Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:

 - Fixed algorithm construction hang when self-test fails.
 - Added SHA variants to talitos AEAD list.
 - New driver for Exynos random number generator.
 - Performance enhancements for arc4.
 - Added hwrng support to caam.
 - Added ahash support to caam.
 - Fixed bad kfree in aesni-intel.
 - Allow aesni-intel in FIPS mode.
 - Added atmel driver with support for AES/3DES/SHA.
 - Bug fixes for mv_cesa.
 - CRC hardware driver for BF60x family processors.

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (66 commits)
  crypto: twofish-avx - remove useless instruction
  crypto: testmgr - add aead cbc aes hmac sha1,256,512 test vectors
  crypto: talitos - add sha224, sha384 and sha512 to existing AEAD algorithms
  crypto: talitos - export the talitos_submit function
  crypto: talitos - move talitos structures to header file
  crypto: atmel - add new tests to tcrypt
  crypto: atmel - add Atmel SHA1/SHA256 driver
  crypto: atmel - add Atmel DES/TDES driver
  crypto: atmel - add Atmel AES driver
  ARM: AT91SAM9G45: add crypto peripherals
  crypto: testmgr - allow aesni-intel and ghash_clmulni-intel in fips mode
  hwrng: exynos - Add support for Exynos random number generator
  crypto: aesni-intel - fix wrong kfree pointer
  crypto: caam - ERA retrieval and printing for SEC device
  crypto: caam - Using alloc_coherent for caam job rings
  crypto: algapi - Fix hang on crypto allocation
  crypto: arc4 - now arc needs blockcipher support
  crypto: caam - one tasklet per job ring
  crypto: caam - consolidate memory barriers from job ring en/dequeue
  crypto: caam - only query h/w in job ring dequeue path
  ...

30 files changed, 8382 insertions, 632 deletions

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 1092a77..7d74d09 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -298,7 +298,7 @@ config CRYPTO_DEV_TEGRA_AES
 	  will be called tegra-aes.
 
 config CRYPTO_DEV_NX
-	tristate "Support for Power7+ in-Nest cryptographic accleration"
+	tristate "Support for Power7+ in-Nest cryptographic acceleration"
 	depends on PPC64 && IBMVIO
 	select CRYPTO_AES
 	select CRYPTO_CBC
@@ -325,4 +325,58 @@ if CRYPTO_DEV_UX500
 	source "drivers/crypto/ux500/Kconfig"
 endif # if CRYPTO_DEV_UX500
 
+config CRYPTO_DEV_BFIN_CRC
+	tristate "Support for Blackfin CRC hardware"
+	depends on BF60x
+	help
+	  Newer Blackfin processors have CRC hardware. Select this if you
+	  want to use the Blackfin CRC module.
+
+config CRYPTO_DEV_ATMEL_AES
+	tristate "Support for Atmel AES hw accelerator"
+	depends on ARCH_AT91
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_AES
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
+	select CONFIG_AT_HDMAC
+	help
+	  Some Atmel processors have AES hw accelerator.
+	  Select this if you want to use the Atmel module for
+	  AES algorithms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called atmel-aes.
+
+config CRYPTO_DEV_ATMEL_TDES
+	tristate "Support for Atmel DES/TDES hw accelerator"
+	depends on ARCH_AT91
+	select CRYPTO_DES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
+	help
+	  Some Atmel processors have DES/TDES hw accelerator.
+	  Select this if you want to use the Atmel module for
+	  DES/TDES algorithms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called atmel-tdes.
+
+config CRYPTO_DEV_ATMEL_SHA
+	tristate "Support for Atmel SHA1/SHA256 hw accelerator"
+	depends on ARCH_AT91
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_ALGAPI
+	help
+	  Some Atmel processors have SHA1/SHA256 hw accelerator.
+	  Select this if you want to use the Atmel module for
+	  SHA1/SHA256 algorithms.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called atmel-sha.
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 0139032..880a47b 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -14,4 +14,9 @@ obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes.o
 obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_TEGRA_AES) += tegra-aes.o
-obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
\ No newline at end of file
+obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
+obj-$(CONFIG_CRYPTO_DEV_BFIN_CRC) += bfin_crc.o
+obj-$(CONFIG_CRYPTO_DEV_NX) += nx/
+obj-$(CONFIG_CRYPTO_DEV_ATMEL_AES) += atmel-aes.o
+obj-$(CONFIG_CRYPTO_DEV_ATMEL_TDES) += atmel-tdes.o
+obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA) += atmel-sha.o
diff --git a/drivers/crypto/atmel-aes-regs.h b/drivers/crypto/atmel-aes-regs.h
new file mode 100644
index 0000000..2786bb1
--- /dev/null
+++ b/drivers/crypto/atmel-aes-regs.h
@@ -0,0 +1,62 @@
+#ifndef __ATMEL_AES_REGS_H__
+#define __ATMEL_AES_REGS_H__
+
+#define AES_CR			0x00
+#define AES_CR_START		(1 << 0)
+#define AES_CR_SWRST		(1 << 8)
+#define AES_CR_LOADSEED		(1 << 16)
+
+#define	AES_MR			0x04
+#define AES_MR_CYPHER_DEC		(0 << 0)
+#define AES_MR_CYPHER_ENC		(1 << 0)
+#define	AES_MR_DUALBUFF			(1 << 3)
+#define AES_MR_PROCDLY_MASK		(0xF << 4)
+#define AES_MR_PROCDLY_OFFSET	4
+#define AES_MR_SMOD_MASK		(0x3 << 8)
+#define AES_MR_SMOD_MANUAL		(0x0 << 8)
+#define AES_MR_SMOD_AUTO		(0x1 << 8)
+#define AES_MR_SMOD_IDATAR0		(0x2 << 8)
+#define	AES_MR_KEYSIZE_MASK		(0x3 << 10)
+#define	AES_MR_KEYSIZE_128		(0x0 << 10)
+#define	AES_MR_KEYSIZE_192		(0x1 << 10)
+#define	AES_MR_KEYSIZE_256		(0x2 << 10)
+#define AES_MR_OPMOD_MASK		(0x7 << 12)
+#define AES_MR_OPMOD_ECB		(0x0 << 12)
+#define AES_MR_OPMOD_CBC		(0x1 << 12)
+#define AES_MR_OPMOD_OFB		(0x2 << 12)
+#define AES_MR_OPMOD_CFB		(0x3 << 12)
+#define AES_MR_OPMOD_CTR		(0x4 << 12)
+#define AES_MR_LOD				(0x1 << 15)
+#define AES_MR_CFBS_MASK		(0x7 << 16)
+#define AES_MR_CFBS_128b		(0x0 << 16)
+#define AES_MR_CFBS_64b			(0x1 << 16)
+#define AES_MR_CFBS_32b			(0x2 << 16)
+#define AES_MR_CFBS_16b			(0x3 << 16)
+#define AES_MR_CFBS_8b			(0x4 << 16)
+#define AES_MR_CKEY_MASK		(0xF << 20)
+#define AES_MR_CKEY_OFFSET		20
+#define AES_MR_CMTYP_MASK		(0x1F << 24)
+#define AES_MR_CMTYP_OFFSET		24
+
+#define	AES_IER		0x10
+#define	AES_IDR		0x14
+#define	AES_IMR		0x18
+#define	AES_ISR		0x1C
+#define AES_INT_DATARDY		(1 << 0)
+#define AES_INT_URAD		(1 << 8)
+#define AES_ISR_URAT_MASK	(0xF << 12)
+#define AES_ISR_URAT_IDR_WR_PROC	(0x0 << 12)
+#define AES_ISR_URAT_ODR_RD_PROC	(0x1 << 12)
+#define AES_ISR_URAT_MR_WR_PROC		(0x2 << 12)
+#define AES_ISR_URAT_ODR_RD_SUBK	(0x3 << 12)
+#define AES_ISR_URAT_MR_WR_SUBK		(0x4 << 12)
+#define AES_ISR_URAT_WOR_RD			(0x5 << 12)
+
+#define AES_KEYWR(x)	(0x20 + ((x) * 0x04))
+#define AES_IDATAR(x)	(0x40 + ((x) * 0x04))
+#define AES_ODATAR(x)	(0x50 + ((x) * 0x04))
+#define AES_IVR(x)		(0x60 + ((x) * 0x04))
+
+#define AES_HW_VERSION	0xFC
+
+#endif /* __ATMEL_AES_REGS_H__ */
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
new file mode 100644
index 0000000..6bb20ff
--- /dev/null
+++ b/drivers/crypto/atmel-aes.c
@@ -0,0 +1,1206 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for ATMEL AES HW acceleration.
+ *
+ * Copyright (c) 2012 Eukréa Electromatique - ATMEL
+ * Author: Nicolas Royer <nicolas@eukrea.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.
+ *
+ * Some ideas are from omap-aes.c driver.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/hw_random.h>
+#include <linux/platform_device.h>
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include <linux/cryptohash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/algapi.h>
+#include <crypto/aes.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+#include <linux/platform_data/atmel-aes.h>
+#include "atmel-aes-regs.h"
+
+#define CFB8_BLOCK_SIZE		1
+#define CFB16_BLOCK_SIZE	2
+#define CFB32_BLOCK_SIZE	4
+#define CFB64_BLOCK_SIZE	8
+
+/* AES flags */
+#define AES_FLAGS_MODE_MASK	0x01ff
+#define AES_FLAGS_ENCRYPT	BIT(0)
+#define AES_FLAGS_CBC		BIT(1)
+#define AES_FLAGS_CFB		BIT(2)
+#define AES_FLAGS_CFB8		BIT(3)
+#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_INIT		BIT(16)
+#define AES_FLAGS_DMA		BIT(17)
+#define AES_FLAGS_BUSY		BIT(18)
+
+#define AES_FLAGS_DUALBUFF	BIT(24)
+
+#define ATMEL_AES_QUEUE_LENGTH	1
+#define ATMEL_AES_CACHE_SIZE	0
+
+#define ATMEL_AES_DMA_THRESHOLD		16
+
+
+struct atmel_aes_dev;
+
+struct atmel_aes_ctx {
+	struct atmel_aes_dev *dd;
+
+	int		keylen;
+	u32		key[AES_KEYSIZE_256 / sizeof(u32)];
+};
+
+struct atmel_aes_reqctx {
+	unsigned long mode;
+};
+
+struct atmel_aes_dma {
+	struct dma_chan			*chan;
+	struct dma_slave_config dma_conf;
+};
+
+struct atmel_aes_dev {
+	struct list_head	list;
+	unsigned long		phys_base;
+	void __iomem		*io_base;
+
+	struct atmel_aes_ctx	*ctx;
+	struct device		*dev;
+	struct clk		*iclk;
+	int	irq;
+
+	unsigned long		flags;
+	int	err;
+
+	spinlock_t		lock;
+	struct crypto_queue	queue;
+
+	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
+
+	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;
+
+	size_t	bufcnt;
+
+	u8	buf_in[ATMEL_AES_DMA_THRESHOLD] __aligned(sizeof(u32));
+	int	dma_in;
+	struct atmel_aes_dma	dma_lch_in;
+
+	u8	buf_out[ATMEL_AES_DMA_THRESHOLD] __aligned(sizeof(u32));
+	int	dma_out;
+	struct atmel_aes_dma	dma_lch_out;
+
+	u32	hw_version;
+};
+
+struct atmel_aes_drv {
+	struct list_head	dev_list;
+	spinlock_t		lock;
+};
+
+static struct atmel_aes_drv atmel_aes = {
+	.dev_list = LIST_HEAD_INIT(atmel_aes.dev_list),
+	.lock = __SPIN_LOCK_UNLOCKED(atmel_aes.lock),
+};
+
+static int atmel_aes_sg_length(struct ablkcipher_request *req,
+			struct scatterlist *sg)
+{
+	unsigned int total = req->nbytes;
+	int sg_nb;
+	unsigned int len;
+	struct scatterlist *sg_list;
+
+	sg_nb = 0;
+	sg_list = sg;
+	total = req->nbytes;
+
+	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 inline u32 atmel_aes_read(struct atmel_aes_dev *dd, u32 offset)
+{
+	return readl_relaxed(dd->io_base + offset);
+}
+
+static inline void atmel_aes_write(struct atmel_aes_dev *dd,
+					u32 offset, u32 value)
+{
+	writel_relaxed(value, dd->io_base + offset);
+}
+
+static void atmel_aes_read_n(struct atmel_aes_dev *dd, u32 offset,
+					u32 *value, int count)
+{
+	for (; count--; value++, offset += 4)
+		*value = atmel_aes_read(dd, offset);
+}
+
+static void atmel_aes_write_n(struct atmel_aes_dev *dd, u32 offset,
+					u32 *value, int count)
+{
+	for (; count--; value++, offset += 4)
+		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;
+	struct atmel_aes_dev *tmp;
+
+	spin_lock_bh(&atmel_aes.lock);
+	if (!ctx->dd) {
+		list_for_each_entry(tmp, &atmel_aes.dev_list, list) {
+			aes_dd = tmp;
+			break;
+		}
+		ctx->dd = aes_dd;
+	} else {
+		aes_dd = ctx->dd;
+	}
+
+	spin_unlock_bh(&atmel_aes.lock);
+
+	return aes_dd;
+}
+
+static int atmel_aes_hw_init(struct atmel_aes_dev *dd)
+{
+	clk_prepare_enable(dd->iclk);
+
+	if (!(dd->flags & AES_FLAGS_INIT)) {
+		atmel_aes_write(dd, AES_CR, AES_CR_SWRST);
+		atmel_aes_dualbuff_test(dd);
+		dd->flags |= AES_FLAGS_INIT;
+		dd->err = 0;
+	}
+
+	return 0;
+}
+
+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);
+
+	clk_disable_unprepare(dd->iclk);
+}
+
+static void atmel_aes_finish_req(struct atmel_aes_dev *dd, int err)
+{
+	struct ablkcipher_request *req = dd->req;
+
+	clk_disable_unprepare(dd->iclk);
+	dd->flags &= ~AES_FLAGS_BUSY;
+
+	req->base.complete(&req->base, err);
+}
+
+static void atmel_aes_dma_callback(void *data)
+{
+	struct atmel_aes_dev *dd = data;
+
+	/* dma_lch_out - completed */
+	tasklet_schedule(&dd->done_task);
+}
+
+static int atmel_aes_crypt_dma(struct atmel_aes_dev *dd)
+{
+	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;
+
+	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;
+
+	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 (!in_desc)
+		goto unmap_in;
+
+	/* callback not needed */
+
+	dd->nb_out_sg = atmel_aes_sg_length(dd->req, dd->out_sg);
+	if (!dd->nb_out_sg)
+		goto unmap_in;
+
+	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;
+
+	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);
+
+	if (!out_desc)
+		goto unmap_out;
+
+	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);
+
+	dmaengine_submit(in_desc);
+	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)
+{
+	dd->flags &= ~AES_FLAGS_DMA;
+
+	/* use cache buffers */
+	dd->nb_in_sg = atmel_aes_sg_length(dd->req, dd->in_sg);
+	if (!dd->nb_in_sg)
+		return -EINVAL;
+
+	dd->nb_out_sg = atmel_aes_sg_length(dd->req, dd->out_sg);
+	if (!dd->nb_in_sg)
+		return -EINVAL;
+
+	dd->bufcnt = sg_copy_to_buffer(dd->in_sg, dd->nb_in_sg,
+					dd->buf_in, dd->total);
+
+	if (!dd->bufcnt)
+		return -EINVAL;
+
+	dd->total -= dd->bufcnt;
+
+	atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
+	atmel_aes_write_n(dd, AES_IDATAR(0), (u32 *) dd->buf_in,
+				dd->bufcnt >> 2);
+
+	return 0;
+}
+
+static int atmel_aes_crypt_dma_start(struct atmel_aes_dev *dd)
+{
+	int err;
+
+	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;
+	}
+
+	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 |= AES_FLAGS_DMA;
+	err = atmel_aes_crypt_dma(dd);
+
+	return err;
+}
+
+static int atmel_aes_write_ctrl(struct atmel_aes_dev *dd)
+{
+	int err;
+	u32 valcr = 0, valmr = 0;
+
+	err = atmel_aes_hw_init(dd);
+
+	if (err)
+		return err;
+
+	/* MR register must be set before IV registers */
+	if (dd->ctx->keylen == AES_KEYSIZE_128)
+		valmr |= AES_MR_KEYSIZE_128;
+	else if (dd->ctx->keylen == AES_KEYSIZE_192)
+		valmr |= AES_MR_KEYSIZE_192;
+	else
+		valmr |= AES_MR_KEYSIZE_256;
+
+	if (dd->flags & AES_FLAGS_CBC) {
+		valmr |= AES_MR_OPMOD_CBC;
+	} else if (dd->flags & AES_FLAGS_CFB) {
+		valmr |= AES_MR_OPMOD_CFB;
+		if (dd->flags & AES_FLAGS_CFB8)
+			valmr |= AES_MR_CFBS_8b;
+		else if (dd->flags & AES_FLAGS_CFB16)
+			valmr |= AES_MR_CFBS_16b;
+		else if (dd->flags & AES_FLAGS_CFB32)
+			valmr |= AES_MR_CFBS_32b;
+		else if (dd->flags & AES_FLAGS_CFB64)
+			valmr |= AES_MR_CFBS_64b;
+	} else if (dd->flags & AES_FLAGS_OFB) {
+		valmr |= AES_MR_OPMOD_OFB;
+	} else if (dd->flags & AES_FLAGS_CTR) {
+		valmr |= AES_MR_OPMOD_CTR;
+	} else {
+		valmr |= AES_MR_OPMOD_ECB;
+	}
+
+	if (dd->flags & AES_FLAGS_ENCRYPT)
+		valmr |= AES_MR_CYPHER_ENC;
+
+	if (dd->total > ATMEL_AES_DMA_THRESHOLD) {
+		valmr |= AES_MR_SMOD_IDATAR0;
+		if (dd->flags & AES_FLAGS_DUALBUFF)
+			valmr |= AES_MR_DUALBUFF;
+	} else {
+		valmr |= AES_MR_SMOD_AUTO;
+	}
+
+	atmel_aes_write(dd, AES_CR, valcr);
+	atmel_aes_write(dd, AES_MR, valmr);
+
+	atmel_aes_write_n(dd, AES_KEYWR(0), dd->ctx->key,
+						dd->ctx->keylen >> 2);
+
+	if (((dd->flags & AES_FLAGS_CBC) || (dd->flags & AES_FLAGS_CFB) ||
+	   (dd->flags & AES_FLAGS_OFB) || (dd->flags & AES_FLAGS_CTR)) &&
+	   dd->req->info) {
+		atmel_aes_write_n(dd, AES_IVR(0), dd->req->info, 4);
+	}
+
+	return 0;
+}
+
+static int atmel_aes_handle_queue(struct atmel_aes_dev *dd,
+			       struct ablkcipher_request *req)
+{
+	struct crypto_async_request *async_req, *backlog;
+	struct atmel_aes_ctx *ctx;
+	struct atmel_aes_reqctx *rctx;
+	unsigned long flags;
+	int err, ret = 0;
+
+	spin_lock_irqsave(&dd->lock, flags);
+	if (req)
+		ret = ablkcipher_enqueue_request(&dd->queue, req);
+	if (dd->flags & AES_FLAGS_BUSY) {
+		spin_unlock_irqrestore(&dd->lock, flags);
+		return ret;
+	}
+	backlog = crypto_get_backlog(&dd->queue);
+	async_req = crypto_dequeue_request(&dd->queue);
+	if (async_req)
+		dd->flags |= AES_FLAGS_BUSY;
+	spin_unlock_irqrestore(&dd->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = ablkcipher_request_cast(async_req);
+
+	/* assign new request to device */
+	dd->req = req;
+	dd->total = req->nbytes;
+	dd->in_sg = req->src;
+	dd->out_sg = req->dst;
+
+	rctx = ablkcipher_request_ctx(req);
+	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	rctx->mode &= AES_FLAGS_MODE_MASK;
+	dd->flags = (dd->flags & ~AES_FLAGS_MODE_MASK) | rctx->mode;
+	dd->ctx = ctx;
+	ctx->dd = dd;
+
+	err = atmel_aes_write_ctrl(dd);
+	if (!err) {
+		if (dd->total > ATMEL_AES_DMA_THRESHOLD)
+			err = atmel_aes_crypt_dma_start(dd);
+		else
+			err = atmel_aes_crypt_cpu_start(dd);
+	}
+	if (err) {
+		/* aes_task will not finish it, so do it here */
+		atmel_aes_finish_req(dd, err);
+		tasklet_schedule(&dd->queue_task);
+	}
+
+	return ret;
+}
+
+static int atmel_aes_crypt_dma_stop(struct atmel_aes_dev *dd)
+{
+	int err = -EINVAL;
+
+	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;
+	}
+
+	return err;
+}
+
+static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
+{
+	struct atmel_aes_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	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;
+	}
+
+	dd = atmel_aes_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
+
+	rctx->mode = mode;
+
+	return atmel_aes_handle_queue(dd, req);
+}
+
+static bool atmel_aes_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_aes_dma_init(struct atmel_aes_dev *dd)
+{
+	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) {
+
+		/* 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_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.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.device_fc = false;
+
+		return 0;
+	} else {
+		return -ENODEV;
+	}
+
+err_dma_out:
+	dma_release_channel(dd->dma_lch_in.chan);
+err_dma_in:
+	return err;
+}
+
+static void atmel_aes_dma_cleanup(struct atmel_aes_dev *dd)
+{
+	dma_release_channel(dd->dma_lch_in.chan);
+	dma_release_channel(dd->dma_lch_out.chan);
+}
+
+static int atmel_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	struct atmel_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+		   keylen != AES_KEYSIZE_256) {
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int atmel_aes_ecb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT);
+}
+
+static int atmel_aes_ecb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		0);
+}
+
+static int atmel_aes_cbc_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CBC);
+}
+
+static int atmel_aes_cbc_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CBC);
+}
+
+static int atmel_aes_ofb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_OFB);
+}
+
+static int atmel_aes_ofb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_OFB);
+}
+
+static int atmel_aes_cfb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB);
+}
+
+static int atmel_aes_cfb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CFB);
+}
+
+static int atmel_aes_cfb64_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB64);
+}
+
+static int atmel_aes_cfb64_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CFB | AES_FLAGS_CFB64);
+}
+
+static int atmel_aes_cfb32_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB32);
+}
+
+static int atmel_aes_cfb32_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CFB | AES_FLAGS_CFB32);
+}
+
+static int atmel_aes_cfb16_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB16);
+}
+
+static int atmel_aes_cfb16_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CFB | AES_FLAGS_CFB16);
+}
+
+static int atmel_aes_cfb8_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT |	AES_FLAGS_CFB | AES_FLAGS_CFB8);
+}
+
+static int atmel_aes_cfb8_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CFB | AES_FLAGS_CFB8);
+}
+
+static int atmel_aes_ctr_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_ENCRYPT | AES_FLAGS_CTR);
+}
+
+static int atmel_aes_ctr_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_aes_crypt(req,
+		AES_FLAGS_CTR);
+}
+
+static int atmel_aes_cra_init(struct crypto_tfm *tfm)
+{
+	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+
+	return 0;
+}
+
+static void atmel_aes_cra_exit(struct crypto_tfm *tfm)
+{
+}
+
+static struct crypto_alg aes_algs[] = {
+{
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "atmel-ecb-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_ecb_encrypt,
+		.decrypt	= atmel_aes_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "atmel-cbc-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cbc_encrypt,
+		.decrypt	= atmel_aes_cbc_decrypt,
+	}
+},
+{
+	.cra_name		= "ofb(aes)",
+	.cra_driver_name	= "atmel-ofb-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_ofb_encrypt,
+		.decrypt	= atmel_aes_ofb_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb(aes)",
+	.cra_driver_name	= "atmel-cfb-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cfb_encrypt,
+		.decrypt	= atmel_aes_cfb_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb32(aes)",
+	.cra_driver_name	= "atmel-cfb32-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cfb32_encrypt,
+		.decrypt	= atmel_aes_cfb32_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb16(aes)",
+	.cra_driver_name	= "atmel-cfb16-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cfb16_encrypt,
+		.decrypt	= atmel_aes_cfb16_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb8(aes)",
+	.cra_driver_name	= "atmel-cfb8-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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cfb8_encrypt,
+		.decrypt	= atmel_aes_cfb8_decrypt,
+	}
+},
+{
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "atmel-ctr-aes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_ctr_encrypt,
+		.decrypt	= atmel_aes_ctr_decrypt,
+	}
+},
+};
+
+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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_aes_cra_init,
+	.cra_exit		= atmel_aes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= atmel_aes_setkey,
+		.encrypt	= atmel_aes_cfb64_encrypt,
+		.decrypt	= atmel_aes_cfb64_decrypt,
+	}
+},
+};
+
+static void atmel_aes_queue_task(unsigned long data)
+{
+	struct atmel_aes_dev *dd = (struct atmel_aes_dev *)data;
+
+	atmel_aes_handle_queue(dd, NULL);
+}
+
+static void atmel_aes_done_task(unsigned long data)
+{
+	struct atmel_aes_dev *dd = (struct atmel_aes_dev *) data;
+	int err;
+
+	if (!(dd->flags & AES_FLAGS_DMA)) {
+		atmel_aes_read_n(dd, AES_ODATAR(0), (u32 *) dd->buf_out,
+				dd->bufcnt >> 2);
+
+		if (sg_copy_from_buffer(dd->out_sg, dd->nb_out_sg,
+			dd->buf_out, dd->bufcnt))
+			err = 0;
+		else
+			err = -EINVAL;
+
+		goto cpu_end;
+	}
+
+	err = atmel_aes_crypt_dma_stop(dd);
+
+	err = dd->err ? : err;
+
+	if (dd->total && !err) {
+		err = atmel_aes_crypt_dma_start(dd);
+		if (!err)
+			return; /* DMA started. Not fininishing. */
+	}
+
+cpu_end:
+	atmel_aes_finish_req(dd, err);
+	atmel_aes_handle_queue(dd, NULL);
+}
+
+static irqreturn_t atmel_aes_irq(int irq, void *dev_id)
+{
+	struct atmel_aes_dev *aes_dd = dev_id;
+	u32 reg;
+
+	reg = atmel_aes_read(aes_dd, AES_ISR);
+	if (reg & atmel_aes_read(aes_dd, AES_IMR)) {
+		atmel_aes_write(aes_dd, AES_IDR, reg);
+		if (AES_FLAGS_BUSY & aes_dd->flags)
+			tasklet_schedule(&aes_dd->done_task);
+		else
+			dev_warn(aes_dd->dev, "AES interrupt when no active requests.\n");
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd)
+{
+	int i;
+
+	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]);
+}
+
+static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
+{
+	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;
+	}
+
+	atmel_aes_hw_version_init(dd);
+
+	if (dd->hw_version >= 0x130) {
+		INIT_LIST_HEAD(&aes_cfb64_alg[0].cra_list);
+		err = crypto_register_alg(&aes_cfb64_alg[0]);
+		if (err)
+			goto err_aes_cfb64_alg;
+	}
+
+	return 0;
+
+err_aes_cfb64_alg:
+	i = ARRAY_SIZE(aes_algs);
+err_aes_algs:
+	for (j = 0; j < i; j++)
+		crypto_unregister_alg(&aes_algs[j]);
+
+	return err;
+}
+
+static int __devinit atmel_aes_probe(struct platform_device *pdev)
+{
+	struct atmel_aes_dev *aes_dd;
+	struct aes_platform_data	*pdata;
+	struct device *dev = &pdev->dev;
+	struct resource *aes_res;
+	unsigned long aes_phys_size;
+	int err;
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		err = -ENXIO;
+		goto aes_dd_err;
+	}
+
+	aes_dd = kzalloc(sizeof(struct atmel_aes_dev), GFP_KERNEL);
+	if (aes_dd == NULL) {
+		dev_err(dev, "unable to alloc data struct.\n");
+		err = -ENOMEM;
+		goto aes_dd_err;
+	}
+
+	aes_dd->dev = dev;
+
+	platform_set_drvdata(pdev, aes_dd);
+
+	INIT_LIST_HEAD(&aes_dd->list);
+
+	tasklet_init(&aes_dd->done_task, atmel_aes_done_task,
+					(unsigned long)aes_dd);
+	tasklet_init(&aes_dd->queue_task, atmel_aes_queue_task,
+					(unsigned long)aes_dd);
+
+	crypto_init_queue(&aes_dd->queue, ATMEL_AES_QUEUE_LENGTH);
+
+	aes_dd->irq = -1;
+
+	/* Get the base address */
+	aes_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!aes_res) {
+		dev_err(dev, "no MEM resource info\n");
+		err = -ENODEV;
+		goto res_err;
+	}
+	aes_dd->phys_base = aes_res->start;
+	aes_phys_size = resource_size(aes_res);
+
+	/* Get the IRQ */
+	aes_dd->irq = platform_get_irq(pdev,  0);
+	if (aes_dd->irq < 0) {
+		dev_err(dev, "no IRQ resource info\n");
+		err = aes_dd->irq;
+		goto aes_irq_err;
+	}
+
+	err = request_irq(aes_dd->irq, atmel_aes_irq, IRQF_SHARED, "atmel-aes",
+						aes_dd);
+	if (err) {
+		dev_err(dev, "unable to request aes irq.\n");
+		goto aes_irq_err;
+	}
+
+	/* Initializing the clock */
+	aes_dd->iclk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(aes_dd->iclk)) {
+		dev_err(dev, "clock intialization failed.\n");
+		err = PTR_ERR(aes_dd->iclk);
+		goto clk_err;
+	}
+
+	aes_dd->io_base = ioremap(aes_dd->phys_base, aes_phys_size);
+	if (!aes_dd->io_base) {
+		dev_err(dev, "can't ioremap\n");
+		err = -ENOMEM;
+		goto aes_io_err;
+	}
+
+	err = atmel_aes_dma_init(aes_dd);
+	if (err)
+		goto err_aes_dma;
+
+	spin_lock(&atmel_aes.lock);
+	list_add_tail(&aes_dd->list, &atmel_aes.dev_list);
+	spin_unlock(&atmel_aes.lock);
+
+	err = atmel_aes_register_algs(aes_dd);
+	if (err)
+		goto err_algs;
+
+	dev_info(dev, "Atmel AES\n");
+
+	return 0;
+
+err_algs:
+	spin_lock(&atmel_aes.lock);
+	list_del(&aes_dd->list);
+	spin_unlock(&atmel_aes.lock);
+	atmel_aes_dma_cleanup(aes_dd);
+err_aes_dma:
+	iounmap(aes_dd->io_base);
+aes_io_err:
+	clk_put(aes_dd->iclk);
+clk_err:
+	free_irq(aes_dd->irq, aes_dd);
+aes_irq_err:
+res_err:
+	tasklet_kill(&aes_dd->done_task);
+	tasklet_kill(&aes_dd->queue_task);
+	kfree(aes_dd);
+	aes_dd = NULL;
+aes_dd_err:
+	dev_err(dev, "initialization failed.\n");
+
+	return err;
+}
+
+static int __devexit atmel_aes_remove(struct platform_device *pdev)
+{
+	static struct atmel_aes_dev *aes_dd;
+
+	aes_dd = platform_get_drvdata(pdev);
+	if (!aes_dd)
+		return -ENODEV;
+	spin_lock(&atmel_aes.lock);
+	list_del(&aes_dd->list);
+	spin_unlock(&atmel_aes.lock);
+
+	atmel_aes_unregister_algs(aes_dd);
+
+	tasklet_kill(&aes_dd->done_task);
+	tasklet_kill(&aes_dd->queue_task);
+
+	atmel_aes_dma_cleanup(aes_dd);
+
+	iounmap(aes_dd->io_base);
+
+	clk_put(aes_dd->iclk);
+
+	if (aes_dd->irq > 0)
+		free_irq(aes_dd->irq, aes_dd);
+
+	kfree(aes_dd);
+	aes_dd = NULL;
+
+	return 0;
+}
+
+static struct platform_driver atmel_aes_driver = {
+	.probe		= atmel_aes_probe,
+	.remove		= __devexit_p(atmel_aes_remove),
+	.driver		= {
+		.name	= "atmel_aes",
+		.owner	= THIS_MODULE,
+	},
+};
+
+module_platform_driver(atmel_aes_driver);
+
+MODULE_DESCRIPTION("Atmel AES hw acceleration support.");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Nicolas Royer - Eukréa Electromatique");
diff --git a/drivers/crypto/atmel-sha-regs.h b/drivers/crypto/atmel-sha-regs.h
new file mode 100644
index 0000000..dc53a20
--- /dev/null
+++ b/drivers/crypto/atmel-sha-regs.h
@@ -0,0 +1,46 @@
+#ifndef __ATMEL_SHA_REGS_H__
+#define __ATMEL_SHA_REGS_H__
+
+#define SHA_REG_DIGEST(x)		(0x80 + ((x) * 0x04))
+#define SHA_REG_DIN(x)			(0x40 + ((x) * 0x04))
+
+#define SHA_CR				0x00
+#define SHA_CR_START			(1 << 0)
+#define SHA_CR_FIRST			(1 << 4)
+#define SHA_CR_SWRST			(1 << 8)
+
+#define SHA_MR				0x04
+#define SHA_MR_MODE_MASK		(0x3 << 0)
+#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_IER				0x10
+#define SHA_IDR				0x14
+#define SHA_IMR				0x18
+#define SHA_ISR				0x1C
+#define SHA_INT_DATARDY			(1 << 0)
+#define SHA_INT_ENDTX			(1 << 1)
+#define SHA_INT_TXBUFE			(1 << 2)
+#define SHA_INT_URAD			(1 << 8)
+#define SHA_ISR_URAT_MASK		(0x7 << 12)
+#define SHA_ISR_URAT_IDR		(0x0 << 12)
+#define SHA_ISR_URAT_ODR		(0x1 << 12)
+#define SHA_ISR_URAT_MR			(0x2 << 12)
+#define SHA_ISR_URAT_WO			(0x5 << 12)
+
+#define SHA_TPR				0x108
+#define SHA_TCR				0x10C
+#define SHA_TNPR			0x118
+#define SHA_TNCR			0x11C
+#define SHA_PTCR			0x120
+#define SHA_PTCR_TXTEN		(1 << 8)
+#define SHA_PTCR_TXTDIS		(1 << 9)
+#define SHA_PTSR			0x124
+#define SHA_PTSR_TXTEN		(1 << 8)
+
+#endif /* __ATMEL_SHA_REGS_H__ */
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
new file mode 100644
index 0000000..f938b9d
--- /dev/null
+++ b/drivers/crypto/atmel-sha.c
@@ -0,0 +1,1112 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for ATMEL SHA1/SHA256 HW acceleration.
+ *
+ * Copyright (c) 2012 Eukréa Electromatique - ATMEL
+ * Author: Nicolas Royer <nicolas@eukrea.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.
+ *
+ * Some ideas are from omap-sham.c drivers.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/hw_random.h>
+#include <linux/platform_device.h>
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include <linux/cryptohash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/algapi.h>
+#include <crypto/sha.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+#include "atmel-sha-regs.h"
+
+/* SHA flags */
+#define SHA_FLAGS_BUSY			BIT(0)
+#define	SHA_FLAGS_FINAL			BIT(1)
+#define SHA_FLAGS_DMA_ACTIVE	BIT(2)
+#define SHA_FLAGS_OUTPUT_READY	BIT(3)
+#define SHA_FLAGS_INIT			BIT(4)
+#define SHA_FLAGS_CPU			BIT(5)
+#define SHA_FLAGS_DMA_READY		BIT(6)
+
+#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_OP_UPDATE	1
+#define SHA_OP_FINAL	2
+
+#define SHA_BUFFER_LEN		PAGE_SIZE
+
+#define ATMEL_SHA_DMA_THRESHOLD		56
+
+
+struct atmel_sha_dev;
+
+struct atmel_sha_reqctx {
+	struct atmel_sha_dev	*dd;
+	unsigned long	flags;
+	unsigned long	op;
+
+	u8	digest[SHA256_DIGEST_SIZE] __aligned(sizeof(u32));
+	size_t	digcnt;
+	size_t	bufcnt;
+	size_t	buflen;
+	dma_addr_t	dma_addr;
+
+	/* walk state */
+	struct scatterlist	*sg;
+	unsigned int	offset;	/* offset in current sg */
+	unsigned int	total;	/* total request */
+
+	u8	buffer[0] __aligned(sizeof(u32));
+};
+
+struct atmel_sha_ctx {
+	struct atmel_sha_dev	*dd;
+
+	unsigned long		flags;
+
+	/* fallback stuff */
+	struct crypto_shash	*fallback;
+
+};
+
+#define ATMEL_SHA_QUEUE_LENGTH	1
+
+struct atmel_sha_dev {
+	struct list_head	list;
+	unsigned long		phys_base;
+	struct device		*dev;
+	struct clk			*iclk;
+	int					irq;
+	void __iomem		*io_base;
+
+	spinlock_t		lock;
+	int			err;
+	struct tasklet_struct	done_task;
+
+	unsigned long		flags;
+	struct crypto_queue	queue;
+	struct ahash_request	*req;
+};
+
+struct atmel_sha_drv {
+	struct list_head	dev_list;
+	spinlock_t		lock;
+};
+
+static struct atmel_sha_drv atmel_sha = {
+	.dev_list = LIST_HEAD_INIT(atmel_sha.dev_list),
+	.lock = __SPIN_LOCK_UNLOCKED(atmel_sha.lock),
+};
+
+static inline u32 atmel_sha_read(struct atmel_sha_dev *dd, u32 offset)
+{
+	return readl_relaxed(dd->io_base + offset);
+}
+
+static inline void atmel_sha_write(struct atmel_sha_dev *dd,
+					u32 offset, u32 value)
+{
+	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;
+
+	while ((ctx->bufcnt < ctx->buflen) && ctx->total) {
+		count = min(ctx->sg->length - ctx->offset, ctx->total);
+		count = min(count, ctx->buflen - ctx->bufcnt);
+
+		if (count <= 0)
+			break;
+
+		scatterwalk_map_and_copy(ctx->buffer + ctx->bufcnt, ctx->sg,
+			ctx->offset, count, 0);
+
+		ctx->bufcnt += count;
+		ctx->offset += count;
+		ctx->total -= count;
+
+		if (ctx->offset == ctx->sg->length) {
+			ctx->sg = sg_next(ctx->sg);
+			if (ctx->sg)
+				ctx->offset = 0;
+			else
+				ctx->total = 0;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * 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.
+ *
+ * padlen is calculated as followed:
+ *  - if message length < 56 bytes then padlen = 56 - message length
+ *  - else padlen = 64 + 56 - 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;
+}
+
+static int atmel_sha_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct atmel_sha_ctx *tctx = crypto_ahash_ctx(tfm);
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	struct atmel_sha_dev *dd = NULL;
+	struct atmel_sha_dev *tmp;
+
+	spin_lock_bh(&atmel_sha.lock);
+	if (!tctx->dd) {
+		list_for_each_entry(tmp, &atmel_sha.dev_list, list) {
+			dd = tmp;
+			break;
+		}
+		tctx->dd = dd;
+	} else {
+		dd = tctx->dd;
+	}
+
+	spin_unlock_bh(&atmel_sha.lock);
+
+	ctx->dd = dd;
+
+	ctx->flags = 0;
+
+	dev_dbg(dd->dev, "init: digest size: %d\n",
+		crypto_ahash_digestsize(tfm));
+
+	if (crypto_ahash_digestsize(tfm) == SHA1_DIGEST_SIZE)
+		ctx->flags |= SHA_FLAGS_SHA1;
+	else if (crypto_ahash_digestsize(tfm) == SHA256_DIGEST_SIZE)
+		ctx->flags |= SHA_FLAGS_SHA256;
+
+	ctx->bufcnt = 0;
+	ctx->digcnt = 0;
+	ctx->buflen = SHA_BUFFER_LEN;
+
+	return 0;
+}
+
+static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+	u32 valcr = 0, valmr = SHA_MR_MODE_AUTO;
+
+	if (likely(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;
+	} else {
+		atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY);
+	}
+
+	if (ctx->flags & SHA_FLAGS_SHA256)
+		valmr |= SHA_MR_ALGO_SHA256;
+
+	/* Setting CR_FIRST only for the first iteration */
+	if (!ctx->digcnt)
+		valcr = SHA_CR_FIRST;
+
+	atmel_sha_write(dd, SHA_CR, valcr);
+	atmel_sha_write(dd, SHA_MR, valmr);
+}
+
+static int atmel_sha_xmit_cpu(struct atmel_sha_dev *dd, const u8 *buf,
+			      size_t length, int final)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+	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);
+
+	atmel_sha_write_ctrl(dd, 0);
+
+	/* should be non-zero before next lines to disable clocks later */
+	ctx->digcnt += length;
+
+	if (final)
+		dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */
+
+	len32 = DIV_ROUND_UP(length, sizeof(u32));
+
+	dd->flags |= SHA_FLAGS_CPU;
+
+	for (count = 0; count < len32; count++)
+		atmel_sha_write(dd, SHA_REG_DIN(count), buffer[count]);
+
+	return -EINPROGRESS;
+}
+
+static int atmel_sha_xmit_pdc(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);
+	int len32;
+
+	dev_dbg(dd->dev, "xmit_pdc: digcnt: %d, length: %d, final: %d\n",
+						ctx->digcnt, length1, final);
+
+	len32 = DIV_ROUND_UP(length1, sizeof(u32));
+	atmel_sha_write(dd, SHA_PTCR, SHA_PTCR_TXTDIS);
+	atmel_sha_write(dd, SHA_TPR, dma_addr1);
+	atmel_sha_write(dd, SHA_TCR, len32);
+
+	len32 = DIV_ROUND_UP(length2, sizeof(u32));
+	atmel_sha_write(dd, SHA_TNPR, dma_addr2);
+	atmel_sha_write(dd, SHA_TNCR, len32);
+
+	atmel_sha_write_ctrl(dd, 1);
+
+	/* should be non-zero before next lines to disable clocks later */
+	ctx->digcnt += length1;
+
+	if (final)
+		dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */
+
+	dd->flags |=  SHA_FLAGS_DMA_ACTIVE;
+
+	/* Start DMA transfer */
+	atmel_sha_write(dd, SHA_PTCR, SHA_PTCR_TXTEN);
+
+	return -EINPROGRESS;
+}
+
+static int atmel_sha_update_cpu(struct atmel_sha_dev *dd)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+	int bufcnt;
+
+	atmel_sha_append_sg(ctx);
+	atmel_sha_fill_padding(ctx, 0);
+
+	bufcnt = ctx->bufcnt;
+	ctx->bufcnt = 0;
+
+	return atmel_sha_xmit_cpu(dd, ctx->buffer, bufcnt, 1);
+}
+
+static int atmel_sha_xmit_dma_map(struct atmel_sha_dev *dd,
+					struct atmel_sha_reqctx *ctx,
+					size_t length, int final)
+{
+	ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer,
+				ctx->buflen + SHA1_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);
+		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);
+}
+
+static int atmel_sha_update_dma_slow(struct atmel_sha_dev *dd)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+	unsigned int final;
+	size_t count;
+
+	atmel_sha_append_sg(ctx);
+
+	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);
+
+	if (final)
+		atmel_sha_fill_padding(ctx, 0);
+
+	if (final || (ctx->bufcnt == ctx->buflen && ctx->total)) {
+		count = ctx->bufcnt;
+		ctx->bufcnt = 0;
+		return atmel_sha_xmit_dma_map(dd, ctx, count, final);
+	}
+
+	return 0;
+}
+
+static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+	unsigned int length, final, tail;
+	struct scatterlist *sg;
+	unsigned int count;
+
+	if (!ctx->total)
+		return 0;
+
+	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);
+
+	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 */
+		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);
+			length -= tail;
+			if (length == 0) {
+				/* offset where to start slow */
+				ctx->offset = length;
+				return atmel_sha_update_dma_slow(dd);
+			}
+		}
+	}
+
+	ctx->total -= length;
+	ctx->offset = length; /* offset where to start slow */
+
+	final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;
+
+	/* Add padding */
+	if (final) {
+		tail = length & (SHA1_BLOCK_SIZE - 1);
+		length -= tail;
+		ctx->total += tail;
+		ctx->offset = length; /* offset where to start slow */
+
+		sg = ctx->sg;
+		atmel_sha_append_sg(ctx);
+
+		atmel_sha_fill_padding(ctx, length);
+
+		ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer,
+			ctx->buflen + SHA1_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);
+			return -EINVAL;
+		}
+
+		if (length == 0) {
+			ctx->flags &= ~SHA_FLAGS_SG;
+			count = ctx->bufcnt;
+			ctx->bufcnt = 0;
+			return atmel_sha_xmit_pdc(dd, ctx->dma_addr, count, 0,
+					0, final);
+		} else {
+			ctx->sg = sg;
+			if (!dma_map_sg(dd->dev, ctx->sg, 1,
+				DMA_TO_DEVICE)) {
+					dev_err(dd->dev, "dma_map_sg  error\n");
+					return -EINVAL;
+			}
+
+			ctx->flags |= SHA_FLAGS_SG;
+
+			count = ctx->bufcnt;
+			ctx->bufcnt = 0;
+			return atmel_sha_xmit_pdc(dd, sg_dma_address(ctx->sg),
+					length, ctx->dma_addr, count, final);
+		}
+	}
+
+	if (!dma_map_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
+		dev_err(dd->dev, "dma_map_sg  error\n");
+		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, sg_dma_address(ctx->sg), length, 0,
+								0, final);
+}
+
+static int atmel_sha_update_dma_stop(struct atmel_sha_dev *dd)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
+
+	if (ctx->flags & SHA_FLAGS_SG) {
+		dma_unmap_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE);
+		if (ctx->sg->length == ctx->offset) {
+			ctx->sg = sg_next(ctx->sg);
+			if (ctx->sg)
+				ctx->offset = 0;
+		}
+		if (ctx->flags & SHA_FLAGS_PAD)
+			dma_unmap_single(dd->dev, ctx->dma_addr,
+				ctx->buflen + SHA1_BLOCK_SIZE, DMA_TO_DEVICE);
+	} else {
+		dma_unmap_single(dd->dev, ctx->dma_addr, ctx->buflen +
+						SHA1_BLOCK_SIZE, DMA_TO_DEVICE);
+	}
+
+	return 0;
+}
+
+static int atmel_sha_update_req(struct atmel_sha_dev *dd)
+{
+	struct ahash_request *req = dd->req;
+	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);
+
+	if (ctx->flags & SHA_FLAGS_CPU)
+		err = atmel_sha_update_cpu(dd);
+	else
+		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);
+
+	return err;
+}
+
+static int atmel_sha_final_req(struct atmel_sha_dev *dd)
+{
+	struct ahash_request *req = dd->req;
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	int err = 0;
+	int count;
+
+	if (ctx->bufcnt >= ATMEL_SHA_DMA_THRESHOLD) {
+		atmel_sha_fill_padding(ctx, 0);
+		count = ctx->bufcnt;
+		ctx->bufcnt = 0;
+		err = atmel_sha_xmit_dma_map(dd, ctx, count, 1);
+	}
+	/* faster to handle last block with cpu */
+	else {
+		atmel_sha_fill_padding(ctx, 0);
+		count = ctx->bufcnt;
+		ctx->bufcnt = 0;
+		err = atmel_sha_xmit_cpu(dd, ctx->buffer, count, 1);
+	}
+
+	dev_dbg(dd->dev, "final_req: err: %d\n", err);
+
+	return err;
+}
+
+static void atmel_sha_copy_hash(struct ahash_request *req)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	u32 *hash = (u32 *)ctx->digest;
+	int i;
+
+	if (likely(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
+		for (i = 0; i < SHA256_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)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	if (!req->result)
+		return;
+
+	if (likely(ctx->flags & SHA_FLAGS_SHA1))
+		memcpy(req->result, ctx->digest, SHA1_DIGEST_SIZE);
+	else
+		memcpy(req->result, ctx->digest, SHA256_DIGEST_SIZE);
+}
+
+static int atmel_sha_finish(struct ahash_request *req)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	struct atmel_sha_dev *dd = ctx->dd;
+	int err = 0;
+
+	if (ctx->digcnt)
+		atmel_sha_copy_ready_hash(req);
+
+	dev_dbg(dd->dev, "digcnt: %d, bufcnt: %d\n", ctx->digcnt,
+		ctx->bufcnt);
+
+	return err;
+}
+
+static void atmel_sha_finish_req(struct ahash_request *req, int err)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	struct atmel_sha_dev *dd = ctx->dd;
+
+	if (!err) {
+		atmel_sha_copy_hash(req);
+		if (SHA_FLAGS_FINAL & dd->flags)
+			err = atmel_sha_finish(req);
+	} else {
+		ctx->flags |= SHA_FLAGS_ERROR;
+	}
+
+	/* atomic operation is not needed here */
+	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
+			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);
+
+	clk_disable_unprepare(dd->iclk);
+
+	if (req->base.complete)
+		req->base.complete(&req->base, err);
+
+	/* handle new request */
+	tasklet_schedule(&dd->done_task);
+}
+
+static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
+{
+	clk_prepare_enable(dd->iclk);
+
+	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;
+	}
+
+	return 0;
+}
+
+static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
+				  struct ahash_request *req)
+{
+	struct crypto_async_request *async_req, *backlog;
+	struct atmel_sha_reqctx *ctx;
+	unsigned long flags;
+	int err = 0, ret = 0;
+
+	spin_lock_irqsave(&dd->lock, flags);
+	if (req)
+		ret = ahash_enqueue_request(&dd->queue, req);
+
+	if (SHA_FLAGS_BUSY & dd->flags) {
+		spin_unlock_irqrestore(&dd->lock, flags);
+		return ret;
+	}
+
+	backlog = crypto_get_backlog(&dd->queue);
+	async_req = crypto_dequeue_request(&dd->queue);
+	if (async_req)
+		dd->flags |= SHA_FLAGS_BUSY;
+
+	spin_unlock_irqrestore(&dd->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = ahash_request_cast(async_req);
+	dd->req = req;
+	ctx = ahash_request_ctx(req);
+
+	dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %d\n",
+						ctx->op, req->nbytes);
+
+	err = atmel_sha_hw_init(dd);
+
+	if (err)
+		goto err1;
+
+	if (ctx->op == SHA_OP_UPDATE) {
+		err = atmel_sha_update_req(dd);
+		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);
+	}
+
+err1:
+	if (err != -EINPROGRESS)
+		/* done_task will not finish it, so do it here */
+		atmel_sha_finish_req(req, err);
+
+	dev_dbg(dd->dev, "exit, err: %d\n", err);
+
+	return ret;
+}
+
+static int atmel_sha_enqueue(struct ahash_request *req, unsigned int op)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+	struct atmel_sha_dev *dd = tctx->dd;
+
+	ctx->op = op;
+
+	return atmel_sha_handle_queue(dd, req);
+}
+
+static int atmel_sha_update(struct ahash_request *req)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	if (!req->nbytes)
+		return 0;
+
+	ctx->total = req->nbytes;
+	ctx->sg = req->src;
+	ctx->offset = 0;
+
+	if (ctx->flags & SHA_FLAGS_FINUP) {
+		if (ctx->bufcnt + ctx->total < ATMEL_SHA_DMA_THRESHOLD)
+			/* faster to use CPU for short transfers */
+			ctx->flags |= SHA_FLAGS_CPU;
+	} else if (ctx->bufcnt + ctx->total < ctx->buflen) {
+		atmel_sha_append_sg(ctx);
+		return 0;
+	}
+	return atmel_sha_enqueue(req, SHA_OP_UPDATE);
+}
+
+static int atmel_sha_final(struct ahash_request *req)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+	struct atmel_sha_dev *dd = tctx->dd;
+
+	int err = 0;
+
+	ctx->flags |= SHA_FLAGS_FINUP;
+
+	if (ctx->flags & SHA_FLAGS_ERROR)
+		return 0; /* uncompleted hash is not needed */
+
+	if (ctx->bufcnt) {
+		return atmel_sha_enqueue(req, SHA_OP_FINAL);
+	} else if (!(ctx->flags & SHA_FLAGS_PAD)) { /* add padding */
+		err = atmel_sha_hw_init(dd);
+		if (err)
+			goto err1;
+
+		dd->flags |= SHA_FLAGS_BUSY;
+		err = atmel_sha_final_req(dd);
+	} else {
+		/* copy ready hash (+ finalize hmac) */
+		return atmel_sha_finish(req);
+	}
+
+err1:
+	if (err != -EINPROGRESS)
+		/* done_task will not finish it, so do it here */
+		atmel_sha_finish_req(req, err);
+
+	return err;
+}
+
+static int atmel_sha_finup(struct ahash_request *req)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+	int err1, err2;
+
+	ctx->flags |= SHA_FLAGS_FINUP;
+
+	err1 = atmel_sha_update(req);
+	if (err1 == -EINPROGRESS || err1 == -EBUSY)
+		return err1;
+
+	/*
+	 * final() has to be always called to cleanup resources
+	 * even if udpate() failed, except EINPROGRESS
+	 */
+	err2 = atmel_sha_final(req);
+
+	return err1 ?: err2;
+}
+
+static int atmel_sha_digest(struct ahash_request *req)
+{
+	return atmel_sha_init(req) ?: atmel_sha_finup(req);
+}
+
+static int atmel_sha_cra_init_alg(struct crypto_tfm *tfm, const char *alg_base)
+{
+	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(tfm);
+	const char *alg_name = crypto_tfm_alg_name(tfm);
+
+	/* Allocate a fallback and abort if it failed. */
+	tctx->fallback = crypto_alloc_shash(alg_name, 0,
+					    CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(tctx->fallback)) {
+		pr_err("atmel-sha: fallback driver '%s' could not be loaded.\n",
+				alg_name);
+		return PTR_ERR(tctx->fallback);
+	}
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct atmel_sha_reqctx) +
+				 SHA_BUFFER_LEN + SHA256_BLOCK_SIZE);
+
+	return 0;
+}
+
+static int atmel_sha_cra_init(struct crypto_tfm *tfm)
+{
+	return atmel_sha_cra_init_alg(tfm, NULL);
+}
+
+static void atmel_sha_cra_exit(struct crypto_tfm *tfm)
+{
+	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_shash(tctx->fallback);
+	tctx->fallback = NULL;
+}
+
+static struct ahash_alg sha_algs[] = {
+{
+	.init		= atmel_sha_init,
+	.update		= atmel_sha_update,
+	.final		= atmel_sha_final,
+	.finup		= atmel_sha_finup,
+	.digest		= atmel_sha_digest,
+	.halg = {
+		.digestsize	= SHA1_DIGEST_SIZE,
+		.base	= {
+			.cra_name		= "sha1",
+			.cra_driver_name	= "atmel-sha1",
+			.cra_priority		= 100,
+			.cra_flags		= CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize		= SHA1_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,
+		}
+	}
+},
+{
+	.init		= atmel_sha_init,
+	.update		= atmel_sha_update,
+	.final		= atmel_sha_final,
+	.finup		= atmel_sha_finup,
+	.digest		= atmel_sha_digest,
+	.halg = {
+		.digestsize	= SHA256_DIGEST_SIZE,
+		.base	= {
+			.cra_name		= "sha256",
+			.cra_driver_name	= "atmel-sha256",
+			.cra_priority		= 100,
+			.cra_flags		= CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+			.cra_blocksize		= SHA256_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 void atmel_sha_done_task(unsigned long data)
+{
+	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;
+	int err = 0;
+
+	if (!(SHA_FLAGS_BUSY & dd->flags)) {
+		atmel_sha_handle_queue(dd, NULL);
+		return;
+	}
+
+	if (SHA_FLAGS_CPU & dd->flags) {
+		if (SHA_FLAGS_OUTPUT_READY & dd->flags) {
+			dd->flags &= ~SHA_FLAGS_OUTPUT_READY;
+			goto finish;
+		}
+	} else if (SHA_FLAGS_DMA_READY & dd->flags) {
+		if (SHA_FLAGS_DMA_ACTIVE & dd->flags) {
+			dd->flags &= ~SHA_FLAGS_DMA_ACTIVE;
+			atmel_sha_update_dma_stop(dd);
+			if (dd->err) {
+				err = dd->err;
+				goto finish;
+			}
+		}
+		if (SHA_FLAGS_OUTPUT_READY & dd->flags) {
+			/* hash or semi-hash ready */
+			dd->flags &= ~(SHA_FLAGS_DMA_READY |
+						SHA_FLAGS_OUTPUT_READY);
+			err = atmel_sha_update_dma_start(dd);
+			if (err != -EINPROGRESS)
+				goto finish;
+		}
+	}
+	return;
+
+finish:
+	/* finish curent request */
+	atmel_sha_finish_req(dd->req, err);
+}
+
+static irqreturn_t atmel_sha_irq(int irq, void *dev_id)
+{
+	struct atmel_sha_dev *sha_dd = dev_id;
+	u32 reg;
+
+	reg = atmel_sha_read(sha_dd, SHA_ISR);
+	if (reg & atmel_sha_read(sha_dd, SHA_IMR)) {
+		atmel_sha_write(sha_dd, SHA_IDR, reg);
+		if (SHA_FLAGS_BUSY & sha_dd->flags) {
+			sha_dd->flags |= SHA_FLAGS_OUTPUT_READY;
+			if (!(SHA_FLAGS_CPU & sha_dd->flags))
+				sha_dd->flags |= SHA_FLAGS_DMA_READY;
+			tasklet_schedule(&sha_dd->done_task);
+		} else {
+			dev_warn(sha_dd->dev, "SHA interrupt when no active requests.\n");
+		}
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+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]);
+}
+
+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]);
+		if (err)
+			goto err_sha_algs;
+	}
+
+	return 0;
+
+err_sha_algs:
+	for (j = 0; j < i; j++)
+		crypto_unregister_ahash(&sha_algs[j]);
+
+	return err;
+}
+
+static int __devinit atmel_sha_probe(struct platform_device *pdev)
+{
+	struct atmel_sha_dev *sha_dd;
+	struct device *dev = &pdev->dev;
+	struct resource *sha_res;
+	unsigned long sha_phys_size;
+	int err;
+
+	sha_dd = kzalloc(sizeof(struct atmel_sha_dev), GFP_KERNEL);
+	if (sha_dd == NULL) {
+		dev_err(dev, "unable to alloc data struct.\n");
+		err = -ENOMEM;
+		goto sha_dd_err;
+	}
+
+	sha_dd->dev = dev;
+
+	platform_set_drvdata(pdev, sha_dd);
+
+	INIT_LIST_HEAD(&sha_dd->list);
+
+	tasklet_init(&sha_dd->done_task, atmel_sha_done_task,
+					(unsigned long)sha_dd);
+
+	crypto_init_queue(&sha_dd->queue, ATMEL_SHA_QUEUE_LENGTH);
+
+	sha_dd->irq = -1;
+
+	/* Get the base address */
+	sha_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!sha_res) {
+		dev_err(dev, "no MEM resource info\n");
+		err = -ENODEV;
+		goto res_err;
+	}
+	sha_dd->phys_base = sha_res->start;
+	sha_phys_size = resource_size(sha_res);
+
+	/* Get the IRQ */
+	sha_dd->irq = platform_get_irq(pdev,  0);
+	if (sha_dd->irq < 0) {
+		dev_err(dev, "no IRQ resource info\n");
+		err = sha_dd->irq;
+		goto res_err;
+	}
+
+	err = request_irq(sha_dd->irq, atmel_sha_irq, IRQF_SHARED, "atmel-sha",
+						sha_dd);
+	if (err) {
+		dev_err(dev, "unable to request sha irq.\n");
+		goto res_err;
+	}
+
+	/* Initializing the clock */
+	sha_dd->iclk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(sha_dd->iclk)) {
+		dev_err(dev, "clock intialization failed.\n");
+		err = PTR_ERR(sha_dd->iclk);
+		goto clk_err;
+	}
+
+	sha_dd->io_base = ioremap(sha_dd->phys_base, sha_phys_size);
+	if (!sha_dd->io_base) {
+		dev_err(dev, "can't ioremap\n");
+		err = -ENOMEM;
+		goto sha_io_err;
+	}
+
+	spin_lock(&atmel_sha.lock);
+	list_add_tail(&sha_dd->list, &atmel_sha.dev_list);
+	spin_unlock(&atmel_sha.lock);
+
+	err = atmel_sha_register_algs(sha_dd);
+	if (err)
+		goto err_algs;
+
+	dev_info(dev, "Atmel SHA1/SHA256\n");
+
+	return 0;
+
+err_algs:
+	spin_lock(&atmel_sha.lock);
+	list_del(&sha_dd->list);
+	spin_unlock(&atmel_sha.lock);
+	iounmap(sha_dd->io_base);
+sha_io_err:
+	clk_put(sha_dd->iclk);
+clk_err:
+	free_irq(sha_dd->irq, sha_dd);
+res_err:
+	tasklet_kill(&sha_dd->done_task);
+	kfree(sha_dd);
+	sha_dd = NULL;
+sha_dd_err:
+	dev_err(dev, "initialization failed.\n");
+
+	return err;
+}
+
+static int __devexit atmel_sha_remove(struct platform_device *pdev)
+{
+	static struct atmel_sha_dev *sha_dd;
+
+	sha_dd = platform_get_drvdata(pdev);
+	if (!sha_dd)
+		return -ENODEV;
+	spin_lock(&atmel_sha.lock);
+	list_del(&sha_dd->list);
+	spin_unlock(&atmel_sha.lock);
+
+	atmel_sha_unregister_algs(sha_dd);
+
+	tasklet_kill(&sha_dd->done_task);
+
+	iounmap(sha_dd->io_base);
+
+	clk_put(sha_dd->iclk);
+
+	if (sha_dd->irq >= 0)
+		free_irq(sha_dd->irq, sha_dd);
+
+	kfree(sha_dd);
+	sha_dd = NULL;
+
+	return 0;
+}
+
+static struct platform_driver atmel_sha_driver = {
+	.probe		= atmel_sha_probe,
+	.remove		= __devexit_p(atmel_sha_remove),
+	.driver		= {
+		.name	= "atmel_sha",
+		.owner	= THIS_MODULE,
+	},
+};
+
+module_platform_driver(atmel_sha_driver);
+
+MODULE_DESCRIPTION("Atmel SHA1/SHA256 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
new file mode 100644
index 0000000..5ac2a90
--- /dev/null
+++ b/drivers/crypto/atmel-tdes-regs.h
@@ -0,0 +1,89 @@
+#ifndef __ATMEL_TDES_REGS_H__
+#define __ATMEL_TDES_REGS_H__
+
+#define TDES_CR			0x00
+#define TDES_CR_START			(1 << 0)
+#define TDES_CR_SWRST			(1 << 8)
+#define TDES_CR_LOADSEED		(1 << 16)
+
+#define	TDES_MR			0x04
+#define TDES_MR_CYPHER_DEC		(0 << 0)
+#define TDES_MR_CYPHER_ENC		(1 << 0)
+#define TDES_MR_TDESMOD_MASK	(0x3 << 1)
+#define TDES_MR_TDESMOD_DES		(0x0 << 1)
+#define TDES_MR_TDESMOD_TDES	(0x1 << 1)
+#define TDES_MR_TDESMOD_XTEA	(0x2 << 1)
+#define TDES_MR_KEYMOD_3KEY		(0 << 4)
+#define TDES_MR_KEYMOD_2KEY		(1 << 4)
+#define TDES_MR_SMOD_MASK		(0x3 << 8)
+#define TDES_MR_SMOD_MANUAL		(0x0 << 8)
+#define TDES_MR_SMOD_AUTO		(0x1 << 8)
+#define TDES_MR_SMOD_PDC		(0x2 << 8)
+#define TDES_MR_OPMOD_MASK		(0x3 << 12)
+#define TDES_MR_OPMOD_ECB		(0x0 << 12)
+#define TDES_MR_OPMOD_CBC		(0x1 << 12)
+#define TDES_MR_OPMOD_OFB		(0x2 << 12)
+#define TDES_MR_OPMOD_CFB		(0x3 << 12)
+#define TDES_MR_LOD				(0x1 << 15)
+#define TDES_MR_CFBS_MASK		(0x3 << 16)
+#define TDES_MR_CFBS_64b		(0x0 << 16)
+#define TDES_MR_CFBS_32b		(0x1 << 16)
+#define TDES_MR_CFBS_16b		(0x2 << 16)
+#define TDES_MR_CFBS_8b			(0x3 << 16)
+#define TDES_MR_CKEY_MASK		(0xF << 20)
+#define TDES_MR_CKEY_OFFSET		20
+#define TDES_MR_CTYPE_MASK		(0x3F << 24)
+#define TDES_MR_CTYPE_OFFSET	24
+
+#define	TDES_IER		0x10
+#define	TDES_IDR		0x14
+#define	TDES_IMR		0x18
+#define	TDES_ISR		0x1C
+#define TDES_INT_DATARDY		(1 << 0)
+#define TDES_INT_ENDRX			(1 << 1)
+#define TDES_INT_ENDTX			(1 << 2)
+#define TDES_INT_RXBUFF			(1 << 3)
+#define TDES_INT_TXBUFE			(1 << 4)
+#define TDES_INT_URAD			(1 << 8)
+#define TDES_ISR_URAT_MASK		(0x3 << 12)
+#define TDES_ISR_URAT_IDR		(0x0 << 12)
+#define TDES_ISR_URAT_ODR		(0x1 << 12)
+#define TDES_ISR_URAT_MR		(0x2 << 12)
+#define TDES_ISR_URAT_WO		(0x3 << 12)
+
+
+#define	TDES_KEY1W1R	0x20
+#define	TDES_KEY1W2R	0x24
+#define	TDES_KEY2W1R	0x28
+#define	TDES_KEY2W2R	0x2C
+#define	TDES_KEY3W1R	0x30
+#define	TDES_KEY3W2R	0x34
+#define	TDES_IDATA1R	0x40
+#define	TDES_IDATA2R	0x44
+#define	TDES_ODATA1R	0x50
+#define	TDES_ODATA2R	0x54
+#define	TDES_IV1R		0x60
+#define	TDES_IV2R		0x64
+
+#define	TDES_XTEARNDR	0x70
+#define	TDES_XTEARNDR_XTEA_RNDS_MASK	(0x3F << 0)
+#define	TDES_XTEARNDR_XTEA_RNDS_OFFSET	0
+
+#define TDES_RPR		0x100
+#define TDES_RCR		0x104
+#define TDES_TPR		0x108
+#define TDES_TCR		0x10C
+#define TDES_RNPR		0x118
+#define TDES_RNCR		0x11C
+#define TDES_TNPR		0x118
+#define TDES_TNCR		0x11C
+#define TDES_PTCR		0x120
+#define TDES_PTCR_RXTEN			(1 << 0)
+#define TDES_PTCR_RXTDIS		(1 << 1)
+#define TDES_PTCR_TXTEN			(1 << 8)
+#define TDES_PTCR_TXTDIS		(1 << 9)
+#define TDES_PTSR		0x124
+#define TDES_PTSR_RXTEN			(1 << 0)
+#define TDES_PTSR_TXTEN			(1 << 8)
+
+#endif /* __ATMEL_TDES_REGS_H__ */
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
new file mode 100644
index 0000000..eb2b61e
--- /dev/null
+++ b/drivers/crypto/atmel-tdes.c
@@ -0,0 +1,1215 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for ATMEL DES/TDES HW acceleration.
+ *
+ * Copyright (c) 2012 Eukréa Electromatique - ATMEL
+ * Author: Nicolas Royer <nicolas@eukrea.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.
+ *
+ * Some ideas are from omap-aes.c drivers.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/hw_random.h>
+#include <linux/platform_device.h>
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include <linux/cryptohash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+#include "atmel-tdes-regs.h"
+
+/* TDES flags  */
+#define TDES_FLAGS_MODE_MASK		0x007f
+#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_INIT		BIT(16)
+#define TDES_FLAGS_FAST		BIT(17)
+#define TDES_FLAGS_BUSY		BIT(18)
+
+#define ATMEL_TDES_QUEUE_LENGTH	1
+
+#define CFB8_BLOCK_SIZE		1
+#define CFB16_BLOCK_SIZE	2
+#define CFB32_BLOCK_SIZE	4
+#define CFB64_BLOCK_SIZE	8
+
+
+struct atmel_tdes_dev;
+
+struct atmel_tdes_ctx {
+	struct atmel_tdes_dev *dd;
+
+	int		keylen;
+	u32		key[3*DES_KEY_SIZE / sizeof(u32)];
+	unsigned long	flags;
+};
+
+struct atmel_tdes_reqctx {
+	unsigned long mode;
+};
+
+struct atmel_tdes_dev {
+	struct list_head	list;
+	unsigned long		phys_base;
+	void __iomem		*io_base;
+
+	struct atmel_tdes_ctx	*ctx;
+	struct device		*dev;
+	struct clk			*iclk;
+	int					irq;
+
+	unsigned long		flags;
+	int			err;
+
+	spinlock_t		lock;
+	struct crypto_queue	queue;
+
+	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
+
+	struct ablkcipher_request	*req;
+	size_t				total;
+
+	struct scatterlist	*in_sg;
+	size_t				in_offset;
+	struct scatterlist	*out_sg;
+	size_t				out_offset;
+
+	size_t	buflen;
+	size_t	dma_size;
+
+	void	*buf_in;
+	int		dma_in;
+	dma_addr_t	dma_addr_in;
+
+	void	*buf_out;
+	int		dma_out;
+	dma_addr_t	dma_addr_out;
+};
+
+struct atmel_tdes_drv {
+	struct list_head	dev_list;
+	spinlock_t		lock;
+};
+
+static struct atmel_tdes_drv atmel_tdes = {
+	.dev_list = LIST_HEAD_INIT(atmel_tdes.dev_list),
+	.lock = __SPIN_LOCK_UNLOCKED(atmel_tdes.lock),
+};
+
+static int atmel_tdes_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_tdes_read(struct atmel_tdes_dev *dd, u32 offset)
+{
+	return readl_relaxed(dd->io_base + offset);
+}
+
+static inline void atmel_tdes_write(struct atmel_tdes_dev *dd,
+					u32 offset, u32 value)
+{
+	writel_relaxed(value, dd->io_base + offset);
+}
+
+static void atmel_tdes_write_n(struct atmel_tdes_dev *dd, u32 offset,
+					u32 *value, int count)
+{
+	for (; count--; value++, offset += 4)
+		atmel_tdes_write(dd, offset, *value);
+}
+
+static struct atmel_tdes_dev *atmel_tdes_find_dev(struct atmel_tdes_ctx *ctx)
+{
+	struct atmel_tdes_dev *tdes_dd = NULL;
+	struct atmel_tdes_dev *tmp;
+
+	spin_lock_bh(&atmel_tdes.lock);
+	if (!ctx->dd) {
+		list_for_each_entry(tmp, &atmel_tdes.dev_list, list) {
+			tdes_dd = tmp;
+			break;
+		}
+		ctx->dd = tdes_dd;
+	} else {
+		tdes_dd = ctx->dd;
+	}
+	spin_unlock_bh(&atmel_tdes.lock);
+
+	return tdes_dd;
+}
+
+static int atmel_tdes_hw_init(struct atmel_tdes_dev *dd)
+{
+	clk_prepare_enable(dd->iclk);
+
+	if (!(dd->flags & TDES_FLAGS_INIT)) {
+		atmel_tdes_write(dd, TDES_CR, TDES_CR_SWRST);
+		dd->flags |= TDES_FLAGS_INIT;
+		dd->err = 0;
+	}
+
+	return 0;
+}
+
+static int atmel_tdes_write_ctrl(struct atmel_tdes_dev *dd)
+{
+	int err;
+	u32 valcr = 0, valmr = TDES_MR_SMOD_PDC;
+
+	err = atmel_tdes_hw_init(dd);
+
+	if (err)
+		return err;
+
+	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)) {
+		valmr |= TDES_MR_KEYMOD_3KEY;
+		valmr |= TDES_MR_TDESMOD_TDES;
+	} else if (dd->ctx->keylen > DES_KEY_SIZE) {
+		valmr |= TDES_MR_KEYMOD_2KEY;
+		valmr |= TDES_MR_TDESMOD_TDES;
+	} else {
+		valmr |= TDES_MR_TDESMOD_DES;
+	}
+
+	if (dd->flags & TDES_FLAGS_CBC) {
+		valmr |= TDES_MR_OPMOD_CBC;
+	} else if (dd->flags & TDES_FLAGS_CFB) {
+		valmr |= TDES_MR_OPMOD_CFB;
+
+		if (dd->flags & TDES_FLAGS_CFB8)
+			valmr |= TDES_MR_CFBS_8b;
+		else if (dd->flags & TDES_FLAGS_CFB16)
+			valmr |= TDES_MR_CFBS_16b;
+		else if (dd->flags & TDES_FLAGS_CFB32)
+			valmr |= TDES_MR_CFBS_32b;
+	} else if (dd->flags & TDES_FLAGS_OFB) {
+		valmr |= TDES_MR_OPMOD_OFB;
+	}
+
+	if ((dd->flags & TDES_FLAGS_ENCRYPT) || (dd->flags & TDES_FLAGS_OFB))
+		valmr |= TDES_MR_CYPHER_ENC;
+
+	atmel_tdes_write(dd, TDES_CR, valcr);
+	atmel_tdes_write(dd, TDES_MR, valmr);
+
+	atmel_tdes_write_n(dd, TDES_KEY1W1R, dd->ctx->key,
+						dd->ctx->keylen >> 2);
+
+	if (((dd->flags & TDES_FLAGS_CBC) || (dd->flags & TDES_FLAGS_CFB) ||
+		(dd->flags & TDES_FLAGS_OFB)) && dd->req->info) {
+		atmel_tdes_write_n(dd, TDES_IV1R, dd->req->info, 2);
+	}
+
+	return 0;
+}
+
+static int atmel_tdes_crypt_dma_stop(struct atmel_tdes_dev *dd)
+{
+	int err = 0;
+	size_t count;
+
+	atmel_tdes_write(dd, TDES_PTCR, TDES_PTCR_TXTDIS|TDES_PTCR_RXTDIS);
+
+	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_dma_init(struct atmel_tdes_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 &= ~(DES_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_tdes_dma_cleanup(struct atmel_tdes_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_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;
+	int len32;
+
+	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_CFB) && (dd->flags & TDES_FLAGS_CFB8))
+		len32 = DIV_ROUND_UP(length, sizeof(u8));
+	else if ((dd->flags & TDES_FLAGS_CFB) && (dd->flags & TDES_FLAGS_CFB16))
+		len32 = DIV_ROUND_UP(length, sizeof(u16));
+	else
+		len32 = DIV_ROUND_UP(length, sizeof(u32));
+
+	atmel_tdes_write(dd, TDES_PTCR, TDES_PTCR_TXTDIS|TDES_PTCR_RXTDIS);
+	atmel_tdes_write(dd, TDES_TPR, dma_addr_in);
+	atmel_tdes_write(dd, TDES_TCR, len32);
+	atmel_tdes_write(dd, TDES_RPR, dma_addr_out);
+	atmel_tdes_write(dd, TDES_RCR, len32);
+
+	/* Enable Interrupt */
+	atmel_tdes_write(dd, TDES_IER, TDES_INT_ENDRX);
+
+	/* Start DMA transfer */
+	atmel_tdes_write(dd, TDES_PTCR, TDES_PTCR_TXTEN | TDES_PTCR_RXTEN);
+
+	return 0;
+}
+
+static int atmel_tdes_crypt_dma_start(struct atmel_tdes_dev *dd)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(
+					crypto_ablkcipher_reqtfm(dd->req));
+	int err, fast = 0, in, out;
+	size_t count;
+	dma_addr_t addr_in, addr_out;
+
+	if (sg_is_last(dd->in_sg) && sg_is_last(dd->out_sg)) {
+		/* check for alignment */
+		in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32));
+		out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32));
+
+		fast = in && out;
+	}
+
+	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");
+			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 |= TDES_FLAGS_FAST;
+
+	} else {
+		/* use cache buffers */
+		count = atmel_tdes_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 &= ~TDES_FLAGS_FAST;
+
+	}
+
+	dd->total -= count;
+
+	err = atmel_tdes_crypt_dma(tfm, addr_in, addr_out, count);
+	if (err) {
+		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;
+}
+
+
+static void atmel_tdes_finish_req(struct atmel_tdes_dev *dd, int err)
+{
+	struct ablkcipher_request *req = dd->req;
+
+	clk_disable_unprepare(dd->iclk);
+
+	dd->flags &= ~TDES_FLAGS_BUSY;
+
+	req->base.complete(&req->base, err);
+}
+
+static int atmel_tdes_handle_queue(struct atmel_tdes_dev *dd,
+			       struct ablkcipher_request *req)
+{
+	struct crypto_async_request *async_req, *backlog;
+	struct atmel_tdes_ctx *ctx;
+	struct atmel_tdes_reqctx *rctx;
+	unsigned long flags;
+	int err, ret = 0;
+
+	spin_lock_irqsave(&dd->lock, flags);
+	if (req)
+		ret = ablkcipher_enqueue_request(&dd->queue, req);
+	if (dd->flags & TDES_FLAGS_BUSY) {
+		spin_unlock_irqrestore(&dd->lock, flags);
+		return ret;
+	}
+	backlog = crypto_get_backlog(&dd->queue);
+	async_req = crypto_dequeue_request(&dd->queue);
+	if (async_req)
+		dd->flags |= TDES_FLAGS_BUSY;
+	spin_unlock_irqrestore(&dd->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = ablkcipher_request_cast(async_req);
+
+	/* 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);
+	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	rctx->mode &= TDES_FLAGS_MODE_MASK;
+	dd->flags = (dd->flags & ~TDES_FLAGS_MODE_MASK) | rctx->mode;
+	dd->ctx = ctx;
+	ctx->dd = dd;
+
+	err = atmel_tdes_write_ctrl(dd);
+	if (!err)
+		err = atmel_tdes_crypt_dma_start(dd);
+	if (err) {
+		/* des_task will not finish it, so do it here */
+		atmel_tdes_finish_req(dd, err);
+		tasklet_schedule(&dd->queue_task);
+	}
+
+	return ret;
+}
+
+
+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;
+		}
+	} 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;
+		}
+	} 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;
+	}
+
+	dd = atmel_tdes_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
+
+	rctx->mode = mode;
+
+	return atmel_tdes_handle_queue(dd, req);
+}
+
+static int atmel_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	u32 tmp[DES_EXPKEY_WORDS];
+	int err;
+	struct crypto_tfm *ctfm = crypto_ablkcipher_tfm(tfm);
+
+	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (keylen != DES_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	err = des_ekey(tmp, key);
+	if (err == 0 && (ctfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		ctfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int atmel_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	const char *alg_name;
+
+	alg_name = crypto_tfm_alg_name(crypto_ablkcipher_tfm(tfm));
+
+	/*
+	 * HW bug in cfb 3-keys mode.
+	 */
+	if (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)) {
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int atmel_tdes_ecb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT);
+}
+
+static int atmel_tdes_ecb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, 0);
+}
+
+static int atmel_tdes_cbc_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CBC);
+}
+
+static int atmel_tdes_cbc_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_CBC);
+}
+static int atmel_tdes_cfb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB);
+}
+
+static int atmel_tdes_cfb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_CFB);
+}
+
+static int atmel_tdes_cfb8_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
+						TDES_FLAGS_CFB8);
+}
+
+static int atmel_tdes_cfb8_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB8);
+}
+
+static int atmel_tdes_cfb16_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
+						TDES_FLAGS_CFB16);
+}
+
+static int atmel_tdes_cfb16_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB16);
+}
+
+static int atmel_tdes_cfb32_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_CFB |
+						TDES_FLAGS_CFB32);
+}
+
+static int atmel_tdes_cfb32_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_CFB | TDES_FLAGS_CFB32);
+}
+
+static int atmel_tdes_ofb_encrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_ENCRYPT | TDES_FLAGS_OFB);
+}
+
+static int atmel_tdes_ofb_decrypt(struct ablkcipher_request *req)
+{
+	return atmel_tdes_crypt(req, TDES_FLAGS_OFB);
+}
+
+static int atmel_tdes_cra_init(struct crypto_tfm *tfm)
+{
+	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_tdes_reqctx);
+
+	return 0;
+}
+
+static void atmel_tdes_cra_exit(struct crypto_tfm *tfm)
+{
+}
+
+static struct crypto_alg tdes_algs[] = {
+{
+	.cra_name		= "ecb(des)",
+	.cra_driver_name	= "atmel-ecb-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_ecb_encrypt,
+		.decrypt	= atmel_tdes_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(des)",
+	.cra_driver_name	= "atmel-cbc-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_cbc_encrypt,
+		.decrypt	= atmel_tdes_cbc_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb(des)",
+	.cra_driver_name	= "atmel-cfb-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_cfb_encrypt,
+		.decrypt	= atmel_tdes_cfb_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb8(des)",
+	.cra_driver_name	= "atmel-cfb8-des",
+	.cra_priority		= 100,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CFB8_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_cfb8_encrypt,
+		.decrypt	= atmel_tdes_cfb8_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb16(des)",
+	.cra_driver_name	= "atmel-cfb16-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_cfb16_encrypt,
+		.decrypt	= atmel_tdes_cfb16_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb32(des)",
+	.cra_driver_name	= "atmel-cfb32-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_cfb32_encrypt,
+		.decrypt	= atmel_tdes_cfb32_decrypt,
+	}
+},
+{
+	.cra_name		= "ofb(des)",
+	.cra_driver_name	= "atmel-ofb-des",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_des_setkey,
+		.encrypt	= atmel_tdes_ofb_encrypt,
+		.decrypt	= atmel_tdes_ofb_decrypt,
+	}
+},
+{
+	.cra_name		= "ecb(des3_ede)",
+	.cra_driver_name	= "atmel-ecb-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2 * DES_KEY_SIZE,
+		.max_keysize	= 3 * DES_KEY_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_ecb_encrypt,
+		.decrypt	= atmel_tdes_ecb_decrypt,
+	}
+},
+{
+	.cra_name		= "cbc(des3_ede)",
+	.cra_driver_name	= "atmel-cbc-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 3*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_cbc_encrypt,
+		.decrypt	= atmel_tdes_cbc_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb(des3_ede)",
+	.cra_driver_name	= "atmel-cfb-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 2*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_cfb_encrypt,
+		.decrypt	= atmel_tdes_cfb_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb8(des3_ede)",
+	.cra_driver_name	= "atmel-cfb8-tdes",
+	.cra_priority		= 100,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CFB8_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 2*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_cfb8_encrypt,
+		.decrypt	= atmel_tdes_cfb8_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb16(des3_ede)",
+	.cra_driver_name	= "atmel-cfb16-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 2*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_cfb16_encrypt,
+		.decrypt	= atmel_tdes_cfb16_decrypt,
+	}
+},
+{
+	.cra_name		= "cfb32(des3_ede)",
+	.cra_driver_name	= "atmel-cfb32-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 2*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_cfb32_encrypt,
+		.decrypt	= atmel_tdes_cfb32_decrypt,
+	}
+},
+{
+	.cra_name		= "ofb(des3_ede)",
+	.cra_driver_name	= "atmel-ofb-tdes",
+	.cra_priority		= 100,
+	.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_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= atmel_tdes_cra_init,
+	.cra_exit		= atmel_tdes_cra_exit,
+	.cra_u.ablkcipher = {
+		.min_keysize	= 2*DES_KEY_SIZE,
+		.max_keysize	= 3*DES_KEY_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.setkey		= atmel_tdes_setkey,
+		.encrypt	= atmel_tdes_ofb_encrypt,
+		.decrypt	= atmel_tdes_ofb_decrypt,
+	}
+},
+};
+
+static void atmel_tdes_queue_task(unsigned long data)
+{
+	struct atmel_tdes_dev *dd = (struct atmel_tdes_dev *)data;
+
+	atmel_tdes_handle_queue(dd, NULL);
+}
+
+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);
+
+	err = dd->err ? : err;
+
+	if (dd->total && !err) {
+		err = atmel_tdes_crypt_dma_start(dd);
+		if (!err)
+			return;
+	}
+
+	atmel_tdes_finish_req(dd, err);
+	atmel_tdes_handle_queue(dd, NULL);
+}
+
+static irqreturn_t atmel_tdes_irq(int irq, void *dev_id)
+{
+	struct atmel_tdes_dev *tdes_dd = dev_id;
+	u32 reg;
+
+	reg = atmel_tdes_read(tdes_dd, TDES_ISR);
+	if (reg & atmel_tdes_read(tdes_dd, TDES_IMR)) {
+		atmel_tdes_write(tdes_dd, TDES_IDR, reg);
+		if (TDES_FLAGS_BUSY & tdes_dd->flags)
+			tasklet_schedule(&tdes_dd->done_task);
+		else
+			dev_warn(tdes_dd->dev, "TDES interrupt when no active requests.\n");
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static void atmel_tdes_unregister_algs(struct atmel_tdes_dev *dd)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tdes_algs); i++)
+		crypto_unregister_alg(&tdes_algs[i]);
+}
+
+static int atmel_tdes_register_algs(struct atmel_tdes_dev *dd)
+{
+	int err, i, j;
+
+	for (i = 0; i < ARRAY_SIZE(tdes_algs); i++) {
+		INIT_LIST_HEAD(&tdes_algs[i].cra_list);
+		err = crypto_register_alg(&tdes_algs[i]);
+		if (err)
+			goto err_tdes_algs;
+	}
+
+	return 0;
+
+err_tdes_algs:
+	for (j = 0; j < i; j++)
+		crypto_unregister_alg(&tdes_algs[j]);
+
+	return err;
+}
+
+static int __devinit atmel_tdes_probe(struct platform_device *pdev)
+{
+	struct atmel_tdes_dev *tdes_dd;
+	struct device *dev = &pdev->dev;
+	struct resource *tdes_res;
+	unsigned long tdes_phys_size;
+	int err;
+
+	tdes_dd = kzalloc(sizeof(struct atmel_tdes_dev), GFP_KERNEL);
+	if (tdes_dd == NULL) {
+		dev_err(dev, "unable to alloc data struct.\n");
+		err = -ENOMEM;
+		goto tdes_dd_err;
+	}
+
+	tdes_dd->dev = dev;
+
+	platform_set_drvdata(pdev, tdes_dd);
+
+	INIT_LIST_HEAD(&tdes_dd->list);
+
+	tasklet_init(&tdes_dd->done_task, atmel_tdes_done_task,
+					(unsigned long)tdes_dd);
+	tasklet_init(&tdes_dd->queue_task, atmel_tdes_queue_task,
+					(unsigned long)tdes_dd);
+
+	crypto_init_queue(&tdes_dd->queue, ATMEL_TDES_QUEUE_LENGTH);
+
+	tdes_dd->irq = -1;
+
+	/* Get the base address */
+	tdes_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!tdes_res) {
+		dev_err(dev, "no MEM resource info\n");
+		err = -ENODEV;
+		goto res_err;
+	}
+	tdes_dd->phys_base = tdes_res->start;
+	tdes_phys_size = resource_size(tdes_res);
+
+	/* Get the IRQ */
+	tdes_dd->irq = platform_get_irq(pdev,  0);
+	if (tdes_dd->irq < 0) {
+		dev_err(dev, "no IRQ resource info\n");
+		err = tdes_dd->irq;
+		goto res_err;
+	}
+
+	err = request_irq(tdes_dd->irq, atmel_tdes_irq, IRQF_SHARED,
+			"atmel-tdes", tdes_dd);
+	if (err) {
+		dev_err(dev, "unable to request tdes irq.\n");
+		goto tdes_irq_err;
+	}
+
+	/* Initializing the clock */
+	tdes_dd->iclk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(tdes_dd->iclk)) {
+		dev_err(dev, "clock intialization failed.\n");
+		err = PTR_ERR(tdes_dd->iclk);
+		goto clk_err;
+	}
+
+	tdes_dd->io_base = ioremap(tdes_dd->phys_base, tdes_phys_size);
+	if (!tdes_dd->io_base) {
+		dev_err(dev, "can't ioremap\n");
+		err = -ENOMEM;
+		goto tdes_io_err;
+	}
+
+	err = atmel_tdes_dma_init(tdes_dd);
+	if (err)
+		goto err_tdes_dma;
+
+	spin_lock(&atmel_tdes.lock);
+	list_add_tail(&tdes_dd->list, &atmel_tdes.dev_list);
+	spin_unlock(&atmel_tdes.lock);
+
+	err = atmel_tdes_register_algs(tdes_dd);
+	if (err)
+		goto err_algs;
+
+	dev_info(dev, "Atmel DES/TDES\n");
+
+	return 0;
+
+err_algs:
+	spin_lock(&atmel_tdes.lock);
+	list_del(&tdes_dd->list);
+	spin_unlock(&atmel_tdes.lock);
+	atmel_tdes_dma_cleanup(tdes_dd);
+err_tdes_dma:
+	iounmap(tdes_dd->io_base);
+tdes_io_err:
+	clk_put(tdes_dd->iclk);
+clk_err:
+	free_irq(tdes_dd->irq, tdes_dd);
+tdes_irq_err:
+res_err:
+	tasklet_kill(&tdes_dd->done_task);
+	tasklet_kill(&tdes_dd->queue_task);
+	kfree(tdes_dd);
+	tdes_dd = NULL;
+tdes_dd_err:
+	dev_err(dev, "initialization failed.\n");
+
+	return err;
+}
+
+static int __devexit atmel_tdes_remove(struct platform_device *pdev)
+{
+	static struct atmel_tdes_dev *tdes_dd;
+
+	tdes_dd = platform_get_drvdata(pdev);
+	if (!tdes_dd)
+		return -ENODEV;
+	spin_lock(&atmel_tdes.lock);
+	list_del(&tdes_dd->list);
+	spin_unlock(&atmel_tdes.lock);
+
+	atmel_tdes_unregister_algs(tdes_dd);
+
+	tasklet_kill(&tdes_dd->done_task);
+	tasklet_kill(&tdes_dd->queue_task);
+
+	atmel_tdes_dma_cleanup(tdes_dd);
+
+	iounmap(tdes_dd->io_base);
+
+	clk_put(tdes_dd->iclk);
+
+	if (tdes_dd->irq >= 0)
+		free_irq(tdes_dd->irq, tdes_dd);
+
+	kfree(tdes_dd);
+	tdes_dd = NULL;
+
+	return 0;
+}
+
+static struct platform_driver atmel_tdes_driver = {
+	.probe		= atmel_tdes_probe,
+	.remove		= __devexit_p(atmel_tdes_remove),
+	.driver		= {
+		.name	= "atmel_tdes",
+		.owner	= THIS_MODULE,
+	},
+};
+
+module_platform_driver(atmel_tdes_driver);
+
+MODULE_DESCRIPTION("Atmel DES/TDES hw acceleration support.");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Nicolas Royer - Eukréa Electromatique");
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
new file mode 100644
index 0000000..5398580
--- /dev/null
+++ b/drivers/crypto/bfin_crc.c
@@ -0,0 +1,780 @@
+/*
+ * Cryptographic API.
+ *
+ * Support Blackfin CRC HW acceleration.
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/err.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/unaligned/access_ok.h>
+#include <linux/crypto.h>
+#include <linux/cryptohash.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/blackfin.h>
+#include <asm/bfin_crc.h>
+#include <asm/dma.h>
+#include <asm/portmux.h>
+
+#define CRC_CCRYPTO_QUEUE_LENGTH	5
+
+#define DRIVER_NAME "bfin-hmac-crc"
+#define CHKSUM_DIGEST_SIZE      4
+#define CHKSUM_BLOCK_SIZE       1
+
+#define CRC_MAX_DMA_DESC	100
+
+#define CRC_CRYPTO_STATE_UPDATE		1
+#define CRC_CRYPTO_STATE_FINALUPDATE	2
+#define CRC_CRYPTO_STATE_FINISH		3
+
+struct bfin_crypto_crc {
+	struct list_head	list;
+	struct device		*dev;
+	spinlock_t		lock;
+
+	int			irq;
+	int			dma_ch;
+	u32			poly;
+	volatile struct crc_register *regs;
+
+	struct ahash_request	*req; /* current request in operation */
+	struct dma_desc_array	*sg_cpu; /* virt addr of sg dma descriptors */
+	dma_addr_t		sg_dma; /* phy addr of sg dma descriptors */
+	u8			*sg_mid_buf;
+
+	struct tasklet_struct	done_task;
+	struct crypto_queue	queue; /* waiting requests */
+
+	u8			busy:1; /* crc device in operation flag */
+};
+
+static struct bfin_crypto_crc_list {
+	struct list_head	dev_list;
+	spinlock_t		lock;
+} crc_list;
+
+struct bfin_crypto_crc_reqctx {
+	struct bfin_crypto_crc	*crc;
+
+	unsigned int		total;	/* total request bytes */
+	size_t			sg_buflen; /* bytes for this update */
+	unsigned int		sg_nents;
+	struct scatterlist	*sg; /* sg list head for this update*/
+	struct scatterlist	bufsl[2]; /* chained sg list */
+
+	size_t			bufnext_len;
+	size_t			buflast_len;
+	u8			bufnext[CHKSUM_DIGEST_SIZE]; /* extra bytes for next udpate */
+	u8			buflast[CHKSUM_DIGEST_SIZE]; /* extra bytes from last udpate */
+
+	u8			flag;
+};
+
+struct bfin_crypto_crc_ctx {
+	struct bfin_crypto_crc	*crc;
+	u32			key;
+};
+
+
+/*
+ * derive number of elements in scatterlist
+ */
+static int sg_count(struct scatterlist *sg_list)
+{
+	struct scatterlist *sg = sg_list;
+	int sg_nents = 1;
+
+	if (sg_list == NULL)
+		return 0;
+
+	while (!sg_is_last(sg)) {
+		sg_nents++;
+		sg = scatterwalk_sg_next(sg);
+	}
+
+	return sg_nents;
+}
+
+/*
+ * get element in scatter list by given index
+ */
+static struct scatterlist *sg_get(struct scatterlist *sg_list, unsigned int nents,
+				unsigned int index)
+{
+	struct scatterlist *sg = NULL;
+	int i;
+
+	for_each_sg(sg_list, sg, nents, i)
+		if (i == index)
+			break;
+
+	return sg;
+}
+
+static int bfin_crypto_crc_init_hw(struct bfin_crypto_crc *crc, u32 key)
+{
+	crc->regs->datacntrld = 0;
+	crc->regs->control = MODE_CALC_CRC << OPMODE_OFFSET;
+	crc->regs->curresult = key;
+
+	/* setup CRC interrupts */
+	crc->regs->status = CMPERRI | DCNTEXPI;
+	crc->regs->intrenset = CMPERRI | DCNTEXPI;
+	SSYNC();
+
+	return 0;
+}
+
+static int bfin_crypto_crc_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
+	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
+	struct bfin_crypto_crc *crc;
+
+	dev_dbg(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;
+		break;
+	}
+	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",
+			CRC_MAX_DMA_DESC);
+		return -EINVAL;
+	}
+
+	ctx->crc = crc;
+	ctx->bufnext_len = 0;
+	ctx->buflast_len = 0;
+	ctx->sg_buflen = 0;
+	ctx->total = 0;
+	ctx->flag = 0;
+
+	/* init crc results */
+	put_unaligned_le32(crc_ctx->key, req->result);
+
+	dev_dbg(crc->dev, "init: digest size: %d\n",
+		crypto_ahash_digestsize(tfm));
+
+	return bfin_crypto_crc_init_hw(crc, crc_ctx->key);
+}
+
+static void bfin_crypto_crc_config_dma(struct bfin_crypto_crc *crc)
+{
+	struct scatterlist *sg;
+	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(crc->req);
+	int i = 0, j = 0;
+	unsigned long dma_config;
+	unsigned int dma_count;
+	unsigned int dma_addr;
+	unsigned int mid_dma_count = 0;
+	int dma_mod;
+
+	dma_map_sg(crc->dev, ctx->sg, ctx->sg_nents, DMA_TO_DEVICE);
+
+	for_each_sg(ctx->sg, sg, ctx->sg_nents, j) {
+		dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 | DMAEN | PSIZE_32;
+		dma_addr = sg_dma_address(sg);
+		/* deduce extra bytes in last sg */
+		if (sg_is_last(sg))
+			dma_count = sg_dma_len(sg) - ctx->bufnext_len;
+		else
+			dma_count = sg_dma_len(sg);
+
+		if (mid_dma_count) {
+			/* Append last middle dma buffer to 4 bytes with first
+			   bytes in current sg buffer. Move addr of current
+			   sg and deduce the length of current sg.
+			 */
+			memcpy(crc->sg_mid_buf +((i-1) << 2) + mid_dma_count,
+				(void *)dma_addr,
+				CHKSUM_DIGEST_SIZE - mid_dma_count);
+			dma_addr += CHKSUM_DIGEST_SIZE - mid_dma_count;
+			dma_count -= CHKSUM_DIGEST_SIZE - mid_dma_count;
+		}
+		/* chop current sg dma len to multiple of 32 bits */
+		mid_dma_count = dma_count % 4;
+		dma_count &= ~0x3;
+
+		if (dma_addr % 4 == 0) {
+			dma_config |= WDSIZE_32;
+			dma_count >>= 2;
+			dma_mod = 4;
+		} else if (dma_addr % 2 == 0) {
+			dma_config |= WDSIZE_16;
+			dma_count >>= 1;
+			dma_mod = 2;
+		} else {
+			dma_config |= WDSIZE_8;
+			dma_mod = 1;
+		}
+
+		crc->sg_cpu[i].start_addr = dma_addr;
+		crc->sg_cpu[i].cfg = dma_config;
+		crc->sg_cpu[i].x_count = dma_count;
+		crc->sg_cpu[i].x_modify = dma_mod;
+		dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
+			"cfg:0x%lx, x_count:0x%lx, x_modify:0x%lx\n",
+			i, crc->sg_cpu[i].start_addr,
+			crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
+			crc->sg_cpu[i].x_modify);
+		i++;
+
+		if (mid_dma_count) {
+			/* copy extra bytes to next middle dma buffer */
+			dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 |
+				DMAEN | PSIZE_32 | WDSIZE_32;
+			memcpy(crc->sg_mid_buf + (i << 2),
+				(void *)(dma_addr + (dma_count << 2)),
+				mid_dma_count);
+			/* setup new dma descriptor for next middle dma */
+			crc->sg_cpu[i].start_addr = dma_map_single(crc->dev,
+					crc->sg_mid_buf + (i << 2),
+					CHKSUM_DIGEST_SIZE, DMA_TO_DEVICE);
+			crc->sg_cpu[i].cfg = dma_config;
+			crc->sg_cpu[i].x_count = 1;
+			crc->sg_cpu[i].x_modify = CHKSUM_DIGEST_SIZE;
+			dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
+				"cfg:0x%lx, x_count:0x%lx, x_modify:0x%lx\n",
+				i, crc->sg_cpu[i].start_addr,
+				crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
+				crc->sg_cpu[i].x_modify);
+			i++;
+		}
+	}
+
+	dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 | DMAEN | PSIZE_32 | WDSIZE_32;
+	/* For final update req, append the buffer for next update as well*/
+	if (ctx->bufnext_len && (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE ||
+		ctx->flag == CRC_CRYPTO_STATE_FINISH)) {
+		crc->sg_cpu[i].start_addr = dma_map_single(crc->dev, ctx->bufnext,
+						CHKSUM_DIGEST_SIZE, DMA_TO_DEVICE);
+		crc->sg_cpu[i].cfg = dma_config;
+		crc->sg_cpu[i].x_count = 1;
+		crc->sg_cpu[i].x_modify = CHKSUM_DIGEST_SIZE;
+		dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
+			"cfg:0x%lx, x_count:0x%lx, x_modify:0x%lx\n",
+			i, crc->sg_cpu[i].start_addr,
+			crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
+			crc->sg_cpu[i].x_modify);
+		i++;
+	}
+
+	if (i == 0)
+		return;
+
+	flush_dcache_range((unsigned int)crc->sg_cpu,
+			(unsigned int)crc->sg_cpu +
+			i * sizeof(struct dma_desc_array));
+
+	/* Set the last descriptor to stop mode */
+	crc->sg_cpu[i - 1].cfg &= ~(DMAFLOW | NDSIZE);
+	crc->sg_cpu[i - 1].cfg |= DI_EN;
+	set_dma_curr_desc_addr(crc->dma_ch, (unsigned long *)crc->sg_dma);
+	set_dma_x_count(crc->dma_ch, 0);
+	set_dma_x_modify(crc->dma_ch, 0);
+	SSYNC();
+	set_dma_config(crc->dma_ch, dma_config);
+}
+
+static int bfin_crypto_crc_handle_queue(struct bfin_crypto_crc *crc,
+				  struct ahash_request *req)
+{
+	struct crypto_async_request *async_req, *backlog;
+	struct bfin_crypto_crc_reqctx *ctx;
+	struct scatterlist *sg;
+	int ret = 0;
+	int nsg, i, j;
+	unsigned int nextlen;
+	unsigned long flags;
+
+	spin_lock_irqsave(&crc->lock, flags);
+	if (req)
+		ret = ahash_enqueue_request(&crc->queue, req);
+	if (crc->busy) {
+		spin_unlock_irqrestore(&crc->lock, flags);
+		return ret;
+	}
+	backlog = crypto_get_backlog(&crc->queue);
+	async_req = crypto_dequeue_request(&crc->queue);
+	if (async_req)
+		crc->busy = 1;
+	spin_unlock_irqrestore(&crc->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = ahash_request_cast(async_req);
+	crc->req = req;
+	ctx = ahash_request_ctx(req);
+	ctx->sg = NULL;
+	ctx->sg_buflen = 0;
+	ctx->sg_nents = 0;
+
+	dev_dbg(crc->dev, "handling new req, flag=%u, nbytes: %d\n",
+						ctx->flag, req->nbytes);
+
+	if (ctx->flag == CRC_CRYPTO_STATE_FINISH) {
+		if (ctx->bufnext_len == 0) {
+			crc->busy = 0;
+			return 0;
+		}
+
+		/* Pack last crc update buffer to 32bit */
+		memset(ctx->bufnext + ctx->bufnext_len, 0,
+				CHKSUM_DIGEST_SIZE - ctx->bufnext_len);
+	} else {
+		/* Pack small data which is less than 32bit to buffer for next update. */
+		if (ctx->bufnext_len + req->nbytes < CHKSUM_DIGEST_SIZE) {
+			memcpy(ctx->bufnext + ctx->bufnext_len,
+				sg_virt(req->src), req->nbytes);
+			ctx->bufnext_len += req->nbytes;
+			if (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE &&
+				ctx->bufnext_len) {
+				goto finish_update;
+			} else {
+				crc->busy = 0;
+				return 0;
+			}
+		}
+
+		if (ctx->bufnext_len) {
+			/* Chain in extra bytes of last update */
+			ctx->buflast_len = ctx->bufnext_len;
+			memcpy(ctx->buflast, ctx->bufnext, ctx->buflast_len);
+
+			nsg = ctx->sg_buflen ? 2 : 1;
+			sg_init_table(ctx->bufsl, nsg);
+			sg_set_buf(ctx->bufsl, ctx->buflast, ctx->buflast_len);
+			if (nsg > 1)
+				scatterwalk_sg_chain(ctx->bufsl, nsg,
+						req->src);
+			ctx->sg = ctx->bufsl;
+		} else
+			ctx->sg = req->src;
+
+		/* Chop crc buffer size to multiple of 32 bit */
+		nsg = ctx->sg_nents = sg_count(ctx->sg);
+		ctx->sg_buflen = ctx->buflast_len + req->nbytes;
+		ctx->bufnext_len = ctx->sg_buflen % 4;
+		ctx->sg_buflen &= ~0x3;
+
+		if (ctx->bufnext_len) {
+			/* copy extra bytes to buffer for next update */
+			memset(ctx->bufnext, 0, CHKSUM_DIGEST_SIZE);
+			nextlen = ctx->bufnext_len;
+			for (i = nsg - 1; i >= 0; i--) {
+				sg = sg_get(ctx->sg, nsg, i);
+				j = min(nextlen, sg_dma_len(sg));
+				memcpy(ctx->bufnext + nextlen - j,
+					sg_virt(sg) + sg_dma_len(sg) - j, j);
+				if (j == sg_dma_len(sg))
+					ctx->sg_nents--;
+				nextlen -= j;
+				if (nextlen == 0)
+					break;
+			}
+		}
+	}
+
+finish_update:
+	if (ctx->bufnext_len && (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE ||
+		ctx->flag == CRC_CRYPTO_STATE_FINISH))
+		ctx->sg_buflen += CHKSUM_DIGEST_SIZE;
+
+	/* set CRC data count before start DMA */
+	crc->regs->datacnt = ctx->sg_buflen >> 2;
+
+	/* setup and enable CRC DMA */
+	bfin_crypto_crc_config_dma(crc);
+
+	/* finally kick off CRC operation */
+	crc->regs->control |= BLKEN;
+	SSYNC();
+
+	return -EINPROGRESS;
+}
+
+static int bfin_crypto_crc_update(struct ahash_request *req)
+{
+	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
+
+	if (!req->nbytes)
+		return 0;
+
+	dev_dbg(ctx->crc->dev, "crc_update\n");
+	ctx->total += req->nbytes;
+	ctx->flag = CRC_CRYPTO_STATE_UPDATE;
+
+	return bfin_crypto_crc_handle_queue(ctx->crc, req);
+}
+
+static int bfin_crypto_crc_final(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
+	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
+
+	dev_dbg(ctx->crc->dev, "crc_final\n");
+	ctx->flag = CRC_CRYPTO_STATE_FINISH;
+	crc_ctx->key = 0;
+
+	return bfin_crypto_crc_handle_queue(ctx->crc, req);
+}
+
+static int bfin_crypto_crc_finup(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
+	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
+
+	dev_dbg(ctx->crc->dev, "crc_finishupdate\n");
+	ctx->total += req->nbytes;
+	ctx->flag = CRC_CRYPTO_STATE_FINALUPDATE;
+	crc_ctx->key = 0;
+
+	return bfin_crypto_crc_handle_queue(ctx->crc, req);
+}
+
+static int bfin_crypto_crc_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = bfin_crypto_crc_init(req);
+	if (ret)
+		return ret;
+
+	return bfin_crypto_crc_finup(req);
+}
+
+static int bfin_crypto_crc_setkey(struct crypto_ahash *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
+
+	dev_dbg(crc_ctx->crc->dev, "crc_setkey\n");
+	if (keylen != CHKSUM_DIGEST_SIZE) {
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	crc_ctx->key = get_unaligned_le32(key);
+
+	return 0;
+}
+
+static int bfin_crypto_crc_cra_init(struct crypto_tfm *tfm)
+{
+	struct bfin_crypto_crc_ctx *crc_ctx = crypto_tfm_ctx(tfm);
+
+	crc_ctx->key = 0;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct bfin_crypto_crc_reqctx));
+
+	return 0;
+}
+
+static void bfin_crypto_crc_cra_exit(struct crypto_tfm *tfm)
+{
+}
+
+static struct ahash_alg algs = {
+	.init		= bfin_crypto_crc_init,
+	.update		= bfin_crypto_crc_update,
+	.final		= bfin_crypto_crc_final,
+	.finup		= bfin_crypto_crc_finup,
+	.digest		= bfin_crypto_crc_digest,
+	.setkey		= bfin_crypto_crc_setkey,
+	.halg.digestsize	= CHKSUM_DIGEST_SIZE,
+	.halg.base	= {
+		.cra_name		= "hmac(crc32)",
+		.cra_driver_name	= DRIVER_NAME,
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct bfin_crypto_crc_ctx),
+		.cra_alignmask		= 3,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= bfin_crypto_crc_cra_init,
+		.cra_exit		= bfin_crypto_crc_cra_exit,
+	}
+};
+
+static void bfin_crypto_crc_done_task(unsigned long data)
+{
+	struct bfin_crypto_crc *crc = (struct bfin_crypto_crc *)data;
+
+	bfin_crypto_crc_handle_queue(crc, NULL);
+}
+
+static irqreturn_t bfin_crypto_crc_handler(int irq, void *dev_id)
+{
+	struct bfin_crypto_crc *crc = dev_id;
+
+	if (crc->regs->status & DCNTEXP) {
+		crc->regs->status = DCNTEXP;
+		SSYNC();
+
+		/* prepare results */
+		put_unaligned_le32(crc->regs->result, crc->req->result);
+
+		crc->regs->control &= ~BLKEN;
+		crc->busy = 0;
+
+		if (crc->req->base.complete)
+			crc->req->base.complete(&crc->req->base, 0);
+
+		tasklet_schedule(&crc->done_task);
+
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
+}
+
+#ifdef CONFIG_PM
+/**
+ *	bfin_crypto_crc_suspend - suspend crc device
+ *	@pdev: device being suspended
+ *	@state: requested suspend state
+ */
+static int bfin_crypto_crc_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct bfin_crypto_crc *crc = platform_get_drvdata(pdev);
+	int i = 100000;
+
+	while ((crc->regs->control & BLKEN) && --i)
+		cpu_relax();
+
+	if (i == 0)
+		return -EBUSY;
+
+	return 0;
+}
+#else
+# define bfin_crypto_crc_suspend NULL
+#endif
+
+#define bfin_crypto_crc_resume NULL
+
+/**
+ *	bfin_crypto_crc_probe - Initialize module
+ *
+ */
+static int __devinit bfin_crypto_crc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct bfin_crypto_crc *crc;
+	unsigned int timeout = 100000;
+	int ret;
+
+	crc = kzalloc(sizeof(*crc), GFP_KERNEL);
+	if (!crc) {
+		dev_err(&pdev->dev, "fail to malloc bfin_crypto_crc\n");
+		return -ENOMEM;
+	}
+
+	crc->dev = dev;
+
+	INIT_LIST_HEAD(&crc->list);
+	spin_lock_init(&crc->lock);
+	tasklet_init(&crc->done_task, bfin_crypto_crc_done_task, (unsigned long)crc);
+	crypto_init_queue(&crc->queue, CRC_CCRYPTO_QUEUE_LENGTH);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res == NULL) {
+		dev_err(&pdev->dev, "Cannot get IORESOURCE_MEM\n");
+		ret = -ENOENT;
+		goto out_error_free_mem;
+	}
+
+	crc->regs = ioremap(res->start, resource_size(res));
+	if (!crc->regs) {
+		dev_err(&pdev->dev, "Cannot map CRC IO\n");
+		ret = -ENXIO;
+		goto out_error_free_mem;
+	}
+
+	crc->irq = platform_get_irq(pdev, 0);
+	if (crc->irq < 0) {
+		dev_err(&pdev->dev, "No CRC DCNTEXP IRQ specified\n");
+		ret = -ENOENT;
+		goto out_error_unmap;
+	}
+
+	ret = request_irq(crc->irq, bfin_crypto_crc_handler, IRQF_SHARED, dev_name(dev), crc);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to request blackfin crc irq\n");
+		goto out_error_unmap;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+	if (res == NULL) {
+		dev_err(&pdev->dev, "No CRC DMA channel specified\n");
+		ret = -ENOENT;
+		goto out_error_irq;
+	}
+	crc->dma_ch = res->start;
+
+	ret = request_dma(crc->dma_ch, dev_name(dev));
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to attach Blackfin CRC DMA channel\n");
+		goto out_error_irq;
+	}
+
+	crc->sg_cpu = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, &crc->sg_dma, GFP_KERNEL);
+	if (crc->sg_cpu == NULL) {
+		ret = -ENOMEM;
+		goto out_error_dma;
+	}
+	/*
+	 * need at most CRC_MAX_DMA_DESC sg + CRC_MAX_DMA_DESC middle  +
+	 * 1 last + 1 next dma descriptors
+	 */
+	crc->sg_mid_buf = (u8 *)(crc->sg_cpu + ((CRC_MAX_DMA_DESC + 1) << 1));
+
+	crc->regs->control = 0;
+	SSYNC();
+	crc->regs->poly = crc->poly = (u32)pdev->dev.platform_data;
+	SSYNC();
+
+	while (!(crc->regs->status & LUTDONE) && (--timeout) > 0)
+		cpu_relax();
+
+	if (timeout == 0)
+		dev_info(&pdev->dev, "init crc poly timeout\n");
+
+	spin_lock(&crc_list.lock);
+	list_add(&crc->list, &crc_list.dev_list);
+	spin_unlock(&crc_list.lock);
+
+	platform_set_drvdata(pdev, crc);
+
+	ret = crypto_register_ahash(&algs);
+	if (ret) {
+		spin_lock(&crc_list.lock);
+		list_del(&crc->list);
+		spin_unlock(&crc_list.lock);
+		dev_err(&pdev->dev, "Cann't register crypto ahash device\n");
+		goto out_error_dma;
+	}
+
+	dev_info(&pdev->dev, "initialized\n");
+
+	return 0;
+
+out_error_dma:
+	if (crc->sg_cpu)
+		dma_free_coherent(&pdev->dev, PAGE_SIZE, crc->sg_cpu, crc->sg_dma);
+	free_dma(crc->dma_ch);
+out_error_irq:
+	free_irq(crc->irq, crc->dev);
+out_error_unmap:
+	iounmap((void *)crc->regs);
+out_error_free_mem:
+	kfree(crc);
+
+	return ret;
+}
+
+/**
+ *	bfin_crypto_crc_remove - Initialize module
+ *
+ */
+static int __devexit bfin_crypto_crc_remove(struct platform_device *pdev)
+{
+	struct bfin_crypto_crc *crc = platform_get_drvdata(pdev);
+
+	if (!crc)
+		return -ENODEV;
+
+	spin_lock(&crc_list.lock);
+	list_del(&crc->list);
+	spin_unlock(&crc_list.lock);
+
+	crypto_unregister_ahash(&algs);
+	tasklet_kill(&crc->done_task);
+	iounmap((void *)crc->regs);
+	free_dma(crc->dma_ch);
+	if (crc->irq > 0)
+		free_irq(crc->irq, crc->dev);
+	kfree(crc);
+
+	return 0;
+}
+
+static struct platform_driver bfin_crypto_crc_driver = {
+	.probe     = bfin_crypto_crc_probe,
+	.remove    = __devexit_p(bfin_crypto_crc_remove),
+	.suspend   = bfin_crypto_crc_suspend,
+	.resume    = bfin_crypto_crc_resume,
+	.driver    = {
+		.name  = DRIVER_NAME,
+		.owner = THIS_MODULE,
+	},
+};
+
+/**
+ *	bfin_crypto_crc_mod_init - Initialize module
+ *
+ *	Checks the module params and registers the platform driver.
+ *	Real work is in the platform probe function.
+ */
+static int __init bfin_crypto_crc_mod_init(void)
+{
+	int ret;
+
+	pr_info("Blackfin hardware CRC crypto driver\n");
+
+	INIT_LIST_HEAD(&crc_list.dev_list);
+	spin_lock_init(&crc_list.lock);
+
+	ret = platform_driver_register(&bfin_crypto_crc_driver);
+	if (ret) {
+		pr_info(KERN_ERR "unable to register driver\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ *	bfin_crypto_crc_mod_exit - Deinitialize module
+ */
+static void __exit bfin_crypto_crc_mod_exit(void)
+{
+	platform_driver_unregister(&bfin_crypto_crc_driver);
+}
+
+module_init(bfin_crypto_crc_mod_init);
+module_exit(bfin_crypto_crc_mod_exit);
+
+MODULE_AUTHOR("Sonic Zhang <sonic.zhang@analog.com>");
+MODULE_DESCRIPTION("Blackfin CRC hardware crypto driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index 2d876bb..65c7668 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -32,10 +32,13 @@ config CRYPTO_DEV_FSL_CAAM_RINGSIZE
 config CRYPTO_DEV_FSL_CAAM_INTC
 	bool "Job Ring interrupt coalescing"
 	depends on CRYPTO_DEV_FSL_CAAM
-	default y
+	default n
 	help
 	  Enable the Job Ring's interrupt coalescing feature.
 
+	  Note: the driver already provides adequate
+	  interrupt coalescing in software.
+
 config CRYPTO_DEV_FSL_CAAM_INTC_COUNT_THLD
 	int "Job Ring interrupt coalescing count threshold"
 	depends on CRYPTO_DEV_FSL_CAAM_INTC
@@ -70,3 +73,28 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
 
 	  To compile this as a module, choose M here: the module
 	  will be called caamalg.
+
+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
+	help
+	  Selecting this will offload ahash for users of the
+	  scatterlist crypto API to the SEC4 via job ring.
+
+	  To compile this as a module, choose M here: the module
+	  will be called caamhash.
+
+config CRYPTO_DEV_FSL_CAAM_RNG_API
+	tristate "Register caam device for hwrng API"
+	depends on CRYPTO_DEV_FSL_CAAM
+	default y
+	select CRYPTO_RNG
+	select HW_RANDOM
+	help
+	  Selecting this will register the SEC4 hardware rng to
+	  the hw_random API for suppying the kernel entropy pool.
+
+	  To compile this as a module, choose M here: the module
+	  will be called caamrng.
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index ef39011..b1eb448 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -4,5 +4,7 @@
 
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o
 
-caam-objs := ctrl.o jr.o error.o
+caam-objs := ctrl.o jr.o error.o key_gen.o
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 4eec389..0c1ea84 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -37,9 +37,10 @@
  * | ShareDesc Pointer |
  * | SEQ_OUT_PTR       |
  * | (output buffer)   |
+ * | (output length)   |
  * | SEQ_IN_PTR        |
  * | (input buffer)    |
- * | LOAD (to DECO)    |
+ * | (input length)    |
  * ---------------------
  */
 
@@ -50,6 +51,8 @@
 #include "desc_constr.h"
 #include "jr.h"
 #include "error.h"
+#include "sg_sw_sec4.h"
+#include "key_gen.h"
 
 /*
  * crypto alg
@@ -62,7 +65,7 @@
 #define CAAM_MAX_IV_LENGTH		16
 
 /* length of descriptors text */
-#define DESC_JOB_IO_LEN			(CAAM_CMD_SZ * 3 + CAAM_PTR_SZ * 3)
+#define DESC_JOB_IO_LEN			(CAAM_CMD_SZ * 5 + CAAM_PTR_SZ * 3)
 
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 16 * CAAM_CMD_SZ)
@@ -143,11 +146,11 @@ static inline void aead_append_ld_iv(u32 *desc, int ivsize)
  */
 static inline void ablkcipher_append_src_dst(u32 *desc)
 {
-	append_math_add(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ); \
-	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ); \
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | \
-			     KEY_VLF | FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1); \
-	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | KEY_VLF); \
+	append_math_add(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 |
+			     KEY_VLF | FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | KEY_VLF);
 }
 
 /*
@@ -452,121 +455,12 @@ static int aead_setauthsize(struct crypto_aead *authenc,
 	return 0;
 }
 
-struct split_key_result {
-	struct completion completion;
-	int err;
-};
-
-static void split_key_done(struct device *dev, u32 *desc, u32 err,
-			   void *context)
+static u32 gen_split_aead_key(struct caam_ctx *ctx, const u8 *key_in,
+			      u32 authkeylen)
 {
-	struct split_key_result *res = context;
-
-#ifdef DEBUG
-	dev_err(dev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
-#endif
-
-	if (err) {
-		char tmp[CAAM_ERROR_STR_MAX];
-
-		dev_err(dev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
-	}
-
-	res->err = err;
-
-	complete(&res->completion);
-}
-
-/*
-get a split ipad/opad key
-
-Split key generation-----------------------------------------------
-
-[00] 0xb0810008    jobdesc: stidx=1 share=never len=8
-[01] 0x04000014        key: class2->keyreg len=20
-			@0xffe01000
-[03] 0x84410014  operation: cls2-op sha1 hmac init dec
-[04] 0x24940000     fifold: class2 msgdata-last2 len=0 imm
-[05] 0xa4000001       jump: class2 local all ->1 [06]
-[06] 0x64260028    fifostr: class2 mdsplit-jdk len=40
-			@0xffe04000
-*/
-static u32 gen_split_key(struct caam_ctx *ctx, const u8 *key_in, u32 authkeylen)
-{
-	struct device *jrdev = ctx->jrdev;
-	u32 *desc;
-	struct split_key_result result;
-	dma_addr_t dma_addr_in, dma_addr_out;
-	int ret = 0;
-
-	desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
-
-	init_job_desc(desc, 0);
-
-	dma_addr_in = dma_map_single(jrdev, (void *)key_in, authkeylen,
-				     DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, dma_addr_in)) {
-		dev_err(jrdev, "unable to map key input memory\n");
-		kfree(desc);
-		return -ENOMEM;
-	}
-	append_key(desc, dma_addr_in, authkeylen, CLASS_2 |
-		       KEY_DEST_CLASS_REG);
-
-	/* Sets MDHA up into an HMAC-INIT */
-	append_operation(desc, ctx->alg_op | OP_ALG_DECRYPT |
-			     OP_ALG_AS_INIT);
-
-	/*
-	 * do a FIFO_LOAD of zero, this will trigger the internal key expansion
-	   into both pads inside MDHA
-	 */
-	append_fifo_load_as_imm(desc, NULL, 0, LDST_CLASS_2_CCB |
-				FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST2);
-
-	/*
-	 * FIFO_STORE with the explicit split-key content store
-	 * (0x26 output type)
-	 */
-	dma_addr_out = dma_map_single(jrdev, ctx->key, ctx->split_key_pad_len,
-				      DMA_FROM_DEVICE);
-	if (dma_mapping_error(jrdev, dma_addr_out)) {
-		dev_err(jrdev, "unable to map key output memory\n");
-		kfree(desc);
-		return -ENOMEM;
-	}
-	append_fifo_store(desc, dma_addr_out, ctx->split_key_len,
-			  LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK);
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, key_in, authkeylen, 1);
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
-#endif
-
-	result.err = 0;
-	init_completion(&result.completion);
-
-	ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result);
-	if (!ret) {
-		/* in progress */
-		wait_for_completion_interruptible(&result.completion);
-		ret = result.err;
-#ifdef DEBUG
-		print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
-			       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
-			       ctx->split_key_pad_len, 1);
-#endif
-	}
-
-	dma_unmap_single(jrdev, dma_addr_out, ctx->split_key_pad_len,
-			 DMA_FROM_DEVICE);
-	dma_unmap_single(jrdev, dma_addr_in, authkeylen, DMA_TO_DEVICE);
-
-	kfree(desc);
-
-	return ret;
+	return gen_split_key(ctx->jrdev, ctx->key, ctx->split_key_len,
+			       ctx->split_key_pad_len, key_in, authkeylen,
+			       ctx->alg_op);
 }
 
 static int aead_setkey(struct crypto_aead *aead,
@@ -610,7 +504,7 @@ static int aead_setkey(struct crypto_aead *aead,
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
-	ret = gen_split_key(ctx, key, authkeylen);
+	ret = gen_split_aead_key(ctx, key, authkeylen);
 	if (ret) {
 		goto badkey;
 	}
@@ -757,72 +651,78 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	return ret;
 }
 
-struct link_tbl_entry {
-	u64 ptr;
-	u32 len;
-	u8 reserved;
-	u8 buf_pool_id;
-	u16 offset;
-};
-
 /*
  * aead_edesc - s/w-extended aead descriptor
  * @assoc_nents: number of segments in associated data (SPI+Seq) scatterlist
+ * @assoc_chained: if source is chained
  * @src_nents: number of segments in input scatterlist
+ * @src_chained: if source is chained
  * @dst_nents: number of segments in output scatterlist
+ * @dst_chained: if destination is chained
  * @iv_dma: dma address of iv for checking continuity and link table
  * @desc: h/w descriptor (variable length; must not exceed MAX_CAAM_DESCSIZE)
- * @link_tbl_bytes: length of dma mapped link_tbl space
- * @link_tbl_dma: bus physical mapped address of h/w link table
+ * @sec4_sg_bytes: length of dma mapped sec4_sg space
+ * @sec4_sg_dma: bus physical mapped address of h/w link table
  * @hw_desc: the h/w job descriptor followed by any referenced link tables
  */
 struct aead_edesc {
 	int assoc_nents;
+	bool assoc_chained;
 	int src_nents;
+	bool src_chained;
 	int dst_nents;
+	bool dst_chained;
 	dma_addr_t iv_dma;
-	int link_tbl_bytes;
-	dma_addr_t link_tbl_dma;
-	struct link_tbl_entry *link_tbl;
+	int sec4_sg_bytes;
+	dma_addr_t sec4_sg_dma;
+	struct sec4_sg_entry *sec4_sg;
 	u32 hw_desc[0];
 };
 
 /*
  * ablkcipher_edesc - s/w-extended ablkcipher descriptor
  * @src_nents: number of segments in input scatterlist
+ * @src_chained: if source is chained
  * @dst_nents: number of segments in output scatterlist
+ * @dst_chained: if destination is chained
  * @iv_dma: dma address of iv for checking continuity and link table
  * @desc: h/w descriptor (variable length; must not exceed MAX_CAAM_DESCSIZE)
- * @link_tbl_bytes: length of dma mapped link_tbl space
- * @link_tbl_dma: bus physical mapped address of h/w link table
+ * @sec4_sg_bytes: length of dma mapped sec4_sg space
+ * @sec4_sg_dma: bus physical mapped address of h/w link table
  * @hw_desc: the h/w job descriptor followed by any referenced link tables
  */
 struct ablkcipher_edesc {
 	int src_nents;
+	bool src_chained;
 	int dst_nents;
+	bool dst_chained;
 	dma_addr_t iv_dma;
-	int link_tbl_bytes;
-	dma_addr_t link_tbl_dma;
-	struct link_tbl_entry *link_tbl;
+	int sec4_sg_bytes;
+	dma_addr_t sec4_sg_dma;
+	struct sec4_sg_entry *sec4_sg;
 	u32 hw_desc[0];
 };
 
 static void caam_unmap(struct device *dev, struct scatterlist *src,
-		       struct scatterlist *dst, int src_nents, int dst_nents,
-		       dma_addr_t iv_dma, int ivsize, dma_addr_t link_tbl_dma,
-		       int link_tbl_bytes)
+		       struct scatterlist *dst, int src_nents,
+		       bool src_chained, int dst_nents, bool dst_chained,
+		       dma_addr_t iv_dma, int ivsize, dma_addr_t sec4_sg_dma,
+		       int sec4_sg_bytes)
 {
-	if (unlikely(dst != src)) {
-		dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
-		dma_unmap_sg(dev, dst, dst_nents, DMA_FROM_DEVICE);
+	if (dst != src) {
+		dma_unmap_sg_chained(dev, src, src_nents ? : 1, DMA_TO_DEVICE,
+				     src_chained);
+		dma_unmap_sg_chained(dev, dst, dst_nents ? : 1, DMA_FROM_DEVICE,
+				     dst_chained);
 	} else {
-		dma_unmap_sg(dev, src, src_nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sg_chained(dev, src, src_nents ? : 1,
+				     DMA_BIDIRECTIONAL, src_chained);
 	}
 
 	if (iv_dma)
 		dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
-	if (link_tbl_bytes)
-		dma_unmap_single(dev, link_tbl_dma, link_tbl_bytes,
+	if (sec4_sg_bytes)
+		dma_unmap_single(dev, sec4_sg_dma, sec4_sg_bytes,
 				 DMA_TO_DEVICE);
 }
 
@@ -833,12 +733,13 @@ static void aead_unmap(struct device *dev,
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	int ivsize = crypto_aead_ivsize(aead);
 
-	dma_unmap_sg(dev, req->assoc, edesc->assoc_nents, DMA_TO_DEVICE);
+	dma_unmap_sg_chained(dev, req->assoc, edesc->assoc_nents,
+			     DMA_TO_DEVICE, edesc->assoc_chained);
 
 	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->dst_nents,
-		   edesc->iv_dma, ivsize, edesc->link_tbl_dma,
-		   edesc->link_tbl_bytes);
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, edesc->iv_dma, ivsize,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
 static void ablkcipher_unmap(struct device *dev,
@@ -849,9 +750,9 @@ static void ablkcipher_unmap(struct device *dev,
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 
 	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->dst_nents,
-		   edesc->iv_dma, ivsize, edesc->link_tbl_dma,
-		   edesc->link_tbl_bytes);
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, edesc->iv_dma, ivsize,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
 static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
@@ -942,7 +843,7 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 		       sizeof(struct iphdr) + req->assoclen +
 		       ((req->cryptlen > 1500) ? 1500 : req->cryptlen) +
 		       ctx->authsize + 36, 1);
-	if (!err && edesc->link_tbl_bytes) {
+	if (!err && edesc->sec4_sg_bytes) {
 		struct scatterlist *sg = sg_last(req->src, edesc->src_nents);
 		print_hex_dump(KERN_ERR, "sglastout@"xstr(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(sg),
@@ -1026,50 +927,6 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	ablkcipher_request_complete(req, err);
 }
 
-static void sg_to_link_tbl_one(struct link_tbl_entry *link_tbl_ptr,
-			       dma_addr_t dma, u32 len, u32 offset)
-{
-	link_tbl_ptr->ptr = dma;
-	link_tbl_ptr->len = len;
-	link_tbl_ptr->reserved = 0;
-	link_tbl_ptr->buf_pool_id = 0;
-	link_tbl_ptr->offset = offset;
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR, "link_tbl_ptr@"xstr(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, link_tbl_ptr,
-		       sizeof(struct link_tbl_entry), 1);
-#endif
-}
-
-/*
- * convert scatterlist to h/w link table format
- * but does not have final bit; instead, returns last entry
- */
-static struct link_tbl_entry *sg_to_link_tbl(struct scatterlist *sg,
-					     int sg_count, struct link_tbl_entry
-					     *link_tbl_ptr, u32 offset)
-{
-	while (sg_count) {
-		sg_to_link_tbl_one(link_tbl_ptr, sg_dma_address(sg),
-				   sg_dma_len(sg), offset);
-		link_tbl_ptr++;
-		sg = sg_next(sg);
-		sg_count--;
-	}
-	return link_tbl_ptr - 1;
-}
-
-/*
- * convert scatterlist to h/w link table format
- * scatterlist must have been previously dma mapped
- */
-static void sg_to_link_tbl_last(struct scatterlist *sg, int sg_count,
-				struct link_tbl_entry *link_tbl_ptr, u32 offset)
-{
-	link_tbl_ptr = sg_to_link_tbl(sg, sg_count, link_tbl_ptr, offset);
-	link_tbl_ptr->len |= 0x40000000;
-}
-
 /*
  * Fill in aead job descriptor
  */
@@ -1085,7 +942,7 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 	u32 *desc = edesc->hw_desc;
 	u32 out_options = 0, in_options;
 	dma_addr_t dst_dma, src_dma;
-	int len, link_tbl_index = 0;
+	int len, sec4_sg_index = 0;
 
 #ifdef DEBUG
 	debug("assoclen %d cryptlen %d authsize %d\n",
@@ -1111,9 +968,9 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 		src_dma = sg_dma_address(req->assoc);
 		in_options = 0;
 	} else {
-		src_dma = edesc->link_tbl_dma;
-		link_tbl_index += (edesc->assoc_nents ? : 1) + 1 +
-				  (edesc->src_nents ? : 1);
+		src_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += (edesc->assoc_nents ? : 1) + 1 +
+				 (edesc->src_nents ? : 1);
 		in_options = LDST_SGF;
 	}
 	if (encrypt)
@@ -1127,7 +984,7 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 		if (all_contig) {
 			dst_dma = sg_dma_address(req->src);
 		} else {
-			dst_dma = src_dma + sizeof(struct link_tbl_entry) *
+			dst_dma = src_dma + sizeof(struct sec4_sg_entry) *
 				  ((edesc->assoc_nents ? : 1) + 1);
 			out_options = LDST_SGF;
 		}
@@ -1135,9 +992,9 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 		if (!edesc->dst_nents) {
 			dst_dma = sg_dma_address(req->dst);
 		} else {
-			dst_dma = edesc->link_tbl_dma +
-				  link_tbl_index *
-				  sizeof(struct link_tbl_entry);
+			dst_dma = edesc->sec4_sg_dma +
+				  sec4_sg_index *
+				  sizeof(struct sec4_sg_entry);
 			out_options = LDST_SGF;
 		}
 	}
@@ -1163,7 +1020,7 @@ static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
 	u32 *desc = edesc->hw_desc;
 	u32 out_options = 0, in_options;
 	dma_addr_t dst_dma, src_dma;
-	int len, link_tbl_index = 0;
+	int len, sec4_sg_index = 0;
 
 #ifdef DEBUG
 	debug("assoclen %d cryptlen %d authsize %d\n",
@@ -1188,8 +1045,8 @@ static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
 		src_dma = sg_dma_address(req->assoc);
 		in_options = 0;
 	} else {
-		src_dma = edesc->link_tbl_dma;
-		link_tbl_index += edesc->assoc_nents + 1 + edesc->src_nents;
+		src_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->assoc_nents + 1 + edesc->src_nents;
 		in_options = LDST_SGF;
 	}
 	append_seq_in_ptr(desc, src_dma, req->assoclen + ivsize +
@@ -1199,13 +1056,13 @@ static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
 		dst_dma = edesc->iv_dma;
 	} else {
 		if (likely(req->src == req->dst)) {
-			dst_dma = src_dma + sizeof(struct link_tbl_entry) *
+			dst_dma = src_dma + sizeof(struct sec4_sg_entry) *
 				  edesc->assoc_nents;
 			out_options = LDST_SGF;
 		} else {
-			dst_dma = edesc->link_tbl_dma +
-				  link_tbl_index *
-				  sizeof(struct link_tbl_entry);
+			dst_dma = edesc->sec4_sg_dma +
+				  sec4_sg_index *
+				  sizeof(struct sec4_sg_entry);
 			out_options = LDST_SGF;
 		}
 	}
@@ -1226,7 +1083,7 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 	u32 *desc = edesc->hw_desc;
 	u32 out_options = 0, in_options;
 	dma_addr_t dst_dma, src_dma;
-	int len, link_tbl_index = 0;
+	int len, sec4_sg_index = 0;
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "presciv@"xstr(__LINE__)": ",
@@ -1244,8 +1101,8 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 		src_dma = edesc->iv_dma;
 		in_options = 0;
 	} else {
-		src_dma = edesc->link_tbl_dma;
-		link_tbl_index += (iv_contig ? 0 : 1) + edesc->src_nents;
+		src_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += (iv_contig ? 0 : 1) + edesc->src_nents;
 		in_options = LDST_SGF;
 	}
 	append_seq_in_ptr(desc, src_dma, req->nbytes + ivsize, in_options);
@@ -1254,16 +1111,16 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 		if (!edesc->src_nents && iv_contig) {
 			dst_dma = sg_dma_address(req->src);
 		} else {
-			dst_dma = edesc->link_tbl_dma +
-				sizeof(struct link_tbl_entry);
+			dst_dma = edesc->sec4_sg_dma +
+				sizeof(struct sec4_sg_entry);
 			out_options = LDST_SGF;
 		}
 	} else {
 		if (!edesc->dst_nents) {
 			dst_dma = sg_dma_address(req->dst);
 		} else {
-			dst_dma = edesc->link_tbl_dma +
-				link_tbl_index * sizeof(struct link_tbl_entry);
+			dst_dma = edesc->sec4_sg_dma +
+				sec4_sg_index * sizeof(struct sec4_sg_entry);
 			out_options = LDST_SGF;
 		}
 	}
@@ -1271,28 +1128,6 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 }
 
 /*
- * derive number of elements in scatterlist
- */
-static int sg_count(struct scatterlist *sg_list, int nbytes)
-{
-	struct scatterlist *sg = sg_list;
-	int sg_nents = 0;
-
-	while (nbytes > 0) {
-		sg_nents++;
-		nbytes -= sg->length;
-		if (!sg_is_last(sg) && (sg + 1)->length == 0)
-			BUG(); /* Not support chaining */
-		sg = scatterwalk_sg_next(sg);
-	}
-
-	if (likely(sg_nents == 1))
-		return 0;
-
-	return sg_nents;
-}
-
-/*
  * allocate and map the aead extended descriptor
  */
 static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
@@ -1308,25 +1143,26 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	dma_addr_t iv_dma = 0;
 	int sgc;
 	bool all_contig = true;
+	bool assoc_chained = false, src_chained = false, dst_chained = false;
 	int ivsize = crypto_aead_ivsize(aead);
-	int link_tbl_index, link_tbl_len = 0, link_tbl_bytes;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 
-	assoc_nents = sg_count(req->assoc, req->assoclen);
-	src_nents = sg_count(req->src, req->cryptlen);
+	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
+	src_nents = sg_count(req->src, req->cryptlen, &src_chained);
 
 	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->cryptlen);
+		dst_nents = sg_count(req->dst, req->cryptlen, &dst_chained);
 
-	sgc = dma_map_sg(jrdev, req->assoc, assoc_nents ? : 1,
-			 DMA_BIDIRECTIONAL);
+	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
+				 DMA_BIDIRECTIONAL, assoc_chained);
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/* Check if data are contiguous */
@@ -1337,50 +1173,53 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 		all_contig = false;
 		assoc_nents = assoc_nents ? : 1;
 		src_nents = src_nents ? : 1;
-		link_tbl_len = assoc_nents + 1 + src_nents;
+		sec4_sg_len = assoc_nents + 1 + src_nents;
 	}
-	link_tbl_len += dst_nents;
+	sec4_sg_len += dst_nents;
 
-	link_tbl_bytes = link_tbl_len * sizeof(struct link_tbl_entry);
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
 	edesc = kmalloc(sizeof(struct aead_edesc) + desc_bytes +
-			link_tbl_bytes, GFP_DMA | flags);
+			sec4_sg_bytes, GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	edesc->assoc_nents = assoc_nents;
+	edesc->assoc_chained = assoc_chained;
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
 	edesc->iv_dma = iv_dma;
-	edesc->link_tbl_bytes = link_tbl_bytes;
-	edesc->link_tbl = (void *)edesc + sizeof(struct aead_edesc) +
-			  desc_bytes;
-	edesc->link_tbl_dma = dma_map_single(jrdev, edesc->link_tbl,
-					     link_tbl_bytes, DMA_TO_DEVICE);
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
+			 desc_bytes;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
 	*all_contig_ptr = all_contig;
 
-	link_tbl_index = 0;
+	sec4_sg_index = 0;
 	if (!all_contig) {
-		sg_to_link_tbl(req->assoc,
-			       (assoc_nents ? : 1),
-			       edesc->link_tbl +
-			       link_tbl_index, 0);
-		link_tbl_index += assoc_nents ? : 1;
-		sg_to_link_tbl_one(edesc->link_tbl + link_tbl_index,
+		sg_to_sec4_sg(req->assoc,
+			      (assoc_nents ? : 1),
+			      edesc->sec4_sg +
+			      sec4_sg_index, 0);
+		sec4_sg_index += assoc_nents ? : 1;
+		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
 				   iv_dma, ivsize, 0);
-		link_tbl_index += 1;
-		sg_to_link_tbl_last(req->src,
-				    (src_nents ? : 1),
-				    edesc->link_tbl +
-				    link_tbl_index, 0);
-		link_tbl_index += src_nents ? : 1;
+		sec4_sg_index += 1;
+		sg_to_sec4_sg_last(req->src,
+				   (src_nents ? : 1),
+				   edesc->sec4_sg +
+				   sec4_sg_index, 0);
+		sec4_sg_index += src_nents ? : 1;
 	}
 	if (dst_nents) {
-		sg_to_link_tbl_last(req->dst, dst_nents,
-				    edesc->link_tbl + link_tbl_index, 0);
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
 	}
 
 	return edesc;
@@ -1487,24 +1326,25 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	int sgc;
 	u32 contig = GIV_SRC_CONTIG | GIV_DST_CONTIG;
 	int ivsize = crypto_aead_ivsize(aead);
-	int link_tbl_index, link_tbl_len = 0, link_tbl_bytes;
+	bool assoc_chained = false, src_chained = false, dst_chained = false;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 
-	assoc_nents = sg_count(req->assoc, req->assoclen);
-	src_nents = sg_count(req->src, req->cryptlen);
+	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
+	src_nents = sg_count(req->src, req->cryptlen, &src_chained);
 
 	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->cryptlen);
+		dst_nents = sg_count(req->dst, req->cryptlen, &dst_chained);
 
-	sgc = dma_map_sg(jrdev, req->assoc, assoc_nents ? : 1,
-			 DMA_BIDIRECTIONAL);
+	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
+				 DMA_BIDIRECTIONAL, assoc_chained);
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/* Check if data are contiguous */
@@ -1516,58 +1356,61 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 		contig &= ~GIV_DST_CONTIG;
 		if (unlikely(req->src != req->dst)) {
 			dst_nents = dst_nents ? : 1;
-			link_tbl_len += 1;
+			sec4_sg_len += 1;
 		}
 	if (!(contig & GIV_SRC_CONTIG)) {
 		assoc_nents = assoc_nents ? : 1;
 		src_nents = src_nents ? : 1;
-		link_tbl_len += assoc_nents + 1 + src_nents;
+		sec4_sg_len += assoc_nents + 1 + src_nents;
 		if (likely(req->src == req->dst))
 			contig &= ~GIV_DST_CONTIG;
 	}
-	link_tbl_len += dst_nents;
+	sec4_sg_len += dst_nents;
 
-	link_tbl_bytes = link_tbl_len * sizeof(struct link_tbl_entry);
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
 	edesc = kmalloc(sizeof(struct aead_edesc) + desc_bytes +
-			link_tbl_bytes, GFP_DMA | flags);
+			sec4_sg_bytes, GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	edesc->assoc_nents = assoc_nents;
+	edesc->assoc_chained = assoc_chained;
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
 	edesc->iv_dma = iv_dma;
-	edesc->link_tbl_bytes = link_tbl_bytes;
-	edesc->link_tbl = (void *)edesc + sizeof(struct aead_edesc) +
-			  desc_bytes;
-	edesc->link_tbl_dma = dma_map_single(jrdev, edesc->link_tbl,
-					     link_tbl_bytes, DMA_TO_DEVICE);
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
+			 desc_bytes;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
 	*contig_ptr = contig;
 
-	link_tbl_index = 0;
+	sec4_sg_index = 0;
 	if (!(contig & GIV_SRC_CONTIG)) {
-		sg_to_link_tbl(req->assoc, assoc_nents,
-			       edesc->link_tbl +
-			       link_tbl_index, 0);
-		link_tbl_index += assoc_nents;
-		sg_to_link_tbl_one(edesc->link_tbl + link_tbl_index,
+		sg_to_sec4_sg(req->assoc, assoc_nents,
+			      edesc->sec4_sg +
+			      sec4_sg_index, 0);
+		sec4_sg_index += assoc_nents;
+		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
 				   iv_dma, ivsize, 0);
-		link_tbl_index += 1;
-		sg_to_link_tbl_last(req->src, src_nents,
-				    edesc->link_tbl +
-				    link_tbl_index, 0);
-		link_tbl_index += src_nents;
+		sec4_sg_index += 1;
+		sg_to_sec4_sg_last(req->src, src_nents,
+				   edesc->sec4_sg +
+				   sec4_sg_index, 0);
+		sec4_sg_index += src_nents;
 	}
 	if (unlikely(req->src != req->dst && !(contig & GIV_DST_CONTIG))) {
-		sg_to_link_tbl_one(edesc->link_tbl + link_tbl_index,
+		dma_to_sec4_sg_one(edesc->sec4_sg + sec4_sg_index,
 				   iv_dma, ivsize, 0);
-		link_tbl_index += 1;
-		sg_to_link_tbl_last(req->dst, dst_nents,
-				    edesc->link_tbl + link_tbl_index, 0);
+		sec4_sg_index += 1;
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
 	}
 
 	return edesc;
@@ -1633,27 +1476,28 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
 					  CRYPTO_TFM_REQ_MAY_SLEEP)) ?
 		       GFP_KERNEL : GFP_ATOMIC;
-	int src_nents, dst_nents = 0, link_tbl_bytes;
+	int src_nents, dst_nents = 0, sec4_sg_bytes;
 	struct ablkcipher_edesc *edesc;
 	dma_addr_t iv_dma = 0;
 	bool iv_contig = false;
 	int sgc;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
-	int link_tbl_index;
+	bool src_chained = false, dst_chained = false;
+	int sec4_sg_index;
 
-	src_nents = sg_count(req->src, req->nbytes);
+	src_nents = sg_count(req->src, req->nbytes, &src_chained);
 
-	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->nbytes);
+	if (req->dst != req->src)
+		dst_nents = sg_count(req->dst, req->nbytes, &dst_chained);
 
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/*
@@ -1665,44 +1509,46 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		iv_contig = true;
 	else
 		src_nents = src_nents ? : 1;
-	link_tbl_bytes = ((iv_contig ? 0 : 1) + src_nents + dst_nents) *
-			 sizeof(struct link_tbl_entry);
+	sec4_sg_bytes = ((iv_contig ? 0 : 1) + src_nents + dst_nents) *
+			sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
 	edesc = kmalloc(sizeof(struct ablkcipher_edesc) + desc_bytes +
-			link_tbl_bytes, GFP_DMA | flags);
+			sec4_sg_bytes, GFP_DMA | flags);
 	if (!edesc) {
 		dev_err(jrdev, "could not allocate extended descriptor\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
-	edesc->link_tbl_bytes = link_tbl_bytes;
-	edesc->link_tbl = (void *)edesc + sizeof(struct ablkcipher_edesc) +
-			  desc_bytes;
+	edesc->dst_chained = dst_chained;
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
+			 desc_bytes;
 
-	link_tbl_index = 0;
+	sec4_sg_index = 0;
 	if (!iv_contig) {
-		sg_to_link_tbl_one(edesc->link_tbl, iv_dma, ivsize, 0);
-		sg_to_link_tbl_last(req->src, src_nents,
-				    edesc->link_tbl + 1, 0);
-		link_tbl_index += 1 + src_nents;
+		dma_to_sec4_sg_one(edesc->sec4_sg, iv_dma, ivsize, 0);
+		sg_to_sec4_sg_last(req->src, src_nents,
+				   edesc->sec4_sg + 1, 0);
+		sec4_sg_index += 1 + src_nents;
 	}
 
-	if (unlikely(dst_nents)) {
-		sg_to_link_tbl_last(req->dst, dst_nents,
-			edesc->link_tbl + link_tbl_index, 0);
+	if (dst_nents) {
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+			edesc->sec4_sg + sec4_sg_index, 0);
 	}
 
-	edesc->link_tbl_dma = dma_map_single(jrdev, edesc->link_tbl,
-					     link_tbl_bytes, DMA_TO_DEVICE);
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
 	edesc->iv_dma = iv_dma;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher link_tbl@"xstr(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->link_tbl,
-		       link_tbl_bytes, 1);
+	print_hex_dump(KERN_ERR, "ablkcipher sec4_sg@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->sec4_sg,
+		       sec4_sg_bytes, 1);
 #endif
 
 	*iv_contig_out = iv_contig;
@@ -2227,7 +2073,7 @@ static int caam_cra_init(struct crypto_tfm *tfm)
 	 * distribute tfms across job rings to ensure in-order
 	 * crypto request processing per tfm
 	 */
-	ctx->jrdev = priv->algapi_jr[(tgt_jr / 2) % priv->num_jrs_for_algapi];
+	ctx->jrdev = priv->jrdev[(tgt_jr / 2) % priv->total_jobrs];
 
 	/* copy descriptor header template value */
 	ctx->class1_alg_type = OP_TYPE_CLASS1_ALG | caam_alg->class1_alg_type;
@@ -2264,7 +2110,6 @@ static void __exit caam_algapi_exit(void)
 	struct device *ctrldev;
 	struct caam_drv_private *priv;
 	struct caam_crypto_alg *t_alg, *n;
-	int i, err;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
 	if (!dev_node) {
@@ -2289,13 +2134,6 @@ static void __exit caam_algapi_exit(void)
 		list_del(&t_alg->entry);
 		kfree(t_alg);
 	}
-
-	for (i = 0; i < priv->total_jobrs; i++) {
-		err = caam_jr_deregister(priv->algapi_jr[i]);
-		if (err < 0)
-			break;
-	}
-	kfree(priv->algapi_jr);
 }
 
 static struct caam_crypto_alg *caam_alg_alloc(struct device *ctrldev,
@@ -2348,7 +2186,7 @@ static int __init caam_algapi_init(void)
 {
 	struct device_node *dev_node;
 	struct platform_device *pdev;
-	struct device *ctrldev, **jrdev;
+	struct device *ctrldev;
 	struct caam_drv_private *priv;
 	int i = 0, err = 0;
 
@@ -2369,24 +2207,6 @@ static int __init caam_algapi_init(void)
 
 	INIT_LIST_HEAD(&priv->alg_list);
 
-	jrdev = kmalloc(sizeof(*jrdev) * priv->total_jobrs, GFP_KERNEL);
-	if (!jrdev)
-		return -ENOMEM;
-
-	for (i = 0; i < priv->total_jobrs; i++) {
-		err = caam_jr_register(ctrldev, &jrdev[i]);
-		if (err < 0)
-			break;
-	}
-	if (err < 0 && i == 0) {
-		dev_err(ctrldev, "algapi error in job ring registration: %d\n",
-			err);
-		kfree(jrdev);
-		return err;
-	}
-
-	priv->num_jrs_for_algapi = i;
-	priv->algapi_jr = jrdev;
 	atomic_set(&priv->tfm_count, -1);
 
 	/* register crypto algorithms the device supports */
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
new file mode 100644
index 0000000..895aaf2
--- /dev/null
+++ b/drivers/crypto/caam/caamhash.c
@@ -0,0 +1,1878 @@
+/*
+ * caam - Freescale FSL CAAM support for ahash functions of crypto API
+ *
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ *
+ * Based on caamalg.c crypto API driver.
+ *
+ * relationship of digest job descriptor or first job descriptor after init to
+ * shared descriptors:
+ *
+ * ---------------                     ---------------
+ * | JobDesc #1  |-------------------->|  ShareDesc  |
+ * | *(packet 1) |                     |  (hashKey)  |
+ * ---------------                     | (operation) |
+ *                                     ---------------
+ *
+ * relationship of subsequent job descriptors to shared descriptors:
+ *
+ * ---------------                     ---------------
+ * | JobDesc #2  |-------------------->|  ShareDesc  |
+ * | *(packet 2) |      |------------->|  (hashKey)  |
+ * ---------------      |    |-------->| (operation) |
+ *       .              |    |         | (load ctx2) |
+ *       .              |    |         ---------------
+ * ---------------      |    |
+ * | JobDesc #3  |------|    |
+ * | *(packet 3) |           |
+ * ---------------           |
+ *       .                   |
+ *       .                   |
+ * ---------------           |
+ * | JobDesc #4  |------------
+ * | *(packet 4) |
+ * ---------------
+ *
+ * The SharedDesc never changes for a connection unless rekeyed, but
+ * each packet will likely be in a different place. So all we need
+ * to know to process the packet is where the input is, where the
+ * output goes, and what context we want to process with. Context is
+ * in the SharedDesc, packet references in the JobDesc.
+ *
+ * So, a job desc looks like:
+ *
+ * ---------------------
+ * | Header            |
+ * | ShareDesc Pointer |
+ * | SEQ_OUT_PTR       |
+ * | (output buffer)   |
+ * | (output length)   |
+ * | SEQ_IN_PTR        |
+ * | (input buffer)    |
+ * | (input length)    |
+ * ---------------------
+ */
+
+#include "compat.h"
+
+#include "regs.h"
+#include "intern.h"
+#include "desc_constr.h"
+#include "jr.h"
+#include "error.h"
+#include "sg_sw_sec4.h"
+#include "key_gen.h"
+
+#define CAAM_CRA_PRIORITY		3000
+
+/* max hash key is max split key size */
+#define CAAM_MAX_HASH_KEY_SIZE		(SHA512_DIGEST_SIZE * 2)
+
+#define CAAM_MAX_HASH_BLOCK_SIZE	SHA512_BLOCK_SIZE
+#define CAAM_MAX_HASH_DIGEST_SIZE	SHA512_DIGEST_SIZE
+
+/* length of descriptors text */
+#define DESC_JOB_IO_LEN			(CAAM_CMD_SZ * 5 + CAAM_PTR_SZ * 3)
+
+#define DESC_AHASH_BASE			(4 * CAAM_CMD_SZ)
+#define DESC_AHASH_UPDATE_LEN		(6 * CAAM_CMD_SZ)
+#define DESC_AHASH_UPDATE_FIRST_LEN	(DESC_AHASH_BASE + 4 * CAAM_CMD_SZ)
+#define DESC_AHASH_FINAL_LEN		(DESC_AHASH_BASE + 5 * CAAM_CMD_SZ)
+#define DESC_AHASH_FINUP_LEN		(DESC_AHASH_BASE + 5 * CAAM_CMD_SZ)
+#define DESC_AHASH_DIGEST_LEN		(DESC_AHASH_BASE + 4 * CAAM_CMD_SZ)
+
+#define DESC_HASH_MAX_USED_BYTES	(DESC_AHASH_FINAL_LEN + \
+					 CAAM_MAX_HASH_KEY_SIZE)
+#define DESC_HASH_MAX_USED_LEN		(DESC_HASH_MAX_USED_BYTES / CAAM_CMD_SZ)
+
+/* caam context sizes for hashes: running digest + 8 */
+#define HASH_MSG_LEN			8
+#define MAX_CTX_LEN			(HASH_MSG_LEN + SHA512_DIGEST_SIZE)
+
+#ifdef DEBUG
+/* for print_hex_dumps with line references */
+#define xstr(s) str(s)
+#define str(s) #s
+#define debug(format, arg...) printk(format, arg)
+#else
+#define debug(format, arg...)
+#endif
+
+/* ahash per-session context */
+struct caam_hash_ctx {
+	struct device *jrdev;
+	u32 sh_desc_update[DESC_HASH_MAX_USED_LEN];
+	u32 sh_desc_update_first[DESC_HASH_MAX_USED_LEN];
+	u32 sh_desc_fin[DESC_HASH_MAX_USED_LEN];
+	u32 sh_desc_digest[DESC_HASH_MAX_USED_LEN];
+	u32 sh_desc_finup[DESC_HASH_MAX_USED_LEN];
+	dma_addr_t sh_desc_update_dma;
+	dma_addr_t sh_desc_update_first_dma;
+	dma_addr_t sh_desc_fin_dma;
+	dma_addr_t sh_desc_digest_dma;
+	dma_addr_t sh_desc_finup_dma;
+	u32 alg_type;
+	u32 alg_op;
+	u8 key[CAAM_MAX_HASH_KEY_SIZE];
+	dma_addr_t key_dma;
+	int ctx_len;
+	unsigned int split_key_len;
+	unsigned int split_key_pad_len;
+};
+
+/* ahash state */
+struct caam_hash_state {
+	dma_addr_t buf_dma;
+	dma_addr_t ctx_dma;
+	u8 buf_0[CAAM_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
+	int buflen_0;
+	u8 buf_1[CAAM_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
+	int buflen_1;
+	u8 caam_ctx[MAX_CTX_LEN];
+	int (*update)(struct ahash_request *req);
+	int (*final)(struct ahash_request *req);
+	int (*finup)(struct ahash_request *req);
+	int current_buf;
+};
+
+/* Common job descriptor seq in/out ptr routines */
+
+/* Map state->caam_ctx, and append seq_out_ptr command that points to it */
+static inline void map_seq_out_ptr_ctx(u32 *desc, struct device *jrdev,
+				       struct caam_hash_state *state,
+				       int ctx_len)
+{
+	state->ctx_dma = dma_map_single(jrdev, state->caam_ctx,
+					ctx_len, DMA_FROM_DEVICE);
+	append_seq_out_ptr(desc, state->ctx_dma, ctx_len, 0);
+}
+
+/* Map req->result, and append seq_out_ptr command that points to it */
+static inline dma_addr_t map_seq_out_ptr_result(u32 *desc, struct device *jrdev,
+						u8 *result, int digestsize)
+{
+	dma_addr_t dst_dma;
+
+	dst_dma = dma_map_single(jrdev, result, digestsize, DMA_FROM_DEVICE);
+	append_seq_out_ptr(desc, dst_dma, digestsize, 0);
+
+	return dst_dma;
+}
+
+/* Map current buffer in state and put it in link table */
+static inline dma_addr_t buf_map_to_sec4_sg(struct device *jrdev,
+					    struct sec4_sg_entry *sec4_sg,
+					    u8 *buf, int buflen)
+{
+	dma_addr_t buf_dma;
+
+	buf_dma = dma_map_single(jrdev, buf, buflen, DMA_TO_DEVICE);
+	dma_to_sec4_sg_one(sec4_sg, buf_dma, buflen, 0);
+
+	return buf_dma;
+}
+
+/* Map req->src and put it in link table */
+static inline void src_map_to_sec4_sg(struct device *jrdev,
+				      struct scatterlist *src, int src_nents,
+				      struct sec4_sg_entry *sec4_sg,
+				      bool chained)
+{
+	dma_map_sg_chained(jrdev, src, src_nents, DMA_TO_DEVICE, chained);
+	sg_to_sec4_sg_last(src, src_nents, sec4_sg, 0);
+}
+
+/*
+ * Only put buffer in link table if it contains data, which is possible,
+ * since a buffer has previously been used, and needs to be unmapped,
+ */
+static inline dma_addr_t
+try_buf_map_to_sec4_sg(struct device *jrdev, struct sec4_sg_entry *sec4_sg,
+		       u8 *buf, dma_addr_t buf_dma, int buflen,
+		       int last_buflen)
+{
+	if (buf_dma && !dma_mapping_error(jrdev, buf_dma))
+		dma_unmap_single(jrdev, buf_dma, last_buflen, DMA_TO_DEVICE);
+	if (buflen)
+		buf_dma = buf_map_to_sec4_sg(jrdev, sec4_sg, buf, buflen);
+	else
+		buf_dma = 0;
+
+	return buf_dma;
+}
+
+/* Map state->caam_ctx, and add it to link table */
+static inline void ctx_map_to_sec4_sg(u32 *desc, struct device *jrdev,
+				      struct caam_hash_state *state,
+				      int ctx_len,
+				      struct sec4_sg_entry *sec4_sg,
+				      u32 flag)
+{
+	state->ctx_dma = dma_map_single(jrdev, state->caam_ctx, ctx_len, flag);
+	dma_to_sec4_sg_one(sec4_sg, state->ctx_dma, ctx_len, 0);
+}
+
+/* Common shared descriptor commands */
+static inline void append_key_ahash(u32 *desc, struct caam_hash_ctx *ctx)
+{
+	append_key_as_imm(desc, ctx->key, ctx->split_key_pad_len,
+			  ctx->split_key_len, CLASS_2 |
+			  KEY_DEST_MDHA_SPLIT | KEY_ENC);
+}
+
+/* Append key if it has been set */
+static inline void init_sh_desc_key_ahash(u32 *desc, struct caam_hash_ctx *ctx)
+{
+	u32 *key_jump_cmd;
+
+	init_sh_desc(desc, HDR_SHARE_WAIT);
+
+	if (ctx->split_key_len) {
+		/* Skip if already shared */
+		key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					   JUMP_COND_SHRD);
+
+		append_key_ahash(desc, ctx);
+
+		set_jump_tgt_here(desc, key_jump_cmd);
+	}
+
+	/* Propagate errors from shared to job descriptor */
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
+}
+
+/*
+ * For ahash read data from seqin following state->caam_ctx,
+ * and write resulting class2 context to seqout, which may be state->caam_ctx
+ * or req->result
+ */
+static inline void ahash_append_load_str(u32 *desc, int digestsize)
+{
+	/* Calculate remaining bytes to read */
+	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
+	/* Read remaining bytes */
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_LAST2 |
+			     FIFOLD_TYPE_MSG | KEY_VLF);
+
+	/* Store class2 context bytes */
+	append_seq_store(desc, digestsize, LDST_CLASS_2_CCB |
+			 LDST_SRCDST_BYTE_CONTEXT);
+}
+
+/*
+ * For ahash update, final and finup, import context, read and write to seqout
+ */
+static inline void ahash_ctx_data_to_out(u32 *desc, u32 op, u32 state,
+					 int digestsize,
+					 struct caam_hash_ctx *ctx)
+{
+	init_sh_desc_key_ahash(desc, ctx);
+
+	/* Import context from software */
+	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_BYTE_CONTEXT |
+		   LDST_CLASS_2_CCB | ctx->ctx_len);
+
+	/* Class 2 operation */
+	append_operation(desc, op | state | OP_ALG_ENCRYPT);
+
+	/*
+	 * Load from buf and/or src and write to req->result or state->context
+	 */
+	ahash_append_load_str(desc, digestsize);
+}
+
+/* For ahash firsts and digest, read and write to seqout */
+static inline void ahash_data_to_out(u32 *desc, u32 op, u32 state,
+				     int digestsize, struct caam_hash_ctx *ctx)
+{
+	init_sh_desc_key_ahash(desc, ctx);
+
+	/* Class 2 operation */
+	append_operation(desc, op | state | OP_ALG_ENCRYPT);
+
+	/*
+	 * Load from buf and/or src and write to req->result or state->context
+	 */
+	ahash_append_load_str(desc, digestsize);
+}
+
+static int ahash_set_sh_desc(struct crypto_ahash *ahash)
+{
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	int digestsize = crypto_ahash_digestsize(ahash);
+	struct device *jrdev = ctx->jrdev;
+	u32 have_key = 0;
+	u32 *desc;
+
+	if (ctx->split_key_len)
+		have_key = OP_ALG_AAI_HMAC_PRECOMP;
+
+	/* ahash_update shared descriptor */
+	desc = ctx->sh_desc_update;
+
+	init_sh_desc(desc, HDR_SHARE_WAIT);
+
+	/* Import context from software */
+	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_BYTE_CONTEXT |
+		   LDST_CLASS_2_CCB | ctx->ctx_len);
+
+	/* Class 2 operation */
+	append_operation(desc, ctx->alg_type | OP_ALG_AS_UPDATE |
+			 OP_ALG_ENCRYPT);
+
+	/* Load data and write to result or context */
+	ahash_append_load_str(desc, ctx->ctx_len);
+
+	ctx->sh_desc_update_dma = dma_map_single(jrdev, desc, desc_bytes(desc),
+						 DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_update_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ahash update shdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	/* ahash_update_first shared descriptor */
+	desc = ctx->sh_desc_update_first;
+
+	ahash_data_to_out(desc, have_key | ctx->alg_type, OP_ALG_AS_INIT,
+			  ctx->ctx_len, ctx);
+
+	ctx->sh_desc_update_first_dma = dma_map_single(jrdev, desc,
+						       desc_bytes(desc),
+						       DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_update_first_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ahash update first shdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	/* ahash_final shared descriptor */
+	desc = ctx->sh_desc_fin;
+
+	ahash_ctx_data_to_out(desc, have_key | ctx->alg_type,
+			      OP_ALG_AS_FINALIZE, digestsize, ctx);
+
+	ctx->sh_desc_fin_dma = dma_map_single(jrdev, desc, desc_bytes(desc),
+					      DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_fin_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ahash final shdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+		       desc_bytes(desc), 1);
+#endif
+
+	/* ahash_finup shared descriptor */
+	desc = ctx->sh_desc_finup;
+
+	ahash_ctx_data_to_out(desc, have_key | ctx->alg_type,
+			      OP_ALG_AS_FINALIZE, digestsize, ctx);
+
+	ctx->sh_desc_finup_dma = dma_map_single(jrdev, desc, desc_bytes(desc),
+						DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_finup_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ahash finup shdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+		       desc_bytes(desc), 1);
+#endif
+
+	/* ahash_digest shared descriptor */
+	desc = ctx->sh_desc_digest;
+
+	ahash_data_to_out(desc, have_key | ctx->alg_type, OP_ALG_AS_INITFINAL,
+			  digestsize, ctx);
+
+	ctx->sh_desc_digest_dma = dma_map_single(jrdev, desc,
+						 desc_bytes(desc),
+						 DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_digest_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ahash digest shdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+		       desc_bytes(desc), 1);
+#endif
+
+	return 0;
+}
+
+static u32 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,
+			       ctx->split_key_pad_len, key_in, keylen,
+			       ctx->alg_op);
+}
+
+/* Digest hash size if it is too large */
+static u32 hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
+			   u32 *keylen, u8 *key_out, u32 digestsize)
+{
+	struct device *jrdev = ctx->jrdev;
+	u32 *desc;
+	struct split_key_result result;
+	dma_addr_t src_dma, dst_dma;
+	int ret = 0;
+
+	desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
+
+	init_job_desc(desc, 0);
+
+	src_dma = dma_map_single(jrdev, (void *)key_in, *keylen,
+				 DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, src_dma)) {
+		dev_err(jrdev, "unable to map key input memory\n");
+		kfree(desc);
+		return -ENOMEM;
+	}
+	dst_dma = dma_map_single(jrdev, (void *)key_out, digestsize,
+				 DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, dst_dma)) {
+		dev_err(jrdev, "unable to map key output memory\n");
+		dma_unmap_single(jrdev, src_dma, *keylen, DMA_TO_DEVICE);
+		kfree(desc);
+		return -ENOMEM;
+	}
+
+	/* Job descriptor to perform unkeyed hash on key_in */
+	append_operation(desc, ctx->alg_type | OP_ALG_ENCRYPT |
+			 OP_ALG_AS_INITFINAL);
+	append_seq_in_ptr(desc, src_dma, *keylen, 0);
+	append_seq_fifo_load(desc, *keylen, FIFOLD_CLASS_CLASS2 |
+			     FIFOLD_TYPE_LAST2 | FIFOLD_TYPE_MSG);
+	append_seq_out_ptr(desc, dst_dma, digestsize, 0);
+	append_seq_store(desc, digestsize, LDST_CLASS_2_CCB |
+			 LDST_SRCDST_BYTE_CONTEXT);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "key_in@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key_in, *keylen, 1);
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	result.err = 0;
+	init_completion(&result.completion);
+
+	ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result);
+	if (!ret) {
+		/* in progress */
+		wait_for_completion_interruptible(&result.completion);
+		ret = result.err;
+#ifdef DEBUG
+		print_hex_dump(KERN_ERR, "digested key@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, key_in,
+			       digestsize, 1);
+#endif
+	}
+	*keylen = digestsize;
+
+	dma_unmap_single(jrdev, src_dma, *keylen, DMA_TO_DEVICE);
+	dma_unmap_single(jrdev, dst_dma, digestsize, DMA_FROM_DEVICE);
+
+	kfree(desc);
+
+	return ret;
+}
+
+static int ahash_setkey(struct crypto_ahash *ahash,
+			const u8 *key, unsigned int keylen)
+{
+	/* Sizes for MDHA pads (*not* keys): MD5, SHA1, 224, 256, 384, 512 */
+	static const u8 mdpadlen[] = { 16, 20, 32, 32, 64, 64 };
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct device *jrdev = ctx->jrdev;
+	int blocksize = crypto_tfm_alg_blocksize(&ahash->base);
+	int digestsize = crypto_ahash_digestsize(ahash);
+	int ret = 0;
+	u8 *hashed_key = NULL;
+
+#ifdef DEBUG
+	printk(KERN_ERR "keylen %d\n", keylen);
+#endif
+
+	if (keylen > blocksize) {
+		hashed_key = kmalloc(sizeof(u8) * digestsize, GFP_KERNEL |
+				     GFP_DMA);
+		if (!hashed_key)
+			return -ENOMEM;
+		ret = hash_digest_key(ctx, key, &keylen, hashed_key,
+				      digestsize);
+		if (ret)
+			goto badkey;
+		key = hashed_key;
+	}
+
+	/* Pick class 2 key length from algorithm submask */
+	ctx->split_key_len = mdpadlen[(ctx->alg_op & OP_ALG_ALGSEL_SUBMASK) >>
+				      OP_ALG_ALGSEL_SHIFT] * 2;
+	ctx->split_key_pad_len = ALIGN(ctx->split_key_len, 16);
+
+#ifdef DEBUG
+	printk(KERN_ERR "split_key_len %d split_key_pad_len %d\n",
+	       ctx->split_key_len, ctx->split_key_pad_len);
+	print_hex_dump(KERN_ERR, "key in @"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+
+	ret = gen_split_hash_key(ctx, key, keylen);
+	if (ret)
+		goto badkey;
+
+	ctx->key_dma = dma_map_single(jrdev, ctx->key, ctx->split_key_pad_len,
+				      DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->key_dma)) {
+		dev_err(jrdev, "unable to map key i/o memory\n");
+		return -ENOMEM;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
+		       ctx->split_key_pad_len, 1);
+#endif
+
+	ret = ahash_set_sh_desc(ahash);
+	if (ret) {
+		dma_unmap_single(jrdev, ctx->key_dma, ctx->split_key_pad_len,
+				 DMA_TO_DEVICE);
+	}
+
+	kfree(hashed_key);
+	return ret;
+badkey:
+	kfree(hashed_key);
+	crypto_ahash_set_flags(ahash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	return -EINVAL;
+}
+
+/*
+ * ahash_edesc - s/w-extended ahash descriptor
+ * @dst_dma: physical mapped address of req->result
+ * @sec4_sg_dma: physical mapped address of h/w link table
+ * @chained: if source is chained
+ * @src_nents: number of segments in input scatterlist
+ * @sec4_sg_bytes: length of dma mapped sec4_sg space
+ * @sec4_sg: pointer to h/w link table
+ * @hw_desc: the h/w job descriptor followed by any referenced link tables
+ */
+struct ahash_edesc {
+	dma_addr_t dst_dma;
+	dma_addr_t sec4_sg_dma;
+	bool chained;
+	int src_nents;
+	int sec4_sg_bytes;
+	struct sec4_sg_entry *sec4_sg;
+	u32 hw_desc[0];
+};
+
+static inline void ahash_unmap(struct device *dev,
+			struct ahash_edesc *edesc,
+			struct ahash_request *req, int dst_len)
+{
+	if (edesc->src_nents)
+		dma_unmap_sg_chained(dev, req->src, edesc->src_nents,
+				     DMA_TO_DEVICE, edesc->chained);
+	if (edesc->dst_dma)
+		dma_unmap_single(dev, edesc->dst_dma, dst_len, DMA_FROM_DEVICE);
+
+	if (edesc->sec4_sg_bytes)
+		dma_unmap_single(dev, edesc->sec4_sg_dma,
+				 edesc->sec4_sg_bytes, DMA_TO_DEVICE);
+}
+
+static inline void ahash_unmap_ctx(struct device *dev,
+			struct ahash_edesc *edesc,
+			struct ahash_request *req, int dst_len, u32 flag)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	if (state->ctx_dma)
+		dma_unmap_single(dev, state->ctx_dma, ctx->ctx_len, flag);
+	ahash_unmap(dev, edesc, req, dst_len);
+}
+
+static void ahash_done(struct device *jrdev, u32 *desc, u32 err,
+		       void *context)
+{
+	struct ahash_request *req = context;
+	struct ahash_edesc *edesc;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	int digestsize = crypto_ahash_digestsize(ahash);
+#ifdef DEBUG
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = (struct ahash_edesc *)((char *)desc -
+		 offsetof(struct ahash_edesc, hw_desc));
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(jrdev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	ahash_unmap(jrdev, edesc, req, digestsize);
+	kfree(edesc);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
+		       ctx->ctx_len, 1);
+	if (req->result)
+		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
+			       digestsize, 1);
+#endif
+
+	req->base.complete(&req->base, err);
+}
+
+static void ahash_done_bi(struct device *jrdev, u32 *desc, u32 err,
+			    void *context)
+{
+	struct ahash_request *req = context;
+	struct ahash_edesc *edesc;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+#ifdef DEBUG
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	int digestsize = crypto_ahash_digestsize(ahash);
+
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = (struct ahash_edesc *)((char *)desc -
+		 offsetof(struct ahash_edesc, hw_desc));
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(jrdev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len, DMA_BIDIRECTIONAL);
+	kfree(edesc);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
+		       ctx->ctx_len, 1);
+	if (req->result)
+		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
+			       digestsize, 1);
+#endif
+
+	req->base.complete(&req->base, err);
+}
+
+static void ahash_done_ctx_src(struct device *jrdev, u32 *desc, u32 err,
+			       void *context)
+{
+	struct ahash_request *req = context;
+	struct ahash_edesc *edesc;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	int digestsize = crypto_ahash_digestsize(ahash);
+#ifdef DEBUG
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = (struct ahash_edesc *)((char *)desc -
+		 offsetof(struct ahash_edesc, hw_desc));
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(jrdev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	ahash_unmap_ctx(jrdev, edesc, req, digestsize, DMA_FROM_DEVICE);
+	kfree(edesc);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
+		       ctx->ctx_len, 1);
+	if (req->result)
+		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
+			       digestsize, 1);
+#endif
+
+	req->base.complete(&req->base, err);
+}
+
+static void ahash_done_ctx_dst(struct device *jrdev, u32 *desc, u32 err,
+			       void *context)
+{
+	struct ahash_request *req = context;
+	struct ahash_edesc *edesc;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+#ifdef DEBUG
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	int digestsize = crypto_ahash_digestsize(ahash);
+
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = (struct ahash_edesc *)((char *)desc -
+		 offsetof(struct ahash_edesc, hw_desc));
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(jrdev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len, DMA_TO_DEVICE);
+	kfree(edesc);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
+		       ctx->ctx_len, 1);
+	if (req->result)
+		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
+			       digestsize, 1);
+#endif
+
+	req->base.complete(&req->base, err);
+}
+
+/* submit update job descriptor */
+static int ahash_update_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int *buflen = state->current_buf ? &state->buflen_1 : &state->buflen_0;
+	u8 *next_buf = state->current_buf ? state->buf_0 : state->buf_1;
+	int *next_buflen = state->current_buf ? &state->buflen_0 :
+			   &state->buflen_1, last_buflen;
+	int in_len = *buflen + req->nbytes, to_hash;
+	u32 *sh_desc = ctx->sh_desc_update, *desc;
+	dma_addr_t ptr = ctx->sh_desc_update_dma;
+	int src_nents, sec4_sg_bytes, sec4_sg_src_index;
+	struct ahash_edesc *edesc;
+	bool chained = false;
+	int ret = 0;
+	int sh_len;
+
+	last_buflen = *next_buflen;
+	*next_buflen = in_len & (crypto_tfm_alg_blocksize(&ahash->base) - 1);
+	to_hash = in_len - *next_buflen;
+
+	if (to_hash) {
+		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen),
+				       &chained);
+		sec4_sg_src_index = 1 + (*buflen ? 1 : 0);
+		sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
+				 sizeof(struct sec4_sg_entry);
+
+		/*
+		 * allocate space for base edesc and hw desc commands,
+		 * link tables
+		 */
+		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+				sec4_sg_bytes, GFP_DMA | flags);
+		if (!edesc) {
+			dev_err(jrdev,
+				"could not allocate extended descriptor\n");
+			return -ENOMEM;
+		}
+
+		edesc->src_nents = src_nents;
+		edesc->chained = chained;
+		edesc->sec4_sg_bytes = sec4_sg_bytes;
+		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+				 DESC_JOB_IO_LEN;
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+						     sec4_sg_bytes,
+						     DMA_TO_DEVICE);
+
+		ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len,
+				   edesc->sec4_sg, DMA_BIDIRECTIONAL);
+
+		state->buf_dma = try_buf_map_to_sec4_sg(jrdev,
+							edesc->sec4_sg + 1,
+							buf, state->buf_dma,
+							*buflen, last_buflen);
+
+		if (src_nents) {
+			src_map_to_sec4_sg(jrdev, req->src, src_nents,
+					   edesc->sec4_sg + sec4_sg_src_index,
+					   chained);
+			if (*next_buflen) {
+				sg_copy_part(next_buf, req->src, to_hash -
+					     *buflen, req->nbytes);
+				state->current_buf = !state->current_buf;
+			}
+		} else {
+			(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
+							SEC4_SG_LEN_FIN;
+		}
+
+		sh_len = desc_len(sh_desc);
+		desc = edesc->hw_desc;
+		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
+				     HDR_REVERSE);
+
+		append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len +
+				       to_hash, LDST_SGF);
+
+		append_seq_out_ptr(desc, state->ctx_dma, ctx->ctx_len, 0);
+
+#ifdef DEBUG
+		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+			       desc_bytes(desc), 1);
+#endif
+
+		ret = caam_jr_enqueue(jrdev, desc, ahash_done_bi, req);
+		if (!ret) {
+			ret = -EINPROGRESS;
+		} else {
+			ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len,
+					   DMA_BIDIRECTIONAL);
+			kfree(edesc);
+		}
+	} else if (*next_buflen) {
+		sg_copy(buf + *buflen, req->src, req->nbytes);
+		*buflen = *next_buflen;
+		*next_buflen = last_buflen;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "buf@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, buf, *buflen, 1);
+	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
+		       *next_buflen, 1);
+#endif
+
+	return ret;
+}
+
+static int ahash_final_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int buflen = state->current_buf ? state->buflen_1 : state->buflen_0;
+	int last_buflen = state->current_buf ? state->buflen_0 :
+			  state->buflen_1;
+	u32 *sh_desc = ctx->sh_desc_fin, *desc;
+	dma_addr_t ptr = ctx->sh_desc_fin_dma;
+	int sec4_sg_bytes;
+	int digestsize = crypto_ahash_digestsize(ahash);
+	struct ahash_edesc *edesc;
+	int ret = 0;
+	int sh_len;
+
+	sec4_sg_bytes = (1 + (buflen ? 1 : 0)) * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+			sec4_sg_bytes, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return -ENOMEM;
+	}
+
+	sh_len = desc_len(sh_desc);
+	desc = edesc->hw_desc;
+	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+			 DESC_JOB_IO_LEN;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	edesc->src_nents = 0;
+
+	ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len, edesc->sec4_sg,
+			   DMA_TO_DEVICE);
+
+	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
+						buf, state->buf_dma, buflen,
+						last_buflen);
+	(edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN;
+
+	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len + buflen,
+			  LDST_SGF);
+
+	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
+						digestsize);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	ret = caam_jr_enqueue(jrdev, desc, ahash_done_ctx_src, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ahash_unmap_ctx(jrdev, edesc, req, digestsize, DMA_FROM_DEVICE);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int ahash_finup_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int buflen = state->current_buf ? state->buflen_1 : state->buflen_0;
+	int last_buflen = state->current_buf ? state->buflen_0 :
+			  state->buflen_1;
+	u32 *sh_desc = ctx->sh_desc_finup, *desc;
+	dma_addr_t ptr = ctx->sh_desc_finup_dma;
+	int sec4_sg_bytes, sec4_sg_src_index;
+	int src_nents;
+	int digestsize = crypto_ahash_digestsize(ahash);
+	struct ahash_edesc *edesc;
+	bool chained = false;
+	int ret = 0;
+	int sh_len;
+
+	src_nents = __sg_count(req->src, req->nbytes, &chained);
+	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
+	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
+			 sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+			sec4_sg_bytes, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return -ENOMEM;
+	}
+
+	sh_len = desc_len(sh_desc);
+	desc = edesc->hw_desc;
+	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	edesc->src_nents = src_nents;
+	edesc->chained = chained;
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+			 DESC_JOB_IO_LEN;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+
+	ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len, edesc->sec4_sg,
+			   DMA_TO_DEVICE);
+
+	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
+						buf, state->buf_dma, buflen,
+						last_buflen);
+
+	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg +
+			   sec4_sg_src_index, chained);
+
+	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len +
+			       buflen + req->nbytes, LDST_SGF);
+
+	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
+						digestsize);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	ret = caam_jr_enqueue(jrdev, desc, ahash_done_ctx_src, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ahash_unmap_ctx(jrdev, edesc, req, digestsize, DMA_FROM_DEVICE);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int ahash_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u32 *sh_desc = ctx->sh_desc_digest, *desc;
+	dma_addr_t ptr = ctx->sh_desc_digest_dma;
+	int digestsize = crypto_ahash_digestsize(ahash);
+	int src_nents, sec4_sg_bytes;
+	dma_addr_t src_dma;
+	struct ahash_edesc *edesc;
+	bool chained = false;
+	int ret = 0;
+	u32 options;
+	int sh_len;
+
+	src_nents = sg_count(req->src, req->nbytes, &chained);
+	dma_map_sg_chained(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE,
+			   chained);
+	sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kmalloc(sizeof(struct ahash_edesc) + sec4_sg_bytes +
+			DESC_JOB_IO_LEN, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return -ENOMEM;
+	}
+	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+			  DESC_JOB_IO_LEN;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	edesc->src_nents = src_nents;
+	edesc->chained = chained;
+
+	sh_len = desc_len(sh_desc);
+	desc = edesc->hw_desc;
+	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	if (src_nents) {
+		sg_to_sec4_sg_last(req->src, src_nents, edesc->sec4_sg, 0);
+		src_dma = edesc->sec4_sg_dma;
+		options = LDST_SGF;
+	} else {
+		src_dma = sg_dma_address(req->src);
+		options = 0;
+	}
+	append_seq_in_ptr(desc, src_dma, req->nbytes, options);
+
+	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
+						digestsize);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	ret = caam_jr_enqueue(jrdev, desc, ahash_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ahash_unmap(jrdev, edesc, req, digestsize);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+/* submit ahash final if it the first job descriptor */
+static int ahash_final_no_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int buflen = state->current_buf ? state->buflen_1 : state->buflen_0;
+	u32 *sh_desc = ctx->sh_desc_digest, *desc;
+	dma_addr_t ptr = ctx->sh_desc_digest_dma;
+	int digestsize = crypto_ahash_digestsize(ahash);
+	struct ahash_edesc *edesc;
+	int ret = 0;
+	int sh_len;
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN,
+			GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return -ENOMEM;
+	}
+
+	sh_len = desc_len(sh_desc);
+	desc = edesc->hw_desc;
+	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	state->buf_dma = dma_map_single(jrdev, buf, buflen, DMA_TO_DEVICE);
+
+	append_seq_in_ptr(desc, state->buf_dma, buflen, 0);
+
+	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
+						digestsize);
+	edesc->src_nents = 0;
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	ret = caam_jr_enqueue(jrdev, desc, ahash_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ahash_unmap(jrdev, edesc, req, digestsize);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+/* submit ahash update if it the first job descriptor after update */
+static int ahash_update_no_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int *buflen = state->current_buf ? &state->buflen_1 : &state->buflen_0;
+	u8 *next_buf = state->current_buf ? state->buf_0 : state->buf_1;
+	int *next_buflen = state->current_buf ? &state->buflen_0 :
+			   &state->buflen_1;
+	int in_len = *buflen + req->nbytes, to_hash;
+	int sec4_sg_bytes, src_nents;
+	struct ahash_edesc *edesc;
+	u32 *desc, *sh_desc = ctx->sh_desc_update_first;
+	dma_addr_t ptr = ctx->sh_desc_update_first_dma;
+	bool chained = false;
+	int ret = 0;
+	int sh_len;
+
+	*next_buflen = in_len & (crypto_tfm_alg_blocksize(&ahash->base) - 1);
+	to_hash = in_len - *next_buflen;
+
+	if (to_hash) {
+		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen),
+				       &chained);
+		sec4_sg_bytes = (1 + src_nents) *
+				sizeof(struct sec4_sg_entry);
+
+		/*
+		 * allocate space for base edesc and hw desc commands,
+		 * link tables
+		 */
+		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+				sec4_sg_bytes, GFP_DMA | flags);
+		if (!edesc) {
+			dev_err(jrdev,
+				"could not allocate extended descriptor\n");
+			return -ENOMEM;
+		}
+
+		edesc->src_nents = src_nents;
+		edesc->chained = chained;
+		edesc->sec4_sg_bytes = sec4_sg_bytes;
+		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+				 DESC_JOB_IO_LEN;
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+						    sec4_sg_bytes,
+						    DMA_TO_DEVICE);
+
+		state->buf_dma = buf_map_to_sec4_sg(jrdev, edesc->sec4_sg,
+						    buf, *buflen);
+		src_map_to_sec4_sg(jrdev, req->src, src_nents,
+				   edesc->sec4_sg + 1, chained);
+		if (*next_buflen) {
+			sg_copy_part(next_buf, req->src, to_hash - *buflen,
+				    req->nbytes);
+			state->current_buf = !state->current_buf;
+		}
+
+		sh_len = desc_len(sh_desc);
+		desc = edesc->hw_desc;
+		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
+				     HDR_REVERSE);
+
+		append_seq_in_ptr(desc, edesc->sec4_sg_dma, to_hash, LDST_SGF);
+
+		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+
+#ifdef DEBUG
+		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+			       desc_bytes(desc), 1);
+#endif
+
+		ret = caam_jr_enqueue(jrdev, desc, ahash_done_ctx_dst, req);
+		if (!ret) {
+			ret = -EINPROGRESS;
+			state->update = ahash_update_ctx;
+			state->finup = ahash_finup_ctx;
+			state->final = ahash_final_ctx;
+		} else {
+			ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len,
+					DMA_TO_DEVICE);
+			kfree(edesc);
+		}
+	} else if (*next_buflen) {
+		sg_copy(buf + *buflen, req->src, req->nbytes);
+		*buflen = *next_buflen;
+		*next_buflen = 0;
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "buf@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, buf, *buflen, 1);
+	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
+		       *next_buflen, 1);
+#endif
+
+	return ret;
+}
+
+/* submit ahash finup if it the first job descriptor after update */
+static int ahash_finup_no_ctx(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int buflen = state->current_buf ? state->buflen_1 : state->buflen_0;
+	int last_buflen = state->current_buf ? state->buflen_0 :
+			  state->buflen_1;
+	u32 *sh_desc = ctx->sh_desc_digest, *desc;
+	dma_addr_t ptr = ctx->sh_desc_digest_dma;
+	int sec4_sg_bytes, sec4_sg_src_index, src_nents;
+	int digestsize = crypto_ahash_digestsize(ahash);
+	struct ahash_edesc *edesc;
+	bool chained = false;
+	int sh_len;
+	int ret = 0;
+
+	src_nents = __sg_count(req->src, req->nbytes, &chained);
+	sec4_sg_src_index = 2;
+	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
+			 sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+			sec4_sg_bytes, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return -ENOMEM;
+	}
+
+	sh_len = desc_len(sh_desc);
+	desc = edesc->hw_desc;
+	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	edesc->src_nents = src_nents;
+	edesc->chained = chained;
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+			 DESC_JOB_IO_LEN;
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+
+	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg, buf,
+						state->buf_dma, buflen,
+						last_buflen);
+
+	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1,
+			   chained);
+
+	append_seq_in_ptr(desc, edesc->sec4_sg_dma, buflen +
+			       req->nbytes, LDST_SGF);
+
+	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
+						digestsize);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	ret = caam_jr_enqueue(jrdev, desc, ahash_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		ahash_unmap(jrdev, edesc, req, digestsize);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+/* submit first update job descriptor after init */
+static int ahash_update_first(struct ahash_request *req)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	u8 *next_buf = state->buf_0 + state->current_buf *
+		       CAAM_MAX_HASH_BLOCK_SIZE;
+	int *next_buflen = &state->buflen_0 + state->current_buf;
+	int to_hash;
+	u32 *sh_desc = ctx->sh_desc_update_first, *desc;
+	dma_addr_t ptr = ctx->sh_desc_update_first_dma;
+	int sec4_sg_bytes, src_nents;
+	dma_addr_t src_dma;
+	u32 options;
+	struct ahash_edesc *edesc;
+	bool chained = false;
+	int ret = 0;
+	int sh_len;
+
+	*next_buflen = req->nbytes & (crypto_tfm_alg_blocksize(&ahash->base) -
+				      1);
+	to_hash = req->nbytes - *next_buflen;
+
+	if (to_hash) {
+		src_nents = sg_count(req->src, req->nbytes - (*next_buflen),
+				     &chained);
+		dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+				   DMA_TO_DEVICE, chained);
+		sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
+
+		/*
+		 * allocate space for base edesc and hw desc commands,
+		 * link tables
+		 */
+		edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
+				sec4_sg_bytes, GFP_DMA | flags);
+		if (!edesc) {
+			dev_err(jrdev,
+				"could not allocate extended descriptor\n");
+			return -ENOMEM;
+		}
+
+		edesc->src_nents = src_nents;
+		edesc->chained = chained;
+		edesc->sec4_sg_bytes = sec4_sg_bytes;
+		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
+				 DESC_JOB_IO_LEN;
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+						    sec4_sg_bytes,
+						    DMA_TO_DEVICE);
+
+		if (src_nents) {
+			sg_to_sec4_sg_last(req->src, src_nents,
+					   edesc->sec4_sg, 0);
+			src_dma = edesc->sec4_sg_dma;
+			options = LDST_SGF;
+		} else {
+			src_dma = sg_dma_address(req->src);
+			options = 0;
+		}
+
+		if (*next_buflen)
+			sg_copy_part(next_buf, req->src, to_hash, req->nbytes);
+
+		sh_len = desc_len(sh_desc);
+		desc = edesc->hw_desc;
+		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
+				     HDR_REVERSE);
+
+		append_seq_in_ptr(desc, src_dma, to_hash, options);
+
+		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+
+#ifdef DEBUG
+		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
+			       desc_bytes(desc), 1);
+#endif
+
+		ret = caam_jr_enqueue(jrdev, desc, ahash_done_ctx_dst,
+				      req);
+		if (!ret) {
+			ret = -EINPROGRESS;
+			state->update = ahash_update_ctx;
+			state->finup = ahash_finup_ctx;
+			state->final = ahash_final_ctx;
+		} else {
+			ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len,
+					DMA_TO_DEVICE);
+			kfree(edesc);
+		}
+	} else if (*next_buflen) {
+		state->update = ahash_update_no_ctx;
+		state->finup = ahash_finup_no_ctx;
+		state->final = ahash_final_no_ctx;
+		sg_copy(next_buf, req->src, req->nbytes);
+	}
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
+		       *next_buflen, 1);
+#endif
+
+	return ret;
+}
+
+static int ahash_finup_first(struct ahash_request *req)
+{
+	return ahash_digest(req);
+}
+
+static int ahash_init(struct ahash_request *req)
+{
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	state->update = ahash_update_first;
+	state->finup = ahash_finup_first;
+	state->final = ahash_final_no_ctx;
+
+	state->current_buf = 0;
+
+	return 0;
+}
+
+static int ahash_update(struct ahash_request *req)
+{
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	return state->update(req);
+}
+
+static int ahash_finup(struct ahash_request *req)
+{
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	return state->finup(req);
+}
+
+static int ahash_final(struct ahash_request *req)
+{
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	return state->final(req);
+}
+
+static int ahash_export(struct ahash_request *req, void *out)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	memcpy(out, ctx, sizeof(struct caam_hash_ctx));
+	memcpy(out + sizeof(struct caam_hash_ctx), state,
+	       sizeof(struct caam_hash_state));
+	return 0;
+}
+
+static int ahash_import(struct ahash_request *req, const void *in)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct caam_hash_state *state = ahash_request_ctx(req);
+
+	memcpy(ctx, in, sizeof(struct caam_hash_ctx));
+	memcpy(state, in + sizeof(struct caam_hash_ctx),
+	       sizeof(struct caam_hash_state));
+	return 0;
+}
+
+struct caam_hash_template {
+	char name[CRYPTO_MAX_ALG_NAME];
+	char driver_name[CRYPTO_MAX_ALG_NAME];
+	char hmac_name[CRYPTO_MAX_ALG_NAME];
+	char hmac_driver_name[CRYPTO_MAX_ALG_NAME];
+	unsigned int blocksize;
+	struct ahash_alg template_ahash;
+	u32 alg_type;
+	u32 alg_op;
+};
+
+/* ahash descriptors */
+static struct caam_hash_template driver_hash[] = {
+	{
+		.name = "sha1",
+		.driver_name = "sha1-caam",
+		.hmac_name = "hmac(sha1)",
+		.hmac_driver_name = "hmac-sha1-caam",
+		.blocksize = SHA1_BLOCK_SIZE,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = SHA1_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_SHA1,
+		.alg_op = OP_ALG_ALGSEL_SHA1 | OP_ALG_AAI_HMAC,
+	}, {
+		.name = "sha224",
+		.driver_name = "sha224-caam",
+		.hmac_name = "hmac(sha224)",
+		.hmac_driver_name = "hmac-sha224-caam",
+		.blocksize = SHA224_BLOCK_SIZE,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = SHA224_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_SHA224,
+		.alg_op = OP_ALG_ALGSEL_SHA224 | OP_ALG_AAI_HMAC,
+	}, {
+		.name = "sha256",
+		.driver_name = "sha256-caam",
+		.hmac_name = "hmac(sha256)",
+		.hmac_driver_name = "hmac-sha256-caam",
+		.blocksize = SHA256_BLOCK_SIZE,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = SHA256_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_SHA256,
+		.alg_op = OP_ALG_ALGSEL_SHA256 | OP_ALG_AAI_HMAC,
+	}, {
+		.name = "sha384",
+		.driver_name = "sha384-caam",
+		.hmac_name = "hmac(sha384)",
+		.hmac_driver_name = "hmac-sha384-caam",
+		.blocksize = SHA384_BLOCK_SIZE,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = SHA384_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_SHA384,
+		.alg_op = OP_ALG_ALGSEL_SHA384 | OP_ALG_AAI_HMAC,
+	}, {
+		.name = "sha512",
+		.driver_name = "sha512-caam",
+		.hmac_name = "hmac(sha512)",
+		.hmac_driver_name = "hmac-sha512-caam",
+		.blocksize = SHA512_BLOCK_SIZE,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = SHA512_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_SHA512,
+		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
+	}, {
+		.name = "md5",
+		.driver_name = "md5-caam",
+		.hmac_name = "hmac(md5)",
+		.hmac_driver_name = "hmac-md5-caam",
+		.blocksize = MD5_BLOCK_WORDS * 4,
+		.template_ahash = {
+			.init = ahash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.finup = ahash_finup,
+			.digest = ahash_digest,
+			.export = ahash_export,
+			.import = ahash_import,
+			.setkey = ahash_setkey,
+			.halg = {
+				.digestsize = MD5_DIGEST_SIZE,
+				},
+			},
+		.alg_type = OP_ALG_ALGSEL_MD5,
+		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+	},
+};
+
+struct caam_hash_alg {
+	struct list_head entry;
+	struct device *ctrldev;
+	int alg_type;
+	int alg_op;
+	struct ahash_alg ahash_alg;
+};
+
+static int caam_hash_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *ahash = __crypto_ahash_cast(tfm);
+	struct crypto_alg *base = tfm->__crt_alg;
+	struct hash_alg_common *halg =
+		 container_of(base, struct hash_alg_common, base);
+	struct ahash_alg *alg =
+		 container_of(halg, struct ahash_alg, halg);
+	struct caam_hash_alg *caam_hash =
+		 container_of(alg, struct caam_hash_alg, ahash_alg);
+	struct caam_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct caam_drv_private *priv = dev_get_drvdata(caam_hash->ctrldev);
+	/* Sizes for MDHA running digests: MD5, SHA1, 224, 256, 384, 512 */
+	static const u8 runninglen[] = { HASH_MSG_LEN + MD5_DIGEST_SIZE,
+					 HASH_MSG_LEN + SHA1_DIGEST_SIZE,
+					 HASH_MSG_LEN + 32,
+					 HASH_MSG_LEN + SHA256_DIGEST_SIZE,
+					 HASH_MSG_LEN + 64,
+					 HASH_MSG_LEN + SHA512_DIGEST_SIZE };
+	int tgt_jr = atomic_inc_return(&priv->tfm_count);
+	int ret = 0;
+
+	/*
+	 * distribute tfms across job rings to ensure in-order
+	 * crypto request processing per tfm
+	 */
+	ctx->jrdev = priv->jrdev[tgt_jr % priv->total_jobrs];
+
+	/* copy descriptor header template value */
+	ctx->alg_type = OP_TYPE_CLASS2_ALG | caam_hash->alg_type;
+	ctx->alg_op = OP_TYPE_CLASS2_ALG | caam_hash->alg_op;
+
+	ctx->ctx_len = runninglen[(ctx->alg_op & OP_ALG_ALGSEL_SUBMASK) >>
+				  OP_ALG_ALGSEL_SHIFT];
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct caam_hash_state));
+
+	ret = ahash_set_sh_desc(ahash);
+
+	return ret;
+}
+
+static void caam_hash_cra_exit(struct crypto_tfm *tfm)
+{
+	struct caam_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (ctx->sh_desc_update_dma &&
+	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_update_dma))
+		dma_unmap_single(ctx->jrdev, ctx->sh_desc_update_dma,
+				 desc_bytes(ctx->sh_desc_update),
+				 DMA_TO_DEVICE);
+	if (ctx->sh_desc_update_first_dma &&
+	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_update_first_dma))
+		dma_unmap_single(ctx->jrdev, ctx->sh_desc_update_first_dma,
+				 desc_bytes(ctx->sh_desc_update_first),
+				 DMA_TO_DEVICE);
+	if (ctx->sh_desc_fin_dma &&
+	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_fin_dma))
+		dma_unmap_single(ctx->jrdev, ctx->sh_desc_fin_dma,
+				 desc_bytes(ctx->sh_desc_fin), DMA_TO_DEVICE);
+	if (ctx->sh_desc_digest_dma &&
+	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_digest_dma))
+		dma_unmap_single(ctx->jrdev, ctx->sh_desc_digest_dma,
+				 desc_bytes(ctx->sh_desc_digest),
+				 DMA_TO_DEVICE);
+	if (ctx->sh_desc_finup_dma &&
+	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_finup_dma))
+		dma_unmap_single(ctx->jrdev, ctx->sh_desc_finup_dma,
+				 desc_bytes(ctx->sh_desc_finup), DMA_TO_DEVICE);
+}
+
+static void __exit caam_algapi_hash_exit(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+	struct caam_hash_alg *t_alg, *n;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node)
+		return;
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev)
+		return;
+
+	ctrldev = &pdev->dev;
+	of_node_put(dev_node);
+	priv = dev_get_drvdata(ctrldev);
+
+	if (!priv->hash_list.next)
+		return;
+
+	list_for_each_entry_safe(t_alg, n, &priv->hash_list, entry) {
+		crypto_unregister_ahash(&t_alg->ahash_alg);
+		list_del(&t_alg->entry);
+		kfree(t_alg);
+	}
+}
+
+static struct caam_hash_alg *
+caam_hash_alloc(struct device *ctrldev, struct caam_hash_template *template,
+		bool keyed)
+{
+	struct caam_hash_alg *t_alg;
+	struct ahash_alg *halg;
+	struct crypto_alg *alg;
+
+	t_alg = kzalloc(sizeof(struct caam_hash_alg), GFP_KERNEL);
+	if (!t_alg) {
+		dev_err(ctrldev, "failed to allocate t_alg\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	t_alg->ahash_alg = template->template_ahash;
+	halg = &t_alg->ahash_alg;
+	alg = &halg->halg.base;
+
+	if (keyed) {
+		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->hmac_name);
+		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->hmac_driver_name);
+	} else {
+		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->name);
+		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->driver_name);
+	}
+	alg->cra_module = THIS_MODULE;
+	alg->cra_init = caam_hash_cra_init;
+	alg->cra_exit = caam_hash_cra_exit;
+	alg->cra_ctxsize = sizeof(struct caam_hash_ctx);
+	alg->cra_priority = CAAM_CRA_PRIORITY;
+	alg->cra_blocksize = template->blocksize;
+	alg->cra_alignmask = 0;
+	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH;
+	alg->cra_type = &crypto_ahash_type;
+
+	t_alg->alg_type = template->alg_type;
+	t_alg->alg_op = template->alg_op;
+	t_alg->ctrldev = ctrldev;
+
+	return t_alg;
+}
+
+static int __init caam_algapi_hash_init(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+	int i = 0, err = 0;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node)
+		return -ENODEV;
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev)
+		return -ENODEV;
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	INIT_LIST_HEAD(&priv->hash_list);
+
+	atomic_set(&priv->tfm_count, -1);
+
+	/* register crypto algorithms the device supports */
+	for (i = 0; i < ARRAY_SIZE(driver_hash); i++) {
+		/* TODO: check if h/w supports alg */
+		struct caam_hash_alg *t_alg;
+
+		/* register hmac version */
+		t_alg = caam_hash_alloc(ctrldev, &driver_hash[i], true);
+		if (IS_ERR(t_alg)) {
+			err = PTR_ERR(t_alg);
+			dev_warn(ctrldev, "%s alg allocation failed\n",
+				 driver_hash[i].driver_name);
+			continue;
+		}
+
+		err = crypto_register_ahash(&t_alg->ahash_alg);
+		if (err) {
+			dev_warn(ctrldev, "%s alg registration failed\n",
+				t_alg->ahash_alg.halg.base.cra_driver_name);
+			kfree(t_alg);
+		} else
+			list_add_tail(&t_alg->entry, &priv->hash_list);
+
+		/* register unkeyed version */
+		t_alg = caam_hash_alloc(ctrldev, &driver_hash[i], false);
+		if (IS_ERR(t_alg)) {
+			err = PTR_ERR(t_alg);
+			dev_warn(ctrldev, "%s alg allocation failed\n",
+				 driver_hash[i].driver_name);
+			continue;
+		}
+
+		err = crypto_register_ahash(&t_alg->ahash_alg);
+		if (err) {
+			dev_warn(ctrldev, "%s alg registration failed\n",
+				t_alg->ahash_alg.halg.base.cra_driver_name);
+			kfree(t_alg);
+		} else
+			list_add_tail(&t_alg->entry, &priv->hash_list);
+	}
+
+	return err;
+}
+
+module_init(caam_algapi_hash_init);
+module_exit(caam_algapi_hash_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("FSL CAAM support for ahash functions of crypto API");
+MODULE_AUTHOR("Freescale Semiconductor - NMG");
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
new file mode 100644
index 0000000..e2bfe16
--- /dev/null
+++ b/drivers/crypto/caam/caamrng.c
@@ -0,0 +1,309 @@
+/*
+ * caam - Freescale FSL CAAM support for hw_random
+ *
+ * Copyright 2011 Freescale Semiconductor, Inc.
+ *
+ * Based on caamalg.c crypto API driver.
+ *
+ * relationship between job descriptors to shared descriptors:
+ *
+ * ---------------                     --------------
+ * | JobDesc #0  |-------------------->| ShareDesc  |
+ * | *(buffer 0) |      |------------->| (generate) |
+ * ---------------      |              | (move)     |
+ *                      |              | (store)    |
+ * ---------------      |              --------------
+ * | JobDesc #1  |------|
+ * | *(buffer 1) |
+ * ---------------
+ *
+ * A job desc looks like this:
+ *
+ * ---------------------
+ * | Header            |
+ * | ShareDesc Pointer |
+ * | SEQ_OUT_PTR       |
+ * | (output buffer)   |
+ * ---------------------
+ *
+ * The SharedDesc never changes, and each job descriptor points to one of two
+ * buffers for each device, from which the data will be copied into the
+ * requested destination
+ */
+
+#include <linux/hw_random.h>
+#include <linux/completion.h>
+#include <linux/atomic.h>
+
+#include "compat.h"
+
+#include "regs.h"
+#include "intern.h"
+#include "desc_constr.h"
+#include "jr.h"
+#include "error.h"
+
+/*
+ * Maximum buffer size: maximum number of random, cache-aligned bytes that
+ * will be generated and moved to seq out ptr (extlen not allowed)
+ */
+#define RN_BUF_SIZE			(0xffff / L1_CACHE_BYTES * \
+					 L1_CACHE_BYTES)
+
+/* length of descriptors */
+#define DESC_JOB_O_LEN			(CAAM_CMD_SZ * 2 + CAAM_PTR_SZ * 2)
+#define DESC_RNG_LEN			(10 * CAAM_CMD_SZ)
+
+/* Buffer, its dma address and lock */
+struct buf_data {
+	u8 buf[RN_BUF_SIZE];
+	dma_addr_t addr;
+	struct completion filled;
+	u32 hw_desc[DESC_JOB_O_LEN];
+#define BUF_NOT_EMPTY 0
+#define BUF_EMPTY 1
+#define BUF_PENDING 2  /* Empty, but with job pending --don't submit another */
+	atomic_t empty;
+};
+
+/* rng per-device context */
+struct caam_rng_ctx {
+	struct device *jrdev;
+	dma_addr_t sh_desc_dma;
+	u32 sh_desc[DESC_RNG_LEN];
+	unsigned int cur_buf_idx;
+	int current_buf;
+	struct buf_data bufs[2];
+};
+
+static struct caam_rng_ctx rng_ctx;
+
+static inline void rng_unmap_buf(struct device *jrdev, struct buf_data *bd)
+{
+	if (bd->addr)
+		dma_unmap_single(jrdev, bd->addr, RN_BUF_SIZE,
+				 DMA_FROM_DEVICE);
+}
+
+static inline void rng_unmap_ctx(struct caam_rng_ctx *ctx)
+{
+	struct device *jrdev = ctx->jrdev;
+
+	if (ctx->sh_desc_dma)
+		dma_unmap_single(jrdev, ctx->sh_desc_dma, DESC_RNG_LEN,
+				 DMA_TO_DEVICE);
+	rng_unmap_buf(jrdev, &ctx->bufs[0]);
+	rng_unmap_buf(jrdev, &ctx->bufs[1]);
+}
+
+static void rng_done(struct device *jrdev, u32 *desc, u32 err, void *context)
+{
+	struct buf_data *bd;
+
+	bd = (struct buf_data *)((char *)desc -
+	      offsetof(struct buf_data, hw_desc));
+
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(jrdev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	atomic_set(&bd->empty, BUF_NOT_EMPTY);
+	complete(&bd->filled);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "rng refreshed buf@: ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, bd->buf, RN_BUF_SIZE, 1);
+#endif
+}
+
+static inline int submit_job(struct caam_rng_ctx *ctx, int to_current)
+{
+	struct buf_data *bd = &ctx->bufs[!(to_current ^ ctx->current_buf)];
+	struct device *jrdev = ctx->jrdev;
+	u32 *desc = bd->hw_desc;
+	int err;
+
+	dev_dbg(jrdev, "submitting job %d\n", !(to_current ^ ctx->current_buf));
+	init_completion(&bd->filled);
+	err = caam_jr_enqueue(jrdev, desc, rng_done, ctx);
+	if (err)
+		complete(&bd->filled); /* don't wait on failed job*/
+	else
+		atomic_inc(&bd->empty); /* note if pending */
+
+	return err;
+}
+
+static int caam_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct caam_rng_ctx *ctx = &rng_ctx;
+	struct buf_data *bd = &ctx->bufs[ctx->current_buf];
+	int next_buf_idx, copied_idx;
+	int err;
+
+	if (atomic_read(&bd->empty)) {
+		/* try to submit job if there wasn't one */
+		if (atomic_read(&bd->empty) == BUF_EMPTY) {
+			err = submit_job(ctx, 1);
+			/* if can't submit job, can't even wait */
+			if (err)
+				return 0;
+		}
+		/* no immediate data, so exit if not waiting */
+		if (!wait)
+			return 0;
+
+		/* waiting for pending job */
+		if (atomic_read(&bd->empty))
+			wait_for_completion(&bd->filled);
+	}
+
+	next_buf_idx = ctx->cur_buf_idx + max;
+	dev_dbg(ctx->jrdev, "%s: start reading at buffer %d, idx %d\n",
+		 __func__, ctx->current_buf, ctx->cur_buf_idx);
+
+	/* if enough data in current buffer */
+	if (next_buf_idx < RN_BUF_SIZE) {
+		memcpy(data, bd->buf + ctx->cur_buf_idx, max);
+		ctx->cur_buf_idx = next_buf_idx;
+		return max;
+	}
+
+	/* else, copy what's left... */
+	copied_idx = RN_BUF_SIZE - ctx->cur_buf_idx;
+	memcpy(data, bd->buf + ctx->cur_buf_idx, copied_idx);
+	ctx->cur_buf_idx = 0;
+	atomic_set(&bd->empty, BUF_EMPTY);
+
+	/* ...refill... */
+	submit_job(ctx, 1);
+
+	/* and use next buffer */
+	ctx->current_buf = !ctx->current_buf;
+	dev_dbg(ctx->jrdev, "switched to buffer %d\n", ctx->current_buf);
+
+	/* since there already is some data read, don't wait */
+	return copied_idx + caam_read(rng, data + copied_idx,
+				      max - copied_idx, false);
+}
+
+static inline void rng_create_sh_desc(struct caam_rng_ctx *ctx)
+{
+	struct device *jrdev = ctx->jrdev;
+	u32 *desc = ctx->sh_desc;
+
+	init_sh_desc(desc, HDR_SHARE_WAIT);
+
+	/* Propagate errors from shared to job descriptor */
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
+
+	/* Generate random bytes */
+	append_operation(desc, OP_ALG_ALGSEL_RNG | OP_TYPE_CLASS1_ALG);
+
+	/* Store bytes */
+	append_seq_fifo_store(desc, RN_BUF_SIZE, FIFOST_TYPE_RNGSTORE);
+
+	ctx->sh_desc_dma = dma_map_single(jrdev, desc, desc_bytes(desc),
+					  DMA_TO_DEVICE);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "rng shdesc@: ", DUMP_PREFIX_ADDRESS, 16, 4,
+		       desc, desc_bytes(desc), 1);
+#endif
+}
+
+static inline void rng_create_job_desc(struct caam_rng_ctx *ctx, int buf_id)
+{
+	struct device *jrdev = ctx->jrdev;
+	struct buf_data *bd = &ctx->bufs[buf_id];
+	u32 *desc = bd->hw_desc;
+	int sh_len = desc_len(ctx->sh_desc);
+
+	init_job_desc_shared(desc, ctx->sh_desc_dma, sh_len, HDR_SHARE_DEFER |
+			     HDR_REVERSE);
+
+	bd->addr = dma_map_single(jrdev, bd->buf, RN_BUF_SIZE, DMA_FROM_DEVICE);
+
+	append_seq_out_ptr_intlen(desc, bd->addr, RN_BUF_SIZE, 0);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "rng job desc@: ", DUMP_PREFIX_ADDRESS, 16, 4,
+		       desc, desc_bytes(desc), 1);
+#endif
+}
+
+static void caam_cleanup(struct hwrng *rng)
+{
+	int i;
+	struct buf_data *bd;
+
+	for (i = 0; i < 2; i++) {
+		bd = &rng_ctx.bufs[i];
+		if (atomic_read(&bd->empty) == BUF_PENDING)
+			wait_for_completion(&bd->filled);
+	}
+
+	rng_unmap_ctx(&rng_ctx);
+}
+
+static void caam_init_buf(struct caam_rng_ctx *ctx, int buf_id)
+{
+	struct buf_data *bd = &ctx->bufs[buf_id];
+
+	rng_create_job_desc(ctx, buf_id);
+	atomic_set(&bd->empty, BUF_EMPTY);
+	submit_job(ctx, buf_id == ctx->current_buf);
+	wait_for_completion(&bd->filled);
+}
+
+static void caam_init_rng(struct caam_rng_ctx *ctx, struct device *jrdev)
+{
+	ctx->jrdev = jrdev;
+	rng_create_sh_desc(ctx);
+	ctx->current_buf = 0;
+	ctx->cur_buf_idx = 0;
+	caam_init_buf(ctx, 0);
+	caam_init_buf(ctx, 1);
+}
+
+static struct hwrng caam_rng = {
+	.name		= "rng-caam",
+	.cleanup	= caam_cleanup,
+	.read		= caam_read,
+};
+
+static void __exit caam_rng_exit(void)
+{
+	hwrng_unregister(&caam_rng);
+}
+
+static int __init caam_rng_init(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node)
+		return -ENODEV;
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev)
+		return -ENODEV;
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	caam_init_rng(&rng_ctx, priv->jrdev[0]);
+
+	dev_info(priv->jrdev[0], "registering rng-caam\n");
+	return hwrng_register(&caam_rng);
+}
+
+module_init(caam_rng_init);
+module_exit(caam_rng_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("FSL CAAM support for hw_random API");
+MODULE_AUTHOR("Freescale Semiconductor - NMG");
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index a63bc65..762aeff 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -11,6 +11,7 @@
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/crypto.h>
+#include <linux/hash.h>
 #include <linux/hw_random.h>
 #include <linux/of_platform.h>
 #include <linux/dma-mapping.h>
@@ -33,5 +34,6 @@
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/internal/hash.h>
 
 #endif /* !defined(CAAM_COMPAT_H) */
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 77557eb..414ba20 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -2,13 +2,16 @@
  * CAAM control-plane driver backend
  * Controller-level driver, kernel property detection, initialization
  *
- * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ * Copyright 2008-2012 Freescale Semiconductor, Inc.
  */
 
 #include "compat.h"
 #include "regs.h"
 #include "intern.h"
 #include "jr.h"
+#include "desc_constr.h"
+#include "error.h"
+#include "ctrl.h"
 
 static int caam_remove(struct platform_device *pdev)
 {
@@ -43,10 +46,154 @@ static int caam_remove(struct platform_device *pdev)
 	return ret;
 }
 
+/*
+ * Descriptor to instantiate RNG State Handle 0 in normal mode and
+ * load the JDKEK, TDKEK and TDSK registers
+ */
+static void build_instantiation_desc(u32 *desc)
+{
+	u32 *jump_cmd;
+
+	init_job_desc(desc, 0);
+
+	/* INIT RNG in non-test mode */
+	append_operation(desc, OP_TYPE_CLASS1_ALG | OP_ALG_ALGSEL_RNG |
+			 OP_ALG_AS_INIT);
+
+	/* wait for done */
+	jump_cmd = append_jump(desc, JUMP_CLASS_CLASS1);
+	set_jump_tgt_here(desc, jump_cmd);
+
+	/*
+	 * load 1 to clear written reg:
+	 * resets the done interrrupt and returns the RNG to idle.
+	 */
+	append_load_imm_u32(desc, 1, LDST_SRCDST_WORD_CLRW);
+
+	/* generate secure keys (non-test) */
+	append_operation(desc, OP_TYPE_CLASS1_ALG | OP_ALG_ALGSEL_RNG |
+			 OP_ALG_RNG4_SK);
+}
+
+struct instantiate_result {
+	struct completion completion;
+	int err;
+};
+
+static void rng4_init_done(struct device *dev, u32 *desc, u32 err,
+			   void *context)
+{
+	struct instantiate_result *instantiation = context;
+
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(dev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	instantiation->err = err;
+	complete(&instantiation->completion);
+}
+
+static int instantiate_rng(struct device *jrdev)
+{
+	struct instantiate_result instantiation;
+
+	dma_addr_t desc_dma;
+	u32 *desc;
+	int ret;
+
+	desc = kmalloc(CAAM_CMD_SZ * 6, GFP_KERNEL | GFP_DMA);
+	if (!desc) {
+		dev_err(jrdev, "cannot allocate RNG init descriptor memory\n");
+		return -ENOMEM;
+	}
+
+	build_instantiation_desc(desc);
+	desc_dma = dma_map_single(jrdev, desc, desc_bytes(desc), DMA_TO_DEVICE);
+	init_completion(&instantiation.completion);
+	ret = caam_jr_enqueue(jrdev, desc, rng4_init_done, &instantiation);
+	if (!ret) {
+		wait_for_completion_interruptible(&instantiation.completion);
+		ret = instantiation.err;
+		if (ret)
+			dev_err(jrdev, "unable to instantiate RNG\n");
+	}
+
+	dma_unmap_single(jrdev, desc_dma, desc_bytes(desc), DMA_TO_DEVICE);
+
+	kfree(desc);
+
+	return ret;
+}
+
+/*
+ * By default, the TRNG runs for 200 clocks per sample;
+ * 800 clocks per sample generates better entropy.
+ */
+static void kick_trng(struct platform_device *pdev)
+{
+	struct device *ctrldev = &pdev->dev;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
+	struct caam_full __iomem *topregs;
+	struct rng4tst __iomem *r4tst;
+	u32 val;
+
+	topregs = (struct caam_full __iomem *)ctrlpriv->ctrl;
+	r4tst = &topregs->ctrl.r4tst[0];
+
+	/* put RNG4 into program mode */
+	setbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+	/* 800 clocks per sample */
+	val = rd_reg32(&r4tst->rtsdctl);
+	val = (val & ~RTSDCTL_ENT_DLY_MASK) | (800 << RTSDCTL_ENT_DLY_SHIFT);
+	wr_reg32(&r4tst->rtsdctl, val);
+	/* min. freq. count */
+	wr_reg32(&r4tst->rtfrqmin, 400);
+	/* max. freq. count */
+	wr_reg32(&r4tst->rtfrqmax, 6400);
+	/* put RNG4 into run mode */
+	clrbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+}
+
+/**
+ * caam_get_era() - Return the ERA of the SEC on SoC, based
+ * on the SEC_VID register.
+ * Returns the ERA number (1..4) or -ENOTSUPP if the ERA is unknown.
+ * @caam_id - the value of the SEC_VID register
+ **/
+int caam_get_era(u64 caam_id)
+{
+	struct sec_vid *sec_vid = (struct sec_vid *)&caam_id;
+	static const struct {
+		u16 ip_id;
+		u8 maj_rev;
+		u8 era;
+	} caam_eras[] = {
+		{0x0A10, 1, 1},
+		{0x0A10, 2, 2},
+		{0x0A12, 1, 3},
+		{0x0A14, 1, 3},
+		{0x0A14, 2, 4},
+		{0x0A16, 1, 4},
+		{0x0A11, 1, 4}
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(caam_eras); i++)
+		if (caam_eras[i].ip_id == sec_vid->ip_id &&
+			caam_eras[i].maj_rev == sec_vid->maj_rev)
+				return caam_eras[i].era;
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(caam_get_era);
+
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
-	int ring, rspec;
+	int ret, ring, rspec;
+	u64 caam_id;
 	struct device *dev;
 	struct device_node *nprop, *np;
 	struct caam_ctrl __iomem *ctrl;
@@ -82,13 +229,18 @@ static int caam_probe(struct platform_device *pdev)
 
 	/*
 	 * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel,
-	 * 36-bit pointers in master configuration register
+	 * long pointers in master configuration register
 	 */
 	setbits32(&topregs->ctrl.mcr, MCFGR_WDENABLE |
 		  (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
 
 	if (sizeof(dma_addr_t) == sizeof(u64))
-		dma_set_mask(dev, DMA_BIT_MASK(36));
+		if (of_device_is_compatible(nprop, "fsl,sec-v5.0"))
+			dma_set_mask(dev, DMA_BIT_MASK(40));
+		else
+			dma_set_mask(dev, DMA_BIT_MASK(36));
+	else
+		dma_set_mask(dev, DMA_BIT_MASK(32));
 
 	/*
 	 * Detect and enable JobRs
@@ -141,14 +293,29 @@ static int caam_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	/*
+	 * RNG4 based SECs (v5+) need special initialization prior
+	 * to executing any descriptors
+	 */
+	if (of_device_is_compatible(nprop, "fsl,sec-v5.0")) {
+		kick_trng(pdev);
+		ret = instantiate_rng(ctrlpriv->jrdev[0]);
+		if (ret) {
+			caam_remove(pdev);
+			return ret;
+		}
+	}
+
 	/* NOTE: RTIC detection ought to go here, around Si time */
 
 	/* Initialize queue allocator lock */
 	spin_lock_init(&ctrlpriv->jr_alloc_lock);
 
+	caam_id = rd_reg64(&topregs->ctrl.perfmon.caam_id);
+
 	/* Report "alive" for developer to see */
-	dev_info(dev, "device ID = 0x%016llx\n",
-		 rd_reg64(&topregs->ctrl.perfmon.caam_id));
+	dev_info(dev, "device ID = 0x%016llx (Era %d)\n", caam_id,
+		 caam_get_era(caam_id));
 	dev_info(dev, "job rings = %d, qi = %d\n",
 		 ctrlpriv->total_jobrs, ctrlpriv->qi_present);
 
diff --git a/drivers/crypto/caam/ctrl.h b/drivers/crypto/caam/ctrl.h
new file mode 100644
index 0000000..980d44e
--- /dev/null
+++ b/drivers/crypto/caam/ctrl.h
@@ -0,0 +1,13 @@
+/*
+ * CAAM control-plane driver backend public-level include definitions
+ *
+ * Copyright 2012 Freescale Semiconductor, Inc.
+ */
+
+#ifndef CTRL_H
+#define CTRL_H
+
+/* Prototypes for backend-level services exposed to APIs */
+int caam_get_era(u64 caam_id);
+
+#endif /* CTRL_H */
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index a17c295..f7f833b 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -8,6 +8,16 @@
 #ifndef DESC_H
 #define DESC_H
 
+struct sec4_sg_entry {
+	u64 ptr;
+#define SEC4_SG_LEN_FIN 0x40000000
+#define SEC4_SG_LEN_EXT 0x80000000
+	u32 len;
+	u8 reserved;
+	u8 buf_pool_id;
+	u16 offset;
+};
+
 /* Max size of any CAAM descriptor in 32-bit words, inclusive of header */
 #define MAX_CAAM_DESCSIZE	64
 
@@ -1162,6 +1172,11 @@
 #define OP_ALG_AAI_GSM		(0x10 << OP_ALG_AAI_SHIFT)
 #define OP_ALG_AAI_EDGE		(0x20 << OP_ALG_AAI_SHIFT)
 
+/* RNG4 set */
+#define OP_ALG_RNG4_SHIFT	4
+#define OP_ALG_RNG4_MASK	(0x1f3 << OP_ALG_RNG4_SHIFT)
+
+#define OP_ALG_RNG4_SK		(0x100 << OP_ALG_RNG4_SHIFT)
 
 #define OP_ALG_AS_SHIFT		2
 #define OP_ALG_AS_MASK		(0x3 << OP_ALG_AS_SHIFT)
@@ -1585,20 +1600,4 @@
 #define NFIFOENTRY_PLEN_SHIFT	0
 #define NFIFOENTRY_PLEN_MASK	(0xFF << NFIFOENTRY_PLEN_SHIFT)
 
-/*
- * PDB internal definitions
- */
-
-/* IPSec ESP CBC Encap/Decap Options */
-#define PDBOPTS_ESPCBC_ARSNONE	0x00	/* no antireplay window	*/
-#define PDBOPTS_ESPCBC_ARS32	0x40	/* 32-entry antireplay window */
-#define PDBOPTS_ESPCBC_ARS64	0xc0	/* 64-entry antireplay window */
-#define PDBOPTS_ESPCBC_IVSRC	0x20	/* IV comes from internal random gen */
-#define PDBOPTS_ESPCBC_ESN	0x10	/* extended sequence included */
-#define PDBOPTS_ESPCBC_OUTFMT	0x08	/* output only decapsulation (decap) */
-#define PDBOPTS_ESPCBC_IPHDRSRC 0x08	/* IP header comes from PDB (encap) */
-#define PDBOPTS_ESPCBC_INCIPHDR 0x04	/* Prepend IP header to output frame */
-#define PDBOPTS_ESPCBC_IPVSN	0x02	/* process IPv6 header */
-#define PDBOPTS_ESPCBC_TUNNEL	0x01	/* tunnel mode next-header byte */
-
 #endif /* DESC_H */
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index 348b882..c85c1f0 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -1,7 +1,7 @@
 /*
  * caam descriptor construction helper functions
  *
- * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ * Copyright 2008-2012 Freescale Semiconductor, Inc.
  */
 
 #include "desc.h"
@@ -51,7 +51,7 @@ static inline void *sh_desc_pdb(u32 *desc)
 
 static inline void init_desc(u32 *desc, u32 options)
 {
-	*desc = options | HDR_ONE | 1;
+	*desc = (options | HDR_ONE) + 1;
 }
 
 static inline void init_sh_desc(u32 *desc, u32 options)
@@ -62,9 +62,9 @@ static inline void init_sh_desc(u32 *desc, u32 options)
 
 static inline void init_sh_desc_pdb(u32 *desc, u32 options, size_t pdb_bytes)
 {
-	u32 pdb_len = pdb_bytes / CAAM_CMD_SZ + 1;
+	u32 pdb_len = (pdb_bytes + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ;
 
-	init_sh_desc(desc, ((pdb_len << HDR_START_IDX_SHIFT) + pdb_len) |
+	init_sh_desc(desc, (((pdb_len + 1) << HDR_START_IDX_SHIFT) + pdb_len) |
 		     options);
 }
 
@@ -117,6 +117,15 @@ static inline void append_cmd_ptr(u32 *desc, dma_addr_t ptr, int len,
 	append_ptr(desc, ptr);
 }
 
+/* Write length after pointer, rather than inside command */
+static inline void append_cmd_ptr_extlen(u32 *desc, dma_addr_t ptr,
+					 unsigned int len, u32 command)
+{
+	append_cmd(desc, command);
+	append_ptr(desc, ptr);
+	append_cmd(desc, len);
+}
+
 static inline void append_cmd_data(u32 *desc, void *data, int len,
 				   u32 command)
 {
@@ -166,13 +175,22 @@ static inline void append_##cmd(u32 *desc, dma_addr_t ptr, unsigned int len, \
 	append_cmd_ptr(desc, ptr, len, CMD_##op | options); \
 }
 APPEND_CMD_PTR(key, KEY)
-APPEND_CMD_PTR(seq_in_ptr, SEQ_IN_PTR)
-APPEND_CMD_PTR(seq_out_ptr, SEQ_OUT_PTR)
 APPEND_CMD_PTR(load, LOAD)
 APPEND_CMD_PTR(store, STORE)
 APPEND_CMD_PTR(fifo_load, FIFO_LOAD)
 APPEND_CMD_PTR(fifo_store, FIFO_STORE)
 
+#define APPEND_SEQ_PTR_INTLEN(cmd, op) \
+static inline void append_seq_##cmd##_ptr_intlen(u32 *desc, dma_addr_t ptr, \
+						 unsigned int len, \
+						 u32 options) \
+{ \
+	PRINT_POS; \
+	append_cmd_ptr(desc, ptr, len, CMD_SEQ_##op##_PTR | options); \
+}
+APPEND_SEQ_PTR_INTLEN(in, IN)
+APPEND_SEQ_PTR_INTLEN(out, OUT)
+
 #define APPEND_CMD_PTR_TO_IMM(cmd, op) \
 static inline void append_##cmd##_as_imm(u32 *desc, void *data, \
 					 unsigned int len, u32 options) \
@@ -183,6 +201,33 @@ static inline void append_##cmd##_as_imm(u32 *desc, void *data, \
 APPEND_CMD_PTR_TO_IMM(load, LOAD);
 APPEND_CMD_PTR_TO_IMM(fifo_load, FIFO_LOAD);
 
+#define APPEND_CMD_PTR_EXTLEN(cmd, op) \
+static inline void append_##cmd##_extlen(u32 *desc, dma_addr_t ptr, \
+					 unsigned int len, u32 options) \
+{ \
+	PRINT_POS; \
+	append_cmd_ptr_extlen(desc, ptr, len, CMD_##op | SQIN_EXT | options); \
+}
+APPEND_CMD_PTR_EXTLEN(seq_in_ptr, SEQ_IN_PTR)
+APPEND_CMD_PTR_EXTLEN(seq_out_ptr, SEQ_OUT_PTR)
+
+/*
+ * Determine whether to store length internally or externally depending on
+ * the size of its type
+ */
+#define APPEND_CMD_PTR_LEN(cmd, op, type) \
+static inline void append_##cmd(u32 *desc, dma_addr_t ptr, \
+				type len, u32 options) \
+{ \
+	PRINT_POS; \
+	if (sizeof(type) > sizeof(u16)) \
+		append_##cmd##_extlen(desc, ptr, len, options); \
+	else \
+		append_##cmd##_intlen(desc, ptr, len, options); \
+}
+APPEND_CMD_PTR_LEN(seq_in_ptr, SEQ_IN_PTR, u32)
+APPEND_CMD_PTR_LEN(seq_out_ptr, SEQ_OUT_PTR, u32)
+
 /*
  * 2nd variant for commands whose specified immediate length differs
  * from length of immediate data provided, e.g., split keys
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 7e2d54b..9955ed9 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -39,18 +39,20 @@ static void report_ccb_status(u32 status, char *outstr)
 	char *cha_id_list[] = {
 		"",
 		"AES",
-		"DES, 3DES",
+		"DES",
 		"ARC4",
-		"MD5, SHA-1, SH-224, SHA-256, SHA-384, SHA-512",
+		"MDHA",
 		"RNG",
 		"SNOW f8",
-		"Kasumi f8, f9",
-		"All Public Key Algorithms",
-		"CRC",
+		"Kasumi f8/9",
+		"PKHA",
+		"CRCA",
 		"SNOW f9",
+		"ZUCE",
+		"ZUCA",
 	};
 	char *err_id_list[] = {
-		"None. No error.",
+		"No error.",
 		"Mode error.",
 		"Data size error.",
 		"Key size error.",
@@ -67,6 +69,20 @@ static void report_ccb_status(u32 status, char *outstr)
 		"Invalid CHA combination was selected",
 		"Invalid CHA selected.",
 	};
+	char *rng_err_id_list[] = {
+		"",
+		"",
+		"",
+		"Instantiate",
+		"Not instantiated",
+		"Test instantiate",
+		"Prediction resistance",
+		"",
+		"Prediction resistance and test request",
+		"Uninstantiate",
+		"",
+		"Secure key generation",
+	};
 	u8 cha_id = (status & JRSTA_CCBERR_CHAID_MASK) >>
 		    JRSTA_CCBERR_CHAID_SHIFT;
 	u8 err_id = status & JRSTA_CCBERR_ERRID_MASK;
@@ -81,7 +97,13 @@ static void report_ccb_status(u32 status, char *outstr)
 			   cha_id, sizeof("ff"));
 	}
 
-	if (err_id < ARRAY_SIZE(err_id_list)) {
+	if ((cha_id << JRSTA_CCBERR_CHAID_SHIFT) == JRSTA_CCBERR_CHAID_RNG &&
+	    err_id < ARRAY_SIZE(rng_err_id_list) &&
+	    strlen(rng_err_id_list[err_id])) {
+		/* RNG-only error */
+		SPRINTFCAT(outstr, "%s", rng_err_id_list[err_id],
+			   strlen(rng_err_id_list[err_id]));
+	} else if (err_id < ARRAY_SIZE(err_id_list)) {
 		SPRINTFCAT(outstr, "%s", err_id_list[err_id],
 			   strlen(err_id_list[err_id]));
 	} else {
@@ -101,10 +123,10 @@ static void report_deco_status(u32 status, char *outstr)
 		u8 value;
 		char *error_text;
 	} desc_error_list[] = {
-		{ 0x00, "None. No error." },
+		{ 0x00, "No error." },
 		{ 0x01, "SGT Length Error. The descriptor is trying to read "
 			"more data than is contained in the SGT table." },
-		{ 0x02, "Reserved." },
+		{ 0x02, "SGT Null Entry Error." },
 		{ 0x03, "Job Ring Control Error. There is a bad value in the "
 			"Job Ring Control register." },
 		{ 0x04, "Invalid Descriptor Command. The Descriptor Command "
@@ -116,7 +138,7 @@ static void report_deco_status(u32 status, char *outstr)
 		{ 0x09, "Invalid OPERATION Command" },
 		{ 0x0A, "Invalid FIFO LOAD Command" },
 		{ 0x0B, "Invalid FIFO STORE Command" },
-		{ 0x0C, "Invalid MOVE Command" },
+		{ 0x0C, "Invalid MOVE/MOVE_LEN Command" },
 		{ 0x0D, "Invalid JUMP Command. A nonlocal JUMP Command is "
 			"invalid because the target is not a Job Header "
 			"Command, or the jump is from a Trusted Descriptor to "
@@ -166,6 +188,8 @@ static void report_deco_status(u32 status, char *outstr)
 			"(input frame; block ciphers) and IPsec decap (output "
 			"frame, when doing the next header byte update) and "
 			"DCRC (output frame)." },
+		{ 0x23, "Read Input Frame error" },
+		{ 0x24, "JDKEK, TDKEK or TDSK not loaded error" },
 		{ 0x80, "DNR (do not run) error" },
 		{ 0x81, "undefined protocol command" },
 		{ 0x82, "invalid setting in PDB" },
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index a34be01..5cd4c1b 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -43,7 +43,7 @@ struct caam_drv_private_jr {
 	struct device *parentdev;	/* points back to controller dev */
 	int ridx;
 	struct caam_job_ring __iomem *rregs;	/* JobR's register space */
-	struct tasklet_struct irqtask[NR_CPUS];
+	struct tasklet_struct irqtask;
 	int irq;			/* One per queue */
 	int assign;			/* busy/free */
 
@@ -86,10 +86,10 @@ struct caam_drv_private {
 
 	/* which jr allocated to scatterlist crypto */
 	atomic_t tfm_count ____cacheline_aligned;
-	int num_jrs_for_algapi;
-	struct device **algapi_jr;
 	/* list of registered crypto algorithms (mk generic context handle?) */
 	struct list_head alg_list;
+	/* list of registered hash algorithms (mk generic context handle?) */
+	struct list_head hash_list;
 
 	/*
 	 * debugfs entries for developer view into driver/device
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 340fa32..53c8c51 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -2,7 +2,7 @@
  * CAAM/SEC 4.x transport/backend driver
  * JobR backend functionality
  *
- * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ * Copyright 2008-2012 Freescale Semiconductor, Inc.
  */
 
 #include "compat.h"
@@ -43,7 +43,7 @@ static irqreturn_t caam_jr_interrupt(int irq, void *st_dev)
 	wr_reg32(&jrp->rregs->jrintstatus, irqstate);
 
 	preempt_disable();
-	tasklet_schedule(&jrp->irqtask[smp_processor_id()]);
+	tasklet_schedule(&jrp->irqtask);
 	preempt_enable();
 
 	return IRQ_HANDLED;
@@ -58,17 +58,16 @@ static void caam_jr_dequeue(unsigned long devarg)
 	void (*usercall)(struct device *dev, u32 *desc, u32 status, void *arg);
 	u32 *userdesc, userstatus;
 	void *userarg;
-	unsigned long flags;
 
-	spin_lock_irqsave(&jrp->outlock, flags);
+	while (rd_reg32(&jrp->rregs->outring_used)) {
 
-	head = ACCESS_ONCE(jrp->head);
-	sw_idx = tail = jrp->tail;
+		head = ACCESS_ONCE(jrp->head);
 
-	while (CIRC_CNT(head, tail, JOBR_DEPTH) >= 1 &&
-	       rd_reg32(&jrp->rregs->outring_used)) {
+		spin_lock_bh(&jrp->outlock);
 
+		sw_idx = tail = jrp->tail;
 		hw_idx = jrp->out_ring_read_index;
+
 		for (i = 0; CIRC_CNT(head, tail + i, JOBR_DEPTH) >= 1; i++) {
 			sw_idx = (tail + i) & (JOBR_DEPTH - 1);
 
@@ -95,7 +94,8 @@ static void caam_jr_dequeue(unsigned long devarg)
 		userdesc = jrp->entinfo[sw_idx].desc_addr_virt;
 		userstatus = jrp->outring[hw_idx].jrstatus;
 
-		smp_mb();
+		/* set done */
+		wr_reg32(&jrp->rregs->outring_rmvd, 1);
 
 		jrp->out_ring_read_index = (jrp->out_ring_read_index + 1) &
 					   (JOBR_DEPTH - 1);
@@ -115,22 +115,12 @@ static void caam_jr_dequeue(unsigned long devarg)
 			jrp->tail = tail;
 		}
 
-		/* set done */
-		wr_reg32(&jrp->rregs->outring_rmvd, 1);
-
-		spin_unlock_irqrestore(&jrp->outlock, flags);
+		spin_unlock_bh(&jrp->outlock);
 
 		/* Finally, execute user's callback */
 		usercall(dev, userdesc, userstatus, userarg);
-
-		spin_lock_irqsave(&jrp->outlock, flags);
-
-		head = ACCESS_ONCE(jrp->head);
-		sw_idx = tail = jrp->tail;
 	}
 
-	spin_unlock_irqrestore(&jrp->outlock, flags);
-
 	/* reenable / unmask IRQs */
 	clrbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
 }
@@ -148,23 +138,22 @@ int caam_jr_register(struct device *ctrldev, struct device **rdev)
 {
 	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
 	struct caam_drv_private_jr *jrpriv = NULL;
-	unsigned long flags;
 	int ring;
 
 	/* Lock, if free ring - assign, unlock */
-	spin_lock_irqsave(&ctrlpriv->jr_alloc_lock, flags);
+	spin_lock(&ctrlpriv->jr_alloc_lock);
 	for (ring = 0; ring < ctrlpriv->total_jobrs; ring++) {
 		jrpriv = dev_get_drvdata(ctrlpriv->jrdev[ring]);
 		if (jrpriv->assign == JOBR_UNASSIGNED) {
 			jrpriv->assign = JOBR_ASSIGNED;
 			*rdev = ctrlpriv->jrdev[ring];
-			spin_unlock_irqrestore(&ctrlpriv->jr_alloc_lock, flags);
+			spin_unlock(&ctrlpriv->jr_alloc_lock);
 			return ring;
 		}
 	}
 
 	/* If assigned, write dev where caller needs it */
-	spin_unlock_irqrestore(&ctrlpriv->jr_alloc_lock, flags);
+	spin_unlock(&ctrlpriv->jr_alloc_lock);
 	*rdev = NULL;
 
 	return -ENODEV;
@@ -182,7 +171,6 @@ int caam_jr_deregister(struct device *rdev)
 {
 	struct caam_drv_private_jr *jrpriv = dev_get_drvdata(rdev);
 	struct caam_drv_private *ctrlpriv;
-	unsigned long flags;
 
 	/* Get the owning controller's private space */
 	ctrlpriv = dev_get_drvdata(jrpriv->parentdev);
@@ -195,9 +183,9 @@ int caam_jr_deregister(struct device *rdev)
 		return -EBUSY;
 
 	/* Release ring */
-	spin_lock_irqsave(&ctrlpriv->jr_alloc_lock, flags);
+	spin_lock(&ctrlpriv->jr_alloc_lock);
 	jrpriv->assign = JOBR_UNASSIGNED;
-	spin_unlock_irqrestore(&ctrlpriv->jr_alloc_lock, flags);
+	spin_unlock(&ctrlpriv->jr_alloc_lock);
 
 	return 0;
 }
@@ -238,7 +226,6 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 {
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	struct caam_jrentry_info *head_entry;
-	unsigned long flags;
 	int head, tail, desc_size;
 	dma_addr_t desc_dma;
 
@@ -249,14 +236,14 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 		return -EIO;
 	}
 
-	spin_lock_irqsave(&jrp->inplock, flags);
+	spin_lock(&jrp->inplock);
 
 	head = jrp->head;
 	tail = ACCESS_ONCE(jrp->tail);
 
 	if (!rd_reg32(&jrp->rregs->inpring_avail) ||
 	    CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) {
-		spin_unlock_irqrestore(&jrp->inplock, flags);
+		spin_unlock(&jrp->inplock);
 		dma_unmap_single(dev, desc_dma, desc_size, DMA_TO_DEVICE);
 		return -EBUSY;
 	}
@@ -276,11 +263,9 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 				    (JOBR_DEPTH - 1);
 	jrp->head = (head + 1) & (JOBR_DEPTH - 1);
 
-	wmb();
-
 	wr_reg32(&jrp->rregs->inpring_jobadd, 1);
 
-	spin_unlock_irqrestore(&jrp->inplock, flags);
+	spin_unlock(&jrp->inplock);
 
 	return 0;
 }
@@ -337,11 +322,9 @@ static int caam_jr_init(struct device *dev)
 
 	jrp = dev_get_drvdata(dev);
 
-	/* Connect job ring interrupt handler. */
-	for_each_possible_cpu(i)
-		tasklet_init(&jrp->irqtask[i], caam_jr_dequeue,
-			     (unsigned long)dev);
+	tasklet_init(&jrp->irqtask, caam_jr_dequeue, (unsigned long)dev);
 
+	/* Connect job ring interrupt handler. */
 	error = request_irq(jrp->irq, caam_jr_interrupt, IRQF_SHARED,
 			    "caam-jobr", dev);
 	if (error) {
@@ -356,10 +339,11 @@ static int caam_jr_init(struct device *dev)
 	if (error)
 		return error;
 
-	jrp->inpring = kzalloc(sizeof(dma_addr_t) * JOBR_DEPTH,
-			       GFP_KERNEL | GFP_DMA);
-	jrp->outring = kzalloc(sizeof(struct jr_outentry) *
-			       JOBR_DEPTH, GFP_KERNEL | GFP_DMA);
+	jrp->inpring = dma_alloc_coherent(dev, sizeof(dma_addr_t) * JOBR_DEPTH,
+					  &inpbusaddr, GFP_KERNEL);
+
+	jrp->outring = dma_alloc_coherent(dev, sizeof(struct jr_outentry) *
+					  JOBR_DEPTH, &outbusaddr, GFP_KERNEL);
 
 	jrp->entinfo = kzalloc(sizeof(struct caam_jrentry_info) * JOBR_DEPTH,
 			       GFP_KERNEL);
@@ -375,31 +359,6 @@ static int caam_jr_init(struct device *dev)
 		jrp->entinfo[i].desc_addr_dma = !0;
 
 	/* Setup rings */
-	inpbusaddr = dma_map_single(dev, jrp->inpring,
-				    sizeof(u32 *) * JOBR_DEPTH,
-				    DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, inpbusaddr)) {
-		dev_err(dev, "caam_jr_init(): can't map input ring\n");
-		kfree(jrp->inpring);
-		kfree(jrp->outring);
-		kfree(jrp->entinfo);
-		return -EIO;
-	}
-
-	outbusaddr = dma_map_single(dev, jrp->outring,
-				    sizeof(struct jr_outentry) * JOBR_DEPTH,
-				    DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, outbusaddr)) {
-		dev_err(dev, "caam_jr_init(): can't map output ring\n");
-			dma_unmap_single(dev, inpbusaddr,
-					 sizeof(u32 *) * JOBR_DEPTH,
-					 DMA_BIDIRECTIONAL);
-		kfree(jrp->inpring);
-		kfree(jrp->outring);
-		kfree(jrp->entinfo);
-		return -EIO;
-	}
-
 	jrp->inp_ring_write_index = 0;
 	jrp->out_ring_read_index = 0;
 	jrp->head = 0;
@@ -431,12 +390,11 @@ int caam_jr_shutdown(struct device *dev)
 {
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	dma_addr_t inpbusaddr, outbusaddr;
-	int ret, i;
+	int ret;
 
 	ret = caam_reset_hw_jr(dev);
 
-	for_each_possible_cpu(i)
-		tasklet_kill(&jrp->irqtask[i]);
+	tasklet_kill(&jrp->irqtask);
 
 	/* Release interrupt */
 	free_irq(jrp->irq, dev);
@@ -444,13 +402,10 @@ int caam_jr_shutdown(struct device *dev)
 	/* Free rings */
 	inpbusaddr = rd_reg64(&jrp->rregs->inpring_base);
 	outbusaddr = rd_reg64(&jrp->rregs->outring_base);
-	dma_unmap_single(dev, outbusaddr,
-			 sizeof(struct jr_outentry) * JOBR_DEPTH,
-			 DMA_BIDIRECTIONAL);
-	dma_unmap_single(dev, inpbusaddr, sizeof(u32 *) * JOBR_DEPTH,
-			 DMA_BIDIRECTIONAL);
-	kfree(jrp->outring);
-	kfree(jrp->inpring);
+	dma_free_coherent(dev, sizeof(dma_addr_t) * JOBR_DEPTH,
+			  jrp->inpring, inpbusaddr);
+	dma_free_coherent(dev, sizeof(struct jr_outentry) * JOBR_DEPTH,
+			  jrp->outring, outbusaddr);
 	kfree(jrp->entinfo);
 
 	return ret;
@@ -503,6 +458,14 @@ int caam_jr_probe(struct platform_device *pdev, struct device_node *np,
 	dev_set_drvdata(jrdev, jrpriv);
 	ctrlpriv->jrdev[ring] = jrdev;
 
+	if (sizeof(dma_addr_t) == sizeof(u64))
+		if (of_device_is_compatible(np, "fsl,sec-v5.0-job-ring"))
+			dma_set_mask(jrdev, DMA_BIT_MASK(40));
+		else
+			dma_set_mask(jrdev, DMA_BIT_MASK(36));
+	else
+		dma_set_mask(jrdev, DMA_BIT_MASK(32));
+
 	/* Identify the interrupt */
 	jrpriv->irq = of_irq_to_resource(np, 0, NULL);
 
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
new file mode 100644
index 0000000..0028881
--- /dev/null
+++ b/drivers/crypto/caam/key_gen.c
@@ -0,0 +1,122 @@
+/*
+ * CAAM/SEC 4.x functions for handling key-generation jobs
+ *
+ * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ *
+ */
+#include "compat.h"
+#include "jr.h"
+#include "error.h"
+#include "desc_constr.h"
+#include "key_gen.h"
+
+void split_key_done(struct device *dev, u32 *desc, u32 err,
+			   void *context)
+{
+	struct split_key_result *res = context;
+
+#ifdef DEBUG
+	dev_err(dev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	if (err) {
+		char tmp[CAAM_ERROR_STR_MAX];
+
+		dev_err(dev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
+	}
+
+	res->err = err;
+
+	complete(&res->completion);
+}
+EXPORT_SYMBOL(split_key_done);
+/*
+get a split ipad/opad key
+
+Split key generation-----------------------------------------------
+
+[00] 0xb0810008    jobdesc: stidx=1 share=never len=8
+[01] 0x04000014        key: class2->keyreg len=20
+			@0xffe01000
+[03] 0x84410014  operation: cls2-op sha1 hmac init dec
+[04] 0x24940000     fifold: class2 msgdata-last2 len=0 imm
+[05] 0xa4000001       jump: class2 local all ->1 [06]
+[06] 0x64260028    fifostr: class2 mdsplit-jdk len=40
+			@0xffe04000
+*/
+u32 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)
+{
+	u32 *desc;
+	struct split_key_result result;
+	dma_addr_t dma_addr_in, dma_addr_out;
+	int ret = 0;
+
+	desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
+
+	init_job_desc(desc, 0);
+
+	dma_addr_in = dma_map_single(jrdev, (void *)key_in, keylen,
+				     DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, dma_addr_in)) {
+		dev_err(jrdev, "unable to map key input memory\n");
+		kfree(desc);
+		return -ENOMEM;
+	}
+	append_key(desc, dma_addr_in, keylen, CLASS_2 | KEY_DEST_CLASS_REG);
+
+	/* Sets MDHA up into an HMAC-INIT */
+	append_operation(desc, alg_op | OP_ALG_DECRYPT | OP_ALG_AS_INIT);
+
+	/*
+	 * do a FIFO_LOAD of zero, this will trigger the internal key expansion
+	 * into both pads inside MDHA
+	 */
+	append_fifo_load_as_imm(desc, NULL, 0, LDST_CLASS_2_CCB |
+				FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST2);
+
+	/*
+	 * FIFO_STORE with the explicit split-key content store
+	 * (0x26 output type)
+	 */
+	dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len,
+				      DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, dma_addr_out)) {
+		dev_err(jrdev, "unable to map key output memory\n");
+		kfree(desc);
+		return -ENOMEM;
+	}
+	append_fifo_store(desc, dma_addr_out, split_key_len,
+			  LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK);
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key_in, keylen, 1);
+	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
+#endif
+
+	result.err = 0;
+	init_completion(&result.completion);
+
+	ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result);
+	if (!ret) {
+		/* in progress */
+		wait_for_completion_interruptible(&result.completion);
+		ret = result.err;
+#ifdef DEBUG
+		print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, key_out,
+			       split_key_pad_len, 1);
+#endif
+	}
+
+	dma_unmap_single(jrdev, dma_addr_out, split_key_pad_len,
+			 DMA_FROM_DEVICE);
+	dma_unmap_single(jrdev, dma_addr_in, keylen, DMA_TO_DEVICE);
+
+	kfree(desc);
+
+	return ret;
+}
diff --git a/drivers/crypto/caam/key_gen.h b/drivers/crypto/caam/key_gen.h
new file mode 100644
index 0000000..d95d290
--- /dev/null
+++ b/drivers/crypto/caam/key_gen.h
@@ -0,0 +1,17 @@
+/*
+ * CAAM/SEC 4.x definitions for handling key-generation jobs
+ *
+ * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ *
+ */
+
+struct split_key_result {
+	struct completion completion;
+	int err;
+};
+
+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 split_key_pad_len, const u8 *key_in, u32 keylen,
+		    u32 alg_op);
diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h
new file mode 100644
index 0000000..62950d2
--- /dev/null
+++ b/drivers/crypto/caam/pdb.h
@@ -0,0 +1,401 @@
+/*
+ * CAAM Protocol Data Block (PDB) definition header file
+ *
+ * Copyright 2008-2012 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef CAAM_PDB_H
+#define CAAM_PDB_H
+
+/*
+ * PDB- IPSec ESP Header Modification Options
+ */
+#define PDBHMO_ESP_DECAP_SHIFT	12
+#define PDBHMO_ESP_ENCAP_SHIFT	4
+/*
+ * Encap and Decap - Decrement TTL (Hop Limit) - Based on the value of the
+ * Options Byte IP version (IPvsn) field:
+ * if IPv4, decrement the inner IP header TTL field (byte 8);
+ * if IPv6 decrement the inner IP header Hop Limit field (byte 7).
+*/
+#define PDBHMO_ESP_DECAP_DEC_TTL	(0x02 << PDBHMO_ESP_DECAP_SHIFT)
+#define PDBHMO_ESP_ENCAP_DEC_TTL	(0x02 << PDBHMO_ESP_ENCAP_SHIFT)
+/*
+ * Decap - DiffServ Copy - Copy the IPv4 TOS or IPv6 Traffic Class byte
+ * from the outer IP header to the inner IP header.
+ */
+#define PDBHMO_ESP_DIFFSERV		(0x01 << PDBHMO_ESP_DECAP_SHIFT)
+/*
+ * Encap- Copy DF bit -if an IPv4 tunnel mode outer IP header is coming from
+ * the PDB, copy the DF bit from the inner IP header to the outer IP header.
+ */
+#define PDBHMO_ESP_DFBIT		(0x04 << PDBHMO_ESP_ENCAP_SHIFT)
+
+/*
+ * PDB - IPSec ESP Encap/Decap Options
+ */
+#define PDBOPTS_ESP_ARSNONE	0x00 /* no antireplay window */
+#define PDBOPTS_ESP_ARS32	0x40 /* 32-entry antireplay window */
+#define PDBOPTS_ESP_ARS64	0xc0 /* 64-entry antireplay window */
+#define PDBOPTS_ESP_IVSRC	0x20 /* IV comes from internal random gen */
+#define PDBOPTS_ESP_ESN		0x10 /* extended sequence included */
+#define PDBOPTS_ESP_OUTFMT	0x08 /* output only decapsulation (decap) */
+#define PDBOPTS_ESP_IPHDRSRC	0x08 /* IP header comes from PDB (encap) */
+#define PDBOPTS_ESP_INCIPHDR	0x04 /* Prepend IP header to output frame */
+#define PDBOPTS_ESP_IPVSN	0x02 /* process IPv6 header */
+#define PDBOPTS_ESP_TUNNEL	0x01 /* tunnel mode next-header byte */
+#define PDBOPTS_ESP_IPV6	0x02 /* ip header version is V6 */
+#define PDBOPTS_ESP_DIFFSERV	0x40 /* copy TOS/TC from inner iphdr */
+#define PDBOPTS_ESP_UPDATE_CSUM 0x80 /* encap-update ip header checksum */
+#define PDBOPTS_ESP_VERIFY_CSUM 0x20 /* decap-validate ip header checksum */
+
+/*
+ * General IPSec encap/decap PDB definitions
+ */
+struct ipsec_encap_cbc {
+	u32 iv[4];
+};
+
+struct ipsec_encap_ctr {
+	u32 ctr_nonce;
+	u32 ctr_initial;
+	u32 iv[2];
+};
+
+struct ipsec_encap_ccm {
+	u32 salt; /* lower 24 bits */
+	u8 b0_flags;
+	u8 ctr_flags;
+	u16 ctr_initial;
+	u32 iv[2];
+};
+
+struct ipsec_encap_gcm {
+	u32 salt; /* lower 24 bits */
+	u32 rsvd1;
+	u32 iv[2];
+};
+
+struct ipsec_encap_pdb {
+	u8 hmo_rsvd;
+	u8 ip_nh;
+	u8 ip_nh_offset;
+	u8 options;
+	u32 seq_num_ext_hi;
+	u32 seq_num;
+	union {
+		struct ipsec_encap_cbc cbc;
+		struct ipsec_encap_ctr ctr;
+		struct ipsec_encap_ccm ccm;
+		struct ipsec_encap_gcm gcm;
+	};
+	u32 spi;
+	u16 rsvd1;
+	u16 ip_hdr_len;
+	u32 ip_hdr[0]; /* optional IP Header content */
+};
+
+struct ipsec_decap_cbc {
+	u32 rsvd[2];
+};
+
+struct ipsec_decap_ctr {
+	u32 salt;
+	u32 ctr_initial;
+};
+
+struct ipsec_decap_ccm {
+	u32 salt;
+	u8 iv_flags;
+	u8 ctr_flags;
+	u16 ctr_initial;
+};
+
+struct ipsec_decap_gcm {
+	u32 salt;
+	u32 resvd;
+};
+
+struct ipsec_decap_pdb {
+	u16 hmo_ip_hdr_len;
+	u8 ip_nh_offset;
+	u8 options;
+	union {
+		struct ipsec_decap_cbc cbc;
+		struct ipsec_decap_ctr ctr;
+		struct ipsec_decap_ccm ccm;
+		struct ipsec_decap_gcm gcm;
+	};
+	u32 seq_num_ext_hi;
+	u32 seq_num;
+	u32 anti_replay[2];
+	u32 end_index[0];
+};
+
+/*
+ * IPSec ESP Datapath Protocol Override Register (DPOVRD)
+ */
+struct ipsec_deco_dpovrd {
+#define IPSEC_ENCAP_DECO_DPOVRD_USE 0x80
+	u8 ovrd_ecn;
+	u8 ip_hdr_len;
+	u8 nh_offset;
+	u8 next_header; /* reserved if decap */
+};
+
+/*
+ * IEEE 802.11i WiFi Protocol Data Block
+ */
+#define WIFI_PDBOPTS_FCS	0x01
+#define WIFI_PDBOPTS_AR		0x40
+
+struct wifi_encap_pdb {
+	u16 mac_hdr_len;
+	u8 rsvd;
+	u8 options;
+	u8 iv_flags;
+	u8 pri;
+	u16 pn1;
+	u32 pn2;
+	u16 frm_ctrl_mask;
+	u16 seq_ctrl_mask;
+	u8 rsvd1[2];
+	u8 cnst;
+	u8 key_id;
+	u8 ctr_flags;
+	u8 rsvd2;
+	u16 ctr_init;
+};
+
+struct wifi_decap_pdb {
+	u16 mac_hdr_len;
+	u8 rsvd;
+	u8 options;
+	u8 iv_flags;
+	u8 pri;
+	u16 pn1;
+	u32 pn2;
+	u16 frm_ctrl_mask;
+	u16 seq_ctrl_mask;
+	u8 rsvd1[4];
+	u8 ctr_flags;
+	u8 rsvd2;
+	u16 ctr_init;
+};
+
+/*
+ * IEEE 802.16 WiMAX Protocol Data Block
+ */
+#define WIMAX_PDBOPTS_FCS	0x01
+#define WIMAX_PDBOPTS_AR	0x40 /* decap only */
+
+struct wimax_encap_pdb {
+	u8 rsvd[3];
+	u8 options;
+	u32 nonce;
+	u8 b0_flags;
+	u8 ctr_flags;
+	u16 ctr_init;
+	/* begin DECO writeback region */
+	u32 pn;
+	/* end DECO writeback region */
+};
+
+struct wimax_decap_pdb {
+	u8 rsvd[3];
+	u8 options;
+	u32 nonce;
+	u8 iv_flags;
+	u8 ctr_flags;
+	u16 ctr_init;
+	/* begin DECO writeback region */
+	u32 pn;
+	u8 rsvd1[2];
+	u16 antireplay_len;
+	u64 antireplay_scorecard;
+	/* end DECO writeback region */
+};
+
+/*
+ * IEEE 801.AE MacSEC Protocol Data Block
+ */
+#define MACSEC_PDBOPTS_FCS	0x01
+#define MACSEC_PDBOPTS_AR	0x40 /* used in decap only */
+
+struct macsec_encap_pdb {
+	u16 aad_len;
+	u8 rsvd;
+	u8 options;
+	u64 sci;
+	u16 ethertype;
+	u8 tci_an;
+	u8 rsvd1;
+	/* begin DECO writeback region */
+	u32 pn;
+	/* end DECO writeback region */
+};
+
+struct macsec_decap_pdb {
+	u16 aad_len;
+	u8 rsvd;
+	u8 options;
+	u64 sci;
+	u8 rsvd1[3];
+	/* begin DECO writeback region */
+	u8 antireplay_len;
+	u32 pn;
+	u64 antireplay_scorecard;
+	/* end DECO writeback region */
+};
+
+/*
+ * SSL/TLS/DTLS Protocol Data Blocks
+ */
+
+#define TLS_PDBOPTS_ARS32	0x40
+#define TLS_PDBOPTS_ARS64	0xc0
+#define TLS_PDBOPTS_OUTFMT	0x08
+#define TLS_PDBOPTS_IV_WRTBK	0x02 /* 1.1/1.2/DTLS only */
+#define TLS_PDBOPTS_EXP_RND_IV	0x01 /* 1.1/1.2/DTLS only */
+
+struct tls_block_encap_pdb {
+	u8 type;
+	u8 version[2];
+	u8 options;
+	u64 seq_num;
+	u32 iv[4];
+};
+
+struct tls_stream_encap_pdb {
+	u8 type;
+	u8 version[2];
+	u8 options;
+	u64 seq_num;
+	u8 i;
+	u8 j;
+	u8 rsvd1[2];
+};
+
+struct dtls_block_encap_pdb {
+	u8 type;
+	u8 version[2];
+	u8 options;
+	u16 epoch;
+	u16 seq_num[3];
+	u32 iv[4];
+};
+
+struct tls_block_decap_pdb {
+	u8 rsvd[3];
+	u8 options;
+	u64 seq_num;
+	u32 iv[4];
+};
+
+struct tls_stream_decap_pdb {
+	u8 rsvd[3];
+	u8 options;
+	u64 seq_num;
+	u8 i;
+	u8 j;
+	u8 rsvd1[2];
+};
+
+struct dtls_block_decap_pdb {
+	u8 rsvd[3];
+	u8 options;
+	u16 epoch;
+	u16 seq_num[3];
+	u32 iv[4];
+	u64 antireplay_scorecard;
+};
+
+/*
+ * SRTP Protocol Data Blocks
+ */
+#define SRTP_PDBOPTS_MKI	0x08
+#define SRTP_PDBOPTS_AR		0x40
+
+struct srtp_encap_pdb {
+	u8 x_len;
+	u8 mki_len;
+	u8 n_tag;
+	u8 options;
+	u32 cnst0;
+	u8 rsvd[2];
+	u16 cnst1;
+	u16 salt[7];
+	u16 cnst2;
+	u32 rsvd1;
+	u32 roc;
+	u32 opt_mki;
+};
+
+struct srtp_decap_pdb {
+	u8 x_len;
+	u8 mki_len;
+	u8 n_tag;
+	u8 options;
+	u32 cnst0;
+	u8 rsvd[2];
+	u16 cnst1;
+	u16 salt[7];
+	u16 cnst2;
+	u16 rsvd1;
+	u16 seq_num;
+	u32 roc;
+	u64 antireplay_scorecard;
+};
+
+/*
+ * DSA/ECDSA Protocol Data Blocks
+ * Two of these exist: DSA-SIGN, and DSA-VERIFY. They are similar
+ * except for the treatment of "w" for verify, "s" for sign,
+ * and the placement of "a,b".
+ */
+#define DSA_PDB_SGF_SHIFT	24
+#define DSA_PDB_SGF_MASK	(0xff << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_Q		(0x80 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_R		(0x40 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_G		(0x20 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_W		(0x10 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_S		(0x10 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_F		(0x08 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_C		(0x04 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_D		(0x02 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_AB_SIGN	(0x02 << DSA_PDB_SGF_SHIFT)
+#define DSA_PDB_SGF_AB_VERIFY	(0x01 << DSA_PDB_SGF_SHIFT)
+
+#define DSA_PDB_L_SHIFT		7
+#define DSA_PDB_L_MASK		(0x3ff << DSA_PDB_L_SHIFT)
+
+#define DSA_PDB_N_MASK		0x7f
+
+struct dsa_sign_pdb {
+	u32 sgf_ln; /* Use DSA_PDB_ defintions per above */
+	u8 *q;
+	u8 *r;
+	u8 *g;	/* or Gx,y */
+	u8 *s;
+	u8 *f;
+	u8 *c;
+	u8 *d;
+	u8 *ab; /* ECC only */
+	u8 *u;
+};
+
+struct dsa_verify_pdb {
+	u32 sgf_ln;
+	u8 *q;
+	u8 *r;
+	u8 *g;	/* or Gx,y */
+	u8 *w; /* or Wx,y */
+	u8 *f;
+	u8 *c;
+	u8 *d;
+	u8 *tmp; /* temporary data block */
+	u8 *ab; /* only used if ECC processing */
+};
+
+#endif
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index e9f7a70..3223fc6 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -117,6 +117,12 @@ struct jr_outentry {
 #define CHA_NUM_DECONUM_SHIFT	56
 #define CHA_NUM_DECONUM_MASK	(0xfull << CHA_NUM_DECONUM_SHIFT)
 
+struct sec_vid {
+	u16 ip_id;
+	u8 maj_rev;
+	u8 min_rev;
+};
+
 struct caam_perfmon {
 	/* Performance Monitor Registers			f00-f9f */
 	u64 req_dequeued;	/* PC_REQ_DEQ - Dequeued Requests	     */
@@ -167,7 +173,7 @@ struct partid {
 	u32 pidr;	/* partition ID, DECO */
 };
 
-/* RNG test mode (replicated twice in some configurations) */
+/* RNGB test mode (replicated twice in some configurations) */
 /* Padded out to 0x100 */
 struct rngtst {
 	u32 mode;		/* RTSTMODEx - Test mode */
@@ -200,6 +206,31 @@ struct rngtst {
 	u32 rsvd14[15];
 };
 
+/* RNG4 TRNG test registers */
+struct rng4tst {
+#define RTMCTL_PRGM 0x00010000	/* 1 -> program mode, 0 -> run mode */
+	u32 rtmctl;		/* misc. control register */
+	u32 rtscmisc;		/* statistical check misc. register */
+	u32 rtpkrrng;		/* poker range register */
+	union {
+		u32 rtpkrmax;	/* PRGM=1: poker max. limit register */
+		u32 rtpkrsq;	/* PRGM=0: poker square calc. result register */
+	};
+#define RTSDCTL_ENT_DLY_SHIFT 16
+#define RTSDCTL_ENT_DLY_MASK (0xffff << RTSDCTL_ENT_DLY_SHIFT)
+	u32 rtsdctl;		/* seed control register */
+	union {
+		u32 rtsblim;	/* PRGM=1: sparse bit limit register */
+		u32 rttotsam;	/* PRGM=0: total samples register */
+	};
+	u32 rtfrqmin;		/* frequency count min. limit register */
+	union {
+		u32 rtfrqmax;	/* PRGM=1: freq. count max. limit register */
+		u32 rtfrqcnt;	/* PRGM=0: freq. count register */
+	};
+	u32 rsvd1[56];
+};
+
 /*
  * caam_ctrl - basic core configuration
  * starts base + 0x0000 padded out to 0x1000
@@ -249,7 +280,10 @@ struct caam_ctrl {
 
 	/* RNG Test/Verification/Debug Access                   600-7ff */
 	/* (Useful in Test/Debug modes only...)                         */
-	struct rngtst rtst[2];
+	union {
+		struct rngtst rtst[2];
+		struct rng4tst r4tst[2];
+	};
 
 	u32 rsvd9[448];
 
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
new file mode 100644
index 0000000..e0037c8
--- /dev/null
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -0,0 +1,156 @@
+/*
+ * CAAM/SEC 4.x functions for using scatterlists in caam driver
+ *
+ * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ *
+ */
+
+struct sec4_sg_entry;
+
+/*
+ * convert single dma address to h/w link table format
+ */
+static inline void dma_to_sec4_sg_one(struct sec4_sg_entry *sec4_sg_ptr,
+				      dma_addr_t dma, u32 len, u32 offset)
+{
+	sec4_sg_ptr->ptr = dma;
+	sec4_sg_ptr->len = len;
+	sec4_sg_ptr->reserved = 0;
+	sec4_sg_ptr->buf_pool_id = 0;
+	sec4_sg_ptr->offset = offset;
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "sec4_sg_ptr@: ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, sec4_sg_ptr,
+		       sizeof(struct sec4_sg_entry), 1);
+#endif
+}
+
+/*
+ * convert scatterlist to h/w link table format
+ * but does not have final bit; instead, returns last entry
+ */
+static inline struct sec4_sg_entry *
+sg_to_sec4_sg(struct scatterlist *sg, int sg_count,
+	      struct sec4_sg_entry *sec4_sg_ptr, u32 offset)
+{
+	while (sg_count) {
+		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg),
+				   sg_dma_len(sg), offset);
+		sec4_sg_ptr++;
+		sg = scatterwalk_sg_next(sg);
+		sg_count--;
+	}
+	return sec4_sg_ptr - 1;
+}
+
+/*
+ * convert scatterlist to h/w link table format
+ * scatterlist must have been previously dma mapped
+ */
+static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
+				      struct sec4_sg_entry *sec4_sg_ptr,
+				      u32 offset)
+{
+	sec4_sg_ptr = sg_to_sec4_sg(sg, sg_count, sec4_sg_ptr, offset);
+	sec4_sg_ptr->len |= SEC4_SG_LEN_FIN;
+}
+
+/* count number of elements in scatterlist */
+static inline int __sg_count(struct scatterlist *sg_list, int nbytes,
+			     bool *chained)
+{
+	struct scatterlist *sg = sg_list;
+	int sg_nents = 0;
+
+	while (nbytes > 0) {
+		sg_nents++;
+		nbytes -= sg->length;
+		if (!sg_is_last(sg) && (sg + 1)->length == 0)
+			*chained = true;
+		sg = scatterwalk_sg_next(sg);
+	}
+
+	return sg_nents;
+}
+
+/* derive number of elements in scatterlist, but return 0 for 1 */
+static inline int sg_count(struct scatterlist *sg_list, int nbytes,
+			     bool *chained)
+{
+	int sg_nents = __sg_count(sg_list, nbytes, chained);
+
+	if (likely(sg_nents == 1))
+		return 0;
+
+	return sg_nents;
+}
+
+static int dma_map_sg_chained(struct device *dev, struct scatterlist *sg,
+			      unsigned int nents, enum dma_data_direction dir,
+			      bool chained)
+{
+	if (unlikely(chained)) {
+		int i;
+		for (i = 0; i < nents; i++) {
+			dma_map_sg(dev, sg, 1, dir);
+			sg = scatterwalk_sg_next(sg);
+		}
+	} else {
+		dma_map_sg(dev, sg, nents, dir);
+	}
+	return nents;
+}
+
+static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg,
+				unsigned int nents, enum dma_data_direction dir,
+				bool chained)
+{
+	if (unlikely(chained)) {
+		int i;
+		for (i = 0; i < nents; i++) {
+			dma_unmap_sg(dev, sg, 1, dir);
+			sg = scatterwalk_sg_next(sg);
+		}
+	} else {
+		dma_unmap_sg(dev, sg, nents, dir);
+	}
+	return nents;
+}
+
+/* Copy from len bytes of sg to dest, starting from beginning */
+static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len)
+{
+	struct scatterlist *current_sg = sg;
+	int cpy_index = 0, next_cpy_index = current_sg->length;
+
+	while (next_cpy_index < len) {
+		memcpy(dest + cpy_index, (u8 *) sg_virt(current_sg),
+		       current_sg->length);
+		current_sg = scatterwalk_sg_next(current_sg);
+		cpy_index = next_cpy_index;
+		next_cpy_index += current_sg->length;
+	}
+	if (cpy_index < len)
+		memcpy(dest + cpy_index, (u8 *) sg_virt(current_sg),
+		       len - cpy_index);
+}
+
+/* Copy sg data, from to_skip to end, to dest */
+static inline void sg_copy_part(u8 *dest, struct scatterlist *sg,
+				      int to_skip, unsigned int end)
+{
+	struct scatterlist *current_sg = sg;
+	int sg_index, cpy_index;
+
+	sg_index = current_sg->length;
+	while (sg_index <= to_skip) {
+		current_sg = scatterwalk_sg_next(current_sg);
+		sg_index += current_sg->length;
+	}
+	cpy_index = sg_index - to_skip;
+	memcpy(dest, (u8 *) sg_virt(current_sg) +
+	       current_sg->length - cpy_index, cpy_index);
+	current_sg = scatterwalk_sg_next(current_sg);
+	if (end - sg_index)
+		sg_copy(dest + cpy_index, current_sg, end - sg_index);
+}
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index 1cc6b3f..0d40717 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -24,6 +24,7 @@
 
 #define MV_CESA	"MV-CESA:"
 #define MAX_HW_HASH_SIZE	0xFFFF
+#define MV_CESA_EXPIRE		500 /* msec */
 
 /*
  * STM:
@@ -87,6 +88,7 @@ struct crypto_priv {
 	spinlock_t lock;
 	struct crypto_queue queue;
 	enum engine_status eng_st;
+	struct timer_list completion_timer;
 	struct crypto_async_request *cur_req;
 	struct req_progress p;
 	int max_req_size;
@@ -138,6 +140,29 @@ struct mv_req_hash_ctx {
 	int count_add;
 };
 
+static void mv_completion_timer_callback(unsigned long unused)
+{
+	int active = readl(cpg->reg + SEC_ACCEL_CMD) & SEC_CMD_EN_SEC_ACCL0;
+
+	printk(KERN_ERR MV_CESA
+	       "completion timer expired (CESA %sactive), cleaning up.\n",
+	       active ? "" : "in");
+
+	del_timer(&cpg->completion_timer);
+	writel(SEC_CMD_DISABLE_SEC, cpg->reg + SEC_ACCEL_CMD);
+	while(readl(cpg->reg + SEC_ACCEL_CMD) & SEC_CMD_DISABLE_SEC)
+		printk(KERN_INFO MV_CESA "%s: waiting for engine finishing\n", __func__);
+	cpg->eng_st = ENGINE_W_DEQUEUE;
+	wake_up_process(cpg->queue_th);
+}
+
+static void mv_setup_timer(void)
+{
+	setup_timer(&cpg->completion_timer, &mv_completion_timer_callback, 0);
+	mod_timer(&cpg->completion_timer,
+			jiffies + msecs_to_jiffies(MV_CESA_EXPIRE));
+}
+
 static void compute_aes_dec_key(struct mv_ctx *ctx)
 {
 	struct crypto_aes_ctx gen_aes_key;
@@ -273,12 +298,8 @@ static void mv_process_current_q(int first_block)
 			sizeof(struct sec_accel_config));
 
 	/* GO */
+	mv_setup_timer();
 	writel(SEC_CMD_EN_SEC_ACCL0, cpg->reg + SEC_ACCEL_CMD);
-
-	/*
-	 * XXX: add timer if the interrupt does not occur for some mystery
-	 * reason
-	 */
 }
 
 static void mv_crypto_algo_completion(void)
@@ -357,12 +378,8 @@ static void mv_process_hash_current(int first_block)
 	memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config));
 
 	/* GO */
+	mv_setup_timer();
 	writel(SEC_CMD_EN_SEC_ACCL0, cpg->reg + SEC_ACCEL_CMD);
-
-	/*
-	* XXX: add timer if the interrupt does not occur for some mystery
-	* reason
-	*/
 }
 
 static inline int mv_hash_import_sha1_ctx(const struct mv_req_hash_ctx *ctx,
@@ -406,6 +423,15 @@ out:
 	return rc;
 }
 
+static void mv_save_digest_state(struct mv_req_hash_ctx *ctx)
+{
+	ctx->state[0] = readl(cpg->reg + DIGEST_INITIAL_VAL_A);
+	ctx->state[1] = readl(cpg->reg + DIGEST_INITIAL_VAL_B);
+	ctx->state[2] = readl(cpg->reg + DIGEST_INITIAL_VAL_C);
+	ctx->state[3] = readl(cpg->reg + DIGEST_INITIAL_VAL_D);
+	ctx->state[4] = readl(cpg->reg + DIGEST_INITIAL_VAL_E);
+}
+
 static void mv_hash_algo_completion(void)
 {
 	struct ahash_request *req = ahash_request_cast(cpg->cur_req);
@@ -420,14 +446,12 @@ static void mv_hash_algo_completion(void)
 			memcpy(req->result, cpg->sram + SRAM_DIGEST_BUF,
 			       crypto_ahash_digestsize(crypto_ahash_reqtfm
 						       (req)));
-		} else
+		} else {
+			mv_save_digest_state(ctx);
 			mv_hash_final_fallback(req);
+		}
 	} else {
-		ctx->state[0] = readl(cpg->reg + DIGEST_INITIAL_VAL_A);
-		ctx->state[1] = readl(cpg->reg + DIGEST_INITIAL_VAL_B);
-		ctx->state[2] = readl(cpg->reg + DIGEST_INITIAL_VAL_C);
-		ctx->state[3] = readl(cpg->reg + DIGEST_INITIAL_VAL_D);
-		ctx->state[4] = readl(cpg->reg + DIGEST_INITIAL_VAL_E);
+		mv_save_digest_state(ctx);
 	}
 }
 
@@ -888,6 +912,10 @@ irqreturn_t crypto_int(int irq, void *priv)
 	if (!(val & SEC_INT_ACCEL0_DONE))
 		return IRQ_NONE;
 
+	if (!del_timer(&cpg->completion_timer)) {
+		printk(KERN_WARNING MV_CESA
+		       "got an interrupt but no pending timer?\n");
+	}
 	val &= ~SEC_INT_ACCEL0_DONE;
 	writel(val, cpg->reg + FPGA_INT_STATUS);
 	writel(val, cpg->reg + SEC_ACCEL_INT_STATUS);
@@ -1061,6 +1089,7 @@ static int mv_probe(struct platform_device *pdev)
 	if (!IS_ERR(cp->clk))
 		clk_prepare_enable(cp->clk);
 
+	writel(0, cpg->reg + SEC_ACCEL_INT_STATUS);
 	writel(SEC_INT_ACCEL0_DONE, cpg->reg + SEC_ACCEL_INT_MASK);
 	writel(SEC_CFG_STOP_DIG_ERR, cpg->reg + SEC_ACCEL_CFG);
 	writel(SRAM_CONFIG, cpg->reg + SEC_ACCEL_DESC_P0);
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 921039e..efff788 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -53,117 +53,6 @@
 
 #include "talitos.h"
 
-#define TALITOS_TIMEOUT 100000
-#define TALITOS_MAX_DATA_LEN 65535
-
-#define DESC_TYPE(desc_hdr) ((be32_to_cpu(desc_hdr) >> 3) & 0x1f)
-#define PRIMARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 28) & 0xf)
-#define SECONDARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 16) & 0xf)
-
-/* descriptor pointer entry */
-struct talitos_ptr {
-	__be16 len;	/* length */
-	u8 j_extent;	/* jump to sg link table and/or extent */
-	u8 eptr;	/* extended address */
-	__be32 ptr;	/* address */
-};
-
-static const struct talitos_ptr zero_entry = {
-	.len = 0,
-	.j_extent = 0,
-	.eptr = 0,
-	.ptr = 0
-};
-
-/* descriptor */
-struct talitos_desc {
-	__be32 hdr;			/* header high bits */
-	__be32 hdr_lo;			/* header low bits */
-	struct talitos_ptr ptr[7];	/* ptr/len pair array */
-};
-
-/**
- * talitos_request - descriptor submission request
- * @desc: descriptor pointer (kernel virtual)
- * @dma_desc: descriptor's physical bus address
- * @callback: whom to call when descriptor processing is done
- * @context: caller context (optional)
- */
-struct talitos_request {
-	struct talitos_desc *desc;
-	dma_addr_t dma_desc;
-	void (*callback) (struct device *dev, struct talitos_desc *desc,
-	                  void *context, int error);
-	void *context;
-};
-
-/* per-channel fifo management */
-struct talitos_channel {
-	void __iomem *reg;
-
-	/* request fifo */
-	struct talitos_request *fifo;
-
-	/* number of requests pending in channel h/w fifo */
-	atomic_t submit_count ____cacheline_aligned;
-
-	/* request submission (head) lock */
-	spinlock_t head_lock ____cacheline_aligned;
-	/* index to next free descriptor request */
-	int head;
-
-	/* request release (tail) lock */
-	spinlock_t tail_lock ____cacheline_aligned;
-	/* index to next in-progress/done descriptor request */
-	int tail;
-};
-
-struct talitos_private {
-	struct device *dev;
-	struct platform_device *ofdev;
-	void __iomem *reg;
-	int irq[2];
-
-	/* SEC global registers lock  */
-	spinlock_t reg_lock ____cacheline_aligned;
-
-	/* SEC version geometry (from device tree node) */
-	unsigned int num_channels;
-	unsigned int chfifo_len;
-	unsigned int exec_units;
-	unsigned int desc_types;
-
-	/* SEC Compatibility info */
-	unsigned long features;
-
-	/*
-	 * length of the request fifo
-	 * fifo_len is chfifo_len rounded up to next power of 2
-	 * so we can use bitwise ops to wrap
-	 */
-	unsigned int fifo_len;
-
-	struct talitos_channel *chan;
-
-	/* next channel to be assigned next incoming descriptor */
-	atomic_t last_chan ____cacheline_aligned;
-
-	/* request callback tasklet */
-	struct tasklet_struct done_task[2];
-
-	/* list of registered algorithms */
-	struct list_head alg_list;
-
-	/* hwrng device */
-	struct hwrng rng;
-};
-
-/* .features flag */
-#define TALITOS_FTR_SRC_LINK_TBL_LEN_INCLUDES_EXTENT 0x00000001
-#define TALITOS_FTR_HW_AUTH_CHECK 0x00000002
-#define TALITOS_FTR_SHA224_HWINIT 0x00000004
-#define TALITOS_FTR_HMAC_OK 0x00000008
-
 static void to_talitos_ptr(struct talitos_ptr *talitos_ptr, dma_addr_t dma_addr)
 {
 	talitos_ptr->ptr = cpu_to_be32(lower_32_bits(dma_addr));
@@ -303,11 +192,11 @@ static int init_device(struct device *dev)
  * callback must check err and feedback in descriptor header
  * for device processing status.
  */
-static int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
-			  void (*callback)(struct device *dev,
-					   struct talitos_desc *desc,
-					   void *context, int error),
-			  void *context)
+int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
+		   void (*callback)(struct device *dev,
+				    struct talitos_desc *desc,
+				    void *context, int error),
+		   void *context)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	struct talitos_request *request;
@@ -348,6 +237,7 @@ static int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 
 	return -EINPROGRESS;
 }
+EXPORT_SYMBOL(talitos_submit);
 
 /*
  * process what was done, notify callback of error if not
@@ -733,7 +623,7 @@ static void talitos_unregister_rng(struct device *dev)
  * crypto alg
  */
 #define TALITOS_CRA_PRIORITY		3000
-#define TALITOS_MAX_KEY_SIZE		64
+#define TALITOS_MAX_KEY_SIZE		96
 #define TALITOS_MAX_IV_LENGTH		16 /* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 
 #define MD5_BLOCK_SIZE    64
@@ -2066,6 +1956,59 @@ static struct talitos_alg_template driver_algs[] = {
 		                     DESC_HDR_MODE1_MDEU_PAD |
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
+	{       .type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha224),cbc(aes))",
+			.cra_driver_name = "authenc-hmac-sha224-cbc-aes-talitos",
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = AES_BLOCK_SIZE,
+				.maxauthsize = SHA224_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha224),cbc(des3_ede))",
+			.cra_driver_name = "authenc-hmac-sha224-cbc-3des-talitos",
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = DES3_EDE_BLOCK_SIZE,
+				.maxauthsize = SHA224_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+			             DESC_HDR_SEL0_DEU |
+		                     DESC_HDR_MODE0_DEU_CBC |
+		                     DESC_HDR_MODE0_DEU_3DES |
+		                     DESC_HDR_SEL1_MDEUA |
+		                     DESC_HDR_MODE1_MDEU_INIT |
+		                     DESC_HDR_MODE1_MDEU_PAD |
+		                     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.crypto = {
 			.cra_name = "authenc(hmac(sha256),cbc(aes))",
@@ -2121,6 +2064,112 @@ static struct talitos_alg_template driver_algs[] = {
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha384),cbc(aes))",
+			.cra_driver_name = "authenc-hmac-sha384-cbc-aes-talitos",
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = AES_BLOCK_SIZE,
+				.maxauthsize = SHA384_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+			             DESC_HDR_SEL0_AESU |
+		                     DESC_HDR_MODE0_AESU_CBC |
+		                     DESC_HDR_SEL1_MDEUB |
+		                     DESC_HDR_MODE1_MDEU_INIT |
+		                     DESC_HDR_MODE1_MDEU_PAD |
+		                     DESC_HDR_MODE1_MDEUB_SHA384_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha384),cbc(des3_ede))",
+			.cra_driver_name = "authenc-hmac-sha384-cbc-3des-talitos",
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = DES3_EDE_BLOCK_SIZE,
+				.maxauthsize = SHA384_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+			             DESC_HDR_SEL0_DEU |
+		                     DESC_HDR_MODE0_DEU_CBC |
+		                     DESC_HDR_MODE0_DEU_3DES |
+		                     DESC_HDR_SEL1_MDEUB |
+		                     DESC_HDR_MODE1_MDEU_INIT |
+		                     DESC_HDR_MODE1_MDEU_PAD |
+		                     DESC_HDR_MODE1_MDEUB_SHA384_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha512),cbc(aes))",
+			.cra_driver_name = "authenc-hmac-sha512-cbc-aes-talitos",
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = AES_BLOCK_SIZE,
+				.maxauthsize = SHA512_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+			             DESC_HDR_SEL0_AESU |
+		                     DESC_HDR_MODE0_AESU_CBC |
+		                     DESC_HDR_SEL1_MDEUB |
+		                     DESC_HDR_MODE1_MDEU_INIT |
+		                     DESC_HDR_MODE1_MDEU_PAD |
+		                     DESC_HDR_MODE1_MDEUB_SHA512_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
+			.cra_name = "authenc(hmac(sha512),cbc(des3_ede))",
+			.cra_driver_name = "authenc-hmac-sha512-cbc-3des-talitos",
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+			.cra_type = &crypto_aead_type,
+			.cra_aead = {
+				.setkey = aead_setkey,
+				.setauthsize = aead_setauthsize,
+				.encrypt = aead_encrypt,
+				.decrypt = aead_decrypt,
+				.givencrypt = aead_givencrypt,
+				.geniv = "<built-in>",
+				.ivsize = DES3_EDE_BLOCK_SIZE,
+				.maxauthsize = SHA512_DIGEST_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
+			             DESC_HDR_SEL0_DEU |
+		                     DESC_HDR_MODE0_DEU_CBC |
+		                     DESC_HDR_MODE0_DEU_3DES |
+		                     DESC_HDR_SEL1_MDEUB |
+		                     DESC_HDR_MODE1_MDEU_INIT |
+		                     DESC_HDR_MODE1_MDEU_PAD |
+		                     DESC_HDR_MODE1_MDEUB_SHA512_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.alg.crypto = {
 			.cra_name = "authenc(hmac(md5),cbc(aes))",
 			.cra_driver_name = "authenc-hmac-md5-cbc-aes-talitos",
 			.cra_blocksize = AES_BLOCK_SIZE,
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 3c17395..61a1405 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -28,6 +28,123 @@
  *
  */
 
+#define TALITOS_TIMEOUT 100000
+#define TALITOS_MAX_DATA_LEN 65535
+
+#define DESC_TYPE(desc_hdr) ((be32_to_cpu(desc_hdr) >> 3) & 0x1f)
+#define PRIMARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 28) & 0xf)
+#define SECONDARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 16) & 0xf)
+
+/* descriptor pointer entry */
+struct talitos_ptr {
+	__be16 len;     /* length */
+	u8 j_extent;    /* jump to sg link table and/or extent */
+	u8 eptr;        /* extended address */
+	__be32 ptr;     /* address */
+};
+
+static const struct talitos_ptr zero_entry = {
+	.len = 0,
+	.j_extent = 0,
+	.eptr = 0,
+	.ptr = 0
+};
+
+/* descriptor */
+struct talitos_desc {
+	__be32 hdr;                     /* header high bits */
+	__be32 hdr_lo;                  /* header low bits */
+	struct talitos_ptr ptr[7];      /* ptr/len pair array */
+};
+
+/**
+ * talitos_request - descriptor submission request
+ * @desc: descriptor pointer (kernel virtual)
+ * @dma_desc: descriptor's physical bus address
+ * @callback: whom to call when descriptor processing is done
+ * @context: caller context (optional)
+ */
+struct talitos_request {
+	struct talitos_desc *desc;
+	dma_addr_t dma_desc;
+	void (*callback) (struct device *dev, struct talitos_desc *desc,
+			  void *context, int error);
+	void *context;
+};
+
+/* per-channel fifo management */
+struct talitos_channel {
+	void __iomem *reg;
+
+	/* request fifo */
+	struct talitos_request *fifo;
+
+	/* number of requests pending in channel h/w fifo */
+	atomic_t submit_count ____cacheline_aligned;
+
+	/* request submission (head) lock */
+	spinlock_t head_lock ____cacheline_aligned;
+	/* index to next free descriptor request */
+	int head;
+
+	/* request release (tail) lock */
+	spinlock_t tail_lock ____cacheline_aligned;
+	/* index to next in-progress/done descriptor request */
+	int tail;
+};
+
+struct talitos_private {
+	struct device *dev;
+	struct platform_device *ofdev;
+	void __iomem *reg;
+	int irq[2];
+
+	/* SEC global registers lock  */
+	spinlock_t reg_lock ____cacheline_aligned;
+
+	/* SEC version geometry (from device tree node) */
+	unsigned int num_channels;
+	unsigned int chfifo_len;
+	unsigned int exec_units;
+	unsigned int desc_types;
+
+	/* SEC Compatibility info */
+	unsigned long features;
+
+	/*
+	 * length of the request fifo
+	 * fifo_len is chfifo_len rounded up to next power of 2
+	 * so we can use bitwise ops to wrap
+	 */
+	unsigned int fifo_len;
+
+	struct talitos_channel *chan;
+
+	/* next channel to be assigned next incoming descriptor */
+	atomic_t last_chan ____cacheline_aligned;
+
+	/* request callback tasklet */
+	struct tasklet_struct done_task[2];
+
+	/* list of registered algorithms */
+	struct list_head alg_list;
+
+	/* hwrng device */
+	struct hwrng rng;
+};
+
+extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
+			  void (*callback)(struct device *dev,
+					   struct talitos_desc *desc,
+					   void *context, int error),
+			  void *context);
+
+/* .features flag */
+#define TALITOS_FTR_SRC_LINK_TBL_LEN_INCLUDES_EXTENT 0x00000001
+#define TALITOS_FTR_HW_AUTH_CHECK 0x00000002
+#define TALITOS_FTR_SHA224_HWINIT 0x00000004
+#define TALITOS_FTR_HMAC_OK 0x00000008
+
 /*
  * TALITOS_xxx_LO addresses point to the low data bits (32-63) of the register
  */
@@ -209,6 +326,12 @@
 					 DESC_HDR_MODE1_MDEU_HMAC)
 #define	DESC_HDR_MODE1_MDEU_SHA1_HMAC	(DESC_HDR_MODE1_MDEU_SHA1 | \
 					 DESC_HDR_MODE1_MDEU_HMAC)
+#define DESC_HDR_MODE1_MDEU_SHA224_HMAC	(DESC_HDR_MODE1_MDEU_SHA224 | \
+					 DESC_HDR_MODE1_MDEU_HMAC)
+#define DESC_HDR_MODE1_MDEUB_SHA384_HMAC	(DESC_HDR_MODE1_MDEUB_SHA384 | \
+						 DESC_HDR_MODE1_MDEU_HMAC)
+#define DESC_HDR_MODE1_MDEUB_SHA512_HMAC	(DESC_HDR_MODE1_MDEUB_SHA512 | \
+						 DESC_HDR_MODE1_MDEU_HMAC)
 
 /* direction of overall data flow (DIR) */
 #define	DESC_HDR_DIR_INBOUND		cpu_to_be32(0x00000002)