MC: Disassembled CFG reconstruction.

This patch builds on some existing code to do CFG reconstruction from
a disassembled binary:
- MCModule represents the binary, and has a list of MCAtoms.
- MCAtom represents either disassembled instructions (MCTextAtom), or
  contiguous data (MCDataAtom), and covers a specific range of addresses.
- MCBasicBlock and MCFunction form the reconstructed CFG. An MCBB is
  backed by an MCTextAtom, and has the usual successors/predecessors.
- MCObjectDisassembler creates a module from an ObjectFile using a
  disassembler. It first builds an atom for each section. It can also
  construct the CFG, and this splits the text atoms into basic blocks.

MCModule and MCAtom were only sketched out; MCFunction and MCBB were
implemented under the experimental "-cfg" llvm-objdump -macho option.
This cleans them up for further use; llvm-objdump -d -cfg now generates
graphviz files for each function found in the binary.

In the future, MCObjectDisassembler may be the right place to do
"intelligent" disassembly: for example, handling constant islands is just
a matter of splitting the atom, using information that may be available
in the ObjectFile. Also, better initial atom formation than just using
sections is possible using symbols (and things like Mach-O's
function_starts load command).

This brings two minor regressions in llvm-objdump -macho -cfg:
- The printing of a relocation's referenced symbol.
- An annotation on loop BBs, i.e., which are their own successor.

Relocation printing is replaced by the MCSymbolizer; the basic CFG
annotation will be superseded by more related functionality.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182628 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 66 insertions, 13 deletions

diff --git a/lib/MC/MCModule.cpp b/lib/MC/MCModule.cpp
index f563160833..50bac476fa 100644
--- a/lib/MC/MCModule.cpp
+++ b/lib/MC/MCModule.cpp
@@ -7,39 +7,92 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/MC/MCAtom.h"
 #include "llvm/MC/MCModule.h"
+#include "llvm/MC/MCAtom.h"
+#include "llvm/MC/MCFunction.h"
+#include <algorithm>
 
 using namespace llvm;
 
-MCAtom *MCModule::createAtom(MCAtom::AtomType Type,
-                             uint64_t Begin, uint64_t End) {
+static bool AtomComp(const MCAtom *L, uint64_t Addr) {
+  return L->getEndAddr() < Addr;
+}
+
+void MCModule::map(MCAtom *NewAtom) {
+  uint64_t Begin = NewAtom->Begin,
+           End = NewAtom->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!");
+  AtomListTy::iterator I = std::lower_bound(atom_begin(), atom_end(),
+                                            Begin, AtomComp);
+  assert((I == atom_end() || (*I)->getBeginAddr() > 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);
+  // Insert the new atom to the list.
+  Atoms.insert(I, NewAtom);
+}
+
+MCTextAtom *MCModule::createTextAtom(uint64_t Begin, uint64_t End) {
+  MCTextAtom *NewAtom = new MCTextAtom(this, Begin, End);
+  map(NewAtom);
+  return NewAtom;
+}
+
+MCDataAtom *MCModule::createDataAtom(uint64_t Begin, uint64_t End) {
+  MCDataAtom *NewAtom = new MCDataAtom(this, Begin, End);
+  map(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!");
+  AtomListTy::iterator I = std::lower_bound(atom_begin(), atom_end(),
+                                            Atom->Begin, AtomComp);
+  assert(I != atom_end() && "Atom offset not found in module!");
   assert(*I == Atom && "Previous atom mapping was invalid!");
-  I.erase();
+  Atoms.erase(I);
 
   // Insert the new mapping.
-  OffsetMap.insert(NewBegin, NewEnd, Atom);
+  AtomListTy::iterator NewI = std::lower_bound(atom_begin(), atom_end(),
+                                               NewBegin, AtomComp);
+  Atoms.insert(NewI, Atom);
 
   // Update the atom internal bounds.
   Atom->Begin = NewBegin;
   Atom->End = NewEnd;
 }
 
+const MCAtom *MCModule::findAtomContaining(uint64_t Addr) const {
+  AtomListTy::const_iterator I = std::lower_bound(atom_begin(), atom_end(),
+                                                  Addr, AtomComp);
+  if (I != atom_end() && (*I)->getBeginAddr() <= Addr)
+    return *I;
+  return 0;
+}
+
+MCAtom *MCModule::findAtomContaining(uint64_t Addr) {
+  AtomListTy::iterator I = std::lower_bound(atom_begin(), atom_end(),
+                                            Addr, AtomComp);
+  if (I != atom_end() && (*I)->getBeginAddr() <= Addr)
+    return *I;
+  return 0;
+}
+
+MCFunction *MCModule::createFunction(const StringRef &Name) {
+  Functions.push_back(new MCFunction(Name));
+  return Functions.back();
+}
+
+MCModule::~MCModule() {
+  for (AtomListTy::iterator AI = atom_begin(),
+                            AE = atom_end();
+                            AI != AE; ++AI)
+    delete *AI;
+  for (FunctionListTy::iterator FI = func_begin(),
+                                FE = func_end();
+                                FI != FE; ++FI)
+    delete *FI;
+}