Start stubbing out MCModule and MCAtom, which provide an API for accessing the rich disassembly of a complete object or executable.

These are very much a work in progress, and not really useful yet.

llvm-svn: 140345

include/llvm/MC/MCAtom.h

@@ -0,0 +1,75 @@
+//===-- llvm/MC/MCAtom.h - MCAtom 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 MCAtom class, which is used to
+// represent a contiguous region in a decoded object that is uniformly data or
+// instructions;
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCATOM_H
+#define LLVM_MC_MCATOM_H
+
+#include "llvm/MC/MCInst.h"
+#include "llvm/Support/DataTypes.h"
+#include <vector>
+
+namespace llvm {
+
+class MCModule;
+
+/// MCData - An entry in a data MCAtom.
+// NOTE: This may change to a more complex type in the future.
+typedef uint8_t MCData;
+
+/// MCAtom - Represents a contiguous range of either instructions (a TextAtom)
+/// or data (a DataAtom).  Address ranges are expressed as _closed_ intervals.
+class MCAtom {
+  friend class MCModule;
+  typedef enum { TextAtom, DataAtom } AtomType;
+
+  AtomType Type;
+  MCModule *Parent;
+  uint64_t Begin, End;
+
+  std::vector<std::pair<uint64_t, MCInst> > Text;
+  std::vector<MCData> Data;
+
+  // Private constructor - only callable by MCModule
+  MCAtom(AtomType T, MCModule *P, uint64_t B, uint64_t E)
+    : Type(T), Parent(P), Begin(B), End(E) { }
+
+public:
+  bool isTextAtom() { return Type == TextAtom; }
+  bool isDataAtom() { return Type == DataAtom; }
+
+  void addInst(const MCInst &I, uint64_t Address) {
+    assert(Type == TextAtom && "Trying to add MCInst to a non-text atom!");
+    Text.push_back(std::make_pair(Address, I));
+  }
+
+  void addData(const MCData &D) {
+    assert(Type == DataAtom && "Trying to add MCData to a non-data atom!");
+    Data.push_back(D);
+  }
+
+  /// split - Splits the atom in two at a given address, which must align with
+  /// and instruction boundary if this is a TextAtom.  Returns the newly created
+  /// atom representing the high part of the split.
+  MCAtom *split(uint64_t SplitPt);
+
+  /// truncate - Truncates an atom so that TruncPt is the last byte address
+  /// contained in the atom.
+  void truncate(uint64_t TruncPt);
+};
+
+}
+
+#endif
+

include/llvm/MC/MCModule.h

@@ -0,0 +1,58 @@
+//===-- llvm/MC/MCModule.h - MCModule 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 MCModule class, which is used to
+// represent a complete, disassembled object file or executable.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCMODULE_H
+#define LLVM_MC_MCMODULE_H
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/IntervalMap.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/Support/DataTypes.h"
+
+namespace llvm {
+
+class MCAtom;
+
+/// MCModule - This class represent a completely disassembled object file or
+/// executable.  It comprises a list of MCAtom's, and a branch target table.
+/// Each atom represents a contiguous range of either instructions or data.
+class MCModule {
+  /// AtomAllocationTracker - An MCModule owns its component MCAtom's, so it
+  /// must track them in order to ensure they are properly freed as atoms are
+  /// merged or otherwise manipulated.
+  SmallPtrSet<MCAtom*, 8> AtomAllocationTracker;
+
+  /// OffsetMap - Efficiently maps offset ranges to MCAtom's.
+  IntervalMap<uint64_t, MCAtom*> OffsetMap;
+
+  /// BranchTargetMap - Maps offsets that are determined to be branches and
+  /// can be statically resolved to their target offsets.
+  DenseMap<uint64_t, MCAtom*> BranchTargetMap;
+
+  friend class MCAtom;
+
+  /// remap - Update the interval mapping for an MCAtom.
+  void remap(MCAtom *Atom, uint64_t NewBegin, uint64_t NewEnd);
+
+public:
+  MCModule(IntervalMap<uint64_t, MCAtom*>::Allocator &A) : OffsetMap(A) { }
+
+  /// createAtom - Creates a new MCAtom covering the specified offset range.
+  MCAtom *createAtom(MCAtom::AtomType Type, uint64_t Begin, uint64_t End);
+};
+
+}
+
+#endif
+

lib/MC/MCAtom.cpp

@@ -0,0 +1,79 @@
+//===- lib/MC/MCAtom.cpp - MCAtom implementation --------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCAtom.h"
+#include "llvm/MC/MCModule.h"
+#include "llvm/Support/ErrorHandling.h"
+
+using namespace llvm;
+
+MCAtom *MCAtom::split(uint64_t SplitPt) {
+  assert((SplitPt > Begin && SplitPt <= End) &&
+         "Splitting at point not contained in atom!");
+
+  // Compute the new begin/end points.
+  uint64_t LeftBegin = Begin;
+  uint64_t LeftEnd = SplitPt - 1;
+  uint64_t RightBegin = SplitPt;
+  uint64_t RightEnd = End;
+
+  // Remap this atom to become the lower of the two new ones.
+  Parent->remap(this, LeftBegin, LeftEnd);
+
+  // Create a new atom for the higher atom.
+  MCAtom *RightAtom = Parent->createAtom(Type, RightBegin, RightEnd);
+
+  // Split the contents of the original atom between it and the new one.  The
+  // precise method depends on whether this is a data or a text atom.
+  if (isDataAtom()) {
+    std::vector<MCData>::iterator I = Data.begin() + (RightBegin - LeftBegin);
+
+    assert(I != Data.end() && "Split point not found in range!");
+
+    std::copy(I, Data.end(), RightAtom->Data.end());
+    Data.erase(I, Data.end());
+  } else if (isTextAtom()) {
+    std::vector<std::pair<uint64_t, MCInst> >::iterator I = Text.begin();
+
+    while (I != Text.end() && I->first < SplitPt) ++I;
+
+    assert(I != Text.end() && "Split point not found in disassembly!");
+    assert(I->first == SplitPt &&
+           "Split point does not fall on instruction boundary!");
+
+    std::copy(I, Text.end(), RightAtom->Text.end());
+    Text.erase(I, Text.end());
+  } else
+    llvm_unreachable("Unknown atom type!");
+
+  return RightAtom;
+}
+
+void MCAtom::truncate(uint64_t TruncPt) {
+  assert((TruncPt >= Begin && TruncPt < End) &&
+         "Truncation point not contained in atom!");
+
+  Parent->remap(this, Begin, TruncPt);
+
+  if (isDataAtom()) {
+    Data.resize(TruncPt - Begin + 1);
+  } else if (isTextAtom()) {
+    std::vector<std::pair<uint64_t, MCInst> >::iterator I = Text.begin();
+
+    while (I != Text.end() && I->first <= TruncPt) ++I;
+
+    assert(I != Text.end() && "Truncation point not found in disassembly!");
+    assert(I->first == TruncPt+1 &&
+           "Truncation point does not fall on instruction boundary");
+
+    Text.erase(I, Text.end());
+  } else
+    llvm_unreachable("Unknown atom type!");
+}
+

lib/MC/MCModule.cpp

@@ -0,0 +1,45 @@
+//===- lib/MC/MCModule.cpp - MCModule implementation --------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCAtom.h"
+#include "llvm/MC/MCModule.h"
+
+using namespace llvm;
+
+MCAtom *MCModule::createAtom(MCAtom::AtomType Type,
+                             uint64_t Begin, uint64_t End) {
+  assert(Begin < End && "Creating MCAtom with endpoints reversed?");
+
+  // Check for atoms already covering this range.
+  IntervalMap<uint64_t, MCAtom*>::iterator I = OffsetMap.find(Begin);
+  assert((!I.valid() || I.start() < End) && "Offset range already occupied!");
+
+  // Create the new atom and add it to our maps.
+  MCAtom *NewAtom = new MCAtom(Type, this, Begin, End);
+  AtomAllocationTracker.insert(NewAtom);
+  OffsetMap.insert(Begin, End, NewAtom);
+  return NewAtom;
+}
+
+// remap - Update the interval mapping for an atom.
+void MCModule::remap(MCAtom *Atom, uint64_t NewBegin, uint64_t NewEnd) {
+  // Find and erase the old mapping.
+  IntervalMap<uint64_t, MCAtom*>::iterator I = OffsetMap.find(Atom->Begin);
+  assert(I.valid() && "Atom offset not found in module!");
+  assert(*I == Atom && "Previous atom mapping was invalid!");
+  I.erase();
+
+  // Insert the new mapping.
+  OffsetMap.insert(NewBegin, NewEnd, Atom);
+
+  // Update the atom internal bounds.
+  Atom->Begin = NewBegin;
+  Atom->End = NewEnd;
+}
+