https://lwn.net/Articles/863574/
Introduce x86 assembler accelerated implementation for SM4 algorithm
From: Tianjia Zhang <tianjia.zhang-AT-linux.alibaba.com>
To: Herbert Xu <herbert-AT-gondor.apana.org.au>, "David S. Miller" <davem-AT-davemloft.net>, Eric Biggers <ebiggers-AT-google.com>, Eric Biggers <ebiggers-AT-kernel.org>, Gilad Ben-Yossef <gilad-AT-benyossef.com>, Ard Biesheuvel <ardb-AT-kernel.org>, "Markku-Juhani O . Saarinen" <mjos-AT-iki.fi>, Jussi Kivilinna <jussi.kivilinna-AT-iki.fi>, Catalin Marinas <catalin.marinas-AT-arm.com>, Will Deacon <will-AT-kernel.org>, Thomas Gleixner <tglx-AT-linutronix.de>, Ingo Molnar <mingo-AT-redhat.com>, Borislav Petkov <bp-AT-alien8.de>, "H. Peter Anvin" <hpa-AT-zytor.com>, x86-AT-kernel.org, linux-crypto-AT-vger.kernel.org, linux-arm-kernel-AT-lists.infradead.org, linux-kernel-AT-vger.kernel.org, Jia Zhang <zhang.jia-AT-linux.alibaba.com>, "YiLin . Li" <YiLin.Li-AT-linux.alibaba.com>
Subject: [PATCH v3 0/4] Introduce x86 assembler accelerated implementation for SM4 algorithm
Date: Tue, 20 Jul 2021 11:46:38 +0800
Message-ID: <20210720034642.19230-1-tianjia.zhang@linux.alibaba.com>
Cc: Tianjia Zhang <tianjia.zhang-AT-linux.alibaba.com>
Archive-link: Article
This patchset extracts the public SM4 algorithm as a separate library,
At the same time, the acceleration implementation of SM4 in arm64 was
adjusted to adapt to this SM4 library. Then introduces an accelerated
implementation of the instruction set on x86_64.
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. And all selftests
have passed already.
The main algorithm implementation comes from SM4 AES-NI work by
libgcrypt and Markku-Juhani O. Saarinen at:
https://github.com/mjosaarinen/sm4ni
Benchmark on Intel Xeon Cascadelake, the data comes from the mode 218
and mode 518 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
---
v3 changes:
* Remove single block algorithm that does not greatly improve performance
* Remove accelerated for sm4 key expand, which is not performance-critical
* Fix the warning on arm64/sm4-ce
v2 changes:
* SM4 library functions use "sm4_" prefix instead of "crypto_" prefix
* sm4-aesni-avx supports accelerated implementation of four specific modes
* tcrypt benchmark supports sm4-aesni-avx
* fixes of other reviews
Tianjia Zhang (4):
crypto: sm4 - create SM4 library based on sm4 generic code
crypto: arm64/sm4-ce - Make dependent on sm4 library instead of
sm4-generic
crypto: x86/sm4 - add AES-NI/AVX/x86_64 implementation
crypto: tcrypt - add the asynchronous speed test for SM4
arch/arm64/crypto/Kconfig | 2 +-
arch/arm64/crypto/sm4-ce-glue.c | 20 +-
arch/x86/crypto/Makefile | 3 +
arch/x86/crypto/sm4-aesni-avx-asm_64.S | 589 +++++++++++++++++++++++++
arch/x86/crypto/sm4_aesni_avx_glue.c | 459 +++++++++++++++++++
crypto/Kconfig | 22 +
crypto/sm4_generic.c | 180 +-------
crypto/tcrypt.c | 26 +-
include/crypto/sm4.h | 25 +-
lib/crypto/Kconfig | 3 +
lib/crypto/Makefile | 3 +
lib/crypto/sm4.c | 176 ++++++++
12 files changed, 1330 insertions(+), 178 deletions(-)
create mode 100644 arch/x86/crypto/sm4-aesni-avx-asm_64.S
create mode 100644 arch/x86/crypto/sm4_aesni_avx_glue.c
create mode 100644 lib/crypto/sm4.c
--
2.19.1.3.ge56e4f7
Hi xiexiuqi, welcome to the openEuler Community.
I'm the Bot here serving you. You can find the instructions on how to interact with me at
https://gitee.com/openeuler/community/blob/master/en/sig-infrastructure/command.md.
If you have any questions, please contact the SIG: Kernel, and any of the maintainers: @Xie XiuQi, @YangYingliang, @成坚 (CHENG Jian).
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。
已提交补丁:
crypto: sm4 - create SM4 library based on sm4 generic code
commit id: 2b31277af577b1b2da62c3ad7d3315b422869102
crypto: arm64/sm4-ce - Make dependent on sm4 library instead of sm4-generic
commit id: c59de48e125c6d49a8abd165e388ca57bfe37b17
crypto: x86/sm4 - add AES-NI/AVX/x86_64 implementation
commit id: a7ee22ee1445c7fdb00ab80116bb9710ca86a860
crypto: tcrypt - add the asynchronous speed test for SM4
commit id: a7fc80bb22eb0f13791ee4f70484e88316cc2a24
测试环境:
CPU:AMD Ryzen 5 PRO 4650U with Radeon Graphics 2.10 GHz
核数:4核
内存:4GB
系统:openeuler21.03
内核:OLK-5.10
测试时间:2s
测试结果如下:
测试效果与源patch基本一致
登录 后才可以发表评论