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

arch/sparc64/kernel/power.c

@@ -4,8 +4,6 @@
  * Copyright (C) 1999 David S. Miller ([email protected])
  */
 
-#define __KERNEL_SYSCALLS__
-
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -14,6 +12,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/pm.h>
+#include <linux/syscalls.h>
 
 #include <asm/system.h>
 #include <asm/auxio.h>
@@ -98,7 +97,7 @@ static int powerd(void *__unused)
 
 	/* 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

@@ -1,4 +1,3 @@
-#define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
@@ -35,7 +34,7 @@ static int __init do_linuxrc(void * shell)
 	(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

@@ -9,8 +9,6 @@
  *  Simplified starting of init:  Michael A. Griffith <[email protected]> 
  */
 
-#define __KERNEL_SYSCALLS__
-
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
@@ -703,7 +701,7 @@ static void do_pre_smp_initcalls(void)
 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

@@ -18,8 +18,6 @@
 	call_usermodehelper wait flag, and remove exec_usermodehelper.
 	Rusty Russell <[email protected]>  Jan 2003
 */
-#define __KERNEL_SYSCALLS__
-
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/syscalls.h>
@@ -169,7 +167,8 @@ static int ____call_usermodehelper(void *data)
 
 	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

@@ -35,6 +35,8 @@ ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
   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

@@ -0,0 +1,23 @@
+#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