[WebAssembly] Add llvm-objdump support for wasm file format

This is the first part of an effort to add wasm binary
support across all llvm tools.

Patch by Sam Clegg

Differential Revision: https://reviews.llvm.org/D26172

llvm-svn: 288251

5 files changed, 166 insertions, 1 deletions

diff --git a/llvm/include/llvm/Object/Binary.h b/llvm/include/llvm/Object/Binary.h
index 5dff5406fcd..00d06e3c743 100644
--- a/llvm/include/llvm/Object/Binary.h
+++ b/llvm/include/llvm/Object/Binary.h
@@ -59,6 +59,8 @@ protected:
     ID_MachO64L, // MachO 64-bit, little endian
     ID_MachO64B, // MachO 64-bit, big endian
 
+    ID_Wasm,
+
     ID_EndObjects
   };
 
@@ -115,6 +117,8 @@ public:
     return TypeID == ID_COFF;
   }
 
+  bool isWasm() const { return TypeID == ID_Wasm; }
+
   bool isCOFFImportFile() const {
     return TypeID == ID_COFFImportFile;
   }
diff --git a/llvm/include/llvm/Object/ObjectFile.h b/llvm/include/llvm/Object/ObjectFile.h
index 07d6b134086..13d5845c3a7 100644
--- a/llvm/include/llvm/Object/ObjectFile.h
+++ b/llvm/include/llvm/Object/ObjectFile.h
@@ -29,6 +29,7 @@ namespace object {
 class ObjectFile;
 class COFFObjectFile;
 class MachOObjectFile;
+class WasmObjectFile;
 
 class SymbolRef;
 class symbol_iterator;
@@ -304,6 +305,8 @@ public:
                         uint32_t UniversalCputype = 0,
                         uint32_t UniversalIndex = 0);
 
+  static Expected<std::unique_ptr<WasmObjectFile>>
+  createWasmObjectFile(MemoryBufferRef Object);
 };
 
 // Inline function definitions.
diff --git a/llvm/include/llvm/Object/Wasm.h b/llvm/include/llvm/Object/Wasm.h
new file mode 100644
index 00000000000..2ece6a6c377
--- /dev/null
+++ b/llvm/include/llvm/Object/Wasm.h
@@ -0,0 +1,99 @@
+//===- WasmObjectFile.h - Wasm object file implementation -------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file declares the WasmObjectFile class, which implements the ObjectFile
+// interface for Wasm files.
+//
+// See: https://github.com/WebAssembly/design/blob/master/BinaryEncoding.md
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_OBJECT_WASM_H
+#define LLVM_OBJECT_WASM_H
+
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Support/Wasm.h"
+
+namespace llvm {
+namespace object {
+
+class WasmObjectFile : public ObjectFile {
+public:
+  WasmObjectFile(MemoryBufferRef Object, Error &Err);
+  const wasm::WasmObjectHeader &getHeader() const;
+  const wasm::WasmSection *getWasmSection(const SectionRef &Section) const;
+  static bool classof(const Binary *v) { return v->isWasm(); }
+
+protected:
+  void moveSymbolNext(DataRefImpl &Symb) const override;
+
+  std::error_code printSymbolName(raw_ostream &OS,
+                                  DataRefImpl Symb) const override;
+
+  uint32_t getSymbolFlags(DataRefImpl Symb) const override;
+
+  basic_symbol_iterator symbol_begin() const override;
+
+  basic_symbol_iterator symbol_end() const override;
+  Expected<StringRef> getSymbolName(DataRefImpl Symb) const override;
+
+  Expected<uint64_t> getSymbolAddress(DataRefImpl Symb) const override;
+  uint64_t getSymbolValueImpl(DataRefImpl Symb) const override;
+  uint32_t getSymbolAlignment(DataRefImpl Symb) const override;
+  uint64_t getCommonSymbolSizeImpl(DataRefImpl Symb) const override;
+  Expected<SymbolRef::Type> getSymbolType(DataRefImpl Symb) const override;
+  Expected<section_iterator> getSymbolSection(DataRefImpl Symb) const override;
+
+  // Overrides from SectionRef.
+  void moveSectionNext(DataRefImpl &Sec) const override;
+  std::error_code getSectionName(DataRefImpl Sec,
+                                 StringRef &Res) const override;
+  uint64_t getSectionAddress(DataRefImpl Sec) const override;
+  uint64_t getSectionSize(DataRefImpl Sec) const override;
+  std::error_code getSectionContents(DataRefImpl Sec,
+                                     StringRef &Res) const override;
+  uint64_t getSectionAlignment(DataRefImpl Sec) const override;
+  bool isSectionCompressed(DataRefImpl Sec) const override;
+  bool isSectionText(DataRefImpl Sec) const override;
+  bool isSectionData(DataRefImpl Sec) const override;
+  bool isSectionBSS(DataRefImpl Sec) const override;
+  bool isSectionVirtual(DataRefImpl Sec) const override;
+  bool isSectionBitcode(DataRefImpl Sec) const override;
+  relocation_iterator section_rel_begin(DataRefImpl Sec) const override;
+  relocation_iterator section_rel_end(DataRefImpl Sec) const override;
+  section_iterator getRelocatedSection(DataRefImpl Sec) const override;
+
+  // Overrides from RelocationRef.
+  void moveRelocationNext(DataRefImpl &Rel) const override;
+  uint64_t getRelocationOffset(DataRefImpl Rel) const override;
+  symbol_iterator getRelocationSymbol(DataRefImpl Rel) const override;
+  uint64_t getRelocationType(DataRefImpl Rel) const override;
+  void getRelocationTypeName(DataRefImpl Rel,
+                             SmallVectorImpl<char> &Result) const override;
+
+  section_iterator section_begin() const override;
+  section_iterator section_end() const override;
+  uint8_t getBytesInAddress() const override;
+  StringRef getFileFormatName() const override;
+  unsigned getArch() const override;
+  SubtargetFeatures getFeatures() const override;
+  bool isRelocatableObject() const override;
+
+private:
+  const uint8_t *getPtr(size_t Offset) const;
+  Error parseUserSection(wasm::WasmSection &Sec, const uint8_t *Ptr,
+                         size_t Length);
+
+  wasm::WasmObjectHeader Header;
+  std::vector<wasm::WasmSection> Sections;
+};
+}
+}
+
+#endif
diff --git a/llvm/include/llvm/Support/FileSystem.h b/llvm/include/llvm/Support/FileSystem.h
index 8503aa35ca7..58db77de4bc 100644
--- a/llvm/include/llvm/Support/FileSystem.h
+++ b/llvm/include/llvm/Support/FileSystem.h
@@ -262,7 +262,8 @@ struct file_magic {
     coff_object,              ///< COFF object file
     coff_import_library,      ///< COFF import library
     pecoff_executable,        ///< PECOFF executable file
-    windows_resource          ///< Windows compiled resource file (.rc)
+    windows_resource,         ///< Windows compiled resource file (.rc)
+    wasm_object               ///< WebAssembly Object file
   };
 
   bool is_object() const {
diff --git a/llvm/include/llvm/Support/Wasm.h b/llvm/include/llvm/Support/Wasm.h
new file mode 100644
index 00000000000..c6e6ff64f7a
--- /dev/null
+++ b/llvm/include/llvm/Support/Wasm.h
@@ -0,0 +1,58 @@
+//===- Wasm.h - Wasm object file format -------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines manifest constants for the wasm object file format.
+// See: https://github.com/WebAssembly/design/blob/master/BinaryEncoding.md
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_WASM_H
+#define LLVM_SUPPORT_WASM_H
+
+#include "llvm/ADT/ArrayRef.h"
+
+namespace llvm {
+namespace wasm {
+
+// Object file magic string.
+const char WasmMagic[] = {'\0', 'a', 's', 'm'};
+// Wasm binary format version
+const uint32_t WasmVersion = 0xd;
+
+struct WasmObjectHeader {
+  StringRef Magic;
+  uint32_t Version;
+};
+
+struct WasmSection {
+  uint32_t Type;             // Section type (See below)
+  uint32_t Offset;           // Offset with in the file
+  StringRef Name;            // Section name (User-defined sections only)
+  ArrayRef<uint8_t> Content; // Section content
+};
+
+enum : unsigned {
+  WASM_SEC_USER = 0,     // User-defined section
+  WASM_SEC_TYPE = 1,     // Function signature declarations
+  WASM_SEC_IMPORT = 2,   // Import declarations
+  WASM_SEC_FUNCTION = 3, // Function declarations
+  WASM_SEC_TABLE = 4,    // Indirect function table and other tables
+  WASM_SEC_MEMORY = 5,   // Memory attributes
+  WASM_SEC_GLOBAL = 6,   // Global declarations
+  WASM_SEC_EXPORT = 7,   // Exports
+  WASM_SEC_START = 8,    // Start function declaration
+  WASM_SEC_ELEM = 9,     // Elements section
+  WASM_SEC_CODE = 10,    // Function bodies (code)
+  WASM_SEC_DATA = 11     // Data segments
+};
+
+} // end namespace wasm
+} // end namespace llvm
+
+#endif