[clang][AST] Support AST files larger than 512M
Summary:
Clang uses 32-bit integers for storing bit offsets from the beginning of
the file that results in 512M limit on AST file. This diff replaces
absolute offsets with relative offsets from the beginning of
corresponding data structure when it is possible. And uses 64-bit
offsets for DeclOffests and TypeOffssts because these coder AST
section may easily exceeds 512M alone.
This diff breaks AST file format compatibility so VERSION_MAJOR bumped.
Test Plan:
Existing clang AST serialization tests
Tested on clangd with ~700M and ~900M preamble files
check-clang with ubsan
Reviewers: rsmith, dexonsmith
Subscribers: ilya-biryukov, kadircet, usaxena95, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D76594
diff --git a/clang/lib/Serialization/ASTWriter.cpp b/clang/lib/Serialization/ASTWriter.cpp
index de59dd2..c8ce3ed 100644
--- a/clang/lib/Serialization/ASTWriter.cpp
+++ b/clang/lib/Serialization/ASTWriter.cpp
@@ -1893,6 +1893,7 @@
// Write out the source location entry table. We skip the first
// entry, which is always the same dummy entry.
std::vector<uint32_t> SLocEntryOffsets;
+ uint64_t SLocEntryOffsetsBase = Stream.GetCurrentBitNo();
RecordData PreloadSLocs;
SLocEntryOffsets.reserve(SourceMgr.local_sloc_entry_size() - 1);
for (unsigned I = 1, N = SourceMgr.local_sloc_entry_size();
@@ -1903,7 +1904,9 @@
assert(&SourceMgr.getSLocEntry(FID) == SLoc);
// Record the offset of this source-location entry.
- SLocEntryOffsets.push_back(Stream.GetCurrentBitNo());
+ uint64_t Offset = Stream.GetCurrentBitNo() - SLocEntryOffsetsBase;
+ assert((Offset >> 32) == 0 && "SLocEntry offset too large");
+ SLocEntryOffsets.push_back(Offset);
// Figure out which record code to use.
unsigned Code;
@@ -2011,12 +2014,14 @@
Abbrev->Add(BitCodeAbbrevOp(SOURCE_LOCATION_OFFSETS));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 16)); // # of slocs
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 16)); // total size
+ Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 32)); // base offset
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob)); // offsets
unsigned SLocOffsetsAbbrev = Stream.EmitAbbrev(std::move(Abbrev));
{
RecordData::value_type Record[] = {
SOURCE_LOCATION_OFFSETS, SLocEntryOffsets.size(),
- SourceMgr.getNextLocalOffset() - 1 /* skip dummy */};
+ SourceMgr.getNextLocalOffset() - 1 /* skip dummy */,
+ SLocEntryOffsetsBase};
Stream.EmitRecordWithBlob(SLocOffsetsAbbrev, Record,
bytes(SLocEntryOffsets));
}
@@ -2093,9 +2098,11 @@
/// Writes the block containing the serialized form of the
/// preprocessor.
void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
+ uint64_t MacroOffsetsBase = Stream.GetCurrentBitNo();
+
PreprocessingRecord *PPRec = PP.getPreprocessingRecord();
if (PPRec)
- WritePreprocessorDetail(*PPRec);
+ WritePreprocessorDetail(*PPRec, MacroOffsetsBase);
RecordData Record;
RecordData ModuleMacroRecord;
@@ -2156,7 +2163,8 @@
// identifier they belong to.
for (const IdentifierInfo *Name : MacroIdentifiers) {
MacroDirective *MD = PP.getLocalMacroDirectiveHistory(Name);
- auto StartOffset = Stream.GetCurrentBitNo();
+ uint64_t StartOffset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+ assert((StartOffset >> 32) == 0 && "Macro identifiers offset too large");
// Emit the macro directives in reverse source order.
for (; MD; MD = MD->getPrevious()) {
@@ -2229,14 +2237,12 @@
// Record the local offset of this macro.
unsigned Index = ID - FirstMacroID;
- if (Index == MacroOffsets.size())
- MacroOffsets.push_back(Stream.GetCurrentBitNo());
- else {
- if (Index > MacroOffsets.size())
- MacroOffsets.resize(Index + 1);
+ if (Index >= MacroOffsets.size())
+ MacroOffsets.resize(Index + 1);
- MacroOffsets[Index] = Stream.GetCurrentBitNo();
- }
+ uint64_t Offset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+ assert((Offset >> 32) == 0 && "Macro offset too large");
+ MacroOffsets[Index] = Offset;
AddIdentifierRef(Name, Record);
AddSourceLocation(MI->getDefinitionLoc(), Record);
@@ -2287,17 +2293,20 @@
Abbrev->Add(BitCodeAbbrevOp(MACRO_OFFSET));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // # of macros
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // first ID
+ Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 32)); // base offset
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob));
unsigned MacroOffsetAbbrev = Stream.EmitAbbrev(std::move(Abbrev));
{
RecordData::value_type Record[] = {MACRO_OFFSET, MacroOffsets.size(),
- FirstMacroID - NUM_PREDEF_MACRO_IDS};
+ FirstMacroID - NUM_PREDEF_MACRO_IDS,
+ MacroOffsetsBase};
Stream.EmitRecordWithBlob(MacroOffsetAbbrev, Record, bytes(MacroOffsets));
}
}
-void ASTWriter::WritePreprocessorDetail(PreprocessingRecord &PPRec) {
+void ASTWriter::WritePreprocessorDetail(PreprocessingRecord &PPRec,
+ uint64_t MacroOffsetsBase) {
if (PPRec.local_begin() == PPRec.local_end())
return;
@@ -2334,8 +2343,10 @@
(void)++E, ++NumPreprocessingRecords, ++NextPreprocessorEntityID) {
Record.clear();
+ uint64_t Offset = Stream.GetCurrentBitNo() - MacroOffsetsBase;
+ assert((Offset >> 32) == 0 && "Preprocessed entity offset too large");
PreprocessedEntityOffsets.push_back(
- PPEntityOffset((*E)->getSourceRange(), Stream.GetCurrentBitNo()));
+ PPEntityOffset((*E)->getSourceRange(), Offset));
if (auto *MD = dyn_cast<MacroDefinitionRecord>(*E)) {
// Record this macro definition's ID.
@@ -2808,10 +2819,10 @@
// Record the offset for this type.
unsigned Index = Idx.getIndex() - FirstTypeID;
if (TypeOffsets.size() == Index)
- TypeOffsets.push_back(Offset);
+ TypeOffsets.emplace_back(Offset);
else if (TypeOffsets.size() < Index) {
TypeOffsets.resize(Index + 1);
- TypeOffsets[Index] = Offset;
+ TypeOffsets[Index].setBitOffset(Offset);
} else {
llvm_unreachable("Types emitted in wrong order");
}
@@ -5144,7 +5155,7 @@
return MacroIDs[MI];
}
-uint64_t ASTWriter::getMacroDirectivesOffset(const IdentifierInfo *Name) {
+uint32_t ASTWriter::getMacroDirectivesOffset(const IdentifierInfo *Name) {
return IdentMacroDirectivesOffsetMap.lookup(Name);
}