static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
{
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *newdentry;
int err;
inode_lock_nested(udir, I_MUTEX_PARENT);
newdentry = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
err = ovl_create_real(udir, newdentry, stat, link, hardlink, false);
if (err)
goto out_dput;
ovl_dentry_version_inc(dentry->d_parent);
ovl_dentry_update(dentry, newdentry);
ovl_copyattr(newdentry->d_inode, inode);
d_instantiate(dentry, inode);
newdentry = NULL;
out_dput:
dput(newdentry);
out_unlock:
inode_unlock(udir);
return err;
}
static int __maybe_unused
ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *realinode = ovl_inode_real(inode);
struct posix_acl *acl = NULL;
int err;
/* Check that everything is OK before copy-up */
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
}
err = -EOPNOTSUPP;
if (!IS_POSIXACL(d_inode(workdir)))
goto out_acl_release;
if (!realinode->i_op->set_acl)
goto out_acl_release;
if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) {
err = acl ? -EACCES : 0;
goto out_acl_release;
}
err = -EPERM;
if (!inode_owner_or_capable(inode))
goto out_acl_release;
posix_acl_release(acl);
/*
* Check if sgid bit needs to be cleared (actual setacl operation will
* be done with mounter's capabilities and so that won't do it for us).
*/
if (unlikely(inode->i_mode & S_ISGID) &&
handler->flags == ACL_TYPE_ACCESS &&
!in_group_p(inode->i_gid) &&
!capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
err = ovl_setattr(dentry, &iattr);
if (err)
return err;
}
err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags);
if (!err)
ovl_copyattr(ovl_inode_real(inode), inode);
return err;
out_acl_release:
posix_acl_release(acl);
return err;
}
int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
int err;
struct dentry *upperdentry;
/*
* Check for permissions before trying to copy-up. This is redundant
* since it will be rechecked later by ->setattr() on upper dentry. But
* without this, copy-up can be triggered by just about anybody.
*
* We don't initialize inode->size, which just means that
* inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
* check for a swapfile (which this won't be anyway).
*/
err = inode_change_ok(dentry->d_inode, attr);
if (err)
return err;
err = ovl_want_write(dentry);
if (err)
goto out;
if (attr->ia_valid & ATTR_SIZE) {
struct inode *realinode = d_inode(ovl_dentry_real(dentry));
err = -ETXTBSY;
if (atomic_read(&realinode->i_writecount) < 0)
goto out_drop_write;
}
err = ovl_copy_up(dentry);
if (!err) {
struct inode *winode = NULL;
upperdentry = ovl_dentry_upper(dentry);
if (attr->ia_valid & ATTR_SIZE) {
winode = d_inode(upperdentry);
err = get_write_access(winode);
if (err)
goto out_drop_write;
}
inode_lock(upperdentry->d_inode);
err = notify_change(upperdentry, attr, NULL);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
if (winode)
put_write_access(winode);
}
out_drop_write:
ovl_drop_write(dentry);
out:
return err;
}
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
ssize_t ret;
if (!iov_iter_count(iter))
return 0;
inode_lock(inode);
/* Update mode */
ovl_copyattr(ovl_inode_real(inode), inode);
ret = file_remove_privs(file);
if (ret)
goto out_unlock;
ret = ovl_real_fdget(file, &real);
if (ret)
goto out_unlock;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
file_start_write(real.file);
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
file_end_write(real.file);
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
out_unlock:
inode_unlock(inode);
return ret;
}
/* Common operations required to be done after creation of file on upper */
static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry, bool hardlink)
{
ovl_dentry_version_inc(dentry->d_parent);
ovl_dentry_update(dentry, newdentry);
if (!hardlink) {
ovl_inode_update(inode, d_inode(newdentry));
ovl_copyattr(newdentry->d_inode, inode);
} else {
WARN_ON(ovl_inode_real(inode, NULL) != d_inode(newdentry));
inc_nlink(inode);
}
d_instantiate(dentry, inode);
}
static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int flags, enum ovl_copyop op)
{
struct inode *inode_out = file_inode(file_out);
struct fd real_in, real_out;
const struct cred *old_cred;
loff_t ret;
ret = ovl_real_fdget(file_out, &real_out);
if (ret)
return ret;
ret = ovl_real_fdget(file_in, &real_in);
if (ret) {
fdput(real_out);
return ret;
}
old_cred = ovl_override_creds(file_inode(file_out)->i_sb);
switch (op) {
case OVL_COPY:
ret = vfs_copy_file_range(real_in.file, pos_in,
real_out.file, pos_out, len, flags);
break;
case OVL_CLONE:
ret = vfs_clone_file_range(real_in.file, pos_in,
real_out.file, pos_out, len, flags);
break;
case OVL_DEDUPE:
ret = vfs_dedupe_file_range_one(real_in.file, pos_in,
real_out.file, pos_out, len,
flags);
break;
}
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode_out), inode_out);
fdput(real_in);
fdput(real_out);
return ret;
}
int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
int err;
struct dentry *upperdentry;
const struct cred *old_cred;
/*
* Check for permissions before trying to copy-up. This is redundant
* since it will be rechecked later by ->setattr() on upper dentry. But
* without this, copy-up can be triggered by just about anybody.
*
* We don't initialize inode->size, which just means that
* inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
* check for a swapfile (which this won't be anyway).
*/
err = setattr_prepare(dentry, attr);
if (err)
return err;
err = ovl_want_write(dentry);
if (err)
goto out;
err = ovl_copy_up(dentry);
if (!err) {
upperdentry = ovl_dentry_upper(dentry);
if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
attr->ia_valid &= ~ATTR_MODE;
inode_lock(upperdentry->d_inode);
old_cred = ovl_override_creds(dentry->d_sb);
err = notify_change(upperdentry, attr, NULL);
revert_creds(old_cred);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
}
ovl_drop_write(dentry);
out:
return err;
}
static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
int ret;
ret = ovl_real_fdget(file, &real);
if (ret)
return ret;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_fallocate(real.file, mode, offset, len);
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
return ret;
}
static int ovl_do_lookup(struct dentry *dentry)
{
struct ovl_entry *oe;
struct dentry *upperdir;
struct dentry *lowerdir;
struct dentry *upperdentry = NULL;
struct dentry *lowerdentry = NULL;
struct inode *inode = NULL;
int err;
err = -ENOMEM;
oe = ovl_alloc_entry();
if (!oe)
goto out;
upperdir = ovl_dentry_upper(dentry->d_parent);
lowerdir = ovl_dentry_lower(dentry->d_parent);
if (upperdir) {
upperdentry = ovl_lookup_real(upperdir, &dentry->d_name);
err = PTR_ERR(upperdentry);
if (IS_ERR(upperdentry))
goto out_put_dir;
if (lowerdir && upperdentry &&
(S_ISLNK(upperdentry->d_inode->i_mode) ||
S_ISDIR(upperdentry->d_inode->i_mode))) {
const struct cred *old_cred;
struct cred *override_cred;
err = -ENOMEM;
override_cred = prepare_creds();
if (!override_cred)
goto out_dput_upper;
/* CAP_SYS_ADMIN needed for getxattr */
cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
old_cred = override_creds(override_cred);
if (ovl_is_opaquedir(upperdentry)) {
oe->opaque = true;
} else if (ovl_is_whiteout(upperdentry)) {
dput(upperdentry);
upperdentry = NULL;
oe->opaque = true;
}
revert_creds(old_cred);
put_cred(override_cred);
}
}
if (lowerdir && !oe->opaque) {
lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name);
err = PTR_ERR(lowerdentry);
if (IS_ERR(lowerdentry))
goto out_dput_upper;
}
if (lowerdentry && upperdentry &&
(!S_ISDIR(upperdentry->d_inode->i_mode) ||
!S_ISDIR(lowerdentry->d_inode->i_mode))) {
dput(lowerdentry);
lowerdentry = NULL;
oe->opaque = true;
}
if (lowerdentry || upperdentry) {
struct dentry *realdentry;
realdentry = upperdentry ? upperdentry : lowerdentry;
err = -ENOMEM;
inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
oe);
if (!inode)
goto out_dput;
ovl_copyattr(realdentry->d_inode, inode);
}
if (upperdentry)
oe->__upperdentry = dget(upperdentry);
if (lowerdentry)
oe->lowerdentry = lowerdentry;
dentry->d_fsdata = oe;
dentry->d_op = &ovl_dentry_operations;
d_add(dentry, inode);
return 0;
out_dput:
dput(lowerdentry);
out_dput_upper:
dput(upperdentry);
out_put_dir:
kfree(oe);
out:
return err;
}
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *upper;
struct dentry *newdentry;
int err;
if (WARN_ON(!workdir))
return -EROFS;
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
newdentry = ovl_lookup_temp(workdir, dentry);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
upper = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_dput;
err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true);
if (err)
goto out_dput2;
if (S_ISDIR(stat->mode)) {
err = ovl_set_opaque(newdentry);
if (err)
goto out_cleanup;
err = ovl_do_rename(wdir, newdentry, udir, upper,
RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup(wdir, upper);
} else {
err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
if (err)
goto out_cleanup;
}
ovl_dentry_version_inc(dentry->d_parent);
ovl_dentry_update(dentry, newdentry);
ovl_copyattr(newdentry->d_inode, inode);
d_instantiate(dentry, inode);
newdentry = NULL;
out_dput2:
dput(upper);
out_dput:
dput(newdentry);
out_unlock:
unlock_rename(workdir, upperdir);
out:
return err;
out_cleanup:
ovl_cleanup(wdir, newdentry);
goto out_dput2;
}
static int ovl_do_lookup(struct dentry *dentry)
{
struct ovl_entry *oe;
struct dentry *upperdir;
struct dentry *lowerdir;
struct dentry *upperdentry = NULL;
struct dentry *lowerdentry = NULL;
struct inode *inode = NULL;
int err;
err = -ENOMEM;
oe = ovl_alloc_entry();
if (!oe)
goto out;
upperdir = ovl_dentry_upper(dentry->d_parent);
lowerdir = ovl_dentry_lower(dentry->d_parent);
if (upperdir) {
upperdentry = ovl_lookup_real(upperdir, &dentry->d_name);
err = PTR_ERR(upperdentry);
if (IS_ERR(upperdentry))
goto out_put_dir;
if (lowerdir && upperdentry) {
if (ovl_is_whiteout(upperdentry)) {
dput(upperdentry);
upperdentry = NULL;
oe->opaque = true;
} else if (ovl_is_opaquedir(upperdentry)) {
oe->opaque = true;
}
}
}
if (lowerdir && !oe->opaque) {
lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name);
err = PTR_ERR(lowerdentry);
if (IS_ERR(lowerdentry))
goto out_dput_upper;
}
if (lowerdentry && upperdentry &&
(!S_ISDIR(upperdentry->d_inode->i_mode) ||
!S_ISDIR(lowerdentry->d_inode->i_mode))) {
dput(lowerdentry);
lowerdentry = NULL;
oe->opaque = true;
}
if (lowerdentry || upperdentry) {
struct dentry *realdentry;
realdentry = upperdentry ? upperdentry : lowerdentry;
err = -ENOMEM;
inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
oe);
if (!inode)
goto out_dput;
ovl_copyattr(realdentry->d_inode, inode);
}
if (upperdentry)
oe->__upperdentry = dget(upperdentry);
if (lowerdentry)
oe->lowerdentry = lowerdentry;
dentry->d_fsdata = oe;
dentry->d_op = &ovl_dentry_operations;
d_add(dentry, inode);
return 0;
out_dput:
dput(lowerdentry);
out_dput_upper:
dput(upperdentry);
out_put_dir:
kfree(oe);
out:
return err;
}