[PATCH 8/9] crypto: sun8i-ce - save hash buffers and dma info to request context

[Ovidiu Panait <ovidiu.panait.oss@gmail.com>]

Similar to sun8i-ce skcipher code, move all request-specific data to
request context.

This simplifies sun8i_ce_hash_run() and it eliminates the remaining
kmalloc() calls from the digest path. It also makes it easier to split
the monolithic sun8i_ce_hash_run() function in the next commit.

Signed-off-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
---
 .../crypto/allwinner/sun8i-ce/sun8i-ce-hash.c | 56 +++++++------------
 drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h  | 17 ++++++
 2 files changed, 38 insertions(+), 35 deletions(-)

diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index df2acef9c679..e28100c07b86 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -328,12 +328,9 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	u32 common;
 	u64 byte_count;
 	__le32 *bf;
-	void *buf, *result;
 	int j, i, todo;
 	u64 bs;
 	int digestsize;
-	dma_addr_t addr_res, addr_pad;
-	int ns = sg_nents_for_len(areq->src, areq->nbytes);
 
 	algt = container_of(alg, struct sun8i_ce_alg_template, alg.hash.base);
 	ce = algt->ce;
@@ -345,19 +342,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	if (digestsize == SHA384_DIGEST_SIZE)
 		digestsize = SHA512_DIGEST_SIZE;
 
-	/* the padding could be up to two block. */
-	buf = kcalloc(2, bs, GFP_KERNEL | GFP_DMA);
-	if (!buf) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	bf = (__le32 *)buf;
-
-	result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA);
-	if (!result) {
-		err = -ENOMEM;
-		goto err_free_buf;
-	}
+	bf = (__le32 *)rctx->pad;
 
 	flow = rctx->flow;
 	chan = &ce->chanlist[flow];
@@ -378,11 +363,12 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	cet->t_sym_ctl = 0;
 	cet->t_asym_ctl = 0;
 
-	nr_sgs = dma_map_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE);
+	rctx->nr_sgs = sg_nents_for_len(areq->src, areq->nbytes);
+	nr_sgs = dma_map_sg(ce->dev, areq->src, rctx->nr_sgs, DMA_TO_DEVICE);
 	if (nr_sgs <= 0 || nr_sgs > MAX_SG) {
 		dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs);
 		err = -EINVAL;
-		goto err_free_result;
+		goto err_out;
 	}
 
 	len = areq->nbytes;
@@ -397,10 +383,13 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 		err = -EINVAL;
 		goto err_unmap_src;
 	}
-	addr_res = dma_map_single(ce->dev, result, digestsize, DMA_FROM_DEVICE);
-	cet->t_dst[0].addr = desc_addr_val_le32(ce, addr_res);
-	cet->t_dst[0].len = cpu_to_le32(digestsize / 4);
-	if (dma_mapping_error(ce->dev, addr_res)) {
+
+	rctx->result_len = digestsize;
+	rctx->addr_res = dma_map_single(ce->dev, rctx->result, rctx->result_len,
+					DMA_FROM_DEVICE);
+	cet->t_dst[0].addr = desc_addr_val_le32(ce, rctx->addr_res);
+	cet->t_dst[0].len = cpu_to_le32(rctx->result_len / 4);
+	if (dma_mapping_error(ce->dev, rctx->addr_res)) {
 		dev_err(ce->dev, "DMA map dest\n");
 		err = -EINVAL;
 		goto err_unmap_src;
@@ -428,10 +417,12 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 		goto err_unmap_result;
 	}
 
-	addr_pad = dma_map_single(ce->dev, buf, j * 4, DMA_TO_DEVICE);
-	cet->t_src[i].addr = desc_addr_val_le32(ce, addr_pad);
+	rctx->pad_len = j * 4;
+	rctx->addr_pad = dma_map_single(ce->dev, rctx->pad, rctx->pad_len,
+					DMA_TO_DEVICE);
+	cet->t_src[i].addr = desc_addr_val_le32(ce, rctx->addr_pad);
 	cet->t_src[i].len = cpu_to_le32(j);
-	if (dma_mapping_error(ce->dev, addr_pad)) {
+	if (dma_mapping_error(ce->dev, rctx->addr_pad)) {
 		dev_err(ce->dev, "DMA error on padding SG\n");
 		err = -EINVAL;
 		goto err_unmap_result;
@@ -444,21 +435,16 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 
 	err = sun8i_ce_run_task(ce, flow, crypto_ahash_alg_name(tfm));
 
-	dma_unmap_single(ce->dev, addr_pad, j * 4, DMA_TO_DEVICE);
+	dma_unmap_single(ce->dev, rctx->addr_pad, rctx->pad_len, DMA_TO_DEVICE);
 
 err_unmap_result:
-	dma_unmap_single(ce->dev, addr_res, digestsize, DMA_FROM_DEVICE);
+	dma_unmap_single(ce->dev, rctx->addr_res, rctx->result_len,
+			 DMA_FROM_DEVICE);
 	if (!err)
-		memcpy(areq->result, result, crypto_ahash_digestsize(tfm));
+		memcpy(areq->result, rctx->result, crypto_ahash_digestsize(tfm));
 
 err_unmap_src:
-	dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE);
-
-err_free_result:
-	kfree(result);
-
-err_free_buf:
-	kfree(buf);
+	dma_unmap_sg(ce->dev, areq->src, rctx->nr_sgs, DMA_TO_DEVICE);
 
 err_out:
 	local_bh_disable();
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
index 0d46531c475c..90b955787d37 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
@@ -110,6 +110,9 @@
 
 #define MAXFLOW 4
 
+#define CE_MAX_HASH_DIGEST_SIZE		SHA512_DIGEST_SIZE
+#define CE_MAX_HASH_BLOCK_SIZE		SHA512_BLOCK_SIZE
+
 /*
  * struct ce_clock - Describe clocks used by sun8i-ce
  * @name:	Name of clock needed by this variant
@@ -304,9 +307,23 @@ struct sun8i_ce_hash_tfm_ctx {
  * struct sun8i_ce_hash_reqctx - context for an ahash request
  * @fallback_req:	pre-allocated fallback request
  * @flow:	the flow to use for this request
+ * @nr_sgs: number of entries in the source scatterlist
+ * @result_len: result length in bytes
+ * @pad_len: padding length in bytes
+ * @addr_res: DMA address of the result buffer, returned by dma_map_single()
+ * @addr_pad: DMA address of the padding buffer, returned by dma_map_single()
+ * @result: per-request result buffer
+ * @pad: per-request padding buffer (up to 2 blocks)
  */
 struct sun8i_ce_hash_reqctx {
 	int flow;
+	int nr_sgs;
+	size_t result_len;
+	size_t pad_len;
+	dma_addr_t addr_res;
+	dma_addr_t addr_pad;
+	u8 result[CE_MAX_HASH_DIGEST_SIZE] ____cacheline_aligned;
+	u8 pad[2 * CE_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
 	struct ahash_request fallback_req; // keep at the end
 };
 
-- 
2.50.0