[lldb][NFC] Change ObjectFile's DataExtractor to a shared ptr (#170066)

ObjectFile has an m_data DataExtractor ivar which may be default
constructed initially, or initialized with a DataBuffer passed in to its
ctor. If the DataExtractor does not get a DataBuffer source passed in,
the subclass will initialize it with access to the object file's data.
When a DataBuffer is passed in to the base class ctor, the DataExtractor
only has its buffer initialized; ObjectFile doesn't yet know the address
size and endianness to fully initialize the DataExtractor.

This patch changes ObjectFile to instead have a DataExtractorSP ivar
which is always initialized with at least a default-constructed
DataExtractor object in the base class ctor. The next patch I will be
writing is to change the ObjectFile ctor to take an optional
DataExtractorSP, so the caller can pass a DataExtractor subclass -- the
VirtualizeDataExtractor being added via
#168802
instead of a DataBuffer which is trivially saved into the DataExtractor.

The change is otherwise mechanical; all `m_data.` changed to
`m_data_sp->` and all the places where `m_data` was passed in for a
by-ref call were changed to `*m_data_sp.get()`. The shared pointer is
always initialized to contain an object.

I built & ran the testsuite on macOS and on aarch64-Ubuntu (thanks for
getting the Linux testsuite to run on SME-only systems David). All of
the ObjectFile subclasses I modifed compile cleanly, but I haven't
tested them beyond any unit tests they may have (prob breakpad).

rdar://148939795

Author: jasonmolenda

lldb/include/lldb/Symbol/ObjectFile.h

@@ -18,6 +18,7 @@
 #include "lldb/Utility/Endian.h"
 #include "lldb/Utility/FileSpec.h"
 #include "lldb/Utility/FileSpecList.h"
+#include "lldb/Utility/NonNullSharedPtr.h"
 #include "lldb/Utility/StructuredData.h"
 #include "lldb/Utility/UUID.h"
 #include "lldb/lldb-private.h"
@@ -418,7 +419,7 @@ class ObjectFile : public std::enable_shared_from_this<ObjectFile>,
   /// Attempts to parse the object header.
   ///
   /// This function is used as a test to see if a given plug-in instance can
-  /// parse the header data already contained in ObjectFile::m_data. If an
+  /// parse the header data already contained in ObjectFile::m_data_nsp. If an
   /// object file parser does not recognize that magic bytes in a header,
   /// false should be returned and the next plug-in can attempt to parse an
   /// object file.
@@ -777,6 +778,8 @@ class ObjectFile : public std::enable_shared_from_this<ObjectFile>,
   std::string GetObjectName() const;
 
 protected:
+  typedef NonNullSharedPtr<lldb_private::DataExtractor> DataExtractorNSP;
+
   // Member variables.
   FileSpec m_file;
   Type m_type;
@@ -786,8 +789,10 @@ class ObjectFile : public std::enable_shared_from_this<ObjectFile>,
   lldb::addr_t m_length; ///< The length of this object file if it is known (can
                          ///be zero if length is unknown or can't be
                          ///determined).
-  DataExtractor
-      m_data; ///< The data for this object file so things can be parsed lazily.
+  DataExtractorNSP m_data_nsp; ///< The data for this object file so things
+                               ///< can be parsed lazily.  This shared pointer
+                               ///< will always have a DataExtractor object,
+                               ///< although it may only be default-constructed.
   lldb::ProcessWP m_process_wp;
   /// Set if the object file only exists in memory.
   const lldb::addr_t m_memory_addr;

lldb/include/lldb/lldb-forward.h

@@ -342,6 +342,7 @@ typedef std::shared_ptr<lldb_private::CompileUnit> CompUnitSP;
 typedef std::shared_ptr<lldb_private::DataBuffer> DataBufferSP;
 typedef std::shared_ptr<lldb_private::WritableDataBuffer> WritableDataBufferSP;
 typedef std::shared_ptr<lldb_private::DataExtractor> DataExtractorSP;
+typedef std::unique_ptr<lldb_private::DataExtractor> DataExtractorUP;
 typedef std::shared_ptr<lldb_private::Debugger> DebuggerSP;
 typedef std::weak_ptr<lldb_private::Debugger> DebuggerWP;
 typedef std::shared_ptr<lldb_private::Disassembler> DisassemblerSP;

lldb/source/Expression/ObjectFileJIT.cpp

@@ -73,8 +73,8 @@ ObjectFileJIT::ObjectFileJIT(const lldb::ModuleSP &module_sp,
     : ObjectFile(module_sp, nullptr, 0, 0, DataBufferSP(), 0), m_delegate_wp() {
   if (delegate_sp) {
     m_delegate_wp = delegate_sp;
-    m_data.SetByteOrder(delegate_sp->GetByteOrder());
-    m_data.SetAddressByteSize(delegate_sp->GetAddressByteSize());
+    m_data_nsp->SetByteOrder(delegate_sp->GetByteOrder());
+    m_data_nsp->SetAddressByteSize(delegate_sp->GetAddressByteSize());
   }
 }
 
@@ -85,12 +85,14 @@ bool ObjectFileJIT::ParseHeader() {
   return false;
 }
 
-ByteOrder ObjectFileJIT::GetByteOrder() const { return m_data.GetByteOrder(); }
+ByteOrder ObjectFileJIT::GetByteOrder() const {
+  return m_data_nsp->GetByteOrder();
+}
 
 bool ObjectFileJIT::IsExecutable() const { return false; }
 
 uint32_t ObjectFileJIT::GetAddressByteSize() const {
-  return m_data.GetAddressByteSize();
+  return m_data_nsp->GetAddressByteSize();
 }
 
 void ObjectFileJIT::ParseSymtab(Symtab &symtab) {

lldb/source/Plugins/ObjectFile/Breakpad/ObjectFileBreakpad.cpp

@@ -130,13 +130,13 @@ void ObjectFileBreakpad::CreateSections(SectionList &unified_section_list) {
 
   std::optional<Record::Kind> current_section;
   offset_t section_start;
-  llvm::StringRef text = toStringRef(m_data.GetData());
+  llvm::StringRef text = toStringRef(m_data_nsp->GetData());
   uint32_t next_section_id = 1;
   auto maybe_add_section = [&](const uint8_t *end_ptr) {
     if (!current_section)
       return; // We have been called before parsing the first line.
 
-    offset_t end_offset = end_ptr - m_data.GetDataStart();
+    offset_t end_offset = end_ptr - m_data_nsp->GetDataStart();
     auto section_sp = std::make_shared<Section>(
         GetModule(), this, next_section_id++,
         ConstString(toString(*current_section)), eSectionTypeOther,
@@ -162,8 +162,8 @@ void ObjectFileBreakpad::CreateSections(SectionList &unified_section_list) {
     maybe_add_section(line.bytes_begin());
     // And start a new one.
     current_section = next_section;
-    section_start = line.bytes_begin() - m_data.GetDataStart();
+    section_start = line.bytes_begin() - m_data_nsp->GetDataStart();
   }
   // Finally, add the last section.
-  maybe_add_section(m_data.GetDataEnd());
+  maybe_add_section(m_data_nsp->GetDataEnd());
 }

lldb/source/Plugins/ObjectFile/COFF/ObjectFileCOFF.cpp

@@ -300,8 +300,8 @@ bool ObjectFileCOFF::ParseHeader() {
 
   std::lock_guard<std::recursive_mutex> guard(module->GetMutex());
 
-  m_data.SetByteOrder(eByteOrderLittle);
-  m_data.SetAddressByteSize(GetAddressByteSize());
+  m_data_nsp->SetByteOrder(eByteOrderLittle);
+  m_data_nsp->SetAddressByteSize(GetAddressByteSize());
 
   return true;
 }

lldb/source/Plugins/ObjectFile/ELF/ObjectFileELF.cpp

@@ -804,7 +804,7 @@ ByteOrder ObjectFileELF::GetByteOrder() const {
 }
 
 uint32_t ObjectFileELF::GetAddressByteSize() const {
-  return m_data.GetAddressByteSize();
+  return m_data_nsp->GetAddressByteSize();
 }
 
 AddressClass ObjectFileELF::GetAddressClass(addr_t file_addr) {
@@ -845,7 +845,7 @@ size_t ObjectFileELF::SectionIndex(const SectionHeaderCollConstIter &I) const {
 
 bool ObjectFileELF::ParseHeader() {
   lldb::offset_t offset = 0;
-  return m_header.Parse(m_data, &offset);
+  return m_header.Parse(*m_data_nsp.get(), &offset);
 }
 
 UUID ObjectFileELF::GetUUID() {
@@ -881,7 +881,7 @@ UUID ObjectFileELF::GetUUID() {
         return UUID();
 
       core_notes_crc =
-          CalculateELFNotesSegmentsCRC32(m_program_headers, m_data);
+          CalculateELFNotesSegmentsCRC32(m_program_headers, *m_data_nsp.get());
 
       if (core_notes_crc) {
         // Use 8 bytes - first 4 bytes for *magic* prefix, mainly to make it
@@ -892,7 +892,7 @@ UUID ObjectFileELF::GetUUID() {
       }
     } else {
       if (!m_gnu_debuglink_crc)
-        m_gnu_debuglink_crc = calc_crc32(0, m_data);
+        m_gnu_debuglink_crc = calc_crc32(0, *m_data_nsp.get());
       if (m_gnu_debuglink_crc) {
         // Use 4 bytes of crc from the .gnu_debuglink section.
         u32le data(m_gnu_debuglink_crc);
@@ -1078,7 +1078,8 @@ size_t ObjectFileELF::GetProgramHeaderInfo(ProgramHeaderColl &program_headers,
 
 // ParseProgramHeaders
 bool ObjectFileELF::ParseProgramHeaders() {
-  return GetProgramHeaderInfo(m_program_headers, m_data, m_header) != 0;
+  return GetProgramHeaderInfo(m_program_headers, *m_data_nsp.get(), m_header) !=
+         0;
 }
 
 lldb_private::Status
@@ -1668,8 +1669,8 @@ ObjectFileELF::StripLinkerSymbolAnnotations(llvm::StringRef symbol_name) const {
 
 // ParseSectionHeaders
 size_t ObjectFileELF::ParseSectionHeaders() {
-  return GetSectionHeaderInfo(m_section_headers, m_data, m_header, m_uuid,
-                              m_gnu_debuglink_file, m_gnu_debuglink_crc,
+  return GetSectionHeaderInfo(m_section_headers, *m_data_nsp.get(), m_header,
+                              m_uuid, m_gnu_debuglink_file, m_gnu_debuglink_crc,
                               m_arch_spec);
 }
 
@@ -3678,7 +3679,8 @@ ArchSpec ObjectFileELF::GetArchitecture() {
       if (H.p_type != PT_NOTE || H.p_offset == 0 || H.p_filesz == 0)
         continue;
       DataExtractor data;
-      if (data.SetData(m_data, H.p_offset, H.p_filesz) == H.p_filesz) {
+      if (data.SetData(*m_data_nsp.get(), H.p_offset, H.p_filesz) ==
+          H.p_filesz) {
         UUID uuid;
         RefineModuleDetailsFromNote(data, m_arch_spec, uuid);
       }
@@ -3833,10 +3835,10 @@ llvm::ArrayRef<ELFProgramHeader> ObjectFileELF::ProgramHeaders() {
 }
 
 DataExtractor ObjectFileELF::GetSegmentData(const ELFProgramHeader &H) {
-  // Try and read the program header from our cached m_data which can come from
-  // the file on disk being mmap'ed or from the initial part of the ELF file we
-  // read from memory and cached.
-  DataExtractor data = DataExtractor(m_data, H.p_offset, H.p_filesz);
+  // Try and read the program header from our cached m_data_nsp which can come
+  // from the file on disk being mmap'ed or from the initial part of the ELF
+  // file we read from memory and cached.
+  DataExtractor data = DataExtractor(*m_data_nsp.get(), H.p_offset, H.p_filesz);
   if (data.GetByteSize() == H.p_filesz)
     return data;
   if (IsInMemory()) {