[Attributor] AAFunctionReachability, Handle CallBase Reachability.

[kuter]

Summary

This patch makes it possible to query callbase reachability
(Can a callbase reach a function Fn transitively).
The patch moves the reachability query handling logic to a member class,
this class will have more users within the AA once we add other function
reachability queries.

[kuter]

Rmove useless comment.

[kuter]

Fix issue with the unittest.
Change tracking issue.

[kuter]

Use the new |= operator for change tracking.

[kuter]

• Use early increment iterator range rather than hacky code.
• Fix the infinite loop issue.
• Negative test case.

[jdoerfert]

llvm/lib/Transforms/IPO/AttributorAttributes.cpp

8617

I don't get this. In line 9331 we iterate over unreachable and ask isReachable but we always would return false because of this, no?

8627

8652

You can use recordDependence here to make it clear what is happening and avoid some unnecessary code.

8744

Documentation for both.

[kuter]

address review.

[jdoerfert]

LG

[kuter]

Use recordDependence

llvm/include/llvm/Transforms/IPO/Attributor.h

struct AAFunctionReachability
     : public StateWrapper<BooleanState, AbstractAttribute> {
   using Base = StateWrapper<BooleanState, AbstractAttribute>;
 
   AAFunctionReachability(const IRPosition &IRP, Attributor &A) : Base(IRP) {}
 
   /// If the function represented by this possition can reach \p Fn.
   virtual bool canReach(Attributor &A, Function *Fn) const = 0;
 
+  /// Can \p CB reach \p Fn
+  virtual bool canReach(Attributor &A, CallBase &CB, Function *Fn) const = 0;
+
   /// Create an abstract attribute view for the position \p IRP.
   static AAFunctionReachability &createForPosition(const IRPosition &IRP,
                                                    Attributor &A);
 
   /// See AbstractAttribute::getName()
   const std::string getName() const override { return "AAFuncitonReacability"; }
 
   /// See AbstractAttribute::getIdAddr()

llvm/lib/Transforms/IPO/AttributorAttributes.cpp

if (!A.checkForAllCallLikeInstructions(ProcessCallInst, *this,
       setHasUnknownCallee(true, Change);
     }
 
     return Change;
   }
 };
 
 struct AAFunctionReachabilityFunction : public AAFunctionReachability {
-  AAFunctionReachabilityFunction(const IRPosition &IRP, Attributor &A)
-      : AAFunctionReachability(IRP, A) {}
+private:
+  struct QuerySet {
+    ChangeStatus update(Attributor &A, const AAFunctionReachability &AA,
+                        ArrayRef<const AACallEdges *> AAEdgesList) {
+      ChangeStatus Change = ChangeStatus::UNCHANGED;
 
-  bool canReach(Attributor &A, Function *Fn) const override {
-    // Assume that we can reach any function if we can reach a call with
-    // unknown callee.
+      for (auto *AAEdges : AAEdgesList) {
+        if (AAEdges->hasUnknownCallee()) {
+          if (CanReachUnknownCallee)
+            Change = ChangeStatus::CHANGED;
+          CanReachUnknownCallee = true;
+          return Change;
+        }
+      }
+
+      for (auto It = Unreachable.begin(); It != Unreachable.end();) {
+        Function *Fn = *It;
+        It++;
+        if (isReachable(A, AA, AAEdgesList, Fn))
+          Change = ChangeStatus::CHANGED;
+      }
+
+      return Change;
+    }
+
+    bool isReachable(Attributor &A, const AAFunctionReachability &AA,
+                     ArrayRef<const AACallEdges *> AAEdgesList, Function *Fn) {
+      // Assume that we can reach the function.
+      // TODO: Be more specific with the unknown callee.
       if (CanReachUnknownCallee)
         return true;
 
-    if (ReachableQueries.count(Fn))
+      if (Reachable.count(Fn))
         return true;
 
-    if (UnreachableQueries.count(Fn))
+      if (Unreachable.count(Fn))
         return false;
 
+      bool Result = checkIfReachable(A, AA, AAEdgesList, Fn);
+      if (Result) {
+        Reachable.insert(Fn);
+        Unreachable.erase(Fn);
+      } else {
+        Unreachable.insert(Fn);
+      }
+      return Result;
+    }
+
+    bool checkIfReachable(Attributor &A, const AAFunctionReachability &AA,
+                          ArrayRef<const AACallEdges *> AAEdgesList,
+                          Function *Fn) const {
+
+      // Handle the most trivial case first.
+      for (auto *AAEdges : AAEdgesList) {
+        const SetVector<Function *> Edges = AAEdges->getOptimisticEdges();
+
+        if (Edges.count(Fn))
+          return true;
+      }
+
+      for (auto &AAEdges : AAEdgesList) {
+        const SetVector<Function *> &Edges = AAEdges->getOptimisticEdges();
+
+        for (Function *Edge : Edges) {
+          // We don't need a dependency if the result is reachable.
+          const AAFunctionReachability &EdgeReachability =
+              A.getAAFor<AAFunctionReachability>(
+                  AA, IRPosition::function(*Edge), DepClassTy::NONE);
+          if (EdgeReachability.canReach(A, Fn))
+            return true;
+        }
+      }
+
+      // The result is false for now, set dependencies and leave.
+      for (auto &AAEdges : AAEdgesList) {
+        const SetVector<Function *> &Edges = AAEdges->getOptimisticEdges();
+
+        for (Function *Fn : Edges) {
+          A.getAAFor<AAFunctionReachability>(AA, IRPosition::function(*Fn),
+                                             DepClassTy::REQUIRED);
+        }
+      }
+      return false;
+    }
+
+    /// Set of functions that we know for sure is reachable.
+    DenseSet<Function *> Reachable;
+
+    /// Set of functions that are unreachable, but might become reachable.
+    DenseSet<Function *> Unreachable;
+
+    /// If we can reach a function with a call to a unknown function we assume
+    /// that we can reach any function.
+    bool CanReachUnknownCallee = false;
+  };
+
+public:
+  AAFunctionReachabilityFunction(const IRPosition &IRP, Attributor &A)
+      : AAFunctionReachability(IRP, A) {}
+
+  bool canReach(Attributor &A, Function *Fn) const override {
     const AACallEdges &AAEdges =
         A.getAAFor<AACallEdges>(*this, getIRPosition(), DepClassTy::REQUIRED);
 
-    const SetVector<Function *> &Edges = AAEdges.getOptimisticEdges();
-    bool Result = checkIfReachable(A, Edges, Fn);
+    // Attributor returns attributes as const, so this function has to be
+    // const for users of this attribute to use it without having to do
+    // a const_cast.
+    // This is a hack for us to be able to cache queries.
+    auto *NonConstThis = const_cast<AAFunctionReachabilityFunction *>(this);
+    bool Result =
+        NonConstThis->WholeFunction.isReachable(A, *this, {&AAEdges}, Fn);
+
+    return Result;
+  }
+
+  /// Can \p CB reach \p Fn
+  bool canReach(Attributor &A, CallBase &CB, Function *Fn) const override {
+    const AACallEdges &AAEdges = A.getAAFor<AACallEdges>(
+        *this, IRPosition::callsite_function(CB), DepClassTy::REQUIRED);
 
     // Attributor returns attributes as const, so this function has to be
     // const for users of this attribute to use it without having to do
     // a const_cast.
     // This is a hack for us to be able to cache queries.
     auto *NonConstThis = const_cast<AAFunctionReachabilityFunction *>(this);
+    QuerySet &CBQuery = NonConstThis->CBQueries[&CB];
 
-    if (Result)
-      NonConstThis->ReachableQueries.insert(Fn);
-    else
-      NonConstThis->UnreachableQueries.insert(Fn);
+    bool Result = CBQuery.isReachable(A, *this, {&AAEdges}, Fn);
 
     return Result;
   }
 
   /// See AbstractAttribute::updateImpl(...).
   ChangeStatus updateImpl(Attributor &A) override {
-    if (CanReachUnknownCallee)
-      return ChangeStatus::UNCHANGED;
-
     const AACallEdges &AAEdges =
         A.getAAFor<AACallEdges>(*this, getIRPosition(), DepClassTy::REQUIRED);
-    const SetVector<Function *> &Edges = AAEdges.getOptimisticEdges();
     ChangeStatus Change = ChangeStatus::UNCHANGED;
 
-    if (AAEdges.hasUnknownCallee()) {
-      bool OldCanReachUnknown = CanReachUnknownCallee;
-      CanReachUnknownCallee = true;
-      return OldCanReachUnknown ? ChangeStatus::UNCHANGED
-                                : ChangeStatus::CHANGED;
-    }
+    WholeFunction.update(A, *this, {&AAEdges});
 
-    // Check if any of the unreachable functions become reachable.
-    for (auto Current = UnreachableQueries.begin();
-         Current != UnreachableQueries.end();) {
-      if (!checkIfReachable(A, Edges, *Current)) {
-        Current++;
-        continue;
-      }
-      ReachableQueries.insert(*Current);
-      UnreachableQueries.erase(*Current++);
-      Change = ChangeStatus::CHANGED;
+    for (auto CBPair : CBQueries) {
+      const AACallEdges &AAEdges = A.getAAFor<AACallEdges>(
+          *this, IRPosition::callsite_function(*CBPair.first),
+          DepClassTy::REQUIRED);
+
+      CBPair.second.update(A, *this, {&AAEdges});
     }
 
     return Change;
   }
 
   const std::string getAsStr() const override {
-    size_t QueryCount = ReachableQueries.size() + UnreachableQueries.size();
+    size_t QueryCount =
+        WholeFunction.Reachable.size() + WholeFunction.Unreachable.size();
 
-    return "FunctionReachability [" + std::to_string(ReachableQueries.size()) +
-           "," + std::to_string(QueryCount) + "]";
+    return "FunctionReachability [" +
+           std::to_string(WholeFunction.Reachable.size()) + "," +
+           std::to_string(QueryCount) + "]";
   }
 
   void trackStatistics() const override {}
-
 private:
-  bool canReachUnknownCallee() const override { return CanReachUnknownCallee; }
-
-  bool checkIfReachable(Attributor &A, const SetVector<Function *> &Edges,
-                        Function *Fn) const {
-    if (Edges.count(Fn))
-      return true;
-
-    for (Function *Edge : Edges) {
-      // We don't need a dependency if the result is reachable.
-      const AAFunctionReachability &EdgeReachability =
-          A.getAAFor<AAFunctionReachability>(*this, IRPosition::function(*Edge),
-                                             DepClassTy::NONE);
-
-      if (EdgeReachability.canReach(A, Fn))
-        return true;
-    }
-    for (Function *Fn : Edges)
-      A.getAAFor<AAFunctionReachability>(*this, IRPosition::function(*Fn),
-                                         DepClassTy::REQUIRED);
+  bool canReachUnknownCallee() const override {
+    return WholeFunction.CanReachUnknownCallee;
 
-    return false;
-  }
-
-  /// Set of functions that we know for sure is reachable.
-  SmallPtrSet<Function *, 8> ReachableQueries;
-
-  /// Set of functions that are unreachable, but might become reachable.
-  SmallPtrSet<Function *, 8> UnreachableQueries;
-
-  /// If we can reach a function with a call to a unknown function we assume
-  /// that we can reach any function.
-  bool CanReachUnknownCallee = false;
+  QuerySet WholeFunction;
+  DenseMap<CallBase *, QuerySet> CBQueries;
 };
 
 } // namespace
 
 AACallGraphNode *AACallEdgeIterator::operator*() const {
   return static_cast<AACallGraphNode *>(const_cast<AACallEdges *>(
       &A.getOrCreateAAFor<AACallEdges>(IRPosition::function(**I))));
 }

llvm/unittests/Transforms/IPO/AttributorTest.cpp

entry:
       ret void
     }
 
     define void @func6() {
     entry:
       call void @func5(void ()* @func3)
       ret void
     }
+
+    define void @func7() {
+    entry:
+      call void @func2()
+      call void @func4()
+      ret void
+    }
   )";
 
   Module &M = parseModule(ModuleString);
 
   SetVector<Function *> Functions;
   AnalysisGetter AG;
   for (Function &F : M)
     Functions.insert(&F);
 
   CallGraphUpdater CGUpdater;
   BumpPtrAllocator Allocator;
   InformationCache InfoCache(M, AG, Allocator, nullptr);
   Attributor A(Functions, InfoCache, CGUpdater);
 
   Function *F1 = M.getFunction("func1");
   Function *F3 = M.getFunction("func3");
   Function *F4 = M.getFunction("func4");
   Function *F6 = M.getFunction("func6");
+  Function *F7 = M.getFunction("func7");
+
+  // call void @func2()
+  CallBase &F7FirstCB = *static_cast<CallBase *>(*F7.getEntryBlock().begin());
 
   const AAFunctionReachability &F1AA =
       A.getOrCreateAAFor<AAFunctionReachability>(IRPosition::function(*F1));
 
   const AAFunctionReachability &F6AA =
       A.getOrCreateAAFor<AAFunctionReachability>(IRPosition::function(*F6));
 
+  const AAFunctionReachability &F7AA =
+      A.getOrCreateAAFor<AAFunctionReachability>(IRPosition::function(*F7));
+
   F1AA.canReach(A, F3);
   F1AA.canReach(A, F4);
   F6AA.canReach(A, F4);
+  F7AA.canReach(A, F7FirstCB, F3);
+  F7AA.canReach(A, F7FirstCB, F4);
 
   A.run();
 
   ASSERT_TRUE(F1AA.canReach(A, F3));
+  ASSERT_TRUE(F7AA.canReach(A, F7FirstCB, F3));
+  ASSERT_TRUE(F7AA.canReach(A, F7FirstCB, F4));
   ASSERT_FALSE(F1AA.canReach(A, F4));
 
   // Assumed to be reacahable, since F6 can reach a function with
   // a unknown callee.
   ASSERT_TRUE(F6AA.canReach(A, F4));
 }
 
 } // namespace llvm