#include <linux/module.h>
#include <linux/pagemap.h>
+#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/mutex.h>
+#include <linux/exportfs.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/uaccess.h>
return 0;
}
-int simple_statfs(struct super_block *sb, struct kstatfs *buf)
+int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
{
- buf->f_type = sb->s_magic;
+ buf->f_type = dentry->d_sb->s_magic;
buf->f_bsize = PAGE_CACHE_SIZE;
buf->f_namelen = NAME_MAX;
return 0;
*/
struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
- static struct dentry_operations simple_dentry_operations = {
+ static const struct dentry_operations simple_dentry_operations = {
.d_delete = simple_delete_dentry,
};
{
static struct qstr cursor_name = {.len = 1, .name = "."};
- file->private_data = d_alloc(file->f_dentry, &cursor_name);
+ file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
return file->private_data ? 0 : -ENOMEM;
}
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
{
- mutex_lock(&file->f_dentry->d_inode->i_mutex);
+ mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
switch (origin) {
case 1:
offset += file->f_pos;
if (offset >= 0)
break;
default:
- mutex_unlock(&file->f_dentry->d_inode->i_mutex);
+ mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
return -EINVAL;
}
if (offset != file->f_pos) {
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) {
+ p = file->f_path.dentry->d_subdirs.next;
+ while (n && p != &file->f_path.dentry->d_subdirs) {
struct dentry *next;
next = list_entry(p, struct dentry, d_u.d_child);
if (!d_unhashed(next) && next->d_inode)
spin_unlock(&dcache_lock);
}
}
- mutex_unlock(&file->f_dentry->d_inode->i_mutex);
+ mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
return offset;
}
int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- struct dentry *dentry = filp->f_dentry;
+ struct dentry *dentry = filp->f_path.dentry;
struct dentry *cursor = filp->private_data;
struct list_head *p, *q = &cursor->d_u.d_child;
ino_t ino;
/* fallthrough */
default:
spin_lock(&dcache_lock);
- if (filp->f_pos == 2) {
- list_del(q);
- list_add(q, &dentry->d_subdirs);
- }
+ 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);
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)
+ 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_del(q);
- list_add(q, p);
+ list_move(q, p);
p = q;
filp->f_pos++;
}
.fsync = simple_sync_file,
};
-struct inode_operations simple_dir_inode_operations = {
+const struct inode_operations simple_dir_inode_operations = {
.lookup = simple_lookup,
};
+static const struct super_operations simple_super_operations = {
+ .statfs = simple_statfs,
+};
+
/*
* Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
* will never be mountable)
*/
-struct super_block *
-get_sb_pseudo(struct file_system_type *fs_type, char *name,
- struct super_operations *ops, unsigned long magic)
+int get_sb_pseudo(struct file_system_type *fs_type, char *name,
+ const 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 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_maxbytes = MAX_LFS_FILESIZE;
+ s->s_blocksize = PAGE_SIZE;
+ s->s_blocksize_bits = PAGE_SHIFT;
s->s_magic = magic;
- s->s_op = ops ? ops : &default_ops;
+ s->s_op = ops ? ops : &simple_super_operations;
s->s_time_gran = 1;
root = new_inode(s);
if (!root)
goto Enomem;
+ /*
+ * 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;
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) {
d_instantiate(dentry, root);
s->s_root = dentry;
s->s_flags |= MS_ACTIVE;
- return s;
+ simple_set_mnt(mnt, s);
+ return 0;
Enomem:
- up_write(&s->s_umount);
- deactivate_super(s);
- return ERR_PTR(-ENOMEM);
+ deactivate_locked_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++;
+ inc_nlink(inode);
atomic_inc(&inode->i_count);
dget(dentry);
d_instantiate(dentry, inode);
struct inode *inode = dentry->d_inode;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
- inode->i_nlink--;
+ drop_nlink(inode);
dput(dentry);
return 0;
}
if (!simple_empty(dentry))
return -ENOTEMPTY;
- dentry->d_inode->i_nlink--;
+ drop_nlink(dentry->d_inode);
simple_unlink(dir, dentry);
- dir->i_nlink--;
+ drop_nlink(dir);
return 0;
}
if (new_dentry->d_inode) {
simple_unlink(new_dir, new_dentry);
if (they_are_dirs)
- old_dir->i_nlink--;
+ drop_nlink(old_dir);
} else if (they_are_dirs) {
- old_dir->i_nlink--;
- new_dir->i_nlink++;
+ drop_nlink(old_dir);
+ inc_nlink(new_dir);
}
old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime =
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);
+ clear_highpage(page);
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)
+int simple_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- 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);
+ struct page *page;
+ pgoff_t index;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page)
+ return -ENOMEM;
+
+ *pagep = page;
+
+ 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;
}
-int simple_commit_write(struct file *file, struct page *page,
- unsigned offset, unsigned to)
+/**
+ * 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.
+ */
+int simple_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
- loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ loff_t last_pos = pos + copied;
+
+ /* zero the stale part of the page if we did a short copy */
+ if (copied < len) {
+ unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+
+ zero_user(page, from + copied, len - copied);
+ }
+ 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 (pos > inode->i_size)
- i_size_write(inode, pos);
+ if (last_pos > inode->i_size)
+ i_size_write(inode, last_pos);
+
set_page_dirty(page);
- return 0;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return copied;
}
+/*
+ * 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.
+ */
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;
s->s_blocksize = PAGE_CACHE_SIZE;
s->s_blocksize_bits = PAGE_CACHE_SHIFT;
s->s_magic = magic;
- s->s_op = &s_ops;
+ s->s_op = &simple_super_operations;
s->s_time_gran = 1;
inode = new_inode(s);
if (!inode)
return -ENOMEM;
+ /*
+ * because the root inode is 1, the files array must not contain an
+ * entry at index 1
+ */
+ inode->i_ino = 1;
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;
for (i = 0; !files->name || files->name[0]; i++, files++) {
if (!files->name)
continue;
+
+ /* 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);
+
dentry = d_alloc_name(root, files->name);
if (!dentry)
goto out;
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;
mntput(mnt);
}
+/**
+ * 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.
+ **/
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;
+ size_t ret;
+
if (pos < 0)
return -EINVAL;
- if (pos >= available)
+ if (pos >= available || !count)
return 0;
if (count > available - pos)
count = available - pos;
- if (copy_to_user(to, from + pos, count))
+ ret = copy_to_user(to, from + pos, count);
+ if (ret == count)
return -EFAULT;
+ count -= ret;
*ppos = pos + count;
return count;
}
+/**
+ * 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;
+}
+
+/**
+ * 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.
+ **/
+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;
+}
+
/*
* 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.
*/
+
+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;
+}
+
char *simple_transaction_get(struct file *file, const char __user *buf, size_t size)
{
struct simple_transaction_argresp *ar;
/* Simple attribute files */
struct simple_attr {
- u64 (*get)(void *);
- void (*set)(void *, u64);
+ int (*get)(void *, u64 *);
+ int (*set)(void *, u64);
char get_buf[24]; /* enough to store a u64 and "\n\0" */
char set_buf[24];
void *data;
/* 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),
+ int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt)
{
struct simple_attr *attr;
attr->get = get;
attr->set = set;
- attr->data = inode->u.generic_ip;
+ attr->data = inode->i_private;
attr->fmt = fmt;
mutex_init(&attr->mutex);
return nonseekable_open(inode, file);
}
-int simple_attr_close(struct inode *inode, struct file *file)
+int simple_attr_release(struct inode *inode, struct file *file)
{
kfree(file->private_data);
return 0;
if (!attr->get)
return -EACCES;
- mutex_lock(&attr->mutex);
- if (*ppos) /* continued read */
+ ret = mutex_lock_interruptible(&attr->mutex);
+ if (ret)
+ return ret;
+
+ if (*ppos) { /* continued read */
size = strlen(attr->get_buf);
- else /* first read */
+ } else { /* first read */
+ u64 val;
+ ret = attr->get(attr->data, &val);
+ if (ret)
+ goto out;
+
size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
- attr->fmt,
- (unsigned long long)attr->get(attr->data));
+ attr->fmt, (unsigned long long)val);
+ }
ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
+out:
mutex_unlock(&attr->mutex);
return ret;
}
ssize_t ret;
attr = file->private_data;
-
if (!attr->set)
return -EACCES;
- mutex_lock(&attr->mutex);
+ ret = mutex_lock_interruptible(&attr->mutex);
+ if (ret)
+ return ret;
+
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);
+ ret = attr->set(attr->data, val);
+ if (ret == 0)
+ ret = len; /* on success, claim we got the whole input */
out:
mutex_unlock(&attr->mutex);
return ret;
}
+/**
+ * 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;
+ }
+
+ return d_obtain_alias(inode);
+}
+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;
+ }
+
+ return d_obtain_alias(inode);
+}
+EXPORT_SYMBOL_GPL(generic_fh_to_parent);
+
+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);
+
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_write_begin);
+EXPORT_SYMBOL(simple_write_end);
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_sync_file);
EXPORT_SYMBOL(simple_unlink);
EXPORT_SYMBOL(simple_read_from_buffer);
+EXPORT_SYMBOL(simple_write_to_buffer);
+EXPORT_SYMBOL(memory_read_from_buffer);
+EXPORT_SYMBOL(simple_transaction_set);
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_release);
EXPORT_SYMBOL_GPL(simple_attr_read);
EXPORT_SYMBOL_GPL(simple_attr_write);