mirror of
https://github.com/torvalds/linux.git
synced 2024-12-10 13:12:04 +00:00
937c30d7f5
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 7c926402a7)
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 <jussi.kivilinna@mbnet.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
42 lines
1.7 KiB
Makefile
42 lines
1.7 KiB
Makefile
#
|
|
# Arch-specific CryptoAPI modules.
|
|
#
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
|
|
obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-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_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
|
|
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
|
|
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
|
|
|
|
aes-i586-y := aes-i586-asm_32.o aes_glue.o
|
|
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
|
|
salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
|
|
|
|
aes-x86_64-y := aes-x86_64-asm_64.o aes_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
|
|
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
|
|
|
|
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
|
|
|
|
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
|
|
|
|
# enable AVX support only when $(AS) can actually assemble the instructions
|
|
ifeq ($(call as-instr,vpxor %xmm0$(comma)%xmm1$(comma)%xmm2,yes,no),yes)
|
|
AFLAGS_sha1_ssse3_asm.o += -DSHA1_ENABLE_AVX_SUPPORT
|
|
CFLAGS_sha1_ssse3_glue.o += -DSHA1_ENABLE_AVX_SUPPORT
|
|
endif
|
|
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
|