chore: make deps, go mod vendor
Some checks failed
continuous-integration/drone/push Build is failing

This commit is contained in:
2024-12-02 01:45:06 +01:00
parent f664599836
commit 31fa9b1a7a
598 changed files with 37898 additions and 18309 deletions

View File

@ -2,7 +2,7 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
//go:build (!amd64 && !ppc64le && !s390x) || !gc || purego
//go:build (!amd64 && !ppc64le && !ppc64 && !s390x) || !gc || purego
package poly1305

View File

@ -1,108 +1,93 @@
// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Code generated by command: go run sum_amd64_asm.go -out ../sum_amd64.s -pkg poly1305. DO NOT EDIT.
//go:build gc && !purego
#include "textflag.h"
#define POLY1305_ADD(msg, h0, h1, h2) \
ADDQ 0(msg), h0; \
ADCQ 8(msg), h1; \
ADCQ $1, h2; \
LEAQ 16(msg), msg
#define POLY1305_MUL(h0, h1, h2, r0, r1, t0, t1, t2, t3) \
MOVQ r0, AX; \
MULQ h0; \
MOVQ AX, t0; \
MOVQ DX, t1; \
MOVQ r0, AX; \
MULQ h1; \
ADDQ AX, t1; \
ADCQ $0, DX; \
MOVQ r0, t2; \
IMULQ h2, t2; \
ADDQ DX, t2; \
\
MOVQ r1, AX; \
MULQ h0; \
ADDQ AX, t1; \
ADCQ $0, DX; \
MOVQ DX, h0; \
MOVQ r1, t3; \
IMULQ h2, t3; \
MOVQ r1, AX; \
MULQ h1; \
ADDQ AX, t2; \
ADCQ DX, t3; \
ADDQ h0, t2; \
ADCQ $0, t3; \
\
MOVQ t0, h0; \
MOVQ t1, h1; \
MOVQ t2, h2; \
ANDQ $3, h2; \
MOVQ t2, t0; \
ANDQ $0xFFFFFFFFFFFFFFFC, t0; \
ADDQ t0, h0; \
ADCQ t3, h1; \
ADCQ $0, h2; \
SHRQ $2, t3, t2; \
SHRQ $2, t3; \
ADDQ t2, h0; \
ADCQ t3, h1; \
ADCQ $0, h2
// func update(state *[7]uint64, msg []byte)
// func update(state *macState, msg []byte)
TEXT ·update(SB), $0-32
MOVQ state+0(FP), DI
MOVQ msg_base+8(FP), SI
MOVQ msg_len+16(FP), R15
MOVQ 0(DI), R8 // h0
MOVQ 8(DI), R9 // h1
MOVQ 16(DI), R10 // h2
MOVQ 24(DI), R11 // r0
MOVQ 32(DI), R12 // r1
CMPQ R15, $16
MOVQ (DI), R8
MOVQ 8(DI), R9
MOVQ 16(DI), R10
MOVQ 24(DI), R11
MOVQ 32(DI), R12
CMPQ R15, $0x10
JB bytes_between_0_and_15
loop:
POLY1305_ADD(SI, R8, R9, R10)
ADDQ (SI), R8
ADCQ 8(SI), R9
ADCQ $0x01, R10
LEAQ 16(SI), SI
multiply:
POLY1305_MUL(R8, R9, R10, R11, R12, BX, CX, R13, R14)
SUBQ $16, R15
CMPQ R15, $16
JAE loop
MOVQ R11, AX
MULQ R8
MOVQ AX, BX
MOVQ DX, CX
MOVQ R11, AX
MULQ R9
ADDQ AX, CX
ADCQ $0x00, DX
MOVQ R11, R13
IMULQ R10, R13
ADDQ DX, R13
MOVQ R12, AX
MULQ R8
ADDQ AX, CX
ADCQ $0x00, DX
MOVQ DX, R8
MOVQ R12, R14
IMULQ R10, R14
MOVQ R12, AX
MULQ R9
ADDQ AX, R13
ADCQ DX, R14
ADDQ R8, R13
ADCQ $0x00, R14
MOVQ BX, R8
MOVQ CX, R9
MOVQ R13, R10
ANDQ $0x03, R10
MOVQ R13, BX
ANDQ $-4, BX
ADDQ BX, R8
ADCQ R14, R9
ADCQ $0x00, R10
SHRQ $0x02, R14, R13
SHRQ $0x02, R14
ADDQ R13, R8
ADCQ R14, R9
ADCQ $0x00, R10
SUBQ $0x10, R15
CMPQ R15, $0x10
JAE loop
bytes_between_0_and_15:
TESTQ R15, R15
JZ done
MOVQ $1, BX
MOVQ $0x00000001, BX
XORQ CX, CX
XORQ R13, R13
ADDQ R15, SI
flush_buffer:
SHLQ $8, BX, CX
SHLQ $8, BX
SHLQ $0x08, BX, CX
SHLQ $0x08, BX
MOVB -1(SI), R13
XORQ R13, BX
DECQ SI
DECQ R15
JNZ flush_buffer
ADDQ BX, R8
ADCQ CX, R9
ADCQ $0, R10
MOVQ $16, R15
ADCQ $0x00, R10
MOVQ $0x00000010, R15
JMP multiply
done:
MOVQ R8, 0(DI)
MOVQ R8, (DI)
MOVQ R9, 8(DI)
MOVQ R10, 16(DI)
RET

View File

@ -2,7 +2,7 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
//go:build gc && !purego
//go:build gc && !purego && (ppc64 || ppc64le)
package poly1305

View File

@ -2,15 +2,25 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
//go:build gc && !purego
//go:build gc && !purego && (ppc64 || ppc64le)
#include "textflag.h"
// This was ported from the amd64 implementation.
#ifdef GOARCH_ppc64le
#define LE_MOVD MOVD
#define LE_MOVWZ MOVWZ
#define LE_MOVHZ MOVHZ
#else
#define LE_MOVD MOVDBR
#define LE_MOVWZ MOVWBR
#define LE_MOVHZ MOVHBR
#endif
#define POLY1305_ADD(msg, h0, h1, h2, t0, t1, t2) \
MOVD (msg), t0; \
MOVD 8(msg), t1; \
LE_MOVD (msg)( R0), t0; \
LE_MOVD (msg)(R24), t1; \
MOVD $1, t2; \
ADDC t0, h0, h0; \
ADDE t1, h1, h1; \
@ -50,10 +60,6 @@
ADDE t3, h1, h1; \
ADDZE h2
DATA ·poly1305Mask<>+0x00(SB)/8, $0x0FFFFFFC0FFFFFFF
DATA ·poly1305Mask<>+0x08(SB)/8, $0x0FFFFFFC0FFFFFFC
GLOBL ·poly1305Mask<>(SB), RODATA, $16
// func update(state *[7]uint64, msg []byte)
TEXT ·update(SB), $0-32
MOVD state+0(FP), R3
@ -66,6 +72,8 @@ TEXT ·update(SB), $0-32
MOVD 24(R3), R11 // r0
MOVD 32(R3), R12 // r1
MOVD $8, R24
CMP R5, $16
BLT bytes_between_0_and_15
@ -94,7 +102,7 @@ flush_buffer:
// Greater than 8 -- load the rightmost remaining bytes in msg
// and put into R17 (h1)
MOVD (R4)(R21), R17
LE_MOVD (R4)(R21), R17
MOVD $16, R22
// Find the offset to those bytes
@ -118,7 +126,7 @@ just1:
BLT less8
// Exactly 8
MOVD (R4), R16
LE_MOVD (R4), R16
CMP R17, $0
@ -133,7 +141,7 @@ less8:
MOVD $0, R22 // shift count
CMP R5, $4
BLT less4
MOVWZ (R4), R16
LE_MOVWZ (R4), R16
ADD $4, R4
ADD $-4, R5
MOVD $32, R22
@ -141,7 +149,7 @@ less8:
less4:
CMP R5, $2
BLT less2
MOVHZ (R4), R21
LE_MOVHZ (R4), R21
SLD R22, R21, R21
OR R16, R21, R16
ADD $16, R22