openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity
linux/arch/arm64/crypto/aes-modes.S

555 lines
12 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 17:19:17 +08:00
/*
* linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
*
crypto: arm64/aes - add NEON/Crypto Extensions CBCMAC/CMAC/XCBC driver On ARMv8 implementations that do not support the Crypto Extensions, such as the Raspberry Pi 3, the CCM driver falls back to the generic table based AES implementation to perform the MAC part of the algorithm, which is slow and not time invariant. So add a CBCMAC implementation to the shared glue code between NEON AES and Crypto Extensions AES, so that it can be used instead now that the CCM driver has been updated to look for CBCMAC implementations other than the one it supplies itself. Also, given how these algorithms mostly only differ in the way the key handling and the final encryption are implemented, expose CMAC and XCBC algorithms as well based on the same core update code. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-02-03 22:49:37 +08:00
* 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 17:19:17 +08:00
*
* 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.
*/
/* included by aes-ce.S and aes-neon.S */
.text
.align 4
/*
* There are several ways to instantiate this code:
* - no interleave, all inline
* - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
* - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
* - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
* - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
*
* Macros imported by this code:
* - enc_prepare - setup NEON registers for encryption
* - dec_prepare - setup NEON registers for decryption
* - enc_switch_key - change to new key after having prepared for encryption
* - encrypt_block - encrypt a single block
* - decrypt block - decrypt a single block
* - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2)
* - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2)
* - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4)
* - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4)
*/
#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp
#define FRAME_POP ldp x29, x30, [sp],#16
#if INTERLEAVE == 2
aes_encrypt_block2x:
encrypt_block2x v0, v1, w3, x2, x6, w7
ret
ENDPROC(aes_encrypt_block2x)
aes_decrypt_block2x:
decrypt_block2x v0, v1, w3, x2, x6, w7
ret
ENDPROC(aes_decrypt_block2x)
#elif INTERLEAVE == 4
aes_encrypt_block4x:
encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
ret
ENDPROC(aes_encrypt_block4x)
aes_decrypt_block4x:
decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
ret
ENDPROC(aes_decrypt_block4x)
#else
#error INTERLEAVE should equal 2 or 4
#endif
.macro do_encrypt_block2x
bl aes_encrypt_block2x
.endm
.macro do_decrypt_block2x
bl aes_decrypt_block2x
.endm
.macro do_encrypt_block4x
bl aes_encrypt_block4x
.endm
.macro do_decrypt_block4x
bl aes_decrypt_block4x
.endm
#else
#define FRAME_PUSH
#define FRAME_POP
.macro do_encrypt_block2x
encrypt_block2x v0, v1, w3, x2, x6, w7
.endm
.macro do_decrypt_block2x
decrypt_block2x v0, v1, w3, x2, x6, w7
.endm
.macro do_encrypt_block4x
encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
.endm
.macro do_decrypt_block4x
decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
.endm
#endif
/*
* aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, int first)
* aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, int first)
*/
AES_ENTRY(aes_ecb_encrypt)
FRAME_PUSH
cbz w5, .LecbencloopNx
enc_prepare w3, x2, x5
.LecbencloopNx:
#if INTERLEAVE >= 2
subs w4, w4, #INTERLEAVE
bmi .Lecbenc1x
#if INTERLEAVE == 2
ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
do_encrypt_block2x
st1 {v0.16b-v1.16b}, [x0], #32
#else
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
do_encrypt_block4x
st1 {v0.16b-v3.16b}, [x0], #64
#endif
b .LecbencloopNx
.Lecbenc1x:
adds w4, w4, #INTERLEAVE
beq .Lecbencout
#endif
.Lecbencloop:
ld1 {v0.16b}, [x1], #16 /* get next pt block */
encrypt_block v0, w3, x2, x5, w6
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lecbencloop
.Lecbencout:
FRAME_POP
ret
AES_ENDPROC(aes_ecb_encrypt)
AES_ENTRY(aes_ecb_decrypt)
FRAME_PUSH
cbz w5, .LecbdecloopNx
dec_prepare w3, x2, x5
.LecbdecloopNx:
#if INTERLEAVE >= 2
subs w4, w4, #INTERLEAVE
bmi .Lecbdec1x
#if INTERLEAVE == 2
ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
do_decrypt_block2x
st1 {v0.16b-v1.16b}, [x0], #32
#else
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
do_decrypt_block4x
st1 {v0.16b-v3.16b}, [x0], #64
#endif
b .LecbdecloopNx
.Lecbdec1x:
adds w4, w4, #INTERLEAVE
beq .Lecbdecout
#endif
.Lecbdecloop:
ld1 {v0.16b}, [x1], #16 /* get next ct block */
decrypt_block v0, w3, x2, x5, w6
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lecbdecloop
.Lecbdecout:
FRAME_POP
ret
AES_ENDPROC(aes_ecb_decrypt)
/*
* aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[], int first)
* aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[], int first)
*/
AES_ENTRY(aes_cbc_encrypt)
cbz w6, .Lcbcencloop
ld1 {v0.16b}, [x5] /* get iv */
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
enc_prepare w3, x2, x6
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 17:19:17 +08:00
.Lcbcencloop:
ld1 {v1.16b}, [x1], #16 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
encrypt_block v0, w3, x2, x6, w7
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 17:19:17 +08:00
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lcbcencloop
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
st1 {v0.16b}, [x5] /* return iv */
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 17:19:17 +08:00
ret
AES_ENDPROC(aes_cbc_encrypt)
AES_ENTRY(aes_cbc_decrypt)
FRAME_PUSH
cbz w6, .LcbcdecloopNx
ld1 {v7.16b}, [x5] /* get iv */
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
dec_prepare w3, x2, x6
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 17:19:17 +08:00
.LcbcdecloopNx:
#if INTERLEAVE >= 2
subs w4, w4, #INTERLEAVE
bmi .Lcbcdec1x
#if INTERLEAVE == 2
ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
mov v2.16b, v0.16b
mov v3.16b, v1.16b
do_decrypt_block2x
eor v0.16b, v0.16b, v7.16b
eor v1.16b, v1.16b, v2.16b
mov v7.16b, v3.16b
st1 {v0.16b-v1.16b}, [x0], #32
#else
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
mov v4.16b, v0.16b
mov v5.16b, v1.16b
mov v6.16b, v2.16b
do_decrypt_block4x
sub x1, x1, #16
eor v0.16b, v0.16b, v7.16b
eor v1.16b, v1.16b, v4.16b
ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */
eor v2.16b, v2.16b, v5.16b
eor v3.16b, v3.16b, v6.16b
st1 {v0.16b-v3.16b}, [x0], #64
#endif
b .LcbcdecloopNx
.Lcbcdec1x:
adds w4, w4, #INTERLEAVE
beq .Lcbcdecout
#endif
.Lcbcdecloop:
ld1 {v1.16b}, [x1], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
decrypt_block v0, w3, x2, x6, w7
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 17:19:17 +08:00
eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
mov v7.16b, v1.16b /* ct is next iv */
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lcbcdecloop
.Lcbcdecout:
FRAME_POP
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
st1 {v7.16b}, [x5] /* return iv */
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 17:19:17 +08:00
ret
AES_ENDPROC(aes_cbc_decrypt)
/*
* aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 ctr[], int first)
*/
AES_ENTRY(aes_ctr_encrypt)
FRAME_PUSH
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
cbz w6, .Lctrnotfirst /* 1st time around? */
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 17:19:17 +08:00
enc_prepare w3, x2, x6
ld1 {v4.16b}, [x5]
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
.Lctrnotfirst:
umov x8, v4.d[1] /* keep swabbed ctr in reg */
rev x8, x8
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 17:19:17 +08:00
#if INTERLEAVE >= 2
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
cmn w8, w4 /* 32 bit overflow? */
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 17:19:17 +08:00
bcs .Lctrloop
.LctrloopNx:
subs w4, w4, #INTERLEAVE
bmi .Lctr1x
#if INTERLEAVE == 2
mov v0.8b, v4.8b
mov v1.8b, v4.8b
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
rev x7, x8
add x8, x8, #1
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 17:19:17 +08:00
ins v0.d[1], x7
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
rev x7, x8
add x8, x8, #1
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 17:19:17 +08:00
ins v1.d[1], x7
ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */
do_encrypt_block2x
eor v0.16b, v0.16b, v2.16b
eor v1.16b, v1.16b, v3.16b
st1 {v0.16b-v1.16b}, [x0], #32
#else
ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
dup v7.4s, w8
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 17:19:17 +08:00
mov v0.16b, v4.16b
add v7.4s, v7.4s, v8.4s
mov v1.16b, v4.16b
rev32 v8.16b, v7.16b
mov v2.16b, v4.16b
mov v3.16b, v4.16b
mov v1.s[3], v8.s[0]
mov v2.s[3], v8.s[1]
mov v3.s[3], v8.s[2]
ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */
do_encrypt_block4x
eor v0.16b, v5.16b, v0.16b
ld1 {v5.16b}, [x1], #16 /* get 1 input block */
eor v1.16b, v6.16b, v1.16b
eor v2.16b, v7.16b, v2.16b
eor v3.16b, v5.16b, v3.16b
st1 {v0.16b-v3.16b}, [x0], #64
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
add x8, x8, #INTERLEAVE
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 17:19:17 +08:00
#endif
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
rev x7, x8
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 17:19:17 +08:00
ins v4.d[1], x7
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
cbz w4, .Lctrout
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 17:19:17 +08:00
b .LctrloopNx
.Lctr1x:
adds w4, w4, #INTERLEAVE
beq .Lctrout
#endif
.Lctrloop:
mov v0.16b, v4.16b
encrypt_block v0, w3, x2, x6, w7
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
adds x8, x8, #1 /* increment BE ctr */
rev x7, x8
ins v4.d[1], x7
bcs .Lctrcarry /* overflow? */
.Lctrcarrydone:
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 17:19:17 +08:00
subs w4, w4, #1
crypto: arm64/aes-blk - remove cra_alignmask Remove the unnecessary alignmask: it is much more efficient to deal with the misalignment in the core algorithm than relying on the crypto API to copy the data to a suitably aligned buffer. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-29 07:25:34 +08:00
bmi .Lctrtailblock /* blocks <0 means tail block */
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 17:19:17 +08:00
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
bne .Lctrloop
.Lctrout:
st1 {v4.16b}, [x5] /* return next CTR value */
FRAME_POP
ret
crypto: arm64/aes-blk - remove cra_alignmask Remove the unnecessary alignmask: it is much more efficient to deal with the misalignment in the core algorithm than relying on the crypto API to copy the data to a suitably aligned buffer. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-29 07:25:34 +08:00
.Lctrtailblock:
st1 {v0.16b}, [x0]
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 17:19:17 +08:00
FRAME_POP
ret
crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes Update the ARMv8 Crypto Extensions and the plain NEON AES implementations in CBC and CTR modes to return the next IV back to the skcipher API client. This is necessary for chaining to work correctly. Note that for CTR, this is only done if the request is a round multiple of the block size, since otherwise, chaining is impossible anyway. Cc: <stable@vger.kernel.org> # v3.16+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-01-17 21:46:29 +08:00
.Lctrcarry:
umov x7, v4.d[0] /* load upper word of ctr */
rev x7, x7 /* ... to handle the carry */
add x7, x7, #1
rev x7, x7
ins v4.d[0], x7
b .Lctrcarrydone
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 17:19:17 +08:00
AES_ENDPROC(aes_ctr_encrypt)
.ltorg
/*
* aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
* int blocks, u8 const rk2[], u8 iv[], int first)
* aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
* int blocks, u8 const rk2[], u8 iv[], int first)
*/
.macro next_tweak, out, in, const, tmp
sshr \tmp\().2d, \in\().2d, #63
and \tmp\().16b, \tmp\().16b, \const\().16b
add \out\().2d, \in\().2d, \in\().2d
ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
eor \out\().16b, \out\().16b, \tmp\().16b
.endm
.Lxts_mul_x:
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>
2016-10-12 02:15:19 +08:00
CPU_LE( .quad 1, 0x87 )
CPU_BE( .quad 0x87, 1 )
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 17:19:17 +08:00
AES_ENTRY(aes_xts_encrypt)
FRAME_PUSH
cbz w7, .LxtsencloopNx
ld1 {v4.16b}, [x6]
enc_prepare w3, x5, x6
encrypt_block v4, w3, x5, x6, w7 /* first tweak */
enc_switch_key w3, x2, x6
ldr q7, .Lxts_mul_x
b .LxtsencNx
.LxtsencloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsencNx:
#if INTERLEAVE >= 2
subs w4, w4, #INTERLEAVE
bmi .Lxtsenc1x
#if INTERLEAVE == 2
ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
do_encrypt_block2x
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
st1 {v0.16b-v1.16b}, [x0], #32
cbz w4, .LxtsencoutNx
next_tweak v4, v5, v7, v8
b .LxtsencNx
.LxtsencoutNx:
mov v4.16b, v5.16b
b .Lxtsencout
#else
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
next_tweak v6, v5, v7, v8
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
next_tweak v7, v6, v7, v8
eor v3.16b, v3.16b, v7.16b
do_encrypt_block4x
eor v3.16b, v3.16b, v7.16b
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v7.16b
cbz w4, .Lxtsencout
b .LxtsencloopNx
#endif
.Lxtsenc1x:
adds w4, w4, #INTERLEAVE
beq .Lxtsencout
#endif
.Lxtsencloop:
ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
encrypt_block v0, w3, x2, x6, w7
eor v0.16b, v0.16b, v4.16b
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
beq .Lxtsencout
next_tweak v4, v4, v7, v8
b .Lxtsencloop
.Lxtsencout:
FRAME_POP
ret
AES_ENDPROC(aes_xts_encrypt)
AES_ENTRY(aes_xts_decrypt)
FRAME_PUSH
cbz w7, .LxtsdecloopNx
ld1 {v4.16b}, [x6]
enc_prepare w3, x5, x6
encrypt_block v4, w3, x5, x6, w7 /* first tweak */
dec_prepare w3, x2, x6
ldr q7, .Lxts_mul_x
b .LxtsdecNx
.LxtsdecloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsdecNx:
#if INTERLEAVE >= 2
subs w4, w4, #INTERLEAVE
bmi .Lxtsdec1x
#if INTERLEAVE == 2
ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
do_decrypt_block2x
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
st1 {v0.16b-v1.16b}, [x0], #32
cbz w4, .LxtsdecoutNx
next_tweak v4, v5, v7, v8
b .LxtsdecNx
.LxtsdecoutNx:
mov v4.16b, v5.16b
b .Lxtsdecout
#else
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
next_tweak v6, v5, v7, v8
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
next_tweak v7, v6, v7, v8
eor v3.16b, v3.16b, v7.16b
do_decrypt_block4x
eor v3.16b, v3.16b, v7.16b
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v7.16b
cbz w4, .Lxtsdecout
b .LxtsdecloopNx
#endif
.Lxtsdec1x:
adds w4, w4, #INTERLEAVE
beq .Lxtsdecout
#endif
.Lxtsdecloop:
ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
decrypt_block v0, w3, x2, x6, w7
eor v0.16b, v0.16b, v4.16b
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
beq .Lxtsdecout
next_tweak v4, v4, v7, v8
b .Lxtsdecloop
.Lxtsdecout:
FRAME_POP
ret
AES_ENDPROC(aes_xts_decrypt)
crypto: arm64/aes - add NEON/Crypto Extensions CBCMAC/CMAC/XCBC driver On ARMv8 implementations that do not support the Crypto Extensions, such as the Raspberry Pi 3, the CCM driver falls back to the generic table based AES implementation to perform the MAC part of the algorithm, which is slow and not time invariant. So add a CBCMAC implementation to the shared glue code between NEON AES and Crypto Extensions AES, so that it can be used instead now that the CCM driver has been updated to look for CBCMAC implementations other than the one it supplies itself. Also, given how these algorithms mostly only differ in the way the key handling and the final encryption are implemented, expose CMAC and XCBC algorithms as well based on the same core update code. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-02-03 22:49:37 +08:00
/*
* aes_mac_update(u8 const in[], u32 const rk[], int rounds,
* int blocks, u8 dg[], int enc_before, int enc_after)
*/
AES_ENTRY(aes_mac_update)
ld1 {v0.16b}, [x4] /* get dg */
enc_prepare w2, x1, x7
cbnz w5, .Lmacenc
.Lmacloop:
cbz w3, .Lmacout
ld1 {v1.16b}, [x0], #16 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */
subs w3, w3, #1
csinv x5, x6, xzr, eq
cbz w5, .Lmacout
.Lmacenc:
encrypt_block v0, w2, x1, x7, w8
b .Lmacloop
.Lmacout:
st1 {v0.16b}, [x4] /* return dg */
ret
AES_ENDPROC(aes_mac_update)