12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424 |
- //===- WholeProgramDevirt.cpp - Whole program virtual call optimization ---===//
- //
- // The LLVM Compiler Infrastructure
- //
- // This file is distributed under the University of Illinois Open Source
- // License. See LICENSE.TXT for details.
- //
- //===----------------------------------------------------------------------===//
- //
- // This pass implements whole program optimization of virtual calls in cases
- // where we know (via !type metadata) that the list of callees is fixed. This
- // includes the following:
- // - Single implementation devirtualization: if a virtual call has a single
- // possible callee, replace all calls with a direct call to that callee.
- // - Virtual constant propagation: if the virtual function's return type is an
- // integer <=64 bits and all possible callees are readnone, for each class and
- // each list of constant arguments: evaluate the function, store the return
- // value alongside the virtual table, and rewrite each virtual call as a load
- // from the virtual table.
- // - Uniform return value optimization: if the conditions for virtual constant
- // propagation hold and each function returns the same constant value, replace
- // each virtual call with that constant.
- // - Unique return value optimization for i1 return values: if the conditions
- // for virtual constant propagation hold and a single vtable's function
- // returns 0, or a single vtable's function returns 1, replace each virtual
- // call with a comparison of the vptr against that vtable's address.
- //
- // This pass is intended to be used during the regular and thin LTO pipelines.
- // During regular LTO, the pass determines the best optimization for each
- // virtual call and applies the resolutions directly to virtual calls that are
- // eligible for virtual call optimization (i.e. calls that use either of the
- // llvm.assume(llvm.type.test) or llvm.type.checked.load intrinsics). During
- // ThinLTO, the pass operates in two phases:
- // - Export phase: this is run during the thin link over a single merged module
- // that contains all vtables with !type metadata that participate in the link.
- // The pass computes a resolution for each virtual call and stores it in the
- // type identifier summary.
- // - Import phase: this is run during the thin backends over the individual
- // modules. The pass applies the resolutions previously computed during the
- // import phase to each eligible virtual call.
- //
- //===----------------------------------------------------------------------===//
- #include "llvm/Transforms/IPO/WholeProgramDevirt.h"
- #include "llvm/ADT/ArrayRef.h"
- #include "llvm/ADT/DenseMap.h"
- #include "llvm/ADT/DenseMapInfo.h"
- #include "llvm/ADT/DenseSet.h"
- #include "llvm/ADT/iterator_range.h"
- #include "llvm/ADT/MapVector.h"
- #include "llvm/ADT/SmallVector.h"
- #include "llvm/Analysis/AliasAnalysis.h"
- #include "llvm/Analysis/BasicAliasAnalysis.h"
- #include "llvm/Analysis/TypeMetadataUtils.h"
- #include "llvm/IR/CallSite.h"
- #include "llvm/IR/Constants.h"
- #include "llvm/IR/DataLayout.h"
- #include "llvm/IR/DebugInfoMetadata.h"
- #include "llvm/IR/DebugLoc.h"
- #include "llvm/IR/DerivedTypes.h"
- #include "llvm/IR/DiagnosticInfo.h"
- #include "llvm/IR/Function.h"
- #include "llvm/IR/GlobalAlias.h"
- #include "llvm/IR/GlobalVariable.h"
- #include "llvm/IR/IRBuilder.h"
- #include "llvm/IR/InstrTypes.h"
- #include "llvm/IR/Instruction.h"
- #include "llvm/IR/Instructions.h"
- #include "llvm/IR/Intrinsics.h"
- #include "llvm/IR/LLVMContext.h"
- #include "llvm/IR/Metadata.h"
- #include "llvm/IR/Module.h"
- #include "llvm/IR/ModuleSummaryIndexYAML.h"
- #include "llvm/Pass.h"
- #include "llvm/PassRegistry.h"
- #include "llvm/PassSupport.h"
- #include "llvm/Support/Casting.h"
- #include "llvm/Support/Error.h"
- #include "llvm/Support/FileSystem.h"
- #include "llvm/Support/MathExtras.h"
- #include "llvm/Transforms/IPO.h"
- #include "llvm/Transforms/IPO/FunctionAttrs.h"
- #include "llvm/Transforms/Utils/Evaluator.h"
- #include <algorithm>
- #include <cstddef>
- #include <map>
- #include <set>
- #include <string>
- using namespace llvm;
- using namespace wholeprogramdevirt;
- #define DEBUG_TYPE "wholeprogramdevirt"
- static cl::opt<PassSummaryAction> ClSummaryAction(
- "wholeprogramdevirt-summary-action",
- cl::desc("What to do with the summary when running this pass"),
- cl::values(clEnumValN(PassSummaryAction::None, "none", "Do nothing"),
- clEnumValN(PassSummaryAction::Import, "import",
- "Import typeid resolutions from summary and globals"),
- clEnumValN(PassSummaryAction::Export, "export",
- "Export typeid resolutions to summary and globals")),
- cl::Hidden);
- static cl::opt<std::string> ClReadSummary(
- "wholeprogramdevirt-read-summary",
- cl::desc("Read summary from given YAML file before running pass"),
- cl::Hidden);
- static cl::opt<std::string> ClWriteSummary(
- "wholeprogramdevirt-write-summary",
- cl::desc("Write summary to given YAML file after running pass"),
- cl::Hidden);
- // Find the minimum offset that we may store a value of size Size bits at. If
- // IsAfter is set, look for an offset before the object, otherwise look for an
- // offset after the object.
- uint64_t
- wholeprogramdevirt::findLowestOffset(ArrayRef<VirtualCallTarget> Targets,
- bool IsAfter, uint64_t Size) {
- // Find a minimum offset taking into account only vtable sizes.
- uint64_t MinByte = 0;
- for (const VirtualCallTarget &Target : Targets) {
- if (IsAfter)
- MinByte = std::max(MinByte, Target.minAfterBytes());
- else
- MinByte = std::max(MinByte, Target.minBeforeBytes());
- }
- // Build a vector of arrays of bytes covering, for each target, a slice of the
- // used region (see AccumBitVector::BytesUsed in
- // llvm/Transforms/IPO/WholeProgramDevirt.h) starting at MinByte. Effectively,
- // this aligns the used regions to start at MinByte.
- //
- // In this example, A, B and C are vtables, # is a byte already allocated for
- // a virtual function pointer, AAAA... (etc.) are the used regions for the
- // vtables and Offset(X) is the value computed for the Offset variable below
- // for X.
- //
- // Offset(A)
- // | |
- // |MinByte
- // A: ################AAAAAAAA|AAAAAAAA
- // B: ########BBBBBBBBBBBBBBBB|BBBB
- // C: ########################|CCCCCCCCCCCCCCCC
- // | Offset(B) |
- //
- // This code produces the slices of A, B and C that appear after the divider
- // at MinByte.
- std::vector<ArrayRef<uint8_t>> Used;
- for (const VirtualCallTarget &Target : Targets) {
- ArrayRef<uint8_t> VTUsed = IsAfter ? Target.TM->Bits->After.BytesUsed
- : Target.TM->Bits->Before.BytesUsed;
- uint64_t Offset = IsAfter ? MinByte - Target.minAfterBytes()
- : MinByte - Target.minBeforeBytes();
- // Disregard used regions that are smaller than Offset. These are
- // effectively all-free regions that do not need to be checked.
- if (VTUsed.size() > Offset)
- Used.push_back(VTUsed.slice(Offset));
- }
- if (Size == 1) {
- // Find a free bit in each member of Used.
- for (unsigned I = 0;; ++I) {
- uint8_t BitsUsed = 0;
- for (auto &&B : Used)
- if (I < B.size())
- BitsUsed |= B[I];
- if (BitsUsed != 0xff)
- return (MinByte + I) * 8 +
- countTrailingZeros(uint8_t(~BitsUsed), ZB_Undefined);
- }
- } else {
- // Find a free (Size/8) byte region in each member of Used.
- // FIXME: see if alignment helps.
- for (unsigned I = 0;; ++I) {
- for (auto &&B : Used) {
- unsigned Byte = 0;
- while ((I + Byte) < B.size() && Byte < (Size / 8)) {
- if (B[I + Byte])
- goto NextI;
- ++Byte;
- }
- }
- return (MinByte + I) * 8;
- NextI:;
- }
- }
- }
- void wholeprogramdevirt::setBeforeReturnValues(
- MutableArrayRef<VirtualCallTarget> Targets, uint64_t AllocBefore,
- unsigned BitWidth, int64_t &OffsetByte, uint64_t &OffsetBit) {
- if (BitWidth == 1)
- OffsetByte = -(AllocBefore / 8 + 1);
- else
- OffsetByte = -((AllocBefore + 7) / 8 + (BitWidth + 7) / 8);
- OffsetBit = AllocBefore % 8;
- for (VirtualCallTarget &Target : Targets) {
- if (BitWidth == 1)
- Target.setBeforeBit(AllocBefore);
- else
- Target.setBeforeBytes(AllocBefore, (BitWidth + 7) / 8);
- }
- }
- void wholeprogramdevirt::setAfterReturnValues(
- MutableArrayRef<VirtualCallTarget> Targets, uint64_t AllocAfter,
- unsigned BitWidth, int64_t &OffsetByte, uint64_t &OffsetBit) {
- if (BitWidth == 1)
- OffsetByte = AllocAfter / 8;
- else
- OffsetByte = (AllocAfter + 7) / 8;
- OffsetBit = AllocAfter % 8;
- for (VirtualCallTarget &Target : Targets) {
- if (BitWidth == 1)
- Target.setAfterBit(AllocAfter);
- else
- Target.setAfterBytes(AllocAfter, (BitWidth + 7) / 8);
- }
- }
- VirtualCallTarget::VirtualCallTarget(Function *Fn, const TypeMemberInfo *TM)
- : Fn(Fn), TM(TM),
- IsBigEndian(Fn->getParent()->getDataLayout().isBigEndian()), WasDevirt(false) {}
- namespace {
- // A slot in a set of virtual tables. The TypeID identifies the set of virtual
- // tables, and the ByteOffset is the offset in bytes from the address point to
- // the virtual function pointer.
- struct VTableSlot {
- Metadata *TypeID;
- uint64_t ByteOffset;
- };
- } // end anonymous namespace
- namespace llvm {
- template <> struct DenseMapInfo<VTableSlot> {
- static VTableSlot getEmptyKey() {
- return {DenseMapInfo<Metadata *>::getEmptyKey(),
- DenseMapInfo<uint64_t>::getEmptyKey()};
- }
- static VTableSlot getTombstoneKey() {
- return {DenseMapInfo<Metadata *>::getTombstoneKey(),
- DenseMapInfo<uint64_t>::getTombstoneKey()};
- }
- static unsigned getHashValue(const VTableSlot &I) {
- return DenseMapInfo<Metadata *>::getHashValue(I.TypeID) ^
- DenseMapInfo<uint64_t>::getHashValue(I.ByteOffset);
- }
- static bool isEqual(const VTableSlot &LHS,
- const VTableSlot &RHS) {
- return LHS.TypeID == RHS.TypeID && LHS.ByteOffset == RHS.ByteOffset;
- }
- };
- } // end namespace llvm
- namespace {
- // A virtual call site. VTable is the loaded virtual table pointer, and CS is
- // the indirect virtual call.
- struct VirtualCallSite {
- Value *VTable;
- CallSite CS;
- // If non-null, this field points to the associated unsafe use count stored in
- // the DevirtModule::NumUnsafeUsesForTypeTest map below. See the description
- // of that field for details.
- unsigned *NumUnsafeUses;
- void emitRemark(const Twine &OptName, const Twine &TargetName) {
- Function *F = CS.getCaller();
- emitOptimizationRemark(
- F->getContext(), DEBUG_TYPE, *F,
- CS.getInstruction()->getDebugLoc(),
- OptName + ": devirtualized a call to " + TargetName);
- }
- void replaceAndErase(const Twine &OptName, const Twine &TargetName,
- bool RemarksEnabled, Value *New) {
- if (RemarksEnabled)
- emitRemark(OptName, TargetName);
- CS->replaceAllUsesWith(New);
- if (auto II = dyn_cast<InvokeInst>(CS.getInstruction())) {
- BranchInst::Create(II->getNormalDest(), CS.getInstruction());
- II->getUnwindDest()->removePredecessor(II->getParent());
- }
- CS->eraseFromParent();
- // This use is no longer unsafe.
- if (NumUnsafeUses)
- --*NumUnsafeUses;
- }
- };
- // Call site information collected for a specific VTableSlot and possibly a list
- // of constant integer arguments. The grouping by arguments is handled by the
- // VTableSlotInfo class.
- struct CallSiteInfo {
- /// The set of call sites for this slot. Used during regular LTO and the
- /// import phase of ThinLTO (as well as the export phase of ThinLTO for any
- /// call sites that appear in the merged module itself); in each of these
- /// cases we are directly operating on the call sites at the IR level.
- std::vector<VirtualCallSite> CallSites;
- // These fields are used during the export phase of ThinLTO and reflect
- // information collected from function summaries.
- /// Whether any function summary contains an llvm.assume(llvm.type.test) for
- /// this slot.
- bool SummaryHasTypeTestAssumeUsers;
- /// CFI-specific: a vector containing the list of function summaries that use
- /// the llvm.type.checked.load intrinsic and therefore will require
- /// resolutions for llvm.type.test in order to implement CFI checks if
- /// devirtualization was unsuccessful. If devirtualization was successful, the
- /// pass will clear this vector by calling markDevirt(). If at the end of the
- /// pass the vector is non-empty, we will need to add a use of llvm.type.test
- /// to each of the function summaries in the vector.
- std::vector<FunctionSummary *> SummaryTypeCheckedLoadUsers;
- bool isExported() const {
- return SummaryHasTypeTestAssumeUsers ||
- !SummaryTypeCheckedLoadUsers.empty();
- }
- /// As explained in the comment for SummaryTypeCheckedLoadUsers.
- void markDevirt() { SummaryTypeCheckedLoadUsers.clear(); }
- };
- // Call site information collected for a specific VTableSlot.
- struct VTableSlotInfo {
- // The set of call sites which do not have all constant integer arguments
- // (excluding "this").
- CallSiteInfo CSInfo;
- // The set of call sites with all constant integer arguments (excluding
- // "this"), grouped by argument list.
- std::map<std::vector<uint64_t>, CallSiteInfo> ConstCSInfo;
- void addCallSite(Value *VTable, CallSite CS, unsigned *NumUnsafeUses);
- private:
- CallSiteInfo &findCallSiteInfo(CallSite CS);
- };
- CallSiteInfo &VTableSlotInfo::findCallSiteInfo(CallSite CS) {
- std::vector<uint64_t> Args;
- auto *CI = dyn_cast<IntegerType>(CS.getType());
- if (!CI || CI->getBitWidth() > 64 || CS.arg_empty())
- return CSInfo;
- for (auto &&Arg : make_range(CS.arg_begin() + 1, CS.arg_end())) {
- auto *CI = dyn_cast<ConstantInt>(Arg);
- if (!CI || CI->getBitWidth() > 64)
- return CSInfo;
- Args.push_back(CI->getZExtValue());
- }
- return ConstCSInfo[Args];
- }
- void VTableSlotInfo::addCallSite(Value *VTable, CallSite CS,
- unsigned *NumUnsafeUses) {
- findCallSiteInfo(CS).CallSites.push_back({VTable, CS, NumUnsafeUses});
- }
- struct DevirtModule {
- Module &M;
- function_ref<AAResults &(Function &)> AARGetter;
- ModuleSummaryIndex *ExportSummary;
- const ModuleSummaryIndex *ImportSummary;
- IntegerType *Int8Ty;
- PointerType *Int8PtrTy;
- IntegerType *Int32Ty;
- IntegerType *Int64Ty;
- IntegerType *IntPtrTy;
- bool RemarksEnabled;
- MapVector<VTableSlot, VTableSlotInfo> CallSlots;
- // This map keeps track of the number of "unsafe" uses of a loaded function
- // pointer. The key is the associated llvm.type.test intrinsic call generated
- // by this pass. An unsafe use is one that calls the loaded function pointer
- // directly. Every time we eliminate an unsafe use (for example, by
- // devirtualizing it or by applying virtual constant propagation), we
- // decrement the value stored in this map. If a value reaches zero, we can
- // eliminate the type check by RAUWing the associated llvm.type.test call with
- // true.
- std::map<CallInst *, unsigned> NumUnsafeUsesForTypeTest;
- DevirtModule(Module &M, function_ref<AAResults &(Function &)> AARGetter,
- ModuleSummaryIndex *ExportSummary,
- const ModuleSummaryIndex *ImportSummary)
- : M(M), AARGetter(AARGetter), ExportSummary(ExportSummary),
- ImportSummary(ImportSummary), Int8Ty(Type::getInt8Ty(M.getContext())),
- Int8PtrTy(Type::getInt8PtrTy(M.getContext())),
- Int32Ty(Type::getInt32Ty(M.getContext())),
- Int64Ty(Type::getInt64Ty(M.getContext())),
- IntPtrTy(M.getDataLayout().getIntPtrType(M.getContext(), 0)),
- RemarksEnabled(areRemarksEnabled()) {
- assert(!(ExportSummary && ImportSummary));
- }
- bool areRemarksEnabled();
- void scanTypeTestUsers(Function *TypeTestFunc, Function *AssumeFunc);
- void scanTypeCheckedLoadUsers(Function *TypeCheckedLoadFunc);
- void buildTypeIdentifierMap(
- std::vector<VTableBits> &Bits,
- DenseMap<Metadata *, std::set<TypeMemberInfo>> &TypeIdMap);
- Constant *getPointerAtOffset(Constant *I, uint64_t Offset);
- bool
- tryFindVirtualCallTargets(std::vector<VirtualCallTarget> &TargetsForSlot,
- const std::set<TypeMemberInfo> &TypeMemberInfos,
- uint64_t ByteOffset);
- void applySingleImplDevirt(VTableSlotInfo &SlotInfo, Constant *TheFn,
- bool &IsExported);
- bool trySingleImplDevirt(MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- VTableSlotInfo &SlotInfo,
- WholeProgramDevirtResolution *Res);
- bool tryEvaluateFunctionsWithArgs(
- MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- ArrayRef<uint64_t> Args);
- void applyUniformRetValOpt(CallSiteInfo &CSInfo, StringRef FnName,
- uint64_t TheRetVal);
- bool tryUniformRetValOpt(MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- CallSiteInfo &CSInfo,
- WholeProgramDevirtResolution::ByArg *Res);
- // Returns the global symbol name that is used to export information about the
- // given vtable slot and list of arguments.
- std::string getGlobalName(VTableSlot Slot, ArrayRef<uint64_t> Args,
- StringRef Name);
- // This function is called during the export phase to create a symbol
- // definition containing information about the given vtable slot and list of
- // arguments.
- void exportGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args, StringRef Name,
- Constant *C);
- // This function is called during the import phase to create a reference to
- // the symbol definition created during the export phase.
- Constant *importGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args,
- StringRef Name, unsigned AbsWidth = 0);
- void applyUniqueRetValOpt(CallSiteInfo &CSInfo, StringRef FnName, bool IsOne,
- Constant *UniqueMemberAddr);
- bool tryUniqueRetValOpt(unsigned BitWidth,
- MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- CallSiteInfo &CSInfo,
- WholeProgramDevirtResolution::ByArg *Res,
- VTableSlot Slot, ArrayRef<uint64_t> Args);
- void applyVirtualConstProp(CallSiteInfo &CSInfo, StringRef FnName,
- Constant *Byte, Constant *Bit);
- bool tryVirtualConstProp(MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- VTableSlotInfo &SlotInfo,
- WholeProgramDevirtResolution *Res, VTableSlot Slot);
- void rebuildGlobal(VTableBits &B);
- // Apply the summary resolution for Slot to all virtual calls in SlotInfo.
- void importResolution(VTableSlot Slot, VTableSlotInfo &SlotInfo);
- // If we were able to eliminate all unsafe uses for a type checked load,
- // eliminate the associated type tests by replacing them with true.
- void removeRedundantTypeTests();
- bool run();
- // Lower the module using the action and summary passed as command line
- // arguments. For testing purposes only.
- static bool runForTesting(Module &M,
- function_ref<AAResults &(Function &)> AARGetter);
- };
- struct WholeProgramDevirt : public ModulePass {
- static char ID;
- bool UseCommandLine = false;
- ModuleSummaryIndex *ExportSummary;
- const ModuleSummaryIndex *ImportSummary;
- WholeProgramDevirt() : ModulePass(ID), UseCommandLine(true) {
- initializeWholeProgramDevirtPass(*PassRegistry::getPassRegistry());
- }
- WholeProgramDevirt(ModuleSummaryIndex *ExportSummary,
- const ModuleSummaryIndex *ImportSummary)
- : ModulePass(ID), ExportSummary(ExportSummary),
- ImportSummary(ImportSummary) {
- initializeWholeProgramDevirtPass(*PassRegistry::getPassRegistry());
- }
- bool runOnModule(Module &M) override {
- if (skipModule(M))
- return false;
- if (UseCommandLine)
- return DevirtModule::runForTesting(M, LegacyAARGetter(*this));
- return DevirtModule(M, LegacyAARGetter(*this), ExportSummary, ImportSummary)
- .run();
- }
- void getAnalysisUsage(AnalysisUsage &AU) const override {
- AU.addRequired<AssumptionCacheTracker>();
- AU.addRequired<TargetLibraryInfoWrapperPass>();
- }
- };
- } // end anonymous namespace
- INITIALIZE_PASS_BEGIN(WholeProgramDevirt, "wholeprogramdevirt",
- "Whole program devirtualization", false, false)
- INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
- INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
- INITIALIZE_PASS_END(WholeProgramDevirt, "wholeprogramdevirt",
- "Whole program devirtualization", false, false)
- char WholeProgramDevirt::ID = 0;
- ModulePass *
- llvm::createWholeProgramDevirtPass(ModuleSummaryIndex *ExportSummary,
- const ModuleSummaryIndex *ImportSummary) {
- return new WholeProgramDevirt(ExportSummary, ImportSummary);
- }
- PreservedAnalyses WholeProgramDevirtPass::run(Module &M,
- ModuleAnalysisManager &AM) {
- auto &FAM = AM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
- auto AARGetter = [&](Function &F) -> AAResults & {
- return FAM.getResult<AAManager>(F);
- };
- if (!DevirtModule(M, AARGetter, nullptr, nullptr).run())
- return PreservedAnalyses::all();
- return PreservedAnalyses::none();
- }
- bool DevirtModule::runForTesting(
- Module &M, function_ref<AAResults &(Function &)> AARGetter) {
- ModuleSummaryIndex Summary;
- // Handle the command-line summary arguments. This code is for testing
- // purposes only, so we handle errors directly.
- if (!ClReadSummary.empty()) {
- ExitOnError ExitOnErr("-wholeprogramdevirt-read-summary: " + ClReadSummary +
- ": ");
- auto ReadSummaryFile =
- ExitOnErr(errorOrToExpected(MemoryBuffer::getFile(ClReadSummary)));
- yaml::Input In(ReadSummaryFile->getBuffer());
- In >> Summary;
- ExitOnErr(errorCodeToError(In.error()));
- }
- bool Changed =
- DevirtModule(
- M, AARGetter,
- ClSummaryAction == PassSummaryAction::Export ? &Summary : nullptr,
- ClSummaryAction == PassSummaryAction::Import ? &Summary : nullptr)
- .run();
- if (!ClWriteSummary.empty()) {
- ExitOnError ExitOnErr(
- "-wholeprogramdevirt-write-summary: " + ClWriteSummary + ": ");
- std::error_code EC;
- raw_fd_ostream OS(ClWriteSummary, EC, sys::fs::F_Text);
- ExitOnErr(errorCodeToError(EC));
- yaml::Output Out(OS);
- Out << Summary;
- }
- return Changed;
- }
- void DevirtModule::buildTypeIdentifierMap(
- std::vector<VTableBits> &Bits,
- DenseMap<Metadata *, std::set<TypeMemberInfo>> &TypeIdMap) {
- DenseMap<GlobalVariable *, VTableBits *> GVToBits;
- Bits.reserve(M.getGlobalList().size());
- SmallVector<MDNode *, 2> Types;
- for (GlobalVariable &GV : M.globals()) {
- Types.clear();
- GV.getMetadata(LLVMContext::MD_type, Types);
- if (Types.empty())
- continue;
- VTableBits *&BitsPtr = GVToBits[&GV];
- if (!BitsPtr) {
- Bits.emplace_back();
- Bits.back().GV = &GV;
- Bits.back().ObjectSize =
- M.getDataLayout().getTypeAllocSize(GV.getInitializer()->getType());
- BitsPtr = &Bits.back();
- }
- for (MDNode *Type : Types) {
- auto TypeID = Type->getOperand(1).get();
- uint64_t Offset =
- cast<ConstantInt>(
- cast<ConstantAsMetadata>(Type->getOperand(0))->getValue())
- ->getZExtValue();
- TypeIdMap[TypeID].insert({BitsPtr, Offset});
- }
- }
- }
- Constant *DevirtModule::getPointerAtOffset(Constant *I, uint64_t Offset) {
- if (I->getType()->isPointerTy()) {
- if (Offset == 0)
- return I;
- return nullptr;
- }
- const DataLayout &DL = M.getDataLayout();
- if (auto *C = dyn_cast<ConstantStruct>(I)) {
- const StructLayout *SL = DL.getStructLayout(C->getType());
- if (Offset >= SL->getSizeInBytes())
- return nullptr;
- unsigned Op = SL->getElementContainingOffset(Offset);
- return getPointerAtOffset(cast<Constant>(I->getOperand(Op)),
- Offset - SL->getElementOffset(Op));
- }
- if (auto *C = dyn_cast<ConstantArray>(I)) {
- ArrayType *VTableTy = C->getType();
- uint64_t ElemSize = DL.getTypeAllocSize(VTableTy->getElementType());
- unsigned Op = Offset / ElemSize;
- if (Op >= C->getNumOperands())
- return nullptr;
- return getPointerAtOffset(cast<Constant>(I->getOperand(Op)),
- Offset % ElemSize);
- }
- return nullptr;
- }
- bool DevirtModule::tryFindVirtualCallTargets(
- std::vector<VirtualCallTarget> &TargetsForSlot,
- const std::set<TypeMemberInfo> &TypeMemberInfos, uint64_t ByteOffset) {
- for (const TypeMemberInfo &TM : TypeMemberInfos) {
- if (!TM.Bits->GV->isConstant())
- return false;
- Constant *Ptr = getPointerAtOffset(TM.Bits->GV->getInitializer(),
- TM.Offset + ByteOffset);
- if (!Ptr)
- return false;
- auto Fn = dyn_cast<Function>(Ptr->stripPointerCasts());
- if (!Fn)
- return false;
- // We can disregard __cxa_pure_virtual as a possible call target, as
- // calls to pure virtuals are UB.
- if (Fn->getName() == "__cxa_pure_virtual")
- continue;
- TargetsForSlot.push_back({Fn, &TM});
- }
- // Give up if we couldn't find any targets.
- return !TargetsForSlot.empty();
- }
- void DevirtModule::applySingleImplDevirt(VTableSlotInfo &SlotInfo,
- Constant *TheFn, bool &IsExported) {
- auto Apply = [&](CallSiteInfo &CSInfo) {
- for (auto &&VCallSite : CSInfo.CallSites) {
- if (RemarksEnabled)
- VCallSite.emitRemark("single-impl", TheFn->getName());
- VCallSite.CS.setCalledFunction(ConstantExpr::getBitCast(
- TheFn, VCallSite.CS.getCalledValue()->getType()));
- // This use is no longer unsafe.
- if (VCallSite.NumUnsafeUses)
- --*VCallSite.NumUnsafeUses;
- }
- if (CSInfo.isExported()) {
- IsExported = true;
- CSInfo.markDevirt();
- }
- };
- Apply(SlotInfo.CSInfo);
- for (auto &P : SlotInfo.ConstCSInfo)
- Apply(P.second);
- }
- bool DevirtModule::trySingleImplDevirt(
- MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- VTableSlotInfo &SlotInfo, WholeProgramDevirtResolution *Res) {
- // See if the program contains a single implementation of this virtual
- // function.
- Function *TheFn = TargetsForSlot[0].Fn;
- for (auto &&Target : TargetsForSlot)
- if (TheFn != Target.Fn)
- return false;
- // If so, update each call site to call that implementation directly.
- if (RemarksEnabled)
- TargetsForSlot[0].WasDevirt = true;
- bool IsExported = false;
- applySingleImplDevirt(SlotInfo, TheFn, IsExported);
- if (!IsExported)
- return false;
- // If the only implementation has local linkage, we must promote to external
- // to make it visible to thin LTO objects. We can only get here during the
- // ThinLTO export phase.
- if (TheFn->hasLocalLinkage()) {
- TheFn->setLinkage(GlobalValue::ExternalLinkage);
- TheFn->setVisibility(GlobalValue::HiddenVisibility);
- TheFn->setName(TheFn->getName() + "$merged");
- }
- Res->TheKind = WholeProgramDevirtResolution::SingleImpl;
- Res->SingleImplName = TheFn->getName();
- return true;
- }
- bool DevirtModule::tryEvaluateFunctionsWithArgs(
- MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- ArrayRef<uint64_t> Args) {
- // Evaluate each function and store the result in each target's RetVal
- // field.
- for (VirtualCallTarget &Target : TargetsForSlot) {
- if (Target.Fn->arg_size() != Args.size() + 1)
- return false;
- Evaluator Eval(M.getDataLayout(), nullptr);
- SmallVector<Constant *, 2> EvalArgs;
- EvalArgs.push_back(
- Constant::getNullValue(Target.Fn->getFunctionType()->getParamType(0)));
- for (unsigned I = 0; I != Args.size(); ++I) {
- auto *ArgTy = dyn_cast<IntegerType>(
- Target.Fn->getFunctionType()->getParamType(I + 1));
- if (!ArgTy)
- return false;
- EvalArgs.push_back(ConstantInt::get(ArgTy, Args[I]));
- }
- Constant *RetVal;
- if (!Eval.EvaluateFunction(Target.Fn, RetVal, EvalArgs) ||
- !isa<ConstantInt>(RetVal))
- return false;
- Target.RetVal = cast<ConstantInt>(RetVal)->getZExtValue();
- }
- return true;
- }
- void DevirtModule::applyUniformRetValOpt(CallSiteInfo &CSInfo, StringRef FnName,
- uint64_t TheRetVal) {
- for (auto Call : CSInfo.CallSites)
- Call.replaceAndErase(
- "uniform-ret-val", FnName, RemarksEnabled,
- ConstantInt::get(cast<IntegerType>(Call.CS.getType()), TheRetVal));
- CSInfo.markDevirt();
- }
- bool DevirtModule::tryUniformRetValOpt(
- MutableArrayRef<VirtualCallTarget> TargetsForSlot, CallSiteInfo &CSInfo,
- WholeProgramDevirtResolution::ByArg *Res) {
- // Uniform return value optimization. If all functions return the same
- // constant, replace all calls with that constant.
- uint64_t TheRetVal = TargetsForSlot[0].RetVal;
- for (const VirtualCallTarget &Target : TargetsForSlot)
- if (Target.RetVal != TheRetVal)
- return false;
- if (CSInfo.isExported()) {
- Res->TheKind = WholeProgramDevirtResolution::ByArg::UniformRetVal;
- Res->Info = TheRetVal;
- }
- applyUniformRetValOpt(CSInfo, TargetsForSlot[0].Fn->getName(), TheRetVal);
- if (RemarksEnabled)
- for (auto &&Target : TargetsForSlot)
- Target.WasDevirt = true;
- return true;
- }
- std::string DevirtModule::getGlobalName(VTableSlot Slot,
- ArrayRef<uint64_t> Args,
- StringRef Name) {
- std::string FullName = "__typeid_";
- raw_string_ostream OS(FullName);
- OS << cast<MDString>(Slot.TypeID)->getString() << '_' << Slot.ByteOffset;
- for (uint64_t Arg : Args)
- OS << '_' << Arg;
- OS << '_' << Name;
- return OS.str();
- }
- void DevirtModule::exportGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args,
- StringRef Name, Constant *C) {
- GlobalAlias *GA = GlobalAlias::create(Int8Ty, 0, GlobalValue::ExternalLinkage,
- getGlobalName(Slot, Args, Name), C, &M);
- GA->setVisibility(GlobalValue::HiddenVisibility);
- }
- Constant *DevirtModule::importGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args,
- StringRef Name, unsigned AbsWidth) {
- Constant *C = M.getOrInsertGlobal(getGlobalName(Slot, Args, Name), Int8Ty);
- auto *GV = dyn_cast<GlobalVariable>(C);
- // We only need to set metadata if the global is newly created, in which
- // case it would not have hidden visibility.
- if (!GV || GV->getVisibility() == GlobalValue::HiddenVisibility)
- return C;
- GV->setVisibility(GlobalValue::HiddenVisibility);
- auto SetAbsRange = [&](uint64_t Min, uint64_t Max) {
- auto *MinC = ConstantAsMetadata::get(ConstantInt::get(IntPtrTy, Min));
- auto *MaxC = ConstantAsMetadata::get(ConstantInt::get(IntPtrTy, Max));
- GV->setMetadata(LLVMContext::MD_absolute_symbol,
- MDNode::get(M.getContext(), {MinC, MaxC}));
- };
- if (AbsWidth == IntPtrTy->getBitWidth())
- SetAbsRange(~0ull, ~0ull); // Full set.
- else if (AbsWidth)
- SetAbsRange(0, 1ull << AbsWidth);
- return GV;
- }
- void DevirtModule::applyUniqueRetValOpt(CallSiteInfo &CSInfo, StringRef FnName,
- bool IsOne,
- Constant *UniqueMemberAddr) {
- for (auto &&Call : CSInfo.CallSites) {
- IRBuilder<> B(Call.CS.getInstruction());
- Value *Cmp = B.CreateICmp(IsOne ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE,
- Call.VTable, UniqueMemberAddr);
- Cmp = B.CreateZExt(Cmp, Call.CS->getType());
- Call.replaceAndErase("unique-ret-val", FnName, RemarksEnabled, Cmp);
- }
- CSInfo.markDevirt();
- }
- bool DevirtModule::tryUniqueRetValOpt(
- unsigned BitWidth, MutableArrayRef<VirtualCallTarget> TargetsForSlot,
- CallSiteInfo &CSInfo, WholeProgramDevirtResolution::ByArg *Res,
- VTableSlot Slot, ArrayRef<uint64_t> Args) {
- // IsOne controls whether we look for a 0 or a 1.
- auto tryUniqueRetValOptFor = [&](bool IsOne) {
- const TypeMemberInfo *UniqueMember = nullptr;
- for (const VirtualCallTarget &Target : TargetsForSlot) {
- if (Target.RetVal == (IsOne ? 1 : 0)) {
- if (UniqueMember)
- return false;
- UniqueMember = Target.TM;
- }
- }
- // We should have found a unique member or bailed out by now. We already
- // checked for a uniform return value in tryUniformRetValOpt.
- assert(UniqueMember);
- Constant *UniqueMemberAddr =
- ConstantExpr::getBitCast(UniqueMember->Bits->GV, Int8PtrTy);
- UniqueMemberAddr = ConstantExpr::getGetElementPtr(
- Int8Ty, UniqueMemberAddr,
- ConstantInt::get(Int64Ty, UniqueMember->Offset));
- if (CSInfo.isExported()) {
- Res->TheKind = WholeProgramDevirtResolution::ByArg::UniqueRetVal;
- Res->Info = IsOne;
- exportGlobal(Slot, Args, "unique_member", UniqueMemberAddr);
- }
- // Replace each call with the comparison.
- applyUniqueRetValOpt(CSInfo, TargetsForSlot[0].Fn->getName(), IsOne,
- UniqueMemberAddr);
- // Update devirtualization statistics for targets.
- if (RemarksEnabled)
- for (auto &&Target : TargetsForSlot)
- Target.WasDevirt = true;
- return true;
- };
- if (BitWidth == 1) {
- if (tryUniqueRetValOptFor(true))
- return true;
- if (tryUniqueRetValOptFor(false))
- return true;
- }
- return false;
- }
- void DevirtModule::applyVirtualConstProp(CallSiteInfo &CSInfo, StringRef FnName,
- Constant *Byte, Constant *Bit) {
- for (auto Call : CSInfo.CallSites) {
- auto *RetType = cast<IntegerType>(Call.CS.getType());
- IRBuilder<> B(Call.CS.getInstruction());
- Value *Addr = B.CreateGEP(Int8Ty, Call.VTable, Byte);
- if (RetType->getBitWidth() == 1) {
- Value *Bits = B.CreateLoad(Addr);
- Value *BitsAndBit = B.CreateAnd(Bits, Bit);
- auto IsBitSet = B.CreateICmpNE(BitsAndBit, ConstantInt::get(Int8Ty, 0));
- Call.replaceAndErase("virtual-const-prop-1-bit", FnName, RemarksEnabled,
- IsBitSet);
- } else {
- Value *ValAddr = B.CreateBitCast(Addr, RetType->getPointerTo());
- Value *Val = B.CreateLoad(RetType, ValAddr);
- Call.replaceAndErase("virtual-const-prop", FnName, RemarksEnabled, Val);
- }
- }
- CSInfo.markDevirt();
- }
- bool DevirtModule::tryVirtualConstProp(
- MutableArrayRef<VirtualCallTarget> TargetsForSlot, VTableSlotInfo &SlotInfo,
- WholeProgramDevirtResolution *Res, VTableSlot Slot) {
- // This only works if the function returns an integer.
- auto RetType = dyn_cast<IntegerType>(TargetsForSlot[0].Fn->getReturnType());
- if (!RetType)
- return false;
- unsigned BitWidth = RetType->getBitWidth();
- if (BitWidth > 64)
- return false;
- // Make sure that each function is defined, does not access memory, takes at
- // least one argument, does not use its first argument (which we assume is
- // 'this'), and has the same return type.
- //
- // Note that we test whether this copy of the function is readnone, rather
- // than testing function attributes, which must hold for any copy of the
- // function, even a less optimized version substituted at link time. This is
- // sound because the virtual constant propagation optimizations effectively
- // inline all implementations of the virtual function into each call site,
- // rather than using function attributes to perform local optimization.
- for (VirtualCallTarget &Target : TargetsForSlot) {
- if (Target.Fn->isDeclaration() ||
- computeFunctionBodyMemoryAccess(*Target.Fn, AARGetter(*Target.Fn)) !=
- MAK_ReadNone ||
- Target.Fn->arg_empty() || !Target.Fn->arg_begin()->use_empty() ||
- Target.Fn->getReturnType() != RetType)
- return false;
- }
- for (auto &&CSByConstantArg : SlotInfo.ConstCSInfo) {
- if (!tryEvaluateFunctionsWithArgs(TargetsForSlot, CSByConstantArg.first))
- continue;
- WholeProgramDevirtResolution::ByArg *ResByArg = nullptr;
- if (Res)
- ResByArg = &Res->ResByArg[CSByConstantArg.first];
- if (tryUniformRetValOpt(TargetsForSlot, CSByConstantArg.second, ResByArg))
- continue;
- if (tryUniqueRetValOpt(BitWidth, TargetsForSlot, CSByConstantArg.second,
- ResByArg, Slot, CSByConstantArg.first))
- continue;
- // Find an allocation offset in bits in all vtables associated with the
- // type.
- uint64_t AllocBefore =
- findLowestOffset(TargetsForSlot, /*IsAfter=*/false, BitWidth);
- uint64_t AllocAfter =
- findLowestOffset(TargetsForSlot, /*IsAfter=*/true, BitWidth);
- // Calculate the total amount of padding needed to store a value at both
- // ends of the object.
- uint64_t TotalPaddingBefore = 0, TotalPaddingAfter = 0;
- for (auto &&Target : TargetsForSlot) {
- TotalPaddingBefore += std::max<int64_t>(
- (AllocBefore + 7) / 8 - Target.allocatedBeforeBytes() - 1, 0);
- TotalPaddingAfter += std::max<int64_t>(
- (AllocAfter + 7) / 8 - Target.allocatedAfterBytes() - 1, 0);
- }
- // If the amount of padding is too large, give up.
- // FIXME: do something smarter here.
- if (std::min(TotalPaddingBefore, TotalPaddingAfter) > 128)
- continue;
- // Calculate the offset to the value as a (possibly negative) byte offset
- // and (if applicable) a bit offset, and store the values in the targets.
- int64_t OffsetByte;
- uint64_t OffsetBit;
- if (TotalPaddingBefore <= TotalPaddingAfter)
- setBeforeReturnValues(TargetsForSlot, AllocBefore, BitWidth, OffsetByte,
- OffsetBit);
- else
- setAfterReturnValues(TargetsForSlot, AllocAfter, BitWidth, OffsetByte,
- OffsetBit);
- if (RemarksEnabled)
- for (auto &&Target : TargetsForSlot)
- Target.WasDevirt = true;
- Constant *ByteConst = ConstantInt::get(Int32Ty, OffsetByte);
- Constant *BitConst = ConstantInt::get(Int8Ty, 1ULL << OffsetBit);
- if (CSByConstantArg.second.isExported()) {
- ResByArg->TheKind = WholeProgramDevirtResolution::ByArg::VirtualConstProp;
- exportGlobal(Slot, CSByConstantArg.first, "byte",
- ConstantExpr::getIntToPtr(ByteConst, Int8PtrTy));
- exportGlobal(Slot, CSByConstantArg.first, "bit",
- ConstantExpr::getIntToPtr(BitConst, Int8PtrTy));
- }
- // Rewrite each call to a load from OffsetByte/OffsetBit.
- applyVirtualConstProp(CSByConstantArg.second,
- TargetsForSlot[0].Fn->getName(), ByteConst, BitConst);
- }
- return true;
- }
- void DevirtModule::rebuildGlobal(VTableBits &B) {
- if (B.Before.Bytes.empty() && B.After.Bytes.empty())
- return;
- // Align each byte array to pointer width.
- unsigned PointerSize = M.getDataLayout().getPointerSize();
- B.Before.Bytes.resize(alignTo(B.Before.Bytes.size(), PointerSize));
- B.After.Bytes.resize(alignTo(B.After.Bytes.size(), PointerSize));
- // Before was stored in reverse order; flip it now.
- for (size_t I = 0, Size = B.Before.Bytes.size(); I != Size / 2; ++I)
- std::swap(B.Before.Bytes[I], B.Before.Bytes[Size - 1 - I]);
- // Build an anonymous global containing the before bytes, followed by the
- // original initializer, followed by the after bytes.
- auto NewInit = ConstantStruct::getAnon(
- {ConstantDataArray::get(M.getContext(), B.Before.Bytes),
- B.GV->getInitializer(),
- ConstantDataArray::get(M.getContext(), B.After.Bytes)});
- auto NewGV =
- new GlobalVariable(M, NewInit->getType(), B.GV->isConstant(),
- GlobalVariable::PrivateLinkage, NewInit, "", B.GV);
- NewGV->setSection(B.GV->getSection());
- NewGV->setComdat(B.GV->getComdat());
- // Copy the original vtable's metadata to the anonymous global, adjusting
- // offsets as required.
- NewGV->copyMetadata(B.GV, B.Before.Bytes.size());
- // Build an alias named after the original global, pointing at the second
- // element (the original initializer).
- auto Alias = GlobalAlias::create(
- B.GV->getInitializer()->getType(), 0, B.GV->getLinkage(), "",
- ConstantExpr::getGetElementPtr(
- NewInit->getType(), NewGV,
- ArrayRef<Constant *>{ConstantInt::get(Int32Ty, 0),
- ConstantInt::get(Int32Ty, 1)}),
- &M);
- Alias->setVisibility(B.GV->getVisibility());
- Alias->takeName(B.GV);
- B.GV->replaceAllUsesWith(Alias);
- B.GV->eraseFromParent();
- }
- bool DevirtModule::areRemarksEnabled() {
- const auto &FL = M.getFunctionList();
- if (FL.empty())
- return false;
- const Function &Fn = FL.front();
- const auto &BBL = Fn.getBasicBlockList();
- if (BBL.empty())
- return false;
- auto DI = OptimizationRemark(DEBUG_TYPE, "", DebugLoc(), &BBL.front());
- return DI.isEnabled();
- }
- void DevirtModule::scanTypeTestUsers(Function *TypeTestFunc,
- Function *AssumeFunc) {
- // Find all virtual calls via a virtual table pointer %p under an assumption
- // of the form llvm.assume(llvm.type.test(%p, %md)). This indicates that %p
- // points to a member of the type identifier %md. Group calls by (type ID,
- // offset) pair (effectively the identity of the virtual function) and store
- // to CallSlots.
- DenseSet<Value *> SeenPtrs;
- for (auto I = TypeTestFunc->use_begin(), E = TypeTestFunc->use_end();
- I != E;) {
- auto CI = dyn_cast<CallInst>(I->getUser());
- ++I;
- if (!CI)
- continue;
- // Search for virtual calls based on %p and add them to DevirtCalls.
- SmallVector<DevirtCallSite, 1> DevirtCalls;
- SmallVector<CallInst *, 1> Assumes;
- findDevirtualizableCallsForTypeTest(DevirtCalls, Assumes, CI);
- // 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 *TypeId =
- cast<MetadataAsValue>(CI->getArgOperand(1))->getMetadata();
- Value *Ptr = CI->getArgOperand(0)->stripPointerCasts();
- if (SeenPtrs.insert(Ptr).second) {
- for (DevirtCallSite Call : DevirtCalls) {
- CallSlots[{TypeId, Call.Offset}].addCallSite(CI->getArgOperand(0),
- Call.CS, nullptr);
- }
- }
- }
- // We no longer need the assumes or the type 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())
- CI->eraseFromParent();
- }
- }
- void DevirtModule::scanTypeCheckedLoadUsers(Function *TypeCheckedLoadFunc) {
- Function *TypeTestFunc = Intrinsic::getDeclaration(&M, Intrinsic::type_test);
- for (auto I = TypeCheckedLoadFunc->use_begin(),
- E = TypeCheckedLoadFunc->use_end();
- I != E;) {
- auto CI = dyn_cast<CallInst>(I->getUser());
- ++I;
- if (!CI)
- continue;
- Value *Ptr = CI->getArgOperand(0);
- Value *Offset = CI->getArgOperand(1);
- Value *TypeIdValue = CI->getArgOperand(2);
- Metadata *TypeId = cast<MetadataAsValue>(TypeIdValue)->getMetadata();
- SmallVector<DevirtCallSite, 1> DevirtCalls;
- SmallVector<Instruction *, 1> LoadedPtrs;
- SmallVector<Instruction *, 1> Preds;
- bool HasNonCallUses = false;
- findDevirtualizableCallsForTypeCheckedLoad(DevirtCalls, LoadedPtrs, Preds,
- HasNonCallUses, CI);
- // Start by generating "pessimistic" code that explicitly loads the function
- // pointer from the vtable and performs the type check. If possible, we will
- // eliminate the load and the type check later.
- // If possible, only generate the load at the point where it is used.
- // This helps avoid unnecessary spills.
- IRBuilder<> LoadB(
- (LoadedPtrs.size() == 1 && !HasNonCallUses) ? LoadedPtrs[0] : CI);
- Value *GEP = LoadB.CreateGEP(Int8Ty, Ptr, Offset);
- Value *GEPPtr = LoadB.CreateBitCast(GEP, PointerType::getUnqual(Int8PtrTy));
- Value *LoadedValue = LoadB.CreateLoad(Int8PtrTy, GEPPtr);
- for (Instruction *LoadedPtr : LoadedPtrs) {
- LoadedPtr->replaceAllUsesWith(LoadedValue);
- LoadedPtr->eraseFromParent();
- }
- // Likewise for the type test.
- IRBuilder<> CallB((Preds.size() == 1 && !HasNonCallUses) ? Preds[0] : CI);
- CallInst *TypeTestCall = CallB.CreateCall(TypeTestFunc, {Ptr, TypeIdValue});
- for (Instruction *Pred : Preds) {
- Pred->replaceAllUsesWith(TypeTestCall);
- Pred->eraseFromParent();
- }
- // We have already erased any extractvalue instructions that refer to the
- // intrinsic call, but the intrinsic may have other non-extractvalue uses
- // (although this is unlikely). In that case, explicitly build a pair and
- // RAUW it.
- if (!CI->use_empty()) {
- Value *Pair = UndefValue::get(CI->getType());
- IRBuilder<> B(CI);
- Pair = B.CreateInsertValue(Pair, LoadedValue, {0});
- Pair = B.CreateInsertValue(Pair, TypeTestCall, {1});
- CI->replaceAllUsesWith(Pair);
- }
- // The number of unsafe uses is initially the number of uses.
- auto &NumUnsafeUses = NumUnsafeUsesForTypeTest[TypeTestCall];
- NumUnsafeUses = DevirtCalls.size();
- // If the function pointer has a non-call user, we cannot eliminate the type
- // check, as one of those users may eventually call the pointer. Increment
- // the unsafe use count to make sure it cannot reach zero.
- if (HasNonCallUses)
- ++NumUnsafeUses;
- for (DevirtCallSite Call : DevirtCalls) {
- CallSlots[{TypeId, Call.Offset}].addCallSite(Ptr, Call.CS,
- &NumUnsafeUses);
- }
- CI->eraseFromParent();
- }
- }
- void DevirtModule::importResolution(VTableSlot Slot, VTableSlotInfo &SlotInfo) {
- const TypeIdSummary *TidSummary =
- ImportSummary->getTypeIdSummary(cast<MDString>(Slot.TypeID)->getString());
- if (!TidSummary)
- return;
- auto ResI = TidSummary->WPDRes.find(Slot.ByteOffset);
- if (ResI == TidSummary->WPDRes.end())
- return;
- const WholeProgramDevirtResolution &Res = ResI->second;
- if (Res.TheKind == WholeProgramDevirtResolution::SingleImpl) {
- // The type of the function in the declaration is irrelevant because every
- // call site will cast it to the correct type.
- auto *SingleImpl = M.getOrInsertFunction(
- Res.SingleImplName, Type::getVoidTy(M.getContext()));
- // This is the import phase so we should not be exporting anything.
- bool IsExported = false;
- applySingleImplDevirt(SlotInfo, SingleImpl, IsExported);
- assert(!IsExported);
- }
- for (auto &CSByConstantArg : SlotInfo.ConstCSInfo) {
- auto I = Res.ResByArg.find(CSByConstantArg.first);
- if (I == Res.ResByArg.end())
- continue;
- auto &ResByArg = I->second;
- // FIXME: We should figure out what to do about the "function name" argument
- // to the apply* functions, as the function names are unavailable during the
- // importing phase. For now we just pass the empty string. This does not
- // impact correctness because the function names are just used for remarks.
- switch (ResByArg.TheKind) {
- case WholeProgramDevirtResolution::ByArg::UniformRetVal:
- applyUniformRetValOpt(CSByConstantArg.second, "", ResByArg.Info);
- break;
- case WholeProgramDevirtResolution::ByArg::UniqueRetVal: {
- Constant *UniqueMemberAddr =
- importGlobal(Slot, CSByConstantArg.first, "unique_member");
- applyUniqueRetValOpt(CSByConstantArg.second, "", ResByArg.Info,
- UniqueMemberAddr);
- break;
- }
- case WholeProgramDevirtResolution::ByArg::VirtualConstProp: {
- Constant *Byte = importGlobal(Slot, CSByConstantArg.first, "byte", 32);
- Byte = ConstantExpr::getPtrToInt(Byte, Int32Ty);
- Constant *Bit = importGlobal(Slot, CSByConstantArg.first, "bit", 8);
- Bit = ConstantExpr::getPtrToInt(Bit, Int8Ty);
- applyVirtualConstProp(CSByConstantArg.second, "", Byte, Bit);
- }
- default:
- break;
- }
- }
- }
- void DevirtModule::removeRedundantTypeTests() {
- auto True = ConstantInt::getTrue(M.getContext());
- for (auto &&U : NumUnsafeUsesForTypeTest) {
- if (U.second == 0) {
- U.first->replaceAllUsesWith(True);
- U.first->eraseFromParent();
- }
- }
- }
- bool DevirtModule::run() {
- Function *TypeTestFunc =
- M.getFunction(Intrinsic::getName(Intrinsic::type_test));
- Function *TypeCheckedLoadFunc =
- M.getFunction(Intrinsic::getName(Intrinsic::type_checked_load));
- Function *AssumeFunc = M.getFunction(Intrinsic::getName(Intrinsic::assume));
- // Normally if there are no users of the devirtualization intrinsics in the
- // module, this pass has nothing to do. But if we are exporting, we also need
- // to handle any users that appear only in the function summaries.
- if (!ExportSummary &&
- (!TypeTestFunc || TypeTestFunc->use_empty() || !AssumeFunc ||
- AssumeFunc->use_empty()) &&
- (!TypeCheckedLoadFunc || TypeCheckedLoadFunc->use_empty()))
- return false;
- if (TypeTestFunc && AssumeFunc)
- scanTypeTestUsers(TypeTestFunc, AssumeFunc);
- if (TypeCheckedLoadFunc)
- scanTypeCheckedLoadUsers(TypeCheckedLoadFunc);
- if (ImportSummary) {
- for (auto &S : CallSlots)
- importResolution(S.first, S.second);
- removeRedundantTypeTests();
- // The rest of the code is only necessary when exporting or during regular
- // LTO, so we are done.
- return true;
- }
- // Rebuild type metadata into a map for easy lookup.
- std::vector<VTableBits> Bits;
- DenseMap<Metadata *, std::set<TypeMemberInfo>> TypeIdMap;
- buildTypeIdentifierMap(Bits, TypeIdMap);
- if (TypeIdMap.empty())
- return true;
- // Collect information from summary about which calls to try to devirtualize.
- if (ExportSummary) {
- DenseMap<GlobalValue::GUID, TinyPtrVector<Metadata *>> MetadataByGUID;
- for (auto &P : TypeIdMap) {
- if (auto *TypeId = dyn_cast<MDString>(P.first))
- MetadataByGUID[GlobalValue::getGUID(TypeId->getString())].push_back(
- TypeId);
- }
- for (auto &P : *ExportSummary) {
- for (auto &S : P.second) {
- auto *FS = dyn_cast<FunctionSummary>(S.get());
- if (!FS)
- continue;
- // FIXME: Only add live functions.
- for (FunctionSummary::VFuncId VF : FS->type_test_assume_vcalls()) {
- for (Metadata *MD : MetadataByGUID[VF.GUID]) {
- CallSlots[{MD, VF.Offset}].CSInfo.SummaryHasTypeTestAssumeUsers =
- true;
- }
- }
- for (FunctionSummary::VFuncId VF : FS->type_checked_load_vcalls()) {
- for (Metadata *MD : MetadataByGUID[VF.GUID]) {
- CallSlots[{MD, VF.Offset}]
- .CSInfo.SummaryTypeCheckedLoadUsers.push_back(FS);
- }
- }
- for (const FunctionSummary::ConstVCall &VC :
- FS->type_test_assume_const_vcalls()) {
- for (Metadata *MD : MetadataByGUID[VC.VFunc.GUID]) {
- CallSlots[{MD, VC.VFunc.Offset}]
- .ConstCSInfo[VC.Args]
- .SummaryHasTypeTestAssumeUsers = true;
- }
- }
- for (const FunctionSummary::ConstVCall &VC :
- FS->type_checked_load_const_vcalls()) {
- for (Metadata *MD : MetadataByGUID[VC.VFunc.GUID]) {
- CallSlots[{MD, VC.VFunc.Offset}]
- .ConstCSInfo[VC.Args]
- .SummaryTypeCheckedLoadUsers.push_back(FS);
- }
- }
- }
- }
- }
- // For each (type, offset) pair:
- bool DidVirtualConstProp = false;
- std::map<std::string, Function*> DevirtTargets;
- for (auto &S : CallSlots) {
- // Search each of the members of the type identifier for the virtual
- // function implementation at offset S.first.ByteOffset, and add to
- // TargetsForSlot.
- std::vector<VirtualCallTarget> TargetsForSlot;
- if (tryFindVirtualCallTargets(TargetsForSlot, TypeIdMap[S.first.TypeID],
- S.first.ByteOffset)) {
- WholeProgramDevirtResolution *Res = nullptr;
- if (ExportSummary && isa<MDString>(S.first.TypeID))
- Res = &ExportSummary
- ->getOrInsertTypeIdSummary(
- cast<MDString>(S.first.TypeID)->getString())
- .WPDRes[S.first.ByteOffset];
- if (!trySingleImplDevirt(TargetsForSlot, S.second, Res) &&
- tryVirtualConstProp(TargetsForSlot, S.second, Res, S.first))
- DidVirtualConstProp = true;
- // Collect functions devirtualized at least for one call site for stats.
- if (RemarksEnabled)
- for (const auto &T : TargetsForSlot)
- if (T.WasDevirt)
- DevirtTargets[T.Fn->getName()] = T.Fn;
- }
- // CFI-specific: if we are exporting and any llvm.type.checked.load
- // intrinsics were *not* devirtualized, we need to add the resulting
- // llvm.type.test intrinsics to the function summaries so that the
- // LowerTypeTests pass will export them.
- if (ExportSummary && isa<MDString>(S.first.TypeID)) {
- auto GUID =
- GlobalValue::getGUID(cast<MDString>(S.first.TypeID)->getString());
- for (auto FS : S.second.CSInfo.SummaryTypeCheckedLoadUsers)
- FS->addTypeTest(GUID);
- for (auto &CCS : S.second.ConstCSInfo)
- for (auto FS : CCS.second.SummaryTypeCheckedLoadUsers)
- FS->addTypeTest(GUID);
- }
- }
- if (RemarksEnabled) {
- // Generate remarks for each devirtualized function.
- for (const auto &DT : DevirtTargets) {
- Function *F = DT.second;
- DISubprogram *SP = F->getSubprogram();
- emitOptimizationRemark(F->getContext(), DEBUG_TYPE, *F, SP,
- Twine("devirtualized ") + F->getName());
- }
- }
- removeRedundantTypeTests();
- // Rebuild each global we touched as part of virtual constant propagation to
- // include the before and after bytes.
- if (DidVirtualConstProp)
- for (VTableBits &B : Bits)
- rebuildGlobal(B);
- return true;
- }
|