static struct dentry *lookup_whiteout(struct dentry *dentry)
{
char *whname;
int bindex = -1, bstart = -1, bend = -1;
struct dentry *parent, *hidden_parent, *wh_dentry;
whname = alloc_whname(dentry->d_name.name, dentry->d_name.len);
if (IS_ERR(whname))
return (void *)whname;
parent = dget_parent(dentry);
unionfs_lock_dentry(parent);
bstart = dbstart(parent);
bend = dbend(parent);
wh_dentry = ERR_PTR(-ENOENT);
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_parent = unionfs_lower_dentry_idx(parent, bindex);
if (!hidden_parent)
continue;
wh_dentry = lookup_one_len(whname, hidden_parent,
dentry->d_name.len + UNIONFS_WHLEN);
if (IS_ERR(wh_dentry))
continue;
if (wh_dentry->d_inode)
break;
dput(wh_dentry);
wh_dentry = ERR_PTR(-ENOENT);
}
unionfs_unlock_dentry(parent);
dput(parent);
kfree(whname);
return wh_dentry;
}
static ssize_t unionfs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
int err = 0;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_write(lower_file, buf, count, ppos);
/* update our inode times+sizes upon a successful lower write */
if (err >= 0) {
fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
UNIONFS_F(file)->wrote_to_file = true; /* for delayed copyup */
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* BKL held by caller.
* dentry->d_inode->i_mutex locked
*/
ssize_t unionfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct dentry *lower_dentry = NULL;
struct dentry *parent;
int err = -EOPNOTSUPP;
char *encoded_list = NULL;
bool valid;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
lower_dentry = unionfs_lower_dentry(dentry);
encoded_list = list;
err = vfs_listxattr(lower_dentry, encoded_list, size);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static ssize_t unionfs_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
int err;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_read(lower_file, buf, count, ppos);
/* update our inode atime upon a successful lower read */
if (err >= 0) {
fsstack_copy_attr_atime(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static ssize_t unionfs_splice_write(struct pipe_inode_info *pipe,
struct file *file, loff_t *ppos,
size_t len, unsigned int flags)
{
ssize_t err = 0;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_splice_from(pipe, lower_file, ppos, len, flags);
/* update our inode times+sizes upon a successful lower write */
if (err >= 0) {
fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* BKL held by caller.
* dentry->d_inode->i_mutex locked
*/
int unionfs_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct dentry *lower_dentry = NULL;
struct dentry *parent;
int err = -EOPNOTSUPP;
bool valid;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
lower_dentry = unionfs_lower_dentry(dentry);
err = vfs_setxattr(lower_dentry, (char *) name, (void *) value,
size, flags);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_readlink(struct dentry *dentry, char __user *buf,
int bufsiz)
{
int err;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false, 0))) {
err = -ESTALE;
goto out;
}
err = __unionfs_readlink(dentry, buf, bufsiz);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/* this @nd *IS* still used */
static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd,
void *cookie)
{
struct dentry *parent;
char *buf;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false)))
printk(KERN_ERR
"unionfs: put_link failed to revalidate dentry\n");
unionfs_check_dentry(dentry);
#if 0
/* XXX: can't run this check b/c this fxn can receive a poisoned 'nd' PTR */
unionfs_check_nd(nd);
#endif
buf = nd_get_link(nd);
if (!IS_ERR(buf))
kfree(buf);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
}
static int unionfs_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool want_excl)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
int valid = 0;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE; /* same as what real_lookup does */
goto out;
}
lower_dentry = find_writeable_branch(dir, dentry);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
lower_parent_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_parent_dentry)) {
err = PTR_ERR(lower_parent_dentry);
goto out_unlock;
}
err = vfs_create(lower_parent_dentry->d_inode, lower_dentry, mode,
want_excl);
if (!err) {
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update no. of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
}
out_unlock:
unlock_dir(lower_parent_dentry);
out:
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
int unionfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
int bindex, bstart, bend;
struct file *lower_file;
struct dentry *lower_dentry;
struct dentry *parent;
struct inode *lower_inode, *inode;
int err = -EINVAL;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
unionfs_check_file(file);
bstart = fbstart(file);
bend = fbend(file);
if (bstart < 0 || bend < 0)
goto out;
inode = dentry->d_inode;
if (unlikely(!inode)) {
printk(KERN_ERR
"unionfs: null lower inode in unionfs_fsync\n");
goto out;
}
for (bindex = bstart; bindex <= bend; bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (!lower_inode || !lower_inode->i_fop->fsync)
continue;
lower_file = unionfs_lower_file_idx(file, bindex);
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
mutex_lock(&lower_inode->i_mutex);
err = lower_inode->i_fop->fsync(lower_file,
lower_dentry,
datasync);
if (!err && bindex == bstart)
fsstack_copy_attr_times(inode, lower_inode);
mutex_unlock(&lower_inode->i_mutex);
if (err)
goto out;
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_d_revalidate_wrap(struct dentry *dentry,
struct nameidata *nd)
{
int err;
unionfs_lock_dentry(dentry);
err = unionfs_d_revalidate(dentry, nd);
unionfs_unlock_dentry(dentry);
return err;
}
int unionfs_unlink(struct inode *dir, struct dentry *dentry)
{
int err = 0;
unionfs_lock_dentry(dentry);
err = unionfs_unlink_whiteout(dir, dentry);
/* call d_drop so the system "forgets" about us */
if (!err)
d_drop(dentry);
unionfs_unlock_dentry(dentry);
return err;
}
static void *unionfs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
char *buf;
int len = PAGE_SIZE, err;
mm_segment_t old_fs;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* This is freed by the put_link method assuming a successful call. */
buf = kmalloc(len, GFP_KERNEL);
if (unlikely(!buf)) {
err = -ENOMEM;
goto out;
}
/* read the symlink, and then we will follow it */
old_fs = get_fs();
set_fs(KERNEL_DS);
err = __unionfs_readlink(dentry, buf, len);
set_fs(old_fs);
if (err < 0) {
kfree(buf);
buf = NULL;
goto out;
}
buf[err] = 0;
nd_set_link(nd, buf);
err = 0;
out:
if (err >= 0) {
unionfs_check_nd(nd);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return ERR_PTR(err);
}
static void unionfs_d_release(struct dentry *dentry)
{
int bindex, bstart, bend;
/* There is no reason to lock the dentry, because we have the only
* reference, but the printing functions verify that we have a lock
* on the dentry before calling dbstart, etc.
*/
unionfs_lock_dentry(dentry);
/* this could be a negative dentry, so check first */
if (!UNIONFS_D(dentry)) {
printk(KERN_DEBUG "dentry without private data: %.*s",
dentry->d_name.len, dentry->d_name.name);
goto out;
} else if (dbstart(dentry) < 0) {
/* this is due to a failed lookup */
printk(KERN_DEBUG "dentry without hidden dentries : %.*s",
dentry->d_name.len, dentry->d_name.name);
goto out_free;
}
/* Release all the hidden dentries */
bstart = dbstart(dentry);
bend = dbend(dentry);
for (bindex = bstart; bindex <= bend; bindex++) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
mntput(unionfs_lower_mnt_idx(dentry, bindex));
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
}
/* free private data (unionfs_dentry_info) here */
kfree(UNIONFS_D(dentry)->lower_paths);
UNIONFS_D(dentry)->lower_paths = NULL;
out_free:
/* No need to unlock it, because it is disappeared. */
free_dentry_private_data(UNIONFS_D(dentry));
dentry->d_fsdata = NULL; /* just to be safe */
out:
return;
}
int unionfs_rmdir(struct inode *dir, struct dentry *dentry)
{
int err = 0;
struct unionfs_dir_state *namelist = NULL;
unionfs_lock_dentry(dentry);
/* check if this unionfs directory is empty or not */
err = check_empty(dentry, &namelist);
if (err)
goto out;
err = unionfs_rmdir_first(dir, dentry, namelist);
/* create whiteout */
if (!err)
err = create_whiteout(dentry, dbstart(dentry));
else {
int new_err;
if (dbstart(dentry) == 0)
goto out;
/* exit if the error returned was NOT -EROFS */
if (!IS_COPYUP_ERR(err))
goto out;
new_err = create_whiteout(dentry, dbstart(dentry) - 1);
if (new_err != -EEXIST)
err = new_err;
}
out:
/* call d_drop so the system "forgets" about us */
if (!err)
d_drop(dentry);
if (namelist)
free_rdstate(namelist);
unionfs_unlock_dentry(dentry);
return err;
}
/* this @nd *IS* still used */
static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd,
void *cookie)
{
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false)))
printk(KERN_ERR
"unionfs: put_link failed to revalidate dentry\n");
unionfs_check_dentry(dentry);
unionfs_check_nd(nd);
kfree(nd_get_link(nd));
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
}
long unionfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
long err;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
/* check if asked for local commands */
switch (cmd) {
case UNIONFS_IOCTL_INCGEN:
/* Increment the superblock generation count */
pr_info("unionfs: incgen ioctl deprecated; "
"use \"-o remount,incgen\"\n");
err = -ENOSYS;
break;
case UNIONFS_IOCTL_QUERYFILE:
/* Return list of branches containing the given file */
err = unionfs_ioctl_queryfile(file, parent, cmd, arg);
break;
default:
/* pass the ioctl down */
err = do_ioctl(file, cmd, arg);
break;
}
out:
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
int unionfs_flush(struct file *file, fl_owner_t id)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex, bstart, bend;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent,
UNIONFS_F(file)->wrote_to_file);
if (unlikely(err))
goto out;
unionfs_check_file(file);
bstart = fbstart(file);
bend = fbend(file);
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (lower_file && lower_file->f_op &&
lower_file->f_op->flush) {
err = lower_file->f_op->flush(lower_file, id);
if (err)
goto out;
}
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
dev_t dev)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *wh_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
char *name = NULL;
int valid = 0;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
/*
* It's only a bug if this dentry was not negative and couldn't be
* revalidated (shouldn't happen).
*/
BUG_ON(!valid && dentry->d_inode);
lower_dentry = find_writeable_branch(dir, dentry);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
lower_parent_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_parent_dentry)) {
err = PTR_ERR(lower_parent_dentry);
goto out_unlock;
}
err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev);
if (!err) {
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update no. of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
}
out_unlock:
unlock_dir(lower_parent_dentry);
out:
dput(wh_dentry);
kfree(name);
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
int bindex = 0, bstart;
char *name = NULL;
int valid;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE; /* same as what real_lookup does */
goto out;
}
bstart = dbstart(dentry);
lower_dentry = unionfs_lower_dentry(dentry);
/* check for a whiteout in new dentry branch, and delete it */
err = check_unlink_whiteout(dentry, lower_dentry, bstart);
if (err > 0) /* whiteout found and removed successfully */
err = 0;
if (err) {
/* exit if the error returned was NOT -EROFS */
if (!IS_COPYUP_ERR(err))
goto out;
bstart--;
}
/* check if copyup's needed, and mkdir */
for (bindex = bstart; bindex >= 0; bindex--) {
int i;
int bend = dbend(dentry);
if (is_robranch_super(dentry->d_sb, bindex))
continue;
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (!lower_dentry) {
lower_dentry = create_parents(dir, dentry,
dentry->d_name.name,
bindex);
if (!lower_dentry || IS_ERR(lower_dentry)) {
printk(KERN_ERR "unionfs: lower dentry "
" NULL for bindex = %d\n", bindex);
continue;
}
}
lower_parent_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_parent_dentry)) {
err = PTR_ERR(lower_parent_dentry);
goto out;
}
err = vfs_mkdir(lower_parent_dentry->d_inode, lower_dentry,
mode);
unlock_dir(lower_parent_dentry);
/* did the mkdir succeed? */
if (err)
break;
for (i = bindex + 1; i <= bend; i++) {
/* XXX: use path_put_lowers? */
if (unionfs_lower_dentry_idx(dentry, i)) {
dput(unionfs_lower_dentry_idx(dentry, i));
unionfs_set_lower_dentry_idx(dentry, i, NULL);
}
}
dbend(dentry) = bindex;
/*
* Only INTERPOSE_LOOKUP can return a value other than 0 on
* err.
*/
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update number of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
err = make_dir_opaque(dentry, dbstart(dentry));
if (err) {
printk(KERN_ERR "unionfs: mkdir: error creating "
".wh.__dir_opaque: %d\n", err);
goto out;
}
/* we are done! */
break;
}
out:
if (!dentry->d_inode)
d_drop(dentry);
kfree(name);
if (!err) {
unionfs_copy_attr_times(dentry->d_inode);
unionfs_postcopyup_setmnt(dentry);
}
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* The locking rules in unionfs_rename are complex. We could use a simpler
* superblock-level name-space lock for renames and copy-ups.
*/
int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
int err = 0;
struct dentry *wh_dentry;
struct dentry *old_parent, *new_parent;
int valid = true;
unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD);
old_parent = dget_parent(old_dentry);
new_parent = dget_parent(new_dentry);
/* un/lock parent dentries only if they differ from old/new_dentry */
if (old_parent != old_dentry &&
old_parent != new_dentry)
unionfs_lock_dentry(old_parent, UNIONFS_DMUTEX_REVAL_PARENT);
if (new_parent != old_dentry &&
new_parent != new_dentry &&
new_parent != old_parent)
unionfs_lock_dentry(new_parent, UNIONFS_DMUTEX_REVAL_CHILD);
unionfs_double_lock_dentry(old_dentry, new_dentry);
valid = __unionfs_d_revalidate(old_dentry, old_parent, false);
if (!valid) {
err = -ESTALE;
goto out;
}
if (!d_deleted(new_dentry) && new_dentry->d_inode) {
valid = __unionfs_d_revalidate(new_dentry, new_parent, false);
if (!valid) {
err = -ESTALE;
goto out;
}
}
if (!S_ISDIR(old_dentry->d_inode->i_mode))
err = unionfs_partial_lookup(old_dentry, old_parent);
else
err = may_rename_dir(old_dentry, old_parent);
if (err)
goto out;
err = unionfs_partial_lookup(new_dentry, new_parent);
if (err)
goto out;
/*
* if new_dentry is already lower because of whiteout,
* simply override it even if the whited-out dir is not empty.
*/
wh_dentry = find_first_whiteout(new_dentry);
if (!IS_ERR(wh_dentry)) {
dput(wh_dentry);
} else if (new_dentry->d_inode) {
if (S_ISDIR(old_dentry->d_inode->i_mode) !=
S_ISDIR(new_dentry->d_inode->i_mode)) {
err = S_ISDIR(old_dentry->d_inode->i_mode) ?
-ENOTDIR : -EISDIR;
goto out;
}
if (S_ISDIR(new_dentry->d_inode->i_mode)) {
struct unionfs_dir_state *namelist = NULL;
/* check if this unionfs directory is empty or not */
err = check_empty(new_dentry, new_parent, &namelist);
if (err)
goto out;
if (!is_robranch(new_dentry))
err = delete_whiteouts(new_dentry,
dbstart(new_dentry),
namelist);
free_rdstate(namelist);
if (err)
goto out;
}
}
err = do_unionfs_rename(old_dir, old_dentry, old_parent,
new_dir, new_dentry, new_parent);
if (err)
goto out;
/*
* force re-lookup since the dir on ro branch is not renamed, and
* lower dentries still indicate the un-renamed ones.
*/
if (S_ISDIR(old_dentry->d_inode->i_mode))
atomic_dec(&UNIONFS_D(old_dentry)->generation);
else
unionfs_postcopyup_release(old_dentry);
if (new_dentry->d_inode && !S_ISDIR(new_dentry->d_inode->i_mode)) {
unionfs_postcopyup_release(new_dentry);
unionfs_postcopyup_setmnt(new_dentry);
if (!unionfs_lower_inode(new_dentry->d_inode)) {
/*
* If we get here, it means that no copyup was
* needed, and that a file by the old name already
* existing on the destination branch; that file got
* renamed earlier in this function, so all we need
* to do here is set the lower inode.
*/
struct inode *inode;
inode = unionfs_lower_inode(old_dentry->d_inode);
igrab(inode);
unionfs_set_lower_inode_idx(new_dentry->d_inode,
dbstart(new_dentry),
inode);
}
}
/* if all of this renaming succeeded, update our times */
unionfs_copy_attr_times(old_dentry->d_inode);
unionfs_copy_attr_times(new_dentry->d_inode);
unionfs_check_inode(old_dir);
unionfs_check_inode(new_dir);
unionfs_check_dentry(old_dentry);
unionfs_check_dentry(new_dentry);
out:
if (err) /* clear the new_dentry stuff created */
d_drop(new_dentry);
unionfs_double_unlock_dentry(old_dentry, new_dentry);
if (new_parent != old_dentry &&
new_parent != new_dentry &&
new_parent != old_parent)
unionfs_unlock_dentry(new_parent);
if (old_parent != old_dentry &&
old_parent != new_dentry)
unionfs_unlock_dentry(old_parent);
dput(new_parent);
dput(old_parent);
unionfs_read_unlock(old_dentry->d_sb);
return err;
}
static int unionfs_mmap(struct file *file, struct vm_area_struct *vma)
{
int err = 0;
bool willwrite;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
struct vm_operations_struct *saved_vm_ops = NULL;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* This might be deferred to mmap's writepage */
willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags);
err = unionfs_file_revalidate(file, parent, willwrite);
if (unlikely(err))
goto out;
unionfs_check_file(file);
/*
* File systems which do not implement ->writepage may use
* generic_file_readonly_mmap as their ->mmap op. If you call
* generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL.
* But we cannot call the lower ->mmap op, so we can't tell that
* writeable mappings won't work. Therefore, our only choice is to
* check if the lower file system supports the ->writepage, and if
* not, return EINVAL (the same error that
* generic_file_readonly_mmap returns in that case).
*/
lower_file = unionfs_lower_file(file);
if (willwrite && !lower_file->f_mapping->a_ops->writepage) {
err = -EINVAL;
printk(KERN_ERR "unionfs: branch %d file system does not "
"support writeable mmap\n", fbstart(file));
goto out;
}
/*
* find and save lower vm_ops.
*
* XXX: the VFS should have a cleaner way of finding the lower vm_ops
*/
if (!UNIONFS_F(file)->lower_vm_ops) {
err = lower_file->f_op->mmap(lower_file, vma);
if (err) {
printk(KERN_ERR "unionfs: lower mmap failed %d\n", err);
goto out;
}
saved_vm_ops = vma->vm_ops;
err = do_munmap(current->mm, vma->vm_start,
vma->vm_end - vma->vm_start);
if (err) {
printk(KERN_ERR "unionfs: do_munmap failed %d\n", err);
goto out;
}
}
file->f_mapping->a_ops = &unionfs_dummy_aops;
err = generic_file_mmap(file, vma);
file->f_mapping->a_ops = &unionfs_aops;
if (err) {
printk(KERN_ERR "unionfs: generic_file_mmap failed %d\n", err);
goto out;
}
vma->vm_ops = &unionfs_vm_ops;
if (!UNIONFS_F(file)->lower_vm_ops)
UNIONFS_F(file)->lower_vm_ops = saved_vm_ops;
out:
if (!err) {
/* copyup could cause parent dir times to change */
unionfs_copy_attr_times(parent->d_inode);
unionfs_check_file(file);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* Don't grab the superblock read-lock in unionfs_permission, which prevents
* a deadlock with the branch-management "add branch" code (which grabbed
* the write lock). It is safe to not grab the read lock here, because even
* with branch management taking place, there is no chance that
* unionfs_permission, or anything it calls, will use stale branch
* information.
*/
static int unionfs_permission(struct inode *inode, int mask)
{
struct inode *lower_inode = NULL;
int err = 0;
int bindex, bstart, bend;
const int is_file = !S_ISDIR(inode->i_mode);
const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ);
struct inode *inode_grabbed = igrab(inode);
struct dentry *dentry = d_find_alias(inode);
if (dentry)
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (!UNIONFS_I(inode)->lower_inodes) {
if (is_file) /* dirs can be unlinked but chdir'ed to */
err = -ESTALE; /* force revalidate */
goto out;
}
bstart = ibstart(inode);
bend = ibend(inode);
if (unlikely(bstart < 0 || bend < 0)) {
/*
* With branch-management, we can get a stale inode here.
* If so, we return ESTALE back to link_path_walk, which
* would discard the dcache entry and re-lookup the
* dentry+inode. This should be equivalent to issuing
* __unionfs_d_revalidate_chain on nd.dentry here.
*/
if (is_file) /* dirs can be unlinked but chdir'ed to */
err = -ESTALE; /* force revalidate */
goto out;
}
for (bindex = bstart; bindex <= bend; bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (!lower_inode)
continue;
/*
* check the condition for D-F-D underlying files/directories,
* we don't have to check for files, if we are checking for
* directories.
*/
if (!is_file && !S_ISDIR(lower_inode->i_mode))
continue;
/*
* We check basic permissions, but we ignore any conditions
* such as readonly file systems or branches marked as
* readonly, because those conditions should lead to a
* copyup taking place later on. However, if user never had
* access to the file, then no copyup could ever take place.
*/
err = __inode_permission(lower_inode, mask);
if (err && err != -EACCES && err != EPERM && bindex > 0) {
umode_t mode = lower_inode->i_mode;
if ((is_robranch_super(inode->i_sb, bindex) ||
__is_rdonly(lower_inode)) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
err = 0;
if (IS_COPYUP_ERR(err))
err = 0;
}
/*
* NFS HACK: NFSv2/3 return EACCES on readonly-exported,
* locally readonly-mounted file systems, instead of EROFS
* like other file systems do. So we have no choice here
* but to intercept this and ignore it for NFS branches
* marked readonly. Specifically, we avoid using NFS's own
* "broken" ->permission method, and rely on
* generic_permission() to do basic checking for us.
*/
if (err && err == -EACCES &&
is_robranch_super(inode->i_sb, bindex) &&
lower_inode->i_sb->s_magic == NFS_SUPER_MAGIC)
err = generic_permission(lower_inode, mask, NULL);
/*
* The permissions are an intersection of the overall directory
* permissions, so we fail if one fails.
*/
if (err)
goto out;
/* only the leftmost file matters. */
if (is_file || write_mask) {
if (is_file && write_mask) {
err = get_write_access(lower_inode);
if (!err)
put_write_access(lower_inode);
}
break;
}
}
/* sync times which may have changed (asynchronously) below */
unionfs_copy_attr_times(inode);
out:
unionfs_check_inode(inode);
if (dentry) {
unionfs_unlock_dentry(dentry);
dput(dentry);
}
iput(inode_grabbed);
return err;
}
/*
* This is not meant to be a generic repositioning function. If you do
* things that aren't supported, then we return EINVAL.
*
* What is allowed:
* (1) seeking to the same position that you are currently at
* This really has no effect, but returns where you are.
* (2) seeking to the beginning of the file
* This throws out all state, and lets you begin again.
*/
static loff_t unionfs_dir_llseek(struct file *file, loff_t offset, int origin)
{
struct unionfs_dir_state *rdstate;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
loff_t err;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
rdstate = UNIONFS_F(file)->rdstate;
/*
* we let users seek to their current position, but not anywhere
* else.
*/
if (!offset) {
switch (origin) {
case SEEK_SET:
if (rdstate) {
free_rdstate(rdstate);
UNIONFS_F(file)->rdstate = NULL;
}
init_rdstate(file);
err = 0;
break;
case SEEK_CUR:
err = file->f_pos;
break;
case SEEK_END:
/* Unsupported, because we would break everything. */
err = -EINVAL;
break;
}
} else {
switch (origin) {
case SEEK_SET:
if (rdstate) {
if (offset == rdstate2offset(rdstate))
err = offset;
else if (file->f_pos == DIREOF)
err = DIREOF;
else
err = -EINVAL;
} else {
struct inode *inode;
inode = dentry->d_inode;
rdstate = find_rdstate(inode, offset);
if (rdstate) {
UNIONFS_F(file)->rdstate = rdstate;
err = rdstate->offset;
} else {
err = -EINVAL;
}
}
break;
case SEEK_CUR:
case SEEK_END:
/* Unsupported, because we would break everything. */
err = -EINVAL;
break;
}
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_setattr(struct dentry *dentry, struct iattr *ia)
{
int err = 0;
struct dentry *lower_dentry;
struct dentry *parent;
struct inode *inode;
struct inode *lower_inode;
int bstart, bend, bindex;
loff_t size;
struct iattr lower_ia;
/* check if user has permission to change inode */
err = inode_change_ok(dentry->d_inode, ia);
if (err)
goto out_err;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false, 0))) {
err = -ESTALE;
goto out;
}
bstart = dbstart(dentry);
bend = dbend(dentry);
inode = dentry->d_inode;
/*
* mode change is for clearing setuid/setgid. Allow lower filesystem
* to reinterpret it in its own way.
*/
if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
ia->ia_valid &= ~ATTR_MODE;
lower_dentry = unionfs_lower_dentry(dentry);
if (!lower_dentry) { /* should never happen after above revalidate */
err = -EINVAL;
goto out;
}
/*
* Get the lower inode directly from lower dentry, in case ibstart
* is -1 (which happens when the file is open but unlinked.
*/
lower_inode = lower_dentry->d_inode;
/* check if user has permission to change lower inode */
err = inode_change_ok(lower_inode, ia);
if (err)
goto out;
/* copyup if the file is on a read only branch */
if (is_robranch_super(dentry->d_sb, bstart)
|| __is_rdonly(lower_inode)) {
/* check if we have a branch to copy up to */
if (bstart <= 0) {
err = -EACCES;
goto out;
}
if (ia->ia_valid & ATTR_SIZE)
size = ia->ia_size;
else
size = i_size_read(inode);
/* copyup to next available branch */
for (bindex = bstart - 1; bindex >= 0; bindex--) {
err = copyup_dentry(parent->d_inode,
dentry, bstart, bindex,
dentry->d_name.name,
dentry->d_name.len,
NULL, size);
if (!err)
break;
}
if (err)
goto out;
/* get updated lower_dentry/inode after copyup */
lower_dentry = unionfs_lower_dentry(dentry);
lower_inode = unionfs_lower_inode(inode);
/*
* check for whiteouts in writeable branch, and remove them
* if necessary.
*/
if (lower_dentry) {
err = check_unlink_whiteout(dentry, lower_dentry,
bindex);
if (err > 0) /* ignore if whiteout found and removed */
err = 0;
}
}
/*
* If shrinking, first truncate upper level to cancel writing dirty
* pages beyond the new eof; and also if its' maxbytes is more
* limiting (fail with -EFBIG before making any change to the lower
* level). There is no need to vmtruncate the upper level
* afterwards in the other cases: we fsstack_copy_inode_size from
* the lower level.
*/
if (ia->ia_valid & ATTR_SIZE) {
err = inode_newsize_ok(inode, ia->ia_size);
if (err)
goto out;
truncate_setsize(inode, ia->ia_size);
}
/* notify the (possibly copied-up) lower inode */
/*
* Note: we use lower_dentry->d_inode, because lower_inode may be
* unlinked (no inode->i_sb and i_ino==0. This happens if someone
* tries to open(), unlink(), then ftruncate() a file.
*/
/* prepare our own lower struct iattr (with our own lower file) */
memcpy(&lower_ia, ia, sizeof(lower_ia));
if (ia->ia_valid & ATTR_FILE) {
lower_ia.ia_file = unionfs_lower_file(ia->ia_file);
BUG_ON(!lower_ia.ia_file); // XXX?
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
err = notify_change(lower_dentry, &lower_ia);
mutex_unlock(&lower_dentry->d_inode->i_mutex);
if (err)
goto out;
/* get attributes from the first lower inode */
if (ibstart(inode) >= 0)
unionfs_copy_attr_all(inode, lower_inode);
/*
* unionfs_copy_attr_all will copy the lower times to our inode if
* the lower ones are newer (useful for cache coherency). However,
* ->setattr is the only place in which we may have to copy the
* lower inode times absolutely, to support utimes(2).
*/
if (ia->ia_valid & ATTR_MTIME_SET)
inode->i_mtime = lower_inode->i_mtime;
if (ia->ia_valid & ATTR_CTIME)
inode->i_ctime = lower_inode->i_ctime;
if (ia->ia_valid & ATTR_ATIME_SET)
inode->i_atime = lower_inode->i_atime;
fsstack_copy_inode_size(inode, lower_inode);
out:
if (!err)
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
out_err:
return err;
}
int unionfs_open(struct inode *inode, struct file *file)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex = 0, bstart = 0, bend = 0;
int size;
int valid = 0;
unionfs_read_lock(inode->i_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* don't open unhashed/deleted files */
if (d_deleted(dentry)) {
err = -ENOENT;
goto out_nofree;
}
/* XXX: should I change 'false' below to the 'willwrite' flag? */
valid = __unionfs_d_revalidate(dentry, parent, false);
if (unlikely(!valid)) {
err = -ESTALE;
goto out_nofree;
}
file->private_data =
kzalloc(sizeof(struct unionfs_file_info), GFP_KERNEL);
if (unlikely(!UNIONFS_F(file))) {
err = -ENOMEM;
goto out_nofree;
}
fbstart(file) = -1;
fbend(file) = -1;
atomic_set(&UNIONFS_F(file)->generation,
atomic_read(&UNIONFS_I(inode)->generation));
size = sizeof(struct file *) * sbmax(inode->i_sb);
UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL);
if (unlikely(!UNIONFS_F(file)->lower_files)) {
err = -ENOMEM;
goto out;
}
size = sizeof(int) * sbmax(inode->i_sb);
UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL);
if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) {
err = -ENOMEM;
goto out;
}
bstart = fbstart(file) = dbstart(dentry);
bend = fbend(file) = dbend(dentry);
/*
* open all directories and make the unionfs file struct point to
* these lower file structs
*/
if (S_ISDIR(inode->i_mode))
err = __open_dir(inode, file); /* open a dir */
else
err = __open_file(inode, file, parent); /* open a file */
/* freeing the allocated resources, and fput the opened files */
if (err) {
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (!lower_file)
continue;
branchput(dentry->d_sb, bindex);
/* fput calls dput for lower_dentry */
fput(lower_file);
}
}
out:
if (err) {
kfree(UNIONFS_F(file)->lower_files);
kfree(UNIONFS_F(file)->saved_branch_ids);
kfree(UNIONFS_F(file));
}
out_nofree:
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_copy_attr_times(inode);
unionfs_check_file(file);
unionfs_check_inode(inode);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(inode->i_sb);
return err;
}
/* This function replicates the directory structure upto given dentry
* in the bindex branch.
*/
static struct dentry *create_parents_named(struct inode *dir,
struct dentry *dentry,
const char *name, int bindex)
{
int err;
struct dentry *child_dentry;
struct dentry *parent_dentry;
struct dentry *hidden_parent_dentry = NULL;
struct dentry *hidden_dentry = NULL;
const char *childname;
unsigned int childnamelen;
int old_kmalloc_size;
int kmalloc_size;
int num_dentry;
int count;
int old_bstart;
int old_bend;
struct dentry **path = NULL;
struct dentry **tmp_path;
struct super_block *sb;
verify_locked(dentry);
/* There is no sense allocating any less than the minimum. */
kmalloc_size = malloc_sizes[0].cs_size;
num_dentry = kmalloc_size / sizeof(struct dentry *);
if ((err = is_robranch_super(dir->i_sb, bindex))) {
hidden_dentry = ERR_PTR(err);
goto out;
}
old_bstart = dbstart(dentry);
old_bend = dbend(dentry);
hidden_dentry = ERR_PTR(-ENOMEM);
path = kzalloc(kmalloc_size, GFP_KERNEL);
if (!path)
goto out;
/* assume the negative dentry of unionfs as the parent dentry */
parent_dentry = dentry;
count = 0;
/* This loop finds the first parent that exists in the given branch.
* We start building the directory structure from there. At the end
* of the loop, the following should hold:
* - child_dentry is the first nonexistent child
* - parent_dentry is the first existent parent
* - path[0] is the = deepest child
* - path[count] is the first child to create
*/
do {
child_dentry = parent_dentry;
/* find the parent directory dentry in unionfs */
parent_dentry = child_dentry->d_parent;
unionfs_lock_dentry(parent_dentry);
/* find out the hidden_parent_dentry in the given branch */
hidden_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
/* store the child dentry */
path[count++] = child_dentry;
/* grow path table */
if (count == num_dentry) {
old_kmalloc_size = kmalloc_size;
kmalloc_size *= 2;
num_dentry = kmalloc_size / sizeof(struct dentry *);
tmp_path = kzalloc(kmalloc_size, GFP_KERNEL);
if (!tmp_path) {
hidden_dentry = ERR_PTR(-ENOMEM);
goto out;
}
memcpy(tmp_path, path, old_kmalloc_size);
kfree(path);
path = tmp_path;
tmp_path = NULL;
}
} while (!hidden_parent_dentry);
count--;
sb = dentry->d_sb;
/* This is basically while(child_dentry != dentry). This loop is
* horrible to follow and should be replaced with cleaner code.
*/
while (1) {
/* get hidden parent dir in the current branch */
hidden_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
unionfs_unlock_dentry(parent_dentry);
/* init the values to lookup */
childname = child_dentry->d_name.name;
childnamelen = child_dentry->d_name.len;
if (child_dentry != dentry) {
/* lookup child in the underlying file system */
hidden_dentry =
lookup_one_len(childname, hidden_parent_dentry,
childnamelen);
if (IS_ERR(hidden_dentry))
goto out;
} else {
/* is the name a whiteout of the childname ?
* lookup the whiteout child in the underlying file system
*/
hidden_dentry =
lookup_one_len(name, hidden_parent_dentry,
strlen(name));
if (IS_ERR(hidden_dentry))
goto out;
/* Replace the current dentry (if any) with the new one. */
dput(unionfs_lower_dentry_idx(dentry, bindex));
unionfs_set_lower_dentry_idx(dentry, bindex, hidden_dentry);
__cleanup_dentry(dentry, bindex, old_bstart, old_bend);
break;
}
if (hidden_dentry->d_inode) {
/* since this already exists we dput to avoid
* multiple references on the same dentry
*/
dput(hidden_dentry);
} else {
struct sioq_args args;
/* its a negative dentry, create a new dir */
hidden_parent_dentry = lock_parent(hidden_dentry);
args.mkdir.parent = hidden_parent_dentry->d_inode;
args.mkdir.dentry = hidden_dentry;
args.mkdir.mode = child_dentry->d_inode->i_mode;
run_sioq(__unionfs_mkdir, &args);
err = args.err;
if (!err)
err = copyup_permissions(dir->i_sb,
child_dentry, hidden_dentry);
unlock_dir(hidden_parent_dentry);
if (err) {
dput(hidden_dentry);
hidden_dentry = ERR_PTR(err);
goto out;
}
}
__set_inode(child_dentry, hidden_dentry, bindex);
__set_dentry(child_dentry, hidden_dentry, bindex);
parent_dentry = child_dentry;
child_dentry = path[--count];
}
out:
kfree(path);
return hidden_dentry;
}
/*
* release all lower object references & free the file info structure
*
* No need to grab sb info's rwsem.
*/
int unionfs_file_release(struct inode *inode, struct file *file)
{
struct file *lower_file = NULL;
struct unionfs_file_info *fileinfo;
struct unionfs_inode_info *inodeinfo;
struct super_block *sb = inode->i_sb;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex, bstart, bend;
int fgen, err = 0;
/*
* Since mm/memory.c:might_fault() (under PROVE_LOCKING) was
* modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this
* has been causing false positives in file system stacking layers.
* In particular, our ->mmap is called after sys_mmap2 already holds
* mmap_sem, then we lock our own mutexes; but earlier, it's
* possible for lockdep to have locked our mutexes first, and then
* we call a lower ->readdir which could call might_fault. The
* different ordering of the locks is what lockdep complains about
* -- unnecessarily. Therefore, we have no choice but to tell
* lockdep to temporarily turn off lockdep here. Note: the comments
* inside might_sleep also suggest that it would have been
* nicer to only annotate paths that needs that might_lock_read.
*/
lockdep_off();
unionfs_read_lock(sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/*
* We try to revalidate, but the VFS ignores return return values
* from file->release, so we must always try to succeed here,
* including to do the kfree and dput below. So if revalidation
* failed, all we can do is print some message and keep going.
*/
err = unionfs_file_revalidate(file, parent,
UNIONFS_F(file)->wrote_to_file);
if (!err)
unionfs_check_file(file);
fileinfo = UNIONFS_F(file);
BUG_ON(file->f_path.dentry->d_inode != inode);
inodeinfo = UNIONFS_I(inode);
/* fput all the lower files */
fgen = atomic_read(&fileinfo->generation);
bstart = fbstart(file);
bend = fbend(file);
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (lower_file) {
unionfs_set_lower_file_idx(file, bindex, NULL);
fput(lower_file);
branchput(sb, bindex);
}
/* if there are no more refs to the dentry, dput it */
if (d_deleted(dentry)) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
}
}
kfree(fileinfo->lower_files);
kfree(fileinfo->saved_branch_ids);
if (fileinfo->rdstate) {
fileinfo->rdstate->access = jiffies;
spin_lock(&inodeinfo->rdlock);
inodeinfo->rdcount++;
list_add_tail(&fileinfo->rdstate->cache,
&inodeinfo->readdircache);
mark_inode_dirty(inode);
spin_unlock(&inodeinfo->rdlock);
fileinfo->rdstate = NULL;
}
kfree(fileinfo);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(sb);
lockdep_on();
return err;
}
static int unionfs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
struct inode *inode = NULL;
struct unionfs_getdents_callback buf;
struct unionfs_dir_state *uds;
int bend;
loff_t offset;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
inode = dentry->d_inode;
uds = UNIONFS_F(file)->rdstate;
if (!uds) {
if (file->f_pos == DIREOF) {
goto out;
} else if (file->f_pos > 0) {
uds = find_rdstate(inode, file->f_pos);
if (unlikely(!uds)) {
err = -ESTALE;
goto out;
}
UNIONFS_F(file)->rdstate = uds;
} else {
init_rdstate(file);
uds = UNIONFS_F(file)->rdstate;
}
}
bend = fbend(file);
while (uds->bindex <= bend) {
lower_file = unionfs_lower_file_idx(file, uds->bindex);
if (!lower_file) {
uds->bindex++;
uds->dirpos = 0;
continue;
}
/* prepare callback buffer */
buf.filldir_called = 0;
buf.filldir_error = 0;
buf.entries_written = 0;
buf.dirent = dirent;
buf.filldir = filldir;
buf.rdstate = uds;
buf.sb = inode->i_sb;
/* Read starting from where we last left off. */
offset = vfs_llseek(lower_file, uds->dirpos, SEEK_SET);
if (offset < 0) {
err = offset;
goto out;
}
err = vfs_readdir(lower_file, unionfs_filldir, &buf);
/* Save the position for when we continue. */
offset = vfs_llseek(lower_file, 0, SEEK_CUR);
if (offset < 0) {
err = offset;
goto out;
}
uds->dirpos = offset;
/* Copy the atime. */
fsstack_copy_attr_atime(inode,
lower_file->f_path.dentry->d_inode);
if (err < 0)
goto out;
if (buf.filldir_error)
break;
if (!buf.entries_written) {
uds->bindex++;
uds->dirpos = 0;
}
}
if (!buf.filldir_error && uds->bindex >= bend) {
/* Save the number of hash entries for next time. */
UNIONFS_I(inode)->hashsize = uds->hashentries;
free_rdstate(uds);
UNIONFS_F(file)->rdstate = NULL;
file->f_pos = DIREOF;
} else {
file->f_pos = rdstate2offset(uds);
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
struct dentry *unionfs_lookup_backend(struct dentry *dentry, struct nameidata *nd,
int lookupmode)
{
int err = 0;
struct dentry *hidden_dentry = NULL;
struct dentry *wh_hidden_dentry = NULL;
struct dentry *hidden_dir_dentry = NULL;
struct dentry *parent_dentry = NULL;
int bindex, bstart, bend, bopaque;
int dentry_count = 0; /* Number of positive dentries. */
int first_dentry_offset = -1;
struct dentry *first_hidden_dentry = NULL;
struct vfsmount *first_hidden_mnt = NULL;
int locked_parent = 0;
int locked_child = 0;
int opaque;
char *whname = NULL;
const char *name;
int namelen;
/* We should already have a lock on this dentry in the case of a
* partial lookup, or a revalidation. Otherwise it is returned from
* new_dentry_private_data already locked.
*/
if (lookupmode == INTERPOSE_PARTIAL || lookupmode == INTERPOSE_REVAL ||
lookupmode == INTERPOSE_REVAL_NEG)
verify_locked(dentry);
else {
BUG_ON(UNIONFS_D(dentry) != NULL);
locked_child = 1;
}
if (lookupmode != INTERPOSE_PARTIAL)
if ((err = new_dentry_private_data(dentry)))
goto out;
/* must initialize dentry operations */
dentry->d_op = &unionfs_dops;
parent_dentry = dget_parent(dentry);
/* We never partial lookup the root directory. */
if (parent_dentry != dentry) {
unionfs_lock_dentry(parent_dentry);
locked_parent = 1;
} else {
dput(parent_dentry);
parent_dentry = NULL;
goto out;
}
name = dentry->d_name.name;
namelen = dentry->d_name.len;
/* No dentries should get created for possible whiteout names. */
if (!is_validname(name)) {
err = -EPERM;
goto out_free;
}
/* Now start the actual lookup procedure. */
bstart = dbstart(parent_dentry);
bend = dbend(parent_dentry);
bopaque = dbopaque(parent_dentry);
BUG_ON(bstart < 0);
/* It would be ideal if we could convert partial lookups to only have
* to do this work when they really need to. It could probably improve
* performance quite a bit, and maybe simplify the rest of the code.
*/
if (lookupmode == INTERPOSE_PARTIAL) {
bstart++;
if ((bopaque != -1) && (bopaque < bend))
bend = bopaque;
}
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (lookupmode == INTERPOSE_PARTIAL && hidden_dentry)
continue;
BUG_ON(hidden_dentry != NULL);
hidden_dir_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
/* if the parent hidden dentry does not exist skip this */
if (!(hidden_dir_dentry && hidden_dir_dentry->d_inode))
continue;
/* also skip it if the parent isn't a directory. */
if (!S_ISDIR(hidden_dir_dentry->d_inode->i_mode))
continue;
/* Reuse the whiteout name because its value doesn't change. */
if (!whname) {
whname = alloc_whname(name, namelen);
if (IS_ERR(whname)) {
err = PTR_ERR(whname);
goto out_free;
}
}
/* check if whiteout exists in this branch: lookup .wh.foo */
wh_hidden_dentry = lookup_one_len(whname, hidden_dir_dentry,
namelen + UNIONFS_WHLEN);
if (IS_ERR(wh_hidden_dentry)) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = PTR_ERR(wh_hidden_dentry);
goto out_free;
}
if (wh_hidden_dentry->d_inode) {
/* We found a whiteout so lets give up. */
if (S_ISREG(wh_hidden_dentry->d_inode->i_mode)) {
set_dbend(dentry, bindex);
set_dbopaque(dentry, bindex);
dput(wh_hidden_dentry);
break;
}
err = -EIO;
printk(KERN_NOTICE "EIO: Invalid whiteout entry type"
" %d.\n", wh_hidden_dentry->d_inode->i_mode);
dput(wh_hidden_dentry);
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
goto out_free;
}
dput(wh_hidden_dentry);
wh_hidden_dentry = NULL;
/* Now do regular lookup; lookup foo */
nd->dentry = unionfs_lower_dentry_idx(dentry, bindex);
/* FIXME: fix following line for mount point crossing */
nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
hidden_dentry = lookup_one_len_nd(name, hidden_dir_dentry,
namelen, nd);
if (IS_ERR(hidden_dentry)) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = PTR_ERR(hidden_dentry);
goto out_free;
}
/* Store the first negative dentry specially, because if they
* are all negative we need this for future creates.
*/
if (!hidden_dentry->d_inode) {
if (!first_hidden_dentry && (dbstart(dentry) == -1)) {
first_hidden_dentry = hidden_dentry;
/* FIXME: following line needs to be changed
* to allow mountpoint crossing
*/
first_hidden_mnt = mntget(
unionfs_lower_mnt_idx(parent_dentry,
bindex));
first_dentry_offset = bindex;
} else
dput(hidden_dentry);
continue;
}
/* number of positive dentries */
dentry_count++;
/* store underlying dentry */
if (dbstart(dentry) == -1)
set_dbstart(dentry, bindex);
unionfs_set_lower_dentry_idx(dentry, bindex, hidden_dentry);
/* FIXME: the following line needs to get fixed to allow
* mountpoint crossing
*/
unionfs_set_lower_mnt_idx(dentry, bindex,
mntget(unionfs_lower_mnt_idx(parent_dentry, bindex)));
set_dbend(dentry, bindex);
/* update parent directory's atime with the bindex */
fsstack_copy_attr_atime(parent_dentry->d_inode,
hidden_dir_dentry->d_inode);
/* We terminate file lookups here. */
if (!S_ISDIR(hidden_dentry->d_inode->i_mode)) {
if (lookupmode == INTERPOSE_PARTIAL)
continue;
if (dentry_count == 1)
goto out_positive;
/* This can only happen with mixed D-*-F-* */
BUG_ON(!S_ISDIR(unionfs_lower_dentry(dentry)->d_inode->i_mode));
continue;
}
opaque = is_opaque_dir(dentry, bindex);
if (opaque < 0) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = opaque;
goto out_free;
} else if (opaque) {
set_dbend(dentry, bindex);
set_dbopaque(dentry, bindex);
break;
}
}
if (dentry_count)
goto out_positive;
else
goto out_negative;
out_negative:
if (lookupmode == INTERPOSE_PARTIAL)
goto out;
/* If we've only got negative dentries, then use the leftmost one. */
if (lookupmode == INTERPOSE_REVAL) {
if (dentry->d_inode)
UNIONFS_I(dentry->d_inode)->stale = 1;
goto out;
}
/* This should only happen if we found a whiteout. */
if (first_dentry_offset == -1) {
nd->dentry = dentry;
/* FIXME: fix following line for mount point crossing */
nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
first_hidden_dentry = lookup_one_len_nd(name, hidden_dir_dentry,
namelen, nd);
first_dentry_offset = bindex;
if (IS_ERR(first_hidden_dentry)) {
err = PTR_ERR(first_hidden_dentry);
goto out;
}
/* FIXME: the following line needs to be changed to allow
* mountpoint crossing
*/
first_hidden_mnt = mntget(unionfs_lower_mnt_idx(dentry, bindex));
}
unionfs_set_lower_dentry_idx(dentry, first_dentry_offset, first_hidden_dentry);
unionfs_set_lower_mnt_idx(dentry, first_dentry_offset, first_hidden_mnt);
set_dbstart(dentry, first_dentry_offset);
set_dbend(dentry, first_dentry_offset);
if (lookupmode == INTERPOSE_REVAL_NEG)
BUG_ON(dentry->d_inode != NULL);
else
d_add(dentry, NULL);
goto out;
/* This part of the code is for positive dentries. */
out_positive:
BUG_ON(dentry_count <= 0);
/* If we're holding onto the first negative dentry & corresponding
* vfsmount - throw it out.
*/
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
/* Partial lookups need to reinterpose, or throw away older negs. */
if (lookupmode == INTERPOSE_PARTIAL) {
if (dentry->d_inode) {
unionfs_reinterpose(dentry);
goto out;
}
/* This somehow turned positive, so it is as if we had a
* negative revalidation.
*/
lookupmode = INTERPOSE_REVAL_NEG;
update_bstart(dentry);
bstart = dbstart(dentry);
bend = dbend(dentry);
}
err = unionfs_interpose(dentry, dentry->d_sb, lookupmode);
if (err)
goto out_drop;
goto out;
out_drop:
d_drop(dentry);
out_free:
/* should dput all the underlying dentries on error condition */
bstart = dbstart(dentry);
if (bstart >= 0) {
bend = dbend(dentry);
for (bindex = bstart; bindex <= bend; bindex++) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
mntput(unionfs_lower_mnt_idx(dentry, bindex));
}
}
kfree(UNIONFS_D(dentry)->lower_paths);
UNIONFS_D(dentry)->lower_paths = NULL;
set_dbstart(dentry, -1);
set_dbend(dentry, -1);
out:
if (!err && UNIONFS_D(dentry)) {
BUG_ON(dbend(dentry) > UNIONFS_D(dentry)->bcount);
BUG_ON(dbend(dentry) > sbmax(dentry->d_sb));
BUG_ON(dbstart(dentry) < 0);
}
kfree(whname);
if (locked_parent)
unionfs_unlock_dentry(parent_dentry);
dput(parent_dentry);
if (locked_child)
unionfs_unlock_dentry(dentry);
return ERR_PTR(err);
}
