访问 C 文件中的汇编宏函数/指令

mah*_*del 0 c assembly gcc nasm inline-assembly

我想知道是否可以在另一个 C 文件中访问类似的汇编指令.directive或类似的宏%macro my_macro

文件:macroasm.S

%macro my_macro 1
   mov rsp, 1
%endmacro
Run Code Online (Sandbox Code Playgroud)

有没有可能的方法来调用和执行my_macroC 文件中的宏并使用 nasm 和 gcc 编译它们?

Pet*_*des 5

与运行时函数调用不同,宏是编译时替换。asm 和 C 是不同的语言,因此这个问题有意义的唯一方法是可以从 inline-asm 使用 asm 宏。

gcc 的 asm 输出必须由 GAS 或理解 GAS 指令的兼容汇编器进行汇编。(https://sourceware.org/binutils/docs/as/)。内联 asm 允许您将手写的内容直接发送到 asm 编译器输出中,成为编译器提供给汇编器的完整汇编器源文件的一部分。

使用 NASM 语法%macro无法在 GNU C 内联汇编中工作,因为可以汇编常规 gcc 输出的汇编器无法理解 NASM 指令。


但如果你愿意,你可以使用 GAS .macrohttps://sourceware.org/binutils/docs/as/Macro.html)。我不会推荐它;GAS 宏不太好用。与 NASM 相比,该语法感觉很笨拙。但既然你问了,那就这么做吧。

asm(".include \"macro-defs.S\"");C 顶部的 可以让您稍后在该编译单元中使用内联汇编中的这些宏。(假设 gcc 不会对输出 asm 中的内容重新排序。)

但当然,您必须知道宏的作用才能为 inline-asm 语句编写正确的约束,因此它实际上并不是超级有用。


例子

macro-defs.S (GAS 语法,不是 NASM)。也许我应该调用它.s,因为我们只.include使用 asm 指令来调用它,而不是#include使用 C 预处理器。(这对于 C 来说是有问题的:你不能双引号字符串中添加#include任何内容。)所以无论如何,我们不能在这里使用 CPP 宏,只能使用 asm 宏。

    #.altmacro  # needed for some things, makes other things harder
    # /sf/ask/1384389471/

# clobbers RDX and RAX
.macro fenced_rdtsc64  dst
    lfence                  # make sure earlier stuff is done
    rdtsc
    lfence                  # don't allow later stuff to start before time is read
    shl $32, %rdx           # allow OoO exec of these with the timed interval
    lea (%rax, %rdx), \dst
.endm

# repeats  pause  n times.  Probably not useful, just a silly example.
# for exponential backoff in a spinloop, you want a *runtime* repeat count.
.macro  pause_n  count
    pause                      # the machine instruction, not a macro
   .if     \count-1
      pause_n  "(\count-1)"    # recursion is GAS equivalent of NASM %rep
   .endif
.endm
Run Code Online (Sandbox Code Playgroud)

这些宏可从以下位置使用foo.S

.include "macro-defs.S"

 # inefficient: the subtraction really only needs to use the low 32 bits of the count
 # so using a macro that merges the high half is a waste    
.globl foo
foo:
    fenced_rdtsc64  %rcx   # start
    pause_n         4
    fenced_rdtsc64  %rax   # end
    sub             %rcx, %rax
    ret
Run Code Online (Sandbox Code Playgroud)

并通过 inline-asm frommain.c(这也称为foo()正常方式)。

#include <stdio.h>

asm(".include \"macro-defs.S\"");

long long foo(void);
int main(void) {
    long long start, end;
    asm volatile("fenced_rdtsc64 %[dst]"
             : [dst]"=r" (start)
             :
             : "rax", "rdx" // forces it to avoid these as output regs, unfortunately
        );

    printf("foo rdtsc ticks: call1 %lld  call2 %lld\n", foo(), foo());

    asm volatile("fenced_rdtsc64 %[dst]"
             : [dst]"=r" (end)
             :
             : "rax", "rdx");
    printf("printf rdtsc ticks: %lld\n", end-start);
}
Run Code Online (Sandbox Code Playgroud)

编译gcc -O3 -Wall main.c foo.S (我用的是gcc7.3,-fpie是默认的)。

运行它for i in {1..50};do ./a.out;done会给出如下输出(在我的 i7-6700k 上,pause需要约 100 个核心时钟周期,并且硬件 P 状态在有负载时会快速提高速度):

... (variable number of lines before the frequency shift)
foo rdtsc ticks: call1 3006  call2 3014
printf rdtsc ticks: 727810
foo rdtsc ticks: call1 3006  call2 3022
printf rdtsc ticks: 707376
foo rdtsc ticks: call1 3006  call2 3017
printf rdtsc ticks: 746375
foo rdtsc ticks: call1 3006  call2 3029
printf rdtsc ticks: 684239
foo rdtsc ticks: call1 3006  call2 3010
printf rdtsc ticks: 652724
foo rdtsc ticks: call1 616  call2 620    # gcc chose to evalute from right to left
printf rdtsc ticks: 133282
foo rdtsc ticks: call1 618  call2 618    # so call1 is with it hot in uop cache
printf rdtsc ticks: 133984
foo rdtsc ticks: call1 616  call2 618
printf rdtsc ticks: 133284
foo rdtsc ticks: call1 614  call2 618
Run Code Online (Sandbox Code Playgroud)

对于 的 asm foo,如果我们反汇编(使用objdump -drwC -Mintel a.out)来查看宏如何扩展:

# I maybe should have used AT&T syntax disassembly like the source
# You can do that if you want, on your own desktop, leaving out -Mintel
00000000000006ba <foo>:
 6ba:   0f ae e8                lfence 
 6bd:   0f 31                   rdtsc  
 6bf:   0f ae e8                lfence 
 6c2:   48 c1 e2 20             shl    rdx,0x20
 6c6:   48 8d 0c 10             lea    rcx,[rax+rdx*1]   # macro expanded with RCX
 6ca:   f3 90                   pause      # pause_n   4  expanded to 4 pause instructions
 6cc:   f3 90                   pause  
 6ce:   f3 90                   pause  
 6d0:   f3 90                   pause  
 6d2:   0f ae e8                lfence 
 6d5:   0f 31                   rdtsc  
 6d7:   0f ae e8                lfence 
 6da:   48 c1 e2 20             shl    rdx,0x20
 6de:   48 8d 04 10             lea    rax,[rax+rdx*1]   # macro expanded with RAX
 6e2:   48 29 c8                sub    rax,rcx
 6e5:   c3                      ret    
Run Code Online (Sandbox Code Playgroud)

编译器生成的 asm(包括我们的内联 asm)是:

0000000000000540 <main>:
 540:   55                      push   rbp
 541:   53                      push   rbx
 542:   48 83 ec 08             sub    rsp,0x8

 546:   0f ae e8                lfence             # first inline asm
 549:   0f 31                   rdtsc  
 54b:   0f ae e8                lfence 
 54e:   48 c1 e2 20             shl    rdx,0x20
 552:   48 8d 1c 10             lea    rbx,[rax+rdx*1]    # The compiler picked RBX for the output operand
                                                 # and substituted fenced_rdtsc64 %rbx into the asm template


 556:   e8 5f 01 00 00          call   6ba <foo>
 55b:   48 89 c5                mov    rbp,rax    # save the return value, not a macro so it couldn't ask for a more convenient register
 55e:   e8 57 01 00 00          call   6ba <foo>
 563:   48 89 ea                mov    rdx,rbp
 566:   48 8d 3d 0b 02 00 00    lea    rdi,[rip+0x20b]        # 778 <_IO_stdin_used+0x8>  # the string literal
 56d:   48 89 c6                mov    rsi,rax
 570:   31 c0                   xor    eax,eax
 572:   e8 b9 ff ff ff          call   530 <printf@plt>

 577:   0f ae e8                lfence         # 2nd inline asm
 57a:   0f 31                   rdtsc  
 57c:   0f ae e8                lfence 
 57f:   48 c1 e2 20             shl    rdx,0x20
 583:   48 8d 34 10             lea    rsi,[rax+rdx*1]   # compiler picked RSI this time
 587:   48 8d 3d 1a 02 00 00    lea    rdi,[rip+0x21a]        # 7a8 <_IO_stdin_used+0x38>
 58e:   48 29 de                sub    rsi,rbx           # where it wanted it as the 2nd arg to printf(.., end-start)
 591:   31 c0                   xor    eax,eax
 593:   e8 98 ff ff ff          call   530 <printf@plt>
 598:   48 83 c4 08             add    rsp,0x8
 59c:   31 c0                   xor    eax,eax
 59e:   5b                      pop    rbx
 59f:   5d                      pop    rbp
 5a0:   c3                      ret    
Run Code Online (Sandbox Code Playgroud)