[0/3] Introduce x86 assembler accelerated implementation for SM4 algorithm

Message

tianjia.zhang June 10, 2021, 1:44 p.m. UTC

This patchset extracts the public SM4 algorithm as a separate library,
and introduces an accelerated implementation of the instruction set on
x86, and will also introduce more mode-specific accelerated
implementations later.

Tianjia Zhang (3):
  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 assembler implementation

 arch/arm64/crypto/Kconfig              |   2 +-
 arch/arm64/crypto/sm4-ce-glue.c        |  14 +-
 arch/x86/crypto/Makefile               |   3 +
 arch/x86/crypto/sm4-aesni-avx-asm_64.S | 339 +++++++++++++++++++++++++
 arch/x86/crypto/sm4_aesni_avx_glue.c   | 115 +++++++++
 crypto/Kconfig                         |  30 +++
 crypto/sm4_generic.c                   | 164 +-----------
 include/crypto/sm4.h                   |  25 +-
 lib/crypto/Kconfig                     |   3 +
 lib/crypto/Makefile                    |   3 +
 lib/crypto/sm4.c                       | 184 ++++++++++++++
 11 files changed, 718 insertions(+), 164 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