diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334e159f..857ad4f8905f 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
 
 	.text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-	mov		%o0, %g1
+	brz,pn		%o2, 99f
+	 mov		%o0, %g1
+
 	cmp		%o0, %o1
-	bleu,pt		%xcc, memcpy
+	bleu,pt		%xcc, 2f
 	 add		%o1, %o2, %g7
 	cmp		%g7, %o0
 	bleu,pt		%xcc, memcpy
@@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */
 	stb		%g7, [%o0]
 	bne,pt		%icc, 1b
 	 sub		%o0, 1, %o0
-
+99:
 	retl
 	 mov		%g1, %o0
+
+	/* We can't just call memcpy for these memmove cases.  On some
+	 * chips the memcpy uses cache initializing stores and when dst
+	 * and src are close enough, those can clobber the source data
+	 * before we've loaded it in.
+	 */
+2:	or		%o0, %o1, %g7
+	or		%o2, %g7, %g7
+	andcc		%g7, 0x7, %g0
+	bne,pn		%xcc, 4f
+	 nop
+
+3:	ldx		[%o1], %g7
+	add		%o1, 8, %o1
+	subcc		%o2, 8, %o2
+	add		%o0, 8, %o0
+	bne,pt		%icc, 3b
+	 stx		%g7, [%o0 - 0x8]
+	ba,a,pt		%xcc, 99b
+
+4:	ldub		[%o1], %g7
+	add		%o1, 1, %o1
+	subcc		%o2, 1, %o2
+	add		%o0, 1, %o0
+	bne,pt		%icc, 4b
+	 stb		%g7, [%o0 - 0x1]
+	ba,a,pt		%xcc, 99b
 ENDPROC(memmove)