Refactor data-in-code annotations.

Use a dedicated MachO load command to annotate data-in-code regions.
This is the same format the linker produces for final executable images,
allowing consistency of representation and use of introspection tools
for both object and executable files.

Data-in-code regions are annotated via ".data_region"/".end_data_region"
directive pairs, with an optional region type.

data_region_directive := ".data_region" { region_type }
region_type := "jt8" | "jt16" | "jt32" | "jta32"
end_data_region_directive := ".end_data_region"

The previous handling of ARM-style "$d.*" labels was broken and has
been removed. Specifically, it didn't handle ARM vs. Thumb mode when
marking the end of the section.

rdar://11459456

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157062 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 19 insertions, 2 deletions

diff --git a/include/llvm/Object/MachOFormat.h b/include/llvm/Object/MachOFormat.h
index 089cde92a0..f30d431b69 100644
--- a/include/llvm/Object/MachOFormat.h
+++ b/include/llvm/Object/MachOFormat.h
@@ -97,7 +97,8 @@ namespace macho {
     DysymtabLoadCommandSize = 80,
     Nlist32Size = 12,
     Nlist64Size = 16,
-    RelocationInfoSize = 8
+    RelocationInfoSize = 8,
+    LinkeditLoadCommandSize = 16
   };
 
   /// \brief Constants for header magic field.
@@ -140,7 +141,8 @@ namespace macho {
     LCT_UUID = 0x1b,
     LCT_CodeSignature = 0x1d,
     LCT_SegmentSplitInfo = 0x1e,
-    LCT_FunctionStarts = 0x26
+    LCT_FunctionStarts = 0x26,
+    LCT_DataInCode = 0x29
   };
 
   /// \brief Load command structure.
@@ -280,6 +282,18 @@ namespace macho {
   };
 
   /// @}
+  /// @name Data-in-code Table Entry
+  /// @{
+
+  // See <mach-o/loader.h>.
+  enum DataRegionType { Data = 1, JumpTable8, JumpTable16, JumpTable32 };
+  struct DataInCodeTableEntry {
+    uint32_t Offset;  /* from mach_header to start of data region */
+    uint16_t Length;  /* number of bytes in data region */
+    uint16_t Kind;    /* a DataRegionType value  */
+  };
+
+  /// @}
   /// @name Indirect Symbol Table
   /// @{
 
diff --git a/include/llvm/Object/MachOObject.h b/include/llvm/Object/MachOObject.h
index 0560402743..86f150a294 100644
--- a/include/llvm/Object/MachOObject.h
+++ b/include/llvm/Object/MachOObject.h
@@ -174,6 +174,9 @@ public:
   void ReadSymbol64TableEntry(
     uint64_t SymbolTableOffset, unsigned Index,
     InMemoryStruct<macho::Symbol64TableEntry> &Res) const;
+  void ReadDataInCodeTableEntry(
+    uint64_t TableOffset, unsigned Index,
+    InMemoryStruct<macho::DataInCodeTableEntry> &Res) const;
   void ReadULEB128s(uint64_t Index, SmallVectorImpl<uint64_t> &Out) const;
 
   /// @}