假设我有：
int some_bss_values[8];
int some_data_values[] = {1,2,3,4,5,6,7,8};
int const some_rodata_values[] = {9,10,11,12,13,14,15,16};
//Some silly code that shows usage of bss, data, and rodata
int some_function(int x) {
some_bss_values[x] = some_rodata_values[x];
return some_data_values[x]++;
}
我的最终目标是将其编译为可以在运行时加载的二进制 blob（这是一个嵌入式系统，因此没有动态链接器甚至 ELF 加载器）。具体来说，我希望能够在任何地址加载此 blob（包括数据）并跳转到
some_function我尝试编写一个简单的链接器脚本：
SECTIONS {
.text : {
*(.text);
}
.data : {
*(.bss); /*Placed here because I explicitly want the BSS to be part of the image*/
*(.data);
} =0
.rodata : { *(.rodata); }
}
我将示例代码编译为 ELF：
# Using -g and -O0 so we can have a readable disassembly. I'm actually using
# a cross-compiler but we'll use regular gcc with x86 for the sake of the question
gcc -Wl,-esome_function -o t.elf -fPIC -nostdlib -T my_linker_script.ld -g -O0 my_code.cpp
然后我生成了一个图像：
objcopy -Obinary -j.text -j.data -j.rodata t.elf t.bin
上面的命令生成了一个二进制 blob 供我使用，包括 BSS 的显式零，但查看反汇编会凸显出一个问题：
objdump -sSxC t.elf
...
Sections:
Idx Name Size VMA LMA File off Algn
0 .note.gnu.build-id 00000024 0000000000000000 0000000000000000 00200000 2**2
CONTENTS, ALLOC, LOAD, READONLY, DATA
1 .text 00000053 0000000000000024 0000000000000024 00200024 2**0
CONTENTS, ALLOC, LOAD, READONLY, CODE
2 .data 00000040 0000000000000080 0000000000000080 00200080 2**5
CONTENTS, ALLOC, LOAD, DATA
...
Disassembly of section .text:
0000000000000024 <some_function(int)>:
int some_bss_values[8];
int some_data_values[] = {1,2,3,4,5,6,7,8};
int const some_rodata_values[] = {9,10,11,12,13,14,15,16};
//Some silly code that shows usage of bss, data, and rodata
int some_function(int x) {
24: 55 push %rbp
25: 48 89 e5 mov %rsp,%rbp
28: 89 7d fc mov %edi,-0x4(%rbp)
some_bss_values[x] = some_rodata_values[x];
2b: 8b 45 fc mov -0x4(%rbp),%eax
2e: 48 98 cltq
30: 48 8d 14 85 00 00 00 lea 0x0(,%rax,4),%rdx
37: 00
38: 48 8d 05 a1 00 00 00 lea 0xa1(%rip),%rax # e0 <some_rodata_values>
3f: 8b 0c 02 mov (%rdx,%rax,1),%ecx
42: 48 c7 c0 80 00 00 00 mov $0x80,%rax
49: 8b 55 fc mov -0x4(%rbp),%edx
4c: 48 63 d2 movslq %edx,%rdx
4f: 89 0c 90 mov %ecx,(%rax,%rdx,4)
return some_data_values[x]++;
52: 48 c7 c0 a0 00 00 00 mov $0xa0,%rax
59: 8b 55 fc mov -0x4(%rbp),%edx
5c: 48 63 d2 movslq %edx,%rdx
5f: 8b 04 90 mov (%rax,%rdx,4),%eax
62: 8d 70 01 lea 0x1(%rax),%esi
65: 48 c7 c2 a0 00 00 00 mov $0xa0,%rdx
6c: 8b 4d fc mov -0x4(%rbp),%ecx
6f: 48 63 c9 movslq %ecx,%rcx
72: 89 34 8a mov %esi,(%rdx,%rcx,4)
}
75: 5d pop %rbp
76: c3 retq
在这里我们看到从
rodata0xA0如何指示 gcc/ld 对 BSS 和
.data编译器和链接器如何生成用于访问变量的代码的详细信息在很大程度上取决于您的体系结构，因此我将在本答案中重点关注 RISC-V（64 位）。我基本上只是复制了您正在做的事情，除了我在链接器脚本中指定了入口点，并且一切正常。最终的程序集通过引用全局偏移表来访问变量，全局偏移表是对象中的地址数组。
$ cat test.c
int some_bss_values[8];
int some_data_values[] = {1,2,3,4,5,6,7,8};
int const some_rodata_values[] = {9,10,11,12,13,14,15,16};
//Some silly code that shows usage of bss, data, and rodata
int some_function(int x) {
some_bss_values[x] = some_rodata_values[x];
return some_data_values[x]++;
}
$ cat test.ld
ENTRY(some_function)
SECTIONS {
.text : {
*(.text);
}
.data : {
*(.bss); /*Placed here because I explicitly want the BSS to be part of the image*/
*(.data);
} =0
.rodata : { *(.rodata); }
}
$ riscv64-unknown-elf-gcc -Og -Wall test.c -fPIC -T test.ld -nostdlib && riscv64-unknown-elf-objdump -d a.out
c:/msys64/mingw64/bin/../lib/gcc/riscv64-unknown-elf/12.2.0/../../../../riscv64-unknown-elf/bin/ld.exe: warning: section `.data' type changed to PROGBITS
c:/msys64/mingw64/bin/../lib/gcc/riscv64-unknown-elf/12.2.0/../../../../riscv64-unknown-elf/bin/ld.exe: warning: a.out has a LOAD segment with RWX permissions
a.out: file format elf64-littleriscv
Disassembly of section .text:
0000000000000000 <some_function>:
0: 050a sll a0,a0,0x2
2: 00000797 auipc a5,0x0
6: 0867b783 ld a5,134(a5) # 88 <_GLOBAL_OFFSET_TABLE_+0x18>
a: 97aa add a5,a5,a0
c: 4398 lw a4,0(a5)
e: 00000797 auipc a5,0x0
12: 06a7b783 ld a5,106(a5) # 78 <_GLOBAL_OFFSET_TABLE_+0x8>
16: 97aa add a5,a5,a0
18: c398 sw a4,0(a5)
1a: 00000797 auipc a5,0x0
1e: 0667b783 ld a5,102(a5) # 80 <_GLOBAL_OFFSET_TABLE_+0x10>
22: 97aa add a5,a5,a0
24: 4388 lw a0,0(a5)
26: 0015071b addw a4,a0,1
2a: c398 sw a4,0(a5)
2c: 8082 ret