[DebugInfo] Fix emitting DWARF64 compilation units (5/19).

[ikudrin]

Summary

The patch also adds a method to choose an appropriate DWARF form to represent section offsets according to the version and the format of producing debug info.

[dblaikie]

Looks good - thanks!

[ikudrin]

• Updated to follow changes in the parent commits.

llvm/lib/CodeGen/AsmPrinter/DIE.cpp

 }
 
 /// SizeOf - Determine size of label value in bytes.
 ///
 unsigned DIELabel::SizeOf(const AsmPrinter *AP, dwarf::Form Form) const {
   switch (Form) {
   case dwarf::DW_FORM_data4:
     return 4;
+  case dwarf::DW_FORM_data8:
+    return 8;
   case dwarf::DW_FORM_sec_offset:
   case dwarf::DW_FORM_strp:
     return AP->getDwarfOffsetByteSize();
   case dwarf::DW_FORM_addr:
     return AP->MAI->getCodePointerSize();
   default:
     llvm_unreachable("DIE Value form not supported yet");
   }

llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h

public:
   unsigned getHeaderSize() const override {
     // DWARF v5 added the DWO ID to the header for split/skeleton units.
     unsigned DWOIdSize =
         DD->getDwarfVersion() >= 5 && DD->useSplitDwarf() ? sizeof(uint64_t)
                                                           : 0;
     return DwarfUnit::getHeaderSize() + DWOIdSize;
   }
   unsigned getLength() {
-    return sizeof(uint32_t) + // Length field
+    return Asm->getUnitLengthFieldByteSize() + // Length field
            getHeaderSize() + getUnitDie().getSize();
   }
 
   void emitHeader(bool UseOffsets) override;
 
   /// Add the DW_AT_addr_base attribute to the unit DIE.
   void addAddrTableBase();
 
   MCSymbol *getLabelBegin() const {

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.h

bool emitDebugEntryValues() const {
     return EmitDebugEntryValues;
   }
 
   bool shareAcrossDWOCUs() const;
 
   /// Returns the Dwarf Version.
   uint16_t getDwarfVersion() const;
 
+  /// Returns a suitable DWARF form to represent a section offset, i.e.
+  /// * DW_FORM_sec_offset for DWARF version >= 4;
+  /// * DW_FORM_data8 for 64-bit DWARFv3;
+  /// * DW_FORM_data4 for 32-bit DWARFv3 and DWARFv2.
+  dwarf::Form getDwarfSectionOffsetForm() const;
+
   /// Returns the previous CU that was being updated
   const DwarfCompileUnit *getPrevCU() const { return PrevCU; }
   void setPrevCU(const DwarfCompileUnit *PrevCU) { this->PrevCU = PrevCU; }
 
   /// Returns the entries for the .debug_loc section.
   const DebugLocStream &getDebugLocs() const { return DebugLocs; }
 
   /// Emit an entry for the debug loc section. This can be used to

llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp

void DwarfDebug::addAccelType(const DICompileUnit &CU, StringRef Name,
                               const DIE &Die, char Flags) {
   addAccelNameImpl(CU, AccelTypes, Name, Die);
 }
 
 uint16_t DwarfDebug::getDwarfVersion() const {
   return Asm->OutStreamer->getContext().getDwarfVersion();
 }
 
+dwarf::Form DwarfDebug::getDwarfSectionOffsetForm() const {
+  if (Asm->getDwarfVersion() >= 4)
+    return dwarf::Form::DW_FORM_sec_offset;
+  assert((!Asm->isDwarf64() || (Asm->getDwarfVersion() == 3)) &&
+         "DWARF64 is not defined prior DWARFv3");
+  return Asm->isDwarf64() ? dwarf::Form::DW_FORM_data8
+                          : dwarf::Form::DW_FORM_data4;
+}
+
 const MCSymbol *DwarfDebug::getSectionLabel(const MCSection *S) {
   return SectionLabels.find(S)->second;
 }
 void DwarfDebug::insertSectionLabel(const MCSymbol *S) {
   if (SectionLabels.insert(std::make_pair(&S->getSection(), S)).second)
     if (useSplitDwarf() || getDwarfVersion() >= 5)
       AddrPool.getIndex(S);
 }

llvm/lib/CodeGen/AsmPrinter/DwarfFile.cpp

for (const auto &TheU : CUs) {
 
     TheU->setDebugSectionOffset(SecOffset);
     SecOffset += computeSizeAndOffsetsForUnit(TheU.get());
   }
 }
 
 unsigned DwarfFile::computeSizeAndOffsetsForUnit(DwarfUnit *TheU) {
   // CU-relative offset is reset to 0 here.
-  unsigned Offset = sizeof(int32_t) +      // Length of Unit Info
-                    TheU->getHeaderSize(); // Unit-specific headers
+  unsigned Offset = Asm->getUnitLengthFieldByteSize() + // Length of Unit Info
+                    TheU->getHeaderSize();              // Unit-specific headers
 
   // The return value here is CU-relative, after laying out
   // all of the CU DIE.
   return computeSizeAndOffset(TheU->getUnitDie(), Offset);
 }
 
 // Compute the size and offset of a DIE. The offset is relative to start of the
 // CU. It returns the offset after laying out the DIE.

llvm/lib/CodeGen/AsmPrinter/DwarfUnit.h

public:
 
   bool useSegmentedStringOffsetsTable() const {
     return DD->useSegmentedStringOffsetsTable();
   }
 
   /// Compute the size of a header for this unit, not including the initial
   /// length field.
   virtual unsigned getHeaderSize() const {
-    return sizeof(int16_t) + // DWARF version number
-           sizeof(int32_t) + // Offset Into Abbrev. Section
-           sizeof(int8_t) +  // Pointer Size (in bytes)
+    return sizeof(int16_t) +               // DWARF version number
+           Asm->getDwarfOffsetByteSize() + // Offset Into Abbrev. Section
+           sizeof(int8_t) +                // Pointer Size (in bytes)
            (DD->getDwarfVersion() >= 5 ? sizeof(int8_t)
                                        : 0); // DWARF v5 unit type
   }
 
   /// Emit the header for this unit, not including the initial length field.
   virtual void emitHeader(bool UseOffsets) = 0;
 
   /// Add the DW_AT_str_offsets_base attribute to the unit DIE.

llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp

if (uint32_t AlignInBytes = DT->getAlignInBytes())
     addUInt(StaticMemberDIE, dwarf::DW_AT_alignment, dwarf::DW_FORM_udata,
             AlignInBytes);
 
   return &StaticMemberDIE;
 }
 
 void DwarfUnit::emitCommonHeader(bool UseOffsets, dwarf::UnitType UT) {
   // Emit size of content not including length itself
-  Asm->OutStreamer->AddComment("Length of Unit");
   if (!DD->useSectionsAsReferences()) {
     StringRef Prefix = isDwoUnit() ? "debug_info_dwo_" : "debug_info_";
     MCSymbol *BeginLabel = Asm->createTempSymbol(Prefix + "start");
     EndLabel = Asm->createTempSymbol(Prefix + "end");
-    Asm->emitLabelDifference(EndLabel, BeginLabel, 4);
+    Asm->emitDwarfUnitLength(EndLabel, BeginLabel, "Length of Unit");
     Asm->OutStreamer->emitLabel(BeginLabel);
   } else
-    Asm->emitInt32(getHeaderSize() + getUnitDie().getSize());
+    Asm->emitDwarfUnitLength(getHeaderSize() + getUnitDie().getSize(),
+                             "Length of Unit");
 
   Asm->OutStreamer->AddComment("DWARF version number");
   unsigned Version = DD->getDwarfVersion();
   Asm->emitInt16(Version);
 
   // DWARF v5 reorders the address size and adds a unit type.
   if (Version >= 5) {
     Asm->OutStreamer->AddComment("DWARF Unit Type");
return Die.addValue(DIEValueAllocator, Attribute,
                                                  : dwarf::DW_FORM_data4,
                       new (DIEValueAllocator) DIEDelta(Hi, Lo));
 }
 
 DIE::value_iterator
 DwarfUnit::addSectionLabel(DIE &Die, dwarf::Attribute Attribute,
                            const MCSymbol *Label, const MCSymbol *Sec) {
   if (Asm->MAI->doesDwarfUseRelocationsAcrossSections())
-    return addLabel(Die, Attribute,
-                    DD->getDwarfVersion() >= 4 ? dwarf::DW_FORM_sec_offset
-                                               : dwarf::DW_FORM_data4,
-                    Label);
+    return addLabel(Die, Attribute, DD->getDwarfSectionOffsetForm(), Label);
   return addSectionDelta(Die, Attribute, Label, Sec);
 }
 
 bool DwarfTypeUnit::isDwoUnit() const {
   // Since there are no skeleton type units, all type units are dwo type units
   // when split DWARF is being used.
   return DD->useSplitDwarf();
 }

llvm/test/DebugInfo/X86/debug-info-dwarf64.ll

+; This checks that .debug_info can be generated in the DWARF64 format.
+
+; RUN: llc -mtriple=x86_64 -dwarf-version=3 -dwarf64 -filetype=obj %s -o %t3
+; RUN: llvm-dwarfdump -debug-abbrev -debug-info -v %t3 | \
+; RUN:   FileCheck %s --check-prefixes=CHECK,DWARFv3
+
+; RUN: llc -mtriple=x86_64 -dwarf-version=4 -dwarf64 -filetype=obj %s -o %t4
+; RUN: llvm-dwarfdump -debug-abbrev -debug-info -v %t4 | \
+; RUN:   FileCheck %s --check-prefixes=CHECK,DWARFv4
+
+; CHECK:        .debug_abbrev contents:
+; CHECK:        [1] DW_TAG_compile_unit   DW_CHILDREN_yes
+; CHECK-NEXT:     DW_AT_producer  DW_FORM_strp
+; CHECK-NEXT:     DW_AT_language  DW_FORM_data2
+; CHECK-NEXT:     DW_AT_name      DW_FORM_strp
+; DWARFv3-NEXT:   DW_AT_stmt_list DW_FORM_data8
+; DWARFv4-NEXT:   DW_AT_stmt_list DW_FORM_sec_offset
+; CHECK-NEXT:     DW_AT_comp_dir  DW_FORM_strp
+; CHECK:        [2] DW_TAG_variable   DW_CHILDREN_no
+; CHECK-NEXT:     DW_AT_name      DW_FORM_strp
+; CHECK-NEXT:     DW_AT_type      DW_FORM_ref4
+; CHECK:        [3] DW_TAG_base_type  DW_CHILDREN_no
+; CHECK-NEXT:     DW_AT_name      DW_FORM_strp
+
+; CHECK:        .debug_info contents:
+; CHECK:        Compile Unit: length = 0x{{([[:xdigit:]]{16})}}, format = DWARF64,
+; CHECK:        DW_TAG_compile_unit [1] *
+; CHECK-NEXT:     DW_AT_producer [DW_FORM_strp]   ( .debug_str[0x{{([[:xdigit:]]{16})}}] = "clang version 12.0.0")
+; CHECK-NEXT:     DW_AT_language [DW_FORM_data2]  (DW_LANG_C99)
+; CHECK-NEXT:     DW_AT_name [DW_FORM_strp]       ( .debug_str[0x{{([[:xdigit:]]{16})}}] = "foo.c")
+; DWARFv3-NEXT:   DW_AT_stmt_list [DW_FORM_data8] (0x0000000000000000)
+; DWARFv4-NEXT:   DW_AT_stmt_list [DW_FORM_sec_offset] (0x0000000000000000)
+; CHECK-NEXT:     DW_AT_comp_dir [DW_FORM_strp]   ( .debug_str[0x{{([[:xdigit:]]{16})}}] = "/tmp")
+; CHECK:        DW_TAG_variable [2]
+; CHECK-NEXT:     DW_AT_name [DW_FORM_strp]       ( .debug_str[0x{{([[:xdigit:]]{16})}}] = "foo")
+; CHECK-NEXT:     DW_AT_type [DW_FORM_ref4]       (cu + {{.+}} => {{.+}} "int")
+; CHECK:        DW_TAG_base_type [3]
+; CHECK-NEXT:     DW_AT_name [DW_FORM_strp]       ( .debug_str[0x{{([[:xdigit:]]{16})}}] = "int")
+
+; IR generated and reduced from:
+; $ cat foo.c
+; int foo;
+; $ clang -g -S -emit-llvm foo.c -o foo.ll
+
+target triple = "x86_64-unknown-linux-gnu"
+
+@foo = dso_local global i32 0, align 4, !dbg !0
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!7, !8, !9}
+!llvm.ident = !{!10}
+
+!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+!1 = distinct !DIGlobalVariable(name: "foo", scope: !2, file: !3, line: 1, type: !6, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang version 12.0.0", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5, splitDebugInlining: false, nameTableKind: None)
+!3 = !DIFile(filename: "foo.c", directory: "/tmp")
+!4 = !{}
+!5 = !{!0}
+!6 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!7 = !{i32 7, !"Dwarf Version", i32 4}
+!8 = !{i32 2, !"Debug Info Version", i32 3}
+!9 = !{i32 1, !"wchar_size", i32 4}
+!10 = !{!"clang version 12.0.0"}

llvm/unittests/CodeGen/DIETest.cpp

TEST_P(DIELabelFixture, EmitValue) {
   ASSERT_NE(ActualArg0, nullptr);
   EXPECT_EQ(&(ActualArg0->getSymbol()), Val);
 }
 
 INSTANTIATE_TEST_CASE_P(
     DIETestParams, DIELabelFixture,
     testing::Values(
         DIETestParams{4, dwarf::DWARF32, dwarf::DW_FORM_data4, 4u},
+        DIETestParams{4, dwarf::DWARF32, dwarf::DW_FORM_data8, 8u},
         DIETestParams{4, dwarf::DWARF32, dwarf::DW_FORM_sec_offset, 4u},
         DIETestParams{4, dwarf::DWARF32, dwarf::DW_FORM_strp, 4u},
         DIETestParams{4, dwarf::DWARF32, dwarf::DW_FORM_addr, 8u},
         DIETestParams{4, dwarf::DWARF64, dwarf::DW_FORM_data4, 4u},
+        DIETestParams{4, dwarf::DWARF64, dwarf::DW_FORM_data8, 8u},
         DIETestParams{4, dwarf::DWARF64, dwarf::DW_FORM_sec_offset, 8u},
         DIETestParams{4, dwarf::DWARF64, dwarf::DW_FORM_strp, 8u},
         DIETestParams{4, dwarf::DWARF64, dwarf::DW_FORM_addr, 8u}), );
 
 struct DIEDeltaFixture : public DIEFixtureBase {
   void SetUp() override {
     DIEFixtureBase::SetUp();
     if (!TestPrinter)