diff --git a/[refs] b/[refs]
index d7503c16ed71..352a33dec693 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 1703a219f7f5ab2c39514f9f0763001cdc907d25
+refs/heads/master: 557e1995a92d318206910d8b5c62075fe02b37e0
diff --git a/trunk/arch/cris/Kconfig b/trunk/arch/cris/Kconfig
index 81b59d18867e..a67244473a39 100644
--- a/trunk/arch/cris/Kconfig
+++ b/trunk/arch/cris/Kconfig
@@ -49,8 +49,6 @@ config CRIS
 	select GENERIC_SMP_IDLE_THREAD if ETRAX_ARCH_V32
 	select GENERIC_CMOS_UPDATE
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config HZ
 	int
diff --git a/trunk/arch/cris/arch-v10/kernel/entry.S b/trunk/arch/cris/arch-v10/kernel/entry.S
index 897bba67bf7a..592fbe9dfb62 100644
--- a/trunk/arch/cris/arch-v10/kernel/entry.S
+++ b/trunk/arch/cris/arch-v10/kernel/entry.S
@@ -35,7 +35,6 @@
 	.globl system_call
 	.globl ret_from_intr
 	.globl ret_from_fork
-	.globl ret_from_kernel_thread
 	.globl resume
 	.globl multiple_interrupt
 	.globl hwbreakpoint
@@ -82,14 +81,7 @@ ret_from_fork:
 	jsr schedule_tail
 	ba  ret_from_sys_call
 	nop
-
-ret_from_kernel_thread:
-	jsr schedule_tail
-	move.d	$r2, $r10	; argument is here
-	jsr	$r1		; call the payload
-	moveq	0, $r9		; no syscall restarts, TYVM...
-	ba  ret_from_sys_call
-
+		
 ret_from_intr:
 	;; check for resched if preemptive kernel or if we're going back to user-mode 
 	;; this test matches the user_regs(regs) macro
@@ -594,6 +586,13 @@ _ugdb_handle_breakpoint:
 	ba	do_sigtrap		; SIGTRAP the offending process. 
 	pop	$dccr			; Restore dccr in delay slot.
 
+	.global kernel_execve
+kernel_execve:
+	move.d __NR_execve, $r9
+	break 13
+	ret
+	nop
+
 	.data
 
 hw_bp_trigs:
diff --git a/trunk/arch/cris/arch-v10/kernel/process.c b/trunk/arch/cris/arch-v10/kernel/process.c
index 1d6458287f38..15ac7150371f 100644
--- a/trunk/arch/cris/arch-v10/kernel/process.c
+++ b/trunk/arch/cris/arch-v10/kernel/process.c
@@ -17,7 +17,6 @@
 #include <arch/svinto.h>
 #include <linux/init.h>
 #include <arch/system.h>
-#include <asm/ptrace.h>
 
 #ifdef CONFIG_ETRAX_GPIO
 void etrax_gpio_wake_up_check(void); /* drivers/gpio.c */
@@ -82,6 +81,31 @@ unsigned long thread_saved_pc(struct task_struct *t)
 	return task_pt_regs(t)->irp;
 }
 
+static void kernel_thread_helper(void* dummy, int (*fn)(void *), void * arg)
+{
+  fn(arg);
+  do_exit(-1); /* Should never be called, return bad exit value */
+}
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+	struct pt_regs regs;
+
+	memset(&regs, 0, sizeof(regs));
+
+        /* Don't use r10 since that is set to 0 in copy_thread */
+	regs.r11 = (unsigned long)fn;
+	regs.r12 = (unsigned long)arg;
+	regs.irp = (unsigned long)kernel_thread_helper;
+	regs.dccr = 1 << I_DCCR_BITNR;
+
+	/* Ok, create the new process.. */
+        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
+}
+
 /* setup the child's kernel stack with a pt_regs and switch_stack on it.
  * it will be un-nested during _resume and _ret_from_sys_call when the
  * new thread is scheduled.
@@ -91,36 +115,30 @@ unsigned long thread_saved_pc(struct task_struct *t)
  *
  */
 asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
+		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
-	struct pt_regs *childregs = task_pt_regs(p);
-	struct switch_stack *swstack = ((struct switch_stack *)childregs) - 1;
+	struct pt_regs * childregs;
+	struct switch_stack *swstack;
 	
 	/* put the pt_regs structure at the end of the new kernel stack page and fix it up
 	 * remember that the task_struct doubles as the kernel stack for the task
 	 */
 
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		memset(swstack, 0,
-			sizeof(struct switch_stack) + sizeof(struct pt_regs));
-		swstack->r1 = usp;
-		swstack->r2 = arg;
-		childregs->dccr = 1 << I_DCCR_BITNR;
-		swstack->return_ip = (unsigned long) ret_from_kernel_thread;
-		p->thread.ksp = (unsigned long) swstack;
-		p->thread.usp = 0;
-		return 0;
-	}
+	childregs = task_pt_regs(p);
+        
 	*childregs = *regs;  /* struct copy of pt_regs */
+        
+        p->set_child_tid = p->clear_child_tid = NULL;
 
         childregs->r10 = 0;  /* child returns 0 after a fork/clone */
-
+	
 	/* put the switch stack right below the pt_regs */
 
+	swstack = ((struct switch_stack *)childregs) - 1;
+
 	swstack->r9 = 0; /* parameter to ret_from_sys_call, 0 == dont restart the syscall */
 
 	/* we want to return into ret_from_sys_call after the _resume */
@@ -129,7 +147,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	
 	/* fix the user-mode stackpointer */
 
-	p->thread.usp = usp;
+	p->thread.usp = usp;	
 
 	/* and the kernel-mode one */
 
@@ -143,28 +161,68 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	return 0;
 }
 
-asmlinkage int sys_fork(void)
+/* 
+ * Be aware of the "magic" 7th argument in the four system-calls below.
+ * They need the latest stackframe, which is put as the 7th argument by
+ * entry.S. The previous arguments are dummies or actually used, but need
+ * to be defined to reach the 7th argument.
+ *
+ * N.B.: Another method to get the stackframe is to use current_regs(). But
+ * it returns the latest stack-frame stacked when going from _user mode_ and
+ * some of these (at least sys_clone) are called from kernel-mode sometimes
+ * (for example during kernel_thread, above) and thus cannot use it. Thus,
+ * to be sure not to get any surprises, we use the method for the other calls
+ * as well.
+ */
+
+asmlinkage int sys_fork(long r10, long r11, long r12, long r13, long mof, long srp,
+			struct pt_regs *regs)
 {
-	return do_fork(SIGCHLD, rdusp(), current_pt_regs(), 0, NULL, NULL);
+	return do_fork(SIGCHLD, rdusp(), regs, 0, NULL, NULL);
 }
 
 /* if newusp is 0, we just grab the old usp */
 /* FIXME: Is parent_tid/child_tid really third/fourth argument? Update lib? */
 asmlinkage int sys_clone(unsigned long newusp, unsigned long flags,
-			 int* parent_tid, int* child_tid)
+			 int* parent_tid, int* child_tid, long mof, long srp,
+			 struct pt_regs *regs)
 {
 	if (!newusp)
 		newusp = rdusp();
-	return do_fork(flags, newusp, current_pt_regs(), 0, parent_tid, child_tid);
+	return do_fork(flags, newusp, regs, 0, parent_tid, child_tid);
 }
 
 /* vfork is a system call in i386 because of register-pressure - maybe
  * we can remove it and handle it in libc but we put it here until then.
  */
 
-asmlinkage int sys_vfork(void)
+asmlinkage int sys_vfork(long r10, long r11, long r12, long r13, long mof, long srp,
+			 struct pt_regs *regs)
+{
+        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, rdusp(), regs, 0, NULL, NULL);
+}
+
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(const char *fname,
+			  const char *const *argv,
+			  const char *const *envp,
+			  long r13, long mof, long srp, 
+			  struct pt_regs *regs)
 {
-        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, rdusp(), current_pt_regs(), 0, NULL, NULL);
+	int error;
+	struct filename *filename;
+
+	filename = getname(fname);
+	error = PTR_ERR(filename);
+
+	if (IS_ERR(filename))
+	        goto out;
+	error = do_execve(filename->name, argv, envp, regs);
+	putname(filename);
+ out:
+	return error;
 }
 
 unsigned long get_wchan(struct task_struct *p)
diff --git a/trunk/arch/cris/arch-v32/kernel/entry.S b/trunk/arch/cris/arch-v32/kernel/entry.S
index faa644111feb..c3ea4694fbaf 100644
--- a/trunk/arch/cris/arch-v32/kernel/entry.S
+++ b/trunk/arch/cris/arch-v32/kernel/entry.S
@@ -31,7 +31,6 @@
 	.globl system_call
 	.globl ret_from_intr
 	.globl ret_from_fork
-	.globl ret_from_kernel_thread
 	.globl resume
 	.globl multiple_interrupt
 	.globl nmi_interrupt
@@ -85,18 +84,6 @@ ret_from_fork:
 	nop
 	.size	ret_from_fork, . - ret_from_fork
 
-	.type	ret_from_kernel_thread,@function
-ret_from_kernel_thread:
-	jsr schedule_tail
-	nop
-	move.d	$r2, $r10
-	jsr	$r1
-	nop
-	moveq	0, $r9			; no syscall restarts, TYVM...
-	ba  ret_from_sys_call
-	nop
-	.size	ret_from_kernel_thread, . - ret_from_kernel_thread
-
 	.type	ret_from_intr,@function
 ret_from_intr:
 	;; Check for resched if preemptive kernel, or if we're going back to
@@ -544,6 +531,15 @@ _ugdb_handle_exception:
 	ba	do_sigtrap		; SIGTRAP the offending process.
 	move.d	[$sp+], $r0		; Restore R0 in delay slot.
 
+	.global kernel_execve
+	.type	kernel_execve,@function
+kernel_execve:
+	move.d __NR_execve, $r9
+	break 13
+	ret
+	nop
+	.size	kernel_execve, . - kernel_execve
+
 	.data
 
 	.section .rodata,"a"
diff --git a/trunk/arch/cris/arch-v32/kernel/process.c b/trunk/arch/cris/arch-v32/kernel/process.c
index fe465401b6ec..4e9992246359 100644
--- a/trunk/arch/cris/arch-v32/kernel/process.c
+++ b/trunk/arch/cris/arch-v32/kernel/process.c
@@ -16,7 +16,6 @@
 #include <hwregs/reg_map.h>
 #include <hwregs/timer_defs.h>
 #include <hwregs/intr_vect_defs.h>
-#include <asm/ptrace.h>
 
 extern void stop_watchdog(void);
 
@@ -95,6 +94,31 @@ unsigned long thread_saved_pc(struct task_struct *t)
 	return task_pt_regs(t)->erp;
 }
 
+static void
+kernel_thread_helper(void* dummy, int (*fn)(void *), void * arg)
+{
+	fn(arg);
+	do_exit(-1); /* Should never be called, return bad exit value. */
+}
+
+/* Create a kernel thread. */
+int
+kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+{
+	struct pt_regs regs;
+
+	memset(&regs, 0, sizeof(regs));
+
+        /* Don't use r10 since that is set to 0 in copy_thread. */
+	regs.r11 = (unsigned long) fn;
+	regs.r12 = (unsigned long) arg;
+	regs.erp = (unsigned long) kernel_thread_helper;
+	regs.ccs = 1 << (I_CCS_BITNR + CCS_SHIFT);
+
+	/* Create the new process. */
+        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
+}
+
 /*
  * Setup the child's kernel stack with a pt_regs and call switch_stack() on it.
  * It will be unnested during _resume and _ret_from_sys_call when the new thread
@@ -105,33 +129,23 @@ unsigned long thread_saved_pc(struct task_struct *t)
  */
 
 extern asmlinkage void ret_from_fork(void);
-extern asmlinkage void ret_from_kernel_thread(void);
 
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg,
+	unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
-	struct pt_regs *childregs = task_pt_regs(p);
-	struct switch_stack *swstack = ((struct switch_stack *) childregs) - 1;
+	struct pt_regs *childregs;
+	struct switch_stack *swstack;
 
 	/*
 	 * Put the pt_regs structure at the end of the new kernel stack page and
 	 * fix it up. Note: the task_struct doubles as the kernel stack for the
 	 * task.
 	 */
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		memset(swstack, 0,
-			sizeof(struct switch_stack) + sizeof(struct pt_regs));
-		swstack->r1 = usp;
-		swstack->r2 = arg;
-		childregs->ccs = 1 << (I_CCS_BITNR + CCS_SHIFT);
-		swstack->return_ip = (unsigned long) ret_from_kernel_thread;
-		p->thread.ksp = (unsigned long) swstack;
-		p->thread.usp = 0;
-		return 0;
-	}
+	childregs = task_pt_regs(p);
 	*childregs = *regs;	/* Struct copy of pt_regs. */
+        p->set_child_tid = p->clear_child_tid = NULL;
         childregs->r10 = 0;	/* Child returns 0 after a fork/clone. */
 
 	/* Set a new TLS ?
@@ -142,6 +156,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	}
 
 	/* Put the switch stack right below the pt_regs. */
+	swstack = ((struct switch_stack *) childregs) - 1;
 
 	/* Parameter to ret_from_sys_call. 0 is don't restart the syscall. */
 	swstack->r9 = 0;
@@ -159,21 +174,35 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	return 0;
 }
 
+/*
+ * Be aware of the "magic" 7th argument in the four system-calls below.
+ * They need the latest stackframe, which is put as the 7th argument by
+ * entry.S. The previous arguments are dummies or actually used, but need
+ * to be defined to reach the 7th argument.
+ *
+ * N.B.: Another method to get the stackframe is to use current_regs(). But
+ * it returns the latest stack-frame stacked when going from _user mode_ and
+ * some of these (at least sys_clone) are called from kernel-mode sometimes
+ * (for example during kernel_thread, above) and thus cannot use it. Thus,
+ * to be sure not to get any surprises, we use the method for the other calls
+ * as well.
+ */
 asmlinkage int
-sys_fork(void)
+sys_fork(long r10, long r11, long r12, long r13, long mof, long srp,
+	struct pt_regs *regs)
 {
-	return do_fork(SIGCHLD, rdusp(), current_pt_regs(), 0, NULL, NULL);
+	return do_fork(SIGCHLD, rdusp(), regs, 0, NULL, NULL);
 }
 
 /* FIXME: Is parent_tid/child_tid really third/fourth argument? Update lib? */
 asmlinkage int
 sys_clone(unsigned long newusp, unsigned long flags, int *parent_tid, int *child_tid,
-	unsigned long tls)
+	unsigned long tls, long srp, struct pt_regs *regs)
 {
 	if (!newusp)
 		newusp = rdusp();
 
-	return do_fork(flags, newusp, current_pt_regs(), 0, parent_tid, child_tid);
+	return do_fork(flags, newusp, regs, 0, parent_tid, child_tid);
 }
 
 /*
@@ -181,9 +210,32 @@ sys_clone(unsigned long newusp, unsigned long flags, int *parent_tid, int *child
  * we can remove it and handle it in libc but we put it here until then.
  */
 asmlinkage int
-sys_vfork(void)
+sys_vfork(long r10, long r11, long r12, long r13, long mof, long srp,
+	struct pt_regs *regs)
+{
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, rdusp(), regs, 0, NULL, NULL);
+}
+
+/* sys_execve() executes a new program. */
+asmlinkage int
+sys_execve(const char *fname,
+	   const char *const *argv,
+	   const char *const *envp, long r13, long mof, long srp,
+	   struct pt_regs *regs)
 {
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, rdusp(), current_pt_regs(), 0, NULL, NULL);
+	int error;
+	struct filename *filename;
+
+	filename = getname(fname);
+	error = PTR_ERR(filename);
+
+	if (IS_ERR(filename))
+	        goto out;
+
+	error = do_execve(filename->name, argv, envp, regs);
+	putname(filename);
+ out:
+	return error;
 }
 
 unsigned long
diff --git a/trunk/arch/cris/include/asm/processor.h b/trunk/arch/cris/include/asm/processor.h
index 675823f70c0f..ef4e1bc3efc8 100644
--- a/trunk/arch/cris/include/asm/processor.h
+++ b/trunk/arch/cris/include/asm/processor.h
@@ -49,6 +49,8 @@ struct task_struct;
 #define task_pt_regs(task) user_regs(task_thread_info(task))
 #define current_regs() task_pt_regs(current)
 
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
 unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_ESP(tsk)   ((tsk) == current ? rdusp() : (tsk)->thread.usp)
diff --git a/trunk/arch/cris/include/asm/unistd.h b/trunk/arch/cris/include/asm/unistd.h
index f181d1fc7632..51873a446f87 100644
--- a/trunk/arch/cris/include/asm/unistd.h
+++ b/trunk/arch/cris/include/asm/unistd.h
@@ -371,7 +371,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 
 /*
  * "Conditional" syscalls
diff --git a/trunk/arch/cris/kernel/crisksyms.c b/trunk/arch/cris/kernel/crisksyms.c
index 5868cee20ebd..7ac000f6a888 100644
--- a/trunk/arch/cris/kernel/crisksyms.c
+++ b/trunk/arch/cris/kernel/crisksyms.c
@@ -30,6 +30,7 @@ extern void __negdi2(void);
 extern void iounmap(volatile void * __iomem);
 
 /* Platform dependent support */
+EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(get_cmos_time);
 EXPORT_SYMBOL(loops_per_usec);
 
diff --git a/trunk/arch/h8300/Kconfig b/trunk/arch/h8300/Kconfig
index 98fabd10e95f..4cef8a91c2a0 100644
--- a/trunk/arch/h8300/Kconfig
+++ b/trunk/arch/h8300/Kconfig
@@ -8,6 +8,7 @@ config H8300
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
+	select GENERIC_KERNEL_THREAD
 
 config SYMBOL_PREFIX
 	string
diff --git a/trunk/arch/h8300/include/asm/processor.h b/trunk/arch/h8300/include/asm/processor.h
index 4c9f6f87b617..4b0ca49bb463 100644
--- a/trunk/arch/h8300/include/asm/processor.h
+++ b/trunk/arch/h8300/include/asm/processor.h
@@ -107,8 +107,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
 /*
  * Free current thread data structures etc..
  */
diff --git a/trunk/arch/h8300/include/asm/ptrace.h b/trunk/arch/h8300/include/asm/ptrace.h
index d09c440bdba7..00502a61bf0a 100644
--- a/trunk/arch/h8300/include/asm/ptrace.h
+++ b/trunk/arch/h8300/include/asm/ptrace.h
@@ -60,6 +60,8 @@ struct pt_regs {
 #define user_mode(regs) (!((regs)->ccr & PS_S))
 #define instruction_pointer(regs) ((regs)->pc)
 #define profile_pc(regs) instruction_pointer(regs)
+#define current_pt_regs() ((struct pt_regs *) \
+	(THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 #endif /* _H8300_PTRACE_H */
diff --git a/trunk/arch/h8300/kernel/entry.S b/trunk/arch/h8300/kernel/entry.S
index ca7431690300..2cdb49a56099 100644
--- a/trunk/arch/h8300/kernel/entry.S
+++ b/trunk/arch/h8300/kernel/entry.S
@@ -158,6 +158,7 @@ INTERRUPTS = 128
 .globl SYMBOL_NAME(system_call)
 .globl SYMBOL_NAME(ret_from_exception)
 .globl SYMBOL_NAME(ret_from_fork)
+.globl SYMBOL_NAME(ret_from_kernel_thread)
 .globl SYMBOL_NAME(ret_from_interrupt)
 .globl SYMBOL_NAME(interrupt_redirect_table)
 .globl SYMBOL_NAME(sw_ksp),SYMBOL_NAME(sw_usp)
@@ -330,6 +331,15 @@ SYMBOL_NAME_LABEL(ret_from_fork)
 	jsr	@SYMBOL_NAME(schedule_tail)
 	jmp	@SYMBOL_NAME(ret_from_exception)
 
+SYMBOL_NAME_LABEL(ret_from_kernel_thread)
+	mov.l	er2,er0
+	jsr	@SYMBOL_NAME(schedule_tail)
+	mov.l	@(LER4:16,sp),er0
+	mov.l	@(LER5:16,sp),er1
+	jsr	@er1
+	sub.l	@er0,@er0
+	jsr	@SYMBOL_NAME(sys_exit)
+
 SYMBOL_NAME_LABEL(resume)
 	/*
 	 * Beware - when entering resume, offset of tss is in d1,
diff --git a/trunk/arch/h8300/kernel/h8300_ksyms.c b/trunk/arch/h8300/kernel/h8300_ksyms.c
index 6866bd9c7fb4..53d7c0e4bd83 100644
--- a/trunk/arch/h8300/kernel/h8300_ksyms.c
+++ b/trunk/arch/h8300/kernel/h8300_ksyms.c
@@ -33,7 +33,6 @@ EXPORT_SYMBOL(strncmp);
 
 EXPORT_SYMBOL(ip_fast_csum);
 
-EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(enable_irq);
 EXPORT_SYMBOL(disable_irq);
 
diff --git a/trunk/arch/h8300/kernel/process.c b/trunk/arch/h8300/kernel/process.c
index e8dc1393a13a..e3dfea71c15f 100644
--- a/trunk/arch/h8300/kernel/process.c
+++ b/trunk/arch/h8300/kernel/process.c
@@ -47,6 +47,7 @@ void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
 asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
 
 /*
  * The idle loop on an H8/300..
@@ -122,39 +123,6 @@ void show_regs(struct pt_regs * regs)
 		printk("\n");
 }
 
-/*
- * Create a kernel thread
- */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-	long retval;
-	long clone_arg;
-	mm_segment_t fs;
-
-	fs = get_fs();
-	set_fs (KERNEL_DS);
-	clone_arg = flags | CLONE_VM;
-	__asm__("mov.l sp,er3\n\t"
-		"sub.l er2,er2\n\t"
-		"mov.l %2,er1\n\t"
-		"mov.l %1,er0\n\t"
-		"trapa #0\n\t"
-		"cmp.l sp,er3\n\t"
-		"beq 1f\n\t"
-		"mov.l %4,er0\n\t"
-		"mov.l %3,er1\n\t"
-		"jsr @er1\n\t"
-		"mov.l %5,er0\n\t"
-		"trapa #0\n"
-		"1:\n\t"
-		"mov.l er0,%0"
-		:"=r"(retval)
-		:"i"(__NR_clone),"g"(clone_arg),"g"(fn),"g"(arg),"i"(__NR_exit)
-		:"er0","er1","er2","er3");
-	set_fs (fs);
-	return retval;
-}
-
 void flush_thread(void)
 {
 }
@@ -198,6 +166,13 @@ int copy_thread(unsigned long clone_flags,
 
 	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
 
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->retpc = (unsigned long) ret_from_kernel_thread;
+		childregs->er4 = topstk; /* arg */
+		childregs->er5 = usp; /* fn */
+		p->thread.ksp = (unsigned long)childregs;
+	}
 	*childregs = *regs;
 	childregs->retpc = (unsigned long) ret_from_fork;
 	childregs->er0 = 0;