深度探索Linux操作系统 —— 编译过程分析
linux系统构建——1.交叉编译工具链
深度探索Linux操作系统 —— 编译过程分析
深度探索Linux操作系统 —— 构建工具链
深度探索Linux操作系统 —— 构建内核
深度探索Linux操作系统 —— 构建initramfs
深度探索Linux操作系统 —— 从内核空间到用户空间
深度探索Linux操作系统 —— 构建根文件系统
深度探索Linux操作系统 —— 构建桌面环境
深度探索Linux操作系统 —— Linux图形原理探讨
文章目录
- 一、源码
-
- foo.h
- hello.c
- foo1.c
- foo2.c
- GCC 指令
- 预处理
-
- 命令
- hello.i
- 编译（Compile only）
-
- 命令
- foo2.s
- 汇编
-
- 命令
- readelf
- readelf -h
- readelf -S
- readelf -r
- readelf -s
- strip
- 链接
本文基于《深度探索Linux操作系统：系统构建和原理解析》
一、源码
foo.h
#if !defined(_FOO_H_)
#define _FOO_H_
#define PI 3.1415926
#define AREA
struct foo_struct {
int a;
};
#endif // _FOO_H_
hello.c
#include "foo.h"
void foo2_func();
extern int foo2;
int main(int argc, char const *argv[]) {
int result;
int r = 5;
#ifdef AREA
result = PI * r * r;
#else
result = PI * r * 2;
#endif
r = foo2;
foo2_func();
return 0;
}
foo1.c
#include foo2.c
#include GCC 指令
gcc --help
-v Display the programs invoked by the compiler.
-E Preprocess only; do not compile, assemble or link.
-S Compile only; do not assemble or link.
-c Compile and assemble, but do not link.
-pie Create a dynamically linked position independent
executable.
-shared Create a shared library.
-x <language> Specify the language of the following input files.
Permissible languages include: c c++ assembler none
'none' means revert to the default behavior of
guessing the language based on the file's extension.
预处理
命令
gcc -E hello.c -o hello.i
hello.i
# 0 "hello.c"
# 0 ""
# 0 ""
# 1 "/usr/include/stdc-predef.h" 1 3 4
# 0 "" 2
# 1 "hello.c"
# 1 "foo.h" 1
struct foo_struct {
int a;
};
# 2 "hello.c" 2
void foo2_func();
extern int foo2;
int main(int argc, char const *argv[]) {
int result;
int r = 5;
result = 3.1415926 * r * r;
r = foo2;
foo2_func();
return 0;
}
编译（Compile only）
命令
-S Compile only; do not assemble or link.
gcc -S foo2.c
foo2.s
.file "foo2.c"
.text
.globl foo2
.bss
.align 4
.type foo2, @object
.size foo2, 4
foo2:
.zero 4
.local foo2_static
.comm foo2_static,4,4
.section .rodata
.LC0:
.string "====>"
.text
.type foo2_func_1, @function
foo2_func_1:
.LFB0:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
movq %rsp, %rbp
.cfi_def_cfa_register 6
leaq .LC0(%rip), %rax
movq %rax, %rdi
movl $0, %eax
call printf@PLT
nop
popq %rbp
.cfi_def_cfa 7, 8
ret
.cfi_endproc
.LFE0:
.size foo2_func_1, .-foo2_func_1
.section .rodata
.LC1:
.string "a: %d"
.text
.globl foo2_func
.type foo2_func, @function
foo2_func:
.LFB1:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
movq %rsp, %rbp
.cfi_def_cfa_register 6
subq $16, %rsp
movl $1, -4(%rbp)
movl -4(%rbp), %eax
movl %eax, %esi
leaq .LC1(%rip), %rax
movq %rax, %rdi
movl $0, %eax
call printf@PLT
nop
leave
.cfi_def_cfa 7, 8
ret
.cfi_endproc
.LFE1:
.size foo2_func, .-foo2_func
.ident "GCC: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0"
.section .note.GNU-stack,"",@progbits
.section .note.gnu.property,"a"
.align 8
.long 1f - 0f
.long 4f - 1f
.long 5
0:
.string "GNU"
1:
.align 8
.long 0xc0000002
.long 3f - 2f
2:
.long 0x3
3:
.align 8
4:
在文件 foo2.c 中，除定义了一个全局变量 foo2 外，仅定义了一个函数 foo2_func，而该函数体中也只有区区一行代码，但为什么产生的汇编代码如此之长？事实上，仔细观察可以发现，文件 foo2.s 中相当一部分是汇编器的伪指令。伪指令是不参与CPU运行的，只指导编译链接过程。比如，代码中以 “.cfi” 开头的伪指令是辅助汇编器创建栈帧（stack frame）信息的。
汇编
命令
-c Compile and assemble, but do not link.
gcc -c hello.c foo1.c foo2.c
# 执行后产生 hello.o foo1.o foo2.o
readelf
readelf --help
用法：readelf <选项> elf-文件
显示关于 ELF 格式文件内容的信息
Options are:
-a --all Equivalent to: -h -l -S -s -r -d -V -A -I
-h --file-header Display the ELF file header
-l --program-headers Display the program headers
--segments An alias for --program-headers
-S --section-headers Display the sections' header
--sections An alias for --section-headers
-g --section-groups Display the section groups
-t --section-details Display the section details
-e --headers Equivalent to: -h -l -S
-s --syms Display the symbol table
--symbols An alias for --syms
--dyn-syms Display the dynamic symbol table
--lto-syms Display LTO symbol tables
--sym-base=[0|8|10|16]
Force base for symbol sizes. The options are
mixed (the default), octal, decimal, hexadecimal.
-C --demangle[=STYLE] Decode mangled/processed symbol names
STYLE can be "none", "auto", "gnu-v3", "java",
"gnat", "dlang", "rust"
--no-demangle Do not demangle low-level symbol names. (default)
--recurse-limit Enable a demangling recursion limit. (default)
--no-recurse-limit Disable a demangling recursion limit
-U[dlexhi] --unicode=[default|locale|escape|hex|highlight|invalid]
Display unicode characters as determined by the current locale
(default), escape sequences, "" , highlighted
escape sequences, or treat them as invalid and display as
"{hex sequences}"
-n --notes Display the core notes (if present)
-r --relocs Display the relocations (if present)
-u --unwind Display the unwind info (if present)
-d --dynamic Display the dynamic section (if present)
-V --version-info Display the version sections (if present)
-A --arch-specific Display architecture specific information (if any)
-c --archive-index Display the symbol/file index in an archive
-D --use-dynamic Use the dynamic section info when displaying symbols
-L --lint|--enable-checks
Display warning messages for possible problems
-x --hex-dump=<number|name>
Dump the contents of section <number|name> as bytes
-p --string-dump=<number|name>
Dump the contents of section <number|name> as strings
-R --relocated-dump=<number|name>
Dump the relocated contents of section <number|name>
-z --decompress Decompress section before dumping it
-w --debug-dump[a/=abbrev, A/=addr, r/=aranges, c/=cu_index, L/=decodedline,
f/=frames, F/=frames-interp, g/=gdb_index, i/=info, o/=loc,
m/=macro, p/=pubnames, t/=pubtypes, R/=Ranges, l/=rawline,
s/=str, O/=str-offsets, u/=trace_abbrev, T/=trace_aranges,
U/=trace_info]
Display the contents of DWARF debug sections
-wk --debug-dump=links Display the contents of sections that link to separate
debuginfo files
-P --process-links Display the contents of non-debug sections in separate
debuginfo files. (Implies -wK)
-wK --debug-dump=follow-links
Follow links to separate debug info files (default)
-wN --debug-dump=no-follow-links
Do not follow links to separate debug info files
--dwarf-depth=N Do not display DIEs at depth N or greater
--dwarf-start=N Display DIEs starting at offset N
--ctf=<number|name> Display CTF info from section <number|name>
--ctf-parent=<name> Use CTF archive member <name> as the CTF parent
--ctf-symbols=<number|name>
Use section <number|name> as the CTF external symtab
--ctf-strings=<number|name>
Use section <number|name> as the CTF external strtab
-I --histogram Display histogram of bucket list lengths
-W --wide Allow output width to exceed 80 characters
-T --silent-truncation If a symbol name is truncated, do not add [...] suffix
@<file> Read options from <file>
-H --help Display this information
-v --version Display the version number of readelf
readelf -h
# -h --file-header Display the ELF file header
readelf -h foo2.o
ELF 头：
Magic： 7f 45 4c 46 02 01 01 00 00 00 00 00 00 00 00 00
类别: ELF64
数据: 2 补码，小端序 (little endian)
Version: 1 (current)
OS/ABI: UNIX - System V
ABI 版本: 0
类型: REL (可重定位文件)
系统架构: Advanced Micro Devices X86-64
版本: 0x1
入口点地址： 0x0
程序头起点： 0 (bytes into file)
Start of section headers: 856 (bytes into file)
标志： 0x0
Size of this header: 64 (bytes)
Size of program headers: 0 (bytes)
Number of program headers: 0
Size of section headers: 64 (bytes)
Number of section headers: 14
Section header string table index: 13
readelf -S
# -S --section-headers Display the sections' header
readelf -S foo2.o
There are 14 section headers, starting at offset 0x358:
节头：
[号] 名称 类型 地址 偏移量
大小 全体大小 旗标 链接 信息 对齐
[ 0] NULL 0000000000000000 00000000
0000000000000000 0000000000000000 0 0 0
[ 1] .text PROGBITS 0000000000000000 00000040
000000000000004e 0000000000000000 AX 0 0 1
[ 2] .rela.text RELA 0000000000000000 00000250
0000000000000060 0000000000000018 I 11 1 8
[ 3] .data PROGBITS 0000000000000000 0000008e
0000000000000000 0000000000000000 WA 0 0 1
[ 4] .bss NOBITS 0000000000000000 00000090
0000000000000008 0000000000000000 WA 0 0 4
[ 5] .rodata PROGBITS 0000000000000000 00000090
000000000000000c 0000000000000000 A 0 0 1
[ 6] .comment PROGBITS 0000000000000000 0000009c
000000000000002c 0000000000000001 MS 0 0 1
[ 7] .note.GNU-stack PROGBITS 0000000000000000 000000c8
0000000000000000 0000000000000000 0 0 1
[ 8] .note.gnu.pr[...] NOTE 0000000000000000 000000c8
0000000000000020 0000000000000000 A 0 0 8
[ 9] .eh_frame PROGBITS 0000000000000000 000000e8
0000000000000058 0000000000000000 A 0 0 8
[10] .rela.eh_frame RELA 0000000000000000 000002b0
0000000000000030 0000000000000018 I 11 9 8
[11] .symtab SYMTAB 0000000000000000 00000140
00000000000000d8 0000000000000018 12 6 8
[12] .strtab STRTAB 0000000000000000 00000218
0000000000000036 0000000000000000 0 0 1
[13] .shstrtab STRTAB 0000000000000000 000002e0
0000000000000074 0000000000000000 0 0 1
Key to Flags:
W (write), A (alloc), X (execute), M (merge), S (strings), I (info),
L (link order), O (extra OS processing required), G (group), T (TLS),
C (compressed), x (unknown), o (OS specific), E (exclude),
D (mbind), l (large), p (processor specific)
readelf -r
# -r --relocs Display the relocations (if present)
readelf -r hello.o
重定位节 '.rela.text' at offset 0x1f8 contains 3 entries:
偏移量 信息 类型 符号值 符号名称 + 加数
000000000027 000300000002 R_X86_64_PC32 0000000000000000 .rodata - 4
000000000045 000500000002 R_X86_64_PC32 0000000000000000 foo2 - 4
000000000052 000600000004 R_X86_64_PLT32 0000000000000000 foo2_func - 4
重定位节 '.rela.eh_frame' at offset 0x240 contains 1 entry:
偏移量 信息 类型 符号值 符号名称 + 加数
000000000020 000200000002 R_X86_64_PC32 0000000000000000 .text + 0
readelf -s
# -s --syms Display the symbol table
# --symbols An alias for --syms
# --dyn-syms Display the dynamic symbol table
# --lto-syms Display LTO symbol tables
# --sym-base=[0|8|10|16]
# Force base for symbol sizes. The options are
# mixed (the default), octal, decimal, hexadecimal.
readelf -s foo2.o
Symbol table '.symtab' contains 9 entries:
Num: Value Size Type Bind Vis Ndx Name
0: 0000000000000000 0 NOTYPE LOCAL DEFAULT UND
1: 0000000000000000 0 FILE LOCAL DEFAULT ABS foo2.c
2: 0000000000000000 0 SECTION LOCAL DEFAULT 1 .text
3: 0000000000000004 4 OBJECT LOCAL DEFAULT 4 foo2_static
4: 0000000000000000 0 SECTION LOCAL DEFAULT 5 .rodata
5: 0000000000000000 31 FUNC LOCAL DEFAULT 1 foo2_func_1
6: 0000000000000000 4 OBJECT GLOBAL DEFAULT 4 foo2
7: 0000000000000000 0 NOTYPE GLOBAL DEFAULT UND printf
8: 000000000000001f 47 FUNC GLOBAL DEFAULT 1 foo2_func
# ======================================================================
readelf -s hello.o
Symbol table '.symtab' contains 7 entries:
Num: Value Size Type Bind Vis Ndx Name
0: 0000000000000000 0 NOTYPE LOCAL DEFAULT UND
1: 0000000000000000 0 FILE LOCAL DEFAULT ABS hello.c
2: 0000000000000000 0 SECTION LOCAL DEFAULT 1 .text
3: 0000000000000000 0 SECTION LOCAL DEFAULT 5 .rodata
4: 0000000000000000 93 FUNC GLOBAL DEFAULT 1 main
5: 0000000000000000 0 NOTYPE GLOBAL DEFAULT UND foo2
6: 0000000000000000 0 NOTYPE GLOBAL DEFAULT UND foo2_func
符号 foo2 和 foo2_func 都在模块 foo2 中定义，对于模块 hello 来说是外部符号，没有在任何一个段中，所以在列 Ndx 中，foo2 和 foo2_func 的值是 UND。UND 是 Undefined 的缩写，表示符号 foo2、foo2_func 是未定义的。
strip
Linux 可执行文件瘦身指令 strip 使用示例
在链接时，对于模块中引用的外部符号，链接器将根据符号表进行符号的重定位。如果我们将符号表删除了，那么链接器在链接时将找不到符号的定义，从而不能进行正确的符号解析。如我们将 foo2.o 中的符号表删除，再次进行链接，则链接器将因找不到符号定义而终止链接，如下所示
gcc -o hello *.o
/usr/bin/ld: hello.o: warning: relocation against `foo2' in read-only section `.text'
/usr/bin/ld: error in foo2.o(.eh_frame); no .eh_frame_hdr table will be created
/usr/bin/ld: hello.o: in function `main':
hello.c:(.text+0x45): undefined reference to `foo2'
/usr/bin/ld: hello.c:(.text+0x52): undefined reference to `foo2_func'
/usr/bin/ld: warning: creating DT_TEXTREL in a PIE
collect2: error: ld returned 1 exit status
链接
按照前面我们提到的目标文件合并理论，理论上三个目标文件 hello.o、foo1.o、foo2.o的 “.text” 段的尺寸加起来应该与可执行文件 hello 的 “.text” 段的尺寸大小相等。但是，通过 readelf 的输出可见，三个目标文件的 “.text” 段的尺寸加起来是 0x46（0x26+0x10+0x10）字节，远小于可执行文件 hello 的 “.text” 段的大小 0x1b8。如果读者在编译时向 gcc 传递了参数 -v，仔细观察 gcc 的输出可以发现，实际上在链接时链接器自作主张地链接了一些特别的文件，包括 crt1.o、crti.o、crtn.o、crtbegin.o 及 crtend.o 等，其实就是我们前面提到的启动文件。所以多出来的尺寸都是合并这些文件的 “.text” 导致的。