mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-04-26 12:16:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/emmansun/gmsm

Browse Source
This commit is contained in:
emmansun 2022-01-01 20:28:43 +08:00
commit 4d24880310
2 changed files with 58 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
sm4/asm_arm64.s
View File

@ -8,7 +8,16 @@
#define t3 V5
#define ZERO V16
#define FLIP_MASK V17
#define NIBBLE_MASK V20
#define INVERSE_SHIFT_ROWS V30
#define M1L V22
#define M1H V23
#define M2L V24
#define M2H V25
#define R08_MASK V26
#define R16_MASK V27
#define R24_MASK V28
#define FK_MASK V29
#define XTMP6 V6
#define XTMP7 V7
@ -23,8 +32,8 @@ DATA nibble_mask<>+0x08(SB)/8, $0x0F0F0F0F0F0F0F0F
GLOBL nibble_mask<>(SB), (NOPTR+RODATA), $16
// inverse shift rows
DATA inverse_shift_rows<>+0x00(SB)/8, $0x0B0E0104070A0D00
DATA inverse_shift_rows<>+0x08(SB)/8, $0x0306090C0F020508
DATA inverse_shift_rows<>+0x00(SB)/8, $0x0106050403020700
DATA inverse_shift_rows<>+0x08(SB)/8, $0x0F0E0D0C0B0A0908
GLOBL inverse_shift_rows<>(SB), (NOPTR+RODATA), $16
// Affine transform 1 (low and high hibbles)
@ -64,37 +73,19 @@ GLOBL fk_mask<>(SB), (NOPTR+RODATA), $16
#define SM4_SBOX(x, y) \
; \ //############################# inner affine ############################//
LDP nibble_mask<>(SB), (R0, R1); \
VMOV R0, XTMP6.D[0]; \
VMOV R1, XTMP6.D[1]; \
VAND x.B16, XTMP6.B16, XTMP7.B16; \
LDP m1_low<>(SB), (R0, R1); \
VMOV R0, y.D[0]; \
VMOV R1, y.D[1]; \
VTBL XTMP7.B16, [y.B16], y.B16; \
VAND x.B16, NIBBLE_MASK.B16, XTMP7.B16; \
VTBL XTMP7.B16, [M1L.B16], y.B16; \
VUSHR $4, x.D2, x.D2; \
VAND x.B16, XTMP6.B16, XTMP7.B16; \
LDP m1_low<>(SB), (R0, R1); \
VMOV R0, V8.D[0]; \
VMOV R1, V8.D[1]; \
VTBL XTMP7.B16, [V8.B16], XTMP7.B16; \
VAND x.B16, NIBBLE_MASK.B16, XTMP7.B16; \
VTBL XTMP7.B16, [M1H.B16], XTMP7.B16; \
VEOR y.B16, XTMP7.B16, x.B16; \
LDP inverse_shift_rows<>(SB), (R0, R1); \
VMOV R0, V8.D[0]; \
VMOV R1, V8.D[1]; \
VTBL V8.B16, [x.B16], x.B16; \
VTBL INVERSE_SHIFT_ROWS.B16, [x.B16], x.B16; \
AESE ZERO.B16, x.B16; \
VAND x.B16, XTMP6.B16, XTMP7.B16; \
LDP m2_low<>(SB), (R0, R1); \
VMOV R0, y.D[0]; \
VMOV R1, y.D[1]; \
VTBL XTMP7.B16, [y.B16], y.B16; \
VAND x.B16, NIBBLE_MASK.B16, XTMP7.B16; \
VTBL XTMP7.B16, [M2L.B16], y.B16; \
VUSHR $4, x.D2, x.D2; \
VAND x.B16, XTMP6.B16, XTMP7.B16; \
LDP m2_high<>(SB), (R0, R1); \
VMOV R0, V8.D[0]; \
VMOV R1, V8.D[1]; \
VTBL XTMP7.B16, [V8.B16], XTMP7.B16; \
VAND x.B16, NIBBLE_MASK.B16, XTMP7.B16; \
VTBL XTMP7.B16, [M2H.B16], XTMP7.B16; \
VEOR y.B16, XTMP7.B16, x.B16
#define SM4_TAO_L1(x, y) \
@ -121,11 +112,7 @@ GLOBL fk_mask<>(SB), (NOPTR+RODATA), $16
VEOR y.B16, x.B16, x.B16
#define SM4_TAO_L2(x, y) \
VMOV R0, XTMP6.D[0]; \
VMOV R1, XTMP6.D[1]; \
VAND x.B16, XTMP6.B16, XTMP7.B16; \
VMOV R0, y.D[0]; \
VMOV R1, y.D[1]; \
SM4_SBOX(x, y); \
; \ //#################### 4 parallel L2 linear transforms ##################//
VSHL $13, x.S4, XTMP6.S4; \
VUSHR $19, x.S4, y.S4; \
@ -142,16 +129,42 @@ TEXT ·expandKeyAsm(SB),NOSPLIT,$0
MOVD ck+8(FP), R9
MOVD enc+16(FP), R10
MOVD dec+24(FP), R11
VLD1 (R8), [t0.B16];
LDP flip_mask<>(SB), (R0, R1)
VMOV R0, FLIP_MASK.D[0]
VMOV R1, FLIP_MASK.D[1]
VTBL FLIP_MASK.B16, [t0.B16], t0.B16
LDP nibble_mask<>(SB), (R0, R1)
VMOV R0, NIBBLE_MASK.D[0]
VMOV R1, NIBBLE_MASK.D[1]
LDP m1_low<>(SB), (R0, R1)
VMOV R0, M1L.D[0]
VMOV R1, M1L.D[1]
LDP m1_high<>(SB), (R0, R1)
VMOV R0, M1H.D[0]
VMOV R1, M1H.D[1]
LDP m2_low<>(SB), (R0, R1)
VMOV R0, M2L.D[0]
VMOV R1, M2L.D[1]
LDP m2_high<>(SB), (R0, R1)
VMOV R0, M2H.D[0]
VMOV R1, M2H.D[1]
LDP fk_mask<>(SB), (R0, R1)
VMOV R0, XTMP7.D[0]
VMOV R1, XTMP7.D[1]
VEOR t0.B16, XTMP7.B16, t0.B16
VMOV R0, FK_MASK.D[0]
VMOV R1, FK_MASK.D[1]
LDP inverse_shift_rows<>(SB), (R0, R1)
VMOV R0, INVERSE_SHIFT_ROWS.D[0]
VMOV R1, INVERSE_SHIFT_ROWS.D[1]
VLD1 (R8), [t0.B16];
VTBL FLIP_MASK.B16, [t0.B16], t0.B16
VEOR t0.B16, FK_MASK.B16, t0.B16
VMOV t0.S[1], t1.S[0]
VMOV t0.S[2], t2.S[0]
VMOV t0.S[3], t3.S[0]
@ -208,6 +221,7 @@ ksLoop:
ADD $16, R0
CMP $128, R0
BNE ksLoop
RET
// func encryptBlocksAsm(xk *uint32, dst, src *byte)

7
sm4/cipher_asm_fuzzy_test.go
View File

@ -4,9 +4,7 @@
package sm4
import (
"crypto/rand"
"fmt"
"io"
"testing"
)
@ -46,15 +44,16 @@ func TestExpandKey(t *testing.T) {
*/
func TestExpandKeySimple(t *testing.T) {
key := make([]byte, 16)
key := []byte{0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba, 0x98, 0x76, 0x54, 0x32, 0x10}
encRes1 := make([]uint32, 32)
decRes1 := make([]uint32, 32)
encRes2 := make([]uint32, 32)
decRes2 := make([]uint32, 32)
io.ReadFull(rand.Reader, key)
expandKeyGo(key, encRes1, decRes1)
expandKeyAsm(&key[0], &ck[0], &encRes2[0], &decRes2[0])
fmt.Printf("expected=%v, result=%v\n", encRes1, encRes2)
fmt.Printf("expected=%v, result=%v\n", decRes1, decRes2)
}