From 937c30d7f560210b0163035edd42b2aef78fed9e Mon Sep 17 00:00:00 2001 From: Jussi Kivilinna Date: Wed, 9 Nov 2011 16:26:25 +0200 Subject: crypto: serpent - add 8-way parallel x86_64/SSE2 assembler implementation Patch adds x86_64/SSE2 assembler implementation of serpent cipher. Assembler functions crypt data in eigth block chunks (two 4 block chunk SSE2 operations in parallel to improve performance on out-of-order CPUs). Glue code is based on one from AES-NI implementation, so requests from irq context are redirected to cryptd. v2: - add missing include of linux/module.h (appearently crypto.h used to include module.h, which changed for 3.2 by commit 7c926402a7e8c9b279968fd94efec8700ba3859e) Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmarks results (serpent-sse2/serpent_generic speed ratios): AMD Phenom II 1055T (fam:16, model:10): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 1.03x 1.01x 1.03x 1.05x 1.00x 0.99x 64B 1.00x 1.01x 1.02x 1.04x 1.02x 1.01x 256B 2.34x 2.41x 0.99x 2.43x 2.39x 2.40x 1024B 2.51x 2.57x 1.00x 2.59x 2.56x 2.56x 8192B 2.50x 2.54x 1.00x 2.55x 2.57x 2.57x Intel Celeron T1600 (fam:6, model:15, step:13): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 0.97x 0.97x 1.01x 1.01x 1.01x 1.02x 64B 1.00x 1.00x 1.00x 1.02x 1.01x 1.01x 256B 3.41x 3.35x 1.00x 3.39x 3.42x 3.44x 1024B 3.75x 3.72x 0.99x 3.74x 3.75x 3.75x 8192B 3.70x 3.68x 0.99x 3.68x 3.69x 3.69x Full output: http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-sse2.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-sse2.txt Signed-off-by: Jussi Kivilinna Signed-off-by: Herbert Xu --- arch/x86/include/asm/serpent.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 arch/x86/include/asm/serpent.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/serpent.h new file mode 100644 index 0000000..b7fd3b5 --- /dev/null +++ b/arch/x86/include/asm/serpent.h @@ -0,0 +1,32 @@ +#ifndef ASM_X86_SERPENT_H +#define ASM_X86_SERPENT_H + +#include +#include + +#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 -- cgit v1.1 From 251496dbfc1be38bc43b49651f3d33c02faccc47 Mon Sep 17 00:00:00 2001 From: Jussi Kivilinna Date: Wed, 9 Nov 2011 16:26:31 +0200 Subject: 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 Signed-off-by: Herbert Xu --- arch/x86/include/asm/serpent.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/serpent.h index b7fd3b5..d3ef63f 100644 --- a/arch/x86/include/asm/serpent.h +++ b/arch/x86/include/asm/serpent.h @@ -4,6 +4,35 @@ #include #include +#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 -- cgit v1.1