[Lldb-commits] [lldb] 0a357e9 - [lldb] Update the String table offset based on the DWARF format (#147054)

[via lldb-commits]

Author: Hemang Gadhavi
Date: 2025-07-14T15:25:45+05:30
New Revision: 0a357e92ca3ebfd68710b58413cac21e2cb9d8ad

URL: https://github.com/llvm/llvm-project/commit/0a357e92ca3ebfd68710b58413cac21e2cb9d8ad
DIFF: https://github.com/llvm/llvm-project/commit/0a357e92ca3ebfd68710b58413cac21e2cb9d8ad.diff

LOG: [lldb] Update the String table offset based on the DWARF format (#147054)

This PR is updating the string table offset (DW_AT_str_offsets_base
which is introduced in `DWARF5`) based on the DWARF format, as per the
DWARF specification; For the 32-bit DWARF format, each offset is 4 bytes
long; for the 64-bit DWARF format, each offset is 8 bytes long.

Added: 
    

Modified: 
    lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
    lldb/unittests/SymbolFile/DWARF/DWARF64UnitTest.cpp

Removed: 
    


################################################################################
diff  --git a/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp b/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
index f216ab13e8936..8b0fade86f177 100644
--- a/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
+++ b/lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp
@@ -1077,8 +1077,10 @@ uint32_t DWARFUnit::GetHeaderByteSize() const { return m_header.getSize(); }
 
 std::optional<uint64_t>
 DWARFUnit::GetStringOffsetSectionItem(uint32_t index) const {
-  lldb::offset_t offset = GetStrOffsetsBase() + index * 4;
-  return m_dwarf.GetDWARFContext().getOrLoadStrOffsetsData().GetU32(&offset);
+  lldb::offset_t offset =
+      GetStrOffsetsBase() + index * m_header.getDwarfOffsetByteSize();
+  return m_dwarf.GetDWARFContext().getOrLoadStrOffsetsData().GetMaxU64(
+      &offset, m_header.getDwarfOffsetByteSize());
 }
 
 llvm::Expected<llvm::DWARFAddressRangesVector>

diff  --git a/lldb/unittests/SymbolFile/DWARF/DWARF64UnitTest.cpp b/lldb/unittests/SymbolFile/DWARF/DWARF64UnitTest.cpp
index 2303f68674e4c..20061ec191ca1 100644
--- a/lldb/unittests/SymbolFile/DWARF/DWARF64UnitTest.cpp
+++ b/lldb/unittests/SymbolFile/DWARF/DWARF64UnitTest.cpp
@@ -84,3 +84,100 @@ TEST(DWARF64UnitTest, DWARF64DebugInfoAndCU) {
   ASSERT_TRUE(declaration.IsValid());
   ASSERT_EQ(declaration.Tag(), DW_TAG_subprogram);
 }
+
+TEST(DWARF64UnitTest, DWARF5StrTable) {
+  const char *yamldata = R"(
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2MSB
+  Type:    ET_EXEC
+  Machine: EM_PPC64
+DWARF:
+  debug_str:
+    - 'clang version 18.1.8 (clang-18.1.8-1)'
+    - 'main.c'
+    - 'foo'
+    - 'main'
+  debug_abbrev:
+    - Table:
+        - Code:            0x1
+          Tag:             DW_TAG_compile_unit
+          Children:        DW_CHILDREN_yes
+          Attributes:
+            - Attribute:       DW_AT_producer
+              Form:            DW_FORM_strx1
+            - Attribute:       DW_AT_language
+              Form:            DW_FORM_data2
+            - Attribute:       DW_AT_name
+              Form:            DW_FORM_strx1
+            - Attribute:       DW_AT_str_offsets_base
+              Form:            DW_FORM_sec_offset
+        - Code:            0x2
+          Tag:             DW_TAG_subprogram
+          Children:        DW_CHILDREN_no
+          Attributes:
+            - Attribute:       DW_AT_name
+              Form:            DW_FORM_strx1
+  debug_info:
+    - Format:          DWARF64
+      Version:         0x05
+      UnitType:        DW_UT_compile
+      AbbrOffset:      0x0
+      AddrSize:        0x08
+      Entries:
+        - AbbrCode:        0x1
+          Values:
+            - Value:           0x0
+            - Value:           0x04
+            - Value:           0x1
+            - Value:           0x00000010
+        - AbbrCode:        0x2
+          Values:
+            - Value:           0x2
+        - AbbrCode:        0x2
+          Values:
+            - Value:           0x3
+        - AbbrCode:	   0x0
+
+  debug_str_offsets:
+    - Format:           DWARF64
+      Version:          "0x05"
+      Offsets:
+          - 0x00000000
+          - 0x00000026
+          - 0x0000002d
+          - 0x00000031
+)";
+
+  YAMLModuleTester t(yamldata);
+  auto *symbol_file =
+      llvm::cast<SymbolFileDWARF>(t.GetModule()->GetSymbolFile());
+  DWARFUnit *unit = symbol_file->DebugInfo().GetUnitAtIndex(0);
+  ASSERT_TRUE(unit);
+  ASSERT_EQ(unit->GetFormParams().Format, DwarfFormat::DWARF64);
+  ASSERT_EQ(unit->GetVersion(), 5);
+  ASSERT_EQ(unit->GetAddressByteSize(), 8);
+
+  DWARFFormValue form_value;
+  const DWARFDebugInfoEntry *cu_entry = unit->DIE().GetDIE();
+  ASSERT_EQ(cu_entry->Tag(), DW_TAG_compile_unit);
+  ASSERT_EQ(unit->GetProducer(), eProducerClang);
+  ASSERT_EQ(unit->GetDWARFLanguageType(), DW_LANG_C_plus_plus);
+  auto attrs = cu_entry->GetAttributes(unit, DWARFDebugInfoEntry::Recurse::yes);
+  attrs.ExtractFormValueAtIndex(3,
+                                form_value); // Validate DW_AT_str_offsets_bae
+  ASSERT_EQ(form_value.Unsigned(), 0x00000010UL);
+  DWARFDIE cu_die(unit, cu_entry);
+  ASSERT_EQ(ConstString(cu_die.GetName()), "main.c");
+
+  auto func_foo = cu_die.GetFirstChild();
+  ASSERT_TRUE(func_foo.IsValid());
+  ASSERT_EQ(func_foo.Tag(), DW_TAG_subprogram);
+  ASSERT_EQ(ConstString(func_foo.GetName()), "foo");
+
+  auto func_main = func_foo.GetSibling();
+  ASSERT_TRUE(func_main.IsValid());
+  ASSERT_EQ(func_main.Tag(), DW_TAG_subprogram);
+  ASSERT_EQ(ConstString(func_main.GetName()), "main");
+}