Skip to content

[clangd] [Modules] Support Reusable Modules Builder #106683

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Nov 12, 2024
Merged

[clangd] [Modules] Support Reusable Modules Builder #106683

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
15aa6af
[clangd] [Modules] Support Reusable Modules Builder
ChuanqiXu9 Aug 30, 2024
4ed7bf5
Remove unique builder
ChuanqiXu9 Oct 31, 2024
dcdd18a
Update
ChuanqiXu9 Nov 4, 2024
370b01f
Address comments
ChuanqiXu9 Nov 6, 2024
4e0f1e3
Address comments
ChuanqiXu9 Nov 12, 2024
821dc8d
address comments
ChuanqiXu9 Nov 12, 2024
483ee8d
fmt
ChuanqiXu9 Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
285 changes: 213 additions & 72 deletions clang-tools-extra/clangd/ModulesBuilder.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@
#include "clang/Frontend/FrontendActions.h"
#include "clang/Serialization/ASTReader.h"
#include "clang/Serialization/InMemoryModuleCache.h"
#include "llvm/ADT/ScopeExit.h"
#include <queue>

namespace clang {
namespace clangd {
Expand Down Expand Up @@ -124,6 +126,11 @@ struct ModuleFile {
llvm::sys::fs::remove(ModuleFilePath);
}

StringRef getModuleName() const { return ModuleName; }

StringRef getModuleFilePath() const { return ModuleFilePath; }

private:
std::string ModuleName;
std::string ModuleFilePath;
};
Expand Down Expand Up @@ -192,33 +199,28 @@ bool IsModuleFilesUpToDate(
});
}

// StandalonePrerequisiteModules - stands for PrerequisiteModules for which all
// ReusablePrerequisiteModules - 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 {
// are owned by the modules builder.
class ReusablePrerequisiteModules : public PrerequisiteModules {
public:
StandalonePrerequisiteModules() = default;
ReusablePrerequisiteModules() = default;

StandalonePrerequisiteModules(const StandalonePrerequisiteModules &) = delete;
StandalonePrerequisiteModules
operator=(const StandalonePrerequisiteModules &) = delete;
StandalonePrerequisiteModules(StandalonePrerequisiteModules &&) = delete;
StandalonePrerequisiteModules
operator=(StandalonePrerequisiteModules &&) = delete;
ReusablePrerequisiteModules(const ReusablePrerequisiteModules &) = delete;
ReusablePrerequisiteModules
operator=(const ReusablePrerequisiteModules &) = delete;
ReusablePrerequisiteModules(ReusablePrerequisiteModules &&) = delete;
ReusablePrerequisiteModules
operator=(ReusablePrerequisiteModules &&) = delete;

~StandalonePrerequisiteModules() override = default;
~ReusablePrerequisiteModules() 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);
RequiredModule->getModuleName().str(),
RequiredModule->getModuleFilePath().str());
}

bool canReuse(const CompilerInvocation &CI,
Expand All @@ -228,54 +230,30 @@ class StandalonePrerequisiteModules : public PrerequisiteModules {
return BuiltModuleNames.contains(ModuleName);
}

void addModuleFile(llvm::StringRef ModuleName,
llvm::StringRef ModuleFilePath) {
RequiredModules.emplace_back(ModuleName, ModuleFilePath);
BuiltModuleNames.insert(ModuleName);
void addModuleFile(std::shared_ptr<ModuleFile> BMI) {
BuiltModuleNames.insert(BMI->getModuleName());
RequiredModules.emplace_back(std::move(BMI));
}

private:
llvm::SmallVector<ModuleFile, 8> RequiredModules;
llvm::SmallVector<std::shared_ptr<ModuleFile>, 8> RequiredModules;
// A helper class to speedup the query if a module is built.
llvm::StringSet<> BuiltModuleNames;
};

// Build a module file for module with `ModuleName`. The information of built
// module file are stored in \param BuiltModuleFiles.
llvm::Error buildModuleFile(llvm::StringRef ModuleName,
const GlobalCompilationDatabase &CDB,
const ThreadsafeFS &TFS, ProjectModules &MDB,
PathRef ModuleFilesPrefix,
StandalonePrerequisiteModules &BuiltModuleFiles) {
if (BuiltModuleFiles.isModuleUnitBuilt(ModuleName))
return llvm::Error::success();

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())
return llvm::createStringError("Failed to get the primary source");

/// Build a module file for module with `ModuleName`. The information of built
/// module file are stored in \param BuiltModuleFiles.
llvm::Expected<ModuleFile>
buildModuleFile(llvm::StringRef ModuleName, PathRef ModuleUnitFileName,
const GlobalCompilationDatabase &CDB, const ThreadsafeFS &TFS,
PathRef ModuleFilesPrefix,
const ReusablePrerequisiteModules &BuiltModuleFiles) {
// Try cheap operation earlier to boil-out cheaply if there are problems.
auto Cmd = CDB.getCompileCommand(ModuleUnitFileName);
if (!Cmd)
return llvm::createStringError(
llvm::formatv("No compile command for {0}", ModuleUnitFileName));

for (auto &RequiredModuleName : MDB.getRequiredModules(ModuleUnitFileName)) {
// Return early if there are errors building the module file.
if (llvm::Error Err = buildModuleFile(RequiredModuleName, CDB, TFS, MDB,
ModuleFilesPrefix, BuiltModuleFiles))
return llvm::createStringError(
llvm::formatv("Failed to build dependency {0}: {1}",
RequiredModuleName, llvm::toString(std::move(Err))));
}

Cmd->Output = getModuleFilePath(ModuleName, ModuleFilesPrefix);

ParseInputs Inputs;
Expand Down Expand Up @@ -316,36 +294,205 @@ llvm::Error buildModuleFile(llvm::StringRef ModuleName,
if (Clang->getDiagnostics().hasErrorOccurred())
return llvm::createStringError("Compilation failed");

BuiltModuleFiles.addModuleFile(ModuleName, Inputs.CompileCommand.Output);
return llvm::Error::success();
return ModuleFile{ModuleName, Inputs.CompileCommand.Output};
}

bool ReusablePrerequisiteModules::canReuse(
const CompilerInvocation &CI,
llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS) const {
if (RequiredModules.empty())
return true;

SmallVector<StringRef> BMIPaths;
for (auto &MF : RequiredModules)
BMIPaths.push_back(MF->getModuleFilePath());
return IsModuleFilesUpToDate(BMIPaths, *this, VFS);
}

class ModuleFileCache {
public:
ModuleFileCache(const GlobalCompilationDatabase &CDB) : CDB(CDB) {}

llvm::Error
getOrBuildModuleFile(StringRef ModuleName, const ThreadsafeFS &TFS,
ProjectModules &MDB,
ReusablePrerequisiteModules &RequiredModules);
const GlobalCompilationDatabase &getCDB() const { return CDB; }

std::shared_ptr<ModuleFile>
getValidModuleFile(StringRef ModuleName, ProjectModules &MDB,
const ThreadsafeFS &TFS,
PrerequisiteModules &BuiltModuleFiles);

void add(StringRef ModuleName, std::shared_ptr<ModuleFile> ModuleFile) {
std::lock_guard<std::mutex> _(ModuleFilesMutex);

ModuleFiles.insert_or_assign(ModuleName, ModuleFile);
}

private:
const GlobalCompilationDatabase &CDB;

llvm::StringMap<std::shared_ptr<ModuleFile>> ModuleFiles;
// Mutex to guard accesses to ModuleFiles.
std::mutex ModuleFilesMutex;
};

/// Collect the directly and indirectly required module names for \param
/// ModuleName. The \param ModuleName is guaranteed to be the first element in
/// \param ModuleNames.
void getAllRequiredModules(ProjectModules &MDB, StringRef ModuleName,
llvm::SmallVector<StringRef> &ModuleNames) {
std::queue<StringRef> Worklist;
llvm::StringSet<> ModuleNamesSet;
Worklist.push(ModuleName);

while (!Worklist.empty()) {
StringRef CurrentModule = Worklist.front();
Worklist.pop();

if (!ModuleNamesSet.insert(CurrentModule).second)
continue;

ModuleNames.push_back(CurrentModule);

for (StringRef RequiredModuleName :
MDB.getRequiredModules(MDB.getSourceForModuleName(CurrentModule)))
if (!ModuleNamesSet.contains(RequiredModuleName))
Worklist.push(RequiredModuleName);
}
}

std::shared_ptr<ModuleFile>
ModuleFileCache::getValidModuleFile(StringRef ModuleName, ProjectModules &MDB,
const ThreadsafeFS &TFS,
PrerequisiteModules &BuiltModuleFiles) {
{
std::lock_guard<std::mutex> _(ModuleFilesMutex);

if (ModuleFiles.find(ModuleName) == ModuleFiles.end())
return nullptr;
}

llvm::SmallVector<StringRef> ModuleNames;
getAllRequiredModules(MDB, ModuleName, ModuleNames);

llvm::SmallVector<std::shared_ptr<ModuleFile>> RequiredModuleFiles;

{
std::lock_guard<std::mutex> _(ModuleFilesMutex);

for (StringRef ModuleName : ModuleNames) {
auto Iter = ModuleFiles.find(ModuleName);
if (Iter == ModuleFiles.end())
return nullptr;

RequiredModuleFiles.push_back(Iter->second);
}
}

if (RequiredModuleFiles.empty())
return nullptr;

if (llvm::all_of(RequiredModuleFiles, [&](auto MF) {
return IsModuleFileUpToDate(MF->getModuleFilePath(), BuiltModuleFiles,
TFS.view(std::nullopt));
}))
return RequiredModuleFiles[0];

return nullptr;
}
} // namespace

class ModulesBuilder::ModulesBuilderImpl {
public:
ModulesBuilderImpl(const GlobalCompilationDatabase &CDB) : Cache(CDB) {}

const GlobalCompilationDatabase &getCDB() const { return Cache.getCDB(); }

llvm::Error
getOrBuildModuleFile(StringRef ModuleName, const ThreadsafeFS &TFS,
ProjectModules &MDB,
ReusablePrerequisiteModules &BuiltModuleFiles);

private:
ModuleFileCache Cache;
};

llvm::Error ModulesBuilder::ModulesBuilderImpl::getOrBuildModuleFile(
StringRef ModuleName, const ThreadsafeFS &TFS, ProjectModules &MDB,
ReusablePrerequisiteModules &BuiltModuleFiles) {
if (BuiltModuleFiles.isModuleUnitBuilt(ModuleName))
return llvm::Error::success();

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 project) 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())
return llvm::createStringError(
llvm::formatv("Don't get the module unit for module {0}", ModuleName));

for (auto &RequiredModuleName : MDB.getRequiredModules(ModuleUnitFileName))
// Return early if there are errors building the module file.
if (!getOrBuildModuleFile(RequiredModuleName, TFS, MDB, BuiltModuleFiles))
return llvm::createStringError(
llvm::formatv("Failed to build module {0}", RequiredModuleName));

if (std::shared_ptr<ModuleFile> Cached =
Cache.getValidModuleFile(ModuleName, MDB, TFS, BuiltModuleFiles)) {
log("Reusing module {0} from {1}", ModuleName, Cached->getModuleFilePath());
BuiltModuleFiles.addModuleFile(Cached);
return llvm::Error::success();
}

log("Building module {0}", ModuleName);

llvm::SmallString<256> ModuleFilesPrefix =
getUniqueModuleFilesPath(ModuleUnitFileName);

llvm::Expected<ModuleFile> MF =
buildModuleFile(ModuleName, ModuleUnitFileName, getCDB(), TFS,
ModuleFilesPrefix, BuiltModuleFiles);
if (llvm::Error Err = MF.takeError())
return Err;

log("Built module {0} to {1}", ModuleName, MF->getModuleFilePath());
auto BuiltModuleFile = std::make_shared<ModuleFile>(std::move(*MF));
Cache.add(ModuleName, BuiltModuleFile);
BuiltModuleFiles.addModuleFile(std::move(BuiltModuleFile));

return llvm::Error::success();
}

std::unique_ptr<PrerequisiteModules>
ModulesBuilder::buildPrerequisiteModulesFor(PathRef File,
const ThreadsafeFS &TFS) const {
std::unique_ptr<ProjectModules> MDB = CDB.getProjectModules(File);
const ThreadsafeFS &TFS) {
std::unique_ptr<ProjectModules> MDB = Impl->getCDB().getProjectModules(File);
if (!MDB) {
elog("Failed to get Project Modules information for {0}", File);
return std::make_unique<FailedPrerequisiteModules>();
}

std::vector<std::string> RequiredModuleNames = MDB->getRequiredModules(File);
if (RequiredModuleNames.empty())
return std::make_unique<StandalonePrerequisiteModules>();
return std::make_unique<ReusablePrerequisiteModules>();

llvm::SmallString<256> ModuleFilesPrefix = getUniqueModuleFilesPath(File);

log("Trying to build required modules for {0} in {1}", File,
ModuleFilesPrefix);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is no longer the case, you can drop this (and the following log after the build)

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done


auto RequiredModules = std::make_unique<StandalonePrerequisiteModules>();
auto RequiredModules = std::make_unique<ReusablePrerequisiteModules>();

for (llvm::StringRef RequiredModuleName : RequiredModuleNames) {
// Return early if there is any error.
if (llvm::Error Err =
buildModuleFile(RequiredModuleName, CDB, TFS, *MDB.get(),
ModuleFilesPrefix, *RequiredModules.get())) {
if (llvm::Error Err = Impl->getOrBuildModuleFile(
RequiredModuleName, TFS, *MDB.get(), *RequiredModules.get())) {
elog("Failed to build module {0}; due to {1}", RequiredModuleName,
toString(std::move(Err)));
return std::make_unique<FailedPrerequisiteModules>();
Expand All @@ -357,17 +504,11 @@ ModulesBuilder::buildPrerequisiteModulesFor(PathRef File,
return std::move(RequiredModules);
}

bool StandalonePrerequisiteModules::canReuse(
const CompilerInvocation &CI,
llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS) const {
if (RequiredModules.empty())
return true;

SmallVector<StringRef> BMIPaths;
for (auto &MF : RequiredModules)
BMIPaths.push_back(MF.ModuleFilePath);
return IsModuleFilesUpToDate(BMIPaths, *this, VFS);
ModulesBuilder::ModulesBuilder(const GlobalCompilationDatabase &CDB) {
Impl = std::make_unique<ModulesBuilderImpl>(CDB);
}

ModulesBuilder::~ModulesBuilder() {}

} // namespace clangd
} // namespace clang
8 changes: 5 additions & 3 deletions clang-tools-extra/clangd/ModulesBuilder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,8 @@ class PrerequisiteModules {
/// different versions and different source files.
class ModulesBuilder {
public:
ModulesBuilder(const GlobalCompilationDatabase &CDB) : CDB(CDB) {}
ModulesBuilder(const GlobalCompilationDatabase &CDB);
~ModulesBuilder();

ModulesBuilder(const ModulesBuilder &) = delete;
ModulesBuilder(ModulesBuilder &&) = delete;
Expand All @@ -94,10 +95,11 @@ class ModulesBuilder {
ModulesBuilder &operator=(ModulesBuilder &&) = delete;

std::unique_ptr<PrerequisiteModules>
buildPrerequisiteModulesFor(PathRef File, const ThreadsafeFS &TFS) const;
buildPrerequisiteModulesFor(PathRef File, const ThreadsafeFS &TFS);

private:
const GlobalCompilationDatabase &CDB;
class ModulesBuilderImpl;
std::unique_ptr<ModulesBuilderImpl> Impl;
};

} // namespace clangd
Expand Down
Loading
Loading