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 struct dentry *open_xa_dir(const struct inode *inode, int flags)
{
struct dentry *xaroot, *xadir;
char namebuf[17];
xaroot = open_xa_root(inode->i_sb, flags);
if (IS_ERR(xaroot))
return xaroot;
snprintf(namebuf, sizeof(namebuf), "%X.%X",
le32_to_cpu(INODE_PKEY(inode)->k_objectid),
inode->i_generation);
inode_lock_nested(d_inode(xaroot), I_MUTEX_XATTR);
xadir = lookup_one_len(namebuf, xaroot, strlen(namebuf));
if (!IS_ERR(xadir) && d_really_is_negative(xadir)) {
int err = -ENODATA;
if (xattr_may_create(flags))
err = xattr_mkdir(d_inode(xaroot), xadir, 0700);
if (err) {
dput(xadir);
xadir = ERR_PTR(err);
}
}
inode_unlock(d_inode(xaroot));
dput(xaroot);
return xadir;
}
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;
if (!hardlink && !IS_POSIXACL(udir))
stat->mode &= ~current_umask();
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_instantiate(dentry, inode, newdentry, !!hardlink);
newdentry = NULL;
out_dput:
dput(newdentry);
out_unlock:
inode_unlock(udir);
return err;
}
static struct dentry *open_xa_root(struct super_block *sb, int flags)
{
struct dentry *privroot = REISERFS_SB(sb)->priv_root;
struct dentry *xaroot;
if (d_really_is_negative(privroot))
return ERR_PTR(-ENODATA);
inode_lock_nested(d_inode(privroot), I_MUTEX_XATTR);
xaroot = dget(REISERFS_SB(sb)->xattr_root);
if (!xaroot)
xaroot = ERR_PTR(-ENODATA);
else if (d_really_is_negative(xaroot)) {
int err = -ENODATA;
if (xattr_may_create(flags))
err = xattr_mkdir(d_inode(privroot), xaroot, 0700);
if (err) {
dput(xaroot);
xaroot = ERR_PTR(err);
}
}
inode_unlock(d_inode(privroot));
return xaroot;
}
static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct cattr *attr, struct dentry *hardlink)
{
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *newdentry;
int err;
if (!hardlink && !IS_POSIXACL(udir))
attr->mode &= ~current_umask();
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, attr, hardlink, false);
if (err)
goto out_dput;
if (ovl_type_merge(dentry->d_parent)) {
/* Setting opaque here is just an optimization, allow to fail */
ovl_set_opaque(dentry, newdentry);
}
ovl_instantiate(dentry, inode, newdentry, !!hardlink);
newdentry = NULL;
out_dput:
dput(newdentry);
out_unlock:
inode_unlock(udir);
return err;
}
static struct dentry *lock_parent(struct dentry *dentry)
{
struct dentry *dir;
dir = dget_parent(dentry);
inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
return dir;
}
/*
* We use I_MUTEX_CHILD here to silence lockdep. It's safe because xattr
* mutation ops aren't called during rename or splace, which are the
* only other users of I_MUTEX_CHILD. It violates the ordering, but that's
* better than allocating another subclass just for this code.
*/
static int xattr_unlink(struct inode *dir, struct dentry *dentry)
{
int error;
BUG_ON(!inode_is_locked(dir));
inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
error = dir->i_op->unlink(dir, dentry);
inode_unlock(d_inode(dentry));
if (!error)
d_delete(dentry);
return error;
}
int configfs_create_file(struct config_item * item, const struct configfs_attribute * attr)
{
struct dentry *dir = item->ci_dentry;
struct configfs_dirent *parent_sd = dir->d_fsdata;
umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
int error = 0;
inode_lock_nested(d_inode(dir), I_MUTEX_NORMAL);
error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode,
CONFIGFS_ITEM_ATTR);
inode_unlock(d_inode(dir));
return error;
}
/*
* Grab the exclusive iolock for a data copy from src to dest, making
* sure to abide vfs locking order (lowest pointer value goes first) and
* breaking the pnfs layout leases on dest before proceeding. The loop
* is needed because we cannot call the blocking break_layout() with the
* src iolock held, and therefore have to back out both locks.
*/
static int
xfs_iolock_two_inodes_and_break_layout(
struct inode *src,
struct inode *dest)
{
int error;
retry:
if (src < dest) {
inode_lock_shared(src);
inode_lock_nested(dest, I_MUTEX_NONDIR2);
} else {
/* src >= dest */
inode_lock(dest);
}
error = break_layout(dest, false);
if (error == -EWOULDBLOCK) {
inode_unlock(dest);
if (src < dest)
inode_unlock_shared(src);
error = break_layout(dest, true);
if (error)
return error;
goto retry;
}
if (error) {
inode_unlock(dest);
if (src < dest)
inode_unlock_shared(src);
return error;
}
if (src > dest)
inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
return 0;
}
static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
const char *name, bool persist)
{
struct inode *dir = ofs->workbasedir->d_inode;
struct vfsmount *mnt = ofs->upper_mnt;
struct dentry *work;
int err;
bool retried = false;
bool locked = false;
inode_lock_nested(dir, I_MUTEX_PARENT);
locked = true;
retry:
work = lookup_one_len(name, ofs->workbasedir, strlen(name));
if (!IS_ERR(work)) {
struct iattr attr = {
.ia_valid = ATTR_MODE,
.ia_mode = S_IFDIR | 0,
};
if (work->d_inode) {
err = -EEXIST;
if (retried)
goto out_dput;
if (persist)
goto out_unlock;
retried = true;
ovl_workdir_cleanup(dir, mnt, work, 0);
dput(work);
goto retry;
}
work = ovl_create_real(dir, work, OVL_CATTR(attr.ia_mode));
err = PTR_ERR(work);
if (IS_ERR(work))
goto out_err;
/*
* Try to remove POSIX ACL xattrs from workdir. We are good if:
*
* a) success (there was a POSIX ACL xattr and was removed)
* b) -ENODATA (there was no POSIX ACL xattr)
* c) -EOPNOTSUPP (POSIX ACL xattrs are not supported)
*
* There are various other error values that could effectively
* mean that the xattr doesn't exist (e.g. -ERANGE is returned
* if the xattr name is too long), but the set of filesystems
* allowed as upper are limited to "normal" ones, where checking
* for the above two errors is sufficient.
*/
err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
if (err && err != -ENODATA && err != -EOPNOTSUPP)
goto out_dput;
err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
if (err && err != -ENODATA && err != -EOPNOTSUPP)
goto out_dput;
/* Clear any inherited mode bits */
inode_lock(work->d_inode);
err = notify_change(work, &attr, NULL);
inode_unlock(work->d_inode);
if (err)
goto out_dput;
} else {
err = PTR_ERR(work);
goto out_err;
}
out_unlock:
if (locked)
inode_unlock(dir);
return work;
out_dput:
dput(work);
out_err:
pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
ofs->config.workdir, name, -err);
work = NULL;
goto out_unlock;
}
static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
struct file *dst_file, loff_t dst_off, u64 count)
{
struct inode *dst_inode = file_inode(dst_file);
struct nfs_server *server = NFS_SERVER(dst_inode);
struct inode *src_inode = file_inode(src_file);
unsigned int bs = server->clone_blksize;
bool same_inode = false;
int ret;
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
goto out;
if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
goto out;
}
if (src_inode == dst_inode)
same_inode = true;
/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
if (same_inode) {
inode_lock(src_inode);
} else if (dst_inode < src_inode) {
inode_lock_nested(dst_inode, I_MUTEX_PARENT);
inode_lock_nested(src_inode, I_MUTEX_CHILD);
} else {
inode_lock_nested(src_inode, I_MUTEX_PARENT);
inode_lock_nested(dst_inode, I_MUTEX_CHILD);
}
/* flush all pending writes on both src and dst so that server
* has the latest data */
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
/* truncate inode page cache of the dst range so that future reads can fetch
* new data from server */
if (!ret)
truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
out_unlock:
if (same_inode) {
inode_unlock(src_inode);
} else if (dst_inode < src_inode) {
inode_unlock(src_inode);
inode_unlock(dst_inode);
} else {
inode_unlock(dst_inode);
inode_unlock(src_inode);
}
out:
return ret;
}
int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
{
int err, e;
unsigned char dmsg;
struct au_mvd_args *args;
struct inode *inode;
inode = d_inode(dentry);
err = -EPERM;
if (unlikely(!capable(CAP_SYS_ADMIN)))
goto out;
err = -ENOMEM;
args = kmalloc(sizeof(*args), GFP_NOFS);
if (unlikely(!args))
goto out;
err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown));
if (!err)
err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg));
if (unlikely(err)) {
err = -EFAULT;
AuTraceErr(err);
goto out_free;
}
AuDbg("flags 0x%x\n", args->mvdown.flags);
args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R);
args->mvdown.au_errno = 0;
args->dentry = dentry;
args->inode = inode;
args->sb = dentry->d_sb;
err = -ENOENT;
dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG);
args->parent = dget_parent(dentry);
args->dir = d_inode(args->parent);
inode_lock_nested(args->dir, I_MUTEX_PARENT);
dput(args->parent);
if (unlikely(args->parent != dentry->d_parent)) {
AU_MVD_PR(dmsg, "parent dir is moved\n");
goto out_dir;
}
inode_lock_nested(inode, I_MUTEX_CHILD);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW);
if (unlikely(err))
goto out_inode;
di_write_lock_parent(args->parent);
err = au_mvd_args(dmsg, args);
if (unlikely(err))
goto out_parent;
err = au_do_mvdown(dmsg, args);
if (unlikely(err))
goto out_parent;
au_cpup_attr_timesizes(args->dir);
au_cpup_attr_timesizes(inode);
if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER))
au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst));
/* au_digen_dec(dentry); */
out_parent:
di_write_unlock(args->parent);
aufs_read_unlock(dentry, AuLock_DW);
out_inode:
inode_unlock(inode);
out_dir:
inode_unlock(args->dir);
out_free:
e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
if (unlikely(e))
err = -EFAULT;
kfree(args);
out:
AuTraceErr(err);
return err;
}
