[clang-repl] Support wasm execution (#86402)

This commit introduces support for running clang-repl and executing C++
code interactively inside a Javascript engine using WebAssembly when
built with Emscripten. This is achieved by producing WASM "shared
libraries" that can be loaded by the Emscripten runtime using dlopen()

More discussion is available in https://reviews.llvm.org/D158140

Co-authored-by: Anubhab Ghosh <anubhabghosh.me@gmail.com>

6 files changed, 179 insertions, 4 deletions

diff --git a/clang/lib/Interpreter/CMakeLists.txt b/clang/lib/Interpreter/CMakeLists.txt
index 9065f99..6a06965 100644
--- a/clang/lib/Interpreter/CMakeLists.txt
+++ b/clang/lib/Interpreter/CMakeLists.txt
@@ -12,6 +12,10 @@ set(LLVM_LINK_COMPONENTS
    TargetParser
   )
 
+if (EMSCRIPTEN AND "lld" IN_LIST LLVM_ENABLE_PROJECTS)
+  set(WASM_SRC Wasm.cpp)
+endif()
+
 add_clang_library(clangInterpreter
   DeviceOffload.cpp
   CodeCompletion.cpp
@@ -20,6 +24,8 @@ add_clang_library(clangInterpreter
   Interpreter.cpp
   InterpreterUtils.cpp
   Value.cpp
+  ${WASM_SRC}
+  PARTIAL_SOURCES_INTENDED
 
   DEPENDS
   intrinsics_gen
diff --git a/clang/lib/Interpreter/IncrementalExecutor.cpp b/clang/lib/Interpreter/IncrementalExecutor.cpp
index 6f03610..1824a5b 100644
--- a/clang/lib/Interpreter/IncrementalExecutor.cpp
+++ b/clang/lib/Interpreter/IncrementalExecutor.cpp
@@ -36,6 +36,8 @@ LLVM_ATTRIBUTE_USED void linkComponents() {
 }
 
 namespace clang {
+IncrementalExecutor::IncrementalExecutor(llvm::orc::ThreadSafeContext &TSC)
+    : TSCtx(TSC) {}
 
 llvm::Expected<std::unique_ptr<llvm::orc::LLJITBuilder>>
 IncrementalExecutor::createDefaultJITBuilder(
diff --git a/clang/lib/Interpreter/IncrementalExecutor.h b/clang/lib/Interpreter/IncrementalExecutor.h
index b434720..7954cde 100644
--- a/clang/lib/Interpreter/IncrementalExecutor.h
+++ b/clang/lib/Interpreter/IncrementalExecutor.h
@@ -43,16 +43,19 @@ class IncrementalExecutor {
   llvm::DenseMap<const PartialTranslationUnit *, llvm::orc::ResourceTrackerSP>
       ResourceTrackers;
 
+protected:
+  IncrementalExecutor(llvm::orc::ThreadSafeContext &TSC);
+
 public:
   enum SymbolNameKind { IRName, LinkerName };
 
   IncrementalExecutor(llvm::orc::ThreadSafeContext &TSC,
                       llvm::orc::LLJITBuilder &JITBuilder, llvm::Error &Err);
-  ~IncrementalExecutor();
+  virtual ~IncrementalExecutor();
 
-  llvm::Error addModule(PartialTranslationUnit &PTU);
-  llvm::Error removeModule(PartialTranslationUnit &PTU);
-  llvm::Error runCtors() const;
+  virtual llvm::Error addModule(PartialTranslationUnit &PTU);
+  virtual llvm::Error removeModule(PartialTranslationUnit &PTU);
+  virtual llvm::Error runCtors() const;
   llvm::Error cleanUp();
   llvm::Expected<llvm::orc::ExecutorAddr>
   getSymbolAddress(llvm::StringRef Name, SymbolNameKind NameKind) const;
diff --git a/clang/lib/Interpreter/Interpreter.cpp b/clang/lib/Interpreter/Interpreter.cpp
index 7a95278..49dc92d 100644
--- a/clang/lib/Interpreter/Interpreter.cpp
+++ b/clang/lib/Interpreter/Interpreter.cpp
@@ -15,6 +15,9 @@
 #include "IncrementalExecutor.h"
 #include "IncrementalParser.h"
 #include "InterpreterUtils.h"
+#ifdef __EMSCRIPTEN__
+#include "Wasm.h"
+#endif // __EMSCRIPTEN__
 
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/Mangle.h"
@@ -186,6 +189,12 @@ IncrementalCompilerBuilder::CreateCpp() {
   std::vector<const char *> Argv;
   Argv.reserve(5 + 1 + UserArgs.size());
   Argv.push_back("-xc++");
+#ifdef __EMSCRIPTEN__
+  Argv.push_back("-target");
+  Argv.push_back("wasm32-unknown-emscripten");
+  Argv.push_back("-pie");
+  Argv.push_back("-shared");
+#endif
   Argv.insert(Argv.end(), UserArgs.begin(), UserArgs.end());
 
   std::string TT = TargetTriple ? *TargetTriple : llvm::sys::getProcessTriple();
@@ -426,8 +435,12 @@ llvm::Error Interpreter::CreateExecutor() {
   }
 
   llvm::Error Err = llvm::Error::success();
+#ifdef __EMSCRIPTEN__
+  auto Executor = std::make_unique<WasmIncrementalExecutor>(*TSCtx);
+#else
   auto Executor =
       std::make_unique<IncrementalExecutor>(*TSCtx, *JITBuilder, Err);
+#endif
   if (!Err)
     IncrExecutor = std::move(Executor);
 
diff --git a/clang/lib/Interpreter/Wasm.cpp b/clang/lib/Interpreter/Wasm.cpp
new file mode 100644
index 0000000..1001410
--- /dev/null
+++ b/clang/lib/Interpreter/Wasm.cpp
@@ -0,0 +1,114 @@
+//===----------------- Wasm.cpp - Wasm Interpreter --------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements interpreter support for code execution in WebAssembly.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Wasm.h"
+#include "IncrementalExecutor.h"
+
+#include <llvm/IR/LegacyPassManager.h>
+#include <llvm/IR/Module.h>
+#include <llvm/MC/TargetRegistry.h>
+#include <llvm/Target/TargetMachine.h>
+
+#include <clang/Interpreter/Interpreter.h>
+
+#include <string>
+
+namespace lld {
+namespace wasm {
+bool link(llvm::ArrayRef<const char *> args, llvm::raw_ostream &stdoutOS,
+          llvm::raw_ostream &stderrOS, bool exitEarly, bool disableOutput);
+} // namespace wasm
+} // namespace lld
+
+#include <dlfcn.h>
+
+namespace clang {
+
+WasmIncrementalExecutor::WasmIncrementalExecutor(
+    llvm::orc::ThreadSafeContext &TSC)
+    : IncrementalExecutor(TSC) {}
+
+llvm::Error WasmIncrementalExecutor::addModule(PartialTranslationUnit &PTU) {
+  std::string ErrorString;
+
+  const llvm::Target *Target = llvm::TargetRegistry::lookupTarget(
+      PTU.TheModule->getTargetTriple(), ErrorString);
+  if (!Target) {
+    return llvm::make_error<llvm::StringError>("Failed to create Wasm Target: ",
+                                               llvm::inconvertibleErrorCode());
+  }
+
+  llvm::TargetOptions TO = llvm::TargetOptions();
+  llvm::TargetMachine *TargetMachine = Target->createTargetMachine(
+      PTU.TheModule->getTargetTriple(), "", "", TO, llvm::Reloc::Model::PIC_);
+  PTU.TheModule->setDataLayout(TargetMachine->createDataLayout());
+  std::string OutputFileName = PTU.TheModule->getName().str() + ".wasm";
+
+  std::error_code Error;
+  llvm::raw_fd_ostream OutputFile(llvm::StringRef(OutputFileName), Error);
+
+  llvm::legacy::PassManager PM;
+  if (TargetMachine->addPassesToEmitFile(PM, OutputFile, nullptr,
+                                         llvm::CodeGenFileType::ObjectFile)) {
+    return llvm::make_error<llvm::StringError>(
+        "Wasm backend cannot produce object.", llvm::inconvertibleErrorCode());
+  }
+
+  if (!PM.run(*PTU.TheModule)) {
+
+    return llvm::make_error<llvm::StringError>("Failed to emit Wasm object.",
+                                               llvm::inconvertibleErrorCode());
+  }
+
+  OutputFile.close();
+
+  std::vector<const char *> LinkerArgs = {"wasm-ld",
+                                          "-pie",
+                                          "--import-memory",
+                                          "--no-entry",
+                                          "--export-all",
+                                          "--experimental-pic",
+                                          "--no-export-dynamic",
+                                          "--stack-first",
+                                          OutputFileName.c_str(),
+                                          "-o",
+                                          OutputFileName.c_str()};
+  int Result =
+      lld::wasm::link(LinkerArgs, llvm::outs(), llvm::errs(), false, false);
+  if (!Result)
+    return llvm::make_error<llvm::StringError>(
+        "Failed to link incremental module", llvm::inconvertibleErrorCode());
+
+  void *LoadedLibModule =
+      dlopen(OutputFileName.c_str(), RTLD_NOW | RTLD_GLOBAL);
+  if (LoadedLibModule == nullptr) {
+    llvm::errs() << dlerror() << '\n';
+    return llvm::make_error<llvm::StringError>(
+        "Failed to load incremental module", llvm::inconvertibleErrorCode());
+  }
+
+  return llvm::Error::success();
+}
+
+llvm::Error WasmIncrementalExecutor::removeModule(PartialTranslationUnit &PTU) {
+  return llvm::make_error<llvm::StringError>("Not implemented yet",
+                                             llvm::inconvertibleErrorCode());
+}
+
+llvm::Error WasmIncrementalExecutor::runCtors() const {
+  // This seems to be automatically done when using dlopen()
+  return llvm::Error::success();
+}
+
+WasmIncrementalExecutor::~WasmIncrementalExecutor() = default;
+
+} // namespace clang
diff --git a/clang/lib/Interpreter/Wasm.h b/clang/lib/Interpreter/Wasm.h
new file mode 100644
index 0000000..b1fd880
--- /dev/null
+++ b/clang/lib/Interpreter/Wasm.h
@@ -0,0 +1,37 @@
+//===------------------ Wasm.h - Wasm Interpreter ---------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements interpreter support for code execution in WebAssembly.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_INTERPRETER_WASM_H
+#define LLVM_CLANG_LIB_INTERPRETER_WASM_H
+
+#ifndef __EMSCRIPTEN__
+#error "This requires emscripten."
+#endif // __EMSCRIPTEN__
+
+#include "IncrementalExecutor.h"
+
+namespace clang {
+
+class WasmIncrementalExecutor : public IncrementalExecutor {
+public:
+  WasmIncrementalExecutor(llvm::orc::ThreadSafeContext &TSC);
+
+  llvm::Error addModule(PartialTranslationUnit &PTU) override;
+  llvm::Error removeModule(PartialTranslationUnit &PTU) override;
+  llvm::Error runCtors() const override;
+
+  ~WasmIncrementalExecutor() override;
+};
+
+} // namespace clang
+
+#endif // LLVM_CLANG_LIB_INTERPRETER_WASM_H