[clang-tools-extra] [clangd] [C++20] [Modules] Introduce initial support for C++20 Modules (PR #66462)
Chuanqi Xu via cfe-commits
cfe-commits at lists.llvm.org
Fri Jun 14 01:50:36 PDT 2024
================
@@ -0,0 +1,370 @@
+//===----------------- ModulesBuilder.cpp ------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "ModulesBuilder.h"
+
+#include "Compiler.h"
+#include "support/Logger.h"
+
+#include "clang/Frontend/FrontendAction.h"
+#include "clang/Frontend/FrontendActions.h"
+
+#include "clang/Serialization/ASTReader.h"
+
+namespace clang {
+namespace clangd {
+
+namespace {
+
+// Create a path to store module files. Generally it should be:
+//
+// {TEMP_DIRS}/clangd/module_files/{PrefixDir}-%%-%%-%%-%%-%%-%%/.
+//
+// {TEMP_DIRS} is the temporary directory for the system, e.g., "/var/tmp"
+// or "C:/TEMP".
+//
+// '%%' means random value to make the generated path unique.
+//
+// \param MainFile is used to get the root of the project from global
+// compilation database. \param PrefixDir is used to get the user
+// defined prefix for module files. This is useful when we want to seperate
+// module files. e.g., we want to build module files for the same module unit
+// `a.cppm` with 2 different users `b.cpp` and `c.cpp` and we don't want the
+// module file for `b.cpp` be conflict with the module files for `c.cpp`. Then
+// we can put the 2 module files into different dirs like:
+//
+// ${TEMP_DIRS}/clangd/module_files/b.cpp/a.pcm
+// ${TEMP_DIRS}/clangd/module_files/c.cpp/a.pcm
+//
+// TODO: Move these module fils out of the temporary directory if the module
+// files are persistent.
+llvm::SmallString<256> getUniqueModuleFilesPath(PathRef MainFile,
+ llvm::StringRef PrefixDir) {
+ llvm::SmallString<256> ResultPattern;
+
+ llvm::sys::path::system_temp_directory(/*erasedOnReboot=*/true,
+ ResultPattern);
+
+ llvm::sys::path::append(ResultPattern, "clangd");
+ llvm::sys::path::append(ResultPattern, "module_files");
+
+ llvm::sys::path::append(ResultPattern, PrefixDir);
+
+ ResultPattern.append("-%%-%%-%%-%%-%%-%%");
+
+ llvm::SmallString<256> Result;
+ llvm::sys::fs::createUniquePath(ResultPattern, Result,
+ /*MakeAbsolute=*/false);
+
+ llvm::sys::fs::create_directories(Result);
+ return Result;
+}
+
+// Get the absolute path for the filename from the compile command.
+llvm::SmallString<128> getAbsolutePath(const tooling::CompileCommand &Cmd) {
+ llvm::SmallString<128> AbsolutePath;
+ if (llvm::sys::path::is_absolute(Cmd.Filename)) {
+ AbsolutePath = Cmd.Filename;
+ } else {
+ AbsolutePath = Cmd.Directory;
+ llvm::sys::path::append(AbsolutePath, Cmd.Filename);
+ llvm::sys::path::remove_dots(AbsolutePath, true);
+ }
+ return AbsolutePath;
+}
+
+// Get a unique module file path under \param ModuleFilesPrefix.
+std::string getModuleFilePath(llvm::StringRef ModuleName,
+ PathRef ModuleFilesPrefix) {
+ llvm::SmallString<256> ModuleFilePattern(ModuleFilesPrefix);
+ auto [PrimaryModuleName, PartitionName] = ModuleName.split(':');
+ llvm::sys::path::append(ModuleFilePattern, PrimaryModuleName);
+ if (!PartitionName.empty()) {
+ ModuleFilePattern.append("-");
+ ModuleFilePattern.append(PartitionName);
+ }
+
+ ModuleFilePattern.append(".pcm");
+
+ llvm::SmallString<256> ModuleFilePath;
+ llvm::sys::fs::createUniquePath(ModuleFilePattern, ModuleFilePath,
+ /*MakeAbsolute=*/false);
+
+ return std::string(ModuleFilePath);
+}
+} // namespace
+
+// FailedPrerequisiteModules - stands for the PrerequisiteModules which has
+// errors happened during the building process.
+class FailedPrerequisiteModules : public PrerequisiteModules {
+public:
+ ~FailedPrerequisiteModules() override = default;
+
+ // We shouldn't adjust the compilation commands based on
+ // FailedPrerequisiteModules.
+ void adjustHeaderSearchOptions(HeaderSearchOptions &Options) const override {
+ }
+
+ // FailedPrerequisiteModules can never be reused.
+ bool
+ canReuse(const CompilerInvocation &CI,
+ llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>) const override {
+ return false;
+ }
+
+ // No module unit got built in FailedPrerequisiteModules.
+ bool isModuleUnitBuilt(llvm::StringRef ModuleName) const override {
+ return false;
+ }
+};
+
+// StandalonePrerequisiteModules - stands for PrerequisiteModules for which all
+// the required modules are built successfully. All the module files
+// are owned by the StandalonePrerequisiteModules class.
+//
+// Any of the built module files won't be shared with other instances of the
+// class. So that we can avoid worrying thread safety.
+//
+// We don't need to worry about duplicated module names here since the standard
+// guarantees the module names should be unique to a program.
+class StandalonePrerequisiteModules : public PrerequisiteModules {
+public:
+ StandalonePrerequisiteModules() = default;
+
+ StandalonePrerequisiteModules(const StandalonePrerequisiteModules &) = delete;
+ StandalonePrerequisiteModules
+ operator=(const StandalonePrerequisiteModules &) = delete;
+ StandalonePrerequisiteModules(StandalonePrerequisiteModules &&) = delete;
+ StandalonePrerequisiteModules
+ operator=(StandalonePrerequisiteModules &&) = delete;
+
+ ~StandalonePrerequisiteModules() override = default;
+
+ void adjustHeaderSearchOptions(HeaderSearchOptions &Options) const override {
+ // Appending all built module files.
+ for (auto &RequiredModule : RequiredModules)
+ Options.PrebuiltModuleFiles.insert_or_assign(
+ RequiredModule.ModuleName, RequiredModule.ModuleFilePath);
+ }
+
+ bool canReuse(const CompilerInvocation &CI,
+ llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>) const override;
+
+ bool isModuleUnitBuilt(llvm::StringRef ModuleName) const override {
+ return BuiltModuleNames.contains(ModuleName);
+ }
+
+ void addModuleFile(llvm::StringRef ModuleName,
+ llvm::StringRef ModuleFilePath) {
+ RequiredModules.emplace_back(ModuleName, ModuleFilePath);
+ BuiltModuleNames.insert(ModuleName);
+ }
+
+private:
+ struct ModuleFile {
+ ModuleFile(llvm::StringRef ModuleName, PathRef ModuleFilePath)
+ : ModuleName(ModuleName.str()), ModuleFilePath(ModuleFilePath.str()) {}
+
+ ModuleFile() = delete;
+
+ ModuleFile(const ModuleFile &) = delete;
+ ModuleFile operator=(const ModuleFile &) = delete;
+
+ // The move constructor is needed for llvm::SmallVector.
+ ModuleFile(ModuleFile &&Other)
+ : ModuleName(std::move(Other.ModuleName)),
+ ModuleFilePath(std::move(Other.ModuleFilePath)) {}
+
+ ModuleFile &operator=(ModuleFile &&Other) = delete;
+
+ ~ModuleFile() {
+ if (!ModuleFilePath.empty())
+ llvm::sys::fs::remove(ModuleFilePath);
+ }
+
+ std::string ModuleName;
+ std::string ModuleFilePath;
+ };
+
+ llvm::SmallVector<ModuleFile, 8> RequiredModules;
+ // A helper class to speedup the query if a module is built.
+ llvm::StringSet<> BuiltModuleNames;
+};
+
+namespace {
+// Build a module file for module with `ModuleName`. Return false
+// when there are problem happens. Return true when the
+// module file exists or built successfully. The information of built
+// module file are stored in \param BuiltModuleFiles.
+bool buildModuleFile(llvm::StringRef ModuleName,
+ const GlobalCompilationDatabase &CDB,
+ const ThreadsafeFS *TFS, ProjectModules *MDB,
+ PathRef ModuleFilesPrefix,
+ StandalonePrerequisiteModules &BuiltModuleFiles) {
+ if (BuiltModuleFiles.isModuleUnitBuilt(ModuleName))
+ return true;
+
+ PathRef ModuleUnitFileName = MDB->getSourceForModuleName(ModuleName);
+ // It is possible that we're meeting third party modules (modules whose
+ // source are not in the project. e.g, the std module may be a third-party
+ // module for most projects) or something wrong with the implementation of
+ // ProjectModules.
+ // FIXME: How should we treat third party modules here? If we want to ignore
+ // third party modules, we should return true instead of false here.
+ // Currently we simply bail out.
+ if (ModuleUnitFileName.empty()) {
+ elog("Failed to get the source for module name {0}. Maybe it is from third "
+ "party libraries or something goes wrong",
+ ModuleName);
+ return false;
+ }
+
+ for (auto &RequiredModuleName : MDB->getRequiredModules(ModuleUnitFileName)) {
+ // Return early if there are errors building the module file.
+ if (!buildModuleFile(RequiredModuleName, CDB, TFS, MDB, ModuleFilesPrefix,
+ BuiltModuleFiles)) {
+ elog("Failed to build {0} since failed to build {1}", ModuleName,
+ RequiredModuleName);
+ return false;
+ }
+ }
+
+ auto Cmd = CDB.getCompileCommand(ModuleUnitFileName);
+ if (!Cmd) {
+ elog("Failed to get compile command for {0}", ModuleName);
+ return false;
+ }
+
+ Cmd->Output = getModuleFilePath(ModuleName, ModuleFilesPrefix);
+
+ ParseInputs Inputs;
+ Inputs.TFS = TFS;
+ Inputs.CompileCommand = std::move(*Cmd);
+
+ IgnoreDiagnostics IgnoreDiags;
+ auto CI = buildCompilerInvocation(Inputs, IgnoreDiags);
+ if (!CI) {
+ elog("Failed to build compiler invocation for {0}", ModuleName);
+ return false;
+ }
+
+ auto FS = Inputs.TFS->view(Inputs.CompileCommand.Directory);
+ auto AbsolutePath = getAbsolutePath(Inputs.CompileCommand);
+ auto Buf = FS->getBufferForFile(AbsolutePath);
+ if (!Buf) {
+ elog("Failed to create buffer for {0}", AbsolutePath);
+ return false;
+ }
+
+ // Hash the contents of input files and store the hash value to the BMI files.
+ // So that we can check if the files are still valid when we want to reuse the
+ // BMI files.
+ CI->getHeaderSearchOpts().ValidateASTInputFilesContent = true;
+
+ BuiltModuleFiles.adjustHeaderSearchOptions(CI->getHeaderSearchOpts());
+
+ CI->getFrontendOpts().OutputFile = Inputs.CompileCommand.Output;
+ auto Clang =
+ prepareCompilerInstance(std::move(CI), /*Preamble=*/nullptr,
+ std::move(*Buf), std::move(FS), IgnoreDiags);
+ if (!Clang) {
+ elog("Failed to prepare compiler instance for {0}", AbsolutePath);
+ return false;
+ }
+
+ GenerateModuleInterfaceAction Action;
+ Clang->ExecuteAction(Action);
+
+ if (Clang->getDiagnostics().hasErrorOccurred()) {
+ elog("Compilation for {0} failed", AbsolutePath);
+ return false;
+ }
+
+ BuiltModuleFiles.addModuleFile(ModuleName, Inputs.CompileCommand.Output);
+ return true;
+}
+} // namespace
+
+std::unique_ptr<PrerequisiteModules>
+ModulesBuilder::buildPrerequisiteModulesFor(PathRef File,
+ const ThreadsafeFS *TFS) const {
+ std::unique_ptr<ProjectModules> MDB = CDB.getProjectModules(File);
+ if (!MDB)
+ return {};
----------------
ChuanqiXu9 wrote:
Makes sense. Done with the following one.
https://github.com/llvm/llvm-project/pull/66462
More information about the cfe-commits
mailing list