WholeProgramDevirt: Move logic for finding devirtualizable call sites to Analysis.

[pcc]

Summary

The plan is to eventually make this logic simpler, however I expect it to
be a little tricky for the foreseeable future (at least until we're rid of
pointee types), so move it here so that it can be reused to build a summary
index for devirtualization.

[tejohnson]

Looks NFC to me. Are there any existing tests or would a unittest for the new Analysis routines be appropriate?

include/llvm/Analysis/BitSetUtils.h

31 ↗

(On Diff #56372)

Use doxygen style comments

[pcc]

Yes, this is covered by the tests for the pass in test/Transforms/WholeProgramDevirt.

llvm/trunk/include/llvm/Analysis/BitSetUtils.h

+//===- BitSetUtils.h - Utilities related to pointer bitsets ------*- C++ -*-==//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains functions that make it easier to manipulate bitsets for
+// devirtualization.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_BITSETUTILS_H
+#define LLVM_ANALYSIS_BITSETUTILS_H
+
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/IR/CallSite.h"
+
+namespace llvm {
+
+// A call site that could be devirtualized.
+struct DevirtCallSite {
+  // The offset from the address point to the virtual function.
+  uint64_t Offset;
+  // The call site itself.
+  CallSite CS;
+};
+
+// Given a call to the intrinsic @llvm.bitset.test, find all devirtualizable
+// call sites based on the call and return them in DevirtCalls.
+void findDevirtualizableCalls(SmallVectorImpl<DevirtCallSite> &DevirtCalls,
+                              SmallVectorImpl<CallInst *> &Assumes,
+                              CallInst *CI);
+}
+
+#endif

llvm/trunk/lib/Analysis/BitSetUtils.cpp

+//===- BitSetUtils.cpp - Utilities related to pointer bitsets -------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains functions that make it easier to manipulate bitsets for
+// devirtualization.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/BitSetUtils.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/Module.h"
+
+using namespace llvm;
+
+// Search for virtual calls that call FPtr and add them to DevirtCalls.
+static void
+findCallsAtConstantOffset(SmallVectorImpl<DevirtCallSite> &DevirtCalls,
+                          Value *FPtr, uint64_t Offset) {
+  for (const Use &U : FPtr->uses()) {
+    Value *User = U.getUser();
+    if (isa<BitCastInst>(User)) {
+      findCallsAtConstantOffset(DevirtCalls, User, Offset);
+    } else if (auto CI = dyn_cast<CallInst>(User)) {
+      DevirtCalls.push_back({Offset, CI});
+    } else if (auto II = dyn_cast<InvokeInst>(User)) {
+      DevirtCalls.push_back({Offset, II});
+    }
+  }
+}
+
+// Search for virtual calls that load from VPtr and add them to DevirtCalls.
+static void
+findLoadCallsAtConstantOffset(Module *M,
+                              SmallVectorImpl<DevirtCallSite> &DevirtCalls,
+                              Value *VPtr, uint64_t Offset) {
+  for (const Use &U : VPtr->uses()) {
+    Value *User = U.getUser();
+    if (isa<BitCastInst>(User)) {
+      findLoadCallsAtConstantOffset(M, DevirtCalls, User, Offset);
+    } else if (isa<LoadInst>(User)) {
+      findCallsAtConstantOffset(DevirtCalls, User, Offset);
+    } else if (auto GEP = dyn_cast<GetElementPtrInst>(User)) {
+      // Take into account the GEP offset.
+      if (VPtr == GEP->getPointerOperand() && GEP->hasAllConstantIndices()) {
+        SmallVector<Value *, 8> Indices(GEP->op_begin() + 1, GEP->op_end());
+        uint64_t GEPOffset = M->getDataLayout().getIndexedOffsetInType(
+            GEP->getSourceElementType(), Indices);
+        findLoadCallsAtConstantOffset(M, DevirtCalls, User, Offset + GEPOffset);
+      }
+    }
+  }
+}
+
+void llvm::findDevirtualizableCalls(
+    SmallVectorImpl<DevirtCallSite> &DevirtCalls,
+    SmallVectorImpl<CallInst *> &Assumes, CallInst *CI) {
+  assert(CI->getCalledFunction()->getIntrinsicID() == Intrinsic::bitset_test);
+
+  Module *M = CI->getParent()->getParent()->getParent();
+
+  // Find llvm.assume intrinsics for this llvm.bitset.test call.
+  for (const Use &CIU : CI->uses()) {
+    auto AssumeCI = dyn_cast<CallInst>(CIU.getUser());
+    if (AssumeCI) {
+      Function *F = AssumeCI->getCalledFunction();
+      if (F && F->getIntrinsicID() == Intrinsic::assume)
+        Assumes.push_back(AssumeCI);
+    }
+  }
+
+  // If we found any, search for virtual calls based on %p and add them to
+  // DevirtCalls.
+  if (!Assumes.empty())
+    findLoadCallsAtConstantOffset(M, DevirtCalls,
+                                  CI->getArgOperand(0)->stripPointerCasts(), 0);
+}

llvm/trunk/lib/Analysis/CMakeLists.txt

 add_llvm_library(LLVMAnalysis
   AliasAnalysis.cpp
   AliasAnalysisEvaluator.cpp
   AliasSetTracker.cpp
   Analysis.cpp
   AssumptionCache.cpp
   BasicAliasAnalysis.cpp
+  BitSetUtils.cpp
   BlockFrequencyInfo.cpp
   BlockFrequencyInfoImpl.cpp
   BranchProbabilityInfo.cpp
   CFG.cpp
   CFGPrinter.cpp
   CFLAliasAnalysis.cpp
   CGSCCPassManager.cpp
   CallGraph.cpp

llvm/trunk/lib/Transforms/IPO/WholeProgramDevirt.cpp

 //   call with a comparison of the vptr against that vtable's address.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Transforms/IPO/WholeProgramDevirt.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/MapVector.h"
+#include "llvm/Analysis/BitSetUtils.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Pass.h"
struct DevirtModule {
   IntegerType *Int32Ty;
 
   MapVector<VTableSlot, std::vector<VirtualCallSite>> CallSlots;
 
   DevirtModule(Module &M)
       : M(M), Int8Ty(Type::getInt8Ty(M.getContext())),
         Int8PtrTy(Type::getInt8PtrTy(M.getContext())),
         Int32Ty(Type::getInt32Ty(M.getContext())) {}
-  void findLoadCallsAtConstantOffset(Metadata *BitSet, Value *Ptr,
-                                     uint64_t Offset, Value *VTable);
-  void findCallsAtConstantOffset(Metadata *BitSet, Value *Ptr, uint64_t Offset,
-                                 Value *VTable);
 
   void buildBitSets(std::vector<VTableBits> &Bits,
                     DenseMap<Metadata *, std::set<BitSetInfo>> &BitSets);
   bool tryFindVirtualCallTargets(std::vector<VirtualCallTarget> &TargetsForSlot,
                                  const std::set<BitSetInfo> &BitSetInfos,
                                  uint64_t ByteOffset);
   bool trySingleImplDevirt(ArrayRef<VirtualCallTarget> TargetsForSlot,
                            MutableArrayRef<VirtualCallSite> CallSites);

 INITIALIZE_PASS(WholeProgramDevirt, "wholeprogramdevirt",
                 "Whole program devirtualization", false, false)
 char WholeProgramDevirt::ID = 0;
 
 ModulePass *llvm::createWholeProgramDevirtPass() {
   return new WholeProgramDevirt;
 }
 
-// Search for virtual calls that call FPtr and add them to CallSlots.
-void DevirtModule::findCallsAtConstantOffset(Metadata *BitSet, Value *FPtr,
-                                             uint64_t Offset, Value *VTable) {
-  for (const Use &U : FPtr->uses()) {
-    Value *User = U.getUser();
-    if (isa<BitCastInst>(User)) {
-      findCallsAtConstantOffset(BitSet, User, Offset, VTable);
-    } else if (auto CI = dyn_cast<CallInst>(User)) {
-      CallSlots[{BitSet, Offset}].push_back({VTable, CI});
-    } else if (auto II = dyn_cast<InvokeInst>(User)) {
-      CallSlots[{BitSet, Offset}].push_back({VTable, II});
-    }
-  }
-}
-
-// Search for virtual calls that load from VPtr and add them to CallSlots.
-void DevirtModule::findLoadCallsAtConstantOffset(Metadata *BitSet, Value *VPtr,
-                                                 uint64_t Offset,
-                                                 Value *VTable) {
-  for (const Use &U : VPtr->uses()) {
-    Value *User = U.getUser();
-    if (isa<BitCastInst>(User)) {
-      findLoadCallsAtConstantOffset(BitSet, User, Offset, VTable);
-    } else if (isa<LoadInst>(User)) {
-      findCallsAtConstantOffset(BitSet, User, Offset, VTable);
-    } else if (auto GEP = dyn_cast<GetElementPtrInst>(User)) {
-      // Take into account the GEP offset.
-      if (VPtr == GEP->getPointerOperand() && GEP->hasAllConstantIndices()) {
-        SmallVector<Value *, 8> Indices(GEP->op_begin() + 1, GEP->op_end());
-        uint64_t GEPOffset = M.getDataLayout().getIndexedOffsetInType(
-            GEP->getSourceElementType(), Indices);
-        findLoadCallsAtConstantOffset(BitSet, User, Offset + GEPOffset, VTable);
-      }
-    }
-  }
-}
-
 void DevirtModule::buildBitSets(
     std::vector<VTableBits> &Bits,
     DenseMap<Metadata *, std::set<BitSetInfo>> &BitSets) {
   NamedMDNode *BitSetNM = M.getNamedMetadata("llvm.bitsets");
   if (!BitSetNM)
     return;
 
   DenseMap<GlobalVariable *, VTableBits *> GVToBits;
bool DevirtModule::run() {
   DenseSet<Value *> SeenPtrs;
   for (auto I = BitSetTestFunc->use_begin(), E = BitSetTestFunc->use_end();
        I != E;) {
     auto CI = dyn_cast<CallInst>(I->getUser());
     ++I;
     if (!CI)
       continue;
 
-    // Find llvm.assume intrinsics for this llvm.bitset.test call.
+    // Search for virtual calls based on %p and add them to DevirtCalls.
+    SmallVector<DevirtCallSite, 1> DevirtCalls;
     SmallVector<CallInst *, 1> Assumes;
-    for (const Use &CIU : CI->uses()) {
-      auto AssumeCI = dyn_cast<CallInst>(CIU.getUser());
-      if (AssumeCI && AssumeCI->getCalledValue() == AssumeFunc)
-        Assumes.push_back(AssumeCI);
-    }
+    findDevirtualizableCalls(DevirtCalls, Assumes, CI);
 
-    // If we found any, search for virtual calls based on %p and add them to
-    // CallSlots.
+    // If we found any, add them to CallSlots. Only do this if we haven't seen
+    // the vtable pointer before, as it may have been CSE'd with pointers from
+    // other call sites, and we don't want to process call sites multiple times.
     if (!Assumes.empty()) {
       Metadata *BitSet =
           cast<MetadataAsValue>(CI->getArgOperand(1))->getMetadata();
       Value *Ptr = CI->getArgOperand(0)->stripPointerCasts();
-      if (SeenPtrs.insert(Ptr).second)
-        findLoadCallsAtConstantOffset(BitSet, Ptr, 0, CI->getArgOperand(0));
+      if (SeenPtrs.insert(Ptr).second) {
+        for (DevirtCallSite Call : DevirtCalls)
+          CallSlots[{BitSet, Call.Offset}].push_back(
+              {CI->getArgOperand(0), Call.CS});
+      }
     }
 
     // We no longer need the assumes or the bitset test.
     for (auto Assume : Assumes)
       Assume->eraseFromParent();
     // We can't use RecursivelyDeleteTriviallyDeadInstructions here because we
     // may use the vtable argument later.
     if (CI->use_empty())