diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 03ccdb0..a2acda4 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -418,4 +418,21 @@ config CRYPTO_DEV_MXS_DCP To compile this driver as a module, choose M here: the module will be called mxs-dcp. +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 482f090..855292a 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/ +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..c2422f7 --- /dev/null +++ b/drivers/crypto/sunxi-ss/sunxi-ss-cipher.c @@ -0,0 +1,461 @@ +/* + * sunxi-ss-cipher.c - hardware cryptographic accelerator for Allwinner A20 SoC + * + * Copyright (C) 2013-2014 Corentin LABBE + * + * This file add support for AES cipher with 128,192,256 bits + * keysize in CBC mode. + * + * You could find the datasheet at + * http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf + * + * 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_req_ctx *op = crypto_ablkcipher_ctx(tfm); + const char *cipher_type; + + cipher_type = crypto_tfm_alg_name(crypto_ablkcipher_tfm(tfm)); + + if (areq->nbytes == 0) { + mutex_unlock(&ss->lock); + return 0; + } + + if (areq->info == NULL) { + dev_err(ss->dev, "ERROR: Empty IV\n"); + mutex_unlock(&ss->lock); + return -EINVAL; + } + + if (areq->src == NULL || areq->dst == NULL) { + dev_err(ss->dev, "ERROR: Some SGs are NULL\n"); + mutex_unlock(&ss->lock); + return -EINVAL; + } + + if (strcmp("cbc(aes)", cipher_type) == 0) { + op->mode |= SS_OP_AES | SS_CBC | SS_ENABLED | mode; + return sunxi_ss_aes_poll(areq); + } + if (strcmp("cbc(des)", cipher_type) == 0) { + op->mode = SS_OP_DES | SS_CBC | SS_ENABLED | mode; + return sunxi_ss_des_poll(areq); + } + if (strcmp("cbc(des3_ede)", cipher_type) == 0) { + op->mode = SS_OP_3DES | SS_CBC | SS_ENABLED | mode; + return sunxi_ss_des_poll(areq); + } + dev_err(ss->dev, "ERROR: Cipher %s not handled\n", cipher_type); + mutex_unlock(&ss->lock); + 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_req_ctx *op = crypto_tfm_ctx(tfm); + + mutex_lock(&ss->lock); + + memset(op, 0, sizeof(struct sunxi_req_ctx)); + return 0; +} + +int sunxi_ss_aes_poll(struct ablkcipher_request *areq) +{ + u32 spaces; + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(areq); + struct sunxi_req_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; + struct scatterlist *out_sg; + 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; + + in_sg = areq->src; + out_sg = areq->dst; + 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(op->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) { + 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; + } + + /* 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(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 + * SGsrc -> buf_in -> SS -> buf_out -> SGdst */ +int sunxi_ss_des_poll(struct ablkcipher_request *areq) +{ + 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_req_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; + + /* if we have only SGs with size multiple of 4, + * we can use the SS AES function */ + struct scatterlist *in_sg; + struct scatterlist *out_sg; + + in_sg = areq->src; + out_sg = areq->dst; + + 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); + in_sg = areq->src; + out_sg = areq->dst; + + nb_in_sg_rx = sg_nents(in_sg); + nb_in_sg_tx = sg_nents(out_sg); + + 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; + } + if (ss->buf_out == NULL) { + mutex_lock(&ss->bufout_lock); + ss->buf_out = kmalloc(areq->nbytes, GFP_KERNEL); + if (ss->buf_out == NULL) { + ss->buf_out_size = 0; + mutex_unlock(&ss->bufout_lock); + dev_err(ss->dev, "Unable to allocate pages.\n"); + return -ENOMEM; + } + ss->buf_out_size = areq->nbytes; + mutex_unlock(&ss->bufout_lock); + } else { + if (areq->nbytes > ss->buf_out_size) { + mutex_lock(&ss->bufout_lock); + 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->bufout_lock); + dev_err(ss->dev, "Unable to allocate pages.\n"); + return -ENOMEM; + } + ss->buf_out_size = areq->nbytes; + mutex_unlock(&ss->bufout_lock); + } + } + + sg_copy_to_buffer(areq->src, nb_in_sg_rx, ss->buf_in, areq->nbytes); + + ir = 0; + it = 0; + + 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(op->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 */ + mutex_lock(&ss->bufout_lock); + 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_req_ctx *op = crypto_ablkcipher_ctx(tfm); + + switch (keylen) { + case 128 / 8: + op->mode = SS_AES_128BITS; + break; + case 192 / 8: + op->mode = SS_AES_192BITS; + break; + case 256 / 8: + op->mode = 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); + mutex_unlock(&ss->lock); + 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_req_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); + mutex_unlock(&ss->lock); + 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_req_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); + mutex_unlock(&ss->lock); + 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..c76016e --- /dev/null +++ b/drivers/crypto/sunxi-ss/sunxi-ss-core.c @@ -0,0 +1,308 @@ +/* + * sunxi-ss.c - hardware cryptographic accelerator for Allwinner A20 SoC + * + * Copyright (C) 2013-2014 Corentin LABBE + * + * Core file which registers crypto algorithms supported by the SS. + * + * You could find the datasheet at + * http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf + * + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sunxi-ss.h" + +struct sunxi_ss_ctx *ss; + +/* General notes: + * I cannot use a key/IV cache because each time one of these change ALL stuff + * need to be re-writed (rewrite SS_KEYX ans SS_IVX). + * And for example, with dm-crypt IV changes on each request. + * + * 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. + * 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 + } + } +}; +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 + } + } +}; + +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_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 = 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; + + 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 the 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); + 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); + 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); + cr = clk_get_rate(ss->ssclk); + if (cr == cr_mod) + 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); + } + + /* TODO Does this information could be usefull ? */ + 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; + + 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 "); 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..6412bfb --- /dev/null +++ b/drivers/crypto/sunxi-ss/sunxi-ss-hash.c @@ -0,0 +1,241 @@ +/* + * sunxi-ss-hash.c - hardware cryptographic accelerator for Allwinner A20 SoC + * + * Copyright (C) 2013-2014 Corentin LABBE + * + * This file add support for MD5 and SHA1. + * + * You could find the datasheet at + * http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf + * + * 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; + +/* sunxi_hash_init: initialize request context + * Activate the SS, and configure it for MD5 or SHA1 + */ +int sunxi_hash_init(struct ahash_request *areq) +{ + const char *hash_type; + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct sunxi_req_ctx *op = crypto_ahash_ctx(tfm); + + mutex_lock(&ss->lock); + + hash_type = crypto_tfm_alg_name(areq->base.tfm); + + op->byte_count = 0; + op->nbwait = 0; + op->waitbuf = 0; + + /* Enable and configure SS for MD5 or SHA1 */ + if (strcmp(hash_type, "sha1") == 0) + op->mode = SS_OP_SHA1; + else + op->mode = SS_OP_MD5; + + writel(op->mode | SS_ENABLED, ss->base + SS_CTL); + return 0; +} + +/* + * 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. + * The remaining data is stored (nbwait bytes) in op->waitbuf + * As an optimisation, we do not check RXFIFO_SPACES, since SS handle + * the FIFO faster than our writes + */ +int sunxi_hash_update(struct ahash_request *areq) +{ + u32 v; + unsigned int i = 0;/* bytes read, to be compared to areq->nbytes */ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct sunxi_req_ctx *op = crypto_ahash_ctx(tfm); + struct scatterlist *in_sg; + unsigned int in_i = 0;/* advancement in the current SG */ + void *src_addr; + + u8 *waitbuf = (u8 *)(&op->waitbuf); + + if (areq->nbytes == 0) + return 0; + + in_sg = areq->src; + do { + src_addr = kmap(sg_page(in_sg)) + in_sg->offset; + /* step 1, if some bytes remains from last SG, + * try to complete them to 4 and sent its */ + if (op->nbwait > 0) { + while (op->nbwait < 4 && i < areq->nbytes && + in_i < in_sg->length) { + waitbuf[op->nbwait] = *(u8 *)(src_addr + in_i); + i++; + in_i++; + op->nbwait++; + } + if (op->nbwait == 4) { + writel(op->waitbuf, ss->base + SS_RXFIFO); + op->byte_count += 4; + op->nbwait = 0; + op->waitbuf = 0; + } + } + /* step 2, main loop, read data 4bytes at a time */ + while (i < areq->nbytes && areq->nbytes - i >= 4 && + in_i < in_sg->length && + in_sg->length - in_i >= 4) { + v = *(u32 *)(src_addr + in_i); + writel_relaxed(v, ss->base + SS_RXFIFO); + i += 4; + op->byte_count += 4; + in_i += 4; + } + /* step 3, if we have less than 4 bytes, copy them in waitbuf + * no need to check for op->nbwait < 4 since we cannot have + * more than 4 bytes remaining */ + if (in_i < in_sg->length && in_sg->length - in_i < 4 && + i < areq->nbytes) { + do { + waitbuf[op->nbwait] = *(u8 *)(src_addr + in_i); + op->nbwait++; + in_i++; + i++; + } while (in_i < in_sg->length && i < areq->nbytes); + } + /* we have finished the current SG, try next one */ + kunmap(sg_page(in_sg)); + in_sg = sg_next(in_sg); + in_i = 0; + } while (in_sg != NULL && i < areq->nbytes); + return 0; +} + +/* + * sunxi_hash_final: finalize hashing operation + * + * If we have some remaining bytes, send it. + * Then ask the SS for finalizing the hash + */ +int sunxi_hash_final(struct ahash_request *areq) +{ + u32 v; + unsigned int i; + int zeros; + unsigned int index, padlen; + __be64 bits; + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct sunxi_req_ctx *op = crypto_ahash_ctx(tfm); + + if (op->nbwait > 0) { + op->waitbuf |= ((1 << 7) << (op->nbwait * 8)); + writel(op->waitbuf, ss->base + SS_RXFIFO); + } else { + writel((1 << 7), ss->base + SS_RXFIFO); + } + + /* number of space to pad to obtain 64o minus 8(size) minus 4 (final 1) + * example len=0 + * example len=56 + * */ + + /* we have already send 4 more byte of which nbwait data */ + if (op->mode == SS_OP_MD5) { + index = (op->byte_count + 4) & 0x3f; + op->byte_count += op->nbwait; + if (index > 56) + zeros = (120 - index) / 4; + else + zeros = (56 - index) / 4; + } else { + op->byte_count += op->nbwait; + index = op->byte_count & 0x3f; + padlen = (index < 56) ? (56 - index) : ((64+56) - index); + zeros = (padlen - 1) / 4; + } + for (i = 0; i < zeros; i++) + writel(0, ss->base + SS_RXFIFO); + + /* write the lenght */ + if (op->mode == SS_OP_SHA1) { + bits = cpu_to_be64(op->byte_count << 3); + writel(bits & 0xffffffff, ss->base + SS_RXFIFO); + writel((bits >> 32) & 0xffffffff, ss->base + SS_RXFIFO); + } else { + writel((op->byte_count << 3) & 0xffffffff, + ss->base + SS_RXFIFO); + writel((op->byte_count >> 29) & 0xffffffff, + ss->base + SS_RXFIFO); + } + + /* stop the hashing */ + v = readl(ss->base + SS_CTL); + v |= SS_DATA_END; + writel(v, ss->base + SS_CTL); + + /* check the end */ + /* The timeout could happend only in case of bad overcloking */ +#define SS_TIMEOUT 100 + 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\n", + i, SS_TIMEOUT); + writel(0, ss->base + SS_CTL); + mutex_unlock(&ss->lock); + return -1; + } + + 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..94aca20 --- /dev/null +++ b/drivers/crypto/sunxi-ss/sunxi-ss.h @@ -0,0 +1,183 @@ +/* + * sunxi-ss.c - hardware cryptographic accelerator for Allwinner A20 SoC + * + * Copyright (C) 2013-2014 Corentin LABBE + * + * Support AES cipher with 128,192,256 bits keysize. + * Support MD5 and SHA1 hash algorithms. + * Support DES and 3DES + * Support PRNG + * + * You could find the datasheet at + * http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf + * + * + * Licensed under the GPL-2. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#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) + +/* 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_req_ctx { + u32 key[AES_MAX_KEY_SIZE / 4];/* divided by sizeof(u32) */ + u32 keylen; + u32 mode; + u64 byte_count; /* number of bytes "uploaded" to the device */ + u32 waitbuf; /* a partial word waiting to be completed and + uploaded to the device */ + /* number of bytes to be uploaded in the waitbuf word */ + unsigned int nbwait; +}; + +#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_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_ss_aes_poll(struct ablkcipher_request *areq); +int sunxi_ss_des_poll(struct ablkcipher_request *areq); +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); -- 1.8.5.5