Add MCSymbolizer for symbolic/annotated disassembly.

This is a basic first step towards symbolization of disassembled
instructions. This used to be done using externally provided (C API)
callbacks. This patch introduces:
- the MCSymbolizer class, that mimics the same functions that were used
  in the X86 and ARM disassemblers to symbolize immediate operands and
  to annotate loads based off PC (for things like c string literals).
- the MCExternalSymbolizer class, which implements the old C API.
- the MCRelocationInfo class, which provides a way for targets to
  translate relocations (either object::RelocationRef, or disassembler
  C API VariantKinds) to MCExprs.
- the MCObjectSymbolizer class, which does symbolization using what it
  finds in an object::ObjectFile. This makes simple symbolization (with
  no fancy relocation stuff) work for all object formats!
- x86-64 Mach-O and ELF MCRelocationInfos.
- A basic ARM Mach-O MCRelocationInfo, that provides just enough to
  support the C API VariantKinds.

Most of what works in otool (the only user of the old symbolization API
that I know of) for x86-64 symbolic disassembly (-tvV) works, namely:
- symbol references: call _foo; jmp 15 <_foo+50>
- relocations:       call _foo-_bar; call _foo-4
- __cf?string:       leaq 193(%rip), %rax ## literal pool for "hello"
Stub support is the main missing part (because libObject doesn't know,
among other things, about mach-o indirect symbols).

As for the MCSymbolizer API, instead of relying on the disassemblers
to call the tryAdding* methods, maybe this could be done automagically
using InstrInfo? For instance, even though PC-relative LEAs are used
to get the address of string literals in a typical Mach-O file, a MOV
would be used in an ELF file. And right now, the explicit symbolization
only recognizes PC-relative LEAs. InstrInfo should have already have
most of what is needed to know what to symbolize, so this can
definitely be improved.

I'd also like to remove object::RelocationRef::getValueString (it seems
only used by relocation printing in objdump), as simply printing the
created MCExpr is definitely enough (and cleaner than string concats).



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182625 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 328 insertions, 31 deletions

diff --git a/include/llvm/MC/MCDisassembler.h b/include/llvm/MC/MCDisassembler.h
index 36fbcb02d9..5ad2d98019 100644
--- a/include/llvm/MC/MCDisassembler.h
+++ b/include/llvm/MC/MCDisassembler.h
@@ -10,6 +10,9 @@
 #define LLVM_MC_MCDISASSEMBLER_H
 
 #include "llvm-c/Disassembler.h"
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/MC/MCSymbolizer.h"
+#include "llvm/MC/MCRelocationInfo.h"
 #include "llvm/Support/DataTypes.h"
 
 namespace llvm {
@@ -53,9 +56,8 @@ public:
   };
 
   /// Constructor     - Performs initial setup for the disassembler.
-  MCDisassembler(const MCSubtargetInfo &STI) : GetOpInfo(0), SymbolLookUp(0),
-                                               DisInfo(0), Ctx(0),
-                                               STI(STI), CommentStream(0) {}
+  MCDisassembler(const MCSubtargetInfo &STI) : STI(STI), Symbolizer(0),
+                                               CommentStream(0) {}
 
   virtual ~MCDisassembler();
 
@@ -82,39 +84,32 @@ public:
                                        raw_ostream &vStream,
                                        raw_ostream &cStream) const = 0;
 
-private:
-  //
-  // Hooks for symbolic disassembly via the public 'C' interface.
-  //
-  // The function to get the symbolic information for operands.
-  LLVMOpInfoCallback GetOpInfo;
-  // The function to lookup a symbol name.
-  LLVMSymbolLookupCallback SymbolLookUp;
-  // The pointer to the block of symbolic information for above call back.
-  void *DisInfo;
-  // The assembly context for creating symbols and MCExprs in place of
-  // immediate operands when there is symbolic information.
-  MCContext *Ctx;
 protected:
   // Subtarget information, for instruction decoding predicates if required.
   const MCSubtargetInfo &STI;
 
+private:
+  OwningPtr<MCSymbolizer> Symbolizer;
+
 public:
-  void setupForSymbolicDisassembly(LLVMOpInfoCallback getOpInfo,
-                                   LLVMSymbolLookupCallback symbolLookUp,
-                                   void *disInfo,
-                                   MCContext *ctx) {
-    GetOpInfo = getOpInfo;
-    SymbolLookUp = symbolLookUp;
-    DisInfo = disInfo;
-    Ctx = ctx;
-  }
-  LLVMOpInfoCallback getLLVMOpInfoCallback() const { return GetOpInfo; }
-  LLVMSymbolLookupCallback getLLVMSymbolLookupCallback() const {
-    return SymbolLookUp;
-  }
-  void *getDisInfoBlock() const { return DisInfo; }
-  MCContext *getMCContext() const { return Ctx; }
+  // Helpers around MCSymbolizer
+  bool tryAddingSymbolicOperand(MCInst &Inst,
+                                int64_t Value,
+                                uint64_t Address, bool IsBranch,
+                                uint64_t Offset, uint64_t InstSize) const;
+
+  void tryAddingPcLoadReferenceComment(int64_t Value, uint64_t Address) const;
+
+  /// Set \p Symzer as the current symbolizer.
+  /// This takes ownership of \p Symzer, and deletes the previously set one.
+  void setSymbolizer(OwningPtr<MCSymbolizer> &Symzer);
+
+  /// Sets up an external symbolizer that uses the C API callbacks.
+  void setupForSymbolicDisassembly(LLVMOpInfoCallback GetOpInfo,
+                                   LLVMSymbolLookupCallback SymbolLookUp,
+                                   void *DisInfo,
+                                   MCContext *Ctx,
+                                   OwningPtr<MCRelocationInfo> &RelInfo);
 
   // Marked mutable because we cache it inside the disassembler, rather than
   // having to pass it around as an argument through all the autogenerated code.
diff --git a/include/llvm/MC/MCExternalSymbolizer.h b/include/llvm/MC/MCExternalSymbolizer.h
new file mode 100644
index 0000000000..c942adca3b
--- /dev/null
+++ b/include/llvm/MC/MCExternalSymbolizer.h
@@ -0,0 +1,58 @@
+//===-- llvm/MC/MCExternalSymbolizer.h - ------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the declaration of the MCExternalSymbolizer class, which
+// enables library users to provide callbacks (through the C API) to do the
+// symbolization externally.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCEXTERNALSYMBOLIZER_H
+#define LLVM_MC_MCEXTERNALSYMBOLIZER_H
+
+#include "llvm-c/Disassembler.h"
+#include "llvm/MC/MCSymbolizer.h"
+
+namespace llvm {
+
+/// \brief Symbolize using user-provided, C API, callbacks.
+///
+/// See llvm-c/Disassembler.h.
+class MCExternalSymbolizer : public MCSymbolizer {
+
+  /// \name Hooks for symbolic disassembly via the public 'C' interface.
+  /// @{
+  /// The function to get the symbolic information for operands.
+  LLVMOpInfoCallback GetOpInfo;
+  /// The function to lookup a symbol name.
+  LLVMSymbolLookupCallback SymbolLookUp;
+  /// The pointer to the block of symbolic information for above call back.
+  void *DisInfo;
+  /// @}
+
+public:
+  MCExternalSymbolizer(MCContext &Ctx,
+                       OwningPtr<MCRelocationInfo> &RelInfo,
+                       LLVMOpInfoCallback getOpInfo,
+                       LLVMSymbolLookupCallback symbolLookUp,
+                       void *disInfo)
+    : MCSymbolizer(Ctx, RelInfo),
+      GetOpInfo(getOpInfo), SymbolLookUp(symbolLookUp), DisInfo(disInfo) {}
+
+  bool tryAddingSymbolicOperand(MCInst &MI, raw_ostream &CommentStream,
+                                int64_t Value,
+                                uint64_t Address, bool IsBranch,
+                                uint64_t Offset, uint64_t InstSize);
+  void tryAddingPcLoadReferenceComment(raw_ostream &CommentStream,
+                                       int64_t Value, uint64_t Address);
+};
+
+}
+
+#endif
diff --git a/include/llvm/MC/MCObjectSymbolizer.h b/include/llvm/MC/MCObjectSymbolizer.h
new file mode 100644
index 0000000000..0e3a17b8f7
--- /dev/null
+++ b/include/llvm/MC/MCObjectSymbolizer.h
@@ -0,0 +1,74 @@
+//===-- llvm/MC/MCObjectSymbolizer.h --------------------------------------===//
+//
+//                     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 MCObjectSymbolizer class, an MCSymbolizer that is
+// backed by an object::ObjectFile.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCOBJECTSYMBOLIZER_H
+#define LLVM_MC_MCOBJECTSYMBOLIZER_H
+
+#include "llvm/ADT/IntervalMap.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/MC/MCSymbolizer.h"
+#include "llvm/Object/ObjectFile.h"
+
+namespace llvm {
+
+class MCExpr;
+class MCInst;
+class MCRelocationInfo;
+class raw_ostream;
+
+/// \brief An ObjectFile-backed symbolizer.
+class MCObjectSymbolizer : public MCSymbolizer {
+protected:
+  const object::ObjectFile *Obj;
+
+  typedef DenseMap<uint64_t, object::RelocationRef> AddrToRelocMap;
+  // FIXME: Working around a missing SectionRef operator!= by storing
+  // DataRefImpl.p instead of SectionRef. Feel free to improve!
+  typedef IntervalMap<uint64_t, uintptr_t> AddrToSectionMap;
+
+  AddrToSectionMap::Allocator AddrToSectionAllocator;
+  AddrToSectionMap AddrToSection;
+
+  // Map a load address to the first relocation that applies there. As far as I
+  // know, if there are several relocations at the exact same address, they are
+  // related and the others can be determined from the first that was found in
+  // the relocation table. For instance, on x86-64 mach-o, a SUBTRACTOR
+  // relocation (referencing the minuend symbol) is followed by an UNSIGNED
+  // relocation (referencing the subtrahend symbol).
+  AddrToRelocMap AddrToReloc;
+
+  MCObjectSymbolizer(MCContext &Ctx, OwningPtr<MCRelocationInfo> &RelInfo,
+                     const object::ObjectFile *Obj);
+
+public:
+  /// \name Overridden MCSymbolizer methods:
+  /// @{
+  bool tryAddingSymbolicOperand(MCInst &MI, raw_ostream &cStream,
+                                int64_t Value,
+                                uint64_t Address, bool IsBranch,
+                                uint64_t Offset, uint64_t InstSize);
+
+  void tryAddingPcLoadReferenceComment(raw_ostream &cStream,
+                                       int64_t Value, uint64_t Address);
+  /// @}
+
+  /// \brief Create an object symbolizer for \p Obj.
+  static MCObjectSymbolizer *
+    createObjectSymbolizer(MCContext &Ctx, OwningPtr<MCRelocationInfo> &RelInfo,
+                           const object::ObjectFile *Obj);
+};
+
+}
+
+#endif
diff --git a/include/llvm/MC/MCRelocationInfo.h b/include/llvm/MC/MCRelocationInfo.h
new file mode 100644
index 0000000000..9dab90099b
--- /dev/null
+++ b/include/llvm/MC/MCRelocationInfo.h
@@ -0,0 +1,55 @@
+//==-- llvm/MC/MCRelocationInfo.h --------------------------------*- 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 MCRelocationInfo class, which provides methods to
+// create MCExprs from relocations, either found in an object::ObjectFile
+// (object::RelocationRef), or provided through the C API.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCRELOCATIONINFO_H
+#define LLVM_MC_MCRELOCATIONINFO_H
+
+#include "llvm/Support/Compiler.h"
+
+namespace llvm {
+
+namespace object {
+class RelocationRef;
+}
+class MCExpr;
+class MCContext;
+
+/// \brief Create MCExprs from relocations found in an object file.
+class MCRelocationInfo {
+  MCRelocationInfo(const MCRelocationInfo &) LLVM_DELETED_FUNCTION;
+  void operator=(const MCRelocationInfo &) LLVM_DELETED_FUNCTION;
+
+protected:
+  MCContext &Ctx;
+
+public:
+  MCRelocationInfo(MCContext &Ctx);
+  virtual ~MCRelocationInfo();
+
+  /// \brief Create an MCExpr for the relocation \p Rel.
+  /// \returns If possible, an MCExpr corresponding to Rel, else 0.
+  virtual const MCExpr *createExprForRelocation(object::RelocationRef Rel);
+
+  /// \brief Create an MCExpr for the target-specific \p VariantKind.
+  /// The VariantKinds are defined in llvm-c/Disassembler.h.
+  /// Used by MCExternalSymbolizer.
+  /// \returns If possible, an MCExpr corresponding to VariantKind, else 0.
+  virtual const MCExpr *createExprForCAPIVariantKind(const MCExpr *SubExpr,
+                                                     unsigned VariantKind);
+};
+
+}
+
+#endif
diff --git a/include/llvm/MC/MCSymbolizer.h b/include/llvm/MC/MCSymbolizer.h
new file mode 100644
index 0000000000..e42a2146dc
--- /dev/null
+++ b/include/llvm/MC/MCSymbolizer.h
@@ -0,0 +1,81 @@
+//===-- llvm/MC/MCSymbolizer.h - MCSymbolizer class -------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the declaration of the MCSymbolizer class, which is used
+// to symbolize instructions decoded from an object, that is, transform their
+// immediate operands to MCExprs.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCSYMBOLIZER_H
+#define LLVM_MC_MCSYMBOLIZER_H
+
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/MC/MCRelocationInfo.h"
+#include "llvm/Support/Compiler.h"
+#include "llvm/Support/DataTypes.h"
+
+namespace llvm {
+
+class MCContext;
+class MCInst;
+class raw_ostream;
+
+/// \brief Symbolize and annotate disassembled instructions.
+///
+/// For now this mimics the old symbolization logic (from both ARM and x86), that
+/// relied on user-provided (C API) callbacks to do the actual symbol lookup in
+/// the object file. This was moved to MCExternalSymbolizer.
+/// A better API would not rely on actually calling the two methods here from
+/// inside each disassembler, but would use the instr info to determine what
+/// operands are actually symbolizable, and in what way. I don't think this
+/// information exists right now.
+class MCSymbolizer {
+  MCSymbolizer(const MCSymbolizer &) LLVM_DELETED_FUNCTION;
+  void operator=(const MCSymbolizer &) LLVM_DELETED_FUNCTION;
+
+protected:
+  MCContext &Ctx;
+  OwningPtr<MCRelocationInfo> RelInfo;
+
+public:
+  /// \brief Construct an MCSymbolizer, taking ownership of \p RelInfo.
+  MCSymbolizer(MCContext &Ctx, OwningPtr<MCRelocationInfo> &RelInfo);
+  virtual ~MCSymbolizer();
+
+  /// \brief Try to add a symbolic operand instead of \p Value to the MCInst.
+  ///
+  /// Instead of having a difficult to read immediate, a symbolic operand would
+  /// represent this immediate in a more understandable way, for instance as a
+  /// symbol or an offset from a symbol. Relocations can also be used to enrich
+  /// the symbolic expression.
+  /// @param Inst      - The MCInst where to insert the symbolic operand.
+  /// @param cStream   - Stream to print comments and annotations on.
+  /// @param Value     - Operand value, pc-adjusted by the caller if necessary.
+  /// @param Address   - Load address of the instruction.
+  /// @param IsBranch  - Is the instruction a branch?
+  /// @param Offset    - Byte offset of the operand inside the inst.
+  /// @param InstSize  - Size of the instruction in bytes.
+  /// @return Whether a symbolic operand was added.
+  virtual bool tryAddingSymbolicOperand(MCInst &Inst, raw_ostream &cStream,
+                                        int64_t Value, uint64_t Address,
+                                        bool IsBranch, uint64_t Offset,
+                                        uint64_t InstSize) = 0;
+
+  /// \brief Try to add a comment on the PC-relative load.
+  /// For instance, in Mach-O, this is used to add annotations to instructions
+  /// that use C string literals, as found in __cstring.
+  virtual void tryAddingPcLoadReferenceComment(raw_ostream &cStream,
+                                               int64_t Value,
+                                               uint64_t Address) = 0;
+};
+
+}
+
+#endif
diff --git a/include/llvm/Support/TargetRegistry.h b/include/llvm/Support/TargetRegistry.h
index e1f6706618..b4e380b344 100644
--- a/include/llvm/Support/TargetRegistry.h
+++ b/include/llvm/Support/TargetRegistry.h
@@ -41,6 +41,7 @@ namespace llvm {
   class MCRegisterInfo;
   class MCStreamer;
   class MCSubtargetInfo;
+  class MCRelocationInfo;
   class MCTargetAsmParser;
   class TargetMachine;
   class TargetOptions;
@@ -56,6 +57,8 @@ namespace llvm {
                                 MCAsmBackend *TAB,
                                 bool ShowInst);
 
+  MCRelocationInfo *createMCRelocationInfo(MCContext &Ctx);
+
   /// Target - Wrapper for Target specific information.
   ///
   /// For registration purposes, this is a POD type so that targets can be
@@ -127,6 +130,8 @@ namespace llvm {
                                              MCCodeEmitter *CE,
                                              MCAsmBackend *TAB,
                                              bool ShowInst);
+    typedef MCRelocationInfo *(*MCRelocationInfoCtorTy)(StringRef TT,
+                                                        MCContext &Ctx);
 
   private:
     /// Next - The next registered target in the linked list, maintained by the
@@ -206,6 +211,10 @@ namespace llvm {
     /// AsmStreamer, if registered (default = llvm::createAsmStreamer).
     AsmStreamerCtorTy AsmStreamerCtorFn;
 
+    /// MCRelocationInfoCtorFn - Construction function for this target's
+    /// MCRelocationInfo, if registered (default = llvm::createMCRelocationInfo)
+    MCRelocationInfoCtorTy MCRelocationInfoCtorFn;
+
   public:
     Target() : AsmStreamerCtorFn(llvm::createAsmStreamer) {}
 
@@ -433,6 +442,16 @@ namespace llvm {
                                useDwarfDirectory, InstPrint, CE, TAB, ShowInst);
     }
 
+    /// createMCRelocationInfo - Create a target specific MCRelocationInfo.
+    ///
+    /// \param TT The target triple.
+    /// \param Ctx The target context.
+    MCRelocationInfo *
+      createMCRelocationInfo(StringRef TT, MCContext &Ctx) const {
+      // MCRelocationInfoCtorFn defaults to createMCRelocationInfo
+      return MCRelocationInfoCtorFn(TT, Ctx);
+    }
+
     /// @}
   };
 
@@ -760,6 +779,21 @@ namespace llvm {
         T.AsmStreamerCtorFn = Fn;
     }
 
+    /// RegisterMCRelocationInfo - Register an MCRelocationInfo
+    /// implementation for the given target.
+    ///
+    /// Clients are responsible for ensuring that registration doesn't occur
+    /// while another thread is attempting to access the registry. Typically
+    /// this is done by initializing all targets at program startup.
+    ///
+    /// @param T - The target being registered.
+    /// @param Fn - A function to construct an MCRelocationInfo for the target.
+    static void RegisterMCRelocationInfo(Target &T,
+                                         Target::MCRelocationInfoCtorTy Fn) {
+      if (!T.MCRelocationInfoCtorFn)
+        T.MCRelocationInfoCtorFn = Fn;
+    }
+
     /// @}
   };