mirror of
https://github.com/checkpoint-restore/criu.git
synced 2026-07-23 18:19:39 +00:00
f233b86a02
This is the difference between two commits criu-dev/b0f6f293/Unify own memcpy/memset/memcmp master/0367a1fe/Drop prefix from own memcpy/memset/memcmp that makes criu-dev after rebase on master with latter commit be the same as it was with former commit before rebase. Signed-off-by: Kir Kolyshkin <kir@openvz.org> Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>
212 lines
3.9 KiB
ArmAsm
212 lines
3.9 KiB
ArmAsm
/*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
*
|
|
* Copyright (C) IBM Corporation, 2012
|
|
*
|
|
* Author: Anton Blanchard <anton@au.ibm.com>
|
|
*
|
|
* --
|
|
* Copied from the kernel file arch/powerpc/lib/memcpy_power7.S
|
|
* Altivec support has been removed so we don't taint restored process.
|
|
*/
|
|
#include "common/asm/linkage.h"
|
|
|
|
/*
|
|
* When building the parasite code, the compiler may rely on the C library
|
|
* service memcpy to initialise big local variable in the stack.
|
|
*/
|
|
ENTRY(memcpy)
|
|
cmpldi r5,16
|
|
std r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
|
|
blt .Lshort_copy
|
|
|
|
.Lnonvmx_copy:
|
|
/* Get the source 8B aligned */
|
|
neg r6,r4
|
|
mtocrf 0x01,r6
|
|
clrldi r6,r6,(64-3)
|
|
|
|
bf cr7*4+3,1f
|
|
lbz r0,0(r4)
|
|
addi r4,r4,1
|
|
stb r0,0(r3)
|
|
addi r3,r3,1
|
|
|
|
1: bf cr7*4+2,2f
|
|
lhz r0,0(r4)
|
|
addi r4,r4,2
|
|
sth r0,0(r3)
|
|
addi r3,r3,2
|
|
|
|
2: bf cr7*4+1,3f
|
|
lwz r0,0(r4)
|
|
addi r4,r4,4
|
|
stw r0,0(r3)
|
|
addi r3,r3,4
|
|
|
|
3: sub r5,r5,r6
|
|
cmpldi r5,128
|
|
blt 5f
|
|
|
|
mflr r0
|
|
stdu r1,-STACKFRAMESIZE(r1)
|
|
std r14,STK_REG(R14)(r1)
|
|
std r15,STK_REG(R15)(r1)
|
|
std r16,STK_REG(R16)(r1)
|
|
std r17,STK_REG(R17)(r1)
|
|
std r18,STK_REG(R18)(r1)
|
|
std r19,STK_REG(R19)(r1)
|
|
std r20,STK_REG(R20)(r1)
|
|
std r21,STK_REG(R21)(r1)
|
|
std r22,STK_REG(R22)(r1)
|
|
std r0,STACKFRAMESIZE+16(r1)
|
|
|
|
srdi r6,r5,7
|
|
mtctr r6
|
|
|
|
/* Now do cacheline (128B) sized loads and stores. */
|
|
.align 5
|
|
4:
|
|
ld r0,0(r4)
|
|
ld r6,8(r4)
|
|
ld r7,16(r4)
|
|
ld r8,24(r4)
|
|
ld r9,32(r4)
|
|
ld r10,40(r4)
|
|
ld r11,48(r4)
|
|
ld r12,56(r4)
|
|
ld r14,64(r4)
|
|
ld r15,72(r4)
|
|
ld r16,80(r4)
|
|
ld r17,88(r4)
|
|
ld r18,96(r4)
|
|
ld r19,104(r4)
|
|
ld r20,112(r4)
|
|
ld r21,120(r4)
|
|
addi r4,r4,128
|
|
std r0,0(r3)
|
|
std r6,8(r3)
|
|
std r7,16(r3)
|
|
std r8,24(r3)
|
|
std r9,32(r3)
|
|
std r10,40(r3)
|
|
std r11,48(r3)
|
|
std r12,56(r3)
|
|
std r14,64(r3)
|
|
std r15,72(r3)
|
|
std r16,80(r3)
|
|
std r17,88(r3)
|
|
std r18,96(r3)
|
|
std r19,104(r3)
|
|
std r20,112(r3)
|
|
std r21,120(r3)
|
|
addi r3,r3,128
|
|
bdnz 4b
|
|
|
|
clrldi r5,r5,(64-7)
|
|
|
|
ld r14,STK_REG(R14)(r1)
|
|
ld r15,STK_REG(R15)(r1)
|
|
ld r16,STK_REG(R16)(r1)
|
|
ld r17,STK_REG(R17)(r1)
|
|
ld r18,STK_REG(R18)(r1)
|
|
ld r19,STK_REG(R19)(r1)
|
|
ld r20,STK_REG(R20)(r1)
|
|
ld r21,STK_REG(R21)(r1)
|
|
ld r22,STK_REG(R22)(r1)
|
|
addi r1,r1,STACKFRAMESIZE
|
|
|
|
/* Up to 127B to go */
|
|
5: srdi r6,r5,4
|
|
mtocrf 0x01,r6
|
|
|
|
6: bf cr7*4+1,7f
|
|
ld r0,0(r4)
|
|
ld r6,8(r4)
|
|
ld r7,16(r4)
|
|
ld r8,24(r4)
|
|
ld r9,32(r4)
|
|
ld r10,40(r4)
|
|
ld r11,48(r4)
|
|
ld r12,56(r4)
|
|
addi r4,r4,64
|
|
std r0,0(r3)
|
|
std r6,8(r3)
|
|
std r7,16(r3)
|
|
std r8,24(r3)
|
|
std r9,32(r3)
|
|
std r10,40(r3)
|
|
std r11,48(r3)
|
|
std r12,56(r3)
|
|
addi r3,r3,64
|
|
|
|
/* Up to 63B to go */
|
|
7: bf cr7*4+2,8f
|
|
ld r0,0(r4)
|
|
ld r6,8(r4)
|
|
ld r7,16(r4)
|
|
ld r8,24(r4)
|
|
addi r4,r4,32
|
|
std r0,0(r3)
|
|
std r6,8(r3)
|
|
std r7,16(r3)
|
|
std r8,24(r3)
|
|
addi r3,r3,32
|
|
|
|
/* Up to 31B to go */
|
|
8: bf cr7*4+3,9f
|
|
ld r0,0(r4)
|
|
ld r6,8(r4)
|
|
addi r4,r4,16
|
|
std r0,0(r3)
|
|
std r6,8(r3)
|
|
addi r3,r3,16
|
|
|
|
9: clrldi r5,r5,(64-4)
|
|
|
|
/* Up to 15B to go */
|
|
.Lshort_copy:
|
|
mtocrf 0x01,r5
|
|
bf cr7*4+0,12f
|
|
lwz r0,0(r4) /* Less chance of a reject with word ops */
|
|
lwz r6,4(r4)
|
|
addi r4,r4,8
|
|
stw r0,0(r3)
|
|
stw r6,4(r3)
|
|
addi r3,r3,8
|
|
|
|
12: bf cr7*4+1,13f
|
|
lwz r0,0(r4)
|
|
addi r4,r4,4
|
|
stw r0,0(r3)
|
|
addi r3,r3,4
|
|
|
|
13: bf cr7*4+2,14f
|
|
lhz r0,0(r4)
|
|
addi r4,r4,2
|
|
sth r0,0(r3)
|
|
addi r3,r3,2
|
|
|
|
14: bf cr7*4+3,15f
|
|
lbz r0,0(r4)
|
|
stb r0,0(r3)
|
|
|
|
15: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
|
|
blr
|
|
|
|
.Lunwind_stack_nonvmx_copy:
|
|
addi r1,r1,STACKFRAMESIZE
|
|
b .Lnonvmx_copy
|
|
|