CreateFunc Create) {
auto Result = HashedRecords.try_emplace(Hash, nextTypeIndex());
- if (LLVM_UNLIKELY(Result.second)) {
+ if (LLVM_UNLIKELY(Result.second /*inserted*/ ||
+ Result.first->second.isSimple())) {
uint8_t *Stable = RecordStorage.Allocate<uint8_t>(RecordSize);
MutableArrayRef<uint8_t> Data(Stable, RecordSize);
- SeenRecords.push_back(Create(Data));
+ ArrayRef<uint8_t> StableRecord = Create(Data);
+ if (StableRecord.empty()) {
+ // Records with forward references into the Type stream will be deferred
+ // for insertion at a later time, on the second pass.
+ Result.first->getSecond() = TypeIndex(SimpleTypeKind::NotTranslated);
+ return TypeIndex(SimpleTypeKind::NotTranslated);
+ }
+ if (Result.first->second.isSimple()) {
+ assert(Result.first->second.getIndex() ==
+ (uint32_t)SimpleTypeKind::NotTranslated);
+ // On the second pass, update with index to remapped record. The
+ // (initially misbehaved) record will now come *after* other records
+ // resolved in the first pass, with proper *back* references in the
+ // stream.
+ Result.first->second = nextTypeIndex();
+ }
+ SeenRecords.push_back(StableRecord);
SeenHashes.push_back(Hash);
}
- // Update the caller's copy of Record to point a stable copy.
return Result.first->second;
}
}
std::array<uint8_t, 8> Hash;
+ bool empty() const { return *(const uint64_t*)Hash.data() == 0; }\r
+
/// Given a sequence of bytes representing a record, compute a global hash for
/// this record. Due to the nature of global hashes incorporating the hashes
/// of referenced records, this function requires a list of types and ids
template <typename Range>
static std::vector<GloballyHashedType> hashTypes(Range &&Records) {
std::vector<GloballyHashedType> Hashes;
- for (const auto &R : Records)
- Hashes.push_back(hashType(R, Hashes, Hashes));
+ bool UnresolvedRecords = false;\r
+ for (const auto &R : Records) {\r
+ GloballyHashedType H = hashType(R, Hashes, Hashes);
+ if (H.empty())
+ UnresolvedRecords = true;
+ Hashes.push_back(H);
+ }
+
+ // In some rare cases, there might be records with forward references in the
+ // stream. Several passes might be needed to fully hash each record in the
+ // Type stream. However this occurs on very small OBJs generated by MASM,
+ // with a dozen records at most. Therefore this codepath isn't
+ // time-critical, as it isn't taken in 99% of cases.
+ while (UnresolvedRecords) {
+ UnresolvedRecords = false;
+ auto HashIt = Hashes.begin();
+ for (const auto &R : Records) {
+ if (HashIt->empty()) {
+ GloballyHashedType H = hashType(R, Hashes, Hashes);
+ if (H.empty())
+ UnresolvedRecords = true;
+ else
+ *HashIt = H;
+ }
+ ++HashIt;
+ }
+ }
return Hashes;
}
reinterpret_cast<const TypeIndex *>(RefData.data()), Ref.Count);
for (TypeIndex TI : Indices) {
ArrayRef<uint8_t> BytesToHash;
- if (TI.isSimple() || TI.isNoneType() || TI.toArrayIndex() >= Prev.size()) {
+ if (TI.isSimple() || TI.isNoneType()) {
const uint8_t *IndexBytes = reinterpret_cast<const uint8_t *>(&TI);
BytesToHash = makeArrayRef(IndexBytes, sizeof(TypeIndex));
} else {
+ if (TI.toArrayIndex() >= Prev.size() ||
+ Prev[TI.toArrayIndex()].empty()) {
+ // There are references to yet-unhashed records. Suspend hashing for
+ // this record until all the other records are processed.
+ return {};
+ }
BytesToHash = Prev[TI.toArrayIndex()].Hash;
}
S.update(BytesToHash);
if (auto EC = Writer.writeObject(*Header))
return EC;
- for (auto Rec : TypeRecords)
+ for (auto Rec : TypeRecords) {
+ assert(!Rec.empty()); // An empty record will not write anything, but it
+ // would shift all offsets from here on.
if (auto EC = Writer.writeBytes(Rec))
return EC;
+ }
if (HashStreamIndex != kInvalidStreamIndex) {
auto HVS = WritableMappedBlockStream::createIndexedStream(
--- /dev/null
+# RUN: yaml2obj %s -o=%t.obj
+# RUN: llvm-readobj -codeview-merged-types %t.obj | FileCheck %s --check-prefix=MERGED
+# RUN: llvm-readobj -codeview-merged-types -codeview-ghash %t.obj | FileCheck %s --check-prefix=MERGED
+
+# MERGED: Format: COFF-x86-64
+# MERGED-NEXT: Arch: x86_64
+# MERGED-NEXT: AddressSize: 64bit
+# MERGED-NEXT: MergedTypeStream [
+# MERGED-NEXT: ArgList (0x1000) {
+# MERGED-NEXT: TypeLeafKind: LF_ARGLIST (0x1201)
+# MERGED-NEXT: NumArgs: 0
+# MERGED-NEXT: Arguments [
+# MERGED-NEXT: ]
+# MERGED-NEXT: }
+# MERGED-NEXT: Modifier (0x1001) {
+# MERGED-NEXT: TypeLeafKind: LF_MODIFIER (0x1001)
+# MERGED-NEXT: ModifiedType: void (0x3)
+# MERGED-NEXT: Modifiers [ (0x3)
+# MERGED-NEXT: Const (0x1)
+# MERGED-NEXT: Volatile (0x2)
+# MERGED-NEXT: ]
+# MERGED-NEXT: }
+# MERGED-NEXT: Procedure (0x1002) {
+# MERGED-NEXT: TypeLeafKind: LF_PROCEDURE (0x1008)
+# MERGED-NEXT: ReturnType: void (0x3)
+# MERGED-NEXT: CallingConvention: NearC (0x0)
+# MERGED-NEXT: FunctionOptions [ (0x0)
+# MERGED-NEXT: ]
+# MERGED-NEXT: NumParameters: 0
+# MERGED-NEXT: ArgListType: () (0x1000)
+# MERGED-NEXT: }
+# MERGED-NEXT: Pointer (0x1003) {
+# MERGED-NEXT: TypeLeafKind: LF_POINTER (0x1002)
+# MERGED-NEXT: PointeeType: const volatile void (0x1001)
+# MERGED-NEXT: PtrType: Near64 (0xC)
+# MERGED-NEXT: PtrMode: Pointer (0x0)
+# MERGED-NEXT: IsFlat: 0
+# MERGED-NEXT: IsConst: 1
+# MERGED-NEXT: IsVolatile: 0
+# MERGED-NEXT: IsUnaligned: 0
+# MERGED-NEXT: IsRestrict: 0
+# MERGED-NEXT: IsThisPtr&: 0
+# MERGED-NEXT: IsThisPtr&&: 0
+# MERGED-NEXT: SizeOf: 8
+# MERGED-NEXT: }
+# MERGED-NEXT: Pointer (0x1004) {
+# MERGED-NEXT: TypeLeafKind: LF_POINTER (0x1002)
+# MERGED-NEXT: PointeeType: const volatile void* const (0x1003)
+# MERGED-NEXT: PtrType: Near64 (0xC)
+# MERGED-NEXT: PtrMode: Pointer (0x0)
+# MERGED-NEXT: IsFlat: 0
+# MERGED-NEXT: IsConst: 1
+# MERGED-NEXT: IsVolatile: 0
+# MERGED-NEXT: IsUnaligned: 0
+# MERGED-NEXT: IsRestrict: 0
+# MERGED-NEXT: IsThisPtr&: 0
+# MERGED-NEXT: IsThisPtr&&: 0
+# MERGED-NEXT: SizeOf: 8
+# MERGED-NEXT: }
+# MERGED-NEXT: Pointer (0x1005) {
+# MERGED-NEXT: TypeLeafKind: LF_POINTER (0x1002)
+# MERGED-NEXT: PointeeType: const volatile void* const* const (0x1004)
+# MERGED-NEXT: PtrType: Near64 (0xC)
+# MERGED-NEXT: PtrMode: Pointer (0x0)
+# MERGED-NEXT: IsFlat: 0
+# MERGED-NEXT: IsConst: 1
+# MERGED-NEXT: IsVolatile: 0
+# MERGED-NEXT: IsUnaligned: 0
+# MERGED-NEXT: IsRestrict: 0
+# MERGED-NEXT: IsThisPtr&: 0
+# MERGED-NEXT: IsThisPtr&&: 0
+# MERGED-NEXT: SizeOf: 8
+# MERGED-NEXT: }
+# MERGED-NEXT: Pointer (0x1006) {
+# MERGED-NEXT: TypeLeafKind: LF_POINTER (0x1002)
+# MERGED-NEXT: PointeeType: const volatile void* const* const* const (0x1005)
+# MERGED-NEXT: PtrType: Near64 (0xC)
+# MERGED-NEXT: PtrMode: Pointer (0x0)
+# MERGED-NEXT: IsFlat: 0
+# MERGED-NEXT: IsConst: 1
+# MERGED-NEXT: IsVolatile: 0
+# MERGED-NEXT: IsUnaligned: 0
+# MERGED-NEXT: IsRestrict: 0
+# MERGED-NEXT: IsThisPtr&: 0
+# MERGED-NEXT: IsThisPtr&&: 0
+# MERGED-NEXT: SizeOf: 8
+# MERGED-NEXT: }
+# MERGED-NEXT: ]
+# MERGED-NEXT: MergedIDStream [
+# MERGED-NEXT: ]
+
+--- !COFF
+header:
+ Machine: IMAGE_FILE_MACHINE_AMD64
+ Characteristics: [ ]
+sections:
+ - Name: '.debug$T'
+ Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_DISCARDABLE, IMAGE_SCN_MEM_READ ]
+ Alignment: 1
+ Types:
+ - Kind: LF_PROCEDURE
+ Procedure:
+ ReturnType: 3
+ CallConv: NearC
+ Options: [ None ]
+ ParameterCount: 0
+ ArgumentList: 4097
+ - Kind: LF_ARGLIST
+ ArgList:
+ ArgIndices: [ ]
+ - Kind: LF_POINTER
+ Pointer:
+ ReferentType: 4099
+ Attrs: 66572
+ - Kind: LF_POINTER
+ Pointer:
+ ReferentType: 4100
+ Attrs: 66572
+ - Kind: LF_POINTER
+ Pointer:
+ ReferentType: 4101
+ Attrs: 66572
+ - Kind: LF_MODIFIER
+ Modifier:
+ ModifiedType: 3
+ Modifiers: [ None, Const, Volatile ]
+ - Kind: LF_POINTER
+ Pointer:
+ ReferentType: 4098
+ Attrs: 66572
+symbols:
+...
void printCOFFResources() override;
void printCOFFLoadConfig() override;
void printCodeViewDebugInfo() override;
- void
- mergeCodeViewTypes(llvm::codeview::MergingTypeTableBuilder &CVIDs,
- llvm::codeview::MergingTypeTableBuilder &CVTypes) override;
+ void mergeCodeViewTypes(llvm::codeview::MergingTypeTableBuilder &CVIDs,
+ llvm::codeview::MergingTypeTableBuilder &CVTypes,
+ llvm::codeview::GlobalTypeTableBuilder &GlobalCVIDs,
+ llvm::codeview::GlobalTypeTableBuilder &GlobalCVTypes,
+ bool GHash) override;
void printStackMap() const override;
void printAddrsig() override;
private:
}
void COFFDumper::mergeCodeViewTypes(MergingTypeTableBuilder &CVIDs,
- MergingTypeTableBuilder &CVTypes) {
+ MergingTypeTableBuilder &CVTypes,
+ GlobalTypeTableBuilder &GlobalCVIDs,
+ GlobalTypeTableBuilder &GlobalCVTypes,
+ bool GHash) {
for (const SectionRef &S : Obj->sections()) {
StringRef SectionName;
error(S.getName(SectionName));
}
SmallVector<TypeIndex, 128> SourceToDest;
Optional<uint32_t> PCHSignature;
- if (auto EC = mergeTypeAndIdRecords(CVIDs, CVTypes, SourceToDest, Types,
- PCHSignature))
- return error(std::move(EC));
+ if (GHash) {
+ std::vector<GloballyHashedType> Hashes =
+ GloballyHashedType::hashTypes(Types);
+ if (auto EC = mergeTypeAndIdRecords(GlobalCVIDs, GlobalCVTypes, SourceToDest, Types,
+ Hashes, PCHSignature))
+ return error(std::move(EC));
+ } else {
+ if (auto EC = mergeTypeAndIdRecords(CVIDs, CVTypes, SourceToDest, Types,
+ PCHSignature))
+ return error(std::move(EC));
+ }
}
}
}
}
}
-void llvm::dumpCodeViewMergedTypes(
- ScopedPrinter &Writer, llvm::codeview::MergingTypeTableBuilder &IDTable,
- llvm::codeview::MergingTypeTableBuilder &CVTypes) {
- // Flatten it first, then run our dumper on it.
- SmallString<0> TypeBuf;
- CVTypes.ForEachRecord([&](TypeIndex TI, const CVType &Record) {
- TypeBuf.append(Record.RecordData.begin(), Record.RecordData.end());
- });
-
- TypeTableCollection TpiTypes(CVTypes.records());
+void llvm::dumpCodeViewMergedTypes(ScopedPrinter &Writer,
+ ArrayRef<ArrayRef<uint8_t>> IpiRecords,
+ ArrayRef<ArrayRef<uint8_t>> TpiRecords) {
+ TypeTableCollection TpiTypes(TpiRecords);
{
ListScope S(Writer, "MergedTypeStream");
TypeDumpVisitor TDV(TpiTypes, &Writer, opts::CodeViewSubsectionBytes);
// Flatten the id stream and print it next. The ID stream refers to names from
// the type stream.
- TypeTableCollection IpiTypes(IDTable.records());
+ TypeTableCollection IpiTypes(IpiRecords);
{
ListScope S(Writer, "MergedIDStream");
TypeDumpVisitor TDV(TpiTypes, &Writer, opts::CodeViewSubsectionBytes);
class ObjectFile;
}
namespace codeview {
+class GlobalTypeTableBuilder;
class MergingTypeTableBuilder;
-}
+} // namespace codeview
class ScopedPrinter;
virtual void printCodeViewDebugInfo() { }
virtual void
mergeCodeViewTypes(llvm::codeview::MergingTypeTableBuilder &CVIDs,
- llvm::codeview::MergingTypeTableBuilder &CVTypes) {}
+ llvm::codeview::MergingTypeTableBuilder &CVTypes,
+ llvm::codeview::GlobalTypeTableBuilder &GlobalCVIDs,
+ llvm::codeview::GlobalTypeTableBuilder &GlobalCVTypes,
+ bool GHash) {}
// Only implemented for MachO.
virtual void printMachODataInCode() { }
void dumpCOFFImportFile(const object::COFFImportFile *File,
ScopedPrinter &Writer);
-void dumpCodeViewMergedTypes(
- ScopedPrinter &Writer, llvm::codeview::MergingTypeTableBuilder &IDTable,
- llvm::codeview::MergingTypeTableBuilder &TypeTable);
+void dumpCodeViewMergedTypes(ScopedPrinter &Writer,
+ ArrayRef<ArrayRef<uint8_t>> IpiRecords,
+ ArrayRef<ArrayRef<uint8_t>> TpiRecords);
} // namespace llvm
#include "Error.h"
#include "ObjDumper.h"
#include "WindowsResourceDumper.h"
+#include "llvm/DebugInfo/CodeView/GlobalTypeTableBuilder.h"
#include "llvm/DebugInfo/CodeView/MergingTypeTableBuilder.h"
#include "llvm/Object/Archive.h"
#include "llvm/Object/COFFImportFile.h"
CodeViewMergedTypes("codeview-merged-types",
cl::desc("Display the merged CodeView type stream"));
+ // -codeview-ghash
+ cl::opt<bool> CodeViewEnableGHash(
+ "codeview-ghash",
+ cl::desc(
+ "Enable global hashing for CodeView type stream de-duplication"));
+
// -codeview-subsection-bytes
cl::opt<bool> CodeViewSubsectionBytes(
"codeview-subsection-bytes",
namespace {
struct ReadObjTypeTableBuilder {
ReadObjTypeTableBuilder()
- : Allocator(), IDTable(Allocator), TypeTable(Allocator) {}
+ : Allocator(), IDTable(Allocator), TypeTable(Allocator),
+ GlobalIDTable(Allocator), GlobalTypeTable(Allocator) {}
llvm::BumpPtrAllocator Allocator;
llvm::codeview::MergingTypeTableBuilder IDTable;
llvm::codeview::MergingTypeTableBuilder TypeTable;
+ llvm::codeview::GlobalTypeTableBuilder GlobalIDTable;
+ llvm::codeview::GlobalTypeTableBuilder GlobalTypeTable;
+ std::vector<OwningBinary<Binary>> Binaries;
};
-}
+} // namespace
static ReadObjTypeTableBuilder CVTypes;
/// Creates an format-specific object file dumper.
if (opts::CodeView)
Dumper->printCodeViewDebugInfo();
if (opts::CodeViewMergedTypes)
- Dumper->mergeCodeViewTypes(CVTypes.IDTable, CVTypes.TypeTable);
+ Dumper->mergeCodeViewTypes(CVTypes.IDTable, CVTypes.TypeTable,
+ CVTypes.GlobalIDTable, CVTypes.GlobalTypeTable,
+ opts::CodeViewEnableGHash);
}
if (Obj->isMachO()) {
if (opts::MachODataInCode)
dumpWindowsResourceFile(WinRes);
else
reportError(File, readobj_error::unrecognized_file_format);
+
+ CVTypes.Binaries.push_back(std::move(*BinaryOrErr));
}
/// Registers aliases that should only be allowed by readobj.
if (opts::CodeViewMergedTypes) {
ScopedPrinter W(outs());
- dumpCodeViewMergedTypes(W, CVTypes.IDTable, CVTypes.TypeTable);
+ if (opts::CodeViewEnableGHash)
+ dumpCodeViewMergedTypes(W, CVTypes.GlobalIDTable.records(),
+ CVTypes.GlobalTypeTable.records());
+ else
+ dumpCodeViewMergedTypes(W, CVTypes.IDTable.records(),
+ CVTypes.TypeTable.records());
}
return 0;
projects / llvm / commitdiff