Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 4.8:

  API:
   - first part of skcipher low-level conversions
   - add KPP (Key-agreement Protocol Primitives) interface.

  Algorithms:
   - fix IPsec/cryptd reordering issues that affects aesni
   - RSA no longer does explicit leading zero removal
   - add SHA3
   - add DH
   - add ECDH
   - improve DRBG performance by not doing CTR by hand

  Drivers:
   - add x86 AVX2 multibuffer SHA256/512
   - add POWER8 optimised crc32c
   - add xts support to vmx
   - add DH support to qat
   - add RSA support to caam
   - add Layerscape support to caam
   - add SEC1 AEAD support to talitos
   - improve performance by chaining requests in marvell/cesa
   - add support for Araneus Alea I USB RNG
   - add support for Broadcom BCM5301 RNG
   - add support for Amlogic Meson RNG
   - add support Broadcom NSP SoC RNG"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (180 commits)
  crypto: vmx - Fix aes_p8_xts_decrypt build failure
  crypto: vmx - Ignore generated files
  crypto: vmx - Adding support for XTS
  crypto: vmx - Adding asm subroutines for XTS
  crypto: skcipher - add comment for skcipher_alg->base
  crypto: testmgr - Print akcipher algorithm name
  crypto: marvell - Fix wrong flag used for GFP in mv_cesa_dma_add_iv_op
  crypto: nx - off by one bug in nx_of_update_msc()
  crypto: rsa-pkcs1pad - fix rsa-pkcs1pad request struct
  crypto: scatterwalk - Inline start/map/done
  crypto: scatterwalk - Remove unnecessary BUG in scatterwalk_start
  crypto: scatterwalk - Remove unnecessary advance in scatterwalk_pagedone
  crypto: scatterwalk - Fix test in scatterwalk_done
  crypto: api - Optimise away crypto_yield when hard preemption is on
  crypto: scatterwalk - add no-copy support to copychunks
  crypto: scatterwalk - Remove scatterwalk_bytes_sglen
  crypto: omap - Stop using crypto scatterwalk_bytes_sglen
  crypto: skcipher - Remove top-level givcipher interface
  crypto: user - Remove crypto_lookup_skcipher call
  crypto: cts - Convert to skcipher
  ...

5 files changed, 481 insertions, 218 deletions

diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index e8ef9fd24a16..e373cc6557c6 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -31,22 +31,42 @@
 
 #include "cesa.h"
 
+/* Limit of the crypto queue before reaching the backlog */
+#define CESA_CRYPTO_DEFAULT_MAX_QLEN 128
+
 static int allhwsupport = !IS_ENABLED(CONFIG_CRYPTO_DEV_MV_CESA);
 module_param_named(allhwsupport, allhwsupport, int, 0444);
 MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if overlaps with the mv_cesa driver)");
 
 struct mv_cesa_dev *cesa_dev;
 
-static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog)
 {
-	struct crypto_async_request *req, *backlog;
+	struct crypto_async_request *req;
+
+	*backlog = crypto_get_backlog(&engine->queue);
+	req = crypto_dequeue_request(&engine->queue);
+
+	if (!req)
+		return NULL;
+
+	return req;
+}
+
+static void mv_cesa_rearm_engine(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req = NULL, *backlog = NULL;
 	struct mv_cesa_ctx *ctx;
 
-	spin_lock_bh(&cesa_dev->lock);
-	backlog = crypto_get_backlog(&cesa_dev->queue);
-	req = crypto_dequeue_request(&cesa_dev->queue);
-	engine->req = req;
-	spin_unlock_bh(&cesa_dev->lock);
+
+	spin_lock_bh(&engine->lock);
+	if (!engine->req) {
+		req = mv_cesa_dequeue_req_locked(engine, &backlog);
+		engine->req = req;
+	}
+	spin_unlock_bh(&engine->lock);
 
 	if (!req)
 		return;
@@ -55,8 +75,47 @@ static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
 		backlog->complete(backlog, -EINPROGRESS);
 
 	ctx = crypto_tfm_ctx(req->tfm);
-	ctx->ops->prepare(req, engine);
 	ctx->ops->step(req);
+
+	return;
+}
+
+static int mv_cesa_std_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req;
+	struct mv_cesa_ctx *ctx;
+	int res;
+
+	req = engine->req;
+	ctx = crypto_tfm_ctx(req->tfm);
+	res = ctx->ops->process(req, status);
+
+	if (res == 0) {
+		ctx->ops->complete(req);
+		mv_cesa_engine_enqueue_complete_request(engine, req);
+	} else if (res == -EINPROGRESS) {
+		ctx->ops->step(req);
+	}
+
+	return res;
+}
+
+static int mv_cesa_int_process(struct mv_cesa_engine *engine, u32 status)
+{
+	if (engine->chain.first && engine->chain.last)
+		return mv_cesa_tdma_process(engine, status);
+
+	return mv_cesa_std_process(engine, status);
+}
+
+static inline void
+mv_cesa_complete_req(struct mv_cesa_ctx *ctx, struct crypto_async_request *req,
+		     int res)
+{
+	ctx->ops->cleanup(req);
+	local_bh_disable();
+	req->complete(req, res);
+	local_bh_enable();
 }
 
 static irqreturn_t mv_cesa_int(int irq, void *priv)
@@ -83,49 +142,54 @@ static irqreturn_t mv_cesa_int(int irq, void *priv)
 		writel(~status, engine->regs + CESA_SA_FPGA_INT_STATUS);
 		writel(~status, engine->regs + CESA_SA_INT_STATUS);
 
+		/* Process fetched requests */
+		res = mv_cesa_int_process(engine, status & mask);
 		ret = IRQ_HANDLED;
+
 		spin_lock_bh(&engine->lock);
 		req = engine->req;
+		if (res != -EINPROGRESS)
+			engine->req = NULL;
 		spin_unlock_bh(&engine->lock);
-		if (req) {
-			ctx = crypto_tfm_ctx(req->tfm);
-			res = ctx->ops->process(req, status & mask);
-			if (res != -EINPROGRESS) {
-				spin_lock_bh(&engine->lock);
-				engine->req = NULL;
-				mv_cesa_dequeue_req_unlocked(engine);
-				spin_unlock_bh(&engine->lock);
-				ctx->ops->cleanup(req);
-				local_bh_disable();
-				req->complete(req, res);
-				local_bh_enable();
-			} else {
-				ctx->ops->step(req);
-			}
+
+		ctx = crypto_tfm_ctx(req->tfm);
+
+		if (res && res != -EINPROGRESS)
+			mv_cesa_complete_req(ctx, req, res);
+
+		/* Launch the next pending request */
+		mv_cesa_rearm_engine(engine);
+
+		/* Iterate over the complete queue */
+		while (true) {
+			req = mv_cesa_engine_dequeue_complete_request(engine);
+			if (!req)
+				break;
+
+			mv_cesa_complete_req(ctx, req, 0);
 		}
 	}
 
 	return ret;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req)
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq)
 {
 	int ret;
-	int i;
+	struct mv_cesa_engine *engine = creq->engine;
+
+	spin_lock_bh(&engine->lock);
+	if (mv_cesa_req_get_type(creq) == CESA_DMA_REQ)
+		mv_cesa_tdma_chain(engine, creq);
 
-	spin_lock_bh(&cesa_dev->lock);
-	ret = crypto_enqueue_request(&cesa_dev->queue, req);
-	spin_unlock_bh(&cesa_dev->lock);
+	ret = crypto_enqueue_request(&engine->queue, req);
+	spin_unlock_bh(&engine->lock);
 
 	if (ret != -EINPROGRESS)
 		return ret;
 
-	for (i = 0; i < cesa_dev->caps->nengines; i++) {
-		spin_lock_bh(&cesa_dev->engines[i].lock);
-		if (!cesa_dev->engines[i].req)
-			mv_cesa_dequeue_req_unlocked(&cesa_dev->engines[i]);
-		spin_unlock_bh(&cesa_dev->engines[i].lock);
-	}
+	mv_cesa_rearm_engine(engine);
 
 	return -EINPROGRESS;
 }
@@ -309,6 +373,10 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
 	if (!dma->padding_pool)
 		return -ENOMEM;
 
+	dma->iv_pool = dmam_pool_create("cesa_iv", dev, 16, 1, 0);
+	if (!dma->iv_pool)
+		return -ENOMEM;
+
 	cesa->dma = dma;
 
 	return 0;
@@ -416,7 +484,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	spin_lock_init(&cesa->lock);
-	crypto_init_queue(&cesa->queue, 50);
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	cesa->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(cesa->regs))
@@ -489,6 +557,10 @@ static int mv_cesa_probe(struct platform_device *pdev)
 						engine);
 		if (ret)
 			goto err_cleanup;
+
+		crypto_init_queue(&engine->queue, CESA_CRYPTO_DEFAULT_MAX_QLEN);
+		atomic_set(&engine->load, 0);
+		INIT_LIST_HEAD(&engine->complete_queue);
 	}
 
 	cesa_dev = cesa;
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index 74071e45ada0..e423d33decd4 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -271,10 +271,13 @@ struct mv_cesa_op_ctx {
 /* TDMA descriptor flags */
 #define CESA_TDMA_DST_IN_SRAM			BIT(31)
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
-#define CESA_TDMA_TYPE_MSK			GENMASK(29, 0)
+#define CESA_TDMA_END_OF_REQ			BIT(29)
+#define CESA_TDMA_BREAK_CHAIN			BIT(28)
+#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
+#define CESA_TDMA_IV				3
 
 /**
  * struct mv_cesa_tdma_desc - TDMA descriptor
@@ -390,6 +393,7 @@ struct mv_cesa_dev_dma {
 	struct dma_pool *op_pool;
 	struct dma_pool *cache_pool;
 	struct dma_pool *padding_pool;
+	struct dma_pool *iv_pool;
 };
 
 /**
@@ -398,7 +402,6 @@ struct mv_cesa_dev_dma {
  * @regs:	device registers
  * @sram_size:	usable SRAM size
  * @lock:	device lock
- * @queue:	crypto request queue
  * @engines:	array of engines
  * @dma:	dma pools
  *
@@ -410,7 +413,6 @@ struct mv_cesa_dev {
 	struct device *dev;
 	unsigned int sram_size;
 	spinlock_t lock;
-	struct crypto_queue queue;
 	struct mv_cesa_engine *engines;
 	struct mv_cesa_dev_dma *dma;
 };
@@ -429,6 +431,11 @@ struct mv_cesa_dev {
  * @int_mask:		interrupt mask cache
  * @pool:		memory pool pointing to the memory region reserved in
  *			SRAM
+ * @queue:		fifo of the pending crypto requests
+ * @load:		engine load counter, useful for load balancing
+ * @chain:		list of the current tdma descriptors being processed
+ * 			by this engine.
+ * @complete_queue:	fifo of the processed requests by the engine
  *
  * Structure storing CESA engine information.
  */
@@ -444,23 +451,27 @@ struct mv_cesa_engine {
 	size_t max_req_len;
 	u32 int_mask;
 	struct gen_pool *pool;
+	struct crypto_queue queue;
+	atomic_t load;
+	struct mv_cesa_tdma_chain chain;
+	struct list_head complete_queue;
 };
 
 /**
  * struct mv_cesa_req_ops - CESA request operations
- * @prepare:	prepare a request to be executed on the specified engine
  * @process:	process a request chunk result (should return 0 if the
  *		operation, -EINPROGRESS if it needs more steps or an error
  *		code)
  * @step:	launch the crypto operation on the next chunk
  * @cleanup:	cleanup the crypto request (release associated data)
+ * @complete:	complete the request, i.e copy result or context from sram when
+ * 		needed.
  */
 struct mv_cesa_req_ops {
-	void (*prepare)(struct crypto_async_request *req,
-			struct mv_cesa_engine *engine);
 	int (*process)(struct crypto_async_request *req, u32 status);
 	void (*step)(struct crypto_async_request *req);
 	void (*cleanup)(struct crypto_async_request *req);
+	void (*complete)(struct crypto_async_request *req);
 };
 
 /**
@@ -507,21 +518,11 @@ enum mv_cesa_req_type {
 
 /**
  * struct mv_cesa_req - CESA request
- * @type:	request type
  * @engine:	engine associated with this request
+ * @chain:	list of tdma descriptors associated  with this request
  */
 struct mv_cesa_req {
-	enum mv_cesa_req_type type;
 	struct mv_cesa_engine *engine;
-};
-
-/**
- * struct mv_cesa_tdma_req - CESA TDMA request
- * @base:	base information
- * @chain:	TDMA chain
- */
-struct mv_cesa_tdma_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_tdma_chain chain;
 };
 
@@ -538,13 +539,11 @@ struct mv_cesa_sg_std_iter {
 
 /**
  * struct mv_cesa_ablkcipher_std_req - cipher standard request
- * @base:	base information
  * @op:		operation context
  * @offset:	current operation offset
  * @size:	size of the crypto operation
  */
 struct mv_cesa_ablkcipher_std_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_op_ctx op;
 	unsigned int offset;
 	unsigned int size;
@@ -558,34 +557,27 @@ struct mv_cesa_ablkcipher_std_req {
  * @dst_nents:	number of entries in the dest sg list
  */
 struct mv_cesa_ablkcipher_req {
-	union {
-		struct mv_cesa_req base;
-		struct mv_cesa_tdma_req dma;
-		struct mv_cesa_ablkcipher_std_req std;
-	} req;
+	struct mv_cesa_req base;
+	struct mv_cesa_ablkcipher_std_req std;
 	int src_nents;
 	int dst_nents;
 };
 
 /**
  * struct mv_cesa_ahash_std_req - standard hash request
- * @base:	base information
  * @offset:	current operation offset
  */
 struct mv_cesa_ahash_std_req {
-	struct mv_cesa_req base;
 	unsigned int offset;
 };
 
 /**
  * struct mv_cesa_ahash_dma_req - DMA hash request
- * @base:		base information
  * @padding:		padding buffer
  * @padding_dma:	DMA address of the padding buffer
  * @cache_dma:		DMA address of the cache buffer
  */
 struct mv_cesa_ahash_dma_req {
-	struct mv_cesa_tdma_req base;
 	u8 *padding;
 	dma_addr_t padding_dma;
 	u8 *cache;
@@ -604,8 +596,8 @@ struct mv_cesa_ahash_dma_req {
  * @state:		hash state
  */
 struct mv_cesa_ahash_req {
+	struct mv_cesa_req base;
 	union {
-		struct mv_cesa_req base;
 		struct mv_cesa_ahash_dma_req dma;
 		struct mv_cesa_ahash_std_req std;
 	} req;
@@ -623,6 +615,35 @@ struct mv_cesa_ahash_req {
 
 extern struct mv_cesa_dev *cesa_dev;
 
+
+static inline void
+mv_cesa_engine_enqueue_complete_request(struct mv_cesa_engine *engine,
+					struct crypto_async_request *req)
+{
+	list_add_tail(&req->list, &engine->complete_queue);
+}
+
+static inline struct crypto_async_request *
+mv_cesa_engine_dequeue_complete_request(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req;
+
+	req = list_first_entry_or_null(&engine->complete_queue,
+				       struct crypto_async_request,
+				       list);
+	if (req)
+		list_del(&req->list);
+
+	return req;
+}
+
+
+static inline enum mv_cesa_req_type
+mv_cesa_req_get_type(struct mv_cesa_req *req)
+{
+	return req->chain.first ? CESA_DMA_REQ : CESA_STD_REQ;
+}
+
 static inline void mv_cesa_update_op_cfg(struct mv_cesa_op_ctx *op,
 					 u32 cfg, u32 mask)
 {
@@ -695,7 +716,32 @@ static inline bool mv_cesa_mac_op_is_first_frag(const struct mv_cesa_op_ctx *op)
 		CESA_SA_DESC_CFG_FIRST_FRAG;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req);
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq);
+
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog);
+
+static inline struct mv_cesa_engine *mv_cesa_select_engine(int weight)
+{
+	int i;
+	u32 min_load = U32_MAX;
+	struct mv_cesa_engine *selected = NULL;
+
+	for (i = 0; i < cesa_dev->caps->nengines; i++) {
+		struct mv_cesa_engine *engine = cesa_dev->engines + i;
+		u32 load = atomic_read(&engine->load);
+		if (load < min_load) {
+			min_load = load;
+			selected = engine;
+		}
+	}
+
+	atomic_add(weight, &selected->load);
+
+	return selected;
+}
 
 /*
  * Helper function that indicates whether a crypto request needs to be
@@ -765,9 +811,9 @@ static inline bool mv_cesa_req_dma_iter_next_op(struct mv_cesa_dma_iter *iter)
 	return iter->op_len;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq);
+void mv_cesa_dma_step(struct mv_cesa_req *dreq);
 
-static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
+static inline int mv_cesa_dma_process(struct mv_cesa_req *dreq,
 				      u32 status)
 {
 	if (!(status & CESA_SA_INT_ACC0_IDMA_DONE))
@@ -779,10 +825,13 @@ static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
 	return 0;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine);
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq);
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq);
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status);
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq);
 
 static inline void
 mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
@@ -790,6 +839,9 @@ mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
 	memset(chain, 0, sizeof(*chain));
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags);
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index dcf1fceb9336..48df03a06066 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -70,25 +70,28 @@ mv_cesa_ablkcipher_dma_cleanup(struct ablkcipher_request *req)
 		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
 			     DMA_BIDIRECTIONAL);
 	}
-	mv_cesa_dma_cleanup(&creq->req.dma);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ablkcipher_cleanup(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_cleanup(req);
 }
 
 static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t  len = min_t(size_t, req->nbytes - sreq->offset,
 			    CESA_SA_SRAM_PAYLOAD_SIZE);
 
+	mv_cesa_adjust_op(engine, &sreq->op);
+	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
+
 	len = sg_pcopy_to_buffer(req->src, creq->src_nents,
 				 engine->sram + CESA_SA_DATA_SRAM_OFFSET,
 				 len, sreq->offset);
@@ -106,6 +109,8 @@ static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -113,8 +118,8 @@ static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
 					  u32 status)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t len;
 
 	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
@@ -133,21 +138,19 @@ static int mv_cesa_ablkcipher_process(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_req *basereq = &creq->base;
+	unsigned int ivsize;
 	int ret;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma, status);
-	else
-		ret = mv_cesa_ablkcipher_std_process(ablkreq, status);
+	if (mv_cesa_req_get_type(basereq) == CESA_STD_REQ)
+		return mv_cesa_ablkcipher_std_process(ablkreq, status);
 
+	ret = mv_cesa_dma_process(basereq, status);
 	if (ret)
 		return ret;
 
-	memcpy_fromio(ablkreq->info,
-		      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
-		      crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+	memcpy_fromio(ablkreq->info, basereq->chain.last->data, ivsize);
 
 	return 0;
 }
@@ -157,8 +160,8 @@ static void mv_cesa_ablkcipher_step(struct crypto_async_request *req)
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ablkcipher_std_step(ablkreq);
 }
@@ -167,22 +170,19 @@ static inline void
 mv_cesa_ablkcipher_dma_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static inline void
 mv_cesa_ablkcipher_std_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
 
 	sreq->size = 0;
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &sreq->op);
-	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
 }
 
 static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
@@ -190,9 +190,9 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_prepare(ablkreq);
 	else
 		mv_cesa_ablkcipher_std_prepare(ablkreq);
@@ -206,11 +206,34 @@ mv_cesa_ablkcipher_req_cleanup(struct crypto_async_request *req)
 	mv_cesa_ablkcipher_cleanup(ablkreq);
 }
 
+static void
+mv_cesa_ablkcipher_complete(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
+	unsigned int ivsize;
+
+	atomic_sub(ablkreq->nbytes, &engine->load);
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ) {
+		struct mv_cesa_req *basereq;
+
+		basereq = &creq->base;
+		memcpy(ablkreq->info, basereq->chain.last->data, ivsize);
+	} else {
+		memcpy_fromio(ablkreq->info,
+			      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+			      ivsize);
+	}
+}
+
 static const struct mv_cesa_req_ops mv_cesa_ablkcipher_req_ops = {
 	.step = mv_cesa_ablkcipher_step,
 	.process = mv_cesa_ablkcipher_process,
-	.prepare = mv_cesa_ablkcipher_prepare,
 	.cleanup = mv_cesa_ablkcipher_req_cleanup,
+	.complete = mv_cesa_ablkcipher_complete,
 };
 
 static int mv_cesa_ablkcipher_cra_init(struct crypto_tfm *tfm)
@@ -295,15 +318,15 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		      GFP_KERNEL : GFP_ATOMIC;
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ablkcipher_dma_iter iter;
 	struct mv_cesa_tdma_chain chain;
 	bool skip_ctx = false;
 	int ret;
+	unsigned int ivsize;
 
-	dreq->base.type = CESA_DMA_REQ;
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (req->src != req->dst) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -358,12 +381,21 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 
 	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
 
-	dreq->chain = chain;
+	/* Add output data for IV */
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
+	ret = mv_cesa_dma_add_iv_op(&chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
+				    ivsize, CESA_TDMA_SRC_IN_SRAM, flags);
+
+	if (ret)
+		goto err_free_tdma;
+
+	basereq->chain = chain;
+	basereq->chain.last->flags |= CESA_TDMA_END_OF_REQ;
 
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	if (req->dst != req->src)
 		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
 			     DMA_FROM_DEVICE);
@@ -380,11 +412,13 @@ mv_cesa_ablkcipher_std_req_init(struct ablkcipher_request *req,
 				const struct mv_cesa_op_ctx *op_templ)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	sreq->base.type = CESA_STD_REQ;
 	sreq->op = *op_templ;
 	sreq->skip_ctx = false;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	return 0;
 }
@@ -414,7 +448,6 @@ static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
 			      CESA_SA_DESC_CFG_OP_MSK);
 
-	/* TODO: add a threshold for DMA usage */
 	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ablkcipher_dma_req_init(req, tmpl);
 	else
@@ -423,28 +456,41 @@ static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
 	return ret;
 }
 
-static int mv_cesa_des_op(struct ablkcipher_request *req,
-			  struct mv_cesa_op_ctx *tmpl)
+static int mv_cesa_ablkcipher_queue_req(struct ablkcipher_request *req,
+					struct mv_cesa_op_ctx *tmpl)
 {
-	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	int ret;
-
-	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
-			      CESA_SA_DESC_CFG_CRYPTM_MSK);
-
-	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_engine *engine;
 
 	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
 	if (ret)
 		return ret;
 
-	ret = mv_cesa_queue_req(&req->base);
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ablkcipher_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
 	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
 }
 
+static int mv_cesa_des_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
+}
+
 static int mv_cesa_ecb_des_encrypt(struct ablkcipher_request *req)
 {
 	struct mv_cesa_op_ctx tmpl;
@@ -547,22 +593,13 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 			   struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_des3_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret;
 
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
 	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_des3_ede_encrypt(struct ablkcipher_request *req)
@@ -673,7 +710,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 			  struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret, i;
+	int i;
 	u32 *key;
 	u32 cfg;
 
@@ -696,15 +733,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK |
 			      CESA_SA_DESC_CFG_AES_LEN_MSK);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_aes_encrypt(struct ablkcipher_request *req)
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 7a5058da9151..c35912b4fffb 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -103,14 +103,14 @@ static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *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);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_cleanup(req);
 }
 
@@ -118,7 +118,7 @@ static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_last_cleanup(req);
 }
 
@@ -157,11 +157,23 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	struct mv_cesa_op_ctx *op;
 	unsigned int new_cache_ptr = 0;
 	u32 frag_mode;
 	size_t  len;
+	unsigned int digsize;
+	int i;
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	for (i = 0; i < digsize / 4; i++)
+		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 
 	if (creq->cache_ptr)
 		memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET,
@@ -237,6 +249,8 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -254,20 +268,17 @@ static int mv_cesa_ahash_std_process(struct ahash_request *req, u32 status)
 static inline void mv_cesa_ahash_dma_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma.base;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
 
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &creq->op_tmpl);
-	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 }
 
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
@@ -275,8 +286,8 @@ static void mv_cesa_ahash_step(struct crypto_async_request *req)
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma.base);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -285,17 +296,20 @@ static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	struct mv_cesa_engine *engine = creq->req.base.engine;
-	unsigned int digsize;
-	int ret, i;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma.base, status);
-	else
-		ret = mv_cesa_ahash_std_process(ahashreq, status);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		return mv_cesa_dma_process(&creq->base, status);
 
-	if (ret == -EINPROGRESS)
-		return ret;
+	return mv_cesa_ahash_std_process(ahashreq, status);
+}
+
+static void mv_cesa_ahash_complete(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
+	unsigned int digsize;
+	int i;
 
 	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
 	for (i = 0; i < digsize / 4; i++)
@@ -325,7 +339,7 @@ static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
 		}
 	}
 
-	return ret;
+	atomic_sub(ahashreq->nbytes, &engine->load);
 }
 
 static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
@@ -333,19 +347,13 @@ static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	unsigned int digsize;
-	int i;
 
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_prepare(ahashreq);
 	else
 		mv_cesa_ahash_std_prepare(ahashreq);
-
-	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
-	for (i = 0; i < digsize / 4; i++)
-		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
 }
 
 static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
@@ -362,8 +370,8 @@ static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
 static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
 	.step = mv_cesa_ahash_step,
 	.process = mv_cesa_ahash_process,
-	.prepare = mv_cesa_ahash_prepare,
 	.cleanup = mv_cesa_ahash_req_cleanup,
+	.complete = mv_cesa_ahash_complete,
 };
 
 static int mv_cesa_ahash_init(struct ahash_request *req,
@@ -553,15 +561,14 @@ static int mv_cesa_ahash_dma_req_init(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;
-	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
-	struct mv_cesa_tdma_req *dreq = &ahashdreq->base;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
 	int ret;
 
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -572,14 +579,14 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 		}
 	}
 
-	mv_cesa_tdma_desc_iter_init(&dreq->chain);
+	mv_cesa_tdma_desc_iter_init(&basereq->chain);
 	mv_cesa_ahash_req_iter_init(&iter, req);
 
 	/*
 	 * Add the cache (left-over data from a previous block) first.
 	 * This will never overflow the SRAM size.
 	 */
-	ret = mv_cesa_ahash_dma_add_cache(&dreq->chain, &iter, creq, flags);
+	ret = mv_cesa_ahash_dma_add_cache(&basereq->chain, &iter, creq, flags);
 	if (ret)
 		goto err_free_tdma;
 
@@ -590,7 +597,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 		 * data. We intentionally do not add the final op block.
 		 */
 		while (true) {
-			ret = mv_cesa_dma_add_op_transfers(&dreq->chain,
+			ret = mv_cesa_dma_add_op_transfers(&basereq->chain,
 							   &iter.base,
 							   &iter.src, flags);
 			if (ret)
@@ -601,7 +608,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 			if (!mv_cesa_ahash_req_iter_next_op(&iter))
 				break;
 
-			op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+			op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 						  frag_len, flags);
 			if (IS_ERR(op)) {
 				ret = PTR_ERR(op);
@@ -619,10 +626,10 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	 * operation, which depends whether this is the final request.
 	 */
 	if (creq->last_req)
-		op = mv_cesa_ahash_dma_last_req(&dreq->chain, &iter, creq,
+		op = mv_cesa_ahash_dma_last_req(&basereq->chain, &iter, creq,
 						frag_len, flags);
 	else if (frag_len)
-		op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+		op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 					  frag_len, flags);
 
 	if (IS_ERR(op)) {
@@ -632,7 +639,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 
 	if (op) {
 		/* Add dummy desc to wait for crypto operation end */
-		ret = mv_cesa_dma_add_dummy_end(&dreq->chain, flags);
+		ret = mv_cesa_dma_add_dummy_end(&basereq->chain, flags);
 		if (ret)
 			goto err_free_tdma;
 	}
@@ -643,10 +650,13 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	else
 		creq->cache_ptr = 0;
 
+	basereq->chain.last->flags |= (CESA_TDMA_END_OF_REQ |
+				       CESA_TDMA_BREAK_CHAIN);
+
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
 
 err:
@@ -660,11 +670,6 @@ static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	int ret;
 
-	if (cesa_dev->caps->has_tdma)
-		creq->req.base.type = CESA_DMA_REQ;
-	else
-		creq->req.base.type = CESA_STD_REQ;
-
 	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
 	if (creq->src_nents < 0) {
 		dev_err(cesa_dev->dev, "Invalid number of src SG");
@@ -678,19 +683,19 @@ static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
 	if (*cached)
 		return 0;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ahash_dma_req_init(req);
 
 	return ret;
 }
 
-static int mv_cesa_ahash_update(struct ahash_request *req)
+static int mv_cesa_ahash_queue_req(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_engine *engine;
 	bool cached = false;
 	int ret;
 
-	creq->len += req->nbytes;
 	ret = mv_cesa_ahash_req_init(req, &cached);
 	if (ret)
 		return ret;
@@ -698,61 +703,48 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 	if (cached)
 		return 0;
 
-	ret = mv_cesa_queue_req(&req->base);
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ahash_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
 	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
 }
 
+static int mv_cesa_ahash_update(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	creq->len += req->nbytes;
+
+	return mv_cesa_ahash_queue_req(req);
+}
+
 static int mv_cesa_ahash_final(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 	req->nbytes = 0;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_finup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	creq->len += req->nbytes;
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_export(struct ahash_request *req, void *hash,
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 0ad8f1ecf175..86a065bcc187 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -37,9 +37,9 @@ bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *iter,
 	return true;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_step(struct mv_cesa_req *dreq)
 {
-	struct mv_cesa_engine *engine = dreq->base.engine;
+	struct mv_cesa_engine *engine = dreq->engine;
 
 	writel_relaxed(0, engine->regs + CESA_SA_CFG);
 
@@ -53,19 +53,25 @@ void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
 		       engine->regs + CESA_SA_CFG);
 	writel_relaxed(dreq->chain.first->cur_dma,
 		       engine->regs + CESA_TDMA_NEXT_ADDR);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq)
 {
 	struct mv_cesa_tdma_desc *tdma;
 
 	for (tdma = dreq->chain.first; tdma;) {
 		struct mv_cesa_tdma_desc *old_tdma = tdma;
+		u32 type = tdma->flags & CESA_TDMA_TYPE_MSK;
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if (type == CESA_TDMA_OP)
 			dma_pool_free(cesa_dev->dma->op_pool, tdma->op,
 				      le32_to_cpu(tdma->src));
+		else if (type == CESA_TDMA_IV)
+			dma_pool_free(cesa_dev->dma->iv_pool, tdma->data,
+				      le32_to_cpu(tdma->dst));
 
 		tdma = tdma->next;
 		dma_pool_free(cesa_dev->dma->tdma_desc_pool, old_tdma,
@@ -76,7 +82,7 @@ void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
 	dreq->chain.last = NULL;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine)
 {
 	struct mv_cesa_tdma_desc *tdma;
@@ -88,11 +94,97 @@ void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
 		if (tdma->flags & CESA_TDMA_SRC_IN_SRAM)
 			tdma->src = cpu_to_le32(tdma->src + engine->sram_dma);
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if ((tdma->flags & CESA_TDMA_TYPE_MSK) == CESA_TDMA_OP)
 			mv_cesa_adjust_op(engine, tdma->op);
 	}
 }
 
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq)
+{
+	if (engine->chain.first == NULL && engine->chain.last == NULL) {
+		engine->chain.first = dreq->chain.first;
+		engine->chain.last  = dreq->chain.last;
+	} else {
+		struct mv_cesa_tdma_desc *last;
+
+		last = engine->chain.last;
+		last->next = dreq->chain.first;
+		engine->chain.last = dreq->chain.last;
+
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+			last->next_dma = dreq->chain.first->cur_dma;
+	}
+}
+
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req = NULL;
+	struct mv_cesa_tdma_desc *tdma = NULL, *next = NULL;
+	dma_addr_t tdma_cur;
+	int res = 0;
+
+	tdma_cur = readl(engine->regs + CESA_TDMA_CUR);
+
+	for (tdma = engine->chain.first; tdma; tdma = next) {
+		spin_lock_bh(&engine->lock);
+		next = tdma->next;
+		spin_unlock_bh(&engine->lock);
+
+		if (tdma->flags & CESA_TDMA_END_OF_REQ) {
+			struct crypto_async_request *backlog = NULL;
+			struct mv_cesa_ctx *ctx;
+			u32 current_status;
+
+			spin_lock_bh(&engine->lock);
+			/*
+			 * if req is NULL, this means we're processing the
+			 * request in engine->req.
+			 */
+			if (!req)
+				req = engine->req;
+			else
+				req = mv_cesa_dequeue_req_locked(engine,
+								 &backlog);
+
+			/* Re-chaining to the next request */
+			engine->chain.first = tdma->next;
+			tdma->next = NULL;
+
+			/* If this is the last request, clear the chain */
+			if (engine->chain.first == NULL)
+				engine->chain.last  = NULL;
+			spin_unlock_bh(&engine->lock);
+
+			ctx = crypto_tfm_ctx(req->tfm);
+			current_status = (tdma->cur_dma == tdma_cur) ?
+					  status : CESA_SA_INT_ACC0_IDMA_DONE;
+			res = ctx->ops->process(req, current_status);
+			ctx->ops->complete(req);
+
+			if (res == 0)
+				mv_cesa_engine_enqueue_complete_request(engine,
+									req);
+
+			if (backlog)
+				backlog->complete(backlog, -EINPROGRESS);
+		}
+
+		if (res || tdma->cur_dma == tdma_cur)
+			break;
+	}
+
+	/* Save the last request in error to engine->req, so that the core
+	 * knows which request was fautly */
+	if (res) {
+		spin_lock_bh(&engine->lock);
+		engine->req = req;
+		spin_unlock_bh(&engine->lock);
+	}
+
+	return res;
+}
+
 static struct mv_cesa_tdma_desc *
 mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
 {
@@ -117,6 +209,32 @@ mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
 	return new_tdma;
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags)
+{
+
+	struct mv_cesa_tdma_desc *tdma;
+	u8 *iv;
+	dma_addr_t dma_handle;
+
+	tdma = mv_cesa_dma_add_desc(chain, gfp_flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	iv = dma_pool_alloc(cesa_dev->dma->iv_pool, gfp_flags, &dma_handle);
+	if (!iv)
+		return -ENOMEM;
+
+	tdma->byte_cnt = cpu_to_le32(size | BIT(31));
+	tdma->src = src;
+	tdma->dst = cpu_to_le32(dma_handle);
+	tdma->data = iv;
+
+	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
+	tdma->flags = flags | CESA_TDMA_IV;
+	return 0;
+}
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,