Linux-libre 4.6.2-gnu

41 files changed, 1847 insertions, 1055 deletions

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 07d494276..477fffdb4 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -296,6 +296,7 @@ config CRYPTO_DEV_OMAP_AES
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_ENGINE
 	help
 	  OMAP processors have AES module accelerator. Select this if you
 	  want to use the OMAP module for AES algorithms.
@@ -487,7 +488,7 @@ config CRYPTO_DEV_IMGTEC_HASH
 
 config CRYPTO_DEV_SUN4I_SS
 	tristate "Support for Allwinner Security System cryptographic accelerator"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI && !64BIT
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_AES
@@ -507,6 +508,10 @@ config CRYPTO_DEV_ROCKCHIP
 	depends on OF && ARCH_ROCKCHIP
 	select CRYPTO_AES
 	select CRYPTO_DES
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
 
 	help
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index 7de007abe..e3d40a8df 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -369,12 +369,6 @@ static inline size_t atmel_aes_padlen(size_t len, size_t block_size)
 	return len ? block_size - len : 0;
 }
 
-static inline struct aead_request *
-aead_request_cast(struct crypto_async_request *req)
-{
-	return container_of(req, struct aead_request, base);
-}
-
 static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_base_ctx *ctx)
 {
 	struct atmel_aes_dev *aes_dd = NULL;
diff --git a/drivers/crypto/atmel-sha-regs.h b/drivers/crypto/atmel-sha-regs.h
index 83b2d7425..e08897109 100644
--- a/drivers/crypto/atmel-sha-regs.h
+++ b/drivers/crypto/atmel-sha-regs.h
@@ -8,6 +8,8 @@
 #define SHA_CR_START			(1 << 0)
 #define SHA_CR_FIRST			(1 << 4)
 #define SHA_CR_SWRST			(1 << 8)
+#define SHA_CR_WUIHV			(1 << 12)
+#define SHA_CR_WUIEHV			(1 << 13)
 
 #define SHA_MR				0x04
 #define SHA_MR_MODE_MASK		(0x3 << 0)
@@ -15,6 +17,8 @@
 #define SHA_MR_MODE_AUTO		0x1
 #define SHA_MR_MODE_PDC			0x2
 #define SHA_MR_PROCDLY			(1 << 4)
+#define SHA_MR_UIHV			(1 << 5)
+#define SHA_MR_UIEHV			(1 << 6)
 #define SHA_MR_ALGO_SHA1		(0 << 8)
 #define SHA_MR_ALGO_SHA256		(1 << 8)
 #define SHA_MR_ALGO_SHA384		(2 << 8)
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 68d47a2da..97e34799e 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -53,6 +53,7 @@
 
 #define SHA_FLAGS_FINUP		BIT(16)
 #define SHA_FLAGS_SG		BIT(17)
+#define SHA_FLAGS_ALGO_MASK	GENMASK(22, 18)
 #define SHA_FLAGS_SHA1		BIT(18)
 #define SHA_FLAGS_SHA224	BIT(19)
 #define SHA_FLAGS_SHA256	BIT(20)
@@ -60,11 +61,12 @@
 #define SHA_FLAGS_SHA512	BIT(22)
 #define SHA_FLAGS_ERROR		BIT(23)
 #define SHA_FLAGS_PAD		BIT(24)
+#define SHA_FLAGS_RESTORE	BIT(25)
 
 #define SHA_OP_UPDATE	1
 #define SHA_OP_FINAL	2
 
-#define SHA_BUFFER_LEN		PAGE_SIZE
+#define SHA_BUFFER_LEN		(PAGE_SIZE / 16)
 
 #define ATMEL_SHA_DMA_THRESHOLD		56
 
@@ -73,10 +75,15 @@ struct atmel_sha_caps {
 	bool	has_dualbuff;
 	bool	has_sha224;
 	bool	has_sha_384_512;
+	bool	has_uihv;
 };
 
 struct atmel_sha_dev;
 
+/*
+ * .statesize = sizeof(struct atmel_sha_reqctx) must be <= PAGE_SIZE / 8 as
+ * tested by the ahash_prepare_alg() function.
+ */
 struct atmel_sha_reqctx {
 	struct atmel_sha_dev	*dd;
 	unsigned long	flags;
@@ -95,7 +102,7 @@ struct atmel_sha_reqctx {
 
 	size_t block_size;
 
-	u8	buffer[0] __aligned(sizeof(u32));
+	u8 buffer[SHA_BUFFER_LEN + SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
 struct atmel_sha_ctx {
@@ -122,6 +129,7 @@ struct atmel_sha_dev {
 	spinlock_t		lock;
 	int			err;
 	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
 
 	unsigned long		flags;
 	struct crypto_queue	queue;
@@ -317,7 +325,8 @@ static int atmel_sha_init(struct ahash_request *req)
 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;
+	u32 valmr = SHA_MR_MODE_AUTO;
+	unsigned int i, hashsize = 0;
 
 	if (likely(dma)) {
 		if (!dd->caps.has_dma)
@@ -329,22 +338,62 @@ static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma)
 		atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY);
 	}
 
-	if (ctx->flags & SHA_FLAGS_SHA1)
+	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+	case SHA_FLAGS_SHA1:
 		valmr |= SHA_MR_ALGO_SHA1;
-	else if (ctx->flags & SHA_FLAGS_SHA224)
+		hashsize = SHA1_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA224:
 		valmr |= SHA_MR_ALGO_SHA224;
-	else if (ctx->flags & SHA_FLAGS_SHA256)
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA256:
 		valmr |= SHA_MR_ALGO_SHA256;
-	else if (ctx->flags & SHA_FLAGS_SHA384)
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA384:
 		valmr |= SHA_MR_ALGO_SHA384;
-	else if (ctx->flags & SHA_FLAGS_SHA512)
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA512:
 		valmr |= SHA_MR_ALGO_SHA512;
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	default:
+		break;
+	}
 
 	/* Setting CR_FIRST only for the first iteration */
-	if (!(ctx->digcnt[0] || ctx->digcnt[1]))
-		valcr = SHA_CR_FIRST;
+	if (!(ctx->digcnt[0] || ctx->digcnt[1])) {
+		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
+	} else if (dd->caps.has_uihv && (ctx->flags & SHA_FLAGS_RESTORE)) {
+		const u32 *hash = (const u32 *)ctx->digest;
+
+		/*
+		 * Restore the hardware context: update the User Initialize
+		 * Hash Value (UIHV) with the value saved when the latest
+		 * 'update' operation completed on this very same crypto
+		 * request.
+		 */
+		ctx->flags &= ~SHA_FLAGS_RESTORE;
+		atmel_sha_write(dd, SHA_CR, SHA_CR_WUIHV);
+		for (i = 0; i < hashsize / sizeof(u32); ++i)
+			atmel_sha_write(dd, SHA_REG_DIN(i), hash[i]);
+		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
+		valmr |= SHA_MR_UIHV;
+	}
+	/*
+	 * WARNING: If the UIHV feature is not available, the hardware CANNOT
+	 * process concurrent requests: the internal registers used to store
+	 * the hash/digest are still set to the partial digest output values
+	 * computed during the latest round.
+	 */
 
-	atmel_sha_write(dd, SHA_CR, valcr);
 	atmel_sha_write(dd, SHA_MR, valmr);
 }
 
@@ -713,23 +762,31 @@ 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;
+	unsigned int i, hashsize;
 
-	if (ctx->flags & SHA_FLAGS_SHA1)
-		for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA224)
-		for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA256)
-		for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA384)
-		for (i = 0; i < SHA384_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else
-		for (i = 0; i < SHA512_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
+	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+	case SHA_FLAGS_SHA1:
+		hashsize = SHA1_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA224:
+	case SHA_FLAGS_SHA256:
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA384:
+	case SHA_FLAGS_SHA512:
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	default:
+		/* Should not happen... */
+		return;
+	}
+
+	for (i = 0; i < hashsize / sizeof(u32); ++i)
+		hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
+	ctx->flags |= SHA_FLAGS_RESTORE;
 }
 
 static void atmel_sha_copy_ready_hash(struct ahash_request *req)
@@ -788,7 +845,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err)
 		req->base.complete(&req->base, err);
 
 	/* handle new request */
-	tasklet_schedule(&dd->done_task);
+	tasklet_schedule(&dd->queue_task);
 }
 
 static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
@@ -922,36 +979,17 @@ static int atmel_sha_update(struct ahash_request *req)
 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 {
+	if (ctx->flags & SHA_FLAGS_PAD)
 		/* 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;
+	return atmel_sha_enqueue(req, SHA_OP_FINAL);
 }
 
 static int atmel_sha_finup(struct ahash_request *req)
@@ -979,11 +1017,27 @@ static int atmel_sha_digest(struct ahash_request *req)
 	return atmel_sha_init(req) ?: atmel_sha_finup(req);
 }
 
+
+static int atmel_sha_export(struct ahash_request *req, void *out)
+{
+	const struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	memcpy(out, ctx, sizeof(*ctx));
+	return 0;
+}
+
+static int atmel_sha_import(struct ahash_request *req, const void *in)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	memcpy(ctx, in, sizeof(*ctx));
+	return 0;
+}
+
 static int atmel_sha_cra_init(struct crypto_tfm *tfm)
 {
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct atmel_sha_reqctx) +
-				 SHA_BUFFER_LEN + SHA512_BLOCK_SIZE);
+				 sizeof(struct atmel_sha_reqctx));
 
 	return 0;
 }
@@ -995,8 +1049,11 @@ static struct ahash_alg sha_1_256_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA1_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha1",
 			.cra_driver_name	= "atmel-sha1",
@@ -1016,8 +1073,11 @@ static struct ahash_alg sha_1_256_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA256_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha256",
 			.cra_driver_name	= "atmel-sha256",
@@ -1039,8 +1099,11 @@ static struct ahash_alg sha_224_alg = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA224_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha224",
 			.cra_driver_name	= "atmel-sha224",
@@ -1062,8 +1125,11 @@ static struct ahash_alg sha_384_512_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA384_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha384",
 			.cra_driver_name	= "atmel-sha384",
@@ -1083,8 +1149,11 @@ static struct ahash_alg sha_384_512_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA512_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha512",
 			.cra_driver_name	= "atmel-sha512",
@@ -1100,16 +1169,18 @@ static struct ahash_alg sha_384_512_algs[] = {
 },
 };
 
+static void atmel_sha_queue_task(unsigned long data)
+{
+	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;
+
+	atmel_sha_handle_queue(dd, NULL);
+}
+
 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;
@@ -1272,14 +1343,23 @@ static void atmel_sha_get_cap(struct atmel_sha_dev *dd)
 	dd->caps.has_dualbuff = 0;
 	dd->caps.has_sha224 = 0;
 	dd->caps.has_sha_384_512 = 0;
+	dd->caps.has_uihv = 0;
 
 	/* keep only major version number */
 	switch (dd->hw_version & 0xff0) {
+	case 0x510:
+		dd->caps.has_dma = 1;
+		dd->caps.has_dualbuff = 1;
+		dd->caps.has_sha224 = 1;
+		dd->caps.has_sha_384_512 = 1;
+		dd->caps.has_uihv = 1;
+		break;
 	case 0x420:
 		dd->caps.has_dma = 1;
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_sha224 = 1;
 		dd->caps.has_sha_384_512 = 1;
+		dd->caps.has_uihv = 1;
 		break;
 	case 0x410:
 		dd->caps.has_dma = 1;
@@ -1366,6 +1446,8 @@ static int atmel_sha_probe(struct platform_device *pdev)
 
 	tasklet_init(&sha_dd->done_task, atmel_sha_done_task,
 					(unsigned long)sha_dd);
+	tasklet_init(&sha_dd->queue_task, atmel_sha_queue_task,
+					(unsigned long)sha_dd);
 
 	crypto_init_queue(&sha_dd->queue, ATMEL_SHA_QUEUE_LENGTH);
 
@@ -1464,6 +1546,7 @@ err_sha_dma:
 iclk_unprepare:
 	clk_unprepare(sha_dd->iclk);
 res_err:
+	tasklet_kill(&sha_dd->queue_task);
 	tasklet_kill(&sha_dd->done_task);
 sha_dd_err:
 	dev_err(dev, "initialization failed.\n");
@@ -1484,6 +1567,7 @@ static int atmel_sha_remove(struct platform_device *pdev)
 
 	atmel_sha_unregister_algs(sha_dd);
 
+	tasklet_kill(&sha_dd->queue_task);
 	tasklet_kill(&sha_dd->done_task);
 
 	if (sha_dd->caps.has_dma)
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 69d4a1326..44d30b45f 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -534,7 +534,7 @@ static int caam_probe(struct platform_device *pdev)
 	 * long pointers in master configuration register
 	 */
 	clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH |
-		      MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE |
+		      MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | MCFGR_LARGE_BURST |
 		      (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
 
 	/*
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index f7e0d8d4c..5ef4be22e 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -65,7 +65,7 @@ static int caam_reset_hw_jr(struct device *dev)
 /*
  * Shutdown JobR independent of platform property code
  */
-int caam_jr_shutdown(struct device *dev)
+static int caam_jr_shutdown(struct device *dev)
 {
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	dma_addr_t inpbusaddr, outbusaddr;
@@ -248,7 +248,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 struct device *caam_jr_alloc(void)
 {
 	struct caam_drv_private_jr *jrpriv, *min_jrpriv = NULL;
-	struct device *dev = NULL;
+	struct device *dev = ERR_PTR(-ENODEV);
 	int min_tfm_cnt	= INT_MAX;
 	int tfm_cnt;
 
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index a8a799756..0ba9c4059 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -455,7 +455,8 @@ struct caam_ctrl {
 #define MCFGR_AXIPIPE_MASK	(0xf << MCFGR_AXIPIPE_SHIFT)
 
 #define MCFGR_AXIPRI		0x00000008 /* Assert AXI priority sideband */
-#define MCFGR_BURST_64		0x00000001 /* Max burst size */
+#define MCFGR_LARGE_BURST	0x00000004 /* 128/256-byte burst size */
+#define MCFGR_BURST_64		0x00000001 /* 64-byte burst size */
 
 /* JRSTART register offsets */
 #define JRSTART_JR0_START       0x00000001 /* Start Job ring 0 */
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
index 55a1f3951..b750592cc 100644
--- a/drivers/crypto/ccp/Makefile
+++ b/drivers/crypto/ccp/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_CRYPTO_DEV_CCP_DD) += ccp.o
-ccp-objs := ccp-dev.o ccp-ops.o ccp-platform.o
+ccp-objs := ccp-dev.o ccp-ops.o ccp-dev-v3.o ccp-platform.o
 ccp-$(CONFIG_PCI) += ccp-pci.o
 
 obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o
diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c
index 7984f9108..89291c150 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) AES crypto API support
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -259,6 +259,7 @@ static struct crypto_alg ccp_aes_rfc3686_defaults = {
 
 struct ccp_aes_def {
 	enum ccp_aes_mode mode;
+	unsigned int version;
 	const char *name;
 	const char *driver_name;
 	unsigned int blocksize;
@@ -269,6 +270,7 @@ struct ccp_aes_def {
 static struct ccp_aes_def aes_algs[] = {
 	{
 		.mode		= CCP_AES_MODE_ECB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ecb(aes)",
 		.driver_name	= "ecb-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -277,6 +279,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CBC,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "cbc(aes)",
 		.driver_name	= "cbc-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -285,6 +288,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CFB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "cfb(aes)",
 		.driver_name	= "cfb-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -293,6 +297,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_OFB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ofb(aes)",
 		.driver_name	= "ofb-aes-ccp",
 		.blocksize	= 1,
@@ -301,6 +306,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CTR,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ctr(aes)",
 		.driver_name	= "ctr-aes-ccp",
 		.blocksize	= 1,
@@ -309,6 +315,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CTR,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "rfc3686(ctr(aes))",
 		.driver_name	= "rfc3686-ctr-aes-ccp",
 		.blocksize	= 1,
@@ -357,8 +364,11 @@ static int ccp_register_aes_alg(struct list_head *head,
 int ccp_register_aes_algs(struct list_head *head)
 {
 	int i, ret;
+	unsigned int ccpversion = ccp_version();
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (aes_algs[i].version > ccpversion)
+			continue;
 		ret = ccp_register_aes_alg(head, &aes_algs[i]);
 		if (ret)
 			return ret;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index ab9945f2c..8f36af62f 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) SHA crypto API support
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -344,6 +344,7 @@ static void ccp_hmac_sha_cra_exit(struct crypto_tfm *tfm)
 }
 
 struct ccp_sha_def {
+	unsigned int version;
 	const char *name;
 	const char *drv_name;
 	enum ccp_sha_type type;
@@ -353,6 +354,7 @@ struct ccp_sha_def {
 
 static struct ccp_sha_def sha_algs[] = {
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha1",
 		.drv_name	= "sha1-ccp",
 		.type		= CCP_SHA_TYPE_1,
@@ -360,6 +362,7 @@ static struct ccp_sha_def sha_algs[] = {
 		.block_size	= SHA1_BLOCK_SIZE,
 	},
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha224",
 		.drv_name	= "sha224-ccp",
 		.type		= CCP_SHA_TYPE_224,
@@ -367,6 +370,7 @@ static struct ccp_sha_def sha_algs[] = {
 		.block_size	= SHA224_BLOCK_SIZE,
 	},
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha256",
 		.drv_name	= "sha256-ccp",
 		.type		= CCP_SHA_TYPE_256,
@@ -483,8 +487,11 @@ static int ccp_register_sha_alg(struct list_head *head,
 int ccp_register_sha_algs(struct list_head *head)
 {
 	int i, ret;
+	unsigned int ccpversion = ccp_version();
 
 	for (i = 0; i < ARRAY_SIZE(sha_algs); i++) {
+		if (sha_algs[i].version > ccpversion)
+			continue;
 		ret = ccp_register_sha_alg(head, &sha_algs[i]);
 		if (ret)
 			return ret;
diff --git a/drivers/crypto/ccp/ccp-dev-v3.c b/drivers/crypto/ccp/ccp-dev-v3.c
new file mode 100644
index 000000000..7d5eab491
--- /dev/null
+++ b/drivers/crypto/ccp/ccp-dev-v3.c
@@ -0,0 +1,533 @@
+/*
+ * AMD Cryptographic Coprocessor (CCP) driver
+ *
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.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.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/interrupt.h>
+#include <linux/ccp.h>
+
+#include "ccp-dev.h"
+
+static int ccp_do_cmd(struct ccp_op *op, u32 *cr, unsigned int cr_count)
+{
+	struct ccp_cmd_queue *cmd_q = op->cmd_q;
+	struct ccp_device *ccp = cmd_q->ccp;
+	void __iomem *cr_addr;
+	u32 cr0, cmd;
+	unsigned int i;
+	int ret = 0;
+
+	/* We could read a status register to see how many free slots
+	 * are actually available, but reading that register resets it
+	 * and you could lose some error information.
+	 */
+	cmd_q->free_slots--;
+
+	cr0 = (cmd_q->id << REQ0_CMD_Q_SHIFT)
+	      | (op->jobid << REQ0_JOBID_SHIFT)
+	      | REQ0_WAIT_FOR_WRITE;
+
+	if (op->soc)
+		cr0 |= REQ0_STOP_ON_COMPLETE
+		       | REQ0_INT_ON_COMPLETE;
+
+	if (op->ioc || !cmd_q->free_slots)
+		cr0 |= REQ0_INT_ON_COMPLETE;
+
+	/* Start at CMD_REQ1 */
+	cr_addr = ccp->io_regs + CMD_REQ0 + CMD_REQ_INCR;
+
+	mutex_lock(&ccp->req_mutex);
+
+	/* Write CMD_REQ1 through CMD_REQx first */
+	for (i = 0; i < cr_count; i++, cr_addr += CMD_REQ_INCR)
+		iowrite32(*(cr + i), cr_addr);
+
+	/* Tell the CCP to start */
+	wmb();
+	iowrite32(cr0, ccp->io_regs + CMD_REQ0);
+
+	mutex_unlock(&ccp->req_mutex);
+
+	if (cr0 & REQ0_INT_ON_COMPLETE) {
+		/* Wait for the job to complete */
+		ret = wait_event_interruptible(cmd_q->int_queue,
+					       cmd_q->int_rcvd);
+		if (ret || cmd_q->cmd_error) {
+			/* On error delete all related jobs from the queue */
+			cmd = (cmd_q->id << DEL_Q_ID_SHIFT)
+			      | op->jobid;
+
+			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
+
+			if (!ret)
+				ret = -EIO;
+		} else if (op->soc) {
+			/* Delete just head job from the queue on SoC */
+			cmd = DEL_Q_ACTIVE
+			      | (cmd_q->id << DEL_Q_ID_SHIFT)
+			      | op->jobid;
+
+			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
+		}
+
+		cmd_q->free_slots = CMD_Q_DEPTH(cmd_q->q_status);
+
+		cmd_q->int_rcvd = 0;
+	}
+
+	return ret;
+}
+
+static int ccp_perform_aes(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_AES << REQ1_ENGINE_SHIFT)
+		| (op->u.aes.type << REQ1_AES_TYPE_SHIFT)
+		| (op->u.aes.mode << REQ1_AES_MODE_SHIFT)
+		| (op->u.aes.action << REQ1_AES_ACTION_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	if (op->u.aes.mode == CCP_AES_MODE_CFB)
+		cr[0] |= ((0x7f) << REQ1_AES_CFB_SIZE_SHIFT);
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	if (op->init)
+		cr[0] |= REQ1_INIT;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_xts_aes(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_XTS_AES_128 << REQ1_ENGINE_SHIFT)
+		| (op->u.xts.action << REQ1_AES_ACTION_SHIFT)
+		| (op->u.xts.unit_size << REQ1_XTS_AES_SIZE_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	if (op->init)
+		cr[0] |= REQ1_INIT;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_sha(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_SHA << REQ1_ENGINE_SHIFT)
+		| (op->u.sha.type << REQ1_SHA_TYPE_SHIFT)
+		| REQ1_INIT;
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+
+	if (op->eom) {
+		cr[0] |= REQ1_EOM;
+		cr[4] = lower_32_bits(op->u.sha.msg_bits);
+		cr[5] = upper_32_bits(op->u.sha.msg_bits);
+	} else {
+		cr[4] = 0;
+		cr[5] = 0;
+	}
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_rsa(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_RSA << REQ1_ENGINE_SHIFT)
+		| (op->u.rsa.mod_size << REQ1_RSA_MOD_SIZE_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT)
+		| REQ1_EOM;
+	cr[1] = op->u.rsa.input_len - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_passthru(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_PASSTHRU << REQ1_ENGINE_SHIFT)
+		| (op->u.passthru.bit_mod << REQ1_PT_BW_SHIFT)
+		| (op->u.passthru.byte_swap << REQ1_PT_BS_SHIFT);
+
+	if (op->src.type == CCP_MEMTYPE_SYSTEM)
+		cr[1] = op->src.u.dma.length - 1;
+	else
+		cr[1] = op->dst.u.dma.length - 1;
+
+	if (op->src.type == CCP_MEMTYPE_SYSTEM) {
+		cr[2] = ccp_addr_lo(&op->src.u.dma);
+		cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+			| ccp_addr_hi(&op->src.u.dma);
+
+		if (op->u.passthru.bit_mod != CCP_PASSTHRU_BITWISE_NOOP)
+			cr[3] |= (op->ksb_key << REQ4_KSB_SHIFT);
+	} else {
+		cr[2] = op->src.u.ksb * CCP_KSB_BYTES;
+		cr[3] = (CCP_MEMTYPE_KSB << REQ4_MEMTYPE_SHIFT);
+	}
+
+	if (op->dst.type == CCP_MEMTYPE_SYSTEM) {
+		cr[4] = ccp_addr_lo(&op->dst.u.dma);
+		cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+			| ccp_addr_hi(&op->dst.u.dma);
+	} else {
+		cr[4] = op->dst.u.ksb * CCP_KSB_BYTES;
+		cr[5] = (CCP_MEMTYPE_KSB << REQ6_MEMTYPE_SHIFT);
+	}
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_ecc(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = REQ1_ECC_AFFINE_CONVERT
+		| (CCP_ENGINE_ECC << REQ1_ENGINE_SHIFT)
+		| (op->u.ecc.function << REQ1_ECC_FUNCTION_SHIFT)
+		| REQ1_EOM;
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct ccp_device *ccp = container_of(rng, struct ccp_device, hwrng);
+	u32 trng_value;
+	int len = min_t(int, sizeof(trng_value), max);
+
+	/*
+	 * Locking is provided by the caller so we can update device
+	 * hwrng-related fields safely
+	 */
+	trng_value = ioread32(ccp->io_regs + TRNG_OUT_REG);
+	if (!trng_value) {
+		/* Zero is returned if not data is available or if a
+		 * bad-entropy error is present. Assume an error if
+		 * we exceed TRNG_RETRIES reads of zero.
+		 */
+		if (ccp->hwrng_retries++ > TRNG_RETRIES)
+			return -EIO;
+
+		return 0;
+	}
+
+	/* Reset the counter and save the rng value */
+	ccp->hwrng_retries = 0;
+	memcpy(data, &trng_value, len);
+
+	return len;
+}
+
+static int ccp_init(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+	struct ccp_cmd_queue *cmd_q;
+	struct dma_pool *dma_pool;
+	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
+	unsigned int qmr, qim, i;
+	int ret;
+
+	/* Find available queues */
+	qim = 0;
+	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
+	for (i = 0; i < MAX_HW_QUEUES; i++) {
+		if (!(qmr & (1 << i)))
+			continue;
+
+		/* Allocate a dma pool for this queue */
+		snprintf(dma_pool_name, sizeof(dma_pool_name), "%s_q%d",
+			 ccp->name, i);
+		dma_pool = dma_pool_create(dma_pool_name, dev,
+					   CCP_DMAPOOL_MAX_SIZE,
+					   CCP_DMAPOOL_ALIGN, 0);
+		if (!dma_pool) {
+			dev_err(dev, "unable to allocate dma pool\n");
+			ret = -ENOMEM;
+			goto e_pool;
+		}
+
+		cmd_q = &ccp->cmd_q[ccp->cmd_q_count];
+		ccp->cmd_q_count++;
+
+		cmd_q->ccp = ccp;
+		cmd_q->id = i;
+		cmd_q->dma_pool = dma_pool;
+
+		/* Reserve 2 KSB regions for the queue */
+		cmd_q->ksb_key = KSB_START + ccp->ksb_start++;
+		cmd_q->ksb_ctx = KSB_START + ccp->ksb_start++;
+		ccp->ksb_count -= 2;
+
+		/* Preset some register values and masks that are queue
+		 * number dependent
+		 */
+		cmd_q->reg_status = ccp->io_regs + CMD_Q_STATUS_BASE +
+				    (CMD_Q_STATUS_INCR * i);
+		cmd_q->reg_int_status = ccp->io_regs + CMD_Q_INT_STATUS_BASE +
+					(CMD_Q_STATUS_INCR * i);
+		cmd_q->int_ok = 1 << (i * 2);
+		cmd_q->int_err = 1 << ((i * 2) + 1);
+
+		cmd_q->free_slots = CMD_Q_DEPTH(ioread32(cmd_q->reg_status));
+
+		init_waitqueue_head(&cmd_q->int_queue);
+
+		/* Build queue interrupt mask (two interrupts per queue) */
+		qim |= cmd_q->int_ok | cmd_q->int_err;
+
+#ifdef CONFIG_ARM64
+		/* For arm64 set the recommended queue cache settings */
+		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
+			  (CMD_Q_CACHE_INC * i));
+#endif
+
+		dev_dbg(dev, "queue #%u available\n", i);
+	}
+	if (ccp->cmd_q_count == 0) {
+		dev_notice(dev, "no command queues available\n");
+		ret = -EIO;
+		goto e_pool;
+	}
+	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
+
+	/* Disable and clear interrupts until ready */
+	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		ioread32(cmd_q->reg_int_status);
+		ioread32(cmd_q->reg_status);
+	}
+	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+
+	/* Request an irq */
+	ret = ccp->get_irq(ccp);
+	if (ret) {
+		dev_err(dev, "unable to allocate an IRQ\n");
+		goto e_pool;
+	}
+
+	/* Initialize the queues used to wait for KSB space and suspend */
+	init_waitqueue_head(&ccp->ksb_queue);
+	init_waitqueue_head(&ccp->suspend_queue);
+
+	/* Create a kthread for each queue */
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		struct task_struct *kthread;
+
+		cmd_q = &ccp->cmd_q[i];
+
+		kthread = kthread_create(ccp_cmd_queue_thread, cmd_q,
+					 "%s-q%u", ccp->name, cmd_q->id);
+		if (IS_ERR(kthread)) {
+			dev_err(dev, "error creating queue thread (%ld)\n",
+				PTR_ERR(kthread));
+			ret = PTR_ERR(kthread);
+			goto e_kthread;
+		}
+
+		cmd_q->kthread = kthread;
+		wake_up_process(kthread);
+	}
+
+	/* Register the RNG */
+	ccp->hwrng.name = ccp->rngname;
+	ccp->hwrng.read = ccp_trng_read;
+	ret = hwrng_register(&ccp->hwrng);
+	if (ret) {
+		dev_err(dev, "error registering hwrng (%d)\n", ret);
+		goto e_kthread;
+	}
+
+	ccp_add_device(ccp);
+
+	/* Enable interrupts */
+	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
+
+	return 0;
+
+e_kthread:
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		if (ccp->cmd_q[i].kthread)
+			kthread_stop(ccp->cmd_q[i].kthread);
+
+	ccp->free_irq(ccp);
+
+e_pool:
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
+
+	return ret;
+}
+
+static void ccp_destroy(struct ccp_device *ccp)
+{
+	struct ccp_cmd_queue *cmd_q;
+	struct ccp_cmd *cmd;
+	unsigned int qim, i;
+
+	/* Remove this device from the list of available units first */
+	ccp_del_device(ccp);
+
+	/* Unregister the RNG */
+	hwrng_unregister(&ccp->hwrng);
+
+	/* Stop the queue kthreads */
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		if (ccp->cmd_q[i].kthread)
+			kthread_stop(ccp->cmd_q[i].kthread);
+
+	/* Build queue interrupt mask (two interrupt masks per queue) */
+	qim = 0;
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+		qim |= cmd_q->int_ok | cmd_q->int_err;
+	}
+
+	/* Disable and clear interrupts */
+	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		ioread32(cmd_q->reg_int_status);
+		ioread32(cmd_q->reg_status);
+	}
+	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+
+	ccp->free_irq(ccp);
+
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
+
+	/* Flush the cmd and backlog queue */
+	while (!list_empty(&ccp->cmd)) {
+		/* Invoke the callback directly with an error code */
+		cmd = list_first_entry(&ccp->cmd, struct ccp_cmd, entry);
+		list_del(&cmd->entry);
+		cmd->callback(cmd->data, -ENODEV);
+	}
+	while (!list_empty(&ccp->backlog)) {
+		/* Invoke the callback directly with an error code */
+		cmd = list_first_entry(&ccp->backlog, struct ccp_cmd, entry);
+		list_del(&cmd->entry);
+		cmd->callback(cmd->data, -ENODEV);
+	}
+}
+
+static irqreturn_t ccp_irq_handler(int irq, void *data)
+{
+	struct device *dev = data;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+	struct ccp_cmd_queue *cmd_q;
+	u32 q_int, status;
+	unsigned int i;
+
+	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
+
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
+		if (q_int) {
+			cmd_q->int_status = status;
+			cmd_q->q_status = ioread32(cmd_q->reg_status);
+			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
+
+			/* On error, only save the first error value */
+			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
+				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
+
+			cmd_q->int_rcvd = 1;
+
+			/* Acknowledge the interrupt and wake the kthread */
+			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
+			wake_up_interruptible(&cmd_q->int_queue);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct ccp_actions ccp3_actions = {
+	.perform_aes = ccp_perform_aes,
+	.perform_xts_aes = ccp_perform_xts_aes,
+	.perform_sha = ccp_perform_sha,
+	.perform_rsa = ccp_perform_rsa,
+	.perform_passthru = ccp_perform_passthru,
+	.perform_ecc = ccp_perform_ecc,
+	.init = ccp_init,
+	.destroy = ccp_destroy,
+	.irqhandler = ccp_irq_handler,
+};
+
+struct ccp_vdata ccpv3 = {
+	.version = CCP_VERSION(3, 0),
+	.perform = &ccp3_actions,
+};
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 861bacc1b..4dbc18727 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -16,6 +16,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <linux/rwlock_types.h>
+#include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/hw_random.h>
@@ -37,20 +39,107 @@ struct ccp_tasklet_data {
 	struct ccp_cmd *cmd;
 };
 
-static struct ccp_device *ccp_dev;
-static inline struct ccp_device *ccp_get_device(void)
+/* List of CCPs, CCP count, read-write access lock, and access functions
+ *
+ * Lock structure: get ccp_unit_lock for reading whenever we need to
+ * examine the CCP list. While holding it for reading we can acquire
+ * the RR lock to update the round-robin next-CCP pointer. The unit lock
+ * must be acquired before the RR lock.
+ *
+ * If the unit-lock is acquired for writing, we have total control over
+ * the list, so there's no value in getting the RR lock.
+ */
+static DEFINE_RWLOCK(ccp_unit_lock);
+static LIST_HEAD(ccp_units);
+
+/* Round-robin counter */
+static DEFINE_SPINLOCK(ccp_rr_lock);
+static struct ccp_device *ccp_rr;
+
+/* Ever-increasing value to produce unique unit numbers */
+static atomic_t ccp_unit_ordinal;
+unsigned int ccp_increment_unit_ordinal(void)
 {
-	return ccp_dev;
+	return atomic_inc_return(&ccp_unit_ordinal);
 }
 
-static inline void ccp_add_device(struct ccp_device *ccp)
+/**
+ * ccp_add_device - add a CCP device to the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Put this CCP on the unit list, which makes it available
+ * for use.
+ *
+ * Returns zero if a CCP device is present, -ENODEV otherwise.
+ */
+void ccp_add_device(struct ccp_device *ccp)
 {
-	ccp_dev = ccp;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	list_add_tail(&ccp->entry, &ccp_units);
+	if (!ccp_rr)
+		/* We already have the list lock (we're first) so this
+		 * pointer can't change on us. Set its initial value.
+		 */
+		ccp_rr = ccp;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
 }
 
-static inline void ccp_del_device(struct ccp_device *ccp)
+/**
+ * ccp_del_device - remove a CCP device from the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Remove this unit from the list of devices. If the next device
+ * up for use is this one, adjust the pointer. If this is the last
+ * device, NULL the pointer.
+ */
+void ccp_del_device(struct ccp_device *ccp)
 {
-	ccp_dev = NULL;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	if (ccp_rr == ccp) {
+		/* ccp_unit_lock is read/write; any read access
+		 * will be suspended while we make changes to the
+		 * list and RR pointer.
+		 */
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+	}
+	list_del(&ccp->entry);
+	if (list_empty(&ccp_units))
+		ccp_rr = NULL;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
+}
+
+static struct ccp_device *ccp_get_device(void)
+{
+	unsigned long flags;
+	struct ccp_device *dp = NULL;
+
+	/* We round-robin through the unit list.
+	 * The (ccp_rr) pointer refers to the next unit to use.
+	 */
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		spin_lock(&ccp_rr_lock);
+		dp = ccp_rr;
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+		spin_unlock(&ccp_rr_lock);
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return dp;
 }
 
 /**
@@ -60,14 +149,41 @@ static inline void ccp_del_device(struct ccp_device *ccp)
  */
 int ccp_present(void)
 {
-	if (ccp_get_device())
-		return 0;
+	unsigned long flags;
+	int ret;
 
-	return -ENODEV;
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	ret = list_empty(&ccp_units);
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret ? -ENODEV : 0;
 }
 EXPORT_SYMBOL_GPL(ccp_present);
 
 /**
+ * ccp_version - get the version of the CCP device
+ *
+ * Returns the version from the first unit on the list;
+ * otherwise a zero if no CCP device is present
+ */
+unsigned int ccp_version(void)
+{
+	struct ccp_device *dp;
+	unsigned long flags;
+	int ret = 0;
+
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		dp = list_first_entry(&ccp_units, struct ccp_device, entry);
+		ret = dp->vdata->version;
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ccp_version);
+
+/**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
  * @cmd: ccp_cmd struct to be processed
@@ -221,7 +337,12 @@ static void ccp_do_cmd_complete(unsigned long data)
 	complete(&tdata->completion);
 }
 
-static int ccp_cmd_queue_thread(void *data)
+/**
+ * ccp_cmd_queue_thread - create a kernel thread to manage a CCP queue
+ *
+ * @data: thread-specific data
+ */
+int ccp_cmd_queue_thread(void *data)
 {
 	struct ccp_cmd_queue *cmd_q = (struct ccp_cmd_queue *)data;
 	struct ccp_cmd *cmd;
@@ -257,35 +378,6 @@ static int ccp_cmd_queue_thread(void *data)
 	return 0;
 }
 
-static int ccp_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
-{
-	struct ccp_device *ccp = container_of(rng, struct ccp_device, hwrng);
-	u32 trng_value;
-	int len = min_t(int, sizeof(trng_value), max);
-
-	/*
-	 * Locking is provided by the caller so we can update device
-	 * hwrng-related fields safely
-	 */
-	trng_value = ioread32(ccp->io_regs + TRNG_OUT_REG);
-	if (!trng_value) {
-		/* Zero is returned if not data is available or if a
-		 * bad-entropy error is present. Assume an error if
-		 * we exceed TRNG_RETRIES reads of zero.
-		 */
-		if (ccp->hwrng_retries++ > TRNG_RETRIES)
-			return -EIO;
-
-		return 0;
-	}
-
-	/* Reset the counter and save the rng value */
-	ccp->hwrng_retries = 0;
-	memcpy(data, &trng_value, len);
-
-	return len;
-}
-
 /**
  * ccp_alloc_struct - allocate and initialize the ccp_device struct
  *
@@ -309,253 +401,11 @@ struct ccp_device *ccp_alloc_struct(struct device *dev)
 	ccp->ksb_count = KSB_COUNT;
 	ccp->ksb_start = 0;
 
-	return ccp;
-}
-
-/**
- * ccp_init - initialize the CCP device
- *
- * @ccp: ccp_device struct
- */
-int ccp_init(struct ccp_device *ccp)
-{
-	struct device *dev = ccp->dev;
-	struct ccp_cmd_queue *cmd_q;
-	struct dma_pool *dma_pool;
-	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
-	unsigned int qmr, qim, i;
-	int ret;
-
-	/* Find available queues */
-	qim = 0;
-	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
-	for (i = 0; i < MAX_HW_QUEUES; i++) {
-		if (!(qmr & (1 << i)))
-			continue;
-
-		/* Allocate a dma pool for this queue */
-		snprintf(dma_pool_name, sizeof(dma_pool_name), "ccp_q%d", i);
-		dma_pool = dma_pool_create(dma_pool_name, dev,
-					   CCP_DMAPOOL_MAX_SIZE,
-					   CCP_DMAPOOL_ALIGN, 0);
-		if (!dma_pool) {
-			dev_err(dev, "unable to allocate dma pool\n");
-			ret = -ENOMEM;
-			goto e_pool;
-		}
-
-		cmd_q = &ccp->cmd_q[ccp->cmd_q_count];
-		ccp->cmd_q_count++;
-
-		cmd_q->ccp = ccp;
-		cmd_q->id = i;
-		cmd_q->dma_pool = dma_pool;
-
-		/* Reserve 2 KSB regions for the queue */
-		cmd_q->ksb_key = KSB_START + ccp->ksb_start++;
-		cmd_q->ksb_ctx = KSB_START + ccp->ksb_start++;
-		ccp->ksb_count -= 2;
-
-		/* Preset some register values and masks that are queue
-		 * number dependent
-		 */
-		cmd_q->reg_status = ccp->io_regs + CMD_Q_STATUS_BASE +
-				    (CMD_Q_STATUS_INCR * i);
-		cmd_q->reg_int_status = ccp->io_regs + CMD_Q_INT_STATUS_BASE +
-					(CMD_Q_STATUS_INCR * i);
-		cmd_q->int_ok = 1 << (i * 2);
-		cmd_q->int_err = 1 << ((i * 2) + 1);
-
-		cmd_q->free_slots = CMD_Q_DEPTH(ioread32(cmd_q->reg_status));
-
-		init_waitqueue_head(&cmd_q->int_queue);
-
-		/* Build queue interrupt mask (two interrupts per queue) */
-		qim |= cmd_q->int_ok | cmd_q->int_err;
+	ccp->ord = ccp_increment_unit_ordinal();
+	snprintf(ccp->name, MAX_CCP_NAME_LEN, "ccp-%u", ccp->ord);
+	snprintf(ccp->rngname, MAX_CCP_NAME_LEN, "ccp-%u-rng", ccp->ord);
 
-#ifdef CONFIG_ARM64
-		/* For arm64 set the recommended queue cache settings */
-		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
-			  (CMD_Q_CACHE_INC * i));
-#endif
-
-		dev_dbg(dev, "queue #%u available\n", i);
-	}
-	if (ccp->cmd_q_count == 0) {
-		dev_notice(dev, "no command queues available\n");
-		ret = -EIO;
-		goto e_pool;
-	}
-	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
-
-	/* Disable and clear interrupts until ready */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	/* Request an irq */
-	ret = ccp->get_irq(ccp);
-	if (ret) {
-		dev_err(dev, "unable to allocate an IRQ\n");
-		goto e_pool;
-	}
-
-	/* Initialize the queues used to wait for KSB space and suspend */
-	init_waitqueue_head(&ccp->ksb_queue);
-	init_waitqueue_head(&ccp->suspend_queue);
-
-	/* Create a kthread for each queue */
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		struct task_struct *kthread;
-
-		cmd_q = &ccp->cmd_q[i];
-
-		kthread = kthread_create(ccp_cmd_queue_thread, cmd_q,
-					 "ccp-q%u", cmd_q->id);
-		if (IS_ERR(kthread)) {
-			dev_err(dev, "error creating queue thread (%ld)\n",
-				PTR_ERR(kthread));
-			ret = PTR_ERR(kthread);
-			goto e_kthread;
-		}
-
-		cmd_q->kthread = kthread;
-		wake_up_process(kthread);
-	}
-
-	/* Register the RNG */
-	ccp->hwrng.name = "ccp-rng";
-	ccp->hwrng.read = ccp_trng_read;
-	ret = hwrng_register(&ccp->hwrng);
-	if (ret) {
-		dev_err(dev, "error registering hwrng (%d)\n", ret);
-		goto e_kthread;
-	}
-
-	/* Make the device struct available before enabling interrupts */
-	ccp_add_device(ccp);
-
-	/* Enable interrupts */
-	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
-
-	return 0;
-
-e_kthread:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	ccp->free_irq(ccp);
-
-e_pool:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	return ret;
-}
-
-/**
- * ccp_destroy - tear down the CCP device
- *
- * @ccp: ccp_device struct
- */
-void ccp_destroy(struct ccp_device *ccp)
-{
-	struct ccp_cmd_queue *cmd_q;
-	struct ccp_cmd *cmd;
-	unsigned int qim, i;
-
-	/* Remove general access to the device struct */
-	ccp_del_device(ccp);
-
-	/* Unregister the RNG */
-	hwrng_unregister(&ccp->hwrng);
-
-	/* Stop the queue kthreads */
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	/* Build queue interrupt mask (two interrupt masks per queue) */
-	qim = 0;
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-		qim |= cmd_q->int_ok | cmd_q->int_err;
-	}
-
-	/* Disable and clear interrupts */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	ccp->free_irq(ccp);
-
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	/* Flush the cmd and backlog queue */
-	while (!list_empty(&ccp->cmd)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->cmd, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-	while (!list_empty(&ccp->backlog)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->backlog, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-}
-
-/**
- * ccp_irq_handler - handle interrupts generated by the CCP device
- *
- * @irq: the irq associated with the interrupt
- * @data: the data value supplied when the irq was created
- */
-irqreturn_t ccp_irq_handler(int irq, void *data)
-{
-	struct device *dev = data;
-	struct ccp_device *ccp = dev_get_drvdata(dev);
-	struct ccp_cmd_queue *cmd_q;
-	u32 q_int, status;
-	unsigned int i;
-
-	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
-
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
-		if (q_int) {
-			cmd_q->int_status = status;
-			cmd_q->q_status = ioread32(cmd_q->reg_status);
-			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
-
-			/* On error, only save the first error value */
-			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
-				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
-
-			cmd_q->int_rcvd = 1;
-
-			/* Acknowledge the interrupt and wake the kthread */
-			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
-			wake_up_interruptible(&cmd_q->int_queue);
-		}
-	}
-
-	return IRQ_HANDLED;
+	return ccp;
 }
 
 #ifdef CONFIG_PM
@@ -577,41 +427,22 @@ bool ccp_queues_suspended(struct ccp_device *ccp)
 }
 #endif
 
-#ifdef CONFIG_X86
-static const struct x86_cpu_id ccp_support[] = {
-	{ X86_VENDOR_AMD, 22, },
-	{ },
-};
-#endif
-
 static int __init ccp_mod_init(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
 	int ret;
 
-	if (!x86_match_cpu(ccp_support))
-		return -ENODEV;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		if ((cpuinfo->x86_model < 48) || (cpuinfo->x86_model > 63))
-			return -ENODEV;
-
-		ret = ccp_pci_init();
-		if (ret)
-			return ret;
-
-		/* Don't leave the driver loaded if init failed */
-		if (!ccp_get_device()) {
-			ccp_pci_exit();
-			return -ENODEV;
-		}
-
-		return 0;
+	ret = ccp_pci_init();
+	if (ret)
+		return ret;
 
-		break;
+	/* Don't leave the driver loaded if init failed */
+	if (ccp_present() != 0) {
+		ccp_pci_exit();
+		return -ENODEV;
 	}
+
+	return 0;
 #endif
 
 #ifdef CONFIG_ARM64
@@ -622,7 +453,7 @@ static int __init ccp_mod_init(void)
 		return ret;
 
 	/* Don't leave the driver loaded if init failed */
-	if (!ccp_get_device()) {
+	if (ccp_present() != 0) {
 		ccp_platform_exit();
 		return -ENODEV;
 	}
@@ -636,13 +467,7 @@ static int __init ccp_mod_init(void)
 static void __exit ccp_mod_exit(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		ccp_pci_exit();
-		break;
-	}
+	ccp_pci_exit();
 #endif
 
 #ifdef CONFIG_ARM64
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 6ff89031f..7745d0be4 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -23,6 +23,7 @@
 #include <linux/hw_random.h>
 #include <linux/bitops.h>
 
+#define MAX_CCP_NAME_LEN		16
 #define MAX_DMAPOOL_NAME_LEN		32
 
 #define MAX_HW_QUEUES			5
@@ -140,6 +141,29 @@
 #define CCP_ECC_RESULT_OFFSET		60
 #define CCP_ECC_RESULT_SUCCESS		0x0001
 
+struct ccp_op;
+
+/* Structure for computation functions that are device-specific */
+struct ccp_actions {
+	int (*perform_aes)(struct ccp_op *);
+	int (*perform_xts_aes)(struct ccp_op *);
+	int (*perform_sha)(struct ccp_op *);
+	int (*perform_rsa)(struct ccp_op *);
+	int (*perform_passthru)(struct ccp_op *);
+	int (*perform_ecc)(struct ccp_op *);
+	int (*init)(struct ccp_device *);
+	void (*destroy)(struct ccp_device *);
+	irqreturn_t (*irqhandler)(int, void *);
+};
+
+/* Structure to hold CCP version-specific values */
+struct ccp_vdata {
+	unsigned int version;
+	struct ccp_actions *perform;
+};
+
+extern struct ccp_vdata ccpv3;
+
 struct ccp_device;
 struct ccp_cmd;
 
@@ -184,6 +208,13 @@ struct ccp_cmd_queue {
 } ____cacheline_aligned;
 
 struct ccp_device {
+	struct list_head entry;
+
+	struct ccp_vdata *vdata;
+	unsigned int ord;
+	char name[MAX_CCP_NAME_LEN];
+	char rngname[MAX_CCP_NAME_LEN];
+
 	struct device *dev;
 
 	/*
@@ -258,18 +289,132 @@ struct ccp_device {
 	unsigned int axcache;
 };
 
+enum ccp_memtype {
+	CCP_MEMTYPE_SYSTEM = 0,
+	CCP_MEMTYPE_KSB,
+	CCP_MEMTYPE_LOCAL,
+	CCP_MEMTYPE__LAST,
+};
+
+struct ccp_dma_info {
+	dma_addr_t address;
+	unsigned int offset;
+	unsigned int length;
+	enum dma_data_direction dir;
+};
+
+struct ccp_dm_workarea {
+	struct device *dev;
+	struct dma_pool *dma_pool;
+	unsigned int length;
+
+	u8 *address;
+	struct ccp_dma_info dma;
+};
+
+struct ccp_sg_workarea {
+	struct scatterlist *sg;
+	int nents;
+
+	struct scatterlist *dma_sg;
+	struct device *dma_dev;
+	unsigned int dma_count;
+	enum dma_data_direction dma_dir;
+
+	unsigned int sg_used;
+
+	u64 bytes_left;
+};
+
+struct ccp_data {
+	struct ccp_sg_workarea sg_wa;
+	struct ccp_dm_workarea dm_wa;
+};
+
+struct ccp_mem {
+	enum ccp_memtype type;
+	union {
+		struct ccp_dma_info dma;
+		u32 ksb;
+	} u;
+};
+
+struct ccp_aes_op {
+	enum ccp_aes_type type;
+	enum ccp_aes_mode mode;
+	enum ccp_aes_action action;
+};
+
+struct ccp_xts_aes_op {
+	enum ccp_aes_action action;
+	enum ccp_xts_aes_unit_size unit_size;
+};
+
+struct ccp_sha_op {
+	enum ccp_sha_type type;
+	u64 msg_bits;
+};
+
+struct ccp_rsa_op {
+	u32 mod_size;
+	u32 input_len;
+};
+
+struct ccp_passthru_op {
+	enum ccp_passthru_bitwise bit_mod;
+	enum ccp_passthru_byteswap byte_swap;
+};
+
+struct ccp_ecc_op {
+	enum ccp_ecc_function function;
+};
+
+struct ccp_op {
+	struct ccp_cmd_queue *cmd_q;
+
+	u32 jobid;
+	u32 ioc;
+	u32 soc;
+	u32 ksb_key;
+	u32 ksb_ctx;
+	u32 init;
+	u32 eom;
+
+	struct ccp_mem src;
+	struct ccp_mem dst;
+
+	union {
+		struct ccp_aes_op aes;
+		struct ccp_xts_aes_op xts;
+		struct ccp_sha_op sha;
+		struct ccp_rsa_op rsa;
+		struct ccp_passthru_op passthru;
+		struct ccp_ecc_op ecc;
+	} u;
+};
+
+static inline u32 ccp_addr_lo(struct ccp_dma_info *info)
+{
+	return lower_32_bits(info->address + info->offset);
+}
+
+static inline u32 ccp_addr_hi(struct ccp_dma_info *info)
+{
+	return upper_32_bits(info->address + info->offset) & 0x0000ffff;
+}
+
 int ccp_pci_init(void);
 void ccp_pci_exit(void);
 
 int ccp_platform_init(void);
 void ccp_platform_exit(void);
 
+void ccp_add_device(struct ccp_device *ccp);
+void ccp_del_device(struct ccp_device *ccp);
+
 struct ccp_device *ccp_alloc_struct(struct device *dev);
-int ccp_init(struct ccp_device *ccp);
-void ccp_destroy(struct ccp_device *ccp);
 bool ccp_queues_suspended(struct ccp_device *ccp);
-
-irqreturn_t ccp_irq_handler(int irq, void *data);
+int ccp_cmd_queue_thread(void *data);
 
 int ccp_run_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd);
 
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 6613aee79..eefdf595f 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -13,124 +13,12 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/kthread.h>
-#include <linux/sched.h>
 #include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-#include <linux/delay.h>
-#include <linux/ccp.h>
-#include <linux/scatterlist.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <linux/ccp.h>
 
 #include "ccp-dev.h"
 
-enum ccp_memtype {
-	CCP_MEMTYPE_SYSTEM = 0,
-	CCP_MEMTYPE_KSB,
-	CCP_MEMTYPE_LOCAL,
-	CCP_MEMTYPE__LAST,
-};
-
-struct ccp_dma_info {
-	dma_addr_t address;
-	unsigned int offset;
-	unsigned int length;
-	enum dma_data_direction dir;
-};
-
-struct ccp_dm_workarea {
-	struct device *dev;
-	struct dma_pool *dma_pool;
-	unsigned int length;
-
-	u8 *address;
-	struct ccp_dma_info dma;
-};
-
-struct ccp_sg_workarea {
-	struct scatterlist *sg;
-	int nents;
-
-	struct scatterlist *dma_sg;
-	struct device *dma_dev;
-	unsigned int dma_count;
-	enum dma_data_direction dma_dir;
-
-	unsigned int sg_used;
-
-	u64 bytes_left;
-};
-
-struct ccp_data {
-	struct ccp_sg_workarea sg_wa;
-	struct ccp_dm_workarea dm_wa;
-};
-
-struct ccp_mem {
-	enum ccp_memtype type;
-	union {
-		struct ccp_dma_info dma;
-		u32 ksb;
-	} u;
-};
-
-struct ccp_aes_op {
-	enum ccp_aes_type type;
-	enum ccp_aes_mode mode;
-	enum ccp_aes_action action;
-};
-
-struct ccp_xts_aes_op {
-	enum ccp_aes_action action;
-	enum ccp_xts_aes_unit_size unit_size;
-};
-
-struct ccp_sha_op {
-	enum ccp_sha_type type;
-	u64 msg_bits;
-};
-
-struct ccp_rsa_op {
-	u32 mod_size;
-	u32 input_len;
-};
-
-struct ccp_passthru_op {
-	enum ccp_passthru_bitwise bit_mod;
-	enum ccp_passthru_byteswap byte_swap;
-};
-
-struct ccp_ecc_op {
-	enum ccp_ecc_function function;
-};
-
-struct ccp_op {
-	struct ccp_cmd_queue *cmd_q;
-
-	u32 jobid;
-	u32 ioc;
-	u32 soc;
-	u32 ksb_key;
-	u32 ksb_ctx;
-	u32 init;
-	u32 eom;
-
-	struct ccp_mem src;
-	struct ccp_mem dst;
-
-	union {
-		struct ccp_aes_op aes;
-		struct ccp_xts_aes_op xts;
-		struct ccp_sha_op sha;
-		struct ccp_rsa_op rsa;
-		struct ccp_passthru_op passthru;
-		struct ccp_ecc_op ecc;
-	} u;
-};
-
 /* SHA initial context values */
 static const __be32 ccp_sha1_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
 	cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1),
@@ -152,253 +40,6 @@ static const __be32 ccp_sha256_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
 	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
 };
 
-static u32 ccp_addr_lo(struct ccp_dma_info *info)
-{
-	return lower_32_bits(info->address + info->offset);
-}
-
-static u32 ccp_addr_hi(struct ccp_dma_info *info)
-{
-	return upper_32_bits(info->address + info->offset) & 0x0000ffff;
-}
-
-static int ccp_do_cmd(struct ccp_op *op, u32 *cr, unsigned int cr_count)
-{
-	struct ccp_cmd_queue *cmd_q = op->cmd_q;
-	struct ccp_device *ccp = cmd_q->ccp;
-	void __iomem *cr_addr;
-	u32 cr0, cmd;
-	unsigned int i;
-	int ret = 0;
-
-	/* We could read a status register to see how many free slots
-	 * are actually available, but reading that register resets it
-	 * and you could lose some error information.
-	 */
-	cmd_q->free_slots--;
-
-	cr0 = (cmd_q->id << REQ0_CMD_Q_SHIFT)
-	      | (op->jobid << REQ0_JOBID_SHIFT)
-	      | REQ0_WAIT_FOR_WRITE;
-
-	if (op->soc)
-		cr0 |= REQ0_STOP_ON_COMPLETE
-		       | REQ0_INT_ON_COMPLETE;
-
-	if (op->ioc || !cmd_q->free_slots)
-		cr0 |= REQ0_INT_ON_COMPLETE;
-
-	/* Start at CMD_REQ1 */
-	cr_addr = ccp->io_regs + CMD_REQ0 + CMD_REQ_INCR;
-
-	mutex_lock(&ccp->req_mutex);
-
-	/* Write CMD_REQ1 through CMD_REQx first */
-	for (i = 0; i < cr_count; i++, cr_addr += CMD_REQ_INCR)
-		iowrite32(*(cr + i), cr_addr);
-
-	/* Tell the CCP to start */
-	wmb();
-	iowrite32(cr0, ccp->io_regs + CMD_REQ0);
-
-	mutex_unlock(&ccp->req_mutex);
-
-	if (cr0 & REQ0_INT_ON_COMPLETE) {
-		/* Wait for the job to complete */
-		ret = wait_event_interruptible(cmd_q->int_queue,
-					       cmd_q->int_rcvd);
-		if (ret || cmd_q->cmd_error) {
-			/* On error delete all related jobs from the queue */
-			cmd = (cmd_q->id << DEL_Q_ID_SHIFT)
-			      | op->jobid;
-
-			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
-
-			if (!ret)
-				ret = -EIO;
-		} else if (op->soc) {
-			/* Delete just head job from the queue on SoC */
-			cmd = DEL_Q_ACTIVE
-			      | (cmd_q->id << DEL_Q_ID_SHIFT)
-			      | op->jobid;
-
-			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
-		}
-
-		cmd_q->free_slots = CMD_Q_DEPTH(cmd_q->q_status);
-
-		cmd_q->int_rcvd = 0;
-	}
-
-	return ret;
-}
-
-static int ccp_perform_aes(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_AES << REQ1_ENGINE_SHIFT)
-		| (op->u.aes.type << REQ1_AES_TYPE_SHIFT)
-		| (op->u.aes.mode << REQ1_AES_MODE_SHIFT)
-		| (op->u.aes.action << REQ1_AES_ACTION_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	if (op->u.aes.mode == CCP_AES_MODE_CFB)
-		cr[0] |= ((0x7f) << REQ1_AES_CFB_SIZE_SHIFT);
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	if (op->init)
-		cr[0] |= REQ1_INIT;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_xts_aes(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_XTS_AES_128 << REQ1_ENGINE_SHIFT)
-		| (op->u.xts.action << REQ1_AES_ACTION_SHIFT)
-		| (op->u.xts.unit_size << REQ1_XTS_AES_SIZE_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	if (op->init)
-		cr[0] |= REQ1_INIT;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_sha(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_SHA << REQ1_ENGINE_SHIFT)
-		| (op->u.sha.type << REQ1_SHA_TYPE_SHIFT)
-		| REQ1_INIT;
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-
-	if (op->eom) {
-		cr[0] |= REQ1_EOM;
-		cr[4] = lower_32_bits(op->u.sha.msg_bits);
-		cr[5] = upper_32_bits(op->u.sha.msg_bits);
-	} else {
-		cr[4] = 0;
-		cr[5] = 0;
-	}
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_rsa(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_RSA << REQ1_ENGINE_SHIFT)
-		| (op->u.rsa.mod_size << REQ1_RSA_MOD_SIZE_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT)
-		| REQ1_EOM;
-	cr[1] = op->u.rsa.input_len - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_passthru(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_PASSTHRU << REQ1_ENGINE_SHIFT)
-		| (op->u.passthru.bit_mod << REQ1_PT_BW_SHIFT)
-		| (op->u.passthru.byte_swap << REQ1_PT_BS_SHIFT);
-
-	if (op->src.type == CCP_MEMTYPE_SYSTEM)
-		cr[1] = op->src.u.dma.length - 1;
-	else
-		cr[1] = op->dst.u.dma.length - 1;
-
-	if (op->src.type == CCP_MEMTYPE_SYSTEM) {
-		cr[2] = ccp_addr_lo(&op->src.u.dma);
-		cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-			| ccp_addr_hi(&op->src.u.dma);
-
-		if (op->u.passthru.bit_mod != CCP_PASSTHRU_BITWISE_NOOP)
-			cr[3] |= (op->ksb_key << REQ4_KSB_SHIFT);
-	} else {
-		cr[2] = op->src.u.ksb * CCP_KSB_BYTES;
-		cr[3] = (CCP_MEMTYPE_KSB << REQ4_MEMTYPE_SHIFT);
-	}
-
-	if (op->dst.type == CCP_MEMTYPE_SYSTEM) {
-		cr[4] = ccp_addr_lo(&op->dst.u.dma);
-		cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-			| ccp_addr_hi(&op->dst.u.dma);
-	} else {
-		cr[4] = op->dst.u.ksb * CCP_KSB_BYTES;
-		cr[5] = (CCP_MEMTYPE_KSB << REQ6_MEMTYPE_SHIFT);
-	}
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_ecc(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = REQ1_ECC_AFFINE_CONVERT
-		| (CCP_ENGINE_ECC << REQ1_ENGINE_SHIFT)
-		| (op->u.ecc.function << REQ1_ECC_FUNCTION_SHIFT)
-		| REQ1_EOM;
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
 static u32 ccp_alloc_ksb(struct ccp_device *ccp, unsigned int count)
 {
 	int start;
@@ -837,7 +478,7 @@ static int ccp_copy_to_from_ksb(struct ccp_cmd_queue *cmd_q,
 
 	op.u.passthru.byte_swap = byte_swap;
 
-	return ccp_perform_passthru(&op);
+	return cmd_q->ccp->vdata->perform->perform_passthru(&op);
 }
 
 static int ccp_copy_to_ksb(struct ccp_cmd_queue *cmd_q,
@@ -969,7 +610,7 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 			}
 		}
 
-		ret = ccp_perform_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_src;
@@ -1131,7 +772,7 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 				op.soc = 1;
 		}
 
-		ret = ccp_perform_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1296,7 +937,7 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 		if (!src.sg_wa.bytes_left)
 			op.eom = 1;
 
-		ret = ccp_perform_xts_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_xts_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1453,7 +1094,7 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		if (sha->final && !src.sg_wa.bytes_left)
 			op.eom = 1;
 
-		ret = ccp_perform_sha(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_sha(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_data;
@@ -1633,7 +1274,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	op.u.rsa.mod_size = rsa->key_size;
 	op.u.rsa.input_len = i_len;
 
-	ret = ccp_perform_rsa(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_rsa(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
@@ -1758,7 +1399,7 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 		op.dst.u.dma.offset = dst.sg_wa.sg_used;
 		op.dst.u.dma.length = op.src.u.dma.length;
 
-		ret = ccp_perform_passthru(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_passthru(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1870,7 +1511,7 @@ static int ccp_run_ecc_mm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	op.u.ecc.function = cmd->u.ecc.function;
 
-	ret = ccp_perform_ecc(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_ecc(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
@@ -2034,7 +1675,7 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	op.u.ecc.function = cmd->u.ecc.function;
 
-	ret = ccp_perform_ecc(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_ecc(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
diff --git a/drivers/crypto/ccp/ccp-pci.c b/drivers/crypto/ccp/ccp-pci.c
index 7690467c4..0bf262e36 100644
--- a/drivers/crypto/ccp/ccp-pci.c
+++ b/drivers/crypto/ccp/ccp-pci.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -59,9 +59,11 @@ static int ccp_get_msix_irqs(struct ccp_device *ccp)
 	ccp_pci->msix_count = ret;
 	for (v = 0; v < ccp_pci->msix_count; v++) {
 		/* Set the interrupt names and request the irqs */
-		snprintf(ccp_pci->msix[v].name, name_len, "ccp-%u", v);
+		snprintf(ccp_pci->msix[v].name, name_len, "%s-%u",
+			 ccp->name, v);
 		ccp_pci->msix[v].vector = msix_entry[v].vector;
-		ret = request_irq(ccp_pci->msix[v].vector, ccp_irq_handler,
+		ret = request_irq(ccp_pci->msix[v].vector,
+				  ccp->vdata->perform->irqhandler,
 				  0, ccp_pci->msix[v].name, dev);
 		if (ret) {
 			dev_notice(dev, "unable to allocate MSI-X IRQ (%d)\n",
@@ -94,7 +96,8 @@ static int ccp_get_msi_irq(struct ccp_device *ccp)
 		return ret;
 
 	ccp->irq = pdev->irq;
-	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
+	ret = request_irq(ccp->irq, ccp->vdata->perform->irqhandler, 0,
+			  ccp->name, dev);
 	if (ret) {
 		dev_notice(dev, "unable to allocate MSI IRQ (%d)\n", ret);
 		goto e_msi;
@@ -179,6 +182,12 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto e_err;
 
 	ccp->dev_specific = ccp_pci;
+	ccp->vdata = (struct ccp_vdata *)id->driver_data;
+	if (!ccp->vdata || !ccp->vdata->version) {
+		ret = -ENODEV;
+		dev_err(dev, "missing driver data\n");
+		goto e_err;
+	}
 	ccp->get_irq = ccp_get_irqs;
 	ccp->free_irq = ccp_free_irqs;
 
@@ -221,7 +230,7 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	dev_set_drvdata(dev, ccp);
 
-	ret = ccp_init(ccp);
+	ret = ccp->vdata->perform->init(ccp);
 	if (ret)
 		goto e_iomap;
 
@@ -251,7 +260,7 @@ static void ccp_pci_remove(struct pci_dev *pdev)
 	if (!ccp)
 		return;
 
-	ccp_destroy(ccp);
+	ccp->vdata->perform->destroy(ccp);
 
 	pci_iounmap(pdev, ccp->io_map);
 
@@ -312,7 +321,7 @@ static int ccp_pci_resume(struct pci_dev *pdev)
 #endif
 
 static const struct pci_device_id ccp_pci_table[] = {
-	{ PCI_VDEVICE(AMD, 0x1537), },
+	{ PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&ccpv3 },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index 66dd7c9d0..351f28d8c 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2014 Advanced Micro Devices, Inc.
+ * Copyright (C) 2014,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -32,6 +32,33 @@ struct ccp_platform {
 	int coherent;
 };
 
+static const struct acpi_device_id ccp_acpi_match[];
+static const struct of_device_id ccp_of_match[];
+
+static struct ccp_vdata *ccp_get_of_version(struct platform_device *pdev)
+{
+#ifdef CONFIG_OF
+	const struct of_device_id *match;
+
+	match = of_match_node(ccp_of_match, pdev->dev.of_node);
+	if (match && match->data)
+		return (struct ccp_vdata *)match->data;
+#endif
+	return 0;
+}
+
+static struct ccp_vdata *ccp_get_acpi_version(struct platform_device *pdev)
+{
+#ifdef CONFIG_ACPI
+	const struct acpi_device_id *match;
+
+	match = acpi_match_device(ccp_acpi_match, &pdev->dev);
+	if (match && match->driver_data)
+		return (struct ccp_vdata *)match->driver_data;
+#endif
+	return 0;
+}
+
 static int ccp_get_irq(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
@@ -43,7 +70,8 @@ static int ccp_get_irq(struct ccp_device *ccp)
 		return ret;
 
 	ccp->irq = ret;
-	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
+	ret = request_irq(ccp->irq, ccp->vdata->perform->irqhandler, 0,
+			  ccp->name, dev);
 	if (ret) {
 		dev_notice(dev, "unable to allocate IRQ (%d)\n", ret);
 		return ret;
@@ -106,6 +134,13 @@ static int ccp_platform_probe(struct platform_device *pdev)
 		goto e_err;
 
 	ccp->dev_specific = ccp_platform;
+	ccp->vdata = pdev->dev.of_node ? ccp_get_of_version(pdev)
+					 : ccp_get_acpi_version(pdev);
+	if (!ccp->vdata || !ccp->vdata->version) {
+		ret = -ENODEV;
+		dev_err(dev, "missing driver data\n");
+		goto e_err;
+	}
 	ccp->get_irq = ccp_get_irqs;
 	ccp->free_irq = ccp_free_irqs;
 
@@ -137,7 +172,7 @@ static int ccp_platform_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(dev, ccp);
 
-	ret = ccp_init(ccp);
+	ret = ccp->vdata->perform->init(ccp);
 	if (ret)
 		goto e_err;
 
@@ -155,7 +190,7 @@ static int ccp_platform_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct ccp_device *ccp = dev_get_drvdata(dev);
 
-	ccp_destroy(ccp);
+	ccp->vdata->perform->destroy(ccp);
 
 	dev_notice(dev, "disabled\n");
 
@@ -214,7 +249,7 @@ static int ccp_platform_resume(struct platform_device *pdev)
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id ccp_acpi_match[] = {
-	{ "AMDI0C00", 0 },
+	{ "AMDI0C00", (kernel_ulong_t)&ccpv3 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, ccp_acpi_match);
@@ -222,7 +257,8 @@ MODULE_DEVICE_TABLE(acpi, ccp_acpi_match);
 
 #ifdef CONFIG_OF
 static const struct of_device_id ccp_of_match[] = {
-	{ .compatible = "amd,ccp-seattle-v1a" },
+	{ .compatible = "amd,ccp-seattle-v1a",
+	  .data = (const void *)&ccpv3 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ccp_of_match);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index e52496a17..229693445 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1031,6 +1031,18 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	BUG_ON(ivsize && !req->iv);
 	memcpy(crypt->iv, req->iv, ivsize);
 
+	buf = chainup_buffers(dev, req->src, crypt->auth_len,
+			      &src_hook, flags, src_direction);
+	req_ctx->src = src_hook.next;
+	crypt->src_buf = src_hook.phys_next;
+	if (!buf)
+		goto free_buf_src;
+
+	lastlen = buf->buf_len;
+	if (lastlen >= authsize)
+		crypt->icv_rev_aes = buf->phys_addr +
+				     buf->buf_len - authsize;
+
 	req_ctx->dst = NULL;
 
 	if (req->src != req->dst) {
@@ -1055,20 +1067,6 @@ static int aead_perform(struct aead_request *req, int encrypt,
 		}
 	}
 
-	buf = chainup_buffers(dev, req->src, crypt->auth_len,
-			      &src_hook, flags, src_direction);
-	req_ctx->src = src_hook.next;
-	crypt->src_buf = src_hook.phys_next;
-	if (!buf)
-		goto free_buf_src;
-
-	if (!encrypt || !req_ctx->dst) {
-		lastlen = buf->buf_len;
-		if (lastlen >= authsize)
-			crypt->icv_rev_aes = buf->phys_addr +
-					     buf->buf_len - authsize;
-	}
-
 	if (unlikely(lastlen < authsize)) {
 		/* The 12 hmac bytes are scattered,
 		 * we need to copy them into a safe buffer */
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index bd985e725..74071e45a 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -588,6 +588,7 @@ struct mv_cesa_ahash_dma_req {
 	struct mv_cesa_tdma_req base;
 	u8 *padding;
 	dma_addr_t padding_dma;
+	u8 *cache;
 	dma_addr_t cache_dma;
 };
 
@@ -609,7 +610,7 @@ struct mv_cesa_ahash_req {
 		struct mv_cesa_ahash_std_req std;
 	} req;
 	struct mv_cesa_op_ctx op_tmpl;
-	u8 *cache;
+	u8 cache[CESA_MAX_HASH_BLOCK_SIZE];
 	unsigned int cache_ptr;
 	u64 len;
 	int src_nents;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 683cca9ac..7ca2e0f9d 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -45,69 +45,25 @@ mv_cesa_ahash_req_iter_next_op(struct mv_cesa_ahash_dma_iter *iter)
 	return mv_cesa_req_dma_iter_next_op(&iter->base);
 }
 
-static inline int mv_cesa_ahash_dma_alloc_cache(struct mv_cesa_ahash_req *creq,
-						gfp_t flags)
+static inline int
+mv_cesa_ahash_dma_alloc_cache(struct mv_cesa_ahash_dma_req *req, gfp_t flags)
 {
-	struct mv_cesa_ahash_dma_req *dreq = &creq->req.dma;
-
-	creq->cache = dma_pool_alloc(cesa_dev->dma->cache_pool, flags,
-				     &dreq->cache_dma);
-	if (!creq->cache)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static inline int mv_cesa_ahash_std_alloc_cache(struct mv_cesa_ahash_req *creq,
-						gfp_t flags)
-{
-	creq->cache = kzalloc(CESA_MAX_HASH_BLOCK_SIZE, flags);
-	if (!creq->cache)
+	req->cache = dma_pool_alloc(cesa_dev->dma->cache_pool, flags,
+				    &req->cache_dma);
+	if (!req->cache)
 		return -ENOMEM;
 
 	return 0;
 }
 
-static int mv_cesa_ahash_alloc_cache(struct ahash_request *req)
-{
-	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-		      GFP_KERNEL : GFP_ATOMIC;
-	int ret;
-
-	if (creq->cache)
-		return 0;
-
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_ahash_dma_alloc_cache(creq, flags);
-	else
-		ret = mv_cesa_ahash_std_alloc_cache(creq, flags);
-
-	return ret;
-}
-
-static inline void mv_cesa_ahash_dma_free_cache(struct mv_cesa_ahash_req *creq)
-{
-	dma_pool_free(cesa_dev->dma->cache_pool, creq->cache,
-		      creq->req.dma.cache_dma);
-}
-
-static inline void mv_cesa_ahash_std_free_cache(struct mv_cesa_ahash_req *creq)
-{
-	kfree(creq->cache);
-}
-
-static void mv_cesa_ahash_free_cache(struct mv_cesa_ahash_req *creq)
+static inline void
+mv_cesa_ahash_dma_free_cache(struct mv_cesa_ahash_dma_req *req)
 {
-	if (!creq->cache)
+	if (!req->cache)
 		return;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_ahash_dma_free_cache(creq);
-	else
-		mv_cesa_ahash_std_free_cache(creq);
-
-	creq->cache = NULL;
+	dma_pool_free(cesa_dev->dma->cache_pool, req->cache,
+		      req->cache_dma);
 }
 
 static int mv_cesa_ahash_dma_alloc_padding(struct mv_cesa_ahash_dma_req *req,
@@ -146,6 +102,7 @@ static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *req)
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
+	mv_cesa_ahash_dma_free_cache(&creq->req.dma);
 	mv_cesa_dma_cleanup(&creq->req.dma.base);
 }
 
@@ -161,8 +118,6 @@ static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	mv_cesa_ahash_free_cache(creq);
-
 	if (creq->req.base.type == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_last_cleanup(req);
 }
@@ -445,14 +400,6 @@ static inline int mv_cesa_ahash_cra_init(struct crypto_tfm *tfm)
 static int mv_cesa_ahash_cache_req(struct ahash_request *req, bool *cached)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	int ret;
-
-	if (((creq->cache_ptr + req->nbytes) & CESA_HASH_BLOCK_SIZE_MSK) &&
-	    !creq->last_req) {
-		ret = mv_cesa_ahash_alloc_cache(req);
-		if (ret)
-			return ret;
-	}
 
 	if (creq->cache_ptr + req->nbytes < 64 && !creq->last_req) {
 		*cached = true;
@@ -505,10 +452,17 @@ mv_cesa_ahash_dma_add_cache(struct mv_cesa_tdma_chain *chain,
 			    gfp_t flags)
 {
 	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	int ret;
 
 	if (!creq->cache_ptr)
 		return 0;
 
+	ret = mv_cesa_ahash_dma_alloc_cache(ahashdreq, flags);
+	if (ret)
+		return ret;
+
+	memcpy(ahashdreq->cache, creq->cache, creq->cache_ptr);
+
 	return mv_cesa_dma_add_data_transfer(chain,
 					     CESA_SA_DATA_SRAM_OFFSET,
 					     ahashdreq->cache_dma,
@@ -848,10 +802,6 @@ static int mv_cesa_ahash_import(struct ahash_request *req, const void *hash,
 	if (!cache_ptr)
 		return 0;
 
-	ret = mv_cesa_ahash_alloc_cache(req);
-	if (ret)
-		return ret;
-
 	memcpy(creq->cache, cache, cache_ptr);
 	creq->cache_ptr = cache_ptr;
 
@@ -860,9 +810,14 @@ static int mv_cesa_ahash_import(struct ahash_request *req, const void *hash,
 
 static int mv_cesa_md5_init(struct ahash_request *req)
 {
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx tmpl = { };
 
 	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_MD5);
+	creq->state[0] = MD5_H0;
+	creq->state[1] = MD5_H1;
+	creq->state[2] = MD5_H2;
+	creq->state[3] = MD5_H3;
 
 	mv_cesa_ahash_init(req, &tmpl, true);
 
@@ -923,9 +878,15 @@ struct ahash_alg mv_md5_alg = {
 
 static int mv_cesa_sha1_init(struct ahash_request *req)
 {
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx tmpl = { };
 
 	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA1);
+	creq->state[0] = SHA1_H0;
+	creq->state[1] = SHA1_H1;
+	creq->state[2] = SHA1_H2;
+	creq->state[3] = SHA1_H3;
+	creq->state[4] = SHA1_H4;
 
 	mv_cesa_ahash_init(req, &tmpl, false);
 
@@ -986,9 +947,18 @@ struct ahash_alg mv_sha1_alg = {
 
 static int mv_cesa_sha256_init(struct ahash_request *req)
 {
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx tmpl = { };
 
 	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA256);
+	creq->state[0] = SHA256_H0;
+	creq->state[1] = SHA256_H1;
+	creq->state[2] = SHA256_H2;
+	creq->state[3] = SHA256_H3;
+	creq->state[4] = SHA256_H4;
+	creq->state[5] = SHA256_H5;
+	creq->state[6] = SHA256_H6;
+	creq->state[7] = SHA256_H7;
 
 	mv_cesa_ahash_init(req, &tmpl, false);
 
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 046c1c454..d94e25df5 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -308,7 +308,7 @@ int nx842_crypto_compress(struct crypto_tfm *tfm,
 		h = !n && add_header ? hdrsize : 0;
 
 		if (ignore)
-			pr_warn("interal error, ignore is set %x\n", ignore);
+			pr_warn("internal error, ignore is set %x\n", ignore);
 
 		ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h);
 		if (ret)
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index dd355bd19..d420ec751 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -36,6 +36,7 @@
 #include <linux/interrupt.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 
 #define DST_MAXBURST			4
 #define DMA_MIN				(DST_MAXBURST * sizeof(u32))
@@ -152,13 +153,10 @@ struct omap_aes_dev {
 	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;
+	struct crypto_engine		*engine;
 
 	/*
 	 * total is used by PIO mode for book keeping so introduce
@@ -532,9 +530,7 @@ static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 
 	pr_debug("err: %d\n", err);
 
-	dd->flags &= ~FLAGS_BUSY;
-
-	req->base.complete(&req->base, err);
+	crypto_finalize_request(dd->engine, req, err);
 }
 
 static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
@@ -604,34 +600,25 @@ static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 }
 
 static int omap_aes_handle_queue(struct omap_aes_dev *dd,
-			       struct ablkcipher_request *req)
+				 struct ablkcipher_request *req)
 {
-	struct crypto_async_request *async_req, *backlog;
-	struct omap_aes_ctx *ctx;
-	struct omap_aes_reqctx *rctx;
-	unsigned long flags;
-	int err, ret = 0, len;
-
-	spin_lock_irqsave(&dd->lock, flags);
 	if (req)
-		ret = ablkcipher_enqueue_request(&dd->queue, req);
-	if (dd->flags & 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 |= FLAGS_BUSY;
-	spin_unlock_irqrestore(&dd->lock, flags);
+		return crypto_transfer_request_to_engine(dd->engine, req);
 
-	if (!async_req)
-		return ret;
+	return 0;
+}
 
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
+static int omap_aes_prepare_req(struct crypto_engine *engine,
+				struct ablkcipher_request *req)
+{
+	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
+	struct omap_aes_reqctx *rctx;
+	int len;
 
-	req = ablkcipher_request_cast(async_req);
+	if (!dd)
+		return -ENODEV;
 
 	/* assign new request to device */
 	dd->req = req;
@@ -662,16 +649,20 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	dd->ctx = ctx;
 	ctx->dd = dd;
 
-	err = omap_aes_write_ctrl(dd);
-	if (!err)
-		err = omap_aes_crypt_dma_start(dd);
-	if (err) {
-		/* aes_task will not finish it, so do it here */
-		omap_aes_finish_req(dd, err);
-		tasklet_schedule(&dd->queue_task);
-	}
+	return omap_aes_write_ctrl(dd);
+}
 
-	return ret; /* return ret, which is enqueue return value */
+static int omap_aes_crypt_req(struct crypto_engine *engine,
+			      struct ablkcipher_request *req)
+{
+	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
+
+	if (!dd)
+		return -ENODEV;
+
+	return omap_aes_crypt_dma_start(dd);
 }
 
 static void omap_aes_done_task(unsigned long data)
@@ -704,18 +695,10 @@ static void omap_aes_done_task(unsigned long data)
 	}
 
 	omap_aes_finish_req(dd, 0);
-	omap_aes_handle_queue(dd, NULL);
 
 	pr_debug("exit\n");
 }
 
-static void omap_aes_queue_task(unsigned long data)
-{
-	struct omap_aes_dev *dd = (struct omap_aes_dev *)data;
-
-	omap_aes_handle_queue(dd, NULL);
-}
-
 static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 {
 	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
@@ -1175,9 +1158,6 @@ static int omap_aes_probe(struct platform_device *pdev)
 	dd->dev = dev;
 	platform_set_drvdata(pdev, dd);
 
-	spin_lock_init(&dd->lock);
-	crypto_init_queue(&dd->queue, OMAP_AES_QUEUE_LENGTH);
-
 	err = (dev->of_node) ? omap_aes_get_res_of(dd, dev, &res) :
 			       omap_aes_get_res_pdev(dd, pdev, &res);
 	if (err)
@@ -1209,7 +1189,6 @@ static int omap_aes_probe(struct platform_device *pdev)
 		 (reg & dd->pdata->minor_mask) >> dd->pdata->minor_shift);
 
 	tasklet_init(&dd->done_task, omap_aes_done_task, (unsigned long)dd);
-	tasklet_init(&dd->queue_task, omap_aes_queue_task, (unsigned long)dd);
 
 	err = omap_aes_dma_init(dd);
 	if (err && AES_REG_IRQ_STATUS(dd) && AES_REG_IRQ_ENABLE(dd)) {
@@ -1250,7 +1229,20 @@ static int omap_aes_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* Initialize crypto engine */
+	dd->engine = crypto_engine_alloc_init(dev, 1);
+	if (!dd->engine)
+		goto err_algs;
+
+	dd->engine->prepare_request = omap_aes_prepare_req;
+	dd->engine->crypt_one_request = omap_aes_crypt_req;
+	err = crypto_engine_start(dd->engine);
+	if (err)
+		goto err_engine;
+
 	return 0;
+err_engine:
+	crypto_engine_exit(dd->engine);
 err_algs:
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
@@ -1260,7 +1252,6 @@ err_algs:
 		omap_aes_dma_cleanup(dd);
 err_irq:
 	tasklet_kill(&dd->done_task);
-	tasklet_kill(&dd->queue_task);
 	pm_runtime_disable(dev);
 err_res:
 	dd = NULL;
@@ -1286,8 +1277,8 @@ static int omap_aes_remove(struct platform_device *pdev)
 			crypto_unregister_alg(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
+	crypto_engine_exit(dd->engine);
 	tasklet_kill(&dd->done_task);
-	tasklet_kill(&dd->queue_task);
 	omap_aes_dma_cleanup(dd);
 	pm_runtime_disable(dd->dev);
 	dd = NULL;
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index f96d427e5..5a07208ce 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -55,8 +55,8 @@
 
 #define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
 #define ADF_DH895XCCVF_DEVICE_NAME "dh895xccvf"
-#define ADF_C62X_DEVICE_NAME "c62x"
-#define ADF_C62XVF_DEVICE_NAME "c62xvf"
+#define ADF_C62X_DEVICE_NAME "c6xx"
+#define ADF_C62XVF_DEVICE_NAME "c6xxvf"
 #define ADF_C3XXX_DEVICE_NAME "c3xxx"
 #define ADF_C3XXXVF_DEVICE_NAME "c3xxxvf"
 #define ADF_DH895XCC_PCI_DEVICE_ID 0x435
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index e78a1d7d8..b40d9c8da 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -121,7 +121,6 @@ static void adf_device_reset_worker(struct work_struct *work)
 	adf_dev_restarting_notify(accel_dev);
 	adf_dev_stop(accel_dev);
 	adf_dev_shutdown(accel_dev);
-	adf_dev_restore(accel_dev);
 	if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) {
 		/* The device hanged and we can't restart it so stop here */
 		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/qat/qat_common/adf_cfg_user.h
index ef5988afd..b5484bfa6 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_user.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_user.h
@@ -58,7 +58,7 @@ struct adf_user_cfg_key_val {
 		uint64_t padding3;
 	};
 	enum adf_cfg_val_type type;
-};
+} __packed;
 
 struct adf_user_cfg_section {
 	char name[ADF_CFG_MAX_SECTION_LEN_IN_BYTES];
@@ -70,7 +70,7 @@ struct adf_user_cfg_section {
 		struct adf_user_cfg_section *next;
 		uint64_t padding3;
 	};
-};
+} __packed;
 
 struct adf_user_cfg_ctl_data {
 	union {
@@ -78,5 +78,5 @@ struct adf_user_cfg_ctl_data {
 		uint64_t padding;
 	};
 	uint8_t device_id;
-};
+} __packed;
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 0e82ce3c3..976b01e58 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -236,6 +236,8 @@ void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
 				 uint32_t vf_mask);
 void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
 void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
+int adf_init_pf_wq(void);
+void adf_exit_pf_wq(void);
 #else
 static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 {
@@ -253,5 +255,14 @@ static inline void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
 static inline void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
 {
 }
+
+static inline int adf_init_pf_wq(void)
+{
+	return 0;
+}
+
+static inline void adf_exit_pf_wq(void)
+{
+}
 #endif
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index 5c897e6e7..3c3f94829 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -462,12 +462,17 @@ static int __init adf_register_ctl_device_driver(void)
 	if (adf_init_aer())
 		goto err_aer;
 
+	if (adf_init_pf_wq())
+		goto err_pf_wq;
+
 	if (qat_crypto_register())
 		goto err_crypto_register;
 
 	return 0;
 
 err_crypto_register:
+	adf_exit_pf_wq();
+err_pf_wq:
 	adf_exit_aer();
 err_aer:
 	adf_chr_drv_destroy();
@@ -480,6 +485,7 @@ static void __exit adf_unregister_ctl_device_driver(void)
 {
 	adf_chr_drv_destroy();
 	adf_exit_aer();
+	adf_exit_pf_wq();
 	qat_crypto_unregister();
 	adf_clean_vf_map(false);
 	mutex_destroy(&adf_ctl_lock);
diff --git a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
index f267d9e42..d7dd18d9b 100644
--- a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
+++ b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
@@ -49,7 +49,6 @@
 #include "adf_transport_internal.h"
 
 #define ADF_ARB_NUM 4
-#define ADF_ARB_REQ_RING_NUM 8
 #define ADF_ARB_REG_SIZE 0x4
 #define ADF_ARB_WTR_SIZE 0x20
 #define ADF_ARB_OFFSET 0x30000
@@ -64,15 +63,6 @@
 	ADF_CSR_WR(csr_addr, ADF_ARB_RINGSRVARBEN_OFFSET + \
 	(ADF_ARB_REG_SLOT * index), value)
 
-#define WRITE_CSR_ARB_RESPORDERING(csr_addr, index, value) \
-	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
-	ADF_ARB_RO_EN_OFFSET) + (ADF_ARB_REG_SIZE * index), value)
-
-#define WRITE_CSR_ARB_WEIGHT(csr_addr, arb, index, value) \
-	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
-	ADF_ARB_WTR_OFFSET) + (ADF_ARB_WTR_SIZE * arb) + \
-	(ADF_ARB_REG_SIZE * index), value)
-
 #define WRITE_CSR_ARB_SARCONFIG(csr_addr, index, value) \
 	ADF_CSR_WR(csr_addr, ADF_ARB_OFFSET + \
 	(ADF_ARB_REG_SIZE * index), value)
@@ -99,15 +89,6 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 	for (arb = 0; arb < ADF_ARB_NUM; arb++)
 		WRITE_CSR_ARB_SARCONFIG(csr, arb, arb_cfg);
 
-	/* Setup service weighting */
-	for (arb = 0; arb < ADF_ARB_NUM; arb++)
-		for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
-			WRITE_CSR_ARB_WEIGHT(csr, arb, i, 0xFFFFFFFF);
-
-	/* Setup ring response ordering */
-	for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
-		WRITE_CSR_ARB_RESPORDERING(csr, i, 0xFFFFFFFF);
-
 	/* Setup worker queue registers */
 	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WQCFG(csr, i, i);
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
index 1117a8b58..38a0415e7 100644
--- a/drivers/crypto/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/qat/qat_common/adf_sriov.c
@@ -119,11 +119,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev)
 	int i;
 	u32 reg;
 
-	/* Workqueue for PF2VF responses */
-	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
-	if (!pf2vf_resp_wq)
-		return -ENOMEM;
-
 	for (i = 0, vf_info = accel_dev->pf.vf_info; i < totalvfs;
 	     i++, vf_info++) {
 		/* This ptr will be populated when VFs will be created */
@@ -216,11 +211,6 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 
 	kfree(accel_dev->pf.vf_info);
 	accel_dev->pf.vf_info = NULL;
-
-	if (pf2vf_resp_wq) {
-		destroy_workqueue(pf2vf_resp_wq);
-		pf2vf_resp_wq = NULL;
-	}
 }
 EXPORT_SYMBOL_GPL(adf_disable_sriov);
 
@@ -304,3 +294,19 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 	return numvfs;
 }
 EXPORT_SYMBOL_GPL(adf_sriov_configure);
+
+int __init adf_init_pf_wq(void)
+{
+	/* Workqueue for PF2VF responses */
+	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
+
+	return !pf2vf_resp_wq ? -ENOMEM : 0;
+}
+
+void adf_exit_pf_wq(void)
+{
+	if (pf2vf_resp_wq) {
+		destroy_workqueue(pf2vf_resp_wq);
+		pf2vf_resp_wq = NULL;
+	}
+}
diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
index d97db9909..5d1ee7e53 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_uclo.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
@@ -112,27 +112,27 @@ enum icp_qat_uof_mem_region {
 };
 
 enum icp_qat_uof_regtype {
-	ICP_NO_DEST,
-	ICP_GPA_REL,
-	ICP_GPA_ABS,
-	ICP_GPB_REL,
-	ICP_GPB_ABS,
-	ICP_SR_REL,
-	ICP_SR_RD_REL,
-	ICP_SR_WR_REL,
-	ICP_SR_ABS,
-	ICP_SR_RD_ABS,
-	ICP_SR_WR_ABS,
-	ICP_DR_REL,
-	ICP_DR_RD_REL,
-	ICP_DR_WR_REL,
-	ICP_DR_ABS,
-	ICP_DR_RD_ABS,
-	ICP_DR_WR_ABS,
-	ICP_LMEM,
-	ICP_LMEM0,
-	ICP_LMEM1,
-	ICP_NEIGH_REL,
+	ICP_NO_DEST	= 0,
+	ICP_GPA_REL	= 1,
+	ICP_GPA_ABS	= 2,
+	ICP_GPB_REL	= 3,
+	ICP_GPB_ABS	= 4,
+	ICP_SR_REL	= 5,
+	ICP_SR_RD_REL	= 6,
+	ICP_SR_WR_REL	= 7,
+	ICP_SR_ABS	= 8,
+	ICP_SR_RD_ABS	= 9,
+	ICP_SR_WR_ABS	= 10,
+	ICP_DR_REL	= 19,
+	ICP_DR_RD_REL	= 20,
+	ICP_DR_WR_REL	= 21,
+	ICP_DR_ABS	= 22,
+	ICP_DR_RD_ABS	= 23,
+	ICP_DR_WR_ABS	= 24,
+	ICP_LMEM	= 26,
+	ICP_LMEM0	= 27,
+	ICP_LMEM1	= 28,
+	ICP_NEIGH_REL	= 31,
 };
 
 enum icp_qat_css_fwtype {
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 59e4c3af1..1e8852a8a 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -1064,8 +1064,7 @@ static int qat_alg_aead_init(struct crypto_aead *tfm,
 	if (IS_ERR(ctx->hash_tfm))
 		return PTR_ERR(ctx->hash_tfm);
 	ctx->qat_hash_alg = hash;
-	crypto_aead_set_reqsize(tfm, sizeof(struct aead_request) +
-				     sizeof(struct qat_crypto_request));
+	crypto_aead_set_reqsize(tfm, sizeof(struct qat_crypto_request));
 	return 0;
 }
 
@@ -1114,8 +1113,7 @@ static int qat_alg_ablkcipher_init(struct crypto_tfm *tfm)
 	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	spin_lock_init(&ctx->lock);
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
-					sizeof(struct qat_crypto_request);
+	tfm->crt_ablkcipher.reqsize = sizeof(struct qat_crypto_request);
 	ctx->tfm = tfm;
 	return 0;
 }
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 51c594fda..e5c0727d4 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -340,14 +340,16 @@ static int qat_rsa_enc(struct akcipher_request *req)
 
 	if (!ret)
 		return -EINPROGRESS;
-unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.enc.m);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.enc.m))
-			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
-					 DMA_TO_DEVICE);
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
@@ -356,15 +358,14 @@ unmap_dst:
 		if (!dma_mapping_error(dev, qat_req->out.enc.c))
 			dma_unmap_single(dev, qat_req->out.enc.c, ctx->key_sz,
 					 DMA_FROM_DEVICE);
-unmap_in_params:
-	if (!dma_mapping_error(dev, qat_req->phy_in))
-		dma_unmap_single(dev, qat_req->phy_in,
-				 sizeof(struct qat_rsa_input_params),
-				 DMA_TO_DEVICE);
-	if (!dma_mapping_error(dev, qat_req->phy_out))
-		dma_unmap_single(dev, qat_req->phy_out,
-				 sizeof(struct qat_rsa_output_params),
-				 DMA_TO_DEVICE);
+unmap_src:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.enc.m);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.enc.m))
+			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
+					 DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -472,14 +473,16 @@ static int qat_rsa_dec(struct akcipher_request *req)
 
 	if (!ret)
 		return -EINPROGRESS;
-unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.dec.c);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.dec.c))
-			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
-					 DMA_TO_DEVICE);
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
@@ -488,15 +491,14 @@ unmap_dst:
 		if (!dma_mapping_error(dev, qat_req->out.dec.m))
 			dma_unmap_single(dev, qat_req->out.dec.m, ctx->key_sz,
 					 DMA_FROM_DEVICE);
-unmap_in_params:
-	if (!dma_mapping_error(dev, qat_req->phy_in))
-		dma_unmap_single(dev, qat_req->phy_in,
-				 sizeof(struct qat_rsa_input_params),
-				 DMA_TO_DEVICE);
-	if (!dma_mapping_error(dev, qat_req->phy_out))
-		dma_unmap_single(dev, qat_req->phy_out,
-				 sizeof(struct qat_rsa_output_params),
-				 DMA_TO_DEVICE);
+unmap_src:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.dec.c);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.dec.c))
+			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
+					 DMA_TO_DEVICE);
 	return ret;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index 25d15f19c..9b961b37a 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -688,7 +688,7 @@ static int qat_uclo_map_ae(struct icp_qat_fw_loader_handle *handle, int max_ae)
 	int mflag = 0;
 	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
 
-	for (ae = 0; ae <= max_ae; ae++) {
+	for (ae = 0; ae < max_ae; ae++) {
 		if (!test_bit(ae,
 			      (unsigned long *)&handle->hal_handle->ae_mask))
 			continue;
diff --git a/drivers/crypto/rockchip/Makefile b/drivers/crypto/rockchip/Makefile
index 7051c6c71..30f91297b 100644
--- a/drivers/crypto/rockchip/Makefile
+++ b/drivers/crypto/rockchip/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rk_crypto.o
 rk_crypto-objs := rk3288_crypto.o \
 		  rk3288_crypto_ablkcipher.o \
+		  rk3288_crypto_ahash.o
diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c
index da9c73dce..af508258d 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.c
+++ b/drivers/crypto/rockchip/rk3288_crypto.c
@@ -208,6 +208,8 @@ static void rk_crypto_tasklet_cb(unsigned long data)
 
 	if (crypto_tfm_alg_type(async_req->tfm) == CRYPTO_ALG_TYPE_ABLKCIPHER)
 		dev->ablk_req = ablkcipher_request_cast(async_req);
+	else
+		dev->ahash_req = ahash_request_cast(async_req);
 	err = dev->start(dev);
 	if (err)
 		dev->complete(dev, err);
@@ -220,6 +222,9 @@ static struct rk_crypto_tmp *rk_cipher_algs[] = {
 	&rk_cbc_des_alg,
 	&rk_ecb_des3_ede_alg,
 	&rk_cbc_des3_ede_alg,
+	&rk_ahash_sha1,
+	&rk_ahash_sha256,
+	&rk_ahash_md5,
 };
 
 static int rk_crypto_register(struct rk_crypto_info *crypto_info)
@@ -229,15 +234,24 @@ static int rk_crypto_register(struct rk_crypto_info *crypto_info)
 
 	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
 		rk_cipher_algs[i]->dev = crypto_info;
-		err = crypto_register_alg(&rk_cipher_algs[i]->alg);
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			err = crypto_register_alg(
+					&rk_cipher_algs[i]->alg.crypto);
+		else
+			err = crypto_register_ahash(
+					&rk_cipher_algs[i]->alg.hash);
 		if (err)
 			goto err_cipher_algs;
 	}
 	return 0;
 
 err_cipher_algs:
-	for (k = 0; k < i; k++)
-		crypto_unregister_alg(&rk_cipher_algs[k]->alg);
+	for (k = 0; k < i; k++) {
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			crypto_unregister_alg(&rk_cipher_algs[k]->alg.crypto);
+		else
+			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
+	}
 	return err;
 }
 
@@ -245,8 +259,12 @@ static void rk_crypto_unregister(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++)
-		crypto_unregister_alg(&rk_cipher_algs[i]->alg);
+	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			crypto_unregister_alg(&rk_cipher_algs[i]->alg.crypto);
+		else
+			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
+	}
 }
 
 static void rk_crypto_action(void *data)
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
index e499c2c6c..d7b71fea3 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.h
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -6,6 +6,10 @@
 #include <crypto/algapi.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <crypto/internal/hash.h>
+
+#include <crypto/md5.h>
+#include <crypto/sha.h>
 
 #define _SBF(v, f)			((v) << (f))
 
@@ -149,6 +153,28 @@
 #define RK_CRYPTO_TDES_KEY3_0		0x0130
 #define RK_CRYPTO_TDES_KEY3_1		0x0134
 
+/* HASH */
+#define RK_CRYPTO_HASH_CTRL		0x0180
+#define RK_CRYPTO_HASH_SWAP_DO		BIT(3)
+#define RK_CRYPTO_HASH_SWAP_DI		BIT(2)
+#define RK_CRYPTO_HASH_SHA1		_SBF(0x00, 0)
+#define RK_CRYPTO_HASH_MD5		_SBF(0x01, 0)
+#define RK_CRYPTO_HASH_SHA256		_SBF(0x02, 0)
+#define RK_CRYPTO_HASH_PRNG		_SBF(0x03, 0)
+
+#define RK_CRYPTO_HASH_STS		0x0184
+#define RK_CRYPTO_HASH_DONE		BIT(0)
+
+#define RK_CRYPTO_HASH_MSG_LEN		0x0188
+#define RK_CRYPTO_HASH_DOUT_0		0x018c
+#define RK_CRYPTO_HASH_DOUT_1		0x0190
+#define RK_CRYPTO_HASH_DOUT_2		0x0194
+#define RK_CRYPTO_HASH_DOUT_3		0x0198
+#define RK_CRYPTO_HASH_DOUT_4		0x019c
+#define RK_CRYPTO_HASH_DOUT_5		0x01a0
+#define RK_CRYPTO_HASH_DOUT_6		0x01a4
+#define RK_CRYPTO_HASH_DOUT_7		0x01a8
+
 #define CRYPTO_READ(dev, offset)		  \
 		readl_relaxed(((dev)->reg + (offset)))
 #define CRYPTO_WRITE(dev, offset, val)	  \
@@ -166,6 +192,7 @@ struct rk_crypto_info {
 	struct crypto_queue		queue;
 	struct tasklet_struct		crypto_tasklet;
 	struct ablkcipher_request	*ablk_req;
+	struct ahash_request		*ahash_req;
 	/* device lock */
 	spinlock_t			lock;
 
@@ -195,15 +222,36 @@ struct rk_crypto_info {
 	void (*unload_data)(struct rk_crypto_info *dev);
 };
 
+/* the private variable of hash */
+struct rk_ahash_ctx {
+	struct rk_crypto_info		*dev;
+	/* for fallback */
+	struct crypto_ahash		*fallback_tfm;
+};
+
+/* the privete variable of hash for fallback */
+struct rk_ahash_rctx {
+	struct ahash_request		fallback_req;
+};
+
 /* the private variable of cipher */
 struct rk_cipher_ctx {
 	struct rk_crypto_info		*dev;
 	unsigned int			keylen;
 };
 
+enum alg_type {
+	ALG_TYPE_HASH,
+	ALG_TYPE_CIPHER,
+};
+
 struct rk_crypto_tmp {
-	struct rk_crypto_info *dev;
-	struct crypto_alg alg;
+	struct rk_crypto_info		*dev;
+	union {
+		struct crypto_alg	crypto;
+		struct ahash_alg	hash;
+	} alg;
+	enum alg_type			type;
 };
 
 extern struct rk_crypto_tmp rk_ecb_aes_alg;
@@ -213,4 +261,8 @@ extern struct rk_crypto_tmp rk_cbc_des_alg;
 extern struct rk_crypto_tmp rk_ecb_des3_ede_alg;
 extern struct rk_crypto_tmp rk_cbc_des3_ede_alg;
 
+extern struct rk_crypto_tmp rk_ahash_sha1;
+extern struct rk_crypto_tmp rk_ahash_sha256;
+extern struct rk_crypto_tmp rk_ahash_md5;
+
 #endif
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
index d98b681f6..b5a3afe22 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
@@ -336,7 +336,7 @@ static int rk_ablk_cra_init(struct crypto_tfm *tfm)
 	struct crypto_alg *alg = tfm->__crt_alg;
 	struct rk_crypto_tmp *algt;
 
-	algt = container_of(alg, struct rk_crypto_tmp, alg);
+	algt = container_of(alg, struct rk_crypto_tmp, alg.crypto);
 
 	ctx->dev = algt->dev;
 	ctx->dev->align_size = crypto_tfm_alg_alignmask(tfm) + 1;
@@ -357,7 +357,8 @@ static void rk_ablk_cra_exit(struct crypto_tfm *tfm)
 }
 
 struct rk_crypto_tmp rk_ecb_aes_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(aes)",
 		.cra_driver_name	= "ecb-aes-rk",
 		.cra_priority		= 300,
@@ -381,7 +382,8 @@ struct rk_crypto_tmp rk_ecb_aes_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_aes_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(aes)",
 		.cra_driver_name	= "cbc-aes-rk",
 		.cra_priority		= 300,
@@ -406,7 +408,8 @@ struct rk_crypto_tmp rk_cbc_aes_alg = {
 };
 
 struct rk_crypto_tmp rk_ecb_des_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(des)",
 		.cra_driver_name	= "ecb-des-rk",
 		.cra_priority		= 300,
@@ -430,7 +433,8 @@ struct rk_crypto_tmp rk_ecb_des_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_des_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(des)",
 		.cra_driver_name	= "cbc-des-rk",
 		.cra_priority		= 300,
@@ -455,7 +459,8 @@ struct rk_crypto_tmp rk_cbc_des_alg = {
 };
 
 struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(des3_ede)",
 		.cra_driver_name	= "ecb-des3-ede-rk",
 		.cra_priority		= 300,
@@ -480,7 +485,8 @@ struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_des3_ede_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(des3_ede)",
 		.cra_driver_name	= "cbc-des3-ede-rk",
 		.cra_priority		= 300,
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
new file mode 100644
index 000000000..718588219
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
@@ -0,0 +1,404 @@
+/*
+ * Crypto acceleration support for Rockchip RK3288
+ *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Zain Wang <zain.wang@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * Some ideas are from marvell/cesa.c and s5p-sss.c driver.
+ */
+#include "rk3288_crypto.h"
+
+/*
+ * IC can not process zero message hash,
+ * so we put the fixed hash out when met zero message.
+ */
+
+static int zero_message_process(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	int rk_digest_size = crypto_ahash_digestsize(tfm);
+
+	switch (rk_digest_size) {
+	case SHA1_DIGEST_SIZE:
+		memcpy(req->result, sha1_zero_message_hash, rk_digest_size);
+		break;
+	case SHA256_DIGEST_SIZE:
+		memcpy(req->result, sha256_zero_message_hash, rk_digest_size);
+		break;
+	case MD5_DIGEST_SIZE:
+		memcpy(req->result, md5_zero_message_hash, rk_digest_size);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void rk_ahash_crypto_complete(struct rk_crypto_info *dev, int err)
+{
+	if (dev->ahash_req->base.complete)
+		dev->ahash_req->base.complete(&dev->ahash_req->base, err);
+}
+
+static void rk_ahash_reg_init(struct rk_crypto_info *dev)
+{
+	int reg_status = 0;
+
+	reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) |
+		     RK_CRYPTO_HASH_FLUSH | _SBF(0xffff, 16);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, reg_status);
+
+	reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL);
+	reg_status &= (~RK_CRYPTO_HASH_FLUSH);
+	reg_status |= _SBF(0xffff, 16);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, reg_status);
+
+	memset_io(dev->reg + RK_CRYPTO_HASH_DOUT_0, 0, 32);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTENA, RK_CRYPTO_HRDMA_ERR_ENA |
+					    RK_CRYPTO_HRDMA_DONE_ENA);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTSTS, RK_CRYPTO_HRDMA_ERR_INT |
+					    RK_CRYPTO_HRDMA_DONE_INT);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_HASH_CTRL, dev->mode |
+					       RK_CRYPTO_HASH_SWAP_DO);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_CONF, RK_CRYPTO_BYTESWAP_HRFIFO |
+					  RK_CRYPTO_BYTESWAP_BRFIFO |
+					  RK_CRYPTO_BYTESWAP_BTFIFO);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_HASH_MSG_LEN, dev->total);
+}
+
+static int rk_ahash_init(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_init(&rctx->fallback_req);
+}
+
+static int rk_ahash_update(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+	rctx->fallback_req.nbytes = req->nbytes;
+	rctx->fallback_req.src = req->src;
+
+	return crypto_ahash_update(&rctx->fallback_req);
+}
+
+static int rk_ahash_final(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+	rctx->fallback_req.result = req->result;
+
+	return crypto_ahash_final(&rctx->fallback_req);
+}
+
+static int rk_ahash_finup(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rctx->fallback_req.nbytes = req->nbytes;
+	rctx->fallback_req.src = req->src;
+	rctx->fallback_req.result = req->result;
+
+	return crypto_ahash_finup(&rctx->fallback_req);
+}
+
+static int rk_ahash_import(struct ahash_request *req, const void *in)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_import(&rctx->fallback_req, in);
+}
+
+static int rk_ahash_export(struct ahash_request *req, void *out)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_export(&rctx->fallback_req, out);
+}
+
+static int rk_ahash_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+	struct rk_crypto_info *dev = NULL;
+	unsigned long flags;
+	int ret;
+
+	if (!req->nbytes)
+		return zero_message_process(req);
+
+	dev = tctx->dev;
+	dev->total = req->nbytes;
+	dev->left_bytes = req->nbytes;
+	dev->aligned = 0;
+	dev->mode = 0;
+	dev->align_size = 4;
+	dev->sg_dst = NULL;
+	dev->sg_src = req->src;
+	dev->first = req->src;
+	dev->nents = sg_nents(req->src);
+
+	switch (crypto_ahash_digestsize(tfm)) {
+	case SHA1_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_SHA1;
+		break;
+	case SHA256_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_SHA256;
+		break;
+	case MD5_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_MD5;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rk_ahash_reg_init(dev);
+
+	spin_lock_irqsave(&dev->lock, flags);
+	ret = crypto_enqueue_request(&dev->queue, &req->base);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	tasklet_schedule(&dev->crypto_tasklet);
+
+	/*
+	 * it will take some time to process date after last dma transmission.
+	 *
+	 * waiting time is relative with the last date len,
+	 * so cannot set a fixed time here.
+	 * 10-50 makes system not call here frequently wasting
+	 * efficiency, and make it response quickly when dma
+	 * complete.
+	 */
+	while (!CRYPTO_READ(dev, RK_CRYPTO_HASH_STS))
+		usleep_range(10, 50);
+
+	memcpy_fromio(req->result, dev->reg + RK_CRYPTO_HASH_DOUT_0,
+		      crypto_ahash_digestsize(tfm));
+
+	return 0;
+}
+
+static void crypto_ahash_dma_start(struct rk_crypto_info *dev)
+{
+	CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAS, dev->addr_in);
+	CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAL, (dev->count + 3) / 4);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_HASH_START |
+					  (RK_CRYPTO_HASH_START << 16));
+}
+
+static int rk_ahash_set_data_start(struct rk_crypto_info *dev)
+{
+	int err;
+
+	err = dev->load_data(dev, dev->sg_src, NULL);
+	if (!err)
+		crypto_ahash_dma_start(dev);
+	return err;
+}
+
+static int rk_ahash_start(struct rk_crypto_info *dev)
+{
+	return rk_ahash_set_data_start(dev);
+}
+
+static int rk_ahash_crypto_rx(struct rk_crypto_info *dev)
+{
+	int err = 0;
+
+	dev->unload_data(dev);
+	if (dev->left_bytes) {
+		if (dev->aligned) {
+			if (sg_is_last(dev->sg_src)) {
+				dev_warn(dev->dev, "[%s:%d], Lack of data\n",
+					 __func__, __LINE__);
+				err = -ENOMEM;
+				goto out_rx;
+			}
+			dev->sg_src = sg_next(dev->sg_src);
+		}
+		err = rk_ahash_set_data_start(dev);
+	} else {
+		dev->complete(dev, 0);
+	}
+
+out_rx:
+	return err;
+}
+
+static int rk_cra_hash_init(struct crypto_tfm *tfm)
+{
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm);
+	struct rk_crypto_tmp *algt;
+	struct ahash_alg *alg = __crypto_ahash_alg(tfm->__crt_alg);
+
+	const char *alg_name = crypto_tfm_alg_name(tfm);
+
+	algt = container_of(alg, struct rk_crypto_tmp, alg.hash);
+
+	tctx->dev = algt->dev;
+	tctx->dev->addr_vir = (void *)__get_free_page(GFP_KERNEL);
+	if (!tctx->dev->addr_vir) {
+		dev_err(tctx->dev->dev, "failed to kmalloc for addr_vir\n");
+		return -ENOMEM;
+	}
+	tctx->dev->start = rk_ahash_start;
+	tctx->dev->update = rk_ahash_crypto_rx;
+	tctx->dev->complete = rk_ahash_crypto_complete;
+
+	/* for fallback */
+	tctx->fallback_tfm = crypto_alloc_ahash(alg_name, 0,
+					       CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(tctx->fallback_tfm)) {
+		dev_err(tctx->dev->dev, "Could not load fallback driver.\n");
+		return PTR_ERR(tctx->fallback_tfm);
+	}
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct rk_ahash_rctx) +
+				 crypto_ahash_reqsize(tctx->fallback_tfm));
+
+	return tctx->dev->enable_clk(tctx->dev);
+}
+
+static void rk_cra_hash_exit(struct crypto_tfm *tfm)
+{
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm);
+
+	free_page((unsigned long)tctx->dev->addr_vir);
+	return tctx->dev->disable_clk(tctx->dev);
+}
+
+struct rk_crypto_tmp rk_ahash_sha1 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = SHA1_DIGEST_SIZE,
+			 .statesize = sizeof(struct sha1_state),
+			 .base = {
+				  .cra_name = "sha1",
+				  .cra_driver_name = "rk-sha1",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA1_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			 }
+	}
+};
+
+struct rk_crypto_tmp rk_ahash_sha256 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = SHA256_DIGEST_SIZE,
+			 .statesize = sizeof(struct sha256_state),
+			 .base = {
+				  .cra_name = "sha256",
+				  .cra_driver_name = "rk-sha256",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA256_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			 }
+	}
+};
+
+struct rk_crypto_tmp rk_ahash_md5 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = MD5_DIGEST_SIZE,
+			 .statesize = sizeof(struct md5_state),
+			 .base = {
+				  .cra_name = "md5",
+				  .cra_driver_name = "rk-md5",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA1_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			}
+	}
+};
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index f214a8755..5f161a977 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -224,6 +224,7 @@ static inline struct samsung_aes_variant *find_s5p_sss_version
 {
 	if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) {
 		const struct of_device_id *match;
+
 		match = of_match_node(s5p_sss_dt_match,
 					pdev->dev.of_node);
 		return (struct samsung_aes_variant *)match->data;
@@ -382,7 +383,7 @@ static void s5p_set_aes(struct s5p_aes_dev *dev,
 	void __iomem *keystart;
 
 	if (iv)
-		memcpy(dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), iv, 0x10);
+		memcpy_toio(dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), iv, 0x10);
 
 	if (keylen == AES_KEYSIZE_256)
 		keystart = dev->aes_ioaddr + SSS_REG_AES_KEY_DATA(0);
@@ -391,13 +392,12 @@ static void s5p_set_aes(struct s5p_aes_dev *dev,
 	else
 		keystart = dev->aes_ioaddr + SSS_REG_AES_KEY_DATA(4);
 
-	memcpy(keystart, key, keylen);
+	memcpy_toio(keystart, key, keylen);
 }
 
 static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 {
 	struct ablkcipher_request  *req = dev->req;
-
 	uint32_t                    aes_control;
 	int                         err;
 	unsigned long               flags;
@@ -518,7 +518,7 @@ static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	struct s5p_aes_dev         *dev    = ctx->dev;
 
 	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
-		pr_err("request size is not exact amount of AES blocks\n");
+		dev_err(dev->dev, "request size is not exact amount of AES blocks\n");
 		return -EINVAL;
 	}
 
@@ -566,7 +566,7 @@ static int s5p_aes_cbc_decrypt(struct ablkcipher_request *req)
 
 static int s5p_aes_cra_init(struct crypto_tfm *tfm)
 {
-	struct s5p_aes_ctx  *ctx = crypto_tfm_ctx(tfm);
+	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	ctx->dev = s5p_dev;
 	tfm->crt_ablkcipher.reqsize = sizeof(struct s5p_aes_reqctx);
@@ -701,7 +701,7 @@ static int s5p_aes_probe(struct platform_device *pdev)
 			goto err_algs;
 	}
 
-	pr_info("s5p-sss driver registered\n");
+	dev_info(dev, "s5p-sss driver registered\n");
 
 	return 0;
 
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 6c4f91c5e..c3f3d89e4 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -182,7 +182,6 @@ struct sahara_sha_reqctx {
 	u8			buf[SAHARA_MAX_SHA_BLOCK_SIZE];
 	u8			rembuf[SAHARA_MAX_SHA_BLOCK_SIZE];
 	u8			context[SHA256_DIGEST_SIZE + 4];
-	struct mutex		mutex;
 	unsigned int		mode;
 	unsigned int		digest_size;
 	unsigned int		context_size;
@@ -1096,7 +1095,6 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last)
 	if (!req->nbytes && !last)
 		return 0;
 
-	mutex_lock(&rctx->mutex);
 	rctx->last = last;
 
 	if (!rctx->active) {
@@ -1109,7 +1107,6 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last)
 	mutex_unlock(&dev->queue_mutex);
 
 	wake_up_process(dev->kthread);
-	mutex_unlock(&rctx->mutex);
 
 	return ret;
 }
@@ -1137,8 +1134,6 @@ static int sahara_sha_init(struct ahash_request *req)
 	rctx->context_size = rctx->digest_size + 4;
 	rctx->active = 0;
 
-	mutex_init(&rctx->mutex);
-
 	return 0;
 }
 
@@ -1167,26 +1162,18 @@ static int sahara_sha_digest(struct ahash_request *req)
 
 static int sahara_sha_export(struct ahash_request *req, void *out)
 {
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
-	struct sahara_ctx *ctx = crypto_ahash_ctx(ahash);
 	struct sahara_sha_reqctx *rctx = ahash_request_ctx(req);
 
-	memcpy(out, ctx, sizeof(struct sahara_ctx));
-	memcpy(out + sizeof(struct sahara_sha_reqctx), rctx,
-	       sizeof(struct sahara_sha_reqctx));
+	memcpy(out, rctx, sizeof(struct sahara_sha_reqctx));
 
 	return 0;
 }
 
 static int sahara_sha_import(struct ahash_request *req, const void *in)
 {
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
-	struct sahara_ctx *ctx = crypto_ahash_ctx(ahash);
 	struct sahara_sha_reqctx *rctx = ahash_request_ctx(req);
 
-	memcpy(ctx, in, sizeof(struct sahara_ctx));
-	memcpy(rctx, in + sizeof(struct sahara_sha_reqctx),
-	       sizeof(struct sahara_sha_reqctx));
+	memcpy(rctx, in, sizeof(struct sahara_sha_reqctx));
 
 	return 0;
 }
@@ -1272,6 +1259,7 @@ static struct ahash_alg sha_v3_algs[] = {
 	.export		= sahara_sha_export,
 	.import		= sahara_sha_import,
 	.halg.digestsize	= SHA1_DIGEST_SIZE,
+	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
 	.halg.base	= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sahara-sha1",
@@ -1299,6 +1287,7 @@ static struct ahash_alg sha_v4_algs[] = {
 	.export		= sahara_sha_export,
 	.import		= sahara_sha_import,
 	.halg.digestsize	= SHA256_DIGEST_SIZE,
+	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
 	.halg.base	= {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sahara-sha256",
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index a19ee127e..3830d7c4e 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -35,6 +35,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq)
 	unsigned int todo;
 	struct sg_mapping_iter mi, mo;
 	unsigned int oi, oo; /* offset for in and out */
+	unsigned long flags;
 
 	if (areq->nbytes == 0)
 		return 0;
@@ -49,7 +50,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq)
 		return -EINVAL;
 	}
 
-	spin_lock_bh(&ss->slock);
+	spin_lock_irqsave(&ss->slock, flags);
 
 	for (i = 0; i < op->keylen; i += 4)
 		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
@@ -117,7 +118,7 @@ release_ss:
 	sg_miter_stop(&mi);
 	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
-	spin_unlock_bh(&ss->slock);
+	spin_unlock_irqrestore(&ss->slock, flags);
 	return err;
 }
 
@@ -149,6 +150,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 	unsigned int ob = 0;	/* offset in buf */
 	unsigned int obo = 0;	/* offset in bufo*/
 	unsigned int obl = 0;	/* length of data in bufo */
+	unsigned long flags;
 
 	if (areq->nbytes == 0)
 		return 0;
@@ -181,7 +183,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 	if (no_chunk == 1)
 		return sun4i_ss_opti_poll(areq);
 
-	spin_lock_bh(&ss->slock);
+	spin_lock_irqsave(&ss->slock, flags);
 
 	for (i = 0; i < op->keylen; i += 4)
 		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
@@ -251,11 +253,10 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 		spaces = readl(ss->base + SS_FCSR);
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
-		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u %u\n",
+		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u\n",
 			mode,
 			oi, mi.length, ileft, areq->nbytes, rx_cnt,
-			oo, mo.length, oleft, areq->nbytes, tx_cnt,
-			todo, ob);
+			oo, mo.length, oleft, areq->nbytes, tx_cnt, ob);
 
 		if (tx_cnt == 0)
 			continue;
@@ -308,7 +309,7 @@ release_ss:
 	sg_miter_stop(&mi);
 	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
-	spin_unlock_bh(&ss->slock);
+	spin_unlock_irqrestore(&ss->slock, flags);
 
 	return err;
 }
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index aae05547b..b7ee8d301 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -835,6 +835,16 @@ struct talitos_ahash_req_ctx {
 	struct scatterlist *psrc;
 };
 
+struct talitos_export_state {
+	u32 hw_context[TALITOS_MDEU_MAX_CONTEXT_SIZE / sizeof(u32)];
+	u8 buf[HASH_MAX_BLOCK_SIZE];
+	unsigned int swinit;
+	unsigned int first;
+	unsigned int last;
+	unsigned int to_hash_later;
+	unsigned int nbuf;
+};
+
 static int aead_setkey(struct crypto_aead *authenc,
 		       const u8 *key, unsigned int keylen)
 {
@@ -1981,6 +1991,46 @@ static int ahash_digest(struct ahash_request *areq)
 	return ahash_process_req(areq, areq->nbytes);
 }
 
+static int ahash_export(struct ahash_request *areq, void *out)
+{
+	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct talitos_export_state *export = out;
+
+	memcpy(export->hw_context, req_ctx->hw_context,
+	       req_ctx->hw_context_size);
+	memcpy(export->buf, req_ctx->buf, req_ctx->nbuf);
+	export->swinit = req_ctx->swinit;
+	export->first = req_ctx->first;
+	export->last = req_ctx->last;
+	export->to_hash_later = req_ctx->to_hash_later;
+	export->nbuf = req_ctx->nbuf;
+
+	return 0;
+}
+
+static int ahash_import(struct ahash_request *areq, const void *in)
+{
+	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	const struct talitos_export_state *export = in;
+
+	memset(req_ctx, 0, sizeof(*req_ctx));
+	req_ctx->hw_context_size =
+		(crypto_ahash_digestsize(tfm) <= SHA256_DIGEST_SIZE)
+			? TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256
+			: TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512;
+	memcpy(req_ctx->hw_context, export->hw_context,
+	       req_ctx->hw_context_size);
+	memcpy(req_ctx->buf, export->buf, export->nbuf);
+	req_ctx->swinit = export->swinit;
+	req_ctx->first = export->first;
+	req_ctx->last = export->last;
+	req_ctx->to_hash_later = export->to_hash_later;
+	req_ctx->nbuf = export->nbuf;
+
+	return 0;
+}
+
 struct keyhash_result {
 	struct completion completion;
 	int err;
@@ -2458,6 +2508,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = MD5_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "md5",
 				.cra_driver_name = "md5-talitos",
@@ -2473,6 +2524,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-talitos",
@@ -2488,6 +2540,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA224_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha224",
 				.cra_driver_name = "sha224-talitos",
@@ -2503,6 +2556,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-talitos",
@@ -2518,6 +2572,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA384_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha384",
 				.cra_driver_name = "sha384-talitos",
@@ -2533,6 +2588,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA512_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha512",
 				.cra_driver_name = "sha512-talitos",
@@ -2548,6 +2604,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = MD5_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "hmac-md5-talitos",
@@ -2563,6 +2620,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-talitos",
@@ -2578,6 +2636,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA224_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "hmac-sha224-talitos",
@@ -2593,6 +2652,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-talitos",
@@ -2608,6 +2668,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA384_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha384)",
 				.cra_driver_name = "hmac-sha384-talitos",
@@ -2623,6 +2684,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA512_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha512)",
 				.cra_driver_name = "hmac-sha512-talitos",
@@ -2814,6 +2876,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		t_alg->algt.alg.hash.finup = ahash_finup;
 		t_alg->algt.alg.hash.digest = ahash_digest;
 		t_alg->algt.alg.hash.setkey = ahash_setkey;
+		t_alg->algt.alg.hash.import = ahash_import;
+		t_alg->algt.alg.hash.export = ahash_export;
 
 		if (!(priv->features & TALITOS_FTR_HMAC_OK) &&
 		    !strncmp(alg->cra_name, "hmac", 4)) {