sparc32: Fixed unaligned memory copying in function __csum_partial_co…

…py_sparc_generic

When we are in the label cc_dword_align, registers %o0 and %o1 have the same last 2 bits,
but it's not guaranteed one of them is zero. So we can get unaligned memory access
in label ccte. Example of parameters which lead to this:
%o0=0x7ff183e9, %o1=0x8e709e7d, %g1=3

With the parameters I had a memory corruption, when the additional 5 bytes were rewritten.
This patch corrects the error.

One comment to the patch. We don't care about the third bit in %o1, because cc_end_cruft
stores word or less.

Signed-off-by: Tkhai Kirill <tkhai@yandex.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/lib/checksum_32.S

@@ -289,10 +289,16 @@ cc_end_cruft:
 
 	/* Also, handle the alignment code out of band. */
 cc_dword_align:
-	cmp	%g1, 6
-	bl,a	ccte
+	cmp	%g1, 16
+	bge	1f
+	 srl	%g1, 1, %o3
+2:	cmp	%o3, 0
+	be,a	ccte
 	 andcc	%g1, 0xf, %o3
-	andcc	%o0, 0x1, %g0
+	andcc	%o3, %o0, %g0	! Check %o0 only (%o1 has the same last 2 bits)
+	be,a	2b
+	 srl	%o3, 1, %o3
+1:	andcc	%o0, 0x1, %g0
 	bne	ccslow
 	 andcc	%o0, 0x2, %g0
 	be	1f