diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ade7e92..8918a2d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -55,6 +55,7 @@
 	select SYS_SUPPORTS_APM_EMULATION
 	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
 	select MODULES_USE_ELF_REL
+	select CLONE_BACKWARDS
 	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/unistd.h b/arch/arm/include/asm/unistd.h
index 8f60b6e..7cd13cc 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -42,6 +42,9 @@
 #define __ARCH_WANT_SYS_SOCKETCALL
 #endif
 #define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_CLONE
 
 /*
  * "Conditional" syscalls
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 831cd38..5935b6a02 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -11,7 +11,7 @@
  */
 /* 0 */		CALL(sys_restart_syscall)
 		CALL(sys_exit)
-		CALL(sys_fork_wrapper)
+		CALL(sys_fork)
 		CALL(sys_read)
 		CALL(sys_write)
 /* 5 */		CALL(sys_open)
@@ -129,7 +129,7 @@
 		CALL(OBSOLETE(ABI(sys_ipc, sys_oabi_ipc)))
 		CALL(sys_fsync)
 		CALL(sys_sigreturn_wrapper)
-/* 120 */	CALL(sys_clone_wrapper)
+/* 120 */	CALL(sys_clone)
 		CALL(sys_setdomainname)
 		CALL(sys_newuname)
 		CALL(sys_ni_syscall)		/* modify_ldt */
@@ -199,7 +199,7 @@
 		CALL(sys_sendfile)
 		CALL(sys_ni_syscall)		/* getpmsg */
 		CALL(sys_ni_syscall)		/* putpmsg */
-/* 190 */	CALL(sys_vfork_wrapper)
+/* 190 */	CALL(sys_vfork)
 		CALL(sys_getrlimit)
 		CALL(sys_mmap2)
 		CALL(ABI(sys_truncate64, sys_oabi_truncate64))
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 3471175..88a07fe 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -510,22 +510,6 @@
 		b	sys_ni_syscall
 ENDPROC(sys_syscall)
 
-sys_fork_wrapper:
-		add	r0, sp, #S_OFF
-		b	sys_fork
-ENDPROC(sys_fork_wrapper)
-
-sys_vfork_wrapper:
-		add	r0, sp, #S_OFF
-		b	sys_vfork
-ENDPROC(sys_vfork_wrapper)
-
-sys_clone_wrapper:
-		add	ip, sp, #S_OFF
-		str	ip, [sp, #4]
-		b	sys_clone
-ENDPROC(sys_clone_wrapper)
-
 sys_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		mov	why, #0		@ prevent syscall restart handling
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 90084a6..4ab80bb 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -376,17 +376,18 @@
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, struct pt_regs *regs)
+	    unsigned long stk_sz, struct task_struct *p, struct pt_regs *unused)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
-	if (likely(regs)) {
-		*childregs = *regs;
+	if (likely(!(p->flags & PF_KTHREAD))) {
+		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
-		childregs->ARM_sp = stack_start;
+		if (stack_start)
+			childregs->ARM_sp = stack_start;
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		thread->cpu_context.r4 = stk_sz;
@@ -399,7 +400,7 @@
 	clear_ptrace_hw_breakpoint(p);
 
 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value = regs->ARM_r3;
+		thread->tp_value = childregs->ARM_r3;
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
 
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index c2a898a..3151f56 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -28,37 +28,6 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 
-/* Fork a new task - this creates a new program thread.
- * This is called indirectly via a small wrapper
- */
-asmlinkage int sys_fork(struct pt_regs *regs)
-{
-#ifdef CONFIG_MMU
-	return do_fork(SIGCHLD, regs->ARM_sp, regs, 0, NULL, NULL);
-#else
-	/* can not support in nommu mode */
-	return(-EINVAL);
-#endif
-}
-
-/* Clone a task - this clones the calling program thread.
- * This is called indirectly via a small wrapper
- */
-asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
-			 int __user *parent_tidptr, int tls_val,
-			 int __user *child_tidptr, struct pt_regs *regs)
-{
-	if (!newsp)
-		newsp = regs->ARM_sp;
-
-	return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr);
-}
-
-asmlinkage int sys_vfork(struct pt_regs *regs)
-{
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->ARM_sp, regs, 0, NULL, NULL);
-}
-
 /*
  * Since loff_t is a 64 bit type we avoid a lot of ABI hassle
  * with a different argument ordering.