crypto: caam - chaining support

support chained scatterlists for aead, ablkcipher and ahash.

Signed-off-by: Yuan Kang <Yuan.Kang@freescale.com>

- fix dma unmap leak
- un-unlikely src == dst, due to experience with AF_ALG

Signed-off-by: Kudupudi Ugendreshwar <B38865@freescale.com>
Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

3 files changed, 147 insertions, 64 deletions

diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 5ab480a..0c1ea84 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -654,8 +654,11 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 /*
  * aead_edesc - s/w-extended aead descriptor
  * @assoc_nents: number of segments in associated data (SPI+Seq) scatterlist
+ * @assoc_chained: if source is chained
  * @src_nents: number of segments in input scatterlist
+ * @src_chained: if source is chained
  * @dst_nents: number of segments in output scatterlist
+ * @dst_chained: if destination is chained
  * @iv_dma: dma address of iv for checking continuity and link table
  * @desc: h/w descriptor (variable length; must not exceed MAX_CAAM_DESCSIZE)
  * @sec4_sg_bytes: length of dma mapped sec4_sg space
@@ -664,8 +667,11 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
  */
 struct aead_edesc {
 	int assoc_nents;
+	bool assoc_chained;
 	int src_nents;
+	bool src_chained;
 	int dst_nents;
+	bool dst_chained;
 	dma_addr_t iv_dma;
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
@@ -676,7 +682,9 @@ struct aead_edesc {
 /*
  * ablkcipher_edesc - s/w-extended ablkcipher descriptor
  * @src_nents: number of segments in input scatterlist
+ * @src_chained: if source is chained
  * @dst_nents: number of segments in output scatterlist
+ * @dst_chained: if destination is chained
  * @iv_dma: dma address of iv for checking continuity and link table
  * @desc: h/w descriptor (variable length; must not exceed MAX_CAAM_DESCSIZE)
  * @sec4_sg_bytes: length of dma mapped sec4_sg space
@@ -685,7 +693,9 @@ struct aead_edesc {
  */
 struct ablkcipher_edesc {
 	int src_nents;
+	bool src_chained;
 	int dst_nents;
+	bool dst_chained;
 	dma_addr_t iv_dma;
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
@@ -694,15 +704,19 @@ struct ablkcipher_edesc {
 };
 
 static void caam_unmap(struct device *dev, struct scatterlist *src,
-		       struct scatterlist *dst, int src_nents, int dst_nents,
+		       struct scatterlist *dst, int src_nents,
+		       bool src_chained, int dst_nents, bool dst_chained,
 		       dma_addr_t iv_dma, int ivsize, dma_addr_t sec4_sg_dma,
 		       int sec4_sg_bytes)
 {
-	if (unlikely(dst != src)) {
-		dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
-		dma_unmap_sg(dev, dst, dst_nents, DMA_FROM_DEVICE);
+	if (dst != src) {
+		dma_unmap_sg_chained(dev, src, src_nents ? : 1, DMA_TO_DEVICE,
+				     src_chained);
+		dma_unmap_sg_chained(dev, dst, dst_nents ? : 1, DMA_FROM_DEVICE,
+				     dst_chained);
 	} else {
-		dma_unmap_sg(dev, src, src_nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sg_chained(dev, src, src_nents ? : 1,
+				     DMA_BIDIRECTIONAL, src_chained);
 	}
 
 	if (iv_dma)
@@ -719,12 +733,13 @@ static void aead_unmap(struct device *dev,
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	int ivsize = crypto_aead_ivsize(aead);
 
-	dma_unmap_sg(dev, req->assoc, edesc->assoc_nents, DMA_TO_DEVICE);
+	dma_unmap_sg_chained(dev, req->assoc, edesc->assoc_nents,
+			     DMA_TO_DEVICE, edesc->assoc_chained);
 
 	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->dst_nents,
-		   edesc->iv_dma, ivsize, edesc->sec4_sg_dma,
-		   edesc->sec4_sg_bytes);
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, edesc->iv_dma, ivsize,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
 static void ablkcipher_unmap(struct device *dev,
@@ -735,9 +750,9 @@ static void ablkcipher_unmap(struct device *dev,
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 
 	caam_unmap(dev, req->src, req->dst,
-		   edesc->src_nents, edesc->dst_nents,
-		   edesc->iv_dma, ivsize, edesc->sec4_sg_dma,
-		   edesc->sec4_sg_bytes);
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, edesc->iv_dma, ivsize,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
 }
 
 static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
@@ -1128,25 +1143,26 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	dma_addr_t iv_dma = 0;
 	int sgc;
 	bool all_contig = true;
+	bool assoc_chained = false, src_chained = false, dst_chained = false;
 	int ivsize = crypto_aead_ivsize(aead);
 	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 
-	assoc_nents = sg_count(req->assoc, req->assoclen);
-	src_nents = sg_count(req->src, req->cryptlen);
+	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
+	src_nents = sg_count(req->src, req->cryptlen, &src_chained);
 
 	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->cryptlen);
+		dst_nents = sg_count(req->dst, req->cryptlen, &dst_chained);
 
-	sgc = dma_map_sg(jrdev, req->assoc, assoc_nents ? : 1,
-			 DMA_BIDIRECTIONAL);
+	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
+				 DMA_BIDIRECTIONAL, assoc_chained);
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/* Check if data are contiguous */
@@ -1172,8 +1188,11 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	}
 
 	edesc->assoc_nents = assoc_nents;
+	edesc->assoc_chained = assoc_chained;
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
 	edesc->iv_dma = iv_dma;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
@@ -1307,24 +1326,25 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	int sgc;
 	u32 contig = GIV_SRC_CONTIG | GIV_DST_CONTIG;
 	int ivsize = crypto_aead_ivsize(aead);
+	bool assoc_chained = false, src_chained = false, dst_chained = false;
 	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
 
-	assoc_nents = sg_count(req->assoc, req->assoclen);
-	src_nents = sg_count(req->src, req->cryptlen);
+	assoc_nents = sg_count(req->assoc, req->assoclen, &assoc_chained);
+	src_nents = sg_count(req->src, req->cryptlen, &src_chained);
 
 	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->cryptlen);
+		dst_nents = sg_count(req->dst, req->cryptlen, &dst_chained);
 
-	sgc = dma_map_sg(jrdev, req->assoc, assoc_nents ? : 1,
-			 DMA_BIDIRECTIONAL);
+	sgc = dma_map_sg_chained(jrdev, req->assoc, assoc_nents ? : 1,
+				 DMA_BIDIRECTIONAL, assoc_chained);
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/* Check if data are contiguous */
@@ -1358,8 +1378,11 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	}
 
 	edesc->assoc_nents = assoc_nents;
+	edesc->assoc_chained = assoc_chained;
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
 	edesc->iv_dma = iv_dma;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
@@ -1459,21 +1482,22 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	bool iv_contig = false;
 	int sgc;
 	int ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	bool src_chained = false, dst_chained = false;
 	int sec4_sg_index;
 
-	src_nents = sg_count(req->src, req->nbytes);
+	src_nents = sg_count(req->src, req->nbytes, &src_chained);
 
-	if (unlikely(req->dst != req->src))
-		dst_nents = sg_count(req->dst, req->nbytes);
+	if (req->dst != req->src)
+		dst_nents = sg_count(req->dst, req->nbytes, &dst_chained);
 
 	if (likely(req->src == req->dst)) {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_BIDIRECTIONAL);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
 	} else {
-		sgc = dma_map_sg(jrdev, req->src, src_nents ? : 1,
-				 DMA_TO_DEVICE);
-		sgc = dma_map_sg(jrdev, req->dst, dst_nents ? : 1,
-				 DMA_FROM_DEVICE);
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
 	}
 
 	/*
@@ -1497,7 +1521,9 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	}
 
 	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
 	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
 			 desc_bytes;
@@ -1510,7 +1536,7 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 		sec4_sg_index += 1 + src_nents;
 	}
 
-	if (unlikely(dst_nents)) {
+	if (dst_nents) {
 		sg_to_sec4_sg_last(req->dst, dst_nents,
 			edesc->sec4_sg + sec4_sg_index, 0);
 	}
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 7dcf28f..895aaf2 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -175,9 +175,10 @@ static inline dma_addr_t buf_map_to_sec4_sg(struct device *jrdev,
 /* Map req->src and put it in link table */
 static inline void src_map_to_sec4_sg(struct device *jrdev,
 				      struct scatterlist *src, int src_nents,
-				      struct sec4_sg_entry *sec4_sg)
+				      struct sec4_sg_entry *sec4_sg,
+				      bool chained)
 {
-	dma_map_sg(jrdev, src, src_nents, DMA_TO_DEVICE);
+	dma_map_sg_chained(jrdev, src, src_nents, DMA_TO_DEVICE, chained);
 	sg_to_sec4_sg_last(src, src_nents, sec4_sg, 0);
 }
 
@@ -563,6 +564,7 @@ badkey:
  * ahash_edesc - s/w-extended ahash descriptor
  * @dst_dma: physical mapped address of req->result
  * @sec4_sg_dma: physical mapped address of h/w link table
+ * @chained: if source is chained
  * @src_nents: number of segments in input scatterlist
  * @sec4_sg_bytes: length of dma mapped sec4_sg space
  * @sec4_sg: pointer to h/w link table
@@ -571,6 +573,7 @@ badkey:
 struct ahash_edesc {
 	dma_addr_t dst_dma;
 	dma_addr_t sec4_sg_dma;
+	bool chained;
 	int src_nents;
 	int sec4_sg_bytes;
 	struct sec4_sg_entry *sec4_sg;
@@ -582,7 +585,8 @@ static inline void ahash_unmap(struct device *dev,
 			struct ahash_request *req, int dst_len)
 {
 	if (edesc->src_nents)
-		dma_unmap_sg(dev, req->src, edesc->src_nents, DMA_TO_DEVICE);
+		dma_unmap_sg_chained(dev, req->src, edesc->src_nents,
+				     DMA_TO_DEVICE, edesc->chained);
 	if (edesc->dst_dma)
 		dma_unmap_single(dev, edesc->dst_dma, dst_len, DMA_FROM_DEVICE);
 
@@ -775,6 +779,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 	dma_addr_t ptr = ctx->sh_desc_update_dma;
 	int src_nents, sec4_sg_bytes, sec4_sg_src_index;
 	struct ahash_edesc *edesc;
+	bool chained = false;
 	int ret = 0;
 	int sh_len;
 
@@ -783,7 +788,8 @@ static int ahash_update_ctx(struct ahash_request *req)
 	to_hash = in_len - *next_buflen;
 
 	if (to_hash) {
-		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen));
+		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen),
+				       &chained);
 		sec4_sg_src_index = 1 + (*buflen ? 1 : 0);
 		sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 				 sizeof(struct sec4_sg_entry);
@@ -801,6 +807,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 		}
 
 		edesc->src_nents = src_nents;
+		edesc->chained = chained;
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
@@ -818,7 +825,8 @@ static int ahash_update_ctx(struct ahash_request *req)
 
 		if (src_nents) {
 			src_map_to_sec4_sg(jrdev, req->src, src_nents,
-					   edesc->sec4_sg + sec4_sg_src_index);
+					   edesc->sec4_sg + sec4_sg_src_index,
+					   chained);
 			if (*next_buflen) {
 				sg_copy_part(next_buf, req->src, to_hash -
 					     *buflen, req->nbytes);
@@ -958,10 +966,11 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	int src_nents;
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct ahash_edesc *edesc;
+	bool chained = false;
 	int ret = 0;
 	int sh_len;
 
-	src_nents = __sg_count(req->src, req->nbytes);
+	src_nents = __sg_count(req->src, req->nbytes, &chained);
 	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
 	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 			 sizeof(struct sec4_sg_entry);
@@ -979,6 +988,7 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
 
 	edesc->src_nents = src_nents;
+	edesc->chained = chained;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			 DESC_JOB_IO_LEN;
@@ -993,7 +1003,7 @@ static int ahash_finup_ctx(struct ahash_request *req)
 						last_buflen);
 
 	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg +
-			   sec4_sg_src_index);
+			   sec4_sg_src_index, chained);
 
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len +
 			       buflen + req->nbytes, LDST_SGF);
@@ -1030,12 +1040,14 @@ static int ahash_digest(struct ahash_request *req)
 	int src_nents, sec4_sg_bytes;
 	dma_addr_t src_dma;
 	struct ahash_edesc *edesc;
+	bool chained = false;
 	int ret = 0;
 	u32 options;
 	int sh_len;
 
-	src_nents = sg_count(req->src, req->nbytes);
-	dma_map_sg(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE);
+	src_nents = sg_count(req->src, req->nbytes, &chained);
+	dma_map_sg_chained(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE,
+			   chained);
 	sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
@@ -1050,6 +1062,7 @@ static int ahash_digest(struct ahash_request *req)
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
 	edesc->src_nents = src_nents;
+	edesc->chained = chained;
 
 	sh_len = desc_len(sh_desc);
 	desc = edesc->hw_desc;
@@ -1157,6 +1170,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 	struct ahash_edesc *edesc;
 	u32 *desc, *sh_desc = ctx->sh_desc_update_first;
 	dma_addr_t ptr = ctx->sh_desc_update_first_dma;
+	bool chained = false;
 	int ret = 0;
 	int sh_len;
 
@@ -1164,7 +1178,8 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 	to_hash = in_len - *next_buflen;
 
 	if (to_hash) {
-		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen));
+		src_nents = __sg_count(req->src, req->nbytes - (*next_buflen),
+				       &chained);
 		sec4_sg_bytes = (1 + src_nents) *
 				sizeof(struct sec4_sg_entry);
 
@@ -1181,6 +1196,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		}
 
 		edesc->src_nents = src_nents;
+		edesc->chained = chained;
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
@@ -1191,7 +1207,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		state->buf_dma = buf_map_to_sec4_sg(jrdev, edesc->sec4_sg,
 						    buf, *buflen);
 		src_map_to_sec4_sg(jrdev, req->src, src_nents,
-				   edesc->sec4_sg + 1);
+				   edesc->sec4_sg + 1, chained);
 		if (*next_buflen) {
 			sg_copy_part(next_buf, req->src, to_hash - *buflen,
 				    req->nbytes);
@@ -1258,10 +1274,11 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	int sec4_sg_bytes, sec4_sg_src_index, src_nents;
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct ahash_edesc *edesc;
+	bool chained = false;
 	int sh_len;
 	int ret = 0;
 
-	src_nents = __sg_count(req->src, req->nbytes);
+	src_nents = __sg_count(req->src, req->nbytes, &chained);
 	sec4_sg_src_index = 2;
 	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 			 sizeof(struct sec4_sg_entry);
@@ -1279,6 +1296,7 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
 
 	edesc->src_nents = src_nents;
+	edesc->chained = chained;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			 DESC_JOB_IO_LEN;
@@ -1289,7 +1307,8 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 						state->buf_dma, buflen,
 						last_buflen);
 
-	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1);
+	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1,
+			   chained);
 
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, buflen +
 			       req->nbytes, LDST_SGF);
@@ -1332,6 +1351,7 @@ static int ahash_update_first(struct ahash_request *req)
 	dma_addr_t src_dma;
 	u32 options;
 	struct ahash_edesc *edesc;
+	bool chained = false;
 	int ret = 0;
 	int sh_len;
 
@@ -1340,8 +1360,10 @@ static int ahash_update_first(struct ahash_request *req)
 	to_hash = req->nbytes - *next_buflen;
 
 	if (to_hash) {
-		src_nents = sg_count(req->src, req->nbytes - (*next_buflen));
-		dma_map_sg(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE);
+		src_nents = sg_count(req->src, req->nbytes - (*next_buflen),
+				     &chained);
+		dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+				   DMA_TO_DEVICE, chained);
 		sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
 
 		/*
@@ -1357,6 +1379,7 @@ static int ahash_update_first(struct ahash_request *req)
 		}
 
 		edesc->src_nents = src_nents;
+		edesc->chained = chained;
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index 2dda9e3..e0037c8 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -37,7 +37,7 @@ sg_to_sec4_sg(struct scatterlist *sg, int sg_count,
 		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg),
 				   sg_dma_len(sg), offset);
 		sec4_sg_ptr++;
-		sg = sg_next(sg);
+		sg = scatterwalk_sg_next(sg);
 		sg_count--;
 	}
 	return sec4_sg_ptr - 1;
@@ -56,7 +56,8 @@ static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
 }
 
 /* count number of elements in scatterlist */
-static inline int __sg_count(struct scatterlist *sg_list, int nbytes)
+static inline int __sg_count(struct scatterlist *sg_list, int nbytes,
+			     bool *chained)
 {
 	struct scatterlist *sg = sg_list;
 	int sg_nents = 0;
@@ -65,7 +66,7 @@ static inline int __sg_count(struct scatterlist *sg_list, int nbytes)
 		sg_nents++;
 		nbytes -= sg->length;
 		if (!sg_is_last(sg) && (sg + 1)->length == 0)
-			BUG(); /* Not support chaining */
+			*chained = true;
 		sg = scatterwalk_sg_next(sg);
 	}
 
@@ -73,9 +74,10 @@ static inline int __sg_count(struct scatterlist *sg_list, int nbytes)
 }
 
 /* derive number of elements in scatterlist, but return 0 for 1 */
-static inline int sg_count(struct scatterlist *sg_list, int nbytes)
+static inline int sg_count(struct scatterlist *sg_list, int nbytes,
+			     bool *chained)
 {
-	int sg_nents = __sg_count(sg_list, nbytes);
+	int sg_nents = __sg_count(sg_list, nbytes, chained);
 
 	if (likely(sg_nents == 1))
 		return 0;
@@ -83,6 +85,38 @@ static inline int sg_count(struct scatterlist *sg_list, int nbytes)
 	return sg_nents;
 }
 
+static int dma_map_sg_chained(struct device *dev, struct scatterlist *sg,
+			      unsigned int nents, enum dma_data_direction dir,
+			      bool chained)
+{
+	if (unlikely(chained)) {
+		int i;
+		for (i = 0; i < nents; i++) {
+			dma_map_sg(dev, sg, 1, dir);
+			sg = scatterwalk_sg_next(sg);
+		}
+	} else {
+		dma_map_sg(dev, sg, nents, dir);
+	}
+	return nents;
+}
+
+static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg,
+				unsigned int nents, enum dma_data_direction dir,
+				bool chained)
+{
+	if (unlikely(chained)) {
+		int i;
+		for (i = 0; i < nents; i++) {
+			dma_unmap_sg(dev, sg, 1, dir);
+			sg = scatterwalk_sg_next(sg);
+		}
+	} else {
+		dma_unmap_sg(dev, sg, nents, dir);
+	}
+	return nents;
+}
+
 /* Copy from len bytes of sg to dest, starting from beginning */
 static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len)
 {