crypto: arm/sha512 - accelerated SHA-512 using ARM generic ASM and NEON

This replaces the SHA-512 NEON module with the faster and more
versatile implementation from the OpenSSL project. It consists
of both a NEON and a generic ASM version of the core SHA-512
transform, where the NEON version reverts to the ASM version
when invoked in non-process context.

This patch is based on the OpenSSL upstream version b1a5d1c65208
of sha512-armv4.pl, which can be found here:

  https://git.openssl.org/gitweb/?p=openssl.git;h=b1a5d1c65208

Performance relative to the generic implementation (measured
using tcrypt.ko mode=306 sec=1 running on a Cortex-A57 under
KVM):

  input size	block size	asm	neon	old neon

  16		16		1.39	2.54	2.21
  64		16		1.32	2.33	2.09
  64		64		1.38	2.53	2.19
  256		16		1.31	2.28	2.06
  256		64		1.38	2.54	2.25
  256		256		1.40	2.77	2.39
  1024		16		1.29	2.22	2.01
  1024		256		1.40	2.82	2.45
  1024		1024		1.41	2.93	2.53
  2048		16		1.33	2.21	2.00
  2048		256		1.40	2.84	2.46
  2048		1024		1.41	2.96	2.55
  2048		2048		1.41	2.98	2.56
  4096		16		1.34	2.20	1.99
  4096		256		1.40	2.84	2.46
  4096		1024		1.41	2.97	2.56
  4096		4096		1.41	3.01	2.58
  8192		16		1.34	2.19	1.99
  8192		256		1.40	2.85	2.47
  8192		1024		1.41	2.98	2.56
  8192		4096		1.41	2.71	2.59
  8192		8192		1.51	3.51	2.69

Acked-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 98 insertions, 0 deletions

diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
new file mode 100644
index 000000000000..32693684a3ab
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,98 @@
+/*
+ * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_ALIAS_CRYPTO("sha384-neon");
+MODULE_ALIAS_CRYPTO("sha512-neon");
+
+asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src,
+					     int blocks);
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	if (!may_use_simd() ||
+	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+		return sha512_arm_update(desc, data, len);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	if (!may_use_simd())
+		return sha512_arm_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	if (len)
+		sha512_base_do_update(desc, data, len,
+			(sha512_block_fn *)sha512_block_data_order_neon);
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };