blob: 9fb968cb5d25638c96ec18d9ee6ec59b7d707bbc [file] [log] [blame]
//===- tools/dsymutil/DwarfLinker.cpp - Dwarf debug info linker -----------===//
// The LLVM Linker
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
#include "BinaryHolder.h"
#include "DebugMap.h"
#include "MachOUtils.h"
#include "NonRelocatableStringpool.h"
#include "dsymutil.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseMapInfo.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/FoldingSet.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/IntervalMap.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/PointerIntPair.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Triple.h"
#include "llvm/ADT/Twine.h"
#include "llvm/BinaryFormat/Dwarf.h"
#include "llvm/BinaryFormat/MachO.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/DIE.h"
#include "llvm/Config/config.h"
#include "llvm/DebugInfo/DIContext.h"
#include "llvm/DebugInfo/DWARF/DWARFAbbreviationDeclaration.h"
#include "llvm/DebugInfo/DWARF/DWARFContext.h"
#include "llvm/DebugInfo/DWARF/DWARFDataExtractor.h"
#include "llvm/DebugInfo/DWARF/DWARFDebugLine.h"
#include "llvm/DebugInfo/DWARF/DWARFDebugRangeList.h"
#include "llvm/DebugInfo/DWARF/DWARFDie.h"
#include "llvm/DebugInfo/DWARF/DWARFFormValue.h"
#include "llvm/DebugInfo/DWARF/DWARFSection.h"
#include "llvm/DebugInfo/DWARF/DWARFUnit.h"
#include "llvm/MC/MCAsmBackend.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/MC/MCInstrInfo.h"
#include "llvm/MC/MCObjectFileInfo.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/MC/MCSection.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/MC/MCTargetOptions.h"
#include "llvm/MC/MCTargetOptionsCommandFlags.h"
#include "llvm/Object/MachO.h"
#include "llvm/Object/ObjectFile.h"
#include "llvm/Object/SymbolicFile.h"
#include "llvm/Support/Allocator.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/DataExtractor.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/ToolOutputFile.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include <algorithm>
#include <cassert>
#include <cinttypes>
#include <climits>
#include <cstdint>
#include <cstdlib>
#include <cstring>
#include <limits>
#include <map>
#include <memory>
#include <string>
#include <system_error>
#include <tuple>
#include <utility>
#include <vector>
namespace llvm {
namespace dsymutil {
namespace {
template <typename KeyT, typename ValT>
using HalfOpenIntervalMap =
IntervalMap<KeyT, ValT, IntervalMapImpl::NodeSizer<KeyT, ValT>::LeafSize,
using FunctionIntervals = HalfOpenIntervalMap<uint64_t, int64_t>;
// FIXME: Delete this structure.
struct PatchLocation {
DIE::value_iterator I;
PatchLocation() = default;
PatchLocation(DIE::value_iterator I) : I(I) {}
void set(uint64_t New) const {
const auto &Old = *I;
assert(Old.getType() == DIEValue::isInteger);
*I = DIEValue(Old.getAttribute(), Old.getForm(), DIEInteger(New));
uint64_t get() const {
return I->getDIEInteger().getValue();
class CompileUnit;
struct DeclMapInfo;
/// A DeclContext is a named program scope that is used for ODR
/// uniquing of types.
/// The set of DeclContext for the ODR-subject parts of a Dwarf link
/// is expanded (and uniqued) with each new object file processed. We
/// need to determine the context of each DIE in an linked object file
/// to see if the corresponding type has already been emitted.
/// The contexts are conceptually organised as a tree (eg. a function
/// scope is contained in a namespace scope that contains other
/// scopes), but storing/accessing them in an actual tree is too
/// inefficient: we need to be able to very quickly query a context
/// for a given child context by name. Storing a StringMap in each
/// DeclContext would be too space inefficient.
/// The solution here is to give each DeclContext a link to its parent
/// (this allows to walk up the tree), but to query the existance of a
/// specific DeclContext using a separate DenseMap keyed on the hash
/// of the fully qualified name of the context.
class DeclContext {
friend DeclMapInfo;
unsigned QualifiedNameHash = 0;
uint32_t Line = 0;
uint32_t ByteSize = 0;
uint16_t Tag = dwarf::DW_TAG_compile_unit;
unsigned DefinedInClangModule : 1;
StringRef Name;
StringRef File;
const DeclContext &Parent;
uint32_t LastSeenCompileUnitID = 0;
uint32_t CanonicalDIEOffset = 0;
using Map = DenseSet<DeclContext *, DeclMapInfo>;
DeclContext() : DefinedInClangModule(0), Parent(*this) {}
DeclContext(unsigned Hash, uint32_t Line, uint32_t ByteSize, uint16_t Tag,
StringRef Name, StringRef File, const DeclContext &Parent,
DWARFDie LastSeenDIE = DWARFDie(), unsigned CUId = 0)
: QualifiedNameHash(Hash), Line(Line), ByteSize(ByteSize), Tag(Tag),
DefinedInClangModule(0), Name(Name), File(File), Parent(Parent),
LastSeenDIE(LastSeenDIE), LastSeenCompileUnitID(CUId) {}
uint32_t getQualifiedNameHash() const { return QualifiedNameHash; }
bool setLastSeenDIE(CompileUnit &U, const DWARFDie &Die);
uint32_t getCanonicalDIEOffset() const { return CanonicalDIEOffset; }
void setCanonicalDIEOffset(uint32_t Offset) { CanonicalDIEOffset = Offset; }
bool isDefinedInClangModule() const { return DefinedInClangModule; }
void setDefinedInClangModule(bool Val) { DefinedInClangModule = Val; }
uint16_t getTag() const { return Tag; }
StringRef getName() const { return Name; }
/// Info type for the DenseMap storing the DeclContext pointers.
struct DeclMapInfo : private DenseMapInfo<DeclContext *> {
using DenseMapInfo<DeclContext *>::getEmptyKey;
using DenseMapInfo<DeclContext *>::getTombstoneKey;
static unsigned getHashValue(const DeclContext *Ctxt) {
return Ctxt->QualifiedNameHash;
static bool isEqual(const DeclContext *LHS, const DeclContext *RHS) {
if (RHS == getEmptyKey() || RHS == getTombstoneKey())
return RHS == LHS;
return LHS->QualifiedNameHash == RHS->QualifiedNameHash &&
LHS->Line == RHS->Line && LHS->ByteSize == RHS->ByteSize &&
LHS-> == RHS-> &&
LHS-> == RHS-> &&
LHS->Parent.QualifiedNameHash == RHS->Parent.QualifiedNameHash;
/// This class gives a tree-like API to the DenseMap that stores the
/// DeclContext objects. It also holds the BumpPtrAllocator where
/// these objects will be allocated.
class DeclContextTree {
BumpPtrAllocator Allocator;
DeclContext Root;
DeclContext::Map Contexts;
/// Get the child of \a Context described by \a DIE in \a Unit. The
/// required strings will be interned in \a StringPool.
/// \returns The child DeclContext along with one bit that is set if
/// this context is invalid.
/// An invalid context means it shouldn't be considered for uniquing, but its
/// not returning null, because some children of that context might be
/// uniquing candidates. FIXME: The invalid bit along the return value is to
/// emulate some dsymutil-classic functionality.
PointerIntPair<DeclContext *, 1>
getChildDeclContext(DeclContext &Context,
const DWARFDie &DIE, CompileUnit &Unit,
NonRelocatableStringpool &StringPool, bool InClangModule);
DeclContext &getRoot() { return Root; }
/// Stores all information relating to a compile unit, be it in its original
/// instance in the object file to its brand new cloned and linked DIE tree.
class CompileUnit {
/// Information gathered about a DIE in the object file.
struct DIEInfo {
/// Address offset to apply to the described entity.
int64_t AddrAdjust;
/// ODR Declaration context.
DeclContext *Ctxt;
/// Cloned version of that DIE.
DIE *Clone;
/// The index of this DIE's parent.
uint32_t ParentIdx;
/// Is the DIE part of the linked output?
bool Keep : 1;
/// Was this DIE's entity found in the map?
bool InDebugMap : 1;
/// Is this a pure forward declaration we can strip?
bool Prune : 1;
/// Does DIE transitively refer an incomplete decl?
bool Incomplete : 1;
CompileUnit(DWARFUnit &OrigUnit, unsigned ID, bool CanUseODR,
StringRef ClangModuleName)
: OrigUnit(OrigUnit), ID(ID), Ranges(RangeAlloc),
ClangModuleName(ClangModuleName) {
auto CUDie = OrigUnit.getUnitDIE(false);
if (auto Lang = dwarf::toUnsigned(CUDie.find(dwarf::DW_AT_language)))
HasODR = CanUseODR && (*Lang == dwarf::DW_LANG_C_plus_plus ||
*Lang == dwarf::DW_LANG_C_plus_plus_03 ||
*Lang == dwarf::DW_LANG_C_plus_plus_11 ||
*Lang == dwarf::DW_LANG_C_plus_plus_14 ||
*Lang == dwarf::DW_LANG_ObjC_plus_plus);
HasODR = false;
DWARFUnit &getOrigUnit() const { return OrigUnit; }
unsigned getUniqueID() const { return ID; }
void createOutputDIE() {
NewUnit.emplace(OrigUnit.getVersion(), OrigUnit.getAddressByteSize(),
DIE *getOutputUnitDIE() const {
if (NewUnit)
return &const_cast<BasicDIEUnit &>(*NewUnit).getUnitDie();
return nullptr;
bool hasODR() const { return HasODR; }
bool isClangModule() const { return !ClangModuleName.empty(); }
const std::string &getClangModuleName() const { return ClangModuleName; }
DIEInfo &getInfo(unsigned Idx) { return Info[Idx]; }
const DIEInfo &getInfo(unsigned Idx) const { return Info[Idx]; }
uint64_t getStartOffset() const { return StartOffset; }
uint64_t getNextUnitOffset() const { return NextUnitOffset; }
void setStartOffset(uint64_t DebugInfoSize) { StartOffset = DebugInfoSize; }
uint64_t getLowPc() const { return LowPc; }
uint64_t getHighPc() const { return HighPc; }
Optional<PatchLocation> getUnitRangesAttribute() const {
return UnitRangeAttribute;
const FunctionIntervals &getFunctionRanges() const { return Ranges; }
const std::vector<PatchLocation> &getRangesAttributes() const {
return RangeAttributes;
const std::vector<std::pair<PatchLocation, int64_t>> &
getLocationAttributes() const {
return LocationAttributes;
void setHasInterestingContent() { HasInterestingContent = true; }
bool hasInterestingContent() { return HasInterestingContent; }
/// Mark every DIE in this unit as kept. This function also
/// marks variables as InDebugMap so that they appear in the
/// reconstructed accelerator tables.
void markEverythingAsKept();
/// Compute the end offset for this unit. Must be called after the CU's DIEs
/// have been cloned. \returns the next unit offset (which is also the
/// current debug_info section size).
uint64_t computeNextUnitOffset();
/// Keep track of a forward reference to DIE \p Die in \p RefUnit by \p
/// Attr. The attribute should be fixed up later to point to the absolute
/// offset of \p Die in the debug_info section or to the canonical offset of
/// \p Ctxt if it is non-null.
void noteForwardReference(DIE *Die, const CompileUnit *RefUnit,
DeclContext *Ctxt, PatchLocation Attr);
/// Apply all fixups recored by noteForwardReference().
void fixupForwardReferences();
/// Add a function range [\p LowPC, \p HighPC) that is relocatad by applying
/// offset \p PCOffset.
void addFunctionRange(uint64_t LowPC, uint64_t HighPC, int64_t PCOffset);
/// Keep track of a DW_AT_range attribute that we will need to patch up later.
void noteRangeAttribute(const DIE &Die, PatchLocation Attr);
/// Keep track of a location attribute pointing to a location list in the
/// debug_loc section.
void noteLocationAttribute(PatchLocation Attr, int64_t PcOffset);
/// Add a name accelerator entry for \p Die with \p Name which is stored in
/// the string table at \p Offset.
void addNameAccelerator(const DIE *Die, const char *Name, uint32_t Offset,
bool SkipPubnamesSection = false);
/// Add a type accelerator entry for \p Die with \p Name which is stored in
/// the string table at \p Offset.
void addTypeAccelerator(const DIE *Die, const char *Name, uint32_t Offset);
struct AccelInfo {
StringRef Name; ///< Name of the entry.
const DIE *Die; ///< DIE this entry describes.
uint32_t NameOffset; ///< Offset of Name in the string pool.
bool SkipPubSection; ///< Emit this entry only in the apple_* sections.
AccelInfo(StringRef Name, const DIE *Die, uint32_t NameOffset,
bool SkipPubSection = false)
: Name(Name), Die(Die), NameOffset(NameOffset),
SkipPubSection(SkipPubSection) {}
const std::vector<AccelInfo> &getPubnames() const { return Pubnames; }
const std::vector<AccelInfo> &getPubtypes() const { return Pubtypes; }
/// Get the full path for file \a FileNum in the line table
StringRef getResolvedPath(unsigned FileNum) {
if (FileNum >= ResolvedPaths.size())
return StringRef();
return ResolvedPaths[FileNum];
/// Set the fully resolved path for the line-table's file \a FileNum
/// to \a Path.
void setResolvedPath(unsigned FileNum, StringRef Path) {
if (ResolvedPaths.size() <= FileNum)
ResolvedPaths.resize(FileNum + 1);
ResolvedPaths[FileNum] = Path;
DWARFUnit &OrigUnit;
unsigned ID;
std::vector<DIEInfo> Info; ///< DIE info indexed by DIE index.
Optional<BasicDIEUnit> NewUnit;
uint64_t StartOffset;
uint64_t NextUnitOffset;
uint64_t LowPc = std::numeric_limits<uint64_t>::max();
uint64_t HighPc = 0;
/// A list of attributes to fixup with the absolute offset of
/// a DIE in the debug_info section.
/// The offsets for the attributes in this array couldn't be set while
/// cloning because for cross-cu forward refences the target DIE's
/// offset isn't known you emit the reference attribute.
std::vector<std::tuple<DIE *, const CompileUnit *, DeclContext *,
PatchLocation>> ForwardDIEReferences;
FunctionIntervals::Allocator RangeAlloc;
/// The ranges in that interval map are the PC ranges for
/// functions in this unit, associated with the PC offset to apply
/// to the addresses to get the linked address.
FunctionIntervals Ranges;
/// DW_AT_ranges attributes to patch after we have gathered
/// all the unit's function addresses.
/// @{
std::vector<PatchLocation> RangeAttributes;
Optional<PatchLocation> UnitRangeAttribute;
/// @}
/// Location attributes that need to be transferred from the
/// original debug_loc section to the liked one. They are stored
/// along with the PC offset that is to be applied to their
/// function's address.
std::vector<std::pair<PatchLocation, int64_t>> LocationAttributes;
/// Accelerator entries for the unit, both for the pub*
/// sections and the apple* ones.
/// @{
std::vector<AccelInfo> Pubnames;
std::vector<AccelInfo> Pubtypes;
/// @}
/// Cached resolved paths from the line table.
/// Note, the StringRefs here point in to the intern (uniquing) string pool.
/// This means that a StringRef returned here doesn't need to then be uniqued
/// for the purposes of getting a unique address for each string.
std::vector<StringRef> ResolvedPaths;
/// Is this unit subject to the ODR rule?
bool HasODR;
/// Did a DIE actually contain a valid reloc?
bool HasInterestingContent;
/// If this is a Clang module, this holds the module's name.
std::string ClangModuleName;
} // end anonymous namespace
void CompileUnit::markEverythingAsKept() {
for (auto &I : Info)
// Mark everything that wasn't explicity marked for pruning.
I.Keep = !I.Prune;
uint64_t CompileUnit::computeNextUnitOffset() {
NextUnitOffset = StartOffset + 11 /* Header size */;
// The root DIE might be null, meaning that the Unit had nothing to
// contribute to the linked output. In that case, we will emit the
// unit header without any actual DIE.
if (NewUnit)
NextUnitOffset += NewUnit->getUnitDie().getSize();
return NextUnitOffset;
/// Keep track of a forward cross-cu reference from this unit
/// to \p Die that lives in \p RefUnit.
void CompileUnit::noteForwardReference(DIE *Die, const CompileUnit *RefUnit,
DeclContext *Ctxt, PatchLocation Attr) {
ForwardDIEReferences.emplace_back(Die, RefUnit, Ctxt, Attr);
/// Apply all fixups recorded by noteForwardReference().
void CompileUnit::fixupForwardReferences() {
for (const auto &Ref : ForwardDIEReferences) {
DIE *RefDie;
const CompileUnit *RefUnit;
PatchLocation Attr;
DeclContext *Ctxt;
std::tie(RefDie, RefUnit, Ctxt, Attr) = Ref;
if (Ctxt && Ctxt->getCanonicalDIEOffset())
Attr.set(RefDie->getOffset() + RefUnit->getStartOffset());
void CompileUnit::addFunctionRange(uint64_t FuncLowPc, uint64_t FuncHighPc,
int64_t PcOffset) {
Ranges.insert(FuncLowPc, FuncHighPc, PcOffset);
this->LowPc = std::min(LowPc, FuncLowPc + PcOffset);
this->HighPc = std::max(HighPc, FuncHighPc + PcOffset);
void CompileUnit::noteRangeAttribute(const DIE &Die, PatchLocation Attr) {
if (Die.getTag() != dwarf::DW_TAG_compile_unit)
UnitRangeAttribute = Attr;
void CompileUnit::noteLocationAttribute(PatchLocation Attr, int64_t PcOffset) {
LocationAttributes.emplace_back(Attr, PcOffset);
/// Add a name accelerator entry for \p Die with \p Name
/// which is stored in the string table at \p Offset.
void CompileUnit::addNameAccelerator(const DIE *Die, const char *Name,
uint32_t Offset, bool SkipPubSection) {
Pubnames.emplace_back(Name, Die, Offset, SkipPubSection);
/// Add a type accelerator entry for \p Die with \p Name
/// which is stored in the string table at \p Offset.
void CompileUnit::addTypeAccelerator(const DIE *Die, const char *Name,
uint32_t Offset) {
Pubtypes.emplace_back(Name, Die, Offset, false);
namespace {
/// The Dwarf streaming logic
/// All interactions with the MC layer that is used to build the debug
/// information binary representation are handled in this class.
class DwarfStreamer {
/// \defgroup MCObjects MC layer objects constructed by the streamer
/// @{
std::unique_ptr<MCRegisterInfo> MRI;
std::unique_ptr<MCAsmInfo> MAI;
std::unique_ptr<MCObjectFileInfo> MOFI;
std::unique_ptr<MCContext> MC;
MCAsmBackend *MAB; // Owned by MCStreamer
std::unique_ptr<MCInstrInfo> MII;
std::unique_ptr<MCSubtargetInfo> MSTI;
MCCodeEmitter *MCE; // Owned by MCStreamer
MCStreamer *MS; // Owned by AsmPrinter
std::unique_ptr<TargetMachine> TM;
std::unique_ptr<AsmPrinter> Asm;
/// @}
/// The file we stream the linked Dwarf to.
std::unique_ptr<ToolOutputFile> OutFile;
uint32_t RangesSectionSize;
uint32_t LocSectionSize;
uint32_t LineSectionSize;
uint32_t FrameSectionSize;
/// Emit the pubnames or pubtypes section contribution for \p
/// Unit into \p Sec. The data is provided in \p Names.
void emitPubSectionForUnit(MCSection *Sec, StringRef Name,
const CompileUnit &Unit,
const std::vector<CompileUnit::AccelInfo> &Names);
/// Actually create the streamer and the ouptut file.
/// This could be done directly in the constructor, but it feels
/// more natural to handle errors through return value.
bool init(Triple TheTriple, StringRef OutputFilename);
/// Dump the file to the disk.
bool finish(const DebugMap &);
AsmPrinter &getAsmPrinter() const { return *Asm; }
/// Set the current output section to debug_info and change
/// the MC Dwarf version to \p DwarfVersion.
void switchToDebugInfoSection(unsigned DwarfVersion);
/// Emit the compilation unit header for \p Unit in the
/// debug_info section.
/// As a side effect, this also switches the current Dwarf version
/// of the MC layer to the one of U.getOrigUnit().
void emitCompileUnitHeader(CompileUnit &Unit);
/// Recursively emit the DIE tree rooted at \p Die.
void emitDIE(DIE &Die);
/// Emit the abbreviation table \p Abbrevs to the debug_abbrev section.
void emitAbbrevs(const std::vector<std::unique_ptr<DIEAbbrev>> &Abbrevs,
unsigned DwarfVersion);
/// Emit the string table described by \p Pool.
void emitStrings(const NonRelocatableStringpool &Pool);
/// Emit the swift_ast section stored in \p Buffer.
void emitSwiftAST(StringRef Buffer);
/// Emit debug_ranges for \p FuncRange by translating the
/// original \p Entries.
void emitRangesEntries(
int64_t UnitPcOffset, uint64_t OrigLowPc,
const FunctionIntervals::const_iterator &FuncRange,
const std::vector<DWARFDebugRangeList::RangeListEntry> &Entries,
unsigned AddressSize);
/// Emit debug_aranges entries for \p Unit and if \p DoRangesSection is true,
/// also emit the debug_ranges entries for the DW_TAG_compile_unit's
/// DW_AT_ranges attribute.
void emitUnitRangesEntries(CompileUnit &Unit, bool DoRangesSection);
uint32_t getRangesSectionSize() const { return RangesSectionSize; }
/// Emit the debug_loc contribution for \p Unit by copying the entries from \p
/// Dwarf and offseting them. Update the location attributes to point to the
/// new entries.
void emitLocationsForUnit(const CompileUnit &Unit, DWARFContext &Dwarf);
/// Emit the line table described in \p Rows into the debug_line section.
void emitLineTableForUnit(MCDwarfLineTableParams Params,
StringRef PrologueBytes, unsigned MinInstLength,
std::vector<DWARFDebugLine::Row> &Rows,
unsigned AdddressSize);
uint32_t getLineSectionSize() const { return LineSectionSize; }
/// Emit the .debug_pubnames contribution for \p Unit.
void emitPubNamesForUnit(const CompileUnit &Unit);
/// Emit the .debug_pubtypes contribution for \p Unit.
void emitPubTypesForUnit(const CompileUnit &Unit);
/// Emit a CIE.
void emitCIE(StringRef CIEBytes);
/// Emit an FDE with data \p Bytes.
void emitFDE(uint32_t CIEOffset, uint32_t AddreSize, uint32_t Address,
StringRef Bytes);
uint32_t getFrameSectionSize() const { return FrameSectionSize; }
} // end anonymous namespace
bool DwarfStreamer::init(Triple TheTriple, StringRef OutputFilename) {
std::string ErrorStr;
std::string TripleName;
StringRef Context = "dwarf streamer init";
// Get the target.
const Target *TheTarget =
TargetRegistry::lookupTarget(TripleName, TheTriple, ErrorStr);
if (!TheTarget)
return error(ErrorStr, Context);
TripleName = TheTriple.getTriple();
// Create all the MC Objects.
if (!MRI)
return error(Twine("no register info for target ") + TripleName, Context);
MAI.reset(TheTarget->createMCAsmInfo(*MRI, TripleName));
if (!MAI)
return error("no asm info for target " + TripleName, Context);
MOFI.reset(new MCObjectFileInfo);
MC.reset(new MCContext(MAI.get(), MRI.get(), MOFI.get()));
MOFI->InitMCObjectFileInfo(TheTriple, /*PIC*/ false, *MC);
MCTargetOptions Options;
MAB = TheTarget->createMCAsmBackend(*MRI, TripleName, "", Options);
if (!MAB)
return error("no asm backend for target " + TripleName, Context);
if (!MII)
return error("no instr info info for target " + TripleName, Context);
MSTI.reset(TheTarget->createMCSubtargetInfo(TripleName, "", ""));
if (!MSTI)
return error("no subtarget info for target " + TripleName, Context);
MCE = TheTarget->createMCCodeEmitter(*MII, *MRI, *MC);
if (!MCE)
return error("no code emitter for target " + TripleName, Context);
// Create the output file.
std::error_code EC;
OutFile =
llvm::make_unique<ToolOutputFile>(OutputFilename, EC, sys::fs::F_None);
if (EC)
return error(Twine(OutputFilename) + ": " + EC.message(), Context);
MCTargetOptions MCOptions = InitMCTargetOptionsFromFlags();
MS = TheTarget->createMCObjectStreamer(
TheTriple, *MC, std::unique_ptr<MCAsmBackend>(MAB), OutFile->os(),
std::unique_ptr<MCCodeEmitter>(MCE), *MSTI, MCOptions.MCRelaxAll,
/*DWARFMustBeAtTheEnd*/ false);
if (!MS)
return error("no object streamer for target " + TripleName, Context);
// Finally create the AsmPrinter we'll use to emit the DIEs.
TM.reset(TheTarget->createTargetMachine(TripleName, "", "", TargetOptions(),
if (!TM)
return error("no target machine for target " + TripleName, Context);
Asm.reset(TheTarget->createAsmPrinter(*TM, std::unique_ptr<MCStreamer>(MS)));
if (!Asm)
return error("no asm printer for target " + TripleName, Context);
RangesSectionSize = 0;
LocSectionSize = 0;
LineSectionSize = 0;
FrameSectionSize = 0;
return true;
bool DwarfStreamer::finish(const DebugMap &DM) {
bool Result = true;
if (DM.getTriple().isOSDarwin() && !DM.getBinaryPath().empty())
Result = MachOUtils::generateDsymCompanion(DM, *MS, OutFile->os());
// Declare success.
return Result;
/// Set the current output section to debug_info and change
/// the MC Dwarf version to \p DwarfVersion.
void DwarfStreamer::switchToDebugInfoSection(unsigned DwarfVersion) {
/// Emit the compilation unit header for \p Unit in the debug_info section.
/// A Dwarf scetion header is encoded as:
/// uint32_t Unit length (omiting this field)
/// uint16_t Version
/// uint32_t Abbreviation table offset
/// uint8_t Address size
/// Leading to a total of 11 bytes.
void DwarfStreamer::emitCompileUnitHeader(CompileUnit &Unit) {
unsigned Version = Unit.getOrigUnit().getVersion();
// Emit size of content not including length itself. The size has
// already been computed in CompileUnit::computeOffsets(). Substract
// 4 to that size to account for the length field.
Asm->EmitInt32(Unit.getNextUnitOffset() - Unit.getStartOffset() - 4);
// We share one abbreviations table across all units so it's always at the
// start of the section.
/// Emit the \p Abbrevs array as the shared abbreviation table
/// for the linked Dwarf file.
void DwarfStreamer::emitAbbrevs(
const std::vector<std::unique_ptr<DIEAbbrev>> &Abbrevs,
unsigned DwarfVersion) {
/// Recursively emit the DIE tree rooted at \p Die.
void DwarfStreamer::emitDIE(DIE &Die) {
/// Emit the debug_str section stored in \p Pool.
void DwarfStreamer::emitStrings(const NonRelocatableStringpool &Pool) {
for (auto *Entry = Pool.getFirstEntry(); Entry;
Entry = Pool.getNextEntry(Entry))
StringRef(Entry->getKey().data(), Entry->getKey().size() + 1));
/// Emit the swift_ast section stored in \p Buffers.
void DwarfStreamer::emitSwiftAST(StringRef Buffer) {
MCSection *SwiftASTSection = MOFI->getDwarfSwiftASTSection();
SwiftASTSection->setAlignment(1 << 5);
/// Emit the debug_range section contents for \p FuncRange by
/// translating the original \p Entries. The debug_range section
/// format is totally trivial, consisting just of pairs of address
/// sized addresses describing the ranges.
void DwarfStreamer::emitRangesEntries(
int64_t UnitPcOffset, uint64_t OrigLowPc,
const FunctionIntervals::const_iterator &FuncRange,
const std::vector<DWARFDebugRangeList::RangeListEntry> &Entries,
unsigned AddressSize) {
// Offset each range by the right amount.
int64_t PcOffset = Entries.empty() ? 0 : FuncRange.value() + UnitPcOffset;
for (const auto &Range : Entries) {
if (Range.isBaseAddressSelectionEntry(AddressSize)) {
warn("unsupported base address selection operation",
"emitting debug_ranges");
// Do not emit empty ranges.
if (Range.StartAddress == Range.EndAddress)
// All range entries should lie in the function range.
if (!(Range.StartAddress + OrigLowPc >= FuncRange.start() &&
Range.EndAddress + OrigLowPc <= FuncRange.stop()))
warn("inconsistent range data.", "emitting debug_ranges");
MS->EmitIntValue(Range.StartAddress + PcOffset, AddressSize);
MS->EmitIntValue(Range.EndAddress + PcOffset, AddressSize);
RangesSectionSize += 2 * AddressSize;
// Add the terminator entry.
MS->EmitIntValue(0, AddressSize);
MS->EmitIntValue(0, AddressSize);
RangesSectionSize += 2 * AddressSize;
/// Emit the debug_aranges contribution of a unit and
/// if \p DoDebugRanges is true the debug_range contents for a
/// compile_unit level DW_AT_ranges attribute (Which are basically the
/// same thing with a different base address).
/// Just aggregate all the ranges gathered inside that unit.
void DwarfStreamer::emitUnitRangesEntries(CompileUnit &Unit,
bool DoDebugRanges) {
unsigned AddressSize = Unit.getOrigUnit().getAddressByteSize();
// Gather the ranges in a vector, so that we can simplify them. The
// IntervalMap will have coalesced the non-linked ranges, but here
// we want to coalesce the linked addresses.
std::vector<std::pair<uint64_t, uint64_t>> Ranges;
const auto &FunctionRanges = Unit.getFunctionRanges();
for (auto Range = FunctionRanges.begin(), End = FunctionRanges.end();
Range != End; ++Range)
Ranges.push_back(std::make_pair(Range.start() + Range.value(),
Range.stop() + Range.value()));
// The object addresses where sorted, but again, the linked
// addresses might end up in a different order.
std::sort(Ranges.begin(), Ranges.end());
if (!Ranges.empty()) {
MCSymbol *BeginLabel = Asm->createTempSymbol("Barange");
MCSymbol *EndLabel = Asm->createTempSymbol("Earange");
unsigned HeaderSize =
sizeof(int32_t) + // Size of contents (w/o this field
sizeof(int16_t) + // DWARF ARange version number
sizeof(int32_t) + // Offset of CU in the .debug_info section
sizeof(int8_t) + // Pointer Size (in bytes)
sizeof(int8_t); // Segment Size (in bytes)
unsigned TupleSize = AddressSize * 2;
unsigned Padding = OffsetToAlignment(HeaderSize, TupleSize);
Asm->EmitLabelDifference(EndLabel, BeginLabel, 4); // Arange length
Asm->EmitInt16(dwarf::DW_ARANGES_VERSION); // Version number
Asm->EmitInt32(Unit.getStartOffset()); // Corresponding unit's offset
Asm->EmitInt8(AddressSize); // Address size
Asm->EmitInt8(0); // Segment size
Asm->OutStreamer->emitFill(Padding, 0x0);
for (auto Range = Ranges.begin(), End = Ranges.end(); Range != End;
++Range) {
uint64_t RangeStart = Range->first;
MS->EmitIntValue(RangeStart, AddressSize);
while ((Range + 1) != End && Range->second == (Range + 1)->first)
MS->EmitIntValue(Range->second - RangeStart, AddressSize);
// Emit terminator
Asm->OutStreamer->EmitIntValue(0, AddressSize);
Asm->OutStreamer->EmitIntValue(0, AddressSize);
if (!DoDebugRanges)
// Offset each range by the right amount.
int64_t PcOffset = -Unit.getLowPc();
// Emit coalesced ranges.
for (auto Range = Ranges.begin(), End = Ranges.end(); Range != End; ++Range) {
MS->EmitIntValue(Range->first + PcOffset, AddressSize);
while (Range + 1 != End && Range->second == (Range + 1)->first)
MS->EmitIntValue(Range->second + PcOffset, AddressSize);
RangesSectionSize += 2 * AddressSize;
// Add the terminator entry.
MS->EmitIntValue(0, AddressSize);
MS->EmitIntValue(0, AddressSize);
RangesSectionSize += 2 * AddressSize;
/// Emit location lists for \p Unit and update attribtues to
/// point to the new entries.
void DwarfStreamer::emitLocationsForUnit(const CompileUnit &Unit,
DWARFContext &Dwarf) {
const auto &Attributes = Unit.getLocationAttributes();
if (Attributes.empty())
unsigned AddressSize = Unit.getOrigUnit().getAddressByteSize();
const DWARFSection &InputSec = Dwarf.getDWARFObj().getLocSection();
DataExtractor Data(InputSec.Data, Dwarf.isLittleEndian(), AddressSize);
DWARFUnit &OrigUnit = Unit.getOrigUnit();
auto OrigUnitDie = OrigUnit.getUnitDIE(false);
int64_t UnitPcOffset = 0;
if (auto OrigLowPc = dwarf::toAddress(OrigUnitDie.find(dwarf::DW_AT_low_pc)))
UnitPcOffset = int64_t(*OrigLowPc) - Unit.getLowPc();
for (const auto &Attr : Attributes) {
uint32_t Offset = Attr.first.get();
// This is the quantity to add to the old location address to get
// the correct address for the new one.
int64_t LocPcOffset = Attr.second + UnitPcOffset;
while (Data.isValidOffset(Offset)) {
uint64_t Low = Data.getUnsigned(&Offset, AddressSize);
uint64_t High = Data.getUnsigned(&Offset, AddressSize);
LocSectionSize += 2 * AddressSize;
if (Low == 0 && High == 0) {
Asm->OutStreamer->EmitIntValue(0, AddressSize);
Asm->OutStreamer->EmitIntValue(0, AddressSize);
Asm->OutStreamer->EmitIntValue(Low + LocPcOffset, AddressSize);
Asm->OutStreamer->EmitIntValue(High + LocPcOffset, AddressSize);
uint64_t Length = Data.getU16(&Offset);
Asm->OutStreamer->EmitIntValue(Length, 2);
// Just copy the bytes over.
StringRef(InputSec.Data.substr(Offset, Length)));
Offset += Length;
LocSectionSize += Length + 2;
void DwarfStreamer::emitLineTableForUnit(MCDwarfLineTableParams Params,
StringRef PrologueBytes,
unsigned MinInstLength,
std::vector<DWARFDebugLine::Row> &Rows,
unsigned PointerSize) {
// Switch to the section where the table will be emitted into.
MCSymbol *LineStartSym = MC->createTempSymbol();
MCSymbol *LineEndSym = MC->createTempSymbol();
// The first 4 bytes is the total length of the information for this
// compilation unit (not including these 4 bytes for the length).
Asm->EmitLabelDifference(LineEndSym, LineStartSym, 4);
// Copy Prologue.
LineSectionSize += PrologueBytes.size() + 4;
SmallString<128> EncodingBuffer;
raw_svector_ostream EncodingOS(EncodingBuffer);
if (Rows.empty()) {
// We only have the dummy entry, dsymutil emits an entry with a 0
// address in that case.
MCDwarfLineAddr::Encode(*MC, Params, std::numeric_limits<int64_t>::max(), 0,
LineSectionSize += EncodingBuffer.size();
// Line table state machine fields
unsigned FileNum = 1;
unsigned LastLine = 1;
unsigned Column = 0;
unsigned IsStatement = 1;
unsigned Isa = 0;
uint64_t Address = -1ULL;
unsigned RowsSinceLastSequence = 0;
for (unsigned Idx = 0; Idx < Rows.size(); ++Idx) {
auto &Row = Rows[Idx];
int64_t AddressDelta;
if (Address == -1ULL) {
MS->EmitIntValue(dwarf::DW_LNS_extended_op, 1);
MS->EmitULEB128IntValue(PointerSize + 1);
MS->EmitIntValue(dwarf::DW_LNE_set_address, 1);
MS->EmitIntValue(Row.Address, PointerSize);
LineSectionSize += 2 + PointerSize + getULEB128Size(PointerSize + 1);
AddressDelta = 0;
} else {
AddressDelta = (Row.Address - Address) / MinInstLength;
// FIXME: code copied and transfromed from
// MCDwarf.cpp::EmitDwarfLineTable. We should find a way to share
// this code, but the current compatibility requirement with
// classic dsymutil makes it hard. Revisit that once this
// requirement is dropped.
if (FileNum != Row.File) {
FileNum = Row.File;
MS->EmitIntValue(dwarf::DW_LNS_set_file, 1);
LineSectionSize += 1 + getULEB128Size(FileNum);
if (Column != Row.Column) {
Column = Row.Column;
MS->EmitIntValue(dwarf::DW_LNS_set_column, 1);
LineSectionSize += 1 + getULEB128Size(Column);
// FIXME: We should handle the discriminator here, but dsymutil
// doesn' consider it, thus ignore it for now.
if (Isa != Row.Isa) {
Isa = Row.Isa;
MS->EmitIntValue(dwarf::DW_LNS_set_isa, 1);
LineSectionSize += 1 + getULEB128Size(Isa);
if (IsStatement != Row.IsStmt) {
IsStatement = Row.IsStmt;
MS->EmitIntValue(dwarf::DW_LNS_negate_stmt, 1);
LineSectionSize += 1;
if (Row.BasicBlock) {
MS->EmitIntValue(dwarf::DW_LNS_set_basic_block, 1);
LineSectionSize += 1;
if (Row.PrologueEnd) {
MS->EmitIntValue(dwarf::DW_LNS_set_prologue_end, 1);
LineSectionSize += 1;
if (Row.EpilogueBegin) {
MS->EmitIntValue(dwarf::DW_LNS_set_epilogue_begin, 1);
LineSectionSize += 1;
int64_t LineDelta = int64_t(Row.Line) - LastLine;
if (!Row.EndSequence) {
MCDwarfLineAddr::Encode(*MC, Params, LineDelta, AddressDelta, EncodingOS);
LineSectionSize += EncodingBuffer.size();
Address = Row.Address;
LastLine = Row.Line;
} else {
if (LineDelta) {
MS->EmitIntValue(dwarf::DW_LNS_advance_line, 1);
LineSectionSize += 1 + getSLEB128Size(LineDelta);
if (AddressDelta) {
MS->EmitIntValue(dwarf::DW_LNS_advance_pc, 1);
LineSectionSize += 1 + getULEB128Size(AddressDelta);
MCDwarfLineAddr::Encode(*MC, Params, std::numeric_limits<int64_t>::max(),
0, EncodingOS);
LineSectionSize += EncodingBuffer.size();
Address = -1ULL;
LastLine = FileNum = IsStatement = 1;
RowsSinceLastSequence = Column = Isa = 0;
if (RowsSinceLastSequence) {
MCDwarfLineAddr::Encode(*MC, Params, std::numeric_limits<int64_t>::max(), 0,
LineSectionSize += EncodingBuffer.size();
/// Emit the pubnames or pubtypes section contribution for \p
/// Unit into \p Sec. The data is provided in \p Names.
void DwarfStreamer::emitPubSectionForUnit(
MCSection *Sec, StringRef SecName, const CompileUnit &Unit,
const std::vector<CompileUnit::AccelInfo> &Names) {
if (Names.empty())
// Start the dwarf pubnames section.
MCSymbol *BeginLabel = Asm->createTempSymbol("pub" + SecName + "_begin");
MCSymbol *EndLabel = Asm->createTempSymbol("pub" + SecName + "_end");
bool HeaderEmitted = false;
// Emit the pubnames for this compilation unit.
for (const auto &Name : Names) {
if (Name.SkipPubSection)
if (!HeaderEmitted) {
// Emit the header.
Asm->EmitLabelDifference(EndLabel, BeginLabel, 4); // Length
Asm->EmitInt16(dwarf::DW_PUBNAMES_VERSION); // Version
Asm->EmitInt32(Unit.getStartOffset()); // Unit offset
Asm->EmitInt32(Unit.getNextUnitOffset() - Unit.getStartOffset()); // Size
HeaderEmitted = true;
StringRef(, Name.Name.size() + 1));
if (!HeaderEmitted)
Asm->EmitInt32(0); // End marker.
/// Emit .debug_pubnames for \p Unit.
void DwarfStreamer::emitPubNamesForUnit(const CompileUnit &Unit) {
"names", Unit, Unit.getPubnames());
/// Emit .debug_pubtypes for \p Unit.
void DwarfStreamer::emitPubTypesForUnit(const CompileUnit &Unit) {
"types", Unit, Unit.getPubtypes());
/// Emit a CIE into the debug_frame section.
void DwarfStreamer::emitCIE(StringRef CIEBytes) {
FrameSectionSize += CIEBytes.size();
/// Emit a FDE into the debug_frame section. \p FDEBytes
/// contains the FDE data without the length, CIE offset and address
/// which will be replaced with the parameter values.
void DwarfStreamer::emitFDE(uint32_t CIEOffset, uint32_t AddrSize,
uint32_t Address, StringRef FDEBytes) {
MS->EmitIntValue(FDEBytes.size() + 4 + AddrSize, 4);
MS->EmitIntValue(CIEOffset, 4);
MS->EmitIntValue(Address, AddrSize);
FrameSectionSize += FDEBytes.size() + 8 + AddrSize;
namespace {
/// The core of the Dwarf linking logic.
/// The link of the dwarf information from the object files will be
/// driven by the selection of 'root DIEs', which are DIEs that
/// describe variables or functions that are present in the linked
/// binary (and thus have entries in the debug map). All the debug
/// information that will be linked (the DIEs, but also the line
/// tables, ranges, ...) is derived from that set of root DIEs.
/// The root DIEs are identified because they contain relocations that
/// correspond to a debug map entry at specific places (the low_pc for
/// a function, the location for a variable). These relocations are
/// called ValidRelocs in the DwarfLinker and are gathered as a very
/// first step when we start processing a DebugMapObject.
class DwarfLinker {
DwarfLinker(StringRef OutputFilename, const LinkOptions &Options)
: OutputFilename(OutputFilename), Options(Options),
BinHolder(Options.Verbose) {}
/// Link the contents of the DebugMap.
bool link(const DebugMap &);
void reportWarning(const Twine &Warning,
const DWARFDie *DIE = nullptr) const;
/// Called at the start of a debug object link.
void startDebugObject(DWARFContext &, DebugMapObject &);
/// Called at the end of a debug object link.
void endDebugObject();
/// Remembers the newest DWARF version we've seen in a unit.
void maybeUpdateMaxDwarfVersion(unsigned Version) {
if (MaxDwarfVersion < Version)
MaxDwarfVersion = Version;
/// Keeps track of relocations.
class RelocationManager {
struct ValidReloc {
uint32_t Offset;
uint32_t Size;
uint64_t Addend;
const DebugMapObject::DebugMapEntry *Mapping;
ValidReloc(uint32_t Offset, uint32_t Size, uint64_t Addend,
const DebugMapObject::DebugMapEntry *Mapping)
: Offset(Offset), Size(Size), Addend(Addend), Mapping(Mapping) {}
bool operator<(const ValidReloc &RHS) const {
return Offset < RHS.Offset;
DwarfLinker &Linker;
/// The valid relocations for the current DebugMapObject.
/// This vector is sorted by relocation offset.
std::vector<ValidReloc> ValidRelocs;
/// Index into ValidRelocs of the next relocation to
/// consider. As we walk the DIEs in acsending file offset and as
/// ValidRelocs is sorted by file offset, keeping this index
/// uptodate is all we have to do to have a cheap lookup during the
/// root DIE selection and during DIE cloning.
unsigned NextValidReloc = 0;
RelocationManager(DwarfLinker &Linker) : Linker(Linker) {}
bool hasValidRelocs() const { return !ValidRelocs.empty(); }
/// Reset the NextValidReloc counter.
void resetValidRelocs() { NextValidReloc = 0; }
/// \defgroup FindValidRelocations Translate debug map into a list
/// of relevant relocations
/// @{
bool findValidRelocsInDebugInfo(const object::ObjectFile &Obj,
const DebugMapObject &DMO);
bool findValidRelocs(const object::SectionRef &Section,
const object::ObjectFile &Obj,
const DebugMapObject &DMO);
void findValidRelocsMachO(const object::SectionRef &Section,
const object::MachOObjectFile &Obj,
const DebugMapObject &DMO);
/// @}
bool hasValidRelocation(uint32_t StartOffset, uint32_t EndOffset,
CompileUnit::DIEInfo &Info);
bool applyValidRelocs(MutableArrayRef<char> Data, uint32_t BaseOffset,
bool isLittleEndian);
/// \defgroup FindRootDIEs Find DIEs corresponding to debug map entries.
/// @{
/// Recursively walk the \p DIE tree and look for DIEs to
/// keep. Store that information in \p CU's DIEInfo.
/// The return value indicates whether the DIE is incomplete.
bool lookForDIEsToKeep(RelocationManager &RelocMgr, const DWARFDie &DIE,
const DebugMapObject &DMO, CompileUnit &CU,
unsigned Flags);
/// If this compile unit is really a skeleton CU that points to a
/// clang module, register it in ClangModules and return true.
/// A skeleton CU is a CU without children, a DW_AT_gnu_dwo_name
/// pointing to the module, and a DW_AT_gnu_dwo_id with the module
/// hash.
bool registerModuleReference(const DWARFDie &CUDie,
const DWARFUnit &Unit, DebugMap &ModuleMap,
unsigned Indent = 0);
/// Recursively add the debug info in this clang module .pcm
/// file (and all the modules imported by it in a bottom-up fashion)
/// to Units.
void loadClangModule(StringRef Filename, StringRef ModulePath,
StringRef ModuleName, uint64_t DwoId,
DebugMap &ModuleMap, unsigned Indent = 0);
/// Flags passed to DwarfLinker::lookForDIEsToKeep
enum TravesalFlags {
TF_Keep = 1 << 0, ///< Mark the traversed DIEs as kept.
TF_InFunctionScope = 1 << 1, ///< Current scope is a fucntion scope.
TF_DependencyWalk = 1 << 2, ///< Walking the dependencies of a kept DIE.
TF_ParentWalk = 1 << 3, ///< Walking up the parents of a kept DIE.
TF_ODR = 1 << 4, ///< Use the ODR whhile keeping dependants.
TF_SkipPC = 1 << 5, ///< Skip all location attributes.
/// Mark the passed DIE as well as all the ones it depends on as kept.
void keepDIEAndDependencies(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit::DIEInfo &MyInfo,
const DebugMapObject &DMO, CompileUnit &CU,
bool UseODR);
unsigned shouldKeepDIE(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit &Unit, CompileUnit::DIEInfo &MyInfo,
unsigned Flags);
unsigned shouldKeepVariableDIE(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit &Unit,
CompileUnit::DIEInfo &MyInfo, unsigned Flags);
unsigned shouldKeepSubprogramDIE(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit &Unit,
CompileUnit::DIEInfo &MyInfo,
unsigned Flags);
bool hasValidRelocation(uint32_t StartOffset, uint32_t EndOffset,
CompileUnit::DIEInfo &Info);
/// @}
/// \defgroup Linking Methods used to link the debug information
/// @{
class DIECloner {
DwarfLinker &Linker;
RelocationManager &RelocMgr;
/// Allocator used for all the DIEValue objects.
BumpPtrAllocator &DIEAlloc;
std::vector<std::unique_ptr<CompileUnit>> &CompileUnits;
LinkOptions Options;
DIECloner(DwarfLinker &Linker, RelocationManager &RelocMgr,
BumpPtrAllocator &DIEAlloc,
std::vector<std::unique_ptr<CompileUnit>> &CompileUnits,
LinkOptions &Options)
: Linker(Linker), RelocMgr(RelocMgr), DIEAlloc(DIEAlloc),
CompileUnits(CompileUnits), Options(Options) {}
/// Recursively clone \p InputDIE into an tree of DIE objects
/// where useless (as decided by lookForDIEsToKeep()) bits have been
/// stripped out and addresses have been rewritten according to the
/// debug map.
/// \param OutOffset is the offset the cloned DIE in the output
/// compile unit.
/// \param PCOffset (while cloning a function scope) is the offset
/// applied to the entry point of the function to get the linked address.
/// \param Die the output DIE to use, pass NULL to create one.
/// \returns the root of the cloned tree or null if nothing was selected.
DIE *cloneDIE(const DWARFDie &InputDIE, CompileUnit &U,
int64_t PCOffset, uint32_t OutOffset, unsigned Flags,
DIE *Die = nullptr);
/// Construct the output DIE tree by cloning the DIEs we
/// chose to keep above. If there are no valid relocs, then there's
/// nothing to clone/emit.
void cloneAllCompileUnits(DWARFContext &DwarfContext);
using AttributeSpec = DWARFAbbreviationDeclaration::AttributeSpec;
/// Information gathered and exchanged between the various
/// clone*Attributes helpers about the attributes of a particular DIE.
struct AttributesInfo {
/// Names.
const char *Name = nullptr;
const char *MangledName = nullptr;
/// Offsets in the string pool.
uint32_t NameOffset = 0;
uint32_t MangledNameOffset = 0;
/// Value of AT_low_pc in the input DIE
uint64_t OrigLowPc = std::numeric_limits<uint64_t>::max();
/// Value of AT_high_pc in the input DIE
uint64_t OrigHighPc = 0;
/// Offset to apply to PC addresses inside a function.
int64_t PCOffset = 0;
/// Does the DIE have a low_pc attribute?
bool HasLowPc = false;
/// Is this DIE only a declaration?
bool IsDeclaration = false;
AttributesInfo() = default;
/// Helper for cloneDIE.
unsigned cloneAttribute(DIE &Die,
const DWARFDie &InputDIE,
CompileUnit &U, const DWARFFormValue &Val,
const AttributeSpec AttrSpec, unsigned AttrSize,
AttributesInfo &AttrInfo);
/// Clone a string attribute described by \p AttrSpec and add
/// it to \p Die.
/// \returns the size of the new attribute.
unsigned cloneStringAttribute(DIE &Die, AttributeSpec AttrSpec,
const DWARFFormValue &Val,
const DWARFUnit &U);
/// Clone an attribute referencing another DIE and add
/// it to \p Die.
/// \returns the size of the new attribute.
cloneDieReferenceAttribute(DIE &Die,
const DWARFDie &InputDIE,
AttributeSpec AttrSpec, unsigned AttrSize,
const DWARFFormValue &Val, CompileUnit &Unit);
/// Clone an attribute referencing another DIE and add
/// it to \p Die.
/// \returns the size of the new attribute.
unsigned cloneBlockAttribute(DIE &Die, AttributeSpec AttrSpec,
const DWARFFormValue &Val, unsigned AttrSize);
/// Clone an attribute referencing another DIE and add
/// it to \p Die.
/// \returns the size of the new attribute.
unsigned cloneAddressAttribute(DIE &Die, AttributeSpec AttrSpec,
const DWARFFormValue &Val,
const CompileUnit &Unit,
AttributesInfo &Info);
/// Clone a scalar attribute and add it to \p Die.
/// \returns the size of the new attribute.
unsigned cloneScalarAttribute(DIE &Die,
const DWARFDie &InputDIE,
CompileUnit &U, AttributeSpec AttrSpec,
const DWARFFormValue &Val, unsigned AttrSize,
AttributesInfo &Info);
/// Get the potential name and mangled name for the entity
/// described by \p Die and store them in \Info if they are not
/// already there.
/// \returns is a name was found.
bool getDIENames(const DWARFDie &Die, AttributesInfo &Info);
/// Create a copy of abbreviation Abbrev.
void copyAbbrev(const DWARFAbbreviationDeclaration &Abbrev, bool hasODR);
/// Assign an abbreviation number to \p Abbrev
void AssignAbbrev(DIEAbbrev &Abbrev);
/// Compute and emit debug_ranges section for \p Unit, and
/// patch the attributes referencing it.
void patchRangesForUnit(const CompileUnit &Unit, DWARFContext &Dwarf) const;
/// Generate and emit the DW_AT_ranges attribute for a
/// compile_unit if it had one.
void generateUnitRanges(CompileUnit &Unit) const;
/// Extract the line tables fromt he original dwarf, extract
/// the relevant parts according to the linked function ranges and
/// emit the result in the debug_line section.
void patchLineTableForUnit(CompileUnit &Unit, DWARFContext &OrigDwarf);
/// Emit the accelerator entries for \p Unit.
void emitAcceleratorEntriesForUnit(CompileUnit &Unit);
/// Patch the frame info for an object file and emit it.
void patchFrameInfoForObject(const DebugMapObject &, DWARFContext &,
unsigned AddressSize);
/// FoldingSet that uniques the abbreviations.
FoldingSet<DIEAbbrev> AbbreviationsSet;
/// Storage for the unique Abbreviations.
/// This is passed to AsmPrinter::emitDwarfAbbrevs(), thus it cannot
/// be changed to a vecot of unique_ptrs.
std::vector<std::unique_ptr<DIEAbbrev>> Abbreviations;
/// DIELoc objects that need to be destructed (but not freed!).
std::vector<DIELoc *> DIELocs;
/// DIEBlock objects that need to be destructed (but not freed!).
std::vector<DIEBlock *> DIEBlocks;
/// Allocator used for all the DIEValue objects.
BumpPtrAllocator DIEAlloc;
/// @}
/// ODR Contexts for that link.
DeclContextTree ODRContexts;
/// \defgroup Helpers Various helper methods.
/// @{
bool createStreamer(const Triple &TheTriple, StringRef OutputFilename);
/// Attempt to load a debug object from disk.
ErrorOr<const object::ObjectFile &> loadObject(BinaryHolder &BinaryHolder,
DebugMapObject &Obj,
const DebugMap &Map);
/// @}
std::string OutputFilename;
LinkOptions Options;
BinaryHolder BinHolder;
std::unique_ptr<DwarfStreamer> Streamer;
uint64_t OutputDebugInfoSize;
/// A unique ID that identifies each compile unit.
unsigned UnitID;
unsigned MaxDwarfVersion = 0;
/// The units of the current debug map object.
std::vector<std::unique_ptr<CompileUnit>> Units;
/// The debug map object currently under consideration.
DebugMapObject *CurrentDebugObject;
/// The Dwarf string pool.
NonRelocatableStringpool StringPool;
/// This map is keyed by the entry PC of functions in that
/// debug object and the associated value is a pair storing the
/// corresponding end PC and the offset to apply to get the linked
/// address.
/// See startDebugObject() for a more complete description of its use.
std::map<uint64_t, std::pair<uint64_t, int64_t>> Ranges;
/// The CIEs that have been emitted in the output
/// section. The actual CIE data serves a the key to this StringMap,
/// this takes care of comparing the semantics of CIEs defined in
/// different object files.
StringMap<uint32_t> EmittedCIEs;
/// Offset of the last CIE that has been emitted in the output
/// debug_frame section.
uint32_t LastCIEOffset = 0;
/// Mapping the PCM filename to the DwoId.
StringMap<uint64_t> ClangModules;
bool ModuleCacheHintDisplayed = false;
bool ArchiveHintDisplayed = false;
} // end anonymous namespace
/// Similar to DWARFUnitSection::getUnitForOffset(), but returning our
/// CompileUnit object instead.
static CompileUnit *getUnitForOffset(
std::vector<std::unique_ptr<CompileUnit>> &Units, unsigned Offset) {
auto CU =
std::upper_bound(Units.begin(), Units.end(), Offset,
[](uint32_t LHS, const std::unique_ptr<CompileUnit> &RHS) {
return LHS < RHS->getOrigUnit().getNextUnitOffset();
return CU != Units.end() ? CU->get() : nullptr;
/// Resolve the DIE attribute reference that has been
/// extracted in \p RefValue. The resulting DIE migh be in another
/// CompileUnit which is stored into \p ReferencedCU.
/// \returns null if resolving fails for any reason.
static DWARFDie resolveDIEReference(
const DwarfLinker &Linker, std::vector<std::unique_ptr<CompileUnit>> &Units,
const DWARFFormValue &RefValue, const DWARFUnit &Unit,
const DWARFDie &DIE, CompileUnit *&RefCU) {
uint64_t RefOffset = *RefValue.getAsReference();
if ((RefCU = getUnitForOffset(Units, RefOffset)))
if (const auto RefDie = RefCU->getOrigUnit().getDIEForOffset(RefOffset)) {
// In a file with broken references, an attribute might point to a NULL
// DIE.
return RefDie;
Linker.reportWarning("could not find referenced DIE", &DIE);
return DWARFDie();
/// \returns whether the passed \a Attr type might contain a DIE
/// reference suitable for ODR uniquing.
static bool isODRAttribute(uint16_t Attr) {
switch (Attr) {
return false;
case dwarf::DW_AT_type:
case dwarf::DW_AT_containing_type:
case dwarf::DW_AT_specification:
case dwarf::DW_AT_abstract_origin:
case dwarf::DW_AT_import:
return true;
llvm_unreachable("Improper attribute.");
/// Set the last DIE/CU a context was seen in and, possibly invalidate
/// the context if it is ambiguous.
/// In the current implementation, we don't handle overloaded
/// functions well, because the argument types are not taken into
/// account when computing the DeclContext tree.
/// Some of this is mitigated byt using mangled names that do contain
/// the arguments types, but sometimes (eg. with function templates)
/// we don't have that. In that case, just do not unique anything that
/// refers to the contexts we are not able to distinguish.
/// If a context that is not a namespace appears twice in the same CU,
/// we know it is ambiguous. Make it invalid.
bool DeclContext::setLastSeenDIE(CompileUnit &U,
const DWARFDie &Die) {
if (LastSeenCompileUnitID == U.getUniqueID()) {
DWARFUnit &OrigUnit = U.getOrigUnit();
uint32_t FirstIdx = OrigUnit.getDIEIndex(LastSeenDIE);
U.getInfo(FirstIdx).Ctxt = nullptr;
return false;
LastSeenCompileUnitID = U.getUniqueID();
LastSeenDIE = Die;
return true;
PointerIntPair<DeclContext *, 1> DeclContextTree::getChildDeclContext(
DeclContext &Context, const DWARFDie &DIE, CompileUnit &U,
NonRelocatableStringpool &StringPool, bool InClangModule) {
unsigned Tag = DIE.getTag();
// FIXME: dsymutil-classic compat: We should bail out here if we
// have a specification or an abstract_origin. We will get the
// parent context wrong here.
switch (Tag) {
// By default stop gathering child contexts.
return PointerIntPair<DeclContext *, 1>(nullptr);
case dwarf::DW_TAG_module:
case dwarf::DW_TAG_compile_unit:
return PointerIntPair<DeclContext *, 1>(&Context);
case dwarf::DW_TAG_subprogram:
// Do not unique anything inside CU local functions.
if ((Context.getTag() == dwarf::DW_TAG_namespace ||
Context.getTag() == dwarf::DW_TAG_compile_unit) &&
!dwarf::toUnsigned(DIE.find(dwarf::DW_AT_external), 0))
return PointerIntPair<DeclContext *, 1>(nullptr);
case dwarf::DW_TAG_member:
case dwarf::DW_TAG_namespace:
case dwarf::DW_TAG_structure_type:
case dwarf::DW_TAG_class_type:
case dwarf::DW_TAG_union_type:
case dwarf::DW_TAG_enumeration_type:
case dwarf::DW_TAG_typedef:
// Artificial things might be ambiguous, because they might be
// created on demand. For example implicitely defined constructors
// are ambiguous because of the way we identify contexts, and they
// won't be generated everytime everywhere.
if (dwarf::toUnsigned(DIE.find(dwarf::DW_AT_artificial), 0))
return PointerIntPair<DeclContext *, 1>(nullptr);
const char *Name = DIE.getName(DINameKind::LinkageName);
const char *ShortName = DIE.getName(DINameKind::ShortName);
StringRef NameRef;
StringRef ShortNameRef;
StringRef FileRef;
if (Name)
NameRef = StringPool.internString(Name);
else if (Tag == dwarf::DW_TAG_namespace)
// FIXME: For dsymutil-classic compatibility. I think uniquing
// within anonymous namespaces is wrong. There is no ODR guarantee
// there.
NameRef = StringPool.internString("(anonymous namespace)");
if (ShortName && ShortName != Name)
ShortNameRef = StringPool.internString(ShortName);
ShortNameRef = NameRef;
if (Tag != dwarf::DW_TAG_class_type && Tag != dwarf::DW_TAG_structure_type &&
Tag != dwarf::DW_TAG_union_type &&
Tag != dwarf::DW_TAG_enumeration_type && NameRef.empty())
return PointerIntPair<DeclContext *, 1>(nullptr);
unsigned Line = 0;
unsigned ByteSize = std::numeric_limits<uint32_t>::max();
if (!InClangModule) {
// Gather some discriminating data about the DeclContext we will be
// creating: File, line number and byte size. This shouldn't be
// necessary, because the ODR is just about names, but given that we
// do some approximations with overloaded functions and anonymous
// namespaces, use these additional data points to make the process
// safer. This is disabled for clang modules, because forward
// declarations of module-defined types do not have a file and line.
ByteSize = dwarf::toUnsigned(DIE.find(dwarf::DW_AT_byte_size),
if (Tag != dwarf::DW_TAG_namespace || !Name) {
if (unsigned FileNum = dwarf::toUnsigned(DIE.find(dwarf::DW_AT_decl_file), 0)) {
if (const auto *LT = U.getOrigUnit().getContext().getLineTableForUnit(
&U.getOrigUnit())) {
// FIXME: dsymutil-classic compatibility. I'd rather not
// unique anything in anonymous namespaces, but if we do, then
// verify that the file and line correspond.
if (!Name && Tag == dwarf::DW_TAG_namespace)
FileNum = 1;
// FIXME: Passing U.getOrigUnit().getCompilationDir()
// instead of "" would allow more uniquing, but for now, do
// it this way to match dsymutil-classic.
if (LT->hasFileAtIndex(FileNum)) {
Line = dwarf::toUnsigned(DIE.find(dwarf::DW_AT_decl_line), 0);
// Cache the resolved paths, because calling realpath is expansive.
StringRef ResolvedPath = U.getResolvedPath(FileNum);
if (!ResolvedPath.empty()) {
FileRef = ResolvedPath;
} else {
std::string File;
bool gotFileName =
LT->getFileNameByIndex(FileNum, "",
assert(gotFileName && "Must get file name from line table");
char RealPath[PATH_MAX + 1];
RealPath[PATH_MAX] = 0;
if (::realpath(File.c_str(), RealPath))
File = RealPath;
FileRef = StringPool.internString(File);
U.setResolvedPath(FileNum, FileRef);
if (!Line && NameRef.empty())
return PointerIntPair<DeclContext *, 1>(nullptr);
// We hash NameRef, which is the mangled name, in order to get most
// overloaded functions resolve correctly.
// Strictly speaking, hashing the Tag is only necessary for a
// DW_TAG_module, to prevent uniquing of a module and a namespace
// with the same name.
// FIXME: dsymutil-classic won't unique the same type presented
// once as a struct and once as a class. Using the Tag in the fully
// qualified name hash to get the same effect.
unsigned Hash = hash_combine(Context.getQualifiedNameHash(), Tag, NameRef);
// FIXME: dsymutil-classic compatibility: when we don't have a name,
// use the filename.
if (Tag == dwarf::DW_TAG_namespace && NameRef == "(anonymous namespace)")
Hash = hash_combine(Hash, FileRef);
// Now look if this context already exists.
DeclContext Key(Hash, Line, ByteSize, Tag, NameRef, FileRef, Context);
auto ContextIter = Contexts.find(&Key);
if (ContextIter == Contexts.end()) {
// The context wasn't found.
bool Inserted;
DeclContext *NewContext =
new (Allocator) DeclContext(Hash, Line, ByteSize, Tag, NameRef, FileRef,
Context, DIE, U.getUniqueID());
std::tie(ContextIter, Inserted) = Contexts.insert(NewContext);
assert(Inserted && "Failed to insert DeclContext");
} else if (Tag != dwarf::DW_TAG_namespace &&
!(*ContextIter)->setLastSeenDIE(U, DIE)) {
// The context was found, but it is ambiguous with another context
// in the same file. Mark it invalid.
return PointerIntPair<DeclContext *, 1>(*ContextIter, /* Invalid= */ 1);
assert(ContextIter != Contexts.end());
// FIXME: dsymutil-classic compatibility. Union types aren't
// uniques, but their children might be.
if ((Tag == dwarf::DW_TAG_subprogram &&
Context.getTag() != dwarf::DW_TAG_structure_type &&
Context.getTag() != dwarf::DW_TAG_class_type) ||
(Tag == dwarf::DW_TAG_union_type))
return PointerIntPair<DeclContext *, 1>(*ContextIter, /* Invalid= */ 1);
return PointerIntPair<DeclContext *, 1>(*ContextIter);
bool DwarfLinker::DIECloner::getDIENames(const DWARFDie &Die,
AttributesInfo &Info) {
// FIXME: a bit wasteful as the first getName might return the
// short name.
if (!Info.MangledName &&
(Info.MangledName = Die.getName(DINameKind::LinkageName)))
Info.MangledNameOffset =
if (!Info.Name && (Info.Name = Die.getName(DINameKind::ShortName)))
Info.NameOffset = Linker.StringPool.getStringOffset(Info.Name);
return Info.Name || Info.MangledName;
/// Report a warning to the user, optionaly including
/// information about a specific \p DIE related to the warning.
void DwarfLinker::reportWarning(const Twine &Warning,
const DWARFDie *DIE) const {
StringRef Context = "<debug map>";
if (CurrentDebugObject)
Context = CurrentDebugObject->getObjectFilename();
warn(Warning, Context);
if (!Options.Verbose || !DIE)
DIDumpOptions DumpOpts;
DumpOpts.RecurseDepth = 0;
DumpOpts.Verbose = Options.Verbose;
errs() << " in DIE:\n";
DIE->dump(errs(), 6 /* Indent */, DumpOpts);
bool DwarfLinker::createStreamer(const Triple &TheTriple,
StringRef OutputFilename) {
if (Options.NoOutput)
return true;
Streamer = llvm::make_unique<DwarfStreamer>();
return Streamer->init(TheTriple, OutputFilename);
/// Recursive helper to build the global DeclContext information and
/// gather the child->parent relationships in the original compile unit.
/// \return true when this DIE and all of its children are only
/// forward declarations to types defined in external clang modules
/// (i.e., forward declarations that are children of a DW_TAG_module).
static bool analyzeContextInfo(const DWARFDie &DIE,
unsigned ParentIdx, CompileUnit &CU,
DeclContext *CurrentDeclContext,
NonRelocatableStringpool &StringPool,
DeclContextTree &Contexts,
bool InImportedModule = false) {
unsigned MyIdx = CU.getOrigUnit().getDIEIndex(DIE);
CompileUnit::DIEInfo &Info = CU.getInfo(MyIdx);
// Clang imposes an ODR on modules(!) regardless of the language:
// "The module-id should consist of only a single identifier,
// which provides the name of the module being defined. Each
// module shall have a single definition."
// This does not extend to the types inside the modules:
// "[I]n C, this implies that if two structs are defined in
// different submodules with the same name, those two types are
// distinct types (but may be compatible types if their
// definitions match)."
// We treat non-C++ modules like namespaces for this reason.
if (DIE.getTag() == dwarf::DW_TAG_module && ParentIdx == 0 &&
dwarf::toString(DIE.find(dwarf::DW_AT_name), "") !=
CU.getClangModuleName()) {
InImportedModule = true;
Info.ParentIdx = ParentIdx;
bool InClangModule = CU.isClangModule() || InImportedModule;
if (CU.hasODR() || InClangModule) {
if (CurrentDeclContext) {
auto PtrInvalidPair = Contexts.getChildDeclContext(
*CurrentDeclContext, DIE, CU, StringPool, InClangModule);
CurrentDeclContext = PtrInvalidPair.getPointer();
Info.Ctxt =
PtrInvalidPair.getInt() ? nullptr : PtrInvalidPair.getPointer();
if (Info.Ctxt)
} else
Info.Ctxt = CurrentDeclContext = nullptr;
Info.Prune = InImportedModule;
if (DIE.hasChildren())
for (auto Child: DIE.children())
Info.Prune &= analyzeContextInfo(Child, MyIdx, CU, CurrentDeclContext,
StringPool, Contexts, InImportedModule);
// Prune this DIE if it is either a forward declaration inside a
// DW_TAG_module or a DW_TAG_module that contains nothing but
// forward declarations.
Info.Prune &=
(DIE.getTag() == dwarf::DW_TAG_module) ||
dwarf::toUnsigned(DIE.find(dwarf::DW_AT_declaration), 0);
// Don't prune it if there is no definition for the DIE.
Info.Prune &= Info.Ctxt && Info.Ctxt->getCanonicalDIEOffset();
return Info.Prune;
static bool dieNeedsChildrenToBeMeaningful(uint32_t Tag) {
switch (Tag) {
return false;
case dwarf::DW_TAG_subprogram:
case dwarf::DW_TAG_lexical_block:
case dwarf::DW_TAG_subroutine_type:
case dwarf::DW_TAG_structure_type:
case dwarf::DW_TAG_class_type:
case dwarf::DW_TAG_union_type:
return true;
llvm_unreachable("Invalid Tag");
void DwarfLinker::startDebugObject(DWARFContext &Dwarf, DebugMapObject &Obj) {
// Iterate over the debug map entries and put all the ones that are
// functions (because they have a size) into the Ranges map. This
// map is very similar to the FunctionRanges that are stored in each
// unit, with 2 notable differences:
// - obviously this one is global, while the other ones are per-unit.
// - this one contains not only the functions described in the DIE
// tree, but also the ones that are only in the debug map.
// The latter information is required to reproduce dsymutil's logic
// while linking line tables. The cases where this information
// matters look like bugs that need to be investigated, but for now
// we need to reproduce dsymutil's behavior.
// FIXME: Once we understood exactly if that information is needed,
// maybe totally remove this (or try to use it to do a real
// -gline-tables-only on Darwin.
for (const auto &Entry : Obj.symbols()) {
const auto &Mapping = Entry.getValue();
if (Mapping.Size && Mapping.ObjectAddress)
Ranges[*Mapping.ObjectAddress] = std::make_pair(
*Mapping.ObjectAddress + Mapping.Size,
int64_t(Mapping.BinaryAddress) - *Mapping.ObjectAddress);
void DwarfLinker::endDebugObject() {
for (auto I = DIEBlocks.begin(), E = DIEBlocks.end(); I != E; ++I)
for (auto I = DIELocs.begin(), E = DIELocs.end(); I != E; ++I)
static bool isMachOPairedReloc(uint64_t RelocType, uint64_t Arch) {
switch (Arch) {
case Triple::x86:
return RelocType == MachO::GENERIC_RELOC_SECTDIFF ||
case Triple::x86_64:
return RelocType == MachO::X86_64_RELOC_SUBTRACTOR;
case Triple::arm:
case Triple::thumb:
return RelocType == MachO::ARM_RELOC_SECTDIFF ||
RelocType == MachO::ARM_RELOC_HALF ||
case Triple::aarch64:
return RelocType == MachO::ARM64_RELOC_SUBTRACTOR;
return false;
/// Iterate over the relocations of the given \p Section and
/// store the ones that correspond to debug map entries into the
/// ValidRelocs array.
void DwarfLinker::RelocationManager::
findValidRelocsMachO(const object::SectionRef &Section,
const object::MachOObjectFile &Obj,
const DebugMapObject &DMO) {
StringRef Contents;
DataExtractor Data(Contents, Obj.isLittleEndian(), 0);
bool SkipNext = false;
for (const object::RelocationRef &Reloc : Section.relocations()) {
if (SkipNext) {
SkipNext = false;
object::DataRefImpl RelocDataRef = Reloc.getRawDataRefImpl();
MachO::any_relocation_info MachOReloc = Obj.getRelocation(RelocDataRef);
if (isMachOPairedReloc(Obj.getAnyRelocationType(MachOReloc),
Obj.getArch())) {
SkipNext = true;
Linker.reportWarning(" unsupported relocation in debug_info section.");
unsigned RelocSize = 1 << Obj.getAnyRelocationLength(MachOReloc);
uint64_t Offset64 = Reloc.getOffset();
if ((RelocSize != 4 && RelocSize != 8)) {
Linker.reportWarning(" unsupported relocation in debug_info section.");
uint32_t Offset = Offset64;
// Mach-o uses REL relocations, the addend is at the relocation offset.
uint64_t Addend = Data.getUnsigned(&Offset, RelocSize);
uint64_t SymAddress;
int64_t SymOffset;
if (Obj.isRelocationScattered(MachOReloc)) {
// The address of the base symbol for scattered relocations is
// stored in the reloc itself. The actual addend will store the
// base address plus the offset.
SymAddress = Obj.getScatteredRelocationValue(MachOReloc);
SymOffset = int64_t(Addend) - SymAddress;
} else {
SymAddress = Addend;
SymOffset = 0;
auto Sym = Reloc.getSymbol();
if (Sym != Obj.symbol_end()) {
Expected<StringRef> SymbolName = Sym->getName();
if (!SymbolName) {
Linker.reportWarning("error getting relocation symbol name.");
if (const auto *Mapping = DMO.lookupSymbol(*SymbolName))
ValidRelocs.emplace_back(Offset64, RelocSize, Addend, Mapping);
} else if (const auto *Mapping = DMO.lookupObjectAddress(SymAddress)) {
// Do not store the addend. The addend was the address of the
// symbol in the object file, the address in the binary that is
// stored in the debug map doesn't need to be offseted.
ValidRelocs.emplace_back(Offset64, RelocSize, SymOffset, Mapping);
/// Dispatch the valid relocation finding logic to the
/// appropriate handler depending on the object file format.
bool DwarfLinker::RelocationManager::findValidRelocs(
const object::SectionRef &Section, const object::ObjectFile &Obj,
const DebugMapObject &DMO) {
// Dispatch to the right handler depending on the file type.
if (auto *MachOObj = dyn_cast<object::MachOObjectFile>(&Obj))
findValidRelocsMachO(Section, *MachOObj, DMO);
Linker.reportWarning(Twine("unsupported object file type: ") +
if (ValidRelocs.empty())
return false;
// Sort the relocations by offset. We will walk the DIEs linearly in
// the file, this allows us to just keep an index in the relocation
// array that we advance during our walk, rather than resorting to
// some associative container. See DwarfLinker::NextValidReloc.
std::sort(ValidRelocs.begin(), ValidRelocs.end());
return true;
/// Look for relocations in the debug_info section that match
/// entries in the debug map. These relocations will drive the Dwarf
/// link by indicating which DIEs refer to symbols present in the
/// linked binary.
/// \returns wether there are any valid relocations in the debug info.
bool DwarfLinker::RelocationManager::
findValidRelocsInDebugInfo(const object::ObjectFile &Obj,
const DebugMapObject &DMO) {
// Find the debug_info section.
for (const object::SectionRef &Section : Obj.sections()) {
StringRef SectionName;
SectionName = SectionName.substr(SectionName.find_first_not_of("._"));
if (SectionName != "debug_info")
return findValidRelocs(Section, Obj, DMO);
return false;
/// Checks that there is a relocation against an actual debug
/// map entry between \p StartOffset and \p NextOffset.
/// This function must be called with offsets in strictly ascending
/// order because it never looks back at relocations it already 'went past'.
/// \returns true and sets Info.InDebugMap if it is the case.
bool DwarfLinker::RelocationManager::
hasValidRelocation(uint32_t StartOffset, uint32_t EndOffset,
CompileUnit::DIEInfo &Info) {
assert(NextValidReloc == 0 ||
StartOffset > ValidRelocs[NextValidReloc - 1].Offset);
if (NextValidReloc >= ValidRelocs.size())
return false;
uint64_t RelocOffset = ValidRelocs[NextValidReloc].Offset;
// We might need to skip some relocs that we didn't consider. For
// example the high_pc of a discarded DIE might contain a reloc that
// is in the list because it actually corresponds to the start of a
// function that is in the debug map.
while (RelocOffset < StartOffset && NextValidReloc < ValidRelocs.size() - 1)
RelocOffset = ValidRelocs[++NextValidReloc].Offset;
if (RelocOffset < StartOffset || RelocOffset >= EndOffset)
return false;
const auto &ValidReloc = ValidRelocs[NextValidReloc++];
const auto &Mapping = ValidReloc.Mapping->getValue();
uint64_t ObjectAddress = Mapping.ObjectAddress
? uint64_t(*Mapping.ObjectAddress)
: std::numeric_limits<uint64_t>::max();
if (Linker.Options.Verbose)
outs() << "Found valid debug map entry: " << ValidReloc.Mapping->getKey()
<< " " << format("\t%016" PRIx64 " => %016" PRIx64, ObjectAddress,
Info.AddrAdjust = int64_t(Mapping.BinaryAddress) + ValidReloc.Addend;
if (Mapping.ObjectAddress)
Info.AddrAdjust -= ObjectAddress;
Info.InDebugMap = true;
return true;
/// Get the starting and ending (exclusive) offset for the
/// attribute with index \p Idx descibed by \p Abbrev. \p Offset is
/// supposed to point to the position of the first attribute described
/// by \p Abbrev.
/// \return [StartOffset, EndOffset) as a pair.
static std::pair<uint32_t, uint32_t>
getAttributeOffsets(const DWARFAbbreviationDeclaration *Abbrev, unsigned Idx,
unsigned Offset, const DWARFUnit &Unit) {
DataExtractor Data = Unit.getDebugInfoExtractor();
for (unsigned i = 0; i < Idx; ++i)
DWARFFormValue::skipValue(Abbrev->getFormByIndex(i), Data, &Offset,
uint32_t End = Offset;
DWARFFormValue::skipValue(Abbrev->getFormByIndex(Idx), Data, &End,
return std::make_pair(Offset, End);
/// Check if a variable describing DIE should be kept.
/// \returns updated TraversalFlags.
unsigned DwarfLinker::shouldKeepVariableDIE(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit &Unit,
CompileUnit::DIEInfo &MyInfo,
unsigned Flags) {
const auto *Abbrev = DIE.getAbbreviationDeclarationPtr();
// Global variables with constant value can always be kept.
if (!(Flags & TF_InFunctionScope) &&
Abbrev->findAttributeIndex(dwarf::DW_AT_const_value)) {
MyInfo.InDebugMap = true;
return Flags | TF_Keep;
Optional<uint32_t> LocationIdx =
if (!LocationIdx)
return Flags;
uint32_t Offset = DIE.getOffset() + getULEB128Size(Abbrev->getCode());
const DWARFUnit &OrigUnit = Unit.getOrigUnit();
uint32_t LocationOffset, LocationEndOffset;
std::tie(LocationOffset, LocationEndOffset) =
getAttributeOffsets(Abbrev, *LocationIdx, Offset, OrigUnit);
// See if there is a relocation to a valid debug map entry inside
// this variable's location. The order is important here. We want to
// always check in the variable has a valid relocation, so that the
// DIEInfo is filled. However, we don't want a static variable in a
// function to force us to keep the enclosing function.
if (!RelocMgr.hasValidRelocation(LocationOffset, LocationEndOffset, MyInfo) ||
(Flags & TF_InFunctionScope))
return Flags;
if (Options.Verbose) {
DIDumpOptions DumpOpts;
DumpOpts.RecurseDepth = 0;
DumpOpts.Verbose = Options.Verbose;
DIE.dump(outs(), 8 /* Indent */, DumpOpts);
return Flags | TF_Keep;
/// Check if a function describing DIE should be kept.
/// \returns updated TraversalFlags.
unsigned DwarfLinker::shouldKeepSubprogramDIE(
RelocationManager &RelocMgr,
const DWARFDie &DIE, CompileUnit &Unit,
CompileUnit::DIEInfo &MyInfo, unsigned Flags) {
const auto *Abbrev = DIE.getAbbreviationDeclarationPtr();
Flags |= TF_InFunctionScope;
Optional<uint32_t> LowPcIdx = Abbrev->findAttributeIndex(dwarf::DW_AT_low_pc);
if (!LowPcIdx)
return Flags;
uint32_t Offset = DIE.getOffset() + getULEB128Size(Abbrev->getCode());
const DWARFUnit &OrigUnit = Unit.getOrigUnit();
uint32_t LowPcOffset, LowPcEndOffset;
std::tie(LowPcOffset, LowPcEndOffset) =
getAttributeOffsets(Abbrev, *LowPcIdx, Offset, OrigUnit);
auto LowPc = dwarf::toAddress(DIE.find(dwarf::DW_AT_low_pc));
assert(LowPc.hasValue() && "low_pc attribute is not an address.");
if (!LowPc ||
!RelocMgr.hasValidRelocation(LowPcOffset, LowPcEndOffset, MyInfo))
return Flags;
if (Options.Verbose) {
DIDumpOptions DumpOpts;
DumpOpts.RecurseDepth = 0;
DumpOpts.Verbose = Options.Verbose;
DIE.dump(outs(), 8 /* Indent */, DumpOpts);
Flags |= TF_Keep;
Optional<uint64_t> HighPc = DIE.getHighPC(*LowPc);
if (!HighPc) {
reportWarning("Function without high_pc. Range will be discarded.\n",
return Flags;
// Replace the debug map range with a more accurate one.
Ranges[*LowPc] = std::make_pair(*HighPc, MyInfo.AddrAdjust);
Unit.addFunctionRange(*LowPc, *HighPc, MyInfo.AddrAdjust);
return Flags;
/// Check if a DIE should be kept.
/// \returns updated TraversalFlags.
unsigned DwarfLinker::shouldKeepDIE(RelocationManager &RelocMgr,
const DWARFDie &DIE,
CompileUnit &Unit,
CompileUnit::DIEInfo &MyInfo,
unsigned Flags) {
switch (DIE.getTag()) {
case dwarf::DW_TAG_constant:
case dwarf::DW_TAG_variable:
return shouldKeepVariableDIE(RelocMgr, DIE, Unit, MyInfo, Flags);
case dwarf::DW_TAG_subprogram:
return shouldKeepSubprogramDIE(RelocMgr, DIE, Unit, MyInfo, Flags);
case dwarf::DW_TAG_imported_module:
case dwarf::DW_TAG_imported_declaration:
case dwarf::DW_TAG_imported_unit:
// We always want to keep these.
return Flags | TF_Keep;
return Flags;
/// Mark the passed DIE as well as all the ones it depends on
/// as kept.
/// This function is called by lookForDIEsToKeep on DIEs that are
/// newly discovered to be needed in the link. It recursively calls
/// back to lookForDIEsToKeep while adding TF_DependencyWalk to the
/// TraversalFlags to inform it that it's not doing the primary DIE
/// tree walk.
void DwarfLinker::keepDIEAndDependencies(RelocationManager &RelocMgr,
const DWARFDie &Die,
CompileUnit::DIEInfo &MyInfo,
const DebugMapObject &DMO,
CompileUnit &CU, bool UseODR) {
DWARFUnit &Unit = CU.getOrigUnit();
MyInfo.Keep = true;
// We're looking for incomplete types.
MyInfo.Incomplete = Die.getTag() != dwarf::DW_TAG_subprogram &&
Die.getTag() != dwarf::DW_TAG_member &&
dwarf::toUnsigned(Die.find(dwarf::DW_AT_declaration), 0);
// First mark all the parent chain as kept.
unsigned AncestorIdx = MyInfo.ParentIdx;
while (!CU.getInfo(AncestorIdx).Keep) {
unsigned ODRFlag = UseODR ? TF_ODR : 0;
lookForDIEsToKeep(RelocMgr, Unit.getDIEAtIndex(AncestorIdx), DMO, CU,
TF_ParentWalk | TF_Keep | TF_DependencyWalk | ODRFlag);
AncestorIdx = CU.getInfo(AncestorIdx).ParentIdx;
// Then we need to mark all the DIEs referenced by this DIE's
// attributes as kept.
DWARFDataExtractor Data = Unit.getDebugInfoExtractor();
const auto *Abbrev = Die.getAbbreviationDeclarationPtr();
uint32_t Offset = Die.getOffset() + getULEB128Size(Abbrev->getCode());
// Mark all DIEs referenced through attributes as kept.
for (const auto &AttrSpec : Abbrev->attributes()) {
DWARFFormValue Val(AttrSpec.Form);
if (!Val.isFormClass(DWARFFormValue::FC_Reference)) {
DWARFFormValue::skipValue(AttrSpec.Form, Data, &Offset,
Val.extractValue(Data, &Offset, &Unit);
CompileUnit *ReferencedCU;
if (auto RefDie =
resolveDIEReference(*this, Units, Val, Unit, Die, ReferencedCU)) {
uint32_t RefIdx = ReferencedCU->getOrigUnit().getDIEIndex(RefDie);
CompileUnit::DIEInfo &Info = ReferencedCU->getInfo(RefIdx);
bool IsModuleRef = Info.Ctxt && Info.Ctxt->getCanonicalDIEOffset() &&
// If the referenced DIE has a DeclContext that has already been
// emitted, then do not keep the one in this CU. We'll link to
// the canonical DIE in cloneDieReferenceAttribute.
// FIXME: compatibility with dsymutil-classic. UseODR shouldn't
// be necessary and could be advantageously replaced by
// ReferencedCU->hasODR() && CU.hasODR().
// FIXME: compatibility with dsymutil-classic. There is no
// reason not to unique ref_addr references.
if (AttrSpec.Form != dwarf::DW_FORM_ref_addr && (UseODR || IsModuleRef) &&
Info.Ctxt &&
Info.Ctxt != ReferencedCU->getInfo(Info.ParentIdx).Ctxt &&
Info.Ctxt->getCanonicalDIEOffset() && isODRAttribute(AttrSpec.Attr))
// Keep a module forward declaration if there is no definition.
if (!(isODRAttribute(AttrSpec.Attr) && Info.Ctxt &&
Info.Prune = false;
unsigned ODRFlag = UseODR ? TF_ODR : 0;
lookForDIEsToKeep(RelocMgr, RefDie, DMO, *ReferencedCU,
TF_Keep | TF_DependencyWalk | ODRFlag);
// The incomplete property is propagated if the current DIE is complete
// but references an incomplete DIE.
if (Info.Incomplete && !MyInfo.Incomplete &&
(Die.getTag() == dwarf::DW_TAG_typedef ||
Die.getTag() == dwarf::DW_TAG_member ||
Die.getTag() == dwarf::DW_TAG_reference_type ||
Die.getTag() == dwarf::DW_TAG_ptr_to_member_type ||
Die.getTag() == dwarf::DW_TAG_pointer_type))
MyInfo.Incomplete = true;
/// Recursively walk the \p DIE tree and look for DIEs to
/// keep. Store that information in \p CU's DIEInfo.
/// This function is the entry point of the DIE selection
/// algorithm. It is expected to walk the DIE tree in file order and
/// (though the mediation of its helper) call hasValidRelocation() on
/// each DIE that might be a 'root DIE' (See DwarfLinker class
/// comment).
/// While walking the dependencies of root DIEs, this function is
/// also called, but during these dependency walks the file order is
/// not respected. The TF_DependencyWalk flag tells us which kind of
/// traversal we are currently doing.
/// The return value indicates whether the DIE is incomplete.
bool DwarfLinker::lookForDIEsToKeep(RelocationManager &RelocMgr,
const DWARFDie &Die,
const DebugMapObject &DMO, CompileUnit &CU,
unsigned Flags) {
unsigned Idx = CU.getOrigUnit().getDIEIndex(Die);
CompileUnit::DIEInfo &MyInfo = CU.getInfo(Idx);
bool AlreadyKept = MyInfo.Keep;
if (MyInfo.Prune)
return true;
// If the Keep flag is set, we are marking a required DIE's
// dependencies. If our target is already marked as kept, we're all
// set.
if ((Flags & TF_DependencyWalk) && AlreadyKept)
return MyInfo.Incomplete;
// We must not call shouldKeepDIE while called from keepDIEAndDependencies,
// because it would screw up the relocation finding logic.
if (!(Flags & TF_DependencyWalk))
Flags = shouldKeepDIE(RelocMgr, Die, CU, MyInfo, Flags);
// If it is a newly kept DIE mark it as well as all its dependencies as kept.
if (!AlreadyKept && (Flags & TF_Keep)) {
bool UseOdr = (Flags & TF_DependencyWalk) ? (Flags & TF_ODR) : CU.hasODR();
keepDIEAndDependencies(RelocMgr, Die, MyInfo, DMO, CU, UseOdr);
// The TF_ParentWalk flag tells us that we are currently walking up
// the parent chain of a required DIE, and we don't want to mark all
// the children of the parents as kept (consider for example a
// DW_TAG_namespace node in the parent chain). There are however a
// set of DIE types for which we want to ignore that directive and still
// walk their children.
if (dieNeedsChildrenToBeMeaningful(Die.getTag()))
Flags &= ~TF_ParentWalk;
if (!Die.hasChildren() || (Flags & TF_ParentWalk))
return MyInfo.Incomplete;
bool Incomplete = false;
for (auto Child : Die.children()) {
Incomplete |= lookForDIEsToKeep(RelocMgr, Child, DMO, CU, Flags);
// If any of the members are incomplete we propagate the incompleteness.
if (!MyInfo.Incomplete && Incomplete &&
(Die.getTag() == dwarf::DW_TAG_structure_type ||
Die.getTag() == dwarf::DW_TAG_class_type))
MyInfo.Incomplete = true;
return MyInfo.Incomplete;
/// Assign an abbreviation numer to \p Abbrev.
/// Our DIEs get freed after every DebugMapObject has been processed,
/// thus the FoldingSet we use to unique DIEAbbrevs cannot refer to
/// the instances hold by the DIEs. When we encounter an abbreviation
/// that we don't know, we create a permanent copy of it.
void DwarfLinker::AssignAbbrev(DIEAbbrev &Abbrev) {
// Check the set for priors.
FoldingSetNodeID ID;
void *InsertToken;
DIEAbbrev *InSet = AbbreviationsSet.FindNodeOrInsertPos(ID, InsertToken);
// If it's newly added.
if (InSet) {
// Assign existing abbreviation number.
} else {
// Add to abbreviation list.
llvm::make_unique<DIEAbbrev>(Abbrev.getTag(), Abbrev.hasChildren()));
for (const auto &Attr : Abbrev.getData())
Abbreviations.back()->AddAttribute(Attr.getAttribute(), Attr.getForm());