From mboxrd@z Thu Jan  1 00:00:00 1970
From: will.deacon@arm.com (Will Deacon)
Date: Thu, 30 Jan 2014 18:56:45 +0000
Subject: [PATCH 5/5] arm64: add Crypto Extensions based synchronous core
 AES cipher
In-Reply-To: <1391014246-9715-6-git-send-email-ard.biesheuvel@linaro.org>
References: <1391014246-9715-1-git-send-email-ard.biesheuvel@linaro.org>
 <1391014246-9715-6-git-send-email-ard.biesheuvel@linaro.org>
Message-ID: <20140130185645.GC4437@mudshark.cambridge.arm.com>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

Hi Ard,

On Wed, Jan 29, 2014 at 04:50:46PM +0000, Ard Biesheuvel wrote:
> diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
> new file mode 100644
> index 000000000000..b5a5d5d6e4b8
> --- /dev/null
> +++ b/arch/arm64/crypto/aes-ce-cipher.c
> @@ -0,0 +1,103 @@
> +/*
> + * linux/arch/arm64/crypto/aes-ce-cipher.c
> + *
> + * Copyright (C) 2013 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
> + * published by the Free Software Foundation.
> + */
> +
> +#include <asm/neon.h>
> +#include <crypto/aes.h>
> +#include <linux/crypto.h>
> +#include <linux/module.h>
> +#include <linux/cpufeature.h>
> +
> +MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
> +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
> +MODULE_LICENSE("GPL");
> +
> +static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
> +{
> +	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
> +	u32 rounds = 6 + ctx->key_length / 4;

Can you document these constants please?

> +
> +	kernel_neon_begin();
> +
> +	__asm__("	ld1		{v0.16b}, [%[in]]		;"
> +		"	ld1		{v1.16b}, [%[key]], #16		;"
> +		"0:	aese		v0.16b, v1.16b			;"
> +		"	subs		%[rounds], %[rounds], #1	;"
> +		"	ld1		{v1.16b}, [%[key]], #16		;"
> +		"	beq		1f				;"
> +		"	aesmc		v0.16b, v0.16b			;"
> +		"	b		0b				;"
> +		"1:	eor		v0.16b, v0.16b, v1.16b		;"
> +		"	st1		{v0.16b}, [%[out]]		;"
> +	: :
> +		[out]		"r"(dst),
> +		[in]		"r"(src),
> +		[rounds]	"r"(rounds),
> +		[key]		"r"(ctx->key_enc)
> +	:			"cc");

You probably need a memory output to stop this being re-ordered by the
compiler. Can GCC not generate the addressing modes you need directly,
allowing you to avoid moving everything into registers?


> +	kernel_neon_end();
> +}
> +
> +static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
> +{
> +	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
> +	u32 rounds = 6 + ctx->key_length / 4;
> +
> +	kernel_neon_begin();
> +
> +	__asm__("	ld1		{v0.16b}, [%[in]]		;"
> +		"	ld1		{v1.16b}, [%[key]], #16		;"
> +		"0:	aesd		v0.16b, v1.16b			;"
> +		"	ld1		{v1.16b}, [%[key]], #16		;"
> +		"	subs		%[rounds], %[rounds], #1	;"
> +		"	beq		1f				;"
> +		"	aesimc		v0.16b, v0.16b			;"
> +		"	b		0b				;"
> +		"1:	eor		v0.16b, v0.16b, v1.16b		;"
> +		"	st1		{v0.16b}, [%[out]]		;"
> +	: :
> +		[out]		"r"(dst),
> +		[in]		"r"(src),
> +		[rounds]	"r"(rounds),
> +		[key]		"r"(ctx->key_dec)
> +	:			"cc");

Same comments here.

FWIW: I spoke to the guy at ARM who designed the crypto instructions and he
reckons your code works :)

Cheers,

Will "got a B in maths" Deacon