diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S
index 64e08df..8b70041 100644
--- a/arch/mips/cavium-octeon/octeon-memcpy.S
+++ b/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -208,18 +208,18 @@
 	ADD	src, src, 16*NBYTES
 EXC(	STORE	t3, UNIT(7)(dst),	s_exc_p9u)
 	ADD	dst, dst, 16*NBYTES
-EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-8)(dst),	s_exc_p8u)
 EXC(	STORE	t1, UNIT(-7)(dst),	s_exc_p7u)
 EXC(	STORE	t2, UNIT(-6)(dst),	s_exc_p6u)
 EXC(	STORE	t3, UNIT(-5)(dst),	s_exc_p5u)
-EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-4)(dst),	s_exc_p4u)
 EXC(	STORE	t1, UNIT(-3)(dst),	s_exc_p3u)
 EXC(	STORE	t2, UNIT(-2)(dst),	s_exc_p2u)
@@ -383,6 +383,10 @@
 	 nop
 	END(memcpy)
 
+l_exc_copy_rewind16:
+	/* Rewind src and dst by 16*NBYTES for l_exc_copy */
+	SUB	src, src, 16*NBYTES
+	SUB	dst, dst, 16*NBYTES
 l_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a