Improve DMA chaining for ahash requests

index 37dadb2..6e7a5c7 100644
@@ -375,10 +375,6 @@ 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;

index e423d33..a768da7 100644
@@ -277,7 +277,7 @@ struct mv_cesa_op_ctx {
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
-#define CESA_TDMA_IV				3
+#define CESA_TDMA_RESULT			3
 
 /**
  * struct mv_cesa_tdma_desc - TDMA descriptor

@@ -393,7 +393,6 @@ 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;
 };
 
 /**

@@ -839,7 +838,7 @@ 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,
+int mv_cesa_dma_add_result_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,

index d19dc96..098871a 100644
@@ -212,7 +212,8 @@ mv_cesa_ablkcipher_complete(struct crypto_async_request *req)
 		struct mv_cesa_req *basereq;
 
 		basereq = &creq->base;
-		memcpy(ablkreq->info, basereq->chain.last->data, ivsize);
+		memcpy(ablkreq->info, basereq->chain.last->op->ctx.blkcipher.iv,
+		       ivsize);
 	} else {
 		memcpy_fromio(ablkreq->info,
 			      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,

@@ -373,8 +374,9 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 
 	/* Add output data for IV */
 	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
-	ret = mv_cesa_dma_add_iv_op(&basereq->chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
-				    ivsize, CESA_TDMA_SRC_IN_SRAM, flags);
+	ret = mv_cesa_dma_add_result_op(&basereq->chain, CESA_SA_CFG_SRAM_OFFSET,
+				    CESA_SA_DATA_SRAM_OFFSET,
+				    CESA_TDMA_SRC_IN_SRAM, flags);
 
 	if (ret)
 		goto err_free_tdma;

index 9fd7a5f..4416b88 100644
@@ -69,9 +69,6 @@ void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq)
 		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,

@@ -209,29 +206,37 @@ 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,
+int mv_cesa_dma_add_result_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;
+	struct mv_cesa_tdma_desc *tdma, *op_desc;
 
 	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;
+	/* We re-use an existing op_desc object to retrieve the context
+	 * and result instead of allocating a new one.
+	 * There is at least one object of this type in a CESA crypto
+	 * req, just pick the first one in the chain.
+	 */
+	for (op_desc = chain->first; op_desc; op_desc = op_desc->next) {
+		u32 type = op_desc->flags & CESA_TDMA_TYPE_MSK;
+
+		if (type == CESA_TDMA_OP)
+			break;
+	}
+
+	if (!op_desc)
+		return -EIO;
 
 	tdma->byte_cnt = cpu_to_le32(size | BIT(31));
 	tdma->src = src;
-	tdma->dst = cpu_to_le32(dma_handle);
-	tdma->data = iv;
+	tdma->dst = op_desc->src;
+	tdma->op = op_desc->op;
 
 	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
-	tdma->flags = flags | CESA_TDMA_IV;
+	tdma->flags = flags | CESA_TDMA_RESULT;
 	return 0;
 }
 

index 9f28468..2a92605 100644
@@ -312,24 +312,40 @@ static void mv_cesa_ahash_complete(struct crypto_async_request *req)
 	int i;
 
 	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
-	for (i = 0; i < digsize / 4; i++)
-		creq->state[i] = readl_relaxed(engine->regs + CESA_IVDIG(i));
 
-	if (creq->last_req) {
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ &&
+	    (creq->base.chain.last->flags & CESA_TDMA_TYPE_MSK) == CESA_TDMA_RESULT) {
+		__le32 *data = NULL;
+
 		/*
-		 * Hardware's MD5 digest is in little endian format, but
-		 * SHA in big endian format
+		 * Result is already in the correct endianess when the SA is
+		 * used
 		 */
-		if (creq->algo_le) {
-			__le32 *result = (void *)ahashreq->result;
+		data = creq->base.chain.last->op->ctx.hash.hash;
+		for (i = 0; i < digsize / 4; i++)
+			creq->state[i] = cpu_to_le32(data[i]);
 
-			for (i = 0; i < digsize / 4; i++)
-				result[i] = cpu_to_le32(creq->state[i]);
-		} else {
-			__be32 *result = (void *)ahashreq->result;
+		memcpy(ahashreq->result, data, digsize);
+	} else {
+		for (i = 0; i < digsize / 4; i++)
+			creq->state[i] = readl_relaxed(engine->regs +
+						       CESA_IVDIG(i));
+		if (creq->last_req) {
+			/*
+			* Hardware's MD5 digest is in little endian format, but
+			* SHA in big endian format
+			*/
+			if (creq->algo_le) {
+				__le32 *result = (void *)ahashreq->result;
+
+				for (i = 0; i < digsize / 4; i++)
+					result[i] = cpu_to_le32(creq->state[i]);
+			} else {
+				__be32 *result = (void *)ahashreq->result;
 
-			for (i = 0; i < digsize / 4; i++)
-				result[i] = cpu_to_be32(creq->state[i]);
+				for (i = 0; i < digsize / 4; i++)
+					result[i] = cpu_to_be32(creq->state[i]);
+			}
 		}
 	}
 

@@ -504,6 +520,12 @@ mv_cesa_ahash_dma_last_req(struct mv_cesa_tdma_chain *chain,
 						CESA_SA_DESC_CFG_LAST_FRAG,
 				      CESA_SA_DESC_CFG_FRAG_MSK);
 
+		ret = mv_cesa_dma_add_result_op(chain,
+						CESA_SA_CFG_SRAM_OFFSET,
+						CESA_SA_DATA_SRAM_OFFSET,
+						CESA_TDMA_SRC_IN_SRAM, flags);
+		if (ret)
+			return ERR_PTR(-ENOMEM);
 		return op;
 	}
 

@@ -564,6 +586,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
 	int ret;
+	u32 type;
 
 	basereq->chain.first = NULL;
 	basereq->chain.last = NULL;

@@ -635,7 +658,15 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 		goto err_free_tdma;
 	}
 
-	if (op) {
+	/*
+	 * If results are copied via DMA, this means that this
+	 * request can be directly processed by the engine,
+	 * without partial updates. So we can chain it at the
+	 * DMA level with other requests.
+	 */
+	type = basereq->chain.last->flags & CESA_TDMA_TYPE_MSK;
+
+	if (op && type != CESA_TDMA_RESULT) {
 		/* Add dummy desc to wait for crypto operation end */
 		ret = mv_cesa_dma_add_dummy_end(&basereq->chain, flags);
 		if (ret)

@@ -648,8 +679,10 @@ 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);
+	basereq->chain.last->flags |= CESA_TDMA_END_OF_REQ;
+
+	if (type != CESA_TDMA_RESULT)
+		basereq->chain.last->flags |= CESA_TDMA_BREAK_CHAIN;
 
 	return 0;