kernel_optimize_test/fs/binfmt_script.c

131 lines
3.0 KiB
C
Raw Normal View History

/*
* linux/fs/binfmt_script.c
*
* Copyright (C) 1996 Martin von Löwis
* original #!-checking implemented by tytso.
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/binfmts.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/err.h>
#include <linux/fs.h>
static int load_script(struct linux_binprm *bprm)
{
const char *i_arg, *i_name;
char *cp;
struct file *file;
int retval;
if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
return -ENOEXEC;
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 08:57:29 +08:00
/*
* If the script filename will be inaccessible after exec, typically
* because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
* up now (on the assumption that the interpreter will want to load
* this file).
*/
if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
return -ENOENT;
/*
* This section does the #! interpretation.
* Sorta complicated, but hopefully it will work. -TYT
*/
allow_write_access(bprm->file);
fput(bprm->file);
bprm->file = NULL;
bprm->buf[BINPRM_BUF_SIZE - 1] = '\0';
if ((cp = strchr(bprm->buf, '\n')) == NULL)
cp = bprm->buf+BINPRM_BUF_SIZE-1;
*cp = '\0';
while (cp > bprm->buf) {
cp--;
if ((*cp == ' ') || (*cp == '\t'))
*cp = '\0';
else
break;
}
for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
if (*cp == '\0')
return -ENOEXEC; /* No interpreter name found */
i_name = cp;
i_arg = NULL;
for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++)
/* nothing */ ;
while ((*cp == ' ') || (*cp == '\t'))
*cp++ = '\0';
if (*cp)
i_arg = cp;
/*
* OK, we've parsed out the interpreter name and
* (optional) argument.
* Splice in (1) the interpreter's name for argv[0]
* (2) (optional) argument to interpreter
* (3) filename of shell script (replace argv[0])
*
* This is done in reverse order, because of how the
* user environment and arguments are stored.
*/
retval = remove_arg_zero(bprm);
if (retval)
return retval;
retval = copy_strings_kernel(1, &bprm->interp, bprm);
if (retval < 0)
return retval;
bprm->argc++;
if (i_arg) {
retval = copy_strings_kernel(1, &i_arg, bprm);
if (retval < 0)
return retval;
bprm->argc++;
}
retval = copy_strings_kernel(1, &i_name, bprm);
if (retval)
return retval;
bprm->argc++;
retval = bprm_change_interp(i_name, bprm);
exec: do not leave bprm->interp on stack If a series of scripts are executed, each triggering module loading via unprintable bytes in the script header, kernel stack contents can leak into the command line. Normally execution of binfmt_script and binfmt_misc happens recursively. However, when modules are enabled, and unprintable bytes exist in the bprm->buf, execution will restart after attempting to load matching binfmt modules. Unfortunately, the logic in binfmt_script and binfmt_misc does not expect to get restarted. They leave bprm->interp pointing to their local stack. This means on restart bprm->interp is left pointing into unused stack memory which can then be copied into the userspace argv areas. After additional study, it seems that both recursion and restart remains the desirable way to handle exec with scripts, misc, and modules. As such, we need to protect the changes to interp. This changes the logic to require allocation for any changes to the bprm->interp. To avoid adding a new kmalloc to every exec, the default value is left as-is. Only when passing through binfmt_script or binfmt_misc does an allocation take place. For a proof of concept, see DoTest.sh from: http://www.halfdog.net/Security/2012/LinuxKernelBinfmtScriptStackDataDisclosure/ Signed-off-by: Kees Cook <keescook@chromium.org> Cc: halfdog <me@halfdog.net> Cc: P J P <ppandit@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 07:05:16 +08:00
if (retval < 0)
return retval;
/*
* OK, now restart the process with the interpreter's dentry.
*/
file = open_exec(i_name);
if (IS_ERR(file))
return PTR_ERR(file);
bprm->file = file;
retval = prepare_binprm(bprm);
if (retval < 0)
return retval;
return search_binary_handler(bprm);
}
static struct linux_binfmt script_format = {
.module = THIS_MODULE,
.load_binary = load_script,
};
static int __init init_script_binfmt(void)
{
register_binfmt(&script_format);
return 0;
}
static void __exit exit_script_binfmt(void)
{
unregister_binfmt(&script_format);
}
core_initcall(init_script_binfmt);
module_exit(exit_script_binfmt);
MODULE_LICENSE("GPL");