C++ 使用libclang从内存中的C代码生成程序集
我需要实现一个库,使用LLVM/Clang作为后端将C代码编译成eBPF字节码。代码将从内存中读取,我也需要在内存中获取生成的汇编代码 到目前为止,我已经能够使用以下代码编译到LLVM IR:C++ 使用libclang从内存中的C代码生成程序集,c++,clang,llvm,libclang,C++,Clang,Llvm,Libclang,我需要实现一个库,使用LLVM/Clang作为后端将C代码编译成eBPF字节码。代码将从内存中读取,我也需要在内存中获取生成的汇编代码 到目前为止,我已经能够使用以下代码编译到LLVM IR: #include <string> #include <vector> #include <clang/Frontend/CompilerInstance.h> #include <clang/Basic/DiagnosticOptions.h> #inc
#include <string>
#include <vector>
#include <clang/Frontend/CompilerInstance.h>
#include <clang/Basic/DiagnosticOptions.h>
#include <clang/Frontend/TextDiagnosticPrinter.h>
#include <clang/CodeGen/CodeGenAction.h>
#include <clang/Basic/TargetInfo.h>
#include <llvm/Support/TargetSelect.h>
using namespace std;
using namespace clang;
using namespace llvm;
int main() {
constexpr auto testCodeFileName = "test.cpp";
constexpr auto testCode = "int test() { return 2+2; }";
// Prepare compilation arguments
vector<const char *> args;
args.push_back(testCodeFileName);
// Prepare DiagnosticEngine
DiagnosticOptions DiagOpts;
TextDiagnosticPrinter *textDiagPrinter =
new clang::TextDiagnosticPrinter(errs(),
&DiagOpts);
IntrusiveRefCntPtr<clang::DiagnosticIDs> pDiagIDs;
DiagnosticsEngine *pDiagnosticsEngine =
new DiagnosticsEngine(pDiagIDs,
&DiagOpts,
textDiagPrinter);
// Initialize CompilerInvocation
CompilerInvocation *CI = new CompilerInvocation();
CompilerInvocation::CreateFromArgs(*CI, &args[0], &args[0] + args.size(), *pDiagnosticsEngine);
// Map code filename to a memoryBuffer
StringRef testCodeData(testCode);
unique_ptr<MemoryBuffer> buffer = MemoryBuffer::getMemBufferCopy(testCodeData);
CI->getPreprocessorOpts().addRemappedFile(testCodeFileName, buffer.get());
// Create and initialize CompilerInstance
CompilerInstance Clang;
Clang.setInvocation(CI);
Clang.createDiagnostics();
// Set target (I guess I can initialize only the BPF target, but I don't know how)
InitializeAllTargets();
const std::shared_ptr<clang::TargetOptions> targetOptions = std::make_shared<clang::TargetOptions>();
targetOptions->Triple = string("bpf");
TargetInfo *pTargetInfo = TargetInfo::CreateTargetInfo(*pDiagnosticsEngine,targetOptions);
Clang.setTarget(pTargetInfo);
// Create and execute action
// CodeGenAction *compilerAction = new EmitLLVMOnlyAction();
CodeGenAction *compilerAction = new EmitAssemblyAction();
Clang.ExecuteAction(*compilerAction);
buffer.release();
}
如果我理解正确,如果我将编译器操作更改为EmitAssemblyAction(),我应该能够生成汇编代码,但我可能没有初始化某些东西,因为我在llvm::TargetPassConfig::AddPasseToHandleExceptions(此=this@entry=0x6d8d30)at/tmp/llvm-3.7.1.src/lib/CodeGen/passs.cpp:419
这一行的代码是:
switch (TM->getMCAsmInfo()->getExceptionHandlingType()) {
有人举过一个例子,或者知道我遗漏了什么吗?因此,如果您在启用asserts的情况下编译LLVM,错误会更清楚,它实际上会告诉您需要做什么:
x: .../src/llvm/lib/CodeGen/LLVMTargetMachine.cpp:63:
void llvm::LLVMTargetMachine::initAsmInfo():
Assertion `TmpAsmInfo && "MCAsmInfo not initialized. "
"Make sure you include the correct TargetSelect.h"
"and that InitializeAllTargetMCs() is being invoked!"' failed.
(我在上面添加了一些换行符,因为它是作为一条长线打印的)
在main
开头添加所需的InitializeAllTargetMCs()
后,我遇到了另一个错误。查看编译器的对象文件生成,我“猜测”这是另一个InitializeAll*
调用的问题。经过一点测试,您还需要initializeAlasmPrinters()代码>-考虑到您想要生成汇编代码,这很有意义
我不完全确定如何“查看”代码的结果,但将这两个结果添加到main
的开头会使代码运行到完成,而不是断言,退出时出现错误或崩溃,这通常是朝着正确方向迈出的一步
这就是“我的”代码中的main
的样子:
[我使用了最新的3.8预发行版来测试这一点,但我非常怀疑它在这方面与3.7.1有很大不同]如果有人面临类似的问题,我已经能够从/到内存进行编译,通过stdin发送代码并从stdout获得输出
我不知道是否有其他方法可以实现这一点,可能是使用clang::Driver,但在阅读clang/LLVM源代码时,我发现获取对象所需执行的操作是EmitObjAction(),如果没有从stdin接收到输入,该操作似乎总是生成一个.o文件
因此,我在执行操作之前为管道替换了stdin/stdout,这样就避免了生成文件
#include <string>
#include <vector>
#include <sstream>
#include <iostream>
#include <cstdio>
#include <unistd.h>
#include <fcntl.h>
#include <clang/Frontend/CompilerInstance.h>
#include <clang/Basic/DiagnosticOptions.h>
#include <clang/Frontend/TextDiagnosticPrinter.h>
#include <clang/CodeGen/CodeGenAction.h>
#include <clang/Basic/TargetInfo.h>
#include <llvm/Support/TargetSelect.h>
#include <llvm/IR/Module.h>
using namespace std;
using namespace clang;
using namespace llvm;
int main(int argc, char *argv[])
{
// code to compile for the eBPF virtual machine
constexpr auto testCode = "int main() { return get_nbs(); }";
// Send code through a pipe to stdin
int codeInPipe[2];
pipe2(codeInPipe, O_NONBLOCK);
write(codeInPipe[1], (void *) testCode, strlen(testCode));
close(codeInPipe[1]); // We need to close the pipe to send an EOF
dup2(codeInPipe[0], STDIN_FILENO);
// Prepare reception of code through stdout
int codeOutPipe[2];
pipe(codeOutPipe);
dup2(codeOutPipe[1], STDOUT_FILENO);
// Initialize various LLVM/Clang components
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
InitializeAllTargets();
// Prepare compilation arguments
vector<const char *> args;
args.push_back("--target=bpf"); // Target is bpf assembly
args.push_back("-xc"); // Code is in c language
args.push_back("-"); // Read code from stdin
CompilerInvocation *CI = createInvocationFromCommandLine(makeArrayRef(args) , NULL);
// Create CompilerInstance
CompilerInstance Clang;
Clang.setInvocation(CI);
// Initialize CompilerInstace
Clang.createDiagnostics();
// Create and execute action
CodeGenAction *compilerAction;
compilerAction = new EmitObjAction();
Clang.ExecuteAction(*compilerAction);
// Get compiled object (be carefull with buffer size)
close(codeInPipe[0]);
char objBuffer[2048];
read(codeOutPipe[0], objBuffer, 2048);
return 0;
}
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
#包括
使用名称空间std;
使用名称空间铿锵;
使用名称空间llvm;
int main(int argc,char*argv[])
{
//要为eBPF虚拟机编译的代码
constexpr auto testCode=“int main(){return get_nbs();}”;
//通过管道将代码发送到stdin
int-codeInPipe[2];
管道2(代码管道,O_非阻塞);
编写(codeInPipe[1],(void*)测试代码,strlen(testCode));
close(codeInPipe[1]);//我们需要关闭管道以发送EOF
dup2(代码管道[0],标准文件号);
//准备通过标准输出接收代码
int代码输出管道[2];
管道(代码输出管道);
dup2(代码输出管道[1],标准输出文件编号);
//初始化各种LLVM/Clang组件
初始化AllTargetMCS();
初始化打印机();
初始化所有目标();
//准备编译参数
向量args;
args.push_back(“--target=bpf”);//目标是bpf程序集
args.push_back(“-xc”);//代码是用c语言编写的
args.push_back(“-”)//从stdin读取代码
CompilerInvocation*CI=createInvocationFromCommandLine(makeArrayRef(args),NULL);
//创建编译器状态
编者的声音;
铿锵.setInvocation(CI);
//初始化编译器状态
Clang.createDiagnostics();
//创建并执行操作
CodeGenAction*编译器操作;
compilerAction=newemitObjAction();
命令执行(*编译器操作);
//获取编译对象(小心缓冲区大小)
关闭(代码管道[0]);
char objBuffer[2048];
read(codeOutPipe[0],objBuffer,2048);
返回0;
}
我想你需要拿出一个可以编译和测试的完整示例…添加了可编译的示例。在修复打字错误后,我得到一个关于致命错误的错误:无法将文件“test.cpp”重新映射到文件“int test(){return 2+2;}”的内容。
Ops,复制时似乎丢失了一些代码,抱歉。你能再试一次吗?谢谢你,这解决了我的问题。我使用调试符号编译了clang/llvm,但没有断言,启用它们有很大帮助。我将附上我得到的最终代码作为回复,因为我必须更改一些东西以从/到内存进行编译。
int main() {
constexpr auto testCodeFileName = "test.cpp";
constexpr auto testCode = "int test() { return 2+2; }";
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
// Prepare compilation arguments
vector<const char *> args;
args.push_back(testCodeFileName);
// Prepare DiagnosticEngine
DiagnosticOptions DiagOpts;
TextDiagnosticPrinter *textDiagPrinter =
new clang::TextDiagnosticPrinter(errs(),
&DiagOpts);
IntrusiveRefCntPtr<clang::DiagnosticIDs> pDiagIDs;
DiagnosticsEngine *pDiagnosticsEngine =
new DiagnosticsEngine(pDiagIDs,
&DiagOpts,
textDiagPrinter);
// Initialize CompilerInvocation
CompilerInvocation *CI = new CompilerInvocation();
CompilerInvocation::CreateFromArgs(*CI, &args[0], &args[0] + args.size(), *pDiagnosticsEngine);
// Map code filename to a memoryBuffer
StringRef testCodeData(testCode);
unique_ptr<MemoryBuffer> buffer = MemoryBuffer::getMemBufferCopy(testCodeData);
CI->getPreprocessorOpts().addRemappedFile(testCodeFileName, buffer.get());
// Create and initialize CompilerInstance
CompilerInstance Clang;
Clang.setInvocation(CI);
Clang.createDiagnostics();
// Set target (I guess I can initialize only the BPF target, but I don't know how)
InitializeAllTargets();
const std::shared_ptr<clang::TargetOptions> targetOptions = std::make_shared<clang::TargetOptions>();
targetOptions->Triple = string("bpf");
TargetInfo *pTargetInfo = TargetInfo::CreateTargetInfo(*pDiagnosticsEngine,targetOptions);
Clang.setTarget(pTargetInfo);
// Create and execute action
// CodeGenAction *compilerAction = new EmitLLVMOnlyAction();
CodeGenAction *compilerAction = new EmitAssemblyAction();
Clang.ExecuteAction(*compilerAction);
buffer.release();
}
export CC=clang
export CXX=clang++
cmake -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=/usr/local/llvm-debug -DLLVM_TAR
GETS_TO_BUILD=X86 ../llvm
#include <string>
#include <vector>
#include <sstream>
#include <iostream>
#include <cstdio>
#include <unistd.h>
#include <fcntl.h>
#include <clang/Frontend/CompilerInstance.h>
#include <clang/Basic/DiagnosticOptions.h>
#include <clang/Frontend/TextDiagnosticPrinter.h>
#include <clang/CodeGen/CodeGenAction.h>
#include <clang/Basic/TargetInfo.h>
#include <llvm/Support/TargetSelect.h>
#include <llvm/IR/Module.h>
using namespace std;
using namespace clang;
using namespace llvm;
int main(int argc, char *argv[])
{
// code to compile for the eBPF virtual machine
constexpr auto testCode = "int main() { return get_nbs(); }";
// Send code through a pipe to stdin
int codeInPipe[2];
pipe2(codeInPipe, O_NONBLOCK);
write(codeInPipe[1], (void *) testCode, strlen(testCode));
close(codeInPipe[1]); // We need to close the pipe to send an EOF
dup2(codeInPipe[0], STDIN_FILENO);
// Prepare reception of code through stdout
int codeOutPipe[2];
pipe(codeOutPipe);
dup2(codeOutPipe[1], STDOUT_FILENO);
// Initialize various LLVM/Clang components
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
InitializeAllTargets();
// Prepare compilation arguments
vector<const char *> args;
args.push_back("--target=bpf"); // Target is bpf assembly
args.push_back("-xc"); // Code is in c language
args.push_back("-"); // Read code from stdin
CompilerInvocation *CI = createInvocationFromCommandLine(makeArrayRef(args) , NULL);
// Create CompilerInstance
CompilerInstance Clang;
Clang.setInvocation(CI);
// Initialize CompilerInstace
Clang.createDiagnostics();
// Create and execute action
CodeGenAction *compilerAction;
compilerAction = new EmitObjAction();
Clang.ExecuteAction(*compilerAction);
// Get compiled object (be carefull with buffer size)
close(codeInPipe[0]);
char objBuffer[2048];
read(codeOutPipe[0], objBuffer, 2048);
return 0;
}