summaryrefslogtreecommitdiffstats
path: root/include/linux/kernfs.h
blob: 814643f7ee529eb6c9e27ec3e1653487d818595e (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
/*
 * kernfs.h - pseudo filesystem decoupled from vfs locking
 *
 * This file is released under the GPLv2.
 */

#ifndef __LINUX_KERNFS_H
#define __LINUX_KERNFS_H

#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/lockdep.h>
#include <linux/rbtree.h>
#include <linux/atomic.h>
#include <linux/uidgid.h>
#include <linux/wait.h>

struct file;
struct dentry;
struct iattr;
struct seq_file;
struct vm_area_struct;
struct super_block;
struct file_system_type;

struct kernfs_open_node;
struct kernfs_iattrs;

enum kernfs_node_type {
	KERNFS_DIR		= 0x0001,
	KERNFS_FILE		= 0x0002,
	KERNFS_LINK		= 0x0004,
};

#define KERNFS_TYPE_MASK	0x000f
#define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK

enum kernfs_node_flag {
	KERNFS_ACTIVATED	= 0x0010,
	KERNFS_NS		= 0x0020,
	KERNFS_HAS_SEQ_SHOW	= 0x0040,
	KERNFS_HAS_MMAP		= 0x0080,
	KERNFS_LOCKDEP		= 0x0100,
	KERNFS_SUICIDAL		= 0x0400,
	KERNFS_SUICIDED		= 0x0800,
	KERNFS_EMPTY_DIR	= 0x1000,
	KERNFS_HAS_RELEASE	= 0x2000,
};

/* @flags for kernfs_create_root() */
enum kernfs_root_flag {
	/*
	 * kernfs_nodes are created in the deactivated state and invisible.
	 * They require explicit kernfs_activate() to become visible.  This
	 * can be used to make related nodes become visible atomically
	 * after all nodes are created successfully.
	 */
	KERNFS_ROOT_CREATE_DEACTIVATED		= 0x0001,

	/*
	 * For regular flies, if the opener has CAP_DAC_OVERRIDE, open(2)
	 * succeeds regardless of the RW permissions.  sysfs had an extra
	 * layer of enforcement where open(2) fails with -EACCES regardless
	 * of CAP_DAC_OVERRIDE if the permission doesn't have the
	 * respective read or write access at all (none of S_IRUGO or
	 * S_IWUGO) or the respective operation isn't implemented.  The
	 * following flag enables that behavior.
	 */
	KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK	= 0x0002,

	/*
	 * The filesystem supports exportfs operation, so userspace can use
	 * fhandle to access nodes of the fs.
	 */
	KERNFS_ROOT_SUPPORT_EXPORTOP		= 0x0004,
};

/* type-specific structures for kernfs_node union members */
struct kernfs_elem_dir {
	unsigned long		subdirs;
	/* children rbtree starts here and goes through kn->rb */
	struct rb_root		children;

	/*
	 * The kernfs hierarchy this directory belongs to.  This fits
	 * better directly in kernfs_node but is here to save space.
	 */
	struct kernfs_root	*root;
};

struct kernfs_elem_symlink {
	struct kernfs_node	*target_kn;
};

struct kernfs_elem_attr {
	const struct kernfs_ops	*ops;
	struct kernfs_open_node	*open;
	loff_t			size;
	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
};

/* represent a kernfs node */
union kernfs_node_id {
	struct {
		/*
		 * blktrace will export this struct as a simplified 'struct
		 * fid' (which is a big data struction), so userspace can use
		 * it to find kernfs node. The layout must match the first two
		 * fields of 'struct fid' exactly.
		 */
		u32		ino;
		u32		generation;
	};
	u64			id;
};

/*
 * kernfs_node - the building block of kernfs hierarchy.  Each and every
 * kernfs node is represented by single kernfs_node.  Most fields are
 * private to kernfs and shouldn't be accessed directly by kernfs users.
 *
 * As long as s_count reference is held, the kernfs_node itself is
 * accessible.  Dereferencing elem or any other outer entity requires
 * active reference.
 */
struct kernfs_node {
	atomic_t		count;
	atomic_t		active;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map	dep_map;
#endif
	/*
	 * Use kernfs_get_parent() and kernfs_name/path() instead of
	 * accessing the following two fields directly.  If the node is
	 * never moved to a different parent, it is safe to access the
	 * parent directly.
	 */
	struct kernfs_node	*parent;
	const char		*name;

	struct rb_node		rb;

	const void		*ns;	/* namespace tag */
	unsigned int		hash;	/* ns + name hash */
	union {
		struct kernfs_elem_dir		dir;
		struct kernfs_elem_symlink	symlink;
		struct kernfs_elem_attr		attr;
	};

	void			*priv;

	union kernfs_node_id	id;
	unsigned short		flags;
	umode_t			mode;
	struct kernfs_iattrs	*iattr;
};

/*
 * kernfs_syscall_ops may be specified on kernfs_create_root() to support
 * syscalls.  These optional callbacks are invoked on the matching syscalls
 * and can perform any kernfs operations which don't necessarily have to be
 * the exact operation requested.  An active reference is held for each
 * kernfs_node parameter.
 */
struct kernfs_syscall_ops {
	int (*remount_fs)(struct kernfs_root *root, int *flags, char *data);
	int (*show_options)(struct seq_file *sf, struct kernfs_root *root);

	int (*mkdir)(struct kernfs_node *parent, const char *name,
		     umode_t mode);
	int (*rmdir)(struct kernfs_node *kn);
	int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent,
		      const char *new_name);
	int (*show_path)(struct seq_file *sf, struct kernfs_node *kn,
			 struct kernfs_root *root);
};

struct kernfs_root {
	/* published fields */
	struct kernfs_node	*kn;
	unsigned int		flags;	/* KERNFS_ROOT_* flags */

	/* private fields, do not use outside kernfs proper */
	struct idr		ino_idr;
	u32			next_generation;
	struct kernfs_syscall_ops *syscall_ops;

	/* list of kernfs_super_info of this root, protected by kernfs_mutex */
	struct list_head	supers;

	wait_queue_head_t	deactivate_waitq;
};

struct kernfs_open_file {
	/* published fields */
	struct kernfs_node	*kn;
	struct file		*file;
	struct seq_file		*seq_file;
	void			*priv;

	/* private fields, do not use outside kernfs proper */
	struct mutex		mutex;
	struct mutex		prealloc_mutex;
	int			event;
	struct list_head	list;
	char			*prealloc_buf;

	size_t			atomic_write_len;
	bool			mmapped:1;
	bool			released:1;
	const struct vm_operations_struct *vm_ops;
};

struct kernfs_ops {
	/*
	 * Optional open/release methods.  Both are called with
	 * @of->seq_file populated.
	 */
	int (*open)(struct kernfs_open_file *of);
	void (*release)(struct kernfs_open_file *of);

	/*
	 * Read is handled by either seq_file or raw_read().
	 *
	 * If seq_show() is present, seq_file path is active.  Other seq
	 * operations are optional and if not implemented, the behavior is
	 * equivalent to single_open().  @sf->private points to the
	 * associated kernfs_open_file.
	 *
	 * read() is bounced through kernel buffer and a read larger than
	 * PAGE_SIZE results in partial operation of PAGE_SIZE.
	 */
	int (*seq_show)(struct seq_file *sf, void *v);

	void *(*seq_start)(struct seq_file *sf, loff_t *ppos);
	void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos);
	void (*seq_stop)(struct seq_file *sf, void *v);

	ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes,
			loff_t off);

	/*
	 * write() is bounced through kernel buffer.  If atomic_write_len
	 * is not set, a write larger than PAGE_SIZE results in partial
	 * operations of PAGE_SIZE chunks.  If atomic_write_len is set,
	 * writes upto the specified size are executed atomically but
	 * larger ones are rejected with -E2BIG.
	 */
	size_t atomic_write_len;
	/*
	 * "prealloc" causes a buffer to be allocated at open for
	 * all read/write requests.  As ->seq_show uses seq_read()
	 * which does its own allocation, it is incompatible with
	 * ->prealloc.  Provide ->read and ->write with ->prealloc.
	 */
	bool prealloc;
	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
			 loff_t off);

	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lock_class_key	lockdep_key;
#endif
};

#ifdef CONFIG_KERNFS

static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
{
	return kn->flags & KERNFS_TYPE_MASK;
}

/**
 * kernfs_enable_ns - enable namespace under a directory
 * @kn: directory of interest, should be empty
 *
 * This is to be called right after @kn is created to enable namespace
 * under it.  All children of @kn must have non-NULL namespace tags and
 * only the ones which match the super_block's tag will be visible.
 */
static inline void kernfs_enable_ns(struct kernfs_node *kn)
{
	WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR);
	WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children));
	kn->flags |= KERNFS_NS;
}

/**
 * kernfs_ns_enabled - test whether namespace is enabled
 * @kn: the node to test
 *
 * Test whether namespace filtering is enabled for the children of @ns.
 */
static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
{
	return kn->flags & KERNFS_NS;
}

int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn,
			  char *buf, size_t buflen);
void pr_cont_kernfs_name(struct kernfs_node *kn);
void pr_cont_kernfs_path(struct kernfs_node *kn);
struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
					   const char *name, const void *ns);
struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
					   const char *path, const void *ns);
void kernfs_get(struct kernfs_node *kn);
void kernfs_put(struct kernfs_node *kn);

struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry);
struct kernfs_root *kernfs_root_from_sb(struct super_block *sb);
struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn);

struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
				  struct super_block *sb);
struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
				       unsigned int flags, void *priv);
void kernfs_destroy_root(struct kernfs_root *root);

struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
					 const char *name, umode_t mode,
					 kuid_t uid, kgid_t gid,
					 void *priv, const void *ns);
struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
					    const char *name);
struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
					 const char *name, umode_t mode,
					 kuid_t uid, kgid_t gid,
					 loff_t size,
					 const struct kernfs_ops *ops,
					 void *priv, const void *ns,
					 struct lock_class_key *key);
struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
				       const char *name,
				       struct kernfs_node *target);
void kernfs_activate(struct kernfs_node *kn);
void kernfs_remove(struct kernfs_node *kn);
void kernfs_break_active_protection(struct kernfs_node *kn);
void kernfs_unbreak_active_protection(struct kernfs_node *kn);
bool kernfs_remove_self(struct kernfs_node *kn);
int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
			     const void *ns);
int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
		     const char *new_name, const void *new_ns);
int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
void kernfs_notify(struct kernfs_node *kn);

const void *kernfs_super_ns(struct super_block *sb);
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
			       struct kernfs_root *root, unsigned long magic,
			       bool *new_sb_created, const void *ns);
void kernfs_kill_sb(struct super_block *sb);
struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns);

void kernfs_init(void);

struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
	const union kernfs_node_id *id);
#else	/* CONFIG_KERNFS */

static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
{ return 0; }	/* whatever */

static inline void kernfs_enable_ns(struct kernfs_node *kn) { }

static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
{ return false; }

static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
{ return -ENOSYS; }

static inline int kernfs_path_from_node(struct kernfs_node *root_kn,
					struct kernfs_node *kn,
					char *buf, size_t buflen)
{ return -ENOSYS; }

static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { }
static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { }

static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
{ return NULL; }

static inline struct kernfs_node *
kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
		       const void *ns)
{ return NULL; }
static inline struct kernfs_node *
kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path,
		       const void *ns)
{ return NULL; }

static inline void kernfs_get(struct kernfs_node *kn) { }
static inline void kernfs_put(struct kernfs_node *kn) { }

static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
{ return NULL; }

static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
{ return NULL; }

static inline struct inode *
kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
{ return NULL; }

static inline struct kernfs_root *
kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
		   void *priv)
{ return ERR_PTR(-ENOSYS); }

static inline void kernfs_destroy_root(struct kernfs_root *root) { }

static inline struct kernfs_node *
kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
		     umode_t mode, kuid_t uid, kgid_t gid,
		     void *priv, const void *ns)
{ return ERR_PTR(-ENOSYS); }

static inline struct kernfs_node *
__kernfs_create_file(struct kernfs_node *parent, const char *name,
		     umode_t mode, kuid_t uid, kgid_t gid,
		     loff_t size, const struct kernfs_ops *ops,
		     void *priv, const void *ns, struct lock_class_key *key)
{ return ERR_PTR(-ENOSYS); }

static inline struct kernfs_node *
kernfs_create_link(struct kernfs_node *parent, const char *name,
		   struct kernfs_node *target)
{ return ERR_PTR(-ENOSYS); }

static inline void kernfs_activate(struct kernfs_node *kn) { }

static inline void kernfs_remove(struct kernfs_node *kn) { }

static inline bool kernfs_remove_self(struct kernfs_node *kn)
{ return false; }

static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn,
					   const char *name, const void *ns)
{ return -ENOSYS; }

static inline int kernfs_rename_ns(struct kernfs_node *kn,
				   struct kernfs_node *new_parent,
				   const char *new_name, const void *new_ns)
{ return -ENOSYS; }

static inline int kernfs_setattr(struct kernfs_node *kn,
				 const struct iattr *iattr)
{ return -ENOSYS; }

static inline void kernfs_notify(struct kernfs_node *kn) { }

static inline const void *kernfs_super_ns(struct super_block *sb)
{ return NULL; }

static inline struct dentry *
kernfs_mount_ns(struct file_system_type *fs_type, int flags,
		struct kernfs_root *root, unsigned long magic,
		bool *new_sb_created, const void *ns)
{ return ERR_PTR(-ENOSYS); }

static inline void kernfs_kill_sb(struct super_block *sb) { }

static inline void kernfs_init(void) { }

#endif	/* CONFIG_KERNFS */

/**
 * kernfs_path - build full path of a given node
 * @kn: kernfs_node of interest
 * @buf: buffer to copy @kn's name into
 * @buflen: size of @buf
 *
 * Builds and returns the full path of @kn in @buf of @buflen bytes.  The
 * path is built from the end of @buf so the returned pointer usually
 * doesn't match @buf.  If @buf isn't long enough, @buf is nul terminated
 * and %NULL is returned.
 */
static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
{
	return kernfs_path_from_node(kn, NULL, buf, buflen);
}

static inline struct kernfs_node *
kernfs_find_and_get(struct kernfs_node *kn, const char *name)
{
	return kernfs_find_and_get_ns(kn, name, NULL);
}

static inline struct kernfs_node *
kernfs_walk_and_get(struct kernfs_node *kn, const char *path)
{
	return kernfs_walk_and_get_ns(kn, path, NULL);
}

static inline struct kernfs_node *
kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
		  void *priv)
{
	return kernfs_create_dir_ns(parent, name, mode,
				    GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
				    priv, NULL);
}

static inline struct kernfs_node *
kernfs_create_file_ns(struct kernfs_node *parent, const char *name,
		      umode_t mode, kuid_t uid, kgid_t gid,
		      loff_t size, const struct kernfs_ops *ops,
		      void *priv, const void *ns)
{
	struct lock_class_key *key = NULL;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	key = (struct lock_class_key *)&ops->lockdep_key;
#endif
	return __kernfs_create_file(parent, name, mode, uid, gid,
				    size, ops, priv, ns, key);
}

static inline struct kernfs_node *
kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode,
		   loff_t size, const struct kernfs_ops *ops, void *priv)
{
	return kernfs_create_file_ns(parent, name, mode,
				     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
				     size, ops, priv, NULL);
}

static inline int kernfs_remove_by_name(struct kernfs_node *parent,
					const char *name)
{
	return kernfs_remove_by_name_ns(parent, name, NULL);
}

static inline int kernfs_rename(struct kernfs_node *kn,
				struct kernfs_node *new_parent,
				const char *new_name)
{
	return kernfs_rename_ns(kn, new_parent, new_name, NULL);
}

static inline struct dentry *
kernfs_mount(struct file_system_type *fs_type, int flags,
		struct kernfs_root *root, unsigned long magic,
		bool *new_sb_created)
{
	return kernfs_mount_ns(fs_type, flags, root,
				magic, new_sb_created, NULL);
}

#endif	/* __LINUX_KERNFS_H */