crypto: arm64/aes-ce - add 5 way interleave routines

In preparation of tweaking the accelerated AES chaining mode routines
to be able to use a 5-way stride, implement the core routines to
support processing 5 blocks of input at a time. While at it, drop
the 2 way versions, which have been unused for a while now.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm64/crypto/aes-ce.S

@@ -52,7 +52,7 @@
 	load_round_keys	\rounds, \temp
 	.endm
 
-	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
+	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3, i4
 	aes\de		\i0\().16b, \k\().16b
 	aes\mc		\i0\().16b, \i0\().16b
 	.ifnb		\i1
@@ -63,27 +63,34 @@
 	aes\mc		\i2\().16b, \i2\().16b
 	aes\de		\i3\().16b, \k\().16b
 	aes\mc		\i3\().16b, \i3\().16b
+	.ifnb		\i4
+	aes\de		\i4\().16b, \k\().16b
+	aes\mc		\i4\().16b, \i4\().16b
+	.endif
 	.endif
 	.endif
 	.endm
 
-	/* up to 4 interleaved encryption rounds with the same round key */
-	.macro		round_Nx, enc, k, i0, i1, i2, i3
+	/* up to 5 interleaved encryption rounds with the same round key */
+	.macro		round_Nx, enc, k, i0, i1, i2, i3, i4
 	.ifc		\enc, e
-	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3
+	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3, \i4
 	.else
-	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3
+	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3, \i4
 	.endif
 	.endm
 
-	/* up to 4 interleaved final rounds */
-	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3
+	/* up to 5 interleaved final rounds */
+	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3, i4
 	aes\de		\i0\().16b, \k\().16b
 	.ifnb		\i1
 	aes\de		\i1\().16b, \k\().16b
 	.ifnb		\i3
 	aes\de		\i2\().16b, \k\().16b
 	aes\de		\i3\().16b, \k\().16b
+	.ifnb		\i4
+	aes\de		\i4\().16b, \k\().16b
+	.endif
 	.endif
 	.endif
 	eor		\i0\().16b, \i0\().16b, \k2\().16b
@@ -92,47 +99,52 @@
 	.ifnb		\i3
 	eor		\i2\().16b, \i2\().16b, \k2\().16b
 	eor		\i3\().16b, \i3\().16b, \k2\().16b
+	.ifnb		\i4
+	eor		\i4\().16b, \i4\().16b, \k2\().16b
+	.endif
 	.endif
 	.endif
 	.endm
 
-	/* up to 4 interleaved blocks */
-	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3
+	/* up to 5 interleaved blocks */
+	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3, i4
 	cmp		\rounds, #12
 	blo		2222f		/* 128 bits */
 	beq		1111f		/* 192 bits */
-	round_Nx	\enc, v17, \i0, \i1, \i2, \i3
-	round_Nx	\enc, v18, \i0, \i1, \i2, \i3
-1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3
-	round_Nx	\enc, v20, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v17, \i0, \i1, \i2, \i3, \i4
+	round_Nx	\enc, v18, \i0, \i1, \i2, \i3, \i4
+1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3, \i4
+	round_Nx	\enc, v20, \i0, \i1, \i2, \i3, \i4
 2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
-	round_Nx	\enc, \key, \i0, \i1, \i2, \i3
+	round_Nx	\enc, \key, \i0, \i1, \i2, \i3, \i4
 	.endr
-	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3
+	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3, \i4
 	.endm
 
 	.macro		encrypt_block, in, rounds, t0, t1, t2
 	do_block_Nx	e, \rounds, \in
 	.endm
 
-	.macro		encrypt_block2x, i0, i1, rounds, t0, t1, t2
-	do_block_Nx	e, \rounds, \i0, \i1
-	.endm
-
 	.macro		encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
 	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3
 	.endm
 
-	.macro		decrypt_block, in, rounds, t0, t1, t2
-	do_block_Nx	d, \rounds, \in
+	.macro		encrypt_block5x, i0, i1, i2, i3, i4, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3, \i4
 	.endm
 
-	.macro		decrypt_block2x, i0, i1, rounds, t0, t1, t2
-	do_block_Nx	d, \rounds, \i0, \i1
+	.macro		decrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \in
 	.endm
 
 	.macro		decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
 	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3
 	.endm
 
+	.macro		decrypt_block5x, i0, i1, i2, i3, i4, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3, \i4
+	.endm
+
+#define MAX_STRIDE	5
+
 #include "aes-modes.S"

arch/arm64/crypto/aes-modes.S

@@ -13,6 +13,10 @@
 	.text
 	.align		4
 
+#ifndef MAX_STRIDE
+#define MAX_STRIDE	4
+#endif
+
 aes_encrypt_block4x:
 	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
 	ret
@@ -23,6 +27,18 @@ aes_decrypt_block4x:
 	ret
 ENDPROC(aes_decrypt_block4x)
 
+#if MAX_STRIDE == 5
+aes_encrypt_block5x:
+	encrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
+	ret
+ENDPROC(aes_encrypt_block5x)
+
+aes_decrypt_block5x:
+	decrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
+	ret
+ENDPROC(aes_decrypt_block5x)
+#endif
+
 	/*
 	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
 	 *		   int blocks)

arch/arm64/crypto/aes-neon.S

@@ -117,26 +117,9 @@
 
 	/*
 	 * Interleaved versions: functionally equivalent to the
-	 * ones above, but applied to 2 or 4 AES states in parallel.
+	 * ones above, but applied to AES states in parallel.
 	 */
 
-	.macro		sub_bytes_2x, in0, in1
-	sub		v8.16b, \in0\().16b, v15.16b
-	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
-	sub		v9.16b, \in1\().16b, v15.16b
-	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
-	sub		v10.16b, v8.16b, v15.16b
-	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
-	sub		v11.16b, v9.16b, v15.16b
-	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
-	sub		v8.16b, v10.16b, v15.16b
-	tbx		\in0\().16b, {v24.16b-v27.16b}, v10.16b
-	sub		v9.16b, v11.16b, v15.16b
-	tbx		\in1\().16b, {v24.16b-v27.16b}, v11.16b
-	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
-	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
-	.endm
-
 	.macro		sub_bytes_4x, in0, in1, in2, in3
 	sub		v8.16b, \in0\().16b, v15.16b
 	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
@@ -215,25 +198,6 @@
 	eor		\in1\().16b, \in1\().16b, v11.16b
 	.endm
 
-	.macro		do_block_2x, enc, in0, in1, rounds, rk, rkp, i
-	ld1		{v15.4s}, [\rk]
-	add		\rkp, \rk, #16
-	mov		\i, \rounds
-1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
-	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
-	movi		v15.16b, #0x40
-	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
-	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
-	sub_bytes_2x	\in0, \in1
-	subs		\i, \i, #1
-	ld1		{v15.4s}, [\rkp], #16
-	beq		2222f
-	mix_columns_2x	\in0, \in1, \enc
-	b		1111b
-2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
-	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
-	.endm
-
 	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
 	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
@@ -260,14 +224,6 @@
 	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
 	.endm
 
-	.macro		encrypt_block2x, in0, in1, rounds, rk, rkp, i
-	do_block_2x	1, \in0, \in1, \rounds, \rk, \rkp, \i
-	.endm
-
-	.macro		decrypt_block2x, in0, in1, rounds, rk, rkp, i
-	do_block_2x	0, \in0, \in1, \rounds, \rk, \rkp, \i
-	.endm
-
 	.macro		encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
 	do_block_4x	1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
 	.endm