crypto: arm/sha1-ce - move SHA-1 ARMv8 implementation to base layer

This removes all the boilerplate from the existing implementation,
and replaces it with calls into the base layer.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/Kconfig

@@ -31,7 +31,6 @@ config CRYPTO_SHA1_ARM_CE
 	tristate "SHA1 digest algorithm (ARM v8 Crypto Extensions)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SHA1_ARM
-	select CRYPTO_SHA1
 	select CRYPTO_HASH
 	help
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented

arch/arm/crypto/sha1-ce-core.S

@@ -61,8 +61,8 @@
 	.word		0xca62c1d6, 0xca62c1d6, 0xca62c1d6, 0xca62c1d6
 
 	/*
-	 * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
-	 *			  u8 *head);
+	 * void sha1_ce_transform(struct sha1_state *sst, u8 const *src,
+	 *			  int blocks);
 	 */
 ENTRY(sha1_ce_transform)
 	/* load round constants */
@@ -71,23 +71,14 @@ ENTRY(sha1_ce_transform)
 	vld1.32		{k2-k3}, [ip, :128]
 
 	/* load state */
-	vld1.32		{dga}, [r2]
-	vldr		dgbs, [r2, #16]
-
-	/* load partial input (if supplied) */
-	teq		r3, #0
-	beq		0f
-	vld1.32		{q8-q9}, [r3]!
-	vld1.32		{q10-q11}, [r3]
-	teq		r0, #0
-	b		1f
+	vld1.32		{dga}, [r0]
+	vldr		dgbs, [r0, #16]
 
 	/* load input */
 0:	vld1.32		{q8-q9}, [r1]!
 	vld1.32		{q10-q11}, [r1]!
-	subs		r0, r0, #1
+	subs		r2, r2, #1
 
-1:
 #ifndef CONFIG_CPU_BIG_ENDIAN
 	vrev32.8	q8, q8
 	vrev32.8	q9, q9
@@ -128,7 +119,7 @@ ENTRY(sha1_ce_transform)
 	bne		0b
 
 	/* store new state */
-	vst1.32		{dga}, [r2]
-	vstr		dgbs, [r2, #16]
+	vst1.32		{dga}, [r0]
+	vstr		dgbs, [r0, #16]
 	bx		lr
 ENDPROC(sha1_ce_transform)

arch/arm/crypto/sha1-ce-glue.c

@@ -10,121 +10,66 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
+#include <crypto/sha1_base.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
 #include <asm/hwcap.h>
 #include <asm/neon.h>
 #include <asm/simd.h>
-#include <asm/unaligned.h>
 
 #include "sha1.h"
 
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
 
-asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state, 
-				  u8 *head);
+asmlinkage void sha1_ce_transform(struct sha1_state *sst, u8 const *src,
+				  int blocks);
 
-static int sha1_init(struct shash_desc *desc)
+static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
+			  unsigned int len)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	*sctx = (struct sha1_state){
-		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
-	};
-	return 0;
-}
-
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-		       unsigned int len)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial;
-
-	if (!may_use_simd())
+	if (!may_use_simd() ||
+	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return sha1_update_arm(desc, data, len);
 
-	partial = sctx->count % SHA1_BLOCK_SIZE;
-	sctx->count += len;
-
-	if ((partial + len) >= SHA1_BLOCK_SIZE) {
-		int blocks;
+	kernel_neon_begin();
+	sha1_base_do_update(desc, data, len, sha1_ce_transform);
+	kernel_neon_end();
 
-		if (partial) {
-			int p = SHA1_BLOCK_SIZE - partial;
-
-			memcpy(sctx->buffer + partial, data, p);
-			data += p;
-			len -= p;
-		}
-
-		blocks = len / SHA1_BLOCK_SIZE;
-		len %= SHA1_BLOCK_SIZE;
-
-		kernel_neon_begin();
-		sha1_ce_transform(blocks, data, sctx->state,
-				  partial ? sctx->buffer : NULL);
-		kernel_neon_end();
-
-		data += blocks * SHA1_BLOCK_SIZE;
-		partial = 0;
-	}
-	if (len)
-		memcpy(sctx->buffer + partial, data, len);
 	return 0;
 }
 
-static int sha1_final(struct shash_desc *desc, u8 *out)
+static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
+			 unsigned int len, u8 *out)
 {
-	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
-
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	__be64 bits = cpu_to_be64(sctx->count << 3);
-	__be32 *dst = (__be32 *)out;
-	int i;
-
-	u32 padlen = SHA1_BLOCK_SIZE
-		     - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
-
-	sha1_update(desc, padding, padlen);
-	sha1_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
-		put_unaligned_be32(sctx->state[i], dst++);
-
-	*sctx = (struct sha1_state){};
-	return 0;
-}
+	if (!may_use_simd())
+		return sha1_finup_arm(desc, data, len, out);
 
-static int sha1_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	struct sha1_state *dst = out;
+	kernel_neon_begin();
+	if (len)
+		sha1_base_do_update(desc, data, len, sha1_ce_transform);
+	sha1_base_do_finalize(desc, sha1_ce_transform);
+	kernel_neon_end();
 
-	*dst = *sctx;
-	return 0;
+	return sha1_base_finish(desc, out);
 }
 
-static int sha1_import(struct shash_desc *desc, const void *in)
+static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	struct sha1_state const *src = in;
-
-	*sctx = *src;
-	return 0;
+	return sha1_ce_finup(desc, NULL, 0, out);
 }
 
 static struct shash_alg alg = {
-	.init			= sha1_init,
-	.update			= sha1_update,
-	.final			= sha1_final,
-	.export			= sha1_export,
-	.import			= sha1_import,
+	.init			= sha1_base_init,
+	.update			= sha1_ce_update,
+	.final			= sha1_ce_final,
+	.finup			= sha1_ce_finup,
 	.descsize		= sizeof(struct sha1_state),
 	.digestsize		= SHA1_DIGEST_SIZE,
-	.statesize		= sizeof(struct sha1_state),
 	.base			= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-ce",