[PATCH] provide kernel_execve on all architectures

This adds the new kernel_execve function on all architectures that were using
_syscall3() to implement execve.

The implementation uses code from the _syscall3 macros provided in the
unistd.h header file.  I don't have cross-compilers for any of these
architectures, so the patch is untested with the exception of i386.

Most architectures can probably implement this in a nicer way in assembly or
by combining it with the sys_execve implementation itself, but this should do
it for now.

[bunk@stusta.de: m68knommu build fix]
[markh@osdl.org: build fix]
[bero@arklinux.org: build fix]
[ralf@linux-mips.org: mips fix]
[schwidefsky@de.ibm.com: s390 fix]
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: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Bernhard Rosenkraenzer <bero@arklinux.org>
Signed-off-by: Mark Haverkamp <markh@osdl.org>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

16 files changed, 300 insertions, 12 deletions

diff --git a/arch/frv/kernel/Makefile b/arch/frv/kernel/Makefile
index 32db349..e8f73ed 100644
--- a/arch/frv/kernel/Makefile
+++ b/arch/frv/kernel/Makefile
@@ -8,7 +8,7 @@ heads-$(CONFIG_MMU)		:= head-mmu-fr451.o
 extra-y:= head.o init_task.o vmlinux.lds
 
 obj-y := $(heads-y) entry.o entry-table.o break.o switch_to.o kernel_thread.o \
-	 process.o traps.o ptrace.o signal.o dma.o \
+	 kernel_execve.o process.o traps.o ptrace.o signal.o dma.o \
 	 sys_frv.o time.o semaphore.o setup.o frv_ksyms.o \
 	 debug-stub.o irq.o sleep.o uaccess.o
 
diff --git a/arch/frv/kernel/kernel_execve.S b/arch/frv/kernel/kernel_execve.S
new file mode 100644
index 0000000..9b074a1
--- /dev/null
+++ b/arch/frv/kernel/kernel_execve.S
@@ -0,0 +1,33 @@
+/* in-kernel program execution
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+###############################################################################
+#
+# Do a system call from kernel instead of calling sys_execve so we end up with
+# proper pt_regs.
+#
+# int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+#
+# On entry: GR8/GR9/GR10: arguments to function
+# On return: GR8: syscall return.
+#
+###############################################################################
+	.globl		kernel_execve
+	.type		kernel_execve,@function
+kernel_execve:
+	setlos		__NR_execve,gr7
+	tira		gr0,#0
+	bralr
+
+	.size		kernel_execve,.-kernel_execve
diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c
index 0f61b7a..302a2df 100644
--- a/arch/h8300/kernel/sys_h8300.c
+++ b/arch/h8300/kernel/sys_h8300.c
@@ -25,6 +25,7 @@
 #include <asm/cachectl.h>
 #include <asm/traps.h>
 #include <asm/ipc.h>
+#include <asm/unistd.h>
 
 /*
  * sys_pipe() is the normal C calling standard for creating
@@ -280,3 +281,26 @@ asmlinkage void syscall_print(void *dummy,...)
                ((regs->pc)&0xffffff)-2,regs->orig_er0,regs->er1,regs->er2,regs->er3,regs->er0);
 }
 #endif
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register long res __asm__("er0");
+	register const char * _a __asm__("er1") = filename;
+	register void *_b __asm__("er2") = argv;
+	register void *_c __asm__("er3") = envp;
+	__asm__ __volatile__ ("mov.l %1,er0\n\t"
+			"trapa	#0\n\t"
+			: "=r" (res)
+			: "g" (__NR_execve),
+			  "g" (_a),
+			  "g" (_b),
+			  "g" (_c)
+			: "cc", "memory");
+	return res;
+}
+
+
diff --git a/arch/i386/kernel/sys_i386.c b/arch/i386/kernel/sys_i386.c
index dc6e3bb..4048397 100644
--- a/arch/i386/kernel/sys_i386.c
+++ b/arch/i386/kernel/sys_i386.c
@@ -21,6 +21,7 @@
 #include <linux/utsname.h>
 
 #include <asm/uaccess.h>
+#include <asm/unistd.h>
 #include <asm/ipc.h>
 
 /*
@@ -248,3 +249,17 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name)
 
 	return error;
 }
+
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	long __res;
+	asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
+	: "=a" (__res)
+	: "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory");
+	return __res;
+}
diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c
index 7c29396..b567351 100644
--- a/arch/m32r/kernel/sys_m32r.c
+++ b/arch/m32r/kernel/sys_m32r.c
@@ -25,6 +25,8 @@
 #include <asm/cachectl.h>
 #include <asm/cacheflush.h>
 #include <asm/ipc.h>
+#include <asm/syscall.h>
+#include <asm/unistd.h>
 
 /*
  * sys_tas() - test-and-set
@@ -223,3 +225,21 @@ asmlinkage int sys_cachectl(char *addr, int nbytes, int op)
 	return -ENOSYS;
 }
 
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register long __scno __asm__ ("r7") = __NR_execve;
+	register long __arg3 __asm__ ("r2") = (long)(envp);
+	register long __arg2 __asm__ ("r1") = (long)(argv);
+	register long __res __asm__ ("r0") = (long)(filename);
+	__asm__ __volatile__ (
+		"trap #" SYSCALL_VECTOR "|| nop"
+		: "=r" (__res)
+		: "r" (__scno), "0" (__res), "r" (__arg2),
+			"r" (__arg3)
+		: "memory");
+	return __res;
+}
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 143c552..90238a8 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -27,6 +27,7 @@
 #include <asm/traps.h>
 #include <asm/ipc.h>
 #include <asm/page.h>
+#include <asm/unistd.h>
 
 /*
  * sys_pipe() is the normal C calling standard for creating
@@ -663,3 +664,18 @@ asmlinkage int sys_getpagesize(void)
 {
 	return PAGE_SIZE;
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register long __res asm ("%d0") = __NR_execve;
+	register long __a asm ("%d1") = (long)(filename);
+	register long __b asm ("%d2") = (long)(argv);
+	register long __c asm ("%d3") = (long)(envp);
+	asm volatile ("trap  #0" : "+d" (__res)
+			: "d" (__a), "d" (__b), "d" (__c));
+	return __res;
+}
diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c
index d87e1e0..c3494b8 100644
--- a/arch/m68knommu/kernel/sys_m68k.c
+++ b/arch/m68knommu/kernel/sys_m68k.c
@@ -26,6 +26,7 @@
 #include <asm/traps.h>
 #include <asm/ipc.h>
 #include <asm/cacheflush.h>
+#include <asm/unistd.h>
 
 /*
  * sys_pipe() is the normal C calling standard for creating
@@ -206,3 +207,17 @@ asmlinkage int sys_getpagesize(void)
 	return PAGE_SIZE;
 }
 
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register long __res asm ("%d0") = __NR_execve;
+	register long __a asm ("%d1") = (long)(filename);
+	register long __b asm ("%d2") = (long)(argv);
+	register long __c asm ("%d3") = (long)(envp);
+	asm volatile ("trap  #0" : "+d" (__res)
+			: "d" (__a), "d" (__b), "d" (__c));
+	return __res;
+}
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 970e3e9..26e1a7e 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -406,3 +406,32 @@ asmlinkage void bad_stack(void)
 {
 	do_exit(SIGSEGV);
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register unsigned long __a0 asm("$4") = (unsigned long) filename;
+	register unsigned long __a1 asm("$5") = (unsigned long) argv;
+	register unsigned long __a2 asm("$6") = (unsigned long) envp;
+	register unsigned long __a3 asm("$7");
+	unsigned long __v0;
+
+	__asm__ volatile ("					\n"
+	"	.set	noreorder				\n"
+	"	li	$2, %5		# __NR_execve		\n"
+	"	syscall						\n"
+	"	move	%0, $2					\n"
+	"	.set	reorder					\n"
+	: "=&r" (__v0), "=r" (__a3)
+	: "r" (__a0), "r" (__a1), "r" (__a2), "i" (__NR_execve)
+	: "$2", "$8", "$9", "$10", "$11", "$12", "$13", "$14", "$15", "$24",
+	  "memory");
+
+	if (__a3 == 0)
+		return __v0;
+
+	return -__v0;
+}
diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
index 50b4bbd..5f66840 100644
--- a/arch/ppc/kernel/misc.S
+++ b/arch/ppc/kernel/misc.S
@@ -942,20 +942,16 @@ _GLOBAL(kernel_thread)
 	addi	r1,r1,16
 	blr
 
+_GLOBAL(kernel_execve)
+	li	r0,__NR_execve
+	sc
+	bnslr
+	neg	r3,r3
+	blr
+
 /*
  * This routine is just here to keep GCC happy - sigh...
  */
 _GLOBAL(__main)
 	blr
 
-#define SYSCALL(name) \
-_GLOBAL(name) \
-	li	r0,__NR_##name; \
-	sc; \
-	bnslr; \
-	lis	r4,errno@ha; \
-	stw	r3,errno@l(r4); \
-	li	r3,-1; \
-	blr
-
-SYSCALL(execve)
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index e351780..584ed95 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -27,6 +27,7 @@
 #include <linux/file.h>
 #include <linux/utsname.h>
 #include <linux/personality.h>
+#include <linux/unistd.h>
 
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
@@ -266,3 +267,22 @@ s390_fadvise64_64(struct fadvise64_64_args __user *args)
 	return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice);
 }
 
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register const char *__arg1 asm("2") = filename;
+	register char *const*__arg2 asm("3") = argv;
+	register char *const*__arg3 asm("4") = envp;
+	register long __svcres asm("2");
+	asm volatile(
+		"svc %b1"
+		: "=d" (__svcres)
+		: "i" (__NR_execve),
+		  "0" (__arg1),
+		  "d" (__arg2),
+		  "d" (__arg3) : "memory");
+	return __svcres;
+}
diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c
index 11c2acd..8fde950 100644
--- a/arch/sh/kernel/sys_sh.c
+++ b/arch/sh/kernel/sys_sh.c
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
+#include <asm/unistd.h>
 
 /*
  * sys_pipe() is the normal C calling standard for creating
@@ -309,3 +310,19 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1,
 				(u64)len0 << 32 | len1,	advice);
 #endif
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register long __sc0 __asm__ ("r3") = __NR_execve;
+	register long __sc4 __asm__ ("r4") = (long) filename;
+	register long __sc5 __asm__ ("r5") = (long) argv;
+	register long __sc6 __asm__ ("r6") = (long) envp;
+	__asm__ __volatile__ ("trapa	#0x13" : "=z" (__sc0)
+			: "0" (__sc0), "r" (__sc4), "r" (__sc5), "r" (__sc6)
+			: "memory");
+	return __sc0;
+}
diff --git a/arch/sh64/kernel/sys_sh64.c b/arch/sh64/kernel/sys_sh64.c
index c6de1a9..ad0fa4e 100644
--- a/arch/sh64/kernel/sys_sh64.c
+++ b/arch/sh64/kernel/sys_sh64.c
@@ -32,6 +32,7 @@
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
 #include <asm/ptrace.h>
+#include <asm/unistd.h>
 
 #define REG_3	3
 
@@ -283,3 +284,21 @@ asmlinkage int sys_uname(struct old_utsname * name)
 	up_read(&uts_sem);
 	return err?-EFAULT:0;
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register unsigned long __sc0 __asm__ ("r9") = ((0x13 << 16) | __NR_execve);
+	register unsigned long __sc2 __asm__ ("r2") = (unsigned long) filename;
+	register unsigned long __sc3 __asm__ ("r3") = (unsigned long) argv;
+	register unsigned long __sc4 __asm__ ("r4") = (unsigned long) envp;
+	__asm__ __volatile__ ("trapa	%1 !\t\t\t execve(%2,%3,%4)"
+	: "=r" (__sc0)
+	: "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) );
+	__asm__ __volatile__ ("!dummy	%0 %1 %2 %3"
+	: : "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) : "memory");
+	return __sc0;
+}
diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c
index 002ab4d..a954a0c 100644
--- a/arch/sparc/kernel/sys_sparc.c
+++ b/arch/sparc/kernel/sys_sparc.c
@@ -24,6 +24,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
+#include <asm/unistd.h>
 
 /* #define DEBUG_UNIMP_SYSCALL */
 
@@ -488,3 +489,25 @@ out:
 	up_read(&uts_sem);
 	return err;
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	long __res;
+	register long __g1 __asm__ ("g1") = __NR_execve;
+	register long __o0 __asm__ ("o0") = (long)(filename);
+	register long __o1 __asm__ ("o1") = (long)(argv);
+	register long __o2 __asm__ ("o2") = (long)(envp);
+	asm volatile ("t 0x10\n\t"
+		      "bcc 1f\n\t"
+		      "mov %%o0, %0\n\t"
+		      "sub %%g0, %%o0, %0\n\t"
+		      "1:\n\t"
+		      : "=r" (__res), "=&r" (__o0)
+		      : "1" (__o0), "r" (__o1), "r" (__o2), "r" (__g1)
+		      : "cc");
+	return __res;
+}
diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c
index 89ac435..a53d4ab 100644
--- a/arch/sparc64/kernel/sys_sparc.c
+++ b/arch/sparc64/kernel/sys_sparc.c
@@ -31,6 +31,7 @@
 #include <asm/utrap.h>
 #include <asm/perfctr.h>
 #include <asm/a.out.h>
+#include <asm/unistd.h>
 
 /* #define DEBUG_UNIMP_SYSCALL */
 
@@ -963,3 +964,23 @@ asmlinkage long sys_perfctr(int opcode, unsigned long arg0, unsigned long arg1,
 	};
 	return err;
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	long __res;
+	register long __g1 __asm__ ("g1") = __NR_execve;
+	register long __o0 __asm__ ("o0") = (long)(filename);
+	register long __o1 __asm__ ("o1") = (long)(argv);
+	register long __o2 __asm__ ("o2") = (long)(envp);
+	asm volatile ("t 0x6d\n\t"
+		      "sub %%g0, %%o0, %0\n\t"
+		      "movcc %%xcc, %%o0, %0\n\t"
+		      : "=r" (__res), "=&r" (__o0)
+		      : "1" (__o0), "r" (__o1), "r" (__o2), "r" (__g1)
+		      : "cc");
+	return __res;
+}
diff --git a/arch/v850/kernel/syscalls.c b/arch/v850/kernel/syscalls.c
index 2ec0700..d2b1fb1 100644
--- a/arch/v850/kernel/syscalls.c
+++ b/arch/v850/kernel/syscalls.c
@@ -33,6 +33,7 @@
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
 #include <asm/semaphore.h>
+#include <asm/unistd.h>
 
 /*
  * sys_ipc() is the de-multiplexer for the SysV IPC calls..
@@ -194,3 +195,22 @@ unsigned long sys_mmap (unsigned long addr, size_t len,
 out:
 	return err;
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	register char *__a __asm__ ("r6") = filename;
+	register void *__b __asm__ ("r7") = argv;
+	register void *__c __asm__ ("r8") = envp;
+	register unsigned long __syscall __asm__ ("r12") = __NR_execve;
+	register unsigned long __ret __asm__ ("r10");
+	__asm__ __volatile__ ("trap 0"
+			: "=r" (__ret), "=r" (__syscall)
+			: "1" (__syscall), "r" (__a), "r" (__b), "r" (__c)
+			: "r1", "r5", "r11", "r13", "r14",
+			  "r15", "r16", "r17", "r18", "r19");
+	return __ret;
+}
diff --git a/arch/xtensa/kernel/syscalls.c b/arch/xtensa/kernel/syscalls.c
index 37c90ca..d9285d4 100644
--- a/arch/xtensa/kernel/syscalls.c
+++ b/arch/xtensa/kernel/syscalls.c
@@ -266,3 +266,23 @@ void system_call (struct pt_regs *regs)
 	regs->areg[2] = res;
 	do_syscall_trace();
 }
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	long __res;
+	asm volatile (
+		"  mov   a5, %2 \n"
+		"  mov   a4, %4 \n"
+		"  mov   a3, %3 \n"
+		"  movi  a2, %1 \n"
+		"  syscall      \n"
+		"  mov   %0, a2 \n"
+		: "=a" (__res)
+		: "i" (__NR_execve), "a" (filename), "a" (argv), "a" (envp)
+		: "a2", "a3", "a4", "a5");
+	return __res;
+}