crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher

Patch adds AVX2/x86-64 implementation of Twofish cipher, requiring 16 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. Implementation also uses 256-bit wide YMM registers,
which should give additional speed up compared to the AVX implementation.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Jussi Kivilinna
2013-04-13 13:46:50 +03:00
committed by Herbert Xu
parent 6048801070
commit cf1521a1a5
8 changed files with 1432 additions and 2 deletions

View File

@@ -28,6 +28,20 @@ asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src);
/* 8-way parallel cipher functions */
asmlinkage void twofish_ecb_enc_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src);
asmlinkage void twofish_ecb_dec_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src);
asmlinkage void twofish_cbc_dec_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src);
asmlinkage void twofish_ctr_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src, le128 *iv);
asmlinkage void twofish_xts_enc_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src, le128 *iv);
asmlinkage void twofish_xts_dec_8way(struct twofish_ctx *ctx, u8 *dst,
const u8 *src, le128 *iv);
/* helpers from twofish_x86_64-3way module */
extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src);
extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
@@ -43,4 +57,8 @@ extern void lrw_twofish_exit_tfm(struct crypto_tfm *tfm);
extern int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
unsigned int keylen);
/* helpers from twofish-avx module */
extern void twofish_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
extern void twofish_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
#endif /* ASM_X86_TWOFISH_H */