diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S
index 46c9331e7ab5f81181b5e19745c154a80c4b852e..9e534d52b1d52289a90f49417db3edb5874fd2de 100644
--- a/arch/ia64/lib/memcpy_mck.S
+++ b/arch/ia64/lib/memcpy_mck.S
@@ -6,7 +6,9 @@
  *	in1:	source address
  *	in2:	number of bytes to copy
  * Output:
- * 	0 if success, or number of byte NOT copied if error occurred.
+ *	for memcpy:    return dest
+ * 	for copy_user: return 0 if success,
+ *		       or number of byte NOT copied if error occurred.
  *
  * Copyright (C) 2002 Intel Corp.
  * Copyright (C) 2002 Ken Chen <kenneth.w.chen@intel.com>
@@ -73,6 +75,7 @@ GLOBAL_ENTRY(memcpy)
 	and	r28=0x7,in0
 	and	r29=0x7,in1
 	mov	f6=f0
+	mov	retval=in0
 	br.cond.sptk .common_code
 	;;
 END(memcpy)
@@ -84,7 +87,7 @@ GLOBAL_ENTRY(__copy_user)
 	mov	f6=f1
 	mov	saved_in0=in0	// save dest pointer
 	mov	saved_in1=in1	// save src pointer
-	mov	saved_in2=in2	// save len
+	mov	retval=r0	// initialize return value
 	;;
 .common_code:
 	cmp.gt	p15,p0=8,in2	// check for small size
@@ -92,7 +95,7 @@ GLOBAL_ENTRY(__copy_user)
 	cmp.ne	p14,p0=0,r29	// check src alignment
 	add	src0=0,in1
 	sub	r30=8,r28	// for .align_dest
-	mov	retval=r0	// initialize return value
+	mov	saved_in2=in2	// save len
 	;;
 	add	dst0=0,in0
 	add	dst1=1,in0	// dest odd index
diff --git a/include/asm-ia64/bitops.h b/include/asm-ia64/bitops.h
index 90921e162793e22f4861e78ebda066d971c4fbc0..6cc517e212a92ee94e461c2e1944f3fe9af0c627 100644
--- a/include/asm-ia64/bitops.h
+++ b/include/asm-ia64/bitops.h
@@ -11,7 +11,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/bitops.h>
 #include <asm/intrinsics.h>
 
 /**