[linux-2.6-block.git] / fs / libfs.c

/*
 *	fs/libfs.c
 *	Library for filesystems writers.
 */

#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/mutex.h>

#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;
}

int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	buf->f_type = dentry->d_sb->s_magic;
	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)
{
	static struct dentry_operations simple_dentry_operations = {
		.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 = "."};

	file->private_data = d_alloc(file->f_dentry, &cursor_name);

	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)
{
	mutex_lock(&file->f_dentry->d_inode->i_mutex);
	switch (origin) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
			mutex_unlock(&file->f_dentry->d_inode->i_mutex);
			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);
			list_del(&cursor->d_u.d_child);
			p = file->f_dentry->d_subdirs.next;
			while (n && p != &file->f_dentry->d_subdirs) {
				struct dentry *next;
				next = list_entry(p, struct dentry, d_u.d_child);
				if (!d_unhashed(next) && next->d_inode)
					n--;
				p = p->next;
			}
			list_add_tail(&cursor->d_u.d_child, p);
			spin_unlock(&dcache_lock);
		}
	}
	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
	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)
{
	struct dentry *dentry = filp->f_dentry;
	struct dentry *cursor = filp->private_data;
	struct list_head *p, *q = &cursor->d_u.d_child;
	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);
			if (filp->f_pos == 2)
				list_move(q, &dentry->d_subdirs);

			for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
				struct dentry *next;
				next = list_entry(p, struct dentry, d_u.d_child);
				if (d_unhashed(next) || !next->d_inode)
					continue;

				spin_unlock(&dcache_lock);
				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)
					return 0;
				spin_lock(&dcache_lock);
				/* next is still alive */
				list_move(q, p);
				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;
}

const struct file_operations simple_dir_operations = {
	.open		= dcache_dir_open,
	.release	= dcache_dir_close,
	.llseek		= dcache_dir_lseek,
	.read		= generic_read_dir,
	.readdir	= dcache_readdir,
	.fsync		= simple_sync_file,
};

struct inode_operations simple_dir_inode_operations = {
	.lookup		= simple_lookup,
};

/*
 * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
 * will never be mountable)
 */
int get_sb_pseudo(struct file_system_type *fs_type, char *name,
	struct super_operations *ops, unsigned long magic,
	struct vfsmount *mnt)
{
	struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
	static struct super_operations default_ops = {.statfs = simple_statfs};
	struct dentry *dentry;
	struct inode *root;
	struct qstr d_name = {.name = name, .len = strlen(name)};

	if (IS_ERR(s))
		return PTR_ERR(s);

	s->s_flags = MS_NOUSER;
	s->s_maxbytes = ~0ULL;
	s->s_blocksize = 1024;
	s->s_blocksize_bits = 10;
	s->s_magic = magic;
	s->s_op = ops ? ops : &default_ops;
	s->s_time_gran = 1;
	root = new_inode(s);
	if (!root)
		goto Enomem;
	root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
	root->i_uid = root->i_gid = 0;
	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;
	return simple_set_mnt(mnt, s);

Enomem:
	up_write(&s->s_umount);
	deactivate_super(s);
	return -ENOMEM;
}

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;
	inode->i_nlink++;
	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);
	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
		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;
	inode->i_nlink--;
	dput(dentry);
	return 0;
}

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

	dentry->d_inode->i_nlink--;
	simple_unlink(dir, dentry);
	dir->i_nlink--;
	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)
			old_dir->i_nlink--;
	} else if (they_are_dirs) {
		old_dir->i_nlink--;
		new_dir->i_nlink++;
	}

	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)
{
	void *kaddr;

	if (PageUptodate(page))
		goto out;

	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr, 0, PAGE_CACHE_SIZE);
	kunmap_atomic(kaddr, KM_USER0);
	flush_dcache_page(page);
	SetPageUptodate(page);
out:
	unlock_page(page);
	return 0;
}

int simple_prepare_write(struct file *file, struct page *page,
			unsigned from, unsigned to)
{
	if (!PageUptodate(page)) {
		if (to - from != PAGE_CACHE_SIZE) {
			void *kaddr = kmap_atomic(page, KM_USER0);
			memset(kaddr, 0, from);
			memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
			flush_dcache_page(page);
			kunmap_atomic(kaddr, KM_USER0);
		}
		SetPageUptodate(page);
	}
	return 0;
}

int simple_commit_write(struct file *file, struct page *page,
			unsigned offset, unsigned to)
{
	struct inode *inode = page->mapping->host;
	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;

	/*
	 * No need to use i_size_read() here, the i_size
	 * cannot change under us because we hold the i_mutex.
	 */
	if (pos > inode->i_size)
		i_size_write(inode, pos);
	set_page_dirty(page);
	return 0;
}

int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files)
{
	static struct super_operations s_ops = {.statfs = simple_statfs};
	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;
	s->s_op = &s_ops;
	s->s_time_gran = 1;

	inode = new_inode(s);
	if (!inode)
		return -ENOMEM;
	inode->i_mode = S_IFDIR | 0755;
	inode->i_uid = inode->i_gid = 0;
	inode->i_blksize = PAGE_CACHE_SIZE;
	inode->i_blocks = 0;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_op = &simple_dir_inode_operations;
	inode->i_fop = &simple_dir_operations;
	inode->i_nlink = 2;
	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;
		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_uid = inode->i_gid = 0;
		inode->i_blksize = PAGE_CACHE_SIZE;
		inode->i_blocks = 0;
		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);

int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
{
	struct vfsmount *mnt = NULL;
	spin_lock(&pin_fs_lock);
	if (unlikely(!*mount)) {
		spin_unlock(&pin_fs_lock);
		mnt = vfs_kern_mount(type, 0, type->name, NULL);
		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);
}

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

/*
 * 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.
 */
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;
}

/* Simple attribute files */

struct simple_attr {
	u64 (*get)(void *);
	void (*set)(void *, u64);
	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 */
	struct mutex mutex;	/* protects access to these buffers */
};

/* 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,
		     u64 (*get)(void *), void (*set)(void *, u64),
		     const char *fmt)
{
	struct simple_attr *attr;

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

	attr->get = get;
	attr->set = set;
	attr->data = inode->u.generic_ip;
	attr->fmt = fmt;
	mutex_init(&attr->mutex);

	file->private_data = attr;

	return nonseekable_open(inode, file);
}

int simple_attr_close(struct inode *inode, struct file *file)
{
	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;

	mutex_lock(&attr->mutex);
	if (*ppos) /* continued read */
		size = strlen(attr->get_buf);
	else	  /* first read */
		size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
				 attr->fmt,
				 (unsigned long long)attr->get(attr->data));

	ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
	mutex_unlock(&attr->mutex);
	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;

	mutex_lock(&attr->mutex);
	ret = -EFAULT;
	size = min(sizeof(attr->set_buf) - 1, len);
	if (copy_from_user(attr->set_buf, buf, size))
		goto out;

	ret = len; /* claim we got the whole input */
	attr->set_buf[size] = '\0';
	val = simple_strtol(attr->set_buf, NULL, 0);
	attr->set(attr->data, val);
out:
	mutex_unlock(&attr->mutex);
	return ret;
}

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);
EXPORT_SYMBOL(simple_commit_write);
EXPORT_SYMBOL(simple_dir_inode_operations);
EXPORT_SYMBOL(simple_dir_operations);
EXPORT_SYMBOL(simple_empty);
EXPORT_SYMBOL(d_alloc_name);
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_prepare_write);
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);
EXPORT_SYMBOL(simple_transaction_get);
EXPORT_SYMBOL(simple_transaction_read);
EXPORT_SYMBOL(simple_transaction_release);
EXPORT_SYMBOL_GPL(simple_attr_open);
EXPORT_SYMBOL_GPL(simple_attr_close);
EXPORT_SYMBOL_GPL(simple_attr_read);
EXPORT_SYMBOL_GPL(simple_attr_write);
Commit	Line	Data
1da177e4 LT	1	/*
	2	* fs/libfs.c
	3	* Library for filesystems writers.
	4	*/
	5
	6	#include <linux/module.h>
	7	#include <linux/pagemap.h>
	8	#include <linux/mount.h>
	9	#include <linux/vfs.h>
7cf34c76 IM	10	#include <linux/mutex.h>
7cf34c76 IM	11
1da177e4 LT	12	#include <asm/uaccess.h>
	13
	14	int simple_getattr(struct vfsmount mnt, struct dentry dentry,
	15	struct kstat *stat)
	16	{
	17	struct inode *inode = dentry->d_inode;
	18	generic_fillattr(inode, stat);
	19	stat->blocks = inode->i_mapping->nrpages << (PAGE_CACHE_SHIFT - 9);
	20	return 0;
	21	}
	22
726c3342	23	int simple_statfs(struct dentry dentry, struct kstatfs buf)
1da177e4	24	{
726c3342	25	buf->f_type = dentry->d_sb->s_magic;
1da177e4 LT	26	buf->f_bsize = PAGE_CACHE_SIZE;
	27	buf->f_namelen = NAME_MAX;
	28	return 0;
	29	}
	30
	31	/*
	32	* Retaining negative dentries for an in-memory filesystem just wastes
	33	* memory and lookup time: arrange for them to be deleted immediately.
	34	*/
	35	static int simple_delete_dentry(struct dentry *dentry)
	36	{
	37	return 1;
	38	}
	39
	40	/*
	41	* Lookup the data. This is trivial - if the dentry didn't already
	42	* exist, we know it is negative. Set d_op to delete negative dentries.
	43	*/
	44	struct dentry simple_lookup(struct inode dir, struct dentry dentry, struct nameidata nd)
	45	{
	46	static struct dentry_operations simple_dentry_operations = {
	47	.d_delete = simple_delete_dentry,
	48	};
	49
	50	if (dentry->d_name.len > NAME_MAX)
	51	return ERR_PTR(-ENAMETOOLONG);
	52	dentry->d_op = &simple_dentry_operations;
	53	d_add(dentry, NULL);
	54	return NULL;
	55	}
	56
	57	int simple_sync_file(struct file * file, struct dentry *dentry, int datasync)
	58	{
	59	return 0;
	60	}
	61
	62	int dcache_dir_open(struct inode inode, struct file file)
	63	{
	64	static struct qstr cursor_name = {.len = 1, .name = "."};
	65
	66	file->private_data = d_alloc(file->f_dentry, &cursor_name);
	67
	68	return file->private_data ? 0 : -ENOMEM;
	69	}
	70
	71	int dcache_dir_close(struct inode inode, struct file file)
	72	{
	73	dput(file->private_data);
	74	return 0;
	75	}
	76
	77	loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
	78	{
1b1dcc1b	79	mutex_lock(&file->f_dentry->d_inode->i_mutex);
1da177e4 LT	80	switch (origin) {
	81	case 1:
	82	offset += file->f_pos;
	83	case 0:
	84	if (offset >= 0)
	85	break;
	86	default:
1b1dcc1b	87	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
1da177e4 LT	88	return -EINVAL;
	89	}
	90	if (offset != file->f_pos) {
	91	file->f_pos = offset;
	92	if (file->f_pos >= 2) {
	93	struct list_head *p;
	94	struct dentry *cursor = file->private_data;
	95	loff_t n = file->f_pos - 2;
	96
	97	spin_lock(&dcache_lock);
5160ee6f	98	list_del(&cursor->d_u.d_child);
1da177e4 LT	99	p = file->f_dentry->d_subdirs.next;
	100	while (n && p != &file->f_dentry->d_subdirs) {
	101	struct dentry *next;
5160ee6f	102	next = list_entry(p, struct dentry, d_u.d_child);
1da177e4 LT	103	if (!d_unhashed(next) && next->d_inode)
	104	n--;
	105	p = p->next;
	106	}
5160ee6f	107	list_add_tail(&cursor->d_u.d_child, p);
1da177e4 LT	108	spin_unlock(&dcache_lock);
	109	}
	110	}
1b1dcc1b	111	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
1da177e4 LT	112	return offset;
	113	}
	114
	115	/* Relationship between i_mode and the DT_xxx types */
	116	static inline unsigned char dt_type(struct inode *inode)
	117	{
	118	return (inode->i_mode >> 12) & 15;
	119	}
	120
	121	/*
	122	* Directory is locked and all positive dentries in it are safe, since
	123	* for ramfs-type trees they can't go away without unlink() or rmdir(),
	124	* both impossible due to the lock on directory.
	125	*/
	126
	127	int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir)
	128	{
	129	struct dentry *dentry = filp->f_dentry;
	130	struct dentry *cursor = filp->private_data;
5160ee6f	131	struct list_head p, q = &cursor->d_u.d_child;
1da177e4 LT	132	ino_t ino;
	133	int i = filp->f_pos;
	134
	135	switch (i) {
	136	case 0:
	137	ino = dentry->d_inode->i_ino;
	138	if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
	139	break;
	140	filp->f_pos++;
	141	i++;
	142	/* fallthrough */
	143	case 1:
	144	ino = parent_ino(dentry);
	145	if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
	146	break;
	147	filp->f_pos++;
	148	i++;
	149	/* fallthrough */
	150	default:
	151	spin_lock(&dcache_lock);
1bfba4e8 AM	152	if (filp->f_pos == 2)
	153	list_move(q, &dentry->d_subdirs);
	154
1da177e4 LT	155	for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
1da177e4 LT	156	struct dentry *next;
5160ee6f	157	next = list_entry(p, struct dentry, d_u.d_child);
1da177e4 LT	158	if (d_unhashed(next) \|\| !next->d_inode)
	159	continue;
	160
	161	spin_unlock(&dcache_lock);
	162	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)
	163	return 0;
	164	spin_lock(&dcache_lock);
	165	/* next is still alive */
1bfba4e8	166	list_move(q, p);
1da177e4 LT	167	p = q;
	168	filp->f_pos++;
	169	}
	170	spin_unlock(&dcache_lock);
	171	}
	172	return 0;
	173	}
	174
	175	ssize_t generic_read_dir(struct file filp, char __user buf, size_t siz, loff_t *ppos)
	176	{
	177	return -EISDIR;
	178	}
	179
4b6f5d20	180	const struct file_operations simple_dir_operations = {
1da177e4 LT	181	.open = dcache_dir_open,
	182	.release = dcache_dir_close,
	183	.llseek = dcache_dir_lseek,
	184	.read = generic_read_dir,
	185	.readdir = dcache_readdir,
8ae0b778	186	.fsync = simple_sync_file,
1da177e4 LT	187	};
	188
	189	struct inode_operations simple_dir_inode_operations = {
	190	.lookup = simple_lookup,
	191	};
	192
	193	/*
	194	* Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
	195	* will never be mountable)
	196	*/
454e2398 DH	197	int get_sb_pseudo(struct file_system_type fs_type, char name,
	198	struct super_operations *ops, unsigned long magic,
	199	struct vfsmount *mnt)
1da177e4 LT	200	{
	201	struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
	202	static struct super_operations default_ops = {.statfs = simple_statfs};
	203	struct dentry *dentry;
	204	struct inode *root;
	205	struct qstr d_name = {.name = name, .len = strlen(name)};
	206
	207	if (IS_ERR(s))
454e2398	208	return PTR_ERR(s);
1da177e4 LT	209
	210	s->s_flags = MS_NOUSER;
	211	s->s_maxbytes = ~0ULL;
	212	s->s_blocksize = 1024;
	213	s->s_blocksize_bits = 10;
	214	s->s_magic = magic;
	215	s->s_op = ops ? ops : &default_ops;
	216	s->s_time_gran = 1;
	217	root = new_inode(s);
	218	if (!root)
	219	goto Enomem;
	220	root->i_mode = S_IFDIR \| S_IRUSR \| S_IWUSR;
	221	root->i_uid = root->i_gid = 0;
	222	root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME;
	223	dentry = d_alloc(NULL, &d_name);
	224	if (!dentry) {
	225	iput(root);
	226	goto Enomem;
	227	}
	228	dentry->d_sb = s;
	229	dentry->d_parent = dentry;
	230	d_instantiate(dentry, root);
	231	s->s_root = dentry;
	232	s->s_flags \|= MS_ACTIVE;
454e2398	233	return simple_set_mnt(mnt, s);
1da177e4 LT	234
	235	Enomem:
	236	up_write(&s->s_umount);
	237	deactivate_super(s);
454e2398	238	return -ENOMEM;
1da177e4 LT	239	}
	240
	241	int simple_link(struct dentry old_dentry, struct inode dir, struct dentry *dentry)
	242	{
	243	struct inode *inode = old_dentry->d_inode;
	244
	245	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	246	inode->i_nlink++;
	247	atomic_inc(&inode->i_count);
	248	dget(dentry);
	249	d_instantiate(dentry, inode);
	250	return 0;
	251	}
	252
	253	static inline int simple_positive(struct dentry *dentry)
	254	{
	255	return dentry->d_inode && !d_unhashed(dentry);
	256	}
	257
	258	int simple_empty(struct dentry *dentry)
	259	{
	260	struct dentry *child;
	261	int ret = 0;
	262
	263	spin_lock(&dcache_lock);
5160ee6f	264	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
1da177e4 LT	265	if (simple_positive(child))
	266	goto out;
	267	ret = 1;
	268	out:
	269	spin_unlock(&dcache_lock);
	270	return ret;
	271	}
	272
	273	int simple_unlink(struct inode dir, struct dentry dentry)
	274	{
	275	struct inode *inode = dentry->d_inode;
	276
	277	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	278	inode->i_nlink--;
	279	dput(dentry);
	280	return 0;
	281	}
	282
	283	int simple_rmdir(struct inode dir, struct dentry dentry)
	284	{
	285	if (!simple_empty(dentry))
	286	return -ENOTEMPTY;
	287
	288	dentry->d_inode->i_nlink--;
	289	simple_unlink(dir, dentry);
	290	dir->i_nlink--;
	291	return 0;
	292	}
	293
	294	int simple_rename(struct inode old_dir, struct dentry old_dentry,
	295	struct inode new_dir, struct dentry new_dentry)
	296	{
	297	struct inode *inode = old_dentry->d_inode;
	298	int they_are_dirs = S_ISDIR(old_dentry->d_inode->i_mode);
	299
	300	if (!simple_empty(new_dentry))
	301	return -ENOTEMPTY;
	302
	303	if (new_dentry->d_inode) {
	304	simple_unlink(new_dir, new_dentry);
	305	if (they_are_dirs)
	306	old_dir->i_nlink--;
	307	} else if (they_are_dirs) {
	308	old_dir->i_nlink--;
	309	new_dir->i_nlink++;
	310	}
	311
	312	old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime =
	313	new_dir->i_mtime = inode->i_ctime = CURRENT_TIME;
	314
	315	return 0;
	316	}
	317
	318	int simple_readpage(struct file file, struct page page)
	319	{
	320	void *kaddr;
	321
	322	if (PageUptodate(page))
	323	goto out;
	324
	325	kaddr = kmap_atomic(page, KM_USER0);
	326	memset(kaddr, 0, PAGE_CACHE_SIZE);
	327	kunmap_atomic(kaddr, KM_USER0);
	328	flush_dcache_page(page);
329	SetPageUptodate(page);
330	out:
331	unlock_page(page);
332	return 0;
333	}
334
335	int simple_prepare_write(struct file file, struct page page,
336	unsigned from, unsigned to)
337	{
338	if (!PageUptodate(page)) {
339	if (to - from != PAGE_CACHE_SIZE) {
340	void *kaddr = kmap_atomic(page, KM_USER0);
341	memset(kaddr, 0, from);
342	memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
343	flush_dcache_page(page);
344	kunmap_atomic(kaddr, KM_USER0);
345	}
346	SetPageUptodate(page);
347	}
348	return 0;
349	}
350
351	int simple_commit_write(struct file file, struct page page,
352	unsigned offset, unsigned to)
353	{
354	struct inode *inode = page->mapping->host;
355	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
356
357	/*
358	* No need to use i_size_read() here, the i_size
1b1dcc1b	359	* cannot change under us because we hold the i_mutex.
1da177e4 LT	360	*/
	361	if (pos > inode->i_size)
	362	i_size_write(inode, pos);
	363	set_page_dirty(page);
	364	return 0;
	365	}
	366
	367	int simple_fill_super(struct super_block s, int magic, struct tree_descr files)
	368	{
	369	static struct super_operations s_ops = {.statfs = simple_statfs};
	370	struct inode *inode;
	371	struct dentry *root;
	372	struct dentry *dentry;
	373	int i;
	374
	375	s->s_blocksize = PAGE_CACHE_SIZE;
	376	s->s_blocksize_bits = PAGE_CACHE_SHIFT;
	377	s->s_magic = magic;
	378	s->s_op = &s_ops;
	379	s->s_time_gran = 1;
	380
	381	inode = new_inode(s);
	382	if (!inode)
	383	return -ENOMEM;
	384	inode->i_mode = S_IFDIR \| 0755;
	385	inode->i_uid = inode->i_gid = 0;
	386	inode->i_blksize = PAGE_CACHE_SIZE;
	387	inode->i_blocks = 0;
	388	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	389	inode->i_op = &simple_dir_inode_operations;
	390	inode->i_fop = &simple_dir_operations;
7656f328	391	inode->i_nlink = 2;
1da177e4 LT	392	root = d_alloc_root(inode);
	393	if (!root) {
	394	iput(inode);
	395	return -ENOMEM;
	396	}
	397	for (i = 0; !files->name \|\| files->name[0]; i++, files++) {
	398	if (!files->name)
	399	continue;
	400	dentry = d_alloc_name(root, files->name);
	401	if (!dentry)
	402	goto out;
	403	inode = new_inode(s);
	404	if (!inode)
	405	goto out;
	406	inode->i_mode = S_IFREG \| files->mode;
	407	inode->i_uid = inode->i_gid = 0;
	408	inode->i_blksize = PAGE_CACHE_SIZE;
	409	inode->i_blocks = 0;
	410	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	411	inode->i_fop = files->ops;
	412	inode->i_ino = i;
	413	d_add(dentry, inode);
	414	}
	415	s->s_root = root;
	416	return 0;
	417	out:
	418	d_genocide(root);
	419	dput(root);
	420	return -ENOMEM;
	421	}
	422
	423	static DEFINE_SPINLOCK(pin_fs_lock);
	424
1f5ce9e9	425	int simple_pin_fs(struct file_system_type type, struct vfsmount mount, int count)
1da177e4 LT	426	{
	427	struct vfsmount *mnt = NULL;
	428	spin_lock(&pin_fs_lock);
	429	if (unlikely(!*mount)) {
	430	spin_unlock(&pin_fs_lock);
1f5ce9e9	431	mnt = vfs_kern_mount(type, 0, type->name, NULL);
1da177e4 LT	432	if (IS_ERR(mnt))
	433	return PTR_ERR(mnt);
	434	spin_lock(&pin_fs_lock);
	435	if (!*mount)
	436	*mount = mnt;
	437	}
	438	mntget(*mount);
	439	++*count;
	440	spin_unlock(&pin_fs_lock);
	441	mntput(mnt);
	442	return 0;
	443	}
	444
	445	void simple_release_fs(struct vfsmount *mount, int count)
	446	{
	447	struct vfsmount *mnt;
	448	spin_lock(&pin_fs_lock);
	449	mnt = *mount;
	450	if (!--*count)
	451	*mount = NULL;
	452	spin_unlock(&pin_fs_lock);
	453	mntput(mnt);
	454	}
	455
	456	ssize_t simple_read_from_buffer(void __user to, size_t count, loff_t ppos,
	457	const void *from, size_t available)
	458	{
	459	loff_t pos = *ppos;
	460	if (pos < 0)
	461	return -EINVAL;
	462	if (pos >= available)
	463	return 0;
	464	if (count > available - pos)
	465	count = available - pos;
	466	if (copy_to_user(to, from + pos, count))
	467	return -EFAULT;
	468	*ppos = pos + count;
	469	return count;
	470	}
	471
	472	/*
	473	* Transaction based IO.
	474	* The file expects a single write which triggers the transaction, and then
	475	* possibly a read which collects the result - which is stored in a
	476	* file-local buffer.
	477	*/
	478	char simple_transaction_get(struct file file, const char __user *buf, size_t size)
	479	{
	480	struct simple_transaction_argresp *ar;
	481	static DEFINE_SPINLOCK(simple_transaction_lock);
	482
	483	if (size > SIMPLE_TRANSACTION_LIMIT - 1)
	484	return ERR_PTR(-EFBIG);
	485
	486	ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL);
	487	if (!ar)
	488	return ERR_PTR(-ENOMEM);
	489
	490	spin_lock(&simple_transaction_lock);
	491
	492	/* only one write allowed per open */
	493	if (file->private_data) {
	494	spin_unlock(&simple_transaction_lock);
	495	free_page((unsigned long)ar);
496	return ERR_PTR(-EBUSY);
497	}
498
499	file->private_data = ar;
500
501	spin_unlock(&simple_transaction_lock);
502
503	if (copy_from_user(ar->data, buf, size))
504	return ERR_PTR(-EFAULT);
505
506	return ar->data;
507	}
508
509	ssize_t simple_transaction_read(struct file file, char __user buf, size_t size, loff_t *pos)
510	{
511	struct simple_transaction_argresp *ar = file->private_data;
512
513	if (!ar)
514	return 0;
515	return simple_read_from_buffer(buf, size, pos, ar->data, ar->size);
516	}
517
518	int simple_transaction_release(struct inode inode, struct file file)
519	{
520	free_page((unsigned long)file->private_data);
521	return 0;
522	}
523
acaefc25 AB	524	/* Simple attribute files */
	525
	526	struct simple_attr {
	527	u64 (get)(void );
	528	void (set)(void , u64);
	529	char get_buf[24]; /* enough to store a u64 and "\n\0" */
	530	char set_buf[24];
	531	void *data;
	532	const char fmt; / format for read operation */
7cf34c76	533	struct mutex mutex; /* protects access to these buffers */
acaefc25 AB	534	};
	535
	536	/* simple_attr_open is called by an actual attribute open file operation
	537	* to set the attribute specific access operations. */
	538	int simple_attr_open(struct inode inode, struct file file,
	539	u64 (get)(void ), void (set)(void , u64),
	540	const char *fmt)
	541	{
	542	struct simple_attr *attr;
	543
	544	attr = kmalloc(sizeof(*attr), GFP_KERNEL);
	545	if (!attr)
	546	return -ENOMEM;
	547
	548	attr->get = get;
	549	attr->set = set;
	550	attr->data = inode->u.generic_ip;
	551	attr->fmt = fmt;
7cf34c76	552	mutex_init(&attr->mutex);
acaefc25 AB	553
	554	file->private_data = attr;
	555
	556	return nonseekable_open(inode, file);
	557	}
	558
	559	int simple_attr_close(struct inode inode, struct file file)
	560	{
	561	kfree(file->private_data);
	562	return 0;
	563	}
	564
	565	/* read from the buffer that is filled with the get function */
	566	ssize_t simple_attr_read(struct file file, char __user buf,
	567	size_t len, loff_t *ppos)
	568	{
	569	struct simple_attr *attr;
	570	size_t size;
	571	ssize_t ret;
	572
	573	attr = file->private_data;
	574
	575	if (!attr->get)
	576	return -EACCES;
	577
7cf34c76	578	mutex_lock(&attr->mutex);
acaefc25 AB	579	if (ppos) / continued read */
	580	size = strlen(attr->get_buf);
	581	else /* first read */
	582	size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
	583	attr->fmt,
	584	(unsigned long long)attr->get(attr->data));
	585
	586	ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
7cf34c76	587	mutex_unlock(&attr->mutex);
acaefc25 AB	588	return ret;
	589	}
	590
	591	/* interpret the buffer as a number to call the set function with */
	592	ssize_t simple_attr_write(struct file file, const char __user buf,
	593	size_t len, loff_t *ppos)
	594	{
	595	struct simple_attr *attr;
	596	u64 val;
	597	size_t size;
	598	ssize_t ret;
	599
	600	attr = file->private_data;
	601
	602	if (!attr->set)
	603	return -EACCES;
	604
7cf34c76	605	mutex_lock(&attr->mutex);
acaefc25 AB	606	ret = -EFAULT;
	607	size = min(sizeof(attr->set_buf) - 1, len);
	608	if (copy_from_user(attr->set_buf, buf, size))
	609	goto out;
	610
	611	ret = len; /* claim we got the whole input */
	612	attr->set_buf[size] = '\0';
	613	val = simple_strtol(attr->set_buf, NULL, 0);
	614	attr->set(attr->data, val);
	615	out:
7cf34c76	616	mutex_unlock(&attr->mutex);
acaefc25 AB	617	return ret;
	618	}
	619
1da177e4 LT	620	EXPORT_SYMBOL(dcache_dir_close);
	621	EXPORT_SYMBOL(dcache_dir_lseek);
	622	EXPORT_SYMBOL(dcache_dir_open);
	623	EXPORT_SYMBOL(dcache_readdir);
	624	EXPORT_SYMBOL(generic_read_dir);
	625	EXPORT_SYMBOL(get_sb_pseudo);
	626	EXPORT_SYMBOL(simple_commit_write);
	627	EXPORT_SYMBOL(simple_dir_inode_operations);
	628	EXPORT_SYMBOL(simple_dir_operations);
	629	EXPORT_SYMBOL(simple_empty);
	630	EXPORT_SYMBOL(d_alloc_name);
	631	EXPORT_SYMBOL(simple_fill_super);
	632	EXPORT_SYMBOL(simple_getattr);
	633	EXPORT_SYMBOL(simple_link);
	634	EXPORT_SYMBOL(simple_lookup);
	635	EXPORT_SYMBOL(simple_pin_fs);
	636	EXPORT_SYMBOL(simple_prepare_write);
	637	EXPORT_SYMBOL(simple_readpage);
	638	EXPORT_SYMBOL(simple_release_fs);
	639	EXPORT_SYMBOL(simple_rename);
	640	EXPORT_SYMBOL(simple_rmdir);
	641	EXPORT_SYMBOL(simple_statfs);
	642	EXPORT_SYMBOL(simple_sync_file);
	643	EXPORT_SYMBOL(simple_unlink);
	644	EXPORT_SYMBOL(simple_read_from_buffer);
	645	EXPORT_SYMBOL(simple_transaction_get);
	646	EXPORT_SYMBOL(simple_transaction_read);
	647	EXPORT_SYMBOL(simple_transaction_release);
acaefc25 AB	648	EXPORT_SYMBOL_GPL(simple_attr_open);
	649	EXPORT_SYMBOL_GPL(simple_attr_close);
	650	EXPORT_SYMBOL_GPL(simple_attr_read);
	651	EXPORT_SYMBOL_GPL(simple_attr_write);