9c1b30d5c1
[ Upstream commit a41b2129461f6c88e087ca9a6e2fde34cb6deb48 ]
This patch adds the NEON acceleration implementation of the SM3 hash
algorithm. The main algorithm is based on SM3 NEON accelerated work of
the libgcrypt project.
Benchmark on T-Head Yitian-710 2.75 GHz, the data comes from the 326 mode
of tcrypt, and compares the performance data of sm3-generic and sm3-ce.
The abscissas are blocks of different lengths. The data is tabulated and
the unit is Mb/s:
update-size | 16 64 256 1024 2048 4096 8192
---------------+--------------------------------------------------------
sm3-generic | 185.24 221.28 301.26 307.43 300.83 308.82 308.91
sm3-neon | 171.81 220.20 322.94 339.28 334.09 343.61 343.87
sm3-ce | 227.48 333.48 502.62 527.87 520.45 534.91 535.40
Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Stable-dep-of: be8f6b649607 ("crypto: arm64/sm3 - fix possible crash with CFI enabled")
Signed-off-by: Sasha Levin <sashal@kernel.org>
93 lines
2.8 KiB
Makefile
93 lines
2.8 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0-only
|
|
#
|
|
# linux/arch/arm64/crypto/Makefile
|
|
#
|
|
# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
|
|
#
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
|
|
sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
|
|
sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA512_ARM64_CE) += sha512-ce.o
|
|
sha512-ce-y := sha512-ce-glue.o sha512-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA3_ARM64) += sha3-ce.o
|
|
sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM3_NEON) += sm3-neon.o
|
|
sm3-neon-y := sm3-neon-glue.o sm3-neon-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o
|
|
sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce-cipher.o
|
|
sm4-ce-cipher-y := sm4-ce-cipher-glue.o sm4-ce-cipher-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_ARM64_CE_BLK) += sm4-ce.o
|
|
sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_ARM64_NEON_BLK) += sm4-neon.o
|
|
sm4-neon-y := sm4-neon-glue.o sm4-neon-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
|
|
ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_POLYVAL_ARM64_CE) += polyval-ce.o
|
|
polyval-ce-y := polyval-ce-glue.o polyval-ce-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o
|
|
crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
|
|
aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
|
|
aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
|
|
aes-ce-blk-y := aes-glue-ce.o aes-ce.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
|
|
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
|
|
sha256-arm64-y := sha256-glue.o sha256-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o
|
|
sha512-arm64-y := sha512-glue.o sha512-core.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
|
|
chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
|
|
poly1305-neon-y := poly1305-core.o poly1305-glue.o
|
|
AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64
|
|
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
|
|
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
|
|
aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o
|
|
aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
|
|
|
|
CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS
|
|
|
|
$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
|
|
$(call if_changed_rule,cc_o_c)
|
|
|
|
quiet_cmd_perlasm = PERLASM $@
|
|
cmd_perlasm = $(PERL) $(<) void $(@)
|
|
|
|
$(obj)/%-core.S: $(src)/%-armv8.pl
|
|
$(call cmd,perlasm)
|
|
|
|
$(obj)/sha256-core.S: $(src)/sha512-armv8.pl
|
|
$(call cmd,perlasm)
|
|
|
|
clean-files += poly1305-core.S sha256-core.S sha512-core.S
|