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annotation will be superseded by more related functionality.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, 67 insertions, 54 deletions

diff --git a/lib/MC/MCAtom.cpp b/lib/MC/MCAtom.cpp
index d71444324f..2626b39db4 100644
--- a/lib/MC/MCAtom.cpp
+++ b/lib/MC/MCAtom.cpp
@@ -10,88 +10,101 @@
 #include "llvm/MC/MCAtom.h"
 #include "llvm/MC/MCModule.h"
 #include "llvm/Support/ErrorHandling.h"
+#include <iterator>
 
 using namespace llvm;
 
-void MCAtom::addInst(const MCInst &I, uint64_t Address, unsigned Size) {
-  assert(Type == TextAtom && "Trying to add MCInst to a non-text atom!");
-
-  assert(Address < End+Size &&
-         "Instruction not contiguous with end of atom!");
-  if (Address > End)
-    Parent->remap(this, Begin, End+Size);
-
-  Text.push_back(std::make_pair(Address, I));
+void MCAtom::remap(uint64_t NewBegin, uint64_t NewEnd) {
+  Parent->remap(this, NewBegin, NewEnd);
 }
 
-void MCAtom::addData(const MCData &D) {
-  assert(Type == DataAtom && "Trying to add MCData to a non-data atom!");
-  Parent->remap(this, Begin, End+1);
-
-  Data.push_back(D);
+void MCAtom::remapForTruncate(uint64_t TruncPt) {
+  assert((TruncPt >= Begin && TruncPt < End) &&
+         "Truncation point not contained in atom!");
+  remap(Begin, TruncPt);
 }
 
-MCAtom *MCAtom::split(uint64_t SplitPt) {
+void MCAtom::remapForSplit(uint64_t SplitPt,
+                           uint64_t &LBegin, uint64_t &LEnd,
+                           uint64_t &RBegin, uint64_t &REnd) {
   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;
+  LBegin = Begin;
+  LEnd = SplitPt - 1;
+  RBegin = SplitPt;
+  REnd = End;
 
   // Remap this atom to become the lower of the two new ones.
-  Parent->remap(this, LeftBegin, LeftEnd);
+  remap(LBegin, LEnd);
+}
 
-  // Create a new atom for the higher atom.
-  MCAtom *RightAtom = Parent->createAtom(Type, RightBegin, RightEnd);
+// MCDataAtom
 
-  // 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);
+void MCDataAtom::addData(const MCData &D) {
+  Data.push_back(D);
+  if (Data.size() > Begin - End)
+    remap(Begin, End + 1);
+}
 
-    assert(I != Data.end() && "Split point not found in range!");
+void MCDataAtom::truncate(uint64_t TruncPt) {
+  remapForTruncate(TruncPt);
 
-    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();
+  Data.resize(TruncPt - Begin + 1);
+}
 
-    while (I != Text.end() && I->first < SplitPt) ++I;
+MCDataAtom *MCDataAtom::split(uint64_t SplitPt) {
+  uint64_t LBegin, LEnd, RBegin, REnd;
+  remapForSplit(SplitPt, LBegin, LEnd, RBegin, REnd);
 
-    assert(I != Text.end() && "Split point not found in disassembly!");
-    assert(I->first == SplitPt &&
-           "Split point does not fall on instruction boundary!");
+  MCDataAtom *RightAtom = Parent->createDataAtom(RBegin, REnd);
+  RightAtom->setName(getName());
 
-    std::copy(I, Text.end(), RightAtom->Text.end());
-    Text.erase(I, Text.end());
-  } else
-    llvm_unreachable("Unknown atom type!");
+  std::vector<MCData>::iterator I = Data.begin() + (RBegin - LBegin);
+  assert(I != Data.end() && "Split point not found in range!");
 
+  std::copy(I, Data.end(), std::back_inserter(RightAtom->Data));
+  Data.erase(I, Data.end());
   return RightAtom;
 }
 
-void MCAtom::truncate(uint64_t TruncPt) {
-  assert((TruncPt >= Begin && TruncPt < End) &&
-         "Truncation point not contained in atom!");
+// MCTextAtom
 
-  Parent->remap(this, Begin, TruncPt);
+void MCTextAtom::addInst(const MCInst &I, uint64_t Size) {
+  if (NextInstAddress > End)
+    remap(Begin, NextInstAddress);
+  Insts.push_back(MCDecodedInst(I, NextInstAddress, Size));
+  NextInstAddress += Size;
+}
 
-  if (isDataAtom()) {
-    Data.resize(TruncPt - Begin + 1);
-  } else if (isTextAtom()) {
-    std::vector<std::pair<uint64_t, MCInst> >::iterator I = Text.begin();
+void MCTextAtom::truncate(uint64_t TruncPt) {
+  remapForTruncate(TruncPt);
 
-    while (I != Text.end() && I->first <= TruncPt) ++I;
+  InstListTy::iterator I = Insts.begin();
+  while (I != Insts.end() && I->Address <= 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");
+  assert(I != Insts.end() && "Truncation point not found in disassembly!");
+  assert(I->Address == TruncPt + 1 &&
+         "Truncation point does not fall on instruction boundary");
 
-    Text.erase(I, Text.end());
-  } else
-    llvm_unreachable("Unknown atom type!");
+  Insts.erase(I, Insts.end());
 }
 
+MCTextAtom *MCTextAtom::split(uint64_t SplitPt) {
+  uint64_t LBegin, LEnd, RBegin, REnd;
+  remapForSplit(SplitPt, LBegin, LEnd, RBegin, REnd);
+
+  MCTextAtom *RightAtom = Parent->createTextAtom(RBegin, REnd);
+  RightAtom->setName(getName());
+
+  InstListTy::iterator I = Insts.begin();
+  while (I != Insts.end() && I->Address < SplitPt) ++I;
+  assert(I != Insts.end() && "Split point not found in disassembly!");
+  assert(I->Address == SplitPt &&
+         "Split point does not fall on instruction boundary!");
+
+  std::copy(I, Insts.end(), std::back_inserter(RightAtom->Insts));
+  Insts.erase(I, Insts.end());
+  return RightAtom;
+}