5. Building a JIT: Remote-JITing – Process Isolation and Laziness at a Distance¶

Chapter 5 Introduction
Full Code Listing

This tutorial is under active development. It is incomplete and details may change frequently. Nonetheless we invite you to try it out as it stands, and we welcome any feedback.

5.1. Chapter 5 Introduction ¶

Welcome to Chapter 5 of the “Building an ORC-based JIT in LLVM” tutorial. This chapter introduces the ORC RemoteJIT Client/Server APIs and shows how to use them to build a JIT stack that will execute its code via a communications channel with a different process. This can be a separate process on the same machine, a process on a different machine, or even a process on a different platform/architecture. The code builds on top of the lazy-AST-compiling JIT stack from Chapter 4.

To be done – this is going to be a long one:

(1) Introduce channels, RPC, RemoteJIT Client and Server APIs

(2) Describe the client code in greater detail. Discuss modifications of the KaleidoscopeJIT class, and the REPL itself.

(3) Describe the server code.

(4) Describe how to run the demo.

5.2. Full Code Listing ¶

Here is the complete code listing for our running example that JITs lazily from Kaleidoscope ASTS. To build this example, use:

# Compile
clang++ -g toy.cpp `llvm-config --cxxflags --ldflags --system-libs --libs core orcjit native` -O3 -o toy
clang++ -g Server/server.cpp `llvm-config --cxxflags --ldflags --system-libs --libs core orcjit native` -O3 -o toy-server
# Run
./toy-server &
./toy

Here is the code for the modified KaleidoscopeJIT:

//===- KaleidoscopeJIT.h - A simple JIT for Kaleidoscope --------*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Contains a simple JIT definition for use in the kaleidoscope tutorials.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_EXECUTIONENGINE_ORC_KALEIDOSCOPEJIT_H
#define LLVM_EXECUTIONENGINE_ORC_KALEIDOSCOPEJIT_H

#include "RemoteJITUtils.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Triple.h"
#include "llvm/ExecutionEngine/ExecutionEngine.h"
#include "llvm/ExecutionEngine/JITSymbol.h"
#include "llvm/ExecutionEngine/Orc/CompileUtils.h"
#include "llvm/ExecutionEngine/Orc/IndirectionUtils.h"
#include "llvm/ExecutionEngine/Orc/IRCompileLayer.h"
#include "llvm/ExecutionEngine/Orc/IRTransformLayer.h"
#include "llvm/ExecutionEngine/Orc/LambdaResolver.h"
#include "llvm/ExecutionEngine/Orc/RTDyldObjectLinkingLayer.h"
#include "llvm/ExecutionEngine/Orc/OrcRemoteTargetClient.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/Support/DynamicLibrary.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/GVN.h"
#include <algorithm>
#include <cassert>
#include <cstdlib>
#include <memory>
#include <string>
#include <vector>

class PrototypeAST;
class ExprAST;

/// FunctionAST - This class represents a function definition itself.
class FunctionAST {
  std::unique_ptr<PrototypeAST> Proto;
  std::unique_ptr<ExprAST> Body;

public:
  FunctionAST(std::unique_ptr<PrototypeAST> Proto,
              std::unique_ptr<ExprAST> Body)
      : Proto(std::move(Proto)), Body(std::move(Body)) {}

  const PrototypeAST& getProto() const;
  const std::string& getName() const;
  llvm::Function *codegen();
};

/// This will compile FnAST to IR, rename the function to add the given
/// suffix (needed to prevent a name-clash with the function's stub),
/// and then take ownership of the module that the function was compiled
/// into.
std::unique_ptr<llvm::Module>
irgenAndTakeOwnership(FunctionAST &FnAST, const std::string &Suffix);

namespace llvm {
namespace orc {

// Typedef the remote-client API.
using MyRemote = remote::OrcRemoteTargetClient;

class KaleidoscopeJIT {
private:
  std::unique_ptr<TargetMachine> TM;
  const DataLayout DL;
  RTDyldObjectLinkingLayer ObjectLayer;
  IRCompileLayer<decltype(ObjectLayer), SimpleCompiler> CompileLayer;

  using OptimizeFunction =
      std::function<std::shared_ptr<Module>(std::shared_ptr<Module>)>;

  IRTransformLayer<decltype(CompileLayer), OptimizeFunction> OptimizeLayer;

  JITCompileCallbackManager *CompileCallbackMgr;
  std::unique_ptr<IndirectStubsManager> IndirectStubsMgr;
  MyRemote &Remote;

public:
  using ModuleHandle = decltype(OptimizeLayer)::ModuleHandleT;

  KaleidoscopeJIT(MyRemote &Remote)
      : TM(EngineBuilder().selectTarget(Triple(Remote.getTargetTriple()), "",
                                        "", SmallVector<std::string, 0>())),
        DL(TM->createDataLayout()),
        ObjectLayer([&Remote]() {
            return cantFail(Remote.createRemoteMemoryManager());
          }),
        CompileLayer(ObjectLayer, SimpleCompiler(*TM)),
        OptimizeLayer(CompileLayer,
                      [this](std::shared_ptr<Module> M) {
                        return optimizeModule(std::move(M));
                      }),
        Remote(Remote) {
    auto CCMgrOrErr = Remote.enableCompileCallbacks(0);
    if (!CCMgrOrErr) {
      logAllUnhandledErrors(CCMgrOrErr.takeError(), errs(),
                            "Error enabling remote compile callbacks:");
      exit(1);
    }
    CompileCallbackMgr = &*CCMgrOrErr;
    IndirectStubsMgr = cantFail(Remote.createIndirectStubsManager());
    llvm::sys::DynamicLibrary::LoadLibraryPermanently(nullptr);
  }

  TargetMachine &getTargetMachine() { return *TM; }

  ModuleHandle addModule(std::unique_ptr<Module> M) {
    // Build our symbol resolver:
    // Lambda 1: Look back into the JIT itself to find symbols that are part of
    //           the same "logical dylib".
    // Lambda 2: Search for external symbols in the host process.
    auto Resolver = createLambdaResolver(
        [&](const std::string &Name) {
          if (auto Sym = IndirectStubsMgr->findStub(Name, false))
            return Sym;
          if (auto Sym = OptimizeLayer.findSymbol(Name, false))
            return Sym;
          return JITSymbol(nullptr);
        },
        [&](const std::string &Name) {
          if (auto AddrOrErr = Remote.getSymbolAddress(Name))
            return JITSymbol(*AddrOrErr, JITSymbolFlags::Exported);
          else {
            logAllUnhandledErrors(AddrOrErr.takeError(), errs(),
                                  "Error resolving remote symbol:");
            exit(1);
          }
          return JITSymbol(nullptr);
        });

    // Add the set to the JIT with the resolver we created above and a newly
    // created SectionMemoryManager.
    return cantFail(OptimizeLayer.addModule(std::move(M),
                                            std::move(Resolver)));
  }

  Error addFunctionAST(std::unique_ptr<FunctionAST> FnAST) {
    // Create a CompileCallback - this is the re-entry point into the compiler
    // for functions that haven't been compiled yet.
    auto CCInfo = cantFail(CompileCallbackMgr->getCompileCallback());

    // Create an indirect stub. This serves as the functions "canonical
    // definition" - an unchanging (constant address) entry point to the
    // function implementation.
    // Initially we point the stub's function-pointer at the compile callback
    // that we just created. In the compile action for the callback (see below)
    // we will update the stub's function pointer to point at the function
    // implementation that we just implemented.
    if (auto Err = IndirectStubsMgr->createStub(mangle(FnAST->getName()),
                                                CCInfo.getAddress(),
                                                JITSymbolFlags::Exported))
      return Err;

    // Move ownership of FnAST to a shared pointer - C++11 lambdas don't support
    // capture-by-move, which is be required for unique_ptr.
    auto SharedFnAST = std::shared_ptr<FunctionAST>(std::move(FnAST));

    // Set the action to compile our AST. This lambda will be run if/when
    // execution hits the compile callback (via the stub).
    //
    // The steps to compile are:
    // (1) IRGen the function.
    // (2) Add the IR module to the JIT to make it executable like any other
    //     module.
    // (3) Use findSymbol to get the address of the compiled function.
    // (4) Update the stub pointer to point at the implementation so that
    ///    subsequent calls go directly to it and bypass the compiler.
    // (5) Return the address of the implementation: this lambda will actually
    //     be run inside an attempted call to the function, and we need to
    //     continue on to the implementation to complete the attempted call.
    //     The JIT runtime (the resolver block) will use the return address of
    //     this function as the address to continue at once it has reset the
    //     CPU state to what it was immediately before the call.
    CCInfo.setCompileAction(
      [this, SharedFnAST]() {
        auto M = irgenAndTakeOwnership(*SharedFnAST, "$impl");
        addModule(std::move(M));
        auto Sym = findSymbol(SharedFnAST->getName() + "$impl");
        assert(Sym && "Couldn't find compiled function?");
        JITTargetAddress SymAddr = cantFail(Sym.getAddress());
        if (auto Err =
              IndirectStubsMgr->updatePointer(mangle(SharedFnAST->getName()),
                                              SymAddr)) {
          logAllUnhandledErrors(std::move(Err), errs(),
                                "Error updating function pointer: ");
          exit(1);
        }

        return SymAddr;
      });

    return Error::success();
  }

  Error executeRemoteExpr(JITTargetAddress ExprAddr) {
    return Remote.callVoidVoid(ExprAddr);
  }

  JITSymbol findSymbol(const std::string Name) {
    return OptimizeLayer.findSymbol(mangle(Name), true);
  }

  void removeModule(ModuleHandle H) {
    cantFail(OptimizeLayer.removeModule(H));
  }

private:
  std::string mangle(const std::string &Name) {
    std::string MangledName;
    raw_string_ostream MangledNameStream(MangledName);
    Mangler::getNameWithPrefix(MangledNameStream, Name, DL);
    return MangledNameStream.str();
  }

  std::shared_ptr<Module> optimizeModule(std::shared_ptr<Module> M) {
    // Create a function pass manager.
    auto FPM = llvm::make_unique<legacy::FunctionPassManager>(M.get());

    // Add some optimizations.
    FPM->add(createInstructionCombiningPass());
    FPM->add(createReassociatePass());
    FPM->add(createGVNPass());
    FPM->add(createCFGSimplificationPass());
    FPM->doInitialization();

    // Run the optimizations over all functions in the module being added to
    // the JIT.
    for (auto &F : *M)
      FPM->run(F);

    return M;
  }
};

} // end namespace orc
} // end namespace llvm

#endif // LLVM_EXECUTIONENGINE_ORC_KALEIDOSCOPEJIT_H

And the code for the JIT server:

#include "../RemoteJITUtils.h"
#include "llvm/ExecutionEngine/RTDyldMemoryManager.h"
#include "llvm/ExecutionEngine/Orc/OrcRemoteTargetServer.h"
#include "llvm/ExecutionEngine/Orc/OrcABISupport.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/DynamicLibrary.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Support/TargetSelect.h"
#include <cstdint>
#include <cstdio>
#include <cstring>
#include <string>
#include <netinet/in.h>
#include <sys/socket.h>

using namespace llvm;
using namespace llvm::orc;

// Command line argument for TCP port.
cl::opt<uint32_t> Port("port",
                       cl::desc("TCP port to listen on"),
                       cl::init(20000));

ExitOnError ExitOnErr;

using MainFun = int (*)(int, const char*[]);

template <typename NativePtrT>
NativePtrT MakeNative(uint64_t P) {
  return reinterpret_cast<NativePtrT>(static_cast<uintptr_t>(P));
}

extern "C"
void printExprResult(double Val) {
  printf("Expression evaluated to: %f\n", Val);
}

// --- LAZY COMPILE TEST ---
int main(int argc, char* argv[]) {
  if (argc == 0)
    ExitOnErr.setBanner("jit_server: ");
  else
    ExitOnErr.setBanner(std::string(argv[0]) + ": ");

  // --- Initialize LLVM ---
  cl::ParseCommandLineOptions(argc, argv, "LLVM lazy JIT example.\n");

  InitializeNativeTarget();
  InitializeNativeTargetAsmPrinter();
  InitializeNativeTargetAsmParser();

  if (sys::DynamicLibrary::LoadLibraryPermanently(nullptr)) {
    errs() << "Error loading program symbols.\n";
    return 1;
  }

  // --- Initialize remote connection ---

  int sockfd = socket(PF_INET, SOCK_STREAM, 0);
  sockaddr_in servAddr, clientAddr;
  socklen_t clientAddrLen = sizeof(clientAddr);
  memset(&servAddr, 0, sizeof(servAddr));
  servAddr.sin_family = PF_INET;
  servAddr.sin_family = INADDR_ANY;
  servAddr.sin_port = htons(Port);

  {
    // avoid "Address already in use" error.
    int yes = 1;
    if (setsockopt(sockfd,SOL_SOCKET,SO_REUSEADDR,&yes,sizeof(int)) == -1) {
      errs() << "Error calling setsockopt.\n";
      return 1;
    }
  }

  if (bind(sockfd, reinterpret_cast<sockaddr*>(&servAddr),
           sizeof(servAddr)) < 0) {
    errs() << "Error on binding.\n";
    return 1;
  }
  listen(sockfd, 1);
  int newsockfd = accept(sockfd, reinterpret_cast<sockaddr*>(&clientAddr),
                         &clientAddrLen);

  auto SymbolLookup =
    [](const std::string &Name) {
      return RTDyldMemoryManager::getSymbolAddressInProcess(Name);
    };

  auto RegisterEHFrames =
    [](uint8_t *Addr, uint32_t Size) {
      RTDyldMemoryManager::registerEHFramesInProcess(Addr, Size);
    };

  auto DeregisterEHFrames =
    [](uint8_t *Addr, uint32_t Size) {
      RTDyldMemoryManager::deregisterEHFramesInProcess(Addr, Size);
    };

  FDRPCChannel TCPChannel(newsockfd, newsockfd);

  using MyServerT = remote::OrcRemoteTargetServer<FDRPCChannel, OrcX86_64_SysV>;

  MyServerT Server(TCPChannel, SymbolLookup, RegisterEHFrames, DeregisterEHFrames);

  while (!Server.receivedTerminate())
    ExitOnErr(Server.handleOne());

  return 0;
}

5. Building a JIT: Remote-JITing – Process Isolation and Laziness at a Distance¶

5.1. Chapter 5 Introduction¶

5.2. Full Code Listing¶

5.1. Chapter 5 Introduction ¶

5.2. Full Code Listing ¶