OpenCloudOS-Kernel/fs/binfmt_em86.c

111 lines
2.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/binfmt_em86.c
*
* Based on linux/fs/binfmt_script.c
* Copyright (C) 1996 Martin von Löwis
* original #!-checking implemented by tytso.
*
* em86 changes Copyright (C) 1997 Jim Paradis
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/binfmts.h>
#include <linux/elf.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/errno.h>
#define EM86_INTERP "/usr/bin/em86"
#define EM86_I_NAME "em86"
static int load_em86(struct linux_binprm *bprm)
{
const char *i_name, *i_arg;
char *interp;
struct file * file;
int retval;
struct elfhdr elf_ex;
/* Make sure this is a Linux/Intel ELF executable... */
elf_ex = *((struct elfhdr *)bprm->buf);
if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
return -ENOEXEC;
/* First of all, some simple consistency checks */
if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
(!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
!bprm->file->f_op->mmap) {
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
/* Need to be able to load the file after exec */
if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
return -ENOENT;
/* Unlike in the script case, we don't have to do any hairy
* parsing to find our interpreter... it's hardcoded!
*/
interp = EM86_INTERP;
i_name = EM86_I_NAME;
i_arg = NULL; /* We reserve the right to add an arg later */
/*
* Splice in (1) the interpreter's name for argv[0]
* (2) (optional) argument to interpreter
* (3) filename of emulated file (replace argv[0])
*
* This is done in reverse order, because of how the
* user environment and arguments are stored.
*/
remove_arg_zero(bprm);
retval = copy_string_kernel(bprm->filename, bprm);
if (retval < 0) return retval;
bprm->argc++;
if (i_arg) {
retval = copy_string_kernel(i_arg, bprm);
if (retval < 0) return retval;
bprm->argc++;
}
retval = copy_string_kernel(i_name, bprm);
if (retval < 0) return retval;
bprm->argc++;
/*
* OK, now restart the process with the interpreter's inode.
* Note that we use open_exec() as the name is now in kernel
* space, and we don't need to copy it.
*/
file = open_exec(interp);
if (IS_ERR(file))
return PTR_ERR(file);
exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2020-05-19 07:43:20 +08:00
bprm->interpreter = file;
return 0;
}
static struct linux_binfmt em86_format = {
.module = THIS_MODULE,
.load_binary = load_em86,
};
static int __init init_em86_binfmt(void)
{
register_binfmt(&em86_format);
return 0;
}
static void __exit exit_em86_binfmt(void)
{
unregister_binfmt(&em86_format);
}
core_initcall(init_em86_binfmt);
module_exit(exit_em86_binfmt);
MODULE_LICENSE("GPL");