251496dbfc
Patch adds i586/SSE2 assembler implementation of serpent cipher. Assembler functions crypt data in four block chunks. Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmarks results (serpent-sse2/serpent_generic speed ratios): Intel Atom N270: size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16 0.95x 1.12x 1.02x 1.07x 0.97x 0.98x 64 1.73x 1.82x 1.08x 1.82x 1.72x 1.73x 256 2.08x 2.00x 1.04x 2.07x 1.99x 2.01x 1024 2.28x 2.18x 1.05x 2.23x 2.17x 2.20x 8192 2.28x 2.13x 1.05x 2.23x 2.18x 2.20x Full output: http://koti.mbnet.fi/axh/kernel/crypto/atom-n270/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/atom-n270/serpent-sse2.txt Userspace test results: Encryption/decryption of sse2-i586 vs generic on Intel Atom N270: encrypt: 2.35x decrypt: 2.54x Encryption/decryption of sse2-i586 vs generic on AMD Phenom II: encrypt: 1.82x decrypt: 2.51x Encryption/decryption of sse2-i586 vs generic on Intel Xeon E7330: encrypt: 2.99x decrypt: 3.48x Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
64 lines
1.5 KiB
C
64 lines
1.5 KiB
C
#ifndef ASM_X86_SERPENT_H
|
|
#define ASM_X86_SERPENT_H
|
|
|
|
#include <linux/crypto.h>
|
|
#include <crypto/serpent.h>
|
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
#define SERPENT_PARALLEL_BLOCKS 4
|
|
|
|
asmlinkage void __serpent_enc_blk_4way(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src, bool xor);
|
|
asmlinkage void serpent_dec_blk_4way(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src);
|
|
|
|
static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
__serpent_enc_blk_4way(ctx, dst, src, false);
|
|
}
|
|
|
|
static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
__serpent_enc_blk_4way(ctx, dst, src, true);
|
|
}
|
|
|
|
static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
serpent_dec_blk_4way(ctx, dst, src);
|
|
}
|
|
|
|
#else
|
|
|
|
#define SERPENT_PARALLEL_BLOCKS 8
|
|
|
|
asmlinkage void __serpent_enc_blk_8way(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src, bool xor);
|
|
asmlinkage void serpent_dec_blk_8way(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src);
|
|
|
|
static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
__serpent_enc_blk_8way(ctx, dst, src, false);
|
|
}
|
|
|
|
static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
__serpent_enc_blk_8way(ctx, dst, src, true);
|
|
}
|
|
|
|
static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
|
|
const u8 *src)
|
|
{
|
|
serpent_dec_blk_8way(ctx, dst, src);
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif
|