linux-hardened/security/inode.c

328 lines
8.7 KiB
C
Raw Normal View History

/*
* inode.c - securityfs
*
* Copyright (C) 2005 Greg Kroah-Hartman <gregkh@suse.de>
*
* 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.
*
* 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/module.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/magic.h>
static struct vfsmount *mount;
static int mount_count;
/*
* TODO:
* I think I can get rid of these default_file_ops, but not quite sure...
*/
static ssize_t default_read_file(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
return 0;
}
static ssize_t default_write_file(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
return count;
}
static int default_open(struct inode *inode, struct file *file)
{
if (inode->i_private)
file->private_data = inode->i_private;
return 0;
}
static const struct file_operations default_file_ops = {
.read = default_read_file,
.write = default_write_file,
.open = default_open,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
.llseek = noop_llseek,
};
static struct inode *get_inode(struct super_block *sb, umode_t mode, dev_t dev)
{
struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
switch (mode & S_IFMT) {
default:
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_fop = &default_file_ops;
break;
case S_IFDIR:
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);
break;
}
}
return inode;
}
/* SMP-safe */
static int mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOMEM;
if (dentry->d_inode)
return -EEXIST;
inode = get_inode(dir->i_sb, mode, dev);
if (inode) {
d_instantiate(dentry, inode);
dget(dentry);
error = 0;
}
return error;
}
static int mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int res;
mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
res = mknod(dir, dentry, mode, 0);
if (!res)
inc_nlink(dir);
return res;
}
static int create(struct inode *dir, struct dentry *dentry, umode_t mode)
{
mode = (mode & S_IALLUGO) | S_IFREG;
return mknod(dir, dentry, mode, 0);
}
static inline int positive(struct dentry *dentry)
{
return dentry->d_inode && !d_unhashed(dentry);
}
static int fill_super(struct super_block *sb, void *data, int silent)
{
static struct tree_descr files[] = {{""}};
return simple_fill_super(sb, SECURITYFS_MAGIC, files);
}
static struct dentry *get_sb(struct file_system_type *fs_type,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:02:57 +02:00
int flags, const char *dev_name,
void *data)
{
return mount_single(fs_type, flags, data, fill_super);
}
static struct file_system_type fs_type = {
.owner = THIS_MODULE,
.name = "securityfs",
.mount = get_sb,
.kill_sb = kill_litter_super,
};
static int create_by_name(const char *name, umode_t mode,
struct dentry *parent,
struct dentry **dentry)
{
int error = 0;
*dentry = NULL;
/* 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 = mount->mnt_root;
mutex_lock(&parent->d_inode->i_mutex);
*dentry = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(*dentry)) {
if (S_ISDIR(mode))
error = mkdir(parent->d_inode, *dentry, mode);
else
error = create(parent->d_inode, *dentry, mode);
if (error)
dput(*dentry);
} else
error = PTR_ERR(*dentry);
mutex_unlock(&parent->d_inode->i_mutex);
return error;
}
/**
* 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 is the basic "create a file" 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 erorr 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)
{
struct dentry *dentry = NULL;
int error;
pr_debug("securityfs: creating file '%s'\n",name);
error = simple_pin_fs(&fs_type, &mount, &mount_count);
if (error) {
dentry = ERR_PTR(error);
goto exit;
}
error = create_by_name(name, mode, parent, &dentry);
if (error) {
dentry = ERR_PTR(error);
simple_release_fs(&mount, &mount_count);
goto exit;
}
if (dentry->d_inode) {
if (fops)
dentry->d_inode->i_fop = fops;
if (data)
dentry->d_inode->i_private = data;
}
exit:
return dentry;
}
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, %NULL will be returned.
*
* If securityfs is not enabled in the kernel, the value %-ENODEV is
* returned. It is not wise to check for this value, but rather, check for
* %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
* code.
*/
struct dentry *securityfs_create_dir(const char *name, struct dentry *parent)
{
return securityfs_create_file(name,
S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
parent, NULL, NULL);
}
EXPORT_SYMBOL_GPL(securityfs_create_dir);
/**
* 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.
*/
void securityfs_remove(struct dentry *dentry)
{
struct dentry *parent;
if (!dentry || IS_ERR(dentry))
return;
parent = dentry->d_parent;
if (!parent || !parent->d_inode)
return;
mutex_lock(&parent->d_inode->i_mutex);
if (positive(dentry)) {
if (dentry->d_inode) {
if (S_ISDIR(dentry->d_inode->i_mode))
simple_rmdir(parent->d_inode, dentry);
else
simple_unlink(parent->d_inode, dentry);
dput(dentry);
}
}
mutex_unlock(&parent->d_inode->i_mutex);
simple_release_fs(&mount, &mount_count);
}
EXPORT_SYMBOL_GPL(securityfs_remove);
static struct kobject *security_kobj;
static int __init securityfs_init(void)
{
int retval;
security_kobj = kobject_create_and_add("security", kernel_kobj);
if (!security_kobj)
return -EINVAL;
retval = register_filesystem(&fs_type);
if (retval)
kobject_put(security_kobj);
return retval;
}
core_initcall(securityfs_init);
MODULE_LICENSE("GPL");