%llu:%lu");
		seq_printf(m, fmt, mfs->mfsrr_watermark,
			   jiffies_to_msecs(mfs->mfs_expire) / MSEC_PER_SEC);
161
		break;
162
163
	default:
		BUG();
164
165
166
	}
}

J. R. Okajima's avatar
J. R. Okajima committed
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
static int au_show_xino(struct seq_file *seq, struct super_block *sb)
{
#ifdef CONFIG_SYSFS
	return 0;
#else
	int err;
	const int len = sizeof(AUFS_XINO_FNAME) - 1;
	aufs_bindex_t bindex, brid;
	struct qstr *name;
	struct file *f;
	struct dentry *d, *h_root;
	struct au_branch *br;

	AuRwMustAnyLock(&sbinfo->si_rwsem);

	err = 0;
	f = au_sbi(sb)->si_xib;
	if (!f)
		goto out;

	/* stop printing the default xino path on the first writable branch */
	h_root = NULL;
	bindex = au_xi_root(sb, f->f_path.dentry);
	if (bindex >= 0) {
		br = au_sbr_sb(sb, bindex);
		h_root = au_br_dentry(br);
	}

	d = f->f_path.dentry;
	name = &d->d_name;
	/* safe ->d_parent because the file is unlinked */
	if (d->d_parent == h_root
	    && name->len == len
	    && !memcmp(name->name, AUFS_XINO_FNAME, len))
		goto out;

	seq_puts(seq, ",xino=");
	err = au_xino_path(seq, f);

out:
	return err;
#endif
}

J. R. Okajima's avatar
J. R. Okajima committed
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
/* seq_file will re-call me in case of too long string */
static int aufs_show_options(struct seq_file *m, struct dentry *dentry)
{
	int err;
	unsigned int mnt_flags, v;
	struct super_block *sb;
	struct au_sbinfo *sbinfo;

#define AuBool(name, str) do { \
	v = au_opt_test(mnt_flags, name); \
	if (v != au_opt_test(AuOpt_Def, name)) \
		seq_printf(m, ",%s" #str, v ? "" : "no"); \
} while (0)

#define AuStr(name, str) do { \
	v = mnt_flags & AuOptMask_##name; \
	if (v != (AuOpt_Def & AuOptMask_##name)) \
		seq_printf(m, "," #str "=%s", au_optstr_##str(v)); \
} while (0)

#define AuUInt(name, str, val) do { \
	if (val != AUFS_##name##_DEF) \
		seq_printf(m, "," #str "=%u", val); \
} while (0)

	sb = dentry->d_sb;
#if 0
	if (sb->s_flags & SB_I_VERSION)
		seq_puts(m, ",i_version");
#endif

	/* lock free root dinfo */
	si_noflush_read_lock(sb);
	sbinfo = au_sbi(sb);
	seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo));

	mnt_flags = au_mntflags(sb);
	if (au_opt_test(mnt_flags, XINO)) {
		err = au_show_xino(m, sb);
		if (unlikely(err))
			goto out;
	} else
		seq_puts(m, ",noxino");

	AuBool(TRUNC_XINO, trunc_xino);
	AuStr(UDBA, udba);
	AuBool(PLINK, plink);
	AuBool(DIO, dio);

	v = sbinfo->si_wbr_create;
	if (v != AuWbrCreate_Def)
		au_show_wbr_create(m, v, sbinfo);

	v = sbinfo->si_wbr_copyup;
	if (v != AuWbrCopyup_Def)
		seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v));

	v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC;
	AuUInt(RDCACHE, rdcache, v);

	AuUInt(RDBLK, rdblk, sbinfo->si_rdblk);
	AuUInt(RDHASH, rdhash, sbinfo->si_rdhash);

out:
	/* be sure to print "br:" last */
	if (!sysaufs_brs) {
		seq_puts(m, ",br:");
		au_show_brs(m, sb);
	}
	si_read_unlock(sb);
	return 0;

#undef AuBool
#undef AuStr
#undef AuUInt
}

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

static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	int err;
	struct path h_path;
	struct super_block *sb;

	/* lock free root dinfo */
	sb = dentry->d_sb;
	si_noflush_read_lock(sb);
	/* sb->s_root for NFS is unreliable */
	h_path.mnt = au_sbr_mnt(sb, 0);
	h_path.dentry = h_path.mnt->mnt_root;
	err = vfs_statfs(&h_path, buf);
	si_read_unlock(sb);

	if (!err) {
		buf->f_type = AUFS_SUPER_MAGIC;
		buf->f_namelen = AUFS_MAX_NAMELEN;
		memset(&buf->f_fsid, 0, sizeof(buf->f_fsid));
	}
	/* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */

	return err;
}

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

static int aufs_sync_fs(struct super_block *sb, int wait)
{
	int err, e;
	aufs_bindex_t bbot, bindex;
	struct au_branch *br;
	struct super_block *h_sb;

	err = 0;
	si_noflush_read_lock(sb);
	bbot = au_sbbot(sb);
	for (bindex = 0; bindex <= bbot; bindex++) {
		br = au_sbr(sb, bindex);
		if (!au_br_writable(br->br_perm))
			continue;

		h_sb = au_sbr_sb(sb, bindex);
		e = vfsub_sync_filesystem(h_sb, wait);
		if (unlikely(e && !err))
			err = e;
		/* go on even if an error happens */
	}
	si_read_unlock(sb);

	return err;
}

J. R. Okajima's avatar
J. R. Okajima committed
343
344
/* ---------------------------------------------------------------------- */

J. R. Okajima's avatar
J. R. Okajima committed
345
346
347
348
349
350
351
352
353
354
355
356
/* final actions when unmounting a file system */
static void aufs_put_super(struct super_block *sb)
{
	struct au_sbinfo *sbinfo;

	sbinfo = au_sbi(sb);
	if (sbinfo)
		kobject_put(&sbinfo->si_kobj);
}

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

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
void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb,
		     struct super_block *sb, void *arg)
{
	void *array;
	unsigned long long n, sz;

	array = NULL;
	n = 0;
	if (!*hint)
		goto out;

	if (*hint > ULLONG_MAX / sizeof(array)) {
		array = ERR_PTR(-EMFILE);
		pr_err("hint %llu\n", *hint);
		goto out;
	}

	sz = sizeof(array) * *hint;
	array = kzalloc(sz, GFP_NOFS);
	if (unlikely(!array))
		array = vzalloc(sz);
	if (unlikely(!array)) {
		array = ERR_PTR(-ENOMEM);
		goto out;
	}

	n = cb(sb, array, *hint, arg);
	AuDebugOn(n > *hint);

out:
	*hint = n;
	return array;
}

static unsigned long long au_iarray_cb(struct super_block *sb, void *a,
				       unsigned long long max __maybe_unused,
				       void *arg)
{
	unsigned long long n;
	struct inode **p, *inode;
	struct list_head *head;

	n = 0;
	p = a;
	head = arg;
	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry(inode, head, i_sb_list) {
		if (!au_is_bad_inode(inode)
		    && au_ii(inode)->ii_btop >= 0) {
			spin_lock(&inode->i_lock);
			if (atomic_read(&inode->i_count)) {
				au_igrab(inode);
				*p++ = inode;
				n++;
				AuDebugOn(n > max);
			}
			spin_unlock(&inode->i_lock);
		}
	}
	spin_unlock(&sb->s_inode_list_lock);

	return n;
}

struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max)
{
	struct au_sbinfo *sbi;

	sbi = au_sbi(sb);
	*max = au_lcnt_read(&sbi->si_ninodes, /*do_rev*/1);
	return au_array_alloc(max, au_iarray_cb, sb, &sb->s_inodes);
}

void au_iarray_free(struct inode **a, unsigned long long max)
{
	unsigned long long ull;

	for (ull = 0; ull < max; ull++)
		iput(a[ull]);
	kvfree(a);
}

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

J. R. Okajima's avatar
J. R. Okajima committed
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
/*
 * refresh dentry and inode at remount time.
 */
/* todo: consolidate with simple_reval_dpath() and au_reval_for_attr() */
static int au_do_refresh(struct dentry *dentry, unsigned int dir_flags,
		      struct dentry *parent)
{
	int err;

	di_write_lock_child(dentry);
	di_read_lock_parent(parent, AuLock_IR);
	err = au_refresh_dentry(dentry, parent);
	if (!err && dir_flags)
		au_hn_reset(d_inode(dentry), dir_flags);
	di_read_unlock(parent, AuLock_IR);
	di_write_unlock(dentry);

	return err;
}

static int au_do_refresh_d(struct dentry *dentry, unsigned int sigen,
			   struct au_sbinfo *sbinfo,
			   const unsigned int dir_flags)
{
	int err;
	struct dentry *parent;

	err = 0;
	parent = dget_parent(dentry);
	if (!au_digen_test(parent, sigen) && au_digen_test(dentry, sigen)) {
		if (d_really_is_positive(dentry)) {
			if (!d_is_dir(dentry))
				err = au_do_refresh(dentry, /*dir_flags*/0,
						 parent);
			else {
				err = au_do_refresh(dentry, dir_flags, parent);
				if (unlikely(err))
					au_fset_si(sbinfo, FAILED_REFRESH_DIR);
			}
		} else
			err = au_do_refresh(dentry, /*dir_flags*/0, parent);
		AuDbgDentry(dentry);
	}
	dput(parent);

	AuTraceErr(err);
	return err;
}

static int au_refresh_d(struct super_block *sb)
{
	int err, i, j, ndentry, e;
	unsigned int sigen;
	struct au_dcsub_pages dpages;
	struct au_dpage *dpage;
	struct dentry **dentries, *d;
	struct au_sbinfo *sbinfo;
	struct dentry *root = sb->s_root;
	const unsigned int dir_flags = au_hi_flags(d_inode(root), /*isdir*/1);

	err = au_dpages_init(&dpages, GFP_NOFS);
	if (unlikely(err))
		goto out;
	err = au_dcsub_pages(&dpages, root, NULL, NULL);
	if (unlikely(err))
		goto out_dpages;

	sigen = au_sigen(sb);
	sbinfo = au_sbi(sb);
	for (i = 0; i < dpages.ndpage; i++) {
		dpage = dpages.dpages + i;
		dentries = dpage->dentries;
		ndentry = dpage->ndentry;
		for (j = 0; j < ndentry; j++) {
			d = dentries[j];
			e = au_do_refresh_d(d, sigen, sbinfo, dir_flags);
			if (unlikely(e && !err))
				err = e;
			/* go on even err */
		}
	}

out_dpages:
	au_dpages_free(&dpages);
out:
	return err;
}

static int au_refresh_i(struct super_block *sb)
{
	int err, e;
	unsigned int sigen;
	unsigned long long max, ull;
	struct inode *inode, **array;

	array = au_iarray_alloc(sb, &max);
	err = PTR_ERR(array);
	if (IS_ERR(array))
		goto out;

	err = 0;
	sigen = au_sigen(sb);
	for (ull = 0; ull < max; ull++) {
		inode = array[ull];
		if (unlikely(!inode))
			break;
		if (au_iigen(inode, NULL) != sigen) {
			ii_write_lock_child(inode);
			e = au_refresh_hinode_self(inode);
			ii_write_unlock(inode);
			if (unlikely(e)) {
				pr_err("error %d, i%lu\n", e, inode->i_ino);
				if (!err)
					err = e;
				/* go on even if err */
			}
		}
	}

	au_iarray_free(array, max);

out:
	return err;
}

static void au_remount_refresh(struct super_block *sb)
{
	int err, e;
	unsigned int udba;
	aufs_bindex_t bindex, bbot;
	struct dentry *root;
	struct inode *inode;
	struct au_branch *br;

	au_sigen_inc(sb);
	au_fclr_si(au_sbi(sb), FAILED_REFRESH_DIR);

	root = sb->s_root;
	DiMustNoWaiters(root);
	inode = d_inode(root);
	IiMustNoWaiters(inode);

	udba = au_opt_udba(sb);
	bbot = au_sbbot(sb);
	for (bindex = 0; bindex <= bbot; bindex++) {
		br = au_sbr(sb, bindex);
		err = au_hnotify_reset_br(udba, br, br->br_perm);
		if (unlikely(err))
			AuIOErr("hnotify failed on br %d, %d, ignored\n",
				bindex, err);
		/* go on even if err */
	}
	au_hn_reset(inode, au_hi_flags(inode, /*isdir*/1));

	di_write_unlock(root);
	err = au_refresh_d(sb);
	e = au_refresh_i(sb);
	if (unlikely(e && !err))
		err = e;
	/* aufs_write_lock() calls ..._child() */
	di_write_lock_child(root);

	au_cpup_attr_all(inode, /*force*/1);

	if (unlikely(err))
		AuIOErr("refresh failed, ignored, %d\n", err);
}

J. R. Okajima's avatar
J. R. Okajima committed
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
/* stop extra interpretation of errno in mount(8), and strange error messages */
static int cvt_err(int err)
{
	AuTraceErr(err);

	switch (err) {
	case -ENOENT:
	case -ENOTDIR:
	case -EEXIST:
	case -EIO:
		err = -EINVAL;
	}
	return err;
}

J. R. Okajima's avatar
J. R. Okajima committed
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
static int aufs_remount_fs(struct super_block *sb, int *flags, char *data)
{
	int err, do_dx;
	unsigned int mntflags;
	struct au_opts opts = {
		.opt = NULL
	};
	struct dentry *root;
	struct inode *inode;
	struct au_sbinfo *sbinfo;

	err = 0;
	root = sb->s_root;
	if (!data || !*data) {
		err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
		if (!err) {
			di_write_lock_child(root);
			err = au_opts_verify(sb, *flags, /*pending*/0);
			aufs_write_unlock(root);
		}
		goto out;
	}

	err = -ENOMEM;
	opts.opt = (void *)__get_free_page(GFP_NOFS);
	if (unlikely(!opts.opt))
		goto out;
	opts.max_opt = PAGE_SIZE / sizeof(*opts.opt);
	opts.flags = AuOpts_REMOUNT;
	opts.sb_flags = *flags;

	/* parse it before aufs lock */
	err = au_opts_parse(sb, data, &opts);
	if (unlikely(err))
		goto out_opts;

	sbinfo = au_sbi(sb);
	inode = d_inode(root);
	inode_lock(inode);
	err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
	if (unlikely(err))
		goto out_mtx;
	di_write_lock_child(root);

	/* au_opts_remount() may return an error */
	err = au_opts_remount(sb, &opts);
	au_opts_free(&opts);

	if (au_ftest_opts(opts.flags, REFRESH))
		au_remount_refresh(sb);

	if (au_ftest_opts(opts.flags, REFRESH_DYAOP)) {
		mntflags = au_mntflags(sb);
		do_dx = !!au_opt_test(mntflags, DIO);
		au_dy_arefresh(do_dx);
	}

	aufs_write_unlock(root);

out_mtx:
	inode_unlock(inode);
out_opts:
	free_page((unsigned long)opts.opt);
out:
	err = cvt_err(err);
	AuTraceErr(err);
	return err;
}

J. R. Okajima's avatar
J. R. Okajima committed
693
694
695
696
static const struct super_operations aufs_sop = {
	.alloc_inode	= aufs_alloc_inode,
	.destroy_inode	= aufs_destroy_inode,
	/* always deleting, no clearing */
J. R. Okajima's avatar
J. R. Okajima committed
697
	.drop_inode	= generic_delete_inode,
J. R. Okajima's avatar
J. R. Okajima committed
698
699
	.show_options	= aufs_show_options,
	.statfs		= aufs_statfs,
J. R. Okajima's avatar
J. R. Okajima committed
700
	.put_super	= aufs_put_super,
J. R. Okajima's avatar
J. R. Okajima committed
701
	.sync_fs	= aufs_sync_fs,
J. R. Okajima's avatar
J. R. Okajima committed
702
	.remount_fs	= aufs_remount_fs
J. R. Okajima's avatar
J. R. Okajima committed
703
};
J. R. Okajima's avatar
J. R. Okajima committed
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

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

static int alloc_root(struct super_block *sb)
{
	int err;
	struct inode *inode;
	struct dentry *root;

	err = -ENOMEM;
	inode = au_iget_locked(sb, AUFS_ROOT_INO);
	err = PTR_ERR(inode);
	if (IS_ERR(inode))
		goto out;

	inode->i_op = &simple_dir_inode_operations; /* replace later */
	inode->i_fop = &simple_dir_operations; /* replace later */
	inode->i_mode = S_IFDIR;
	set_nlink(inode, 2);
	unlock_new_inode(inode);

	root = d_make_root(inode);
	if (unlikely(!root))
		goto out;
	err = PTR_ERR(root);
	if (IS_ERR(root))
		goto out;

	err = au_di_init(root);
	if (!err) {
		sb->s_root = root;
		return 0; /* success */
	}
	dput(root);

out:
	return err;
}

static int aufs_fill_super(struct super_block *sb, void *raw_data,
			   int silent __maybe_unused)
{
	int err;
	struct au_opts opts = {
		.opt = NULL
	};
	struct dentry *root;
	struct inode *inode;
	char *arg = raw_data;

	if (unlikely(!arg || !*arg)) {
		err = -EINVAL;
		pr_err("no arg\n");
		goto out;
	}

	err = -ENOMEM;
	opts.opt = (void *)__get_free_page(GFP_NOFS);
	if (unlikely(!opts.opt))
		goto out;
	opts.max_opt = PAGE_SIZE / sizeof(*opts.opt);
	opts.sb_flags = sb->s_flags;

	err = au_si_alloc(sb);
	if (unlikely(err))
		goto out_opts;

	/* all timestamps always follow the ones on the branch */
	sb->s_flags |= SB_NOATIME | SB_NODIRATIME;
	sb->s_flags |= SB_I_VERSION; /* do we really need this? */
	sb->s_op = &aufs_sop;
J. R. Okajima's avatar
J. R. Okajima committed
775
	sb->s_d_op = &aufs_dop;
J. R. Okajima's avatar
J. R. Okajima committed
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
	sb->s_magic = AUFS_SUPER_MAGIC;
	sb->s_maxbytes = 0;
	sb->s_stack_depth = 1;

	err = alloc_root(sb);
	if (unlikely(err)) {
		si_write_unlock(sb);
		goto out_info;
	}
	root = sb->s_root;
	inode = d_inode(root);

	/*
	 * actually we can parse options regardless aufs lock here.
	 * but at remount time, parsing must be done before aufs lock.
	 * so we follow the same rule.
	 */
	ii_write_lock_parent(inode);
	aufs_write_unlock(root);
	err = au_opts_parse(sb, arg, &opts);
	if (unlikely(err))
		goto out_root;

	/* lock vfs_inode first, then aufs. */
	inode_lock(inode);
	aufs_write_lock(root);
	err = au_opts_mount(sb, &opts);
	au_opts_free(&opts);
	aufs_write_unlock(root);
	inode_unlock(inode);
	if (!err)
		goto out_opts; /* success */

out_root:
	dput(root);
	sb->s_root = NULL;
out_info:
	kobject_put(&au_sbi(sb)->si_kobj);
	sb->s_fs_info = NULL;
out_opts:
	free_page((unsigned long)opts.opt);
out:
	AuTraceErr(err);
	err = cvt_err(err);
	AuTraceErr(err);
	return err;
}

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

static struct dentry *aufs_mount(struct file_system_type *fs_type, int flags,
				 const char *dev_name __maybe_unused,
				 void *raw_data)
{
	struct dentry *root;

	/* all timestamps always follow the ones on the branch */
	/* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */
	root = mount_nodev(fs_type, flags, raw_data, aufs_fill_super);
	if (IS_ERR(root))
		goto out;

	au_sbilist_add(root->d_sb);

out:
	return root;
}

static void aufs_kill_sb(struct super_block *sb)
{
	struct au_sbinfo *sbinfo;

	sbinfo = au_sbi(sb);
	if (sbinfo) {
		au_sbilist_del(sb);
		aufs_write_lock(sb->s_root);
		if (sbinfo->si_wbr_create_ops->fin)
			sbinfo->si_wbr_create_ops->fin(sb);
J. R. Okajima's avatar
J. R. Okajima committed
854
855
856
857
		if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) {
			au_opt_set_udba(sbinfo->si_mntflags, UDBA_NONE);
			au_remount_refresh(sb);
		}
J. R. Okajima's avatar
J. R. Okajima committed
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
		if (au_opt_test(sbinfo->si_mntflags, PLINK))
			au_plink_put(sb, /*verbose*/1);
		au_xino_clr(sb);
		sbinfo->si_sb = NULL;
		aufs_write_unlock(sb->s_root);
		au_nwt_flush(&sbinfo->si_nowait);
	}
	kill_anon_super(sb);
}

struct file_system_type aufs_fs_type = {
	.name		= AUFS_FSTYPE,
	.mount		= aufs_mount,
	.kill_sb	= aufs_kill_sb,
	/* no need to __module_get() and module_put(). */
	.owner		= THIS_MODULE,
};