libfs.c 25.6 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7
/*
 *	fs/libfs.c
 *	Library for filesystems writers.
 */

#include <linux/module.h>
#include <linux/pagemap.h>
8
#include <linux/slab.h>
L
Linus Torvalds 已提交
9 10
#include <linux/mount.h>
#include <linux/vfs.h>
11
#include <linux/quotaops.h>
I
Ingo Molnar 已提交
12
#include <linux/mutex.h>
C
Christoph Hellwig 已提交
13
#include <linux/exportfs.h>
A
Al Viro 已提交
14 15
#include <linux/writeback.h>
#include <linux/buffer_head.h>
I
Ingo Molnar 已提交
16

L
Linus Torvalds 已提交
17 18 19 20 21 22 23 24 25 26 27
#include <asm/uaccess.h>

int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
		   struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	generic_fillattr(inode, stat);
	stat->blocks = inode->i_mapping->nrpages << (PAGE_CACHE_SHIFT - 9);
	return 0;
}

28
int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
L
Linus Torvalds 已提交
29
{
30
	buf->f_type = dentry->d_sb->s_magic;
L
Linus Torvalds 已提交
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
	buf->f_bsize = PAGE_CACHE_SIZE;
	buf->f_namelen = NAME_MAX;
	return 0;
}

/*
 * Retaining negative dentries for an in-memory filesystem just wastes
 * memory and lookup time: arrange for them to be deleted immediately.
 */
static int simple_delete_dentry(struct dentry *dentry)
{
	return 1;
}

/*
 * Lookup the data. This is trivial - if the dentry didn't already
 * exist, we know it is negative.  Set d_op to delete negative dentries.
 */
struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
A
Al Viro 已提交
51
	static const struct dentry_operations simple_dentry_operations = {
L
Linus Torvalds 已提交
52 53 54 55 56 57 58 59 60 61 62 63 64 65
		.d_delete = simple_delete_dentry,
	};

	if (dentry->d_name.len > NAME_MAX)
		return ERR_PTR(-ENAMETOOLONG);
	dentry->d_op = &simple_dentry_operations;
	d_add(dentry, NULL);
	return NULL;
}

int dcache_dir_open(struct inode *inode, struct file *file)
{
	static struct qstr cursor_name = {.len = 1, .name = "."};

66
	file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
L
Linus Torvalds 已提交
67 68 69 70 71 72 73 74 75 76 77 78

	return file->private_data ? 0 : -ENOMEM;
}

int dcache_dir_close(struct inode *inode, struct file *file)
{
	dput(file->private_data);
	return 0;
}

loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
{
79
	mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
80 81 82 83 84 85 86
	switch (origin) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
87
			mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
88 89 90 91 92 93 94 95 96 97
			return -EINVAL;
	}
	if (offset != file->f_pos) {
		file->f_pos = offset;
		if (file->f_pos >= 2) {
			struct list_head *p;
			struct dentry *cursor = file->private_data;
			loff_t n = file->f_pos - 2;

			spin_lock(&dcache_lock);
E
Eric Dumazet 已提交
98
			list_del(&cursor->d_u.d_child);
99 100
			p = file->f_path.dentry->d_subdirs.next;
			while (n && p != &file->f_path.dentry->d_subdirs) {
L
Linus Torvalds 已提交
101
				struct dentry *next;
E
Eric Dumazet 已提交
102
				next = list_entry(p, struct dentry, d_u.d_child);
L
Linus Torvalds 已提交
103 104 105 106
				if (!d_unhashed(next) && next->d_inode)
					n--;
				p = p->next;
			}
E
Eric Dumazet 已提交
107
			list_add_tail(&cursor->d_u.d_child, p);
L
Linus Torvalds 已提交
108 109 110
			spin_unlock(&dcache_lock);
		}
	}
111
	mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
	return offset;
}

/* Relationship between i_mode and the DT_xxx types */
static inline unsigned char dt_type(struct inode *inode)
{
	return (inode->i_mode >> 12) & 15;
}

/*
 * Directory is locked and all positive dentries in it are safe, since
 * for ramfs-type trees they can't go away without unlink() or rmdir(),
 * both impossible due to the lock on directory.
 */

int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
129
	struct dentry *dentry = filp->f_path.dentry;
L
Linus Torvalds 已提交
130
	struct dentry *cursor = filp->private_data;
E
Eric Dumazet 已提交
131
	struct list_head *p, *q = &cursor->d_u.d_child;
L
Linus Torvalds 已提交
132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
	ino_t ino;
	int i = filp->f_pos;

	switch (i) {
		case 0:
			ino = dentry->d_inode->i_ino;
			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
				break;
			filp->f_pos++;
			i++;
			/* fallthrough */
		case 1:
			ino = parent_ino(dentry);
			if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
				break;
			filp->f_pos++;
			i++;
			/* fallthrough */
		default:
			spin_lock(&dcache_lock);
A
Akinobu Mita 已提交
152 153 154
			if (filp->f_pos == 2)
				list_move(q, &dentry->d_subdirs);

L
Linus Torvalds 已提交
155 156
			for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
				struct dentry *next;
E
Eric Dumazet 已提交
157
				next = list_entry(p, struct dentry, d_u.d_child);
L
Linus Torvalds 已提交
158 159 160 161
				if (d_unhashed(next) || !next->d_inode)
					continue;

				spin_unlock(&dcache_lock);
162 163 164 165
				if (filldir(dirent, next->d_name.name, 
					    next->d_name.len, filp->f_pos, 
					    next->d_inode->i_ino, 
					    dt_type(next->d_inode)) < 0)
L
Linus Torvalds 已提交
166 167 168
					return 0;
				spin_lock(&dcache_lock);
				/* next is still alive */
A
Akinobu Mita 已提交
169
				list_move(q, p);
L
Linus Torvalds 已提交
170 171 172 173 174 175 176 177 178 179 180 181 182
				p = q;
				filp->f_pos++;
			}
			spin_unlock(&dcache_lock);
	}
	return 0;
}

ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos)
{
	return -EISDIR;
}

183
const struct file_operations simple_dir_operations = {
L
Linus Torvalds 已提交
184 185 186 187 188
	.open		= dcache_dir_open,
	.release	= dcache_dir_close,
	.llseek		= dcache_dir_lseek,
	.read		= generic_read_dir,
	.readdir	= dcache_readdir,
189
	.fsync		= noop_fsync,
L
Linus Torvalds 已提交
190 191
};

192
const struct inode_operations simple_dir_inode_operations = {
L
Linus Torvalds 已提交
193 194 195
	.lookup		= simple_lookup,
};

196 197 198 199
static const struct super_operations simple_super_operations = {
	.statfs		= simple_statfs,
};

L
Linus Torvalds 已提交
200 201 202 203
/*
 * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
 * will never be mountable)
 */
204
int get_sb_pseudo(struct file_system_type *fs_type, char *name,
205
	const struct super_operations *ops, unsigned long magic,
206
	struct vfsmount *mnt)
L
Linus Torvalds 已提交
207 208 209 210 211 212 213
{
	struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
	struct dentry *dentry;
	struct inode *root;
	struct qstr d_name = {.name = name, .len = strlen(name)};

	if (IS_ERR(s))
214
		return PTR_ERR(s);
L
Linus Torvalds 已提交
215 216

	s->s_flags = MS_NOUSER;
217
	s->s_maxbytes = MAX_LFS_FILESIZE;
218 219
	s->s_blocksize = PAGE_SIZE;
	s->s_blocksize_bits = PAGE_SHIFT;
L
Linus Torvalds 已提交
220
	s->s_magic = magic;
221
	s->s_op = ops ? ops : &simple_super_operations;
L
Linus Torvalds 已提交
222 223 224 225
	s->s_time_gran = 1;
	root = new_inode(s);
	if (!root)
		goto Enomem;
226 227 228 229 230 231
	/*
	 * since this is the first inode, make it number 1. New inodes created
	 * after this must take care not to collide with it (by passing
	 * max_reserved of 1 to iunique).
	 */
	root->i_ino = 1;
L
Linus Torvalds 已提交
232 233 234 235 236 237 238 239 240 241 242 243
	root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
	root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME;
	dentry = d_alloc(NULL, &d_name);
	if (!dentry) {
		iput(root);
		goto Enomem;
	}
	dentry->d_sb = s;
	dentry->d_parent = dentry;
	d_instantiate(dentry, root);
	s->s_root = dentry;
	s->s_flags |= MS_ACTIVE;
244 245
	simple_set_mnt(mnt, s);
	return 0;
L
Linus Torvalds 已提交
246 247

Enomem:
248
	deactivate_locked_super(s);
249
	return -ENOMEM;
L
Linus Torvalds 已提交
250 251 252 253 254 255 256
}

int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = old_dentry->d_inode;

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
257
	inc_nlink(inode);
L
Linus Torvalds 已提交
258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
	atomic_inc(&inode->i_count);
	dget(dentry);
	d_instantiate(dentry, inode);
	return 0;
}

static inline int simple_positive(struct dentry *dentry)
{
	return dentry->d_inode && !d_unhashed(dentry);
}

int simple_empty(struct dentry *dentry)
{
	struct dentry *child;
	int ret = 0;

	spin_lock(&dcache_lock);
E
Eric Dumazet 已提交
275
	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
L
Linus Torvalds 已提交
276 277 278 279 280 281 282 283 284 285 286 287 288
		if (simple_positive(child))
			goto out;
	ret = 1;
out:
	spin_unlock(&dcache_lock);
	return ret;
}

int simple_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
289
	drop_nlink(inode);
L
Linus Torvalds 已提交
290 291 292 293 294 295 296 297 298
	dput(dentry);
	return 0;
}

int simple_rmdir(struct inode *dir, struct dentry *dentry)
{
	if (!simple_empty(dentry))
		return -ENOTEMPTY;

299
	drop_nlink(dentry->d_inode);
L
Linus Torvalds 已提交
300
	simple_unlink(dir, dentry);
301
	drop_nlink(dir);
L
Linus Torvalds 已提交
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
	return 0;
}

int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
		struct inode *new_dir, struct dentry *new_dentry)
{
	struct inode *inode = old_dentry->d_inode;
	int they_are_dirs = S_ISDIR(old_dentry->d_inode->i_mode);

	if (!simple_empty(new_dentry))
		return -ENOTEMPTY;

	if (new_dentry->d_inode) {
		simple_unlink(new_dir, new_dentry);
		if (they_are_dirs)
317
			drop_nlink(old_dir);
L
Linus Torvalds 已提交
318
	} else if (they_are_dirs) {
319
		drop_nlink(old_dir);
320
		inc_nlink(new_dir);
L
Linus Torvalds 已提交
321 322 323 324 325 326 327 328
	}

	old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime =
		new_dir->i_mtime = inode->i_ctime = CURRENT_TIME;

	return 0;
}

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
/**
 * simple_setsize - handle core mm and vfs requirements for file size change
 * @inode: inode
 * @newsize: new file size
 *
 * Returns 0 on success, -error on failure.
 *
 * simple_setsize must be called with inode_mutex held.
 *
 * simple_setsize will check that the requested new size is OK (see
 * inode_newsize_ok), and then will perform the necessary i_size update
 * and pagecache truncation (if necessary). It will be typically be called
 * from the filesystem's setattr function when ATTR_SIZE is passed in.
 *
 * The inode itself must have correct permissions and attributes to allow
 * i_size to be changed, this function then just checks that the new size
 * requested is valid.
 *
 * In the case of simple in-memory filesystems with inodes stored solely
 * in the inode cache, and file data in the pagecache, nothing more needs
 * to be done to satisfy a truncate request. Filesystems with on-disk
 * blocks for example will need to free them in the case of truncate, in
 * that case it may be easier not to use simple_setsize (but each of its
 * components will likely be required at some point to update pagecache
 * and inode etc).
 */
int simple_setsize(struct inode *inode, loff_t newsize)
{
	loff_t oldsize;
	int error;

	error = inode_newsize_ok(inode, newsize);
	if (error)
		return error;

	oldsize = inode->i_size;
	i_size_write(inode, newsize);
	truncate_pagecache(inode, oldsize, newsize);

	return error;
}
EXPORT_SYMBOL(simple_setsize);

/**
C
Christoph Hellwig 已提交
373
 * simple_setattr - setattr for simple filesystem
374 375 376 377 378
 * @dentry: dentry
 * @iattr: iattr structure
 *
 * Returns 0 on success, -error on failure.
 *
C
Christoph Hellwig 已提交
379 380 381 382 383 384
 * simple_setattr is a simple ->setattr implementation without a proper
 * implementation of size changes.
 *
 * It can either be used for in-memory filesystems or special files
 * on simple regular filesystems.  Anything that needs to change on-disk
 * or wire state on size changes needs its own setattr method.
385 386 387 388 389 390
 */
int simple_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = dentry->d_inode;
	int error;

C
Christoph Hellwig 已提交
391 392
	WARN_ON_ONCE(inode->i_op->truncate);

393 394 395 396 397 398 399 400 401 402
	error = inode_change_ok(inode, iattr);
	if (error)
		return error;

	if (iattr->ia_valid & ATTR_SIZE) {
		error = simple_setsize(inode, iattr->ia_size);
		if (error)
			return error;
	}

C
Christoph Hellwig 已提交
403
	setattr_copy(inode, iattr);
C
Christoph Hellwig 已提交
404 405
	mark_inode_dirty(inode);
	return 0;
406 407 408
}
EXPORT_SYMBOL(simple_setattr);

L
Linus Torvalds 已提交
409 410
int simple_readpage(struct file *file, struct page *page)
{
411
	clear_highpage(page);
L
Linus Torvalds 已提交
412 413 414 415 416 417
	flush_dcache_page(page);
	SetPageUptodate(page);
	unlock_page(page);
	return 0;
}

418 419 420 421 422 423 424 425 426
int simple_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	struct page *page;
	pgoff_t index;

	index = pos >> PAGE_CACHE_SHIFT;

427
	page = grab_cache_page_write_begin(mapping, index, flags);
428 429 430 431 432
	if (!page)
		return -ENOMEM;

	*pagep = page;

433 434 435 436 437 438
	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
		unsigned from = pos & (PAGE_CACHE_SIZE - 1);

		zero_user_segments(page, 0, from, from + len, PAGE_CACHE_SIZE);
	}
	return 0;
439 440
}

441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
/**
 * simple_write_end - .write_end helper for non-block-device FSes
 * @available: See .write_end of address_space_operations
 * @file: 		"
 * @mapping: 		"
 * @pos: 		"
 * @len: 		"
 * @copied: 		"
 * @page: 		"
 * @fsdata: 		"
 *
 * simple_write_end does the minimum needed for updating a page after writing is
 * done. It has the same API signature as the .write_end of
 * address_space_operations vector. So it can just be set onto .write_end for
 * FSes that don't need any other processing. i_mutex is assumed to be held.
 * Block based filesystems should use generic_write_end().
 * NOTE: Even though i_size might get updated by this function, mark_inode_dirty
 * is not called, so a filesystem that actually does store data in .write_inode
 * should extend on what's done here with a call to mark_inode_dirty() in the
 * case that i_size has changed.
 */
462 463 464 465
int simple_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
466 467
	struct inode *inode = page->mapping->host;
	loff_t last_pos = pos + copied;
468 469 470

	/* zero the stale part of the page if we did a short copy */
	if (copied < len) {
471 472 473
		unsigned from = pos & (PAGE_CACHE_SIZE - 1);

		zero_user(page, from + copied, len - copied);
474 475
	}

476 477 478 479 480 481 482 483
	if (!PageUptodate(page))
		SetPageUptodate(page);
	/*
	 * No need to use i_size_read() here, the i_size
	 * cannot change under us because we hold the i_mutex.
	 */
	if (last_pos > inode->i_size)
		i_size_write(inode, last_pos);
484

485
	set_page_dirty(page);
486 487 488 489 490 491
	unlock_page(page);
	page_cache_release(page);

	return copied;
}

492 493 494 495 496
/*
 * the inodes created here are not hashed. If you use iunique to generate
 * unique inode values later for this filesystem, then you must take care
 * to pass it an appropriate max_reserved value to avoid collisions.
 */
497 498
int simple_fill_super(struct super_block *s, unsigned long magic,
		      struct tree_descr *files)
L
Linus Torvalds 已提交
499 500 501 502 503 504 505 506 507
{
	struct inode *inode;
	struct dentry *root;
	struct dentry *dentry;
	int i;

	s->s_blocksize = PAGE_CACHE_SIZE;
	s->s_blocksize_bits = PAGE_CACHE_SHIFT;
	s->s_magic = magic;
508
	s->s_op = &simple_super_operations;
L
Linus Torvalds 已提交
509 510 511 512 513
	s->s_time_gran = 1;

	inode = new_inode(s);
	if (!inode)
		return -ENOMEM;
514 515 516 517 518
	/*
	 * because the root inode is 1, the files array must not contain an
	 * entry at index 1
	 */
	inode->i_ino = 1;
L
Linus Torvalds 已提交
519 520 521 522
	inode->i_mode = S_IFDIR | 0755;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_op = &simple_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
523
	inode->i_nlink = 2;
L
Linus Torvalds 已提交
524 525 526 527 528 529 530 531
	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		return -ENOMEM;
	}
	for (i = 0; !files->name || files->name[0]; i++, files++) {
		if (!files->name)
			continue;
532 533 534 535 536 537 538

		/* warn if it tries to conflict with the root inode */
		if (unlikely(i == 1))
			printk(KERN_WARNING "%s: %s passed in a files array"
				"with an index of 1!\n", __func__,
				s->s_type->name);

L
Linus Torvalds 已提交
539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560
		dentry = d_alloc_name(root, files->name);
		if (!dentry)
			goto out;
		inode = new_inode(s);
		if (!inode)
			goto out;
		inode->i_mode = S_IFREG | files->mode;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_fop = files->ops;
		inode->i_ino = i;
		d_add(dentry, inode);
	}
	s->s_root = root;
	return 0;
out:
	d_genocide(root);
	dput(root);
	return -ENOMEM;
}

static DEFINE_SPINLOCK(pin_fs_lock);

561
int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
L
Linus Torvalds 已提交
562 563 564 565 566
{
	struct vfsmount *mnt = NULL;
	spin_lock(&pin_fs_lock);
	if (unlikely(!*mount)) {
		spin_unlock(&pin_fs_lock);
567
		mnt = vfs_kern_mount(type, 0, type->name, NULL);
L
Linus Torvalds 已提交
568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591
		if (IS_ERR(mnt))
			return PTR_ERR(mnt);
		spin_lock(&pin_fs_lock);
		if (!*mount)
			*mount = mnt;
	}
	mntget(*mount);
	++*count;
	spin_unlock(&pin_fs_lock);
	mntput(mnt);
	return 0;
}

void simple_release_fs(struct vfsmount **mount, int *count)
{
	struct vfsmount *mnt;
	spin_lock(&pin_fs_lock);
	mnt = *mount;
	if (!--*count)
		*mount = NULL;
	spin_unlock(&pin_fs_lock);
	mntput(mnt);
}

592 593 594 595 596 597 598 599 600 601 602 603 604 605
/**
 * simple_read_from_buffer - copy data from the buffer to user space
 * @to: the user space buffer to read to
 * @count: the maximum number of bytes to read
 * @ppos: the current position in the buffer
 * @from: the buffer to read from
 * @available: the size of the buffer
 *
 * The simple_read_from_buffer() function reads up to @count bytes from the
 * buffer @from at offset @ppos into the user space address starting at @to.
 *
 * On success, the number of bytes read is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
L
Linus Torvalds 已提交
606 607 608 609
ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
				const void *from, size_t available)
{
	loff_t pos = *ppos;
610 611
	size_t ret;

L
Linus Torvalds 已提交
612 613
	if (pos < 0)
		return -EINVAL;
614
	if (pos >= available || !count)
L
Linus Torvalds 已提交
615 616 617
		return 0;
	if (count > available - pos)
		count = available - pos;
618 619
	ret = copy_to_user(to, from + pos, count);
	if (ret == count)
L
Linus Torvalds 已提交
620
		return -EFAULT;
621
	count -= ret;
L
Linus Torvalds 已提交
622 623 624 625
	*ppos = pos + count;
	return count;
}

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
/**
 * simple_write_to_buffer - copy data from user space to the buffer
 * @to: the buffer to write to
 * @available: the size of the buffer
 * @ppos: the current position in the buffer
 * @from: the user space buffer to read from
 * @count: the maximum number of bytes to read
 *
 * The simple_write_to_buffer() function reads up to @count bytes from the user
 * space address starting at @from into the buffer @to at offset @ppos.
 *
 * On success, the number of bytes written is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
		const void __user *from, size_t count)
{
	loff_t pos = *ppos;
	size_t res;

	if (pos < 0)
		return -EINVAL;
	if (pos >= available || !count)
		return 0;
	if (count > available - pos)
		count = available - pos;
	res = copy_from_user(to + pos, from, count);
	if (res == count)
		return -EFAULT;
	count -= res;
	*ppos = pos + count;
	return count;
}

660 661 662 663 664 665 666 667 668 669 670 671 672 673
/**
 * memory_read_from_buffer - copy data from the buffer
 * @to: the kernel space buffer to read to
 * @count: the maximum number of bytes to read
 * @ppos: the current position in the buffer
 * @from: the buffer to read from
 * @available: the size of the buffer
 *
 * The memory_read_from_buffer() function reads up to @count bytes from the
 * buffer @from at offset @ppos into the kernel space address starting at @to.
 *
 * On success, the number of bytes read is returned and the offset @ppos is
 * advanced by this number, or negative value is returned on error.
 **/
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
				const void *from, size_t available)
{
	loff_t pos = *ppos;

	if (pos < 0)
		return -EINVAL;
	if (pos >= available)
		return 0;
	if (count > available - pos)
		count = available - pos;
	memcpy(to, from + pos, count);
	*ppos = pos + count;

	return count;
}

L
Linus Torvalds 已提交
691 692 693 694 695 696
/*
 * Transaction based IO.
 * The file expects a single write which triggers the transaction, and then
 * possibly a read which collects the result - which is stored in a
 * file-local buffer.
 */
697 698 699 700 701 702 703 704 705 706 707 708 709 710 711

void simple_transaction_set(struct file *file, size_t n)
{
	struct simple_transaction_argresp *ar = file->private_data;

	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);

	/*
	 * The barrier ensures that ar->size will really remain zero until
	 * ar->data is ready for reading.
	 */
	smp_mb();
	ar->size = n;
}

L
Linus Torvalds 已提交
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
char *simple_transaction_get(struct file *file, const char __user *buf, size_t size)
{
	struct simple_transaction_argresp *ar;
	static DEFINE_SPINLOCK(simple_transaction_lock);

	if (size > SIMPLE_TRANSACTION_LIMIT - 1)
		return ERR_PTR(-EFBIG);

	ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL);
	if (!ar)
		return ERR_PTR(-ENOMEM);

	spin_lock(&simple_transaction_lock);

	/* only one write allowed per open */
	if (file->private_data) {
		spin_unlock(&simple_transaction_lock);
		free_page((unsigned long)ar);
		return ERR_PTR(-EBUSY);
	}

	file->private_data = ar;

	spin_unlock(&simple_transaction_lock);

	if (copy_from_user(ar->data, buf, size))
		return ERR_PTR(-EFAULT);

	return ar->data;
}

ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
{
	struct simple_transaction_argresp *ar = file->private_data;

	if (!ar)
		return 0;
	return simple_read_from_buffer(buf, size, pos, ar->data, ar->size);
}

int simple_transaction_release(struct inode *inode, struct file *file)
{
	free_page((unsigned long)file->private_data);
	return 0;
}

758 759 760
/* Simple attribute files */

struct simple_attr {
761 762
	int (*get)(void *, u64 *);
	int (*set)(void *, u64);
763 764 765 766
	char get_buf[24];	/* enough to store a u64 and "\n\0" */
	char set_buf[24];
	void *data;
	const char *fmt;	/* format for read operation */
I
Ingo Molnar 已提交
767
	struct mutex mutex;	/* protects access to these buffers */
768 769 770 771 772
};

/* simple_attr_open is called by an actual attribute open file operation
 * to set the attribute specific access operations. */
int simple_attr_open(struct inode *inode, struct file *file,
773
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
774 775 776 777 778 779 780 781 782 783
		     const char *fmt)
{
	struct simple_attr *attr;

	attr = kmalloc(sizeof(*attr), GFP_KERNEL);
	if (!attr)
		return -ENOMEM;

	attr->get = get;
	attr->set = set;
784
	attr->data = inode->i_private;
785
	attr->fmt = fmt;
I
Ingo Molnar 已提交
786
	mutex_init(&attr->mutex);
787 788 789 790 791 792

	file->private_data = attr;

	return nonseekable_open(inode, file);
}

793
int simple_attr_release(struct inode *inode, struct file *file)
794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811
{
	kfree(file->private_data);
	return 0;
}

/* read from the buffer that is filled with the get function */
ssize_t simple_attr_read(struct file *file, char __user *buf,
			 size_t len, loff_t *ppos)
{
	struct simple_attr *attr;
	size_t size;
	ssize_t ret;

	attr = file->private_data;

	if (!attr->get)
		return -EACCES;

812 813 814 815
	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

816
	if (*ppos) {		/* continued read */
817
		size = strlen(attr->get_buf);
818 819 820 821 822 823
	} else {		/* first read */
		u64 val;
		ret = attr->get(attr->data, &val);
		if (ret)
			goto out;

824
		size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
825 826
				 attr->fmt, (unsigned long long)val);
	}
827 828

	ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
829
out:
I
Ingo Molnar 已提交
830
	mutex_unlock(&attr->mutex);
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
	return ret;
}

/* interpret the buffer as a number to call the set function with */
ssize_t simple_attr_write(struct file *file, const char __user *buf,
			  size_t len, loff_t *ppos)
{
	struct simple_attr *attr;
	u64 val;
	size_t size;
	ssize_t ret;

	attr = file->private_data;
	if (!attr->set)
		return -EACCES;

847 848 849 850
	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

851 852 853 854 855 856 857
	ret = -EFAULT;
	size = min(sizeof(attr->set_buf) - 1, len);
	if (copy_from_user(attr->set_buf, buf, size))
		goto out;

	attr->set_buf[size] = '\0';
	val = simple_strtol(attr->set_buf, NULL, 0);
858 859 860
	ret = attr->set(attr->data, val);
	if (ret == 0)
		ret = len; /* on success, claim we got the whole input */
861
out:
I
Ingo Molnar 已提交
862
	mutex_unlock(&attr->mutex);
863 864 865
	return ret;
}

C
Christoph Hellwig 已提交
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893
/**
 * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
 * @sb:		filesystem to do the file handle conversion on
 * @fid:	file handle to convert
 * @fh_len:	length of the file handle in bytes
 * @fh_type:	type of file handle
 * @get_inode:	filesystem callback to retrieve inode
 *
 * This function decodes @fid as long as it has one of the well-known
 * Linux filehandle types and calls @get_inode on it to retrieve the
 * inode for the object specified in the file handle.
 */
struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type, struct inode *(*get_inode)
			(struct super_block *sb, u64 ino, u32 gen))
{
	struct inode *inode = NULL;

	if (fh_len < 2)
		return NULL;

	switch (fh_type) {
	case FILEID_INO32_GEN:
	case FILEID_INO32_GEN_PARENT:
		inode = get_inode(sb, fid->i32.ino, fid->i32.gen);
		break;
	}

894
	return d_obtain_alias(inode);
C
Christoph Hellwig 已提交
895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926
}
EXPORT_SYMBOL_GPL(generic_fh_to_dentry);

/**
 * generic_fh_to_dentry - generic helper for the fh_to_parent export operation
 * @sb:		filesystem to do the file handle conversion on
 * @fid:	file handle to convert
 * @fh_len:	length of the file handle in bytes
 * @fh_type:	type of file handle
 * @get_inode:	filesystem callback to retrieve inode
 *
 * This function decodes @fid as long as it has one of the well-known
 * Linux filehandle types and calls @get_inode on it to retrieve the
 * inode for the _parent_ object specified in the file handle if it
 * is specified in the file handle, or NULL otherwise.
 */
struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type, struct inode *(*get_inode)
			(struct super_block *sb, u64 ino, u32 gen))
{
	struct inode *inode = NULL;

	if (fh_len <= 2)
		return NULL;

	switch (fh_type) {
	case FILEID_INO32_GEN_PARENT:
		inode = get_inode(sb, fid->i32.parent_ino,
				  (fh_len > 3 ? fid->i32.parent_gen : 0));
		break;
	}

927
	return d_obtain_alias(inode);
C
Christoph Hellwig 已提交
928 929 930
}
EXPORT_SYMBOL_GPL(generic_fh_to_parent);

931 932 933 934 935 936 937 938 939 940
/**
 * generic_file_fsync - generic fsync implementation for simple filesystems
 * @file:	file to synchronize
 * @datasync:	only synchronize essential metadata if true
 *
 * This is a generic implementation of the fsync method for simple
 * filesystems which track all non-inode metadata in the buffers list
 * hanging off the address_space structure.
 */
int generic_file_fsync(struct file *file, int datasync)
A
Al Viro 已提交
941 942 943 944 945
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 0, /* metadata-only; caller takes care of data */
	};
946
	struct inode *inode = file->f_mapping->host;
A
Al Viro 已提交
947 948 949 950 951 952 953 954 955 956 957 958 959 960
	int err;
	int ret;

	ret = sync_mapping_buffers(inode->i_mapping);
	if (!(inode->i_state & I_DIRTY))
		return ret;
	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
		return ret;

	err = sync_inode(inode, &wbc);
	if (ret == 0)
		ret = err;
	return ret;
}
961 962 963 964 965 966 967 968 969
EXPORT_SYMBOL(generic_file_fsync);

/*
 * No-op implementation of ->fsync for in-memory filesystems.
 */
int noop_fsync(struct file *file, int datasync)
{
	return 0;
}
A
Al Viro 已提交
970

L
Linus Torvalds 已提交
971 972 973 974 975 976
EXPORT_SYMBOL(dcache_dir_close);
EXPORT_SYMBOL(dcache_dir_lseek);
EXPORT_SYMBOL(dcache_dir_open);
EXPORT_SYMBOL(dcache_readdir);
EXPORT_SYMBOL(generic_read_dir);
EXPORT_SYMBOL(get_sb_pseudo);
977 978
EXPORT_SYMBOL(simple_write_begin);
EXPORT_SYMBOL(simple_write_end);
L
Linus Torvalds 已提交
979 980 981 982 983 984 985 986 987 988 989 990 991
EXPORT_SYMBOL(simple_dir_inode_operations);
EXPORT_SYMBOL(simple_dir_operations);
EXPORT_SYMBOL(simple_empty);
EXPORT_SYMBOL(simple_fill_super);
EXPORT_SYMBOL(simple_getattr);
EXPORT_SYMBOL(simple_link);
EXPORT_SYMBOL(simple_lookup);
EXPORT_SYMBOL(simple_pin_fs);
EXPORT_SYMBOL(simple_readpage);
EXPORT_SYMBOL(simple_release_fs);
EXPORT_SYMBOL(simple_rename);
EXPORT_SYMBOL(simple_rmdir);
EXPORT_SYMBOL(simple_statfs);
992
EXPORT_SYMBOL(noop_fsync);
L
Linus Torvalds 已提交
993 994
EXPORT_SYMBOL(simple_unlink);
EXPORT_SYMBOL(simple_read_from_buffer);
995
EXPORT_SYMBOL(simple_write_to_buffer);
996
EXPORT_SYMBOL(memory_read_from_buffer);
997
EXPORT_SYMBOL(simple_transaction_set);
L
Linus Torvalds 已提交
998 999 1000
EXPORT_SYMBOL(simple_transaction_get);
EXPORT_SYMBOL(simple_transaction_read);
EXPORT_SYMBOL(simple_transaction_release);
1001
EXPORT_SYMBOL_GPL(simple_attr_open);
1002
EXPORT_SYMBOL_GPL(simple_attr_release);
1003 1004
EXPORT_SYMBOL_GPL(simple_attr_read);
EXPORT_SYMBOL_GPL(simple_attr_write);