[DWARF parser] Make DWARF parser more robust against missing compile/type units.

DWARF standard claims that each compilation/type unit header in
.debug_info/.debug_types section must be followed by corresponding
compile/type unit DIE, possibly with its children. Two situations
are possible:

 * compile/type unit DIE is missing because DWARF producer failed to
   emit it.
 * DWARF parser failed to parse unit DIE correctly, for instance if it
   contains some unsupported attributes (see r237721, for instance).

In either of these cases, the library, and the tools that use it
(llvm-dwarfdump, llvm-symbolizer) should not crash. Insert appropriate
checks to protect against this.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237733 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/DebugInfo/DWARF/DWARFUnit.h

@@ -195,9 +195,8 @@ public:
     BaseAddr = base_addr;
   }
 
-  const DWARFDebugInfoEntryMinimal *
+  const DWARFDebugInfoEntryMinimal *getUnitDIE(bool ExtractUnitDIEOnly = true) {
-  getCompileUnitDIE(bool extract_cu_die_only = true) {
+    extractDIEsIfNeeded(ExtractUnitDIEOnly);
-    extractDIEsIfNeeded(extract_cu_die_only);
     return DieArray.empty() ? nullptr : &DieArray[0];
   }
 
@@ -226,8 +225,7 @@ public:
   /// It is illegal to call this method with a DIE that hasn't be
   /// created by this unit. In other word, it's illegal to call this
   /// method on a DIE that isn't accessible by following
-  /// children/sibling links starting from this unit's
+  /// children/sibling links starting from this unit's getUnitDIE().
-  /// getCompileUnitDIE().
   uint32_t getDIEIndex(const DWARFDebugInfoEntryMinimal *DIE) {
     assert(!DieArray.empty() && DIE >= &DieArray[0] &&
            DIE < &DieArray[0] + DieArray.size());

lib/DebugInfo/DWARF/DWARFCompileUnit.cpp

@@ -22,9 +22,10 @@ void DWARFCompileUnit::dump(raw_ostream &OS) {
      << " (next unit at " << format("0x%08x", getNextUnitOffset())
      << ")\n";
 
-  const DWARFDebugInfoEntryMinimal *CU = getCompileUnitDIE(false);
+  if (const DWARFDebugInfoEntryMinimal *CU = getUnitDIE(false))
-  assert(CU && "Null Compile Unit?");
     CU->dump(OS, this, -1U);
+  else
+    OS << "<compile unit can't be parsed!>\n\n";
 }
 
 // VTable anchor.

lib/DebugInfo/DWARF/DWARFContext.cpp

@@ -140,8 +140,10 @@ void DWARFContext::dump(raw_ostream &OS, DIDumpType DumpType) {
     OS << "\n.debug_line contents:\n";
     for (const auto &CU : compile_units()) {
       savedAddressByteSize = CU->getAddressByteSize();
-      unsigned stmtOffset =
+      const auto *CUDIE = CU->getUnitDIE();
-          CU->getCompileUnitDIE()->getAttributeValueAsSectionOffset(
+      if (CUDIE == nullptr)
+        continue;
+      unsigned stmtOffset = CUDIE->getAttributeValueAsSectionOffset(
           CU.get(), DW_AT_stmt_list, -1U);
       if (stmtOffset != -1U) {
         DataExtractor lineData(getLineSection().Data, isLittleEndian(),
@@ -321,13 +323,14 @@ const DWARFDebugFrame *DWARFContext::getDebugFrame() {
 }
 
 const DWARFLineTable *
-DWARFContext::getLineTableForUnit(DWARFUnit *cu) {
+DWARFContext::getLineTableForUnit(DWARFUnit *U) {
   if (!Line)
     Line.reset(new DWARFDebugLine(&getLineSection().Relocs));
-
+  const auto *UnitDIE = U->getUnitDIE();
+  if (UnitDIE == nullptr)
+    return nullptr;
   unsigned stmtOffset =
-      cu->getCompileUnitDIE()->getAttributeValueAsSectionOffset(
+      UnitDIE->getAttributeValueAsSectionOffset(U, DW_AT_stmt_list, -1U);
-          cu, DW_AT_stmt_list, -1U);
   if (stmtOffset == -1U)
     return nullptr; // No line table for this compile unit.
 
@@ -337,7 +340,7 @@ DWARFContext::getLineTableForUnit(DWARFUnit *cu) {
 
   // We have to parse it first.
   DataExtractor lineData(getLineSection().Data, isLittleEndian(),
-                         cu->getAddressByteSize());
+                         U->getAddressByteSize());
   return Line->getOrParseLineTable(lineData, stmtOffset);
 }
 

lib/DebugInfo/DWARF/DWARFTypeUnit.cpp

@@ -33,7 +33,8 @@ void DWARFTypeUnit::dump(raw_ostream &OS) {
      << " (next unit at " << format("0x%08x", getNextUnitOffset())
      << ")\n";
 
-  const DWARFDebugInfoEntryMinimal *CU = getCompileUnitDIE(false);
+  if (const DWARFDebugInfoEntryMinimal *TU = getUnitDIE(false))
-  assert(CU && "Null Compile Unit?");
+    TU->dump(OS, this, -1U);
-  CU->dump(OS, this, -1U);
+  else
+    OS << "<type unit can't be parsed!>\n\n";
 }

lib/DebugInfo/DWARF/DWARFUnit.cpp

@@ -310,8 +310,11 @@ void DWARFUnit::clearDIEs(bool KeepCUDie) {
 }
 
 void DWARFUnit::collectAddressRanges(DWARFAddressRangesVector &CURanges) {
-  // First, check if CU DIE describes address ranges for the unit.
+  const auto *U = getUnitDIE();
-  const auto &CUDIERanges = getCompileUnitDIE()->getAddressRanges(this);
+  if (U == nullptr)
+    return;
+  // First, check if unit DIE describes address ranges for the whole unit.
+  const auto &CUDIERanges = U->getAddressRanges(this);
   if (!CUDIERanges.empty()) {
     CURanges.insert(CURanges.end(), CUDIERanges.begin(), CUDIERanges.end());
     return;

tools/dsymutil/DwarfLinker.cpp

@@ -729,7 +729,7 @@ void DwarfStreamer::emitLocationsForUnit(const CompileUnit &Unit,
   const DWARFSection &InputSec = Dwarf.getLocSection();
   DataExtractor Data(InputSec.Data, Dwarf.isLittleEndian(), AddressSize);
   DWARFUnit &OrigUnit = Unit.getOrigUnit();
-  const auto *OrigUnitDie = OrigUnit.getCompileUnitDIE(false);
+  const auto *OrigUnitDie = OrigUnit.getUnitDIE(false);
   int64_t UnitPcOffset = 0;
   uint64_t OrigLowPc = OrigUnitDie->getAttributeValueAsAddress(
       &OrigUnit, dwarf::DW_AT_low_pc, -1ULL);
@@ -2203,7 +2203,7 @@ void DwarfLinker::patchRangesForUnit(const CompileUnit &Unit,
                                OrigDwarf.isLittleEndian(), AddressSize);
   auto InvalidRange = FunctionRanges.end(), CurrRange = InvalidRange;
   DWARFUnit &OrigUnit = Unit.getOrigUnit();
-  const auto *OrigUnitDie = OrigUnit.getCompileUnitDIE(false);
+  const auto *OrigUnitDie = OrigUnit.getUnitDIE(false);
   uint64_t OrigLowPc = OrigUnitDie->getAttributeValueAsAddress(
       &OrigUnit, dwarf::DW_AT_low_pc, -1ULL);
   // Ranges addresses are based on the unit's low_pc. Compute the
@@ -2287,7 +2287,7 @@ static void insertLineSequence(std::vector<DWARFDebugLine::Row> &Seq,
 void DwarfLinker::patchLineTableForUnit(CompileUnit &Unit,
                                         DWARFContext &OrigDwarf) {
   const DWARFDebugInfoEntryMinimal *CUDie =
-      Unit.getOrigUnit().getCompileUnitDIE();
+      Unit.getOrigUnit().getUnitDIE();
   uint64_t StmtList = CUDie->getAttributeValueAsSectionOffset(
       &Unit.getOrigUnit(), dwarf::DW_AT_stmt_list, -1ULL);
   if (StmtList == -1ULL)
@@ -2461,7 +2461,7 @@ bool DwarfLinker::link(const DebugMap &Map) {
     // In a first phase, just read in the debug info and store the DIE
     // parent links that we will use during the next phase.
     for (const auto &CU : DwarfContext.compile_units()) {
-      auto *CUDie = CU->getCompileUnitDIE(false);
+      auto *CUDie = CU->getUnitDIE(false);
       if (Options.Verbose) {
         outs() << "Input compilation unit:";
         CUDie->dump(outs(), CU.get(), 0);
@@ -2476,7 +2476,7 @@ bool DwarfLinker::link(const DebugMap &Map) {
     // references require the ParentIdx to be setup for every CU in
     // the object file before calling this.
     for (auto &CurrentUnit : Units)
-      lookForDIEsToKeep(*CurrentUnit.getOrigUnit().getCompileUnitDIE(), *Obj,
+      lookForDIEsToKeep(*CurrentUnit.getOrigUnit().getUnitDIE(), *Obj,
                         CurrentUnit, 0);
 
     // The calls to applyValidRelocs inside cloneDIE will walk the
@@ -2489,7 +2489,7 @@ bool DwarfLinker::link(const DebugMap &Map) {
     // to clone/emit.
     if (!ValidRelocs.empty())
       for (auto &CurrentUnit : Units) {
-        const auto *InputDIE = CurrentUnit.getOrigUnit().getCompileUnitDIE();
+        const auto *InputDIE = CurrentUnit.getOrigUnit().getUnitDIE();
         CurrentUnit.setStartOffset(OutputDebugInfoSize);
         DIE *OutputDIE = cloneDIE(*InputDIE, CurrentUnit, 0 /* PCOffset */,
                                   11 /* Unit Header size */);