kernel-ark/arch/arm64/crypto/ghash-ce-core.S
Ard Biesheuvel 22240df7ac crypto: arm64/ghash-ce - implement 4-way aggregation
Enhance the GHASH implementation that uses 64-bit polynomial
multiplication by adding support for 4-way aggregation. This
more than doubles the performance, from 2.4 cycles per byte
to 1.1 cpb on Cortex-A53.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-08-07 17:51:40 +08:00

579 lines
12 KiB
ArmAsm

/*
* Accelerated GHASH implementation with ARMv8 PMULL instructions.
*
* Copyright (C) 2014 - 2018 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>
SHASH .req v0
SHASH2 .req v1
T1 .req v2
T2 .req v3
MASK .req v4
XL .req v5
XM .req v6
XH .req v7
IN1 .req v7
k00_16 .req v8
k32_48 .req v9
t3 .req v10
t4 .req v11
t5 .req v12
t6 .req v13
t7 .req v14
t8 .req v15
t9 .req v16
perm1 .req v17
perm2 .req v18
perm3 .req v19
sh1 .req v20
sh2 .req v21
sh3 .req v22
sh4 .req v23
ss1 .req v24
ss2 .req v25
ss3 .req v26
ss4 .req v27
XL2 .req v8
XM2 .req v9
XH2 .req v10
XL3 .req v11
XM3 .req v12
XH3 .req v13
TT3 .req v14
TT4 .req v15
HH .req v16
HH3 .req v17
HH4 .req v18
HH34 .req v19
.text
.arch armv8-a+crypto
.macro __pmull_p64, rd, rn, rm
pmull \rd\().1q, \rn\().1d, \rm\().1d
.endm
.macro __pmull2_p64, rd, rn, rm
pmull2 \rd\().1q, \rn\().2d, \rm\().2d
.endm
.macro __pmull_p8, rq, ad, bd
ext t3.8b, \ad\().8b, \ad\().8b, #1 // A1
ext t5.8b, \ad\().8b, \ad\().8b, #2 // A2
ext t7.8b, \ad\().8b, \ad\().8b, #3 // A3
__pmull_p8_\bd \rq, \ad
.endm
.macro __pmull2_p8, rq, ad, bd
tbl t3.16b, {\ad\().16b}, perm1.16b // A1
tbl t5.16b, {\ad\().16b}, perm2.16b // A2
tbl t7.16b, {\ad\().16b}, perm3.16b // A3
__pmull2_p8_\bd \rq, \ad
.endm
.macro __pmull_p8_SHASH, rq, ad
__pmull_p8_tail \rq, \ad\().8b, SHASH.8b, 8b,, sh1, sh2, sh3, sh4
.endm
.macro __pmull_p8_SHASH2, rq, ad
__pmull_p8_tail \rq, \ad\().8b, SHASH2.8b, 8b,, ss1, ss2, ss3, ss4
.endm
.macro __pmull2_p8_SHASH, rq, ad
__pmull_p8_tail \rq, \ad\().16b, SHASH.16b, 16b, 2, sh1, sh2, sh3, sh4
.endm
.macro __pmull_p8_tail, rq, ad, bd, nb, t, b1, b2, b3, b4
pmull\t t3.8h, t3.\nb, \bd // F = A1*B
pmull\t t4.8h, \ad, \b1\().\nb // E = A*B1
pmull\t t5.8h, t5.\nb, \bd // H = A2*B
pmull\t t6.8h, \ad, \b2\().\nb // G = A*B2
pmull\t t7.8h, t7.\nb, \bd // J = A3*B
pmull\t t8.8h, \ad, \b3\().\nb // I = A*B3
pmull\t t9.8h, \ad, \b4\().\nb // K = A*B4
pmull\t \rq\().8h, \ad, \bd // D = A*B
eor t3.16b, t3.16b, t4.16b // L = E + F
eor t5.16b, t5.16b, t6.16b // M = G + H
eor t7.16b, t7.16b, t8.16b // N = I + J
uzp1 t4.2d, t3.2d, t5.2d
uzp2 t3.2d, t3.2d, t5.2d
uzp1 t6.2d, t7.2d, t9.2d
uzp2 t7.2d, t7.2d, t9.2d
// t3 = (L) (P0 + P1) << 8
// t5 = (M) (P2 + P3) << 16
eor t4.16b, t4.16b, t3.16b
and t3.16b, t3.16b, k32_48.16b
// t7 = (N) (P4 + P5) << 24
// t9 = (K) (P6 + P7) << 32
eor t6.16b, t6.16b, t7.16b
and t7.16b, t7.16b, k00_16.16b
eor t4.16b, t4.16b, t3.16b
eor t6.16b, t6.16b, t7.16b
zip2 t5.2d, t4.2d, t3.2d
zip1 t3.2d, t4.2d, t3.2d
zip2 t9.2d, t6.2d, t7.2d
zip1 t7.2d, t6.2d, t7.2d
ext t3.16b, t3.16b, t3.16b, #15
ext t5.16b, t5.16b, t5.16b, #14
ext t7.16b, t7.16b, t7.16b, #13
ext t9.16b, t9.16b, t9.16b, #12
eor t3.16b, t3.16b, t5.16b
eor t7.16b, t7.16b, t9.16b
eor \rq\().16b, \rq\().16b, t3.16b
eor \rq\().16b, \rq\().16b, t7.16b
.endm
.macro __pmull_pre_p64
add x8, x3, #16
ld1 {HH.2d-HH4.2d}, [x8]
trn1 SHASH2.2d, SHASH.2d, HH.2d
trn2 T1.2d, SHASH.2d, HH.2d
eor SHASH2.16b, SHASH2.16b, T1.16b
trn1 HH34.2d, HH3.2d, HH4.2d
trn2 T1.2d, HH3.2d, HH4.2d
eor HH34.16b, HH34.16b, T1.16b
movi MASK.16b, #0xe1
shl MASK.2d, MASK.2d, #57
.endm
.macro __pmull_pre_p8
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
eor SHASH2.16b, SHASH2.16b, SHASH.16b
// k00_16 := 0x0000000000000000_000000000000ffff
// k32_48 := 0x00000000ffffffff_0000ffffffffffff
movi k32_48.2d, #0xffffffff
mov k32_48.h[2], k32_48.h[0]
ushr k00_16.2d, k32_48.2d, #32
// prepare the permutation vectors
mov_q x5, 0x080f0e0d0c0b0a09
movi T1.8b, #8
dup perm1.2d, x5
eor perm1.16b, perm1.16b, T1.16b
ushr perm2.2d, perm1.2d, #8
ushr perm3.2d, perm1.2d, #16
ushr T1.2d, perm1.2d, #24
sli perm2.2d, perm1.2d, #56
sli perm3.2d, perm1.2d, #48
sli T1.2d, perm1.2d, #40
// precompute loop invariants
tbl sh1.16b, {SHASH.16b}, perm1.16b
tbl sh2.16b, {SHASH.16b}, perm2.16b
tbl sh3.16b, {SHASH.16b}, perm3.16b
tbl sh4.16b, {SHASH.16b}, T1.16b
ext ss1.8b, SHASH2.8b, SHASH2.8b, #1
ext ss2.8b, SHASH2.8b, SHASH2.8b, #2
ext ss3.8b, SHASH2.8b, SHASH2.8b, #3
ext ss4.8b, SHASH2.8b, SHASH2.8b, #4
.endm
//
// PMULL (64x64->128) based reduction for CPUs that can do
// it in a single instruction.
//
.macro __pmull_reduce_p64
pmull T2.1q, XL.1d, MASK.1d
eor XM.16b, XM.16b, T1.16b
mov XH.d[0], XM.d[1]
mov XM.d[1], XL.d[0]
eor XL.16b, XM.16b, T2.16b
ext T2.16b, XL.16b, XL.16b, #8
pmull XL.1q, XL.1d, MASK.1d
.endm
//
// Alternative reduction for CPUs that lack support for the
// 64x64->128 PMULL instruction
//
.macro __pmull_reduce_p8
eor XM.16b, XM.16b, T1.16b
mov XL.d[1], XM.d[0]
mov XH.d[0], XM.d[1]
shl T1.2d, XL.2d, #57
shl T2.2d, XL.2d, #62
eor T2.16b, T2.16b, T1.16b
shl T1.2d, XL.2d, #63
eor T2.16b, T2.16b, T1.16b
ext T1.16b, XL.16b, XH.16b, #8
eor T2.16b, T2.16b, T1.16b
mov XL.d[1], T2.d[0]
mov XH.d[0], T2.d[1]
ushr T2.2d, XL.2d, #1
eor XH.16b, XH.16b, XL.16b
eor XL.16b, XL.16b, T2.16b
ushr T2.2d, T2.2d, #6
ushr XL.2d, XL.2d, #1
.endm
.macro __pmull_ghash, pn
ld1 {SHASH.2d}, [x3]
ld1 {XL.2d}, [x1]
__pmull_pre_\pn
/* do the head block first, if supplied */
cbz x4, 0f
ld1 {T1.2d}, [x4]
mov x4, xzr
b 3f
0: .ifc \pn, p64
tbnz w0, #0, 2f // skip until #blocks is a
tbnz w0, #1, 2f // round multiple of 4
1: ld1 {XM3.16b-TT4.16b}, [x2], #64
sub w0, w0, #4
rev64 T1.16b, XM3.16b
rev64 T2.16b, XH3.16b
rev64 TT4.16b, TT4.16b
rev64 TT3.16b, TT3.16b
ext IN1.16b, TT4.16b, TT4.16b, #8
ext XL3.16b, TT3.16b, TT3.16b, #8
eor TT4.16b, TT4.16b, IN1.16b
pmull2 XH2.1q, SHASH.2d, IN1.2d // a1 * b1
pmull XL2.1q, SHASH.1d, IN1.1d // a0 * b0
pmull XM2.1q, SHASH2.1d, TT4.1d // (a1 + a0)(b1 + b0)
eor TT3.16b, TT3.16b, XL3.16b
pmull2 XH3.1q, HH.2d, XL3.2d // a1 * b1
pmull XL3.1q, HH.1d, XL3.1d // a0 * b0
pmull2 XM3.1q, SHASH2.2d, TT3.2d // (a1 + a0)(b1 + b0)
ext IN1.16b, T2.16b, T2.16b, #8
eor XL2.16b, XL2.16b, XL3.16b
eor XH2.16b, XH2.16b, XH3.16b
eor XM2.16b, XM2.16b, XM3.16b
eor T2.16b, T2.16b, IN1.16b
pmull2 XH3.1q, HH3.2d, IN1.2d // a1 * b1
pmull XL3.1q, HH3.1d, IN1.1d // a0 * b0
pmull XM3.1q, HH34.1d, T2.1d // (a1 + a0)(b1 + b0)
eor XL2.16b, XL2.16b, XL3.16b
eor XH2.16b, XH2.16b, XH3.16b
eor XM2.16b, XM2.16b, XM3.16b
ext IN1.16b, T1.16b, T1.16b, #8
ext TT3.16b, XL.16b, XL.16b, #8
eor XL.16b, XL.16b, IN1.16b
eor T1.16b, T1.16b, TT3.16b
pmull2 XH.1q, HH4.2d, XL.2d // a1 * b1
eor T1.16b, T1.16b, XL.16b
pmull XL.1q, HH4.1d, XL.1d // a0 * b0
pmull2 XM.1q, HH34.2d, T1.2d // (a1 + a0)(b1 + b0)
eor XL.16b, XL.16b, XL2.16b
eor XH.16b, XH.16b, XH2.16b
eor XM.16b, XM.16b, XM2.16b
eor T2.16b, XL.16b, XH.16b
ext T1.16b, XL.16b, XH.16b, #8
eor XM.16b, XM.16b, T2.16b
__pmull_reduce_p64
eor T2.16b, T2.16b, XH.16b
eor XL.16b, XL.16b, T2.16b
cbz w0, 5f
b 1b
.endif
2: ld1 {T1.2d}, [x2], #16
sub w0, w0, #1
3: /* multiply XL by SHASH in GF(2^128) */
CPU_LE( rev64 T1.16b, T1.16b )
ext T2.16b, XL.16b, XL.16b, #8
ext IN1.16b, T1.16b, T1.16b, #8
eor T1.16b, T1.16b, T2.16b
eor XL.16b, XL.16b, IN1.16b
__pmull2_\pn XH, XL, SHASH // a1 * b1
eor T1.16b, T1.16b, XL.16b
__pmull_\pn XL, XL, SHASH // a0 * b0
__pmull_\pn XM, T1, SHASH2 // (a1 + a0)(b1 + b0)
4: eor T2.16b, XL.16b, XH.16b
ext T1.16b, XL.16b, XH.16b, #8
eor XM.16b, XM.16b, T2.16b
__pmull_reduce_\pn
eor T2.16b, T2.16b, XH.16b
eor XL.16b, XL.16b, T2.16b
cbnz w0, 0b
5: st1 {XL.2d}, [x1]
ret
.endm
/*
* void pmull_ghash_update(int blocks, u64 dg[], const char *src,
* struct ghash_key const *k, const char *head)
*/
ENTRY(pmull_ghash_update_p64)
__pmull_ghash p64
ENDPROC(pmull_ghash_update_p64)
ENTRY(pmull_ghash_update_p8)
__pmull_ghash p8
ENDPROC(pmull_ghash_update_p8)
KS0 .req v12
KS1 .req v13
INP0 .req v14
INP1 .req v15
.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
.macro enc_round, state, key
aese \state\().16b, \key\().16b
aesmc \state\().16b, \state\().16b
.endm
.macro enc_block, state, rounds
cmp \rounds, #12
b.lo 2222f /* 128 bits */
b.eq 1111f /* 192 bits */
enc_round \state, v17
enc_round \state, v18
1111: enc_round \state, v19
enc_round \state, v20
2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29
enc_round \state, \key
.endr
aese \state\().16b, v30.16b
eor \state\().16b, \state\().16b, v31.16b
.endm
.macro pmull_gcm_do_crypt, enc
ld1 {SHASH.2d}, [x4], #16
ld1 {HH.2d}, [x4]
ld1 {XL.2d}, [x1]
ldr x8, [x5, #8] // load lower counter
movi MASK.16b, #0xe1
trn1 SHASH2.2d, SHASH.2d, HH.2d
trn2 T1.2d, SHASH.2d, HH.2d
CPU_LE( rev x8, x8 )
shl MASK.2d, MASK.2d, #57
eor SHASH2.16b, SHASH2.16b, T1.16b
.if \enc == 1
ldr x10, [sp]
ld1 {KS0.16b-KS1.16b}, [x10]
.endif
cbnz x6, 4f
0: ld1 {INP0.16b-INP1.16b}, [x3], #32
rev x9, x8
add x11, x8, #1
add x8, x8, #2
.if \enc == 1
eor INP0.16b, INP0.16b, KS0.16b // encrypt input
eor INP1.16b, INP1.16b, KS1.16b
.endif
ld1 {KS0.8b}, [x5] // load upper counter
rev x11, x11
sub w0, w0, #2
mov KS1.8b, KS0.8b
ins KS0.d[1], x9 // set lower counter
ins KS1.d[1], x11
rev64 T1.16b, INP1.16b
cmp w7, #12
b.ge 2f // AES-192/256?
1: enc_round KS0, v21
ext IN1.16b, T1.16b, T1.16b, #8
enc_round KS1, v21
pmull2 XH2.1q, SHASH.2d, IN1.2d // a1 * b1
enc_round KS0, v22
eor T1.16b, T1.16b, IN1.16b
enc_round KS1, v22
pmull XL2.1q, SHASH.1d, IN1.1d // a0 * b0
enc_round KS0, v23
pmull XM2.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0)
enc_round KS1, v23
rev64 T1.16b, INP0.16b
ext T2.16b, XL.16b, XL.16b, #8
enc_round KS0, v24
ext IN1.16b, T1.16b, T1.16b, #8
eor T1.16b, T1.16b, T2.16b
enc_round KS1, v24
eor XL.16b, XL.16b, IN1.16b
enc_round KS0, v25
eor T1.16b, T1.16b, XL.16b
enc_round KS1, v25
pmull2 XH.1q, HH.2d, XL.2d // a1 * b1
enc_round KS0, v26
pmull XL.1q, HH.1d, XL.1d // a0 * b0
enc_round KS1, v26
pmull2 XM.1q, SHASH2.2d, T1.2d // (a1 + a0)(b1 + b0)
enc_round KS0, v27
eor XL.16b, XL.16b, XL2.16b
eor XH.16b, XH.16b, XH2.16b
enc_round KS1, v27
eor XM.16b, XM.16b, XM2.16b
ext T1.16b, XL.16b, XH.16b, #8
enc_round KS0, v28
eor T2.16b, XL.16b, XH.16b
eor XM.16b, XM.16b, T1.16b
enc_round KS1, v28
eor XM.16b, XM.16b, T2.16b
enc_round KS0, v29
pmull T2.1q, XL.1d, MASK.1d
enc_round KS1, v29
mov XH.d[0], XM.d[1]
mov XM.d[1], XL.d[0]
aese KS0.16b, v30.16b
eor XL.16b, XM.16b, T2.16b
aese KS1.16b, v30.16b
ext T2.16b, XL.16b, XL.16b, #8
eor KS0.16b, KS0.16b, v31.16b
pmull XL.1q, XL.1d, MASK.1d
eor T2.16b, T2.16b, XH.16b
eor KS1.16b, KS1.16b, v31.16b
eor XL.16b, XL.16b, T2.16b
.if \enc == 0
eor INP0.16b, INP0.16b, KS0.16b
eor INP1.16b, INP1.16b, KS1.16b
.endif
st1 {INP0.16b-INP1.16b}, [x2], #32
cbnz w0, 0b
CPU_LE( rev x8, x8 )
st1 {XL.2d}, [x1]
str x8, [x5, #8] // store lower counter
.if \enc == 1
st1 {KS0.16b-KS1.16b}, [x10]
.endif
ret
2: b.eq 3f // AES-192?
enc_round KS0, v17
enc_round KS1, v17
enc_round KS0, v18
enc_round KS1, v18
3: enc_round KS0, v19
enc_round KS1, v19
enc_round KS0, v20
enc_round KS1, v20
b 1b
4: load_round_keys w7, x6
b 0b
.endm
/*
* void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
* struct ghash_key const *k, u8 ctr[],
* int rounds, u8 ks[])
*/
ENTRY(pmull_gcm_encrypt)
pmull_gcm_do_crypt 1
ENDPROC(pmull_gcm_encrypt)
/*
* void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
* struct ghash_key const *k, u8 ctr[],
* int rounds)
*/
ENTRY(pmull_gcm_decrypt)
pmull_gcm_do_crypt 0
ENDPROC(pmull_gcm_decrypt)
/*
* void pmull_gcm_encrypt_block(u8 dst[], u8 src[], u8 rk[], int rounds)
*/
ENTRY(pmull_gcm_encrypt_block)
cbz x2, 0f
load_round_keys w3, x2
0: ld1 {v0.16b}, [x1]
enc_block v0, w3
st1 {v0.16b}, [x0]
ret
ENDPROC(pmull_gcm_encrypt_block)