[NFC] Split portions of DWARFDataExtractor into DWARFDataExtractorSimple.

Currently, DWARFDataExtractor can extract data without performing
relocations, but is coded such that it still depends on all the
relocation machinery, like DWARFSections and similar.

Extract most functionality into a new base class,
DWARFDataExtractorSimple, and have DWARFDataExtractor add the
relocation dependent pieces as overrides. This will allow moving
DWARFDataExtractorSimple into a new lower-level, lighter-weight
library with fewer external dependencies.

This is another in a series of refactoring changes to create a new
better-layered, lo-level Dwarf library that can be called from
lower-level code without circular dependencies.

Author: Sterling-Augustine

llvm/include/llvm/DebugInfo/DWARF/DWARFDataExtractor.h

@@ -10,79 +10,46 @@
 #define LLVM_DEBUGINFO_DWARF_DWARFDATAEXTRACTOR_H
 
 #include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/DebugInfo/DWARF/DWARFDataExtractorSimple.h"
 #include "llvm/DebugInfo/DWARF/DWARFSection.h"
-#include "llvm/Support/DataExtractor.h"
 
 namespace llvm {
 class DWARFObject;
 
-/// A DataExtractor (typically for an in-memory copy of an object-file section)
-/// plus a relocation map for that section, if there is one.
-class DWARFDataExtractor : public DataExtractor {
+/// A DWARFDataExtractorSimple (typically for an in-memory copy of an
+/// object-file section) plus a relocation map for that section, if there is
+/// one.
+class DWARFDataExtractor : public DWARFDataExtractorSimple {
   const DWARFObject *Obj = nullptr;
   const DWARFSection *Section = nullptr;
 
 public:
+  using DWARFDataExtractorSimple::DWARFDataExtractorSimple;
+
   /// Constructor for the normal case of extracting data from a DWARF section.
   /// The DWARFSection's lifetime must be at least as long as the extractor's.
   DWARFDataExtractor(const DWARFObject &Obj, const DWARFSection &Section,
                      bool IsLittleEndian, uint8_t AddressSize)
-      : DataExtractor(Section.Data, IsLittleEndian, AddressSize), Obj(&Obj),
-        Section(&Section) {}
-
-  /// Constructor for cases when there are no relocations.
-  DWARFDataExtractor(StringRef Data, bool IsLittleEndian, uint8_t AddressSize)
-    : DataExtractor(Data, IsLittleEndian, AddressSize) {}
-  DWARFDataExtractor(ArrayRef<uint8_t> Data, bool IsLittleEndian,
-                     uint8_t AddressSize)
-      : DataExtractor(
-            StringRef(reinterpret_cast<const char *>(Data.data()), Data.size()),
-            IsLittleEndian, AddressSize) {}
+      : DWARFDataExtractorSimple(Section.Data, IsLittleEndian, AddressSize),
+        Obj(&Obj), Section(&Section) {}
 
   /// Truncating constructor
   DWARFDataExtractor(const DWARFDataExtractor &Other, size_t Length)
-      : DataExtractor(Other.getData().substr(0, Length), Other.isLittleEndian(),
-                      Other.getAddressSize()),
+      : DWARFDataExtractorSimple(Other.getData().substr(0, Length),
+                                 Other.isLittleEndian(),
+                                 Other.getAddressSize()),
         Obj(Other.Obj), Section(Other.Section) {}
 
-  /// Extracts the DWARF "initial length" field, which can either be a 32-bit
-  /// value smaller than 0xfffffff0, or the value 0xffffffff followed by a
-  /// 64-bit length. Returns the actual length, and the DWARF format which is
-  /// encoded in the field. In case of errors, it returns {0, DWARF32} and
-  /// leaves the offset unchanged.
-  std::pair<uint64_t, dwarf::DwarfFormat>
-  getInitialLength(uint64_t *Off, Error *Err = nullptr) const;
-
-  std::pair<uint64_t, dwarf::DwarfFormat> getInitialLength(Cursor &C) const {
-    return getInitialLength(&getOffset(C), &getError(C));
-  }
-
   /// Extracts a value and applies a relocation to the result if
   /// one exists for the given offset.
   uint64_t getRelocatedValue(uint32_t Size, uint64_t *Off,
                              uint64_t *SectionIndex = nullptr,
-                             Error *Err = nullptr) const;
+                             Error *Err = nullptr) const override;
+
   uint64_t getRelocatedValue(Cursor &C, uint32_t Size,
-                             uint64_t *SectionIndex = nullptr) const {
+                             uint64_t *SectionIndex = nullptr) const override {
     return getRelocatedValue(Size, &getOffset(C), SectionIndex, &getError(C));
   }
-
-  /// Extracts an address-sized value and applies a relocation to the result if
-  /// one exists for the given offset.
-  uint64_t getRelocatedAddress(uint64_t *Off, uint64_t *SecIx = nullptr) const {
-    return getRelocatedValue(getAddressSize(), Off, SecIx);
-  }
-  uint64_t getRelocatedAddress(Cursor &C, uint64_t *SecIx = nullptr) const {
-    return getRelocatedValue(getAddressSize(), &getOffset(C), SecIx,
-                             &getError(C));
-  }
-
-  /// Extracts a DWARF-encoded pointer in \p Offset using \p Encoding.
-  /// There is a DWARF encoding that uses a PC-relative adjustment.
-  /// For these values, \p AbsPosOffset is used to fix them, which should
-  /// reflect the absolute address of this pointer.
-  std::optional<uint64_t> getEncodedPointer(uint64_t *Offset, uint8_t Encoding,
-                                            uint64_t AbsPosOffset = 0) const;
 };
 
 } // end namespace llvm

llvm/include/llvm/DebugInfo/DWARF/DWARFDataExtractorSimple.h

@@ -0,0 +1,88 @@
+//===- DWARFDataExtractorSimple.h -------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+// Non relocating, low-level dwarf-data extractor. Suitable for use from
+// libraries that cannot have build-time dependencies on relocation providers.
+
+#ifndef LLVM_DEBUGINFO_DWARF_DWARFDATAEXTRACTORSIMPLE_H
+#define LLVM_DEBUGINFO_DWARF_DWARFDATAEXTRACTORSIMPLE_H
+
+#include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/Support/DataExtractor.h"
+
+namespace llvm {
+
+/// A DataExtractor suitable use for parsing dwarf from memory with minimal
+/// dwarf context--no sections and no objects.  getRelocated* functions
+/// return raw values.
+
+class DWARFDataExtractorSimple : public DataExtractor {
+
+public:
+  DWARFDataExtractorSimple(StringRef Data, bool IsLittleEndian,
+                           uint8_t AddressSize)
+      : DataExtractor(Data, IsLittleEndian, AddressSize) {}
+  DWARFDataExtractorSimple(ArrayRef<uint8_t> Data, bool IsLittleEndian,
+                           uint8_t AddressSize)
+      : DataExtractor(
+            StringRef(reinterpret_cast<const char *>(Data.data()), Data.size()),
+            IsLittleEndian, AddressSize) {}
+
+  /// Truncating constructor
+  DWARFDataExtractorSimple(const DWARFDataExtractorSimple &Other, size_t Length)
+      : DataExtractor(Other.getData().substr(0, Length), Other.isLittleEndian(),
+                      Other.getAddressSize()) {}
+
+  virtual ~DWARFDataExtractorSimple() = default;
+
+  /// Extracts the DWARF "initial length" field, which can either be a 32-bit
+  /// value smaller than 0xfffffff0, or the value 0xffffffff followed by a
+  /// 64-bit length. Returns the actual length, and the DWARF format which is
+  /// encoded in the field. In case of errors, it returns {0, DWARF32} and
+  /// leaves the offset unchanged.
+  std::pair<uint64_t, dwarf::DwarfFormat>
+  getInitialLength(uint64_t *Off, Error *Err = nullptr) const;
+
+  std::pair<uint64_t, dwarf::DwarfFormat> getInitialLength(Cursor &C) const {
+    return getInitialLength(&getOffset(C), &getError(C));
+  }
+
+  /// Extracts a value and returns it unrelocated. Named such to implement the
+  /// required interface.
+  virtual uint64_t getRelocatedValue(uint32_t Size, uint64_t *Off,
+                                     uint64_t *SectionIndex = nullptr,
+                                     Error *Err = nullptr) const {
+    assert(SectionIndex == nullptr &&
+           "DWARFDATAExtractorSimple cannot take section indices.");
+    return getUnsigned(Off, Size, Err);
+  }
+  virtual uint64_t getRelocatedValue(Cursor &C, uint32_t Size,
+                                     uint64_t *SectionIndex = nullptr) const {
+    return getRelocatedValue(Size, &getOffset(C), SectionIndex, &getError(C));
+  }
+
+  /// Extracts an address-sized value.
+  uint64_t getRelocatedAddress(uint64_t *Off, uint64_t *SecIx = nullptr) const {
+    return getRelocatedValue(getAddressSize(), Off, SecIx);
+  }
+  uint64_t getRelocatedAddress(Cursor &C, uint64_t *SecIx = nullptr) const {
+    return getRelocatedValue(getAddressSize(), &getOffset(C), SecIx,
+                             &getError(C));
+  }
+
+  /// Extracts a DWARF-encoded pointer in \p Offset using \p Encoding.
+  /// There is a DWARF encoding that uses a PC-relative adjustment.
+  /// For these values, \p AbsPosOffset is used to fix them, which should
+  /// reflect the absolute address of this pointer.
+  std::optional<uint64_t> getEncodedPointer(uint64_t *Offset, uint8_t Encoding,
+                                            uint64_t AbsPosOffset = 0) const;
+};
+
+} // end namespace llvm
+
+#endif // LLVM_DEBUGINFO_DWARF_DWARFDATAEXTRACTOR_H

llvm/lib/DebugInfo/DWARF/CMakeLists.txt

@@ -5,6 +5,7 @@ add_llvm_component_library(LLVMDebugInfoDWARF
   DWARFCompileUnit.cpp
   DWARFContext.cpp
   DWARFDataExtractor.cpp
+  DWARFDataExtractorSimple.cpp
   DWARFDebugAbbrev.cpp
   DWARFDebugAddr.cpp
   DWARFDebugArangeSet.cpp

llvm/lib/DebugInfo/DWARF/DWARFDataExtractor.cpp

@@ -13,38 +13,6 @@
 
 using namespace llvm;
 
-std::pair<uint64_t, dwarf::DwarfFormat>
-DWARFDataExtractor::getInitialLength(uint64_t *Off, Error *Err) const {
-  ErrorAsOutParameter ErrAsOut(Err);
-  if (Err && *Err)
-    return {0, dwarf::DWARF32};
-
-  Cursor C(*Off);
-  uint64_t Length = getRelocatedValue(C, 4);
-  dwarf::DwarfFormat Format = dwarf::DWARF32;
-  if (Length == dwarf::DW_LENGTH_DWARF64) {
-    Length = getRelocatedValue(C, 8);
-    Format = dwarf::DWARF64;
-  } else if (Length >= dwarf::DW_LENGTH_lo_reserved) {
-    cantFail(C.takeError());
-    if (Err)
-      *Err = createStringError(
-          errc::invalid_argument,
-          "unsupported reserved unit length of value 0x%8.8" PRIx64, Length);
-    return {0, dwarf::DWARF32};
-  }
-
-  if (C) {
-    *Off = C.tell();
-    return {Length, Format};
-  }
-  if (Err)
-    *Err = C.takeError();
-  else
-    consumeError(C.takeError());
-  return {0, dwarf::DWARF32};
-}
-
 uint64_t DWARFDataExtractor::getRelocatedValue(uint32_t Size, uint64_t *Off,
                                                uint64_t *SecNdx,
                                                Error *Err) const {
@@ -67,71 +35,3 @@ uint64_t DWARFDataExtractor::getRelocatedValue(uint32_t Size, uint64_t *Off,
     R = object::resolveRelocation(E->Resolver, *E->Reloc2, E->SymbolValue2, R);
   return R;
 }
-
-std::optional<uint64_t>
-DWARFDataExtractor::getEncodedPointer(uint64_t *Offset, uint8_t Encoding,
-                                      uint64_t PCRelOffset) const {
-  if (Encoding == dwarf::DW_EH_PE_omit)
-    return std::nullopt;
-
-  uint64_t Result = 0;
-  uint64_t OldOffset = *Offset;
-  // First get value
-  switch (Encoding & 0x0F) {
-  case dwarf::DW_EH_PE_absptr:
-    switch (getAddressSize()) {
-    case 2:
-    case 4:
-    case 8:
-      Result = getUnsigned(Offset, getAddressSize());
-      break;
-    default:
-      return std::nullopt;
-    }
-    break;
-  case dwarf::DW_EH_PE_uleb128:
-    Result = getULEB128(Offset);
-    break;
-  case dwarf::DW_EH_PE_sleb128:
-    Result = getSLEB128(Offset);
-    break;
-  case dwarf::DW_EH_PE_udata2:
-    Result = getUnsigned(Offset, 2);
-    break;
-  case dwarf::DW_EH_PE_udata4:
-    Result = getUnsigned(Offset, 4);
-    break;
-  case dwarf::DW_EH_PE_udata8:
-    Result = getUnsigned(Offset, 8);
-    break;
-  case dwarf::DW_EH_PE_sdata2:
-    Result = getSigned(Offset, 2);
-    break;
-  case dwarf::DW_EH_PE_sdata4:
-    Result = SignExtend64<32>(getRelocatedValue(4, Offset));
-    break;
-  case dwarf::DW_EH_PE_sdata8:
-    Result = getRelocatedValue(8, Offset);
-    break;
-  default:
-    return std::nullopt;
-  }
-  // Then add relative offset, if required
-  switch (Encoding & 0x70) {
-  case dwarf::DW_EH_PE_absptr:
-    // do nothing
-    break;
-  case dwarf::DW_EH_PE_pcrel:
-    Result += PCRelOffset;
-    break;
-  case dwarf::DW_EH_PE_datarel:
-  case dwarf::DW_EH_PE_textrel:
-  case dwarf::DW_EH_PE_funcrel:
-  case dwarf::DW_EH_PE_aligned:
-  default:
-    *Offset = OldOffset;
-    return std::nullopt;
-  }
-
-  return Result;
-}