diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2f88d8d9770116014f7ff55e80d98c65fbb191ed..a949eec2286190c8739e60017165f2e50381b917 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -49,6 +49,7 @@ config ARM
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN
+	select GENERIC_KERNEL_THREAD
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 99afa7498260cdad985eaf9c74fd713095dd09f6..06e7d509eaac218864cc9d089ce9e6f4177c22f9 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -85,11 +85,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
-/*
- * Create a new kernel thread
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 978eac57e04a783f8901a16986f6d88f96f125ba..9a48b7a577e72d80a8c25b95dfa6f6b75997a94a 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -91,6 +91,18 @@ ENTRY(ret_from_fork)
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
 
+ENTRY(ret_from_kernel_thread)
+ UNWIND(.fnstart)
+ UNWIND(.cantunwind)
+	bl	schedule_tail
+	mov	r0, r4
+	adr	lr, BSYM(1f)	@ kernel threads should not exit
+	mov	pc, r5
+1:	bl	do_exit
+	nop
+ UNWIND(.fnend)
+ENDPROC(ret_from_kernel_thread)
+
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
 #include "calls.S"
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 693b744fd572f163f053c9fef42d563e246e04d3..c10e4395bc47c20b14ae09dd6e212d6c027849b9 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -373,6 +373,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
@@ -381,13 +382,20 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
 
-	*childregs = *regs;
-	childregs->ARM_r0 = 0;
-	childregs->ARM_sp = stack_start;
-
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
+
+	if (likely(regs)) {
+		*childregs = *regs;
+		childregs->ARM_r0 = 0;
+		childregs->ARM_sp = stack_start;
+		thread->cpu_context.pc = (unsigned long)ret_from_fork;
+	} else {
+		thread->cpu_context.r4 = stk_sz;
+		thread->cpu_context.r5 = stack_start;
+		thread->cpu_context.pc = (unsigned long)ret_from_kernel_thread;
+		childregs->ARM_cpsr = SVC_MODE;
+	}
 	thread->cpu_context.sp = (unsigned long)childregs;
-	thread->cpu_context.pc = (unsigned long)ret_from_fork;
 
 	clear_ptrace_hw_breakpoint(p);
 
@@ -423,63 +431,6 @@ int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
 }
 EXPORT_SYMBOL(dump_fpu);
 
-/*
- * Shuffle the argument into the correct register before calling the
- * thread function.  r4 is the thread argument, r5 is the pointer to
- * the thread function, and r6 points to the exit function.
- */
-extern void kernel_thread_helper(void);
-asm(	".pushsection .text\n"
-"	.align\n"
-"	.type	kernel_thread_helper, #function\n"
-"kernel_thread_helper:\n"
-#ifdef CONFIG_TRACE_IRQFLAGS
-"	bl	trace_hardirqs_on\n"
-#endif
-"	msr	cpsr_c, r7\n"
-"	mov	r0, r4\n"
-"	mov	lr, r6\n"
-"	mov	pc, r5\n"
-"	.size	kernel_thread_helper, . - kernel_thread_helper\n"
-"	.popsection");
-
-#ifdef CONFIG_ARM_UNWIND
-extern void kernel_thread_exit(long code);
-asm(	".pushsection .text\n"
-"	.align\n"
-"	.type	kernel_thread_exit, #function\n"
-"kernel_thread_exit:\n"
-"	.fnstart\n"
-"	.cantunwind\n"
-"	bl	do_exit\n"
-"	nop\n"
-"	.fnend\n"
-"	.size	kernel_thread_exit, . - kernel_thread_exit\n"
-"	.popsection");
-#else
-#define kernel_thread_exit	do_exit
-#endif
-
-/*
- * Create a kernel thread.
- */
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-
-	regs.ARM_r4 = (unsigned long)arg;
-	regs.ARM_r5 = (unsigned long)fn;
-	regs.ARM_r6 = (unsigned long)kernel_thread_exit;
-	regs.ARM_r7 = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE;
-	regs.ARM_pc = (unsigned long)kernel_thread_helper;
-	regs.ARM_cpsr = regs.ARM_r7 | PSR_I_BIT;
-
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;