linux_dsm_epyc7002/arch/arm64/crypto/aes-cipher-core.S
Ard Biesheuvel c458c4ada0 crypto: arm64/aes - performance tweak
Shuffle some instructions around in the __hround macro to shave off
0.1 cycles per byte on Cortex-A57.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-02-03 18:16:20 +08:00

111 lines
2.5 KiB
ArmAsm

/*
* Scalar AES core transform
*
* Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
.text
rk .req x0
out .req x1
in .req x2
rounds .req x3
tt .req x4
lt .req x2
.macro __pair, enc, reg0, reg1, in0, in1e, in1d, shift
ubfx \reg0, \in0, #\shift, #8
.if \enc
ubfx \reg1, \in1e, #\shift, #8
.else
ubfx \reg1, \in1d, #\shift, #8
.endif
ldr \reg0, [tt, \reg0, uxtw #2]
ldr \reg1, [tt, \reg1, uxtw #2]
.endm
.macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
ldp \out0, \out1, [rk], #8
__pair \enc, w13, w14, \in0, \in1, \in3, 0
__pair \enc, w15, w16, \in1, \in2, \in0, 8
__pair \enc, w17, w18, \in2, \in3, \in1, 16
__pair \enc, \t0, \t1, \in3, \in0, \in2, 24
eor \out0, \out0, w13
eor \out1, \out1, w14
eor \out0, \out0, w15, ror #24
eor \out1, \out1, w16, ror #24
eor \out0, \out0, w17, ror #16
eor \out1, \out1, w18, ror #16
eor \out0, \out0, \t0, ror #8
eor \out1, \out1, \t1, ror #8
.endm
.macro fround, out0, out1, out2, out3, in0, in1, in2, in3
__hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
__hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
.endm
.macro iround, out0, out1, out2, out3, in0, in1, in2, in3
__hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
__hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
.endm
.macro do_crypt, round, ttab, ltab
ldp w5, w6, [in]
ldp w7, w8, [in, #8]
ldp w9, w10, [rk], #16
ldp w11, w12, [rk, #-8]
CPU_BE( rev w5, w5 )
CPU_BE( rev w6, w6 )
CPU_BE( rev w7, w7 )
CPU_BE( rev w8, w8 )
eor w5, w5, w9
eor w6, w6, w10
eor w7, w7, w11
eor w8, w8, w12
adr_l tt, \ttab
adr_l lt, \ltab
tbnz rounds, #1, 1f
0: \round w9, w10, w11, w12, w5, w6, w7, w8
\round w5, w6, w7, w8, w9, w10, w11, w12
1: subs rounds, rounds, #4
\round w9, w10, w11, w12, w5, w6, w7, w8
csel tt, tt, lt, hi
\round w5, w6, w7, w8, w9, w10, w11, w12
b.hi 0b
CPU_BE( rev w5, w5 )
CPU_BE( rev w6, w6 )
CPU_BE( rev w7, w7 )
CPU_BE( rev w8, w8 )
stp w5, w6, [out]
stp w7, w8, [out, #8]
ret
.endm
.align 5
ENTRY(__aes_arm64_encrypt)
do_crypt fround, crypto_ft_tab, crypto_fl_tab
ENDPROC(__aes_arm64_encrypt)
.align 5
ENTRY(__aes_arm64_decrypt)
do_crypt iround, crypto_it_tab, crypto_il_tab
ENDPROC(__aes_arm64_decrypt)