crypto: sun8i-ss - handle requests if last block is not modulo 64

The current sun8i-ss handle only requests with all SG length being
modulo 64.
But the last SG could be always handled by copying it on the pad buffer.
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c

@@ -487,7 +487,7 @@ static int allocate_flows(struct sun8i_ss_dev *ss)
 		}
 
 		/* the padding could be up to two block. */
-		ss->flows[i].pad = devm_kmalloc(ss->dev, SHA256_BLOCK_SIZE * 2,
+		ss->flows[i].pad = devm_kmalloc(ss->dev, MAX_PAD_SIZE,
 						GFP_KERNEL | GFP_DMA);
 		if (!ss->flows[i].pad)
 			goto error_engine;

drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c

@@ -14,6 +14,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
 #include <crypto/internal/hash.h>
+#include <crypto/scatterwalk.h>
 #include <crypto/sha1.h>
 #include <crypto/sha2.h>
 #include <crypto/md5.h>
@@ -262,6 +263,9 @@ static bool sun8i_ss_hash_need_fallback(struct ahash_request *areq)
 
 	if (areq->nbytes == 0)
 		return true;
+	if (areq->nbytes >= MAX_PAD_SIZE - 64)
+		return true;
+
 	/* we need to reserve one SG for the padding one */
 	if (sg_nents(areq->src) > MAX_SG - 1)
 		return true;
@@ -270,10 +274,13 @@ static bool sun8i_ss_hash_need_fallback(struct ahash_request *areq)
 		/* SS can operate hash only on full block size
 		 * since SS support only MD5,sha1,sha224 and sha256, blocksize
 		 * is always 64
-		 * TODO: handle request if last SG is not len%64
-		 * but this will need to copy data on a new SG of size=64
 		 */
-		if (sg->length % 64 || !IS_ALIGNED(sg->offset, sizeof(u32)))
+		/* Only the last block could be bounced to the pad buffer */
+		if (sg->length % 64 && sg_next(sg))
+			return true;
+		if (!IS_ALIGNED(sg->offset, sizeof(u32)))
+			return true;
+		if (sg->length % 4)
 			return true;
 		sg = sg_next(sg);
 	}
@@ -361,6 +368,7 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq)
 		goto theend;
 	}
 
+	j = 0;
 	len = areq->nbytes;
 	sg = areq->src;
 	i = 0;
@@ -369,12 +377,19 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq)
 			sg = sg_next(sg);
 			continue;
 		}
-		rctx->t_src[i].addr = sg_dma_address(sg);
 		todo = min(len, sg_dma_len(sg));
+		/* only the last SG could be with a size not modulo64 */
+		if (todo % 64 == 0) {
+			rctx->t_src[i].addr = sg_dma_address(sg);
 			rctx->t_src[i].len = todo / 4;
-		len -= todo;
 			rctx->t_dst[i].addr = addr_res;
 			rctx->t_dst[i].len = digestsize / 4;
+			len -= todo;
+		} else {
+			scatterwalk_map_and_copy(bf, sg, 0, todo, 0);
+			j += todo / 4;
+			len -= todo;
+		}
 		sg = sg_next(sg);
 		i++;
 	}
@@ -384,8 +399,10 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq)
 		goto theend;
 	}
 
+	if (j > 0)
+		i--;
+
 	byte_count = areq->nbytes;
-	j = 0;
 	bf[j++] = cpu_to_le32(0x80);
 
 	fill = 64 - (byte_count % 64);

drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h

@@ -82,6 +82,8 @@
 #define PRNG_DATA_SIZE (160 / 8)
 #define PRNG_SEED_SIZE DIV_ROUND_UP(175, 8)
 
+#define MAX_PAD_SIZE 4096
+
 /*
  * struct ss_clock - Describe clocks used by sun8i-ss
  * @name:       Name of clock needed by this variant