crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher

Patch adds AVX2/x86-64 implementation of Blowfish cipher, requiring 32 parallel
blocks for input (256 bytes). Table look-ups are performed using vpgatherdd
instruction directly from vector registers and thus should be faster than
earlier implementations.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 0e7a237..6b9564f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -820,6 +820,24 @@
 	  See also:
 	  <http://www.schneier.com/blowfish.html>
 
+config CRYPTO_BLOWFISH_AVX2_X86_64
+	tristate "Blowfish cipher algorithm (x86_64/AVX2)"
+	depends on X86 && 64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_ABLK_HELPER_X86
+	select CRYPTO_BLOWFISH_COMMON
+	select CRYPTO_BLOWFISH_X86_64
+	help
+	  Blowfish cipher algorithm (x86_64/AVX2), by Bruce Schneier.
+
+	  This is a variable key length cipher which can use keys from 32
+	  bits to 448 bits in length.  It's fast, simple and specifically
+	  designed for use on "large microprocessors".
+
+	  See also:
+	  <http://www.schneier.com/blowfish.html>
+
 config CRYPTO_CAMELLIA
 	tristate "Camellia cipher algorithms"
 	depends on CRYPTO