summaryrefslogtreecommitdiff
path: root/fs/kernfs/mount.c
blob: c4bf26142eec9baf2d955166ccb892705a1834a8 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * fs/kernfs/mount.c - kernfs mount implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
 */

#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/seq_file.h>
#include <linux/exportfs.h>
#include <linux/uuid.h>
#include <linux/statfs.h>

#include "kernfs-internal.h"

struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
struct kernfs_global_locks *kernfs_locks;

static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
{
	struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
	struct kernfs_syscall_ops *scops = root->syscall_ops;

	if (scops && scops->show_options)
		return scops->show_options(sf, root);
	return 0;
}

static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
{
	struct kernfs_node *node = kernfs_dentry_node(dentry);
	struct kernfs_root *root = kernfs_root(node);
	struct kernfs_syscall_ops *scops = root->syscall_ops;

	if (scops && scops->show_path)
		return scops->show_path(sf, node, root);

	seq_dentry(sf, dentry, " \t\n\\");
	return 0;
}

static int kernfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	simple_statfs(dentry, buf);
	buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b);
	return 0;
}

const struct super_operations kernfs_sops = {
	.statfs		= kernfs_statfs,
	.drop_inode	= generic_delete_inode,
	.evict_inode	= kernfs_evict_inode,

	.show_options	= kernfs_sop_show_options,
	.show_path	= kernfs_sop_show_path,
};

static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
			    struct inode *parent)
{
	struct kernfs_node *kn = inode->i_private;

	if (*max_len < 2) {
		*max_len = 2;
		return FILEID_INVALID;
	}

	*max_len = 2;
	*(u64 *)fh = kn->id;
	return FILEID_KERNFS;
}

static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
					    struct fid *fid, int fh_len,
					    int fh_type, bool get_parent)
{
	struct kernfs_super_info *info = kernfs_info(sb);
	struct kernfs_node *kn;
	struct inode *inode;
	u64 id;

	if (fh_len < 2)
		return NULL;

	switch (fh_type) {
	case FILEID_KERNFS:
		id = *(u64 *)fid;
		break;
	case FILEID_INO32_GEN:
	case FILEID_INO32_GEN_PARENT:
		/*
		 * blk_log_action() exposes "LOW32,HIGH32" pair without
		 * type and userland can call us with generic fid
		 * constructed from them.  Combine it back to ID.  See
		 * blk_log_action().
		 */
		id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
		break;
	default:
		return NULL;
	}

	kn = kernfs_find_and_get_node_by_id(info->root, id);
	if (!kn)
		return ERR_PTR(-ESTALE);

	if (get_parent) {
		struct kernfs_node *parent;

		parent = kernfs_get_parent(kn);
		kernfs_put(kn);
		kn = parent;
		if (!kn)
			return ERR_PTR(-ESTALE);
	}

	inode = kernfs_get_inode(sb, kn);
	kernfs_put(kn);
	if (!inode)
		return ERR_PTR(-ESTALE);

	return d_obtain_alias(inode);
}

static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
					  struct fid *fid, int fh_len,
					  int fh_type)
{
	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
}

static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
					  struct fid *fid, int fh_len,
					  int fh_type)
{
	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
}

static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
{
	struct kernfs_node *kn = kernfs_dentry_node(child);

	return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent));
}

static const struct export_operations kernfs_export_ops = {
	.encode_fh	= kernfs_encode_fh,
	.fh_to_dentry	= kernfs_fh_to_dentry,
	.fh_to_parent	= kernfs_fh_to_parent,
	.get_parent	= kernfs_get_parent_dentry,
};

/**
 * kernfs_root_from_sb - determine kernfs_root associated with a super_block
 * @sb: the super_block in question
 *
 * Return: the kernfs_root associated with @sb.  If @sb is not a kernfs one,
 * %NULL is returned.
 */
struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
{
	if (sb->s_op == &kernfs_sops)
		return kernfs_info(sb)->root;
	return NULL;
}

/*
 * find the next ancestor in the path down to @child, where @parent was the
 * ancestor whose descendant we want to find.
 *
 * Say the path is /a/b/c/d.  @child is d, @parent is %NULL.  We return the root
 * node.  If @parent is b, then we return the node for c.
 * Passing in d as @parent is not ok.
 */
static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
					      struct kernfs_node *parent)
{
	if (child == parent) {
		pr_crit_once("BUG in find_next_ancestor: called with parent == child");
		return NULL;
	}

	while (child->parent != parent) {
		if (!child->parent)
			return NULL;
		child = child->parent;
	}

	return child;
}

/**
 * kernfs_node_dentry - get a dentry for the given kernfs_node
 * @kn: kernfs_node for which a dentry is needed
 * @sb: the kernfs super_block
 *
 * Return: the dentry pointer
 */
struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
				  struct super_block *sb)
{
	struct dentry *dentry;
	struct kernfs_node *knparent = NULL;

	BUG_ON(sb->s_op != &kernfs_sops);

	dentry = dget(sb->s_root);

	/* Check if this is the root kernfs_node */
	if (!kn->parent)
		return dentry;

	knparent = find_next_ancestor(kn, NULL);
	if (WARN_ON(!knparent)) {
		dput(dentry);
		return ERR_PTR(-EINVAL);
	}

	do {
		struct dentry *dtmp;
		struct kernfs_node *kntmp;

		if (kn == knparent)
			return dentry;
		kntmp = find_next_ancestor(kn, knparent);
		if (WARN_ON(!kntmp)) {
			dput(dentry);
			return ERR_PTR(-EINVAL);
		}
		dtmp = lookup_positive_unlocked(kntmp->name, dentry,
					       strlen(kntmp->name));
		dput(dentry);
		if (IS_ERR(dtmp))
			return dtmp;
		knparent = kntmp;
		dentry = dtmp;
	} while (true);
}

static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc)
{
	struct kernfs_super_info *info = kernfs_info(sb);
	struct kernfs_root *kf_root = kfc->root;
	struct inode *inode;
	struct dentry *root;

	info->sb = sb;
	/* Userspace would break if executables or devices appear on sysfs */
	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
	sb->s_blocksize = PAGE_SIZE;
	sb->s_blocksize_bits = PAGE_SHIFT;
	sb->s_magic = kfc->magic;
	sb->s_op = &kernfs_sops;
	sb->s_xattr = kernfs_xattr_handlers;
	if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
		sb->s_export_op = &kernfs_export_ops;
	sb->s_time_gran = 1;

	/* sysfs dentries and inodes don't require IO to create */
	sb->s_shrink.seeks = 0;

	/* get root inode, initialize and unlock it */
	down_read(&kf_root->kernfs_rwsem);
	inode = kernfs_get_inode(sb, info->root->kn);
	up_read(&kf_root->kernfs_rwsem);
	if (!inode) {
		pr_debug("kernfs: could not get root inode\n");
		return -ENOMEM;
	}

	/* instantiate and link root dentry */
	root = d_make_root(inode);
	if (!root) {
		pr_debug("%s: could not get root dentry!\n", __func__);
		return -ENOMEM;
	}
	sb->s_root = root;
	sb->s_d_op = &kernfs_dops;
	return 0;
}

static int kernfs_test_super(struct super_block *sb, struct fs_context *fc)
{
	struct kernfs_super_info *sb_info = kernfs_info(sb);
	struct kernfs_super_info *info = fc->s_fs_info;

	return sb_info->root == info->root && sb_info->ns == info->ns;
}

static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
{
	struct kernfs_fs_context *kfc = fc->fs_private;

	kfc->ns_tag = NULL;
	return set_anon_super_fc(sb, fc);
}

/**
 * kernfs_super_ns - determine the namespace tag of a kernfs super_block
 * @sb: super_block of interest
 *
 * Return: the namespace tag associated with kernfs super_block @sb.
 */
const void *kernfs_super_ns(struct super_block *sb)
{
	struct kernfs_super_info *info = kernfs_info(sb);

	return info->ns;
}

/**
 * kernfs_get_tree - kernfs filesystem access/retrieval helper
 * @fc: The filesystem context.
 *
 * This is to be called from each kernfs user's fs_context->ops->get_tree()
 * implementation, which should set the specified ->@fs_type and ->@flags, and
 * specify the hierarchy and namespace tag to mount via ->@root and ->@ns,
 * respectively.
 *
 * Return: %0 on success, -errno on failure.
 */
int kernfs_get_tree(struct fs_context *fc)
{
	struct kernfs_fs_context *kfc = fc->fs_private;
	struct super_block *sb;
	struct kernfs_super_info *info;
	int error;

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (!info)
		return -ENOMEM;

	info->root = kfc->root;
	info->ns = kfc->ns_tag;
	INIT_LIST_HEAD(&info->node);

	fc->s_fs_info = info;
	sb = sget_fc(fc, kernfs_test_super, kernfs_set_super);
	if (IS_ERR(sb))
		return PTR_ERR(sb);

	if (!sb->s_root) {
		struct kernfs_super_info *info = kernfs_info(sb);
		struct kernfs_root *root = kfc->root;

		kfc->new_sb_created = true;

		error = kernfs_fill_super(sb, kfc);
		if (error) {
			deactivate_locked_super(sb);
			return error;
		}
		sb->s_flags |= SB_ACTIVE;

		uuid_gen(&sb->s_uuid);

		down_write(&root->kernfs_supers_rwsem);
		list_add(&info->node, &info->root->supers);
		up_write(&root->kernfs_supers_rwsem);
	}

	fc->root = dget(sb->s_root);
	return 0;
}

void kernfs_free_fs_context(struct fs_context *fc)
{
	/* Note that we don't deal with kfc->ns_tag here. */
	kfree(fc->s_fs_info);
	fc->s_fs_info = NULL;
}

/**
 * kernfs_kill_sb - kill_sb for kernfs
 * @sb: super_block being killed
 *
 * This can be used directly for file_system_type->kill_sb().  If a kernfs
 * user needs extra cleanup, it can implement its own kill_sb() and call
 * this function at the end.
 */
void kernfs_kill_sb(struct super_block *sb)
{
	struct kernfs_super_info *info = kernfs_info(sb);
	struct kernfs_root *root = info->root;

	down_write(&root->kernfs_supers_rwsem);
	list_del(&info->node);
	up_write(&root->kernfs_supers_rwsem);

	/*
	 * Remove the superblock from fs_supers/s_instances
	 * so we can't find it, before freeing kernfs_super_info.
	 */
	kill_anon_super(sb);
	kfree(info);
}

static void __init kernfs_mutex_init(void)
{
	int count;

	for (count = 0; count < NR_KERNFS_LOCKS; count++)
		mutex_init(&kernfs_locks->open_file_mutex[count]);
}

static void __init kernfs_lock_init(void)
{
	kernfs_locks = kmalloc(sizeof(struct kernfs_global_locks), GFP_KERNEL);
	WARN_ON(!kernfs_locks);

	kernfs_mutex_init();
}

void __init kernfs_init(void)
{
	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
					      sizeof(struct kernfs_node),
					      0, SLAB_PANIC, NULL);

	/* Creates slab cache for kernfs inode attributes */
	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",
					      sizeof(struct kernfs_iattrs),
					      0, SLAB_PANIC, NULL);

	kernfs_lock_init();
}