mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-29 05:55:02 +08:00
a7ee22ee14
This patch adds AES-NI/AVX/x86_64 assembler implementation of SM4 block cipher. Through two affine transforms, we can use the AES S-Box to simulate the SM4 S-Box to achieve the effect of instruction acceleration. The main algorithm implementation comes from SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at: https://github.com/mjosaarinen/sm4ni This optimization supports the four modes of SM4, ECB, CBC, CFB, and CTR. Since CBC and CFB do not support multiple block parallel encryption, the optimization effect is not obvious. Benchmark on Intel Xeon Cascadelake, the data comes from the 218 mode and 518 mode of tcrypt. The abscissas are blocks of different lengths. The data is tabulated and the unit is Mb/s: sm4-generic | 16 64 128 256 1024 1420 4096 ECB enc | 40.99 46.50 48.05 48.41 49.20 49.25 49.28 ECB dec | 41.07 46.99 48.15 48.67 49.20 49.25 49.29 CBC enc | 37.71 45.28 46.77 47.60 48.32 48.37 48.40 CBC dec | 36.48 44.82 46.43 47.45 48.23 48.30 48.36 CFB enc | 37.94 44.84 46.12 46.94 47.57 47.46 47.68 CFB dec | 37.50 42.84 43.74 44.37 44.85 44.80 44.96 CTR enc | 39.20 45.63 46.75 47.49 48.09 47.85 48.08 CTR dec | 39.64 45.70 46.72 47.47 47.98 47.88 48.06 sm4-aesni-avx ECB enc | 33.75 134.47 221.64 243.43 264.05 251.58 258.13 ECB dec | 34.02 134.92 223.11 245.14 264.12 251.04 258.33 CBC enc | 38.85 46.18 47.67 48.34 49.00 48.96 49.14 CBC dec | 33.54 131.29 223.88 245.27 265.50 252.41 263.78 CFB enc | 38.70 46.10 47.58 48.29 49.01 48.94 49.19 CFB dec | 32.79 128.40 223.23 244.87 265.77 253.31 262.79 CTR enc | 32.58 122.23 220.29 241.16 259.57 248.32 256.69 CTR dec | 32.81 122.47 218.99 241.54 258.42 248.58 256.61 Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
98 lines
4.3 KiB
Makefile
98 lines
4.3 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# x86 crypto algorithms
|
|
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
|
|
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
|
|
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
|
|
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
|
|
twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
|
|
serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
|
|
serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
|
|
serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
|
|
serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
|
|
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
|
|
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o
|
|
camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o camellia_aesni_avx_glue.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
|
|
camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
|
|
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
|
|
cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
|
|
cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
|
|
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
|
|
chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o
|
|
chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
|
|
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
|
|
aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
|
|
sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
|
|
sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
|
|
sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
|
|
sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
|
|
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o
|
|
blake2s-x86_64-y := blake2s-core.o blake2s-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
|
|
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
|
|
crc32c-intel-y := crc32c-intel_glue.o
|
|
crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
|
|
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
|
|
crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
|
|
poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
|
|
targets += poly1305-x86_64-cryptogams.S
|
|
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
|
|
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
|
|
nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64) += sm4-aesni-avx-x86_64.o
|
|
sm4-aesni-avx-x86_64-y := sm4-aesni-avx-asm_64.o sm4_aesni_avx_glue.o
|
|
|
|
quiet_cmd_perlasm = PERLASM $@
|
|
cmd_perlasm = $(PERL) $< > $@
|
|
$(obj)/%.S: $(src)/%.pl FORCE
|
|
$(call if_changed,perlasm)
|