Files
linux/security/inode.c
Linus Torvalds 7cd122b552 Merge tag 'pull-persistency' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull persistent dentry infrastructure and conversion from Al Viro:
 "Some filesystems use a kinda-sorta controlled dentry refcount leak to
  pin dentries of created objects in dcache (and undo it when removing
  those). A reference is grabbed and not released, but it's not actually
  _stored_ anywhere.

  That works, but it's hard to follow and verify; among other things, we
  have no way to tell _which_ of the increments is intended to be an
  unpaired one. Worse, on removal we need to decide whether the
  reference had already been dropped, which can be non-trivial if that
  removal is on umount and we need to figure out if this dentry is
  pinned due to e.g. unlink() not done. Usually that is handled by using
  kill_litter_super() as ->kill_sb(), but there are open-coded special
  cases of the same (consider e.g. /proc/self).

  Things get simpler if we introduce a new dentry flag
  (DCACHE_PERSISTENT) marking those "leaked" dentries. Having it set
  claims responsibility for +1 in refcount.

  The end result this series is aiming for:

   - get these unbalanced dget() and dput() replaced with new primitives
     that would, in addition to adjusting refcount, set and clear
     persistency flag.

   - instead of having kill_litter_super() mess with removing the
     remaining "leaked" references (e.g. for all tmpfs files that hadn't
     been removed prior to umount), have the regular
     shrink_dcache_for_umount() strip DCACHE_PERSISTENT of all dentries,
     dropping the corresponding reference if it had been set. After that
     kill_litter_super() becomes an equivalent of kill_anon_super().

  Doing that in a single step is not feasible - it would affect too many
  places in too many filesystems. It has to be split into a series.

  This work has really started early in 2024; quite a few preliminary
  pieces have already gone into mainline. This chunk is finally getting
  to the meat of that stuff - infrastructure and most of the conversions
  to it.

  Some pieces are still sitting in the local branches, but the bulk of
  that stuff is here"

* tag 'pull-persistency' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (54 commits)
  d_make_discardable(): warn if given a non-persistent dentry
  kill securityfs_recursive_remove()
  convert securityfs
  get rid of kill_litter_super()
  convert rust_binderfs
  convert nfsctl
  convert rpc_pipefs
  convert hypfs
  hypfs: swich hypfs_create_u64() to returning int
  hypfs: switch hypfs_create_str() to returning int
  hypfs: don't pin dentries twice
  convert gadgetfs
  gadgetfs: switch to simple_remove_by_name()
  convert functionfs
  functionfs: switch to simple_remove_by_name()
  functionfs: fix the open/removal races
  functionfs: need to cancel ->reset_work in ->kill_sb()
  functionfs: don't bother with ffs->ref in ffs_data_{opened,closed}()
  functionfs: don't abuse ffs_data_closed() on fs shutdown
  convert selinuxfs
  ...
2025-12-05 14:36:21 -08:00

381 lines
11 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* inode.c - securityfs
*
* Copyright (C) 2005 Greg Kroah-Hartman <gregkh@suse.de>
*
* Based on fs/debugfs/inode.c which had the following copyright notice:
* Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2004 IBM Inc.
*/
/* #define DEBUG */
#include <linux/sysfs.h>
#include <linux/kobject.h>
#include <linux/fs.h>
#include <linux/fs_context.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/lsm_hooks.h>
#include <linux/magic.h>
#include "lsm.h"
static struct vfsmount *mount;
static int mount_count;
static void securityfs_free_inode(struct inode *inode)
{
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
free_inode_nonrcu(inode);
}
static const struct super_operations securityfs_super_operations = {
.statfs = simple_statfs,
.free_inode = securityfs_free_inode,
};
static int securityfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
static const struct tree_descr files[] = {{""}};
int error;
error = simple_fill_super(sb, SECURITYFS_MAGIC, files);
if (error)
return error;
sb->s_op = &securityfs_super_operations;
return 0;
}
static int securityfs_get_tree(struct fs_context *fc)
{
return get_tree_single(fc, securityfs_fill_super);
}
static const struct fs_context_operations securityfs_context_ops = {
.get_tree = securityfs_get_tree,
};
static int securityfs_init_fs_context(struct fs_context *fc)
{
fc->ops = &securityfs_context_ops;
return 0;
}
static struct file_system_type fs_type = {
.owner = THIS_MODULE,
.name = "securityfs",
.init_fs_context = securityfs_init_fs_context,
.kill_sb = kill_anon_super,
};
/**
* securityfs_create_dentry - create a dentry in the securityfs 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 securityfs 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.
* @iops: a point to a struct of inode_operations that should be used for
* this file/dir
*
* This is the basic "create a file/dir/symlink" function for
* securityfs. It allows for a wide range of flexibility in creating
* a file, or a directory (if you want to create a directory, the
* securityfs_create_dir() function is recommended to be used
* instead).
*
* This function returns a pointer to a dentry if it succeeds. This
* pointer must be passed to the securityfs_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, the
* function will return the error value (via ERR_PTR).
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned.
*/
static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops,
const struct inode_operations *iops)
{
struct dentry *dentry;
struct inode *dir, *inode;
int error;
bool pinned = false;
if (!(mode & S_IFMT))
mode = (mode & S_IALLUGO) | S_IFREG;
pr_debug("securityfs: creating file '%s'\n",name);
if (!parent) {
error = simple_pin_fs(&fs_type, &mount, &mount_count);
if (error)
return ERR_PTR(error);
pinned = true;
parent = mount->mnt_root;
}
inode = new_inode(parent->d_sb);
if (unlikely(!inode)) {
dentry = ERR_PTR(-ENOMEM);
goto out;
}
dir = d_inode(parent);
dentry = simple_start_creating(parent, name);
if (IS_ERR(dentry)) {
iput(inode);
goto out;
}
inode->i_ino = get_next_ino();
inode->i_mode = mode;
simple_inode_init_ts(inode);
inode->i_private = data;
if (S_ISDIR(mode)) {
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
inc_nlink(inode);
inc_nlink(dir);
} else if (S_ISLNK(mode)) {
inode->i_op = iops ? iops : &simple_symlink_inode_operations;
inode->i_link = data;
} else {
inode->i_fop = fops;
}
d_make_persistent(dentry, inode);
simple_done_creating(dentry);
return dentry; // borrowed
out:
if (pinned)
simple_release_fs(&mount, &mount_count);
return dentry;
}
/**
* securityfs_create_file - create a file in the securityfs 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 securityfs 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 function creates a file in securityfs with the given @name.
*
* This function returns a pointer to a dentry if it succeeds. This
* pointer must be passed to the securityfs_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, the function will return
* the error value (via ERR_PTR).
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned.
*/
struct dentry *securityfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
return securityfs_create_dentry(name, mode, parent, data, fops, NULL);
}
EXPORT_SYMBOL_GPL(securityfs_create_file);
/**
* securityfs_create_dir - create a directory in the securityfs 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 securityfs filesystem.
*
* This function creates a directory in securityfs with the given @name.
*
* This function returns a pointer to a dentry if it succeeds. This
* pointer must be passed to the securityfs_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, the function will return
* the error value (via ERR_PTR).
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned.
*/
struct dentry *securityfs_create_dir(const char *name, struct dentry *parent)
{
return securityfs_create_file(name, S_IFDIR | 0755, parent, NULL, NULL);
}
EXPORT_SYMBOL_GPL(securityfs_create_dir);
/**
* securityfs_create_symlink - create a symlink in the securityfs filesystem
*
* @name: a pointer to a string containing the name of the symlink to
* create.
* @parent: a pointer to the parent dentry for the symlink. This should be a
* directory dentry if set. If this parameter is %NULL, then the
* directory will be created in the root of the securityfs filesystem.
* @target: a pointer to a string containing the name of the symlink's target.
* If this parameter is %NULL, then the @iops parameter needs to be
* setup to handle .readlink and .get_link inode_operations.
* @iops: a pointer to the struct inode_operations to use for the symlink. If
* this parameter is %NULL, then the default simple_symlink_inode
* operations will be used.
*
* This function creates a symlink in securityfs with the given @name.
*
* This function returns a pointer to a dentry if it succeeds. This
* pointer must be passed to the securityfs_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, the function will return
* the error value (via ERR_PTR).
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned.
*/
struct dentry *securityfs_create_symlink(const char *name,
struct dentry *parent,
const char *target,
const struct inode_operations *iops)
{
struct dentry *dent;
char *link = NULL;
if (target) {
link = kstrdup(target, GFP_KERNEL);
if (!link)
return ERR_PTR(-ENOMEM);
}
dent = securityfs_create_dentry(name, S_IFLNK | 0444, parent,
link, NULL, iops);
if (IS_ERR(dent))
kfree(link);
return dent;
}
EXPORT_SYMBOL_GPL(securityfs_create_symlink);
static void remove_one(struct dentry *victim)
{
if (victim->d_parent == victim->d_sb->s_root)
simple_release_fs(&mount, &mount_count);
}
/**
* securityfs_remove - removes a file or directory from the securityfs filesystem
*
* @dentry: a pointer to a the dentry of the file or directory to be removed.
*
* This function removes a file or directory in securityfs that was previously
* created with a call to another securityfs function (like
* securityfs_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.
*
* AV: when applied to directory it will take all children out; no need to call
* it for descendents if ancestor is getting killed.
*/
void securityfs_remove(struct dentry *dentry)
{
if (IS_ERR_OR_NULL(dentry))
return;
simple_pin_fs(&fs_type, &mount, &mount_count);
simple_recursive_removal(dentry, remove_one);
simple_release_fs(&mount, &mount_count);
}
EXPORT_SYMBOL_GPL(securityfs_remove);
#ifdef CONFIG_SECURITY
#include <linux/spinlock.h>
static struct dentry *lsm_dentry;
static ssize_t lsm_read(struct file *filp, char __user *buf, size_t count,
loff_t *ppos)
{
int i;
static char *str;
static size_t len;
static DEFINE_SPINLOCK(lock);
/* NOTE: we never free or modify the string once it is set */
if (unlikely(!str || !len)) {
char *str_tmp;
size_t len_tmp = 0;
for (i = 0; i < lsm_active_cnt; i++)
/* the '+ 1' accounts for either a comma or a NUL */
len_tmp += strlen(lsm_idlist[i]->name) + 1;
str_tmp = kmalloc(len_tmp, GFP_KERNEL);
if (!str_tmp)
return -ENOMEM;
str_tmp[0] = '\0';
for (i = 0; i < lsm_active_cnt; i++) {
if (i > 0)
strcat(str_tmp, ",");
strcat(str_tmp, lsm_idlist[i]->name);
}
spin_lock(&lock);
if (!str) {
str = str_tmp;
len = len_tmp - 1;
} else
kfree(str_tmp);
spin_unlock(&lock);
}
return simple_read_from_buffer(buf, count, ppos, str, len);
}
static const struct file_operations lsm_ops = {
.read = lsm_read,
.llseek = generic_file_llseek,
};
#endif
int __init securityfs_init(void)
{
int retval;
retval = sysfs_create_mount_point(kernel_kobj, "security");
if (retval)
return retval;
retval = register_filesystem(&fs_type);
if (retval) {
sysfs_remove_mount_point(kernel_kobj, "security");
return retval;
}
#ifdef CONFIG_SECURITY
lsm_dentry = securityfs_create_file("lsm", 0444, NULL, NULL,
&lsm_ops);
#endif
return 0;
}