133 lines
3.3 KiB
ArmAsm
133 lines
3.3 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Scalar AES core transform
|
|
*
|
|
* Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/cache.h>
|
|
|
|
.text
|
|
|
|
rk .req x0
|
|
out .req x1
|
|
in .req x2
|
|
rounds .req x3
|
|
tt .req x2
|
|
|
|
.macro __pair1, sz, op, reg0, reg1, in0, in1e, in1d, shift
|
|
.ifc \op\shift, b0
|
|
ubfiz \reg0, \in0, #2, #8
|
|
ubfiz \reg1, \in1e, #2, #8
|
|
.else
|
|
ubfx \reg0, \in0, #\shift, #8
|
|
ubfx \reg1, \in1e, #\shift, #8
|
|
.endif
|
|
|
|
/*
|
|
* AArch64 cannot do byte size indexed loads from a table containing
|
|
* 32-bit quantities, i.e., 'ldrb w12, [tt, w12, uxtw #2]' is not a
|
|
* valid instruction. So perform the shift explicitly first for the
|
|
* high bytes (the low byte is shifted implicitly by using ubfiz rather
|
|
* than ubfx above)
|
|
*/
|
|
.ifnc \op, b
|
|
ldr \reg0, [tt, \reg0, uxtw #2]
|
|
ldr \reg1, [tt, \reg1, uxtw #2]
|
|
.else
|
|
.if \shift > 0
|
|
lsl \reg0, \reg0, #2
|
|
lsl \reg1, \reg1, #2
|
|
.endif
|
|
ldrb \reg0, [tt, \reg0, uxtw]
|
|
ldrb \reg1, [tt, \reg1, uxtw]
|
|
.endif
|
|
.endm
|
|
|
|
.macro __pair0, sz, op, reg0, reg1, in0, in1e, in1d, shift
|
|
ubfx \reg0, \in0, #\shift, #8
|
|
ubfx \reg1, \in1d, #\shift, #8
|
|
ldr\op \reg0, [tt, \reg0, uxtw #\sz]
|
|
ldr\op \reg1, [tt, \reg1, uxtw #\sz]
|
|
.endm
|
|
|
|
.macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc, sz, op
|
|
ldp \out0, \out1, [rk], #8
|
|
|
|
__pair\enc \sz, \op, w12, w13, \in0, \in1, \in3, 0
|
|
__pair\enc \sz, \op, w14, w15, \in1, \in2, \in0, 8
|
|
__pair\enc \sz, \op, w16, w17, \in2, \in3, \in1, 16
|
|
__pair\enc \sz, \op, \t0, \t1, \in3, \in0, \in2, 24
|
|
|
|
eor \out0, \out0, w12
|
|
eor \out1, \out1, w13
|
|
eor \out0, \out0, w14, ror #24
|
|
eor \out1, \out1, w15, ror #24
|
|
eor \out0, \out0, w16, ror #16
|
|
eor \out1, \out1, w17, 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, sz=2, op
|
|
__hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
|
|
__hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op
|
|
.endm
|
|
|
|
.macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
|
|
__hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
|
|
__hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op
|
|
.endm
|
|
|
|
.macro do_crypt, round, ttab, ltab, bsz
|
|
ldp w4, w5, [in]
|
|
ldp w6, w7, [in, #8]
|
|
ldp w8, w9, [rk], #16
|
|
ldp w10, w11, [rk, #-8]
|
|
|
|
CPU_BE( rev w4, w4 )
|
|
CPU_BE( rev w5, w5 )
|
|
CPU_BE( rev w6, w6 )
|
|
CPU_BE( rev w7, w7 )
|
|
|
|
eor w4, w4, w8
|
|
eor w5, w5, w9
|
|
eor w6, w6, w10
|
|
eor w7, w7, w11
|
|
|
|
adr_l tt, \ttab
|
|
|
|
tbnz rounds, #1, 1f
|
|
|
|
0: \round w8, w9, w10, w11, w4, w5, w6, w7
|
|
\round w4, w5, w6, w7, w8, w9, w10, w11
|
|
|
|
1: subs rounds, rounds, #4
|
|
\round w8, w9, w10, w11, w4, w5, w6, w7
|
|
b.ls 3f
|
|
2: \round w4, w5, w6, w7, w8, w9, w10, w11
|
|
b 0b
|
|
3: adr_l tt, \ltab
|
|
\round w4, w5, w6, w7, w8, w9, w10, w11, \bsz, b
|
|
|
|
CPU_BE( rev w4, w4 )
|
|
CPU_BE( rev w5, w5 )
|
|
CPU_BE( rev w6, w6 )
|
|
CPU_BE( rev w7, w7 )
|
|
|
|
stp w4, w5, [out]
|
|
stp w6, w7, [out, #8]
|
|
ret
|
|
.endm
|
|
|
|
SYM_FUNC_START(__aes_arm64_encrypt)
|
|
do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
|
|
SYM_FUNC_END(__aes_arm64_encrypt)
|
|
|
|
.align 5
|
|
SYM_FUNC_START(__aes_arm64_decrypt)
|
|
do_crypt iround, crypto_it_tab, crypto_aes_inv_sbox, 0
|
|
SYM_FUNC_END(__aes_arm64_decrypt)
|