Assembly 当我尝试在Armv8程序集中分配数组时,执行冻结
所以我在assemply中编程,这只是一个简单的代码,所以我可以学习如何分配数组,以便稍后在NEON编程中使用它们Assembly 当我尝试在Armv8程序集中分配数组时,执行冻结,assembly,arm,armv8,Assembly,Arm,Armv8,所以我在assemply中编程,这只是一个简单的代码,所以我可以学习如何分配数组,以便稍后在NEON编程中使用它们 ASM_FUNC(FPE) .data .balign 8 array: .skip 80 array1: .word 10,20,30,40 .text ldr x0,=array mov x1,#10 check: cmp x1,#1 bne loop b exit loop: str x1,[x0],#8 //St
ASM_FUNC(FPE)
.data
.balign 8
array: .skip 80
array1: .word 10,20,30,40
.text
ldr x0,=array
mov x1,#10
check:
cmp x1,#1
bne loop
b exit
loop:
str x1,[x0],#8 //Stores the value in x1 into x0 and moves the address +8 bytes
sub x1,x1,#1 //x1--
b check
exit:
mov x0,#11
ret
因此,对某些部分进行了注释,以便我可以尝试查找代码的中断位置(我的系统上没有调试)。我开始评论计算部分,并在ret之前添加了一个mov x0,#11,看看问题是否出在计算上。原来不是。 当我取消对数组的注释:.skip 80和ldr x0,=array时,如果没有响应,我的应用程序将只停留在那里 谁能告诉我我做错了什么? 我在armv8总成上使用A64 从该c程序调用入口点:
void PocAsm_EntryPoint ( )
{
Print(L"========== ASM ==========\n");
UINT32 fff = FPE();
Print(L" %d \n",fff);
Print(L"=========== ASM ===========\n");
Print(L"Test version 0.24 \n");
return 0;
}
不幸的是,我没有找到打印的定义,因此我很抱歉,这是试图回答以下问题:
FPE()
函数是否按照预期工作,同时使用标准工具(如qemu-system-aarch64
和GDB
)从等式中删除所有其他内容
FPE()
函数的代码将为Cortex-A53 qemu virt机器编译
先决条件:
- qemu-system-aarch64已安装:
sudo-apt-get-install-qemu-system-arm
Windows 10:从下载并安装
qemu-w64-setup-20201120.exe安装程序
- 已安装
Cortex-A
的aarch64无elf
工具链。可从以下网址下载。Linux和Windows 10都有相应的版本
FPE.s
:
.arch armv8-a
.file "FPE.s"
.data
.balign 8
.globl array
array: .skip 80
array1: .word 10,20,30,40
.text
.align 2
.globl FPE
FPE:
ldr x0,=array
mov x1,#10
check:
cmp x1,#1
bne loop
b exit
loop:
str x1,[x0],#8 //Stores the value in x1 into x0 and moves the address +8 bits
sub x1,x1,#1 //x1--
b check
exit:
mov x0,#11
ret
.end
.title startup64.s
.arch armv8-a
.text
.section .text.startup,"ax"
.globl _start
_start:
ldr x0, =__StackTop
mov sp, x0
bl FPE
wait: wfe
b wait
.end
startup.s
:
.arch armv8-a
.file "FPE.s"
.data
.balign 8
.globl array
array: .skip 80
array1: .word 10,20,30,40
.text
.align 2
.globl FPE
FPE:
ldr x0,=array
mov x1,#10
check:
cmp x1,#1
bne loop
b exit
loop:
str x1,[x0],#8 //Stores the value in x1 into x0 and moves the address +8 bits
sub x1,x1,#1 //x1--
b check
exit:
mov x0,#11
ret
.end
.title startup64.s
.arch armv8-a
.text
.section .text.startup,"ax"
.globl _start
_start:
ldr x0, =__StackTop
mov sp, x0
bl FPE
wait: wfe
b wait
.end
建筑:
我们将为qemu virt机器构建FPE.elf
(RAM从0x40000000
开始):
调试:
在shell中启动qemu:
/opt/qemu-5.1.0/bin/qemu-system-aarch64 -semihosting -m 1M -nographic -serial telnet::4444,server,nowait -machine virt,gic-version=2,secure=on,virtualization=on -S -gdb tcp::1234,ipv4 -cpu cortex-a53 -kernel FPE.elf
启动GDB
opt/arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-gdb --quiet -nx -ex 'target remote localhost:1234' -ex 'load' --ex 'b _start' -ex 'b exit' FPE.elf
GDB
应启动:
Reading symbols from FPE.elf...
Remote debugging using localhost:1234
_start () at startup.s:7
7 ldr x0, =__StackTop
Loading section .text, size 0x50 lma 0x40000000
Loading section .data, size 0x60 lma 0x40010050
Start address 0x40000000, load size 176
Transfer rate: 85 KB/sec, 88 bytes/write.
Breakpoint 1 at 0x40000000: file startup.s, line 7.
Breakpoint 2 at 0x40000040: file FPE.s, line 28.
从这一点开始,可以使用命令stepi
、p/x$x0
和x/10g 0x40010050
来监视程序行为,直到它到达退出
标签
在这里,我们将在开始和退出断点处显示数组中的10个元素:
gdb) x/10g 0x40010050
0x40010050: 0 0
0x40010060: 0 0
0x40010070: 0 0
0x40010080: 0 0
0x40010090: 0 0
(gdb) continue
Continuing.
Breakpoint 2, exit () at FPE.s:28
28 mov x0,#11
(gdb) x/10g 0x40010050
0x40010050: 10 9
0x40010060: 8 7
0x40010070: 6 5
0x40010080: 4 3
0x40010090: 2 0
从这一点开始单步执行表示程序从执行中正确返回:
(gdb) stepi
29 ret
(gdb) stepi
wait () at startup.s:10
10 wait: wfe
(gdb) stepi
11 b wait
(gdb) stepi
10 wait: wfe
因此,问题的答案是:是的,FPE()
函数的代码工作正常
同样的过程可以在Windows 10上运行,这只是调整用于运行aarch64 none-elf-gcc
、qemu-system-aarch64
和GDB
的三个命令的问题
将目标文件的转储与我测试的转储进行比较可能有助于了解问题:
/opt.arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-as -o FPE.o FPE.s
/opt/arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-objdump -D FPE.o
FPE.o: file format elf64-littleaarch64
Disassembly of section .text:
0000000000000000 <FPE>:
0: 58000140 ldr x0, 28 <exit+0x8>
4: d2800141 mov x1, #0xa // #10
0000000000000008 <check>:
8: f100043f cmp x1, #0x1
c: 54000041 b.ne 14 <loop> // b.any
10: 14000004 b 20 <exit>
0000000000000014 <loop>:
14: f8008401 str x1, [x0], #8
18: d1000421 sub x1, x1, #0x1
1c: 17fffffb b 8 <check>
0000000000000020 <exit>:
20: d2800160 mov x0, #0xb // #11
24: d65f03c0 ret
...
Disassembly of section .data:
0000000000000000 <array>:
...
0000000000000050 <array1>:
50: 0000000a .inst 0x0000000a ; undefined
54: 00000014 .inst 0x00000014 ; undefined
58: 0000001e .inst 0x0000001e ; undefined
5c: 00000028 .inst 0x00000028 ; undefined
/opt.arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-as-o FPE.o FPE.s
/opt/arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-objdump-D FPE.o
o:文件格式elf64-LittleArch64
第节的分解。正文:
0000000000000000 :
0:58000140 ldr x0,28
4:d2800141 mov x1,#0xa/#10
0000000000000008 :
8:f100043f cmp x1,#0x1
c:54000041北东14//b.任何
10:1400004 b 20
0000000000000014 :
14:f8008401 str x1[x0],#8
18:d1000421子x1,x1,#0x1
1c:17FFFB b 8
0000000000000020 :
20:d2800160 mov x0,#0xb/#11
24:d65f03c0 ret
...
分解截面。数据:
0000000000000000 :
...
0000000000000050 :
50:0000000a.指令0x0000000a;未定义
54:00000014.指令0x00000014;未定义
58:0000001e指令0x0000001e;未定义
5c:00000028.指令0x00000028;未定义
转储最小示例的完整ELF文件将给出:
opt/arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-objdump -D FPE.elf
FPE.elf: file format elf64-littleaarch64
Disassembly of section .text:
0000000040000000 <_start>:
40000000: 580000c0 ldr x0, 40000018 <wait+0xc>
40000004: 9100001f mov sp, x0
40000008: 94000006 bl 40000020 <FPE>
000000004000000c <wait>:
4000000c: d503205f wfe
40000010: 17ffffff b 4000000c <wait>
40000014: 00000000 .inst 0x00000000 ; undefined
40000018: 40010000 .inst 0x40010000 ; undefined
4000001c: 00000000 .inst 0x00000000 ; undefined
0000000040000020 <FPE>:
40000020: 58000140 ldr x0, 40000048 <exit+0x8>
40000024: d2800141 mov x1, #0xa // #10
0000000040000028 <check>:
40000028: f100043f cmp x1, #0x1
4000002c: 54000041 b.ne 40000034 <loop> // b.any
40000030: 14000004 b 40000040 <exit>
0000000040000034 <loop>:
40000034: f8008401 str x1, [x0], #8
40000038: d1000421 sub x1, x1, #0x1
4000003c: 17fffffb b 40000028 <check>
0000000040000040 <exit>:
40000040: d2800160 mov x0, #0xb // #11
40000044: d65f03c0 ret
40000048: 40010050 .inst 0x40010050 ; undefined
4000004c: 00000000 .inst 0x00000000 ; undefined
Disassembly of section .data:
0000000040010050 <__data_start>:
...
00000000400100a0 <array1>:
400100a0: 0000000a .inst 0x0000000a ; undefined
400100a4: 00000014 .inst 0x00000014 ; undefined
400100a8: 0000001e .inst 0x0000001e ; undefined
400100ac: 00000028 .inst 0x00000028 ; undefined
opt/arm/9/gcc-arm-9.2-2019.12-x86_64-aarch64-none-elf/bin/aarch64-none-elf-objdump-D FPE.elf
FPE.elf:文件格式elf64-LittleArch64
第节的分解。正文:
0000000040000000 :
40000000:580000c0 ldr x0,40000018
40000004:9100001f mov sp,x0
40000008:94000006 bl 40000020
00000000 4000000C:
4000000c:d503205f wfe
40000010:17ffffff b 4000000c
40000014:00000000。指令0x00000000;未定义
40000018:40010000。仪器0x40010000;未定义
4000001c:00000000。仪器0x00000000;未定义
0000000040000020 :
40000020:58000140 ldr x0,40000048
40000024:d2800141 mov x1,#0xa/#10
0000000040000028 :
40000028:f100043f cmp x1,#0x1
4000002c:54000041 b.ne 40000034//b.any
40000030:1400004 b 40000040
0000000040000034 :
40000034:f8008401 str x1[x0],#8
40000038:d1000421子x1,x1,#0x1
4000003c:17fffffb b 40000028
0000000040000040 :
40000040:d2800160 mov x0,#0xb/#11
40000044:d65f03c0 ret
40000048:40010050。仪器0x40010050;未定义
4000004c:00000000。仪器0x00000000;未定义
分解截面。数据:
0000000040010050 :
...
00000000 400100A0:
400100a0:0000000a.仪器0x0000000a;未定义
400100a4:00000014.指令0x00000014;未定义
400100a8:0000001e仪器0x0000001e;未定义
400100ac:00000028。仪器0x00000028;未定义
您在一台64位计算机上,64位值是8字节,而不是4字节。如果要存储32位值,则应存储w1
,而不是x1
。此外,代码需要一个入口点。你是如何装配和安装的