763 lines
17 KiB
ArmAsm
763 lines
17 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Accelerated GHASH implementation with ARMv8 PMULL instructions.
|
|
*
|
|
* Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
|
|
SHASH .req v0
|
|
SHASH2 .req v1
|
|
T1 .req v2
|
|
T2 .req v3
|
|
MASK .req v4
|
|
XM .req v5
|
|
XL .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)
|
|
*/
|
|
SYM_FUNC_START(pmull_ghash_update_p64)
|
|
__pmull_ghash p64
|
|
SYM_FUNC_END(pmull_ghash_update_p64)
|
|
|
|
SYM_FUNC_START(pmull_ghash_update_p8)
|
|
__pmull_ghash p8
|
|
SYM_FUNC_END(pmull_ghash_update_p8)
|
|
|
|
KS0 .req v8
|
|
KS1 .req v9
|
|
KS2 .req v10
|
|
KS3 .req v11
|
|
|
|
INP0 .req v21
|
|
INP1 .req v22
|
|
INP2 .req v23
|
|
INP3 .req v24
|
|
|
|
K0 .req v25
|
|
K1 .req v26
|
|
K2 .req v27
|
|
K3 .req v28
|
|
K4 .req v12
|
|
K5 .req v13
|
|
K6 .req v4
|
|
K7 .req v5
|
|
K8 .req v14
|
|
K9 .req v15
|
|
KK .req v29
|
|
KL .req v30
|
|
KM .req v31
|
|
|
|
.macro load_round_keys, rounds, rk, tmp
|
|
add \tmp, \rk, #64
|
|
ld1 {K0.4s-K3.4s}, [\rk]
|
|
ld1 {K4.4s-K5.4s}, [\tmp]
|
|
add \tmp, \rk, \rounds, lsl #4
|
|
sub \tmp, \tmp, #32
|
|
ld1 {KK.4s-KM.4s}, [\tmp]
|
|
.endm
|
|
|
|
.macro enc_round, state, key
|
|
aese \state\().16b, \key\().16b
|
|
aesmc \state\().16b, \state\().16b
|
|
.endm
|
|
|
|
.macro enc_qround, s0, s1, s2, s3, key
|
|
enc_round \s0, \key
|
|
enc_round \s1, \key
|
|
enc_round \s2, \key
|
|
enc_round \s3, \key
|
|
.endm
|
|
|
|
.macro enc_block, state, rounds, rk, tmp
|
|
add \tmp, \rk, #96
|
|
ld1 {K6.4s-K7.4s}, [\tmp], #32
|
|
.irp key, K0, K1, K2, K3, K4 K5
|
|
enc_round \state, \key
|
|
.endr
|
|
|
|
tbnz \rounds, #2, .Lnot128_\@
|
|
.Lout256_\@:
|
|
enc_round \state, K6
|
|
enc_round \state, K7
|
|
|
|
.Lout192_\@:
|
|
enc_round \state, KK
|
|
aese \state\().16b, KL.16b
|
|
eor \state\().16b, \state\().16b, KM.16b
|
|
|
|
.subsection 1
|
|
.Lnot128_\@:
|
|
ld1 {K8.4s-K9.4s}, [\tmp], #32
|
|
enc_round \state, K6
|
|
enc_round \state, K7
|
|
ld1 {K6.4s-K7.4s}, [\tmp]
|
|
enc_round \state, K8
|
|
enc_round \state, K9
|
|
tbz \rounds, #1, .Lout192_\@
|
|
b .Lout256_\@
|
|
.previous
|
|
.endm
|
|
|
|
.align 6
|
|
.macro pmull_gcm_do_crypt, enc
|
|
stp x29, x30, [sp, #-32]!
|
|
mov x29, sp
|
|
str x19, [sp, #24]
|
|
|
|
load_round_keys x7, x6, x8
|
|
|
|
ld1 {SHASH.2d}, [x3], #16
|
|
ld1 {HH.2d-HH4.2d}, [x3]
|
|
|
|
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
|
|
|
|
ld1 {XL.2d}, [x4]
|
|
|
|
cbz x0, 3f // tag only?
|
|
|
|
ldr w8, [x5, #12] // load lower counter
|
|
CPU_LE( rev w8, w8 )
|
|
|
|
0: mov w9, #4 // max blocks per round
|
|
add x10, x0, #0xf
|
|
lsr x10, x10, #4 // remaining blocks
|
|
|
|
subs x0, x0, #64
|
|
csel w9, w10, w9, mi
|
|
add w8, w8, w9
|
|
|
|
bmi 1f
|
|
ld1 {INP0.16b-INP3.16b}, [x2], #64
|
|
.subsection 1
|
|
/*
|
|
* Populate the four input registers right to left with up to 63 bytes
|
|
* of data, using overlapping loads to avoid branches.
|
|
*
|
|
* INP0 INP1 INP2 INP3
|
|
* 1 byte | | | |x |
|
|
* 16 bytes | | | |xxxxxxxx|
|
|
* 17 bytes | | |xxxxxxxx|x |
|
|
* 47 bytes | |xxxxxxxx|xxxxxxxx|xxxxxxx |
|
|
* etc etc
|
|
*
|
|
* Note that this code may read up to 15 bytes before the start of
|
|
* the input. It is up to the calling code to ensure this is safe if
|
|
* this happens in the first iteration of the loop (i.e., when the
|
|
* input size is < 16 bytes)
|
|
*/
|
|
1: mov x15, #16
|
|
ands x19, x0, #0xf
|
|
csel x19, x19, x15, ne
|
|
adr_l x17, .Lpermute_table + 16
|
|
|
|
sub x11, x15, x19
|
|
add x12, x17, x11
|
|
sub x17, x17, x11
|
|
ld1 {T1.16b}, [x12]
|
|
sub x10, x1, x11
|
|
sub x11, x2, x11
|
|
|
|
cmp x0, #-16
|
|
csel x14, x15, xzr, gt
|
|
cmp x0, #-32
|
|
csel x15, x15, xzr, gt
|
|
cmp x0, #-48
|
|
csel x16, x19, xzr, gt
|
|
csel x1, x1, x10, gt
|
|
csel x2, x2, x11, gt
|
|
|
|
ld1 {INP0.16b}, [x2], x14
|
|
ld1 {INP1.16b}, [x2], x15
|
|
ld1 {INP2.16b}, [x2], x16
|
|
ld1 {INP3.16b}, [x2]
|
|
tbl INP3.16b, {INP3.16b}, T1.16b
|
|
b 2f
|
|
.previous
|
|
|
|
2: .if \enc == 0
|
|
bl pmull_gcm_ghash_4x
|
|
.endif
|
|
|
|
bl pmull_gcm_enc_4x
|
|
|
|
tbnz x0, #63, 6f
|
|
st1 {INP0.16b-INP3.16b}, [x1], #64
|
|
.if \enc == 1
|
|
bl pmull_gcm_ghash_4x
|
|
.endif
|
|
bne 0b
|
|
|
|
3: ldp x19, x10, [sp, #24]
|
|
cbz x10, 5f // output tag?
|
|
|
|
ld1 {INP3.16b}, [x10] // load lengths[]
|
|
mov w9, #1
|
|
bl pmull_gcm_ghash_4x
|
|
|
|
mov w11, #(0x1 << 24) // BE '1U'
|
|
ld1 {KS0.16b}, [x5]
|
|
mov KS0.s[3], w11
|
|
|
|
enc_block KS0, x7, x6, x12
|
|
|
|
ext XL.16b, XL.16b, XL.16b, #8
|
|
rev64 XL.16b, XL.16b
|
|
eor XL.16b, XL.16b, KS0.16b
|
|
st1 {XL.16b}, [x10] // store tag
|
|
|
|
4: ldp x29, x30, [sp], #32
|
|
ret
|
|
|
|
5:
|
|
CPU_LE( rev w8, w8 )
|
|
str w8, [x5, #12] // store lower counter
|
|
st1 {XL.2d}, [x4]
|
|
b 4b
|
|
|
|
6: ld1 {T1.16b-T2.16b}, [x17], #32 // permute vectors
|
|
sub x17, x17, x19, lsl #1
|
|
|
|
cmp w9, #1
|
|
beq 7f
|
|
.subsection 1
|
|
7: ld1 {INP2.16b}, [x1]
|
|
tbx INP2.16b, {INP3.16b}, T1.16b
|
|
mov INP3.16b, INP2.16b
|
|
b 8f
|
|
.previous
|
|
|
|
st1 {INP0.16b}, [x1], x14
|
|
st1 {INP1.16b}, [x1], x15
|
|
st1 {INP2.16b}, [x1], x16
|
|
tbl INP3.16b, {INP3.16b}, T1.16b
|
|
tbx INP3.16b, {INP2.16b}, T2.16b
|
|
8: st1 {INP3.16b}, [x1]
|
|
|
|
.if \enc == 1
|
|
ld1 {T1.16b}, [x17]
|
|
tbl INP3.16b, {INP3.16b}, T1.16b // clear non-data bits
|
|
bl pmull_gcm_ghash_4x
|
|
.endif
|
|
b 3b
|
|
.endm
|
|
|
|
/*
|
|
* void pmull_gcm_encrypt(int blocks, u8 dst[], const u8 src[],
|
|
* struct ghash_key const *k, u64 dg[], u8 ctr[],
|
|
* int rounds, u8 tag)
|
|
*/
|
|
SYM_FUNC_START(pmull_gcm_encrypt)
|
|
pmull_gcm_do_crypt 1
|
|
SYM_FUNC_END(pmull_gcm_encrypt)
|
|
|
|
/*
|
|
* void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[],
|
|
* struct ghash_key const *k, u64 dg[], u8 ctr[],
|
|
* int rounds, u8 tag)
|
|
*/
|
|
SYM_FUNC_START(pmull_gcm_decrypt)
|
|
pmull_gcm_do_crypt 0
|
|
SYM_FUNC_END(pmull_gcm_decrypt)
|
|
|
|
SYM_FUNC_START_LOCAL(pmull_gcm_ghash_4x)
|
|
movi MASK.16b, #0xe1
|
|
shl MASK.2d, MASK.2d, #57
|
|
|
|
rev64 T1.16b, INP0.16b
|
|
rev64 T2.16b, INP1.16b
|
|
rev64 TT3.16b, INP2.16b
|
|
rev64 TT4.16b, INP3.16b
|
|
|
|
ext XL.16b, XL.16b, XL.16b, #8
|
|
|
|
tbz w9, #2, 0f // <4 blocks?
|
|
.subsection 1
|
|
0: movi XH2.16b, #0
|
|
movi XM2.16b, #0
|
|
movi XL2.16b, #0
|
|
|
|
tbz w9, #0, 1f // 2 blocks?
|
|
tbz w9, #1, 2f // 1 block?
|
|
|
|
eor T2.16b, T2.16b, XL.16b
|
|
ext T1.16b, T2.16b, T2.16b, #8
|
|
b .Lgh3
|
|
|
|
1: eor TT3.16b, TT3.16b, XL.16b
|
|
ext T2.16b, TT3.16b, TT3.16b, #8
|
|
b .Lgh2
|
|
|
|
2: eor TT4.16b, TT4.16b, XL.16b
|
|
ext IN1.16b, TT4.16b, TT4.16b, #8
|
|
b .Lgh1
|
|
.previous
|
|
|
|
eor T1.16b, T1.16b, XL.16b
|
|
ext IN1.16b, T1.16b, T1.16b, #8
|
|
|
|
pmull2 XH2.1q, HH4.2d, IN1.2d // a1 * b1
|
|
eor T1.16b, T1.16b, IN1.16b
|
|
pmull XL2.1q, HH4.1d, IN1.1d // a0 * b0
|
|
pmull2 XM2.1q, HH34.2d, T1.2d // (a1 + a0)(b1 + b0)
|
|
|
|
ext T1.16b, T2.16b, T2.16b, #8
|
|
.Lgh3: eor T2.16b, T2.16b, T1.16b
|
|
pmull2 XH.1q, HH3.2d, T1.2d // a1 * b1
|
|
pmull XL.1q, HH3.1d, T1.1d // a0 * b0
|
|
pmull XM.1q, HH34.1d, T2.1d // (a1 + a0)(b1 + b0)
|
|
|
|
eor XH2.16b, XH2.16b, XH.16b
|
|
eor XL2.16b, XL2.16b, XL.16b
|
|
eor XM2.16b, XM2.16b, XM.16b
|
|
|
|
ext T2.16b, TT3.16b, TT3.16b, #8
|
|
.Lgh2: eor TT3.16b, TT3.16b, T2.16b
|
|
pmull2 XH.1q, HH.2d, T2.2d // a1 * b1
|
|
pmull XL.1q, HH.1d, T2.1d // a0 * b0
|
|
pmull2 XM.1q, SHASH2.2d, TT3.2d // (a1 + a0)(b1 + b0)
|
|
|
|
eor XH2.16b, XH2.16b, XH.16b
|
|
eor XL2.16b, XL2.16b, XL.16b
|
|
eor XM2.16b, XM2.16b, XM.16b
|
|
|
|
ext IN1.16b, TT4.16b, TT4.16b, #8
|
|
.Lgh1: eor TT4.16b, TT4.16b, IN1.16b
|
|
pmull XL.1q, SHASH.1d, IN1.1d // a0 * b0
|
|
pmull2 XH.1q, SHASH.2d, IN1.2d // a1 * b1
|
|
pmull XM.1q, SHASH2.1d, TT4.1d // (a1 + a0)(b1 + b0)
|
|
|
|
eor XH.16b, XH.16b, XH2.16b
|
|
eor XL.16b, XL.16b, XL2.16b
|
|
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
|
|
|
|
ret
|
|
SYM_FUNC_END(pmull_gcm_ghash_4x)
|
|
|
|
SYM_FUNC_START_LOCAL(pmull_gcm_enc_4x)
|
|
ld1 {KS0.16b}, [x5] // load upper counter
|
|
sub w10, w8, #4
|
|
sub w11, w8, #3
|
|
sub w12, w8, #2
|
|
sub w13, w8, #1
|
|
rev w10, w10
|
|
rev w11, w11
|
|
rev w12, w12
|
|
rev w13, w13
|
|
mov KS1.16b, KS0.16b
|
|
mov KS2.16b, KS0.16b
|
|
mov KS3.16b, KS0.16b
|
|
ins KS0.s[3], w10 // set lower counter
|
|
ins KS1.s[3], w11
|
|
ins KS2.s[3], w12
|
|
ins KS3.s[3], w13
|
|
|
|
add x10, x6, #96 // round key pointer
|
|
ld1 {K6.4s-K7.4s}, [x10], #32
|
|
.irp key, K0, K1, K2, K3, K4, K5
|
|
enc_qround KS0, KS1, KS2, KS3, \key
|
|
.endr
|
|
|
|
tbnz x7, #2, .Lnot128
|
|
.subsection 1
|
|
.Lnot128:
|
|
ld1 {K8.4s-K9.4s}, [x10], #32
|
|
.irp key, K6, K7
|
|
enc_qround KS0, KS1, KS2, KS3, \key
|
|
.endr
|
|
ld1 {K6.4s-K7.4s}, [x10]
|
|
.irp key, K8, K9
|
|
enc_qround KS0, KS1, KS2, KS3, \key
|
|
.endr
|
|
tbz x7, #1, .Lout192
|
|
b .Lout256
|
|
.previous
|
|
|
|
.Lout256:
|
|
.irp key, K6, K7
|
|
enc_qround KS0, KS1, KS2, KS3, \key
|
|
.endr
|
|
|
|
.Lout192:
|
|
enc_qround KS0, KS1, KS2, KS3, KK
|
|
|
|
aese KS0.16b, KL.16b
|
|
aese KS1.16b, KL.16b
|
|
aese KS2.16b, KL.16b
|
|
aese KS3.16b, KL.16b
|
|
|
|
eor KS0.16b, KS0.16b, KM.16b
|
|
eor KS1.16b, KS1.16b, KM.16b
|
|
eor KS2.16b, KS2.16b, KM.16b
|
|
eor KS3.16b, KS3.16b, KM.16b
|
|
|
|
eor INP0.16b, INP0.16b, KS0.16b
|
|
eor INP1.16b, INP1.16b, KS1.16b
|
|
eor INP2.16b, INP2.16b, KS2.16b
|
|
eor INP3.16b, INP3.16b, KS3.16b
|
|
|
|
ret
|
|
SYM_FUNC_END(pmull_gcm_enc_4x)
|
|
|
|
.section ".rodata", "a"
|
|
.align 6
|
|
.Lpermute_table:
|
|
.byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
|
|
.byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
|
|
.byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
|
|
.byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf
|
|
.byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
|
|
.byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
|
|
.byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
|
|
.byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf
|
|
.previous
|