path: root/tools/bugpoint/CrashDebugger.cpp

//===- CrashDebugger.cpp - Debug compilation crashes ----------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file was developed by the LLVM research group and is distributed under
// the University of Illinois Open Source License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the bugpoint internals that narrow down compilation crashes
//
//===----------------------------------------------------------------------===//

#include "BugDriver.h"
#include "ToolRunner.h"
#include "ListReducer.h"
#include "llvm/Constant.h"
#include "llvm/DerivedTypes.h"
#include "llvm/Instructions.h"
#include "llvm/Module.h"
#include "llvm/Pass.h"
#include "llvm/PassManager.h"
#include "llvm/ValueSymbolTable.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Bytecode/Writer.h"
#include "llvm/Support/CFG.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Support/FileUtilities.h"
#include "llvm/Support/CommandLine.h"
#include <fstream>
#include <set>
using namespace llvm;

namespace {
  cl::opt<bool>
  KeepMain("keep-main",
           cl::desc("Force function reduction to keep main"),
           cl::init(false));
}

namespace llvm {
  class ReducePassList : public ListReducer<const PassInfo*> {
    BugDriver &BD;
  public:
    ReducePassList(BugDriver &bd) : BD(bd) {}

    // doTest - Return true iff running the "removed" passes succeeds, and
    // running the "Kept" passes fail when run on the output of the "removed"
    // passes.  If we return true, we update the current module of bugpoint.
    //
    virtual TestResult doTest(std::vector<const PassInfo*> &Removed,
                              std::vector<const PassInfo*> &Kept);
  };
}

ReducePassList::TestResult
ReducePassList::doTest(std::vector<const PassInfo*> &Prefix,
                       std::vector<const PassInfo*> &Suffix) {
  sys::Path PrefixOutput;
  Module *OrigProgram = 0;
  if (!Prefix.empty()) {
    std::cout << "Checking to see if these passes crash: "
              << getPassesString(Prefix) << ": ";
    std::string PfxOutput;
    if (BD.runPasses(Prefix, PfxOutput))
      return KeepPrefix;

    PrefixOutput.set(PfxOutput);
    OrigProgram = BD.Program;

    BD.Program = ParseInputFile(PrefixOutput.toString());
    if (BD.Program == 0) {
      std::cerr << BD.getToolName() << ": Error reading bytecode file '"
                << PrefixOutput << "'!\n";
      exit(1);
    }
    PrefixOutput.eraseFromDisk();
  }

  std::cout << "Checking to see if these passes crash: "
            << getPassesString(Suffix) << ": ";

  if (BD.runPasses(Suffix)) {
    delete OrigProgram;            // The suffix crashes alone...
    return KeepSuffix;
  }

  // Nothing failed, restore state...
  if (OrigProgram) {
    delete BD.Program;
    BD.Program = OrigProgram;
  }
  return NoFailure;
}

namespace {
  /// ReduceCrashingGlobalVariables - This works by removing the global
  /// variable's initializer and seeing if the program still crashes. If it
  /// does, then we keep that program and try again.
  ///
  class ReduceCrashingGlobalVariables : public ListReducer<GlobalVariable*> {
    BugDriver &BD;
    bool (*TestFn)(BugDriver &, Module *);
  public:
    ReduceCrashingGlobalVariables(BugDriver &bd,
                                  bool (*testFn)(BugDriver&, Module*))
      : BD(bd), TestFn(testFn) {}

    virtual TestResult doTest(std::vector<GlobalVariable*>& Prefix,
                              std::vector<GlobalVariable*>& Kept) {
      if (!Kept.empty() && TestGlobalVariables(Kept))
        return KeepSuffix;

      if (!Prefix.empty() && TestGlobalVariables(Prefix))
        return KeepPrefix;

      return NoFailure;
    }

    bool TestGlobalVariables(std::vector<GlobalVariable*>& GVs);
  };
}

bool
ReduceCrashingGlobalVariables::TestGlobalVariables(
                              std::vector<GlobalVariable*>& GVs) {
  // Clone the program to try hacking it apart...
  Module *M = CloneModule(BD.getProgram());

  // Convert list to set for fast lookup...
  std::set<GlobalVariable*> GVSet;

  for (unsigned i = 0, e = GVs.size(); i != e; ++i) {
    GlobalVariable* CMGV = M->getNamedGlobal(GVs[i]->getName());
    assert(CMGV && "Global Variable not in module?!");
    GVSet.insert(CMGV);
  }

  std::cout << "Checking for crash with only these global variables: ";
  PrintGlobalVariableList(GVs);
  std::cout << ": ";

  // Loop over and delete any global variables which we aren't supposed to be
  // playing with...
  for (Module::global_iterator I = M->global_begin(), E = M->global_end();
       I != E; ++I)
    if (I->hasInitializer()) {
      I->setInitializer(0);
      I->setLinkage(GlobalValue::ExternalLinkage);
    }

  // Try running the hacked up program...
  if (TestFn(BD, M)) {
    BD.setNewProgram(M);        // It crashed, keep the trimmed version...

    // Make sure to use global variable pointers that point into the now-current
    // module.
    GVs.assign(GVSet.begin(), GVSet.end());
    return true;
  }

  delete M;
  return false;
}

namespace llvm {
  /// ReduceCrashingFunctions reducer - This works by removing functions and
  /// seeing if the program still crashes. If it does, then keep the newer,
  /// smaller program.
  ///
  class ReduceCrashingFunctions : public ListReducer<Function*> {
    BugDriver &BD;
    bool (*TestFn)(BugDriver &, Module *);
  public:
    ReduceCrashingFunctions(BugDriver &bd,
                            bool (*testFn)(BugDriver &, Module *))
      : BD(bd), TestFn(testFn) {}

    virtual TestResult doTest(std::vector<Function*> &Prefix,
                              std::vector<Function*> &Kept) {
      if (!Kept.empty() && TestFuncs(Kept))
        return KeepSuffix;
      if (!Prefix.empty() && TestFuncs(Prefix))
        return KeepPrefix;
      return NoFailure;
    }

    bool TestFuncs(std::vector<Function*> &Prefix);
  };
}

bool ReduceCrashingFunctions::TestFuncs(std::vector<Function*> &Funcs) {

  //if main isn't present, claim there is no problem
  if (KeepMain && find(Funcs.begin(), Funcs.end(),
                       BD.getProgram()->getFunction("main")) == Funcs.end())
    return false;

  // Clone the program to try hacking it apart...
  Module *M = CloneModule(BD.getProgram());

  // Convert list to set for fast lookup...
  std::set<Function*> Functions;
  for (unsigned i = 0, e = Funcs.size(); i != e; ++i) {
    // FIXME: bugpoint should add names to all stripped symbols.
    assert(!Funcs[i]->getName().empty() &&
           "Bugpoint doesn't work on stripped modules yet PR718!");
    Function *CMF = M->getFunction(