diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 3f131129d1c1a496607637f39eb1f563596768d0..fe2d34e5332d8250dd778ca77489631e2a4e9266 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -18,11 +18,23 @@ _GLOBAL(memcpy)
 	andi.	r6,r6,7
 	dcbt	0,r4
 	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+   CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+   cleared.
+   At the time of writing the only CPU that has this combination of bits
+   set is Power6. */
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
 	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-	andi.	r0,r4,7
 	addi	r3,r3,-16
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
 	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	srdi	r7,r5,4
 	ld	r9,0(r4)
 	addi	r4,r4,-8
@@ -131,7 +143,7 @@ _GLOBAL(memcpy)
 	PPC_MTOCRF	0x01,r6		# put #bytes to 8B bdry into cr7
 	subf	r5,r6,r5
 	li	r7,0
-	cmpldi	r1,r5,16
+	cmpldi	cr1,r5,16
 	bf	cr7*4+3,1f
 	lbz	r0,0(r4)
 	stb	r0,0(r3)