Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 3.15:
   - Added 3DES driver for OMAP4/AM43xx
   - Added AVX2 acceleration for SHA
   - Added hash-only AEAD algorithms in caam
   - Removed tegra driver as it is not functioning and the hardware is
     too slow
   - Allow blkcipher walks over AEAD (needed for ARM)
   - Fixed unprotected FPU/SSE access in ghash-clmulni-intel
   - Fixed highmem crash in omap-sham
   - Add (zero entropy) randomness when initialising hardware RNGs
   - Fixed unaligned ahash comletion functions
   - Added soft module depedency for crc32c for initrds that use crc32c"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (60 commits)
  crypto: ghash-clmulni-intel - use C implementation for setkey()
  crypto: x86/sha1 - reduce size of the AVX2 asm implementation
  crypto: x86/sha1 - fix stack alignment of AVX2 variant
  crypto: x86/sha1 - re-enable the AVX variant
  crypto: sha - SHA1 transform x86_64 AVX2
  crypto: crypto_wq - Fix late crypto work queue initialization
  crypto: caam - add missing key_dma unmap
  crypto: caam - add support for aead null encryption
  crypto: testmgr - add aead null encryption test vectors
  crypto: export NULL algorithms defines
  crypto: caam - remove error propagation handling
  crypto: hash - Simplify the ahash_finup implementation
  crypto: hash - Pull out the functions to save/restore request
  crypto: hash - Fix the pointer voodoo in unaligned ahash
  crypto: caam - Fix first parameter to caam_init_rng
  crypto: omap-sham - Map SG pages if they are HIGHMEM before accessing
  crypto: caam - Dynamic memory allocation for caam_rng_ctx object
  crypto: allow blkcipher walks over AEAD data
  crypto: remove direct blkcipher_walk dependency on transform
  hwrng: add randomness to system from rng sources
  ...

1 files changed, 47 insertions, 6 deletions

diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 4a11a9d72451..74d16ef707c7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/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,
@@ -201,27 +220,49 @@ static bool __init avx_usable(void)
 
 	return true;
 }
+
+#ifdef CONFIG_AS_AVX2
+static bool __init avx2_usable(void)
+{
+	if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) &&
+	    boot_cpu_has(X86_FEATURE_BMI2))
+		return true;
+
+	return false;
+}
+#endif
 #endif
 
 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())
+	if (avx_usable()) {
 		sha1_transform_asm = sha1_transform_avx;
+		algo_name = "AVX";
+#ifdef CONFIG_AS_AVX2
+		/* allow AVX2 to override AVX, it's a little faster */
+		if (avx2_usable()) {
+			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;
 }