[PATCH] introduce kernel_execve

The use of execve() in the kernel is dubious, since it relies on the
__KERNEL_SYSCALLS__ mechanism that stores the result in a global errno
variable. As a first step of getting rid of this, change all users to a
global kernel_execve function that returns a proper error code.

This function is a terrible hack, and a later patch removes it again after the
kernel syscalls are gone.

Signed-off-by: Arnd Bergmann <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Paul Mackerras <[e-mail]>
Cc: Benjamin Herrenschmidt <[e-mail]>
Cc: Richard Henderson <[e-mail]>
Cc: Ivan Kokshaysky <[e-mail]>
Cc: Russell King <[e-mail]>
Cc: Ian Molton <[e-mail]>
Cc: Mikael Starvik <[e-mail]>
Cc: David Howells <[e-mail]>
Cc: Yoshinori Sato <[e-mail]>
Cc: Hirokazu Takata <[e-mail]>
Cc: Ralf Baechle <[e-mail]>
Cc: Kyle McMartin <[e-mail]>
Cc: Heiko Carstens <[e-mail]>
Cc: Martin Schwidefsky <[e-mail]>
Cc: Paul Mundt <[e-mail]>
Cc: Kazumoto Kojima <[e-mail]>
Cc: Richard Curnow <[e-mail]>
Cc: William Lee Irwin III <[e-mail]>
Cc: "David S. Miller" <[e-mail]>
Cc: Jeff Dike <[e-mail]>
Cc: Paolo 'Blaisorblade' Giarrusso <[e-mail]>
Cc: Miles Bader <[e-mail]>
Cc: Chris Zankel <[e-mail]>
Cc: "Luck, Tony" <[e-mail]>
Cc: Geert Uytterhoeven <[e-mail]>
Cc: Roman Zippel <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/sparc64/kernel/power.c

···
  * Copyright (C) 1999 David S. Miller ([e-mail])
  */
 
-#define __KERNEL_SYSCALLS__
-
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
···
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/pm.h>
+#include <linux/syscalls.h>
 
 #include <asm/system.h>
 #include <asm/auxio.h>
···
 
 	/* Ok, down we go... */
 	button_pressed = 0;
-	if (execve("/sbin/shutdown", argv, envp) < 0) {
+	if (kernel_execve("/sbin/shutdown", argv, envp) < 0) {
 		printk("powerd: shutdown execution failed\n");
 		add_wait_queue(&powerd_wait, &wait);
 		goto again;

init/do_mounts_initrd.c

···
-#define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
···
 	(void) sys_open("/dev/console",O_RDWR,0);
 	(void) sys_dup(0);
 	(void) sys_dup(0);
-	return execve(shell, argv, envp_init);
+	return kernel_execve(shell, argv, envp_init);
 }
 
 static void __init handle_initrd(void)

init/main.c

···
  *  Simplified starting of init:  Michael A. Griffith <[e-mail]> 
  */
 
-#define __KERNEL_SYSCALLS__
-
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
···
 static void run_init_process(char *init_filename)
 {
 	argv_init[0] = init_filename;
-	execve(init_filename, argv_init, envp_init);
+	kernel_execve(init_filename, argv_init, envp_init);
 }
 
 static int init(void * unused)

kernel/kmod.c

···
 	call_usermodehelper wait flag, and remove exec_usermodehelper.
 	Rusty Russell <[e-mail]>  Jan 2003
 */
-#define __KERNEL_SYSCALLS__
-
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/syscalls.h>
···
 
 	retval = -EPERM;
 	if (current->fs->root)
-		retval = execve(sub_info->path, sub_info->argv, sub_info->envp);
+		retval = kernel_execve(sub_info->path,
+				sub_info->argv, sub_info->envp);
 
 	/* Exec failed? */
 	sub_info->retval = retval;

lib/Makefile

···
   lib-y += dec_and_lock.o
 endif
 
+lib-y += execve.o
+
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC32)	+= crc32.o

lib/execve.c

···
+#include <asm/bug.h>
+#include <asm/uaccess.h>
+
+#define __KERNEL_SYSCALLS__
+static int errno __attribute__((unused));
+#include <asm/unistd.h>
+
+#ifdef _syscall3
+int kernel_execve (const char *filename, char *const argv[], char *const envp[])
+								__attribute__((__weak__));
+int kernel_execve (const char *filename, char *const argv[], char *const envp[])
+{
+	mm_segment_t fs = get_fs();
+	int ret;
+
+	WARN_ON(segment_eq(fs, USER_DS));
+	ret = execve(filename, (char **)argv, (char **)envp);
+	if (ret)
+		ret = -errno;
+
+	return ret;
+}
+#endif