[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 <arnd@arndb.de>
Cc: Andi Kleen <ak@muc.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ian Molton <spyro@f2s.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Hirokazu Takata <takata.hirokazu@renesas.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp>
Cc: Chris Zankel <chris@zankel.net>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 31 insertions, 11 deletions

diff --git a/arch/sparc64/kernel/power.c b/arch/sparc64/kernel/power.c
index e55466c..0b9c706 100644
--- a/arch/sparc64/kernel/power.c
+++ b/arch/sparc64/kernel/power.c
@@ -4,8 +4,6 @@
  * Copyright (C) 1999 David S. Miller (davem@redhat.com)
  */
 
-#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 @@ again:
 
 	/* 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;
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index a06f037..919a80c 100644
--- a/init/do_mounts_initrd.c
+++ b/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)
diff --git a/init/main.c b/init/main.c
index 0766e69..a49b002 100644
--- a/init/main.c
+++ b/init/main.c
@@ -9,8 +9,6 @@
  *  Simplified starting of init:  Michael A. Griffith <grif@acm.org> 
  */
 
-#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)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index f8121b9..bb4e29d 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -18,8 +18,6 @@
 	call_usermodehelper wait flag, and remove exec_usermodehelper.
 	Rusty Russell <rusty@rustcorp.com.au>  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;
diff --git a/lib/Makefile b/lib/Makefile
index ddf3e67..4d752be 100644
--- a/lib/Makefile
+++ b/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
diff --git a/lib/execve.c b/lib/execve.c
new file mode 100644
index 0000000..2667ebc
--- /dev/null
+++ b/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