static struct kernfs_node *kernfs_dir_pos(const void *ns,
struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
{
if (pos) {
int valid = kernfs_active(pos) &&
pos->parent == parent && hash == pos->hash;
kernfs_put(pos);
if (!valid)
pos = NULL;
}
if (!pos && (hash > 1) && (hash < INT_MAX)) {
struct rb_node *node = parent->dir.children.rb_node;
while (node) {
pos = rb_to_kn(node);
if (hash < pos->hash)
node = node->rb_left;
else if (hash > pos->hash)
node = node->rb_right;
else
break;
}
}
/* Skip over entries which are dying/dead or in the wrong namespace */
while (pos && (!kernfs_active(pos) || pos->ns != ns)) {
struct rb_node *node = rb_next(&pos->rb);
if (!node)
pos = NULL;
else
pos = rb_to_kn(node);
}
return pos;
}
/**
* kernfs_add_one - add kernfs_node to parent without warning
* @kn: kernfs_node to be added
*
* The caller must already have initialized @kn->parent. This
* function increments nlink of the parent's inode if @kn is a
* directory and link into the children list of the parent.
*
* RETURNS:
* 0 on success, -EEXIST if entry with the given name already
* exists.
*/
int kernfs_add_one(struct kernfs_node *kn)
{
struct kernfs_node *parent = kn->parent;
struct kernfs_iattrs *ps_iattr;
bool has_ns;
int ret;
mutex_lock(&kernfs_mutex);
ret = -EINVAL;
has_ns = kernfs_ns_enabled(parent);
if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
has_ns ? "required" : "invalid", parent->name, kn->name))
goto out_unlock;
if (kernfs_type(parent) != KERNFS_DIR)
goto out_unlock;
ret = -ENOENT;
if (parent->flags & KERNFS_EMPTY_DIR)
goto out_unlock;
if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
goto out_unlock;
kn->hash = kernfs_name_hash(kn->name, kn->ns);
ret = kernfs_link_sibling(kn);
if (ret)
goto out_unlock;
/* Update timestamps on the parent */
ps_iattr = parent->iattr;
if (ps_iattr) {
struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
ktime_get_real_ts(&ps_iattrs->ia_ctime);
ps_iattrs->ia_mtime = ps_iattrs->ia_ctime;
}
mutex_unlock(&kernfs_mutex);
/*
* Activate the new node unless CREATE_DEACTIVATED is requested.
* If not activated here, the kernfs user is responsible for
* activating the node with kernfs_activate(). A node which hasn't
* been activated is not visible to userland and its removal won't
* trigger deactivation.
*/
if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
kernfs_activate(kn);
return 0;
out_unlock:
mutex_unlock(&kernfs_mutex);
return ret;
}
static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
{
struct kernfs_node *kn;
if (flags & LOOKUP_RCU)
return -ECHILD;
/* Always perform fresh lookup for negatives */
if (!dentry->d_inode)
goto out_bad_unlocked;
kn = dentry->d_fsdata;
mutex_lock(&kernfs_mutex);
/* The kernfs node has been deactivated */
if (!kernfs_active(kn))
goto out_bad;
/* The kernfs node has been moved? */
if (dentry->d_parent->d_fsdata != kn->parent)
goto out_bad;
/* The kernfs node has been renamed */
if (strcmp(dentry->d_name.name, kn->name) != 0)
goto out_bad;
/* The kernfs node has been moved to a different namespace */
if (kn->parent && kernfs_ns_enabled(kn->parent) &&
kernfs_info(dentry->d_sb)->ns != kn->ns)
goto out_bad;
mutex_unlock(&kernfs_mutex);
out_valid:
return 1;
out_bad:
mutex_unlock(&kernfs_mutex);
out_bad_unlocked:
/*
* @dentry doesn't match the underlying kernfs node, drop the
* dentry and force lookup. If we have submounts we must allow the
* vfs caches to lie about the state of the filesystem to prevent
* leaks and other nasty things, so use check_submounts_and_drop()
* instead of d_drop().
*/
if (check_submounts_and_drop(dentry) != 0)
goto out_valid;
return 0;
}
static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
{
pos = kernfs_dir_pos(ns, parent, ino, pos);
if (pos) {
do {
struct rb_node *node = rb_next(&pos->rb);
if (!node)
pos = NULL;
else
pos = rb_to_kn(node);
} while (pos && (!kernfs_active(pos) || pos->ns != ns));
}
return pos;
}
static struct dentry *kernfs_iop_lookup(struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct dentry *ret;
struct kernfs_node *parent = dentry->d_parent->d_fsdata;
struct kernfs_node *kn;
struct inode *inode;
const void *ns = NULL;
mutex_lock(&kernfs_mutex);
if (kernfs_ns_enabled(parent))
ns = kernfs_info(dir->i_sb)->ns;
kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
/* no such entry */
if (!kn || !kernfs_active(kn)) {
ret = NULL;
goto out_unlock;
}
kernfs_get(kn);
dentry->d_fsdata = kn;
/* attach dentry and inode */
inode = kernfs_get_inode(dir->i_sb, kn);
if (!inode) {
ret = ERR_PTR(-ENOMEM);
goto out_unlock;
}
/* instantiate and hash dentry */
ret = d_splice_alias(inode, dentry);
out_unlock:
mutex_unlock(&kernfs_mutex);
return ret;
}
static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
{
struct kernfs_node *kn;
if (flags & LOOKUP_RCU)
return -ECHILD;
/* Always perform fresh lookup for negatives */
if (d_really_is_negative(dentry))
goto out_bad_unlocked;
kn = dentry->d_fsdata;
mutex_lock(&kernfs_mutex);
/* The kernfs node has been deactivated */
if (!kernfs_active(kn))
goto out_bad;
/* The kernfs node has been moved? */
if (dentry->d_parent->d_fsdata != kn->parent)
goto out_bad;
/* The kernfs node has been renamed */
if (strcmp(dentry->d_name.name, kn->name) != 0)
goto out_bad;
/* The kernfs node has been moved to a different namespace */
if (kn->parent && kernfs_ns_enabled(kn->parent) &&
kernfs_info(dentry->d_sb)->ns != kn->ns)
goto out_bad;
mutex_unlock(&kernfs_mutex);
return 1;
out_bad:
mutex_unlock(&kernfs_mutex);
out_bad_unlocked:
return 0;
}
/**
* kernfs_rename_ns - move and rename a kernfs_node
* @kn: target node
* @new_parent: new parent to put @sd under
* @new_name: new name
* @new_ns: new namespace tag
*/
int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
const char *new_name, const void *new_ns)
{
struct kernfs_node *old_parent;
const char *old_name = NULL;
int error;
/* can't move or rename root */
if (!kn->parent)
return -EINVAL;
mutex_lock(&kernfs_mutex);
error = -ENOENT;
if (!kernfs_active(kn) || !kernfs_active(new_parent) ||
(new_parent->flags & KERNFS_EMPTY_DIR))
goto out;
error = 0;
if ((kn->parent == new_parent) && (kn->ns == new_ns) &&
(strcmp(kn->name, new_name) == 0))
goto out; /* nothing to rename */
error = -EEXIST;
if (kernfs_find_ns(new_parent, new_name, new_ns))
goto out;
/* rename kernfs_node */
if (strcmp(kn->name, new_name) != 0) {
error = -ENOMEM;
new_name = kstrdup_const(new_name, GFP_KERNEL);
if (!new_name)
goto out;
} else {
new_name = NULL;
}
/*
* Move to the appropriate place in the appropriate directories rbtree.
*/
kernfs_unlink_sibling(kn);
kernfs_get(new_parent);
/* rename_lock protects ->parent and ->name accessors */
spin_lock_irq(&kernfs_rename_lock);
old_parent = kn->parent;
kn->parent = new_parent;
kn->ns = new_ns;
if (new_name) {
old_name = kn->name;
kn->name = new_name;
}
spin_unlock_irq(&kernfs_rename_lock);
kn->hash = kernfs_name_hash(kn->name, kn->ns);
kernfs_link_sibling(kn);
kernfs_put(old_parent);
kfree_const(old_name);
error = 0;
out:
mutex_unlock(&kernfs_mutex);
return error;
}
static void __kernfs_remove(struct kernfs_node *kn)
{
struct kernfs_node *pos;
lockdep_assert_held(&kernfs_mutex);
/*
* Short-circuit if non-root @kn has already finished removal.
* This is for kernfs_remove_self() which plays with active ref
* after removal.
*/
if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
return;
pr_debug("kernfs %s: removing\n", kn->name);
/* prevent any new usage under @kn by deactivating all nodes */
pos = NULL;
while ((pos = kernfs_next_descendant_post(pos, kn)))
if (kernfs_active(pos))
atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
/* deactivate and unlink the subtree node-by-node */
do {
pos = kernfs_leftmost_descendant(kn);
/*
* kernfs_drain() drops kernfs_mutex temporarily and @pos's
* base ref could have been put by someone else by the time
* the function returns. Make sure it doesn't go away
* underneath us.
*/
kernfs_get(pos);
/*
* Drain iff @kn was activated. This avoids draining and
* its lockdep annotations for nodes which have never been
* activated and allows embedding kernfs_remove() in create
* error paths without worrying about draining.
*/
if (kn->flags & KERNFS_ACTIVATED)
kernfs_drain(pos);
else
WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
/*
* kernfs_unlink_sibling() succeeds once per node. Use it
* to decide who's responsible for cleanups.
*/
if (!pos->parent || kernfs_unlink_sibling(pos)) {
struct kernfs_iattrs *ps_iattr =
pos->parent ? pos->parent->iattr : NULL;
/* update timestamps on the parent */
if (ps_iattr) {
ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
}
kernfs_put(pos);
}
kernfs_put(pos);
} while (pos != kn);
}