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

2 files changed, 51 insertions, 16 deletions

diff --git a/tools/llvm-objdump/llvm-objdump.cpp b/tools/llvm-objdump/llvm-objdump.cpp
index b5a0488b00..570ec7ed6f 100644
--- a/tools/llvm-objdump/llvm-objdump.cpp
+++ b/tools/llvm-objdump/llvm-objdump.cpp
@@ -23,12 +23,16 @@
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCDisassembler.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstPrinter.h"
 #include "llvm/MC/MCInstrInfo.h"
+#include "llvm/MC/MCObjectFileInfo.h"
+#include "llvm/MC/MCObjectSymbolizer.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/MC/MCRelocationInfo.h"
 #include "llvm/Object/Archive.h"
 #include "llvm/Object/COFF.h"
 #include "llvm/Object/MachO.h"
@@ -123,6 +127,10 @@ static cl::alias
 PrivateHeadersShort("p", cl::desc("Alias for --private-headers"),
                     cl::aliasopt(PrivateHeaders));
 
+static cl::opt<bool>
+Symbolize("symbolize", cl::desc("When disassembling instructions, "
+                                "try to symbolize operands."));
+
 static StringRef ToolName;
 
 bool llvm::error(error_code ec) {
@@ -137,8 +145,13 @@ static const Target *getTarget(const ObjectFile *Obj = NULL) {
   // Figure out the target triple.
   llvm::Triple TheTriple("unknown-unknown-unknown");
   if (TripleName.empty()) {
-    if (Obj)
+    if (Obj) {
       TheTriple.setArch(Triple::ArchType(Obj->getArch()));
+      // TheTriple defaults to ELF, and COFF doesn't have an environment:
+      // the best we can do here is indicate that it is mach-o.
+      if (Obj->isMachO())
+        TheTriple.setEnvironment(Triple::MachO);
+    }
   } else
     TheTriple.setTriple(Triple::normalize(TripleName));
 
@@ -216,7 +229,6 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
   // Set up disassembler.
   OwningPtr<const MCAsmInfo> AsmInfo(
     TheTarget->createMCAsmInfo(*MRI, TripleName));
-
   if (!AsmInfo) {
     errs() << "error: no assembly info for target " << TripleName << "\n";
     return;
@@ -224,23 +236,37 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
 
   OwningPtr<const MCSubtargetInfo> STI(
     TheTarget->createMCSubtargetInfo(TripleName, "", FeaturesStr));
-
   if (!STI) {
     errs() << "error: no subtarget info for target " << TripleName << "\n";
     return;
   }
 
-  OwningPtr<const MCDisassembler> DisAsm(
-    TheTarget->createMCDisassembler(*STI));
+  OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
+  if (!MII) {
+    errs() << "error: no instruction info for target " << TripleName << "\n";
+    return;
+  }
+
+  OwningPtr<MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI));
   if (!DisAsm) {
     errs() << "error: no disassembler for target " << TripleName << "\n";
     return;
   }
 
-  OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
-  if (!MII) {
-    errs() << "error: no instruction info for target " << TripleName << "\n";
-    return;
+  OwningPtr<const MCObjectFileInfo> MOFI;
+  OwningPtr<MCContext> Ctx;
+
+  if (Symbolize) {
+    MOFI.reset(new MCObjectFileInfo);
+    Ctx.reset(new MCContext(*AsmInfo.get(), *MRI.get(), MOFI.get()));
+    OwningPtr<MCRelocationInfo> RelInfo(
+      TheTarget->createMCRelocationInfo(TripleName, *Ctx.get()));
+    if (RelInfo) {
+      OwningPtr<MCSymbolizer> Symzer(
+        MCObjectSymbolizer::createObjectSymbolizer(*Ctx.get(), RelInfo, Obj));
+      if (Symzer)
+        DisAsm->setSymbolizer(Symzer);
+    }
   }
 
   int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
@@ -317,9 +343,13 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
     if (Symbols.empty())
       Symbols.push_back(std::make_pair(0, name));
 
+
+    SmallString<40> Comments;
+    raw_svector_ostream CommentStream(Comments);
+
     StringRef Bytes;
     if (error(i->getContents(Bytes))) break;
-    StringRefMemoryObject memoryObject(Bytes);
+    StringRefMemoryObject memoryObject(Bytes, SectionAddr);
     uint64_t Size;
     uint64_t Index;
     uint64_t SectSize;
@@ -353,14 +383,17 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
       for (Index = Start; Index < End; Index += Size) {
         MCInst Inst;
 
-        if (DisAsm->getInstruction(Inst, Size, memoryObject, Index,
-                                   DebugOut, nulls())) {
+        if (DisAsm->getInstruction(Inst, Size, memoryObject,
+                                   SectionAddr + Index,
+                                   DebugOut, CommentStream)) {
           outs() << format("%8" PRIx64 ":", SectionAddr + Index);
           if (!NoShowRawInsn) {
             outs() << "\t";
             DumpBytes(StringRef(Bytes.data() + Index, Size));
           }
           IP->printInst(&Inst, outs(), "");
+          outs() << CommentStream.str();
+          Comments.clear();
           outs() << "\n";
         } else {
           errs() << ToolName << ": warning: invalid instruction encoding\n";
diff --git a/tools/llvm-objdump/llvm-objdump.h b/tools/llvm-objdump/llvm-objdump.h
index ca7bced635..3c62240f8f 100644
--- a/tools/llvm-objdump/llvm-objdump.h
+++ b/tools/llvm-objdump/llvm-objdump.h
@@ -38,16 +38,18 @@ void printELFFileHeader(const object::ObjectFile *o);
 class StringRefMemoryObject : public MemoryObject {
   virtual void anchor();
   StringRef Bytes;
+  uint64_t Base;
 public:
-  StringRefMemoryObject(StringRef bytes) : Bytes(bytes) {}
+  StringRefMemoryObject(StringRef bytes, uint64_t Base = 0)
+    : Bytes(bytes), Base(Base) {}
 
-  uint64_t getBase() const { return 0; }
+  uint64_t getBase() const { return Base; }
   uint64_t getExtent() const { return Bytes.size(); }
 
   int readByte(uint64_t Addr, uint8_t *Byte) const {
-    if (Addr >= getExtent())
+    if (Addr >= Base + getExtent() || Addr < Base)
       return -1;
-    *Byte = Bytes[Addr];
+    *Byte = Bytes[Addr - Base];
     return 0;
   }
 };