diff options
Diffstat (limited to 'fs/configfs')
| -rw-r--r-- | fs/configfs/Kconfig | 12 | ||||
| -rw-r--r-- | fs/configfs/Makefile | 8 | ||||
| -rw-r--r-- | fs/configfs/configfs_internal.h | 159 | ||||
| -rw-r--r-- | fs/configfs/dir.c | 1980 | ||||
| -rw-r--r-- | fs/configfs/file.c | 554 | ||||
| -rw-r--r-- | fs/configfs/inode.c | 251 | ||||
| -rw-r--r-- | fs/configfs/item.c | 192 | ||||
| -rw-r--r-- | fs/configfs/mount.c | 180 | ||||
| -rw-r--r-- | fs/configfs/symlink.c | 270 |
9 files changed, 3606 insertions, 0 deletions
diff --git a/fs/configfs/Kconfig b/fs/configfs/Kconfig new file mode 100644 index 000000000..272b64456 --- /dev/null +++ b/fs/configfs/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +config CONFIGFS_FS + tristate "Userspace-driven configuration filesystem" + select SYSFS + help + configfs is a RAM-based filesystem that provides the converse + of sysfs's functionality. Where sysfs is a filesystem-based + view of kernel objects, configfs is a filesystem-based manager + of kernel objects, or config_items. + + Both sysfs and configfs can and should exist together on the + same system. One is not a replacement for the other. diff --git a/fs/configfs/Makefile b/fs/configfs/Makefile new file mode 100644 index 000000000..0200498ed --- /dev/null +++ b/fs/configfs/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the configfs virtual filesystem +# + +obj-$(CONFIG_CONFIGFS_FS) += configfs.o + +configfs-objs := inode.o file.o dir.o symlink.o mount.o item.o diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h new file mode 100644 index 000000000..22dce2d35 --- /dev/null +++ b/fs/configfs/configfs_internal.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* -*- mode: c; c-basic-offset:8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * configfs_internal.h - Internal stuff for configfs + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + */ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/spinlock.h> + +struct configfs_fragment { + atomic_t frag_count; + struct rw_semaphore frag_sem; + bool frag_dead; +}; + +void put_fragment(struct configfs_fragment *); +struct configfs_fragment *get_fragment(struct configfs_fragment *); + +struct configfs_dirent { + atomic_t s_count; + int s_dependent_count; + struct list_head s_sibling; + struct list_head s_children; + int s_links; + void * s_element; + int s_type; + umode_t s_mode; + struct dentry * s_dentry; + struct iattr * s_iattr; +#ifdef CONFIG_LOCKDEP + int s_depth; +#endif + struct configfs_fragment *s_frag; +}; + +#define CONFIGFS_ROOT 0x0001 +#define CONFIGFS_DIR 0x0002 +#define CONFIGFS_ITEM_ATTR 0x0004 +#define CONFIGFS_ITEM_BIN_ATTR 0x0008 +#define CONFIGFS_ITEM_LINK 0x0020 +#define CONFIGFS_USET_DIR 0x0040 +#define CONFIGFS_USET_DEFAULT 0x0080 +#define CONFIGFS_USET_DROPPING 0x0100 +#define CONFIGFS_USET_IN_MKDIR 0x0200 +#define CONFIGFS_USET_CREATING 0x0400 +#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR) + +extern struct mutex configfs_symlink_mutex; +extern spinlock_t configfs_dirent_lock; + +extern struct kmem_cache *configfs_dir_cachep; + +extern int configfs_is_root(struct config_item *item); + +extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *); +extern struct inode *configfs_create(struct dentry *, umode_t mode); + +extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); +extern int configfs_create_bin_file(struct config_item *, + const struct configfs_bin_attribute *); +extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, + void *, umode_t, int, struct configfs_fragment *); +extern int configfs_dirent_is_ready(struct configfs_dirent *); + +extern void configfs_hash_and_remove(struct dentry * dir, const char * name); + +extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); +extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); +extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr); + +extern struct dentry *configfs_pin_fs(void); +extern void configfs_release_fs(void); + +extern const struct file_operations configfs_dir_operations; +extern const struct file_operations configfs_file_operations; +extern const struct file_operations configfs_bin_file_operations; +extern const struct inode_operations configfs_dir_inode_operations; +extern const struct inode_operations configfs_root_inode_operations; +extern const struct inode_operations configfs_symlink_inode_operations; +extern const struct dentry_operations configfs_dentry_ops; + +extern int configfs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname); +extern int configfs_unlink(struct inode *dir, struct dentry *dentry); + +int configfs_create_link(struct configfs_dirent *target, struct dentry *parent, + struct dentry *dentry, char *body); + +static inline struct config_item * to_item(struct dentry * dentry) +{ + struct configfs_dirent * sd = dentry->d_fsdata; + return ((struct config_item *) sd->s_element); +} + +static inline struct configfs_attribute * to_attr(struct dentry * dentry) +{ + struct configfs_dirent * sd = dentry->d_fsdata; + return ((struct configfs_attribute *) sd->s_element); +} + +static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry) +{ + struct configfs_attribute *attr = to_attr(dentry); + + return container_of(attr, struct configfs_bin_attribute, cb_attr); +} + +static inline struct config_item *configfs_get_config_item(struct dentry *dentry) +{ + struct config_item * item = NULL; + + spin_lock(&dentry->d_lock); + if (!d_unhashed(dentry)) { + struct configfs_dirent * sd = dentry->d_fsdata; + item = config_item_get(sd->s_element); + } + spin_unlock(&dentry->d_lock); + + return item; +} + +static inline void release_configfs_dirent(struct configfs_dirent * sd) +{ + if (!(sd->s_type & CONFIGFS_ROOT)) { + kfree(sd->s_iattr); + put_fragment(sd->s_frag); + kmem_cache_free(configfs_dir_cachep, sd); + } +} + +static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd) +{ + if (sd) { + WARN_ON(!atomic_read(&sd->s_count)); + atomic_inc(&sd->s_count); + } + return sd; +} + +static inline void configfs_put(struct configfs_dirent * sd) +{ + WARN_ON(!atomic_read(&sd->s_count)); + if (atomic_dec_and_test(&sd->s_count)) + release_configfs_dirent(sd); +} + diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c new file mode 100644 index 000000000..12388ed4f --- /dev/null +++ b/fs/configfs/dir.c @@ -0,0 +1,1980 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * dir.c - Operations for configfs directories. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + */ + +#undef DEBUG + +#include <linux/fs.h> +#include <linux/fsnotify.h> +#include <linux/mount.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/err.h> + +#include <linux/configfs.h> +#include "configfs_internal.h" + +/* + * Protects mutations of configfs_dirent linkage together with proper i_mutex + * Also protects mutations of symlinks linkage to target configfs_dirent + * Mutators of configfs_dirent linkage must *both* have the proper inode locked + * and configfs_dirent_lock locked, in that order. + * This allows one to safely traverse configfs_dirent trees and symlinks without + * having to lock inodes. + * + * Protects setting of CONFIGFS_USET_DROPPING: checking the flag + * unlocked is not reliable unless in detach_groups() called from + * rmdir()/unregister() and from configfs_attach_group() + */ +DEFINE_SPINLOCK(configfs_dirent_lock); + +/* + * All of link_obj/unlink_obj/link_group/unlink_group require that + * subsys->su_mutex is held. + * But parent configfs_subsystem is NULL when config_item is root. + * Use this mutex when config_item is root. + */ +static DEFINE_MUTEX(configfs_subsystem_mutex); + +static void configfs_d_iput(struct dentry * dentry, + struct inode * inode) +{ + struct configfs_dirent *sd = dentry->d_fsdata; + + if (sd) { + /* Coordinate with configfs_readdir */ + spin_lock(&configfs_dirent_lock); + /* + * Set sd->s_dentry to null only when this dentry is the one + * that is going to be killed. Otherwise configfs_d_iput may + * run just after configfs_attach_attr and set sd->s_dentry to + * NULL even it's still in use. + */ + if (sd->s_dentry == dentry) + sd->s_dentry = NULL; + + spin_unlock(&configfs_dirent_lock); + configfs_put(sd); + } + iput(inode); +} + +const struct dentry_operations configfs_dentry_ops = { + .d_iput = configfs_d_iput, + .d_delete = always_delete_dentry, +}; + +#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 */ + +static struct configfs_fragment *new_fragment(void) +{ + struct configfs_fragment *p; + + p = kmalloc(sizeof(struct configfs_fragment), GFP_KERNEL); + if (p) { + atomic_set(&p->frag_count, 1); + init_rwsem(&p->frag_sem); + p->frag_dead = false; + } + return p; +} + +void put_fragment(struct configfs_fragment *frag) +{ + if (frag && atomic_dec_and_test(&frag->frag_count)) + kfree(frag); +} + +struct configfs_fragment *get_fragment(struct configfs_fragment *frag) +{ + if (likely(frag)) + atomic_inc(&frag->frag_count); + return frag; +} + +/* + * 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, int type, + struct configfs_fragment *frag) +{ + struct configfs_dirent * sd; + + sd = kmem_cache_zalloc(configfs_dir_cachep, GFP_KERNEL); + if (!sd) + return ERR_PTR(-ENOMEM); + + atomic_set(&sd->s_count, 1); + 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); + kmem_cache_free(configfs_dir_cachep, sd); + return ERR_PTR(-ENOENT); + } + sd->s_frag = get_fragment(frag); + list_add(&sd->s_sibling, &parent_sd->s_children); + spin_unlock(&configfs_dirent_lock); + + return sd; +} + +/* + * + * Return -EEXIST if there is already a configfs element with the same + * name for the same parent. + * + * called with parent inode's i_mutex held + */ +static int configfs_dirent_exists(struct configfs_dirent *parent_sd, + const unsigned char *new) +{ + struct configfs_dirent * sd; + + list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { + if (sd->s_element) { + const unsigned char *existing = configfs_get_name(sd); + if (strcmp(existing, new)) + continue; + else + return -EEXIST; + } + } + + return 0; +} + + +int configfs_make_dirent(struct configfs_dirent * parent_sd, + struct dentry * dentry, void * element, + umode_t mode, int type, struct configfs_fragment *frag) +{ + struct configfs_dirent * sd; + + sd = configfs_new_dirent(parent_sd, element, type, frag); + if (IS_ERR(sd)) + return PTR_ERR(sd); + + sd->s_mode = mode; + sd->s_dentry = dentry; + if (dentry) + dentry->d_fsdata = configfs_get(sd); + + return 0; +} + +static void configfs_remove_dirent(struct dentry *dentry) +{ + struct configfs_dirent *sd = dentry->d_fsdata; + + if (!sd) + return; + spin_lock(&configfs_dirent_lock); + list_del_init(&sd->s_sibling); + spin_unlock(&configfs_dirent_lock); + configfs_put(sd); +} + +/** + * 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, + struct configfs_fragment *frag) +{ + int error; + umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; + struct dentry *p = dentry->d_parent; + struct inode *inode; + + BUG_ON(!item); + + error = configfs_dirent_exists(p->d_fsdata, dentry->d_name.name); + if (unlikely(error)) + return error; + + error = configfs_make_dirent(p->d_fsdata, dentry, item, mode, + CONFIGFS_DIR | CONFIGFS_USET_CREATING, + frag); + if (unlikely(error)) + return error; + + configfs_set_dir_dirent_depth(p->d_fsdata, dentry->d_fsdata); + inode = configfs_create(dentry, mode); + if (IS_ERR(inode)) + goto out_remove; + + inode->i_op = &configfs_dir_inode_operations; + inode->i_fop = &configfs_dir_operations; + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + d_instantiate(dentry, inode); + /* already hashed */ + dget(dentry); /* pin directory dentries in core */ + inc_nlink(d_inode(p)); + item->ci_dentry = dentry; + return 0; + +out_remove: + configfs_put(dentry->d_fsdata); + configfs_remove_dirent(dentry); + return PTR_ERR(inode); +} + +/* + * 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_dirent *target, struct dentry *parent, + struct dentry *dentry, char *body) +{ + int err = 0; + umode_t mode = S_IFLNK | S_IRWXUGO; + struct configfs_dirent *p = parent->d_fsdata; + struct inode *inode; + + err = configfs_make_dirent(p, dentry, target, mode, CONFIGFS_ITEM_LINK, + p->s_frag); + if (err) + return err; + + inode = configfs_create(dentry, mode); + if (IS_ERR(inode)) + goto out_remove; + + inode->i_link = body; + inode->i_op = &configfs_symlink_inode_operations; + d_instantiate(dentry, inode); + dget(dentry); /* pin link dentries in core */ + return 0; + +out_remove: + configfs_put(dentry->d_fsdata); + configfs_remove_dirent(dentry); + return PTR_ERR(inode); +} + +static void remove_dir(struct dentry * d) +{ + struct dentry * parent = dget(d->d_parent); + + configfs_remove_dirent(d); + + if (d_really_is_positive(d)) + simple_rmdir(d_inode(parent),d); + + pr_debug(" o %pd removing done (%d)\n", d, d_count(d)); + + dput(parent); +} + +/** + * configfs_remove_dir - remove an config_item's directory. + * @item: config_item we're removing. + * + * 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 dentry * dentry = dget(item->ci_dentry); + + if (!dentry) + return; + + remove_dir(dentry); + /** + * Drop reference from dget() on entrance. + */ + dput(dentry); +} + + +/* attaches attribute's configfs_dirent to the dentry corresponding to the + * attribute file + */ +static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * dentry) +{ + struct configfs_attribute * attr = sd->s_element; + struct inode *inode; + + spin_lock(&configfs_dirent_lock); + dentry->d_fsdata = configfs_get(sd); + sd->s_dentry = dentry; + spin_unlock(&configfs_dirent_lock); + + inode = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG); + if (IS_ERR(inode)) { + configfs_put(sd); + return PTR_ERR(inode); + } + if (sd->s_type & CONFIGFS_ITEM_BIN_ATTR) { + inode->i_size = 0; + inode->i_fop = &configfs_bin_file_operations; + } else { + inode->i_size = PAGE_SIZE; + inode->i_fop = &configfs_file_operations; + } + d_add(dentry, inode); + return 0; +} + +static struct dentry * configfs_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags) +{ + struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata; + struct configfs_dirent * sd; + int found = 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) { + const unsigned char * name = configfs_get_name(sd); + + if (strcmp(name, dentry->d_name.name)) + continue; + + found = 1; + err = configfs_attach_attr(sd, dentry); + break; + } + } + + if (!found) { + /* + * If it doesn't exist and it isn't a NOT_PINNED item, + * it must be negative. + */ + if (dentry->d_name.len > NAME_MAX) + return ERR_PTR(-ENAMETOOLONG); + d_add(dentry, NULL); + return NULL; + } + +out: + return ERR_PTR(err); +} + +/* + * Only subdirectories count here. Files (CONFIGFS_NOT_PINNED) are + * attributes and are removed by rmdir(). We recurse, setting + * CONFIGFS_USET_DROPPING on all children that are candidates for + * default detach. + * If there is an error, the caller will reset the flags via + * configfs_detach_rollback(). + */ +static int configfs_detach_prep(struct dentry *dentry, struct dentry **wait) +{ + struct configfs_dirent *parent_sd = dentry->d_fsdata; + struct configfs_dirent *sd; + int ret; + + /* Mark that we're trying to drop the group */ + parent_sd->s_type |= CONFIGFS_USET_DROPPING; + + ret = -EBUSY; + if (parent_sd->s_links) + goto out; + + ret = 0; + list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { + if (!sd->s_element || + (sd->s_type & CONFIGFS_NOT_PINNED)) + continue; + if (sd->s_type & CONFIGFS_USET_DEFAULT) { + /* Abort if racing with mkdir() */ + if (sd->s_type & CONFIGFS_USET_IN_MKDIR) { + if (wait) + *wait= dget(sd->s_dentry); + return -EAGAIN; + } + + /* + * Yup, recursive. If there's a problem, blame + * deep nesting of default_groups + */ + ret = configfs_detach_prep(sd->s_dentry, wait); + if (!ret) + continue; + } else + ret = -ENOTEMPTY; + + break; + } + +out: + return ret; +} + +/* + * Walk the tree, resetting CONFIGFS_USET_DROPPING wherever it was + * set. + */ +static void configfs_detach_rollback(struct dentry *dentry) +{ + struct configfs_dirent *parent_sd = dentry->d_fsdata; + struct configfs_dirent *sd; + + parent_sd->s_type &= ~CONFIGFS_USET_DROPPING; + + list_for_each_entry(sd, &parent_sd->s_children, s_sibling) + if (sd->s_type & CONFIGFS_USET_DEFAULT) + configfs_detach_rollback(sd->s_dentry); +} + +static void detach_attrs(struct config_item * item) +{ + struct dentry * dentry = dget(item->ci_dentry); + struct configfs_dirent * parent_sd; + struct configfs_dirent * sd, * tmp; + + if (!dentry) + return; + + pr_debug("configfs %s: dropping attrs for dir\n", + dentry->d_name.name); + + parent_sd = dentry->d_fsdata; + list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) { + if (!sd->s_element || !(sd->s_type & CONFIGFS_NOT_PINNED)) + continue; + spin_lock(&configfs_dirent_lock); + list_del_init(&sd->s_sibling); + spin_unlock(&configfs_dirent_lock); + configfs_drop_dentry(sd, dentry); + configfs_put(sd); + } + + /** + * Drop reference from dget() on entrance. + */ + dput(dentry); +} + +static int populate_attrs(struct config_item *item) +{ + const struct config_item_type *t = item->ci_type; + struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; + int error = 0; + int i; + + if (!t) + return -EINVAL; + if (t->ct_attrs) { + for (i = 0; (attr = t->ct_attrs[i]) != NULL; i++) { + if ((error = configfs_create_file(item, attr))) + break; + } + } + if (t->ct_bin_attrs) { + for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) { + error = configfs_create_bin_file(item, bin_attr); + if (error) + break; + } + } + + if (error) + detach_attrs(item); + + return error; +} + +static int configfs_attach_group(struct config_item *parent_item, + struct config_item *item, + struct dentry *dentry, + struct configfs_fragment *frag); +static void configfs_detach_group(struct config_item *item); + +static void detach_groups(struct config_group *group) +{ + struct dentry * dentry = dget(group->cg_item.ci_dentry); + struct dentry *child; + struct configfs_dirent *parent_sd; + struct configfs_dirent *sd, *tmp; + + if (!dentry) + return; + + parent_sd = dentry->d_fsdata; + list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) { + if (!sd->s_element || + !(sd->s_type & CONFIGFS_USET_DEFAULT)) + continue; + + child = sd->s_dentry; + + inode_lock(d_inode(child)); + + configfs_detach_group(sd->s_element); + d_inode(child)->i_flags |= S_DEAD; + dont_mount(child); + + inode_unlock(d_inode(child)); + + d_delete(child); + dput(child); + } + + /** + * Drop reference from dget() on entrance. + */ + dput(dentry); +} + +/* + * This fakes mkdir(2) on a default_groups[] entry. It + * creates a dentry, attachs it, and then does fixup + * on the sd->s_type. + * + * We could, perhaps, tweak our parent's ->mkdir for a minute and + * try using vfs_mkdir. Just a thought. + */ +static int create_default_group(struct config_group *parent_group, + struct config_group *group, + struct configfs_fragment *frag) +{ + int ret; + struct configfs_dirent *sd; + /* We trust the caller holds a reference to parent */ + struct dentry *child, *parent = parent_group->cg_item.ci_dentry; + + if (!group->cg_item.ci_name) + group->cg_item.ci_name = group->cg_item.ci_namebuf; + + ret = -ENOMEM; + child = d_alloc_name(parent, group->cg_item.ci_name); + if (child) { + d_add(child, NULL); + + ret = configfs_attach_group(&parent_group->cg_item, + &group->cg_item, child, frag); + if (!ret) { + sd = child->d_fsdata; + sd->s_type |= CONFIGFS_USET_DEFAULT; + } else { + BUG_ON(d_inode(child)); + d_drop(child); + dput(child); + } + } + + return ret; +} + +static int populate_groups(struct config_group *group, + struct configfs_fragment *frag) +{ + struct config_group *new_group; + int ret = 0; + + list_for_each_entry(new_group, &group->default_groups, group_entry) { + ret = create_default_group(group, new_group, frag); + if (ret) { + detach_groups(group); + break; + } + } + + return ret; +} + +void configfs_remove_default_groups(struct config_group *group) +{ + struct config_group *g, *n; + + list_for_each_entry_safe(g, n, &group->default_groups, group_entry) { + list_del(&g->group_entry); + config_item_put(&g->cg_item); + } +} +EXPORT_SYMBOL(configfs_remove_default_groups); + +/* + * All of link_obj/unlink_obj/link_group/unlink_group require that + * subsys->su_mutex is held. + */ + +static void unlink_obj(struct config_item *item) +{ + struct config_group *group; + + group = item->ci_group; + if (group) { + list_del_init(&item->ci_entry); + + item->ci_group = NULL; + item->ci_parent = NULL; + + /* Drop the reference for ci_entry */ + config_item_put(item); + + /* Drop the reference for ci_parent */ + config_group_put(group); + } +} + +static void link_obj(struct config_item *parent_item, struct config_item *item) +{ + /* + * Parent seems redundant with group, but it makes certain + * traversals much nicer. + */ + item->ci_parent = parent_item; + + /* + * We hold a reference on the parent for the child's ci_parent + * link. + */ + item->ci_group = config_group_get(to_config_group(parent_item)); + list_add_tail(&item->ci_entry, &item->ci_group->cg_children); + + /* + * We hold a reference on the child for ci_entry on the parent's + * cg_children + */ + config_item_get(item); +} + +static void unlink_group(struct config_group *group) +{ + struct config_group *new_group; + + list_for_each_entry(new_group, &group->default_groups, group_entry) + unlink_group(new_group); + + group->cg_subsys = NULL; + unlink_obj(&group->cg_item); +} + +static void link_group(struct config_group *parent_group, struct config_group *group) +{ + struct config_group *new_group; + struct configfs_subsystem *subsys = NULL; /* gcc is a turd */ + + link_obj(&parent_group->cg_item, &group->cg_item); + + if (parent_group->cg_subsys) + subsys = parent_group->cg_subsys; + else if (configfs_is_root(&parent_group->cg_item)) + subsys = to_configfs_subsystem(group); + else + BUG(); + group->cg_subsys = subsys; + + list_for_each_entry(new_group, &group->default_groups, group_entry) + link_group(group, new_group); +} + +/* + * The goal is that configfs_attach_item() (and + * configfs_attach_group()) can be called from either the VFS or this + * module. That is, they assume that the items have been created, + * the dentry allocated, and the dcache is all ready to go. + * + * If they fail, they must clean up after themselves as if they + * had never been called. The caller (VFS or local function) will + * handle cleaning up the dcache bits. + * + * configfs_detach_group() and configfs_detach_item() behave similarly on + * the way out. They assume that the proper semaphores are held, they + * clean up the configfs items, and they expect their callers will + * handle the dcache bits. + */ +static int configfs_attach_item(struct config_item *parent_item, + struct config_item *item, + struct dentry *dentry, + struct configfs_fragment *frag) +{ + int ret; + + ret = configfs_create_dir(item, dentry, frag); + 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. + */ + inode_lock(d_inode(dentry)); + configfs_remove_dir(item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + inode_unlock(d_inode(dentry)); + 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); + configfs_remove_dir(item); +} + +static int configfs_attach_group(struct config_item *parent_item, + struct config_item *item, + struct dentry *dentry, + struct configfs_fragment *frag) +{ + int ret; + struct configfs_dirent *sd; + + ret = configfs_attach_item(parent_item, item, dentry, frag); + if (!ret) { + 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. + */ + inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); + configfs_adjust_dir_dirent_depth_before_populate(sd); + ret = populate_groups(to_config_group(item), frag); + if (ret) { + configfs_detach_item(item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + } + configfs_adjust_dir_dirent_depth_after_populate(sd); + inode_unlock(d_inode(dentry)); + 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)); + configfs_detach_item(item); +} + +/* + * After the item has been detached from the filesystem view, we are + * ready to tear it out of the hierarchy. Notify the client before + * we do that so they can perform any cleanup that requires + * navigating the hierarchy. A client does not need to provide this + * callback. The subsystem semaphore MUST be held by the caller, and + * references must be valid for both items. It also assumes the + * caller has validated ci_type. + */ +static void client_disconnect_notify(struct config_item *parent_item, + struct config_item *item) +{ + const struct config_item_type *type; + + type = parent_item->ci_type; + BUG_ON(!type); + + if (type->ct_group_ops && type->ct_group_ops->disconnect_notify) + type->ct_group_ops->disconnect_notify(to_config_group(parent_item), + item); +} + +/* + * Drop the initial reference from make_item()/make_group() + * This function assumes that reference is held on item + * and that item holds a valid reference to the parent. Also, it + * assumes the caller has validated ci_type. + */ +static void client_drop_item(struct config_item *parent_item, + struct config_item *item) +{ + const struct config_item_type *type; + + type = parent_item->ci_type; + BUG_ON(!type); + + /* + * If ->drop_item() exists, it is responsible for the + * config_item_put(). + */ + if (type->ct_group_ops && type->ct_group_ops->drop_item) + type->ct_group_ops->drop_item(to_config_group(parent_item), + item); + else + config_item_put(item); +} + +#ifdef DEBUG +static void configfs_dump_one(struct configfs_dirent *sd, int level) +{ + pr_info("%*s\"%s\":\n", level, " ", configfs_get_name(sd)); + +#define type_print(_type) if (sd->s_type & _type) pr_info("%*s %s\n", level, " ", #_type); + type_print(CONFIGFS_ROOT); + type_print(CONFIGFS_DIR); + type_print(CONFIGFS_ITEM_ATTR); + type_print(CONFIGFS_ITEM_LINK); + type_print(CONFIGFS_USET_DIR); + type_print(CONFIGFS_USET_DEFAULT); + type_print(CONFIGFS_USET_DROPPING); +#undef type_print +} + +static int configfs_dump(struct configfs_dirent *sd, int level) +{ + struct configfs_dirent *child_sd; + int ret = 0; + + configfs_dump_one(sd, level); + + if (!(sd->s_type & (CONFIGFS_DIR|CONFIGFS_ROOT))) + return 0; + + list_for_each_entry(child_sd, &sd->s_children, s_sibling) { + ret = configfs_dump(child_sd, level + 2); + if (ret) + break; + } + + return ret; +} +#endif + + +/* + * configfs_depend_item() and configfs_undepend_item() + * + * WARNING: Do not call these from a configfs callback! + * + * This describes these functions and their helpers. + * + * Allow another kernel system to depend on a config_item. If this + * happens, the item cannot go away until the dependent can live without + * it. The idea is to give client modules as simple an interface as + * possible. When a system asks them to depend on an item, they just + * call configfs_depend_item(). If the item is live and the client + * driver is in good shape, we'll happily do the work for them. + * + * Why is the locking complex? Because configfs uses the VFS to handle + * all locking, but this function is called outside the normal + * VFS->configfs path. So it must take VFS locks to prevent the + * VFS->configfs stuff (configfs_mkdir(), configfs_rmdir(), etc). This is + * why you can't call these functions underneath configfs callbacks. + * + * 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 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 configfs_dirent_lock helps + * locking out mkdir() and rmdir(), who might be racing us. + */ + +/* + * configfs_depend_prep() + * + * Only subdirectories count here. Files (CONFIGFS_NOT_PINNED) are + * attributes. This is similar but not the same to configfs_detach_prep(). + * Note that configfs_detach_prep() expects the parent to be locked when it + * is called, but we lock the parent *inside* configfs_depend_prep(). We + * 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 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. + * + * This adds a requirement that all config_items be unique! + * + * 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. + */ +static int configfs_depend_prep(struct dentry *origin, + struct config_item *target) +{ + struct configfs_dirent *child_sd, *sd; + int ret = 0; + + BUG_ON(!origin || !origin->d_fsdata); + sd = origin->d_fsdata; + + 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) && + !(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) + goto out; /* Child path boo-yah */ + } + } + + /* We looped all our children and didn't find target */ + ret = -ENOENT; + +out: + return ret; +} + +static int configfs_do_depend_item(struct dentry *subsys_dentry, + struct config_item *target) +{ + struct configfs_dirent *p; + int ret; + + spin_lock(&configfs_dirent_lock); + /* Scan the tree, return 0 if found */ + ret = configfs_depend_prep(subsys_dentry, target); + if (ret) + goto out_unlock_dirent_lock; + + /* + * 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; + +out_unlock_dirent_lock: + spin_unlock(&configfs_dirent_lock); + + return ret; +} + +static inline struct configfs_dirent * +configfs_find_subsys_dentry(struct configfs_dirent *root_sd, + struct config_item *subsys_item) +{ + struct configfs_dirent *p; + struct configfs_dirent *ret = NULL; + + list_for_each_entry(p, &root_sd->s_children, s_sibling) { + if (p->s_type & CONFIGFS_DIR && + p->s_element == subsys_item) { + ret = p; + break; + } + } + + return ret; +} + + +int configfs_depend_item(struct configfs_subsystem *subsys, + struct config_item *target) +{ + int ret; + struct configfs_dirent *subsys_sd; + struct config_item *s_item = &subsys->su_group.cg_item; + struct dentry *root; + + /* + * Pin the configfs filesystem. This means we can safely access + * the root of the configfs filesystem. + */ + root = configfs_pin_fs(); + if (IS_ERR(root)) + return PTR_ERR(root); + + /* + * Next, lock the root directory. We're going to check that the + * subsystem is really registered, and so we need to lock out + * configfs_[un]register_subsystem(). + */ + inode_lock(d_inode(root)); + + subsys_sd = configfs_find_subsys_dentry(root->d_fsdata, s_item); + if (!subsys_sd) { + ret = -ENOENT; + goto out_unlock_fs; + } + + /* Ok, now we can trust subsys/s_item */ + ret = configfs_do_depend_item(subsys_sd->s_dentry, target); + +out_unlock_fs: + inode_unlock(d_inode(root)); + + /* + * If we succeeded, the fs is pinned via other methods. If not, + * we're done with it anyway. So release_fs() is always right. + */ + configfs_release_fs(); + + return ret; +} +EXPORT_SYMBOL(configfs_depend_item); + +/* + * Release the dependent linkage. This is much simpler than + * configfs_depend_item() because we know that the client driver is + * pinned, thus the subsystem is pinned, and therefore configfs is pinned. + */ +void configfs_undepend_item(struct config_item *target) +{ + struct configfs_dirent *sd; + + /* + * Since we can trust everything is pinned, we just need + * configfs_dirent_lock. + */ + spin_lock(&configfs_dirent_lock); + + sd = target->ci_dentry->d_fsdata; + BUG_ON(sd->s_dependent_count < 1); + + sd->s_dependent_count -= 1; + + /* + * After this unlock, we cannot trust the item to stay alive! + * DO NOT REFERENCE item after this unlock. + */ + spin_unlock(&configfs_dirent_lock); +} +EXPORT_SYMBOL(configfs_undepend_item); + +/* + * caller_subsys is a caller's subsystem not target's. This is used to + * determine if we should lock root and check subsys or not. When we are + * in the same subsystem as our target there is no need to do locking as + * we know that subsys is valid and is not unregistered during this function + * as we are called from callback of one of his children and VFS holds a lock + * on some inode. Otherwise we have to lock our root to ensure that target's + * subsystem it is not unregistered during this function. + */ +int configfs_depend_item_unlocked(struct configfs_subsystem *caller_subsys, + struct config_item *target) +{ + struct configfs_subsystem *target_subsys; + struct config_group *root, *parent; + struct configfs_dirent *subsys_sd; + int ret = -ENOENT; + + /* Disallow this function for configfs root */ + if (configfs_is_root(target)) + return -EINVAL; + + parent = target->ci_group; + /* + * This may happen when someone is trying to depend root + * directory of some subsystem + */ + if (configfs_is_root(&parent->cg_item)) { + target_subsys = to_configfs_subsystem(to_config_group(target)); + root = parent; + } else { + target_subsys = parent->cg_subsys; + /* Find a cofnigfs root as we may need it for locking */ + for (root = parent; !configfs_is_root(&root->cg_item); + root = root->cg_item.ci_group) + ; + } + + if (target_subsys != caller_subsys) { + /* + * We are in other configfs subsystem, so we have to do + * additional locking to prevent other subsystem from being + * unregistered + */ + inode_lock(d_inode(root->cg_item.ci_dentry)); + + /* + * As we are trying to depend item from other subsystem + * we have to check if this subsystem is still registered + */ + subsys_sd = configfs_find_subsys_dentry( + root->cg_item.ci_dentry->d_fsdata, + &target_subsys->su_group.cg_item); + if (!subsys_sd) + goto out_root_unlock; + } else { + subsys_sd = target_subsys->su_group.cg_item.ci_dentry->d_fsdata; + } + + /* Now we can execute core of depend item */ + ret = configfs_do_depend_item(subsys_sd->s_dentry, target); + + if (target_subsys != caller_subsys) +out_root_unlock: + /* + * We were called from subsystem other than our target so we + * took some locks so now it's time to release them + */ + inode_unlock(d_inode(root->cg_item.ci_dentry)); + + return ret; +} +EXPORT_SYMBOL(configfs_depend_item_unlocked); + +static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int ret = 0; + int module_got = 0; + struct config_group *group = NULL; + struct config_item *item = NULL; + struct config_item *parent_item; + struct configfs_subsystem *subsys; + struct configfs_dirent *sd; + const struct config_item_type *type; + struct module *subsys_owner = NULL, *new_item_owner = NULL; + struct configfs_fragment *frag; + char *name; + + 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; + } + + frag = new_fragment(); + if (!frag) { + ret = -ENOMEM; + goto out; + } + + /* Get a working ref for the duration of this function */ + parent_item = configfs_get_config_item(dentry->d_parent); + type = parent_item->ci_type; + subsys = to_config_group(parent_item)->cg_subsys; + BUG_ON(!subsys); + + if (!type || !type->ct_group_ops || + (!type->ct_group_ops->make_group && + !type->ct_group_ops->make_item)) { + ret = -EPERM; /* Lack-of-mkdir returns -EPERM */ + 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_subsys_put; + } + + snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name); + + mutex_lock(&subsys->su_mutex); + if (type->ct_group_ops->make_group) { + group = type->ct_group_ops->make_group(to_config_group(parent_item), name); + if (!group) + group = ERR_PTR(-ENOMEM); + if (!IS_ERR(group)) { + link_group(to_config_group(parent_item), group); + item = &group->cg_item; + } else + ret = PTR_ERR(group); + } else { + item = type->ct_group_ops->make_item(to_config_group(parent_item), name); + if (!item) + item = ERR_PTR(-ENOMEM); + if (!IS_ERR(item)) + link_obj(parent_item, item); + else + ret = PTR_ERR(item); + } + mutex_unlock(&subsys->su_mutex); + + kfree(name); + if (ret) { + /* + * If ret != 0, then link_obj() was never called. + * There are no extra references to clean up. + */ + goto out_subsys_put; + } + + /* + * link_obj() has been called (via link_group() for groups). + * From here on out, errors must clean that up. + */ + + type = item->ci_type; + if (!type) { + ret = -EINVAL; + goto out_unlink; + } + + new_item_owner = type->ct_owner; + if (!try_module_get(new_item_owner)) { + ret = -EINVAL; + goto out_unlink; + } + + /* + * I hate doing it this way, but if there is + * an error, module_put() probably should + * happen after any cleanup. + */ + module_got = 1; + + /* + * Make racing rmdir() fail if it did not tag parent with + * CONFIGFS_USET_DROPPING + * Note: if CONFIGFS_USET_DROPPING is already set, attach_group() will + * fail and let rmdir() terminate correctly + */ + spin_lock(&configfs_dirent_lock); + /* This will make configfs_detach_prep() fail */ + sd->s_type |= CONFIGFS_USET_IN_MKDIR; + spin_unlock(&configfs_dirent_lock); + + if (group) + ret = configfs_attach_group(parent_item, item, dentry, frag); + else + ret = configfs_attach_item(parent_item, item, dentry, frag); + + 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: + if (ret) { + /* Tear down everything we built up */ + mutex_lock(&subsys->su_mutex); + + client_disconnect_notify(parent_item, item); + if (group) + unlink_group(group); + else + unlink_obj(item); + client_drop_item(parent_item, item); + + mutex_unlock(&subsys->su_mutex); + + if (module_got) + 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, + * so the parent is safely pinned. We can drop our working + * reference. + */ + config_item_put(parent_item); + put_fragment(frag); + +out: + return ret; +} + +static int configfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct config_item *parent_item; + struct config_item *item; + struct configfs_subsystem *subsys; + struct configfs_dirent *sd; + struct configfs_fragment *frag; + struct module *subsys_owner = NULL, *dead_item_owner = NULL; + int ret; + + sd = dentry->d_fsdata; + if (sd->s_type & CONFIGFS_USET_DEFAULT) + return -EPERM; + + /* 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; + BUG_ON(!subsys); + + if (!parent_item->ci_type) { + config_item_put(parent_item); + 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 + */ + do { + struct dentry *wait; + + 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); + if (ret) + configfs_detach_rollback(dentry); + } + spin_unlock(&configfs_dirent_lock); + mutex_unlock(&configfs_symlink_mutex); + + if (ret) { + if (ret != -EAGAIN) { + config_item_put(parent_item); + return ret; + } + + /* Wait until the racing operation terminates */ + inode_lock(d_inode(wait)); + inode_unlock(d_inode(wait)); + dput(wait); + } + } while (ret == -EAGAIN); + + frag = sd->s_frag; + if (down_write_killable(&frag->frag_sem)) { + spin_lock(&configfs_dirent_lock); + configfs_detach_rollback(dentry); + spin_unlock(&configfs_dirent_lock); + config_item_put(parent_item); + return -EINTR; + } + frag->frag_dead = true; + up_write(&frag->frag_sem); + + /* Get a working ref for the duration of this function */ + item = configfs_get_config_item(dentry); + + /* Drop reference from above, item already holds one. */ + config_item_put(parent_item); + + if (item->ci_type) + dead_item_owner = item->ci_type->ct_owner; + + if (sd->s_type & CONFIGFS_USET_DIR) { + configfs_detach_group(item); + + mutex_lock(&subsys->su_mutex); + client_disconnect_notify(parent_item, item); + unlink_group(to_config_group(item)); + } else { + configfs_detach_item(item); + + mutex_lock(&subsys->su_mutex); + client_disconnect_notify(parent_item, item); + unlink_obj(item); + } + + client_drop_item(parent_item, item); + mutex_unlock(&subsys->su_mutex); + + /* Drop our reference from above */ + config_item_put(item); + + module_put(dead_item_owner); + module_put(subsys_owner); + + return 0; +} + +const struct inode_operations configfs_dir_inode_operations = { + .mkdir = configfs_mkdir, + .rmdir = configfs_rmdir, + .symlink = configfs_symlink, + .unlink = configfs_unlink, + .lookup = configfs_lookup, + .setattr = configfs_setattr, +}; + +const struct inode_operations configfs_root_inode_operations = { + .lookup = configfs_lookup, + .setattr = configfs_setattr, +}; + +static int configfs_dir_open(struct inode *inode, struct file *file) +{ + struct dentry * dentry = file->f_path.dentry; + struct configfs_dirent * parent_sd = dentry->d_fsdata; + int err; + + inode_lock(d_inode(dentry)); + /* + * 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, NULL); + if (IS_ERR(file->private_data)) + err = PTR_ERR(file->private_data); + else + err = 0; + } + inode_unlock(d_inode(dentry)); + + return err; +} + +static int configfs_dir_close(struct inode *inode, struct file *file) +{ + struct dentry * dentry = file->f_path.dentry; + struct configfs_dirent * cursor = file->private_data; + + inode_lock(d_inode(dentry)); + spin_lock(&configfs_dirent_lock); + list_del_init(&cursor->s_sibling); + spin_unlock(&configfs_dirent_lock); + inode_unlock(d_inode(dentry)); + + release_configfs_dirent(cursor); + + return 0; +} + +/* Relationship between s_mode and the DT_xxx types */ +static inline unsigned char dt_type(struct configfs_dirent *sd) +{ + return (sd->s_mode >> 12) & 15; +} + +static int configfs_readdir(struct file *file, struct dir_context *ctx) +{ + struct dentry *dentry = file->f_path.dentry; + struct super_block *sb = dentry->d_sb; + struct configfs_dirent * parent_sd = dentry->d_fsdata; + struct configfs_dirent *cursor = file->private_data; + struct list_head *p, *q = &cursor->s_sibling; + ino_t ino = 0; + + if (!dir_emit_dots(file, ctx)) + return 0; + spin_lock(&configfs_dirent_lock); + if (ctx->pos == 2) + list_move(q, &parent_sd->s_children); + for (p = q->next; p != &parent_sd->s_children; p = p->next) { + struct configfs_dirent *next; + const char *name; + int len; + struct inode *inode = NULL; + + next = list_entry(p, struct configfs_dirent, s_sibling); + if (!next->s_element) + continue; + + /* + * We'll have a dentry and an inode for + * PINNED items and for open attribute + * files. We lock here to prevent a race + * with configfs_d_iput() clearing + * s_dentry before calling iput(). + * + * Why do we go to the trouble? If + * someone has an attribute file open, + * the inode number should match until + * they close it. Beyond that, we don't + * care. + */ + dentry = next->s_dentry; + if (dentry) + inode = d_inode(dentry); + if (inode) + ino = inode->i_ino; + spin_unlock(&configfs_dirent_lock); + if (!inode) + ino = iunique(sb, 2); + + name = configfs_get_name(next); + len = strlen(name); + + if (!dir_emit(ctx, name, len, ino, dt_type(next))) + return 0; + + spin_lock(&configfs_dirent_lock); + list_move(q, p); + p = q; + ctx->pos++; + } + spin_unlock(&configfs_dirent_lock); + return 0; +} + +static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) +{ + struct dentry * dentry = file->f_path.dentry; + + switch (whence) { + case 1: + offset += file->f_pos; + fallthrough; + case 0: + if (offset >= 0) + break; + fallthrough; + default: + return -EINVAL; + } + if (offset != file->f_pos) { + file->f_pos = offset; + if (file->f_pos >= 2) { + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_dirent *cursor = file->private_data; + struct list_head *p; + loff_t n = file->f_pos - 2; + + spin_lock(&configfs_dirent_lock); + list_del(&cursor->s_sibling); + p = sd->s_children.next; + while (n && p != &sd->s_children) { + struct configfs_dirent *next; + next = list_entry(p, struct configfs_dirent, + s_sibling); + if (next->s_element) + n--; + p = p->next; + } + list_add_tail(&cursor->s_sibling, p); + spin_unlock(&configfs_dirent_lock); + } + } + return offset; +} + +const struct file_operations configfs_dir_operations = { + .open = configfs_dir_open, + .release = configfs_dir_close, + .llseek = configfs_dir_lseek, + .read = generic_read_dir, + .iterate_shared = configfs_readdir, +}; + +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + struct configfs_fragment *frag; + int ret; + + frag = new_fragment(); + if (!frag) + return -ENOMEM; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); + ret = create_default_group(parent_group, group, frag); + if (ret) + goto err_out; + + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + inode_unlock(d_inode(parent)); + put_fragment(frag); + return 0; +err_out: + inode_unlock(d_inode(parent)); + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); + put_fragment(frag); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; + + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); + + inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_drop(dentry); + fsnotify_rmdir(d_inode(parent), dentry); + inode_unlock(d_inode(parent)); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + const struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + +int configfs_register_subsystem(struct configfs_subsystem *subsys) +{ + int err; + struct config_group *group = &subsys->su_group; + struct dentry *dentry; + struct dentry *root; + struct configfs_dirent *sd; + struct configfs_fragment *frag; + + frag = new_fragment(); + if (!frag) + return -ENOMEM; + + root = configfs_pin_fs(); + if (IS_ERR(root)) { + put_fragment(frag); + return PTR_ERR(root); + } + + if (!group->cg_item.ci_name) + group->cg_item.ci_name = group->cg_item.ci_namebuf; + + sd = root->d_fsdata; + mutex_lock(&configfs_subsystem_mutex); + link_group(to_config_group(sd->s_element), group); + mutex_unlock(&configfs_subsystem_mutex); + + inode_lock_nested(d_inode(root), I_MUTEX_PARENT); + + err = -ENOMEM; + dentry = d_alloc_name(root, group->cg_item.ci_name); + if (dentry) { + d_add(dentry, NULL); + + err = configfs_attach_group(sd->s_element, &group->cg_item, + dentry, frag); + if (err) { + BUG_ON(d_inode(dentry)); + d_drop(dentry); + dput(dentry); + } else { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + } + + inode_unlock(d_inode(root)); + + if (err) { + mutex_lock(&configfs_subsystem_mutex); + unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); + configfs_release_fs(); + } + put_fragment(frag); + + return err; +} + +void configfs_unregister_subsystem(struct configfs_subsystem *subsys) +{ + struct config_group *group = &subsys->su_group; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *root = dentry->d_sb->s_root; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; + + if (dentry->d_parent != root) { + pr_err("Tried to unregister non-subsystem!\n"); + return; + } + + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); + + inode_lock_nested(d_inode(root), + I_MUTEX_PARENT); + inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); + mutex_lock(&configfs_symlink_mutex); + spin_lock(&configfs_dirent_lock); + if (configfs_detach_prep(dentry, NULL)) { + pr_err("Tried to unregister non-empty subsystem!\n"); + } + spin_unlock(&configfs_dirent_lock); + mutex_unlock(&configfs_symlink_mutex); + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + inode_unlock(d_inode(dentry)); + + d_drop(dentry); + fsnotify_rmdir(d_inode(root), dentry); + + inode_unlock(d_inode(root)); + + dput(dentry); + + mutex_lock(&configfs_subsystem_mutex); + unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); + configfs_release_fs(); +} + +EXPORT_SYMBOL(configfs_register_subsystem); +EXPORT_SYMBOL(configfs_unregister_subsystem); diff --git a/fs/configfs/file.c b/fs/configfs/file.c new file mode 100644 index 000000000..4d0825213 --- /dev/null +++ b/fs/configfs/file.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * file.c - operations for regular (text) files. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + */ + +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/vmalloc.h> +#include <linux/uaccess.h> + +#include <linux/configfs.h> +#include "configfs_internal.h" + +/* + * A simple attribute can only be 4096 characters. Why 4k? Because the + * original code limited it to PAGE_SIZE. That's a bad idea, though, + * because an attribute of 16k on ia64 won't work on x86. So we limit to + * 4k, our minimum common page size. + */ +#define SIMPLE_ATTR_SIZE 4096 + +struct configfs_buffer { + size_t count; + loff_t pos; + char * page; + struct configfs_item_operations * ops; + struct mutex mutex; + int needs_read_fill; + bool read_in_progress; + bool write_in_progress; + char *bin_buffer; + int bin_buffer_size; + int cb_max_size; + struct config_item *item; + struct module *owner; + union { + struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; + }; +}; + +static inline struct configfs_fragment *to_frag(struct file *file) +{ + struct configfs_dirent *sd = file->f_path.dentry->d_fsdata; + + return sd->s_frag; +} + +static int fill_read_buffer(struct file *file, struct configfs_buffer *buffer) +{ + struct configfs_fragment *frag = to_frag(file); + ssize_t count = -ENOENT; + + if (!buffer->page) + buffer->page = (char *) get_zeroed_page(GFP_KERNEL); + if (!buffer->page) + return -ENOMEM; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) + count = buffer->attr->show(buffer->item, buffer->page); + up_read(&frag->frag_sem); + + if (count < 0) + return count; + if (WARN_ON_ONCE(count > (ssize_t)SIMPLE_ATTR_SIZE)) + return -EIO; + buffer->needs_read_fill = 0; + buffer->count = count; + return 0; +} + +/** + * configfs_read_file - read an attribute. + * @file: file pointer. + * @buf: buffer to fill. + * @count: number of bytes to read. + * @ppos: starting offset in file. + * + * Userspace wants to read an attribute file. The attribute descriptor + * is in the file's ->d_fsdata. The target item is in the directory's + * ->d_fsdata. + * + * We call fill_read_buffer() to allocate and fill the buffer from the + * item's show() method exactly once (if the read is happening from + * the beginning of the file). That should fill the entire buffer with + * all the data the item has to offer for that attribute. + * We then call flush_read_buffer() to copy the buffer to userspace + * in the increments specified. + */ + +static ssize_t +configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + ssize_t retval = 0; + + mutex_lock(&buffer->mutex); + if (buffer->needs_read_fill) { + retval = fill_read_buffer(file, buffer); + if (retval) + goto out; + } + pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n", + __func__, count, *ppos, buffer->page); + retval = simple_read_from_buffer(buf, count, ppos, buffer->page, + buffer->count); +out: + mutex_unlock(&buffer->mutex); + return retval; +} + +/** + * configfs_read_bin_file - read a binary attribute. + * @file: file pointer. + * @buf: buffer to fill. + * @count: number of bytes to read. + * @ppos: starting offset in file. + * + * Userspace wants to read a binary attribute file. The attribute + * descriptor is in the file's ->d_fsdata. The target item is in the + * directory's ->d_fsdata. + * + * We check whether we need to refill the buffer. If so we will + * call the attributes' attr->read() twice. The first time we + * will pass a NULL as a buffer pointer, which the attributes' method + * will use to return the size of the buffer required. If no error + * occurs we will allocate the buffer using vmalloc and call + * attr->read() again passing that buffer as an argument. + * Then we just copy to user-space using simple_read_from_buffer. + */ + +static ssize_t +configfs_read_bin_file(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_fragment *frag = to_frag(file); + struct configfs_buffer *buffer = file->private_data; + ssize_t retval = 0; + ssize_t len = min_t(size_t, count, PAGE_SIZE); + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->write_in_progress) { + retval = -ETXTBSY; + goto out; + } + buffer->read_in_progress = true; + + if (buffer->needs_read_fill) { + /* perform first read with buf == NULL to get extent */ + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, NULL, 0); + else + len = -ENOENT; + up_read(&frag->frag_sem); + if (len <= 0) { + retval = len; + goto out; + } + + /* do not exceed the maximum value */ + if (buffer->cb_max_size && len > buffer->cb_max_size) { + retval = -EFBIG; + goto out; + } + + buffer->bin_buffer = vmalloc(len); + if (buffer->bin_buffer == NULL) { + retval = -ENOMEM; + goto out; + } + buffer->bin_buffer_size = len; + + /* perform second read to fill buffer */ + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, + buffer->bin_buffer, len); + else + len = -ENOENT; + up_read(&frag->frag_sem); + if (len < 0) { + retval = len; + vfree(buffer->bin_buffer); + buffer->bin_buffer_size = 0; + buffer->bin_buffer = NULL; + goto out; + } + + buffer->needs_read_fill = 0; + } + + retval = simple_read_from_buffer(buf, count, ppos, buffer->bin_buffer, + buffer->bin_buffer_size); +out: + mutex_unlock(&buffer->mutex); + return retval; +} + + +/** + * fill_write_buffer - copy buffer from userspace. + * @buffer: data buffer for file. + * @buf: data from user. + * @count: number of bytes in @userbuf. + * + * Allocate @buffer->page if it hasn't been already, then + * copy the user-supplied buffer into it. + */ + +static int +fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size_t count) +{ + int error; + + if (!buffer->page) + buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); + if (!buffer->page) + return -ENOMEM; + + if (count >= SIMPLE_ATTR_SIZE) + count = SIMPLE_ATTR_SIZE - 1; + error = copy_from_user(buffer->page,buf,count); + buffer->needs_read_fill = 1; + /* if buf is assumed to contain a string, terminate it by \0, + * so e.g. sscanf() can scan the string easily */ + buffer->page[count] = 0; + return error ? -EFAULT : count; +} + +static int +flush_write_buffer(struct file *file, struct configfs_buffer *buffer, size_t count) +{ + struct configfs_fragment *frag = to_frag(file); + int res = -ENOENT; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) + res = buffer->attr->store(buffer->item, buffer->page, count); + up_read(&frag->frag_sem); + return res; +} + + +/** + * configfs_write_file - write an attribute. + * @file: file pointer + * @buf: data to write + * @count: number of bytes + * @ppos: starting offset + * + * Similar to configfs_read_file(), though working in the opposite direction. + * We allocate and fill the data from the user in fill_write_buffer(), + * then push it to the config_item in flush_write_buffer(). + * There is no easy way for us to know if userspace is only doing a partial + * write, so we don't support them. We expect the entire buffer to come + * on the first write. + * Hint: if you're writing a value, first read the file, modify only + * the value you're changing, then write entire buffer back. + */ + +static ssize_t +configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + ssize_t len; + + mutex_lock(&buffer->mutex); + len = fill_write_buffer(buffer, buf, count); + if (len > 0) + len = flush_write_buffer(file, buffer, len); + if (len > 0) + *ppos += len; + mutex_unlock(&buffer->mutex); + return len; +} + +/** + * configfs_write_bin_file - write a binary attribute. + * @file: file pointer + * @buf: data to write + * @count: number of bytes + * @ppos: starting offset + * + * Writing to a binary attribute file is similar to a normal read. + * We buffer the consecutive writes (binary attribute files do not + * support lseek) in a continuously growing buffer, but we don't + * commit until the close of the file. + */ + +static ssize_t +configfs_write_bin_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + void *tbuf = NULL; + ssize_t len; + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->read_in_progress) { + len = -ETXTBSY; + goto out; + } + buffer->write_in_progress = true; + + /* buffer grows? */ + if (*ppos + count > buffer->bin_buffer_size) { + + if (buffer->cb_max_size && + *ppos + count > buffer->cb_max_size) { + len = -EFBIG; + goto out; + } + + tbuf = vmalloc(*ppos + count); + if (tbuf == NULL) { + len = -ENOMEM; + goto out; + } + + /* copy old contents */ + if (buffer->bin_buffer) { + memcpy(tbuf, buffer->bin_buffer, + buffer->bin_buffer_size); + vfree(buffer->bin_buffer); + } + + /* clear the new area */ + memset(tbuf + buffer->bin_buffer_size, 0, + *ppos + count - buffer->bin_buffer_size); + buffer->bin_buffer = tbuf; + buffer->bin_buffer_size = *ppos + count; + } + + len = simple_write_to_buffer(buffer->bin_buffer, + buffer->bin_buffer_size, ppos, buf, count); +out: + mutex_unlock(&buffer->mutex); + return len; +} + +static int __configfs_open_file(struct inode *inode, struct file *file, int type) +{ + struct dentry *dentry = file->f_path.dentry; + struct configfs_fragment *frag = to_frag(file); + struct configfs_attribute *attr; + struct configfs_buffer *buffer; + int error; + + error = -ENOMEM; + buffer = kzalloc(sizeof(struct configfs_buffer), GFP_KERNEL); + if (!buffer) + goto out; + + error = -ENOENT; + down_read(&frag->frag_sem); + if (unlikely(frag->frag_dead)) + goto out_free_buffer; + + error = -EINVAL; + buffer->item = to_item(dentry->d_parent); + if (!buffer->item) + goto out_free_buffer; + + attr = to_attr(dentry); + if (!attr) + goto out_free_buffer; + + if (type & CONFIGFS_ITEM_BIN_ATTR) { + buffer->bin_attr = to_bin_attr(dentry); + buffer->cb_max_size = buffer->bin_attr->cb_max_size; + } else { + buffer->attr = attr; + } + + buffer->owner = attr->ca_owner; + /* Grab the module reference for this attribute if we have one */ + error = -ENODEV; + if (!try_module_get(buffer->owner)) + goto out_free_buffer; + + error = -EACCES; + if (!buffer->item->ci_type) + goto out_put_module; + + buffer->ops = buffer->item->ci_type->ct_item_ops; + + /* File needs write support. + * The inode's perms must say it's ok, + * and we must have a store method. + */ + if (file->f_mode & FMODE_WRITE) { + if (!(inode->i_mode & S_IWUGO)) + goto out_put_module; + if ((type & CONFIGFS_ITEM_ATTR) && !attr->store) + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->write) + goto out_put_module; + } + + /* File needs read support. + * The inode's perms must say it's ok, and we there + * must be a show method for it. + */ + if (file->f_mode & FMODE_READ) { + if (!(inode->i_mode & S_IRUGO)) + goto out_put_module; + if ((type & CONFIGFS_ITEM_ATTR) && !attr->show) + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->read) + goto out_put_module; + } + + mutex_init(&buffer->mutex); + buffer->needs_read_fill = 1; + buffer->read_in_progress = false; + buffer->write_in_progress = false; + file->private_data = buffer; + up_read(&frag->frag_sem); + return 0; + +out_put_module: + module_put(buffer->owner); +out_free_buffer: + up_read(&frag->frag_sem); + kfree(buffer); +out: + return error; +} + +static int configfs_release(struct inode *inode, struct file *filp) +{ + struct configfs_buffer *buffer = filp->private_data; + + module_put(buffer->owner); + if (buffer->page) + free_page((unsigned long)buffer->page); + mutex_destroy(&buffer->mutex); + kfree(buffer); + return 0; +} + +static int configfs_open_file(struct inode *inode, struct file *filp) +{ + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_ATTR); +} + +static int configfs_open_bin_file(struct inode *inode, struct file *filp) +{ + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_BIN_ATTR); +} + +static int configfs_release_bin_file(struct inode *inode, struct file *file) +{ + struct configfs_buffer *buffer = file->private_data; + + buffer->read_in_progress = false; + + if (buffer->write_in_progress) { + struct configfs_fragment *frag = to_frag(file); + buffer->write_in_progress = false; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) { + /* result of ->release() is ignored */ + buffer->bin_attr->write(buffer->item, + buffer->bin_buffer, + buffer->bin_buffer_size); + } + up_read(&frag->frag_sem); + } + + vfree(buffer->bin_buffer); + buffer->bin_buffer = NULL; + buffer->bin_buffer_size = 0; + buffer->needs_read_fill = 1; + + configfs_release(inode, file); + return 0; +} + + +const struct file_operations configfs_file_operations = { + .read = configfs_read_file, + .write = configfs_write_file, + .llseek = generic_file_llseek, + .open = configfs_open_file, + .release = configfs_release, +}; + +const struct file_operations configfs_bin_file_operations = { + .read = configfs_read_bin_file, + .write = configfs_write_bin_file, + .llseek = NULL, /* bin file is not seekable */ + .open = configfs_open_bin_file, + .release = configfs_release_bin_file, +}; + +/** + * configfs_create_file - create an attribute file for an item. + * @item: item we're creating for. + * @attr: atrribute descriptor. + */ + +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, parent_sd->s_frag); + inode_unlock(d_inode(dir)); + + return error; +} + +/** + * configfs_create_bin_file - create a binary attribute file for an item. + * @item: item we're creating for. + * @attr: atrribute descriptor. + */ + +int configfs_create_bin_file(struct config_item *item, + const struct configfs_bin_attribute *bin_attr) +{ + struct dentry *dir = item->ci_dentry; + struct configfs_dirent *parent_sd = dir->d_fsdata; + umode_t mode = (bin_attr->cb_attr.ca_mode & S_IALLUGO) | S_IFREG; + int error = 0; + + inode_lock_nested(dir->d_inode, I_MUTEX_NORMAL); + error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode, + CONFIGFS_ITEM_BIN_ATTR, parent_sd->s_frag); + inode_unlock(dir->d_inode); + + return error; +} diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c new file mode 100644 index 000000000..8bd6a883c --- /dev/null +++ b/fs/configfs/inode.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * inode.c - basic inode and dentry operations. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + * + * Please see Documentation/filesystems/configfs.rst for more + * information. + */ + +#undef DEBUG + +#include <linux/pagemap.h> +#include <linux/namei.h> +#include <linux/backing-dev.h> +#include <linux/capability.h> +#include <linux/sched.h> +#include <linux/lockdep.h> +#include <linux/slab.h> + +#include <linux/configfs.h> +#include "configfs_internal.h" + +#ifdef CONFIG_LOCKDEP +static struct lock_class_key default_group_class[MAX_LOCK_DEPTH]; +#endif + +static const struct address_space_operations configfs_aops = { + .readpage = simple_readpage, + .write_begin = simple_write_begin, + .write_end = simple_write_end, +}; + +static const struct inode_operations configfs_inode_operations ={ + .setattr = configfs_setattr, +}; + +int configfs_setattr(struct dentry * dentry, struct iattr * iattr) +{ + struct inode * inode = d_inode(dentry); + struct configfs_dirent * sd = dentry->d_fsdata; + struct iattr * sd_iattr; + unsigned int ia_valid = iattr->ia_valid; + int error; + + if (!sd) + return -EINVAL; + + sd_iattr = sd->s_iattr; + if (!sd_iattr) { + /* setting attributes for the first time, allocate now */ + sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL); + if (!sd_iattr) + return -ENOMEM; + /* assign default attributes */ + sd_iattr->ia_mode = sd->s_mode; + sd_iattr->ia_uid = GLOBAL_ROOT_UID; + sd_iattr->ia_gid = GLOBAL_ROOT_GID; + sd_iattr->ia_atime = sd_iattr->ia_mtime = + sd_iattr->ia_ctime = current_time(inode); + sd->s_iattr = sd_iattr; + } + /* attributes were changed atleast once in past */ + + error = simple_setattr(dentry, iattr); + if (error) + return error; + + if (ia_valid & ATTR_UID) + sd_iattr->ia_uid = iattr->ia_uid; + if (ia_valid & ATTR_GID) + sd_iattr->ia_gid = iattr->ia_gid; + if (ia_valid & ATTR_ATIME) + sd_iattr->ia_atime = iattr->ia_atime; + if (ia_valid & ATTR_MTIME) + sd_iattr->ia_mtime = iattr->ia_mtime; + if (ia_valid & ATTR_CTIME) + sd_iattr->ia_ctime = iattr->ia_ctime; + if (ia_valid & ATTR_MODE) { + umode_t mode = iattr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + sd_iattr->ia_mode = sd->s_mode = mode; + } + + return error; +} + +static inline void set_default_inode_attr(struct inode * inode, umode_t mode) +{ + inode->i_mode = mode; + inode->i_atime = inode->i_mtime = + inode->i_ctime = current_time(inode); +} + +static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) +{ + inode->i_mode = iattr->ia_mode; + inode->i_uid = iattr->ia_uid; + inode->i_gid = iattr->ia_gid; + inode->i_atime = iattr->ia_atime; + inode->i_mtime = iattr->ia_mtime; + inode->i_ctime = iattr->ia_ctime; +} + +struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, + struct super_block *s) +{ + struct inode * inode = new_inode(s); + if (inode) { + inode->i_ino = get_next_ino(); + inode->i_mapping->a_ops = &configfs_aops; + inode->i_op = &configfs_inode_operations; + + if (sd->s_iattr) { + /* sysfs_dirent has non-default attributes + * get them for the new inode from persistent copy + * in sysfs_dirent + */ + set_inode_attr(inode, sd->s_iattr); + } else + set_default_inode_attr(inode, mode); + } + return inode; +} + +#ifdef CONFIG_LOCKDEP + +static void configfs_set_inode_lock_class(struct configfs_dirent *sd, + struct inode *inode) +{ + int depth = sd->s_depth; + + if (depth > 0) { + if (depth <= ARRAY_SIZE(default_group_class)) { + lockdep_set_class(&inode->i_rwsem, + &default_group_class[depth - 1]); + } else { + /* + * In practice the maximum level of locking depth is + * already reached. Just inform about possible reasons. + */ + pr_info("Too many levels of inodes for the locking correctness validator.\n"); + pr_info("Spurious warnings may appear.\n"); + } + } +} + +#else /* CONFIG_LOCKDEP */ + +static void configfs_set_inode_lock_class(struct configfs_dirent *sd, + struct inode *inode) +{ +} + +#endif /* CONFIG_LOCKDEP */ + +struct inode *configfs_create(struct dentry *dentry, umode_t mode) +{ + struct inode *inode = NULL; + struct configfs_dirent *sd; + struct inode *p_inode; + + if (!dentry) + return ERR_PTR(-ENOENT); + + if (d_really_is_positive(dentry)) + return ERR_PTR(-EEXIST); + + sd = dentry->d_fsdata; + inode = configfs_new_inode(mode, sd, dentry->d_sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + p_inode = d_inode(dentry->d_parent); + p_inode->i_mtime = p_inode->i_ctime = current_time(p_inode); + configfs_set_inode_lock_class(sd, inode); + return inode; +} + +/* + * Get the name for corresponding element represented by the given configfs_dirent + */ +const unsigned char * configfs_get_name(struct configfs_dirent *sd) +{ + struct configfs_attribute *attr; + + BUG_ON(!sd || !sd->s_element); + + /* These always have a dentry, so use that */ + if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) + return sd->s_dentry->d_name.name; + + if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) { + attr = sd->s_element; + return attr->ca_name; + } + return NULL; +} + + +/* + * Unhashes the dentry corresponding to given configfs_dirent + * Called with parent inode's i_mutex held. + */ +void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent) +{ + struct dentry * dentry = sd->s_dentry; + + if (dentry) { + spin_lock(&dentry->d_lock); + if (simple_positive(dentry)) { + dget_dlock(dentry); + __d_drop(dentry); + spin_unlock(&dentry->d_lock); + simple_unlink(d_inode(parent), dentry); + } else + spin_unlock(&dentry->d_lock); + } +} + +void configfs_hash_and_remove(struct dentry * dir, const char * name) +{ + struct configfs_dirent * sd; + struct configfs_dirent * parent_sd = dir->d_fsdata; + + if (d_really_is_negative(dir)) + /* no inode means this hasn't been made visible yet */ + return; + + inode_lock(d_inode(dir)); + list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { + if (!sd->s_element) + continue; + if (!strcmp(configfs_get_name(sd), name)) { + spin_lock(&configfs_dirent_lock); + list_del_init(&sd->s_sibling); + spin_unlock(&configfs_dirent_lock); + configfs_drop_dentry(sd, dir); + configfs_put(sd); + break; + } + } + inode_unlock(d_inode(dir)); +} diff --git a/fs/configfs/item.c b/fs/configfs/item.c new file mode 100644 index 000000000..704a4356f --- /dev/null +++ b/fs/configfs/item.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * item.c - library routines for handling generic config items + * + * Based on kobject: + * kobject is Copyright (c) 2002-2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + * + * Please see the file Documentation/filesystems/configfs.rst for + * critical information about using the config_item interface. + */ + +#include <linux/string.h> +#include <linux/module.h> +#include <linux/stat.h> +#include <linux/slab.h> + +#include <linux/configfs.h> + + +static inline struct config_item *to_item(struct list_head *entry) +{ + return container_of(entry, struct config_item, ci_entry); +} + +/* Evil kernel */ +static void config_item_release(struct kref *kref); + +/** + * config_item_init - initialize item. + * @item: item in question. + */ +static void config_item_init(struct config_item *item) +{ + kref_init(&item->ci_kref); + INIT_LIST_HEAD(&item->ci_entry); +} + +/** + * config_item_set_name - Set the name of an item + * @item: item. + * @fmt: The vsnprintf()'s format string. + * + * If strlen(name) >= CONFIGFS_ITEM_NAME_LEN, then use a + * dynamically allocated string that @item->ci_name points to. + * Otherwise, use the static @item->ci_namebuf array. + */ +int config_item_set_name(struct config_item *item, const char *fmt, ...) +{ + int limit = CONFIGFS_ITEM_NAME_LEN; + int need; + va_list args; + char *name; + + /* + * First, try the static array + */ + va_start(args, fmt); + need = vsnprintf(item->ci_namebuf, limit, fmt, args); + va_end(args); + if (need < limit) + name = item->ci_namebuf; + else { + va_start(args, fmt); + name = kvasprintf(GFP_KERNEL, fmt, args); + va_end(args); + if (!name) + return -EFAULT; + } + + /* Free the old name, if necessary. */ + if (item->ci_name && item->ci_name != item->ci_namebuf) + kfree(item->ci_name); + + /* Now, set the new name */ + item->ci_name = name; + return 0; +} +EXPORT_SYMBOL(config_item_set_name); + +void config_item_init_type_name(struct config_item *item, + const char *name, + const struct config_item_type *type) +{ + config_item_set_name(item, "%s", name); + item->ci_type = type; + config_item_init(item); +} +EXPORT_SYMBOL(config_item_init_type_name); + +void config_group_init_type_name(struct config_group *group, const char *name, + const struct config_item_type *type) +{ + config_item_set_name(&group->cg_item, "%s", name); + group->cg_item.ci_type = type; + config_group_init(group); +} +EXPORT_SYMBOL(config_group_init_type_name); + +struct config_item *config_item_get(struct config_item *item) +{ + if (item) + kref_get(&item->ci_kref); + return item; +} +EXPORT_SYMBOL(config_item_get); + +struct config_item *config_item_get_unless_zero(struct config_item *item) +{ + if (item && kref_get_unless_zero(&item->ci_kref)) + return item; + return NULL; +} +EXPORT_SYMBOL(config_item_get_unless_zero); + +static void config_item_cleanup(struct config_item *item) +{ + const struct config_item_type *t = item->ci_type; + struct config_group *s = item->ci_group; + struct config_item *parent = item->ci_parent; + + pr_debug("config_item %s: cleaning up\n", config_item_name(item)); + if (item->ci_name != item->ci_namebuf) + kfree(item->ci_name); + item->ci_name = NULL; + if (t && t->ct_item_ops && t->ct_item_ops->release) + t->ct_item_ops->release(item); + if (s) + config_group_put(s); + if (parent) + config_item_put(parent); +} + +static void config_item_release(struct kref *kref) +{ + config_item_cleanup(container_of(kref, struct config_item, ci_kref)); +} + +/** + * config_item_put - decrement refcount for item. + * @item: item. + * + * Decrement the refcount, and if 0, call config_item_cleanup(). + */ +void config_item_put(struct config_item *item) +{ + if (item) + kref_put(&item->ci_kref, config_item_release); +} +EXPORT_SYMBOL(config_item_put); + +/** + * config_group_init - initialize a group for use + * @group: config_group + */ +void config_group_init(struct config_group *group) +{ + config_item_init(&group->cg_item); + INIT_LIST_HEAD(&group->cg_children); + INIT_LIST_HEAD(&group->default_groups); +} +EXPORT_SYMBOL(config_group_init); + +/** + * config_group_find_item - search for item in group. + * @group: group we're looking in. + * @name: item's name. + * + * Iterate over @group->cg_list, looking for a matching config_item. + * If matching item is found take a reference and return the item. + * Caller must have locked group via @group->cg_subsys->su_mtx. + */ +struct config_item *config_group_find_item(struct config_group *group, + const char *name) +{ + struct list_head *entry; + struct config_item *ret = NULL; + + list_for_each(entry, &group->cg_children) { + struct config_item *item = to_item(entry); + if (config_item_name(item) && + !strcmp(config_item_name(item), name)) { + ret = config_item_get(item); + break; + } + } + return ret; +} +EXPORT_SYMBOL(config_group_find_item); diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c new file mode 100644 index 000000000..0c6e8cf61 --- /dev/null +++ b/fs/configfs/mount.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * mount.c - operations for initializing and mounting configfs. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + */ + +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/mount.h> +#include <linux/fs_context.h> +#include <linux/pagemap.h> +#include <linux/init.h> +#include <linux/slab.h> + +#include <linux/configfs.h> +#include "configfs_internal.h" + +/* Random magic number */ +#define CONFIGFS_MAGIC 0x62656570 + +static struct vfsmount *configfs_mount = NULL; +struct kmem_cache *configfs_dir_cachep; +static int configfs_mnt_count = 0; + + +static void configfs_free_inode(struct inode *inode) +{ + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static const struct super_operations configfs_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .free_inode = configfs_free_inode, +}; + +static struct config_group configfs_root_group = { + .cg_item = { + .ci_namebuf = "root", + .ci_name = configfs_root_group.cg_item.ci_namebuf, + }, +}; + +int configfs_is_root(struct config_item *item) +{ + return item == &configfs_root_group.cg_item; +} + +static struct configfs_dirent configfs_root = { + .s_sibling = LIST_HEAD_INIT(configfs_root.s_sibling), + .s_children = LIST_HEAD_INIT(configfs_root.s_children), + .s_element = &configfs_root_group.cg_item, + .s_type = CONFIGFS_ROOT, + .s_iattr = NULL, +}; + +static int configfs_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct inode *inode; + struct dentry *root; + + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_magic = CONFIGFS_MAGIC; + sb->s_op = &configfs_ops; + sb->s_time_gran = 1; + + inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, + &configfs_root, sb); + if (inode) { + inode->i_op = &configfs_root_inode_operations; + inode->i_fop = &configfs_dir_operations; + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + } else { + pr_debug("could not get root inode\n"); + return -ENOMEM; + } + + root = d_make_root(inode); + if (!root) { + pr_debug("%s: could not get root dentry!\n",__func__); + return -ENOMEM; + } + config_group_init(&configfs_root_group); + configfs_root_group.cg_item.ci_dentry = root; + root->d_fsdata = &configfs_root; + sb->s_root = root; + sb->s_d_op = &configfs_dentry_ops; /* the rest get that */ + return 0; +} + +static int configfs_get_tree(struct fs_context *fc) +{ + return get_tree_single(fc, configfs_fill_super); +} + +static const struct fs_context_operations configfs_context_ops = { + .get_tree = configfs_get_tree, +}; + +static int configfs_init_fs_context(struct fs_context *fc) +{ + fc->ops = &configfs_context_ops; + return 0; +} + +static struct file_system_type configfs_fs_type = { + .owner = THIS_MODULE, + .name = "configfs", + .init_fs_context = configfs_init_fs_context, + .kill_sb = kill_litter_super, +}; +MODULE_ALIAS_FS("configfs"); + +struct dentry *configfs_pin_fs(void) +{ + int err = simple_pin_fs(&configfs_fs_type, &configfs_mount, + &configfs_mnt_count); + return err ? ERR_PTR(err) : configfs_mount->mnt_root; +} + +void configfs_release_fs(void) +{ + simple_release_fs(&configfs_mount, &configfs_mnt_count); +} + + +static int __init configfs_init(void) +{ + int err = -ENOMEM; + + configfs_dir_cachep = kmem_cache_create("configfs_dir_cache", + sizeof(struct configfs_dirent), + 0, 0, NULL); + if (!configfs_dir_cachep) + goto out; + + err = sysfs_create_mount_point(kernel_kobj, "config"); + if (err) + goto out2; + + err = register_filesystem(&configfs_fs_type); + if (err) + goto out3; + + return 0; +out3: + pr_err("Unable to register filesystem!\n"); + sysfs_remove_mount_point(kernel_kobj, "config"); +out2: + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; +out: + return err; +} + +static void __exit configfs_exit(void) +{ + unregister_filesystem(&configfs_fs_type); + sysfs_remove_mount_point(kernel_kobj, "config"); + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; +} + +MODULE_AUTHOR("Oracle"); +MODULE_LICENSE("GPL"); +MODULE_VERSION("0.0.2"); +MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration."); + +core_initcall(configfs_init); +module_exit(configfs_exit); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c new file mode 100644 index 000000000..cb6146747 --- /dev/null +++ b/fs/configfs/symlink.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * symlink.c - operations for configfs symlinks. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + */ + +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/namei.h> +#include <linux/slab.h> + +#include <linux/configfs.h> +#include "configfs_internal.h" + +/* Protects attachments of new symlinks */ +DEFINE_MUTEX(configfs_symlink_mutex); + +static int item_depth(struct config_item * item) +{ + struct config_item * p = item; + int depth = 0; + do { depth++; } while ((p = p->ci_parent) && !configfs_is_root(p)); + return depth; +} + +static int item_path_length(struct config_item * item) +{ + struct config_item * p = item; + int length = 1; + do { + length += strlen(config_item_name(p)) + 1; + p = p->ci_parent; + } while (p && !configfs_is_root(p)); + return length; +} + +static void fill_item_path(struct config_item * item, char * buffer, int length) +{ + struct config_item * p; + + --length; + for (p = item; p && !configfs_is_root(p); p = p->ci_parent) { + int cur = strlen(config_item_name(p)); + + /* back up enough to print this bus id with '/' */ + length -= cur; + memcpy(buffer + length, config_item_name(p), cur); + *(buffer + --length) = '/'; + } +} + +static int configfs_get_target_path(struct config_item *item, + struct config_item *target, char *path) +{ + int depth, size; + char *s; + + depth = item_depth(item); + size = item_path_length(target) + depth * 3 - 1; + if (size > PATH_MAX) + return -ENAMETOOLONG; + + pr_debug("%s: depth = %d, size = %d\n", __func__, depth, size); + + for (s = path; depth--; s += 3) + strcpy(s,"../"); + + fill_item_path(target, path, size); + pr_debug("%s: path = '%s'\n", __func__, path); + return 0; +} + +static int create_link(struct config_item *parent_item, + struct config_item *item, + struct dentry *dentry) +{ + struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata; + char *body; + int ret; + + if (!configfs_dirent_is_ready(target_sd)) + return -ENOENT; + + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) + return -ENOMEM; + + configfs_get(target_sd); + spin_lock(&configfs_dirent_lock); + if (target_sd->s_type & CONFIGFS_USET_DROPPING) { + spin_unlock(&configfs_dirent_lock); + configfs_put(target_sd); + kfree(body); + return -ENOENT; + } + target_sd->s_links++; + spin_unlock(&configfs_dirent_lock); + ret = configfs_get_target_path(parent_item, item, body); + if (!ret) + ret = configfs_create_link(target_sd, parent_item->ci_dentry, + dentry, body); + if (ret) { + spin_lock(&configfs_dirent_lock); + target_sd->s_links--; + spin_unlock(&configfs_dirent_lock); + configfs_put(target_sd); + kfree(body); + } + return ret; +} + + +static int get_target(const char *symname, struct path *path, + struct config_item **target, struct super_block *sb) +{ + int ret; + + ret = kern_path(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, path); + if (!ret) { + if (path->dentry->d_sb == sb) { + *target = configfs_get_config_item(path->dentry); + if (!*target) { + ret = -ENOENT; + path_put(path); + } + } else { + ret = -EPERM; + path_put(path); + } + } + + return ret; +} + + +int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + int ret; + struct path path; + struct configfs_dirent *sd; + struct config_item *parent_item; + struct config_item *target_item = NULL; + const struct config_item_type *type; + + 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)) + return -ENOENT; + + parent_item = configfs_get_config_item(dentry->d_parent); + type = parent_item->ci_type; + + ret = -EPERM; + if (!type || !type->ct_item_ops || + !type->ct_item_ops->allow_link) + goto out_put; + + /* + * This is really sick. What they wanted was a hybrid of + * link(2) and symlink(2) - they wanted the target resolved + * at syscall time (as link(2) would've done), be a directory + * (which link(2) would've refused to do) *AND* be a deep + * fucking magic, making the target busy from rmdir POV. + * symlink(2) is nothing of that sort, and the locking it + * gets matches the normal symlink(2) semantics. Without + * attempts to resolve the target (which might very well + * not even exist yet) done prior to locking the parent + * directory. This perversion, OTOH, needs to resolve + * the target, which would lead to obvious deadlocks if + * attempted with any directories locked. + * + * Unfortunately, that garbage is userland ABI and we should've + * said "no" back in 2005. Too late now, so we get to + * play very ugly games with locking. + * + * Try *ANYTHING* of that sort in new code, and you will + * really regret it. Just ask yourself - what could a BOFH + * do to me and do I want to find it out first-hand? + * + * AV, a thoroughly annoyed bastard. + */ + inode_unlock(dir); + ret = get_target(symname, &path, &target_item, dentry->d_sb); + inode_lock(dir); + if (ret) + goto out_put; + + if (dentry->d_inode || d_unhashed(dentry)) + ret = -EEXIST; + else + ret = inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (!ret) + ret = type->ct_item_ops->allow_link(parent_item, target_item); + if (!ret) { + mutex_lock(&configfs_symlink_mutex); + ret = create_link(parent_item, target_item, dentry); + mutex_unlock(&configfs_symlink_mutex); + if (ret && type->ct_item_ops->drop_link) + type->ct_item_ops->drop_link(parent_item, + target_item); + } + + config_item_put(target_item); + path_put(&path); + +out_put: + config_item_put(parent_item); + return ret; +} + +int configfs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct configfs_dirent *sd = dentry->d_fsdata, *target_sd; + struct config_item *parent_item; + const struct config_item_type *type; + int ret; + + ret = -EPERM; /* What lack-of-symlink returns */ + if (!(sd->s_type & CONFIGFS_ITEM_LINK)) + goto out; + + target_sd = sd->s_element; + + parent_item = configfs_get_config_item(dentry->d_parent); + type = parent_item->ci_type; + + spin_lock(&configfs_dirent_lock); + list_del_init(&sd->s_sibling); + spin_unlock(&configfs_dirent_lock); + configfs_drop_dentry(sd, dentry->d_parent); + dput(dentry); + configfs_put(sd); + + /* + * drop_link() must be called before + * decrementing target's ->s_links, so that the order of + * drop_link(this, target) and drop_item(target) is preserved. + */ + if (type && type->ct_item_ops && + type->ct_item_ops->drop_link) + type->ct_item_ops->drop_link(parent_item, + target_sd->s_element); + + spin_lock(&configfs_dirent_lock); + target_sd->s_links--; + spin_unlock(&configfs_dirent_lock); + configfs_put(target_sd); + + config_item_put(parent_item); + + ret = 0; + +out: + return ret; +} + +const struct inode_operations configfs_symlink_inode_operations = { + .get_link = simple_get_link, + .setattr = configfs_setattr, +}; + |