mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 20:51:44 +00:00
7f78e03513
Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
287 lines
6.4 KiB
C
287 lines
6.4 KiB
C
/*
|
|
* linux/fs/filesystems.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* table of configured filesystems
|
|
*/
|
|
|
|
#include <linux/syscalls.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/kmod.h>
|
|
#include <linux/init.h>
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
/*
|
|
* Handling of filesystem drivers list.
|
|
* Rules:
|
|
* Inclusion to/removals from/scanning of list are protected by spinlock.
|
|
* During the unload module must call unregister_filesystem().
|
|
* We can access the fields of list element if:
|
|
* 1) spinlock is held or
|
|
* 2) we hold the reference to the module.
|
|
* The latter can be guaranteed by call of try_module_get(); if it
|
|
* returned 0 we must skip the element, otherwise we got the reference.
|
|
* Once the reference is obtained we can drop the spinlock.
|
|
*/
|
|
|
|
static struct file_system_type *file_systems;
|
|
static DEFINE_RWLOCK(file_systems_lock);
|
|
|
|
/* WARNING: This can be used only if we _already_ own a reference */
|
|
void get_filesystem(struct file_system_type *fs)
|
|
{
|
|
__module_get(fs->owner);
|
|
}
|
|
|
|
void put_filesystem(struct file_system_type *fs)
|
|
{
|
|
module_put(fs->owner);
|
|
}
|
|
|
|
static struct file_system_type **find_filesystem(const char *name, unsigned len)
|
|
{
|
|
struct file_system_type **p;
|
|
for (p=&file_systems; *p; p=&(*p)->next)
|
|
if (strlen((*p)->name) == len &&
|
|
strncmp((*p)->name, name, len) == 0)
|
|
break;
|
|
return p;
|
|
}
|
|
|
|
/**
|
|
* register_filesystem - register a new filesystem
|
|
* @fs: the file system structure
|
|
*
|
|
* Adds the file system passed to the list of file systems the kernel
|
|
* is aware of for mount and other syscalls. Returns 0 on success,
|
|
* or a negative errno code on an error.
|
|
*
|
|
* The &struct file_system_type that is passed is linked into the kernel
|
|
* structures and must not be freed until the file system has been
|
|
* unregistered.
|
|
*/
|
|
|
|
int register_filesystem(struct file_system_type * fs)
|
|
{
|
|
int res = 0;
|
|
struct file_system_type ** p;
|
|
|
|
BUG_ON(strchr(fs->name, '.'));
|
|
if (fs->next)
|
|
return -EBUSY;
|
|
write_lock(&file_systems_lock);
|
|
p = find_filesystem(fs->name, strlen(fs->name));
|
|
if (*p)
|
|
res = -EBUSY;
|
|
else
|
|
*p = fs;
|
|
write_unlock(&file_systems_lock);
|
|
return res;
|
|
}
|
|
|
|
EXPORT_SYMBOL(register_filesystem);
|
|
|
|
/**
|
|
* unregister_filesystem - unregister a file system
|
|
* @fs: filesystem to unregister
|
|
*
|
|
* Remove a file system that was previously successfully registered
|
|
* with the kernel. An error is returned if the file system is not found.
|
|
* Zero is returned on a success.
|
|
*
|
|
* Once this function has returned the &struct file_system_type structure
|
|
* may be freed or reused.
|
|
*/
|
|
|
|
int unregister_filesystem(struct file_system_type * fs)
|
|
{
|
|
struct file_system_type ** tmp;
|
|
|
|
write_lock(&file_systems_lock);
|
|
tmp = &file_systems;
|
|
while (*tmp) {
|
|
if (fs == *tmp) {
|
|
*tmp = fs->next;
|
|
fs->next = NULL;
|
|
write_unlock(&file_systems_lock);
|
|
synchronize_rcu();
|
|
return 0;
|
|
}
|
|
tmp = &(*tmp)->next;
|
|
}
|
|
write_unlock(&file_systems_lock);
|
|
|
|
return -EINVAL;
|
|
}
|
|
|
|
EXPORT_SYMBOL(unregister_filesystem);
|
|
|
|
static int fs_index(const char __user * __name)
|
|
{
|
|
struct file_system_type * tmp;
|
|
struct filename *name;
|
|
int err, index;
|
|
|
|
name = getname(__name);
|
|
err = PTR_ERR(name);
|
|
if (IS_ERR(name))
|
|
return err;
|
|
|
|
err = -EINVAL;
|
|
read_lock(&file_systems_lock);
|
|
for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) {
|
|
if (strcmp(tmp->name, name->name) == 0) {
|
|
err = index;
|
|
break;
|
|
}
|
|
}
|
|
read_unlock(&file_systems_lock);
|
|
putname(name);
|
|
return err;
|
|
}
|
|
|
|
static int fs_name(unsigned int index, char __user * buf)
|
|
{
|
|
struct file_system_type * tmp;
|
|
int len, res;
|
|
|
|
read_lock(&file_systems_lock);
|
|
for (tmp = file_systems; tmp; tmp = tmp->next, index--)
|
|
if (index <= 0 && try_module_get(tmp->owner))
|
|
break;
|
|
read_unlock(&file_systems_lock);
|
|
if (!tmp)
|
|
return -EINVAL;
|
|
|
|
/* OK, we got the reference, so we can safely block */
|
|
len = strlen(tmp->name) + 1;
|
|
res = copy_to_user(buf, tmp->name, len) ? -EFAULT : 0;
|
|
put_filesystem(tmp);
|
|
return res;
|
|
}
|
|
|
|
static int fs_maxindex(void)
|
|
{
|
|
struct file_system_type * tmp;
|
|
int index;
|
|
|
|
read_lock(&file_systems_lock);
|
|
for (tmp = file_systems, index = 0 ; tmp ; tmp = tmp->next, index++)
|
|
;
|
|
read_unlock(&file_systems_lock);
|
|
return index;
|
|
}
|
|
|
|
/*
|
|
* Whee.. Weird sysv syscall.
|
|
*/
|
|
SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2)
|
|
{
|
|
int retval = -EINVAL;
|
|
|
|
switch (option) {
|
|
case 1:
|
|
retval = fs_index((const char __user *) arg1);
|
|
break;
|
|
|
|
case 2:
|
|
retval = fs_name(arg1, (char __user *) arg2);
|
|
break;
|
|
|
|
case 3:
|
|
retval = fs_maxindex();
|
|
break;
|
|
}
|
|
return retval;
|
|
}
|
|
|
|
int __init get_filesystem_list(char *buf)
|
|
{
|
|
int len = 0;
|
|
struct file_system_type * tmp;
|
|
|
|
read_lock(&file_systems_lock);
|
|
tmp = file_systems;
|
|
while (tmp && len < PAGE_SIZE - 80) {
|
|
len += sprintf(buf+len, "%s\t%s\n",
|
|
(tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev",
|
|
tmp->name);
|
|
tmp = tmp->next;
|
|
}
|
|
read_unlock(&file_systems_lock);
|
|
return len;
|
|
}
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
static int filesystems_proc_show(struct seq_file *m, void *v)
|
|
{
|
|
struct file_system_type * tmp;
|
|
|
|
read_lock(&file_systems_lock);
|
|
tmp = file_systems;
|
|
while (tmp) {
|
|
seq_printf(m, "%s\t%s\n",
|
|
(tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev",
|
|
tmp->name);
|
|
tmp = tmp->next;
|
|
}
|
|
read_unlock(&file_systems_lock);
|
|
return 0;
|
|
}
|
|
|
|
static int filesystems_proc_open(struct inode *inode, struct file *file)
|
|
{
|
|
return single_open(file, filesystems_proc_show, NULL);
|
|
}
|
|
|
|
static const struct file_operations filesystems_proc_fops = {
|
|
.open = filesystems_proc_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
static int __init proc_filesystems_init(void)
|
|
{
|
|
proc_create("filesystems", 0, NULL, &filesystems_proc_fops);
|
|
return 0;
|
|
}
|
|
module_init(proc_filesystems_init);
|
|
#endif
|
|
|
|
static struct file_system_type *__get_fs_type(const char *name, int len)
|
|
{
|
|
struct file_system_type *fs;
|
|
|
|
read_lock(&file_systems_lock);
|
|
fs = *(find_filesystem(name, len));
|
|
if (fs && !try_module_get(fs->owner))
|
|
fs = NULL;
|
|
read_unlock(&file_systems_lock);
|
|
return fs;
|
|
}
|
|
|
|
struct file_system_type *get_fs_type(const char *name)
|
|
{
|
|
struct file_system_type *fs;
|
|
const char *dot = strchr(name, '.');
|
|
int len = dot ? dot - name : strlen(name);
|
|
|
|
fs = __get_fs_type(name, len);
|
|
if (!fs && (request_module("fs-%.*s", len, name) == 0))
|
|
fs = __get_fs_type(name, len);
|
|
|
|
if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
|
|
put_filesystem(fs);
|
|
fs = NULL;
|
|
}
|
|
return fs;
|
|
}
|
|
|
|
EXPORT_SYMBOL(get_fs_type);
|