C++ 中如何实现非静态、非虚拟方法？

发布于 2025-01-11 03:49:30 字数 6912 浏览 1 评论 0原文

我想知道 C++ 中的方法是如何实现的。我想知道方法是如何“在幕后”实现的。因此，我制作了一个简单的 C++ 程序，其中有一个带有 1 个非静态字段和 1 个非静态、非虚拟方法的类。

然后我在主函数中实例化该类并调用该方法。我使用了 objdump -d 选项来查看该程序的 CPU 指令。我有一个 x86-64 处理器。代码如下：

#include<stdio.h>


class TestClass {
public:
   int x;
   int xPlus2(){
       return x + 2;
   }
};

int main(){
    TestClass tc1 = {5};
    int variable = tc1.xPlus2();
    printf("%d \n", variable);
    return 0;
}

这是方法xPlus2的说明：

  0000000000402c30 <_ZN9TestClass6xPlus2Ev>:
  402c30:   55                      push   %rbp
  402c31:   48 89 e5                mov    %rsp,%rbp
  402c34:   48 89 4d 10             mov    %rcx,0x10(%rbp)
  402c38:   48 8b 45 10             mov    0x10(%rbp),%rax
  402c3c:   8b 00                   mov    (%rax),%eax
  402c3e:   83 c0 02                add    $0x2,%eax
  402c41:   5d                      pop    %rbp
  402c42:   c3                      retq   
  402c43:   90                      nop
  402c44:   90                      nop
  402c45:   90                      nop
  402c46:   90                      nop
  402c47:   90                      nop
  402c48:   90                      nop
  402c49:   90                      nop
  402c4a:   90                      nop
  402c4b:   90                      nop
  402c4c:   90                      nop
  402c4d:   90                      nop
  402c4e:   90                      nop
  402c4f:   90                      nop

如果我理解正确的话，这些指令可以只用3条指令代替，因为我相信我不需要使用堆栈，我认为编译器冗余地使用了它：

mov (%rcx), eax
add $2, eax
retq

然后也许我仍然需要大量 nop 指令用于同步目的或其他目的。如果您查看 CPU 指令，您会发现 x 字段的值 存储在内存中 rcx 寄存器 保存的位置。稍后您将看到其余的 CPU 指令。对我来说跟踪这里发生的事情有点困难（特别是调用 _main 函数时发生了什么），我什至不知道汇编的哪些部分是重要的。编译器生成 main 函数（正如我所期望的），但随后它也生成了从 main 调用的 _main 函数，这两个函数之间也有一些奇怪的函数。以下是我认为可能有趣的组件的其他部分：

  0000000000401550 <main>:
  401550:   55                      push   %rbp
  401551:   48 89 e5                mov    %rsp,%rbp
  401554:   48 83 ec 30             sub    $0x30,%rsp
  401558:   e8 e3 00 00 00          callq  401640 <__main>
  40155d:   c7 45 f8 05 00 00 00    movl   $0x5,-0x8(%rbp)
  401564:   48 8d 45 f8             lea    -0x8(%rbp),%rax
  401568:   48 89 c1                mov    %rax,%rcx
  40156b:   e8 c0 16 00 00          callq  402c30 <_ZN9TestClass6xPlus2Ev>
  401570:   89 45 fc                mov    %eax,-0x4(%rbp)
  401573:   8b 45 fc                mov    -0x4(%rbp),%eax
  401576:   89 c2                   mov    %eax,%edx
  401578:   48 8d 0d 81 2a 00 00    lea    0x2a81(%rip),%rcx        # 404000 <.rdata>
  40157f:   e8 ec 14 00 00          callq  402a70 <printf>
  401584:   b8 00 00 00 00          mov    $0x0,%eax
  401589:   48 83 c4 30             add    $0x30,%rsp
  40158d:   5d                      pop    %rbp
  40158e:   c3                      retq   
  40158f:   90                      nop

0000000000401590 <__do_global_dtors>:
  401590:   48 83 ec 28             sub    $0x28,%rsp
  401594:   48 8b 05 75 1a 00 00    mov    0x1a75(%rip),%rax        # 403010 <p.93846>
  40159b:   48 8b 00                mov    (%rax),%rax
  40159e:   48 85 c0                test   %rax,%rax
  4015a1:   74 1d                   je     4015c0 <__do_global_dtors+0x30>
  4015a3:   ff d0                   callq  *%rax
  4015a5:   48 8b 05 64 1a 00 00    mov    0x1a64(%rip),%rax        # 403010 <p.93846>
  4015ac:   48 8d 50 08             lea    0x8(%rax),%rdx
  4015b0:   48 8b 40 08             mov    0x8(%rax),%rax
  4015b4:   48 89 15 55 1a 00 00    mov    %rdx,0x1a55(%rip)        # 403010 <p.93846>
  4015bb:   48 85 c0                test   %rax,%rax
  4015be:   75 e3                   jne    4015a3 <__do_global_dtors+0x13>
  4015c0:   48 83 c4 28             add    $0x28,%rsp
  4015c4:   c3                      retq   
  4015c5:   90                      nop
  4015c6:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
  4015cd:   00 00 00 

00000000004015d0 <__do_global_ctors>:
  4015d0:   56                      push   %rsi
  4015d1:   53                      push   %rbx
  4015d2:   48 83 ec 28             sub    $0x28,%rsp
  4015d6:   48 8b 0d 23 2d 00 00    mov    0x2d23(%rip),%rcx        # 404300 <.refptr.__CTOR_LIST__>
  4015dd:   48 8b 11                mov    (%rcx),%rdx
  4015e0:   83 fa ff                cmp    $0xffffffff,%edx
  4015e3:   89 d0                   mov    %edx,%eax
  4015e5:   74 39                   je     401620 <__do_global_ctors+0x50>
  4015e7:   85 c0                   test   %eax,%eax
  4015e9:   74 20                   je     40160b <__do_global_ctors+0x3b>
  4015eb:   89 c2                   mov    %eax,%edx
  4015ed:   83 e8 01                sub    $0x1,%eax
  4015f0:   48 8d 1c d1             lea    (%rcx,%rdx,8),%rbx
  4015f4:   48 29 c2                sub    %rax,%rdx
  4015f7:   48 8d 74 d1 f8          lea    -0x8(%rcx,%rdx,8),%rsi
  4015fc:   0f 1f 40 00             nopl   0x0(%rax)
  401600:   ff 13                   callq  *(%rbx)
  401602:   48 83 eb 08             sub    $0x8,%rbx
  401606:   48 39 f3                cmp    %rsi,%rbx
  401609:   75 f5                   jne    401600 <__do_global_ctors+0x30>
  40160b:   48 8d 0d 7e ff ff ff    lea    -0x82(%rip),%rcx        # 401590 <__do_global_dtors>
  401612:   48 83 c4 28             add    $0x28,%rsp
  401616:   5b                      pop    %rbx
  401617:   5e                      pop    %rsi
  401618:   e9 f3 fe ff ff          jmpq   401510 <atexit>
  40161d:   0f 1f 00                nopl   (%rax)
  401620:   31 c0                   xor    %eax,%eax
  401622:   eb 02                   jmp    401626 <__do_global_ctors+0x56>
  401624:   89 d0                   mov    %edx,%eax
  401626:   44 8d 40 01             lea    0x1(%rax),%r8d
  40162a:   4a 83 3c c1 00          cmpq   $0x0,(%rcx,%r8,8)
  40162f:   4c 89 c2                mov    %r8,%rdx
  401632:   75 f0                   jne    401624 <__do_global_ctors+0x54>
  401634:   eb b1                   jmp    4015e7 <__do_global_ctors+0x17>
  401636:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
  40163d:   00 00 00 

0000000000401640 <__main>:
  401640:   8b 05 ea 59 00 00       mov    0x59ea(%rip),%eax        # 407030 <initialized>
  401646:   85 c0                   test   %eax,%eax
  401648:   74 06                   je     401650 <__main+0x10>
  40164a:   c3                      retq   
  40164b:   0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
  401650:   c7 05 d6 59 00 00 01    movl   $0x1,0x59d6(%rip)        # 407030 <initialized>
  401657:   00 00 00 
  40165a:   e9 71 ff ff ff          jmpq   4015d0 <__do_global_ctors>
  40165f:   90                      nop

原文

I wanted to know how methods are implemented in C++. I wanted to know how methods are implemented "under the hood".
So, I have made a simple C++ program which has a class with 1 non static field and 1 non static, non virtual method.

Then I instantiated the class in the main function and called the method. I have used objdump -d option in order to see the CPU instructions of this program. I have a x86-64 processor.
Here's the code:

#include<stdio.h>


class TestClass {
public:
   int x;
   int xPlus2(){
       return x + 2;
   }
};

int main(){
    TestClass tc1 = {5};
    int variable = tc1.xPlus2();
    printf("%d \n", variable);
    return 0;
}

Here are instructions for the method xPlus2:

  0000000000402c30 <_ZN9TestClass6xPlus2Ev>:
  402c30:   55                      push   %rbp
  402c31:   48 89 e5                mov    %rsp,%rbp
  402c34:   48 89 4d 10             mov    %rcx,0x10(%rbp)
  402c38:   48 8b 45 10             mov    0x10(%rbp),%rax
  402c3c:   8b 00                   mov    (%rax),%eax
  402c3e:   83 c0 02                add    $0x2,%eax
  402c41:   5d                      pop    %rbp
  402c42:   c3                      retq   
  402c43:   90                      nop
  402c44:   90                      nop
  402c45:   90                      nop
  402c46:   90                      nop
  402c47:   90                      nop
  402c48:   90                      nop
  402c49:   90                      nop
  402c4a:   90                      nop
  402c4b:   90                      nop
  402c4c:   90                      nop
  402c4d:   90                      nop
  402c4e:   90                      nop
  402c4f:   90                      nop

If I understand it correctly, these instructions can be replaced by just 3 instructions, because I believe that I don't need to use the stack, I think the compiler used it redundantly:

mov (%rcx), eax
add $2, eax
retq

and then maybe I still need lots of nop instructions for synchronization purposes or whatnot. If you look at the CPU instructions, it looks like the value that x field has is stored at the location in memory which rcx register holds. You will see the rest of the CPU instructions in a moment. It is a little bit hard for me to track what has happened here (especially what is going on with the call of _main function), I don't even know what parts of assembly are important to look at. Compiler produces main function (as I expected), but then it also produced _main function which is called from the main, there are some weird functions in between those two as well.
Here are other parts of the assembly that I think may be interesting:

  0000000000401550 <main>:
  401550:   55                      push   %rbp
  401551:   48 89 e5                mov    %rsp,%rbp
  401554:   48 83 ec 30             sub    $0x30,%rsp
  401558:   e8 e3 00 00 00          callq  401640 <__main>
  40155d:   c7 45 f8 05 00 00 00    movl   $0x5,-0x8(%rbp)
  401564:   48 8d 45 f8             lea    -0x8(%rbp),%rax
  401568:   48 89 c1                mov    %rax,%rcx
  40156b:   e8 c0 16 00 00          callq  402c30 <_ZN9TestClass6xPlus2Ev>
  401570:   89 45 fc                mov    %eax,-0x4(%rbp)
  401573:   8b 45 fc                mov    -0x4(%rbp),%eax
  401576:   89 c2                   mov    %eax,%edx
  401578:   48 8d 0d 81 2a 00 00    lea    0x2a81(%rip),%rcx        # 404000 <.rdata>
  40157f:   e8 ec 14 00 00          callq  402a70 <printf>
  401584:   b8 00 00 00 00          mov    $0x0,%eax
  401589:   48 83 c4 30             add    $0x30,%rsp
  40158d:   5d                      pop    %rbp
  40158e:   c3                      retq   
  40158f:   90                      nop

0000000000401590 <__do_global_dtors>:
  401590:   48 83 ec 28             sub    $0x28,%rsp
  401594:   48 8b 05 75 1a 00 00    mov    0x1a75(%rip),%rax        # 403010 <p.93846>
  40159b:   48 8b 00                mov    (%rax),%rax
  40159e:   48 85 c0                test   %rax,%rax
  4015a1:   74 1d                   je     4015c0 <__do_global_dtors+0x30>
  4015a3:   ff d0                   callq  *%rax
  4015a5:   48 8b 05 64 1a 00 00    mov    0x1a64(%rip),%rax        # 403010 <p.93846>
  4015ac:   48 8d 50 08             lea    0x8(%rax),%rdx
  4015b0:   48 8b 40 08             mov    0x8(%rax),%rax
  4015b4:   48 89 15 55 1a 00 00    mov    %rdx,0x1a55(%rip)        # 403010 <p.93846>
  4015bb:   48 85 c0                test   %rax,%rax
  4015be:   75 e3                   jne    4015a3 <__do_global_dtors+0x13>
  4015c0:   48 83 c4 28             add    $0x28,%rsp
  4015c4:   c3                      retq   
  4015c5:   90                      nop
  4015c6:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
  4015cd:   00 00 00 

00000000004015d0 <__do_global_ctors>:
  4015d0:   56                      push   %rsi
  4015d1:   53                      push   %rbx
  4015d2:   48 83 ec 28             sub    $0x28,%rsp
  4015d6:   48 8b 0d 23 2d 00 00    mov    0x2d23(%rip),%rcx        # 404300 <.refptr.__CTOR_LIST__>
  4015dd:   48 8b 11                mov    (%rcx),%rdx
  4015e0:   83 fa ff                cmp    $0xffffffff,%edx
  4015e3:   89 d0                   mov    %edx,%eax
  4015e5:   74 39                   je     401620 <__do_global_ctors+0x50>
  4015e7:   85 c0                   test   %eax,%eax
  4015e9:   74 20                   je     40160b <__do_global_ctors+0x3b>
  4015eb:   89 c2                   mov    %eax,%edx
  4015ed:   83 e8 01                sub    $0x1,%eax
  4015f0:   48 8d 1c d1             lea    (%rcx,%rdx,8),%rbx
  4015f4:   48 29 c2                sub    %rax,%rdx
  4015f7:   48 8d 74 d1 f8          lea    -0x8(%rcx,%rdx,8),%rsi
  4015fc:   0f 1f 40 00             nopl   0x0(%rax)
  401600:   ff 13                   callq  *(%rbx)
  401602:   48 83 eb 08             sub    $0x8,%rbx
  401606:   48 39 f3                cmp    %rsi,%rbx
  401609:   75 f5                   jne    401600 <__do_global_ctors+0x30>
  40160b:   48 8d 0d 7e ff ff ff    lea    -0x82(%rip),%rcx        # 401590 <__do_global_dtors>
  401612:   48 83 c4 28             add    $0x28,%rsp
  401616:   5b                      pop    %rbx
  401617:   5e                      pop    %rsi
  401618:   e9 f3 fe ff ff          jmpq   401510 <atexit>
  40161d:   0f 1f 00                nopl   (%rax)
  401620:   31 c0                   xor    %eax,%eax
  401622:   eb 02                   jmp    401626 <__do_global_ctors+0x56>
  401624:   89 d0                   mov    %edx,%eax
  401626:   44 8d 40 01             lea    0x1(%rax),%r8d
  40162a:   4a 83 3c c1 00          cmpq   $0x0,(%rcx,%r8,8)
  40162f:   4c 89 c2                mov    %r8,%rdx
  401632:   75 f0                   jne    401624 <__do_global_ctors+0x54>
  401634:   eb b1                   jmp    4015e7 <__do_global_ctors+0x17>
  401636:   66 2e 0f 1f 84 00 00    nopw   %cs:0x0(%rax,%rax,1)
  40163d:   00 00 00 

0000000000401640 <__main>:
  401640:   8b 05 ea 59 00 00       mov    0x59ea(%rip),%eax        # 407030 <initialized>
  401646:   85 c0                   test   %eax,%eax
  401648:   74 06                   je     401650 <__main+0x10>
  40164a:   c3                      retq   
  40164b:   0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
  401650:   c7 05 d6 59 00 00 01    movl   $0x1,0x59d6(%rip)        # 407030 <initialized>
  401657:   00 00 00 
  40165a:   e9 71 ff ff ff          jmpq   4015d0 <__do_global_ctors>
  40165f:   90                      nop

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

楠木可依 2025-01-18 03:49:30

我认为您正在寻找的是这些指令：

 40155d:   c7 45 f8 05 00 00 00    movl   $0x5,-0x8(%rbp)
 401564:   48 8d 45 f8             lea    -0x8(%rbp),%rax
 401568:   48 89 c1                mov    %rax,%rcx
 40156b:   e8 c0 16 00 00          callq  402c30 <_ZN9TestClass6xPlus2Ev>
 401570:   89 45 fc                mov    %eax,-0x4(%rbp)

指令与 main 中的代码匹配：

TestClass tc1 = {5};
int variable = tc1.xPlus2();

在地址 40155d 处，字段 tc1.x 初始化为值 5。
这些 401564 指向 tc1 的指针被加载到寄存器 %rax
在地址 401568 处，指向 tc1 的指针是复制到寄存器 %rcx
在地址 40156b 处调用方法 tc1.xPlus2()
在地址 401570 处结果存储在 <代码>变量

I think what you are looking for are these instructions:

 40155d:   c7 45 f8 05 00 00 00    movl   $0x5,-0x8(%rbp)
 401564:   48 8d 45 f8             lea    -0x8(%rbp),%rax
 401568:   48 89 c1                mov    %rax,%rcx
 40156b:   e8 c0 16 00 00          callq  402c30 <_ZN9TestClass6xPlus2Ev>
 401570:   89 45 fc                mov    %eax,-0x4(%rbp)

These match with the code from main:

TestClass tc1 = {5};
int variable = tc1.xPlus2();

At address 40155d the field tc1.x is initialized with the value 5.
At address 401564 the pointer to tc1 is loaded into the register %rax
At address 401568 the pointer to tc1 is copied into the register %rcx
At address 40156b is the call of the method tc1.xPlus2()
At address 401570 the result is store in variable

回复收藏 0 原文

小嗲 2025-01-18 03:49:30

您的观察大多是正确的。 rcx 保存指向调用该方法的对象的 this 指针。 x 存储在 this 指针指向的第一个内存区域中，因此这就是取消引用 rcx 并将结果添加到其中的原因。调用者有责任在调用函数之前确保 rcx 是对象的地址。我们可以看到 main 通过将 rcx 设置为堆栈帧中的地址来准备 rcx。您是正确的，编译器在这里生成了低效的代码并且不需要使用堆栈。使用更高的优化级别 -O1、-O2 或 -O3 进行编译可能会解决该问题。这些更高的优化也可能会消除 nop，因为它们用于函数对齐。您基本上可以忽略__main。它用于 libc 初始化。