return 1;
}
-static struct dentry_operations configfs_dentry_ops = {
+static const struct dentry_operations configfs_dentry_ops = {
.d_iput = configfs_d_iput,
/* simple_delete_dentry() isn't exported */
.d_delete = configfs_d_delete,
};
+#ifdef CONFIG_LOCKDEP
+
+/*
+ * Helpers to make lockdep happy with our recursive locking of default groups'
+ * inodes (see configfs_attach_group() and configfs_detach_group()).
+ * We put default groups i_mutexes in separate classes according to their depth
+ * from the youngest non-default group ancestor.
+ *
+ * For a non-default group A having default groups A/B, A/C, and A/C/D, default
+ * groups A/B and A/C will have their inode's mutex in class
+ * default_group_class[0], and default group A/C/D will be in
+ * default_group_class[1].
+ *
+ * The lock classes are declared and assigned in inode.c, according to the
+ * s_depth value.
+ * The s_depth value is initialized to -1, adjusted to >= 0 when attaching
+ * default groups, and reset to -1 when all default groups are attached. During
+ * attachment, if configfs_create() sees s_depth > 0, the lock class of the new
+ * inode's mutex is set to default_group_class[s_depth - 1].
+ */
+
+static void configfs_init_dirent_depth(struct configfs_dirent *sd)
+{
+ sd->s_depth = -1;
+}
+
+static void configfs_set_dir_dirent_depth(struct configfs_dirent *parent_sd,
+ struct configfs_dirent *sd)
+{
+ int parent_depth = parent_sd->s_depth;
+
+ if (parent_depth >= 0)
+ sd->s_depth = parent_depth + 1;
+}
+
+static void
+configfs_adjust_dir_dirent_depth_before_populate(struct configfs_dirent *sd)
+{
+ /*
+ * item's i_mutex class is already setup, so s_depth is now only
+ * used to set new sub-directories s_depth, which is always done
+ * with item's i_mutex locked.
+ */
+ /*
+ * sd->s_depth == -1 iff we are a non default group.
+ * else (we are a default group) sd->s_depth > 0 (see
+ * create_dir()).
+ */
+ if (sd->s_depth == -1)
+ /*
+ * We are a non default group and we are going to create
+ * default groups.
+ */
+ sd->s_depth = 0;
+}
+
+static void
+configfs_adjust_dir_dirent_depth_after_populate(struct configfs_dirent *sd)
+{
+ /* We will not create default groups anymore. */
+ sd->s_depth = -1;
+}
+
+#else /* CONFIG_LOCKDEP */
+
+static void configfs_init_dirent_depth(struct configfs_dirent *sd)
+{
+}
+
+static void configfs_set_dir_dirent_depth(struct configfs_dirent *parent_sd,
+ struct configfs_dirent *sd)
+{
+}
+
+static void
+configfs_adjust_dir_dirent_depth_before_populate(struct configfs_dirent *sd)
+{
+}
+
+static void
+configfs_adjust_dir_dirent_depth_after_populate(struct configfs_dirent *sd)
+{
+}
+
+#endif /* CONFIG_LOCKDEP */
+
/*
* Allocates a new configfs_dirent and links it to the parent configfs_dirent
*/
-static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * parent_sd,
- void * element)
+static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *parent_sd,
+ void *element, int type)
{
struct configfs_dirent * sd;
INIT_LIST_HEAD(&sd->s_links);
INIT_LIST_HEAD(&sd->s_children);
sd->s_element = element;
+ sd->s_type = type;
+ configfs_init_dirent_depth(sd);
spin_lock(&configfs_dirent_lock);
if (parent_sd->s_type & CONFIGFS_USET_DROPPING) {
spin_unlock(&configfs_dirent_lock);
{
struct configfs_dirent * sd;
- sd = configfs_new_dirent(parent_sd, element);
+ sd = configfs_new_dirent(parent_sd, element, type);
if (IS_ERR(sd))
return PTR_ERR(sd);
sd->s_mode = mode;
- sd->s_type = type;
sd->s_dentry = dentry;
if (dentry) {
dentry->d_fsdata = configfs_get(sd);
error = configfs_dirent_exists(p->d_fsdata, d->d_name.name);
if (!error)
error = configfs_make_dirent(p->d_fsdata, d, k, mode,
- CONFIGFS_DIR);
+ CONFIGFS_DIR | CONFIGFS_USET_CREATING);
if (!error) {
+ configfs_set_dir_dirent_depth(p->d_fsdata, d->d_fsdata);
error = configfs_create(d, mode, init_dir);
if (!error) {
inc_nlink(p->d_inode);
* configfs_create_dir - create a directory for an config_item.
* @item: config_itemwe're creating directory for.
* @dentry: config_item's dentry.
+ *
+ * Note: user-created entries won't be allowed under this new directory
+ * until it is validated by configfs_dir_set_ready()
*/
static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
return error;
}
+/*
+ * Allow userspace to create new entries under a new directory created with
+ * configfs_create_dir(), and under all of its chidlren directories recursively.
+ * @sd configfs_dirent of the new directory to validate
+ *
+ * Caller must hold configfs_dirent_lock.
+ */
+static void configfs_dir_set_ready(struct configfs_dirent *sd)
+{
+ struct configfs_dirent *child_sd;
+
+ sd->s_type &= ~CONFIGFS_USET_CREATING;
+ list_for_each_entry(child_sd, &sd->s_children, s_sibling)
+ if (child_sd->s_type & CONFIGFS_USET_CREATING)
+ configfs_dir_set_ready(child_sd);
+}
+
+/*
+ * Check that a directory does not belong to a directory hierarchy being
+ * attached and not validated yet.
+ * @sd configfs_dirent of the directory to check
+ *
+ * @return non-zero iff the directory was validated
+ *
+ * Note: takes configfs_dirent_lock, so the result may change from false to true
+ * in two consecutive calls, but never from true to false.
+ */
+int configfs_dirent_is_ready(struct configfs_dirent *sd)
+{
+ int ret;
+
+ spin_lock(&configfs_dirent_lock);
+ ret = !(sd->s_type & CONFIGFS_USET_CREATING);
+ spin_unlock(&configfs_dirent_lock);
+
+ return ret;
+}
+
int configfs_create_link(struct configfs_symlink *sl,
struct dentry *parent,
struct dentry *dentry)
* The only thing special about this is that we remove any files in
* the directory before we remove the directory, and we've inlined
* what used to be configfs_rmdir() below, instead of calling separately.
+ *
+ * Caller holds the mutex of the item's inode
*/
static void configfs_remove_dir(struct config_item * item)
struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
struct configfs_dirent * sd;
int found = 0;
- int err = 0;
+ int err;
+
+ /*
+ * Fake invisibility if dir belongs to a group/default groups hierarchy
+ * being attached
+ *
+ * This forbids userspace to read/write attributes of items which may
+ * not complete their initialization, since the dentries of the
+ * attributes won't be instantiated.
+ */
+ err = -ENOENT;
+ if (!configfs_dirent_is_ready(parent_sd))
+ goto out;
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
if (sd->s_type & CONFIGFS_NOT_PINNED) {
return simple_lookup(dir, dentry, nd);
}
+out:
return ERR_PTR(err);
}
ret = 0;
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
- if (sd->s_type & CONFIGFS_NOT_PINNED)
+ if (!sd->s_element ||
+ (sd->s_type & CONFIGFS_NOT_PINNED))
continue;
if (sd->s_type & CONFIGFS_USET_DEFAULT) {
/* Abort if racing with mkdir() */
configfs_detach_group(sd->s_element);
child->d_inode->i_flags |= S_DEAD;
+ dont_mount(child);
mutex_unlock(&child->d_inode->i_mutex);
static int populate_groups(struct config_group *group)
{
struct config_group *new_group;
- struct dentry *dentry = group->cg_item.ci_dentry;
int ret = 0;
int i;
if (group->default_groups) {
- /*
- * FYI, we're faking mkdir here
- * I'm not sure we need this semaphore, as we're called
- * from our parent's mkdir. That holds our parent's
- * i_mutex, so afaik lookup cannot continue through our
- * parent to find us, let alone mess with our tree.
- * That said, taking our i_mutex is closer to mkdir
- * emulation, and shouldn't hurt.
- */
- mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
-
for (i = 0; group->default_groups[i]; i++) {
new_group = group->default_groups[i];
ret = create_default_group(group, new_group);
- if (ret)
+ if (ret) {
+ detach_groups(group);
break;
+ }
}
-
- mutex_unlock(&dentry->d_inode->i_mutex);
}
- if (ret)
- detach_groups(group);
-
return ret;
}
if (!ret) {
ret = populate_attrs(item);
if (ret) {
+ /*
+ * We are going to remove an inode and its dentry but
+ * the VFS may already have hit and used them. Thus,
+ * we must lock them as rmdir() would.
+ */
+ mutex_lock(&dentry->d_inode->i_mutex);
configfs_remove_dir(item);
+ dentry->d_inode->i_flags |= S_DEAD;
+ dont_mount(dentry);
+ mutex_unlock(&dentry->d_inode->i_mutex);
d_delete(dentry);
}
}
return ret;
}
+/* Caller holds the mutex of the item's inode */
static void configfs_detach_item(struct config_item *item)
{
detach_attrs(item);
sd = dentry->d_fsdata;
sd->s_type |= CONFIGFS_USET_DIR;
+ /*
+ * FYI, we're faking mkdir in populate_groups()
+ * We must lock the group's inode to avoid races with the VFS
+ * which can already hit the inode and try to add/remove entries
+ * under it.
+ *
+ * We must also lock the inode to remove it safely in case of
+ * error, as rmdir() would.
+ */
+ mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+ configfs_adjust_dir_dirent_depth_before_populate(sd);
ret = populate_groups(to_config_group(item));
if (ret) {
configfs_detach_item(item);
- d_delete(dentry);
+ dentry->d_inode->i_flags |= S_DEAD;
+ dont_mount(dentry);
}
+ configfs_adjust_dir_dirent_depth_after_populate(sd);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ if (ret)
+ d_delete(dentry);
}
return ret;
}
+/* Caller holds the mutex of the group's inode */
static void configfs_detach_group(struct config_item *item)
{
detach_groups(to_config_group(item));
* Note, btw, that this can be called at *any* time, even when a configfs
* subsystem isn't registered, or when configfs is loading or unloading.
* Just like configfs_register_subsystem(). So we take the same
- * precautions. We pin the filesystem. We lock each i_mutex _in_order_
- * on our way down the tree. If we can find the target item in the
+ * precautions. We pin the filesystem. We lock configfs_dirent_lock.
+ * If we can find the target item in the
* configfs tree, it must be part of the subsystem tree as well, so we
- * do not need the subsystem semaphore. Holding the i_mutex chain locks
- * out mkdir() and rmdir(), who might be racing us.
+ * do not need the subsystem semaphore. Holding configfs_dirent_lock helps
+ * locking out mkdir() and rmdir(), who might be racing us.
*/
/*
* do that so we can unlock it if we find nothing.
*
* Here we do a depth-first search of the dentry hierarchy looking for
- * our object. We take i_mutex on each step of the way down. IT IS
- * ESSENTIAL THAT i_mutex LOCKING IS ORDERED. If we come back up a branch,
- * we'll drop the i_mutex.
+ * our object.
+ * We deliberately ignore items tagged as dropping since they are virtually
+ * dead, as well as items in the middle of attachment since they virtually
+ * do not exist yet. This completes the locking out of racing mkdir() and
+ * rmdir().
+ * Note: subdirectories in the middle of attachment start with s_type =
+ * CONFIGFS_DIR|CONFIGFS_USET_CREATING set by create_dir(). When
+ * CONFIGFS_USET_CREATING is set, we ignore the item. The actual set of
+ * s_type is in configfs_new_dirent(), which has configfs_dirent_lock.
*
- * If the target is not found, -ENOENT is bubbled up and we have released
- * all locks. If the target was found, the locks will be cleared by
- * configfs_depend_rollback().
+ * If the target is not found, -ENOENT is bubbled up.
*
* This adds a requirement that all config_items be unique!
*
- * This is recursive because the locking traversal is tricky. There isn't
+ * This is recursive. There isn't
* much on the stack, though, so folks that need this function - be careful
* about your stack! Patches will be accepted to make it iterative.
*/
BUG_ON(!origin || !sd);
- /* Lock this guy on the way down */
- mutex_lock(&sd->s_dentry->d_inode->i_mutex);
if (sd->s_element == target) /* Boo-yah */
goto out;
list_for_each_entry(child_sd, &sd->s_children, s_sibling) {
- if (child_sd->s_type & CONFIGFS_DIR) {
+ if ((child_sd->s_type & CONFIGFS_DIR) &&
+ !(child_sd->s_type & CONFIGFS_USET_DROPPING) &&
+ !(child_sd->s_type & CONFIGFS_USET_CREATING)) {
ret = configfs_depend_prep(child_sd->s_dentry,
target);
if (!ret)
}
/* We looped all our children and didn't find target */
- mutex_unlock(&sd->s_dentry->d_inode->i_mutex);
ret = -ENOENT;
out:
return ret;
}
-/*
- * This is ONLY called if configfs_depend_prep() did its job. So we can
- * trust the entire path from item back up to origin.
- *
- * We walk backwards from item, unlocking each i_mutex. We finish by
- * unlocking origin.
- */
-static void configfs_depend_rollback(struct dentry *origin,
- struct config_item *item)
-{
- struct dentry *dentry = item->ci_dentry;
-
- while (dentry != origin) {
- mutex_unlock(&dentry->d_inode->i_mutex);
- dentry = dentry->d_parent;
- }
-
- mutex_unlock(&origin->d_inode->i_mutex);
-}
-
int configfs_depend_item(struct configfs_subsystem *subsys,
struct config_item *target)
{
/* Ok, now we can trust subsys/s_item */
- /* Scan the tree, locking i_mutex recursively, return 0 if found */
+ spin_lock(&configfs_dirent_lock);
+ /* Scan the tree, return 0 if found */
ret = configfs_depend_prep(subsys_sd->s_dentry, target);
if (ret)
- goto out_unlock_fs;
+ goto out_unlock_dirent_lock;
- /* We hold all i_mutexes from the subsystem down to the target */
+ /*
+ * We are sure that the item is not about to be removed by rmdir(), and
+ * not in the middle of attachment by mkdir().
+ */
p = target->ci_dentry->d_fsdata;
p->s_dependent_count += 1;
- configfs_depend_rollback(subsys_sd->s_dentry, target);
-
+out_unlock_dirent_lock:
+ spin_unlock(&configfs_dirent_lock);
out_unlock_fs:
mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex);
struct configfs_dirent *sd;
/*
- * Since we can trust everything is pinned, we just need i_mutex
- * on the item.
+ * Since we can trust everything is pinned, we just need
+ * configfs_dirent_lock.
*/
- mutex_lock(&target->ci_dentry->d_inode->i_mutex);
+ spin_lock(&configfs_dirent_lock);
sd = target->ci_dentry->d_fsdata;
BUG_ON(sd->s_dependent_count < 1);
* After this unlock, we cannot trust the item to stay alive!
* DO NOT REFERENCE item after this unlock.
*/
- mutex_unlock(&target->ci_dentry->d_inode->i_mutex);
+ spin_unlock(&configfs_dirent_lock);
}
EXPORT_SYMBOL(configfs_undepend_item);
struct configfs_subsystem *subsys;
struct configfs_dirent *sd;
struct config_item_type *type;
- struct module *owner = NULL;
+ struct module *subsys_owner = NULL, *new_item_owner = NULL;
char *name;
if (dentry->d_parent == configfs_sb->s_root) {
}
sd = dentry->d_parent->d_fsdata;
+
+ /*
+ * Fake invisibility if dir belongs to a group/default groups hierarchy
+ * being attached
+ */
+ if (!configfs_dirent_is_ready(sd)) {
+ ret = -ENOENT;
+ goto out;
+ }
+
if (!(sd->s_type & CONFIGFS_USET_DIR)) {
ret = -EPERM;
goto out;
goto out_put;
}
+ /*
+ * The subsystem may belong to a different module than the item
+ * being created. We don't want to safely pin the new item but
+ * fail to pin the subsystem it sits under.
+ */
+ if (!subsys->su_group.cg_item.ci_type) {
+ ret = -EINVAL;
+ goto out_put;
+ }
+ subsys_owner = subsys->su_group.cg_item.ci_type->ct_owner;
+ if (!try_module_get(subsys_owner)) {
+ ret = -EINVAL;
+ goto out_put;
+ }
+
name = kmalloc(dentry->d_name.len + 1, GFP_KERNEL);
if (!name) {
ret = -ENOMEM;
- goto out_put;
+ goto out_subsys_put;
}
snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name);
* If ret != 0, then link_obj() was never called.
* There are no extra references to clean up.
*/
- goto out_put;
+ goto out_subsys_put;
}
/*
goto out_unlink;
}
- owner = type->ct_owner;
- if (!try_module_get(owner)) {
+ new_item_owner = type->ct_owner;
+ if (!try_module_get(new_item_owner)) {
ret = -EINVAL;
goto out_unlink;
}
spin_lock(&configfs_dirent_lock);
sd->s_type &= ~CONFIGFS_USET_IN_MKDIR;
+ if (!ret)
+ configfs_dir_set_ready(dentry->d_fsdata);
spin_unlock(&configfs_dirent_lock);
out_unlink:
mutex_unlock(&subsys->su_mutex);
if (module_got)
- module_put(owner);
+ module_put(new_item_owner);
}
+out_subsys_put:
+ if (ret)
+ module_put(subsys_owner);
+
out_put:
/*
* link_obj()/link_group() took a reference from child->parent,
struct config_item *item;
struct configfs_subsystem *subsys;
struct configfs_dirent *sd;
- struct module *owner = NULL;
+ struct module *subsys_owner = NULL, *dead_item_owner = NULL;
int ret;
if (dentry->d_parent == configfs_sb->s_root)
if (sd->s_type & CONFIGFS_USET_DEFAULT)
return -EPERM;
- /*
- * Here's where we check for dependents. We're protected by
- * i_mutex.
- */
- if (sd->s_dependent_count)
- return -EBUSY;
-
/* Get a working ref until we have the child */
parent_item = configfs_get_config_item(dentry->d_parent);
subsys = to_config_group(parent_item)->cg_subsys;
return -EINVAL;
}
+ /* configfs_mkdir() shouldn't have allowed this */
+ BUG_ON(!subsys->su_group.cg_item.ci_type);
+ subsys_owner = subsys->su_group.cg_item.ci_type->ct_owner;
+
/*
* Ensure that no racing symlink() will make detach_prep() fail while
* the new link is temporarily attached
*/
- mutex_lock(&configfs_symlink_mutex);
- spin_lock(&configfs_dirent_lock);
do {
struct mutex *wait_mutex;
- ret = configfs_detach_prep(dentry, &wait_mutex);
+ mutex_lock(&configfs_symlink_mutex);
+ spin_lock(&configfs_dirent_lock);
+ /*
+ * Here's where we check for dependents. We're protected by
+ * configfs_dirent_lock.
+ * If no dependent, atomically tag the item as dropping.
+ */
+ ret = sd->s_dependent_count ? -EBUSY : 0;
+ if (!ret) {
+ ret = configfs_detach_prep(dentry, &wait_mutex);
+ if (ret)
+ configfs_detach_rollback(dentry);
+ }
+ spin_unlock(&configfs_dirent_lock);
+ mutex_unlock(&configfs_symlink_mutex);
+
if (ret) {
- configfs_detach_rollback(dentry);
- spin_unlock(&configfs_dirent_lock);
- mutex_unlock(&configfs_symlink_mutex);
if (ret != -EAGAIN) {
config_item_put(parent_item);
return ret;
/* Wait until the racing operation terminates */
mutex_lock(wait_mutex);
mutex_unlock(wait_mutex);
-
- mutex_lock(&configfs_symlink_mutex);
- spin_lock(&configfs_dirent_lock);
}
} while (ret == -EAGAIN);
- spin_unlock(&configfs_dirent_lock);
- mutex_unlock(&configfs_symlink_mutex);
/* Get a working ref for the duration of this function */
item = configfs_get_config_item(dentry);
config_item_put(parent_item);
if (item->ci_type)
- owner = item->ci_type->ct_owner;
+ dead_item_owner = item->ci_type->ct_owner;
if (sd->s_type & CONFIGFS_USET_DIR) {
configfs_detach_group(item);
/* Drop our reference from above */
config_item_put(item);
- module_put(owner);
+ module_put(dead_item_owner);
+ module_put(subsys_owner);
return 0;
}
{
struct dentry * dentry = file->f_path.dentry;
struct configfs_dirent * parent_sd = dentry->d_fsdata;
+ int err;
mutex_lock(&dentry->d_inode->i_mutex);
- file->private_data = configfs_new_dirent(parent_sd, NULL);
+ /*
+ * Fake invisibility if dir belongs to a group/default groups hierarchy
+ * being attached
+ */
+ err = -ENOENT;
+ if (configfs_dirent_is_ready(parent_sd)) {
+ file->private_data = configfs_new_dirent(parent_sd, NULL, 0);
+ if (IS_ERR(file->private_data))
+ err = PTR_ERR(file->private_data);
+ else
+ err = 0;
+ }
mutex_unlock(&dentry->d_inode->i_mutex);
- return IS_ERR(file->private_data) ? PTR_ERR(file->private_data) : 0;
-
+ return err;
}
static int configfs_dir_close(struct inode *inode, struct file *file)
if (err) {
d_delete(dentry);
dput(dentry);
+ } else {
+ spin_lock(&configfs_dirent_lock);
+ configfs_dir_set_ready(dentry->d_fsdata);
+ spin_unlock(&configfs_dirent_lock);
}
}
mutex_unlock(&configfs_symlink_mutex);
configfs_detach_group(&group->cg_item);
dentry->d_inode->i_flags |= S_DEAD;
+ dont_mount(dentry);
mutex_unlock(&dentry->d_inode->i_mutex);
d_delete(dentry);