Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-19 18:41:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
6caf7adc5e
linux/arch/arm64/crypto/aes-ce.S

134 lines
3.4 KiB
ArmAsm
Raw Normal View History

arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
/*
* linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
* Crypto Extensions
*
crypto: arm64/aes-ce-cipher - match round key endianness with generic code In order to be able to reuse the generic AES code as a fallback for situations where the NEON may not be used, update the key handling to match the byte order of the generic code: it stores round keys as sequences of 32-bit quantities rather than streams of bytes, and so our code needs to be updated to reflect that. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-07-24 10:28:10 +00:00
* Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
*
* 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>
crypto: arm64/aes-xts-ce: fix for big endian Emit the XTS tweak literal constants in the appropriate order for a single 128-bit scalar literal load. Fixes: 49788fe2a128 ("arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions") Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2016-10-11 18:15:19 +00:00
#include <asm/assembler.h>
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
#define AES_ENTRY(func) ENTRY(ce_ ## func)
#define AES_ENDPROC(func) ENDPROC(ce_ ## func)
.arch armv8-a+crypto
/* preload all round keys */
.macro load_round_keys, rounds, rk
cmp \rounds, #12
blo 2222f /* 128 bits */
beq 1111f /* 192 bits */
crypto: arm64/aes-ce-cipher - match round key endianness with generic code In order to be able to reuse the generic AES code as a fallback for situations where the NEON may not be used, update the key handling to match the byte order of the generic code: it stores round keys as sequences of 32-bit quantities rather than streams of bytes, and so our code needs to be updated to reflect that. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-07-24 10:28:10 +00:00
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]
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
.endm
/* prepare for encryption with key in rk[] */
crypto: arm64/aes-blk - yield NEON after every block of input Avoid excessive scheduling delays under a preemptible kernel by yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-04-30 16:18:24 +00:00
.macro enc_prepare, rounds, rk, temp
mov \temp, \rk
load_round_keys \rounds, \temp
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
.endm
/* prepare for encryption (again) but with new key in rk[] */
crypto: arm64/aes-blk - yield NEON after every block of input Avoid excessive scheduling delays under a preemptible kernel by yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-04-30 16:18:24 +00:00
.macro enc_switch_key, rounds, rk, temp
mov \temp, \rk
load_round_keys \rounds, \temp
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
.endm
/* prepare for decryption with key in rk[] */
crypto: arm64/aes-blk - yield NEON after every block of input Avoid excessive scheduling delays under a preemptible kernel by yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-04-30 16:18:24 +00:00
.macro dec_prepare, rounds, rk, temp
mov \temp, \rk
load_round_keys \rounds, \temp
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
.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
arm64/crypto: issue aese/aesmc instructions in pairs This changes the AES core transform implementations to issue aese/aesmc (and aesd/aesimc) in pairs. This enables a micro-architectural optimization in recent Cortex-A5x cores that improves performance by 50-90%. Measured performance in cycles per byte (Cortex-A57): CBC enc CBC dec CTR before 3.64 1.34 1.32 after 1.95 0.85 0.93 Note that this results in a ~5% performance decrease for older cores. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-17 18:05:13 +00:00
aes\de \i1\().16b, \k\().16b
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
aes\mc \i1\().16b, \i1\().16b
.ifnb \i3
arm64/crypto: issue aese/aesmc instructions in pairs This changes the AES core transform implementations to issue aese/aesmc (and aesd/aesimc) in pairs. This enables a micro-architectural optimization in recent Cortex-A5x cores that improves performance by 50-90%. Measured performance in cycles per byte (Cortex-A57): CBC enc CBC dec CTR before 3.64 1.34 1.32 after 1.95 0.85 0.93 Note that this results in a ~5% performance decrease for older cores. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-17 18:05:13 +00:00
aes\de \i2\().16b, \k\().16b
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
aes\mc \i2\().16b, \i2\().16b
arm64/crypto: issue aese/aesmc instructions in pairs This changes the AES core transform implementations to issue aese/aesmc (and aesd/aesimc) in pairs. This enables a micro-architectural optimization in recent Cortex-A5x cores that improves performance by 50-90%. Measured performance in cycles per byte (Cortex-A57): CBC enc CBC dec CTR before 3.64 1.34 1.32 after 1.95 0.85 0.93 Note that this results in a ~5% performance decrease for older cores. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-17 18:05:13 +00:00
aes\de \i3\().16b, \k\().16b
arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions This adds ARMv8 implementations of AES in ECB, CBC, CTR and XTS modes, both for ARMv8 with Crypto Extensions and for plain ARMv8 NEON. The Crypto Extensions version can only run on ARMv8 implementations that have support for these optional extensions. The plain NEON version is a table based yet time invariant implementation. All S-box substitutions are performed in parallel, leveraging the wide range of ARMv8's tbl/tbx instructions, and the huge NEON register file, which can comfortably hold the entire S-box and still have room to spare for doing the actual computations. The key expansion routines were borrowed from aes_generic. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-03-21 09:19:17 +00:00
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"
Reference in New Issue Copy Permalink