crypto: arm64/ghash-ce - fix for big endian

The GHASH key and digest are both pairs of 64-bit quantities, but the
GHASH code does not always refer to them as such, causing failures when
built for big endian. So replace the 16x1 loads and stores with 2x8 ones.

Fixes: b913a6404ce2 ("arm64/crypto: improve performance of GHASH algorithm")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm64/crypto/ghash-ce-core.S

@@ -29,8 +29,8 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{SHASH.16b}, [x3]
-	ld1		{XL.16b}, [x1]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	shl		MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.16b}, [x1]
+	st1		{XL.2d}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)