crypto: marvell - Copy IV vectors by DMA transfers for acipher requests

Add a TDMA descriptor at the end of the request for copying the
output IV vector via a DMA transfer. This is a good way for offloading
as much as processing as possible to the DMA and the crypto engine.
This is also required for processing multiple cipher requests
in chained mode, otherwise the content of the IV vector would be
overwritten by the last processed request.
Signed-off-by: Romain Perier <romain.perier@free-electrons.com>
Acked-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/marvell/cesa.c

@@ -312,6 +312,10 @@ 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;

drivers/crypto/marvell/cesa.h

@@ -275,6 +275,7 @@ 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
 
 /**
  * struct mv_cesa_tdma_desc - TDMA descriptor
@@ -390,6 +391,7 @@ 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;
 };
 
 /**
@@ -790,6 +792,9 @@ 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,

drivers/crypto/marvell/cipher.c

@@ -118,6 +118,7 @@ static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
 	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
 	struct mv_cesa_engine *engine = sreq->base.engine;
 	size_t len;
+	unsigned int ivsize;
 
 	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
 				   engine->sram + CESA_SA_DATA_SRAM_OFFSET,
@@ -127,6 +128,10 @@ static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
 	if (sreq->offset < req->nbytes)
 		return -EINPROGRESS;
 
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
+	memcpy_fromio(req->info,
+		      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET, ivsize);
+
 	return 0;
 }
 
@@ -135,21 +140,20 @@ 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_tdma_req *dreq;
+	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 (creq->req.base.type == CESA_STD_REQ)
+		return mv_cesa_ablkcipher_std_process(ablkreq, status);
 
+	ret = mv_cesa_dma_process(&creq->req.dma, status);
 	if (ret)
 		return ret;
 
-	memcpy_fromio(ablkreq->info,
-		      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
-		      crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+	dreq = &creq->req.dma;
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+	memcpy_fromio(ablkreq->info, dreq->chain.last->data, ivsize);
 
 	return 0;
 }
@@ -302,6 +306,7 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 	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;
@@ -360,6 +365,14 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 
 	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
 
+	/* 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;
+
 	dreq->chain = chain;
 
 	return 0;

drivers/crypto/marvell/tdma.c

@@ -69,6 +69,9 @@ void mv_cesa_dma_cleanup(struct mv_cesa_tdma_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,
@@ -120,6 +123,32 @@ 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, 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,