diff --git a/arch/arm/cpu/arm946es/start.S b/arch/arm/cpu/arm946es/start.S
index 84fabf4..90c15f2 100644
--- a/arch/arm/cpu/arm946es/start.S
+++ b/arch/arm/cpu/arm946es/start.S
@@ -167,16 +167,15 @@
 	mov	r6, r2	/* save addr of destination */
 
 	adr	r0, _start
-	cmp	r0, r6
-	moveq	r9, #0		/* no relocation. relocation offset(r9) = 0 */
+	subs	r9, r6, r0		/* r9 <- relocation offset */
 	beq	relocate_done		/* skip relocation */
 	mov	r1, r6			/* r1 <- scratch for copy_loop */
 	ldr	r3, _bss_start_ofs
 	add	r2, r0, r3		/* r2 <- source end address	    */
 
 copy_loop:
-	ldmia	r0!, {r9-r10}		/* copy from source address [r0]    */
-	stmia	r1!, {r9-r10}		/* copy to   target address [r1]    */
+	ldmia	r0!, {r10-r11}		/* copy from source address [r0]    */
+	stmia	r1!, {r10-r11}		/* copy to   target address [r1]    */
 	cmp	r0, r2			/* until source end address [r2]    */
 	blo	copy_loop
 
@@ -185,7 +184,6 @@
 	 * fix .rel.dyn relocations
 	 */
 	ldr	r0, _TEXT_BASE		/* r0 <- Text base */
-	sub	r9, r6, r0		/* r9 <- relocation offset */
 	ldr	r10, _dynsym_start_ofs	/* r10 <- sym table ofs */
 	add	r10, r10, r0		/* r10 <- sym table in FLASH */
 	ldr	r2, _rel_dyn_start_ofs	/* r2 <- rel dyn start ofs */