blob: 6f5fa67117c091918714cedc2f5a560e333f388a [file] [log] [blame]
//===- ASTReader.cpp - AST File Reader ------------------------------------===//
//
// 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 defines the ASTReader class, which reads AST files.
//
//===----------------------------------------------------------------------===//
#include "clang/Basic/OpenMPKinds.h"
#include "clang/Serialization/ASTRecordReader.h"
#include "ASTCommon.h"
#include "ASTReaderInternals.h"
#include "clang/AST/AbstractTypeReader.h"
#include "clang/AST/ASTConsumer.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/ASTMutationListener.h"
#include "clang/AST/ASTUnresolvedSet.h"
#include "clang/AST/Decl.h"
#include "clang/AST/DeclBase.h"
#include "clang/AST/DeclCXX.h"
#include "clang/AST/DeclFriend.h"
#include "clang/AST/DeclGroup.h"
#include "clang/AST/DeclObjC.h"
#include "clang/AST/DeclTemplate.h"
#include "clang/AST/DeclarationName.h"
#include "clang/AST/Expr.h"
#include "clang/AST/ExprCXX.h"
#include "clang/AST/ExternalASTSource.h"
#include "clang/AST/NestedNameSpecifier.h"
#include "clang/AST/OpenMPClause.h"
#include "clang/AST/ODRHash.h"
#include "clang/AST/RawCommentList.h"
#include "clang/AST/TemplateBase.h"
#include "clang/AST/TemplateName.h"
#include "clang/AST/Type.h"
#include "clang/AST/TypeLoc.h"
#include "clang/AST/TypeLocVisitor.h"
#include "clang/AST/UnresolvedSet.h"
#include "clang/Basic/CommentOptions.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/DiagnosticOptions.h"
#include "clang/Basic/ExceptionSpecificationType.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/FileSystemOptions.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/LLVM.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/Module.h"
#include "clang/Basic/ObjCRuntime.h"
#include "clang/Basic/OperatorKinds.h"
#include "clang/Basic/PragmaKinds.h"
#include "clang/Basic/Sanitizers.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Basic/SourceManagerInternals.h"
#include "clang/Basic/Specifiers.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Basic/TargetOptions.h"
#include "clang/Basic/TokenKinds.h"
#include "clang/Basic/Version.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/HeaderSearchOptions.h"
#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/ModuleMap.h"
#include "clang/Lex/PreprocessingRecord.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/PreprocessorOptions.h"
#include "clang/Lex/Token.h"
#include "clang/Sema/ObjCMethodList.h"
#include "clang/Sema/Scope.h"
#include "clang/Sema/Sema.h"
#include "clang/Sema/Weak.h"
#include "clang/Serialization/ASTBitCodes.h"
#include "clang/Serialization/ASTDeserializationListener.h"
#include "clang/Serialization/ContinuousRangeMap.h"
#include "clang/Serialization/GlobalModuleIndex.h"
#include "clang/Serialization/InMemoryModuleCache.h"
#include "clang/Serialization/ModuleFile.h"
#include "clang/Serialization/ModuleFileExtension.h"
#include "clang/Serialization/ModuleManager.h"
#include "clang/Serialization/PCHContainerOperations.h"
#include "clang/Serialization/SerializationDiagnostic.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/APSInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/FloatingPointMode.h"
#include "llvm/ADT/FoldingSet.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/IntrusiveRefCntPtr.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Triple.h"
#include "llvm/ADT/iterator_range.h"
#include "llvm/Bitstream/BitstreamReader.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/DJB.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/SaveAndRestore.h"
#include "llvm/Support/Timer.h"
#include "llvm/Support/VersionTuple.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <cstdio>
#include <ctime>
#include <iterator>
#include <limits>
#include <map>
#include <memory>
#include <string>
#include <system_error>
#include <tuple>
#include <utility>
#include <vector>
using namespace clang;
using namespace clang::serialization;
using namespace clang::serialization::reader;
using llvm::BitstreamCursor;
using llvm::RoundingMode;
//===----------------------------------------------------------------------===//
// ChainedASTReaderListener implementation
//===----------------------------------------------------------------------===//
bool
ChainedASTReaderListener::ReadFullVersionInformation(StringRef FullVersion) {
return First->ReadFullVersionInformation(FullVersion) ||
Second->ReadFullVersionInformation(FullVersion);
}
void ChainedASTReaderListener::ReadModuleName(StringRef ModuleName) {
First->ReadModuleName(ModuleName);
Second->ReadModuleName(ModuleName);
}
void ChainedASTReaderListener::ReadModuleMapFile(StringRef ModuleMapPath) {
First->ReadModuleMapFile(ModuleMapPath);
Second->ReadModuleMapFile(ModuleMapPath);
}
bool
ChainedASTReaderListener::ReadLanguageOptions(const LangOptions &LangOpts,
bool Complain,
bool AllowCompatibleDifferences) {
return First->ReadLanguageOptions(LangOpts, Complain,
AllowCompatibleDifferences) ||
Second->ReadLanguageOptions(LangOpts, Complain,
AllowCompatibleDifferences);
}
bool ChainedASTReaderListener::ReadTargetOptions(
const TargetOptions &TargetOpts, bool Complain,
bool AllowCompatibleDifferences) {
return First->ReadTargetOptions(TargetOpts, Complain,
AllowCompatibleDifferences) ||
Second->ReadTargetOptions(TargetOpts, Complain,
AllowCompatibleDifferences);
}
bool ChainedASTReaderListener::ReadDiagnosticOptions(
IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts, bool Complain) {
return First->ReadDiagnosticOptions(DiagOpts, Complain) ||
Second->ReadDiagnosticOptions(DiagOpts, Complain);
}
bool
ChainedASTReaderListener::ReadFileSystemOptions(const FileSystemOptions &FSOpts,
bool Complain) {
return First->ReadFileSystemOptions(FSOpts, Complain) ||
Second->ReadFileSystemOptions(FSOpts, Complain);
}
bool ChainedASTReaderListener::ReadHeaderSearchOptions(
const HeaderSearchOptions &HSOpts, StringRef SpecificModuleCachePath,
bool Complain) {
return First->ReadHeaderSearchOptions(HSOpts, SpecificModuleCachePath,
Complain) ||
Second->ReadHeaderSearchOptions(HSOpts, SpecificModuleCachePath,
Complain);
}
bool ChainedASTReaderListener::ReadPreprocessorOptions(
const PreprocessorOptions &PPOpts, bool Complain,
std::string &SuggestedPredefines) {
return First->ReadPreprocessorOptions(PPOpts, Complain,
SuggestedPredefines) ||
Second->ReadPreprocessorOptions(PPOpts, Complain, SuggestedPredefines);
}
void ChainedASTReaderListener::ReadCounter(const serialization::ModuleFile &M,
unsigned Value) {
First->ReadCounter(M, Value);
Second->ReadCounter(M, Value);
}
bool ChainedASTReaderListener::needsInputFileVisitation() {
return First->needsInputFileVisitation() ||
Second->needsInputFileVisitation();
}
bool ChainedASTReaderListener::needsSystemInputFileVisitation() {
return First->needsSystemInputFileVisitation() ||
Second->needsSystemInputFileVisitation();
}
void ChainedASTReaderListener::visitModuleFile(StringRef Filename,
ModuleKind Kind) {
First->visitModuleFile(Filename, Kind);
Second->visitModuleFile(Filename, Kind);
}
bool ChainedASTReaderListener::visitInputFile(StringRef Filename,
bool isSystem,
bool isOverridden,
bool isExplicitModule) {
bool Continue = false;
if (First->needsInputFileVisitation() &&
(!isSystem || First->needsSystemInputFileVisitation()))
Continue |= First->visitInputFile(Filename, isSystem, isOverridden,
isExplicitModule);
if (Second->needsInputFileVisitation() &&
(!isSystem || Second->needsSystemInputFileVisitation()))
Continue |= Second->visitInputFile(Filename, isSystem, isOverridden,
isExplicitModule);
return Continue;
}
void ChainedASTReaderListener::readModuleFileExtension(
const ModuleFileExtensionMetadata &Metadata) {
First->readModuleFileExtension(Metadata);
Second->readModuleFileExtension(Metadata);
}
//===----------------------------------------------------------------------===//
// PCH validator implementation
//===----------------------------------------------------------------------===//
ASTReaderListener::~ASTReaderListener() = default;
/// Compare the given set of language options against an existing set of
/// language options.
///
/// \param Diags If non-NULL, diagnostics will be emitted via this engine.
/// \param AllowCompatibleDifferences If true, differences between compatible
/// language options will be permitted.
///
/// \returns true if the languagae options mis-match, false otherwise.
static bool checkLanguageOptions(const LangOptions &LangOpts,
const LangOptions &ExistingLangOpts,
DiagnosticsEngine *Diags,
bool AllowCompatibleDifferences = true) {
#define LANGOPT(Name, Bits, Default, Description) \
if (ExistingLangOpts.Name != LangOpts.Name) { \
if (Diags) \
Diags->Report(diag::err_pch_langopt_mismatch) \
<< Description << LangOpts.Name << ExistingLangOpts.Name; \
return true; \
}
#define VALUE_LANGOPT(Name, Bits, Default, Description) \
if (ExistingLangOpts.Name != LangOpts.Name) { \
if (Diags) \
Diags->Report(diag::err_pch_langopt_value_mismatch) \
<< Description; \
return true; \
}
#define ENUM_LANGOPT(Name, Type, Bits, Default, Description) \
if (ExistingLangOpts.get##Name() != LangOpts.get##Name()) { \
if (Diags) \
Diags->Report(diag::err_pch_langopt_value_mismatch) \
<< Description; \
return true; \
}
#define COMPATIBLE_LANGOPT(Name, Bits, Default, Description) \
if (!AllowCompatibleDifferences) \
LANGOPT(Name, Bits, Default, Description)
#define COMPATIBLE_ENUM_LANGOPT(Name, Bits, Default, Description) \
if (!AllowCompatibleDifferences) \
ENUM_LANGOPT(Name, Bits, Default, Description)
#define COMPATIBLE_VALUE_LANGOPT(Name, Bits, Default, Description) \
if (!AllowCompatibleDifferences) \
VALUE_LANGOPT(Name, Bits, Default, Description)
#define BENIGN_LANGOPT(Name, Bits, Default, Description)
#define BENIGN_ENUM_LANGOPT(Name, Type, Bits, Default, Description)
#define BENIGN_VALUE_LANGOPT(Name, Type, Bits, Default, Description)
#include "clang/Basic/LangOptions.def"
if (ExistingLangOpts.ModuleFeatures != LangOpts.ModuleFeatures) {
if (Diags)
Diags->Report(diag::err_pch_langopt_value_mismatch) << "module features";
return true;
}
if (ExistingLangOpts.ObjCRuntime != LangOpts.ObjCRuntime) {
if (Diags)
Diags->Report(diag::err_pch_langopt_value_mismatch)
<< "target Objective-C runtime";
return true;
}
if (ExistingLangOpts.CommentOpts.BlockCommandNames !=
LangOpts.CommentOpts.BlockCommandNames) {
if (Diags)
Diags->Report(diag::err_pch_langopt_value_mismatch)
<< "block command names";
return true;
}
// Sanitizer feature mismatches are treated as compatible differences. If
// compatible differences aren't allowed, we still only want to check for
// mismatches of non-modular sanitizers (the only ones which can affect AST
// generation).
if (!AllowCompatibleDifferences) {
SanitizerMask ModularSanitizers = getPPTransparentSanitizers();
SanitizerSet ExistingSanitizers = ExistingLangOpts.Sanitize;
SanitizerSet ImportedSanitizers = LangOpts.Sanitize;
ExistingSanitizers.clear(ModularSanitizers);
ImportedSanitizers.clear(ModularSanitizers);
if (ExistingSanitizers.Mask != ImportedSanitizers.Mask) {
const std::string Flag = "-fsanitize=";
if (Diags) {
#define SANITIZER(NAME, ID) \
{ \
bool InExistingModule = ExistingSanitizers.has(SanitizerKind::ID); \
bool InImportedModule = ImportedSanitizers.has(SanitizerKind::ID); \
if (InExistingModule != InImportedModule) \
Diags->Report(diag::err_pch_targetopt_feature_mismatch) \
<< InExistingModule << (Flag + NAME); \
}
#include "clang/Basic/Sanitizers.def"
}
return true;
}
}
return false;
}
/// Compare the given set of target options against an existing set of
/// target options.
///
/// \param Diags If non-NULL, diagnostics will be emitted via this engine.
///
/// \returns true if the target options mis-match, false otherwise.
static bool checkTargetOptions(const TargetOptions &TargetOpts,
const TargetOptions &ExistingTargetOpts,
DiagnosticsEngine *Diags,
bool AllowCompatibleDifferences = true) {
#define CHECK_TARGET_OPT(Field, Name) \
if (TargetOpts.Field != ExistingTargetOpts.Field) { \
if (Diags) \
Diags->Report(diag::err_pch_targetopt_mismatch) \
<< Name << TargetOpts.Field << ExistingTargetOpts.Field; \
return true; \
}
// The triple and ABI must match exactly.
CHECK_TARGET_OPT(Triple, "target");
CHECK_TARGET_OPT(ABI, "target ABI");
// We can tolerate different CPUs in many cases, notably when one CPU
// supports a strict superset of another. When allowing compatible
// differences skip this check.
if (!AllowCompatibleDifferences) {
CHECK_TARGET_OPT(CPU, "target CPU");
CHECK_TARGET_OPT(TuneCPU, "tune CPU");
}
#undef CHECK_TARGET_OPT
// Compare feature sets.
SmallVector<StringRef, 4> ExistingFeatures(
ExistingTargetOpts.FeaturesAsWritten.begin(),
ExistingTargetOpts.FeaturesAsWritten.end());
SmallVector<StringRef, 4> ReadFeatures(TargetOpts.FeaturesAsWritten.begin(),
TargetOpts.FeaturesAsWritten.end());
llvm::sort(ExistingFeatures);
llvm::sort(ReadFeatures);
// We compute the set difference in both directions explicitly so that we can
// diagnose the differences differently.
SmallVector<StringRef, 4> UnmatchedExistingFeatures, UnmatchedReadFeatures;
std::set_difference(
ExistingFeatures.begin(), ExistingFeatures.end(), ReadFeatures.begin(),
ReadFeatures.end(), std::back_inserter(UnmatchedExistingFeatures));
std::set_difference(ReadFeatures.begin(), ReadFeatures.end(),
ExistingFeatures.begin(), ExistingFeatures.end(),
std::back_inserter(UnmatchedReadFeatures));
// If we are allowing compatible differences and the read feature set is
// a strict subset of the existing feature set, there is nothing to diagnose.
if (AllowCompatibleDifferences && UnmatchedReadFeatures.empty())
return false;
if (Diags) {
for (StringRef Feature : UnmatchedReadFeatures)
Diags->Report(diag::err_pch_targetopt_feature_mismatch)
<< /* is-existing-feature */ false << Feature;
for (StringRef Feature : UnmatchedExistingFeatures)
Diags->Report(diag::err_pch_targetopt_feature_mismatch)
<< /* is-existing-feature */ true << Feature;
}
return !UnmatchedReadFeatures.empty() || !UnmatchedExistingFeatures.empty();
}
bool
PCHValidator::ReadLanguageOptions(const LangOptions &LangOpts,
bool Complain,
bool AllowCompatibleDifferences) {
const LangOptions &ExistingLangOpts = PP.getLangOpts();
return checkLanguageOptions(LangOpts, ExistingLangOpts,
Complain ? &Reader.Diags : nullptr,
AllowCompatibleDifferences);
}
bool PCHValidator::ReadTargetOptions(const TargetOptions &TargetOpts,
bool Complain,
bool AllowCompatibleDifferences) {
const TargetOptions &ExistingTargetOpts = PP.getTargetInfo().getTargetOpts();
return checkTargetOptions(TargetOpts, ExistingTargetOpts,
Complain ? &Reader.Diags : nullptr,
AllowCompatibleDifferences);
}
namespace {
using MacroDefinitionsMap =
llvm::StringMap<std::pair<StringRef, bool /*IsUndef*/>>;
using DeclsMap = llvm::DenseMap<DeclarationName, SmallVector<NamedDecl *, 8>>;
} // namespace
static bool checkDiagnosticGroupMappings(DiagnosticsEngine &StoredDiags,
DiagnosticsEngine &Diags,
bool Complain) {
using Level = DiagnosticsEngine::Level;
// Check current mappings for new -Werror mappings, and the stored mappings
// for cases that were explicitly mapped to *not* be errors that are now
// errors because of options like -Werror.
DiagnosticsEngine *MappingSources[] = { &Diags, &StoredDiags };
for (DiagnosticsEngine *MappingSource : MappingSources) {
for (auto DiagIDMappingPair : MappingSource->getDiagnosticMappings()) {
diag::kind DiagID = DiagIDMappingPair.first;
Level CurLevel = Diags.getDiagnosticLevel(DiagID, SourceLocation());
if (CurLevel < DiagnosticsEngine::Error)
continue; // not significant
Level StoredLevel =
StoredDiags.getDiagnosticLevel(DiagID, SourceLocation());
if (StoredLevel < DiagnosticsEngine::Error) {
if (Complain)
Diags.Report(diag::err_pch_diagopt_mismatch) << "-Werror=" +
Diags.getDiagnosticIDs()->getWarningOptionForDiag(DiagID).str();
return true;
}
}
}
return false;
}
static bool isExtHandlingFromDiagsError(DiagnosticsEngine &Diags) {
diag::Severity Ext = Diags.getExtensionHandlingBehavior();
if (Ext == diag::Severity::Warning && Diags.getWarningsAsErrors())
return true;
return Ext >= diag::Severity::Error;
}
static bool checkDiagnosticMappings(DiagnosticsEngine &StoredDiags,
DiagnosticsEngine &Diags,
bool IsSystem, bool Complain) {
// Top-level options
if (IsSystem) {
if (Diags.getSuppressSystemWarnings())
return false;
// If -Wsystem-headers was not enabled before, be conservative
if (StoredDiags.getSuppressSystemWarnings()) {
if (Complain)
Diags.Report(diag::err_pch_diagopt_mismatch) << "-Wsystem-headers";
return true;
}
}
if (Diags.getWarningsAsErrors() && !StoredDiags.getWarningsAsErrors()) {
if (Complain)
Diags.Report(diag::err_pch_diagopt_mismatch) << "-Werror";
return true;
}
if (Diags.getWarningsAsErrors() && Diags.getEnableAllWarnings() &&
!StoredDiags.getEnableAllWarnings()) {
if (Complain)
Diags.Report(diag::err_pch_diagopt_mismatch) << "-Weverything -Werror";
return true;
}
if (isExtHandlingFromDiagsError(Diags) &&
!isExtHandlingFromDiagsError(StoredDiags)) {
if (Complain)
Diags.Report(diag::err_pch_diagopt_mismatch) << "-pedantic-errors";
return true;
}
return checkDiagnosticGroupMappings(StoredDiags, Diags, Complain);
}
/// Return the top import module if it is implicit, nullptr otherwise.
static Module *getTopImportImplicitModule(ModuleManager &ModuleMgr,
Preprocessor &PP) {
// If the original import came from a file explicitly generated by the user,
// don't check the diagnostic mappings.
// FIXME: currently this is approximated by checking whether this is not a
// module import of an implicitly-loaded module file.
// Note: ModuleMgr.rbegin() may not be the current module, but it must be in
// the transitive closure of its imports, since unrelated modules cannot be
// imported until after this module finishes validation.
ModuleFile *TopImport = &*ModuleMgr.rbegin();
while (!TopImport->ImportedBy.empty())
TopImport = TopImport->ImportedBy[0];
if (TopImport->Kind != MK_ImplicitModule)
return nullptr;
StringRef ModuleName = TopImport->ModuleName;
assert(!ModuleName.empty() && "diagnostic options read before module name");
Module *M = PP.getHeaderSearchInfo().lookupModule(ModuleName);
assert(M && "missing module");
return M;
}
bool PCHValidator::ReadDiagnosticOptions(
IntrusiveRefCntPtr<DiagnosticOptions> DiagOpts, bool Complain) {
DiagnosticsEngine &ExistingDiags = PP.getDiagnostics();
IntrusiveRefCntPtr<DiagnosticIDs> DiagIDs(ExistingDiags.getDiagnosticIDs());
IntrusiveRefCntPtr<DiagnosticsEngine> Diags(
new DiagnosticsEngine(DiagIDs, DiagOpts.get()));
// This should never fail, because we would have processed these options
// before writing them to an ASTFile.
ProcessWarningOptions(*Diags, *DiagOpts, /*Report*/false);
ModuleManager &ModuleMgr = Reader.getModuleManager();
assert(ModuleMgr.size() >= 1 && "what ASTFile is this then");
Module *TopM = getTopImportImplicitModule(ModuleMgr, PP);
if (!TopM)
return false;
// FIXME: if the diagnostics are incompatible, save a DiagnosticOptions that
// contains the union of their flags.
return checkDiagnosticMappings(*Diags, ExistingDiags, TopM->IsSystem,
Complain);
}
/// Collect the macro definitions provided by the given preprocessor
/// options.
static void
collectMacroDefinitions(const PreprocessorOptions &PPOpts,
MacroDefinitionsMap &Macros,
SmallVectorImpl<StringRef> *MacroNames = nullptr) {
for (unsigned I = 0, N = PPOpts.Macros.size(); I != N; ++I) {
StringRef Macro = PPOpts.Macros[I].first;
bool IsUndef = PPOpts.Macros[I].second;
std::pair<StringRef, StringRef> MacroPair = Macro.split('=');
StringRef MacroName = MacroPair.first;
StringRef MacroBody = MacroPair.second;
// For an #undef'd macro, we only care about the name.
if (IsUndef) {
if (MacroNames && !Macros.count(MacroName))
MacroNames->push_back(MacroName);
Macros[MacroName] = std::make_pair("", true);
continue;
}
// For a #define'd macro, figure out the actual definition.
if (MacroName.size() == Macro.size())
MacroBody = "1";
else {
// Note: GCC drops anything following an end-of-line character.
StringRef::size_type End = MacroBody.find_first_of("\n\r");
MacroBody = MacroBody.substr(0, End);
}
if (MacroNames && !Macros.count(MacroName))
MacroNames->push_back(MacroName);
Macros[MacroName] = std::make_pair(MacroBody, false);
}
}
/// Check the preprocessor options deserialized from the control block
/// against the preprocessor options in an existing preprocessor.
///
/// \param Diags If non-null, produce diagnostics for any mismatches incurred.
/// \param Validate If true, validate preprocessor options. If false, allow
/// macros defined by \p ExistingPPOpts to override those defined by
/// \p PPOpts in SuggestedPredefines.
static bool checkPreprocessorOptions(const PreprocessorOptions &PPOpts,
const PreprocessorOptions &ExistingPPOpts,
DiagnosticsEngine *Diags,
FileManager &FileMgr,
std::string &SuggestedPredefines,
const LangOptions &LangOpts,
bool Validate = true) {
// Check macro definitions.
MacroDefinitionsMap ASTFileMacros;
collectMacroDefinitions(PPOpts, ASTFileMacros);
MacroDefinitionsMap ExistingMacros;
SmallVector<StringRef, 4> ExistingMacroNames;
collectMacroDefinitions(ExistingPPOpts, ExistingMacros, &ExistingMacroNames);
for (unsigned I = 0, N = ExistingMacroNames.size(); I != N; ++I) {
// Dig out the macro definition in the existing preprocessor options.
StringRef MacroName = ExistingMacroNames[I];
std::pair<StringRef, bool> Existing = ExistingMacros[MacroName];
// Check whether we know anything about this macro name or not.
llvm::StringMap<std::pair<StringRef, bool /*IsUndef*/>>::iterator Known =
ASTFileMacros.find(MacroName);
if (!Validate || Known == ASTFileMacros.end()) {
// FIXME: Check whether this identifier was referenced anywhere in the
// AST file. If so, we should reject the AST file. Unfortunately, this
// information isn't in the control block. What shall we do about it?
if (Existing.second) {
SuggestedPredefines += "#undef ";
SuggestedPredefines += MacroName.str();
SuggestedPredefines += '\n';
} else {
SuggestedPredefines += "#define ";
SuggestedPredefines += MacroName.str();
SuggestedPredefines += ' ';
SuggestedPredefines += Existing.first.str();
SuggestedPredefines += '\n';
}
continue;
}
// If the macro was defined in one but undef'd in the other, we have a
// conflict.
if (Existing.second != Known->second.second) {
if (Diags) {
Diags->Report(diag::err_pch_macro_def_undef)
<< MacroName << Known->second.second;
}
return true;
}
// If the macro was #undef'd in both, or if the macro bodies are identical,
// it's fine.
if (Existing.second || Existing.first == Known->second.first)
continue;
// The macro bodies differ; complain.
if (Diags) {
Diags->Report(diag::err_pch_macro_def_conflict)
<< MacroName << Known->second.first << Existing.first;
}
return true;
}
// Check whether we're using predefines.
if (PPOpts.UsePredefines != ExistingPPOpts.UsePredefines && Validate) {
if (Diags) {
Diags->Report(diag::err_pch_undef) << ExistingPPOpts.UsePredefines;
}
return true;
}
// Detailed record is important since it is used for the module cache hash.
if (LangOpts.Modules &&
PPOpts.DetailedRecord != ExistingPPOpts.DetailedRecord && Validate) {
if (Diags) {
Diags->Report(diag::err_pch_pp_detailed_record) << PPOpts.DetailedRecord;
}
return true;
}
// Compute the #include and #include_macros lines we need.
for (unsigned I = 0, N = ExistingPPOpts.Includes.size(); I != N; ++I) {
StringRef File = ExistingPPOpts.Includes[I];
if (!ExistingPPOpts.ImplicitPCHInclude.empty() &&
!ExistingPPOpts.PCHThroughHeader.empty()) {
// In case the through header is an include, we must add all the includes
// to the predefines so the start point can be determined.
SuggestedPredefines += "#include \"";
SuggestedPredefines += File;
SuggestedPredefines += "\"\n";
continue;
}
if (File == ExistingPPOpts.ImplicitPCHInclude)
continue;
if (std::find(PPOpts.Includes.begin(), PPOpts.Includes.end(), File)
!= PPOpts.Includes.end())
continue;
SuggestedPredefines += "#include \"";
SuggestedPredefines += File;
SuggestedPredefines += "\"\n";
}
for (unsigned I = 0, N = ExistingPPOpts.MacroIncludes.size(); I != N; ++I) {
StringRef File = ExistingPPOpts.MacroIncludes[I];
if (std::find(PPOpts.MacroIncludes.begin(), PPOpts.MacroIncludes.end(),
File)
!= PPOpts.MacroIncludes.end())
continue;
SuggestedPredefines += "#__include_macros \"";
SuggestedPredefines += File;
SuggestedPredefines += "\"\n##\n";
}
return false;
}
bool PCHValidator::ReadPreprocessorOptions(const PreprocessorOptions &PPOpts,
bool Complain,
std::string &SuggestedPredefines) {
const PreprocessorOptions &ExistingPPOpts = PP.getPreprocessorOpts();
return checkPreprocessorOptions(PPOpts, ExistingPPOpts,
Complain? &Reader.Diags : nullptr,
PP.getFileManager(),
SuggestedPredefines,
PP.getLangOpts());
}
bool SimpleASTReaderListener::ReadPreprocessorOptions(
const PreprocessorOptions &PPOpts,
bool Complain,
std::string &SuggestedPredefines) {
return checkPreprocessorOptions(PPOpts,
PP.getPreprocessorOpts(),
nullptr,
PP.getFileManager(),
SuggestedPredefines,
PP.getLangOpts(),
false);
}
/// Check the header search options deserialized from the control block
/// against the header search options in an existing preprocessor.
///
/// \param Diags If non-null, produce diagnostics for any mismatches incurred.
static bool checkHeaderSearchOptions(const HeaderSearchOptions &HSOpts,
StringRef SpecificModuleCachePath,
StringRef ExistingModuleCachePath,
DiagnosticsEngine *Diags,
const LangOptions &LangOpts) {
if (LangOpts.Modules) {
if (SpecificModuleCachePath != ExistingModuleCachePath) {
if (Diags)
Diags->Report(diag::err_pch_modulecache_mismatch)
<< SpecificModuleCachePath << ExistingModuleCachePath;
return true;
}
}
return false;
}
bool PCHValidator::ReadHeaderSearchOptions(const HeaderSearchOptions &HSOpts,
StringRef SpecificModuleCachePath,
bool Complain) {
return checkHeaderSearchOptions(HSOpts, SpecificModuleCachePath,
PP.getHeaderSearchInfo().getModuleCachePath(),
Complain ? &Reader.Diags : nullptr,
PP.getLangOpts());
}
void PCHValidator::ReadCounter(const ModuleFile &M, unsigned Value) {
PP.setCounterValue(Value);
}
//===----------------------------------------------------------------------===//
// AST reader implementation
//===----------------------------------------------------------------------===//
void ASTReader::setDeserializationListener(ASTDeserializationListener *Listener,
bool TakeOwnership) {
DeserializationListener = Listener;
OwnsDeserializationListener = TakeOwnership;
}
unsigned ASTSelectorLookupTrait::ComputeHash(Selector Sel) {
return serialization::ComputeHash(Sel);
}
std::pair<unsigned, unsigned>
ASTSelectorLookupTrait::ReadKeyDataLength(const unsigned char*& d) {
using namespace llvm::support;
unsigned KeyLen = endian::readNext<uint16_t, little, unaligned>(d);
unsigned DataLen = endian::readNext<uint16_t, little, unaligned>(d);
return std::make_pair(KeyLen, DataLen);
}
ASTSelectorLookupTrait::internal_key_type
ASTSelectorLookupTrait::ReadKey(const unsigned char* d, unsigned) {
using namespace llvm::support;
SelectorTable &SelTable = Reader.getContext().Selectors;
unsigned N = endian::readNext<uint16_t, little, unaligned>(d);
IdentifierInfo *FirstII = Reader.getLocalIdentifier(
F, endian::readNext<uint32_t, little, unaligned>(d));
if (N == 0)
return SelTable.getNullarySelector(FirstII);
else if (N == 1)
return SelTable.getUnarySelector(FirstII);
SmallVector<IdentifierInfo *, 16> Args;
Args.push_back(FirstII);
for (unsigned I = 1; I != N; ++I)
Args.push_back(Reader.getLocalIdentifier(
F, endian::readNext<uint32_t, little, unaligned>(d)));
return SelTable.getSelector(N, Args.data());
}
ASTSelectorLookupTrait::data_type
ASTSelectorLookupTrait::ReadData(Selector, const unsigned char* d,
unsigned DataLen) {
using namespace llvm::support;
data_type Result;
Result.ID = Reader.getGlobalSelectorID(
F, endian::readNext<uint32_t, little, unaligned>(d));
unsigned FullInstanceBits = endian::readNext<uint16_t, little, unaligned>(d);
unsigned FullFactoryBits = endian::readNext<uint16_t, little, unaligned>(d);
Result.InstanceBits = FullInstanceBits & 0x3;
Result.InstanceHasMoreThanOneDecl = (FullInstanceBits >> 2) & 0x1;
Result.FactoryBits = FullFactoryBits & 0x3;
Result.FactoryHasMoreThanOneDecl = (FullFactoryBits >> 2) & 0x1;
unsigned NumInstanceMethods = FullInstanceBits >> 3;
unsigned NumFactoryMethods = FullFactoryBits >> 3;
// Load instance methods
for (unsigned I = 0; I != NumInstanceMethods; ++I) {
if (ObjCMethodDecl *Method = Reader.GetLocalDeclAs<ObjCMethodDecl>(
F, endian::readNext<uint32_t, little, unaligned>(d)))
Result.Instance.push_back(Method);
}
// Load factory methods
for (unsigned I = 0; I != NumFactoryMethods; ++I) {
if (ObjCMethodDecl *Method = Reader.GetLocalDeclAs<ObjCMethodDecl>(
F, endian::readNext<uint32_t, little, unaligned>(d)))
Result.Factory.push_back(Method);
}
return Result;
}
unsigned ASTIdentifierLookupTraitBase::ComputeHash(const internal_key_type& a) {
return llvm::djbHash(a);
}
std::pair<unsigned, unsigned>
ASTIdentifierLookupTraitBase::ReadKeyDataLength(const unsigned char*& d) {
using namespace llvm::support;
unsigned DataLen = endian::readNext<uint16_t, little, unaligned>(d);
unsigned KeyLen = endian::readNext<uint16_t, little, unaligned>(d);
return std::make_pair(KeyLen, DataLen);
}
ASTIdentifierLookupTraitBase::internal_key_type
ASTIdentifierLookupTraitBase::ReadKey(const unsigned char* d, unsigned n) {
assert(n >= 2 && d[n-1] == '\0');
return StringRef((const char*) d, n-1);
}
/// Whether the given identifier is "interesting".
static bool isInterestingIdentifier(ASTReader &Reader, IdentifierInfo &II,
bool IsModule) {
return II.hadMacroDefinition() ||
II.isPoisoned() ||
(IsModule ? II.hasRevertedBuiltin() : II.getObjCOrBuiltinID()) ||
II.hasRevertedTokenIDToIdentifier() ||
(!(IsModule && Reader.getPreprocessor().getLangOpts().CPlusPlus) &&
II.getFETokenInfo());
}
static bool readBit(unsigned &Bits) {
bool Value = Bits & 0x1;
Bits >>= 1;
return Value;
}
IdentID ASTIdentifierLookupTrait::ReadIdentifierID(const unsigned char *d) {
using namespace llvm::support;
unsigned RawID = endian::readNext<uint32_t, little, unaligned>(d);
return Reader.getGlobalIdentifierID(F, RawID >> 1);
}
static void markIdentifierFromAST(ASTReader &Reader, IdentifierInfo &II) {
if (!II.isFromAST()) {
II.setIsFromAST();
bool IsModule = Reader.getPreprocessor().getCurrentModule() != nullptr;
if (isInterestingIdentifier(Reader, II, IsModule))
II.setChangedSinceDeserialization();
}
}
IdentifierInfo *ASTIdentifierLookupTrait::ReadData(const internal_key_type& k,
const unsigned char* d,
unsigned DataLen) {
using namespace llvm::support;
unsigned RawID = endian::readNext<uint32_t, little, unaligned>(d);
bool IsInteresting = RawID & 0x01;
// Wipe out the "is interesting" bit.
RawID = RawID >> 1;
// Build the IdentifierInfo and link the identifier ID with it.
IdentifierInfo *II = KnownII;
if (!II) {
II = &Reader.getIdentifierTable().getOwn(k);
KnownII = II;
}
markIdentifierFromAST(Reader, *II);
Reader.markIdentifierUpToDate(II);
IdentID ID = Reader.getGlobalIdentifierID(F, RawID);
if (!IsInteresting) {
// For uninteresting identifiers, there's nothing else to do. Just notify
// the reader that we've finished loading this identifier.
Reader.SetIdentifierInfo(ID, II);
return II;
}
unsigned ObjCOrBuiltinID = endian::readNext<uint16_t, little, unaligned>(d);
unsigned Bits = endian::readNext<uint16_t, little, unaligned>(d);
bool CPlusPlusOperatorKeyword = readBit(Bits);
bool HasRevertedTokenIDToIdentifier = readBit(Bits);
bool HasRevertedBuiltin = readBit(Bits);
bool Poisoned = readBit(Bits);
bool ExtensionToken = readBit(Bits);
bool HadMacroDefinition = readBit(Bits);
assert(Bits == 0 && "Extra bits in the identifier?");
DataLen -= 8;
// Set or check the various bits in the IdentifierInfo structure.
// Token IDs are read-only.
if (HasRevertedTokenIDToIdentifier && II->getTokenID() != tok::identifier)
II->revertTokenIDToIdentifier();
if (!F.isModule())
II->setObjCOrBuiltinID(ObjCOrBuiltinID);
else if (HasRevertedBuiltin && II->getBuiltinID()) {
II->revertBuiltin();
assert((II->hasRevertedBuiltin() ||
II->getObjCOrBuiltinID() == ObjCOrBuiltinID) &&
"Incorrect ObjC keyword or builtin ID");
}
assert(II->isExtensionToken() == ExtensionToken &&
"Incorrect extension token flag");
(void)ExtensionToken;
if (Poisoned)
II->setIsPoisoned(true);
assert(II->isCPlusPlusOperatorKeyword() == CPlusPlusOperatorKeyword &&
"Incorrect C++ operator keyword flag");
(void)CPlusPlusOperatorKeyword;
// If this identifier is a macro, deserialize the macro
// definition.
if (HadMacroDefinition) {
uint32_t MacroDirectivesOffset =
endian::readNext<uint32_t, little, unaligned>(d);
DataLen -= 4;
Reader.addPendingMacro(II, &F, MacroDirectivesOffset);
}
Reader.SetIdentifierInfo(ID, II);
// Read all of the declarations visible at global scope with this
// name.
if (DataLen > 0) {
SmallVector<uint32_t, 4> DeclIDs;
for (; DataLen > 0; DataLen -= 4)
DeclIDs.push_back(Reader.getGlobalDeclID(
F, endian::readNext<uint32_t, little, unaligned>(d)));
Reader.SetGloballyVisibleDecls(II, DeclIDs);
}
return II;
}
DeclarationNameKey::DeclarationNameKey(DeclarationName Name)
: Kind(Name.getNameKind()) {
switch (Kind) {
case DeclarationName::Identifier:
Data = (uint64_t)Name.getAsIdentifierInfo();
break;
case DeclarationName::ObjCZeroArgSelector:
case DeclarationName::ObjCOneArgSelector:
case DeclarationName::ObjCMultiArgSelector:
Data = (uint64_t)Name.getObjCSelector().getAsOpaquePtr();
break;
case DeclarationName::CXXOperatorName:
Data = Name.getCXXOverloadedOperator();
break;
case DeclarationName::CXXLiteralOperatorName:
Data = (uint64_t)Name.getCXXLiteralIdentifier();
break;
case DeclarationName::CXXDeductionGuideName:
Data = (uint64_t)Name.getCXXDeductionGuideTemplate()
->getDeclName().getAsIdentifierInfo();
break;
case DeclarationName::CXXConstructorName:
case DeclarationName::CXXDestructorName:
case DeclarationName::CXXConversionFunctionName:
case DeclarationName::CXXUsingDirective:
Data = 0;
break;
}
}
unsigned DeclarationNameKey::getHash() const {
llvm::FoldingSetNodeID ID;
ID.AddInteger(Kind);
switch (Kind) {
case DeclarationName::Identifier:
case DeclarationName::CXXLiteralOperatorName:
case DeclarationName::CXXDeductionGuideName:
ID.AddString(((IdentifierInfo*)Data)->getName());
break;
case DeclarationName::ObjCZeroArgSelector:
case DeclarationName::ObjCOneArgSelector:
case DeclarationName::ObjCMultiArgSelector:
ID.AddInteger(serialization::ComputeHash(Selector(Data)));
break;
case DeclarationName::CXXOperatorName:
ID.AddInteger((OverloadedOperatorKind)Data);
break;
case DeclarationName::CXXConstructorName:
case DeclarationName::CXXDestructorName:
case DeclarationName::CXXConversionFunctionName:
case DeclarationName::CXXUsingDirective:
break;
}
return ID.ComputeHash();
}
ModuleFile *
ASTDeclContextNameLookupTrait::ReadFileRef(const unsigned char *&d) {
using namespace llvm::support;
uint32_t ModuleFileID = endian::readNext<uint32_t, little, unaligned>(d);
return Reader.getLocalModuleFile(F, ModuleFileID);
}
std::pair<unsigned, unsigned>
ASTDeclContextNameLookupTrait::ReadKeyDataLength(const unsigned char *&d) {
using namespace llvm::support;
unsigned KeyLen = endian::readNext<uint16_t, little, unaligned>(d);
unsigned DataLen = endian::readNext<uint16_t, little, unaligned>(d);
return std::make_pair(KeyLen, DataLen);
}
ASTDeclContextNameLookupTrait::internal_key_type
ASTDeclContextNameLookupTrait::ReadKey(const unsigned char *d, unsigned) {
using namespace llvm::support;
auto Kind = (DeclarationName::NameKind)*d++;
uint64_t Data;
switch (Kind) {
case DeclarationName::Identifier:
case DeclarationName::CXXLiteralOperatorName:
case DeclarationName::CXXDeductionGuideName:
Data = (uint64_t)Reader.getLocalIdentifier(
F, endian::readNext<uint32_t, little, unaligned>(d));
break;
case DeclarationName::ObjCZeroArgSelector:
case DeclarationName::ObjCOneArgSelector:
case DeclarationName::ObjCMultiArgSelector:
Data =
(uint64_t)Reader.getLocalSelector(
F, endian::readNext<uint32_t, little, unaligned>(
d)).getAsOpaquePtr();
break;
case DeclarationName::CXXOperatorName:
Data = *d++; // OverloadedOperatorKind
break;
case DeclarationName::CXXConstructorName:
case DeclarationName::CXXDestructorName:
case DeclarationName::CXXConversionFunctionName:
case DeclarationName::CXXUsingDirective:
Data = 0;
break;
}
return DeclarationNameKey(Kind, Data);
}
void ASTDeclContextNameLookupTrait::ReadDataInto(internal_key_type,
const unsigned char *d,
unsigned DataLen,
data_type_builder &Val) {
using namespace llvm::support;
for (unsigned NumDecls = DataLen / 4; NumDecls; --NumDecls) {
uint32_t LocalID = endian::readNext<uint32_t, little, unaligned>(d);
Val.insert(Reader.getGlobalDeclID(F, LocalID));
}
}
bool ASTReader::ReadLexicalDeclContextStorage(ModuleFile &M,
BitstreamCursor &Cursor,
uint64_t Offset,
DeclContext *DC) {
assert(Offset != 0);
SavedStreamPosition SavedPosition(Cursor);
if (llvm::Error Err = Cursor.JumpToBit(Offset)) {
Error(std::move(Err));
return true;
}
RecordData Record;
StringRef Blob;
Expected<unsigned> MaybeCode = Cursor.ReadCode();
if (!MaybeCode) {
Error(MaybeCode.takeError());
return true;
}
unsigned Code = MaybeCode.get();
Expected<unsigned> MaybeRecCode = Cursor.readRecord(Code, Record, &Blob);
if (!MaybeRecCode) {
Error(MaybeRecCode.takeError());
return true;
}
unsigned RecCode = MaybeRecCode.get();
if (RecCode != DECL_CONTEXT_LEXICAL) {
Error("Expected lexical block");
return true;
}
assert(!isa<TranslationUnitDecl>(DC) &&
"expected a TU_UPDATE_LEXICAL record for TU");
// If we are handling a C++ class template instantiation, we can see multiple
// lexical updates for the same record. It's important that we select only one
// of them, so that field numbering works properly. Just pick the first one we
// see.
auto &Lex = LexicalDecls[DC];
if (!Lex.first) {
Lex = std::make_pair(
&M, llvm::makeArrayRef(
reinterpret_cast<const llvm::support::unaligned_uint32_t *>(
Blob.data()),
Blob.size() / 4));
}
DC->setHasExternalLexicalStorage(true);
return false;
}
bool ASTReader::ReadVisibleDeclContextStorage(ModuleFile &M,
BitstreamCursor &Cursor,
uint64_t Offset,
DeclID ID) {
assert(Offset != 0);
SavedStreamPosition SavedPosition(Cursor);
if (llvm::Error Err = Cursor.JumpToBit(Offset)) {
Error(std::move(Err));
return true;
}
RecordData Record;
StringRef Blob;
Expected<unsigned> MaybeCode = Cursor.ReadCode();
if (!MaybeCode) {
Error(MaybeCode.takeError());
return true;
}
unsigned Code = MaybeCode.get();
Expected<unsigned> MaybeRecCode = Cursor.readRecord(Code, Record, &Blob);
if (!MaybeRecCode) {
Error(MaybeRecCode.takeError());
return true;
}
unsigned RecCode = MaybeRecCode.get();
if (RecCode != DECL_CONTEXT_VISIBLE) {
Error("Expected visible lookup table block");
return true;
}
// We can't safely determine the primary context yet, so delay attaching the
// lookup table until we're done with recursive deserialization.
auto *Data = (const unsigned char*)Blob.data();
PendingVisibleUpdates[ID].push_back(PendingVisibleUpdate{&M, Data});
return false;
}
void ASTReader::Error(StringRef Msg) const {
Error(diag::err_fe_pch_malformed, Msg);
if (PP.getLangOpts().Modules && !Diags.isDiagnosticInFlight() &&
!PP.getHeaderSearchInfo().getModuleCachePath().empty()) {
Diag(diag::note_module_cache_path)
<< PP.getHeaderSearchInfo().getModuleCachePath();
}
}
void ASTReader::Error(unsigned DiagID, StringRef Arg1, StringRef Arg2,
StringRef Arg3) const {
if (Diags.isDiagnosticInFlight())
Diags.SetDelayedDiagnostic(DiagID, Arg1, Arg2, Arg3);
else
Diag(DiagID) << Arg1 << Arg2 << Arg3;
}
void ASTReader::Error(unsigned DiagID, StringRef Arg1, StringRef Arg2,
unsigned Select) const {
if (!Diags.isDiagnosticInFlight())
Diag(DiagID) << Arg1 << Arg2 << Select;
}
void ASTReader::Error(llvm::Error &&Err) const {
Error(toString(std::move(Err)));
}
//===----------------------------------------------------------------------===//
// Source Manager Deserialization
//===----------------------------------------------------------------------===//
/// Read the line table in the source manager block.
/// \returns true if there was an error.
bool ASTReader::ParseLineTable(ModuleFile &F,
const RecordData &Record) {
unsigned Idx = 0;
LineTableInfo &LineTable = SourceMgr.getLineTable();
// Parse the file names
std::map<int, int> FileIDs;
FileIDs[-1] = -1; // For unspecified filenames.
for (unsigned I = 0; Record[Idx]; ++I) {
// Extract the file name
auto Filename = ReadPath(F, Record, Idx);
FileIDs[I] = LineTable.getLineTableFilenameID(Filename);
}
++Idx;
// Parse the line entries
std::vector<LineEntry> Entries;
while (Idx < Record.size()) {
int FID = Record[Idx++];
assert(FID >= 0 && "Serialized line entries for non-local file.");
// Remap FileID from 1-based old view.
FID += F.SLocEntryBaseID - 1;
// Extract the line entries
unsigned NumEntries = Record[Idx++];
assert(NumEntries && "no line entries for file ID");
Entries.clear();
Entries.reserve(NumEntries);
for (unsigned I = 0; I != NumEntries; ++I) {
unsigned FileOffset = Record[Idx++];
unsigned LineNo = Record[Idx++];
int FilenameID = FileIDs[Record[Idx++]];
SrcMgr::CharacteristicKind FileKind
= (SrcMgr::CharacteristicKind)Record[Idx++];
unsigned IncludeOffset = Record[Idx++];
Entries.push_back(LineEntry::get(FileOffset, LineNo, FilenameID,
FileKind, IncludeOffset));
}
LineTable.AddEntry(FileID::get(FID), Entries);
}
return false;
}
/// Read a source manager block
bool ASTReader::ReadSourceManagerBlock(ModuleFile &F) {
using namespace SrcMgr;
BitstreamCursor &SLocEntryCursor = F.SLocEntryCursor;
// Set the source-location entry cursor to the current position in
// the stream. This cursor will be used to read the contents of the
// source manager block initially, and then lazily read
// source-location entries as needed.
SLocEntryCursor = F.Stream;
// The stream itself is going to skip over the source manager block.
if (llvm::Error Err = F.Stream.SkipBlock()) {
Error(std::move(Err));
return true;
}
// Enter the source manager block.
if (llvm::Error Err =
SLocEntryCursor.EnterSubBlock(SOURCE_MANAGER_BLOCK_ID)) {
Error(std::move(Err));
return true;
}
F.SourceManagerBlockStartOffset = SLocEntryCursor.GetCurrentBitNo();
RecordData Record;
while (true) {
Expected<llvm::BitstreamEntry> MaybeE =
SLocEntryCursor.advanceSkippingSubblocks();
if (!MaybeE) {
Error(MaybeE.takeError());
return true;
}
llvm::BitstreamEntry E = MaybeE.get();
switch (E.Kind) {
case llvm::BitstreamEntry::SubBlock: // Handled for us already.
case llvm::BitstreamEntry::Error:
Error("malformed block record in AST file");
return true;
case llvm::BitstreamEntry::EndBlock:
return false;
case llvm::BitstreamEntry::Record:
// The interesting case.
break;
}
// Read a record.
Record.clear();
StringRef Blob;
Expected<unsigned> MaybeRecord =
SLocEntryCursor.readRecord(E.ID, Record, &Blob);
if (!MaybeRecord) {
Error(MaybeRecord.takeError());
return true;
}
switch (MaybeRecord.get()) {
default: // Default behavior: ignore.
break;
case SM_SLOC_FILE_ENTRY:
case SM_SLOC_BUFFER_ENTRY:
case SM_SLOC_EXPANSION_ENTRY:
// Once we hit one of the source location entries, we're done.
return false;
}
}
}
/// If a header file is not found at the path that we expect it to be
/// and the PCH file was moved from its original location, try to resolve the
/// file by assuming that header+PCH were moved together and the header is in
/// the same place relative to the PCH.
static std::string
resolveFileRelativeToOriginalDir(const std::string &Filename,
const std::string &OriginalDir,
const std::string &CurrDir) {
assert(OriginalDir != CurrDir &&
"No point trying to resolve the file if the PCH dir didn't change");
using namespace llvm::sys;
SmallString<128> filePath(Filename);
fs::make_absolute(filePath);
assert(path::is_absolute(OriginalDir));
SmallString<128> currPCHPath(CurrDir);
path::const_iterator fileDirI = path::begin(path::parent_path(filePath)),
fileDirE = path::end(path::parent_path(filePath));
path::const_iterator origDirI = path::begin(OriginalDir),
origDirE = path::end(OriginalDir);
// Skip the common path components from filePath and OriginalDir.
while (fileDirI != fileDirE && origDirI != origDirE &&
*fileDirI == *origDirI) {
++fileDirI;
++origDirI;
}
for (; origDirI != origDirE; ++origDirI)
path::append(currPCHPath, "..");
path::append(currPCHPath, fileDirI, fileDirE);
path::append(currPCHPath, path::filename(Filename));
return std::string(currPCHPath.str());
}
bool ASTReader::ReadSLocEntry(int ID) {
if (ID == 0)
return false;
if (unsigned(-ID) - 2 >= getTotalNumSLocs() || ID > 0) {
Error("source location entry ID out-of-range for AST file");
return true;
}
// Local helper to read the (possibly-compressed) buffer data following the
// entry record.
auto ReadBuffer = [this](
BitstreamCursor &SLocEntryCursor,
StringRef Name) -> std::unique_ptr<llvm::MemoryBuffer> {
RecordData Record;
StringRef Blob;
Expected<unsigned> MaybeCode = SLocEntryCursor.ReadCode();
if (!MaybeCode) {
Error(MaybeCode.takeError());
return nullptr;
}
unsigned Code = MaybeCode.get();
Expected<unsigned> MaybeRecCode =
SLocEntryCursor.readRecord(Code, Record, &Blob);
if (!MaybeRecCode) {
Error(MaybeRecCode.takeError());
return nullptr;
}
unsigned RecCode = MaybeRecCode.get();
if (RecCode == SM_SLOC_BUFFER_BLOB_COMPRESSED) {
if (!llvm::zlib::isAvailable()) {
Error("zlib is not available");
return nullptr;
}
SmallString<0> Uncompressed;
if (llvm::Error E =
llvm::zlib::uncompress(Blob, Uncompressed, Record[0])) {
Error("could not decompress embedded file contents: " +
llvm::toString(std::move(E)));
return nullptr;
}
return llvm::MemoryBuffer::getMemBufferCopy(Uncompressed, Name);
} else if (RecCode == SM_SLOC_BUFFER_BLOB) {
return llvm::MemoryBuffer::getMemBuffer(Blob.drop_back(1), Name, true);
} else {
Error("AST record has invalid code");
return nullptr;
}
};
ModuleFile *F = GlobalSLocEntryMap.find(-ID)->second;
if (llvm::Error Err = F->SLocEntryCursor.JumpToBit(
F->SLocEntryOffsetsBase +
F->SLocEntryOffsets[ID - F->SLocEntryBaseID])) {
Error(std::move(Err));
return true;
}
BitstreamCursor &SLocEntryCursor = F->SLocEntryCursor;
unsigned BaseOffset = F->SLocEntryBaseOffset;
++NumSLocEntriesRead;
Expected<llvm::BitstreamEntry> MaybeEntry = SLocEntryCursor.advance();
if (!MaybeEntry) {
Error(MaybeEntry.takeError());
return true;
}
llvm::BitstreamEntry Entry = MaybeEntry.get();
if (Entry.Kind != llvm::BitstreamEntry::Record) {
Error("incorrectly-formatted source location entry in AST file");
return true;
}
RecordData Record;
StringRef Blob;
Expected<unsigned> MaybeSLOC =
SLocEntryCursor.readRecord(Entry.ID, Record, &Blob);
if (!MaybeSLOC) {
Error(MaybeSLOC.takeError());
return true;
}
switch (MaybeSLOC.get()) {
default:
Error("incorrectly-formatted source location entry in AST file");
return true;
case SM_SLOC_FILE_ENTRY: {
// We will detect whether a file changed and return 'Failure' for it, but
// we will also try to fail gracefully by setting up the SLocEntry.
unsigned InputID = Record[4];
InputFile IF = getInputFile(*F, InputID);
const FileEntry *File = IF.getFile();
bool OverriddenBuffer = IF.isOverridden();
// Note that we only check if a File was returned. If it was out-of-date
// we have complained but we will continue creating a FileID to recover
// gracefully.
if (!File)
return true;
SourceLocation IncludeLoc = ReadSourceLocation(*F, Record[1]);
if (IncludeLoc.isInvalid() && F->Kind != MK_MainFile) {
// This is the module's main file.
IncludeLoc = getImportLocation(F);
}
SrcMgr::CharacteristicKind
FileCharacter = (SrcMgr::CharacteristicKind)Record[2];
// FIXME: The FileID should be created from the FileEntryRef.
FileID FID = SourceMgr.createFileID(File, IncludeLoc, FileCharacter,
ID, BaseOffset + Record[0]);
SrcMgr::FileInfo &FileInfo =
const_cast<SrcMgr::FileInfo&>(SourceMgr.getSLocEntry(FID).getFile());
FileInfo.NumCreatedFIDs = Record[5];
if (Record[3])
FileInfo.setHasLineDirectives();
unsigned NumFileDecls = Record[7];
if (NumFileDecls && ContextObj) {
const DeclID *FirstDecl = F->FileSortedDecls + Record[6];
assert(F->FileSortedDecls && "FILE_SORTED_DECLS not encountered yet ?");
FileDeclIDs[FID] = FileDeclsInfo(F, llvm::makeArrayRef(FirstDecl,
NumFileDecls));
}
const SrcMgr::ContentCache *ContentCache
= SourceMgr.getOrCreateContentCache(File, isSystem(FileCharacter));
if (OverriddenBuffer && !ContentCache->BufferOverridden &&
ContentCache->ContentsEntry == ContentCache->OrigEntry &&
!ContentCache->getRawBuffer()) {
auto Buffer = ReadBuffer(SLocEntryCursor, File->getName());
if (!Buffer)
return true;
SourceMgr.overrideFileContents(File, std::move(Buffer));
}
break;
}
case SM_SLOC_BUFFER_ENTRY: {
const char *Name = Blob.data();
unsigned Offset = Record[0];
SrcMgr::CharacteristicKind
FileCharacter = (SrcMgr::CharacteristicKind)Record[2];
SourceLocation IncludeLoc = ReadSourceLocation(*F, Record[1]);
if (IncludeLoc.isInvalid() && F->isModule()) {
IncludeLoc = getImportLocation(F);
}
auto Buffer = ReadBuffer(SLocEntryCursor, Name);
if (!Buffer)
return true;
SourceMgr.createFileID(std::move(Buffer), FileCharacter, ID,
BaseOffset + Offset, IncludeLoc);
break;
}
case SM_SLOC_EXPANSION_ENTRY: {
SourceLocation SpellingLoc = ReadSourceLocation(*F, Record[1]);
SourceMgr.createExpansionLoc(SpellingLoc,
ReadSourceLocation(*F, Record[2]),
ReadSourceLocation(*F, Record[3]),
Record[5],
Record[4],
ID,
BaseOffset + Record[0]);
break;
}
}
return false;
}
std::pair<SourceLocation, StringRef> ASTReader::getModuleImportLoc(int ID) {
if (ID == 0)
return std::make_pair(SourceLocation(), "");
if (unsigned(-ID) - 2 >= getTotalNumSLocs() || ID > 0) {
Error("source location entry ID out-of-range for AST file");
return std::make_pair(SourceLocation(), "");
}
// Find which module file this entry lands in.
ModuleFile *M = GlobalSLocEntryMap.find(-ID)->second;
if (!M->isModule())
return std::make_pair(SourceLocation(), "");
// FIXME: Can we map this down to a particular submodule? That would be
// ideal.
return std::make_pair(M->ImportLoc, StringRef(M->ModuleName));
}
/// Find the location where the module F is imported.
SourceLocation ASTReader::getImportLocation(ModuleFile *F) {
if (F->ImportLoc.isValid())
return F->ImportLoc;
// Otherwise we have a PCH. It's considered to be "imported" at the first
// location of its includer.
if (F->ImportedBy.empty() || !F->ImportedBy[0]) {
// Main file is the importer.
assert(SourceMgr.getMainFileID().isValid() && "missing main file");
return SourceMgr.getLocForStartOfFile(SourceMgr.getMainFileID());
}
return F->ImportedBy[0]->FirstLoc;
}
/// Enter a subblock of the specified BlockID with the specified cursor. Read
/// the abbreviations that are at the top of the block and then leave the cursor
/// pointing into the block.
bool ASTReader::ReadBlockAbbrevs(BitstreamCursor &Cursor, unsigned BlockID,
uint64_t *StartOfBlockOffset) {
if (llvm::Error Err = Cursor.EnterSubBlock(BlockID)) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
return true;
}
if (StartOfBlockOffset)
*StartOfBlockOffset = Cursor.GetCurrentBitNo();
while (true) {
uint64_t Offset = Cursor.GetCurrentBitNo();
Expected<unsigned> MaybeCode = Cursor.ReadCode();
if (!MaybeCode) {
// FIXME this drops errors on the floor.
consumeError(MaybeCode.takeError());
return true;
}
unsigned Code = MaybeCode.get();
// We expect all abbrevs to be at the start of the block.
if (Code != llvm::bitc::DEFINE_ABBREV) {
if (llvm::Error Err = Cursor.JumpToBit(Offset)) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
return true;
}
return false;
}
if (llvm::Error Err = Cursor.ReadAbbrevRecord()) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
return true;
}
}
}
Token ASTReader::ReadToken(ModuleFile &F, const RecordDataImpl &Record,
unsigned &Idx) {
Token Tok;
Tok.startToken();
Tok.setLocation(ReadSourceLocation(F, Record, Idx));
Tok.setLength(Record[Idx++]);
if (IdentifierInfo *II = getLocalIdentifier(F, Record[Idx++]))
Tok.setIdentifierInfo(II);
Tok.setKind((tok::TokenKind)Record[Idx++]);
Tok.setFlag((Token::TokenFlags)Record[Idx++]);
return Tok;
}
MacroInfo *ASTReader::ReadMacroRecord(ModuleFile &F, uint64_t Offset) {
BitstreamCursor &Stream = F.MacroCursor;
// Keep track of where we are in the stream, then jump back there
// after reading this macro.
SavedStreamPosition SavedPosition(Stream);
if (llvm::Error Err = Stream.JumpToBit(Offset)) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
return nullptr;
}
RecordData Record;
SmallVector<IdentifierInfo*, 16> MacroParams;
MacroInfo *Macro = nullptr;
while (true) {
// Advance to the next record, but if we get to the end of the block, don't
// pop it (removing all the abbreviations from the cursor) since we want to
// be able to reseek within the block and read entries.
unsigned Flags = BitstreamCursor::AF_DontPopBlockAtEnd;
Expected<llvm::BitstreamEntry> MaybeEntry =
Stream.advanceSkippingSubblocks(Flags);
if (!MaybeEntry) {
Error(MaybeEntry.takeError());
return Macro;
}
llvm::BitstreamEntry Entry = MaybeEntry.get();
switch (Entry.Kind) {
case llvm::BitstreamEntry::SubBlock: // Handled for us already.
case llvm::BitstreamEntry::Error:
Error("malformed block record in AST file");
return Macro;
case llvm::BitstreamEntry::EndBlock:
return Macro;
case llvm::BitstreamEntry::Record:
// The interesting case.
break;
}
// Read a record.
Record.clear();
PreprocessorRecordTypes RecType;
if (Expected<unsigned> MaybeRecType = Stream.readRecord(Entry.ID, Record))
RecType = (PreprocessorRecordTypes)MaybeRecType.get();
else {
Error(MaybeRecType.takeError());
return Macro;
}
switch (RecType) {
case PP_MODULE_MACRO:
case PP_MACRO_DIRECTIVE_HISTORY:
return Macro;
case PP_MACRO_OBJECT_LIKE:
case PP_MACRO_FUNCTION_LIKE: {
// If we already have a macro, that means that we've hit the end
// of the definition of the macro we were looking for. We're
// done.
if (Macro)
return Macro;
unsigned NextIndex = 1; // Skip identifier ID.
SourceLocation Loc = ReadSourceLocation(F, Record, NextIndex);
MacroInfo *MI = PP.AllocateMacroInfo(Loc);
MI->setDefinitionEndLoc(ReadSourceLocation(F, Record, NextIndex));
MI->setIsUsed(Record[NextIndex++]);
MI->setUsedForHeaderGuard(Record[NextIndex++]);
if (RecType == PP_MACRO_FUNCTION_LIKE) {
// Decode function-like macro info.
bool isC99VarArgs = Record[NextIndex++];
bool isGNUVarArgs = Record[NextIndex++];
bool hasCommaPasting = Record[NextIndex++];
MacroParams.clear();
unsigned NumArgs = Record[NextIndex++];
for (unsigned i = 0; i != NumArgs; ++i)
MacroParams.push_back(getLocalIdentifier(F, Record[NextIndex++]));
// Install function-like macro info.
MI->setIsFunctionLike();
if (isC99VarArgs) MI->setIsC99Varargs();
if (isGNUVarArgs) MI->setIsGNUVarargs();
if (hasCommaPasting) MI->setHasCommaPasting();
MI->setParameterList(MacroParams, PP.getPreprocessorAllocator());
}
// Remember that we saw this macro last so that we add the tokens that
// form its body to it.
Macro = MI;
if (NextIndex + 1 == Record.size() && PP.getPreprocessingRecord() &&
Record[NextIndex]) {
// We have a macro definition. Register the association
PreprocessedEntityID
GlobalID = getGlobalPreprocessedEntityID(F, Record[NextIndex]);
PreprocessingRecord &PPRec = *PP.getPreprocessingRecord();
PreprocessingRecord::PPEntityID PPID =
PPRec.getPPEntityID(GlobalID - 1, /*isLoaded=*/true);
MacroDefinitionRecord *PPDef = cast_or_null<MacroDefinitionRecord>(
PPRec.getPreprocessedEntity(PPID));
if (PPDef)
PPRec.RegisterMacroDefinition(Macro, PPDef);
}
++NumMacrosRead;
break;
}
case PP_TOKEN: {
// If we see a TOKEN before a PP_MACRO_*, then the file is
// erroneous, just pretend we didn't see this.
if (!Macro) break;
unsigned Idx = 0;
Token Tok = ReadToken(F, Record, Idx);
Macro->AddTokenToBody(Tok);
break;
}
}
}
}
PreprocessedEntityID
ASTReader::getGlobalPreprocessedEntityID(ModuleFile &M,
unsigned LocalID) const {
if (!M.ModuleOffsetMap.empty())
ReadModuleOffsetMap(M);
ContinuousRangeMap<uint32_t, int, 2>::const_iterator
I = M.PreprocessedEntityRemap.find(LocalID - NUM_PREDEF_PP_ENTITY_IDS);
assert(I != M.PreprocessedEntityRemap.end()
&& "Invalid index into preprocessed entity index remap");
return LocalID + I->second;
}
unsigned HeaderFileInfoTrait::ComputeHash(internal_key_ref ikey) {
return llvm::hash_combine(ikey.Size, ikey.ModTime);
}
HeaderFileInfoTrait::internal_key_type
HeaderFileInfoTrait::GetInternalKey(const FileEntry *FE) {
internal_key_type ikey = {FE->getSize(),
M.HasTimestamps ? FE->getModificationTime() : 0,
FE->getName(), /*Imported*/ false};
return ikey;
}
bool HeaderFileInfoTrait::EqualKey(internal_key_ref a, internal_key_ref b) {
if (a.Size != b.Size || (a.ModTime && b.ModTime && a.ModTime != b.ModTime))
return false;
if (llvm::sys::path::is_absolute(a.Filename) && a.Filename == b.Filename)
return true;
// Determine whether the actual files are equivalent.
FileManager &FileMgr = Reader.getFileManager();
auto GetFile = [&](const internal_key_type &Key) -> const FileEntry* {
if (!Key.Imported) {
if (auto File = FileMgr.getFile(Key.Filename))
return *File;
return nullptr;
}
std::string Resolved = std::string(Key.Filename);
Reader.ResolveImportedPath(M, Resolved);
if (auto File = FileMgr.getFile(Resolved))
return *File;
return nullptr;
};
const FileEntry *FEA = GetFile(a);
const FileEntry *FEB = GetFile(b);
return FEA && FEA == FEB;
}
std::pair<unsigned, unsigned>
HeaderFileInfoTrait::ReadKeyDataLength(const unsigned char*& d) {
using namespace llvm::support;
unsigned KeyLen = (unsigned) endian::readNext<uint16_t, little, unaligned>(d);
unsigned DataLen = (unsigned) *d++;
return std::make_pair(KeyLen, DataLen);
}
HeaderFileInfoTrait::internal_key_type
HeaderFileInfoTrait::ReadKey(const unsigned char *d, unsigned) {
using namespace llvm::support;
internal_key_type ikey;
ikey.Size = off_t(endian::readNext<uint64_t, little, unaligned>(d));
ikey.ModTime = time_t(endian::readNext<uint64_t, little, unaligned>(d));
ikey.Filename = (const char *)d;
ikey.Imported = true;
return ikey;
}
HeaderFileInfoTrait::data_type
HeaderFileInfoTrait::ReadData(internal_key_ref key, const unsigned char *d,
unsigned DataLen) {
using namespace llvm::support;
const unsigned char *End = d + DataLen;
HeaderFileInfo HFI;
unsigned Flags = *d++;
// FIXME: Refactor with mergeHeaderFileInfo in HeaderSearch.cpp.
HFI.isImport |= (Flags >> 5) & 0x01;
HFI.isPragmaOnce |= (Flags >> 4) & 0x01;
HFI.DirInfo = (Flags >> 1) & 0x07;
HFI.IndexHeaderMapHeader = Flags & 0x01;
// FIXME: Find a better way to handle this. Maybe just store a
// "has been included" flag?
HFI.NumIncludes = std::max(endian::readNext<uint16_t, little, unaligned>(d),
HFI.NumIncludes);
HFI.ControllingMacroID = Reader.getGlobalIdentifierID(
M, endian::readNext<uint32_t, little, unaligned>(d));
if (unsigned FrameworkOffset =
endian::readNext<uint32_t, little, unaligned>(d)) {
// The framework offset is 1 greater than the actual offset,
// since 0 is used as an indicator for "no framework name".
StringRef FrameworkName(FrameworkStrings + FrameworkOffset - 1);
HFI.Framework = HS->getUniqueFrameworkName(FrameworkName);
}
assert((End - d) % 4 == 0 &&
"Wrong data length in HeaderFileInfo deserialization");
while (d != End) {
uint32_t LocalSMID = endian::readNext<uint32_t, little, unaligned>(d);
auto HeaderRole = static_cast<ModuleMap::ModuleHeaderRole>(LocalSMID & 3);
LocalSMID >>= 2;
// This header is part of a module. Associate it with the module to enable
// implicit module import.
SubmoduleID GlobalSMID = Reader.getGlobalSubmoduleID(M, LocalSMID);
Module *Mod = Reader.getSubmodule(GlobalSMID);
FileManager &FileMgr = Reader.getFileManager();
ModuleMap &ModMap =
Reader.getPreprocessor().getHeaderSearchInfo().getModuleMap();
std::string Filename = std::string(key.Filename);
if (key.Imported)
Reader.ResolveImportedPath(M, Filename);
// FIXME: This is not always the right filename-as-written, but we're not
// going to use this information to rebuild the module, so it doesn't make
// a lot of difference.
Module::Header H = {std::string(key.Filename), *FileMgr.getFile(Filename)};
ModMap.addHeader(Mod, H, HeaderRole, /*Imported*/true);
HFI.isModuleHeader |= !(HeaderRole & ModuleMap::TextualHeader);
}
// This HeaderFileInfo was externally loaded.
HFI.External = true;
HFI.IsValid = true;
return HFI;
}
void ASTReader::addPendingMacro(IdentifierInfo *II, ModuleFile *M,
uint32_t MacroDirectivesOffset) {
assert(NumCurrentElementsDeserializing > 0 &&"Missing deserialization guard");
PendingMacroIDs[II].push_back(PendingMacroInfo(M, MacroDirectivesOffset));
}
void ASTReader::ReadDefinedMacros() {
// Note that we are loading defined macros.
Deserializing Macros(this);
for (ModuleFile &I : llvm::reverse(ModuleMgr)) {
BitstreamCursor &MacroCursor = I.MacroCursor;
// If there was no preprocessor block, skip this file.
if (MacroCursor.getBitcodeBytes().empty())
continue;
BitstreamCursor Cursor = MacroCursor;
if (llvm::Error Err = Cursor.JumpToBit(I.MacroStartOffset)) {
Error(std::move(Err));
return;
}
RecordData Record;
while (true) {
Expected<llvm::BitstreamEntry> MaybeE = Cursor.advanceSkippingSubblocks();
if (!MaybeE) {
Error(MaybeE.takeError());
return;
}
llvm::BitstreamEntry E = MaybeE.get();
switch (E.Kind) {
case llvm::BitstreamEntry::SubBlock: // Handled for us already.
case llvm::BitstreamEntry::Error:
Error("malformed block record in AST file");
return;
case llvm::BitstreamEntry::EndBlock:
goto NextCursor;
case llvm::BitstreamEntry::Record: {
Record.clear();
Expected<unsigned> MaybeRecord = Cursor.readRecord(E.ID, Record);
if (!MaybeRecord) {
Error(MaybeRecord.takeError());
return;
}
switch (MaybeRecord.get()) {
default: // Default behavior: ignore.
break;
case PP_MACRO_OBJECT_LIKE:
case PP_MACRO_FUNCTION_LIKE: {
IdentifierInfo *II = getLocalIdentifier(I, Record[0]);
if (II->isOutOfDate())
updateOutOfDateIdentifier(*II);
break;
}
case PP_TOKEN:
// Ignore tokens.
break;
}
break;
}
}
}
NextCursor: ;
}
}
namespace {
/// Visitor class used to look up identifirs in an AST file.
class IdentifierLookupVisitor {
StringRef Name;
unsigned NameHash;
unsigned PriorGeneration;
unsigned &NumIdentifierLookups;
unsigned &NumIdentifierLookupHits;
IdentifierInfo *Found = nullptr;
public:
IdentifierLookupVisitor(StringRef Name, unsigned PriorGeneration,
unsigned &NumIdentifierLookups,
unsigned &NumIdentifierLookupHits)
: Name(Name), NameHash(ASTIdentifierLookupTrait::ComputeHash(Name)),
PriorGeneration(PriorGeneration),
NumIdentifierLookups(NumIdentifierLookups),
NumIdentifierLookupHits(NumIdentifierLookupHits) {}
bool operator()(ModuleFile &M) {
// If we've already searched this module file, skip it now.
if (M.Generation <= PriorGeneration)
return true;
ASTIdentifierLookupTable *IdTable
= (ASTIdentifierLookupTable *)M.IdentifierLookupTable;
if (!IdTable)
return false;
ASTIdentifierLookupTrait Trait(IdTable->getInfoObj().getReader(), M,
Found);
++NumIdentifierLookups;
ASTIdentifierLookupTable::iterator Pos =
IdTable->find_hashed(Name, NameHash, &Trait);
if (Pos == IdTable->end())
return false;
// Dereferencing the iterator has the effect of building the
// IdentifierInfo node and populating it with the various
// declarations it needs.
++NumIdentifierLookupHits;
Found = *Pos;
return true;
}
// Retrieve the identifier info found within the module
// files.
IdentifierInfo *getIdentifierInfo() const { return Found; }
};
} // namespace
void ASTReader::updateOutOfDateIdentifier(IdentifierInfo &II) {
// Note that we are loading an identifier.
Deserializing AnIdentifier(this);
unsigned PriorGeneration = 0;
if (getContext().getLangOpts().Modules)
PriorGeneration = IdentifierGeneration[&II];
// If there is a global index, look there first to determine which modules
// provably do not have any results for this identifier.
GlobalModuleIndex::HitSet Hits;
GlobalModuleIndex::HitSet *HitsPtr = nullptr;
if (!loadGlobalIndex()) {
if (GlobalIndex->lookupIdentifier(II.getName(), Hits)) {
HitsPtr = &Hits;
}
}
IdentifierLookupVisitor Visitor(II.getName(), PriorGeneration,
NumIdentifierLookups,
NumIdentifierLookupHits);
ModuleMgr.visit(Visitor, HitsPtr);
markIdentifierUpToDate(&II);
}
void ASTReader::markIdentifierUpToDate(IdentifierInfo *II) {
if (!II)
return;
II->setOutOfDate(false);
// Update the generation for this identifier.
if (getContext().getLangOpts().Modules)
IdentifierGeneration[II] = getGeneration();
}
void ASTReader::resolvePendingMacro(IdentifierInfo *II,
const PendingMacroInfo &PMInfo) {
ModuleFile &M = *PMInfo.M;
BitstreamCursor &Cursor = M.MacroCursor;
SavedStreamPosition SavedPosition(Cursor);
if (llvm::Error Err =
Cursor.JumpToBit(M.MacroOffsetsBase + PMInfo.MacroDirectivesOffset)) {
Error(std::move(Err));
return;
}
struct ModuleMacroRecord {
SubmoduleID SubModID;
MacroInfo *MI;
SmallVector<SubmoduleID, 8> Overrides;
};
llvm::SmallVector<ModuleMacroRecord, 8> ModuleMacros;
// We expect to see a sequence of PP_MODULE_MACRO records listing exported
// macros, followed by a PP_MACRO_DIRECTIVE_HISTORY record with the complete
// macro histroy.
RecordData Record;
while (true) {
Expected<llvm::BitstreamEntry> MaybeEntry =
Cursor.advance(BitstreamCursor::AF_DontPopBlockAtEnd);
if (!MaybeEntry) {
Error(MaybeEntry.takeError());
return;
}
llvm::BitstreamEntry Entry = MaybeEntry.get();
if (Entry.Kind != llvm::BitstreamEntry::Record) {
Error("malformed block record in AST file");
return;
}
Record.clear();
Expected<unsigned> MaybePP = Cursor.readRecord(Entry.ID, Record);
if (!MaybePP) {
Error(MaybePP.takeError());
return;
}
switch ((PreprocessorRecordTypes)MaybePP.get()) {
case PP_MACRO_DIRECTIVE_HISTORY:
break;
case PP_MODULE_MACRO: {
ModuleMacros.push_back(ModuleMacroRecord());
auto &Info = ModuleMacros.back();
Info.SubModID = getGlobalSubmoduleID(M, Record[0]);
Info.MI = getMacro(getGlobalMacroID(M, Record[1]));
for (int I = 2, N = Record.size(); I != N; ++I)
Info.Overrides.push_back(getGlobalSubmoduleID(M, Record[I]));
continue;
}
default:
Error("malformed block record in AST file");
return;
}
// We found the macro directive history; that's the last record
// for this macro.
break;
}
// Module macros are listed in reverse dependency order.
{
std::reverse(ModuleMacros.begin(), ModuleMacros.end());
llvm::SmallVector<ModuleMacro*, 8> Overrides;
for (auto &MMR : ModuleMacros) {
Overrides.clear();
for (unsigned ModID : MMR.Overrides) {
Module *Mod = getSubmodule(ModID);
auto *Macro = PP.getModuleMacro(Mod, II);
assert(Macro && "missing definition for overridden macro");
Overrides.push_back(Macro);
}
bool Inserted = false;
Module *Owner = getSubmodule(MMR.SubModID);
PP.addModuleMacro(Owner, II, MMR.MI, Overrides, Inserted);
}
}
// Don't read the directive history for a module; we don't have anywhere
// to put it.
if (M.isModule())
return;
// Deserialize the macro directives history in reverse source-order.
MacroDirective *Latest = nullptr, *Earliest = nullptr;
unsigned Idx = 0, N = Record.size();
while (Idx < N) {
MacroDirective *MD = nullptr;
SourceLocation Loc = ReadSourceLocation(M, Record, Idx);
MacroDirective::Kind K = (MacroDirective::Kind)Record[Idx++];
switch (K) {
case MacroDirective::MD_Define: {
MacroInfo *MI = getMacro(getGlobalMacroID(M, Record[Idx++]));
MD = PP.AllocateDefMacroDirective(MI, Loc);
break;
}
case MacroDirective::MD_Undefine:
MD = PP.AllocateUndefMacroDirective(Loc);
break;
case MacroDirective::MD_Visibility:
bool isPublic = Record[Idx++];
MD = PP.AllocateVisibilityMacroDirective(Loc, isPublic);
break;
}
if (!Latest)
Latest = MD;
if (Earliest)
Earliest->setPrevious(MD);
Earliest = MD;
}
if (Latest)
PP.setLoadedMacroDirective(II, Earliest, Latest);
}
ASTReader::InputFileInfo
ASTReader::readInputFileInfo(ModuleFile &F, unsigned ID) {
// Go find this input file.
BitstreamCursor &Cursor = F.InputFilesCursor;
SavedStreamPosition SavedPosition(Cursor);
if (llvm::Error Err = Cursor.JumpToBit(F.InputFileOffsets[ID - 1])) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
}
Expected<unsigned> MaybeCode = Cursor.ReadCode();
if (!MaybeCode) {
// FIXME this drops errors on the floor.
consumeError(MaybeCode.takeError());
}
unsigned Code = MaybeCode.get();
RecordData Record;
StringRef Blob;
if (Expected<unsigned> Maybe = Cursor.readRecord(Code, Record, &Blob))
assert(static_cast<InputFileRecordTypes>(Maybe.get()) == INPUT_FILE &&
"invalid record type for input file");
else {
// FIXME this drops errors on the floor.
consumeError(Maybe.takeError());
}
assert(Record[0] == ID && "Bogus stored ID or offset");
InputFileInfo R;
R.StoredSize = static_cast<off_t>(Record[1]);
R.StoredTime = static_cast<time_t>(Record[2]);
R.Overridden = static_cast<bool>(Record[3]);
R.Transient = static_cast<bool>(Record[4]);
R.TopLevelModuleMap = static_cast<bool>(Record[5]);
R.Filename = std::string(Blob);
ResolveImportedPath(F, R.Filename);
Expected<llvm::BitstreamEntry> MaybeEntry = Cursor.advance();
if (!MaybeEntry) // FIXME this drops errors on the floor.
consumeError(MaybeEntry.takeError());
llvm::BitstreamEntry Entry = MaybeEntry.get();
assert(Entry.Kind == llvm::BitstreamEntry::Record &&
"expected record type for input file hash");
Record.clear();
if (Expected<unsigned> Maybe = Cursor.readRecord(Entry.ID, Record))
assert(static_cast<InputFileRecordTypes>(Maybe.get()) == INPUT_FILE_HASH &&
"invalid record type for input file hash");
else {
// FIXME this drops errors on the floor.
consumeError(Maybe.takeError());
}
R.ContentHash = (static_cast<uint64_t>(Record[1]) << 32) |
static_cast<uint64_t>(Record[0]);
return R;
}
static unsigned moduleKindForDiagnostic(ModuleKind Kind);
InputFile ASTReader::getInputFile(ModuleFile &F, unsigned ID, bool Complain) {
// If this ID is bogus, just return an empty input file.
if (ID == 0 || ID > F.InputFilesLoaded.size())
return InputFile();
// If we've already loaded this input file, return it.
if (F.InputFilesLoaded[ID-1].getFile())
return F.InputFilesLoaded[ID-1];
if (F.InputFilesLoaded[ID-1].isNotFound())
return InputFile();
// Go find this input file.
BitstreamCursor &Cursor = F.InputFilesCursor;
SavedStreamPosition SavedPosition(Cursor);
if (llvm::Error Err = Cursor.JumpToBit(F.InputFileOffsets[ID - 1])) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
}
InputFileInfo FI = readInputFileInfo(F, ID);
off_t StoredSize = FI.StoredSize;
time_t StoredTime = FI.StoredTime;
bool Overridden = FI.Overridden;
bool Transient = FI.Transient;
StringRef Filename = FI.Filename;
uint64_t StoredContentHash = FI.ContentHash;
const FileEntry *File = nullptr;
if (auto FE = FileMgr.getFile(Filename, /*OpenFile=*/false))
File = *FE;
// If we didn't find the file, resolve it relative to the
// original directory from which this AST file was created.
if (File == nullptr && !F.OriginalDir.empty() && !F.BaseDirectory.empty() &&
F.OriginalDir != F.BaseDirectory) {
std::string Resolved = resolveFileRelativeToOriginalDir(
std::string(Filename), F.OriginalDir, F.BaseDirectory);
if (!Resolved.empty())
if (auto FE = FileMgr.getFile(Resolved))
File = *FE;
}
// For an overridden file, create a virtual file with the stored
// size/timestamp.
if ((Overridden || Transient) && File == nullptr)
File = FileMgr.getVirtualFile(Filename, StoredSize, StoredTime);
if (File == nullptr) {
if (Complain) {
std::string ErrorStr = "could not find file '";
ErrorStr += Filename;
ErrorStr += "' referenced by AST file '";
ErrorStr += F.FileName;
ErrorStr += "'";
Error(ErrorStr);
}
// Record that we didn't find the file.
F.InputFilesLoaded[ID-1] = InputFile::getNotFound();
return InputFile();
}
// Check if there was a request to override the contents of the file
// that was part of the precompiled header. Overriding such a file
// can lead to problems when lexing using the source locations from the
// PCH.
SourceManager &SM = getSourceManager();
// FIXME: Reject if the overrides are different.
if ((!Overridden && !Transient) && SM.isFileOverridden(File)) {
if (Complain)
Error(diag::err_fe_pch_file_overridden, Filename);
// After emitting the diagnostic, bypass the overriding file to recover
// (this creates a separate FileEntry).
File = SM.bypassFileContentsOverride(*File);
if (!File) {
F.InputFilesLoaded[ID - 1] = InputFile::getNotFound();
return InputFile();
}
}
enum ModificationType {
Size,
ModTime,
Content,
None,
};
auto HasInputFileChanged = [&]() {
if (StoredSize != File->getSize())
return ModificationType::Size;
if (!DisableValidation && StoredTime &&
StoredTime != File->getModificationTime()) {
// In case the modification time changes but not the content,
// accept the cached file as legit.
if (ValidateASTInputFilesContent &&
StoredContentHash != static_cast<uint64_t>(llvm::hash_code(-1))) {
auto MemBuffOrError = FileMgr.getBufferForFile(File);
if (!MemBuffOrError) {
if (!Complain)
return ModificationType::ModTime;
std::string ErrorStr = "could not get buffer for file '";
ErrorStr += File->getName();
ErrorStr += "'";
Error(ErrorStr);
return ModificationType::ModTime;
}
auto ContentHash = hash_value(MemBuffOrError.get()->getBuffer());
if (StoredContentHash == static_cast<uint64_t>(ContentHash))
return ModificationType::None;
return ModificationType::Content;
}
return ModificationType::ModTime;
}
return ModificationType::None;
};
bool IsOutOfDate = false;
auto FileChange = HasInputFileChanged();
// For an overridden file, there is nothing to validate.
if (!Overridden && FileChange != ModificationType::None) {
if (Complain) {
// Build a list of the PCH imports that got us here (in reverse).
SmallVector<ModuleFile *, 4> ImportStack(1, &F);
while (!ImportStack.back()->ImportedBy.empty())
ImportStack.push_back(ImportStack.back()->ImportedBy[0]);
// The top-level PCH is stale.
StringRef TopLevelPCHName(ImportStack.back()->FileName);
unsigned DiagnosticKind =
moduleKindForDiagnostic(ImportStack.back()->Kind);
if (DiagnosticKind == 0)
Error(diag::err_fe_pch_file_modified, Filename, TopLevelPCHName,
(unsigned)FileChange);
else if (DiagnosticKind == 1)
Error(diag::err_fe_module_file_modified, Filename, TopLevelPCHName,
(unsigned)FileChange);
else
Error(diag::err_fe_ast_file_modified, Filename, TopLevelPCHName,
(unsigned)FileChange);
// Print the import stack.
if (ImportStack.size() > 1 && !Diags.isDiagnosticInFlight()) {
Diag(diag::note_pch_required_by)
<< Filename << ImportStack[0]->FileName;
for (unsigned I = 1; I < ImportStack.size(); ++I)
Diag(diag::note_pch_required_by)
<< ImportStack[I-1]->FileName << ImportStack[I]->FileName;
}
if (!Diags.isDiagnosticInFlight())
Diag(diag::note_pch_rebuild_required) << TopLevelPCHName;
}
IsOutOfDate = true;
}
// FIXME: If the file is overridden and we've already opened it,
// issue an error (or split it into a separate FileEntry).
InputFile IF = InputFile(File, Overridden || Transient, IsOutOfDate);
// Note that we've loaded this input file.
F.InputFilesLoaded[ID-1] = IF;
return IF;
}
/// If we are loading a relocatable PCH or module file, and the filename
/// is not an absolute path, add the system or module root to the beginning of
/// the file name.
void ASTReader::ResolveImportedPath(ModuleFile &M, std::string &Filename) {
// Resolve relative to the base directory, if we have one.
if (!M.BaseDirectory.empty())
return ResolveImportedPath(Filename, M.BaseDirectory);
}
void ASTReader::ResolveImportedPath(std::string &Filename, StringRef Prefix) {
if (Filename.empty() || llvm::sys::path::is_absolute(Filename))
return;
SmallString<128> Buffer;
llvm::sys::path::append(Buffer, Prefix, Filename);
Filename.assign(Buffer.begin(), Buffer.end());
}
static bool isDiagnosedResult(ASTReader::ASTReadResult ARR, unsigned Caps) {
switch (ARR) {
case ASTReader::Failure: return true;
case ASTReader::Missing: return !(Caps & ASTReader::ARR_Missing);
case ASTReader::OutOfDate: return !(Caps & ASTReader::ARR_OutOfDate);
case ASTReader::VersionMismatch: return !(Caps & ASTReader::ARR_VersionMismatch);
case ASTReader::ConfigurationMismatch:
return !(Caps & ASTReader::ARR_ConfigurationMismatch);
case ASTReader::HadErrors: return true;
case ASTReader::Success: return false;
}
llvm_unreachable("unknown ASTReadResult");
}
ASTReader::ASTReadResult ASTReader::ReadOptionsBlock(
BitstreamCursor &Stream, unsigned ClientLoadCapabilities,
bool AllowCompatibleConfigurationMismatch, ASTReaderListener &Listener,
std::string &SuggestedPredefines) {
if (llvm::Error Err = Stream.EnterSubBlock(OPTIONS_BLOCK_ID)) {
// FIXME this drops errors on the floor.
consumeError(std::move(Err));
return Failure;
}
// Read all of the records in the options block.
RecordData Record;
ASTReadResult Result = Success;
while (true) {
Expected<llvm::BitstreamEntry> MaybeEntry = Stream.advance();
if (!MaybeEntry) {
// FIXME this drops errors on the floor.
consumeError(MaybeEntry.takeError());
return Failure;
}
llvm::BitstreamEntry Entry = MaybeEntry.get();
switch (Entry.Kind) {
case llvm::BitstreamEntry::Error:
case llvm::BitstreamEntry::SubBlock:
return Failure;
case llvm::BitstreamEntry::EndBlock:
return Result;
case llvm::BitstreamEntry::Record:
// The interesting case.
break;
}
// Read and process a record.
Record.clear();
Expected<unsigned> MaybeRecordType = Stream.readRecord(Entry.ID, Record);
if (!MaybeRecordType) {
// FIXME this drops errors on the floor.
consumeError(MaybeRecordType.takeError());
return Failure;
}
switch ((OptionsRecordTypes)MaybeRecordType.get()) {
case LANGUAGE_OPTIONS: {
bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
if (ParseLanguageOptions(Record, Complain, Listener,
AllowCompatibleConfigurationMismatch))
Result = ConfigurationMismatch;
break;
}
case TARGET_OPTIONS: {
bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
if (ParseTargetOptions(Record, Complain, Listener,
AllowCompatibleConfigurationMismatch))
Result = ConfigurationMismatch;
break;
}
case FILE_SYSTEM_OPTIONS: {
bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
if (!AllowCompatibleConfigurationMismatch &&
ParseFileSystemOptions(Record, Complain, Listener))
Result = ConfigurationMismatch;
break;
}
case HEADER_SEARCH_OPTIONS: {
bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
if (!AllowCompatibleConfigurationMismatch &&
ParseHeaderSearchOptions(Record, Complain, Listener))
Result = ConfigurationMismatch;
break;
}
case PREPROCESSOR_OPTIONS:
bool Complain = (ClientLoadCapabilities & ARR_ConfigurationMismatch) == 0;
if (!AllowCompatibleConfigurationMismatch &&
ParsePreprocessorOptions(Record, Complain, Listener,
SuggestedPredefines))
Result = ConfigurationMismatch;
break;
}
}
}
ASTReader::ASTReadResult
ASTReader::ReadControlBlock(ModuleFile &F,
SmallVectorImpl<ImportedModule> &Loaded,
const ModuleFile *ImportedBy,
unsigned ClientLoadCapabilities) {
BitstreamCursor &Stream = F.Stream;
if (llvm::Error Err = Stream.EnterSubBlock(CONTROL_BLOCK_ID)) {
Error(std::move(Err));
return Failure;
}
// Lambda to read the unhashed control block the first time it's called.
//
// For PCM files, the unhashed control block cannot be read until after the
// MODULE_NAME record. However, PCH files have no MODULE_NAME, and yet still
// need to look ahead before reading the IMPORTS record. For consistency,
// this block is always read somehow (see BitstreamEntry::EndBlock).
bool HasReadUnhashedControlBlock = false;
auto readUnhashedControlBlockOnce = [&]() {
if (!HasReadUnhashedControlBlock) {
HasReadUnhashedControlBlock = true;
if (ASTReadResult Result =
readUnhashedControlBlock(F, ImportedBy, ClientLoadCapabilities))
return Result;
}
return Success;
};
// Read all of the records and blocks in the control block.
RecordData Record;
unsigned NumInputs = 0;
unsigned NumUserInputs = 0;
StringRef BaseDirectoryAsWritten;
while (true) {
Expected<llvm::BitstreamEntry> MaybeEntry = Stream.advance();
if (!MaybeEntry) {
Error(MaybeEntry.takeError());
return Failure;
}
llvm::BitstreamEntry Entry = MaybeEntry.get();
switch (Entry.Kind) {
case llvm::BitstreamEntry::Error:
Error("malformed block record in AST file");
return Failure;
case llvm::BitstreamEntry::EndBlock: {
// Validate the module before returning. This call catches an AST with
// no module name and no imports.
if (ASTReadResult Result = readUnhashedControlBlockOnce())
return Result;
// Validate input files.
const HeaderSearchOptions &HSOpts =
PP.getHeaderSearchInfo().getHeaderSearchOpts();
// All user input files reside at the index range [0, NumUserInputs), and
// system input files reside at [NumUserInputs, NumInputs). For explicitly
// loaded module files, ignore missing inputs.
if (!DisableValidation && F.Kind != MK_ExplicitModule &&
F.Kind != MK_PrebuiltModule) {
bool Complain = (ClientLoadCapabilities & ARR_OutOfDate) == 0;
// If we are reading a module, we will create a verification timestamp,
// so we verify all input files. Otherwise, verify only user input
// files.
unsigned N = NumUserInputs;
if (ValidateSystemInputs ||
(HSOpts.ModulesValidateOncePerBuildSession &&
F.InputFilesValidationTimestamp <= HSOpts.BuildSessionTimestamp &&
F.Kind == MK_ImplicitModule))
N = NumInputs;
for (unsigned I = 0; I < N; ++I) {
InputFile IF = getInputFile(F, I+1, Complain);
if (!IF.getFile() || IF.isOutOfDate())
return OutOfDate;
}
}
if (Listener)
Listener->visitModuleFile(F.FileName, F.Kind);
if (Listener && Listener->needsInputFileVisitation()) {
unsigned N = Listener->needsSystemInputFileVisitation() ? NumInputs
: NumUserInputs;
for (unsigned I = 0; I < N; ++I) {
bool IsSystem = I >= NumUserInputs;
InputFileInfo FI = readInputFileInfo(F, I+1);
Listener->visitInputFile(FI.Filename, IsSystem, FI.Overridden,
F.Kind == MK_ExplicitModule ||
F.Kind == MK_PrebuiltModule);
}
}
return Success;
}
case llvm::BitstreamEntry::SubBlock:
switch (Entry.ID) {
case INPUT_FILES_BLOCK_ID:
F.InputFilesCursor = Stream;
if (llvm::Error Err = Stream.SkipBlock()) {
Error(std::move(Err));
return Failure;
}
if (ReadBlockAbbrevs(F.InputFilesCursor, INPUT_FILES_BLOCK_ID)) {
Error("malformed block record in AST file");
return Failure;
}
continue;
case OPTIONS_BLOCK_ID:
// If we're reading the first module for this group, check its options
// are compatible with ours. For modules it imports, no further checking
// is required, because we checked them when we built it.
if (Listener && !ImportedBy) {
// Should we allow the configuration of the module file to differ from
// the configuration of the current translation unit in a compatible
// way?
//
// FIXME: Allow this for files explicitly specified with -include-pch.
bool AllowCompatibleConfigurationMismatch =
F.Kind == MK_ExplicitModule || F.Kind == MK_PrebuiltModule;
ASTReadResult Result =
ReadOptionsBlock(Stream, ClientLoadCapabilities,
AllowCompatibleConfigurationMismatch, *Listener,
SuggestedPredefines);
if (Result == Failure) {
Error("malformed block record in AST file");
return Result;
}
if