185 lines
2.7 KiB
ArmAsm
185 lines
2.7 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
*
|
|
* Copyright (C) IBM Corporation, 2012
|
|
*
|
|
* Author: Anton Blanchard <anton@au.ibm.com>
|
|
*/
|
|
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/linkage.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/export.h>
|
|
|
|
.section ".toc","aw"
|
|
PPC64_CACHES:
|
|
.tc ppc64_caches[TC],ppc64_caches
|
|
.section ".text"
|
|
|
|
/**
|
|
* __arch_clear_user: - Zero a block of memory in user space, with less checking.
|
|
* @to: Destination address, in user space.
|
|
* @n: Number of bytes to zero.
|
|
*
|
|
* Zero a block of memory in user space. Caller must check
|
|
* the specified block with access_ok() before calling this function.
|
|
*
|
|
* Returns number of bytes that could not be cleared.
|
|
* On success, this will be zero.
|
|
*/
|
|
|
|
.macro err1
|
|
100:
|
|
EX_TABLE(100b,.Ldo_err1)
|
|
.endm
|
|
|
|
.macro err2
|
|
200:
|
|
EX_TABLE(200b,.Ldo_err2)
|
|
.endm
|
|
|
|
.macro err3
|
|
300:
|
|
EX_TABLE(300b,.Ldo_err3)
|
|
.endm
|
|
|
|
.Ldo_err1:
|
|
mr r3,r8
|
|
|
|
.Ldo_err2:
|
|
mtctr r4
|
|
1:
|
|
err3; stb r0,0(r3)
|
|
addi r3,r3,1
|
|
addi r4,r4,-1
|
|
bdnz 1b
|
|
|
|
.Ldo_err3:
|
|
mr r3,r4
|
|
blr
|
|
|
|
_GLOBAL_TOC(__arch_clear_user)
|
|
cmpdi r4,32
|
|
neg r6,r3
|
|
li r0,0
|
|
blt .Lshort_clear
|
|
mr r8,r3
|
|
mtocrf 0x01,r6
|
|
clrldi r6,r6,(64-3)
|
|
|
|
/* Get the destination 8 byte aligned */
|
|
bf cr7*4+3,1f
|
|
err1; stb r0,0(r3)
|
|
addi r3,r3,1
|
|
|
|
1: bf cr7*4+2,2f
|
|
err1; sth r0,0(r3)
|
|
addi r3,r3,2
|
|
|
|
2: bf cr7*4+1,3f
|
|
err1; stw r0,0(r3)
|
|
addi r3,r3,4
|
|
|
|
3: sub r4,r4,r6
|
|
|
|
cmpdi r4,32
|
|
cmpdi cr1,r4,512
|
|
blt .Lshort_clear
|
|
bgt cr1,.Llong_clear
|
|
|
|
.Lmedium_clear:
|
|
srdi r6,r4,5
|
|
mtctr r6
|
|
|
|
/* Do 32 byte chunks */
|
|
4:
|
|
err2; std r0,0(r3)
|
|
err2; std r0,8(r3)
|
|
err2; std r0,16(r3)
|
|
err2; std r0,24(r3)
|
|
addi r3,r3,32
|
|
addi r4,r4,-32
|
|
bdnz 4b
|
|
|
|
.Lshort_clear:
|
|
/* up to 31 bytes to go */
|
|
cmpdi r4,16
|
|
blt 6f
|
|
err2; std r0,0(r3)
|
|
err2; std r0,8(r3)
|
|
addi r3,r3,16
|
|
addi r4,r4,-16
|
|
|
|
/* Up to 15 bytes to go */
|
|
6: mr r8,r3
|
|
clrldi r4,r4,(64-4)
|
|
mtocrf 0x01,r4
|
|
bf cr7*4+0,7f
|
|
err1; std r0,0(r3)
|
|
addi r3,r3,8
|
|
|
|
7: bf cr7*4+1,8f
|
|
err1; stw r0,0(r3)
|
|
addi r3,r3,4
|
|
|
|
8: bf cr7*4+2,9f
|
|
err1; sth r0,0(r3)
|
|
addi r3,r3,2
|
|
|
|
9: bf cr7*4+3,10f
|
|
err1; stb r0,0(r3)
|
|
|
|
10: li r3,0
|
|
blr
|
|
|
|
.Llong_clear:
|
|
ld r5,PPC64_CACHES@toc(r2)
|
|
|
|
bf cr7*4+0,11f
|
|
err2; std r0,0(r3)
|
|
addi r3,r3,8
|
|
addi r4,r4,-8
|
|
|
|
/* Destination is 16 byte aligned, need to get it cache block aligned */
|
|
11: lwz r7,DCACHEL1LOGBLOCKSIZE(r5)
|
|
lwz r9,DCACHEL1BLOCKSIZE(r5)
|
|
|
|
/*
|
|
* With worst case alignment the long clear loop takes a minimum
|
|
* of 1 byte less than 2 cachelines.
|
|
*/
|
|
sldi r10,r9,2
|
|
cmpd r4,r10
|
|
blt .Lmedium_clear
|
|
|
|
neg r6,r3
|
|
addi r10,r9,-1
|
|
and. r5,r6,r10
|
|
beq 13f
|
|
|
|
srdi r6,r5,4
|
|
mtctr r6
|
|
mr r8,r3
|
|
12:
|
|
err1; std r0,0(r3)
|
|
err1; std r0,8(r3)
|
|
addi r3,r3,16
|
|
bdnz 12b
|
|
|
|
sub r4,r4,r5
|
|
|
|
13: srd r6,r4,r7
|
|
mtctr r6
|
|
mr r8,r3
|
|
14:
|
|
err1; dcbz 0,r3
|
|
add r3,r3,r9
|
|
bdnz 14b
|
|
|
|
and r4,r4,r10
|
|
|
|
cmpdi r4,32
|
|
blt .Lshort_clear
|
|
b .Lmedium_clear
|
|
EXPORT_SYMBOL(__arch_clear_user)
|