[BOLT][DWARF][NFC] Fix DebugStrOffsetsWriter (llvm#100672)

Fix DebugStrOffsetsWriter so updateAddressMap can't be called after it
is finalized.

Author: sayhaan

bolt/include/bolt/Core/DebugData.h

@@ -475,7 +475,8 @@ class DebugStrOffsetsWriter {
   }
 
   /// Update Str offset in .debug_str in .debug_str_offsets.
-  void updateAddressMap(uint32_t Index, uint32_t Address);
+  void updateAddressMap(uint32_t Index, uint32_t Address,
+                        const DWARFUnit &Unit);
 
   /// Get offset for given index in original .debug_str_offsets section.
   uint64_t getOffset(uint32_t Index) const { return StrOffsets[Index]; }
@@ -507,6 +508,8 @@ class DebugStrOffsetsWriter {
   std::unique_ptr<DebugStrOffsetsBufferVector> StrOffsetsBuffer;
   std::unique_ptr<raw_svector_ostream> StrOffsetsStream;
   std::map<uint32_t, uint32_t> IndexToAddressMap;
+  [[maybe_unused]]
+  DenseSet<uint64_t> DebugStrOffsetFinalized;
   SmallVector<uint32_t, 5> StrOffsets;
   std::unordered_map<uint64_t, uint64_t> ProcessedBaseOffsets;
   bool StrOffsetSectionWasModified = false;

bolt/lib/Core/DIEBuilder.cpp

@@ -78,7 +78,7 @@ static void addStringHelper(DebugStrOffsetsWriter &StrOffstsWriter,
   uint32_t NewOffset = StrWriter.addString(Str);
   if (Unit.getVersion() >= 5) {
     StrOffstsWriter.updateAddressMap(DIEAttrInfo.getDIEInteger().getValue(),
-                                     NewOffset);
+                                     NewOffset, Unit);
     return;
   }
   DIEBldr.replaceValue(&Die, DIEAttrInfo.getAttribute(), DIEAttrInfo.getForm(),

bolt/lib/Core/DebugData.cpp

@@ -851,7 +851,11 @@ void DebugStrOffsetsWriter::initialize(DWARFUnit &Unit) {
         StrOffsetsSection.Data.data() + Contr->Base + Offset));
 }
 
-void DebugStrOffsetsWriter::updateAddressMap(uint32_t Index, uint32_t Address) {
+void DebugStrOffsetsWriter::updateAddressMap(uint32_t Index, uint32_t Address,
+                                             const DWARFUnit &Unit) {
+  assert(DebugStrOffsetFinalized.count(Unit.getOffset()) == 0 &&
+         "Cannot update address map since debug_str_offsets was already "
+         "finalized for this CU.");
   IndexToAddressMap[Index] = Address;
   StrOffsetSectionWasModified = true;
 }
@@ -906,6 +910,8 @@ void DebugStrOffsetsWriter::finalizeSection(DWARFUnit &Unit,
   }
 
   StrOffsetSectionWasModified = false;
+  assert(DebugStrOffsetFinalized.insert(Unit.getOffset()).second &&
+         "debug_str_offsets was already finalized for this CU.");
   clear();
 }
 

bolt/lib/Rewrite/DWARFRewriter.cpp

@@ -714,7 +714,8 @@ void DWARFRewriter::updateDebugInfo() {
       RangesBase = RangesSectionWriter.getSectionOffset() +
                    getDWARF5RngListLocListHeaderSize();
       RangesSectionWriter.initSection(Unit);
-      StrOffstsWriter->finalizeSection(Unit, DIEBlder);
+      if (!SplitCU)
+        StrOffstsWriter->finalizeSection(Unit, DIEBlder);
     } else if (SplitCU) {
       RangesBase = LegacyRangesSectionWriter.get()->getSectionOffset();
     }
@@ -760,6 +761,8 @@ void DWARFRewriter::updateDebugInfo() {
               : std::optional<std::string>(opts::DwarfOutputPath.c_str());
       std::string DWOName = DIEBlder.updateDWONameCompDir(
           *StrOffstsWriter, *StrWriter, *CU, DwarfOutputPath, std::nullopt);
+      if (CU->getVersion() >= 5)
+        StrOffstsWriter->finalizeSection(*CU, DIEBlder);
       processSplitCU(*CU, **SplitCU, DIEBlder, *TempRangesSectionWriter,
                      AddressWriter, DWOName, DwarfOutputPath);
     }

bolt/test/X86/dwarf5-df-larger-batch-size.test

@@ -0,0 +1,28 @@
+; RUN: rm -rf %t
+; RUN: mkdir %t
+; RUN: cd %t
+; RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-df-input-lowpc-ranges-main.s \
+; RUN: -split-dwarf-file=main.dwo -o main.o
+; RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-df-input-lowpc-ranges-other.s \
+; RUN: -split-dwarf-file=mainOther.dwo -o other.o
+; RUN: %clang %cflags main.o other.o -o main.exe
+; RUN: llvm-bolt main.exe -o main.exe.bolt --update-debug-sections --cu-processing-batch-size=1
+; RUN: llvm-bolt main.exe -o main-batch.exe.bolt --update-debug-sections --cu-processing-batch-size=2
+; RUN: llvm-dwarfdump --show-form --verbose --debug-info main.exe.bolt >> %t/foo.txt
+; RUN: cat %t/foo.txt | FileCheck -check-prefix=BOLT %s
+; RUN: llvm-dwarfdump --show-form --verbose --debug-info main.exe.bolt >> %t/foo-batch.txt
+; RUN: cat %t/foo-batch.txt | FileCheck -check-prefix=BOLT-BATCH %s
+
+;; Tests that BOLT correctly handles DWO name strings with larger batch sizes.
+
+; BOLT: DW_TAG_skeleton_unit
+; BOLT: DW_AT_dwo_name [DW_FORM_strx1]  (indexed (00000001) string = "main.dwo.dwo")
+
+; BOLT: DW_TAG_skeleton_unit
+; BOLT: DW_AT_dwo_name [DW_FORM_strx1]  (indexed (00000001) string = "mainOther.dwo.dwo")
+
+; BOLT-BATCH: DW_TAG_skeleton_unit
+; BOLT-BATCH: DW_AT_dwo_name [DW_FORM_strx1]  (indexed (00000001) string = "main.dwo.dwo")
+
+; BOLT-BATCH: DW_TAG_skeleton_unit
+; BOLT-BATCH: DW_AT_dwo_name [DW_FORM_strx1]  (indexed (00000001) string = "mainOther.dwo.dwo")