[DataFlow] Factor two worklist implementations out

Right now every dataflow algorithm uses its own worklist implementation.
This is a first step to reduce this duplication. Some upcoming
algorithms such as the lifetime analysis is going to use the factored
out implementations.

Differential Revision: https://reviews.llvm.org/D72380

clang/include/clang/Analysis/FlowSensitive/DataflowValues.h

@@ -168,4 +168,4 @@ protected:
 };
 
 } // end namespace clang
-#endif
+#endif // LLVM_CLANG_ANALYSES_DATAFLOW_VALUES

clang/include/clang/Analysis/FlowSensitive/DataflowWorklist.h

@@ -0,0 +1,94 @@
+//===- DataflowWorklist.h ---------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// A simple and reusable worklist for flow-sensitive analyses.
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_CLANG_ANALYSIS_FLOWSENSITIVE_DATAFLOWWORKLIST_H
+#define LLVM_CLANG_ANALYSIS_FLOWSENSITIVE_DATAFLOWWORKLIST_H
+
+#include "clang/Analysis/Analyses/PostOrderCFGView.h"
+#include "clang/Analysis/CFG.h"
+#include "llvm/ADT/PriorityQueue.h"
+
+namespace clang {
+/// A worklist implementation where the enqueued blocks will be dequeued based
+/// on the order defined by 'Comp'.
+template <typename Comp, unsigned QueueSize> class DataflowWorklistBase {
+  llvm::BitVector EnqueuedBlocks;
+  PostOrderCFGView *POV;
+  llvm::PriorityQueue<const CFGBlock *,
+                      SmallVector<const CFGBlock *, QueueSize>, Comp>
+      WorkList;
+
+public:
+  DataflowWorklistBase(const CFG &Cfg, PostOrderCFGView *POV, Comp C)
+      : EnqueuedBlocks(Cfg.getNumBlockIDs()), POV(POV), WorkList(C) {}
+
+  const PostOrderCFGView *getCFGView() const { return POV; }
+
+  void enqueueBlock(const CFGBlock *Block) {
+    if (Block && !EnqueuedBlocks[Block->getBlockID()]) {
+      EnqueuedBlocks[Block->getBlockID()] = true;
+      WorkList.push(Block);
+    }
+  }
+
+  const CFGBlock *dequeue() {
+    if (WorkList.empty())
+      return nullptr;
+    const CFGBlock *B = WorkList.top();
+    WorkList.pop();
+    EnqueuedBlocks[B->getBlockID()] = false;
+    return B;
+  }
+};
+
+struct ReversePostOrderCompare {
+  PostOrderCFGView::BlockOrderCompare Cmp;
+  bool operator()(const CFGBlock *lhs, const CFGBlock *rhs) const {
+    return Cmp(rhs, lhs);
+  }
+};
+
+/// A worklist implementation for forward dataflow analysis. The enqueued
+/// blocks will be dequeued in reverse post order. The worklist cannot contain
+/// the same block multiple times at once.
+struct ForwardDataflowWorklist
+    : DataflowWorklistBase<ReversePostOrderCompare, 20> {
+  ForwardDataflowWorklist(const CFG &Cfg, AnalysisDeclContext &Ctx)
+      : DataflowWorklistBase(
+            Cfg, Ctx.getAnalysis<PostOrderCFGView>(),
+            ReversePostOrderCompare{
+                Ctx.getAnalysis<PostOrderCFGView>()->getComparator()}) {}
+
+  void enqueueSuccessors(const CFGBlock *Block) {
+    for (auto B : Block->succs())
+      enqueueBlock(B);
+  }
+};
+
+/// A worklist implementation for backward dataflow analysis. The enqueued
+/// block will be dequeued in post order. The worklist cannot contain the same
+/// block multiple times at once.
+struct BackwardDataflowWorklist
+    : DataflowWorklistBase<PostOrderCFGView::BlockOrderCompare, 20> {
+  BackwardDataflowWorklist(const CFG &Cfg, AnalysisDeclContext &Ctx)
+      : DataflowWorklistBase(
+            Cfg, Ctx.getAnalysis<PostOrderCFGView>(),
+            Ctx.getAnalysis<PostOrderCFGView>()->getComparator()) {}
+
+  void enqueuePredecessors(const CFGBlock *Block) {
+    for (auto B : Block->preds())
+      enqueueBlock(B);
+  }
+};
+
+} // namespace clang
+
+#endif // LLVM_CLANG_ANALYSIS_ANALYSES_CONSUMED_H

clang/lib/Analysis/LiveVariables.cpp

@@ -13,63 +13,16 @@
 #include "clang/Analysis/Analyses/LiveVariables.h"
 #include "clang/AST/Stmt.h"
 #include "clang/AST/StmtVisitor.h"
-#include "clang/Analysis/Analyses/PostOrderCFGView.h"
 #include "clang/Analysis/AnalysisDeclContext.h"
 #include "clang/Analysis/CFG.h"
+#include "clang/Analysis/FlowSensitive/DataflowWorklist.h"
 #include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/PostOrderIterator.h"
-#include "llvm/ADT/PriorityQueue.h"
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <vector>
 
 using namespace clang;
 
-namespace {
-
-class DataflowWorklist {
-  llvm::BitVector enqueuedBlocks;
-  PostOrderCFGView *POV;
-  llvm::PriorityQueue<const CFGBlock *, SmallVector<const CFGBlock *, 20>,
-                      PostOrderCFGView::BlockOrderCompare> worklist;
-
-public:
-  DataflowWorklist(const CFG &cfg, AnalysisDeclContext &Ctx)
-    : enqueuedBlocks(cfg.getNumBlockIDs()),
-      POV(Ctx.getAnalysis<PostOrderCFGView>()),
-      worklist(POV->getComparator()) {}
-
-  void enqueueBlock(const CFGBlock *block);
-  void enqueuePredecessors(const CFGBlock *block);
-
-  const CFGBlock *dequeue();
-};
-
-}
-
-void DataflowWorklist::enqueueBlock(const clang::CFGBlock *block) {
-  if (block && !enqueuedBlocks[block->getBlockID()]) {
-    enqueuedBlocks[block->getBlockID()] = true;
-    worklist.push(block);
-  }
-}
-
-void DataflowWorklist::enqueuePredecessors(const clang::CFGBlock *block) {
-  for (CFGBlock::const_pred_iterator I = block->pred_begin(),
-       E = block->pred_end(); I != E; ++I) {
-    enqueueBlock(*I);
-  }
-}
-
-const CFGBlock *DataflowWorklist::dequeue() {
-  if (worklist.empty())
-    return nullptr;
-  const CFGBlock *b = worklist.top();
-  worklist.pop();
-  enqueuedBlocks[b->getBlockID()] = false;
-  return b;
-}
-
 namespace {
 class LiveVariablesImpl {
 public:
@@ -136,7 +89,7 @@ namespace {
     }
     return A;
   }
-}
+} // namespace
 
 void LiveVariables::Observer::anchor() { }
 
@@ -218,7 +171,7 @@ public:
   void VisitUnaryOperator(UnaryOperator *UO);
   void Visit(Stmt *S);
 };
-}
+} // namespace
 
 static const VariableArrayType *FindVA(QualType Ty) {
   const Type *ty = Ty.getTypePtr();
@@ -555,7 +508,7 @@ LiveVariables::computeLiveness(AnalysisDeclContext &AC,
 
   // Construct the dataflow worklist.  Enqueue the exit block as the
   // start of the analysis.
-  DataflowWorklist worklist(*cfg, AC);
+  BackwardDataflowWorklist worklist(*cfg, AC);
   llvm::BitVector everAnalyzedBlock(cfg->getNumBlockIDs());
 
   // FIXME: we should enqueue using post order.

clang/lib/Analysis/UninitializedValues.cpp

@@ -24,6 +24,7 @@
 #include "clang/Analysis/AnalysisDeclContext.h"
 #include "clang/Analysis/CFG.h"
 #include "clang/Analysis/DomainSpecific/ObjCNoReturn.h"
+#include "clang/Analysis/FlowSensitive/DataflowWorklist.h"
 #include "clang/Basic/LLVM.h"
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/DenseMap.h"
@@ -212,68 +213,6 @@ ValueVector::reference CFGBlockValues::operator[](const VarDecl *vd) {
   return scratch[idx.getValue()];
 }
 
-//------------------------------------------------------------------------====//
-// Worklist: worklist for dataflow analysis.
-//====------------------------------------------------------------------------//
-
-namespace {
-
-class DataflowWorklist {
-  PostOrderCFGView::iterator PO_I, PO_E;
-  SmallVector<const CFGBlock *, 20> worklist;
-  llvm::BitVector enqueuedBlocks;
-
-public:
-  DataflowWorklist(const CFG &cfg, PostOrderCFGView &view)
-      : PO_I(view.begin()), PO_E(view.end()),
-        enqueuedBlocks(cfg.getNumBlockIDs(), true) {
-    // Treat the first block as already analyzed.
-    if (PO_I != PO_E) {
-      assert(*PO_I == &cfg.getEntry());
-      enqueuedBlocks[(*PO_I)->getBlockID()] = false;
-      ++PO_I;
-    }
-  }
-
-  void enqueueSuccessors(const CFGBlock *block);
-  const CFGBlock *dequeue();
-};
-
-} // namespace
-
-void DataflowWorklist::enqueueSuccessors(const CFGBlock *block) {
-  for (CFGBlock::const_succ_iterator I = block->succ_begin(),
-       E = block->succ_end(); I != E; ++I) {
-    const CFGBlock *Successor = *I;
-    if (!Successor || enqueuedBlocks[Successor->getBlockID()])
-      continue;
-    worklist.push_back(Successor);
-    enqueuedBlocks[Successor->getBlockID()] = true;
-  }
-}
-
-const CFGBlock *DataflowWorklist::dequeue() {
-  const CFGBlock *B = nullptr;
-
-  // First dequeue from the worklist.  This can represent
-  // updates along backedges that we want propagated as quickly as possible.
-  if (!worklist.empty())
-    B = worklist.pop_back_val();
-
-  // Next dequeue from the initial reverse post order.  This is the
-  // theoretical ideal in the presence of no back edges.
-  else if (PO_I != PO_E) {
-    B = *PO_I;
-    ++PO_I;
-  }
-  else
-    return nullptr;
-
-  assert(enqueuedBlocks[B->getBlockID()] == true);
-  enqueuedBlocks[B->getBlockID()] = false;
-  return B;
-}
-
 //------------------------------------------------------------------------====//
 // Classification of DeclRefExprs as use or initialization.
 //====------------------------------------------------------------------------//
@@ -924,7 +863,7 @@ void clang::runUninitializedVariablesAnalysis(
   }
 
   // Proceed with the workist.
-  DataflowWorklist worklist(cfg, *ac.getAnalysis<PostOrderCFGView>());
+  ForwardDataflowWorklist worklist(cfg, ac);
   llvm::BitVector previouslyVisited(cfg.getNumBlockIDs());
   worklist.enqueueSuccessors(&cfg.getEntry());
   llvm::BitVector wasAnalyzed(cfg.getNumBlockIDs(), false);

clang/unittests/Analysis/CFGBuildResult.h

@@ -23,18 +23,21 @@ public:
     BuiltCFG,
   };
 
-  BuildResult(Status S, std::unique_ptr<CFG> Cfg = nullptr,
+  BuildResult(Status S, const FunctionDecl *Func = nullptr,
+              std::unique_ptr<CFG> Cfg = nullptr,
               std::unique_ptr<ASTUnit> AST = nullptr)
-      : S(S), Cfg(std::move(Cfg)), AST(std::move(AST)) {}
+      : S(S), Cfg(std::move(Cfg)), AST(std::move(AST)), Func(Func) {}
 
   Status getStatus() const { return S; }
   CFG *getCFG() const { return Cfg.get(); }
   ASTUnit *getAST() const { return AST.get(); }
+  const FunctionDecl *getFunc() const { return Func; }
 
 private:
   Status S;
   std::unique_ptr<CFG> Cfg;
   std::unique_ptr<ASTUnit> AST;
+  const FunctionDecl *Func;
 };
 
 class CFGCallback : public ast_matchers::MatchFinder::MatchCallback {
@@ -54,7 +57,8 @@ public:
     Options.AddImplicitDtors = true;
     if (std::unique_ptr<CFG> Cfg =
             CFG::buildCFG(nullptr, Body, Result.Context, Options))
-      TheBuildResult = {BuildResult::BuiltCFG, std::move(Cfg), std::move(AST)};
+      TheBuildResult = {BuildResult::BuiltCFG, Func, std::move(Cfg),
+                        std::move(AST)};
   }
 };
 

clang/unittests/Analysis/CFGTest.cpp

@@ -7,10 +7,14 @@
 //===----------------------------------------------------------------------===//
 
 #include "CFGBuildResult.h"
+#include "clang/AST/Decl.h"
 #include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/Analysis/AnalysisDeclContext.h"
 #include "clang/Analysis/CFG.h"
+#include "clang/Analysis/FlowSensitive/DataflowWorklist.h"
 #include "clang/Tooling/Tooling.h"
 #include "gtest/gtest.h"
+#include <algorithm>
 #include <string>
 #include <vector>
 
@@ -216,6 +220,54 @@ TEST(CFG, ElementRefIterator) {
   EXPECT_EQ(++(CMainBlock->rref_begin()), CMainBlock->rref_begin() + 1);
 }
 
+TEST(CFG, Worklists) {
+  const char *Code = "int f(bool cond) {\n"
+                     "  int a = 5;\n"
+                     "  if (cond)\n"
+                     "    a += 1;\n"
+                     "  return a;\n"
+                     "}\n";
+  BuildResult B = BuildCFG(Code);
+  EXPECT_EQ(BuildResult::BuiltCFG, B.getStatus());
+  const FunctionDecl *Func = B.getFunc();
+  AnalysisDeclContext AC(nullptr, Func);
+  auto *CFG = AC.getCFG();
+
+  std::vector<const CFGBlock *> ReferenceOrder;
+  for (const auto *B : *AC.getAnalysis<PostOrderCFGView>())
+    ReferenceOrder.push_back(B);
+
+  {
+    ForwardDataflowWorklist ForwardWorklist(*CFG, AC);
+    for (const auto *B : *CFG)
+      ForwardWorklist.enqueueBlock(B);
+
+    std::vector<const CFGBlock *> ForwardNodes;
+    while (const CFGBlock *B = ForwardWorklist.dequeue())
+      ForwardNodes.push_back(B);
+
+    EXPECT_EQ(ForwardNodes.size(), ReferenceOrder.size());
+    EXPECT_TRUE(std::equal(ReferenceOrder.begin(), ReferenceOrder.end(),
+                           ForwardNodes.begin()));
+  }
+
+  std::reverse(ReferenceOrder.begin(), ReferenceOrder.end());
+
+  {
+    BackwardDataflowWorklist BackwardWorklist(*CFG, AC);
+    for (const auto *B : *CFG)
+      BackwardWorklist.enqueueBlock(B);
+
+    std::vector<const CFGBlock *> BackwardNodes;
+    while (const CFGBlock *B = BackwardWorklist.dequeue())
+      BackwardNodes.push_back(B);
+
+    EXPECT_EQ(BackwardNodes.size(), ReferenceOrder.size());
+    EXPECT_TRUE(std::equal(ReferenceOrder.begin(), ReferenceOrder.end(),
+                           BackwardNodes.begin()));
+  }
+}
+
 } // namespace
 } // namespace analysis
 } // namespace clang