linux_dsm_epyc7002/fs/filesystems.c
Luis R. Rodriguez 41124db869 fs: warn in case userspace lied about modprobe return
kmod <= v19 was broken -- it could return 0 to modprobe calls,
incorrectly assuming that a kernel module was built-in, whereas in
reality the module was just forming in the kernel. The reason for this
is an incorrect userspace heuristics. A userspace kmod fix is available
for it [0], however should userspace break again we could go on with
an failed get_fs_type() which is hard to debug as the request_module()
is detected as returning 0. The first suspect would be that there is
something worth with the kernel's module loader and obviously in this
case that is not the issue.

Since these issues are painful to debug complain when we know userspace
has outright lied to us.

[0] http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4

Suggested-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jessica Yu <jeyu@redhat.com>
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-06-29 20:05:43 -04:00

291 lines
6.5 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 <linux/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 (strncmp((*p)->name, name, len) == 0 &&
!(*p)->name[len])
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);
#ifdef CONFIG_SYSFS_SYSCALL
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;
}
#endif
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);
WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name);
}
if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
put_filesystem(fs);
fs = NULL;
}
return fs;
}
EXPORT_SYMBOL(get_fs_type);