mirror of
https://github.com/golang/go
synced 2024-11-20 00:14:44 -07:00
87e48c5afd
Since barrier-less memclr is only safe in very narrow circumstances, this commit renames memclr to avoid accidentally calling memclr on typed memory. This can cause subtle, non-deterministic bugs, so it's worth some effort to prevent. In the near term, this will also prevent bugs creeping in from any concurrent CLs that add calls to memclr; if this happens, whichever patch hits master second will fail to compile. This also adds the other new memclr variants to the compiler's builtin.go to minimize the churn on that binary blob. We'll use these in future commits. Updates #17503. Change-Id: I00eead049f5bd35ca107ea525966831f3d1ed9ca Reviewed-on: https://go-review.googlesource.com/31369 Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Rick Hudson <rlh@golang.org>
136 lines
2.4 KiB
ArmAsm
136 lines
2.4 KiB
ArmAsm
// Copyright 2014 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.
|
|
|
|
// +build !plan9
|
|
|
|
#include "textflag.h"
|
|
|
|
// NOTE: Windows externalthreadhandler expects memclr to preserve DX.
|
|
|
|
// void runtime·memclrNoHeapPointers(void*, uintptr)
|
|
TEXT runtime·memclrNoHeapPointers(SB), NOSPLIT, $0-8
|
|
MOVL ptr+0(FP), DI
|
|
MOVL n+4(FP), BX
|
|
XORL AX, AX
|
|
|
|
// MOVOU seems always faster than REP STOSL.
|
|
tail:
|
|
TESTL BX, BX
|
|
JEQ _0
|
|
CMPL BX, $2
|
|
JBE _1or2
|
|
CMPL BX, $4
|
|
JB _3
|
|
JE _4
|
|
CMPL BX, $8
|
|
JBE _5through8
|
|
CMPL BX, $16
|
|
JBE _9through16
|
|
TESTL $0x4000000, runtime·cpuid_edx(SB) // check for sse2
|
|
JEQ nosse2
|
|
PXOR X0, X0
|
|
CMPL BX, $32
|
|
JBE _17through32
|
|
CMPL BX, $64
|
|
JBE _33through64
|
|
CMPL BX, $128
|
|
JBE _65through128
|
|
CMPL BX, $256
|
|
JBE _129through256
|
|
// TODO: use branch table and BSR to make this just a single dispatch
|
|
|
|
loop:
|
|
MOVOU X0, 0(DI)
|
|
MOVOU X0, 16(DI)
|
|
MOVOU X0, 32(DI)
|
|
MOVOU X0, 48(DI)
|
|
MOVOU X0, 64(DI)
|
|
MOVOU X0, 80(DI)
|
|
MOVOU X0, 96(DI)
|
|
MOVOU X0, 112(DI)
|
|
MOVOU X0, 128(DI)
|
|
MOVOU X0, 144(DI)
|
|
MOVOU X0, 160(DI)
|
|
MOVOU X0, 176(DI)
|
|
MOVOU X0, 192(DI)
|
|
MOVOU X0, 208(DI)
|
|
MOVOU X0, 224(DI)
|
|
MOVOU X0, 240(DI)
|
|
SUBL $256, BX
|
|
ADDL $256, DI
|
|
CMPL BX, $256
|
|
JAE loop
|
|
JMP tail
|
|
|
|
_1or2:
|
|
MOVB AX, (DI)
|
|
MOVB AX, -1(DI)(BX*1)
|
|
RET
|
|
_0:
|
|
RET
|
|
_3:
|
|
MOVW AX, (DI)
|
|
MOVB AX, 2(DI)
|
|
RET
|
|
_4:
|
|
// We need a separate case for 4 to make sure we clear pointers atomically.
|
|
MOVL AX, (DI)
|
|
RET
|
|
_5through8:
|
|
MOVL AX, (DI)
|
|
MOVL AX, -4(DI)(BX*1)
|
|
RET
|
|
_9through16:
|
|
MOVL AX, (DI)
|
|
MOVL AX, 4(DI)
|
|
MOVL AX, -8(DI)(BX*1)
|
|
MOVL AX, -4(DI)(BX*1)
|
|
RET
|
|
_17through32:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
_33through64:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, 16(DI)
|
|
MOVOU X0, -32(DI)(BX*1)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
_65through128:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, 16(DI)
|
|
MOVOU X0, 32(DI)
|
|
MOVOU X0, 48(DI)
|
|
MOVOU X0, -64(DI)(BX*1)
|
|
MOVOU X0, -48(DI)(BX*1)
|
|
MOVOU X0, -32(DI)(BX*1)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
_129through256:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, 16(DI)
|
|
MOVOU X0, 32(DI)
|
|
MOVOU X0, 48(DI)
|
|
MOVOU X0, 64(DI)
|
|
MOVOU X0, 80(DI)
|
|
MOVOU X0, 96(DI)
|
|
MOVOU X0, 112(DI)
|
|
MOVOU X0, -128(DI)(BX*1)
|
|
MOVOU X0, -112(DI)(BX*1)
|
|
MOVOU X0, -96(DI)(BX*1)
|
|
MOVOU X0, -80(DI)(BX*1)
|
|
MOVOU X0, -64(DI)(BX*1)
|
|
MOVOU X0, -48(DI)(BX*1)
|
|
MOVOU X0, -32(DI)(BX*1)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
nosse2:
|
|
MOVL BX, CX
|
|
SHRL $2, CX
|
|
REP
|
|
STOSL
|
|
ANDL $3, BX
|
|
JNE tail
|
|
RET
|