crypto: sha - SHA1 transform x86_64 AVX2

This git patch adds x86_64 AVX2 optimization of SHA1
transform to crypto support. The patch has been tested with 3.14.0-rc1
kernel.

On a Haswell desktop, with turbo disabled and all cpus running
at maximum frequency, tcrypt shows AVX2 performance improvement
from 3% for 256 bytes update to 16% for 1024 bytes update over
AVX implementation.

This patch adds sha1_avx2_transform(), the glue, build and
configuration changes needed for AVX2 optimization of
SHA1 transform to crypto support.

sha1-ssse3 is one module which adds the necessary optimization
support (SSSE3/AVX/AVX2) for the low-level SHA1 transform function.
With better optimization support, transform function is overridden
as the case may be. In the case of AVX2, due to performance reasons
across datablock sizes, the AVX or AVX2 transform function is used
at run-time as it suits best. The Makefile change therefore appends
the necessary objects to the linkage. Due to this, the patch merely
appends AVX2 transform to the existing build mix and Kconfig support
and leaves the configuration build support as is.
Signed-off-by: Chandramouli Narayanan <mouli@linux.intel.com>
Reviewed-by: Marek Vasut <marex@denx.de>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/Makefile

@@ -79,6 +79,9 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+ifeq ($(avx2_supported),yes)
+sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+endif
 crc32c-intel-y := crc32c-intel_glue.o
 crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
 crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o

arch/x86/crypto/sha1_ssse3_glue.c

@@ -10,6 +10,7 @@
  * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  * Copyright (c) Mathias Krause <minipli@googlemail.com>
+ * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -39,6 +40,12 @@ asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
 asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
 				   unsigned int rounds);
 #endif
+#ifdef CONFIG_AS_AVX2
+#define SHA1_AVX2_BLOCK_OPTSIZE	4	/* optimal 4*64 bytes of SHA1 blocks */
+
+asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
+				unsigned int rounds);
+#endif
 
 static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int);
 
@@ -165,6 +172,18 @@ static int sha1_ssse3_import(struct shash_desc *desc, const void *in)
 	return 0;
 }
 
+#ifdef CONFIG_AS_AVX2
+static void sha1_apply_transform_avx2(u32 *digest, const char *data,
+				unsigned int rounds)
+{
+	/* Select the optimal transform based on data block size */
+	if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE)
+		sha1_transform_avx2(digest, data, rounds);
+	else
+		sha1_transform_avx(digest, data, rounds);
+}
+#endif
+
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_ssse3_init,
@@ -189,7 +208,11 @@ static bool __init avx_usable(void)
 {
 	u64 xcr0;
 
+#if defined(CONFIG_AS_AVX2)
+	if (!cpu_has_avx || !cpu_has_avx2 || !cpu_has_osxsave)
+#else
 	if (!cpu_has_avx || !cpu_has_osxsave)
+#endif
 		return false;
 
 	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
@@ -205,23 +228,35 @@ static bool __init avx_usable(void)
 
 static int __init sha1_ssse3_mod_init(void)
 {
+	char *algo_name;
 	/* test for SSSE3 first */
-	if (cpu_has_ssse3)
+	if (cpu_has_ssse3) {
 		sha1_transform_asm = sha1_transform_ssse3;
+		algo_name = "SSSE3";
+	}
 
 #ifdef CONFIG_AS_AVX
 	/* allow AVX to override SSSE3, it's a little faster */
-	if (avx_usable())
-		sha1_transform_asm = sha1_transform_avx;
+	if (avx_usable()) {
+		if (cpu_has_avx) {
+			sha1_transform_asm = sha1_transform_avx;
+			algo_name = "AVX";
+		}
+#ifdef CONFIG_AS_AVX2
+		if (cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI2)) {
+			/* allow AVX2 to override AVX, it's a little faster */
+			sha1_transform_asm = sha1_apply_transform_avx2;
+			algo_name = "AVX2";
+		}
+#endif
+	}
 #endif
 
 	if (sha1_transform_asm) {
-		pr_info("Using %s optimized SHA-1 implementation\n",
-		        sha1_transform_asm == sha1_transform_ssse3 ? "SSSE3"
-		                                                   : "AVX");
+		pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
 		return crypto_register_shash(&alg);
 	}
-	pr_info("Neither AVX nor SSSE3 is available/usable.\n");
+	pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");
 
 	return -ENODEV;
 }

crypto/Kconfig

@@ -491,14 +491,14 @@ config CRYPTO_SHA1
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
 
 config CRYPTO_SHA1_SSSE3
-	tristate "SHA1 digest algorithm (SSSE3/AVX)"
+	tristate "SHA1 digest algorithm (SSSE3/AVX/AVX2)"
 	depends on X86 && 64BIT
 	select CRYPTO_SHA1
 	select CRYPTO_HASH
 	help
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
 	  using Supplemental SSE3 (SSSE3) instructions or Advanced Vector
-	  Extensions (AVX), when available.
+	  Extensions (AVX/AVX2), when available.
 
 config CRYPTO_SHA256_SSSE3
 	tristate "SHA256 digest algorithm (SSSE3/AVX/AVX2)"