Pull user namespace updates from Eric Biederman: "Long ago and far away when user namespaces where young it was realized that allowing fresh mounts of proc and sysfs with only user namespace permissions could violate the basic rule that only root gets to decide if proc or sysfs should be mounted at all. Some hacks were put in place to reduce the worst of the damage could be done, and the common sense rule was adopted that fresh mounts of proc and sysfs should allow no more than bind mounts of proc and sysfs. Unfortunately that rule has not been fully enforced. There are two kinds of gaps in that enforcement. Only filesystems mounted on empty directories of proc and sysfs should be ignored but the test for empty directories was insufficient. So in my tree directories on proc, sysctl and sysfs that will always be empty are created specially. Every other technique is imperfect as an ordinary directory can have entries added even after a readdir returns and shows that the directory is empty. Special creation of directories for mount points makes the code in the kernel a smidge clearer about it's purpose. I asked container developers from the various container projects to help test this and no holes were found in the set of mount points on proc and sysfs that are created specially. This set of changes also starts enforcing the mount flags of fresh mounts of proc and sysfs are consistent with the existing mount of proc and sysfs. I expected this to be the boring part of the work but unfortunately unprivileged userspace winds up mounting fresh copies of proc and sysfs with noexec and nosuid clear when root set those flags on the previous mount of proc and sysfs. So for now only the atime, read-only and nodev attributes which userspace happens to keep consistent are enforced. Dealing with the noexec and nosuid attributes remains for another time. This set of changes also addresses an issue with how open file descriptors from /proc/<pid>/ns/* are displayed. Recently readlink of /proc/<pid>/fd has been triggering a WARN_ON that has not been meaningful since it was added (as all of the code in the kernel was converted) and is not now actively wrong. There is also a short list of issues that have not been fixed yet that I will mention briefly. It is possible to rename a directory from below to above a bind mount. At which point any directory pointers below the renamed directory can be walked up to the root directory of the filesystem. With user namespaces enabled a bind mount of the bind mount can be created allowing the user to pick a directory whose children they can rename to outside of the bind mount. This is challenging to fix and doubly so because all obvious solutions must touch code that is in the performance part of pathname resolution. As mentioned above there is also a question of how to ensure that developers by accident or with purpose do not introduce exectuable files on sysfs and proc and in doing so introduce security regressions in the current userspace that will not be immediately obvious and as such are likely to require breaking userspace in painful ways once they are recognized" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: vfs: Remove incorrect debugging WARN in prepend_path mnt: Update fs_fully_visible to test for permanently empty directories sysfs: Create mountpoints with sysfs_create_mount_point sysfs: Add support for permanently empty directories to serve as mount points. kernfs: Add support for always empty directories. proc: Allow creating permanently empty directories that serve as mount points sysctl: Allow creating permanently empty directories that serve as mountpoints. fs: Add helper functions for permanently empty directories. vfs: Ignore unlocked mounts in fs_fully_visible mnt: Modify fs_fully_visible to deal with locked ro nodev and atime mnt: Refactor the logic for mounting sysfs and proc in a user namespace
736 lines
21 KiB
C
736 lines
21 KiB
C
/*
|
|
* inode.c - part of debugfs, a tiny little debug file system
|
|
*
|
|
* Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
|
|
* Copyright (C) 2004 IBM Inc.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License version
|
|
* 2 as published by the Free Software Foundation.
|
|
*
|
|
* debugfs is for people to use instead of /proc or /sys.
|
|
* See Documentation/DocBook/kernel-api for more details.
|
|
*
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/fsnotify.h>
|
|
#include <linux/string.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/parser.h>
|
|
#include <linux/magic.h>
|
|
#include <linux/slab.h>
|
|
|
|
#define DEBUGFS_DEFAULT_MODE 0700
|
|
|
|
static struct vfsmount *debugfs_mount;
|
|
static int debugfs_mount_count;
|
|
static bool debugfs_registered;
|
|
|
|
static struct inode *debugfs_get_inode(struct super_block *sb)
|
|
{
|
|
struct inode *inode = new_inode(sb);
|
|
if (inode) {
|
|
inode->i_ino = get_next_ino();
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
|
|
}
|
|
return inode;
|
|
}
|
|
|
|
static inline int debugfs_positive(struct dentry *dentry)
|
|
{
|
|
return d_really_is_positive(dentry) && !d_unhashed(dentry);
|
|
}
|
|
|
|
struct debugfs_mount_opts {
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
umode_t mode;
|
|
};
|
|
|
|
enum {
|
|
Opt_uid,
|
|
Opt_gid,
|
|
Opt_mode,
|
|
Opt_err
|
|
};
|
|
|
|
static const match_table_t tokens = {
|
|
{Opt_uid, "uid=%u"},
|
|
{Opt_gid, "gid=%u"},
|
|
{Opt_mode, "mode=%o"},
|
|
{Opt_err, NULL}
|
|
};
|
|
|
|
struct debugfs_fs_info {
|
|
struct debugfs_mount_opts mount_opts;
|
|
};
|
|
|
|
static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
|
|
{
|
|
substring_t args[MAX_OPT_ARGS];
|
|
int option;
|
|
int token;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
char *p;
|
|
|
|
opts->mode = DEBUGFS_DEFAULT_MODE;
|
|
|
|
while ((p = strsep(&data, ",")) != NULL) {
|
|
if (!*p)
|
|
continue;
|
|
|
|
token = match_token(p, tokens, args);
|
|
switch (token) {
|
|
case Opt_uid:
|
|
if (match_int(&args[0], &option))
|
|
return -EINVAL;
|
|
uid = make_kuid(current_user_ns(), option);
|
|
if (!uid_valid(uid))
|
|
return -EINVAL;
|
|
opts->uid = uid;
|
|
break;
|
|
case Opt_gid:
|
|
if (match_int(&args[0], &option))
|
|
return -EINVAL;
|
|
gid = make_kgid(current_user_ns(), option);
|
|
if (!gid_valid(gid))
|
|
return -EINVAL;
|
|
opts->gid = gid;
|
|
break;
|
|
case Opt_mode:
|
|
if (match_octal(&args[0], &option))
|
|
return -EINVAL;
|
|
opts->mode = option & S_IALLUGO;
|
|
break;
|
|
/*
|
|
* We might like to report bad mount options here;
|
|
* but traditionally debugfs has ignored all mount options
|
|
*/
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int debugfs_apply_options(struct super_block *sb)
|
|
{
|
|
struct debugfs_fs_info *fsi = sb->s_fs_info;
|
|
struct inode *inode = d_inode(sb->s_root);
|
|
struct debugfs_mount_opts *opts = &fsi->mount_opts;
|
|
|
|
inode->i_mode &= ~S_IALLUGO;
|
|
inode->i_mode |= opts->mode;
|
|
|
|
inode->i_uid = opts->uid;
|
|
inode->i_gid = opts->gid;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int debugfs_remount(struct super_block *sb, int *flags, char *data)
|
|
{
|
|
int err;
|
|
struct debugfs_fs_info *fsi = sb->s_fs_info;
|
|
|
|
sync_filesystem(sb);
|
|
err = debugfs_parse_options(data, &fsi->mount_opts);
|
|
if (err)
|
|
goto fail;
|
|
|
|
debugfs_apply_options(sb);
|
|
|
|
fail:
|
|
return err;
|
|
}
|
|
|
|
static int debugfs_show_options(struct seq_file *m, struct dentry *root)
|
|
{
|
|
struct debugfs_fs_info *fsi = root->d_sb->s_fs_info;
|
|
struct debugfs_mount_opts *opts = &fsi->mount_opts;
|
|
|
|
if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
|
|
seq_printf(m, ",uid=%u",
|
|
from_kuid_munged(&init_user_ns, opts->uid));
|
|
if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
|
|
seq_printf(m, ",gid=%u",
|
|
from_kgid_munged(&init_user_ns, opts->gid));
|
|
if (opts->mode != DEBUGFS_DEFAULT_MODE)
|
|
seq_printf(m, ",mode=%o", opts->mode);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void debugfs_evict_inode(struct inode *inode)
|
|
{
|
|
truncate_inode_pages_final(&inode->i_data);
|
|
clear_inode(inode);
|
|
if (S_ISLNK(inode->i_mode))
|
|
kfree(inode->i_link);
|
|
}
|
|
|
|
static const struct super_operations debugfs_super_operations = {
|
|
.statfs = simple_statfs,
|
|
.remount_fs = debugfs_remount,
|
|
.show_options = debugfs_show_options,
|
|
.evict_inode = debugfs_evict_inode,
|
|
};
|
|
|
|
static struct vfsmount *debugfs_automount(struct path *path)
|
|
{
|
|
struct vfsmount *(*f)(void *);
|
|
f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata;
|
|
return f(d_inode(path->dentry)->i_private);
|
|
}
|
|
|
|
static const struct dentry_operations debugfs_dops = {
|
|
.d_delete = always_delete_dentry,
|
|
.d_automount = debugfs_automount,
|
|
};
|
|
|
|
static int debug_fill_super(struct super_block *sb, void *data, int silent)
|
|
{
|
|
static struct tree_descr debug_files[] = {{""}};
|
|
struct debugfs_fs_info *fsi;
|
|
int err;
|
|
|
|
save_mount_options(sb, data);
|
|
|
|
fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
|
|
sb->s_fs_info = fsi;
|
|
if (!fsi) {
|
|
err = -ENOMEM;
|
|
goto fail;
|
|
}
|
|
|
|
err = debugfs_parse_options(data, &fsi->mount_opts);
|
|
if (err)
|
|
goto fail;
|
|
|
|
err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
|
|
if (err)
|
|
goto fail;
|
|
|
|
sb->s_op = &debugfs_super_operations;
|
|
sb->s_d_op = &debugfs_dops;
|
|
|
|
debugfs_apply_options(sb);
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
kfree(fsi);
|
|
sb->s_fs_info = NULL;
|
|
return err;
|
|
}
|
|
|
|
static struct dentry *debug_mount(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name,
|
|
void *data)
|
|
{
|
|
return mount_single(fs_type, flags, data, debug_fill_super);
|
|
}
|
|
|
|
static struct file_system_type debug_fs_type = {
|
|
.owner = THIS_MODULE,
|
|
.name = "debugfs",
|
|
.mount = debug_mount,
|
|
.kill_sb = kill_litter_super,
|
|
};
|
|
MODULE_ALIAS_FS("debugfs");
|
|
|
|
static struct dentry *start_creating(const char *name, struct dentry *parent)
|
|
{
|
|
struct dentry *dentry;
|
|
int error;
|
|
|
|
pr_debug("debugfs: creating file '%s'\n",name);
|
|
|
|
if (IS_ERR(parent))
|
|
return parent;
|
|
|
|
error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
|
|
&debugfs_mount_count);
|
|
if (error)
|
|
return ERR_PTR(error);
|
|
|
|
/* If the parent is not specified, we create it in the root.
|
|
* We need the root dentry to do this, which is in the super
|
|
* block. A pointer to that is in the struct vfsmount that we
|
|
* have around.
|
|
*/
|
|
if (!parent)
|
|
parent = debugfs_mount->mnt_root;
|
|
|
|
mutex_lock(&d_inode(parent)->i_mutex);
|
|
dentry = lookup_one_len(name, parent, strlen(name));
|
|
if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
|
|
dput(dentry);
|
|
dentry = ERR_PTR(-EEXIST);
|
|
}
|
|
if (IS_ERR(dentry))
|
|
mutex_unlock(&d_inode(parent)->i_mutex);
|
|
return dentry;
|
|
}
|
|
|
|
static struct dentry *failed_creating(struct dentry *dentry)
|
|
{
|
|
mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
|
|
dput(dentry);
|
|
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
|
|
return NULL;
|
|
}
|
|
|
|
static struct dentry *end_creating(struct dentry *dentry)
|
|
{
|
|
mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
|
|
return dentry;
|
|
}
|
|
|
|
/**
|
|
* debugfs_create_file - create a file in the debugfs filesystem
|
|
* @name: a pointer to a string containing the name of the file to create.
|
|
* @mode: the permission that the file should have.
|
|
* @parent: a pointer to the parent dentry for this file. This should be a
|
|
* directory dentry if set. If this parameter is NULL, then the
|
|
* file will be created in the root of the debugfs filesystem.
|
|
* @data: a pointer to something that the caller will want to get to later
|
|
* on. The inode.i_private pointer will point to this value on
|
|
* the open() call.
|
|
* @fops: a pointer to a struct file_operations that should be used for
|
|
* this file.
|
|
*
|
|
* This is the basic "create a file" function for debugfs. It allows for a
|
|
* wide range of flexibility in creating a file, or a directory (if you want
|
|
* to create a directory, the debugfs_create_dir() function is
|
|
* recommended to be used instead.)
|
|
*
|
|
* This function will return a pointer to a dentry if it succeeds. This
|
|
* pointer must be passed to the debugfs_remove() function when the file is
|
|
* to be removed (no automatic cleanup happens if your module is unloaded,
|
|
* you are responsible here.) If an error occurs, %NULL will be returned.
|
|
*
|
|
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *debugfs_create_file(const char *name, umode_t mode,
|
|
struct dentry *parent, void *data,
|
|
const struct file_operations *fops)
|
|
{
|
|
struct dentry *dentry;
|
|
struct inode *inode;
|
|
|
|
if (!(mode & S_IFMT))
|
|
mode |= S_IFREG;
|
|
BUG_ON(!S_ISREG(mode));
|
|
dentry = start_creating(name, parent);
|
|
|
|
if (IS_ERR(dentry))
|
|
return NULL;
|
|
|
|
inode = debugfs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode))
|
|
return failed_creating(dentry);
|
|
|
|
inode->i_mode = mode;
|
|
inode->i_fop = fops ? fops : &debugfs_file_operations;
|
|
inode->i_private = data;
|
|
d_instantiate(dentry, inode);
|
|
fsnotify_create(d_inode(dentry->d_parent), dentry);
|
|
return end_creating(dentry);
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_create_file);
|
|
|
|
/**
|
|
* debugfs_create_file_size - create a file in the debugfs filesystem
|
|
* @name: a pointer to a string containing the name of the file to create.
|
|
* @mode: the permission that the file should have.
|
|
* @parent: a pointer to the parent dentry for this file. This should be a
|
|
* directory dentry if set. If this parameter is NULL, then the
|
|
* file will be created in the root of the debugfs filesystem.
|
|
* @data: a pointer to something that the caller will want to get to later
|
|
* on. The inode.i_private pointer will point to this value on
|
|
* the open() call.
|
|
* @fops: a pointer to a struct file_operations that should be used for
|
|
* this file.
|
|
* @file_size: initial file size
|
|
*
|
|
* This is the basic "create a file" function for debugfs. It allows for a
|
|
* wide range of flexibility in creating a file, or a directory (if you want
|
|
* to create a directory, the debugfs_create_dir() function is
|
|
* recommended to be used instead.)
|
|
*
|
|
* This function will return a pointer to a dentry if it succeeds. This
|
|
* pointer must be passed to the debugfs_remove() function when the file is
|
|
* to be removed (no automatic cleanup happens if your module is unloaded,
|
|
* you are responsible here.) If an error occurs, %NULL will be returned.
|
|
*
|
|
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
|
|
struct dentry *parent, void *data,
|
|
const struct file_operations *fops,
|
|
loff_t file_size)
|
|
{
|
|
struct dentry *de = debugfs_create_file(name, mode, parent, data, fops);
|
|
|
|
if (de)
|
|
d_inode(de)->i_size = file_size;
|
|
return de;
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_create_file_size);
|
|
|
|
/**
|
|
* debugfs_create_dir - create a directory in the debugfs filesystem
|
|
* @name: a pointer to a string containing the name of the directory to
|
|
* create.
|
|
* @parent: a pointer to the parent dentry for this file. This should be a
|
|
* directory dentry if set. If this parameter is NULL, then the
|
|
* directory will be created in the root of the debugfs filesystem.
|
|
*
|
|
* This function creates a directory in debugfs with the given name.
|
|
*
|
|
* This function will return a pointer to a dentry if it succeeds. This
|
|
* pointer must be passed to the debugfs_remove() function when the file is
|
|
* to be removed (no automatic cleanup happens if your module is unloaded,
|
|
* you are responsible here.) If an error occurs, %NULL will be returned.
|
|
*
|
|
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
|
|
{
|
|
struct dentry *dentry = start_creating(name, parent);
|
|
struct inode *inode;
|
|
|
|
if (IS_ERR(dentry))
|
|
return NULL;
|
|
|
|
inode = debugfs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode))
|
|
return failed_creating(dentry);
|
|
|
|
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
|
|
inode->i_op = &simple_dir_inode_operations;
|
|
inode->i_fop = &simple_dir_operations;
|
|
|
|
/* directory inodes start off with i_nlink == 2 (for "." entry) */
|
|
inc_nlink(inode);
|
|
d_instantiate(dentry, inode);
|
|
inc_nlink(d_inode(dentry->d_parent));
|
|
fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
|
|
return end_creating(dentry);
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_create_dir);
|
|
|
|
/**
|
|
* debugfs_create_automount - create automount point in the debugfs filesystem
|
|
* @name: a pointer to a string containing the name of the file to create.
|
|
* @parent: a pointer to the parent dentry for this file. This should be a
|
|
* directory dentry if set. If this parameter is NULL, then the
|
|
* file will be created in the root of the debugfs filesystem.
|
|
* @f: function to be called when pathname resolution steps on that one.
|
|
* @data: opaque argument to pass to f().
|
|
*
|
|
* @f should return what ->d_automount() would.
|
|
*/
|
|
struct dentry *debugfs_create_automount(const char *name,
|
|
struct dentry *parent,
|
|
struct vfsmount *(*f)(void *),
|
|
void *data)
|
|
{
|
|
struct dentry *dentry = start_creating(name, parent);
|
|
struct inode *inode;
|
|
|
|
if (IS_ERR(dentry))
|
|
return NULL;
|
|
|
|
inode = debugfs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode))
|
|
return failed_creating(dentry);
|
|
|
|
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
|
|
inode->i_flags |= S_AUTOMOUNT;
|
|
inode->i_private = data;
|
|
dentry->d_fsdata = (void *)f;
|
|
d_instantiate(dentry, inode);
|
|
return end_creating(dentry);
|
|
}
|
|
EXPORT_SYMBOL(debugfs_create_automount);
|
|
|
|
/**
|
|
* debugfs_create_symlink- create a symbolic link in the debugfs filesystem
|
|
* @name: a pointer to a string containing the name of the symbolic link to
|
|
* create.
|
|
* @parent: a pointer to the parent dentry for this symbolic link. This
|
|
* should be a directory dentry if set. If this parameter is NULL,
|
|
* then the symbolic link will be created in the root of the debugfs
|
|
* filesystem.
|
|
* @target: a pointer to a string containing the path to the target of the
|
|
* symbolic link.
|
|
*
|
|
* This function creates a symbolic link with the given name in debugfs that
|
|
* links to the given target path.
|
|
*
|
|
* This function will return a pointer to a dentry if it succeeds. This
|
|
* pointer must be passed to the debugfs_remove() function when the symbolic
|
|
* link is to be removed (no automatic cleanup happens if your module is
|
|
* unloaded, you are responsible here.) If an error occurs, %NULL will be
|
|
* returned.
|
|
*
|
|
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
|
|
const char *target)
|
|
{
|
|
struct dentry *dentry;
|
|
struct inode *inode;
|
|
char *link = kstrdup(target, GFP_KERNEL);
|
|
if (!link)
|
|
return NULL;
|
|
|
|
dentry = start_creating(name, parent);
|
|
if (IS_ERR(dentry)) {
|
|
kfree(link);
|
|
return NULL;
|
|
}
|
|
|
|
inode = debugfs_get_inode(dentry->d_sb);
|
|
if (unlikely(!inode)) {
|
|
kfree(link);
|
|
return failed_creating(dentry);
|
|
}
|
|
inode->i_mode = S_IFLNK | S_IRWXUGO;
|
|
inode->i_op = &simple_symlink_inode_operations;
|
|
inode->i_link = link;
|
|
d_instantiate(dentry, inode);
|
|
return end_creating(dentry);
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_create_symlink);
|
|
|
|
static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (debugfs_positive(dentry)) {
|
|
dget(dentry);
|
|
if (d_is_dir(dentry))
|
|
ret = simple_rmdir(d_inode(parent), dentry);
|
|
else
|
|
simple_unlink(d_inode(parent), dentry);
|
|
if (!ret)
|
|
d_delete(dentry);
|
|
dput(dentry);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* debugfs_remove - removes a file or directory from the debugfs filesystem
|
|
* @dentry: a pointer to a the dentry of the file or directory to be
|
|
* removed.
|
|
*
|
|
* This function removes a file or directory in debugfs that was previously
|
|
* created with a call to another debugfs function (like
|
|
* debugfs_create_file() or variants thereof.)
|
|
*
|
|
* This function is required to be called in order for the file to be
|
|
* removed, no automatic cleanup of files will happen when a module is
|
|
* removed, you are responsible here.
|
|
*/
|
|
void debugfs_remove(struct dentry *dentry)
|
|
{
|
|
struct dentry *parent;
|
|
int ret;
|
|
|
|
if (IS_ERR_OR_NULL(dentry))
|
|
return;
|
|
|
|
parent = dentry->d_parent;
|
|
if (!parent || d_really_is_negative(parent))
|
|
return;
|
|
|
|
mutex_lock(&d_inode(parent)->i_mutex);
|
|
ret = __debugfs_remove(dentry, parent);
|
|
mutex_unlock(&d_inode(parent)->i_mutex);
|
|
if (!ret)
|
|
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_remove);
|
|
|
|
/**
|
|
* debugfs_remove_recursive - recursively removes a directory
|
|
* @dentry: a pointer to a the dentry of the directory to be removed.
|
|
*
|
|
* This function recursively removes a directory tree in debugfs that
|
|
* was previously created with a call to another debugfs function
|
|
* (like debugfs_create_file() or variants thereof.)
|
|
*
|
|
* This function is required to be called in order for the file to be
|
|
* removed, no automatic cleanup of files will happen when a module is
|
|
* removed, you are responsible here.
|
|
*/
|
|
void debugfs_remove_recursive(struct dentry *dentry)
|
|
{
|
|
struct dentry *child, *parent;
|
|
|
|
if (IS_ERR_OR_NULL(dentry))
|
|
return;
|
|
|
|
parent = dentry->d_parent;
|
|
if (!parent || d_really_is_negative(parent))
|
|
return;
|
|
|
|
parent = dentry;
|
|
down:
|
|
mutex_lock(&d_inode(parent)->i_mutex);
|
|
loop:
|
|
/*
|
|
* The parent->d_subdirs is protected by the d_lock. Outside that
|
|
* lock, the child can be unlinked and set to be freed which can
|
|
* use the d_u.d_child as the rcu head and corrupt this list.
|
|
*/
|
|
spin_lock(&parent->d_lock);
|
|
list_for_each_entry(child, &parent->d_subdirs, d_child) {
|
|
if (!debugfs_positive(child))
|
|
continue;
|
|
|
|
/* perhaps simple_empty(child) makes more sense */
|
|
if (!list_empty(&child->d_subdirs)) {
|
|
spin_unlock(&parent->d_lock);
|
|
mutex_unlock(&d_inode(parent)->i_mutex);
|
|
parent = child;
|
|
goto down;
|
|
}
|
|
|
|
spin_unlock(&parent->d_lock);
|
|
|
|
if (!__debugfs_remove(child, parent))
|
|
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
|
|
|
|
/*
|
|
* The parent->d_lock protects agaist child from unlinking
|
|
* from d_subdirs. When releasing the parent->d_lock we can
|
|
* no longer trust that the next pointer is valid.
|
|
* Restart the loop. We'll skip this one with the
|
|
* debugfs_positive() check.
|
|
*/
|
|
goto loop;
|
|
}
|
|
spin_unlock(&parent->d_lock);
|
|
|
|
mutex_unlock(&d_inode(parent)->i_mutex);
|
|
child = parent;
|
|
parent = parent->d_parent;
|
|
mutex_lock(&d_inode(parent)->i_mutex);
|
|
|
|
if (child != dentry)
|
|
/* go up */
|
|
goto loop;
|
|
|
|
if (!__debugfs_remove(child, parent))
|
|
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
|
|
mutex_unlock(&d_inode(parent)->i_mutex);
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
|
|
|
|
/**
|
|
* debugfs_rename - rename a file/directory in the debugfs filesystem
|
|
* @old_dir: a pointer to the parent dentry for the renamed object. This
|
|
* should be a directory dentry.
|
|
* @old_dentry: dentry of an object to be renamed.
|
|
* @new_dir: a pointer to the parent dentry where the object should be
|
|
* moved. This should be a directory dentry.
|
|
* @new_name: a pointer to a string containing the target name.
|
|
*
|
|
* This function renames a file/directory in debugfs. The target must not
|
|
* exist for rename to succeed.
|
|
*
|
|
* This function will return a pointer to old_dentry (which is updated to
|
|
* reflect renaming) if it succeeds. If an error occurs, %NULL will be
|
|
* returned.
|
|
*
|
|
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
|
|
* returned.
|
|
*/
|
|
struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
|
|
struct dentry *new_dir, const char *new_name)
|
|
{
|
|
int error;
|
|
struct dentry *dentry = NULL, *trap;
|
|
const char *old_name;
|
|
|
|
trap = lock_rename(new_dir, old_dir);
|
|
/* Source or destination directories don't exist? */
|
|
if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
|
|
goto exit;
|
|
/* Source does not exist, cyclic rename, or mountpoint? */
|
|
if (d_really_is_negative(old_dentry) || old_dentry == trap ||
|
|
d_mountpoint(old_dentry))
|
|
goto exit;
|
|
dentry = lookup_one_len(new_name, new_dir, strlen(new_name));
|
|
/* Lookup failed, cyclic rename or target exists? */
|
|
if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
|
|
goto exit;
|
|
|
|
old_name = fsnotify_oldname_init(old_dentry->d_name.name);
|
|
|
|
error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
|
|
dentry);
|
|
if (error) {
|
|
fsnotify_oldname_free(old_name);
|
|
goto exit;
|
|
}
|
|
d_move(old_dentry, dentry);
|
|
fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name,
|
|
d_is_dir(old_dentry),
|
|
NULL, old_dentry);
|
|
fsnotify_oldname_free(old_name);
|
|
unlock_rename(new_dir, old_dir);
|
|
dput(dentry);
|
|
return old_dentry;
|
|
exit:
|
|
if (dentry && !IS_ERR(dentry))
|
|
dput(dentry);
|
|
unlock_rename(new_dir, old_dir);
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_rename);
|
|
|
|
/**
|
|
* debugfs_initialized - Tells whether debugfs has been registered
|
|
*/
|
|
bool debugfs_initialized(void)
|
|
{
|
|
return debugfs_registered;
|
|
}
|
|
EXPORT_SYMBOL_GPL(debugfs_initialized);
|
|
|
|
static int __init debugfs_init(void)
|
|
{
|
|
int retval;
|
|
|
|
retval = sysfs_create_mount_point(kernel_kobj, "debug");
|
|
if (retval)
|
|
return retval;
|
|
|
|
retval = register_filesystem(&debug_fs_type);
|
|
if (retval)
|
|
sysfs_remove_mount_point(kernel_kobj, "debug");
|
|
else
|
|
debugfs_registered = true;
|
|
|
|
return retval;
|
|
}
|
|
core_initcall(debugfs_init);
|
|
|