diff --git a/[refs] b/[refs]
index 1d85df82223e..80d10b8c420c 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 71915d21e59c153c1202e3198916817c2d18da32
+refs/heads/master: ea4a1da9b2e6f419526b5fde15cd5563096368eb
diff --git a/trunk/arch/h8300/Kconfig b/trunk/arch/h8300/Kconfig
index 04bef4d25b4a..98fabd10e95f 100644
--- a/trunk/arch/h8300/Kconfig
+++ b/trunk/arch/h8300/Kconfig
@@ -8,8 +8,6 @@ config H8300
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config SYMBOL_PREFIX
 	string
diff --git a/trunk/arch/h8300/include/asm/processor.h b/trunk/arch/h8300/include/asm/processor.h
index 4b0ca49bb463..4c9f6f87b617 100644
--- a/trunk/arch/h8300/include/asm/processor.h
+++ b/trunk/arch/h8300/include/asm/processor.h
@@ -107,6 +107,8 @@ 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 00502a61bf0a..d09c440bdba7 100644
--- a/trunk/arch/h8300/include/asm/ptrace.h
+++ b/trunk/arch/h8300/include/asm/ptrace.h
@@ -60,8 +60,6 @@ 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/include/asm/unistd.h b/trunk/arch/h8300/include/asm/unistd.h
index 07afcfaec995..5cd882801d79 100644
--- a/trunk/arch/h8300/include/asm/unistd.h
+++ b/trunk/arch/h8300/include/asm/unistd.h
@@ -356,7 +356,6 @@
 #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/h8300/kernel/entry.S b/trunk/arch/h8300/kernel/entry.S
index 617a6878787f..ca7431690300 100644
--- a/trunk/arch/h8300/kernel/entry.S
+++ b/trunk/arch/h8300/kernel/entry.S
@@ -158,7 +158,6 @@ 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)
@@ -331,14 +330,6 @@ 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
-	jmp	@SYMBOL_NAME(ret_from_exception)
-
 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 53d7c0e4bd83..6866bd9c7fb4 100644
--- a/trunk/arch/h8300/kernel/h8300_ksyms.c
+++ b/trunk/arch/h8300/kernel/h8300_ksyms.c
@@ -33,6 +33,7 @@ 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 2a45718cc5e8..e8dc1393a13a 100644
--- a/trunk/arch/h8300/kernel/process.c
+++ b/trunk/arch/h8300/kernel/process.c
@@ -47,7 +47,6 @@ 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..
@@ -123,6 +122,39 @@ 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)
 {
 }
@@ -166,13 +198,6 @@ 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;
@@ -183,6 +208,27 @@ int copy_thread(unsigned long clone_flags,
 	return 0;
 }
 
+/*
+ * sys_execve() executes a new program.
+ */
+asmlinkage int sys_execve(const char *name,
+			  const char *const *argv,
+			  const char *const *envp,
+			  int dummy, ...)
+{
+	int error;
+	struct filename *filename;
+	struct pt_regs *regs = (struct pt_regs *) ((unsigned char *)&dummy-4);
+
+	filename = getname(name);
+	error = PTR_ERR(filename);
+	if (IS_ERR(filename))
+		return error;
+	error = do_execve(filename->name, argv, envp, regs);
+	putname(filename);
+	return error;
+}
+
 unsigned long thread_saved_pc(struct task_struct *tsk)
 {
 	return ((struct pt_regs *)tsk->thread.esp0)->pc;
diff --git a/trunk/arch/h8300/kernel/sys_h8300.c b/trunk/arch/h8300/kernel/sys_h8300.c
index bf350cb7f597..4bdc7311784e 100644
--- a/trunk/arch/h8300/kernel/sys_h8300.c
+++ b/trunk/arch/h8300/kernel/sys_h8300.c
@@ -46,3 +46,29 @@ 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.
+ */
+asmlinkage
+int kernel_execve(const char *filename,
+		  const char *const argv[],
+		  const char *const envp[])
+{
+	register long res __asm__("er0");
+	register const char *const *_c __asm__("er3") = envp;
+	register const char *const *_b __asm__("er2") = argv;
+	register const char * _a __asm__("er1") = filename;
+	__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/trunk/arch/m32r/Kconfig b/trunk/arch/m32r/Kconfig
index f807721e19a5..5183f43a2cf7 100644
--- a/trunk/arch/m32r/Kconfig
+++ b/trunk/arch/m32r/Kconfig
@@ -15,6 +15,8 @@ config M32R
 	select GENERIC_ATOMIC64
 	select ARCH_USES_GETTIMEOFFSET
 	select MODULES_USE_ELF_RELA
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 
 config SBUS
 	bool
diff --git a/trunk/arch/m32r/include/asm/processor.h b/trunk/arch/m32r/include/asm/processor.h
index da17253b5735..5767367550c6 100644
--- a/trunk/arch/m32r/include/asm/processor.h
+++ b/trunk/arch/m32r/include/asm/processor.h
@@ -118,11 +118,6 @@ struct mm_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/*
- * create a kernel thread without removing it from tasklists
- */
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
 /* Copy and release all segment info associated with a VM */
 extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
 extern void release_segments(struct mm_struct * mm);
diff --git a/trunk/arch/m32r/kernel/entry.S b/trunk/arch/m32r/kernel/entry.S
index 225412bc227e..0c01543f10cd 100644
--- a/trunk/arch/m32r/kernel/entry.S
+++ b/trunk/arch/m32r/kernel/entry.S
@@ -125,6 +125,15 @@
 	and	\reg, sp
 	.endm
 
+ENTRY(ret_from_kernel_thread)
+	pop	r0
+	bl	schedule_tail
+	GET_THREAD_INFO(r8)
+	ld	r0, R0(r8)
+	ld	r1, R1(r8)
+	jl	r1
+	bra	syscall_exit
+
 ENTRY(ret_from_fork)
 	pop	r0
 	bl	schedule_tail
diff --git a/trunk/arch/m32r/kernel/process.c b/trunk/arch/m32r/kernel/process.c
index e7366276ef30..fa89f027c04a 100644
--- a/trunk/arch/m32r/kernel/process.c
+++ b/trunk/arch/m32r/kernel/process.c
@@ -164,41 +164,6 @@ void show_regs(struct pt_regs * regs)
 #endif
 }
 
-/*
- * Create a kernel thread
- */
-
-/*
- * This is the mechanism for creating a new kernel thread.
- *
- * NOTE! Only a kernel-only process(ie the swapper or direct descendants
- * who haven't done an "execve()") should use this: it will work within
- * a system call from a "real" process, but the process memory space will
- * not be free'd until both the parent and the child have exited.
- */
-static void kernel_thread_helper(void *nouse, int (*fn)(void *), void *arg)
-{
-	fn(arg);
-	do_exit(-1);
-}
-
-int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof (regs));
-	regs.r1 = (unsigned long)fn;
-	regs.r2 = (unsigned long)arg;
-
-	regs.bpc = (unsigned long)kernel_thread_helper;
-
-	regs.psw = M32R_PSW_BIE;
-
-	/* Ok, create the new process. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL,
-		NULL);
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -227,19 +192,26 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long spu,
-	unsigned long unused, struct task_struct *tsk, struct pt_regs *regs)
+	unsigned long arg, struct task_struct *tsk, struct pt_regs *regs)
 {
 	struct pt_regs *childregs = task_pt_regs(tsk);
 	extern void ret_from_fork(void);
-
-	/* Copy registers */
-	*childregs = *regs;
-
-	childregs->spu = spu;
-	childregs->r0 = 0;	/* Child gets zero as return value */
-	regs->r0 = tsk->pid;
+	extern void ret_from_kernel_thread(void);
+
+	if (unlikely(tsk->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->psw = M32R_PSW_BIE;
+		childregs->r1 = spu;	/* fn */
+		childregs->r0 = arg;
+		tsk->thread.lr = (unsigned long)ret_from_kernel_thread;
+	} else {
+		/* Copy registers */
+		*childregs = *regs;
+		childregs->spu = spu;
+		childregs->r0 = 0;	/* Child gets zero as return value */
+		tsk->thread.lr = (unsigned long)ret_from_fork;
+	}
 	tsk->thread.sp = (unsigned long)childregs;
-	tsk->thread.lr = (unsigned long)ret_from_fork;
 
 	return 0;
 }
diff --git a/trunk/arch/m32r/kernel/sys_m32r.c b/trunk/arch/m32r/kernel/sys_m32r.c
index d841fb6cc703..c3fdd632fba7 100644
--- a/trunk/arch/m32r/kernel/sys_m32r.c
+++ b/trunk/arch/m32r/kernel/sys_m32r.c
@@ -88,24 +88,3 @@ asmlinkage int sys_cachectl(char *addr, int nbytes, int op)
 	/* Not implemented yet. */
 	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,
-		  const char *const argv[],
-		  const 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;
-}