libfs.c 21.8 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>
I
Ingo Molnar 已提交
11
#include <linux/mutex.h>
C
Christoph Hellwig 已提交
12
#include <linux/exportfs.h>
A
Al Viro 已提交
13 14
#include <linux/writeback.h>
#include <linux/buffer_head.h>
I
Ingo Molnar 已提交
15

L
Linus Torvalds 已提交
16 17 18 19 20 21 22 23 24 25 26
#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;
}

27
int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
L
Linus Torvalds 已提交
28
{
29
	buf->f_type = dentry->d_sb->s_magic;
L
Linus Torvalds 已提交
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
	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
50
	static const struct dentry_operations simple_dentry_operations = {
L
Linus Torvalds 已提交
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
		.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 simple_sync_file(struct file * file, struct dentry *dentry, int datasync)
{
	return 0;
}
 
int dcache_dir_open(struct inode *inode, struct file *file)
{
	static struct qstr cursor_name = {.len = 1, .name = "."};

70
	file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
L
Linus Torvalds 已提交
71 72 73 74 75 76 77 78 79 80 81 82

	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)
{
83
	mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
84 85 86 87 88 89 90
	switch (origin) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
91
			mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
92 93 94 95 96 97 98 99 100 101
			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
102
			list_del(&cursor->d_u.d_child);
103 104
			p = file->f_path.dentry->d_subdirs.next;
			while (n && p != &file->f_path.dentry->d_subdirs) {
L
Linus Torvalds 已提交
105
				struct dentry *next;
E
Eric Dumazet 已提交
106
				next = list_entry(p, struct dentry, d_u.d_child);
L
Linus Torvalds 已提交
107 108 109 110
				if (!d_unhashed(next) && next->d_inode)
					n--;
				p = p->next;
			}
E
Eric Dumazet 已提交
111
			list_add_tail(&cursor->d_u.d_child, p);
L
Linus Torvalds 已提交
112 113 114
			spin_unlock(&dcache_lock);
		}
	}
115
	mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
	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)
{
133
	struct dentry *dentry = filp->f_path.dentry;
L
Linus Torvalds 已提交
134
	struct dentry *cursor = filp->private_data;
E
Eric Dumazet 已提交
135
	struct list_head *p, *q = &cursor->d_u.d_child;
L
Linus Torvalds 已提交
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
	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
156 157 158
			if (filp->f_pos == 2)
				list_move(q, &dentry->d_subdirs);

L
Linus Torvalds 已提交
159 160
			for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
				struct dentry *next;
E
Eric Dumazet 已提交
161
				next = list_entry(p, struct dentry, d_u.d_child);
L
Linus Torvalds 已提交
162 163 164 165
				if (d_unhashed(next) || !next->d_inode)
					continue;

				spin_unlock(&dcache_lock);
166 167 168 169
				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
170 171 172
					return 0;
				spin_lock(&dcache_lock);
				/* next is still alive */
A
Akinobu Mita 已提交
173
				list_move(q, p);
L
Linus Torvalds 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186
				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;
}

187
const struct file_operations simple_dir_operations = {
L
Linus Torvalds 已提交
188 189 190 191 192
	.open		= dcache_dir_open,
	.release	= dcache_dir_close,
	.llseek		= dcache_dir_lseek,
	.read		= generic_read_dir,
	.readdir	= dcache_readdir,
193
	.fsync		= simple_sync_file,
L
Linus Torvalds 已提交
194 195
};

196
const struct inode_operations simple_dir_inode_operations = {
L
Linus Torvalds 已提交
197 198 199
	.lookup		= simple_lookup,
};

200 201 202 203
static const struct super_operations simple_super_operations = {
	.statfs		= simple_statfs,
};

L
Linus Torvalds 已提交
204 205 206 207
/*
 * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
 * will never be mountable)
 */
208
int get_sb_pseudo(struct file_system_type *fs_type, char *name,
209
	const struct super_operations *ops, unsigned long magic,
210
	struct vfsmount *mnt)
L
Linus Torvalds 已提交
211 212 213 214 215 216 217
{
	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))
218
		return PTR_ERR(s);
L
Linus Torvalds 已提交
219 220

	s->s_flags = MS_NOUSER;
221
	s->s_maxbytes = MAX_LFS_FILESIZE;
222 223
	s->s_blocksize = PAGE_SIZE;
	s->s_blocksize_bits = PAGE_SHIFT;
L
Linus Torvalds 已提交
224
	s->s_magic = magic;
225
	s->s_op = ops ? ops : &simple_super_operations;
L
Linus Torvalds 已提交
226 227 228 229
	s->s_time_gran = 1;
	root = new_inode(s);
	if (!root)
		goto Enomem;
230 231 232 233 234 235
	/*
	 * 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
236 237 238 239 240 241 242 243 244 245 246 247
	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;
248 249
	simple_set_mnt(mnt, s);
	return 0;
L
Linus Torvalds 已提交
250 251

Enomem:
252
	deactivate_locked_super(s);
253
	return -ENOMEM;
L
Linus Torvalds 已提交
254 255 256 257 258 259 260
}

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;
261
	inc_nlink(inode);
L
Linus Torvalds 已提交
262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
	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
279
	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
L
Linus Torvalds 已提交
280 281 282 283 284 285 286 287 288 289 290 291 292
		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;
293
	drop_nlink(inode);
L
Linus Torvalds 已提交
294 295 296 297 298 299 300 301 302
	dput(dentry);
	return 0;
}

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

303
	drop_nlink(dentry->d_inode);
L
Linus Torvalds 已提交
304
	simple_unlink(dir, dentry);
305
	drop_nlink(dir);
L
Linus Torvalds 已提交
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
	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)
321
			drop_nlink(old_dir);
L
Linus Torvalds 已提交
322
	} else if (they_are_dirs) {
323
		drop_nlink(old_dir);
324
		inc_nlink(new_dir);
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334
	}

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

	return 0;
}

int simple_readpage(struct file *file, struct page *page)
{
335
	clear_highpage(page);
L
Linus Torvalds 已提交
336 337 338 339 340 341
	flush_dcache_page(page);
	SetPageUptodate(page);
	unlock_page(page);
	return 0;
}

342 343 344 345 346 347 348 349 350
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;

351
	page = grab_cache_page_write_begin(mapping, index, flags);
352 353 354 355 356
	if (!page)
		return -ENOMEM;

	*pagep = page;

357 358 359 360 361 362
	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;
363 364
}

365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
/**
 * 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.
 */
386 387 388 389
int simple_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
390 391
	struct inode *inode = page->mapping->host;
	loff_t last_pos = pos + copied;
392 393 394

	/* zero the stale part of the page if we did a short copy */
	if (copied < len) {
395 396 397
		unsigned from = pos & (PAGE_CACHE_SIZE - 1);

		zero_user(page, from + copied, len - copied);
398 399
	}

400 401 402 403 404 405 406 407
	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);
408

409
	set_page_dirty(page);
410 411 412 413 414 415
	unlock_page(page);
	page_cache_release(page);

	return copied;
}

416 417 418 419 420
/*
 * 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.
 */
L
Linus Torvalds 已提交
421 422 423 424 425 426 427 428 429 430
int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files)
{
	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;
431
	s->s_op = &simple_super_operations;
L
Linus Torvalds 已提交
432 433 434 435 436
	s->s_time_gran = 1;

	inode = new_inode(s);
	if (!inode)
		return -ENOMEM;
437 438 439 440 441
	/*
	 * 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
442 443 444 445
	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;
446
	inode->i_nlink = 2;
L
Linus Torvalds 已提交
447 448 449 450 451 452 453 454
	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;
455 456 457 458 459 460 461

		/* 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
462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
		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);

484
int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
L
Linus Torvalds 已提交
485 486 487 488 489
{
	struct vfsmount *mnt = NULL;
	spin_lock(&pin_fs_lock);
	if (unlikely(!*mount)) {
		spin_unlock(&pin_fs_lock);
490
		mnt = vfs_kern_mount(type, 0, type->name, NULL);
L
Linus Torvalds 已提交
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514
		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);
}

515 516 517 518 519 520 521 522 523 524 525 526 527 528
/**
 * 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
529 530 531 532
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;
533 534
	size_t ret;

L
Linus Torvalds 已提交
535 536
	if (pos < 0)
		return -EINVAL;
537
	if (pos >= available || !count)
L
Linus Torvalds 已提交
538 539 540
		return 0;
	if (count > available - pos)
		count = available - pos;
541 542
	ret = copy_to_user(to, from + pos, count);
	if (ret == count)
L
Linus Torvalds 已提交
543
		return -EFAULT;
544
	count -= ret;
L
Linus Torvalds 已提交
545 546 547 548
	*ppos = pos + count;
	return count;
}

549 550 551 552 553 554 555 556 557 558 559 560 561 562
/**
 * 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.
 **/
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579
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
580 581 582 583 584 585
/*
 * 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.
 */
586 587 588 589 590 591 592 593 594 595 596 597 598 599 600

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
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646
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;
}

647 648 649
/* Simple attribute files */

struct simple_attr {
650 651
	int (*get)(void *, u64 *);
	int (*set)(void *, u64);
652 653 654 655
	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
656
	struct mutex mutex;	/* protects access to these buffers */
657 658 659 660 661
};

/* 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,
662
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
663 664 665 666 667 668 669 670 671 672
		     const char *fmt)
{
	struct simple_attr *attr;

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

	attr->get = get;
	attr->set = set;
673
	attr->data = inode->i_private;
674
	attr->fmt = fmt;
I
Ingo Molnar 已提交
675
	mutex_init(&attr->mutex);
676 677 678 679 680 681

	file->private_data = attr;

	return nonseekable_open(inode, file);
}

682
int simple_attr_release(struct inode *inode, struct file *file)
683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700
{
	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;

701 702 703 704
	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

705
	if (*ppos) {		/* continued read */
706
		size = strlen(attr->get_buf);
707 708 709 710 711 712
	} else {		/* first read */
		u64 val;
		ret = attr->get(attr->data, &val);
		if (ret)
			goto out;

713
		size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
714 715
				 attr->fmt, (unsigned long long)val);
	}
716 717

	ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
718
out:
I
Ingo Molnar 已提交
719
	mutex_unlock(&attr->mutex);
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735
	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;

736 737 738 739
	ret = mutex_lock_interruptible(&attr->mutex);
	if (ret)
		return ret;

740 741 742 743 744 745 746
	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);
747 748 749
	ret = attr->set(attr->data, val);
	if (ret == 0)
		ret = len; /* on success, claim we got the whole input */
750
out:
I
Ingo Molnar 已提交
751
	mutex_unlock(&attr->mutex);
752 753 754
	return ret;
}

C
Christoph Hellwig 已提交
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
/**
 * 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;
	}

783
	return d_obtain_alias(inode);
C
Christoph Hellwig 已提交
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
}
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;
	}

816
	return d_obtain_alias(inode);
C
Christoph Hellwig 已提交
817 818 819
}
EXPORT_SYMBOL_GPL(generic_fh_to_parent);

A
Al Viro 已提交
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842
int simple_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 0, /* metadata-only; caller takes care of data */
	};
	struct inode *inode = dentry->d_inode;
	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;
}
EXPORT_SYMBOL(simple_fsync);

L
Linus Torvalds 已提交
843 844 845 846 847 848
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);
849 850
EXPORT_SYMBOL(simple_write_begin);
EXPORT_SYMBOL(simple_write_end);
L
Linus Torvalds 已提交
851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866
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);
EXPORT_SYMBOL(simple_sync_file);
EXPORT_SYMBOL(simple_unlink);
EXPORT_SYMBOL(simple_read_from_buffer);
867
EXPORT_SYMBOL(memory_read_from_buffer);
868
EXPORT_SYMBOL(simple_transaction_set);
L
Linus Torvalds 已提交
869 870 871
EXPORT_SYMBOL(simple_transaction_get);
EXPORT_SYMBOL(simple_transaction_read);
EXPORT_SYMBOL(simple_transaction_release);
872
EXPORT_SYMBOL_GPL(simple_attr_open);
873
EXPORT_SYMBOL_GPL(simple_attr_release);
874 875
EXPORT_SYMBOL_GPL(simple_attr_read);
EXPORT_SYMBOL_GPL(simple_attr_write);