crypto: arm64/aes-ce-cipher - match round key endianness with generic code

In order to be able to reuse the generic AES code as a fallback for
situations where the NEON may not be used, update the key handling
to match the byte order of the generic code: it stores round keys
as sequences of 32-bit quantities rather than streams of bytes, and
so our code needs to be updated to reflect that.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm64/crypto/aes-ce-ccm-core.S

 /*
  * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
  *
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -32,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	8f				/* out of input? */
 	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.16b}, [x4]			/* load first round key */
+1:	ld1	{v3.4s}, [x4]			/* load first round key */
 	prfm	pldl1strm, [x1]
 	cmp	w5, #12				/* which key size? */
 	add	x6, x4, #16
@@ -42,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
 	mov	v5.16b, v3.16b
 	b	4f
 2:	mov	v4.16b, v3.16b
-	ld1	{v5.16b}, [x6], #16		/* load 2nd round key */
+	ld1	{v5.4s}, [x6], #16		/* load 2nd round key */
 3:	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
-4:	ld1	{v3.16b}, [x6], #16		/* load next round key */
+4:	ld1	{v3.4s}, [x6], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
-5:	ld1	{v4.16b}, [x6], #16		/* load next round key */
+5:	ld1	{v4.4s}, [x6], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
-	ld1	{v5.16b}, [x6], #16		/* load next round key */
+	ld1	{v5.4s}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
 	subs	w2, w2, #16			/* last data? */
@@ -90,7 +90,7 @@ ENDPROC(ce_aes_ccm_auth_data)
 	 * 			 u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_final)
-	ld1	{v3.16b}, [x2], #16		/* load first round key */
+	ld1	{v3.4s}, [x2], #16		/* load first round key */
 	ld1	{v0.16b}, [x0]			/* load mac */
 	cmp	w3, #12				/* which key size? */
 	sub	w3, w3, #2			/* modified # of rounds */
@@ -100,17 +100,17 @@ ENTRY(ce_aes_ccm_final)
 	mov	v5.16b, v3.16b
 	b	2f
 0:	mov	v4.16b, v3.16b
-1:	ld1	{v5.16b}, [x2], #16		/* load next round key */
+1:	ld1	{v5.4s}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.16b}, [x2], #16		/* load next round key */
+2:	ld1	{v3.4s}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.16b}, [x2], #16		/* load next round key */
+3:	ld1	{v4.4s}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
@@ -137,31 +137,31 @@ CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 	cmp	w4, #12				/* which key size? */
 	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.16b}, [x3]			/* load first round key */
+	ld1	{v3.4s}, [x3]			/* load first round key */
 	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
 	b	3f
 1:	mov	v4.16b, v3.16b
-	ld1	{v5.16b}, [x10], #16		/* load 2nd round key */
+	ld1	{v5.4s}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.16b}, [x10], #16		/* load next round key */
+3:	ld1	{v3.4s}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.16b}, [x10], #16		/* load next round key */
+4:	ld1	{v4.4s}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
-	ld1	{v5.16b}, [x10], #16		/* load next round key */
+	ld1	{v5.4s}, [x10], #16		/* load next round key */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b

arch/arm64/crypto/aes-ce-cipher.c

 /*
  * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
  *
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
  */
 
 #include <asm/neon.h>
+#include <asm/unaligned.h>
 #include <crypto/aes.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
@@ -47,24 +48,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.16b}, [%[key]], #16		;"
+		"	ld1	{v1.4s}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.16b}, [%[key]], #16		;"
+		"	ld1	{v3.4s}, [%[key]], #16		;"
 		"1:	aese	v0.16b, v2.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.16b}, [%[key]], #16		;"
+		"2:	ld1	{v1.4s}, [%[key]], #16		;"
 		"	aese	v0.16b, v3.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.16b}, [%[key]], #16		;"
+		"3:	ld1	{v2.4s}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aese	v0.16b, v1.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.16b}, [%[key]], #16		;"
+		"	ld1	{v3.4s}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aese	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -92,24 +93,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.16b}, [%[key]], #16		;"
+		"	ld1	{v1.4s}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.16b}, [%[key]], #16		;"
+		"	ld1	{v3.4s}, [%[key]], #16		;"
 		"1:	aesd	v0.16b, v2.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.16b}, [%[key]], #16		;"
+		"2:	ld1	{v1.4s}, [%[key]], #16		;"
 		"	aesd	v0.16b, v3.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.16b}, [%[key]], #16		;"
+		"3:	ld1	{v2.4s}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aesd	v0.16b, v1.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.16b}, [%[key]], #16		;"
+		"	ld1	{v3.4s}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aesd	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -165,20 +166,16 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 	    key_len != AES_KEYSIZE_256)
 		return -EINVAL;
 
-	memcpy(ctx->key_enc, in_key, key_len);
 	ctx->key_length = key_len;
+	for (i = 0; i < kwords; i++)
+		ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
 
 	kernel_neon_begin_partial(2);
 	for (i = 0; i < sizeof(rcon); i++) {
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
-#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
-#else
-		rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
-			 rki[0];
-#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
@@ -210,9 +207,9 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 
 	key_dec[0] = key_enc[j];
 	for (i = 1, j--; j > 0; i++, j--)
-		__asm__("ld1	{v0.16b}, %[in]		;"
+		__asm__("ld1	{v0.4s}, %[in]		;"
 			"aesimc	v1.16b, v0.16b		;"
-			"st1	{v1.16b}, %[out]	;"
+			"st1	{v1.4s}, %[out]	;"
 
 		:	[out]	"=Q"(key_dec[i])
 		:	[in]	"Q"(key_enc[j])

arch/arm64/crypto/aes-ce.S

@@ -2,7 +2,7 @@
  * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
  *                                    Crypto Extensions
  *
- * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -22,11 +22,11 @@
 	cmp		\rounds, #12
 	blo		2222f		/* 128 bits */
 	beq		1111f		/* 192 bits */
-	ld1		{v17.16b-v18.16b}, [\rk], #32
-1111:	ld1		{v19.16b-v20.16b}, [\rk], #32
-2222:	ld1		{v21.16b-v24.16b}, [\rk], #64
-	ld1		{v25.16b-v28.16b}, [\rk], #64
-	ld1		{v29.16b-v31.16b}, [\rk]
+	ld1		{v17.4s-v18.4s}, [\rk], #32
+1111:	ld1		{v19.4s-v20.4s}, [\rk], #32
+2222:	ld1		{v21.4s-v24.4s}, [\rk], #64
+	ld1		{v25.4s-v28.4s}, [\rk], #64
+	ld1		{v29.4s-v31.4s}, [\rk]
 	.endm
 
 	/* prepare for encryption with key in rk[] */