diff options
| author | Jussi Kivilinna <jussi.kivilinna@mbnet.fi> | 2011-11-09 15:26:31 +0100 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2011-11-21 09:13:23 +0100 |
| commit | 251496dbfc1be38bc43b49651f3d33c02faccc47 (patch) | |
| tree | e17a6704b90b94d0da126eba603fe20cb7ca822c /arch/x86/include/asm | |
| parent | crypto: serpent - add 8-way parallel x86_64/SSE2 assembler implementation (diff) | |
| download | linux-251496dbfc1be38bc43b49651f3d33c02faccc47.tar.xz linux-251496dbfc1be38bc43b49651f3d33c02faccc47.zip | |
crypto: serpent - add 4-way parallel i586/SSE2 assembler implementation
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>
Diffstat (limited to 'arch/x86/include/asm')
| -rw-r--r-- | arch/x86/include/asm/serpent.h | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/serpent.h index b7fd3b595b27..d3ef63fe0c81 100644 --- a/arch/x86/include/asm/serpent.h +++ b/arch/x86/include/asm/serpent.h @@ -4,6 +4,35 @@ #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, @@ -30,3 +59,5 @@ static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst, } #endif + +#endif |