crypto: serpent - add AVX2/x86_64 assembler implementation of serpent…

… cipher

Patch adds AVX2/x86-64 implementation of Serpent cipher, requiring 16 parallel
blocks for input (256 bytes). Implementation is based on the AVX implementation
and extends to use the 256-bit wide YMM registers. Since serpent does not use
table look-ups, this implementation should be close to two times faster than
the AVX implementation.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/Makefile

@@ -43,6 +43,7 @@ endif
 # These modules require assembler to support AVX2.
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_BLOWFISH_AVX2_X86_64) += blowfish-avx2.o
+	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
 	obj-$(CONFIG_CRYPTO_TWOFISH_AVX2_X86_64) += twofish-avx2.o
 endif
 
@@ -72,6 +73,7 @@ endif
 
 ifeq ($(avx2_supported),yes)
 	blowfish-avx2-y := blowfish-avx2-asm_64.o blowfish_avx2_glue.o
+	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 	twofish-avx2-y := twofish-avx2-asm_64.o twofish_avx2_glue.o
 endif