Skip to contentSkip to conversation

crypto: twofish - add x86_64/avx assembler implementation

PATCH In review Johannes Goetzfried 2 participants 2 messages May 28, 2012 – Jun 12, 2012

Subsystems (3)
x86 Crypto API Arm STM32
lore
Share & tools
lore

Johannes Goetzfried

author
#0 lore raw

PATCH 1/1 crypto: twofish - add x86_64/avx assembler implementation

This patch adds a x86_64/avx assembler implementation of the Twofish block cipher. The implementation processes eight blocks in parallel (two 4 block chunk AVX operations). The table-lookups are done in general-purpose registers. For small blocksizes the 3way-parallel functions from the twofish-x86_64-3way module are called. A good performance increase is provided for blocksizes greater or equal to 128B.

Patch has been tested with tcrypt and automated filesystem tests.

Tcrypt benchmark results:

Intel Core i5-2500 CPU (fam:6, model:42, step:7)

twofish-avx-x86_64 vs. twofish-x86_64-3way
128bit key: (lrw:256bit) (xts:256bit)

size    ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec lrw-enc lrw-dec xts-enc xts-dec
16B     0.96x   0.97x   1.00x   0.95x   0.97x   0.97x   0.96x   0.95x   0.95x   0.98x
64B     0.99x   0.99x   1.00x   0.99x   0.98x   0.98x   0.99x   0.98x   0.99x   0.98x
256B    1.20x   1.21x   1.00x   1.19x   1.15x   1.14x   1.19x   1.20x   1.18x   1.19x
1024B   1.29x   1.30x   1.00x   1.28x   1.23x   1.24x   1.26x   1.28x   1.26x   1.27x
8192B   1.31x   1.32x   1.00x   1.31x   1.25x   1.25x   1.28x   1.29x   1.28x   1.30x

256bit key: (lrw:384bit) (xts:512bit)

size    ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec lrw-enc lrw-dec xts-enc xts-dec
16B     0.96x   0.96x   1.00x   0.96x   0.97x   0.98x   0.95x   0.95x   0.95x   0.96x
64B     1.00x   0.99x   1.00x   0.98x   0.98x   1.01x   0.98x   0.98x   0.98x   0.98x
256B    1.20x   1.21x   1.00x   1.21x   1.15x   1.15x   1.19x   1.20x   1.18x   1.19x
1024B   1.29x   1.30x   1.00x   1.28x   1.23x   1.23x   1.26x   1.27x   1.26x   1.27x
8192B   1.31x   1.33x   1.00x   1.31x   1.26x   1.26x   1.29x   1.29x   1.28x   1.30x

twofish-avx-x86_64 vs aes-asm (8kB block):

         128bit  256bit
ecb-enc  1.19x   1.63x
ecb-dec  1.18x   1.62x
cbc-enc  0.75x   1.03x
cbc-dec  1.23x   1.67x
ctr-enc  1.24x   1.65x
ctr-dec  1.24x   1.65x
lrw-enc  1.15x   1.53x
lrw-dec  1.14x   1.52x
xts-enc  1.16x   1.56x
xts-dec  1.16x   1.56x
Signed-off-by Johannes Goetzfried <[email protected]>
---
 arch/x86/crypto/Makefile                    |    2 +
 arch/x86/crypto/twofish-avx-x86_64-asm_64.S |  302 ++++++++
 arch/x86/crypto/twofish_avx_glue.c          | 1086 +++++++++++++++++++++++++++
 arch/x86/crypto/twofish_glue_3way.c         |    2 +
 crypto/Kconfig                              |   24 +
 crypto/tcrypt.c                             |   23 +
 crypto/testmgr.c                            |   60 ++
 7 files changed, 1499 insertions(+), 0 deletions(-)
 create mode 100644 arch/x86/crypto/twofish-avx-x86_64-asm_64.S
 create mode 100644 arch/x86/crypto/twofish_avx_glue.c
arch/x86/crypto/Makefile +2 -0
index e191ac0..b02a73e 100644
@@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
+obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o

@@ -30,6 +31,7 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
+twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
arch/x86/crypto/twofish-avx-x86_64-asm_64.S new file +302 -0

302 lines not on this page · raw message

arch/x86/crypto/twofish_avx_glue.c new file +1086 -0

1,086 lines not on this page · raw message

arch/x86/crypto/twofish_glue_3way.c +2 -0
index 922ab24..77e4e55 100644
@@ -45,8 +45,10 @@ asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
 /* 3-way parallel cipher functions */
 asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 				       const u8 *src, bool xor);
+EXPORT_SYMBOL_GPL(__twofish_enc_blk_3way);
 asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 				     const u8 *src);
+EXPORT_SYMBOL_GPL(twofish_dec_blk_3way);
 
 static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 					const u8 *src)
crypto/Kconfig +24 -0
index 8e84225..e00a4e4 100644
@@ -913,6 +913,30 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 	  See also:
 	  <http://www.schneier.com/twofish.html>
 
+config CRYPTO_TWOFISH_AVX_X86_64
+	tristate "Twofish cipher algorithm (x86_64/AVX)"
+	depends on X86 && 64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_TWOFISH_COMMON
+	select CRYPTO_TWOFISH_X86_64
+	select CRYPTO_TWOFISH_X86_64_3WAY
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Twofish cipher algorithm (x86_64/AVX).
+
+	  Twofish was submitted as an AES (Advanced Encryption Standard)
+	  candidate cipher by researchers at CounterPane Systems.  It is a
+	  16 round block cipher supporting key sizes of 128, 192, and 256
+	  bits.
+
+	  This module provides the Twofish cipher algorithm that processes
+	  eight blocks parallel using the AVX Instruction Set.
+
+	  See also:
+	  <http://www.schneier.com/twofish.html>
+
 comment "Compression"
 
 config CRYPTO_DEFLATE
crypto/tcrypt.c +23 -0
index 8f147bf..69b6fb1 100644
@@ -1563,6 +1563,29 @@ static int do_test(int m)
 				   speed_template_32_64);
 		break;
 
+	case 504:
+		test_acipher_speed("ecb(twofish)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("ecb(twofish)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cbc(twofish)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cbc(twofish)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("ctr(twofish)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("ctr(twofish)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("lrw(twofish)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_40_48);
+		test_acipher_speed("lrw(twofish)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_40_48);
+		test_acipher_speed("xts(twofish)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_48_64);
+		test_acipher_speed("xts(twofish)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_48_64);
+		break;
+
 	case 1000:
 		test_available();
 		break;
crypto/testmgr.c +60 -0

84 lines not on this page · raw message

Signature · 1 line
1.7.2.5
#1 lore raw
Quoted 8 lines · Johannes Goetzfried

This patch adds a x86_64/avx assembler implementation of the Twofish block cipher. The implementation processes eight blocks in parallel (two 4 block chunk AVX operations). The table-lookups are done in general-purpose registers. For small blocksizes the 3way-parallel functions from the twofish-x86_64-3way module are called. A good performance increase is provided for blocksizes greater or equal to 128B.

Patch has been tested with tcrypt and automated filesystem tests.

All applied. Thanks!

Signature · 3 lines
Email: Herbert Xu <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt