linux_dsm_epyc7002/arch/arm64/crypto/aes-modes.S
Ard Biesheuvel 870c163a0e crypto: arm64/aes-blk - add 4 way interleave to CBC-MAC encrypt path
CBC MAC is strictly sequential, and so the current AES code simply
processes the input one block at a time. However, we are about to add
yield support, which adds a bit of overhead, and which we prefer to
align with other modes in terms of granularity (i.e., it is better to
have all routines yield every 64 bytes and not have an exception for
CBC MAC which yields every 16 bytes)

So unroll the loop by 4. We still cannot perform the AES algorithm in
parallel, but we can at least merge the loads and stores.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-03-16 23:35:58 +08:00

436 lines
9.9 KiB
ArmAsm

/*
* linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
*
* 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.
*/
/* included by aes-ce.S and aes-neon.S */
.text
.align 4
aes_encrypt_block4x:
encrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7
ret
ENDPROC(aes_encrypt_block4x)
aes_decrypt_block4x:
decrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7
ret
ENDPROC(aes_decrypt_block4x)
/*
* aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks)
* aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks)
*/
AES_ENTRY(aes_ecb_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
enc_prepare w3, x2, x5
.LecbencloopNx:
subs w4, w4, #4
bmi .Lecbenc1x
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
bl aes_encrypt_block4x
st1 {v0.16b-v3.16b}, [x0], #64
b .LecbencloopNx
.Lecbenc1x:
adds w4, w4, #4
beq .Lecbencout
.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:
ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_ecb_encrypt)
AES_ENTRY(aes_ecb_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
dec_prepare w3, x2, x5
.LecbdecloopNx:
subs w4, w4, #4
bmi .Lecbdec1x
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
bl aes_decrypt_block4x
st1 {v0.16b-v3.16b}, [x0], #64
b .LecbdecloopNx
.Lecbdec1x:
adds w4, w4, #4
beq .Lecbdecout
.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:
ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_ecb_decrypt)
/*
* aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
* aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
*/
AES_ENTRY(aes_cbc_encrypt)
ld1 {v4.16b}, [x5] /* get iv */
enc_prepare w3, x2, x6
.Lcbcencloop4x:
subs w4, w4, #4
bmi .Lcbcenc1x
ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
eor v0.16b, v0.16b, v4.16b /* ..and xor with iv */
encrypt_block v0, w3, x2, x6, w7
eor v1.16b, v1.16b, v0.16b
encrypt_block v1, w3, x2, x6, w7
eor v2.16b, v2.16b, v1.16b
encrypt_block v2, w3, x2, x6, w7
eor v3.16b, v3.16b, v2.16b
encrypt_block v3, w3, x2, x6, w7
st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v3.16b
b .Lcbcencloop4x
.Lcbcenc1x:
adds w4, w4, #4
beq .Lcbcencout
.Lcbcencloop:
ld1 {v0.16b}, [x1], #16 /* get next pt block */
eor v4.16b, v4.16b, v0.16b /* ..and xor with iv */
encrypt_block v4, w3, x2, x6, w7
st1 {v4.16b}, [x0], #16
subs w4, w4, #1
bne .Lcbcencloop
.Lcbcencout:
st1 {v4.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_encrypt)
AES_ENTRY(aes_cbc_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
ld1 {v7.16b}, [x5] /* get iv */
dec_prepare w3, x2, x6
.LcbcdecloopNx:
subs w4, w4, #4
bmi .Lcbcdec1x
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
bl aes_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
b .LcbcdecloopNx
.Lcbcdec1x:
adds w4, w4, #4
beq .Lcbcdecout
.Lcbcdecloop:
ld1 {v1.16b}, [x1], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
decrypt_block v0, w3, x2, x6, w7
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:
st1 {v7.16b}, [x5] /* return iv */
ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_cbc_decrypt)
/*
* aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 ctr[])
*/
AES_ENTRY(aes_ctr_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
enc_prepare w3, x2, x6
ld1 {v4.16b}, [x5]
umov x6, v4.d[1] /* keep swabbed ctr in reg */
rev x6, x6
cmn w6, w4 /* 32 bit overflow? */
bcs .Lctrloop
.LctrloopNx:
subs w4, w4, #4
bmi .Lctr1x
ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
dup v7.4s, w6
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 */
bl aes_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
add x6, x6, #4
rev x7, x6
ins v4.d[1], x7
cbz w4, .Lctrout
b .LctrloopNx
.Lctr1x:
adds w4, w4, #4
beq .Lctrout
.Lctrloop:
mov v0.16b, v4.16b
encrypt_block v0, w3, x2, x8, w7
adds x6, x6, #1 /* increment BE ctr */
rev x7, x6
ins v4.d[1], x7
bcs .Lctrcarry /* overflow? */
.Lctrcarrydone:
subs w4, w4, #1
bmi .Lctrtailblock /* blocks <0 means tail block */
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
bne .Lctrloop
.Lctrout:
st1 {v4.16b}, [x5] /* return next CTR value */
ldp x29, x30, [sp], #16
ret
.Lctrtailblock:
st1 {v0.16b}, [x0]
ldp x29, x30, [sp], #16
ret
.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
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:
CPU_LE( .quad 1, 0x87 )
CPU_BE( .quad 0x87, 1 )
AES_ENTRY(aes_xts_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
ld1 {v4.16b}, [x6]
cbz w7, .Lxtsencnotfirst
enc_prepare w3, x5, x8
encrypt_block v4, w3, x5, x8, w7 /* first tweak */
enc_switch_key w3, x2, x8
ldr q7, .Lxts_mul_x
b .LxtsencNx
.Lxtsencnotfirst:
enc_prepare w3, x2, x8
.LxtsencloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsencNx:
subs w4, w4, #4
bmi .Lxtsenc1x
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
bl aes_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
.Lxtsenc1x:
adds w4, w4, #4
beq .Lxtsencout
.Lxtsencloop:
ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
encrypt_block v0, w3, x2, x8, 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:
st1 {v4.16b}, [x6]
ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_xts_encrypt)
AES_ENTRY(aes_xts_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
ld1 {v4.16b}, [x6]
cbz w7, .Lxtsdecnotfirst
enc_prepare w3, x5, x8
encrypt_block v4, w3, x5, x8, w7 /* first tweak */
dec_prepare w3, x2, x8
ldr q7, .Lxts_mul_x
b .LxtsdecNx
.Lxtsdecnotfirst:
dec_prepare w3, x2, x8
.LxtsdecloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsdecNx:
subs w4, w4, #4
bmi .Lxtsdec1x
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
bl aes_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
.Lxtsdec1x:
adds w4, w4, #4
beq .Lxtsdecout
.Lxtsdecloop:
ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
decrypt_block v0, w3, x2, x8, 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:
st1 {v4.16b}, [x6]
ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_xts_decrypt)
/*
* 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
cbz w5, .Lmacloop4x
encrypt_block v0, w2, x1, x7, w8
.Lmacloop4x:
subs w3, w3, #4
bmi .Lmac1x
ld1 {v1.16b-v4.16b}, [x0], #64 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */
encrypt_block v0, w2, x1, x7, w8
eor v0.16b, v0.16b, v2.16b
encrypt_block v0, w2, x1, x7, w8
eor v0.16b, v0.16b, v3.16b
encrypt_block v0, w2, x1, x7, w8
eor v0.16b, v0.16b, v4.16b
cmp w3, wzr
csinv x5, x6, xzr, eq
cbz w5, .Lmacout
encrypt_block v0, w2, x1, x7, w8
b .Lmacloop4x
.Lmac1x:
add w3, w3, #4
.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
encrypt_block v0, w2, x1, x7, w8
b .Lmacloop
.Lmacout:
st1 {v0.16b}, [x4] /* return dg */
ret
AES_ENDPROC(aes_mac_update)