DWARF parsing and writing support using LLVM (#2520)

This imports LLVM code for DWARF handling. That code has the
Apache 2 license like us. It's also the same code used to
emit DWARF in the common toolchain, so it seems like a safe choice.

This adds two passes: --dwarfdump which runs the same code LLVM
runs for llvm-dwarfdump. This shows we can parse it ok, and will
be useful for debugging. And --dwarfupdate writes out the DWARF
sections (unchanged from what we read, so it just roundtrips - for
updating we need #2515).

This puts LLVM in thirdparty which is added here.

All the LLVM code is behind USE_LLVM_DWARF, which is on
by default, but off in JS for now, as it increases code size by 20%.

This current approach imports the LLVM files directly. This is not
how they are intended to be used, so it required a bunch of
local changes - more than I expected actually, for the platform-specific
stuff. For now this seems to work, so it may be good enough, but
in the long term we may want to switch to linking against libllvm.
A downside to doing that is that binaryen users would need to
have an LLVM build, and even in the waterfall builds we'd have a
problem - while we ship LLVM there anyhow, we constantly update
it, which means that binaryen would need to be on latest llvm all
the time too (which otherwise, given DWARF is quite stable, we
might not need to constantly update).

An even larger issue is that as I did this work I learned about how
DWARF works in LLVM, and while the reading code is easy to
reuse, the writing code is trickier. The main code path is heavily
integrated with the MC layer, which we don't have - we might want
to create a "fake MC layer" for that, but it sounds hard. Instead,
there is the YAML path which is used mostly for testing, and which
can convert DWARF to and from YAML and from binary. Using
the non-YAML parts there, we can convert binary DWARF to
the YAML layer's nice Info data, then convert that to binary. This
works, however, this is not the path LLVM uses normally, and it
supports only some basic DWARF sections - I had to add ranges
support, in fact. So if we need more complex things, we may end
up needing to use the MC layer approach, or consider some other
DWARF library. However, hopefully that should not affect the core
binaryen code which just calls a library for DWARF stuff.

Helps #2400

1 files changed, 320 insertions, 0 deletions

diff --git a/third_party/llvm-project/include/llvm/ObjectYAML/DWARFYAML.h b/third_party/llvm-project/include/llvm/ObjectYAML/DWARFYAML.h
new file mode 100644
index 000000000..8ab3de4f1
--- /dev/null
+++ b/third_party/llvm-project/include/llvm/ObjectYAML/DWARFYAML.h
@@ -0,0 +1,320 @@
+//===- DWARFYAML.h - DWARF YAMLIO implementation ----------------*- 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
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file declares classes for handling the YAML representation
+/// of DWARF Debug Info.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_OBJECTYAML_DWARFYAML_H
+#define LLVM_OBJECTYAML_DWARFYAML_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/Support/YAMLTraits.h"
+#include <cstdint>
+#include <vector>
+
+namespace llvm {
+namespace DWARFYAML {
+
+struct InitialLength {
+  uint32_t TotalLength;
+  uint64_t TotalLength64;
+
+  bool isDWARF64() const { return TotalLength == UINT32_MAX; }
+
+  uint64_t getLength() const {
+    return isDWARF64() ? TotalLength64 : TotalLength;
+  }
+
+  void setLength(uint64_t Len) {
+    if (Len >= (uint64_t)UINT32_MAX) {
+      TotalLength64 = Len;
+      TotalLength = UINT32_MAX;
+    } else {
+      TotalLength = Len;
+    }
+  }
+};
+
+struct AttributeAbbrev {
+  llvm::dwarf::Attribute Attribute;
+  llvm::dwarf::Form Form;
+  llvm::yaml::Hex64 Value; // Some DWARF5 attributes have values
+};
+
+struct Abbrev {
+  llvm::yaml::Hex32 Code;
+  llvm::dwarf::Tag Tag;
+  llvm::dwarf::Constants Children;
+  std::vector<AttributeAbbrev> Attributes;
+};
+
+struct ARangeDescriptor {
+  llvm::yaml::Hex64 Address;
+  uint64_t Length;
+};
+
+struct ARange {
+  InitialLength Length;
+  uint16_t Version;
+  uint32_t CuOffset;
+  uint8_t AddrSize;
+  uint8_t SegSize;
+  std::vector<ARangeDescriptor> Descriptors;
+};
+
+// XXX BINARYEN <--
+struct Range {
+  uint64_t Start;
+  uint64_t End;
+  uint64_t SectionIndex; // XXX ?
+};
+// XXX BINARYEN -->
+
+struct PubEntry {
+  llvm::yaml::Hex32 DieOffset;
+  llvm::yaml::Hex8 Descriptor;
+  StringRef Name;
+};
+
+struct PubSection {
+  InitialLength Length;
+  uint16_t Version;
+  uint32_t UnitOffset;
+  uint32_t UnitSize;
+  bool IsGNUStyle = false;
+  std::vector<PubEntry> Entries;
+};
+
+struct FormValue {
+  llvm::yaml::Hex64 Value;
+  StringRef CStr;
+  std::vector<llvm::yaml::Hex8> BlockData;
+};
+
+struct Entry {
+  llvm::yaml::Hex32 AbbrCode;
+  std::vector<FormValue> Values;
+};
+
+struct Unit {
+  InitialLength Length;
+  uint16_t Version;
+  llvm::dwarf::UnitType Type; // Added in DWARF 5
+  uint32_t AbbrOffset;
+  uint8_t AddrSize;
+  std::vector<Entry> Entries;
+};
+
+struct File {
+  StringRef Name;
+  uint64_t DirIdx;
+  uint64_t ModTime;
+  uint64_t Length;
+};
+
+struct LineTableOpcode {
+  dwarf::LineNumberOps Opcode;
+  uint64_t ExtLen;
+  dwarf::LineNumberExtendedOps SubOpcode;
+  uint64_t Data;
+  int64_t SData;
+  File FileEntry;
+  std::vector<llvm::yaml::Hex8> UnknownOpcodeData;
+  std::vector<llvm::yaml::Hex64> StandardOpcodeData;
+};
+
+struct LineTable {
+  InitialLength Length;
+  uint16_t Version;
+  uint64_t PrologueLength;
+  uint8_t MinInstLength;
+  uint8_t MaxOpsPerInst;
+  uint8_t DefaultIsStmt;
+  uint8_t LineBase;
+  uint8_t LineRange;
+  uint8_t OpcodeBase;
+  std::vector<uint8_t> StandardOpcodeLengths;
+  std::vector<StringRef> IncludeDirs;
+  std::vector<File> Files;
+  std::vector<LineTableOpcode> Opcodes;
+};
+
+struct Data {
+  bool IsLittleEndian;
+  std::vector<Abbrev> AbbrevDecls;
+  std::vector<StringRef> DebugStrings;
+  std::vector<ARange> ARanges;
+  std::vector<Range> Ranges; // XXX BINARYEN
+  PubSection PubNames;
+  PubSection PubTypes;
+
+  PubSection GNUPubNames;
+  PubSection GNUPubTypes;
+
+  std::vector<Unit> CompileUnits;
+
+  std::vector<LineTable> DebugLines;
+
+  bool isEmpty() const;
+};
+
+} // end namespace DWARFYAML
+} // end namespace llvm
+
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::AttributeAbbrev)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::Abbrev)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::ARangeDescriptor)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::ARange)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::Range) // XXX BINARYEN
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::PubEntry)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::Unit)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::FormValue)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::Entry)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::File)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::LineTable)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::LineTableOpcode)
+
+namespace llvm {
+namespace yaml {
+
+template <> struct MappingTraits<DWARFYAML::Data> {
+  static void mapping(IO &IO, DWARFYAML::Data &DWARF);
+};
+
+template <> struct MappingTraits<DWARFYAML::Abbrev> {
+  static void mapping(IO &IO, DWARFYAML::Abbrev &Abbrev);
+};
+
+template <> struct MappingTraits<DWARFYAML::AttributeAbbrev> {
+  static void mapping(IO &IO, DWARFYAML::AttributeAbbrev &AttAbbrev);
+};
+
+template <> struct MappingTraits<DWARFYAML::ARangeDescriptor> {
+  static void mapping(IO &IO, DWARFYAML::ARangeDescriptor &Descriptor);
+};
+
+template <> struct MappingTraits<DWARFYAML::ARange> {
+  static void mapping(IO &IO, DWARFYAML::ARange &Range);
+};
+
+template <> struct MappingTraits<DWARFYAML::Range> { // XXX BINARYEN
+  static void mapping(IO &IO, DWARFYAML::Range &Range);
+};
+
+template <> struct MappingTraits<DWARFYAML::PubEntry> {
+  static void mapping(IO &IO, DWARFYAML::PubEntry &Entry);
+};
+
+template <> struct MappingTraits<DWARFYAML::PubSection> {
+  static void mapping(IO &IO, DWARFYAML::PubSection &Section);
+};
+
+template <> struct MappingTraits<DWARFYAML::Unit> {
+  static void mapping(IO &IO, DWARFYAML::Unit &Unit);
+};
+
+template <> struct MappingTraits<DWARFYAML::Entry> {
+  static void mapping(IO &IO, DWARFYAML::Entry &Entry);
+};
+
+template <> struct MappingTraits<DWARFYAML::FormValue> {
+  static void mapping(IO &IO, DWARFYAML::FormValue &FormValue);
+};
+
+template <> struct MappingTraits<DWARFYAML::File> {
+  static void mapping(IO &IO, DWARFYAML::File &File);
+};
+
+template <> struct MappingTraits<DWARFYAML::LineTableOpcode> {
+  static void mapping(IO &IO, DWARFYAML::LineTableOpcode &LineTableOpcode);
+};
+
+template <> struct MappingTraits<DWARFYAML::LineTable> {
+  static void mapping(IO &IO, DWARFYAML::LineTable &LineTable);
+};
+
+template <> struct MappingTraits<DWARFYAML::InitialLength> {
+  static void mapping(IO &IO, DWARFYAML::InitialLength &DWARF);
+};
+
+#define HANDLE_DW_TAG(unused, name, unused2, unused3, unused4)                 \
+  io.enumCase(value, "DW_TAG_" #name, dwarf::DW_TAG_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::Tag> {
+  static void enumeration(IO &io, dwarf::Tag &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex16>(value);
+  }
+};
+
+#define HANDLE_DW_LNS(unused, name)                                            \
+  io.enumCase(value, "DW_LNS_" #name, dwarf::DW_LNS_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::LineNumberOps> {
+  static void enumeration(IO &io, dwarf::LineNumberOps &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex8>(value);
+  }
+};
+
+#define HANDLE_DW_LNE(unused, name)                                            \
+  io.enumCase(value, "DW_LNE_" #name, dwarf::DW_LNE_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::LineNumberExtendedOps> {
+  static void enumeration(IO &io, dwarf::LineNumberExtendedOps &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex16>(value);
+  }
+};
+
+#define HANDLE_DW_AT(unused, name, unused2, unused3)                           \
+  io.enumCase(value, "DW_AT_" #name, dwarf::DW_AT_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::Attribute> {
+  static void enumeration(IO &io, dwarf::Attribute &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex16>(value);
+  }
+};
+
+#define HANDLE_DW_FORM(unused, name, unused2, unused3)                         \
+  io.enumCase(value, "DW_FORM_" #name, dwarf::DW_FORM_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::Form> {
+  static void enumeration(IO &io, dwarf::Form &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex16>(value);
+  }
+};
+
+#define HANDLE_DW_UT(unused, name)                                             \
+  io.enumCase(value, "DW_UT_" #name, dwarf::DW_UT_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::UnitType> {
+  static void enumeration(IO &io, dwarf::UnitType &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex8>(value);
+  }
+};
+
+template <> struct ScalarEnumerationTraits<dwarf::Constants> {
+  static void enumeration(IO &io, dwarf::Constants &value) {
+    io.enumCase(value, "DW_CHILDREN_no", dwarf::DW_CHILDREN_no);
+    io.enumCase(value, "DW_CHILDREN_yes", dwarf::DW_CHILDREN_yes);
+    io.enumFallback<Hex16>(value);
+  }
+};
+
+} // end namespace yaml
+} // end namespace llvm
+
+#endif // LLVM_OBJECTYAML_DWARFYAML_H