glibc/sysdeps/arm/memcpy.S

321 lines
7.3 KiB
ArmAsm
Raw Normal View History

/* Copyright (C) 2006-2019 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by MontaVista Software, Inc. (written by Nicolas Pitre)
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
2012-03-09 23:56:38 +00:00
License along with the GNU C Library. If not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
<https://www.gnu.org/licenses/>. */
/* Thumb requires excessive IT insns here. */
#define NO_THUMB
#include <sysdep.h>
#include <arm-features.h>
/*
* Data preload for architectures that support it (ARM V5TE and above)
*/
#if (!defined (__ARM_ARCH_2__) && !defined (__ARM_ARCH_3__) \
&& !defined (__ARM_ARCH_3M__) && !defined (__ARM_ARCH_4__) \
&& !defined (__ARM_ARCH_4T__) && !defined (__ARM_ARCH_5__) \
&& !defined (__ARM_ARCH_5T__))
#define PLD(code...) code
#else
#define PLD(code...)
#endif
/*
* This can be used to enable code to cacheline align the source pointer.
* Experiments on tested architectures (StrongARM and XScale) didn't show
* this a worthwhile thing to do. That might be different in the future.
*/
//#define CALGN(code...) code
#define CALGN(code...)
/*
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
#define PULL lsr
#define PUSH lsl
#else
#define PULL lsl
#define PUSH lsr
#endif
.text
.syntax unified
/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
ENTRY(memcpy)
push {r0, r4, lr}
cfi_adjust_cfa_offset (12)
cfi_rel_offset (r4, 4)
cfi_rel_offset (lr, 8)
cfi_remember_state
subs r2, r2, #4
blt 8f
ands ip, r0, #3
PLD( pld [r1, #0] )
bne 9f
ands ip, r1, #3
bne 10f
1: subs r2, r2, #(28)
push {r5 - r8}
cfi_adjust_cfa_offset (16)
cfi_rel_offset (r5, 0)
cfi_rel_offset (r6, 4)
cfi_rel_offset (r7, 8)
cfi_rel_offset (r8, 12)
blt 5f
CALGN( ands ip, r1, #31 )
CALGN( rsb r3, ip, #32 )
CALGN( sbcsne r4, r3, r2 ) @ C is always set here
CALGN( bcs 2f )
CALGN( adr r4, 6f )
CALGN( subs r2, r2, r3 ) @ C gets set
#ifndef ARM_ALWAYS_BX
2013-03-13 19:36:53 +00:00
CALGN( add pc, r4, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2))
#else
2013-03-13 19:36:53 +00:00
CALGN( add r4, r4, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2))
CALGN( bx r4 )
#endif
PLD( pld [r1, #0] )
2: PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 4f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
3: PLD( pld [r1, #124] )
4: ldmia r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
subs r2, r2, #32
stmia r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
bge 3b
PLD( cmn r2, #96 )
PLD( bge 4b )
5: ands ip, r2, #28
rsb ip, ip, #32
#ifndef ARM_ALWAYS_BX
2013-03-13 19:36:53 +00:00
/* C is always clear here. */
addne pc, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
b 7f
#else
beq 7f
push {r10}
cfi_adjust_cfa_offset (4)
cfi_rel_offset (r10, 0)
0: add r10, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
/* If alignment is not perfect, then there will be some
padding (nop) instructions between this BX and label 6.
The computation above assumed that two instructions
later is exactly the right spot. */
add r10, #(6f - (0b + PC_OFS))
bx r10
#endif
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
6: nop
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r3, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r4, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r5, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r6, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r7, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr r8, [r1], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
ldr lr, [r1], #4
#ifndef ARM_ALWAYS_BX
2013-03-13 19:36:53 +00:00
add pc, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
nop
#else
0: add r10, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
/* If alignment is not perfect, then there will be some
padding (nop) instructions between this BX and label 66.
The computation above assumed that two instructions
later is exactly the right spot. */
add r10, #(66f - (0b + PC_OFS))
bx r10
#endif
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
66: nop
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r3, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r4, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r5, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r6, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r7, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str r8, [r0], #4
2013-03-13 19:36:53 +00:00
.p2align ARM_BX_ALIGN_LOG2
str lr, [r0], #4
#ifdef ARM_ALWAYS_BX
pop {r10}
cfi_adjust_cfa_offset (-4)
cfi_restore (r10)
#endif
CALGN( bcs 2b )
7: pop {r5 - r8}
cfi_adjust_cfa_offset (-16)
cfi_restore (r5)
cfi_restore (r6)
cfi_restore (r7)
cfi_restore (r8)
8: movs r2, r2, lsl #31
ldrbne r3, [r1], #1
ldrbcs r4, [r1], #1
ldrbcs ip, [r1]
strbne r3, [r0], #1
strbcs r4, [r0], #1
strbcs ip, [r0]
#if ((defined (__ARM_ARCH_4T__) && defined(__THUMB_INTERWORK__)) \
|| defined (ARM_ALWAYS_BX))
pop {r0, r4, lr}
cfi_adjust_cfa_offset (-12)
cfi_restore (r4)
cfi_restore (lr)
bx lr
#else
pop {r0, r4, pc}
#endif
cfi_restore_state
9: rsb ip, ip, #4
cmp ip, #2
ldrbgt r3, [r1], #1
ldrbge r4, [r1], #1
ldrb lr, [r1], #1
strbgt r3, [r0], #1
strbge r4, [r0], #1
subs r2, r2, ip
strb lr, [r0], #1
blt 8b
ands ip, r1, #3
beq 1b
10: bic r1, r1, #3
cmp ip, #2
ldr lr, [r1], #4
beq 17f
bgt 18f
.macro forward_copy_shift pull push
subs r2, r2, #28
blt 14f
CALGN( ands ip, r1, #31 )
CALGN( rsb ip, ip, #32 )
CALGN( sbcsne r4, ip, r2 ) @ C is always set here
CALGN( subcc r2, r2, ip )
CALGN( bcc 15f )
2013-03-11 17:57:55 +00:00
11: push {r5 - r8, r10}
cfi_adjust_cfa_offset (20)
cfi_rel_offset (r5, 0)
cfi_rel_offset (r6, 4)
cfi_rel_offset (r7, 8)
cfi_rel_offset (r8, 12)
2013-03-11 17:57:55 +00:00
cfi_rel_offset (r10, 16)
PLD( pld [r1, #0] )
PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 13f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
12: PLD( pld [r1, #124] )
13: ldmia r1!, {r4, r5, r6, r7}
mov r3, lr, PULL #\pull
subs r2, r2, #32
ldmia r1!, {r8, r10, ip, lr}
orr r3, r3, r4, PUSH #\push
mov r4, r4, PULL #\pull
orr r4, r4, r5, PUSH #\push
mov r5, r5, PULL #\pull
orr r5, r5, r6, PUSH #\push
mov r6, r6, PULL #\pull
orr r6, r6, r7, PUSH #\push
mov r7, r7, PULL #\pull
orr r7, r7, r8, PUSH #\push
mov r8, r8, PULL #\pull
2013-03-11 17:57:55 +00:00
orr r8, r8, r10, PUSH #\push
mov r10, r10, PULL #\pull
orr r10, r10, ip, PUSH #\push
mov ip, ip, PULL #\pull
orr ip, ip, lr, PUSH #\push
stmia r0!, {r3, r4, r5, r6, r7, r8, r10, ip}
bge 12b
PLD( cmn r2, #96 )
PLD( bge 13b )
2013-03-11 17:57:55 +00:00
pop {r5 - r8, r10}
cfi_adjust_cfa_offset (-20)
cfi_restore (r5)
cfi_restore (r6)
cfi_restore (r7)
cfi_restore (r8)
2013-03-11 17:57:55 +00:00
cfi_restore (r10)
14: ands ip, r2, #28
beq 16f
15: mov r3, lr, PULL #\pull
ldr lr, [r1], #4
subs ip, ip, #4
orr r3, r3, lr, PUSH #\push
str r3, [r0], #4
bgt 15b
CALGN( cmp r2, #0 )
CALGN( bge 11b )
16: sub r1, r1, #(\push / 8)
b 8b
.endm
forward_copy_shift pull=8 push=24
17: forward_copy_shift pull=16 push=16
18: forward_copy_shift pull=24 push=8
END(memcpy)
libc_hidden_builtin_def (memcpy)