Syscall/sysenter on LLVM

前端 未结 1 1332
慢半拍i
慢半拍i 2021-02-05 06:07

How do I write the LLVM bitcode required to emit an architecture-specific system call instruction?

More specifically, clang supports inline assembly, and cl

1条回答
  •  悲哀的现实
    2021-02-05 06:24

    Posting an answer here since exa has put up a bounty.

    I realized this was somewhat a silly question to ask after Ross Ridge's comments, and some playing around with clang.

    Let's assume we have the following program, which uses inline assembly to directly call write().

    #include 
    int main(void)
    {
        char *buf = "test\n";
        ssize_t n;
        asm volatile (
            "movl $0x00000002, %%edi\n"  /* first argument == stderr */
            "movl $0x00000006, %%edx\n"  /* third argument == number of bytes */
            "movl $1, %%eax\n"  /* syscall number == write on amd64 linux */
            "syscall\n"
            : "=A"(n)         /* %rax: return value */
            : "S"(buf));      /* %rsi: second argument == address of data to write */
        return n;
    }
    

    We can compile this with either gcc or clang and get roughly the same result.

    $ gcc -o syscall.gcc syscall.c
    $ clang -o syscall.clang syscall.c
    $ ./syscall.gcc
    test
    $ ./syscall.clang
    test
    

    If we wish to see the exact LLVM instructions which would be used to emit this code, we can simply use the -emit-llvm flag. As you can see, there is a call i64 asm sideeffect line which has the full inline assembly string.

    $ clang -S -emit-llvm syscall.c
    $ cat syscall.ll
    ; ModuleID = 'syscall.c'
    target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
    target triple = "x86_64-pc-linux-gnu"
    
    @.str = private unnamed_addr constant [6 x i8] c"test\0A\00", align 1
    
    ; Function Attrs: nounwind uwtable
    define i32 @main() #0 {
      %1 = alloca i32, align 4
      %buf = alloca i8*, align 8
      %n = alloca i64, align 8
      store i32 0, i32* %1
      store i8* getelementptr inbounds ([6 x i8]* @.str, i32 0, i32 0), i8** %buf, align 8
      %2 = load i8** %buf, align 8
      %3 = call i64 asm sideeffect "movl $$0x00000002, %edi\0Amovl $$0x00000006, %edx\0Amovl $$1, %eax\0Asyscall\0A", "=A,{si},~{dirflag},~{fpsr},~{flags}"(i8* %2) #1, !srcloc !1
      store i64 %3, i64* %n, align 8
      %4 = load i64* %n, align 8
      %5 = trunc i64 %4 to i32
      ret i32 %5
    }
    
    attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
    attributes #1 = { nounwind }
    
    !llvm.ident = !{!0}
    
    !0 = metadata !{metadata !"Ubuntu clang version 3.5-1ubuntu1 (trunk) (based on LLVM 3.5)"}
    !1 = metadata !{i32 134, i32 197, i32 259, i32 312}
    

    0 讨论(0)
提交回复
热议问题