summaryrefslogtreecommitdiffstats
path: root/fs/pnode.c
blob: d15c63e97ef1e6df711c9e78c1e72c77cd69709e (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
/*
 *  linux/fs/pnode.c
 *
 * (C) Copyright IBM Corporation 2005.
 *	Released under GPL v2.
 *	Author : Ram Pai (linuxram@us.ibm.com)
 *
 */
#include <linux/mnt_namespace.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/nsproxy.h>
#include "internal.h"
#include "pnode.h"

/* return the next shared peer mount of @p */
static inline struct mount *next_peer(struct mount *p)
{
	return list_entry(p->mnt_share.next, struct mount, mnt_share);
}

static inline struct mount *first_slave(struct mount *p)
{
	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
}

static inline struct mount *last_slave(struct mount *p)
{
	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
}

static inline struct mount *next_slave(struct mount *p)
{
	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
}

static struct mount *get_peer_under_root(struct mount *mnt,
					 struct mnt_namespace *ns,
					 const struct path *root)
{
	struct mount *m = mnt;

	do {
		/* Check the namespace first for optimization */
		if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root))
			return m;

		m = next_peer(m);
	} while (m != mnt);

	return NULL;
}

/*
 * Get ID of closest dominating peer group having a representative
 * under the given root.
 *
 * Caller must hold namespace_sem
 */
int get_dominating_id(struct mount *mnt, const struct path *root)
{
	struct mount *m;

	for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) {
		struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root);
		if (d)
			return d->mnt_group_id;
	}

	return 0;
}

static int do_make_slave(struct mount *mnt)
{
	struct mount *peer_mnt = mnt, *master = mnt->mnt_master;
	struct mount *slave_mnt;

	/*
	 * slave 'mnt' to a peer mount that has the
	 * same root dentry. If none is available then
	 * slave it to anything that is available.
	 */
	while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
	       peer_mnt->mnt.mnt_root != mnt->mnt.mnt_root) ;

	if (peer_mnt == mnt) {
		peer_mnt = next_peer(mnt);
		if (peer_mnt == mnt)
			peer_mnt = NULL;
	}
	if (mnt->mnt_group_id && IS_MNT_SHARED(mnt) &&
	    list_empty(&mnt->mnt_share))
		mnt_release_group_id(mnt);

	list_del_init(&mnt->mnt_share);
	mnt->mnt_group_id = 0;

	if (peer_mnt)
		master = peer_mnt;

	if (master) {
		list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
			slave_mnt->mnt_master = master;
		list_move(&mnt->mnt_slave, &master->mnt_slave_list);
		list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
		INIT_LIST_HEAD(&mnt->mnt_slave_list);
	} else {
		struct list_head *p = &mnt->mnt_slave_list;
		while (!list_empty(p)) {
                        slave_mnt = list_first_entry(p,
					struct mount, mnt_slave);
			list_del_init(&slave_mnt->mnt_slave);
			slave_mnt->mnt_master = NULL;
		}
	}
	mnt->mnt_master = master;
	CLEAR_MNT_SHARED(mnt);
	return 0;
}

/*
 * vfsmount lock must be held for write
 */
void change_mnt_propagation(struct mount *mnt, int type)
{
	if (type == MS_SHARED) {
		set_mnt_shared(mnt);
		return;
	}
	do_make_slave(mnt);
	if (type != MS_SLAVE) {
		list_del_init(&mnt->mnt_slave);
		mnt->mnt_master = NULL;
		if (type == MS_UNBINDABLE)
			mnt->mnt.mnt_flags |= MNT_UNBINDABLE;
		else
			mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;
	}
}

/*
 * get the next mount in the propagation tree.
 * @m: the mount seen last
 * @origin: the original mount from where the tree walk initiated
 *
 * Note that peer groups form contiguous segments of slave lists.
 * We rely on that in get_source() to be able to find out if
 * vfsmount found while iterating with propagation_next() is
 * a peer of one we'd found earlier.
 */
static struct mount *propagation_next(struct mount *m,
					 struct mount *origin)
{
	/* are there any slaves of this mount? */
	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
		return first_slave(m);

	while (1) {
		struct mount *master = m->mnt_master;

		if (master == origin->mnt_master) {
			struct mount *next = next_peer(m);
			return (next == origin) ? NULL : next;
		} else if (m->mnt_slave.next != &master->mnt_slave_list)
			return next_slave(m);

		/* back at master */
		m = master;
	}
}

static struct mount *skip_propagation_subtree(struct mount *m,
						struct mount *origin)
{
	/*
	 * Advance m such that propagation_next will not return
	 * the slaves of m.
	 */
	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
		m = last_slave(m);

	return m;
}

static struct mount *next_group(struct mount *m, struct mount *origin)
{
	while (1) {
		while (1) {
			struct mount *next;
			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
				return first_slave(m);
			next = next_peer(m);
			if (m->mnt_group_id == origin->mnt_group_id) {
				if (next == origin)
					return NULL;
			} else if (m->mnt_slave.next != &next->mnt_slave)
				break;
			m = next;
		}
		/* m is the last peer */
		while (1) {
			struct mount *master = m->mnt_master;
			if (m->mnt_slave.next != &master->mnt_slave_list)
				return next_slave(m);
			m = next_peer(master);
			if (master->mnt_group_id == origin->mnt_group_id)
				break;
			if (master->mnt_slave.next == &m->mnt_slave)
				break;
			m = master;
		}
		if (m == origin)
			return NULL;
	}
}

/* all accesses are serialized by namespace_sem */
static struct user_namespace *user_ns;
static struct mount *last_dest, *first_source, *last_source, *dest_master;
static struct mountpoint *mp;
static struct hlist_head *list;

static inline bool peers(struct mount *m1, struct mount *m2)
{
	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
}

static int propagate_one(struct mount *m)
{
	struct mount *child;
	int type;
	/* skip ones added by this propagate_mnt() */
	if (IS_MNT_NEW(m))
		return 0;
	/* skip if mountpoint isn't covered by it */
	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
		return 0;
	if (peers(m, last_dest)) {
		type = CL_MAKE_SHARED;
	} else {
		struct mount *n, *p;
		bool done;
		for (n = m; ; n = p) {
			p = n->mnt_master;
			if (p == dest_master || IS_MNT_MARKED(p))
				break;
		}
		do {
			struct mount *parent = last_source->mnt_parent;
			if (last_source == first_source)
				break;
			done = parent->mnt_master == p;
			if (done && peers(n, parent))
				break;
			last_source = last_source->mnt_master;
		} while (!done);

		type = CL_SLAVE;
		/* beginning of peer group among the slaves? */
		if (IS_MNT_SHARED(m))
			type |= CL_MAKE_SHARED;
	}
		
	/* Notice when we are propagating across user namespaces */
	if (m->mnt_ns->user_ns != user_ns)
		type |= CL_UNPRIVILEGED;
	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
	if (IS_ERR(child))
		return PTR_ERR(child);
	child->mnt.mnt_flags &= ~MNT_LOCKED;
	mnt_set_mountpoint(m, mp, child);
	last_dest = m;
	last_source = child;
	if (m->mnt_master != dest_master) {
		read_seqlock_excl(&mount_lock);
		SET_MNT_MARK(m->mnt_master);
		read_sequnlock_excl(&mount_lock);
	}
	hlist_add_head(&child->mnt_hash, list);
	return count_mounts(m->mnt_ns, child);
}

/*
 * mount 'source_mnt' under the destination 'dest_mnt' at
 * dentry 'dest_dentry'. And propagate that mount to
 * all the peer and slave mounts of 'dest_mnt'.
 * Link all the new mounts into a propagation tree headed at
 * source_mnt. Also link all the new mounts using ->mnt_list
 * headed at source_mnt's ->mnt_list
 *
 * @dest_mnt: destination mount.
 * @dest_dentry: destination dentry.
 * @source_mnt: source mount.
 * @tree_list : list of heads of trees to be attached.
 */
int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
		    struct mount *source_mnt, struct hlist_head *tree_list)
{
	struct mount *m, *n;
	int ret = 0;

	/*
	 * we don't want to bother passing tons of arguments to
	 * propagate_one(); everything is serialized by namespace_sem,
	 * so globals will do just fine.
	 */
	user_ns = current->nsproxy->mnt_ns->user_ns;
	last_dest = dest_mnt;
	first_source = source_mnt;
	last_source = source_mnt;
	mp = dest_mp;
	list = tree_list;
	dest_master = dest_mnt->mnt_master;

	/* all peers of dest_mnt, except dest_mnt itself */
	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
		ret = propagate_one(n);
		if (ret)
			goto out;
	}

	/* all slave groups */
	for (m = next_group(dest_mnt, dest_mnt); m;
			m = next_group(m, dest_mnt)) {
		/* everything in that slave group */
		n = m;
		do {
			ret = propagate_one(n);
			if (ret)
				goto out;
			n = next_peer(n);
		} while (n != m);
	}
out:
	read_seqlock_excl(&mount_lock);
	hlist_for_each_entry(n, tree_list, mnt_hash) {
		m = n->mnt_parent;
		if (m->mnt_master != dest_mnt->mnt_master)
			CLEAR_MNT_MARK(m->mnt_master);
	}
	read_sequnlock_excl(&mount_lock);
	return ret;
}

static struct mount *find_topper(struct mount *mnt)
{
	/* If there is exactly one mount covering mnt completely return it. */
	struct mount *child;

	if (!list_is_singular(&mnt->mnt_mounts))
		return NULL;

	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
		return NULL;

	return child;
}

/*
 * return true if the refcount is greater than count
 */
static inline int do_refcount_check(struct mount *mnt, int count)
{
	return mnt_get_count(mnt) > count;
}

/*
 * check if the mount 'mnt' can be unmounted successfully.
 * @mnt: the mount to be checked for unmount
 * NOTE: unmounting 'mnt' would naturally propagate to all
 * other mounts its parent propagates to.
 * Check if any of these mounts that **do not have submounts**
 * have more references than 'refcnt'. If so return busy.
 *
 * vfsmount lock must be held for write
 */
int propagate_mount_busy(struct mount *mnt, int refcnt)
{
	struct mount *m, *child, *topper;
	struct mount *parent = mnt->mnt_parent;

	if (mnt == parent)
		return do_refcount_check(mnt, refcnt);

	/*
	 * quickly check if the current mount can be unmounted.
	 * If not, we don't have to go checking for all other
	 * mounts
	 */
	if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt))
		return 1;

	for (m = propagation_next(parent, parent); m;
	     		m = propagation_next(m, parent)) {
		int count = 1;
		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
		if (!child)
			continue;

		/* Is there exactly one mount on the child that covers
		 * it completely whose reference should be ignored?
		 */
		topper = find_topper(child);
		if (topper)
			count += 1;
		else if (!list_empty(&child->mnt_mounts))
			continue;

		if (do_refcount_check(child, count))
			return 1;
	}
	return 0;
}

/*
 * Clear MNT_LOCKED when it can be shown to be safe.
 *
 * mount_lock lock must be held for write
 */
void propagate_mount_unlock(struct mount *mnt)
{
	struct mount *parent = mnt->mnt_parent;
	struct mount *m, *child;

	BUG_ON(parent == mnt);

	for (m = propagation_next(parent, parent); m;
			m = propagation_next(m, parent)) {
		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
		if (child)
			child->mnt.mnt_flags &= ~MNT_LOCKED;
	}
}

static void umount_one(struct mount *mnt, struct list_head *to_umount)
{
	CLEAR_MNT_MARK(mnt);
	mnt->mnt.mnt_flags |= MNT_UMOUNT;
	list_del_init(&mnt->mnt_child);
	list_del_init(&mnt->mnt_umounting);
	list_move_tail(&mnt->mnt_list, to_umount);
}

/*
 * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
 * parent propagates to.
 */
static bool __propagate_umount(struct mount *mnt,
			       struct list_head *to_umount,
			       struct list_head *to_restore)
{
	bool progress = false;
	struct mount *child;

	/*
	 * The state of the parent won't change if this mount is
	 * already unmounted or marked as without children.
	 */
	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
		goto out;

	/* Verify topper is the only grandchild that has not been
	 * speculatively unmounted.
	 */
	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
			continue;
		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
			continue;
		/* Found a mounted child */
		goto children;
	}

	/* Mark mounts that can be unmounted if not locked */
	SET_MNT_MARK(mnt);
	progress = true;

	/* If a mount is without children and not locked umount it. */
	if (!IS_MNT_LOCKED(mnt)) {
		umount_one(mnt, to_umount);
	} else {
children:
		list_move_tail(&mnt->mnt_umounting, to_restore);
	}
out:
	return progress;
}

static void umount_list(struct list_head *to_umount,
			struct list_head *to_restore)
{
	struct mount *mnt, *child, *tmp;
	list_for_each_entry(mnt, to_umount, mnt_list) {
		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
			/* topper? */
			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
				list_move_tail(&child->mnt_umounting, to_restore);
			else
				umount_one(child, to_umount);
		}
	}
}

static void restore_mounts(struct list_head *to_restore)
{
	/* Restore mounts to a clean working state */
	while (!list_empty(to_restore)) {
		struct mount *mnt, *parent;
		struct mountpoint *mp;

		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
		CLEAR_MNT_MARK(mnt);
		list_del_init(&mnt->mnt_umounting);

		/* Should this mount be reparented? */
		mp = mnt->mnt_mp;
		parent = mnt->mnt_parent;
		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
			mp = parent->mnt_mp;
			parent = parent->mnt_parent;
		}
		if (parent != mnt->mnt_parent)
			mnt_change_mountpoint(parent, mp, mnt);
	}
}

static void cleanup_umount_visitations(struct list_head *visited)
{
	while (!list_empty(visited)) {
		struct mount *mnt =
			list_first_entry(visited, struct mount, mnt_umounting);
		list_del_init(&mnt->mnt_umounting);
	}
}

/*
 * collect all mounts that receive propagation from the mount in @list,
 * and return these additional mounts in the same list.
 * @list: the list of mounts to be unmounted.
 *
 * vfsmount lock must be held for write
 */
int propagate_umount(struct list_head *list)
{
	struct mount *mnt;
	LIST_HEAD(to_restore);
	LIST_HEAD(to_umount);
	LIST_HEAD(visited);

	/* Find candidates for unmounting */
	list_for_each_entry_reverse(mnt, list, mnt_list) {
		struct mount *parent = mnt->mnt_parent;
		struct mount *m;

		/*
		 * If this mount has already been visited it is known that it's
		 * entire peer group and all of their slaves in the propagation
		 * tree for the mountpoint has already been visited and there is
		 * no need to visit them again.
		 */
		if (!list_empty(&mnt->mnt_umounting))
			continue;

		list_add_tail(&mnt->mnt_umounting, &visited);
		for (m = propagation_next(parent, parent); m;
		     m = propagation_next(m, parent)) {
			struct mount *child = __lookup_mnt(&m->mnt,
							   mnt->mnt_mountpoint);
			if (!child)
				continue;

			if (!list_empty(&child->mnt_umounting)) {
				/*
				 * If the child has already been visited it is
				 * know that it's entire peer group and all of
				 * their slaves in the propgation tree for the
				 * mountpoint has already been visited and there
				 * is no need to visit this subtree again.
				 */
				m = skip_propagation_subtree(m, parent);
				continue;
			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
				/*
				 * We have come accross an partially unmounted
				 * mount in list that has not been visited yet.
				 * Remember it has been visited and continue
				 * about our merry way.
				 */
				list_add_tail(&child->mnt_umounting, &visited);
				continue;
			}

			/* Check the child and parents while progress is made */
			while (__propagate_umount(child,
						  &to_umount, &to_restore)) {
				/* Is the parent a umount candidate? */
				child = child->mnt_parent;
				if (list_empty(&child->mnt_umounting))
					break;
			}
		}
	}

	umount_list(&to_umount, &to_restore);
	restore_mounts(&to_restore);
	cleanup_umount_visitations(&visited);
	list_splice_tail(&to_umount, list);

	return 0;
}