diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-02 14:53:12 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-02 14:53:12 -0700 |
commit | 797994f81a8b2bdca2eecffa415c1e7a89a4f961 (patch) | |
tree | 1383dc469c26ad37fdf960f682d9a48c782935c5 /drivers | |
parent | c8d8566952fda026966784a62f324c8352f77430 (diff) | |
parent | 3862de1f6c442d53bd828d39f86d07d933a70605 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
Pull crypto update from Herbert Xu:
- XTS mode optimisation for twofish/cast6/camellia/aes on x86
- AVX2/x86_64 implementation for blowfish/twofish/serpent/camellia
- SSSE3/AVX/AVX2 optimisations for sha256/sha512
- Added driver for SAHARA2 crypto accelerator
- Fix for GMAC when used in non-IPsec secnarios
- Added generic CMAC implementation (including IPsec glue)
- IP update for crypto/atmel
- Support for more than one device in hwrng/timeriomem
- Added Broadcom BCM2835 RNG driver
- Misc fixes
* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (59 commits)
crypto: caam - fix job ring cleanup code
crypto: camellia - add AVX2/AES-NI/x86_64 assembler implementation of camellia cipher
crypto: serpent - add AVX2/x86_64 assembler implementation of serpent cipher
crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher
crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher
crypto: tcrypt - add async cipher speed tests for blowfish
crypto: testmgr - extend camellia test-vectors for camellia-aesni/avx2
crypto: aesni_intel - fix Kconfig problem with CRYPTO_GLUE_HELPER_X86
crypto: aesni_intel - add more optimized XTS mode for x86-64
crypto: x86/camellia-aesni-avx - add more optimized XTS code
crypto: cast6-avx: use new optimized XTS code
crypto: x86/twofish-avx - use optimized XTS code
crypto: x86 - add more optimized XTS-mode for serpent-avx
xfrm: add rfc4494 AES-CMAC-96 support
crypto: add CMAC support to CryptoAPI
crypto: testmgr - add empty test vectors for null ciphers
crypto: testmgr - add AES GMAC test vectors
crypto: gcm - fix rfc4543 to handle async crypto correctly
crypto: gcm - make GMAC work when dst and src are different
hwrng: timeriomem - added devicetree hooks
...
Diffstat (limited to 'drivers')
29 files changed, 2580 insertions, 393 deletions
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index c5a0262251b..2f9dbf7568f 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -86,6 +86,18 @@ config HW_RANDOM_BCM63XX If unusure, say Y. +config HW_RANDOM_BCM2835 + tristate "Broadcom BCM2835 Random Number Generator support" + depends on HW_RANDOM && ARCH_BCM2835 + default HW_RANDOM + ---help--- + This driver provides kernel-side support for the Random Number + Generator hardware found on the Broadcom BCM2835 SoCs. + + To compile this driver as a module, choose M here: the + module will be called bcm2835-rng + + If unsure, say Y. config HW_RANDOM_GEODE tristate "AMD Geode HW Random Number Generator support" diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile index 1fd7eec9fbf..bed467c9300 100644 --- a/drivers/char/hw_random/Makefile +++ b/drivers/char/hw_random/Makefile @@ -26,3 +26,4 @@ obj-$(CONFIG_HW_RANDOM_PPC4XX) += ppc4xx-rng.o obj-$(CONFIG_HW_RANDOM_PSERIES) += pseries-rng.o obj-$(CONFIG_HW_RANDOM_EXYNOS) += exynos-rng.o obj-$(CONFIG_HW_RANDOM_TPM) += tpm-rng.o +obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c new file mode 100644 index 00000000000..eb7f14725eb --- /dev/null +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -0,0 +1,113 @@ +/** + * Copyright (c) 2010-2012 Broadcom. All rights reserved. + * Copyright (c) 2013 Lubomir Rintel + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License ("GPL") + * version 2, as published by the Free Software Foundation. + */ + +#include <linux/hw_random.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/printk.h> + +#define RNG_CTRL 0x0 +#define RNG_STATUS 0x4 +#define RNG_DATA 0x8 + +/* enable rng */ +#define RNG_RBGEN 0x1 + +/* the initial numbers generated are "less random" so will be discarded */ +#define RNG_WARMUP_COUNT 0x40000 + +static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max, + bool wait) +{ + void __iomem *rng_base = (void __iomem *)rng->priv; + + while ((__raw_readl(rng_base + RNG_STATUS) >> 24) == 0) { + if (!wait) + return 0; + cpu_relax(); + } + + *(u32 *)buf = __raw_readl(rng_base + RNG_DATA); + return sizeof(u32); +} + +static struct hwrng bcm2835_rng_ops = { + .name = "bcm2835", + .read = bcm2835_rng_read, +}; + +static int bcm2835_rng_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + void __iomem *rng_base; + int err; + + /* map peripheral */ + rng_base = of_iomap(np, 0); + if (!rng_base) { + dev_err(dev, "failed to remap rng regs"); + return -ENODEV; + } + bcm2835_rng_ops.priv = (unsigned long)rng_base; + + /* register driver */ + err = hwrng_register(&bcm2835_rng_ops); + if (err) { + dev_err(dev, "hwrng registration failed\n"); + iounmap(rng_base); + } else { + dev_info(dev, "hwrng registered\n"); + + /* set warm-up count & enable */ + __raw_writel(RNG_WARMUP_COUNT, rng_base + RNG_STATUS); + __raw_writel(RNG_RBGEN, rng_base + RNG_CTRL); + } + return err; +} + +static int bcm2835_rng_remove(struct platform_device *pdev) +{ + void __iomem *rng_base = (void __iomem *)bcm2835_rng_ops.priv; + + /* disable rng hardware */ + __raw_writel(0, rng_base + RNG_CTRL); + + /* unregister driver */ + hwrng_unregister(&bcm2835_rng_ops); + iounmap(rng_base); + + return 0; +} + +static const struct of_device_id bcm2835_rng_of_match[] = { + { .compatible = "brcm,bcm2835-rng", }, + {}, +}; +MODULE_DEVICE_TABLE(of, bcm2835_rng_of_match); + +static struct platform_driver bcm2835_rng_driver = { + .driver = { + .name = "bcm2835-rng", + .owner = THIS_MODULE, + .of_match_table = bcm2835_rng_of_match, + }, + .probe = bcm2835_rng_probe, + .remove = bcm2835_rng_remove, +}; +module_platform_driver(bcm2835_rng_driver); + +MODULE_AUTHOR("Lubomir Rintel <lkundrak@v3.sk>"); +MODULE_DESCRIPTION("BCM2835 Random Number Generator (RNG) driver"); +MODULE_LICENSE("GPLv2"); diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c index ac47631ab34..402ccfb625c 100644 --- a/drivers/char/hw_random/exynos-rng.c +++ b/drivers/char/hw_random/exynos-rng.c @@ -144,6 +144,7 @@ static int exynos_rng_remove(struct platform_device *pdev) return 0; } +#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_RUNTIME) static int exynos_rng_runtime_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -161,7 +162,7 @@ static int exynos_rng_runtime_resume(struct device *dev) return clk_prepare_enable(exynos_rng->clk); } - +#endif static UNIVERSAL_DEV_PM_OPS(exynos_rng_pm_ops, exynos_rng_runtime_suspend, exynos_rng_runtime_resume, NULL); diff --git a/drivers/char/hw_random/mxc-rnga.c b/drivers/char/hw_random/mxc-rnga.c index 895d0b8fb9a..4ca35e8a5d8 100644 --- a/drivers/char/hw_random/mxc-rnga.c +++ b/drivers/char/hw_random/mxc-rnga.c @@ -142,7 +142,7 @@ static void mxc_rnga_cleanup(struct hwrng *rng) static int __init mxc_rnga_probe(struct platform_device *pdev) { int err = -ENODEV; - struct resource *res, *mem; + struct resource *res; struct mxc_rng *mxc_rng; mxc_rng = devm_kzalloc(&pdev->dev, sizeof(struct mxc_rng), @@ -172,15 +172,9 @@ static int __init mxc_rnga_probe(struct platform_device *pdev) goto err_region; } - mem = request_mem_region(res->start, resource_size(res), pdev->name); - if (mem == NULL) { - err = -EBUSY; - goto err_region; - } - - mxc_rng->mem = ioremap(res->start, resource_size(res)); - if (!mxc_rng->mem) { - err = -ENOMEM; + mxc_rng->mem = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(mxc_rng->mem)) { + err = PTR_ERR(mxc_rng->mem); goto err_ioremap; } @@ -195,8 +189,6 @@ static int __init mxc_rnga_probe(struct platform_device *pdev) return 0; err_ioremap: - release_mem_region(res->start, resource_size(res)); - err_region: clk_disable_unprepare(mxc_rng->clk); @@ -206,15 +198,10 @@ out: static int __exit mxc_rnga_remove(struct platform_device *pdev) { - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct mxc_rng *mxc_rng = platform_get_drvdata(pdev); hwrng_unregister(&mxc_rng->rng); - iounmap(mxc_rng->mem); - - release_mem_region(res->start, resource_size(res)); - clk_disable_unprepare(mxc_rng->clk); return 0; diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c index 849db199c02..3e75737f5fe 100644 --- a/drivers/char/hw_random/timeriomem-rng.c +++ b/drivers/char/hw_random/timeriomem-rng.c @@ -23,127 +23,209 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/platform_device.h> +#include <linux/of.h> #include <linux/hw_random.h> #include <linux/io.h> +#include <linux/slab.h> #include <linux/timeriomem-rng.h> #include <linux/jiffies.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/completion.h> -static struct timeriomem_rng_data *timeriomem_rng_data; +struct timeriomem_rng_private_data { + void __iomem *io_base; + unsigned int expires; + unsigned int period; + unsigned int present:1; -static void timeriomem_rng_trigger(unsigned long); -static DEFINE_TIMER(timeriomem_rng_timer, timeriomem_rng_trigger, 0, 0); + struct timer_list timer; + struct completion completion; + + struct hwrng timeriomem_rng_ops; +}; + +#define to_rng_priv(rng) \ + ((struct timeriomem_rng_private_data *)rng->priv) /* * have data return 1, however return 0 if we have nothing */ static int timeriomem_rng_data_present(struct hwrng *rng, int wait) { - if (rng->priv == 0) - return 1; + struct timeriomem_rng_private_data *priv = to_rng_priv(rng); - if (!wait || timeriomem_rng_data->present) - return timeriomem_rng_data->present; + if (!wait || priv->present) + return priv->present; - wait_for_completion(&timeriomem_rng_data->completion); + wait_for_completion(&priv->completion); return 1; } static int timeriomem_rng_data_read(struct hwrng *rng, u32 *data) { + struct timeriomem_rng_private_data *priv = to_rng_priv(rng); unsigned long cur; s32 delay; - *data = readl(timeriomem_rng_data->address); + *data = readl(priv->io_base); - if (rng->priv != 0) { - cur = jiffies; + cur = jiffies; - delay = cur - timeriomem_rng_timer.expires; - delay = rng->priv - (delay % rng->priv); + delay = cur - priv->expires; + delay = priv->period - (delay % priv->period); - timeriomem_rng_timer.expires = cur + delay; - timeriomem_rng_data->present = 0; + priv->expires = cur + delay; + priv->present = 0; - init_completion(&timeriomem_rng_data->completion); - add_timer(&timeriomem_rng_timer); - } + INIT_COMPLETION(priv->completion); + mod_timer(&priv->timer, priv->expires); return 4; } -static void timeriomem_rng_trigger(unsigned long dummy) +static void timeriomem_rng_trigger(unsigned long data) { - timeriomem_rng_data->present = 1; - complete(&timeriomem_rng_data->completion); -} + struct timeriomem_rng_private_data *priv + = (struct timeriomem_rng_private_data *)data; -static struct hwrng timeriomem_rng_ops = { - .name = "timeriomem", - .data_present = timeriomem_rng_data_present, - .data_read = timeriomem_rng_data_read, - .priv = 0, -}; + priv->present = 1; + complete(&priv->completion); +} static int timeriomem_rng_probe(struct platform_device *pdev) { + struct timeriomem_rng_data *pdata = pdev->dev.platform_data; + struct timeriomem_rng_private_data *priv; struct resource *res; - int ret; + int err = 0; + int period; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!pdev->dev.of_node && !pdata) { + dev_err(&pdev->dev, "timeriomem_rng_data is missing\n"); + return -EINVAL; + } + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) - return -ENOENT; + return -ENXIO; - timeriomem_rng_data = pdev->dev.platform_data; + if (res->start % 4 != 0 || resource_size(res) != 4) { + dev_err(&pdev->dev, + "address must be four bytes wide and aligned\n"); + return -EINVAL; + } - timeriomem_rng_data->address = ioremap(res->start, resource_size(res)); - if (!timeriomem_rng_data->address) - return -EIO; + /* Allocate memory for the device structure (and zero it) */ + priv = kzalloc(sizeof(struct timeriomem_rng_private_data), GFP_KERNEL); + if (!priv) { + dev_err(&pdev->dev, "failed to allocate device structure.\n"); + return -ENOMEM; + } + + platform_set_drvdata(pdev, priv); + + if (pdev->dev.of_node) { + int i; + + if (!of_property_read_u32(pdev->dev.of_node, + "period", &i)) + period = i; + else { + dev_err(&pdev->dev, "missing period\n"); + err = -EINVAL; + goto out_free; + } + } else + period = pdata->period; + + priv->period = usecs_to_jiffies(period); + if (priv->period < 1) { + dev_err(&pdev->dev, "period is less than one jiffy\n"); + err = -EINVAL; + goto out_free; + } - if (timeriomem_rng_data->period != 0 - && usecs_to_jiffies(timeriomem_rng_data->period) > 0) { - timeriomem_rng_timer.expires = jiffies; + priv->expires = jiffies; + priv->present = 1; - timeriomem_rng_ops.priv = usecs_to_jiffies( - timeriomem_rng_data->period); + init_completion(&priv->completion); + complete(&priv->completion); + + setup_timer(&priv->timer, timeriomem_rng_trigger, (unsigned long)priv); + + priv->timeriomem_rng_ops.name = dev_name(&pdev->dev); + priv->timeriomem_rng_ops.data_present = timeriomem_rng_data_present; + priv->timeriomem_rng_ops.data_read = timeriomem_rng_data_read; + priv->timeriomem_rng_ops.priv = (unsigned long)priv; + + if (!request_mem_region(res->start, resource_size(res), + dev_name(&pdev->dev))) { + dev_err(&pdev->dev, "request_mem_region failed\n"); + err = -EBUSY; + goto out_timer; } - timeriomem_rng_data->present = 1; - ret = hwrng_register(&timeriomem_rng_ops); - if (ret) - goto failed; + priv->io_base = ioremap(res->start, resource_size(res)); + if (priv->io_base == NULL) { + dev_err(&pdev->dev, "ioremap failed\n"); + err = -EIO; + goto out_release_io; + } + + err = hwrng_register(&priv->timeriomem_rng_ops); + if (err) { + dev_err(&pdev->dev, "problem registering\n"); + goto out; + } dev_info(&pdev->dev, "32bits from 0x%p @ %dus\n", - timeriomem_rng_data->address, - timeriomem_rng_data->period); + priv->io_base, period); return 0; -failed: - dev_err(&pdev->dev, "problem registering\n"); - iounmap(timeriomem_rng_data->address); - - return ret; +out: + iounmap(priv->io_base); +out_release_io: + release_mem_region(res->start, resource_size(res)); +out_timer: + del_timer_sync(&priv->timer); +out_free: + platform_set_drvdata(pdev, NULL); + kfree(priv); + return err; } static int timeriomem_rng_remove(struct platform_device *pdev) { - del_timer_sync(&timeriomem_rng_timer); - hwrng_unregister(&timeriomem_rng_ops); + struct timeriomem_rng_private_data *priv = platform_get_drvdata(pdev); + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - iounmap(timeriomem_rng_data->address); + hwrng_unregister(&priv->timeriomem_rng_ops); + + del_timer_sync(&priv->timer); + iounmap(priv->io_base); + release_mem_region(res->start, resource_size(res)); + platform_set_drvdata(pdev, NULL); + kfree(priv); return 0; } +static const struct of_device_id timeriomem_rng_match[] = { + { .compatible = "timeriomem_rng" }, + {}, +}; +MODULE_DEVICE_TABLE(of, timeriomem_rng_match); + static struct platform_driver timeriomem_rng_driver = { .driver = { .name = "timeriomem_rng", .owner = THIS_MODULE, + .of_match_table = timeriomem_rng_match, }, .probe = timeriomem_rng_probe, .remove = timeriomem_rng_remove, diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 87ec4d027c2..dffb8552536 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -276,6 +276,16 @@ config CRYPTO_DEV_PICOXCELL Saying m here will build a module named pipcoxcell_crypto. +config CRYPTO_DEV_SAHARA + tristate "Support for SAHARA crypto accelerator" + depends on ARCH_MXC && EXPERIMENTAL && OF + select CRYPTO_BLKCIPHER + select CRYPTO_AES + select CRYPTO_ECB + help + This option enables support for the SAHARA HW crypto accelerator + found in some Freescale i.MX chips. + config CRYPTO_DEV_S5P tristate "Support for Samsung S5PV210 crypto accelerator" depends on ARCH_S5PV210 @@ -361,15 +371,17 @@ config CRYPTO_DEV_ATMEL_TDES will be called atmel-tdes. config CRYPTO_DEV_ATMEL_SHA - tristate "Support for Atmel SHA1/SHA256 hw accelerator" + tristate "Support for Atmel SHA hw accelerator" depends on ARCH_AT91 select CRYPTO_SHA1 select CRYPTO_SHA256 + select CRYPTO_SHA512 select CRYPTO_ALGAPI help - Some Atmel processors have SHA1/SHA256 hw accelerator. + Some Atmel processors have SHA1/SHA224/SHA256/SHA384/SHA512 + hw accelerator. Select this if you want to use the Atmel module for - SHA1/SHA256 algorithms. + SHA1/SHA224/SHA256/SHA384/SHA512 algorithms. To compile this driver as a module, choose M here: the module will be called atmel-sha. diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile index 880a47b0b02..38ce13d3b79 100644 --- a/drivers/crypto/Makefile +++ b/drivers/crypto/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/ obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes.o obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o +obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o obj-$(CONFIG_CRYPTO_DEV_TEGRA_AES) += tegra-aes.o obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/ diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 6f22ba51f96..c1efd910d97 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -38,7 +38,7 @@ #include <crypto/aes.h> #include <crypto/hash.h> #include <crypto/internal/hash.h> -#include <linux/platform_data/atmel-aes.h> +#include <linux/platform_data/crypto-atmel.h> #include "atmel-aes-regs.h" #define CFB8_BLOCK_SIZE 1 @@ -47,7 +47,7 @@ #define CFB64_BLOCK_SIZE 8 /* AES flags */ -#define AES_FLAGS_MODE_MASK 0x01ff +#define AES_FLAGS_MODE_MASK 0x03ff #define AES_FLAGS_ENCRYPT BIT(0) #define AES_FLAGS_CBC BIT(1) #define AES_FLAGS_CFB BIT(2) @@ -55,21 +55,26 @@ #define AES_FLAGS_CFB16 BIT(4) #define AES_FLAGS_CFB32 BIT(5) #define AES_FLAGS_CFB64 BIT(6) -#define AES_FLAGS_OFB BIT(7) -#define AES_FLAGS_CTR BIT(8) +#define AES_FLAGS_CFB128 BIT(7) +#define AES_FLAGS_OFB BIT(8) +#define AES_FLAGS_CTR BIT(9) #define AES_FLAGS_INIT BIT(16) #define AES_FLAGS_DMA BIT(17) #define AES_FLAGS_BUSY BIT(18) +#define AES_FLAGS_FAST BIT(19) -#define AES_FLAGS_DUALBUFF BIT(24) - -#define ATMEL_AES_QUEUE_LENGTH 1 -#define ATMEL_AES_CACHE_SIZE 0 +#define ATMEL_AES_QUEUE_LENGTH 50 #define ATMEL_AES_DMA_THRESHOLD 16 +struct atmel_aes_caps { + bool has_dualbuff; + bool has_cfb64; + u32 max_burst_size; +}; + struct atmel_aes_dev; struct atmel_aes_ctx { @@ -77,6 +82,8 @@ struct atmel_aes_ctx { int keylen; u32 key[AES_KEYSIZE_256 / sizeof(u32)]; + + u16 block_size; }; struct atmel_aes_reqctx { @@ -112,20 +119,27 @@ struct atmel_aes_dev { struct scatterlist *in_sg; unsigned int nb_in_sg; - + size_t in_offset; struct scatterlist *out_sg; unsigned int nb_out_sg; + size_t out_offset; size_t bufcnt; + size_t buflen; + size_t dma_size; - u8 buf_in[ATMEL_AES_DMA_THRESHOLD] __aligned(sizeof(u32)); - int dma_in; + void *buf_in; + int dma_in; + dma_addr_t dma_addr_in; struct atmel_aes_dma dma_lch_in; - u8 buf_out[ATMEL_AES_DMA_THRESHOLD] __aligned(sizeof(u32)); - int dma_out; + void *buf_out; + int dma_out; + dma_addr_t dma_addr_out; struct atmel_aes_dma dma_lch_out; + struct atmel_aes_caps caps; + u32 hw_version; }; @@ -165,6 +179,37 @@ static int atmel_aes_sg_length(struct ablkcipher_request *req, return sg_nb; } +static int atmel_aes_sg_copy(struct scatterlist **sg, size_t *offset, + void *buf, size_t buflen, size_t total, int out) +{ + unsigned int count, off = 0; + + while (buflen && total) { + count = min((*sg)->length - *offset, total); + count = min(count, buflen); + + if (!count) + return off; + + scatterwalk_map_and_copy(buf + off, *sg, *offset, count, out); + + off += count; + buflen -= count; + *offset += count; + total -= count; + + if (*offset == (*sg)->length) { + *sg = sg_next(*sg); + if (*sg) + *offset = 0; + else + total = 0; + } + } + + return off; +} + static inline u32 atmel_aes_read(struct atmel_aes_dev *dd, u32 offset) { return readl_relaxed(dd->io_base + offset); @@ -190,14 +235,6 @@ static void atmel_aes_write_n(struct atmel_aes_dev *dd, u32 offset, atmel_aes_write(dd, offset, *value); } -static void atmel_aes_dualbuff_test(struct atmel_aes_dev *dd) -{ - atmel_aes_write(dd, AES_MR, AES_MR_DUALBUFF); - - if (atmel_aes_read(dd, AES_MR) & AES_MR_DUALBUFF) - dd->flags |= AES_FLAGS_DUALBUFF; -} - static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_ctx *ctx) { struct atmel_aes_dev *aes_dd = NULL; @@ -225,7 +262,7 @@ static int atmel_aes_hw_init(struct atmel_aes_dev *dd) if (!(dd->flags & AES_FLAGS_INIT)) { atmel_aes_write(dd, AES_CR, AES_CR_SWRST); - atmel_aes_dualbuff_test(dd); + atmel_aes_write(dd, AES_MR, 0xE << AES_MR_CKEY_OFFSET); dd->flags |= AES_FLAGS_INIT; dd->err = 0; } @@ -233,11 +270,19 @@ static int atmel_aes_hw_init(struct atmel_aes_dev *dd) return 0; } +static inline unsigned int atmel_aes_get_version(struct atmel_aes_dev *dd) +{ + return atmel_aes_read(dd, AES_HW_VERSION) & 0x00000fff; +} + static void atmel_aes_hw_version_init(struct atmel_aes_dev *dd) { atmel_aes_hw_init(dd); - dd->hw_version = atmel_aes_read(dd, AES_HW_VERSION); + dd->hw_version = atmel_aes_get_version(dd); + + dev_info(dd->dev, + "version: 0x%x\n", dd->hw_version); clk_disable_unprepare(dd->iclk); } @@ -260,50 +305,77 @@ static void atmel_aes_dma_callback(void *data) tasklet_schedule(&dd->done_task); } -static int atmel_aes_crypt_dma(struct atmel_aes_dev *dd) +static int atmel_aes_crypt_dma(struct atmel_aes_dev *dd, + dma_addr_t dma_addr_in, dma_addr_t dma_addr_out, int length) { + struct scatterlist sg[2]; struct dma_async_tx_descriptor *in_desc, *out_desc; - int nb_dma_sg_in, nb_dma_sg_out; - dd->nb_in_sg = atmel_aes_sg_length(dd->req, dd->in_sg); - if (!dd->nb_in_sg) - goto exit_err; + dd->dma_size = length; - nb_dma_sg_in = dma_map_sg(dd->dev, dd->in_sg, dd->nb_in_sg, - DMA_TO_DEVICE); - if (!nb_dma_sg_in) - goto exit_err; + if (!(dd->flags & AES_FLAGS_FAST)) { + dma_sync_single_for_device(dd->dev, dma_addr_in, length, + DMA_TO_DEVICE); + } - in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, dd->in_sg, - nb_dma_sg_in, DMA_MEM_TO_DEV, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (dd->flags & AES_FLAGS_CFB8) { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_1_BYTE; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_1_BYTE; + } else if (dd->flags & AES_FLAGS_CFB16) { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_2_BYTES; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_2_BYTES; + } else { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + } - if (!in_desc) - goto unmap_in; + if (dd->flags & (AES_FLAGS_CFB8 | AES_FLAGS_CFB16 | + AES_FLAGS_CFB32 | AES_FLAGS_CFB64)) { + dd->dma_lch_in.dma_conf.src_maxburst = 1; + dd->dma_lch_in.dma_conf.dst_maxburst = 1; + dd->dma_lch_out.dma_conf.src_maxburst = 1; + dd->dma_lch_out.dma_conf.dst_maxburst = 1; + } else { + dd->dma_lch_in.dma_conf.src_maxburst = dd->caps.max_burst_size; + dd->dma_lch_in.dma_conf.dst_maxburst = dd->caps.max_burst_size; + dd->dma_lch_out.dma_conf.src_maxburst = dd->caps.max_burst_size; + dd->dma_lch_out.dma_conf.dst_maxburst = dd->caps.max_burst_size; + } - /* callback not needed */ + dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf); + dmaengine_slave_config(dd->dma_lch_out.chan, &dd->dma_lch_out.dma_conf); - dd->nb_out_sg = atmel_aes_sg_length(dd->req, dd->out_sg); - if (!dd->nb_out_sg) - goto unmap_in; + dd->flags |= AES_FLAGS_DMA; - nb_dma_sg_out = dma_map_sg(dd->dev, dd->out_sg, dd->nb_out_sg, - DMA_FROM_DEVICE); - if (!nb_dma_sg_out) - goto unmap_out; + sg_init_table(&sg[0], 1); + sg_dma_address(&sg[0]) = dma_addr_in; + sg_dma_len(&sg[0]) = length; - out_desc = dmaengine_prep_slave_sg(dd->dma_lch_out.chan, dd->out_sg, - nb_dma_sg_out, DMA_DEV_TO_MEM, - DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + sg_init_table(&sg[1], 1); + sg_dma_address(&sg[1]) = dma_addr_out; + sg_dma_len(&sg[1]) = length; + + in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, &sg[0], + 1, DMA_MEM_TO_DEV, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!in_desc) + return -EINVAL; + out_desc = dmaengine_prep_slave_sg(dd->dma_lch_out.chan, &sg[1], + 1, DMA_DEV_TO_MEM, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!out_desc) - goto unmap_out; + return -EINVAL; out_desc->callback = atmel_aes_dma_callback; out_desc->callback_param = dd; - dd->total -= dd->req->nbytes; - dmaengine_submit(out_desc); dma_async_issue_pending(dd->dma_lch_out.chan); @@ -311,15 +383,6 @@ static int atmel_aes_crypt_dma(struct atmel_aes_dev *dd) dma_async_issue_pending(dd->dma_lch_in.chan); return 0; - -unmap_out: - dma_unmap_sg(dd->dev, dd->out_sg, dd->nb_out_sg, - DMA_FROM_DEVICE); -unmap_in: - dma_unmap_sg(dd->dev, dd->in_sg, dd->nb_in_sg, - DMA_TO_DEVICE); -exit_err: - return -EINVAL; } static int atmel_aes_crypt_cpu_start(struct atmel_aes_dev *dd) @@ -352,30 +415,66 @@ static int atmel_aes_crypt_cpu_start(struct atmel_aes_dev *dd) static int atmel_aes_crypt_dma_start(struct atmel_aes_dev *dd) { - int err; + int err, fast = 0, in, out; + size_t count; + dma_addr_t addr_in, addr_out; + + if ((!dd->in_offset) && (!dd->out_offset)) { + /* check for alignment */ + in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32)) && + IS_ALIGNED(dd->in_sg->length, dd->ctx->block_size); + out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32)) && + IS_ALIGNED(dd->out_sg->length, dd->ctx->block_size); + fast = in && out; + + if (sg_dma_len(dd->in_sg) != sg_dma_len(dd->out_sg)) + fast = 0; + } + + + if (fast) { + count = min(dd->total, sg_dma_len(dd->in_sg)); + count = min(count, sg_dma_len(dd->out_sg)); + + err = dma_map_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); + if (!err) { + dev_err(dd->dev, "dma_map_sg() error\n"); + return -EINVAL; + } + + err = dma_map_sg(dd->dev, dd->out_sg, 1, + DMA_FROM_DEVICE); + if (!err) { + dev_err(dd->dev, "dma_map_sg() error\n"); + dma_unmap_sg(dd->dev, dd->in_sg, 1, + DMA_TO_DEVICE); + return -EINVAL; + } + + addr_in = sg_dma_address(dd->in_sg); + addr_out = sg_dma_address(dd->out_sg); + + dd->flags |= AES_FLAGS_FAST; - if (dd->flags & AES_FLAGS_CFB8) { - dd->dma_lch_in.dma_conf.dst_addr_width = - DMA_SLAVE_BUSWIDTH_1_BYTE; - dd->dma_lch_out.dma_conf.src_addr_width = - DMA_SLAVE_BUSWIDTH_1_BYTE; - } else if (dd->flags & AES_FLAGS_CFB16) { - dd->dma_lch_in.dma_conf.dst_addr_width = - DMA_SLAVE_BUSWIDTH_2_BYTES; - dd->dma_lch_out.dma_conf.src_addr_width = - DMA_SLAVE_BUSWIDTH_2_BYTES; } else { - dd->dma_lch_in.dma_conf.dst_addr_width = - DMA_SLAVE_BUSWIDTH_4_BYTES; - dd->dma_lch_out.dma_conf.src_addr_width = - DMA_SLAVE_BUSWIDTH_4_BYTES; + /* use cache buffers */ + count = atmel_aes_sg_copy(&dd->in_sg, &dd->in_offset, + dd->buf_in, dd->buflen, dd->total, 0); + + addr_in = dd->dma_addr_in; + addr_out = dd->dma_addr_out; + + dd->flags &= ~AES_FLAGS_FAST; } - dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf); - dmaengine_slave_config(dd->dma_lch_out.chan, &dd->dma_lch_out.dma_conf); + dd->total -= count; - dd->flags |= AES_FLAGS_DMA; - err = atmel_aes_crypt_dma(dd); + err = atmel_aes_crypt_dma(dd, addr_in, addr_out, count); + + if (err && (dd->flags & AES_FLAGS_FAST)) { + dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); + dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_TO_DEVICE); + } return err; } @@ -410,6 +509,8 @@ static int atmel_aes_write_ctrl(struct atmel_aes_dev *dd) valmr |= AES_MR_CFBS_32b; else if (dd->flags & AES_FLAGS_CFB64) valmr |= AES_MR_CFBS_64b; + else if (dd->flags & AES_FLAGS_CFB128) + valmr |= AES_MR_CFBS_128b; } else if (dd->flags & AES_FLAGS_OFB) { valmr |= AES_MR_OPMOD_OFB; } else if (dd->flags & AES_FLAGS_CTR) { @@ -423,7 +524,7 @@ static int atmel_aes_write_ctrl(struct atmel_aes_dev *dd) if (dd->total > ATMEL_AES_DMA_THRESHOLD) { valmr |= AES_MR_SMOD_IDATAR0; - if (dd->flags & AES_FLAGS_DUALBUFF) + if (dd->caps.has_dualbuff) valmr |= AES_MR_DUALBUFF; } else { valmr |= AES_MR_SMOD_AUTO; @@ -477,7 +578,9 @@ static int atmel_aes_handle_queue(struct atmel_aes_dev *dd, /* assign new request to device */ dd->req = req; dd->total = req->nbytes; + dd->in_offset = 0; dd->in_sg = req->src; + dd->out_offset = 0; dd->out_sg = req->dst; rctx = ablkcipher_request_ctx(req); @@ -506,18 +609,86 @@ static int atmel_aes_handle_queue(struct atmel_aes_dev *dd, static int atmel_aes_crypt_dma_stop(struct atmel_aes_dev *dd) { int err = -EINVAL; + size_t count; if (dd->flags & AES_FLAGS_DMA) { - dma_unmap_sg(dd->dev, dd->out_sg, - dd->nb_out_sg, DMA_FROM_DEVICE); - dma_unmap_sg(dd->dev, dd->in_sg, - dd->nb_in_sg, DMA_TO_DEVICE); err = 0; + if (dd->flags & AES_FLAGS_FAST) { + dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_FROM_DEVICE); + dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); + } else { + dma_sync_single_for_device(dd->dev, dd->dma_addr_out, + dd->dma_size, DMA_FROM_DEVICE); + + /* copy data */ + count = atmel_aes_sg_copy(&dd->out_sg, &dd->out_offset, + dd->buf_out, dd->buflen, dd->dma_size, 1); + if (count != dd->dma_size) { + err = -EINVAL; + pr_err("not all data converted: %u\n", count); + } + } } return err; } + +static int atmel_aes_buff_init(struct atmel_aes_dev *dd) +{ + int err = -ENOMEM; + + dd->buf_in = (void *)__get_free_pages(GFP_KERNEL, 0); + dd->buf_out = (void *)__get_free_pages(GFP_KERNEL, 0); + dd->buflen = PAGE_SIZE; + dd->buflen &= ~(AES_BLOCK_SIZE - 1); + + if (!dd->buf_in || !dd->buf_out) { + dev_err(dd->dev, "unable to alloc pages.\n"); + goto err_alloc; + } + + /* MAP here */ + dd->dma_addr_in = dma_map_single(dd->dev, dd->buf_in, + dd->buflen, DMA_TO_DEVICE); + if (dma_mapping_error(dd->dev, dd->dma_addr_in)) { + dev_err(dd->dev, "dma %d bytes error\n", dd->buflen); + err = -EINVAL; + goto err_map_in; + } + + dd->dma_addr_out = dma_map_single(dd->dev, dd->buf_out, + dd->buflen, DMA_FROM_DEVICE); + if (dma_mapping_error(dd->dev, dd->dma_addr_out)) { + dev_err(dd->dev, "dma %d bytes error\n", dd->buflen); + err = -EINVAL; + goto err_map_out; + } + + return 0; + +err_map_out: + dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen, + DMA_TO_DEVICE); +err_map_in: + free_page((unsigned long)dd->buf_out); + free_page((unsigned long)dd->buf_in); +err_alloc: + if (err) + pr_err("error: %d\n", err); + return err; +} + +static void atmel_aes_buff_cleanup(struct atmel_aes_dev *dd) +{ + dma_unmap_single(dd->dev, dd->dma_addr_out, dd->buflen, + DMA_FROM_DEVICE); + dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen, + DMA_TO_DEVICE); + free_page((unsigned long)dd->buf_out); + free_page((unsigned long)dd->buf_in); +} + static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode) { struct atmel_aes_ctx *ctx = crypto_ablkcipher_ctx( @@ -525,9 +696,30 @@ static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode) struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req); struct atmel_aes_dev *dd; - if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) { - pr_err("request size is not exact amount of AES blocks\n"); - return -EINVAL; + if (mode & AES_FLAGS_CFB8) { + if (!IS_ALIGNED(req->nbytes, CFB8_BLOCK_SIZE)) { + pr_err("request size is not exact amount of CFB8 blocks\n"); + return -EINVAL; + } + ctx->block_size = CFB8_BLOCK_SIZE; + } else if (mode & AES_FLAGS_CFB16) { + if (!IS_ALIGNED(req->nbytes, CFB16_BLOCK_SIZE)) { + pr_err("request size is not exact amount of CFB16 blocks\n"); + return -EINVAL; + } + ctx->block_size = CFB16_BLOCK_SIZE; + } else if (mode & AES_FLAGS_CFB32) { + if (!IS_ALIGNED(req->nbytes, CFB32_BLOCK_SIZE)) { + pr_err("request size is not exact amount of CFB32 blocks\n"); + return -EINVAL; + } + ctx->block_size = CFB32_BLOCK_SIZE; + } else { + if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) { + pr_err("request size is not exact amount of AES blocks\n"); + return -EINVAL; + } + ctx->block_size = AES_BLOCK_SIZE; } dd = atmel_aes_find_dev(ctx); @@ -551,14 +743,12 @@ static bool atmel_aes_filter(struct dma_chan *chan, void *slave) } } -static int atmel_aes_dma_init(struct atmel_aes_dev *dd) +static int atmel_aes_dma_init(struct atmel_aes_dev *dd, + struct crypto_platform_data *pdata) { int err = -ENOMEM; - struct aes_platform_data *pdata; dma_cap_mask_t mask_in, mask_out; - pdata = dd->dev->platform_data; - if (pdata && pdata->dma_slave->txdata.dma_dev && pdata->dma_slave->rxdata.dma_dev) { @@ -568,28 +758,38 @@ static int atmel_aes_dma_init(struct atmel_aes_dev *dd) dd->dma_lch_in.chan = dma_request_channel(mask_in, atmel_aes_filter, &pdata->dma_slave->rxdata); + if (!dd->dma_lch_in.chan) goto err_dma_in; dd->dma_lch_in.dma_conf.direction = DMA_MEM_TO_DEV; dd->dma_lch_in.dma_conf.dst_addr = dd->phys_base + AES_IDATAR(0); - dd->dma_lch_in.dma_conf.src_maxburst = 1; - dd->dma_lch_in.dma_conf.dst_maxburst = 1; + dd->dma_lch_in.dma_conf.src_maxburst = dd->caps.max_burst_size; + dd->dma_lch_in.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_in.dma_conf.dst_maxburst = dd->caps.max_burst_size; + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; dd->dma_lch_in.dma_conf.device_fc = false; dma_cap_zero(mask_out); dma_cap_set(DMA_SLAVE, mask_out); dd->dma_lch_out.chan = dma_request_channel(mask_out, atmel_aes_filter, &pdata->dma_slave->txdata); + if (!dd->dma_lch_out.chan) goto err_dma_out; dd->dma_lch_out.dma_conf.direction = DMA_DEV_TO_MEM; dd->dma_lch_out.dma_conf.src_addr = dd->phys_base + AES_ODATAR(0); - dd->dma_lch_out.dma_conf.src_maxburst = 1; - dd->dma_lch_out.dma_conf.dst_maxburst = 1; + dd->dma_lch_out.dma_conf.src_maxburst = dd->caps.max_burst_size; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_out.dma_conf.dst_maxburst = dd->caps.max_burst_size; + dd->dma_lch_out.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; dd->dma_lch_out.dma_conf.device_fc = false; return 0; @@ -665,13 +865,13 @@ static int atmel_aes_ofb_decrypt(struct ablkcipher_request *req) static int atmel_aes_cfb_encrypt(struct ablkcipher_request *req) { return atmel_aes_crypt(req, - AES_FLAGS_ENCRYPT | AES_FLAGS_CFB); + AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB128); } static int atmel_aes_cfb_decrypt(struct ablkcipher_request *req) { return atmel_aes_crypt(req, - AES_FLAGS_CFB); + AES_FLAGS_CFB | AES_FLAGS_CFB128); } static int atmel_aes_cfb64_encrypt(struct ablkcipher_request *req) @@ -753,7 +953,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0xf, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -773,7 +973,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0xf, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -794,7 +994,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0xf, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -815,7 +1015,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0xf, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -836,7 +1036,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0x3, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -857,7 +1057,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB16_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0x1, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -899,7 +1099,7 @@ static struct crypto_alg aes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0xf, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -915,15 +1115,14 @@ static struct crypto_alg aes_algs[] = { }, }; -static struct crypto_alg aes_cfb64_alg[] = { -{ +static struct crypto_alg aes_cfb64_alg = { .cra_name = "cfb64(aes)", .cra_driver_name = "atmel-cfb64-aes", .cra_priority = 100, .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB64_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_aes_ctx), - .cra_alignmask = 0x0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_aes_cra_init, @@ -936,7 +1135,6 @@ static struct crypto_alg aes_cfb64_alg[] = { .encrypt = atmel_aes_cfb64_encrypt, .decrypt = atmel_aes_cfb64_decrypt, } -}, }; static void atmel_aes_queue_task(unsigned long data) @@ -969,7 +1167,14 @@ static void atmel_aes_done_task(unsigned long data) err = dd->err ? : err; if (dd->total && !err) { - err = atmel_aes_crypt_dma_start(dd); + if (dd->flags & AES_FLAGS_FAST) { + dd->in_sg = sg_next(dd->in_sg); + dd->out_sg = sg_next(dd->out_sg); + if (!dd->in_sg || !dd->out_sg) + err = -EINVAL; + } + if (!err) + err = atmel_aes_crypt_dma_start(dd); if (!err) return; /* DMA started. Not fininishing. */ } @@ -1003,8 +1208,8 @@ static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd) for (i = 0; i < ARRAY_SIZE(aes_algs); i++) crypto_unregister_alg(&aes_algs[i]); - if (dd->hw_version >= 0x130) - crypto_unregister_alg(&aes_cfb64_alg[0]); + if (dd->caps.has_cfb64) + crypto_unregister_alg(&aes_cfb64_alg); } static int atmel_aes_register_algs(struct atmel_aes_dev *dd) @@ -1017,10 +1222,8 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) goto err_aes_algs; } - atmel_aes_hw_version_init(dd); - - if (dd->hw_version >= 0x130) { - err = crypto_register_alg(&aes_cfb64_alg[0]); + if (dd->caps.has_cfb64) { + err = crypto_register_alg(&aes_cfb64_alg); if (err) goto err_aes_cfb64_alg; } @@ -1036,10 +1239,32 @@ err_aes_algs: return err; } +static void atmel_aes_get_cap(struct atmel_aes_dev *dd) +{ + dd->caps.has_dualbuff = 0; + dd->caps.has_cfb64 = 0; + dd->caps.max_burst_size = 1; + + /* keep only major version number */ + switch (dd->hw_version & 0xff0) { + case 0x130: + dd->caps.has_dualbuff = 1; + dd->caps.has_cfb64 = 1; + dd->caps.max_burst_size = 4; + break; + case 0x120: + break; + default: + dev_warn(dd->dev, + "Unmanaged aes version, set minimum capabilities\n"); + break; + } +} + static int atmel_aes_probe(struct platform_device *pdev) { struct atmel_aes_dev *aes_dd; - struct aes_platform_data *pdata; + struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *aes_res; unsigned long aes_phys_size; @@ -1099,7 +1324,7 @@ static int atmel_aes_probe(struct platform_device *pdev) } /* Initializing the clock */ - aes_dd->iclk = clk_get(&pdev->dev, NULL); + aes_dd->iclk = clk_get(&pdev->dev, "aes_clk"); if (IS_ERR(aes_dd->iclk)) { dev_err(dev, "clock intialization failed.\n"); err = PTR_ERR(aes_dd->iclk); @@ -1113,7 +1338,15 @@ static int atmel_aes_probe(struct platform_device *pdev) goto aes_io_err; } - err = atmel_aes_dma_init(aes_dd); + atmel_aes_hw_version_init(aes_dd); + + atmel_aes_get_cap(aes_dd); + + err = atmel_aes_buff_init(aes_dd); + if (err) + goto err_aes_buff; + + err = atmel_aes_dma_init(aes_dd, pdata); if (err) goto err_aes_dma; @@ -1135,6 +1368,8 @@ err_algs: spin_unlock(&atmel_aes.lock); atmel_aes_dma_cleanup(aes_dd); err_aes_dma: + atmel_aes_buff_cleanup(aes_dd); +err_aes_buff: iounmap(aes_dd->io_base); aes_io_err: clk_put(aes_dd->iclk); diff --git a/drivers/crypto/atmel-sha-regs.h b/drivers/crypto/atmel-sha-regs.h index dc53a20d7da..83b2d742566 100644 --- a/drivers/crypto/atmel-sha-regs.h +++ b/drivers/crypto/atmel-sha-regs.h @@ -14,10 +14,13 @@ #define SHA_MR_MODE_MANUAL 0x0 #define SHA_MR_MODE_AUTO 0x1 #define SHA_MR_MODE_PDC 0x2 -#define SHA_MR_DUALBUFF (1 << 3) #define SHA_MR_PROCDLY (1 << 4) #define SHA_MR_ALGO_SHA1 (0 << 8) #define SHA_MR_ALGO_SHA256 (1 << 8) +#define SHA_MR_ALGO_SHA384 (2 << 8) +#define SHA_MR_ALGO_SHA512 (3 << 8) +#define SHA_MR_ALGO_SHA224 (4 << 8) +#define SHA_MR_DUALBUFF (1 << 16) #define SHA_IER 0x10 #define SHA_IDR 0x14 @@ -33,6 +36,8 @@ #define SHA_ISR_URAT_MR (0x2 << 12) #define SHA_ISR_URAT_WO (0x5 << 12) +#define SHA_HW_VERSION 0xFC + #define SHA_TPR 0x108 #define SHA_TCR 0x10C #define SHA_TNPR 0x118 diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 4918e9424d3..eaed8bf183b 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -38,6 +38,7 @@ #include <crypto/sha.h> #include <crypto/hash.h> #include <crypto/internal/hash.h> +#include <linux/platform_data/crypto-atmel.h> #include "atmel-sha-regs.h" /* SHA flags */ @@ -52,11 +53,12 @@ #define SHA_FLAGS_FINUP BIT(16) #define SHA_FLAGS_SG BIT(17) #define SHA_FLAGS_SHA1 BIT(18) -#define SHA_FLAGS_SHA256 BIT(19) -#define SHA_FLAGS_ERROR BIT(20) -#define SHA_FLAGS_PAD BIT(21) - -#define SHA_FLAGS_DUALBUFF BIT(24) +#define SHA_FLAGS_SHA224 BIT(19) +#define SHA_FLAGS_SHA256 BIT(20) +#define SHA_FLAGS_SHA384 BIT(21) +#define SHA_FLAGS_SHA512 BIT(22) +#define SHA_FLAGS_ERROR BIT(23) +#define SHA_FLAGS_PAD BIT(24) #define SHA_OP_UPDATE 1 #define SHA_OP_FINAL 2 @@ -65,6 +67,12 @@ #define ATMEL_SHA_DMA_THRESHOLD 56 +struct atmel_sha_caps { + bool has_dma; + bool has_dualbuff; + bool has_sha224; + bool has_sha_384_512; +}; struct atmel_sha_dev; @@ -73,8 +81,8 @@ struct atmel_sha_reqctx { unsigned long flags; unsigned long op; - u8 digest[SHA256_DIGEST_SIZE] __aligned(sizeof(u32)); - size_t digcnt; + u8 digest[SHA512_DIGEST_SIZE] __aligned(sizeof(u32)); + u64 digcnt[2]; size_t bufcnt; size_t buflen; dma_addr_t dma_addr; @@ -84,6 +92,8 @@ struct atmel_sha_reqctx { unsigned int offset; /* offset in current sg */ unsigned int total; /* total request */ + size_t block_size; + u8 buffer[0] __aligned(sizeof(u32)); }; @@ -97,7 +107,12 @@ struct atmel_sha_ctx { }; -#define ATMEL_SHA_QUEUE_LENGTH 1 +#define ATMEL_SHA_QUEUE_LENGTH 50 + +struct atmel_sha_dma { + struct dma_chan *chan; + struct dma_slave_config dma_conf; +}; struct atmel_sha_dev { struct list_head list; @@ -114,6 +129,12 @@ struct atmel_sha_dev { unsigned long flags; struct crypto_queue queue; struct ahash_request *req; + + struct atmel_sha_dma dma_lch_in; + + struct atmel_sha_caps caps; + + u32 hw_version; }; struct atmel_sha_drv { @@ -137,14 +158,6 @@ static inline void atmel_sha_write(struct atmel_sha_dev *dd, writel_relaxed(value, dd->io_base + offset); } -static void atmel_sha_dualbuff_test(struct atmel_sha_dev *dd) -{ - atmel_sha_write(dd, SHA_MR, SHA_MR_DUALBUFF); - - if (atmel_sha_read(dd, SHA_MR) & SHA_MR_DUALBUFF) - dd->flags |= SHA_FLAGS_DUALBUFF; -} - static size_t atmel_sha_append_sg(struct atmel_sha_reqctx *ctx) { size_t count; @@ -176,31 +189,58 @@ static size_t atmel_sha_append_sg(struct atmel_sha_reqctx *ctx) } /* - * The purpose of this padding is to ensure that the padded message - * is a multiple of 512 bits. The bit "1" is appended at the end of - * the message followed by "padlen-1" zero bits. Then a 64 bits block - * equals to the message length in bits is appended. + * The purpose of this padding is to ensure that the padded message is a + * multiple of 512 bits (SHA1/SHA224/SHA256) or 1024 bits (SHA384/SHA512). + * The bit "1" is appended at the end of the message followed by + * "padlen-1" zero bits. Then a 64 bits block (SHA1/SHA224/SHA256) or + * 128 bits block (SHA384/SHA512) equals to the message length in bits + * is appended. * - * padlen is calculated as followed: + * For SHA1/SHA224/SHA256, padlen is calculated as followed: * - if message length < 56 bytes then padlen = 56 - message length * - else padlen = 64 + 56 - message length + * + * For SHA384/SHA512, padlen is calculated as followed: + * - if message length < 112 bytes then padlen = 112 - message length + * - else padlen = 128 + 112 - message length */ static void atmel_sha_fill_padding(struct atmel_sha_reqctx *ctx, int length) { unsigned int index, padlen; - u64 bits; - u64 size; - - bits = (ctx->bufcnt + ctx->digcnt + length) << 3; - size = cpu_to_be64(bits); - - index = ctx->bufcnt & 0x3f; - padlen = (index < 56) ? (56 - index) : ((64+56) - index); - *(ctx->buffer + ctx->bufcnt) = 0x80; - memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen-1); - memcpy(ctx->buffer + ctx->bufcnt + padlen, &size, 8); - ctx->bufcnt += padlen + 8; - ctx->flags |= SHA_FLAGS_PAD; + u64 bits[2]; + u64 size[2]; + + size[0] = ctx->digcnt[0]; + size[1] = ctx->digcnt[1]; + + size[0] += ctx->bufcnt; + if (size[0] < ctx->bufcnt) + size[1]++; + + size[0] += length; + if (size[0] < length) + size[1]++; + + bits[1] = cpu_to_be64(size[0] << 3); + bits[0] = cpu_to_be64(size[1] << 3 | size[0] >> 61); + + if (ctx->flags & (SHA_FLAGS_SHA384 | SHA_FLAGS_SHA512)) { + index = ctx->bufcnt & 0x7f; + padlen = (index < 112) ? (112 - index) : ((128+112) - index); + *(ctx->buffer + ctx->bufcnt) = 0x80; + memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen-1); + memcpy(ctx->buffer + ctx->bufcnt + padlen, bits, 16); + ctx->bufcnt += padlen + 16; + ctx->flags |= SHA_FLAGS_PAD; + } else { + index = ctx->bufcnt & 0x3f; + padlen = (index < 56) ? (56 - index) : ((64+56) - index); + *(ctx->buffer + ctx->bufcnt) = 0x80; + memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen-1); + memcpy(ctx->buffer + ctx->bufcnt + padlen, &bits[1], 8); + ctx->bufcnt += padlen + 8; + ctx->flags |= SHA_FLAGS_PAD; + } } static int atmel_sha_init(struct ahash_request *req) @@ -231,13 +271,35 @@ static int atmel_sha_init(struct ahash_request *req) dev_dbg(dd->dev, "init: digest size: %d\n", crypto_ahash_digestsize(tfm)); - if (crypto_ahash_digestsize(tfm) == SHA1_DIGEST_SIZE) + switch (crypto_ahash_digestsize(tfm)) { + case SHA1_DIGEST_SIZE: ctx->flags |= SHA_FLAGS_SHA1; - else if (crypto_ahash_digestsize(tfm) == SHA256_DIGEST_SIZE) + ctx->block_size = SHA1_BLOCK_SIZE; + break; + case SHA224_DIGEST_SIZE: + ctx->flags |= SHA_FLAGS_SHA224; + ctx->block_size = SHA224_BLOCK_SIZE; + break; + case SHA256_DIGEST_SIZE: ctx->flags |= SHA_FLAGS_SHA256; + ctx->block_size = SHA256_BLOCK_SIZE; + break; + case SHA384_DIGEST_SIZE: + ctx->flags |= SHA_FLAGS_SHA384; + ctx->block_size = SHA384_BLOCK_SIZE; + break; + case SHA512_DIGEST_SIZE: + ctx->flags |= SHA_FLAGS_SHA512; + ctx->block_size = SHA512_BLOCK_SIZE; + break; + default: + return -EINVAL; + break; + } ctx->bufcnt = 0; - ctx->digcnt = 0; + ctx->digcnt[0] = 0; + ctx->digcnt[1] = 0; ctx->buflen = SHA_BUFFER_LEN; return 0; @@ -249,19 +311,28 @@ static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma) u32 valcr = 0, valmr = SHA_MR_MODE_AUTO; if (likely(dma)) { - atmel_sha_write(dd, SHA_IER, SHA_INT_TXBUFE); + if (!dd->caps.has_dma) + atmel_sha_write(dd, SHA_IER, SHA_INT_TXBUFE); valmr = SHA_MR_MODE_PDC; - if (dd->flags & SHA_FLAGS_DUALBUFF) - valmr = SHA_MR_DUALBUFF; + if (dd->caps.has_dualbuff) + valmr |= SHA_MR_DUALBUFF; } else { atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY); } - if (ctx->flags & SHA_FLAGS_SHA256) + if (ctx->flags & SHA_FLAGS_SHA1) + valmr |= SHA_MR_ALGO_SHA1; + else if (ctx->flags & SHA_FLAGS_SHA224) + valmr |= SHA_MR_ALGO_SHA224; + else if (ctx->flags & SHA_FLAGS_SHA256) valmr |= SHA_MR_ALGO_SHA256; + else if (ctx->flags & SHA_FLAGS_SHA384) + valmr |= SHA_MR_ALGO_SHA384; + else if (ctx->flags & SHA_FLAGS_SHA512) + valmr |= SHA_MR_ALGO_SHA512; /* Setting CR_FIRST only for the first iteration */ - if (!ctx->digcnt) + if (!(ctx->digcnt[0] || ctx->digcnt[1])) valcr = SHA_CR_FIRST; atmel_sha_write(dd, SHA_CR, valcr); @@ -275,13 +346,15 @@ static int atmel_sha_xmit_cpu(struct atmel_sha_dev *dd, const u8 *buf, int count, len32; const u32 *buffer = (const u32 *)buf; - dev_dbg(dd->dev, "xmit_cpu: digcnt: %d, length: %d, final: %d\n", - ctx->digcnt, length, final); + dev_dbg(dd->dev, "xmit_cpu: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n", + ctx->digcnt[1], ctx->digcnt[0], length, final); atmel_sha_write_ctrl(dd, 0); /* should be non-zero before next lines to disable clocks later */ - ctx->digcnt += length; + ctx->digcnt[0] += length; + if (ctx->digcnt[0] < length) + ctx->digcnt[1]++; if (final) dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */ @@ -302,8 +375,8 @@ static int atmel_sha_xmit_pdc(struct atmel_sha_dev *dd, dma_addr_t dma_addr1, struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req); int len32; - dev_dbg(dd->dev, "xmit_pdc: digcnt: %d, length: %d, final: %d\n", - ctx->digcnt, length1, final); + dev_dbg(dd->dev, "xmit_pdc: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n", + ctx->digcnt[1], ctx->digcnt[0], length1, final); len32 = DIV_ROUND_UP(length1, sizeof(u32)); atmel_sha_write(dd, SHA_PTCR, SHA_PTCR_TXTDIS); @@ -317,7 +390,9 @@ static int atmel_sha_xmit_pdc(struct atmel_sha_dev *dd, dma_addr_t dma_addr1, atmel_sha_write_ctrl(dd, 1); /* should be non-zero before next lines to disable clocks later */ - ctx->digcnt += length1; + ctx->digcnt[0] += length1; + if (ctx->digcnt[0] < length1) + ctx->digcnt[1]++; if (final) dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */ @@ -330,6 +405,86 @@ static int atmel_sha_xmit_pdc(struct atmel_sha_dev *dd, dma_addr_t dma_addr1, return -EINPROGRESS; } +static void atmel_sha_dma_callback(void *data) +{ + struct atmel_sha_dev *dd = data; + + /* dma_lch_in - completed - wait DATRDY */ + atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY); +} + +static int atmel_sha_xmit_dma(struct atmel_sha_dev *dd, dma_addr_t dma_addr1, + size_t length1, dma_addr_t dma_addr2, size_t length2, int final) +{ + struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req); + struct dma_async_tx_descriptor *in_desc; + struct scatterlist sg[2]; + + dev_dbg(dd->dev, "xmit_dma: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n", + ctx->digcnt[1], ctx->digcnt[0], length1, final); + + if (ctx->flags & (SHA_FLAGS_SHA1 | SHA_FLAGS_SHA224 | + SHA_FLAGS_SHA256)) { + dd->dma_lch_in.dma_conf.src_maxburst = 16; + dd->dma_lch_in.dma_conf.dst_maxburst = 16; + } else { + dd->dma_lch_in.dma_conf.src_maxburst = 32; + dd->dma_lch_in.dma_conf.dst_maxburst = 32; + } + + dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf); + + if (length2) { + sg_init_table(sg, 2); + sg_dma_address(&sg[0]) = dma_addr1; + sg_dma_len(&sg[0]) = length1; + sg_dma_address(&sg[1]) = dma_addr2; + sg_dma_len(&sg[1]) = length2; + in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, sg, 2, + DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + } else { + sg_init_table(sg, 1); + sg_dma_address(&sg[0]) = dma_addr1; + sg_dma_len(&sg[0]) = length1; + in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, sg, 1, + DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + } + if (!in_desc) + return -EINVAL; + + in_desc->callback = atmel_sha_dma_callback; + in_desc->callback_param = dd; + + atmel_sha_write_ctrl(dd, 1); + + /* should be non-zero before next lines to disable clocks later */ + ctx->digcnt[0] += length1; + if (ctx->digcnt[0] < length1) + ctx->digcnt[1]++; + + if (final) + dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */ + + dd->flags |= SHA_FLAGS_DMA_ACTIVE; + + /* Start DMA transfer */ + dmaengine_submit(in_desc); + dma_async_issue_pending(dd->dma_lch_in.chan); + + return -EINPROGRESS; +} + +static int atmel_sha_xmit_start(struct atmel_sha_dev *dd, dma_addr_t dma_addr1, + size_t length1, dma_addr_t dma_addr2, size_t length2, int final) +{ + if (dd->caps.has_dma) + return atmel_sha_xmit_dma(dd, dma_addr1, length1, + dma_addr2, length2, final); + else + return atmel_sha_xmit_pdc(dd, dma_addr1, length1, + dma_addr2, length2, final); +} + static int atmel_sha_update_cpu(struct atmel_sha_dev *dd) { struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req); @@ -337,7 +492,6 @@ static int atmel_sha_update_cpu(struct atmel_sha_dev *dd) atmel_sha_append_sg(ctx); atmel_sha_fill_padding(ctx, 0); - bufcnt = ctx->bufcnt; ctx->bufcnt = 0; @@ -349,17 +503,17 @@ static int atmel_sha_xmit_dma_map(struct atmel_sha_dev *dd, size_t length, int final) { ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer, - ctx->buflen + SHA1_BLOCK_SIZE, DMA_TO_DEVICE); + ctx->buflen + ctx->block_size, DMA_TO_DEVICE); if (dma_mapping_error(dd->dev, ctx->dma_addr)) { dev_err(dd->dev, "dma %u bytes error\n", ctx->buflen + - SHA1_BLOCK_SIZE); + ctx->block_size); return -EINVAL; } ctx->flags &= ~SHA_FLAGS_SG; /* next call does not fail... so no unmap in the case of error */ - return atmel_sha_xmit_pdc(dd, ctx->dma_addr, length, 0, 0, final); + return atmel_sha_xmit_start(dd, ctx->dma_addr, length, 0, 0, final); } static int atmel_sha_update_dma_slow(struct atmel_sha_dev *dd) @@ -372,8 +526,8 @@ static int atmel_sha_update_dma_slow(struct atmel_sha_dev *dd) final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total; - dev_dbg(dd->dev, "slow: bufcnt: %u, digcnt: %d, final: %d\n", - ctx->bufcnt, ctx->digcnt, final); + dev_dbg(dd->dev, "slow: bufcnt: %u, digcnt: 0x%llx 0x%llx, final: %d\n", + ctx->bufcnt, ctx->digcnt[1], ctx->digcnt[0], final); if (final) atmel_sha_fill_padding(ctx, 0); @@ -400,30 +554,25 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) if (ctx->bufcnt || ctx->offset) return atmel_sha_update_dma_slow(dd); - dev_dbg(dd->dev, "fast: digcnt: %d, bufcnt: %u, total: %u\n", - ctx->digcnt, ctx->bufcnt, ctx->total); + dev_dbg(dd->dev, "fast: digcnt: 0x%llx 0x%llx, bufcnt: %u, total: %u\n", + ctx->digcnt[1], ctx->digcnt[0], ctx->bufcnt, ctx->total); sg = ctx->sg; if (!IS_ALIGNED(sg->offset, sizeof(u32))) return atmel_sha_update_dma_slow(dd); - if (!sg_is_last(sg) && !IS_ALIGNED(sg->length, SHA1_BLOCK_SIZE)) - /* size is not SHA1_BLOCK_SIZE aligned */ + if (!sg_is_last(sg) && !IS_ALIGNED(sg->length, ctx->block_size)) + /* size is not ctx->block_size aligned */ return atmel_sha_update_dma_slow(dd); length = min(ctx->total, sg->length); if (sg_is_last(sg)) { if (!(ctx->flags & SHA_FLAGS_FINUP)) { - /* not last sg must be SHA1_BLOCK_SIZE aligned */ - tail = length & (SHA1_BLOCK_SIZE - 1); + /* not last sg must be ctx->block_size aligned */ + tail = length & (ctx->block_size - 1); length -= tail; - if (length == 0) { - /* offset where to start slow */ - ctx->offset = length; - return atmel_sha_update_dma_slow(dd); - } } } @@ -434,7 +583,7 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) /* Add padding */ if (final) { - tail = length & (SHA1_BLOCK_SIZE - 1); + tail = length & (ctx->block_size - 1); length -= tail; ctx->total += tail; ctx->offset = length; /* offset where to start slow */ @@ -445,10 +594,10 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) atmel_sha_fill_padding(ctx, length); ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer, - ctx->buflen + SHA1_BLOCK_SIZE, DMA_TO_DEVICE); + ctx->buflen + ctx->block_size, DMA_TO_DEVICE); if (dma_mapping_error(dd->dev, ctx->dma_addr)) { dev_err(dd->dev, "dma %u bytes error\n", - ctx->buflen + SHA1_BLOCK_SIZE); + ctx->buflen + ctx->block_size); return -EINVAL; } @@ -456,7 +605,7 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) ctx->flags &= ~SHA_FLAGS_SG; count = ctx->bufcnt; ctx->bufcnt = 0; - return atmel_sha_xmit_pdc(dd, ctx->dma_addr, count, 0, + return atmel_sha_xmit_start(dd, ctx->dma_addr, count, 0, 0, final); } else { ctx->sg = sg; @@ -470,7 +619,7 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) count = ctx->bufcnt; ctx->bufcnt = 0; - return atmel_sha_xmit_pdc(dd, sg_dma_address(ctx->sg), + return atmel_sha_xmit_start(dd, sg_dma_address(ctx->sg), length, ctx->dma_addr, count, final); } } @@ -483,7 +632,7 @@ static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd) ctx->flags |= SHA_FLAGS_SG; /* next call does not fail... so no unmap in the case of error */ - return atmel_sha_xmit_pdc(dd, sg_dma_address(ctx->sg), length, 0, + return atmel_sha_xmit_start(dd, sg_dma_address(ctx->sg), length, 0, 0, final); } @@ -498,12 +647,13 @@ static int atmel_sha_update_dma_stop(struct atmel_sha_dev *dd) if (ctx->sg) ctx->offset = 0; } - if (ctx->flags & SHA_FLAGS_PAD) + if (ctx->flags & SHA_FLAGS_PAD) { dma_unmap_single(dd->dev, ctx->dma_addr, - ctx->buflen + SHA1_BLOCK_SIZE, DMA_TO_DEVICE); + ctx->buflen + ctx->block_size, DMA_TO_DEVICE); + } } else { dma_unmap_single(dd->dev, ctx->dma_addr, ctx->buflen + - SHA1_BLOCK_SIZE, DMA_TO_DEVICE); + ctx->block_size, DMA_TO_DEVICE); } return 0; @@ -515,8 +665,8 @@ static int atmel_sha_update_req(struct atmel_sha_dev *dd) struct atmel_sha_reqctx *ctx = ahash_request_ctx(req); int err; - dev_dbg(dd->dev, "update_req: total: %u, digcnt: %d, finup: %d\n", - ctx->total, ctx->digcnt, (ctx->flags & SHA_FLAGS_FINUP) != 0); + dev_dbg(dd->dev, "update_req: total: %u, digcnt: 0x%llx 0x%llx\n", + ctx->total, ctx->digcnt[1], ctx->digcnt[0]); if (ctx->flags & SHA_FLAGS_CPU) err = atmel_sha_update_cpu(dd); @@ -524,8 +674,8 @@ static int atmel_sha_update_req(struct atmel_sha_dev *dd) err = atmel_sha_update_dma_start(dd); /* wait for dma completion before can take more data */ - dev_dbg(dd->dev, "update: err: %d, digcnt: %d\n", - err, ctx->digcnt); + dev_dbg(dd->dev, "update: err: %d, digcnt: 0x%llx 0%llx\n", + err, ctx->digcnt[1], ctx->digcnt[0]); return err; } @@ -562,12 +712,21 @@ static void atmel_sha_copy_hash(struct ahash_request *req) u32 *hash = (u32 *)ctx->digest; int i; - if (likely(ctx->flags & SHA_FLAGS_SHA1)) + if (ctx->flags & SHA_FLAGS_SHA1) for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i)); - else + else if (ctx->flags & SHA_FLAGS_SHA224) + for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(u32); i++) + hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i)); + else if (ctx->flags & SHA_FLAGS_SHA256) for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(u32); i++) hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i)); + else if (ctx->flags & SHA_FLAGS_SHA384) + for (i = 0; i < SHA384_DIGEST_SIZE / sizeof(u32); i++) + hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i)); + else + for (i = 0; i < SHA512_DIGEST_SIZE / sizeof(u32); i++) + hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i)); } static void atmel_sha_copy_ready_hash(struct ahash_request *req) @@ -577,10 +736,16 @@ static void atmel_sha_copy_ready_hash(struct ahash_request *req) if (!req->result) return; - if (likely(ctx->flags & SHA_FLAGS_SHA1)) + if (ctx->flags & SHA_FLAGS_SHA1) memcpy(req->result, ctx->digest, SHA1_DIGEST_SIZE); - else + else if (ctx->flags & SHA_FLAGS_SHA224) + memcpy(req->result, ctx->digest, SHA224_DIGEST_SIZE); + else if (ctx->flags & SHA_FLAGS_SHA256) memcpy(req->result, ctx->digest, SHA256_DIGEST_SIZE); + else if (ctx->flags & SHA_FLAGS_SHA384) + memcpy(req->result, ctx->digest, SHA384_DIGEST_SIZE); + else + memcpy(req->result, ctx->digest, SHA512_DIGEST_SIZE); } static int atmel_sha_finish(struct ahash_request *req) @@ -589,11 +754,11 @@ static int atmel_sha_finish(struct ahash_request *req) struct atmel_sha_dev *dd = ctx->dd; int err = 0; - if (ctx->digcnt) + if (ctx->digcnt[0] || ctx->digcnt[1]) atmel_sha_copy_ready_hash(req); - dev_dbg(dd->dev, "digcnt: %d, bufcnt: %d\n", ctx->digcnt, - ctx->bufcnt); + dev_dbg(dd->dev, "digcnt: 0x%llx 0x%llx, bufcnt: %d\n", ctx->digcnt[1], + ctx->digcnt[0], ctx->bufcnt); return err; } @@ -628,9 +793,8 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd) { clk_prepare_enable(dd->iclk); - if (SHA_FLAGS_INIT & dd->flags) { + if (!(SHA_FLAGS_INIT & dd->flags)) { atmel_sha_write(dd, SHA_CR, SHA_CR_SWRST); - atmel_sha_dualbuff_test(dd); dd->flags |= SHA_FLAGS_INIT; dd->err = 0; } @@ -638,6 +802,23 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd) return 0; } +static inline unsigned int atmel_sha_get_version(struct atmel_sha_dev *dd) +{ + return atmel_sha_read(dd, SHA_HW_VERSION) & 0x00000fff; +} + +static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd) +{ + atmel_sha_hw_init(dd); + + dd->hw_version = atmel_sha_get_version(dd); + + dev_info(dd->dev, + "version: 0x%x\n", dd->hw_version); + + clk_disable_unprepare(dd->iclk); +} + static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, struct ahash_request *req) { @@ -682,10 +863,9 @@ static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, if (ctx->op == SHA_OP_UPDATE) { err = atmel_sha_update_req(dd); - if (err != -EINPROGRESS && (ctx->flags & SHA_FLAGS_FINUP)) { + if (err != -EINPROGRESS && (ctx->flags & SHA_FLAGS_FINUP)) /* no final() after finup() */ err = atmel_sha_final_req(dd); - } } else if (ctx->op == SHA_OP_FINAL) { err = atmel_sha_final_req(dd); } @@ -808,7 +988,7 @@ static int atmel_sha_cra_init_alg(struct crypto_tfm *tfm, const char *alg_base) } crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), sizeof(struct atmel_sha_reqctx) + - SHA_BUFFER_LEN + SHA256_BLOCK_SIZE); + SHA_BUFFER_LEN + SHA512_BLOCK_SIZE); return 0; } @@ -826,7 +1006,7 @@ static void atmel_sha_cra_exit(struct crypto_tfm *tfm) tctx->fallback = NULL; } -static struct ahash_alg sha_algs[] = { +static struct ahash_alg sha_1_256_algs[] = { { .init = atmel_sha_init, .update = atmel_sha_update, @@ -875,6 +1055,79 @@ static struct ahash_alg sha_algs[] = { }, }; +static struct ahash_alg sha_224_alg = { + .init = atmel_sha_init, + .update = atmel_sha_update, + .final = atmel_sha_final, + .finup = atmel_sha_finup, + .digest = atmel_sha_digest, + .halg = { + .digestsize = SHA224_DIGEST_SIZE, + .base = { + .cra_name = "sha224", + .cra_driver_name = "atmel-sha224", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct atmel_sha_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_init = atmel_sha_cra_init, + .cra_exit = atmel_sha_cra_exit, + } + } +}; + +static struct ahash_alg sha_384_512_algs[] = { +{ + .init = atmel_sha_init, + .update = atmel_sha_update, + .final = atmel_sha_final, + .finup = atmel_sha_finup, + .digest = atmel_sha_digest, + .halg = { + .digestsize = SHA384_DIGEST_SIZE, + .base = { + .cra_name = "sha384", + .cra_driver_name = "atmel-sha384", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct atmel_sha_ctx), + .cra_alignmask = 0x3, + .cra_module = THIS_MODULE, + .cra_init = atmel_sha_cra_init, + .cra_exit = atmel_sha_cra_exit, + } + } +}, +{ + .init = atmel_sha_init, + .update = atmel_sha_update, + .final = atmel_sha_final, + .finup = atmel_sha_finup, + .digest = atmel_sha_digest, + .halg = { + .digestsize = SHA512_DIGEST_SIZE, + .base = { + .cra_name = "sha512", + .cra_driver_name = "atmel-sha512", + .cra_priority = 100, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct atmel_sha_ctx), + .cra_alignmask = 0x3, + .cra_module = THIS_MODULE, + .cra_init = atmel_sha_cra_init, + .cra_exit = atmel_sha_cra_exit, + } + } +}, +}; + static void atmel_sha_done_task(unsigned long data) { struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data; @@ -941,32 +1194,142 @@ static void atmel_sha_unregister_algs(struct atmel_sha_dev *dd) { int i; - for (i = 0; i < ARRAY_SIZE(sha_algs); i++) - crypto_unregister_ahash(&sha_algs[i]); + for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++) + crypto_unregister_ahash(&sha_1_256_algs[i]); + + if (dd->caps.has_sha224) + crypto_unregister_ahash(&sha_224_alg); + + if (dd->caps.has_sha_384_512) { + for (i = 0; i < ARRAY_SIZE(sha_384_512_algs); i++) + crypto_unregister_ahash(&sha_384_512_algs[i]); + } } static int atmel_sha_register_algs(struct atmel_sha_dev *dd) { int err, i, j; - for (i = 0; i < ARRAY_SIZE(sha_algs); i++) { - err = crypto_register_ahash(&sha_algs[i]); + for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++) { + err = crypto_register_ahash(&sha_1_256_algs[i]); if (err) - goto err_sha_algs; + goto err_sha_1_256_algs; + } + + if (dd->caps.has_sha224) { + err = crypto_register_ahash(&sha_224_alg); + if (err) + goto err_sha_224_algs; + } + + if (dd->caps.has_sha_384_512) { + for (i = 0; i < ARRAY_SIZE(sha_384_512_algs); i++) { + err = crypto_register_ahash(&sha_384_512_algs[i]); + if (err) + goto err_sha_384_512_algs; + } } return 0; -err_sha_algs: +err_sha_384_512_algs: + for (j = 0; j < i; j++) + crypto_unregister_ahash(&sha_384_512_algs[j]); + crypto_unregister_ahash(&sha_224_alg); +err_sha_224_algs: + i = ARRAY_SIZE(sha_1_256_algs); +err_sha_1_256_algs: for (j = 0; j < i; j++) - crypto_unregister_ahash(&sha_algs[j]); + crypto_unregister_ahash(&sha_1_256_algs[j]); return err; } +static bool atmel_sha_filter(struct dma_chan *chan, void *slave) +{ + struct at_dma_slave *sl = slave; + + if (sl && sl->dma_dev == chan->device->dev) { + chan->private = sl; + return true; + } else { + return false; + } +} + +static int atmel_sha_dma_init(struct atmel_sha_dev *dd, + struct crypto_platform_data *pdata) +{ + int err = -ENOMEM; + dma_cap_mask_t mask_in; + + if (pdata && pdata->dma_slave->rxdata.dma_dev) { + /* Try to grab DMA channel */ + dma_cap_zero(mask_in); + dma_cap_set(DMA_SLAVE, mask_in); + + dd->dma_lch_in.chan = dma_request_channel(mask_in, + atmel_sha_filter, &pdata->dma_slave->rxdata); + + if (!dd->dma_lch_in.chan) + return err; + + dd->dma_lch_in.dma_conf.direction = DMA_MEM_TO_DEV; + dd->dma_lch_in.dma_conf.dst_addr = dd->phys_base + + SHA_REG_DIN(0); + dd->dma_lch_in.dma_conf.src_maxburst = 1; + dd->dma_lch_in.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_in.dma_conf.dst_maxburst = 1; + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_in.dma_conf.device_fc = false; + + return 0; + } + + return -ENODEV; +} + +static void atmel_sha_dma_cleanup(struct atmel_sha_dev *dd) +{ + dma_release_channel(dd->dma_lch_in.chan); +} + +static void atmel_sha_get_cap(struct atmel_sha_dev *dd) +{ + + dd->caps.has_dma = 0; + dd->caps.has_dualbuff = 0; + dd->caps.has_sha224 = 0; + dd->caps.has_sha_384_512 = 0; + + /* keep only major version number */ + switch (dd->hw_version & 0xff0) { + case 0x410: + dd->caps.has_dma = 1; + dd->caps.has_dualbuff = 1; + dd->caps.has_sha224 = 1; + dd->caps.has_sha_384_512 = 1; + break; + case 0x400: + dd->caps.has_dma = 1; + dd->caps.has_dualbuff = 1; + dd->caps.has_sha224 = 1; + break; + case 0x320: + break; + default: + dev_warn(dd->dev, + "Unmanaged sha version, set minimum capabilities\n"); + break; + } +} + static int atmel_sha_probe(struct platform_device *pdev) { struct atmel_sha_dev *sha_dd; + struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *sha_res; unsigned long sha_phys_size; @@ -1018,7 +1381,7 @@ static int atmel_sha_probe(struct platform_device *pdev) } /* Initializing the clock */ - sha_dd->iclk = clk_get(&pdev->dev, NULL); + sha_dd->iclk = clk_get(&pdev->dev, "sha_clk"); if (IS_ERR(sha_dd->iclk)) { dev_err(dev, "clock intialization failed.\n"); err = PTR_ERR(sha_dd->iclk); @@ -1032,6 +1395,22 @@ static int atmel_sha_probe(struct platform_device *pdev) goto sha_io_err; } + atmel_sha_hw_version_init(sha_dd); + + atmel_sha_get_cap(sha_dd); + + if (sha_dd->caps.has_dma) { + pdata = pdev->dev.platform_data; + if (!pdata) { + dev_err(&pdev->dev, "platform data not available\n"); + err = -ENXIO; + goto err_pdata; + } + err = atmel_sha_dma_init(sha_dd, pdata); + if (err) + goto err_sha_dma; + } + spin_lock(&atmel_sha.lock); list_add_tail(&sha_dd->list, &atmel_sha.dev_list); spin_unlock(&atmel_sha.lock); @@ -1048,6 +1427,10 @@ err_algs: spin_lock(&atmel_sha.lock); list_del(&sha_dd->list); spin_unlock(&atmel_sha.lock); + if (sha_dd->caps.has_dma) + atmel_sha_dma_cleanup(sha_dd); +err_sha_dma: +err_pdata: iounmap(sha_dd->io_base); sha_io_err: clk_put(sha_dd->iclk); @@ -1078,6 +1461,9 @@ static int atmel_sha_remove(struct platform_device *pdev) tasklet_kill(&sha_dd->done_task); + if (sha_dd->caps.has_dma) + atmel_sha_dma_cleanup(sha_dd); + iounmap(sha_dd->io_base); clk_put(sha_dd->iclk); @@ -1102,6 +1488,6 @@ static struct platform_driver atmel_sha_driver = { module_platform_driver(atmel_sha_driver); -MODULE_DESCRIPTION("Atmel SHA1/SHA256 hw acceleration support."); +MODULE_DESCRIPTION("Atmel SHA (1/256/224/384/512) hw acceleration support."); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Nicolas Royer - Eukréa Electromatique"); diff --git a/drivers/crypto/atmel-tdes-regs.h b/drivers/crypto/atmel-tdes-regs.h index 5ac2a900d80..f86734d0fda 100644 --- a/drivers/crypto/atmel-tdes-regs.h +++ b/drivers/crypto/atmel-tdes-regs.h @@ -69,6 +69,8 @@ #define TDES_XTEARNDR_XTEA_RNDS_MASK (0x3F << 0) #define TDES_XTEARNDR_XTEA_RNDS_OFFSET 0 +#define TDES_HW_VERSION 0xFC + #define TDES_RPR 0x100 #define TDES_RCR 0x104 #define TDES_TPR 0x108 diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 7c73fbb1753..4a99564a08e 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -38,29 +38,35 @@ #include <crypto/des.h> #include <crypto/hash.h> #include <crypto/internal/hash.h> +#include <linux/platform_data/crypto-atmel.h> #include "atmel-tdes-regs.h" /* TDES flags */ -#define TDES_FLAGS_MODE_MASK 0x007f +#define TDES_FLAGS_MODE_MASK 0x00ff #define TDES_FLAGS_ENCRYPT BIT(0) #define TDES_FLAGS_CBC BIT(1) #define TDES_FLAGS_CFB BIT(2) #define TDES_FLAGS_CFB8 BIT(3) #define TDES_FLAGS_CFB16 BIT(4) #define TDES_FLAGS_CFB32 BIT(5) -#define TDES_FLAGS_OFB BIT(6) +#define TDES_FLAGS_CFB64 BIT(6) +#define TDES_FLAGS_OFB BIT(7) #define TDES_FLAGS_INIT BIT(16) #define TDES_FLAGS_FAST BIT(17) #define TDES_FLAGS_BUSY BIT(18) +#define TDES_FLAGS_DMA BIT(19) -#define ATMEL_TDES_QUEUE_LENGTH 1 +#define ATMEL_TDES_QUEUE_LENGTH 50 #define CFB8_BLOCK_SIZE 1 #define CFB16_BLOCK_SIZE 2 #define CFB32_BLOCK_SIZE 4 -#define CFB64_BLOCK_SIZE 8 +struct atmel_tdes_caps { + bool has_dma; + u32 has_cfb_3keys; +}; struct atmel_tdes_dev; @@ -70,12 +76,19 @@ struct atmel_tdes_ctx { int keylen; u32 key[3*DES_KEY_SIZE / sizeof(u32)]; unsigned long flags; + + u16 block_size; }; struct atmel_tdes_reqctx { unsigned long mode; }; +struct atmel_tdes_dma { + struct dma_chan *chan; + struct dma_slave_config dma_conf; +}; + struct atmel_tdes_dev { struct list_head list; unsigned long phys_base; @@ -99,8 +112,10 @@ struct atmel_tdes_dev { size_t total; struct scatterlist *in_sg; + unsigned int nb_in_sg; size_t in_offset; struct scatterlist *out_sg; + unsigned int nb_out_sg; size_t out_offset; size_t buflen; @@ -109,10 +124,16 @@ struct atmel_tdes_dev { void *buf_in; int dma_in; dma_addr_t dma_addr_in; + struct atmel_tdes_dma dma_lch_in; void *buf_out; int dma_out; dma_addr_t dma_addr_out; + struct atmel_tdes_dma dma_lch_out; + + struct atmel_tdes_caps caps; + + u32 hw_version; }; struct atmel_tdes_drv { @@ -207,6 +228,31 @@ static int atmel_tdes_hw_init(struct atmel_tdes_dev *dd) return 0; } +static inline unsigned int atmel_tdes_get_version(struct atmel_tdes_dev *dd) +{ + return atmel_tdes_read(dd, TDES_HW_VERSION) & 0x00000fff; +} + +static void atmel_tdes_hw_version_init(struct atmel_tdes_dev *dd) +{ + atmel_tdes_hw_init(dd); + + dd->hw_version = atmel_tdes_get_version(dd); + + dev_info(dd->dev, + "version: 0x%x\n", dd->hw_version); + + clk_disable_unprepare(dd->iclk); +} + +static void atmel_tdes_dma_callback(void *data) +{ + struct atmel_tdes_dev *dd = data; + + /* dma_lch_out - completed */ + tasklet_schedule(&dd->done_task); +} + static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd) { int err; @@ -217,7 +263,9 @@ static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd) if (err) return err; - atmel_tdes_write(dd, TDES_PTCR, TDES_PTCR_TXTDIS|TDES_PTCR_RXTDIS); + if (!dd->caps.has_dma) + atmel_tdes_write(dd, TDES_PTCR, + TDES_PTCR_TXTDIS | TDES_PTCR_RXTDIS); /* MR register must be set before IV registers */ if (dd->ctx->keylen > (DES_KEY_SIZE << 1)) { @@ -241,6 +289,8 @@ static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd) valmr |= TDES_MR_CFBS_16b; else if (dd->flags & TDES_FLAGS_CFB32) valmr |= TDES_MR_CFBS_32b; + else if (dd->flags & TDES_FLAGS_CFB64) + valmr |= TDES_MR_CFBS_64b; } else if (dd->flags & TDES_FLAGS_OFB) { valmr |= TDES_MR_OPMOD_OFB; } @@ -262,7 +312,7 @@ static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd) return 0; } -static int atmel_tdes_crypt_dma_stop(struct atmel_tdes_dev *dd) +static int atmel_tdes_crypt_pdc_stop(struct atmel_tdes_dev *dd) { int err = 0; size_t count; @@ -288,7 +338,7 @@ static int atmel_tdes_crypt_dma_stop(struct atmel_tdes_dev *dd) return err; } -static int atmel_tdes_dma_init(struct atmel_tdes_dev *dd) +static int atmel_tdes_buff_init(struct atmel_tdes_dev *dd) { int err = -ENOMEM; @@ -333,7 +383,7 @@ err_alloc: return err; } -static void atmel_tdes_dma_cleanup(struct atmel_tdes_dev *dd) +static void atmel_tdes_buff_cleanup(struct atmel_tdes_dev *dd) { dma_unmap_single(dd->dev, dd->dma_addr_out, dd->buflen, DMA_FROM_DEVICE); @@ -343,7 +393,7 @@ static void atmel_tdes_dma_cleanup(struct atmel_tdes_dev *dd) free_page((unsigned long)dd->buf_in); } -static int atmel_tdes_crypt_dma(struct crypto_tfm *tfm, dma_addr_t dma_addr_in, +static int atmel_tdes_crypt_pdc(struct crypto_tfm *tfm, dma_addr_t dma_addr_in, dma_addr_t dma_addr_out, int length) { struct atmel_tdes_ctx *ctx = crypto_tfm_ctx(tfm); @@ -379,7 +429,76 @@ static int atmel_tdes_crypt_dma(struct crypto_tfm *tfm, dma_addr_t dma_addr_in, return 0; } -static int atmel_tdes_crypt_dma_start(struct atmel_tdes_dev *dd) +static int atmel_tdes_crypt_dma(struct crypto_tfm *tfm, dma_addr_t dma_addr_in, + dma_addr_t dma_addr_out, int length) +{ + struct atmel_tdes_ctx *ctx = crypto_tfm_ctx(tfm); + struct atmel_tdes_dev *dd = ctx->dd; + struct scatterlist sg[2]; + struct dma_async_tx_descriptor *in_desc, *out_desc; + + dd->dma_size = length; + + if (!(dd->flags & TDES_FLAGS_FAST)) { + dma_sync_single_for_device(dd->dev, dma_addr_in, length, + DMA_TO_DEVICE); + } + + if (dd->flags & TDES_FLAGS_CFB8) { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_1_BYTE; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_1_BYTE; + } else if (dd->flags & TDES_FLAGS_CFB16) { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_2_BYTES; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_2_BYTES; + } else { + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + } + + dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf); + dmaengine_slave_config(dd->dma_lch_out.chan, &dd->dma_lch_out.dma_conf); + + dd->flags |= TDES_FLAGS_DMA; + + sg_init_table(&sg[0], 1); + sg_dma_address(&sg[0]) = dma_addr_in; + sg_dma_len(&sg[0]) = length; + + sg_init_table(&sg[1], 1); + sg_dma_address(&sg[1]) = dma_addr_out; + sg_dma_len(&sg[1]) = length; + + in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, &sg[0], + 1, DMA_MEM_TO_DEV, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!in_desc) + return -EINVAL; + + out_desc = dmaengine_prep_slave_sg(dd->dma_lch_out.chan, &sg[1], + 1, DMA_DEV_TO_MEM, + DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + if (!out_desc) + return -EINVAL; + + out_desc->callback = atmel_tdes_dma_callback; + out_desc->callback_param = dd; + + dmaengine_submit(out_desc); + dma_async_issue_pending(dd->dma_lch_out.chan); + + dmaengine_submit(in_desc); + dma_async_issue_pending(dd->dma_lch_in.chan); + + return 0; +} + +static int atmel_tdes_crypt_start(struct atmel_tdes_dev *dd) { struct crypto_tfm *tfm = crypto_ablkcipher_tfm( crypto_ablkcipher_reqtfm(dd->req)); @@ -387,23 +506,23 @@ static int atmel_tdes_crypt_dma_start(struct atmel_tdes_dev *dd) size_t count; dma_addr_t addr_in, addr_out; - if (sg_is_last(dd->in_sg) && sg_is_last(dd->out_sg)) { + if ((!dd->in_offset) && (!dd->out_offset)) { /* check for alignment */ - in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32)); - out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32)); - + in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32)) && + IS_ALIGNED(dd->in_sg->length, dd->ctx->block_size); + out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32)) && + IS_ALIGNED(dd->out_sg->length, dd->ctx->block_size); fast = in && out; + + if (sg_dma_len(dd->in_sg) != sg_dma_len(dd->out_sg)) + fast = 0; } + if (fast) { count = min(dd->total, sg_dma_len(dd->in_sg)); count = min(count, sg_dma_len(dd->out_sg)); - if (count != dd->total) { - pr_err("request length != buffer length\n"); - return -EINVAL; - } - err = dma_map_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); if (!err) { dev_err(dd->dev, "dma_map_sg() error\n"); @@ -433,13 +552,16 @@ static int atmel_tdes_crypt_dma_start(struct atmel_tdes_dev *dd) addr_out = dd->dma_addr_out; dd->flags &= ~TDES_FLAGS_FAST; - } dd->total -= count; - err = atmel_tdes_crypt_dma(tfm, addr_in, addr_out, count); - if (err) { + if (dd->caps.has_dma) + err = atmel_tdes_crypt_dma(tfm, addr_in, addr_out, count); + else + err = atmel_tdes_crypt_pdc(tfm, addr_in, addr_out, count); + + if (err && (dd->flags & TDES_FLAGS_FAST)) { dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_TO_DEVICE); } @@ -447,7 +569,6 @@ static int atmel_tdes_crypt_dma_start(struct atmel_tdes_dev *dd) return err; } - static void atmel_tdes_finish_req(struct atmel_tdes_dev *dd, int err) { struct ablkcipher_request *req = dd->req; @@ -506,7 +627,7 @@ static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd, err = atmel_tdes_write_ctrl(dd); if (!err) - err = atmel_tdes_crypt_dma_start(dd); + err = atmel_tdes_crypt_start(dd); if (err) { /* des_task will not finish it, so do it here */ atmel_tdes_finish_req(dd, err); @@ -516,41 +637,145 @@ static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd, return ret; } +static int atmel_tdes_crypt_dma_stop(struct atmel_tdes_dev *dd) +{ + int err = -EINVAL; + size_t count; + + if (dd->flags & TDES_FLAGS_DMA) { + err = 0; + if (dd->flags & TDES_FLAGS_FAST) { + dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_FROM_DEVICE); + dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); + } else { + dma_sync_single_for_device(dd->dev, dd->dma_addr_out, + dd->dma_size, DMA_FROM_DEVICE); + + /* copy data */ + count = atmel_tdes_sg_copy(&dd->out_sg, &dd->out_offset, + dd->buf_out, dd->buflen, dd->dma_size, 1); + if (count != dd->dma_size) { + err = -EINVAL; + pr_err("not all data converted: %u\n", count); + } + } + } + return err; +} static int atmel_tdes_crypt(struct ablkcipher_request *req, unsigned long mode) { struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx( crypto_ablkcipher_reqtfm(req)); struct atmel_tdes_reqctx *rctx = ablkcipher_request_ctx(req); - struct atmel_tdes_dev *dd; if (mode & TDES_FLAGS_CFB8) { if (!IS_ALIGNED(req->nbytes, CFB8_BLOCK_SIZE)) { pr_err("request size is not exact amount of CFB8 blocks\n"); return -EINVAL; } + ctx->block_size = CFB8_BLOCK_SIZE; } else if (mode & TDES_FLAGS_CFB16) { if (!IS_ALIGNED(req->nbytes, CFB16_BLOCK_SIZE)) { pr_err("request size is not exact amount of CFB16 blocks\n"); return -EINVAL; } + ctx->block_size = CFB16_BLOCK_SIZE; } else if (mode & TDES_FLAGS_CFB32) { if (!IS_ALIGNED(req->nbytes, CFB32_BLOCK_SIZE)) { pr_err("request size is not exact amount of CFB32 blocks\n"); return -EINVAL; } - } else if (!IS_ALIGNED(req->nbytes, DES_BLOCK_SIZE)) { - pr_err("request size is not exact amount of DES blocks\n"); - return -EINVAL; + ctx->block_size = CFB32_BLOCK_SIZE; + } else { + if (!IS_ALIGNED(req->nbytes, DES_BLOCK_SIZE)) { + pr_err("request size is not exact amount of DES blocks\n"); + return -EINVAL; + } + ctx->block_size = DES_BLOCK_SIZE; } - dd = atmel_tdes_find_dev(ctx); - if (!dd) + rctx->mode = mode; + + return atmel_tdes_handle_queue(ctx->dd, req); +} + +static bool atmel_tdes_filter(struct dma_chan *chan, void *slave) +{ + struct at_dma_slave *sl = slave; + + if (sl && sl->dma_dev == chan->device->dev) { + chan->private = sl; + return true; + } else { + return false; + } +} + +static int atmel_tdes_dma_init(struct atmel_tdes_dev *dd, + struct crypto_platform_data *pdata) +{ + int err = -ENOMEM; + dma_cap_mask_t mask_in, mask_out; + + if (pdata && pdata->dma_slave->txdata.dma_dev && + pdata->dma_slave->rxdata.dma_dev) { + + /* Try to grab 2 DMA channels */ + dma_cap_zero(mask_in); + dma_cap_set(DMA_SLAVE, mask_in); + + dd->dma_lch_in.chan = dma_request_channel(mask_in, + atmel_tdes_filter, &pdata->dma_slave->rxdata); + + if (!dd->dma_lch_in.chan) + goto err_dma_in; + + dd->dma_lch_in.dma_conf.direction = DMA_MEM_TO_DEV; + dd->dma_lch_in.dma_conf.dst_addr = dd->phys_base + + TDES_IDATA1R; + dd->dma_lch_in.dma_conf.src_maxburst = 1; + dd->dma_lch_in.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_in.dma_conf.dst_maxburst = 1; + dd->dma_lch_in.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_in.dma_conf.device_fc = false; + + dma_cap_zero(mask_out); + dma_cap_set(DMA_SLAVE, mask_out); + dd->dma_lch_out.chan = dma_request_channel(mask_out, + atmel_tdes_filter, &pdata->dma_slave->txdata); + + if (!dd->dma_lch_out.chan) + goto err_dma_out; + + dd->dma_lch_out.dma_conf.direction = DMA_DEV_TO_MEM; + dd->dma_lch_out.dma_conf.src_addr = dd->phys_base + + TDES_ODATA1R; + dd->dma_lch_out.dma_conf.src_maxburst = 1; + dd->dma_lch_out.dma_conf.src_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_out.dma_conf.dst_maxburst = 1; + dd->dma_lch_out.dma_conf.dst_addr_width = + DMA_SLAVE_BUSWIDTH_4_BYTES; + dd->dma_lch_out.dma_conf.device_fc = false; + + return 0; + } else { return -ENODEV; + } - rctx->mode = mode; +err_dma_out: + dma_release_channel(dd->dma_lch_in.chan); +err_dma_in: + return err; +} - return atmel_tdes_handle_queue(dd, req); +static void atmel_tdes_dma_cleanup(struct atmel_tdes_dev *dd) +{ + dma_release_channel(dd->dma_lch_in.chan); + dma_release_channel(dd->dma_lch_out.chan); } static int atmel_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key, @@ -590,7 +815,8 @@ static int atmel_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key, /* * HW bug in cfb 3-keys mode. */ - if (strstr(alg_name, "cfb") && (keylen != 2*DES_KEY_SIZE)) { + if (!ctx->dd->caps.has_cfb_3keys && strstr(alg_name, "cfb") + && (keylen != 2*DES_KEY_SIZE)) { crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } else if ((keylen != 2*DES_KEY_SIZE) && (keylen != 3*DES_KEY_SIZE)) { @@ -678,8 +904,15 @@ static int atmel_tdes_ofb_decrypt(struct ablkcipher_request *req) static int atmel_tdes_cra_init(struct crypto_tfm *tfm) { + struct atmel_tdes_ctx *ctx = crypto_tfm_ctx(tfm); + struct atmel_tdes_dev *dd; + tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_tdes_reqctx); + dd = atmel_tdes_find_dev(ctx); + if (!dd) + return -ENODEV; + return 0; } @@ -695,7 +928,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -715,7 +948,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -736,7 +969,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -778,7 +1011,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB16_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x1, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -799,7 +1032,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x3, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -820,7 +1053,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -841,7 +1074,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -861,7 +1094,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -882,7 +1115,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -924,7 +1157,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB16_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x1, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -945,7 +1178,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = CFB32_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x3, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -966,7 +1199,7 @@ static struct crypto_alg tdes_algs[] = { .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC, .cra_blocksize = DES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct atmel_tdes_ctx), - .cra_alignmask = 0, + .cra_alignmask = 0x7, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, .cra_init = atmel_tdes_cra_init, @@ -994,14 +1227,24 @@ static void atmel_tdes_done_task(unsigned long data) struct atmel_tdes_dev *dd = (struct atmel_tdes_dev *) data; int err; - err = atmel_tdes_crypt_dma_stop(dd); + if (!(dd->flags & TDES_FLAGS_DMA)) + err = atmel_tdes_crypt_pdc_stop(dd); + else + err = atmel_tdes_crypt_dma_stop(dd); err = dd->err ? : err; if (dd->total && !err) { - err = atmel_tdes_crypt_dma_start(dd); + if (dd->flags & TDES_FLAGS_FAST) { + dd->in_sg = sg_next(dd->in_sg); + dd->out_sg = sg_next(dd->out_sg); + if (!dd->in_sg || !dd->out_sg) + err = -EINVAL; + } if (!err) - return; + err = atmel_tdes_crypt_start(dd); + if (!err) + return; /* DMA started. Not fininishing. */ } atmel_tdes_finish_req(dd, err); @@ -1053,9 +1296,31 @@ err_tdes_algs: return err; } +static void atmel_tdes_get_cap(struct atmel_tdes_dev *dd) +{ + + dd->caps.has_dma = 0; + dd->caps.has_cfb_3keys = 0; + + /* keep only major version number */ + switch (dd->hw_version & 0xf00) { + case 0x700: + dd->caps.has_dma = 1; + dd->caps.has_cfb_3keys = 1; + break; + case 0x600: + break; + default: + dev_warn(dd->dev, + "Unmanaged tdes version, set minimum capabilities\n"); + break; + } +} + static int atmel_tdes_probe(struct platform_device *pdev) { struct atmel_tdes_dev *tdes_dd; + struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *tdes_res; unsigned long tdes_phys_size; @@ -1109,7 +1374,7 @@ static int atmel_tdes_probe(struct platform_device *pdev) } /* Initializing the clock */ - tdes_dd->iclk = clk_get(&pdev->dev, NULL); + tdes_dd->iclk = clk_get(&pdev->dev, "tdes_clk"); if (IS_ERR(tdes_dd->iclk)) { dev_err(dev, "clock intialization failed.\n"); err = PTR_ERR(tdes_dd->iclk); @@ -1123,9 +1388,25 @@ static int atmel_tdes_probe(struct platform_device *pdev) goto tdes_io_err; } - err = atmel_tdes_dma_init(tdes_dd); + atmel_tdes_hw_version_init(tdes_dd); + + atmel_tdes_get_cap(tdes_dd); + + err = atmel_tdes_buff_init(tdes_dd); if (err) - goto err_tdes_dma; + goto err_tdes_buff; + + if (tdes_dd->caps.has_dma) { + pdata = pdev->dev.platform_data; + if (!pdata) { + dev_err(&pdev->dev, "platform data not available\n"); + err = -ENXIO; + goto err_pdata; + } + err = atmel_tdes_dma_init(tdes_dd, pdata); + if (err) + goto err_tdes_dma; + } spin_lock(&atmel_tdes.lock); list_add_tail(&tdes_dd->list, &atmel_tdes.dev_list); @@ -1143,8 +1424,12 @@ err_algs: spin_lock(&atmel_tdes.lock); list_del(&tdes_dd->list); spin_unlock(&atmel_tdes.lock); - atmel_tdes_dma_cleanup(tdes_dd); + if (tdes_dd->caps.has_dma) + atmel_tdes_dma_cleanup(tdes_dd); err_tdes_dma: +err_pdata: + atmel_tdes_buff_cleanup(tdes_dd); +err_tdes_buff: iounmap(tdes_dd->io_base); tdes_io_err: clk_put(tdes_dd->iclk); @@ -1178,7 +1463,10 @@ static int atmel_tdes_remove(struct platform_device *pdev) tasklet_kill(&tdes_dd->done_task); tasklet_kill(&tdes_dd->queue_task); - atmel_tdes_dma_cleanup(tdes_dd); + if (tdes_dd->caps.has_dma) + atmel_tdes_dma_cleanup(tdes_dd); + + atmel_tdes_buff_cleanup(tdes_dd); iounmap(tdes_dd->io_base); diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c index 827913d7d33..d797f31f5d8 100644 --- a/drivers/crypto/bfin_crc.c +++ b/drivers/crypto/bfin_crc.c @@ -151,7 +151,7 @@ static int bfin_crypto_crc_init(struct ahash_request *req) struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req); struct bfin_crypto_crc *crc; - dev_dbg(crc->dev, "crc_init\n"); + dev_dbg(ctx->crc->dev, "crc_init\n"); spin_lock_bh(&crc_list.lock); list_for_each_entry(crc, &crc_list.dev_list, list) { crc_ctx->crc = crc; @@ -160,7 +160,7 @@ static int bfin_crypto_crc_init(struct ahash_request *req) spin_unlock_bh(&crc_list.lock); if (sg_count(req->src) > CRC_MAX_DMA_DESC) { - dev_dbg(crc->dev, "init: requested sg list is too big > %d\n", + dev_dbg(ctx->crc->dev, "init: requested sg list is too big > %d\n", CRC_MAX_DMA_DESC); return -EINVAL; } @@ -175,7 +175,7 @@ static int bfin_crypto_crc_init(struct ahash_request *req) /* init crc results */ put_unaligned_le32(crc_ctx->key, req->result); - dev_dbg(crc->dev, "init: digest size: %d\n", + dev_dbg(ctx->crc->dev, "init: digest size: %d\n", crypto_ahash_digestsize(tfm)); return bfin_crypto_crc_init_hw(crc, crc_ctx->key); diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig index 65c7668614a..b44091c47f7 100644 --- a/drivers/crypto/caam/Kconfig +++ b/drivers/crypto/caam/Kconfig @@ -78,7 +78,7 @@ config CRYPTO_DEV_FSL_CAAM_AHASH_API tristate "Register hash algorithm implementations with Crypto API" depends on CRYPTO_DEV_FSL_CAAM default y - select CRYPTO_AHASH + select CRYPTO_HASH help Selecting this will offload ahash for users of the scatterlist crypto API to the SEC4 via job ring. diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index cf268b14ae9..765fdf5ce57 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -1693,6 +1693,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha224),cbc(aes))", .driver_name = "authenc-hmac-sha224-cbc-aes-caam", .blocksize = AES_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, @@ -1732,6 +1733,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha384),cbc(aes))", .driver_name = "authenc-hmac-sha384-cbc-aes-caam", .blocksize = AES_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, @@ -1810,6 +1812,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha224),cbc(des3_ede))", .driver_name = "authenc-hmac-sha224-cbc-des3_ede-caam", .blocksize = DES3_EDE_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, @@ -1849,6 +1852,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha384),cbc(des3_ede))", .driver_name = "authenc-hmac-sha384-cbc-des3_ede-caam", .blocksize = DES3_EDE_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, @@ -1926,6 +1930,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha224),cbc(des))", .driver_name = "authenc-hmac-sha224-cbc-des-caam", .blocksize = DES_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, @@ -1965,6 +1970,7 @@ static struct caam_alg_template driver_algs[] = { .name = "authenc(hmac(sha384),cbc(des))", .driver_name = "authenc-hmac-sha384-cbc-des-caam", .blocksize = DES_BLOCK_SIZE, + .type = CRYPTO_ALG_TYPE_AEAD, .template_aead = { .setkey = aead_setkey, .setauthsize = aead_setauthsize, diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 32aba7a6150..5996521a1ca 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -411,7 +411,7 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash) return 0; } -static u32 gen_split_hash_key(struct caam_hash_ctx *ctx, const u8 *key_in, +static int gen_split_hash_key(struct caam_hash_ctx *ctx, const u8 *key_in, u32 keylen) { return gen_split_key(ctx->jrdev, ctx->key, ctx->split_key_len, @@ -420,7 +420,7 @@ static u32 gen_split_hash_key(struct caam_hash_ctx *ctx, const u8 *key_in, } /* Digest hash size if it is too large */ -static u32 hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in, +static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in, u32 *keylen, u8 *key_out, u32 digestsize) { struct device *jrdev = ctx->jrdev; diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8acf00490fd..6e94bcd9467 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -304,6 +304,9 @@ static int caam_probe(struct platform_device *pdev) caam_remove(pdev); return ret; } + + /* Enable RDB bit so that RNG works faster */ + setbits32(&topregs->ctrl.scfgr, SCFGR_RDBENABLE); } /* NOTE: RTIC detection ought to go here, around Si time */ diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c index 30b8f74833d..9f25f529602 100644 --- a/drivers/crypto/caam/error.c +++ b/drivers/crypto/caam/error.c @@ -36,7 +36,7 @@ static void report_jump_idx(u32 status, char *outstr) static void report_ccb_status(u32 status, char *outstr) { - char *cha_id_list[] = { + static const char * const cha_id_list[] = { "", "AES", "DES", @@ -51,7 +51,7 @@ static void report_ccb_status(u32 status, char *outstr) "ZUCE", "ZUCA", }; - char *err_id_list[] = { + static const char * const err_id_list[] = { "No error.", "Mode error.", "Data size error.", @@ -69,7 +69,7 @@ static void report_ccb_status(u32 status, char *outstr) "Invalid CHA combination was selected", "Invalid CHA selected.", }; - char *rng_err_id_list[] = { + static const char * const rng_err_id_list[] = { "", "", "", @@ -117,7 +117,7 @@ static void report_jump_status(u32 status, char *outstr) static void report_deco_status(u32 status, char *outstr) { - const struct { + static const struct { u8 value; char *error_text; } desc_error_list[] = { @@ -245,7 +245,7 @@ static void report_cond_code_status(u32 status, char *outstr) char *caam_jr_strstatus(char *outstr, u32 status) { - struct stat_src { + static const struct stat_src { void (*report_ssed)(u32 status, char *outstr); char *error; } status_src[] = { diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h index 5cd4c1b268a..e4a16b74137 100644 --- a/drivers/crypto/caam/intern.h +++ b/drivers/crypto/caam/intern.h @@ -41,6 +41,7 @@ struct caam_jrentry_info { /* Private sub-storage for a single JobR */ struct caam_drv_private_jr { struct device *parentdev; /* points back to controller dev */ + struct platform_device *jr_pdev;/* points to platform device for JR */ int ridx; struct caam_job_ring __iomem *rregs; /* JobR's register space */ struct tasklet_struct irqtask; diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index 93d14070141..b4aa773ecbc 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -407,6 +407,7 @@ int caam_jr_shutdown(struct device *dev) dma_free_coherent(dev, sizeof(struct jr_outentry) * JOBR_DEPTH, jrp->outring, outbusaddr); kfree(jrp->entinfo); + of_device_unregister(jrp->jr_pdev); return ret; } @@ -454,6 +455,8 @@ int caam_jr_probe(struct platform_device *pdev, struct device_node *np, kfree(jrpriv); return -EINVAL; } + + jrpriv->jr_pdev = jr_pdev; jrdev = &jr_pdev->dev; dev_set_drvdata(jrdev, jrpriv); ctrlpriv->jrdev[ring] = jrdev; @@ -472,6 +475,7 @@ int caam_jr_probe(struct platform_device *pdev, struct device_node *np, /* Now do the platform independent part */ error = caam_jr_init(jrdev); /* now turn on hardware */ if (error) { + of_device_unregister(jr_pdev); kfree(jrpriv); return error; } diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index f6dba10246c..87138d2adb5 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -44,7 +44,7 @@ Split key generation----------------------------------------------- [06] 0x64260028 fifostr: class2 mdsplit-jdk len=40 @0xffe04000 */ -u32 gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, +int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, int split_key_pad_len, const u8 *key_in, u32 keylen, u32 alg_op) { diff --git a/drivers/crypto/caam/key_gen.h b/drivers/crypto/caam/key_gen.h index d95d290c6e8..c5588f6d810 100644 --- a/drivers/crypto/caam/key_gen.h +++ b/drivers/crypto/caam/key_gen.h @@ -12,6 +12,6 @@ struct split_key_result { void split_key_done(struct device *dev, u32 *desc, u32 err, void *context); -u32 gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, +int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, int split_key_pad_len, const u8 *key_in, u32 keylen, u32 alg_op); diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h index 3223fc6d647..cd6fedad993 100644 --- a/drivers/crypto/caam/regs.h +++ b/drivers/crypto/caam/regs.h @@ -252,7 +252,8 @@ struct caam_ctrl { /* Read/Writable */ u32 rsvd1; u32 mcr; /* MCFG Master Config Register */ - u32 rsvd2[2]; + u32 rsvd2; + u32 scfgr; /* SCFGR, Security Config Register */ /* Bus Access Configuration Section 010-11f */ /* Read/Writable */ @@ -299,6 +300,7 @@ struct caam_ctrl { #define MCFGR_WDFAIL 0x20000000 /* DECO watchdog force-fail */ #define MCFGR_DMA_RESET 0x10000000 #define MCFGR_LONG_PTR 0x00010000 /* Use >32-bit desc addressing */ +#define SCFGR_RDBENABLE 0x00000400 /* AXI read cache control */ #define MCFGR_ARCACHE_SHIFT 12 diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c index 6aa425fe0ed..ee15b0f7849 100644 --- a/drivers/crypto/omap-aes.c +++ b/drivers/crypto/omap-aes.c @@ -636,7 +636,7 @@ static void omap_aes_finish_req(struct omap_aes_dev *dd, int err) pr_debug("err: %d\n", err); - pm_runtime_put_sync(dd->dev); + pm_runtime_put(dd->dev); dd->flags &= ~FLAGS_BUSY; req->base.complete(&req->base, err); @@ -1248,18 +1248,7 @@ static struct platform_driver omap_aes_driver = { }, }; -static int __init omap_aes_mod_init(void) -{ - return platform_driver_register(&omap_aes_driver); -} - -static void __exit omap_aes_mod_exit(void) -{ - platform_driver_unregister(&omap_aes_driver); -} - -module_init(omap_aes_mod_init); -module_exit(omap_aes_mod_exit); +module_platform_driver(omap_aes_driver); MODULE_DESCRIPTION("OMAP AES hw acceleration support."); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index 3d1611f5aec..a1e1b4756ee 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -923,7 +923,7 @@ static void omap_sham_finish_req(struct ahash_request *req, int err) dd->flags &= ~(BIT(FLAGS_BUSY) | BIT(FLAGS_FINAL) | BIT(FLAGS_CPU) | BIT(FLAGS_DMA_READY) | BIT(FLAGS_OUTPUT_READY)); - pm_runtime_put_sync(dd->dev); + pm_runtime_put(dd->dev); if (req->base.complete) req->base.complete(&req->base, err); @@ -1813,18 +1813,7 @@ static struct platform_driver omap_sham_driver = { }, }; -static int __init omap_sham_mod_init(void) -{ - return platform_driver_register(&omap_sham_driver); -} - -static void __exit omap_sham_mod_exit(void) -{ - platform_driver_unregister(&omap_sham_driver); -} - -module_init(omap_sham_mod_init); -module_exit(omap_sham_mod_exit); +module_platform_driver(omap_sham_driver); MODULE_DESCRIPTION("OMAP SHA1/MD5 hw acceleration support."); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c index 2096d4685a9..ac30724d923 100644 --- a/drivers/crypto/picoxcell_crypto.c +++ b/drivers/crypto/picoxcell_crypto.c @@ -1688,8 +1688,6 @@ static const struct of_device_id spacc_of_id_table[] = { { .compatible = "picochip,spacc-l2" }, {} }; -#else /* CONFIG_OF */ -#define spacc_of_id_table NULL #endif /* CONFIG_OF */ static bool spacc_is_compatible(struct platform_device *pdev, @@ -1874,7 +1872,7 @@ static struct platform_driver spacc_driver = { #ifdef CONFIG_PM .pm = &spacc_pm_ops, #endif /* CONFIG_PM */ - .of_match_table = spacc_of_id_table, + .of_match_table = of_match_ptr(spacc_of_id_table), }, .id_table = spacc_id_table, }; diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c new file mode 100644 index 00000000000..a97bb6c1596 --- /dev/null +++ b/drivers/crypto/sahara.c @@ -0,0 +1,1070 @@ +/* + * Cryptographic API. + * + * Support for SAHARA cryptographic accelerator. + * + * Copyright (c) 2013 Vista Silicon S.L. + * Author: Javier Martin <javier.martin@vista-silicon.com> + * + * 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. + * + * Based on omap-aes.c and tegra-aes.c + */ + +#include <crypto/algapi.h> +#include <crypto/aes.h> + +#include <linux/clk.h> +#include <linux/crypto.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#define SAHARA_NAME "sahara" +#define SAHARA_VERSION_3 3 +#define SAHARA_TIMEOUT_MS 1000 +#define SAHARA_MAX_HW_DESC 2 +#define SAHARA_MAX_HW_LINK 20 + +#define FLAGS_MODE_MASK 0x000f +#define FLAGS_ENCRYPT BIT(0) +#define FLAGS_CBC BIT(1) +#define FLAGS_NEW_KEY BIT(3) +#define FLAGS_BUSY 4 + +#define SAHARA_HDR_BASE 0x00800000 +#define SAHARA_HDR_SKHA_ALG_AES 0 +#define SAHARA_HDR_SKHA_OP_ENC (1 << 2) +#define SAHARA_HDR_SKHA_MODE_ECB (0 << 3) +#define SAHARA_HDR_SKHA_MODE_CBC (1 << 3) +#define SAHARA_HDR_FORM_DATA (5 << 16) +#define SAHARA_HDR_FORM_KEY (8 << 16) +#define SAHARA_HDR_LLO (1 << 24) +#define SAHARA_HDR_CHA_SKHA (1 << 28) +#define SAHARA_HDR_CHA_MDHA (2 << 28) +#define SAHARA_HDR_PARITY_BIT (1 << 31) + +/* SAHARA can only process one request at a time */ +#define SAHARA_QUEUE_LENGTH 1 + +#define SAHARA_REG_VERSION 0x00 +#define SAHARA_REG_DAR 0x04 +#define SAHARA_REG_CONTROL 0x08 +#define SAHARA_CONTROL_SET_THROTTLE(x) (((x) & 0xff) << 24) +#define SAHARA_CONTROL_SET_MAXBURST(x) (((x) & 0xff) << 16) +#define SAHARA_CONTROL_RNG_AUTORSD (1 << 7) +#define SAHARA_CONTROL_ENABLE_INT (1 << 4) +#define SAHARA_REG_CMD 0x0C +#define SAHARA_CMD_RESET (1 << 0) +#define SAHARA_CMD_CLEAR_INT (1 << 8) +#define SAHARA_CMD_CLEAR_ERR (1 << 9) +#define SAHARA_CMD_SINGLE_STEP (1 << 10) +#define SAHARA_CMD_MODE_BATCH (1 << 16) +#define SAHARA_CMD_MODE_DEBUG (1 << 18) +#define SAHARA_REG_STATUS 0x10 +#define SAHARA_STATUS_GET_STATE(x) ((x) & 0x7) +#define SAHARA_STATE_IDLE 0 +#define SAHARA_STATE_BUSY 1 +#define SAHARA_STATE_ERR 2 +#define SAHARA_STATE_FAULT 3 +#define SAHARA_STATE_COMPLETE 4 +#define SAHARA_STATE_COMP_FLAG (1 << 2) +#define SAHARA_STATUS_DAR_FULL (1 << 3) +#define SAHARA_STATUS_ERROR (1 << 4) +#define SAHARA_STATUS_SECURE (1 << 5) +#define SAHARA_STATUS_FAIL (1 << 6) +#define SAHARA_STATUS_INIT (1 << 7) +#define SAHARA_STATUS_RNG_RESEED (1 << 8) +#define SAHARA_STATUS_ACTIVE_RNG (1 << 9) +#define SAHARA_STATUS_ACTIVE_MDHA (1 << 10) +#define SAHARA_STATUS_ACTIVE_SKHA (1 << 11) +#define SAHARA_STATUS_MODE_BATCH (1 << 16) +#define SAHARA_STATUS_MODE_DEDICATED (1 << 17) +#define SAHARA_STATUS_MODE_DEBUG (1 << 18) +#define SAHARA_STATUS_GET_ISTATE(x) (((x) >> 24) & 0xff) +#define SAHARA_REG_ERRSTATUS 0x14 +#define SAHARA_ERRSTATUS_GET_SOURCE(x) ((x) & 0xf) +#define SAHARA_ERRSOURCE_CHA 14 +#define SAHARA_ERRSOURCE_DMA 15 +#define SAHARA_ERRSTATUS_DMA_DIR (1 << 8) +#define SAHARA_ERRSTATUS_GET_DMASZ(x)(((x) >> 9) & 0x3) +#define SAHARA_ERRSTATUS_GET_DMASRC(x) (((x) >> 13) & 0x7) +#define SAHARA_ERRSTATUS_GET_CHASRC(x) (((x) >> 16) & 0xfff) +#define SAHARA_ERRSTATUS_GET_CHAERR(x) (((x) >> 28) & 0x3) +#define SAHARA_REG_FADDR 0x18 +#define SAHARA_REG_CDAR 0x1C +#define SAHARA_REG_IDAR 0x20 + +struct sahara_hw_desc { + u32 hdr; + u32 len1; + dma_addr_t p1; + u32 len2; + dma_addr_t p2; + dma_addr_t next; +}; + +struct sahara_hw_link { + u32 len; + dma_addr_t p; + dma_addr_t next; +}; + +struct sahara_ctx { + struct sahara_dev *dev; + unsigned long flags; + int keylen; + u8 key[AES_KEYSIZE_128]; + struct crypto_ablkcipher *fallback; +}; + +struct sahara_aes_reqctx { + unsigned long mode; +}; + +struct sahara_dev { + struct device *device; + void __iomem *regs_base; + struct clk *clk_ipg; + struct clk *clk_ahb; + + struct sahara_ctx *ctx; + spinlock_t lock; + struct crypto_queue queue; + unsigned long flags; + + struct tasklet_struct done_task; + struct tasklet_struct queue_task; + + struct sahara_hw_desc *hw_desc[SAHARA_MAX_HW_DESC]; + dma_addr_t hw_phys_desc[SAHARA_MAX_HW_DESC]; + + u8 *key_base; + dma_addr_t key_phys_base; + + u8 *iv_base; + dma_addr_t iv_phys_base; + + struct sahara_hw_link *hw_link[SAHARA_MAX_HW_LINK]; + dma_addr_t hw_phys_link[SAHARA_MAX_HW_LINK]; + + struct ablkcipher_request *req; + size_t total; + struct scatterlist *in_sg; + unsigned int nb_in_sg; + struct scatterlist *out_sg; + unsigned int nb_out_sg; + + u32 error; + struct timer_list watchdog; +}; + +static struct sahara_dev *dev_ptr; + +static inline void sahara_write(struct sahara_dev *dev, u32 data, u32 reg) +{ + writel(data, dev->regs_base + reg); +} + +static inline unsigned int sahara_read(struct sahara_dev *dev, u32 reg) +{ + return readl(dev->regs_base + reg); +} + +static u32 sahara_aes_key_hdr(struct sahara_dev *dev) +{ + u32 hdr = SAHARA_HDR_BASE | SAHARA_HDR_SKHA_ALG_AES | + SAHARA_HDR_FORM_KEY | SAHARA_HDR_LLO | + SAHARA_HDR_CHA_SKHA | SAHARA_HDR_PARITY_BIT; + + if (dev->flags & FLAGS_CBC) { + hdr |= SAHARA_HDR_SKHA_MODE_CBC; + hdr ^= SAHARA_HDR_PARITY_BIT; + } + + if (dev->flags & FLAGS_ENCRYPT) { + hdr |= SAHARA_HDR_SKHA_OP_ENC; + hdr ^= SAHARA_HDR_PARITY_BIT; + } + + return hdr; +} + +static u32 sahara_aes_data_link_hdr(struct sahara_dev *dev) +{ + return SAHARA_HDR_BASE | SAHARA_HDR_FORM_DATA | + SAHARA_HDR_CHA_SKHA | SAHARA_HDR_PARITY_BIT; +} + +static int sahara_sg_length(struct scatterlist *sg, + unsigned int total) +{ + int sg_nb; + unsigned int len; + struct scatterlist *sg_list; + + sg_nb = 0; + sg_list = sg; + + while (total) { + len = min(sg_list->length, total); + + sg_nb++; + total -= len; + + sg_list = sg_next(sg_list); + if (!sg_list) + total = 0; + } + + return sg_nb; +} + +static char *sahara_err_src[16] = { + "No error", + "Header error", + "Descriptor length error", + "Descriptor length or pointer error", + "Link length error", + "Link pointer error", + "Input buffer error", + "Output buffer error", + "Output buffer starvation", + "Internal state fault", + "General descriptor problem", + "Reserved", + "Descriptor address error", + "Link address error", + "CHA error", + "DMA error" +}; + +static char *sahara_err_dmasize[4] = { + "Byte transfer", + "Half-word transfer", + "Word transfer", + "Reserved" +}; + +static char *sahara_err_dmasrc[8] = { + "No error", + "AHB bus error", + "Internal IP bus error", + "Parity error", + "DMA crosses 256 byte boundary", + "DMA is busy", + "Reserved", + "DMA HW error" +}; + +static char *sahara_cha_errsrc[12] = { + "Input buffer non-empty", + "Illegal address", + "Illegal mode", + "Illegal data size", + "Illegal key size", + "Write during processing", + "CTX read during processing", + "HW error", + "Input buffer disabled/underflow", + "Output buffer disabled/overflow", + "DES key parity error", + "Reserved" +}; + +static char *sahara_cha_err[4] = { "No error", "SKHA", "MDHA", "RNG" }; + +static void sahara_decode_error(struct sahara_dev *dev, unsigned int error) +{ + u8 source = SAHARA_ERRSTATUS_GET_SOURCE(error); + u16 chasrc = ffs(SAHARA_ERRSTATUS_GET_CHASRC(error)); + + dev_err(dev->device, "%s: Error Register = 0x%08x\n", __func__, error); + + dev_err(dev->device, " - %s.\n", sahara_err_src[source]); + + if (source == SAHARA_ERRSOURCE_DMA) { + if (error & SAHARA_ERRSTATUS_DMA_DIR) + dev_err(dev->device, " * DMA read.\n"); + else + dev_err(dev->device, " * DMA write.\n"); + + dev_err(dev->device, " * %s.\n", + sahara_err_dmasize[SAHARA_ERRSTATUS_GET_DMASZ(error)]); + dev_err(dev->device, " * %s.\n", + sahara_err_dmasrc[SAHARA_ERRSTATUS_GET_DMASRC(error)]); + } else if (source == SAHARA_ERRSOURCE_CHA) { + dev_err(dev->device, " * %s.\n", + sahara_cha_errsrc[chasrc]); + dev_err(dev->device, " * %s.\n", + sahara_cha_err[SAHARA_ERRSTATUS_GET_CHAERR(error)]); + } + dev_err(dev->device, "\n"); +} + +static char *sahara_state[4] = { "Idle", "Busy", "Error", "HW Fault" }; + +static void sahara_decode_status(struct sahara_dev *dev, unsigned int status) +{ + u8 state; + + if (!IS_ENABLED(DEBUG)) + return; + + state = SAHARA_STATUS_GET_STATE(status); + + dev_dbg(dev->device, "%s: Status Register = 0x%08x\n", + __func__, status); + + dev_dbg(dev->device, " - State = %d:\n", state); + if (state & SAHARA_STATE_COMP_FLAG) + dev_dbg(dev->device, " * Descriptor completed. IRQ pending.\n"); + + dev_dbg(dev->device, " * %s.\n", + sahara_state[state & ~SAHARA_STATE_COMP_FLAG]); + + if (status & SAHARA_STATUS_DAR_FULL) + dev_dbg(dev->device, " - DAR Full.\n"); + if (status & SAHARA_STATUS_ERROR) + dev_dbg(dev->device, " - Error.\n"); + if (status & SAHARA_STATUS_SECURE) + dev_dbg(dev->device, " - Secure.\n"); + if (status & SAHARA_STATUS_FAIL) + dev_dbg(dev->device, " - Fail.\n"); + if (status & SAHARA_STATUS_RNG_RESEED) + dev_dbg(dev->device, " - RNG Reseed Request.\n"); + if (status & SAHARA_STATUS_ACTIVE_RNG) + dev_dbg(dev->device, " - RNG Active.\n"); + if (status & SAHARA_STATUS_ACTIVE_MDHA) + dev_dbg(dev->device, " - MDHA Active.\n"); + if (status & SAHARA_STATUS_ACTIVE_SKHA) + dev_dbg(dev->device, " - SKHA Active.\n"); + + if (status & SAHARA_STATUS_MODE_BATCH) + dev_dbg(dev->device, " - Batch Mode.\n"); + else if (status & SAHARA_STATUS_MODE_DEDICATED) + dev_dbg(dev->device, " - Decidated Mode.\n"); + else if (status & SAHARA_STATUS_MODE_DEBUG) + dev_dbg(dev->device, " - Debug Mode.\n"); + + dev_dbg(dev->device, " - Internal state = 0x%02x\n", + SAHARA_STATUS_GET_ISTATE(status)); + + dev_dbg(dev->device, "Current DAR: 0x%08x\n", + sahara_read(dev, SAHARA_REG_CDAR)); + dev_dbg(dev->device, "Initial DAR: 0x%08x\n\n", + sahara_read(dev, SAHARA_REG_IDAR)); +} + +static void sahara_dump_descriptors(struct sahara_dev *dev) +{ + int i; + + if (!IS_ENABLED(DEBUG)) + return; + + for (i = 0; i < SAHARA_MAX_HW_DESC; i++) { + dev_dbg(dev->device, "Descriptor (%d) (0x%08x):\n", + i, dev->hw_phys_desc[i]); + dev_dbg(dev->device, "\thdr = 0x%08x\n", dev->hw_desc[i]->hdr); + dev_dbg(dev->device, "\tlen1 = %u\n", dev->hw_desc[i]->len1); + dev_dbg(dev->device, "\tp1 = 0x%08x\n", dev->hw_desc[i]->p1); + dev_dbg(dev->device, "\tlen2 = %u\n", dev->hw_desc[i]->len2); + dev_dbg(dev->device, "\tp2 = 0x%08x\n", dev->hw_desc[i]->p2); + dev_dbg(dev->device, "\tnext = 0x%08x\n", + dev->hw_desc[i]->next); + } + dev_dbg(dev->device, "\n"); +} + +static void sahara_dump_links(struct sahara_dev *dev) +{ + int i; + + if (!IS_ENABLED(DEBUG)) + return; + + for (i = 0; i < SAHARA_MAX_HW_LINK; i++) { + dev_dbg(dev->device, "Link (%d) (0x%08x):\n", + i, dev->hw_phys_link[i]); + dev_dbg(dev->device, "\tlen = %u\n", dev->hw_link[i]->len); + dev_dbg(dev->device, "\tp = 0x%08x\n", dev->hw_link[i]->p); + dev_dbg(dev->device, "\tnext = 0x%08x\n", + dev->hw_link[i]->next); + } + dev_dbg(dev->device, "\n"); +} + +static void sahara_aes_done_task(unsigned long data) +{ + struct sahara_dev *dev = (struct sahara_dev *)data; + + dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, + DMA_TO_DEVICE); + dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, + DMA_FROM_DEVICE); + + spin_lock(&dev->lock); + clear_bit(FLAGS_BUSY, &dev->flags); + spin_unlock(&dev->lock); + + dev->req->base.complete(&dev->req->base, dev->error); +} + +void sahara_watchdog(unsigned long data) +{ + struct sahara_dev *dev = (struct sahara_dev *)data; + unsigned int err = sahara_read(dev, SAHARA_REG_ERRSTATUS); + unsigned int stat = sahara_read(dev, SAHARA_REG_STATUS); + + sahara_decode_status(dev, stat); + sahara_decode_error(dev, err); + dev->error = -ETIMEDOUT; + sahara_aes_done_task(data); +} + +static int sahara_hw_descriptor_create(struct sahara_dev *dev) +{ + struct sahara_ctx *ctx = dev->ctx; + struct scatterlist *sg; + int ret; + int i, j; + + /* Copy new key if necessary */ + if (ctx->flags & FLAGS_NEW_KEY) { + memcpy(dev->key_base, ctx->key, ctx->keylen); + ctx->flags &= ~FLAGS_NEW_KEY; + + if (dev->flags & FLAGS_CBC) { + dev->hw_desc[0]->len1 = AES_BLOCK_SIZE; + dev->hw_desc[0]->p1 = dev->iv_phys_base; + } else { + dev->hw_desc[0]->len1 = 0; + dev->hw_desc[0]->p1 = 0; + } + dev->hw_desc[0]->len2 = ctx->keylen; + dev->hw_desc[0]->p2 = dev->key_phys_base; + dev->hw_desc[0]->next = dev->hw_phys_desc[1]; + } + dev->hw_desc[0]->hdr = sahara_aes_key_hdr(dev); + + dev->nb_in_sg = sahara_sg_length(dev->in_sg, dev->total); + dev->nb_out_sg = sahara_sg_length(dev->out_sg, dev->total); + if ((dev->nb_in_sg + dev->nb_out_sg) > SAHARA_MAX_HW_LINK) { + dev_err(dev->device, "not enough hw links (%d)\n", + dev->nb_in_sg + dev->nb_out_sg); + return -EINVAL; + } + + ret = dma_map_sg(dev->device, dev->in_sg, dev->nb_in_sg, + DMA_TO_DEVICE); + if (ret != dev->nb_in_sg) { + dev_err(dev->device, "couldn't map in sg\n"); + goto unmap_in; + } + ret = dma_map_sg(dev->device, dev->out_sg, dev->nb_out_sg, + DMA_FROM_DEVICE); + if (ret != dev->nb_out_sg) { + dev_err(dev->device, "couldn't map out sg\n"); + goto unmap_out; + } + + /* Create input links */ + dev->hw_desc[1]->p1 = dev->hw_phys_link[0]; + sg = dev->in_sg; + for (i = 0; i < dev->nb_in_sg; i++) { + dev->hw_link[i]->len = sg->length; + dev->hw_link[i]->p = sg->dma_address; + if (i == (dev->nb_in_sg - 1)) { + dev->hw_link[i]->next = 0; + } else { + dev->hw_link[i]->next = dev->hw_phys_link[i + 1]; + sg = sg_next(sg); + } + } + + /* Create output links */ + dev->hw_desc[1]->p2 = dev->hw_phys_link[i]; + sg = dev->out_sg; + for (j = i; j < dev->nb_out_sg + i; j++) { + dev->hw_link[j]->len = sg->length; + dev->hw_link[j]->p = sg->dma_address; + if (j == (dev->nb_out_sg + i - 1)) { + dev->hw_link[j]->next = 0; + } else { + dev->hw_link[j]->next = dev->hw_phys_link[j + 1]; + sg = sg_next(sg); + } + } + + /* Fill remaining fields of hw_desc[1] */ + dev->hw_desc[1]->hdr = sahara_aes_data_link_hdr(dev); + dev->hw_desc[1]->len1 = dev->total; + dev->hw_desc[1]->len2 = dev->total; + dev->hw_desc[1]->next = 0; + + sahara_dump_descriptors(dev); + sahara_dump_links(dev); + + /* Start processing descriptor chain. */ + mod_timer(&dev->watchdog, + jiffies + msecs_to_jiffies(SAHARA_TIMEOUT_MS)); + sahara_write(dev, dev->hw_phys_desc[0], SAHARA_REG_DAR); + + return 0; + +unmap_out: + dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, + DMA_TO_DEVICE); +unmap_in: + dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, + DMA_FROM_DEVICE); + + return -EINVAL; +} + +static void sahara_aes_queue_task(unsigned long data) +{ + struct sahara_dev *dev = (struct sahara_dev *)data; + struct crypto_async_request *async_req, *backlog; + struct sahara_ctx *ctx; + struct sahara_aes_reqctx *rctx; + struct ablkcipher_request *req; + int ret; + + spin_lock(&dev->lock); + backlog = crypto_get_backlog(&dev->queue); + async_req = crypto_dequeue_request(&dev->queue); + if (!async_req) + clear_bit(FLAGS_BUSY, &dev->flags); + spin_unlock(&dev->lock); + + if (!async_req) + return; + + if (backlog) + backlog->complete(backlog, -EINPROGRESS); + + req = ablkcipher_request_cast(async_req); + + /* Request is ready to be dispatched by the device */ + dev_dbg(dev->device, + "dispatch request (nbytes=%d, src=%p, dst=%p)\n", + req->nbytes, req->src, req->dst); + + /* assign new request to device */ + dev->req = req; + dev->total = req->nbytes; + dev->in_sg = req->src; + dev->out_sg = req->dst; + + rctx = ablkcipher_request_ctx(req); + ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req)); + rctx->mode &= FLAGS_MODE_MASK; + dev->flags = (dev->flags & ~FLAGS_MODE_MASK) | rctx->mode; + + if ((dev->flags & FLAGS_CBC) && req->info) + memcpy(dev->iv_base, req->info, AES_KEYSIZE_128); + + /* assign new context to device */ + ctx->dev = dev; + dev->ctx = ctx; + + ret = sahara_hw_descriptor_create(dev); + if (ret < 0) { + spin_lock(&dev->lock); + clear_bit(FLAGS_BUSY, &dev->flags); + spin_unlock(&dev->lock); + dev->req->base.complete(&dev->req->base, ret); + } +} + +static int sahara_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key, + unsigned int keylen) +{ + struct sahara_ctx *ctx = crypto_ablkcipher_ctx(tfm); + int ret; + + ctx->keylen = keylen; + + /* SAHARA only supports 128bit keys */ + if (keylen == AES_KEYSIZE_128) { + memcpy(ctx->key, key, keylen); + ctx->flags |= FLAGS_NEW_KEY; + return 0; + } + + if (keylen != AES_KEYSIZE_128 && + keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_256) + return -EINVAL; + + /* + * The requested key size is not supported by HW, do a fallback. + */ + ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; + ctx->fallback->base.crt_flags |= + (tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK); + + ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen); + if (ret) { + struct crypto_tfm *tfm_aux = crypto_ablkcipher_tfm(tfm); + + tfm_aux->crt_flags &= ~CRYPTO_TFM_RES_MASK; + tfm_aux->crt_flags |= + (ctx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK); + } + return ret; +} + +static int sahara_aes_crypt(struct ablkcipher_request *req, unsigned long mode) +{ + struct sahara_ctx *ctx = crypto_ablkcipher_ctx( + crypto_ablkcipher_reqtfm(req)); + struct sahara_aes_reqctx *rctx = ablkcipher_request_ctx(req); + struct sahara_dev *dev = dev_ptr; + int err = 0; + int busy; + + dev_dbg(dev->device, "nbytes: %d, enc: %d, cbc: %d\n", + req->nbytes, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC)); + + if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) { + dev_err(dev->device, + "request size is not exact amount of AES blocks\n"); + return -EINVAL; + } + + ctx->dev = dev; + + rctx->mode = mode; + spin_lock_bh(&dev->lock); + err = ablkcipher_enqueue_request(&dev->queue, req); + busy = test_and_set_bit(FLAGS_BUSY, &dev->flags); + spin_unlock_bh(&dev->lock); + + if (!busy) + tasklet_schedule(&dev->queue_task); + + return err; +} + +static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req) +{ + struct crypto_tfm *tfm = + crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req)); + struct sahara_ctx *ctx = crypto_ablkcipher_ctx( + crypto_ablkcipher_reqtfm(req)); + int err; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { + ablkcipher_request_set_tfm(req, ctx->fallback); + err = crypto_ablkcipher_encrypt(req); + ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm)); + return err; + } + + return sahara_aes_crypt(req, FLAGS_ENCRYPT); +} + +static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req) +{ + struct crypto_tfm *tfm = + crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req)); + struct sahara_ctx *ctx = crypto_ablkcipher_ctx( + crypto_ablkcipher_reqtfm(req)); + int err; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { + ablkcipher_request_set_tfm(req, ctx->fallback); + err = crypto_ablkcipher_decrypt(req); + ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm)); + return err; + } + + return sahara_aes_crypt(req, 0); +} + +static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req) +{ + struct crypto_tfm *tfm = + crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req)); + struct sahara_ctx *ctx = crypto_ablkcipher_ctx( + crypto_ablkcipher_reqtfm(req)); + int err; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { + ablkcipher_request_set_tfm(req, ctx->fallback); + err = crypto_ablkcipher_encrypt(req); + ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm)); + return err; + } + + return sahara_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC); +} + +static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req) +{ + struct crypto_tfm *tfm = + crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req)); + struct sahara_ctx *ctx = crypto_ablkcipher_ctx( + crypto_ablkcipher_reqtfm(req)); + int err; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { + ablkcipher_request_set_tfm(req, ctx->fallback); + err = crypto_ablkcipher_decrypt(req); + ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm)); + return err; + } + + return sahara_aes_crypt(req, FLAGS_CBC); +} + +static int sahara_aes_cra_init(struct crypto_tfm *tfm) +{ + const char *name = tfm->__crt_alg->cra_name; + struct sahara_ctx *ctx = crypto_tfm_ctx(tfm); + + ctx->fallback = crypto_alloc_ablkcipher(name, 0, + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ctx->fallback)) { + pr_err("Error allocating fallback algo %s\n", name); + return PTR_ERR(ctx->fallback); + } + + tfm->crt_ablkcipher.reqsize = sizeof(struct sahara_aes_reqctx); + + return 0; +} + +static void sahara_aes_cra_exit(struct crypto_tfm *tfm) +{ + struct sahara_ctx *ctx = crypto_tfm_ctx(tfm); + + if (ctx->fallback) + crypto_free_ablkcipher(ctx->fallback); + ctx->fallback = NULL; +} + +static struct crypto_alg aes_algs[] = { +{ + .cra_name = "ecb(aes)", + .cra_driver_name = "sahara-ecb-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sahara_ctx), + .cra_alignmask = 0x0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = sahara_aes_cra_init, + .cra_exit = sahara_aes_cra_exit, + .cra_u.ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE , + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = sahara_aes_setkey, + .encrypt = sahara_aes_ecb_encrypt, + .decrypt = sahara_aes_ecb_decrypt, + } +}, { + .cra_name = "cbc(aes)", + .cra_driver_name = "sahara-cbc-aes", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | + CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sahara_ctx), + .cra_alignmask = 0x0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = sahara_aes_cra_init, + .cra_exit = sahara_aes_cra_exit, + .cra_u.ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE , + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = sahara_aes_setkey, + .encrypt = sahara_aes_cbc_encrypt, + .decrypt = sahara_aes_cbc_decrypt, + } +} +}; + +static irqreturn_t sahara_irq_handler(int irq, void *data) +{ + struct sahara_dev *dev = (struct sahara_dev *)data; + unsigned int stat = sahara_read(dev, SAHARA_REG_STATUS); + unsigned int err = sahara_read(dev, SAHARA_REG_ERRSTATUS); + + del_timer(&dev->watchdog); + + sahara_write(dev, SAHARA_CMD_CLEAR_INT | SAHARA_CMD_CLEAR_ERR, + SAHARA_REG_CMD); + + sahara_decode_status(dev, stat); + + if (SAHARA_STATUS_GET_STATE(stat) == SAHARA_STATE_BUSY) { + return IRQ_NONE; + } else if (SAHARA_STATUS_GET_STATE(stat) == SAHARA_STATE_COMPLETE) { + dev->error = 0; + } else { + sahara_decode_error(dev, err); + dev->error = -EINVAL; + } + + tasklet_schedule(&dev->done_task); + + return IRQ_HANDLED; +} + + +static int sahara_register_algs(struct sahara_dev *dev) +{ + int err, i, j; + + for (i = 0; i < ARRAY_SIZE(aes_algs); i++) { + INIT_LIST_HEAD(&aes_algs[i].cra_list); + err = crypto_register_alg(&aes_algs[i]); + if (err) + goto err_aes_algs; + } + + return 0; + +err_aes_algs: + for (j = 0; j < i; j++) + crypto_unregister_alg(&aes_algs[j]); + + return err; +} + +static void sahara_unregister_algs(struct sahara_dev *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(aes_algs); i++) + crypto_unregister_alg(&aes_algs[i]); +} + +static struct platform_device_id sahara_platform_ids[] = { + { .name = "sahara-imx27" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, sahara_platform_ids); + +static struct of_device_id sahara_dt_ids[] = { + { .compatible = "fsl,imx27-sahara" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, sahara_dt_ids); + +static int sahara_probe(struct platform_device *pdev) +{ + struct sahara_dev *dev; + struct resource *res; + u32 version; + int irq; + int err; + int i; + + dev = devm_kzalloc(&pdev->dev, sizeof(struct sahara_dev), GFP_KERNEL); + if (dev == NULL) { + dev_err(&pdev->dev, "unable to alloc data struct.\n"); + return -ENOMEM; + } + + dev->device = &pdev->dev; + platform_set_drvdata(pdev, dev); + + /* Get the base address */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "failed to get memory region resource\n"); + return -ENODEV; + } + + if (devm_request_mem_region(&pdev->dev, res->start, + resource_size(res), SAHARA_NAME) == NULL) { + dev_err(&pdev->dev, "failed to request memory region\n"); + return -ENOENT; + } + dev->regs_base = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!dev->regs_base) { + dev_err(&pdev->dev, "failed to ioremap address region\n"); + return -ENOENT; + } + + /* Get the IRQ */ + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "failed to get irq resource\n"); + return irq; + } + + if (devm_request_irq(&pdev->dev, irq, sahara_irq_handler, + 0, SAHARA_NAME, dev) < 0) { + dev_err(&pdev->dev, "failed to request irq\n"); + return -ENOENT; + } + + /* clocks */ + dev->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); + if (IS_ERR(dev->clk_ipg)) { + dev_err(&pdev->dev, "Could not get ipg clock\n"); + return PTR_ERR(dev->clk_ipg); + } + + dev->clk_ahb = devm_clk_get(&pdev->dev, "ahb"); + if (IS_ERR(dev->clk_ahb)) { + dev_err(&pdev->dev, "Could not get ahb clock\n"); + return PTR_ERR(dev->clk_ahb); + } + + /* Allocate HW descriptors */ + dev->hw_desc[0] = dma_alloc_coherent(&pdev->dev, + SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc), + &dev->hw_phys_desc[0], GFP_KERNEL); + if (!dev->hw_desc[0]) { + dev_err(&pdev->dev, "Could not allocate hw descriptors\n"); + return -ENOMEM; + } + dev->hw_desc[1] = dev->hw_desc[0] + 1; + dev->hw_phys_desc[1] = dev->hw_phys_desc[0] + + sizeof(struct sahara_hw_desc); + + /* Allocate space for iv and key */ + dev->key_base = dma_alloc_coherent(&pdev->dev, 2 * AES_KEYSIZE_128, + &dev->key_phys_base, GFP_KERNEL); + if (!dev->key_base) { + dev_err(&pdev->dev, "Could not allocate memory for key\n"); + err = -ENOMEM; + goto err_key; + } + dev->iv_base = dev->key_base + AES_KEYSIZE_128; + dev->iv_phys_base = dev->key_phys_base + AES_KEYSIZE_128; + + /* Allocate space for HW links */ + dev->hw_link[0] = dma_alloc_coherent(&pdev->dev, + SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link), + &dev->hw_phys_link[0], GFP_KERNEL); + if (!dev->hw_link) { + dev_err(&pdev->dev, "Could not allocate hw links\n"); + err = -ENOMEM; + goto err_link; + } + for (i = 1; i < SAHARA_MAX_HW_LINK; i++) { + dev->hw_phys_link[i] = dev->hw_phys_link[i - 1] + + sizeof(struct sahara_hw_link); + dev->hw_link[i] = dev->hw_link[i - 1] + 1; + } + + crypto_init_queue(&dev->queue, SAHARA_QUEUE_LENGTH); + + dev_ptr = dev; + + tasklet_init(&dev->queue_task, sahara_aes_queue_task, + (unsigned long)dev); + tasklet_init(&dev->done_task, sahara_aes_done_task, + (unsigned long)dev); + + init_timer(&dev->watchdog); + dev->watchdog.function = &sahara_watchdog; + dev->watchdog.data = (unsigned long)dev; + + clk_prepare_enable(dev->clk_ipg); + clk_prepare_enable(dev->clk_ahb); + + version = sahara_read(dev, SAHARA_REG_VERSION); + if (version != SAHARA_VERSION_3) { + dev_err(&pdev->dev, "SAHARA version %d not supported\n", + version); + err = -ENODEV; + goto err_algs; + } + + sahara_write(dev, SAHARA_CMD_RESET | SAHARA_CMD_MODE_BATCH, + SAHARA_REG_CMD); + sahara_write(dev, SAHARA_CONTROL_SET_THROTTLE(0) | + SAHARA_CONTROL_SET_MAXBURST(8) | + SAHARA_CONTROL_RNG_AUTORSD | + SAHARA_CONTROL_ENABLE_INT, + SAHARA_REG_CONTROL); + + err = sahara_register_algs(dev); + if (err) + goto err_algs; + + dev_info(&pdev->dev, "SAHARA version %d initialized\n", version); + + return 0; + +err_algs: + dma_free_coherent(&pdev->dev, + SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link), + dev->hw_link[0], dev->hw_phys_link[0]); + clk_disable_unprepare(dev->clk_ipg); + clk_disable_unprepare(dev->clk_ahb); + dev_ptr = NULL; +err_link: + dma_free_coherent(&pdev->dev, + 2 * AES_KEYSIZE_128, + dev->key_base, dev->key_phys_base); +err_key: + dma_free_coherent(&pdev->dev, + SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc), + dev->hw_desc[0], dev->hw_phys_desc[0]); + + return err; +} + +static int sahara_remove(struct platform_device *pdev) +{ + struct sahara_dev *dev = platform_get_drvdata(pdev); + + dma_free_coherent(&pdev->dev, + SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link), + dev->hw_link[0], dev->hw_phys_link[0]); + dma_free_coherent(&pdev->dev, + 2 * AES_KEYSIZE_128, + dev->key_base, dev->key_phys_base); + dma_free_coherent(&pdev->dev, + SAHARA_MAX_HW_DESC * sizeof(struct sahara_hw_desc), + dev->hw_desc[0], dev->hw_phys_desc[0]); + + tasklet_kill(&dev->done_task); + tasklet_kill(&dev->queue_task); + + sahara_unregister_algs(dev); + + clk_disable_unprepare(dev->clk_ipg); + clk_disable_unprepare(dev->clk_ahb); + + dev_ptr = NULL; + + return 0; +} + +static struct platform_driver sahara_driver = { + .probe = sahara_probe, + .remove = sahara_remove, + .driver = { + .name = SAHARA_NAME, + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(sahara_dt_ids), + }, + .id_table = sahara_platform_ids, +}; + +module_platform_driver(sahara_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Javier Martin <javier.martin@vista-silicon.com>"); +MODULE_DESCRIPTION("SAHARA2 HW crypto accelerator"); diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 1827e9f1f87..cf550896753 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -938,6 +938,7 @@ static int hash_dma_final(struct ahash_request *req) if (!ctx->device->dma.nents) { dev_err(device_data->dev, "[%s] " "ctx->device->dma.nents = 0", __func__); + ret = ctx->device->dma.nents; goto out; } @@ -945,6 +946,7 @@ static int hash_dma_final(struct ahash_request *req) if (bytes_written != req->nbytes) { dev_err(device_data->dev, "[%s] " "hash_dma_write() failed!", __func__); + ret = bytes_written; goto out; } @@ -1367,14 +1369,12 @@ static int hash_setkey(struct crypto_ahash *tfm, /** * Freed in final. */ - ctx->key = kmalloc(keylen, GFP_KERNEL); + ctx->key = kmemdup(key, keylen, GFP_KERNEL); if (!ctx->key) { pr_err(DEV_DBG_NAME " [%s] Failed to allocate ctx->key " "for %d\n", __func__, alg); return -ENOMEM; } - - memcpy(ctx->key, key, keylen); ctx->keylen = keylen; return ret; |