mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
2e5d2f33d1
The Crypto Extension instantiation of the aes-modes.S collection of skciphers uses only 15 NEON registers for the round key array, whereas the pure NEON flavor uses 16 NEON registers for the AES S-box. This means we have a spare register available that we can use to hold the XTS mask vector, removing the need to reload it at every iteration of the inner loop. Since the pure NEON version does not permit this optimization, tweak the macros so we can factor out this functionality. Also, replace the literal load with a short sequence to compose the mask vector. On Cortex-A53, this results in a ~4% speedup. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
139 lines
3.4 KiB
ArmAsm
139 lines
3.4 KiB
ArmAsm
/*
|
|
* linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
|
|
* Crypto Extensions
|
|
*
|
|
* 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(ce_ ## func)
|
|
#define AES_ENDPROC(func) ENDPROC(ce_ ## func)
|
|
|
|
.arch armv8-a+crypto
|
|
|
|
xtsmask .req v16
|
|
|
|
.macro xts_reload_mask, tmp
|
|
.endm
|
|
|
|
/* preload all round keys */
|
|
.macro load_round_keys, rounds, rk
|
|
cmp \rounds, #12
|
|
blo 2222f /* 128 bits */
|
|
beq 1111f /* 192 bits */
|
|
ld1 {v17.4s-v18.4s}, [\rk], #32
|
|
1111: ld1 {v19.4s-v20.4s}, [\rk], #32
|
|
2222: ld1 {v21.4s-v24.4s}, [\rk], #64
|
|
ld1 {v25.4s-v28.4s}, [\rk], #64
|
|
ld1 {v29.4s-v31.4s}, [\rk]
|
|
.endm
|
|
|
|
/* prepare for encryption with key in rk[] */
|
|
.macro enc_prepare, rounds, rk, temp
|
|
mov \temp, \rk
|
|
load_round_keys \rounds, \temp
|
|
.endm
|
|
|
|
/* prepare for encryption (again) but with new key in rk[] */
|
|
.macro enc_switch_key, rounds, rk, temp
|
|
mov \temp, \rk
|
|
load_round_keys \rounds, \temp
|
|
.endm
|
|
|
|
/* prepare for decryption with key in rk[] */
|
|
.macro dec_prepare, rounds, rk, temp
|
|
mov \temp, \rk
|
|
load_round_keys \rounds, \temp
|
|
.endm
|
|
|
|
.macro do_enc_Nx, de, mc, k, i0, i1, i2, i3
|
|
aes\de \i0\().16b, \k\().16b
|
|
aes\mc \i0\().16b, \i0\().16b
|
|
.ifnb \i1
|
|
aes\de \i1\().16b, \k\().16b
|
|
aes\mc \i1\().16b, \i1\().16b
|
|
.ifnb \i3
|
|
aes\de \i2\().16b, \k\().16b
|
|
aes\mc \i2\().16b, \i2\().16b
|
|
aes\de \i3\().16b, \k\().16b
|
|
aes\mc \i3\().16b, \i3\().16b
|
|
.endif
|
|
.endif
|
|
.endm
|
|
|
|
/* up to 4 interleaved encryption rounds with the same round key */
|
|
.macro round_Nx, enc, k, i0, i1, i2, i3
|
|
.ifc \enc, e
|
|
do_enc_Nx e, mc, \k, \i0, \i1, \i2, \i3
|
|
.else
|
|
do_enc_Nx d, imc, \k, \i0, \i1, \i2, \i3
|
|
.endif
|
|
.endm
|
|
|
|
/* up to 4 interleaved final rounds */
|
|
.macro fin_round_Nx, de, k, k2, i0, i1, i2, i3
|
|
aes\de \i0\().16b, \k\().16b
|
|
.ifnb \i1
|
|
aes\de \i1\().16b, \k\().16b
|
|
.ifnb \i3
|
|
aes\de \i2\().16b, \k\().16b
|
|
aes\de \i3\().16b, \k\().16b
|
|
.endif
|
|
.endif
|
|
eor \i0\().16b, \i0\().16b, \k2\().16b
|
|
.ifnb \i1
|
|
eor \i1\().16b, \i1\().16b, \k2\().16b
|
|
.ifnb \i3
|
|
eor \i2\().16b, \i2\().16b, \k2\().16b
|
|
eor \i3\().16b, \i3\().16b, \k2\().16b
|
|
.endif
|
|
.endif
|
|
.endm
|
|
|
|
/* up to 4 interleaved blocks */
|
|
.macro do_block_Nx, enc, rounds, i0, i1, i2, i3
|
|
cmp \rounds, #12
|
|
blo 2222f /* 128 bits */
|
|
beq 1111f /* 192 bits */
|
|
round_Nx \enc, v17, \i0, \i1, \i2, \i3
|
|
round_Nx \enc, v18, \i0, \i1, \i2, \i3
|
|
1111: round_Nx \enc, v19, \i0, \i1, \i2, \i3
|
|
round_Nx \enc, v20, \i0, \i1, \i2, \i3
|
|
2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29
|
|
round_Nx \enc, \key, \i0, \i1, \i2, \i3
|
|
.endr
|
|
fin_round_Nx \enc, v30, v31, \i0, \i1, \i2, \i3
|
|
.endm
|
|
|
|
.macro encrypt_block, in, rounds, t0, t1, t2
|
|
do_block_Nx e, \rounds, \in
|
|
.endm
|
|
|
|
.macro encrypt_block2x, i0, i1, rounds, t0, t1, t2
|
|
do_block_Nx e, \rounds, \i0, \i1
|
|
.endm
|
|
|
|
.macro encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
|
|
do_block_Nx e, \rounds, \i0, \i1, \i2, \i3
|
|
.endm
|
|
|
|
.macro decrypt_block, in, rounds, t0, t1, t2
|
|
do_block_Nx d, \rounds, \in
|
|
.endm
|
|
|
|
.macro decrypt_block2x, i0, i1, rounds, t0, t1, t2
|
|
do_block_Nx d, \rounds, \i0, \i1
|
|
.endm
|
|
|
|
.macro decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
|
|
do_block_Nx d, \rounds, \i0, \i1, \i2, \i3
|
|
.endm
|
|
|
|
#include "aes-modes.S"
|