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

5 files changed, 66 insertions, 107 deletions

diff --git a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index fb82945..284761c 100644
--- a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -503,102 +503,9 @@ static bool tryAddingSymbolicOperand(uint64_t Address, int32_t Value,
                                      bool isBranch, uint64_t InstSize,
                                      MCInst &MI, const void *Decoder) {
   const MCDisassembler *Dis = static_cast<const MCDisassembler*>(Decoder);
-  LLVMOpInfoCallback getOpInfo = Dis->getLLVMOpInfoCallback();
-  struct LLVMOpInfo1 SymbolicOp;
-  memset(&SymbolicOp, '\0', sizeof(struct LLVMOpInfo1));
-  SymbolicOp.Value = Value;
-  void *DisInfo = Dis->getDisInfoBlock();
-
-  if (!getOpInfo ||
-      !getOpInfo(DisInfo, Address, 0 /* Offset */, InstSize, 1, &SymbolicOp)) {
-    // Clear SymbolicOp.Value from above and also all other fields.
-    memset(&SymbolicOp, '\0', sizeof(struct LLVMOpInfo1));
-    LLVMSymbolLookupCallback SymbolLookUp = Dis->getLLVMSymbolLookupCallback();
-    if (!SymbolLookUp)
-      return false;
-    uint64_t ReferenceType;
-    if (isBranch)
-       ReferenceType = LLVMDisassembler_ReferenceType_In_Branch;
-    else
-       ReferenceType = LLVMDisassembler_ReferenceType_InOut_None;
-    const char *ReferenceName;
-    uint64_t SymbolValue = 0x00000000ffffffffULL & Value;
-    const char *Name = SymbolLookUp(DisInfo, SymbolValue, &ReferenceType,
-                                    Address, &ReferenceName);
-    if (Name) {
-      SymbolicOp.AddSymbol.Name = Name;
-      SymbolicOp.AddSymbol.Present = true;
-    }
-    // For branches always create an MCExpr so it gets printed as hex address.
-    else if (isBranch) {
-      SymbolicOp.Value = Value;
-    }
-    if(ReferenceType == LLVMDisassembler_ReferenceType_Out_SymbolStub)
-      (*Dis->CommentStream) << "symbol stub for: " << ReferenceName;
-    if (!Name && !isBranch)
-      return false;
-  }
-
-  MCContext *Ctx = Dis->getMCContext();
-  const MCExpr *Add = NULL;
-  if (SymbolicOp.AddSymbol.Present) {
-    if (SymbolicOp.AddSymbol.Name) {
-      StringRef Name(SymbolicOp.AddSymbol.Name);
-      MCSymbol *Sym = Ctx->GetOrCreateSymbol(Name);
-      Add = MCSymbolRefExpr::Create(Sym, *Ctx);
-    } else {
-      Add = MCConstantExpr::Create(SymbolicOp.AddSymbol.Value, *Ctx);
-    }
-  }
-
-  const MCExpr *Sub = NULL;
-  if (SymbolicOp.SubtractSymbol.Present) {
-    if (SymbolicOp.SubtractSymbol.Name) {
-      StringRef Name(SymbolicOp.SubtractSymbol.Name);
-      MCSymbol *Sym = Ctx->GetOrCreateSymbol(Name);
-      Sub = MCSymbolRefExpr::Create(Sym, *Ctx);
-    } else {
-      Sub = MCConstantExpr::Create(SymbolicOp.SubtractSymbol.Value, *Ctx);
-    }
-  }
-
-  const MCExpr *Off = NULL;
-  if (SymbolicOp.Value != 0)
-    Off = MCConstantExpr::Create(SymbolicOp.Value, *Ctx);
-
-  const MCExpr *Expr;
-  if (Sub) {
-    const MCExpr *LHS;
-    if (Add)
-      LHS = MCBinaryExpr::CreateSub(Add, Sub, *Ctx);
-    else
-      LHS = MCUnaryExpr::CreateMinus(Sub, *Ctx);
-    if (Off != 0)
-      Expr = MCBinaryExpr::CreateAdd(LHS, Off, *Ctx);
-    else
-      Expr = LHS;
-  } else if (Add) {
-    if (Off != 0)
-      Expr = MCBinaryExpr::CreateAdd(Add, Off, *Ctx);
-    else
-      Expr = Add;
-  } else {
-    if (Off != 0)
-      Expr = Off;
-    else
-      Expr = MCConstantExpr::Create(0, *Ctx);
-  }
-
-  if (SymbolicOp.VariantKind == LLVMDisassembler_VariantKind_ARM_HI16)
-    MI.addOperand(MCOperand::CreateExpr(ARMMCExpr::CreateUpper16(Expr, *Ctx)));
-  else if (SymbolicOp.VariantKind == LLVMDisassembler_VariantKind_ARM_LO16)
-    MI.addOperand(MCOperand::CreateExpr(ARMMCExpr::CreateLower16(Expr, *Ctx)));
-  else if (SymbolicOp.VariantKind == LLVMDisassembler_VariantKind_None)
-    MI.addOperand(MCOperand::CreateExpr(Expr));
-  else
-    llvm_unreachable("bad SymbolicOp.VariantKind");
-
-  return true;
+  // FIXME: Does it make sense for value to be negative?
+  return Dis->tryAddingSymbolicOperand(MI, (uint32_t)Value, Address, isBranch,
+                                       /* Offset */ 0, InstSize);
 }
 
 /// tryAddingPcLoadReferenceComment - trys to add a comment as to what is being
@@ -613,17 +520,7 @@ static bool tryAddingSymbolicOperand(uint64_t Address, int32_t Value,
 static void tryAddingPcLoadReferenceComment(uint64_t Address, int Value,
                                             const void *Decoder) {
   const MCDisassembler *Dis = static_cast<const MCDisassembler*>(Decoder);
-  LLVMSymbolLookupCallback SymbolLookUp = Dis->getLLVMSymbolLookupCallback();
-  if (SymbolLookUp) {
-    void *DisInfo = Dis->getDisInfoBlock();
-    uint64_t ReferenceType;
-    ReferenceType = LLVMDisassembler_ReferenceType_In_PCrel_Load;
-    const char *ReferenceName;
-    (void)SymbolLookUp(DisInfo, Value, &ReferenceType, Address, &ReferenceName);
-    if(ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_SymAddr ||
-       ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr)
-      (*Dis->CommentStream) << "literal pool for: " << ReferenceName;
-  }
+  Dis->tryAddingPcLoadReferenceComment(Value, Address);
 }
 
 // Thumb1 instructions don't have explicit S bits.  Rather, they
diff --git a/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.cpp b/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.cpp
index b858fff..52fc28d 100644
--- a/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.cpp
+++ b/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.cpp
@@ -212,6 +212,14 @@ static MCInstPrinter *createARMMCInstPrinter(const Target &T,
   return 0;
 }
 
+static MCRelocationInfo *createMCRelocationInfo(StringRef TT, MCContext &Ctx) {
+  Triple TheTriple(TT);
+  if (TheTriple.isEnvironmentMachO())
+    return createARMMachORelocationInfo(Ctx);
+  // Default to the stock relocation info.
+  return llvm::createMCRelocationInfo(Ctx);
+}
+
 namespace {
 
 class ARMMCInstrAnalysis : public MCInstrAnalysis {
@@ -295,4 +303,10 @@ extern "C" void LLVMInitializeARMTargetMC() {
   // Register the MCInstPrinter.
   TargetRegistry::RegisterMCInstPrinter(TheARMTarget, createARMMCInstPrinter);
   TargetRegistry::RegisterMCInstPrinter(TheThumbTarget, createARMMCInstPrinter);
+
+  // Register the MC relocation info.
+  TargetRegistry::RegisterMCRelocationInfo(TheARMTarget,
+                                           createMCRelocationInfo);
+  TargetRegistry::RegisterMCRelocationInfo(TheThumbTarget,
+                                           createMCRelocationInfo);
 }
diff --git a/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.h b/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.h
index a89981e..4e94c53 100644
--- a/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.h
+++ b/lib/Target/ARM/MCTargetDesc/ARMMCTargetDesc.h
@@ -25,6 +25,7 @@ class MCInstrInfo;
 class MCObjectWriter;
 class MCRegisterInfo;
 class MCSubtargetInfo;
+class MCRelocationInfo;
 class StringRef;
 class Target;
 class raw_ostream;
@@ -58,6 +59,9 @@ MCObjectWriter *createARMMachObjectWriter(raw_ostream &OS,
                                           uint32_t CPUType,
                                           uint32_t CPUSubtype);
 
+
+/// createARMMachORelocationInfo - Construct ARM Mach-O relocation info.
+MCRelocationInfo *createARMMachORelocationInfo(MCContext &Ctx);
 } // End llvm namespace
 
 // Defines symbolic names for ARM registers.  This defines a mapping from
diff --git a/lib/Target/ARM/MCTargetDesc/ARMMachORelocationInfo.cpp b/lib/Target/ARM/MCTargetDesc/ARMMachORelocationInfo.cpp
new file mode 100644
index 0000000..807c948
--- /dev/null
+++ b/lib/Target/ARM/MCTargetDesc/ARMMachORelocationInfo.cpp
@@ -0,0 +1,43 @@
+//===-- ARMMachORelocationInfo.cpp ----------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "MCTargetDesc/ARMMCTargetDesc.h"
+#include "ARMMCExpr.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCRelocationInfo.h"
+#include "llvm-c/Disassembler.h"
+
+using namespace llvm;
+using namespace object;
+
+namespace {
+class ARMMachORelocationInfo : public MCRelocationInfo {
+public:
+  ARMMachORelocationInfo(MCContext &Ctx) : MCRelocationInfo(Ctx) {}
+
+  const MCExpr *createExprForCAPIVariantKind(const MCExpr *SubExpr,
+                                             unsigned VariantKind) {
+    switch(VariantKind) {
+    case LLVMDisassembler_VariantKind_ARM_HI16:
+      return ARMMCExpr::CreateUpper16(SubExpr, Ctx);
+    case LLVMDisassembler_VariantKind_ARM_LO16:
+      return ARMMCExpr::CreateLower16(SubExpr, Ctx);
+    default:
+      return MCRelocationInfo::createExprForCAPIVariantKind(SubExpr,
+                                                            VariantKind);
+    }
+  }
+};
+} // End unnamed namespace
+
+/// createARMMachORelocationInfo - Construct an ARM Mach-O RelocationInfo.
+MCRelocationInfo *llvm::createARMMachORelocationInfo(MCContext &Ctx) {
+  return new ARMMachORelocationInfo(Ctx);
+}
diff --git a/lib/Target/ARM/MCTargetDesc/CMakeLists.txt b/lib/Target/ARM/MCTargetDesc/CMakeLists.txt
index a7ac5ca..bab59f4 100644
--- a/lib/Target/ARM/MCTargetDesc/CMakeLists.txt
+++ b/lib/Target/ARM/MCTargetDesc/CMakeLists.txt
@@ -9,6 +9,7 @@ add_llvm_library(LLVMARMDesc
   ARMMachObjectWriter.cpp
   ARMELFObjectWriter.cpp
   ARMUnwindOpAsm.cpp
+  ARMMachORelocationInfo.cpp
   )
 add_dependencies(LLVMARMDesc ARMCommonTableGen)