linux/arch/arm64/crypto/aes-neon.S
Ard Biesheuvel 67cfa5d3b7 crypto: arm64/aes-neonbs - implement ciphertext stealing for XTS
Update the AES-XTS implementation based on NEON instructions so that it
can deal with inputs whose size is not a multiple of the cipher block
size. This is part of the original XTS specification, but was never
implemented before in the Linux kernel.

Since the bit slicing driver is only faster if it can operate on at
least 7 blocks of input at the same time, let's reuse the alternate
path we are adding for CTS to process any data tail whose size is
not a multiple of 128 bytes.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-09-09 17:35:39 +10:00

251 lines
7.4 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
*
* Copyright (C) 2013 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
#define AES_ENTRY(func) ENTRY(neon_ ## func)
#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
xtsmask .req v7
cbciv .req v7
vctr .req v4
.macro xts_reload_mask, tmp
xts_load_mask \tmp
.endm
/* special case for the neon-bs driver calling into this one for CTS */
.macro xts_cts_skip_tw, reg, lbl
tbnz \reg, #1, \lbl
.endm
/* 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
movi v12.16b, #0x1b
ldr_l q13, \shiftrows, \temp
ldr_l q14, .Lror32by8, \temp
adr_l \temp, \sbox
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 crypto_aes_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 crypto_aes_inv_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 AES states in parallel.
*/
.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_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_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"
.section ".rodata", "a"
.align 4
.LForward_ShiftRows:
.octa 0x0b06010c07020d08030e09040f0a0500
.LReverse_ShiftRows:
.octa 0x0306090c0f0205080b0e0104070a0d00
.Lror32by8:
.octa 0x0c0f0e0d080b0a090407060500030201