* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
* Added options to /proc/mounts:
- * Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
+ * Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/writeback.h> /* for the emergency remount stuff */
#include <linux/idr.h>
#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/file.h>
#include <asm/uaccess.h>
+#include "internal.h"
-void get_filesystem(struct file_system_type *fs);
-void put_filesystem(struct file_system_type *fs);
-struct file_system_type *get_fs_type(const char *name);
-
LIST_HEAD(super_blocks);
DEFINE_SPINLOCK(sb_lock);
/**
* alloc_super - create new superblock
+ * @type: filesystem type superblock should belong to
*
* Allocates and initializes a new &struct super_block. alloc_super()
* returns a pointer new superblock or %NULL if allocation had failed.
*/
-static struct super_block *alloc_super(void)
+static struct super_block *alloc_super(struct file_system_type *type)
{
- struct super_block *s = kmalloc(sizeof(struct super_block), GFP_USER);
+ struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
static struct super_operations default_op;
if (s) {
- memset(s, 0, sizeof(struct super_block));
if (security_sb_alloc(s)) {
kfree(s);
s = NULL;
}
INIT_LIST_HEAD(&s->s_dirty);
INIT_LIST_HEAD(&s->s_io);
+ INIT_LIST_HEAD(&s->s_more_io);
INIT_LIST_HEAD(&s->s_files);
INIT_LIST_HEAD(&s->s_instances);
INIT_HLIST_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
+ INIT_LIST_HEAD(&s->s_dentry_lru);
init_rwsem(&s->s_umount);
mutex_init(&s->s_lock);
+ lockdep_set_class(&s->s_umount, &type->s_umount_key);
+ /*
+ * The locking rules for s_lock are up to the
+ * filesystem. For example ext3fs has different
+ * lock ordering than usbfs:
+ */
+ lockdep_set_class(&s->s_lock, &type->s_lock_key);
down_write(&s->s_umount);
s->s_count = S_BIAS;
atomic_set(&s->s_active, 1);
- sema_init(&s->s_vfs_rename_sem,1);
- sema_init(&s->s_dquot.dqio_sem, 1);
- sema_init(&s->s_dquot.dqonoff_sem, 1);
+ mutex_init(&s->s_vfs_rename_mutex);
+ mutex_init(&s->s_dquot.dqio_mutex);
+ mutex_init(&s->s_dquot.dqonoff_mutex);
init_rwsem(&s->s_dquot.dqptr_sem);
init_waitqueue_head(&s->s_wait_unfrozen);
s->s_maxbytes = MAX_NON_LFS;
static inline void destroy_super(struct super_block *s)
{
security_sb_free(s);
+ kfree(s->s_subtype);
+ kfree(s->s_options);
kfree(s);
}
* Drop a superblock's refcount. Returns non-zero if the superblock was
* destroyed. The caller must hold sb_lock.
*/
-int __put_super(struct super_block *sb)
+static int __put_super(struct super_block *sb)
{
int ret = 0;
if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
s->s_count -= S_BIAS-1;
spin_unlock(&sb_lock);
- DQUOT_OFF(s);
+ DQUOT_OFF(s, 0);
down_write(&s->s_umount);
fs->kill_sb(s);
put_filesystem(fs);
* success, 0 if we had failed (superblock contents was already dead or
* dying when grab_super() had been called).
*/
-static int grab_super(struct super_block *s)
+static int grab_super(struct super_block *s) __releases(sb_lock)
{
s->s_count++;
spin_unlock(&sb_lock);
return 0;
}
+/*
+ * Superblock locking. We really ought to get rid of these two.
+ */
+void lock_super(struct super_block * sb)
+{
+ get_fs_excl();
+ mutex_lock(&sb->s_lock);
+}
+
+void unlock_super(struct super_block * sb)
+{
+ put_fs_excl();
+ mutex_unlock(&sb->s_lock);
+}
+
+EXPORT_SYMBOL(lock_super);
+EXPORT_SYMBOL(unlock_super);
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock. Filesystem data as well as the underlying block
+ * device. Takes the superblock lock. Requires a second blkdev
+ * flush by the caller to complete the operation.
+ */
+void __fsync_super(struct super_block *sb)
+{
+ sync_inodes_sb(sb, 0);
+ DQUOT_SYNC(sb);
+ lock_super(sb);
+ if (sb->s_dirt && sb->s_op->write_super)
+ sb->s_op->write_super(sb);
+ unlock_super(sb);
+ if (sb->s_op->sync_fs)
+ sb->s_op->sync_fs(sb, 1);
+ sync_blockdev(sb->s_bdev);
+ sync_inodes_sb(sb, 1);
+}
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock. Filesystem data as well as the underlying block
+ * device. Takes the superblock lock.
+ */
+int fsync_super(struct super_block *sb)
+{
+ __fsync_super(sb);
+ return sync_blockdev(sb->s_bdev);
+}
+
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
* that need destruction out of superblock, call generic_shutdown_super()
* and release aforementioned objects. Note: dentries and inodes _are_
* taken care of and do not need specific handling.
+ *
+ * Upon calling this function, the filesystem may no longer alter or
+ * rearrange the set of dentries belonging to this super_block, nor may it
+ * change the attachments of dentries to inodes.
*/
void generic_shutdown_super(struct super_block *sb)
{
- struct dentry *root = sb->s_root;
- struct super_operations *sop = sb->s_op;
+ const struct super_operations *sop = sb->s_op;
- if (root) {
- sb->s_root = NULL;
- shrink_dcache_parent(root);
- shrink_dcache_anon(&sb->s_anon);
- dput(root);
+ if (sb->s_root) {
+ shrink_dcache_for_umount(sb);
fsync_super(sb);
lock_super(sb);
sb->s_flags &= ~MS_ACTIVE;
/* Forget any remaining inodes */
if (invalidate_inodes(sb)) {
- printk("VFS: Busy inodes after unmount. "
- "Self-destruct in 5 seconds. Have a nice day...\n");
+ printk("VFS: Busy inodes after unmount of %s. "
+ "Self-destruct in 5 seconds. Have a nice day...\n",
+ sb->s_id);
}
unlock_kernel();
void *data)
{
struct super_block *s = NULL;
- struct list_head *p;
+ struct super_block *old;
int err;
retry:
spin_lock(&sb_lock);
- if (test) list_for_each(p, &type->fs_supers) {
- struct super_block *old;
- old = list_entry(p, struct super_block, s_instances);
- if (!test(old, data))
- continue;
- if (!grab_super(old))
- goto retry;
- if (s)
- destroy_super(s);
- return old;
+ if (test) {
+ list_for_each_entry(old, &type->fs_supers, s_instances) {
+ if (!test(old, data))
+ continue;
+ if (!grab_super(old))
+ goto retry;
+ if (s)
+ destroy_super(s);
+ return old;
+ }
}
if (!s) {
spin_unlock(&sb_lock);
- s = alloc_super();
+ s = alloc_super(type);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
}
/*
- * Call the ->sync_fs super_op against all filesytems which are r/w and
+ * Call the ->sync_fs super_op against all filesystems which are r/w and
* which implement it.
*
* This operation is careful to avoid the livelock which could easily happen
* is used only here. We set it against all filesystems and then clear it as
* we sync them. So redirtied filesystems are skipped.
*
- * But if process A is currently running sync_filesytems and then process B
+ * But if process A is currently running sync_filesystems and then process B
* calls sync_filesystems as well, process B will set all the s_need_sync_fs
* flags again, which will cause process A to resync everything. Fix that with
* a local mutex.
void sync_filesystems(int wait)
{
struct super_block *sb;
- static DECLARE_MUTEX(mutex);
+ static DEFINE_MUTEX(mutex);
- down(&mutex); /* Could be down_interruptible */
+ mutex_lock(&mutex); /* Could be down_interruptible */
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (!sb->s_op->sync_fs)
goto restart;
}
spin_unlock(&sb_lock);
- up(&mutex);
+ mutex_unlock(&mutex);
}
/**
s = user_get_super(new_decode_dev(dev));
if (s == NULL)
goto out;
- err = vfs_statfs(s, &sbuf);
+ err = vfs_statfs(s->s_root, &sbuf);
drop_super(s);
if (err)
goto out;
}
/**
- * mark_files_ro
+ * mark_files_ro - mark all files read-only
* @sb: superblock in question
*
- * All files are marked read/only. We don't care about pending
- * delete files so this should be used in 'force' mode only
+ * All files are marked read-only. We don't care about pending
+ * delete files so this should be used in 'force' mode only.
*/
static void mark_files_ro(struct super_block *sb)
{
struct file *f;
+retry:
file_list_lock();
list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
- if (S_ISREG(f->f_dentry->d_inode->i_mode) && file_count(f))
- f->f_mode &= ~FMODE_WRITE;
+ struct vfsmount *mnt;
+ if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
+ continue;
+ if (!file_count(f))
+ continue;
+ if (!(f->f_mode & FMODE_WRITE))
+ continue;
+ f->f_mode &= ~FMODE_WRITE;
+ if (file_check_writeable(f) != 0)
+ continue;
+ file_release_write(f);
+ mnt = mntget(f->f_path.mnt);
+ file_list_unlock();
+ /*
+ * This can sleep, so we can't hold
+ * the file_list_lock() spinlock.
+ */
+ mnt_drop_write(mnt);
+ mntput(mnt);
+ goto retry;
}
file_list_unlock();
}
int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
{
int retval;
+ int remount_rw;
+#ifdef CONFIG_BLOCK
if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
return -EACCES;
+#endif
if (flags & MS_RDONLY)
acct_auto_close(sb);
shrink_dcache_sb(sb);
mark_files_ro(sb);
else if (!fs_may_remount_ro(sb))
return -EBUSY;
+ retval = DQUOT_OFF(sb, 1);
+ if (retval < 0 && retval != -ENOSYS)
+ return -EBUSY;
}
+ remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY);
if (sb->s_op->remount_fs) {
lock_super(sb);
return retval;
}
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
+ if (remount_rw)
+ DQUOT_ON_REMOUNT(sb);
return 0;
}
* filesystems which don't use real block-devices. -- jrs
*/
-static struct idr unnamed_dev_idr;
+static DEFINE_IDA(unnamed_dev_ida);
static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
int set_anon_super(struct super_block *s, void *data)
int error;
retry:
- if (idr_pre_get(&unnamed_dev_idr, GFP_ATOMIC) == 0)
+ if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0)
return -ENOMEM;
spin_lock(&unnamed_dev_lock);
- error = idr_get_new(&unnamed_dev_idr, NULL, &dev);
+ error = ida_get_new(&unnamed_dev_ida, &dev);
spin_unlock(&unnamed_dev_lock);
if (error == -EAGAIN)
/* We raced and lost with another CPU. */
if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) {
spin_lock(&unnamed_dev_lock);
- idr_remove(&unnamed_dev_idr, dev);
+ ida_remove(&unnamed_dev_ida, dev);
spin_unlock(&unnamed_dev_lock);
return -EMFILE;
}
generic_shutdown_super(sb);
spin_lock(&unnamed_dev_lock);
- idr_remove(&unnamed_dev_idr, slot);
+ ida_remove(&unnamed_dev_ida, slot);
spin_unlock(&unnamed_dev_lock);
}
EXPORT_SYMBOL(kill_anon_super);
-void __init unnamed_dev_init(void)
-{
- idr_init(&unnamed_dev_idr);
-}
-
void kill_litter_super(struct super_block *sb)
{
if (sb->s_root)
EXPORT_SYMBOL(kill_litter_super);
+#ifdef CONFIG_BLOCK
static int set_bdev_super(struct super_block *s, void *data)
{
s->s_bdev = data;
return (void *)s->s_bdev == data;
}
-struct super_block *get_sb_bdev(struct file_system_type *fs_type,
+int get_sb_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
- int (*fill_super)(struct super_block *, void *, int))
+ int (*fill_super)(struct super_block *, void *, int),
+ struct vfsmount *mnt)
{
struct block_device *bdev;
struct super_block *s;
+ fmode_t mode = FMODE_READ;
int error = 0;
- bdev = open_bdev_excl(dev_name, flags, fs_type);
+ if (!(flags & MS_RDONLY))
+ mode |= FMODE_WRITE;
+
+ bdev = open_bdev_exclusive(dev_name, mode, fs_type);
if (IS_ERR(bdev))
- return (struct super_block *)bdev;
+ return PTR_ERR(bdev);
/*
* once the super is inserted into the list by sget, s_umount
s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
up(&bdev->bd_mount_sem);
if (IS_ERR(s))
- goto out;
+ goto error_s;
if (s->s_root) {
if ((flags ^ s->s_flags) & MS_RDONLY) {
up_write(&s->s_umount);
deactivate_super(s);
- s = ERR_PTR(-EBUSY);
+ error = -EBUSY;
+ goto error_bdev;
}
- goto out;
+
+ close_bdev_exclusive(bdev, mode);
} else {
char b[BDEVNAME_SIZE];
s->s_flags = flags;
+ s->s_mode = mode;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(bdev));
- error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0);
+ error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
up_write(&s->s_umount);
deactivate_super(s);
- s = ERR_PTR(error);
- } else
- s->s_flags |= MS_ACTIVE;
+ goto error;
+ }
+
+ s->s_flags |= MS_ACTIVE;
}
- return s;
+ return simple_set_mnt(mnt, s);
-out:
- close_bdev_excl(bdev);
- return s;
+error_s:
+ error = PTR_ERR(s);
+error_bdev:
+ close_bdev_exclusive(bdev, mode);
+error:
+ return error;
}
EXPORT_SYMBOL(get_sb_bdev);
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
+ fmode_t mode = sb->s_mode;
generic_shutdown_super(sb);
sync_blockdev(bdev);
- close_bdev_excl(bdev);
+ close_bdev_exclusive(bdev, mode);
}
EXPORT_SYMBOL(kill_block_super);
+#endif
-struct super_block *get_sb_nodev(struct file_system_type *fs_type,
+int get_sb_nodev(struct file_system_type *fs_type,
int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int))
+ int (*fill_super)(struct super_block *, void *, int),
+ struct vfsmount *mnt)
{
int error;
struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
if (IS_ERR(s))
- return s;
+ return PTR_ERR(s);
s->s_flags = flags;
- error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0);
+ error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
up_write(&s->s_umount);
deactivate_super(s);
- return ERR_PTR(error);
+ return error;
}
s->s_flags |= MS_ACTIVE;
- return s;
+ return simple_set_mnt(mnt, s);
}
EXPORT_SYMBOL(get_sb_nodev);
return 1;
}
-struct super_block *get_sb_single(struct file_system_type *fs_type,
+int get_sb_single(struct file_system_type *fs_type,
int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int))
+ int (*fill_super)(struct super_block *, void *, int),
+ struct vfsmount *mnt)
{
struct super_block *s;
int error;
s = sget(fs_type, compare_single, set_anon_super, NULL);
if (IS_ERR(s))
- return s;
+ return PTR_ERR(s);
if (!s->s_root) {
s->s_flags = flags;
- error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0);
+ error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
up_write(&s->s_umount);
deactivate_super(s);
- return ERR_PTR(error);
+ return error;
}
s->s_flags |= MS_ACTIVE;
}
do_remount_sb(s, flags, data, 0);
- return s;
+ return simple_set_mnt(mnt, s);
}
EXPORT_SYMBOL(get_sb_single);
struct vfsmount *
-do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
{
- struct file_system_type *type = get_fs_type(fstype);
- struct super_block *sb = ERR_PTR(-ENOMEM);
struct vfsmount *mnt;
- int error;
char *secdata = NULL;
+ int error;
if (!type)
return ERR_PTR(-ENODEV);
+ error = -ENOMEM;
mnt = alloc_vfsmnt(name);
if (!mnt)
goto out;
- if (data) {
+ if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
secdata = alloc_secdata();
- if (!secdata) {
- sb = ERR_PTR(-ENOMEM);
+ if (!secdata)
goto out_mnt;
- }
- error = security_sb_copy_data(type, data, secdata);
- if (error) {
- sb = ERR_PTR(error);
+ error = security_sb_copy_data(data, secdata);
+ if (error)
goto out_free_secdata;
- }
}
- sb = type->get_sb(type, flags, name, data);
- if (IS_ERR(sb))
+ error = type->get_sb(type, flags, name, data, mnt);
+ if (error < 0)
goto out_free_secdata;
- error = security_sb_kern_mount(sb, secdata);
+ BUG_ON(!mnt->mnt_sb);
+
+ error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata);
if (error)
goto out_sb;
- mnt->mnt_sb = sb;
- mnt->mnt_root = dget(sb->s_root);
- mnt->mnt_mountpoint = sb->s_root;
+
+ mnt->mnt_mountpoint = mnt->mnt_root;
mnt->mnt_parent = mnt;
- up_write(&sb->s_umount);
+ up_write(&mnt->mnt_sb->s_umount);
free_secdata(secdata);
- put_filesystem(type);
return mnt;
out_sb:
- up_write(&sb->s_umount);
- deactivate_super(sb);
- sb = ERR_PTR(error);
+ dput(mnt->mnt_root);
+ up_write(&mnt->mnt_sb->s_umount);
+ deactivate_super(mnt->mnt_sb);
out_free_secdata:
free_secdata(secdata);
out_mnt:
free_vfsmnt(mnt);
out:
- put_filesystem(type);
- return (struct vfsmount *)sb;
+ return ERR_PTR(error);
+}
+
+EXPORT_SYMBOL_GPL(vfs_kern_mount);
+
+static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
+{
+ int err;
+ const char *subtype = strchr(fstype, '.');
+ if (subtype) {
+ subtype++;
+ err = -EINVAL;
+ if (!subtype[0])
+ goto err;
+ } else
+ subtype = "";
+
+ mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
+ err = -ENOMEM;
+ if (!mnt->mnt_sb->s_subtype)
+ goto err;
+ return mnt;
+
+ err:
+ mntput(mnt);
+ return ERR_PTR(err);
}
+struct vfsmount *
+do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+{
+ struct file_system_type *type = get_fs_type(fstype);
+ struct vfsmount *mnt;
+ if (!type)
+ return ERR_PTR(-ENODEV);
+ mnt = vfs_kern_mount(type, flags, name, data);
+ if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+ !mnt->mnt_sb->s_subtype)
+ mnt = fs_set_subtype(mnt, fstype);
+ put_filesystem(type);
+ return mnt;
+}
EXPORT_SYMBOL_GPL(do_kern_mount);
-struct vfsmount *kern_mount(struct file_system_type *type)
+struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
{
- return do_kern_mount(type->name, 0, type->name, NULL);
+ return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
}
-EXPORT_SYMBOL(kern_mount);
+EXPORT_SYMBOL_GPL(kern_mount_data);