mirror of
https://github.com/emmansun/gmsm.git
synced 2025-04-26 20:26:19 +08:00
[SM4] try arm64 gcmSm4Init
This commit is contained in:
Emman
parent
46fb08c038
commit
3e32a52bee
125
sm4/gcm_arm64.s
125
sm4/gcm_arm64.s
@ -107,71 +107,45 @@ TEXT ·gcmSm4Finish(SB),NOSPLIT,$0
|
||||
#undef dlen
|
||||
|
||||
#define SM4_SBOX(x, y, z, z1, z2) \
|
||||
MOVD $0x0F0F0F0F0F0F0F0F, R19; \
|
||||
VMOV R19, z1.D2; \ // nibble mask
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
MOVD $0x9197E2E474720701, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0xC7C1B4B222245157, R19; \
|
||||
VMOV R19, z.D[1]; \ // m1 low
|
||||
VTBL z2.B16, [z.B16], y.B16; \
|
||||
VUSHR $4, x.D2, x.D2; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
MOVD $0xE240AB09EB49A200, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0xF052B91BF95BB012, R19; \
|
||||
VMOV R19, z.D[1]; \ // m1 high
|
||||
VTBL z2.B16, [z.B16], z2.B16; \
|
||||
VEOR y.B16, z2.B16, x.B16; \
|
||||
MOVD $0x0B0E0104070A0D00, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0x0306090C0F020508, R19; \
|
||||
VMOV R19, z.D[1]; \ // inverse shift row
|
||||
VTBL z.B16, [x.B16], x.B16; \
|
||||
AESE ZERO.B16, x.B16; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
MOVD $0x5B67F2CEA19D0834, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0xEDD14478172BBE82, R19; \
|
||||
VMOV R19, z.D[1]; \ // m2 low
|
||||
VTBL z2.B16, [z.B16], y.B16; \
|
||||
VUSHR $4, x.D2, x.D2; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
MOVD $0xAE7201DD73AFDC00, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0x11CDBE62CC1063BF, R19; \
|
||||
VMOV R19, z.D[1]; \ // m2 high
|
||||
VTBL z2.B16, [z.B16], z2.B16; \
|
||||
VMOVQ $0x0F0F0F0F0F0F0F0F, $0x0F0F0F0F0F0F0F0F, z1; \ // nibble mask
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
VMOVQ $0xC7C1B4B222245157, $0x9197E2E474720701, z; \
|
||||
VTBL z2.B16, [z.B16], y.B16; \
|
||||
VUSHR $4, x.D2, x.D2; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
VMOVQ $0xF052B91BF95BB012, $0xE240AB09EB49A200, z; \
|
||||
VTBL z2.B16, [z.B16], z2.B16; \
|
||||
VEOR y.B16, z2.B16, x.B16; \
|
||||
VMOVQ $0x0306090C0F020508, $0x0B0E0104070A0D00, z; \
|
||||
VTBL z.B16, [x.B16], x.B16; \
|
||||
AESE ZERO.B16, x.B16; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
VMOVQ $0xEDD14478172BBE82, $0x5B67F2CEA19D0834, z; \
|
||||
VTBL z2.B16, [z.B16], y.B16; \
|
||||
VUSHR $4, x.D2, x.D2; \
|
||||
VAND x.B16, z1.B16, z2.B16; \
|
||||
VMOVQ $0x11CDBE62CC1063BF, $0xAE7201DD73AFDC00, z; \
|
||||
VTBL z2.B16, [z.B16], z2.B16; \
|
||||
VEOR y.B16, z2.B16, x.B16
|
||||
|
||||
#define SM4_TAO_L1(x, y, z, z1, z2) \
|
||||
SM4_SBOX(x, y, z, z1, z2); \
|
||||
; \
|
||||
MOVD $0x0605040702010003, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0x0E0D0C0F0A09080B, R19; \
|
||||
VMOV R19, z.D[1]; \ // r08 mask
|
||||
VTBL z.B16, [x.B16], y.B16; \
|
||||
VEOR y.B16, x.B16, y.B16; \
|
||||
MOVD $0x0504070601000302, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0x0D0C0F0E09080B0A, R19; \
|
||||
VMOV R19, z.D[1]; \ // r16 mask
|
||||
VTBL z.B16, [x.B16], z.B16; \
|
||||
VEOR z.B16, y.B16, y.B16; \
|
||||
VSHL $2, y.S4, z.S4; \
|
||||
VUSHR $30, y.S4, y.S4; \
|
||||
VORR y.B16, z.B16, y.B16; \
|
||||
MOVD $0x0407060500030201, R19; \
|
||||
VMOV R19, z.D[0]; \
|
||||
MOVD $0x0C0F0E0D080B0A09, R19; \
|
||||
VMOV R19, z.D[1]; \ // r24 mask
|
||||
VTBL z.B16, [x.B16], z.B16; \
|
||||
VEOR z.B16, x.B16, x.B16; \
|
||||
SM4_SBOX(x, y, z, z1, z2); \
|
||||
VMOVQ $0x0E0D0C0F0A09080B, $0x0605040702010003, z; \
|
||||
VTBL z.B16, [x.B16], y.B16; \
|
||||
VEOR y.B16, x.B16, y.B16; \
|
||||
VMOVQ $0x0D0C0F0E09080B0A, $0x0504070601000302, z; \
|
||||
VTBL z.B16, [x.B16], z.B16; \
|
||||
VEOR z.B16, y.B16, y.B16; \
|
||||
VSHL $2, y.S4, z.S4; \
|
||||
VUSHR $30, y.S4, y.S4; \
|
||||
VORR y.B16, z.B16, y.B16; \
|
||||
VMOVQ $0x0C0F0E0D080B0A09, $0x0407060500030201, z; \
|
||||
VTBL z.B16, [x.B16], z.B16; \
|
||||
VEOR z.B16, x.B16, x.B16; \
|
||||
VEOR y.B16, x.B16, x.B16
|
||||
|
||||
#define SM4_ROUND(RK, x, y, z, z1, z2, t0, t1, t2, t3) \
|
||||
MOVW.P 4(RK), R19; \
|
||||
#define SM4_ROUND(index, RK, x, y, z, z1, z2, t0, t1, t2, t3) \
|
||||
MOVW (index*4)(RK), R19; \
|
||||
VMOV R19, x.S4; \
|
||||
VEOR t1.B16, x.B16, x.B16; \
|
||||
VEOR t2.B16, x.B16, x.B16; \
|
||||
@ -179,10 +153,10 @@ TEXT ·gcmSm4Finish(SB),NOSPLIT,$0
|
||||
SM4_TAO_L1(x, y, z, z1, z2); \
|
||||
VEOR x.B16, t0.B16, t0.B16
|
||||
|
||||
// func precomputeTableAsm(productTable *[256]byte, src *[16]byte)
|
||||
TEXT ·precomputeTableAsm(SB),NOSPLIT,$0
|
||||
// func gcmSm4Init(productTable *[256]byte, rk []uint32)
|
||||
TEXT ·gcmSm4Init(SB),NOSPLIT,$0
|
||||
#define pTbl R0
|
||||
#define SRC R1
|
||||
#define RK R1
|
||||
#define I R2
|
||||
|
||||
MOVD productTable+0(FP), pTbl
|
||||
@ -195,8 +169,27 @@ TEXT ·precomputeTableAsm(SB),NOSPLIT,$0
|
||||
VMOV I, POLY.D[1]
|
||||
VEOR ZERO.B16, ZERO.B16, ZERO.B16
|
||||
|
||||
VLD1 (SRC), [B0.B16]
|
||||
VREV64 B0.B16, B0.B16
|
||||
// Encrypt block 0 with the SM4 keys to generate the hash key H
|
||||
VEOR B0.B16, B0.B16, B0.B16
|
||||
VEOR B1.B16, B1.B16, B1.B16
|
||||
VEOR B2.B16, B2.B16, B2.B16
|
||||
VEOR B3.B16, B3.B16, B3.B16
|
||||
EOR R3, R3
|
||||
|
||||
sm4InitEncLoop:
|
||||
SM4_ROUND(0, RK, K0, K1, K2, K3, K4, B0, B1, B2, B3)
|
||||
SM4_ROUND(1, RK, K0, K1, K2, K3, K4, B1, B2, B3, B0)
|
||||
SM4_ROUND(2, RK, K0, K1, K2, K3, K4, B2, B3, B0, B1)
|
||||
SM4_ROUND(3, RK, K0, K1, K2, K3, K4, B3, B0, B1, B2)
|
||||
|
||||
ADD $16, R3
|
||||
CMP $128, R3
|
||||
BNE sm4InitEncLoop
|
||||
|
||||
VMOV B0.S[0], B0.S[2]
|
||||
VMOV B1.S[0], B0.S[3]
|
||||
VMOV B2.S[0], B0.S[0]
|
||||
VMOV B3.S[0], B0.S[1]
|
||||
|
||||
// Multiply by 2 modulo P
|
||||
VMOV B0.D[0], I
|
||||
@ -254,7 +247,7 @@ initLoop:
|
||||
BNE initLoop
|
||||
RET
|
||||
#undef I
|
||||
#undef SRC
|
||||
#undef RK
|
||||
#undef pTbl
|
||||
|
||||
// func gcmSm4Data(productTable *[256]byte, data []byte, T *[16]byte)
|
||||
|
||||
@ -21,7 +21,7 @@ type sm4CipherGCM struct {
|
||||
var _ gcmAble = (*sm4CipherGCM)(nil)
|
||||
|
||||
//go:noescape
|
||||
func precomputeTableAsm(productTable *[256]byte, src *[16]byte)
|
||||
func gcmSm4Init(productTable *[256]byte, rk []uint32)
|
||||
|
||||
//go:noescape
|
||||
func gcmSm4Data(productTable *[256]byte, data []byte, T *[16]byte)
|
||||
@ -41,9 +41,7 @@ func (c *sm4CipherGCM) NewGCM(nonceSize, tagSize int) (cipher.AEAD, error) {
|
||||
g.cipher = &c.sm4CipherAsm
|
||||
g.nonceSize = nonceSize
|
||||
g.tagSize = tagSize
|
||||
var key [gcmBlockSize]byte
|
||||
c.Encrypt(key[:], key[:])
|
||||
precomputeTableAsm(&g.bytesProductTable, &key)
|
||||
gcmSm4Init(&g.bytesProductTable, g.cipher.enc)
|
||||
return g, nil
|
||||
}
|
||||
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
//go:build amd64
|
||||
// +build amd64
|
||||
//go:build amd64 || arm64
|
||||
// +build amd64 arm64
|
||||
|
||||
package sm4
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user