174 lines
5.3 KiB
ArmAsm
174 lines
5.3 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>
|
|
#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
|
|
|
|
ENTRY(__aes_arm64_encrypt)
|
|
do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
|
|
ENDPROC(__aes_arm64_encrypt)
|
|
|
|
.align 5
|
|
ENTRY(__aes_arm64_decrypt)
|
|
do_crypt iround, crypto_it_tab, __aes_arm64_inverse_sbox, 0
|
|
ENDPROC(__aes_arm64_decrypt)
|
|
|
|
.section ".rodata", "a"
|
|
.align L1_CACHE_SHIFT
|
|
.type __aes_arm64_inverse_sbox, %object
|
|
__aes_arm64_inverse_sbox:
|
|
.byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
|
|
.byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
|
|
.byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
|
|
.byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
|
|
.byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
|
|
.byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
|
|
.byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
|
|
.byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
|
|
.byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
|
|
.byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
|
|
.byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
|
|
.byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
|
|
.byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
|
|
.byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
|
|
.byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
|
|
.byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
|
|
.byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
|
|
.byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
|
|
.byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
|
|
.byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
|
|
.byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
|
|
.byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
|
|
.byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
|
|
.byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
|
|
.byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
|
|
.byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
|
|
.byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
|
|
.byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
|
|
.byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
|
|
.byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
|
|
.byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
|
|
.byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
|
|
.size __aes_arm64_inverse_sbox, . - __aes_arm64_inverse_sbox
|