crypto: arm64/aes - performance tweak

Shuffle some instructions around in the __hround macro to shave off
0.1 cycles per byte on Cortex-A57.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm64/crypto/aes-cipher-core.S

@@ -20,46 +20,32 @@
 	tt		.req	x4
 	lt		.req	x2
 
-	.macro		__hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
-	ldp		\out0, \out1, [rk], #8
-
-	ubfx		w13, \in0, #0, #8
-	ubfx		w14, \in1, #8, #8
-	ldr		w13, [tt, w13, uxtw #2]
-	ldr		w14, [tt, w14, uxtw #2]
-
+	.macro		__pair, enc, reg0, reg1, in0, in1e, in1d, shift
+	ubfx		\reg0, \in0, #\shift, #8
 	.if		\enc
-	ubfx		w17, \in1, #0, #8
-	ubfx		w18, \in2, #8, #8
+	ubfx		\reg1, \in1e, #\shift, #8
 	.else
-	ubfx		w17, \in3, #0, #8
-	ubfx		w18, \in0, #8, #8
+	ubfx		\reg1, \in1d, #\shift, #8
 	.endif
-	ldr		w17, [tt, w17, uxtw #2]
-	ldr		w18, [tt, w18, uxtw #2]
+	ldr		\reg0, [tt, \reg0, uxtw #2]
+	ldr		\reg1, [tt, \reg1, uxtw #2]
+	.endm
 
-	ubfx		w15, \in2, #16, #8
-	ubfx		w16, \in3, #24, #8
-	ldr		w15, [tt, w15, uxtw #2]
-	ldr		w16, [tt, w16, uxtw #2]
+	.macro		__hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
+	ldp		\out0, \out1, [rk], #8
 
-	.if		\enc
-	ubfx		\t0, \in3, #16, #8
-	ubfx		\t1, \in0, #24, #8
-	.else
-	ubfx		\t0, \in1, #16, #8
-	ubfx		\t1, \in2, #24, #8
-	.endif
-	ldr		\t0, [tt, \t0, uxtw #2]
-	ldr		\t1, [tt, \t1, uxtw #2]
+	__pair		\enc, w13, w14, \in0, \in1, \in3, 0
+	__pair		\enc, w15, w16, \in1, \in2, \in0, 8
+	__pair		\enc, w17, w18, \in2, \in3, \in1, 16
+	__pair		\enc, \t0, \t1, \in3, \in0, \in2, 24
 
 	eor		\out0, \out0, w13
-	eor		\out1, \out1, w17
-	eor		\out0, \out0, w14, ror #24
-	eor		\out1, \out1, w18, ror #24
-	eor		\out0, \out0, w15, ror #16
-	eor		\out1, \out1, \t0, ror #16
-	eor		\out0, \out0, w16, ror #8
+	eor		\out1, \out1, w14
+	eor		\out0, \out0, w15, ror #24
+	eor		\out1, \out1, w16, ror #24
+	eor		\out0, \out0, w17, ror #16
+	eor		\out1, \out1, w18, ror #16
+	eor		\out0, \out0, \t0, ror #8
 	eor		\out1, \out1, \t1, ror #8
 	.endm