Commit 56d76c96 authored by Jussi Kivilinna's avatar Jussi Kivilinna Committed by Herbert Xu
Browse files

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: default avatarJussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent cf1521a1

arch/x86/crypto/Makefile

+2 −0
Original line number Diff line number Diff line
@@ -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

arch/x86/crypto/serpent-avx2-asm_64.S

0 → 100644
+800 −0

File added.

Preview size limit exceeded, changes collapsed.

arch/x86/crypto/serpent_avx2_glue.c

0 → 100644
+562 −0

File added.

Preview size limit exceeded, changes collapsed.

arch/x86/crypto/serpent_avx_glue.c

+42 −20

File changed.

Preview size limit exceeded, changes collapsed.

arch/x86/include/asm/crypto/serpent-avx.h

+24 −0
Original line number Diff line number Diff line
@@ -6,6 +6,16 @@ 


#define SERPENT_PARALLEL_BLOCKS 8



struct serpent_lrw_ctx {

	struct lrw_table_ctx lrw_table;

	struct serpent_ctx serpent_ctx;

};



struct serpent_xts_ctx {

	struct serpent_ctx tweak_ctx;

	struct serpent_ctx crypt_ctx;

};



asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,

					 const u8 *src);

asmlinkage void serpent_ecb_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
@@ -21,4 +31,18 @@ asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst, 
asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,

					 const u8 *src, le128 *iv);



extern void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src,

				le128 *iv);



extern void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);

extern void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);



extern int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,

			      unsigned int keylen);



extern void lrw_serpent_exit_tfm(struct crypto_tfm *tfm);



extern int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,

			      unsigned int keylen);



#endif

CRA Git | Maintained and supported by SUSTech CRA and CCSE