linux/arch/arm64/crypto/aes-neon.S
Ard Biesheuvel 4edd7d015b crypto: arm64/aes-neon-blk - tweak performance for low end cores
The non-bitsliced AES implementation using the NEON is highly sensitive
to micro-architectural details, and, as it turns out, the Cortex-A53 on
the Raspberry Pi 3 is a core that can benefit from this code, given that
its scalar AES performance is abysmal (32.9 cycles per byte).

The new bitsliced AES code manages 19.8 cycles per byte on this core,
but can only operate on 8 blocks at a time, which is not supported by
all chaining modes. With a bit of tweaking, we can get the plain NEON
code to run at 22.0 cycles per byte, making it useful for sequential
modes like CBC encryption. (Like bitsliced NEON, the plain NEON
implementation does not use any lookup tables, which makes it easy on
the D-cache, and invulnerable to cache timing attacks)

So tweak the plain NEON AES code to use tbl instructions rather than
shl/sri pairs, and to avoid the need to reload permutation vectors or
other constants from memory in every round. Also, improve the decryption
performance by switching to 16x8 pmul instructions for the performing
the multiplications in GF(2^8).

To allow the ECB and CBC encrypt routines to be reused by the bitsliced
NEON code in a subsequent patch, export them from the module.

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

353 lines
12 KiB
ArmAsm

/*
* linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
*
* Copyright (C) 2013 - 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>
#define AES_ENTRY(func) ENTRY(neon_ ## func)
#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
/* multiply by polynomial 'x' in GF(2^8) */
.macro mul_by_x, out, in, temp, const
sshr \temp, \in, #7
shl \out, \in, #1
and \temp, \temp, \const
eor \out, \out, \temp
.endm
/* multiply by polynomial 'x^2' in GF(2^8) */
.macro mul_by_x2, out, in, temp, const
ushr \temp, \in, #6
shl \out, \in, #2
pmul \temp, \temp, \const
eor \out, \out, \temp
.endm
/* preload the entire Sbox */
.macro prepare, sbox, shiftrows, temp
adr \temp, \sbox
movi v12.16b, #0x1b
ldr q13, \shiftrows
ldr q14, .Lror32by8
ld1 {v16.16b-v19.16b}, [\temp], #64
ld1 {v20.16b-v23.16b}, [\temp], #64
ld1 {v24.16b-v27.16b}, [\temp], #64
ld1 {v28.16b-v31.16b}, [\temp]
.endm
/* do preload for encryption */
.macro enc_prepare, ignore0, ignore1, temp
prepare .LForward_Sbox, .LForward_ShiftRows, \temp
.endm
.macro enc_switch_key, ignore0, ignore1, temp
/* do nothing */
.endm
/* do preload for decryption */
.macro dec_prepare, ignore0, ignore1, temp
prepare .LReverse_Sbox, .LReverse_ShiftRows, \temp
.endm
/* apply SubBytes transformation using the the preloaded Sbox */
.macro sub_bytes, in
sub v9.16b, \in\().16b, v15.16b
tbl \in\().16b, {v16.16b-v19.16b}, \in\().16b
sub v10.16b, v9.16b, v15.16b
tbx \in\().16b, {v20.16b-v23.16b}, v9.16b
sub v11.16b, v10.16b, v15.16b
tbx \in\().16b, {v24.16b-v27.16b}, v10.16b
tbx \in\().16b, {v28.16b-v31.16b}, v11.16b
.endm
/* apply MixColumns transformation */
.macro mix_columns, in, enc
.if \enc == 0
/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
mul_by_x2 v8.16b, \in\().16b, v9.16b, v12.16b
eor \in\().16b, \in\().16b, v8.16b
rev32 v8.8h, v8.8h
eor \in\().16b, \in\().16b, v8.16b
.endif
mul_by_x v9.16b, \in\().16b, v8.16b, v12.16b
rev32 v8.8h, \in\().8h
eor v8.16b, v8.16b, v9.16b
eor \in\().16b, \in\().16b, v8.16b
tbl \in\().16b, {\in\().16b}, v14.16b
eor \in\().16b, \in\().16b, v8.16b
.endm
.macro do_block, enc, in, rounds, rk, rkp, i
ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
movi v15.16b, #0x40
tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */
sub_bytes \in
subs \i, \i, #1
ld1 {v15.4s}, [\rkp], #16
beq 2222f
mix_columns \in, \enc
b 1111b
2222: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
.endm
.macro encrypt_block, in, rounds, rk, rkp, i
do_block 1, \in, \rounds, \rk, \rkp, \i
.endm
.macro decrypt_block, in, rounds, rk, rkp, i
do_block 0, \in, \rounds, \rk, \rkp, \i
.endm
/*
* Interleaved versions: functionally equivalent to the
* ones above, but applied to 2 or 4 AES states in parallel.
*/
.macro sub_bytes_2x, in0, in1
sub v8.16b, \in0\().16b, v15.16b
tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
sub v9.16b, \in1\().16b, v15.16b
tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
sub v10.16b, v8.16b, v15.16b
tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
sub v11.16b, v9.16b, v15.16b
tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
sub v8.16b, v10.16b, v15.16b
tbx \in0\().16b, {v24.16b-v27.16b}, v10.16b
sub v9.16b, v11.16b, v15.16b
tbx \in1\().16b, {v24.16b-v27.16b}, v11.16b
tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
.endm
.macro sub_bytes_4x, in0, in1, in2, in3
sub v8.16b, \in0\().16b, v15.16b
tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
sub v9.16b, \in1\().16b, v15.16b
tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
sub v10.16b, \in2\().16b, v15.16b
tbl \in2\().16b, {v16.16b-v19.16b}, \in2\().16b
sub v11.16b, \in3\().16b, v15.16b
tbl \in3\().16b, {v16.16b-v19.16b}, \in3\().16b
tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
sub v8.16b, v8.16b, v15.16b
tbx \in2\().16b, {v20.16b-v23.16b}, v10.16b
sub v9.16b, v9.16b, v15.16b
tbx \in3\().16b, {v20.16b-v23.16b}, v11.16b
sub v10.16b, v10.16b, v15.16b
tbx \in0\().16b, {v24.16b-v27.16b}, v8.16b
sub v11.16b, v11.16b, v15.16b
tbx \in1\().16b, {v24.16b-v27.16b}, v9.16b
sub v8.16b, v8.16b, v15.16b
tbx \in2\().16b, {v24.16b-v27.16b}, v10.16b
sub v9.16b, v9.16b, v15.16b
tbx \in3\().16b, {v24.16b-v27.16b}, v11.16b
sub v10.16b, v10.16b, v15.16b
tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
sub v11.16b, v11.16b, v15.16b
tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
tbx \in2\().16b, {v28.16b-v31.16b}, v10.16b
tbx \in3\().16b, {v28.16b-v31.16b}, v11.16b
.endm
.macro mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
sshr \tmp0\().16b, \in0\().16b, #7
shl \out0\().16b, \in0\().16b, #1
sshr \tmp1\().16b, \in1\().16b, #7
and \tmp0\().16b, \tmp0\().16b, \const\().16b
shl \out1\().16b, \in1\().16b, #1
and \tmp1\().16b, \tmp1\().16b, \const\().16b
eor \out0\().16b, \out0\().16b, \tmp0\().16b
eor \out1\().16b, \out1\().16b, \tmp1\().16b
.endm
.macro mul_by_x2_2x, out0, out1, in0, in1, tmp0, tmp1, const
ushr \tmp0\().16b, \in0\().16b, #6
shl \out0\().16b, \in0\().16b, #2
ushr \tmp1\().16b, \in1\().16b, #6
pmul \tmp0\().16b, \tmp0\().16b, \const\().16b
shl \out1\().16b, \in1\().16b, #2
pmul \tmp1\().16b, \tmp1\().16b, \const\().16b
eor \out0\().16b, \out0\().16b, \tmp0\().16b
eor \out1\().16b, \out1\().16b, \tmp1\().16b
.endm
.macro mix_columns_2x, in0, in1, enc
.if \enc == 0
/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
mul_by_x2_2x v8, v9, \in0, \in1, v10, v11, v12
eor \in0\().16b, \in0\().16b, v8.16b
rev32 v8.8h, v8.8h
eor \in1\().16b, \in1\().16b, v9.16b
rev32 v9.8h, v9.8h
eor \in0\().16b, \in0\().16b, v8.16b
eor \in1\().16b, \in1\().16b, v9.16b
.endif
mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v12
rev32 v10.8h, \in0\().8h
rev32 v11.8h, \in1\().8h
eor v10.16b, v10.16b, v8.16b
eor v11.16b, v11.16b, v9.16b
eor \in0\().16b, \in0\().16b, v10.16b
eor \in1\().16b, \in1\().16b, v11.16b
tbl \in0\().16b, {\in0\().16b}, v14.16b
tbl \in1\().16b, {\in1\().16b}, v14.16b
eor \in0\().16b, \in0\().16b, v10.16b
eor \in1\().16b, \in1\().16b, v11.16b
.endm
.macro do_block_2x, enc, in0, in1, rounds, rk, rkp, i
ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
movi v15.16b, #0x40
tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
sub_bytes_2x \in0, \in1
subs \i, \i, #1
ld1 {v15.4s}, [\rkp], #16
beq 2222f
mix_columns_2x \in0, \in1, \enc
b 1111b
2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
.endm
.macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
ld1 {v15.4s}, [\rk]
add \rkp, \rk, #16
mov \i, \rounds
1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
movi v15.16b, #0x40
tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */
tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */
sub_bytes_4x \in0, \in1, \in2, \in3
subs \i, \i, #1
ld1 {v15.4s}, [\rkp], #16
beq 2222f
mix_columns_2x \in0, \in1, \enc
mix_columns_2x \in2, \in3, \enc
b 1111b
2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
.endm
.macro encrypt_block2x, in0, in1, rounds, rk, rkp, i
do_block_2x 1, \in0, \in1, \rounds, \rk, \rkp, \i
.endm
.macro decrypt_block2x, in0, in1, rounds, rk, rkp, i
do_block_2x 0, \in0, \in1, \rounds, \rk, \rkp, \i
.endm
.macro encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
do_block_4x 1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
.endm
.macro decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
do_block_4x 0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
.endm
#include "aes-modes.S"
.text
.align 6
.LForward_Sbox:
.byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
.byte 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
.byte 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
.byte 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
.byte 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
.byte 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
.byte 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
.byte 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
.byte 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
.byte 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
.byte 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
.byte 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
.byte 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
.byte 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
.byte 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
.byte 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
.byte 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
.byte 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
.byte 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
.byte 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
.byte 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
.byte 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
.byte 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
.byte 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
.byte 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
.byte 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
.byte 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
.byte 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
.byte 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
.byte 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
.byte 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
.byte 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
.LReverse_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
.LForward_ShiftRows:
.octa 0x0b06010c07020d08030e09040f0a0500
.LReverse_ShiftRows:
.octa 0x0306090c0f0205080b0e0104070a0d00
.Lror32by8:
.octa 0x0c0f0e0d080b0a090407060500030201