1
0
mirror of https://github.com/golang/go synced 2024-11-07 14:56:16 -07:00
go/src/runtime/memclr_386.s
Austin Clements c19759aa48 runtime: eliminate externalthreadhandler
This function is no longer used.

Eliminating this actually fixes several problems:

- It made assumptions about what registers memclrNoHeapPointers would
  preserve. Besides being an abstraction violation and lurking
  maintenance issue, this actively became a problem for regabi because
  the call to memclrNoHeapPointers now happens through an ABI wrapper,
  which is generated by the compiler and hence we can't easily control
  what registers it clobbers.

- The amd64 implementation (at least), does not interact with the host
  ABI correctly. Notably, it doesn't save many of the registers that
  are callee-save in the host ABI but caller-save in the Go ABI.

- It interacts strangely with the NOSPLIT checker because it allocates
  an entire M and G on its stack. It worked around this on arm64, and
  happened to do things the NOSPLIT checker couldn't track on 386 and
  amd64, and happened to be *4 bytes* below the limit on arm (so any
  addition to the m or g structs would cause a NOSPLIT failure). See
  CL 309031 for a more complete explanation.

Fixes #45530.
Updates #40724.

Change-Id: Ic70d4d7e1c17f1d796575b3377b8529449e93576
Reviewed-on: https://go-review.googlesource.com/c/go/+/309634
Trust: Austin Clements <austin@google.com>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Michael Knyszek <mknyszek@google.com>
2021-04-13 21:13:12 +00:00

137 lines
2.4 KiB
ArmAsm
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// 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 "go_asm.h"
#include "textflag.h"
// See memclrNoHeapPointers Go doc for important implementation constraints.
// func memclrNoHeapPointers(ptr unsafe.Pointer, n 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:
// BSR+branch table make almost all memmove/memclr benchmarks worse. Not worth doing.
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
CMPB internalcpu·X86+const_offsetX86HasSSE2(SB), $1
JNE nosse2
PXOR X0, X0
CMPL BX, $32
JBE _17through32
CMPL BX, $64
JBE _33through64
CMPL BX, $128
JBE _65through128
CMPL BX, $256
JBE _129through256
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