lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Tue, 21 Oct 2014 02:28:37 +0300
From:	Vladimir Zapolskiy <vz@...ia.com>
To:	LABBE Corentin <clabbe.montjoie@...il.com>, robh+dt@...nel.org,
	pawel.moll@....com, mark.rutland@....com,
	ijc+devicetree@...lion.org.uk, galak@...eaurora.org,
	maxime.ripard@...e-electrons.com, linux@....linux.org.uk,
	herbert@...dor.apana.org.au, davem@...emloft.net,
	grant.likely@...aro.org, akpm@...ux-foundation.org,
	gregkh@...uxfoundation.org, joe@...ches.com,
	mchehab@....samsung.com, crope@....fi
CC:	devicetree@...r.kernel.org, linux-kernel@...r.kernel.org,
	linux-sunxi@...glegroups.com, linux-crypto@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org
Subject: Re: [PATCH v5 4/4] crypto: Add Allwinner Security System crypto accelerator

Hello LABBE,

On 19.10.2014 17:16, LABBE Corentin wrote:
> Add support for the Security System included in Allwinner SoC A20.
> The Security System is a hardware cryptographic accelerator that support AES/MD5/SHA1/DES/3DES/PRNG algorithms.
> 
> Signed-off-by: LABBE Corentin <clabbe.montjoie@...il.com>
> ---
>  drivers/crypto/Kconfig                    |  17 ++
>  drivers/crypto/Makefile                   |   1 +
>  drivers/crypto/sunxi-ss/Makefile          |   2 +
>  drivers/crypto/sunxi-ss/sunxi-ss-cipher.c | 489 ++++++++++++++++++++++++++++++
>  drivers/crypto/sunxi-ss/sunxi-ss-core.c   | 318 +++++++++++++++++++
>  drivers/crypto/sunxi-ss/sunxi-ss-hash.c   | 445 +++++++++++++++++++++++++++
>  drivers/crypto/sunxi-ss/sunxi-ss.h        | 193 ++++++++++++
>  7 files changed, 1465 insertions(+)
>  create mode 100644 drivers/crypto/sunxi-ss/Makefile
>  create mode 100644 drivers/crypto/sunxi-ss/sunxi-ss-cipher.c
>  create mode 100644 drivers/crypto/sunxi-ss/sunxi-ss-core.c
>  create mode 100644 drivers/crypto/sunxi-ss/sunxi-ss-hash.c
>  create mode 100644 drivers/crypto/sunxi-ss/sunxi-ss.h
> 
> diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
> index 2fb0fdf..9ba9759 100644
> --- a/drivers/crypto/Kconfig
> +++ b/drivers/crypto/Kconfig
> @@ -436,4 +436,21 @@ config CRYPTO_DEV_QCE
>  	  hardware. To compile this driver as a module, choose M here. The
>  	  module will be called qcrypto.
>  
> +config CRYPTO_DEV_SUNXI_SS
> +	tristate "Support for Allwinner Security System cryptographic accelerator"
> +	depends on ARCH_SUNXI
> +	select CRYPTO_MD5
> +	select CRYPTO_SHA1
> +	select CRYPTO_AES
> +	select CRYPTO_DES
> +	select CRYPTO_BLKCIPHER
> +	help
> +	  Some Allwinner SoC have a crypto accelerator named
> +	  Security System. Select this if you want to use it.
> +	  The Security System handle AES/DES/3DES ciphers in CBC mode
> +	  and SHA1 and MD5 hash algorithms.
> +
> +	  To compile this driver as a module, choose M here: the module
> +	  will be called sunxi-ss.
> +
>  endif # CRYPTO_HW
> diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
> index 3924f93..856545c 100644
> --- a/drivers/crypto/Makefile
> +++ b/drivers/crypto/Makefile
> @@ -25,3 +25,4 @@ obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o
>  obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
>  obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
>  obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
> +obj-$(CONFIG_CRYPTO_DEV_SUNXI_SS) += sunxi-ss/
> diff --git a/drivers/crypto/sunxi-ss/Makefile b/drivers/crypto/sunxi-ss/Makefile
> new file mode 100644
> index 0000000..8bb287d
> --- /dev/null
> +++ b/drivers/crypto/sunxi-ss/Makefile
> @@ -0,0 +1,2 @@
> +obj-$(CONFIG_CRYPTO_DEV_SUNXI_SS) += sunxi-ss.o
> +sunxi-ss-y += sunxi-ss-core.o sunxi-ss-hash.o sunxi-ss-cipher.o
> diff --git a/drivers/crypto/sunxi-ss/sunxi-ss-cipher.c b/drivers/crypto/sunxi-ss/sunxi-ss-cipher.c
> new file mode 100644
> index 0000000..8d0416e
> --- /dev/null
> +++ b/drivers/crypto/sunxi-ss/sunxi-ss-cipher.c
> @@ -0,0 +1,489 @@
> +/*
> + * sunxi-ss-cipher.c - hardware cryptographic accelerator for Allwinner A20 SoC
> + *
> + * Copyright (C) 2013-2014 Corentin LABBE <clabbe.montjoie@...il.com>
> + *
> + * This file add support for AES cipher with 128,192,256 bits
> + * keysize in CBC mode.
> + * Add support also for DES and 3DES in CBC mode.
> + *
> + * You could find the datasheet in Documentation/arm/sunxi/README
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + */
> +#include "sunxi-ss.h"
> +
> +extern struct sunxi_ss_ctx *ss;
> +
> +static int sunxi_ss_cipher(struct ablkcipher_request *areq, u32 mode)
> +{
> +	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +	const char *cipher_type;
> +
> +	if (areq->nbytes == 0)
> +		return 0;
> +
> +	if (areq->info == NULL) {
> +		dev_err(ss->dev, "ERROR: Empty IV\n");
> +		return -EINVAL;
> +	}
> +
> +	if (areq->src == NULL || areq->dst == NULL) {
> +		dev_err(ss->dev, "ERROR: Some SGs are NULL\n");
> +		return -EINVAL;
> +	}
> +
> +	cipher_type = crypto_tfm_alg_name(crypto_ablkcipher_tfm(tfm));
> +
> +	if (strcmp("cbc(aes)", cipher_type) == 0) {
> +		mode |= SS_OP_AES | SS_CBC | SS_ENABLED | op->keymode;
> +		return sunxi_ss_aes_poll(areq, mode);
> +	}
> +
> +	if (strcmp("cbc(des)", cipher_type) == 0) {
> +		mode |= SS_OP_DES | SS_CBC | SS_ENABLED | op->keymode;
> +		return sunxi_ss_des_poll(areq, mode);
> +	}
> +
> +	if (strcmp("cbc(des3_ede)", cipher_type) == 0) {
> +		mode |= SS_OP_3DES | SS_CBC | SS_ENABLED | op->keymode;
> +		return sunxi_ss_des_poll(areq, mode);
> +	}
> +
> +	dev_err(ss->dev, "ERROR: Cipher %s not handled\n", cipher_type);
> +	return -EINVAL;
> +}
> +
> +int sunxi_ss_cipher_encrypt(struct ablkcipher_request *areq)
> +{
> +	return sunxi_ss_cipher(areq, SS_ENCRYPTION);
> +}
> +
> +int sunxi_ss_cipher_decrypt(struct ablkcipher_request *areq)
> +{
> +	return sunxi_ss_cipher(areq, SS_DECRYPTION);
> +}
> +
> +int sunxi_ss_cipher_init(struct crypto_tfm *tfm)
> +{
> +	struct sunxi_tfm_ctx *op = crypto_tfm_ctx(tfm);
> +
> +	memset(op, 0, sizeof(struct sunxi_tfm_ctx));
> +	return 0;
> +}
> +
> +/*
> + * Optimized function for the case where we have only one SG,
> + * so we can use kmap_atomic
> + */
> +static int sunxi_ss_aes_poll_atomic(struct ablkcipher_request *areq)
> +{
> +	u32 spaces;
> +	struct scatterlist *in_sg = areq->src;
> +	struct scatterlist *out_sg = areq->dst;
> +	void *src_addr;
> +	void *dst_addr;
> +	unsigned int ileft = areq->nbytes;
> +	unsigned int oleft = areq->nbytes;
> +	unsigned int todo;
> +	u32 *src32;
> +	u32 *dst32;
> +	u32 rx_cnt = 32;
> +	u32 tx_cnt = 0;
> +	int i;
> +
> +	src_addr = kmap_atomic(sg_page(in_sg)) + in_sg->offset;
> +	if (src_addr == NULL) {
> +		dev_err(ss->dev, "kmap_atomic error for src SG\n");
> +		writel(0, ss->base + SS_CTL);
> +		mutex_unlock(&ss->lock);
> +		return -EINVAL;
> +	}
> +
> +	dst_addr = kmap_atomic(sg_page(out_sg)) + out_sg->offset;
> +	if (dst_addr == NULL) {
> +		dev_err(ss->dev, "kmap_atomic error for dst SG\n");
> +		writel(0, ss->base + SS_CTL);
> +		kunmap_atomic(src_addr);
> +		mutex_unlock(&ss->lock);
> +		return -EINVAL;
> +	}
> +
> +	src32 = (u32 *)src_addr;
> +	dst32 = (u32 *)dst_addr;
> +	ileft = areq->nbytes / 4;
> +	oleft = areq->nbytes / 4;
> +	i = 0;
> +	do {
> +		if (ileft > 0 && rx_cnt > 0) {
> +			todo = min(rx_cnt, ileft);
> +			ileft -= todo;
> +			do {
> +				writel_relaxed(*src32++,
> +						ss->base +
> +						SS_RXFIFO);
> +				todo--;
> +			} while (todo > 0);
> +		}
> +		if (tx_cnt > 0) {
> +			todo = min(tx_cnt, oleft);
> +			oleft -= todo;
> +			do {
> +				*dst32++ = readl_relaxed(ss->base +
> +						SS_TXFIFO);
> +				todo--;
> +			} while (todo > 0);
> +		}
> +		spaces = readl_relaxed(ss->base + SS_FCSR);
> +		rx_cnt = SS_RXFIFO_SPACES(spaces);
> +		tx_cnt = SS_TXFIFO_SPACES(spaces);
> +	} while (oleft > 0);
> +	writel(0, ss->base + SS_CTL);
> +	kunmap_atomic(src_addr);
> +	kunmap_atomic(dst_addr);
> +	mutex_unlock(&ss->lock);
> +	return 0;
> +}
> +
> +int sunxi_ss_aes_poll(struct ablkcipher_request *areq, u32 mode)
> +{
> +	u32 spaces;
> +	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
> +	/* when activating SS, the default FIFO space is 32 */
> +	u32 rx_cnt = 32;
> +	u32 tx_cnt = 0;
> +	u32 v;
> +	int i;
> +	struct scatterlist *in_sg = areq->src;
> +	struct scatterlist *out_sg = areq->dst;
> +	void *src_addr;
> +	void *dst_addr;
> +	unsigned int ileft = areq->nbytes;
> +	unsigned int oleft = areq->nbytes;
> +	unsigned int sgileft = areq->src->length;
> +	unsigned int sgoleft = areq->dst->length;
> +	unsigned int todo;
> +	u32 *src32;
> +	u32 *dst32;
> +
> +	mutex_lock(&ss->lock);
> +
> +	for (i = 0; i < op->keylen; i += 4)
> +		writel(*(op->key + i/4), ss->base + SS_KEY0 + i);
> +
> +	if (areq->info != NULL) {
> +		for (i = 0; i < 4 && i < ivsize / 4; i++) {
> +			v = *(u32 *)(areq->info + i * 4);
> +			writel(v, ss->base + SS_IV0 + i * 4);
> +		}
> +	}
> +	writel(mode, ss->base + SS_CTL);
> +
> +	/* If we have only one SG, we can use kmap_atomic */
> +	if (sg_next(in_sg) == NULL && sg_next(out_sg) == NULL)
> +		return sunxi_ss_aes_poll_atomic(areq);

for clarity it might be better to move all "mutex_unlock(&ss->lock)"
calls from sunxi_ss_aes_poll_atomic() body right to here.

> +
> +	/*
> +	 * If we have more than one SG, we cannot use kmap_atomic since
> +	 * we hold the mapping too long
> +	 */
> +	src_addr = kmap(sg_page(in_sg)) + in_sg->offset;
> +	if (src_addr == NULL) {
> +		dev_err(ss->dev, "KMAP error for src SG\n");
> +		mutex_unlock(&ss->lock);
> +		return -EINVAL;
> +	}
> +	dst_addr = kmap(sg_page(out_sg)) + out_sg->offset;
> +	if (dst_addr == NULL) {
> +		kunmap(sg_page(in_sg));
> +		dev_err(ss->dev, "KMAP error for dst SG\n");
> +		mutex_unlock(&ss->lock);
> +		return -EINVAL;
> +	}
> +	src32 = (u32 *)src_addr;
> +	dst32 = (u32 *)dst_addr;
> +	ileft = areq->nbytes / 4;
> +	oleft = areq->nbytes / 4;
> +	sgileft = in_sg->length / 4;
> +	sgoleft = out_sg->length / 4;
> +	do {
> +		spaces = readl_relaxed(ss->base + SS_FCSR);
> +		rx_cnt = SS_RXFIFO_SPACES(spaces);
> +		tx_cnt = SS_TXFIFO_SPACES(spaces);
> +		todo = min3(rx_cnt, ileft, sgileft);
> +		if (todo > 0) {
> +			ileft -= todo;
> +			sgileft -= todo;
> +		}
> +		while (todo > 0) {
> +			writel_relaxed(*src32++, ss->base + SS_RXFIFO);
> +			todo--;
> +		}
> +		if (in_sg != NULL && sgileft == 0 && ileft > 0) {
> +			kunmap(sg_page(in_sg));
> +			in_sg = sg_next(in_sg);
> +			while (in_sg != NULL && in_sg->length == 0)
> +				in_sg = sg_next(in_sg);
> +			if (in_sg != NULL && ileft > 0) {
> +				src_addr = kmap(sg_page(in_sg)) + in_sg->offset;
> +				if (src_addr == NULL) {
> +					dev_err(ss->dev, "ERROR: KMAP for src SG\n");
> +					mutex_unlock(&ss->lock);
> +					return -EINVAL;
> +				}
> +				src32 = src_addr;
> +				sgileft = in_sg->length / 4;
> +			}
> +		}
> +		/* do not test oleft since when oleft == 0 we have finished */
> +		todo = min3(tx_cnt, oleft, sgoleft);
> +		if (todo > 0) {
> +			oleft -= todo;
> +			sgoleft -= todo;
> +		}
> +		while (todo > 0) {
> +			*dst32++ = readl_relaxed(ss->base + SS_TXFIFO);
> +			todo--;
> +		}
> +		if (out_sg != NULL && sgoleft == 0 && oleft >= 0) {
> +			kunmap(sg_page(out_sg));
> +			out_sg = sg_next(out_sg);
> +			while (out_sg != NULL && out_sg->length == 0)
> +				out_sg = sg_next(out_sg);
> +			if (out_sg != NULL && oleft > 0) {
> +				dst_addr = kmap(sg_page(out_sg)) +
> +					out_sg->offset;
> +				if (dst_addr == NULL) {
> +					dev_err(ss->dev, "KMAP error\n");
> +					mutex_unlock(&ss->lock);
> +					return -EINVAL;
> +				}
> +				dst32 = dst_addr;
> +				sgoleft = out_sg->length / 4;
> +			}
> +		}
> +	} while (oleft > 0);
> +
> +	writel_relaxed(0, ss->base + SS_CTL);
> +	mutex_unlock(&ss->lock);
> +	return 0;
> +}
> +
> +/*
> + * Pure CPU way of doing DES/3DES with SS
> + * Since DES and 3DES SGs could be smaller than 4 bytes, I use sg_copy_to_buffer
> + * for "linearize" them.
> + * The problem with that is that I alloc (2 x areq->nbytes) for buf_in/buf_out
> + * TODO: change this system, I need to support other mode than CBC where len
> + * is not a multiple of 4 and the hack of linearize use too much memory
> + * SGsrc -> buf_in -> SS -> buf_out -> SGdst
> + */
> +int sunxi_ss_des_poll(struct ablkcipher_request *areq, u32 mode)
> +{
> +	u32 value, spaces;
> +	size_t nb_in_sg_tx, nb_in_sg_rx;
> +	size_t ir, it;
> +	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq);
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +	unsigned int ivsize = crypto_ablkcipher_ivsize(tfm);
> +	u32 tx_cnt = 0;
> +	u32 rx_cnt = 0;
> +	u32 v;
> +	int i;
> +	int no_chunk = 1;
> +	struct scatterlist *in_sg = areq->src;
> +	struct scatterlist *out_sg = areq->dst;
> +
> +	/*
> +	 * if we have only SGs with size multiple of 4,
> +	 * we can use the SS AES function
> +	 */
> +	while (in_sg != NULL && no_chunk == 1) {
> +		if ((in_sg->length % 4) != 0)
> +			no_chunk = 0;
> +		in_sg = sg_next(in_sg);
> +	}
> +	while (out_sg != NULL && no_chunk == 1) {
> +		if ((out_sg->length % 4) != 0)
> +			no_chunk = 0;
> +		out_sg = sg_next(out_sg);
> +	}
> +
> +	if (no_chunk == 1)
> +		return sunxi_ss_aes_poll(areq, mode);
> +
> +	in_sg = areq->src;
> +	out_sg = areq->dst;
> +
> +	nb_in_sg_rx = sg_nents(in_sg);
> +	nb_in_sg_tx = sg_nents(out_sg);
> +
> +	/*
> +	 * buf_in and buf_out are allocated only one time
> +	 * then we keep the buffer until driver end
> +	 * the allocation can only grow more
> +	 * we do not reduce it for simplification
> +	 */
> +	mutex_lock(&ss->bufin_lock);
> +	if (ss->buf_in == NULL) {
> +		ss->buf_in = kmalloc(areq->nbytes, GFP_KERNEL);
> +		ss->buf_in_size = areq->nbytes;
> +	} else {
> +		if (areq->nbytes > ss->buf_in_size) {
> +			kfree(ss->buf_in);
> +			ss->buf_in = kmalloc(areq->nbytes, GFP_KERNEL);
> +			ss->buf_in_size = areq->nbytes;
> +		}
> +	}
> +	if (ss->buf_in == NULL) {
> +		ss->buf_in_size = 0;
> +		mutex_unlock(&ss->bufin_lock);
> +		dev_err(ss->dev, "Unable to allocate pages.\n");
> +		return -ENOMEM;
> +	}
> +	mutex_lock(&ss->bufout_lock);
> +	if (ss->buf_out == NULL) {
> +		ss->buf_out = kmalloc(areq->nbytes, GFP_KERNEL);
> +		if (ss->buf_out == NULL) {
> +			ss->buf_out_size = 0;
> +			mutex_unlock(&ss->bufin_lock);
> +			mutex_unlock(&ss->bufout_lock);
> +			dev_err(ss->dev, "Unable to allocate pages.\n");
> +			return -ENOMEM;
> +		}
> +		ss->buf_out_size = areq->nbytes;
> +	} else {
> +		if (areq->nbytes > ss->buf_out_size) {
> +			kfree(ss->buf_out);
> +			ss->buf_out = kmalloc(areq->nbytes, GFP_KERNEL);
> +			if (ss->buf_out == NULL) {
> +				ss->buf_out_size = 0;
> +				mutex_unlock(&ss->bufin_lock);
> +				mutex_unlock(&ss->bufout_lock);
> +				dev_err(ss->dev, "Unable to allocate pages.\n");
> +				return -ENOMEM;
> +			}
> +			ss->buf_out_size = areq->nbytes;
> +		}
> +	}
> +
> +	sg_copy_to_buffer(areq->src, nb_in_sg_rx, ss->buf_in, areq->nbytes);
> +
> +	ir = 0;
> +	it = 0;
> +	mutex_lock(&ss->lock);
> +
> +	for (i = 0; i < op->keylen; i += 4)
> +		writel(*(op->key + i/4), ss->base + SS_KEY0 + i);
> +	if (areq->info != NULL) {
> +		for (i = 0; i < 4 && i < ivsize / 4; i++) {
> +			v = *(u32 *)(areq->info + i * 4);
> +			writel(v, ss->base + SS_IV0 + i * 4);
> +		}
> +	}
> +	writel(mode, ss->base + SS_CTL);
> +
> +	do {
> +		if (rx_cnt == 0 || tx_cnt == 0) {
> +			spaces = readl(ss->base + SS_FCSR);
> +			rx_cnt = SS_RXFIFO_SPACES(spaces);
> +			tx_cnt = SS_TXFIFO_SPACES(spaces);
> +		}
> +		if (rx_cnt > 0 && ir < areq->nbytes) {
> +			do {
> +				value = *(u32 *)(ss->buf_in + ir);
> +				writel(value, ss->base + SS_RXFIFO);
> +				ir += 4;
> +				rx_cnt--;
> +			} while (rx_cnt > 0 && ir < areq->nbytes);
> +		}
> +		if (tx_cnt > 0 && it < areq->nbytes) {
> +			do {
> +				value = readl(ss->base + SS_TXFIFO);
> +				*(u32 *)(ss->buf_out + it) = value;
> +				it += 4;
> +				tx_cnt--;
> +			} while (tx_cnt > 0 && it < areq->nbytes);
> +		}
> +		if (ir == areq->nbytes) {
> +			mutex_unlock(&ss->bufin_lock);
> +			ir++;
> +		}
> +	} while (it < areq->nbytes);
> +
> +	writel(0, ss->base + SS_CTL);
> +	mutex_unlock(&ss->lock);
> +
> +	/*
> +	 * a simple optimization, since we dont need the hardware for this copy
> +	 * we release the lock and do the copy. With that we gain 5/10% perf
> +	 */
> +	sg_copy_from_buffer(areq->dst, nb_in_sg_tx, ss->buf_out, areq->nbytes);
> +
> +	mutex_unlock(&ss->bufout_lock);
> +	return 0;
> +}
> +
> +/* check and set the AES key, prepare the mode to be used */
> +int sunxi_ss_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen)
> +{
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +
> +	switch (keylen) {
> +	case 128 / 8:
> +		op->keymode = SS_AES_128BITS;
> +		break;
> +	case 192 / 8:
> +		op->keymode = SS_AES_192BITS;
> +		break;
> +	case 256 / 8:
> +		op->keymode = SS_AES_256BITS;
> +		break;
> +	default:
> +		dev_err(ss->dev, "ERROR: Invalid keylen %u\n", keylen);
> +		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
> +		return -EINVAL;
> +	}
> +	op->keylen = keylen;
> +	memcpy(op->key, key, keylen);
> +	return 0;
> +}
> +
> +/* check and set the DES key, prepare the mode to be used */
> +int sunxi_ss_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen)
> +{
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +
> +	if (keylen != DES_KEY_SIZE) {
> +		dev_err(ss->dev, "Invalid keylen %u\n", keylen);
> +		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
> +		return -EINVAL;
> +	}
> +	op->keylen = keylen;
> +	memcpy(op->key, key, keylen);
> +	return 0;
> +}
> +
> +/* check and set the 3DES key, prepare the mode to be used */
> +int sunxi_ss_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen)
> +{
> +	struct sunxi_tfm_ctx *op = crypto_ablkcipher_ctx(tfm);
> +
> +	if (keylen != 3 * DES_KEY_SIZE) {
> +		dev_err(ss->dev, "Invalid keylen %u\n", keylen);
> +		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
> +		return -EINVAL;
> +	}
> +	op->keylen = keylen;
> +	memcpy(op->key, key, keylen);
> +	return 0;
> +}
> diff --git a/drivers/crypto/sunxi-ss/sunxi-ss-core.c b/drivers/crypto/sunxi-ss/sunxi-ss-core.c
> new file mode 100644
> index 0000000..e66d7e2
> --- /dev/null
> +++ b/drivers/crypto/sunxi-ss/sunxi-ss-core.c
> @@ -0,0 +1,318 @@
> +/*
> + * sunxi-ss-core.c - hardware cryptographic accelerator for Allwinner A20 SoC
> + *
> + * Copyright (C) 2013-2014 Corentin LABBE <clabbe.montjoie@...il.com>
> + *
> + * Core file which registers crypto algorithms supported by the SS.
> + *
> + * You could find a link for the datasheet in Documentation/arm/sunxi/README
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + */
> +#include <linux/clk.h>
> +#include <linux/crypto.h>
> +#include <linux/io.h>
> +#include <linux/module.h>
> +#include <linux/of.h>
> +#include <linux/platform_device.h>
> +#include <crypto/scatterwalk.h>
> +#include <linux/scatterlist.h>
> +#include <linux/interrupt.h>
> +#include <linux/delay.h>
> +
> +#include "sunxi-ss.h"
> +
> +struct sunxi_ss_ctx *ss;
> +
> +/*
> + * General notes for whole driver:
> + *
> + * After each request the device must be disabled with a write of 0 in SS_CTL
> + *
> + * For performance reason, we use writel_relaxed/read_relaxed for all
> + * operations on RX and TX FIFO and also SS_FCSR.
> + * Excepts for the last write on TX FIFO.
> + * For all other registers, we use writel/readl.
> + * See http://permalink.gmane.org/gmane.linux.ports.arm.kernel/117644
> + * and http://permalink.gmane.org/gmane.linux.ports.arm.kernel/117640
> + */
> +
> +static struct ahash_alg sunxi_md5_alg = {
> +	.init = sunxi_hash_init,
> +	.update = sunxi_hash_update,
> +	.final = sunxi_hash_final,
> +	.finup = sunxi_hash_finup,
> +	.digest = sunxi_hash_digest,
> +	.halg = {
> +		.digestsize = MD5_DIGEST_SIZE,
> +		.base = {
> +			.cra_name = "md5",
> +			.cra_driver_name = "md5-sunxi-ss",
> +			.cra_priority = 300,
> +			.cra_alignmask = 3,
> +			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
> +			.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
> +			.cra_ctxsize = sizeof(struct sunxi_req_ctx),
> +			.cra_module = THIS_MODULE,
> +			.cra_type = &crypto_ahash_type,
> +			.cra_init = sunxi_hash_crainit
> +		}
> +	}
> +};
> +
> +static struct ahash_alg sunxi_sha1_alg = {
> +	.init = sunxi_hash_init,
> +	.update = sunxi_hash_update,
> +	.final = sunxi_hash_final,
> +	.finup = sunxi_hash_finup,
> +	.digest = sunxi_hash_digest,
> +	.halg = {
> +		.digestsize = SHA1_DIGEST_SIZE,
> +		.base = {
> +			.cra_name = "sha1",
> +			.cra_driver_name = "sha1-sunxi-ss",
> +			.cra_priority = 300,
> +			.cra_alignmask = 3,
> +			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
> +			.cra_blocksize = SHA1_BLOCK_SIZE,
> +			.cra_ctxsize = sizeof(struct sunxi_req_ctx),
> +			.cra_module = THIS_MODULE,
> +			.cra_type = &crypto_ahash_type,
> +			.cra_init = sunxi_hash_crainit
> +		}
> +	}
> +};
> +
> +static struct crypto_alg sunxi_cipher_algs[] = {
> +{
> +	.cra_name = "cbc(aes)",
> +	.cra_driver_name = "cbc-aes-sunxi-ss",
> +	.cra_priority = 300,
> +	.cra_blocksize = AES_BLOCK_SIZE,
> +	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
> +	.cra_ctxsize = sizeof(struct sunxi_tfm_ctx),
> +	.cra_module = THIS_MODULE,
> +	.cra_alignmask = 3,
> +	.cra_type = &crypto_ablkcipher_type,
> +	.cra_init = sunxi_ss_cipher_init,
> +	.cra_u = {
> +		.ablkcipher = {
> +			.min_keysize    = AES_MIN_KEY_SIZE,
> +			.max_keysize    = AES_MAX_KEY_SIZE,
> +			.ivsize         = AES_BLOCK_SIZE,
> +			.setkey         = sunxi_ss_aes_setkey,
> +			.encrypt        = sunxi_ss_cipher_encrypt,
> +			.decrypt        = sunxi_ss_cipher_decrypt,
> +		}
> +	}
> +}, {
> +	.cra_name = "cbc(des)",
> +	.cra_driver_name = "cbc-des-sunxi-ss",
> +	.cra_priority = 300,
> +	.cra_blocksize = DES_BLOCK_SIZE,
> +	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
> +	.cra_ctxsize = sizeof(struct sunxi_req_ctx),
> +	.cra_module = THIS_MODULE,
> +	.cra_alignmask = 3,
> +	.cra_type = &crypto_ablkcipher_type,
> +	.cra_init = sunxi_ss_cipher_init,
> +	.cra_u.ablkcipher = {
> +		.min_keysize    = DES_KEY_SIZE,
> +		.max_keysize    = DES_KEY_SIZE,
> +		.ivsize         = DES_BLOCK_SIZE,
> +		.setkey         = sunxi_ss_des_setkey,
> +		.encrypt        = sunxi_ss_cipher_encrypt,
> +		.decrypt        = sunxi_ss_cipher_decrypt,
> +	}
> +}, {
> +	.cra_name = "cbc(des3_ede)",
> +	.cra_driver_name = "cbc-des3-sunxi-ss",
> +	.cra_priority = 300,
> +	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
> +	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
> +	.cra_ctxsize = sizeof(struct sunxi_req_ctx),
> +	.cra_module = THIS_MODULE,
> +	.cra_alignmask = 3,
> +	.cra_type = &crypto_ablkcipher_type,
> +	.cra_init = sunxi_ss_cipher_init,
> +	.cra_u.ablkcipher = {
> +		.min_keysize    = DES3_EDE_KEY_SIZE,
> +		.max_keysize    = DES3_EDE_KEY_SIZE,
> +		.ivsize         = DES3_EDE_BLOCK_SIZE,
> +		.setkey         = sunxi_ss_des3_setkey,
> +		.encrypt        = sunxi_ss_cipher_encrypt,
> +		.decrypt        = sunxi_ss_cipher_decrypt,
> +	}
> +}
> +};
> +
> +static int sunxi_ss_probe(struct platform_device *pdev)
> +{
> +	struct resource *res;
> +	u32 v;
> +	int err;
> +	unsigned long cr;
> +	const unsigned long cr_ahb = 24 * 1000 * 1000;
> +	const unsigned long cr_mod = 150 * 1000 * 1000;
> +
> +	if (!pdev->dev.of_node)
> +		return -ENODEV;
> +
> +	ss = devm_kzalloc(&pdev->dev, sizeof(*ss), GFP_KERNEL);
> +	if (ss == NULL)
> +		return -ENOMEM;

Why do you dynamically allocate memory for "struct sunxi_ss_ctx *ss"?
Since you have a single global pointer, it makes sense to declare
"struct sunxi_ss_ctx ss" statically instead.

And even a better solution is to remove a single global pointer.

> +
> +	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> +	ss->base = devm_ioremap_resource(&pdev->dev, res);
> +	if (IS_ERR(ss->base)) {
> +		dev_err(&pdev->dev, "Cannot request MMIO\n");
> +		return PTR_ERR(ss->base);
> +	}
> +
> +	ss->ssclk = devm_clk_get(&pdev->dev, "mod");
> +	if (IS_ERR(ss->ssclk)) {
> +		err = PTR_ERR(ss->ssclk);
> +		dev_err(&pdev->dev, "Cannot get SS clock err=%d\n", err);
> +		return err;
> +	}
> +	dev_dbg(&pdev->dev, "clock ss acquired\n");
> +
> +	ss->busclk = devm_clk_get(&pdev->dev, "ahb");
> +	if (IS_ERR(ss->busclk)) {
> +		err = PTR_ERR(ss->busclk);
> +		dev_err(&pdev->dev, "Cannot get AHB SS clock err=%d\n", err);
> +		return err;
> +	}
> +	dev_dbg(&pdev->dev, "clock ahb_ss acquired\n");
> +
> +	/* Enable both clocks */
> +	err = clk_prepare_enable(ss->busclk);
> +	if (err != 0) {
> +		dev_err(&pdev->dev, "Cannot prepare_enable busclk\n");
> +		return err;
> +	}
> +	err = clk_prepare_enable(ss->ssclk);
> +	if (err != 0) {
> +		dev_err(&pdev->dev, "Cannot prepare_enable ssclk\n");
> +		clk_disable_unprepare(ss->busclk);

goto somewhere to the end of the function?

> +		return err;
> +	}
> +
> +	/*
> +	 * Check that clock have the correct rates gived in the datasheet
> +	 * Try to set the clock to the maximum allowed
> +	 */
> +	err = clk_set_rate(ss->ssclk, cr_mod);
> +	if (err != 0) {
> +		dev_err(&pdev->dev, "Cannot set clock rate to ssclk\n");
> +		clk_disable_unprepare(ss->ssclk);
> +		clk_disable_unprepare(ss->busclk);

goto "error_md5"?

> +		return err;
> +	}
> +
> +	cr = clk_get_rate(ss->busclk);
> +	if (cr >= cr_ahb)
> +		dev_dbg(&pdev->dev, "Clock bus %lu (%lu MHz) (must be >= %lu)\n",
> +				cr, cr / 1000000, cr_ahb);
> +	else
> +		dev_warn(&pdev->dev, "Clock bus %lu (%lu MHz) (must be >= %lu)\n",
> +				cr, cr / 1000000, cr_ahb);

See next comment.

> +	cr = clk_get_rate(ss->ssclk);
> +	if (cr <= cr_mod)
> +		if (cr < cr_mod)
> +			dev_info(&pdev->dev, "Clock ss %lu (%lu MHz) (must be <= %lu)\n",
> +					cr, cr / 1000000, cr_mod);
> +		else
> +			dev_dbg(&pdev->dev, "Clock ss %lu (%lu MHz) (must be <= %lu)\n",
> +					cr, cr / 1000000, cr_mod);
> +	else
> +		dev_warn(&pdev->dev, "Clock ss is at %lu (%lu MHz) (must be <= %lu)\n",
> +				cr, cr / 1000000, cr_mod);

The management of kernel log levels looks pretty strange. As far as I
understand there is no error on any clock rate, I'd recommend to keep
only one information message.

> +	/*
> +	 * Datasheet named it "Die Bonding ID"
> +	 * I expect to be a sort of Security System Revision number.
> +	 * Since the A80 seems to have an other version of SS
> +	 * this info could be useful
> +	 */
> +	writel(SS_ENABLED, ss->base + SS_CTL);
> +	v = readl(ss->base + SS_CTL);
> +	v >>= 16;
> +	v &= 0x07;
> +	dev_info(&pdev->dev, "Die ID %d\n", v);
> +	writel(0, ss->base + SS_CTL);
> +
> +	ss->dev = &pdev->dev;
> +
> +	mutex_init(&ss->lock);
> +	mutex_init(&ss->bufin_lock);
> +	mutex_init(&ss->bufout_lock);
> +
> +	err = crypto_register_ahash(&sunxi_md5_alg);
> +	if (err)
> +		goto error_md5;
> +	err = crypto_register_ahash(&sunxi_sha1_alg);
> +	if (err)
> +		goto error_sha1;
> +	err = crypto_register_algs(sunxi_cipher_algs,
> +			ARRAY_SIZE(sunxi_cipher_algs));
> +	if (err)
> +		goto error_ciphers;
> +
> +	return 0;
> +error_ciphers:
> +	crypto_unregister_ahash(&sunxi_sha1_alg);
> +error_sha1:
> +	crypto_unregister_ahash(&sunxi_md5_alg);
> +error_md5:
> +	clk_disable_unprepare(ss->ssclk);
> +	clk_disable_unprepare(ss->busclk);
> +	return err;
> +}
> +
> +static int __exit sunxi_ss_remove(struct platform_device *pdev)
> +{
> +	if (!pdev->dev.of_node)
> +		return 0;

Redundant check.

> +
> +	crypto_unregister_ahash(&sunxi_md5_alg);
> +	crypto_unregister_ahash(&sunxi_sha1_alg);
> +	crypto_unregister_algs(sunxi_cipher_algs,
> +			ARRAY_SIZE(sunxi_cipher_algs));
> +
> +	if (ss->buf_in != NULL)
> +		kfree(ss->buf_in);
> +	if (ss->buf_out != NULL)
> +		kfree(ss->buf_out);
> +
> +	writel(0, ss->base + SS_CTL);
> +	clk_disable_unprepare(ss->busclk);
> +	clk_disable_unprepare(ss->ssclk);
> +	return 0;
> +}
> +
> +static const struct of_device_id a20ss_crypto_of_match_table[] = {
> +	{ .compatible = "allwinner,sun7i-a20-crypto" },
> +	{}
> +};
> +MODULE_DEVICE_TABLE(of, a20ss_crypto_of_match_table);
> +
> +static struct platform_driver sunxi_ss_driver = {
> +	.probe          = sunxi_ss_probe,
> +	.remove         = __exit_p(sunxi_ss_remove),
> +	.driver         = {
> +		.owner          = THIS_MODULE,
> +		.name           = "sunxi-ss",
> +		.of_match_table	= a20ss_crypto_of_match_table,
> +	},
> +};
> +
> +module_platform_driver(sunxi_ss_driver);
> +
> +MODULE_DESCRIPTION("Allwinner Security System cryptographic accelerator");
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Corentin LABBE <clabbe.montjoie@...il.com>");
> diff --git a/drivers/crypto/sunxi-ss/sunxi-ss-hash.c b/drivers/crypto/sunxi-ss/sunxi-ss-hash.c
> new file mode 100644
> index 0000000..ec8758f
> --- /dev/null
> +++ b/drivers/crypto/sunxi-ss/sunxi-ss-hash.c
> @@ -0,0 +1,445 @@
> +/*
> + * sunxi-ss-hash.c - hardware cryptographic accelerator for Allwinner A20 SoC
> + *
> + * Copyright (C) 2013-2014 Corentin LABBE <clabbe.montjoie@...il.com>
> + *
> + * This file add support for MD5 and SHA1.
> + *
> + * You could find the datasheet in Documentation/arm/sunxi/README
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + */
> +#include "sunxi-ss.h"
> +
> +/* This is a totaly arbitrary value */
> +#define SS_TIMEOUT 100
> +
> +extern struct sunxi_ss_ctx *ss;
> +
> +int sunxi_hash_crainit(struct crypto_tfm *tfm)
> +{
> +	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
> +			sizeof(struct sunxi_req_ctx));
> +	return 0;
> +}
> +
> +/* sunxi_hash_init: initialize request context */
> +int sunxi_hash_init(struct ahash_request *areq)
> +{
> +	const char *hash_type;
> +	struct sunxi_req_ctx *op = ahash_request_ctx(areq);
> +
> +	memset(op, 0, sizeof(struct sunxi_req_ctx));
> +
> +	hash_type = crypto_tfm_alg_name(areq->base.tfm);
> +
> +	if (strcmp(hash_type, "sha1") == 0)
> +		op->mode = SS_OP_SHA1;
> +	if (strcmp(hash_type, "md5") == 0)
> +		op->mode = SS_OP_MD5;
> +	if (op->mode == 0)
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +
> +static u32 rx_cnt;
> +
> +inline void ss_writer(const u32 v)
> +{
> +	u32 spaces;
> +
> +	writel(v, ss->base + SS_RXFIFO);
> +	rx_cnt--;
> +	while (rx_cnt == 0) {
> +		spaces = readl_relaxed(ss->base + SS_FCSR);
> +		rx_cnt = SS_RXFIFO_SPACES(spaces);
> +	}
> +}
> +
> +inline void ss_writer_relaxed(const u32 v)
> +{
> +	u32 spaces;
> +
> +	writel_relaxed(v, ss->base + SS_RXFIFO);
> +	rx_cnt--;
> +	while (rx_cnt == 0) {
> +		spaces = readl_relaxed(ss->base + SS_FCSR);
> +		rx_cnt = SS_RXFIFO_SPACES(spaces);
> +	}
> +}
> +
> +/*
> + * sunxi_hash_update: update hash engine
> + *
> + * Could be used for both SHA1 and MD5
> + * Write data by step of 32bits and put then in the SS.
> + *
> + * Since we cannot leave partial data and hash state in the engine,
> + * we need to get the hash state at the end of this function.
> + * After some work, I have found that we can get the hash state every 64o
> + *
> + * So the first work is to get the number of bytes to write to SS modulo 64
> + * The extra bytes will go to two different destination:
> + * op->wait for full 32bits word
> + * op->wb (waiting bytes) for partial 32 bits word
> + * So we can have up to (64/4)-1 op->wait words and 0/1/2/3 bytes in wb
> + *
> + * So at the begin of update()
> + * if op->nwait * 4 + areq->nbytes < 64
> + * => all data writed to wait buffers and end=0
> + * if not write all nwait to the device and position end to complete to 64o
> + *
> + * example 1:
> + * update1 60o => nwait=15
> + * update2 60o => need one more word to have 64o
> + * end=4
> + * so write all data in op->wait and one word of SGs
> + * write remaining data in op->wait
> + * final state op->nwait=14
> + */
> +int sunxi_hash_update(struct ahash_request *areq)
> +{
> +	u32 v, ivmode = 0;
> +	unsigned int i = 0;
> +	/*
> +	 * i is the total bytes read from SGs, to be compared to areq->nbytes
> +	 * i is important because we cannot rely on SG length since the sum of
> +	 * SG->length could be greater than areq->nbytes
> +	 */
> +
> +	struct sunxi_req_ctx *op = ahash_request_ctx(areq);
> +	struct scatterlist *in_sg;
> +	unsigned int in_i = 0; /* advancement in the current SG */
> +	u64 end;
> +	/*
> +	 * end is the position when we need to stop writing to the device,
> +	 * to be compared to i
> +	 */
> +	int in_r;
> +	void *src_addr;
> +
> +	dev_dbg(ss->dev, "%s %s bc=%llu len=%u mode=%x bw=%u ww=%u",
> +			__func__, crypto_tfm_alg_name(areq->base.tfm),
> +			op->byte_count, areq->nbytes, op->mode,
> +			op->nbw, op->nwait);
> +
> +	if (areq->nbytes == 0)
> +		return 0;
> +
> +	end = ((areq->nbytes + op->nwait * 4 + op->nbw) / 64) * 64
> +		- op->nbw - op->nwait * 4;
> +
> +	if (end > areq->nbytes || areq->nbytes - end > 63) {
> +		dev_err(ss->dev, "ERROR: Bound error %llu %u\n",
> +				end, areq->nbytes);
> +		return -EINVAL;
> +	}
> +
> +	if (op->nwait > 0 && end > 0) {
> +		/* a precedent update was done */
> +		for (i = 0; i < op->nwait; i++) {
> +			ss_writer(op->wait[i]);
> +			op->byte_count += 4;
> +		}
> +		op->nwait = 0;
> +	}
> +
> +	mutex_lock(&ss->lock);
> +	/*
> +	 * if some data have been processed before,
> +	 * we need to restore the partial hash state
> +	 */
> +	if (op->byte_count > 0) {
> +		ivmode = SS_IV_ARBITRARY;
> +		for (i = 0; i < 5; i++)
> +			writel(op->hash[i], ss->base + SS_IV0 + i * 4);
> +	}
> +	/* Enable the device */
> +	writel(op->mode | SS_ENABLED | ivmode, ss->base + SS_CTL);
> +
> +	rx_cnt = 0;
> +	i = 0;
> +
> +	in_sg = areq->src;
> +	src_addr = kmap(sg_page(in_sg)) + in_sg->offset;
> +	if (src_addr == NULL) {
> +		mutex_unlock(&ss->lock);
> +		dev_err(ss->dev, "ERROR: Cannot kmap source buffer\n");
> +		return -EFAULT;
> +	}
> +	do {
> +		/*
> +		 * step 1, if some bytes remains from last SG,
> +		 * try to complete them to 4 and send that word
> +		 */
> +		if (op->nbw > 0) {
> +			while (op->nbw < 4 && i < areq->nbytes &&
> +					in_i < in_sg->length) {
> +				op->wb |= (*(u8 *)(src_addr + in_i))
> +					<< (8 * op->nbw);
> +				dev_dbg(ss->dev, "%s Complete w=%d wb=%x\n",
> +						__func__, op->nbw, op->wb);
> +				i++;
> +				in_i++;
> +				op->nbw++;
> +			}
> +			if (op->nbw == 4) {
> +				if (i <= end) {
> +					ss_writer(op->wb);
> +					op->byte_count += 4;
> +				} else {
> +					op->wait[op->nwait] = op->wb;
> +					op->nwait++;
> +					dev_dbg(ss->dev, "%s Keep %u bytes after %llu\n",
> +						__func__, op->nwait, end);
> +				}
> +				op->nbw = 0;
> +				op->wb = 0;
> +			}
> +		}
> +		/* step 2, main loop, read data 4bytes at a time */
> +		while (i < areq->nbytes && in_i < in_sg->length) {
> +			/* how many bytes we can read, (we need 4) */
> +			in_r = min(in_sg->length - in_i, areq->nbytes - i);
> +			if (in_r < 4) {
> +				/* Not enough data to write to the device */
> +				op->wb = 0;
> +				while (in_r > 0) {
> +					op->wb |= (*(u8 *)(src_addr + in_i))
> +						<< (8 * op->nbw);
> +					dev_dbg(ss->dev, "%s ending bw=%d wb=%x\n",
> +						__func__, op->nbw, op->wb);
> +					in_r--;
> +					i++;
> +					in_i++;
> +					op->nbw++;
> +				}
> +				goto nextsg;
> +			}
> +			v = *(u32 *)(src_addr + in_i);
> +			if (i < end) {
> +				/* last write must be done without relaxed */
> +				if (i + 4 >= end)
> +					ss_writer(v);
> +				else
> +					ss_writer_relaxed(v);
> +				i += 4;
> +				op->byte_count += 4;
> +				in_i += 4;
> +			} else {
> +				op->wait[op->nwait] = v;
> +				i += 4;
> +				in_i += 4;
> +				op->nwait++;
> +				dev_dbg(ss->dev, "%s Keep word ww=%u after %llu\n",
> +						__func__, op->nwait, end);
> +				if (op->nwait > 15) {
> +					dev_err(ss->dev, "FATAL: Cannot enqueue more, bug?\n");
> +					writel(0, ss->base + SS_CTL);
> +					mutex_unlock(&ss->lock);
> +					return -EIO;
> +				}
> +			}
> +		}
> +nextsg:
> +		/* Nothing more to read in this SG */
> +		if (in_i == in_sg->length) {
> +			kunmap(sg_page(in_sg));
> +			do {
> +				in_sg = sg_next(in_sg);
> +			} while (in_sg != NULL && in_sg->length == 0);
> +			in_i = 0;
> +			if (in_sg != NULL) {
> +				src_addr = kmap(sg_page(in_sg)) + in_sg->offset;
> +				if (src_addr == NULL) {
> +					mutex_unlock(&ss->lock);
> +					dev_err(ss->dev, "ERROR: Cannot kmap source buffer\n");
> +					return -EFAULT;
> +				}
> +			}
> +		}
> +	} while (in_sg != NULL && i < areq->nbytes);
> +
> +	/* ask the device to finish the hashing */
> +	writel(op->mode | SS_ENABLED | SS_DATA_END, ss->base + SS_CTL);
> +	i = 0;
> +	do {
> +		v = readl(ss->base + SS_CTL);
> +		i++;
> +	} while (i < SS_TIMEOUT && (v & SS_DATA_END) > 0);
> +	if (i >= SS_TIMEOUT) {
> +		dev_err(ss->dev, "ERROR: %s hash end timeout after %d loop, CTL=%x\n",
> +				__func__, i, v);
> +		writel(0, ss->base + SS_CTL);
> +		mutex_unlock(&ss->lock);
> +		return -EIO;
> +	}
> +
> +	/* get the partial hash */
> +	if (op->mode == SS_OP_SHA1) {
> +		for (i = 0; i < 5; i++)
> +			op->hash[i] = readl(ss->base + SS_MD0 + i * 4);
> +	} else {
> +		for (i = 0; i < 4; i++)
> +			op->hash[i] = readl(ss->base + SS_MD0 + i * 4);
> +	}
> +
> +	writel(0, ss->base + SS_CTL);
> +	mutex_unlock(&ss->lock);
> +	return 0;
> +}
> +
> +/*
> + * sunxi_hash_final: finalize hashing operation
> + *
> + * If we have some remaining bytes, we write them.
> + * Then ask the SS for finalizing the hashing operation
> + */
> +int sunxi_hash_final(struct ahash_request *areq)
> +{
> +	u32 v, ivmode = 0;
> +	unsigned int i;
> +	int zeros;
> +	unsigned int index, padlen;
> +	__be64 bits;
> +	struct sunxi_req_ctx *op = ahash_request_ctx(areq);
> +
> +	dev_dbg(ss->dev, "%s byte=%llu len=%u mode=%x bw=%u %x h=%x ww=%u",
> +			__func__, op->byte_count, areq->nbytes, op->mode,
> +			op->nbw, op->wb, op->hash[0], op->nwait);
> +
> +	mutex_lock(&ss->lock);
> +	rx_cnt = 0;
> +
> +	/*
> +	 * if we have already writed something,
> +	 * restore the partial hash state
> +	 */
> +	if (op->byte_count > 0) {
> +		ivmode = SS_IV_ARBITRARY;
> +		for (i = 0; i < 5; i++)
> +			writel(op->hash[i], ss->base + SS_IV0 + i * 4);
> +	}
> +	writel(op->mode | SS_ENABLED | ivmode, ss->base + SS_CTL);
> +
> +	/* write the remaining words of the wait buffer */
> +	if (op->nwait > 0) {
> +		for (i = 0; i < op->nwait; i++) {
> +			v = op->wait[i];
> +			ss_writer(v);
> +			op->byte_count += 4;
> +			dev_dbg(ss->dev, "%s write %llu i=%u %x\n",
> +					__func__, op->byte_count, i, v);
> +		}
> +		op->nwait = 0;
> +	}
> +
> +	/* write the remaining bytes of the nbw buffer */
> +	if (op->nbw > 0) {
> +		op->wb |= ((1 << 7) << (op->nbw * 8));
> +		ss_writer(op->wb);
> +	} else {
> +		ss_writer((1 << 7));
> +	}
> +
> +	/*
> +	 * number of space to pad to obtain 64o minus 8(size) minus 4 (final 1)
> +	 * I take the operations from other md5/sha1 implementations
> +	 */
> +
> +	/* we have already send 4 more byte of which nbw data */
> +	if (op->mode == SS_OP_MD5) {
> +		index = (op->byte_count + 4) & 0x3f;
> +		op->byte_count += op->nbw;
> +		if (index > 56)
> +			zeros = (120 - index) / 4;
> +		else
> +			zeros = (56 - index) / 4;
> +	} else {
> +		op->byte_count += op->nbw;
> +		index = op->byte_count & 0x3f;
> +		padlen = (index < 56) ? (56 - index) : ((64+56) - index);
> +		zeros = (padlen - 1) / 4;
> +	}
> +	for (i = 0; i < zeros; i++)
> +		ss_writer(0);
> +
> +	/* write the length of data */
> +	if (op->mode == SS_OP_SHA1) {
> +		bits = cpu_to_be64(op->byte_count << 3);
> +		ss_writer(bits & 0xffffffff);
> +		ss_writer((bits >> 32) & 0xffffffff);
> +	} else {
> +		ss_writer((op->byte_count << 3) & 0xffffffff);
> +		ss_writer((op->byte_count >> 29) & 0xffffffff);
> +	}
> +
> +	/* Tell the SS to stop the hashing */
> +	writel(op->mode | SS_ENABLED | SS_DATA_END, ss->base + SS_CTL);
> +
> +	/*
> +	 * Wait for SS to finish the hash.
> +	 * The timeout could happend only in case of bad overcloking
> +	 * or driver bug.
> +	 */
> +	i = 0;
> +	do {
> +		v = readl(ss->base + SS_CTL);
> +		i++;
> +	} while (i < SS_TIMEOUT && (v & SS_DATA_END) > 0);
> +	if (i >= SS_TIMEOUT) {
> +		dev_err(ss->dev, "ERROR: hash end timeout %d>%d ctl=%x len=%u\n",
> +				i, SS_TIMEOUT, v, areq->nbytes);
> +		writel(0, ss->base + SS_CTL);
> +		mutex_unlock(&ss->lock);
> +		return -EIO;
> +	}
> +
> +	/* Get the hash from the device */
> +	if (op->mode == SS_OP_SHA1) {
> +		for (i = 0; i < 5; i++) {
> +			v = cpu_to_be32(readl(ss->base + SS_MD0 + i * 4));
> +			memcpy(areq->result + i * 4, &v, 4);
> +		}
> +	} else {
> +		for (i = 0; i < 4; i++) {
> +			v = readl(ss->base + SS_MD0 + i * 4);
> +			memcpy(areq->result + i * 4, &v, 4);
> +		}
> +	}
> +	writel(0, ss->base + SS_CTL);
> +	mutex_unlock(&ss->lock);
> +	return 0;
> +}
> +
> +/* sunxi_hash_finup: finalize hashing operation after an update */
> +int sunxi_hash_finup(struct ahash_request *areq)
> +{
> +	int err;
> +
> +	err = sunxi_hash_update(areq);
> +	if (err != 0)
> +		return err;
> +
> +	return sunxi_hash_final(areq);
> +}
> +
> +/* combo of init/update/final functions */
> +int sunxi_hash_digest(struct ahash_request *areq)
> +{
> +	int err;
> +
> +	err = sunxi_hash_init(areq);
> +	if (err != 0)
> +		return err;
> +
> +	err = sunxi_hash_update(areq);
> +	if (err != 0)
> +		return err;
> +
> +	return sunxi_hash_final(areq);
> +}
> diff --git a/drivers/crypto/sunxi-ss/sunxi-ss.h b/drivers/crypto/sunxi-ss/sunxi-ss.h
> new file mode 100644
> index 0000000..331e75b
> --- /dev/null
> +++ b/drivers/crypto/sunxi-ss/sunxi-ss.h
> @@ -0,0 +1,193 @@
> +/*
> + * sunxi-ss.c - hardware cryptographic accelerator for Allwinner A20 SoC
> + *
> + * Copyright (C) 2013-2014 Corentin LABBE <clabbe.montjoie@...il.com>
> + *
> + * Support AES cipher with 128,192,256 bits keysize.
> + * Support MD5 and SHA1 hash algorithms.
> + * Support DES and 3DES
> + *
> + * You could find the datasheet in Documentation/arm/sunxi/README
> + *
> + * Licensed under the GPL-2.
> + */
> +
> +#include <linux/clk.h>
> +#include <linux/crypto.h>
> +#include <linux/io.h>
> +#include <linux/module.h>
> +#include <linux/of.h>
> +#include <linux/platform_device.h>
> +#include <crypto/scatterwalk.h>
> +#include <linux/scatterlist.h>
> +#include <linux/interrupt.h>
> +#include <linux/delay.h>
> +#include <crypto/md5.h>
> +#include <crypto/sha.h>
> +#include <crypto/hash.h>
> +#include <crypto/internal/hash.h>
> +#include <crypto/aes.h>
> +#include <crypto/des.h>
> +#include <crypto/internal/rng.h>
> +
> +#define SS_CTL            0x00
> +#define SS_KEY0           0x04
> +#define SS_KEY1           0x08
> +#define SS_KEY2           0x0C
> +#define SS_KEY3           0x10
> +#define SS_KEY4           0x14
> +#define SS_KEY5           0x18
> +#define SS_KEY6           0x1C
> +#define SS_KEY7           0x20
> +
> +#define SS_IV0            0x24
> +#define SS_IV1            0x28
> +#define SS_IV2            0x2C
> +#define SS_IV3            0x30
> +
> +#define SS_CNT0           0x34
> +#define SS_CNT1           0x38
> +#define SS_CNT2           0x3C
> +#define SS_CNT3           0x40
> +
> +#define SS_FCSR           0x44
> +#define SS_ICSR           0x48
> +
> +#define SS_MD0            0x4C
> +#define SS_MD1            0x50
> +#define SS_MD2            0x54
> +#define SS_MD3            0x58
> +#define SS_MD4            0x5C
> +
> +#define SS_RXFIFO         0x200
> +#define SS_TXFIFO         0x204
> +
> +/* SS_CTL configuration values */
> +
> +/* PRNG generator mode - bit 15 */
> +#define SS_PRNG_ONESHOT		(0 << 15)
> +#define SS_PRNG_CONTINUE	(1 << 15)
> +
> +/* IV mode for hash */
> +#define SS_IV_ARBITRARY		(1 << 14)
> +
> +/* SS operation mode - bits 12-13 */
> +#define SS_ECB			(0 << 12)
> +#define SS_CBC			(1 << 12)
> +#define SS_CNT			(2 << 12)
> +
> +/* Counter width for CNT mode - bits 10-11 */
> +#define SS_CNT_16BITS		(0 << 10)
> +#define SS_CNT_32BITS		(1 << 10)
> +#define SS_CNT_64BITS		(2 << 10)
> +
> +/* Key size for AES - bits 8-9 */
> +#define SS_AES_128BITS		(0 << 8)
> +#define SS_AES_192BITS		(1 << 8)
> +#define SS_AES_256BITS		(2 << 8)
> +
> +/* Operation direction - bit 7 */
> +#define SS_ENCRYPTION		(0 << 7)
> +#define SS_DECRYPTION		(1 << 7)
> +
> +/* SS Method - bits 4-6 */
> +#define SS_OP_AES		(0 << 4)
> +#define SS_OP_DES		(1 << 4)
> +#define SS_OP_3DES		(2 << 4)
> +#define SS_OP_SHA1		(3 << 4)
> +#define SS_OP_MD5		(4 << 4)
> +#define SS_OP_PRNG		(5 << 4)
> +
> +/* Data end bit - bit 2 */
> +#define SS_DATA_END		(1 << 2)
> +
> +/* PRNG start bit - bit 1 */
> +#define SS_PRNG_START		(1 << 1)
> +
> +/* SS Enable bit - bit 0 */
> +#define SS_DISABLED		(0 << 0)
> +#define SS_ENABLED		(1 << 0)
> +
> +/* SS_FCSR configuration values */
> +/* RX FIFO status - bit 30 */
> +#define SS_RXFIFO_FREE		(1 << 30)
> +
> +/* RX FIFO empty spaces - bits 24-29 */
> +#define SS_RXFIFO_SPACES(val)	(((val) >> 24) & 0x3f)
> +
> +/* TX FIFO status - bit 22 */
> +#define SS_TXFIFO_AVAILABLE	(1 << 22)
> +
> +/* TX FIFO available spaces - bits 16-21 */
> +#define SS_TXFIFO_SPACES(val)	(((val) >> 16) & 0x3f)
> +
> +#define SS_RXFIFO_EMP_INT_PENDING	(1 << 10)
> +#define SS_TXFIFO_AVA_INT_PENDING	(1 << 8)
> +#define SS_RXFIFO_EMP_INT_ENABLE	(1 << 2)
> +#define SS_TXFIFO_AVA_INT_ENABLE	(1 << 0)
> +
> +/* SS_ICSR configuration values */
> +#define SS_ICS_DRQ_ENABLE		(1 << 4)
> +
> +struct sunxi_ss_ctx {
> +	void __iomem *base;
> +	int irq;
> +	struct clk *busclk;
> +	struct clk *ssclk;
> +	struct device *dev;
> +	struct resource *res;
> +	void *buf_in; /* pointer to data to be uploaded to the device */
> +	size_t buf_in_size; /* size of buf_in */
> +	void *buf_out;
> +	size_t buf_out_size;
> +	struct mutex lock; /* control the use of the device */
> +	struct mutex bufout_lock; /* control the use of buf_out*/
> +	struct mutex bufin_lock; /* control the sue of buf_in*/
> +};
> +
> +struct sunxi_tfm_ctx {
> +	u32 key[AES_MAX_KEY_SIZE / 4];/* divided by sizeof(u32) */
> +	u32 keylen;
> +	u32 keymode;
> +};
> +
> +struct sunxi_req_ctx {
> +	u32 mode;
> +	u64 byte_count; /* number of bytes "uploaded" to the device */
> +	u32 wb; /* a partial word waiting to be completed and
> +			uploaded to the device */
> +	/* number of bytes to be uploaded in the wb word */
> +	unsigned int nbw;
> +	u32 hash[5];
> +	u32 wait[64];
> +	unsigned int nwait;
> +};
> +
> +#define SS_SEED_LEN (192/8)
> +#define SS_DATA_LEN (160/8)
> +
> +struct prng_context {
> +	u32 seed[SS_SEED_LEN/4];
> +	unsigned int slen;
> +};
> +
> +int sunxi_hash_crainit(struct crypto_tfm *tfm);
> +int sunxi_hash_init(struct ahash_request *areq);
> +int sunxi_hash_update(struct ahash_request *areq);
> +int sunxi_hash_final(struct ahash_request *areq);
> +int sunxi_hash_finup(struct ahash_request *areq);
> +int sunxi_hash_digest(struct ahash_request *areq);
> +int sunxi_hash_export(struct ahash_request *areq, void *out);
> +int sunxi_hash_import(struct ahash_request *areq, const void *in);
> +
> +int sunxi_ss_aes_poll(struct ablkcipher_request *areq, u32 mode);
> +int sunxi_ss_des_poll(struct ablkcipher_request *areq, u32 mode);
> +int sunxi_ss_cipher_init(struct crypto_tfm *tfm);
> +int sunxi_ss_cipher_encrypt(struct ablkcipher_request *areq);
> +int sunxi_ss_cipher_decrypt(struct ablkcipher_request *areq);
> +int sunxi_ss_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen);
> +int sunxi_ss_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen);
> +int sunxi_ss_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
> +		unsigned int keylen);
> 


--
With best wishes,
Vladimir
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists