4 files changed, 179 insertions, 487 deletions

diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index 5ee4ade99b99..fbc84eb7fedf 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -19,22 +19,26 @@
  * any later version.
  */
 
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/md5.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/string.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
+#include <linux/unaligned.h>
 
 #include "octeon-crypto.h"
 
+struct octeon_md5_state {
+	__le32 hash[MD5_HASH_WORDS];
+	u64 byte_count;
+};
+
 /*
  * We pass everything as 64-bit. OCTEON can handle misaligned data.
  */
 
-static void octeon_md5_store_hash(struct md5_state *ctx)
+static void octeon_md5_store_hash(struct octeon_md5_state *ctx)
 {
 	u64 *hash = (u64 *)ctx->hash;
 
@@ -42,7 +46,7 @@ static void octeon_md5_store_hash(struct md5_state *ctx)
 	write_octeon_64bit_hash_dword(hash[1], 1);
 }
 
-static void octeon_md5_read_hash(struct md5_state *ctx)
+static void octeon_md5_read_hash(struct octeon_md5_state *ctx)
 {
 	u64 *hash = (u64 *)ctx->hash;
 
@@ -66,13 +70,12 @@ static void octeon_md5_transform(const void *_block)
 
 static int octeon_md5_init(struct shash_desc *desc)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = MD5_H0;
-	mctx->hash[1] = MD5_H1;
-	mctx->hash[2] = MD5_H2;
-	mctx->hash[3] = MD5_H3;
-	cpu_to_le32_array(mctx->hash, 4);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
@@ -81,52 +84,38 @@ static int octeon_md5_init(struct shash_desc *desc)
 static int octeon_md5_update(struct shash_desc *desc, const u8 *data,
 			     unsigned int len)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
-	const u32 avail = sizeof(mctx->block) - (mctx->byte_count & 0x3f);
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
 
 	mctx->byte_count += len;
-
-	if (avail > len) {
-		memcpy((char *)mctx->block + (sizeof(mctx->block) - avail),
-		       data, len);
-		return 0;
-	}
-
-	memcpy((char *)mctx->block + (sizeof(mctx->block) - avail), data,
-	       avail);
-
 	flags = octeon_crypto_enable(&state);
 	octeon_md5_store_hash(mctx);
 
-	octeon_md5_transform(mctx->block);
-	data += avail;
-	len -= avail;
-
-	while (len >= sizeof(mctx->block)) {
+	do {
 		octeon_md5_transform(data);
-		data += sizeof(mctx->block);
-		len -= sizeof(mctx->block);
-	}
+		data += MD5_HMAC_BLOCK_SIZE;
+		len -= MD5_HMAC_BLOCK_SIZE;
+	} while (len >= MD5_HMAC_BLOCK_SIZE);
 
 	octeon_md5_read_hash(mctx);
 	octeon_crypto_disable(&state, flags);
-
-	memcpy(mctx->block, data, len);
-
-	return 0;
+	mctx->byte_count -= len;
+	return len;
 }
 
-static int octeon_md5_final(struct shash_desc *desc, u8 *out)
+static int octeon_md5_finup(struct shash_desc *desc, const u8 *src,
+			    unsigned int offset, u8 *out)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
-	const unsigned int offset = mctx->byte_count & 0x3f;
-	char *p = (char *)mctx->block + offset;
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 	int padding = 56 - (offset + 1);
 	struct octeon_cop2_state state;
+	u32 block[MD5_BLOCK_WORDS];
 	unsigned long flags;
+	char *p;
 
+	p = memcpy(block, src, offset);
+	p += offset;
 	*p++ = 0x80;
 
 	flags = octeon_crypto_enable(&state);
@@ -134,39 +123,56 @@ static int octeon_md5_final(struct shash_desc *desc, u8 *out)
 
 	if (padding < 0) {
 		memset(p, 0x00, padding + sizeof(u64));
-		octeon_md5_transform(mctx->block);
-		p = (char *)mctx->block;
+		octeon_md5_transform(block);
+		p = (char *)block;
 		padding = 56;
 	}
 
 	memset(p, 0, padding);
-	mctx->block[14] = mctx->byte_count << 3;
-	mctx->block[15] = mctx->byte_count >> 29;
-	cpu_to_le32_array(mctx->block + 14, 2);
-	octeon_md5_transform(mctx->block);
+	mctx->byte_count += offset;
+	block[14] = mctx->byte_count << 3;
+	block[15] = mctx->byte_count >> 29;
+	cpu_to_le32_array(block + 14, 2);
+	octeon_md5_transform(block);
 
 	octeon_md5_read_hash(mctx);
 	octeon_crypto_disable(&state, flags);
 
+	memzero_explicit(block, sizeof(block));
 	memcpy(out, mctx->hash, sizeof(mctx->hash));
-	memset(mctx, 0, sizeof(*mctx));
 
 	return 0;
 }
 
 static int octeon_md5_export(struct shash_desc *desc, void *out)
 {
-	struct md5_state *ctx = shash_desc_ctx(desc);
-
-	memcpy(out, ctx, sizeof(*ctx));
+	struct octeon_md5_state *ctx = shash_desc_ctx(desc);
+	union {
+		u8 *u8;
+		u32 *u32;
+		u64 *u64;
+	} p = { .u8 = out };
+	int i;
+
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		put_unaligned(le32_to_cpu(ctx->hash[i]), p.u32++);
+	put_unaligned(ctx->byte_count, p.u64);
 	return 0;
 }
 
 static int octeon_md5_import(struct shash_desc *desc, const void *in)
 {
-	struct md5_state *ctx = shash_desc_ctx(desc);
-
-	memcpy(ctx, in, sizeof(*ctx));
+	struct octeon_md5_state *ctx = shash_desc_ctx(desc);
+	union {
+		const u8 *u8;
+		const u32 *u32;
+		const u64 *u64;
+	} p = { .u8 = in };
+	int i;
+
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		ctx->hash[i] = cpu_to_le32(get_unaligned(p.u32++));
+	ctx->byte_count = get_unaligned(p.u64);
 	return 0;
 }
 
@@ -174,15 +180,16 @@ static struct shash_alg alg = {
 	.digestsize	=	MD5_DIGEST_SIZE,
 	.init		=	octeon_md5_init,
 	.update		=	octeon_md5_update,
-	.final		=	octeon_md5_final,
+	.finup		=	octeon_md5_finup,
 	.export		=	octeon_md5_export,
 	.import		=	octeon_md5_import,
-	.descsize	=	sizeof(struct md5_state),
-	.statesize	=	sizeof(struct md5_state),
+	.statesize	=	MD5_STATE_SIZE,
+	.descsize	=	sizeof(struct octeon_md5_state),
 	.base		=	{
 		.cra_name	=	"md5",
 		.cra_driver_name=	"octeon-md5",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha1.c b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
index 37a07b3c4568..e70f21a473da 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha1.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
@@ -13,15 +13,13 @@
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  */
 
-#include <linux/mm.h>
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
 
 #include "octeon-crypto.h"
 
@@ -58,49 +56,23 @@ static void octeon_sha1_read_hash(struct sha1_state *sctx)
 	memzero_explicit(&hash_tail.dword, sizeof(hash_tail.dword));
 }
 
-static void octeon_sha1_transform(const void *_block)
+static void octeon_sha1_transform(struct sha1_state *sctx, const u8 *src,
+				  int blocks)
 {
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_dword(block[0], 0);
-	write_octeon_64bit_block_dword(block[1], 1);
-	write_octeon_64bit_block_dword(block[2], 2);
-	write_octeon_64bit_block_dword(block[3], 3);
-	write_octeon_64bit_block_dword(block[4], 4);
-	write_octeon_64bit_block_dword(block[5], 5);
-	write_octeon_64bit_block_dword(block[6], 6);
-	octeon_sha1_start(block[7]);
-}
-
-static void __octeon_sha1_update(struct sha1_state *sctx, const u8 *data,
-				 unsigned int len)
-{
-	unsigned int partial;
-	unsigned int done;
-	const u8 *src;
-
-	partial = sctx->count % SHA1_BLOCK_SIZE;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) >= SHA1_BLOCK_SIZE) {
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buffer + partial, data,
-			       done + SHA1_BLOCK_SIZE);
-			src = sctx->buffer;
-		}
-
-		do {
-			octeon_sha1_transform(src);
-			done += SHA1_BLOCK_SIZE;
-			src = data + done;
-		} while (done + SHA1_BLOCK_SIZE <= len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buffer + partial, src, len - done);
+	do {
+		const u64 *block = (const u64 *)src;
+
+		write_octeon_64bit_block_dword(block[0], 0);
+		write_octeon_64bit_block_dword(block[1], 1);
+		write_octeon_64bit_block_dword(block[2], 2);
+		write_octeon_64bit_block_dword(block[3], 3);
+		write_octeon_64bit_block_dword(block[4], 4);
+		write_octeon_64bit_block_dword(block[5], 5);
+		write_octeon_64bit_block_dword(block[6], 6);
+		octeon_sha1_start(block[7]);
+
+		src += SHA1_BLOCK_SIZE;
+	} while (--blocks);
 }
 
 static int octeon_sha1_update(struct shash_desc *desc, const u8 *data,
@@ -109,95 +81,47 @@ static int octeon_sha1_update(struct shash_desc *desc, const u8 *data,
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha1 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
-		return crypto_sha1_update(desc, data, len);
+	int remain;
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha1_store_hash(sctx);
 
-	__octeon_sha1_update(sctx, data, len);
+	remain = sha1_base_do_update_blocks(desc, data, len,
+					    octeon_sha1_transform);
 
 	octeon_sha1_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	return 0;
+	return remain;
 }
 
-static int octeon_sha1_final(struct shash_desc *desc, u8 *out)
+static int octeon_sha1_finup(struct shash_desc *desc, const u8 *src,
+			     unsigned int len, u8 *out)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
-	static const u8 padding[64] = { 0x80, };
 	struct octeon_cop2_state state;
-	__be32 *dst = (__be32 *)out;
-	unsigned int pad_len;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits;
-	int i;
-
-	/* Save number of bits. */
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64. */
-	index = sctx->count & 0x3f;
-	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha1_store_hash(sctx);
 
-	__octeon_sha1_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha1_update(sctx, (const u8 *)&bits, sizeof(bits));
+	sha1_base_do_finup(desc, src, len, octeon_sha1_transform);
 
 	octeon_sha1_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest */
-	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int octeon_sha1_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int octeon_sha1_import(struct shash_desc *desc, const void *in)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
+	return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg octeon_sha1_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	octeon_sha1_update,
-	.final		=	octeon_sha1_final,
-	.export		=	octeon_sha1_export,
-	.import		=	octeon_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
+	.finup		=	octeon_sha1_finup,
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"octeon-sha1",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha256.c b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
index 435e4a6e7f13..f93faaf1f4af 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha256.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Cryptographic API.
- *
- * SHA-224 and SHA-256 Secure Hash Algorithm.
+ * SHA-256 Secure Hash Algorithm.
  *
  * Adapted for OCTEON by Aaro Koskinen <aaro.koskinen@iki.fi>.
  *
@@ -14,15 +12,10 @@
  * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
  */
 
-#include <linux/mm.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <asm/byteorder.h>
 #include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 #include "octeon-crypto.h"
 
@@ -30,212 +23,51 @@
  * We pass everything as 64-bit. OCTEON can handle misaligned data.
  */
 
-static void octeon_sha256_store_hash(struct sha256_state *sctx)
-{
-	u64 *hash = (u64 *)sctx->state;
-
-	write_octeon_64bit_hash_dword(hash[0], 0);
-	write_octeon_64bit_hash_dword(hash[1], 1);
-	write_octeon_64bit_hash_dword(hash[2], 2);
-	write_octeon_64bit_hash_dword(hash[3], 3);
-}
-
-static void octeon_sha256_read_hash(struct sha256_state *sctx)
-{
-	u64 *hash = (u64 *)sctx->state;
-
-	hash[0] = read_octeon_64bit_hash_dword(0);
-	hash[1] = read_octeon_64bit_hash_dword(1);
-	hash[2] = read_octeon_64bit_hash_dword(2);
-	hash[3] = read_octeon_64bit_hash_dword(3);
-}
-
-static void octeon_sha256_transform(const void *_block)
-{
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_dword(block[0], 0);
-	write_octeon_64bit_block_dword(block[1], 1);
-	write_octeon_64bit_block_dword(block[2], 2);
-	write_octeon_64bit_block_dword(block[3], 3);
-	write_octeon_64bit_block_dword(block[4], 4);
-	write_octeon_64bit_block_dword(block[5], 5);
-	write_octeon_64bit_block_dword(block[6], 6);
-	octeon_sha256_start(block[7]);
-}
-
-static void __octeon_sha256_update(struct sha256_state *sctx, const u8 *data,
-				   unsigned int len)
-{
-	unsigned int partial;
-	unsigned int done;
-	const u8 *src;
-
-	partial = sctx->count % SHA256_BLOCK_SIZE;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) >= SHA256_BLOCK_SIZE) {
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buf + partial, data,
-			       done + SHA256_BLOCK_SIZE);
-			src = sctx->buf;
-		}
-
-		do {
-			octeon_sha256_transform(src);
-			done += SHA256_BLOCK_SIZE;
-			src = data + done;
-		} while (done + SHA256_BLOCK_SIZE <= len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buf + partial, src, len - done);
-}
-
-static int octeon_sha256_update(struct shash_desc *desc, const u8 *data,
-				unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	struct octeon_cop2_state state;
-	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha256 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
-		return crypto_sha256_update(desc, data, len);
-
-	flags = octeon_crypto_enable(&state);
-	octeon_sha256_store_hash(sctx);
-
-	__octeon_sha256_update(sctx, data, len);
-
-	octeon_sha256_read_hash(sctx);
-	octeon_crypto_disable(&state, flags);
-
-	return 0;
-}
-
-static int octeon_sha256_final(struct shash_desc *desc, u8 *out)
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
 {
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	static const u8 padding[64] = { 0x80, };
-	struct octeon_cop2_state state;
-	__be32 *dst = (__be32 *)out;
-	unsigned int pad_len;
+	struct octeon_cop2_state cop2_state;
+	u64 *state64 = (u64 *)state;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits;
-	int i;
-
-	/* Save number of bits. */
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64. */
-	index = sctx->count & 0x3f;
-	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
-
-	flags = octeon_crypto_enable(&state);
-	octeon_sha256_store_hash(sctx);
-
-	__octeon_sha256_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha256_update(sctx, (const u8 *)&bits, sizeof(bits));
-
-	octeon_sha256_read_hash(sctx);
-	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int octeon_sha224_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA256_DIGEST_SIZE];
-
-	octeon_sha256_final(desc, D);
 
-	memcpy(hash, D, SHA224_DIGEST_SIZE);
-	memzero_explicit(D, SHA256_DIGEST_SIZE);
-
-	return 0;
-}
-
-static int octeon_sha256_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int octeon_sha256_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg octeon_sha256_algs[2] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	octeon_sha256_update,
-	.final		=	octeon_sha256_final,
-	.export		=	octeon_sha256_export,
-	.import		=	octeon_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"octeon-sha256",
-		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	octeon_sha256_update,
-	.final		=	octeon_sha224_final,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"octeon-sha224",
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init octeon_sha256_mod_init(void)
-{
 	if (!octeon_has_crypto())
-		return -ENOTSUPP;
-	return crypto_register_shashes(octeon_sha256_algs,
-				       ARRAY_SIZE(octeon_sha256_algs));
+		return sha256_blocks_generic(state, data, nblocks);
+
+	flags = octeon_crypto_enable(&cop2_state);
+	write_octeon_64bit_hash_dword(state64[0], 0);
+	write_octeon_64bit_hash_dword(state64[1], 1);
+	write_octeon_64bit_hash_dword(state64[2], 2);
+	write_octeon_64bit_hash_dword(state64[3], 3);
+
+	do {
+		const u64 *block = (const u64 *)data;
+
+		write_octeon_64bit_block_dword(block[0], 0);
+		write_octeon_64bit_block_dword(block[1], 1);
+		write_octeon_64bit_block_dword(block[2], 2);
+		write_octeon_64bit_block_dword(block[3], 3);
+		write_octeon_64bit_block_dword(block[4], 4);
+		write_octeon_64bit_block_dword(block[5], 5);
+		write_octeon_64bit_block_dword(block[6], 6);
+		octeon_sha256_start(block[7]);
+
+		data += SHA256_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state64[0] = read_octeon_64bit_hash_dword(0);
+	state64[1] = read_octeon_64bit_hash_dword(1);
+	state64[2] = read_octeon_64bit_hash_dword(2);
+	state64[3] = read_octeon_64bit_hash_dword(3);
+	octeon_crypto_disable(&cop2_state, flags);
 }
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
 
-static void __exit octeon_sha256_mod_fini(void)
+bool sha256_is_arch_optimized(void)
 {
-	crypto_unregister_shashes(octeon_sha256_algs,
-				  ARRAY_SIZE(octeon_sha256_algs));
+	return octeon_has_crypto();
 }
-
-module_init(octeon_sha256_mod_init);
-module_exit(octeon_sha256_mod_fini);
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm (OCTEON)");
+MODULE_DESCRIPTION("SHA-256 Secure Hash Algorithm (OCTEON)");
 MODULE_AUTHOR("Aaro Koskinen <aaro.koskinen@iki.fi>");
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha512.c b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
index 2dee9354e33f..215311053db3 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha512.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
@@ -13,15 +13,12 @@
  * Copyright (c) 2003 Kyle McMartin <kyle@debian.org>
  */
 
-#include <linux/mm.h>
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
 
 #include "octeon-crypto.h"
 
@@ -53,60 +50,31 @@ static void octeon_sha512_read_hash(struct sha512_state *sctx)
 	sctx->state[7] = read_octeon_64bit_hash_sha512(7);
 }
 
-static void octeon_sha512_transform(const void *_block)
+static void octeon_sha512_transform(struct sha512_state *sctx,
+				    const u8 *src, int blocks)
 {
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_sha512(block[0], 0);
-	write_octeon_64bit_block_sha512(block[1], 1);
-	write_octeon_64bit_block_sha512(block[2], 2);
-	write_octeon_64bit_block_sha512(block[3], 3);
-	write_octeon_64bit_block_sha512(block[4], 4);
-	write_octeon_64bit_block_sha512(block[5], 5);
-	write_octeon_64bit_block_sha512(block[6], 6);
-	write_octeon_64bit_block_sha512(block[7], 7);
-	write_octeon_64bit_block_sha512(block[8], 8);
-	write_octeon_64bit_block_sha512(block[9], 9);
-	write_octeon_64bit_block_sha512(block[10], 10);
-	write_octeon_64bit_block_sha512(block[11], 11);
-	write_octeon_64bit_block_sha512(block[12], 12);
-	write_octeon_64bit_block_sha512(block[13], 13);
-	write_octeon_64bit_block_sha512(block[14], 14);
-	octeon_sha512_start(block[15]);
-}
-
-static void __octeon_sha512_update(struct sha512_state *sctx, const u8 *data,
-				   unsigned int len)
-{
-	unsigned int part_len;
-	unsigned int index;
-	unsigned int i;
-
-	/* Compute number of bytes mod 128. */
-	index = sctx->count[0] % SHA512_BLOCK_SIZE;
-
-	/* Update number of bytes. */
-	if ((sctx->count[0] += len) < len)
-		sctx->count[1]++;
-
-	part_len = SHA512_BLOCK_SIZE - index;
-
-	/* Transform as many times as possible. */
-	if (len >= part_len) {
-		memcpy(&sctx->buf[index], data, part_len);
-		octeon_sha512_transform(sctx->buf);
-
-		for (i = part_len; i + SHA512_BLOCK_SIZE <= len;
-			i += SHA512_BLOCK_SIZE)
-			octeon_sha512_transform(&data[i]);
-
-		index = 0;
-	} else {
-		i = 0;
-	}
-
-	/* Buffer remaining input. */
-	memcpy(&sctx->buf[index], &data[i], len - i);
+	do {
+		const u64 *block = (const u64 *)src;
+
+		write_octeon_64bit_block_sha512(block[0], 0);
+		write_octeon_64bit_block_sha512(block[1], 1);
+		write_octeon_64bit_block_sha512(block[2], 2);
+		write_octeon_64bit_block_sha512(block[3], 3);
+		write_octeon_64bit_block_sha512(block[4], 4);
+		write_octeon_64bit_block_sha512(block[5], 5);
+		write_octeon_64bit_block_sha512(block[6], 6);
+		write_octeon_64bit_block_sha512(block[7], 7);
+		write_octeon_64bit_block_sha512(block[8], 8);
+		write_octeon_64bit_block_sha512(block[9], 9);
+		write_octeon_64bit_block_sha512(block[10], 10);
+		write_octeon_64bit_block_sha512(block[11], 11);
+		write_octeon_64bit_block_sha512(block[12], 12);
+		write_octeon_64bit_block_sha512(block[13], 13);
+		write_octeon_64bit_block_sha512(block[14], 14);
+		octeon_sha512_start(block[15]);
+
+		src += SHA512_BLOCK_SIZE;
+	} while (--blocks);
 }
 
 static int octeon_sha512_update(struct shash_desc *desc, const u8 *data,
@@ -115,89 +83,48 @@ static int octeon_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha512 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
-		return crypto_sha512_update(desc, data, len);
+	int remain;
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha512_store_hash(sctx);
 
-	__octeon_sha512_update(sctx, data, len);
+	remain = sha512_base_do_update_blocks(desc, data, len,
+					      octeon_sha512_transform);
 
 	octeon_sha512_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	return 0;
+	return remain;
 }
 
-static int octeon_sha512_final(struct shash_desc *desc, u8 *hash)
+static int octeon_sha512_finup(struct shash_desc *desc, const u8 *src,
+			       unsigned int len, u8 *hash)
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
-	static u8 padding[128] = { 0x80, };
 	struct octeon_cop2_state state;
-	__be64 *dst = (__be64 *)hash;
-	unsigned int pad_len;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits[2];
-	int i;
-
-	/* Save number of bits. */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128. */
-	index = sctx->count[0] & 0x7f;
-	pad_len = (index < 112) ? (112 - index) : ((128+112) - index);
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha512_store_hash(sctx);
 
-	__octeon_sha512_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha512_update(sctx, (const u8 *)bits, sizeof(bits));
+	sha512_base_do_finup(desc, src, len, octeon_sha512_transform);
 
 	octeon_sha512_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest. */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(struct sha512_state));
-
-	return 0;
-}
-
-static int octeon_sha384_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[64];
-
-	octeon_sha512_final(desc, D);
-
-	memcpy(hash, D, 48);
-	memzero_explicit(D, 64);
-
-	return 0;
+	return sha512_base_finish(desc, hash);
 }
 
 static struct shash_alg octeon_sha512_algs[2] = { {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	octeon_sha512_update,
-	.final		=	octeon_sha512_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	octeon_sha512_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"octeon-sha512",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -205,12 +132,14 @@ static struct shash_alg octeon_sha512_algs[2] = { {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	octeon_sha512_update,
-	.final		=	octeon_sha384_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	octeon_sha512_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"octeon-sha384",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}