mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-04-26 04:06:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

sm4: xts asm arm64 test one by one

Browse Source
This commit is contained in:
Sun Yimin 2023-08-24 16:28:43 +08:00 committed by GitHub
parent 28a6939861
commit a8714d9782
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 150 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

150
sm4/xts_arm64.s
View File

@ -372,6 +372,156 @@ xtsSm4EncDone:
// func encryptSm4XtsGB(xk *uint32, tweak *[BlockSize]byte, dst, src []byte) // func encryptSm4XtsGB(xk *uint32, tweak *[BlockSize]byte, dst, src []byte)
TEXT ·encryptSm4XtsGB(SB),0,$128-64 TEXT ·encryptSm4XtsGB(SB),0,$128-64
LOAD_SM4_AESNI_CONSTS()
MOVD xk+0(FP), rk
MOVD tweak+8(FP), twPtr
MOVD dst+16(FP), dstPtr
MOVD src+40(FP), srcPtr
MOVD src_len+48(FP), srcPtrLen
VEOR POLY.B16, POLY.B16, POLY.B16
VEOR ZERO.B16, ZERO.B16, ZERO.B16
MOVD $0xE1, I
LSL $56, I
VMOV I, POLY.D[1]
MOVD rk, rkSave
VLD1 (twPtr), [TW.B16]
xtsSm4EncOctets:
CMP $128, srcPtrLen
BLT xtsSm4EncNibbles
SUB $128, srcPtrLen
prepareGB8Tweaks
load8blocks
MOVD rkSave, rk
EOR R13, R13
encOctetsEnc8Blocks:
SM4_8BLOCKS_ROUND(rk, R19, K0, K1, K2, K3, B0, B1, B2, B3, B4, B5, B6, B7)
SM4_8BLOCKS_ROUND(rk, R19, K0, K1, K2, K3, B1, B2, B3, B0, B5, B6, B7, B4)
SM4_8BLOCKS_ROUND(rk, R19, K0, K1, K2, K3, B2, B3, B0, B1, B6, B7, B4, B5)
SM4_8BLOCKS_ROUND(rk, R19, K0, K1, K2, K3, B3, B0, B1, B2, B7, B4, B5, B6)
ADD $1, R13
CMP $8, R13
BNE encOctetsEnc8Blocks
store8blocks
B xtsSm4EncOctets
xtsSm4EncNibbles:
CMP $64, srcPtrLen
BLT xtsSm4EncSingles
SUB $64, srcPtrLen
prepareGB4Tweaks
load4blocks
MOVD rkSave, rk
EOR R13, R13
encNibblesEnc4Blocks:
SM4_ROUND(rk, R19, K0, K1, K2, B0, B1, B2, B3)
SM4_ROUND(rk, R19, K0, K1, K2, B1, B2, B3, B0)
SM4_ROUND(rk, R19, K0, K1, K2, B2, B3, B0, B1)
SM4_ROUND(rk, R19, K0, K1, K2, B3, B0, B1, B2)
ADD $1, R13
CMP $8, R13
BNE encNibblesEnc4Blocks
store4blocks
xtsSm4EncSingles:
CMP $16, srcPtrLen
BLT xtsSm4EncTail
SUB $16, srcPtrLen
loadOneBlock
MOVD rkSave, rk
EOR R13, R13
encSinglesEnc4Blocks:
SM4_ROUND(rk, R19, K0, K1, K2, B0, B1, B2, B3)
SM4_ROUND(rk, R19, K0, K1, K2, B1, B2, B3, B0)
SM4_ROUND(rk, R19, K0, K1, K2, B2, B3, B0, B1)
SM4_ROUND(rk, R19, K0, K1, K2, B3, B0, B1, B2)
ADD $1, R13
CMP $8, R13
BNE encSinglesEnc4Blocks
storeOneBlock
mul2GBInline
B xtsSm4EncSingles
xtsSm4EncTail:
CBZ srcPtrLen, xtsSm4EncDone
SUB $16, dstPtr, R7
MOVD R7, R9
MOVD RSP, R8
VLD1 (R7), [B0.B16]
VST1 [B0.B16], (R8)
TBZ $3, srcPtrLen, less_than8
MOVD.P 8(srcPtr), R11
MOVD.P R11, 8(R8)
MOVD.P 8(R7), R12
MOVD.P R12, 8(dstPtr)
less_than8:
TBZ $2, srcPtrLen, less_than4
MOVWU.P 4(srcPtr), R11
MOVWU.P R11, 4(R8)
MOVWU.P 4(R7), R12
MOVWU.P R12, 4(dstPtr)
less_than4:
TBZ $1, srcPtrLen, less_than2
MOVHU.P 2(srcPtr), R11
MOVHU.P R11, 2(R8)
MOVHU.P 2(R7), R12
MOVHU.P R12, 2(dstPtr)
less_than2:
TBZ $0, srcPtrLen, xtsSm4EncTailEnc
MOVBU (srcPtr), R11
MOVBU R11, (R8)
MOVBU (R7), R12
MOVBU R12, (dstPtr)
xtsSm4EncTailEnc:
VLD1 (RSP), [B0.B16]
VEOR TW.B16, B0.B16, B0.B16
VREV32 B0.B16, B0.B16
VMOV B0.S[1], B1.S[0]
VMOV B0.S[2], B2.S[0]
VMOV B0.S[3], B3.S[0]
MOVD rkSave, rk
EOR R13, R13
tailEncLoop:
SM4_ROUND(rk, R19, K0, K1, K2, B0, B1, B2, B3)
SM4_ROUND(rk, R19, K0, K1, K2, B1, B2, B3, B0)
SM4_ROUND(rk, R19, K0, K1, K2, B2, B3, B0, B1)
SM4_ROUND(rk, R19, K0, K1, K2, B3, B0, B1, B2)
ADD $1, R13
CMP $8, R13
BNE tailEncLoop
VMOV B2.S[0], B3.S[1]
VMOV B1.S[0], B3.S[2]
VMOV B0.S[0], B3.S[3]
VREV32 B3.B16, B3.B16
VEOR TW.B16, B3.B16, B3.B16
VST1 [B3.B16], (R9)
xtsSm4EncDone:
VST1 [TW.B16], (twPtr)
RET RET
// func decryptSm4Xts(xk *uint32, tweak *[BlockSize]byte, dst, src []byte) // func decryptSm4Xts(xk *uint32, tweak *[BlockSize]byte, dst, src []byte)