From d84b0f9851ad50d8d2a8e7f3b09f5d9f13f7b6e7 Mon Sep 17 00:00:00 2001 From: Kuba Brecka Date: Mon, 14 Nov 2016 21:41:13 +0000 Subject: [PATCH] [tsan] Add support for C++ exceptions into TSan (call __tsan_func_exit during unwinding), LLVM part This adds support for TSan C++ exception handling, where we need to add extra calls to __tsan_func_exit when a function is exitted via exception mechanisms. Otherwise the shadow stack gets corrupted (leaked). This patch moves and enhances the existing implementation of EscapeEnumerator that finds all possible function exit points, and adds extra EH cleanup blocks where needed. Differential Revision: https://reviews.llvm.org/D26177 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286893 91177308-0d34-0410-b5e6-96231b3b80d8 --- include/llvm/Analysis/EHPersonalities.h | 5 + .../llvm/Transforms/Utils/EscapeEnumerator.h | 49 ++++++++ include/llvm/Transforms/Utils/Local.h | 7 ++ lib/Analysis/EHPersonalities.cpp | 23 ++++ lib/CodeGen/ShadowStackGCLowering.cpp | 116 +----------------- .../Instrumentation/ThreadSanitizer.cpp | 68 +++++----- lib/Transforms/Utils/CMakeLists.txt | 1 + lib/Transforms/Utils/EscapeEnumerator.cpp | 96 +++++++++++++++ lib/Transforms/Utils/InlineFunction.cpp | 32 +---- lib/Transforms/Utils/Local.cpp | 37 ++++++ test/Instrumentation/ThreadSanitizer/eh.ll | 57 +++++++++ .../ThreadSanitizer/no_sanitize_thread.ll | 2 +- .../sanitize-thread-no-checking.ll | 2 +- .../ThreadSanitizer/str-nobuiltin.ll | 14 +-- 14 files changed, 322 insertions(+), 187 deletions(-) create mode 100644 include/llvm/Transforms/Utils/EscapeEnumerator.h create mode 100644 lib/Transforms/Utils/EscapeEnumerator.cpp create mode 100644 test/Instrumentation/ThreadSanitizer/eh.ll diff --git a/include/llvm/Analysis/EHPersonalities.h b/include/llvm/Analysis/EHPersonalities.h index a26c575cfe1..2c45ab4693e 100644 --- a/include/llvm/Analysis/EHPersonalities.h +++ b/include/llvm/Analysis/EHPersonalities.h @@ -12,6 +12,7 @@ #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/TinyPtrVector.h" +#include "llvm/ADT/Triple.h" #include "llvm/Support/ErrorHandling.h" namespace llvm { @@ -39,6 +40,10 @@ enum class EHPersonality { /// Unknown. EHPersonality classifyEHPersonality(const Value *Pers); +StringRef getEHPersonalityName(EHPersonality Pers); + +EHPersonality getDefaultEHPersonality(const Triple &T); + /// \brief Returns true if this personality function catches asynchronous /// exceptions. inline bool isAsynchronousEHPersonality(EHPersonality Pers) { diff --git a/include/llvm/Transforms/Utils/EscapeEnumerator.h b/include/llvm/Transforms/Utils/EscapeEnumerator.h new file mode 100644 index 00000000000..80d16ed4cf5 --- /dev/null +++ b/include/llvm/Transforms/Utils/EscapeEnumerator.h @@ -0,0 +1,49 @@ +//===-- EscapeEnumerator.h --------------------------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// Defines a helper class that enumerates all possible exits from a function, +// including exception handling. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_TRANSFORMS_UTILS_ESCAPEENUMERATOR_H +#define LLVM_TRANSFORMS_UTILS_ESCAPEENUMERATOR_H + +#include "llvm/IR/IRBuilder.h" +#include "llvm/IR/Function.h" + +namespace llvm { + +/// EscapeEnumerator - This is a little algorithm to find all escape points +/// from a function so that "finally"-style code can be inserted. In addition +/// to finding the existing return and unwind instructions, it also (if +/// necessary) transforms any call instructions into invokes and sends them to +/// a landing pad. +class EscapeEnumerator { + Function &F; + const char *CleanupBBName; + + Function::iterator StateBB, StateE; + IRBuilder<> Builder; + bool Done; + bool HandleExceptions; + +public: + EscapeEnumerator(Function &F, const char *N = "cleanup", + bool HandleExceptions = true) + : F(F), CleanupBBName(N), StateBB(F.begin()), StateE(F.end()), + Builder(F.getContext()), Done(false), + HandleExceptions(HandleExceptions) {} + + IRBuilder<> *Next(); +}; + +} + +#endif // LLVM_TRANSFORMS_UTILS_ESCAPEENUMERATOR_H diff --git a/include/llvm/Transforms/Utils/Local.h b/include/llvm/Transforms/Utils/Local.h index e4185448f01..d967bd5840a 100644 --- a/include/llvm/Transforms/Utils/Local.h +++ b/include/llvm/Transforms/Utils/Local.h @@ -314,6 +314,13 @@ unsigned removeAllNonTerminatorAndEHPadInstructions(BasicBlock *BB); /// instruction, making it and the rest of the code in the block dead. unsigned changeToUnreachable(Instruction *I, bool UseLLVMTrap); +/// Convert the CallInst to InvokeInst with the specified unwind edge basic +/// block. This also splits the basic block where CI is located, because +/// InvokeInst is a terminator instruction. Returns the newly split basic +/// block. +BasicBlock *changeToInvokeAndSplitBasicBlock(CallInst *CI, + BasicBlock *UnwindEdge); + /// Replace 'BB's terminator with one that does not have an unwind successor /// block. Rewrites `invoke` to `call`, etc. Updates any PHIs in unwind /// successor. diff --git a/lib/Analysis/EHPersonalities.cpp b/lib/Analysis/EHPersonalities.cpp index 8896ef06d0c..ebf0a370b0b 100644 --- a/lib/Analysis/EHPersonalities.cpp +++ b/lib/Analysis/EHPersonalities.cpp @@ -40,6 +40,29 @@ EHPersonality llvm::classifyEHPersonality(const Value *Pers) { .Default(EHPersonality::Unknown); } +StringRef llvm::getEHPersonalityName(EHPersonality Pers) { + switch (Pers) { + case EHPersonality::GNU_Ada: return "__gnat_eh_personality"; + case EHPersonality::GNU_CXX: return "__gxx_personality_v0"; + case EHPersonality::GNU_CXX_SjLj: return "__gxx_personality_sj0"; + case EHPersonality::GNU_C: return "__gcc_personality_v0"; + case EHPersonality::GNU_C_SjLj: return "__gcc_personality_sj0"; + case EHPersonality::GNU_ObjC: return "__objc_personality_v0"; + case EHPersonality::MSVC_X86SEH: return "_except_handler3"; + case EHPersonality::MSVC_Win64SEH: return "__C_specific_handler"; + case EHPersonality::MSVC_CXX: return "__CxxFrameHandler3"; + case EHPersonality::CoreCLR: return "ProcessCLRException"; + case EHPersonality::Rust: return "rust_eh_personality"; + case EHPersonality::Unknown: llvm_unreachable("Unknown EHPersonality!"); + } + + llvm_unreachable("Invalid EHPersonality!"); +} + +EHPersonality llvm::getDefaultEHPersonality(const Triple &T) { + return EHPersonality::GNU_C; +} + bool llvm::canSimplifyInvokeNoUnwind(const Function *F) { EHPersonality Personality = classifyEHPersonality(F->getPersonalityFn()); // We can't simplify any invokes to nounwind functions if the personality diff --git a/lib/CodeGen/ShadowStackGCLowering.cpp b/lib/CodeGen/ShadowStackGCLowering.cpp index 1efc440cd70..ff7d205c1f4 100644 --- a/lib/CodeGen/ShadowStackGCLowering.cpp +++ b/lib/CodeGen/ShadowStackGCLowering.cpp @@ -23,6 +23,7 @@ #include "llvm/IR/IRBuilder.h" #include "llvm/IR/IntrinsicInst.h" #include "llvm/IR/Module.h" +#include "llvm/Transforms/Utils/EscapeEnumerator.h" using namespace llvm; @@ -81,121 +82,6 @@ ShadowStackGCLowering::ShadowStackGCLowering() initializeShadowStackGCLoweringPass(*PassRegistry::getPassRegistry()); } -namespace { -/// EscapeEnumerator - This is a little algorithm to find all escape points -/// from a function so that "finally"-style code can be inserted. In addition -/// to finding the existing return and unwind instructions, it also (if -/// necessary) transforms any call instructions into invokes and sends them to -/// a landing pad. -/// -/// It's wrapped up in a state machine using the same transform C# uses for -/// 'yield return' enumerators, This transform allows it to be non-allocating. -class EscapeEnumerator { - Function &F; - const char *CleanupBBName; - - // State. - int State; - Function::iterator StateBB, StateE; - IRBuilder<> Builder; - -public: - EscapeEnumerator(Function &F, const char *N = "cleanup") - : F(F), CleanupBBName(N), State(0), Builder(F.getContext()) {} - - IRBuilder<> *Next() { - switch (State) { - default: - return nullptr; - - case 0: - StateBB = F.begin(); - StateE = F.end(); - State = 1; - - case 1: - // Find all 'return', 'resume', and 'unwind' instructions. - while (StateBB != StateE) { - BasicBlock *CurBB = &*StateBB++; - - // Branches and invokes do not escape, only unwind, resume, and return - // do. - TerminatorInst *TI = CurBB->getTerminator(); - if (!isa(TI) && !isa(TI)) - continue; - - Builder.SetInsertPoint(TI); - return &Builder; - } - - State = 2; - - // Find all 'call' instructions. - SmallVector Calls; - for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB) - for (BasicBlock::iterator II = BB->begin(), EE = BB->end(); II != EE; - ++II) - if (CallInst *CI = dyn_cast(II)) - if (!CI->getCalledFunction() || - !CI->getCalledFunction()->getIntrinsicID()) - Calls.push_back(CI); - - if (Calls.empty()) - return nullptr; - - // Create a cleanup block. - LLVMContext &C = F.getContext(); - BasicBlock *CleanupBB = BasicBlock::Create(C, CleanupBBName, &F); - Type *ExnTy = - StructType::get(Type::getInt8PtrTy(C), Type::getInt32Ty(C), nullptr); - if (!F.hasPersonalityFn()) { - Constant *PersFn = F.getParent()->getOrInsertFunction( - "__gcc_personality_v0", - FunctionType::get(Type::getInt32Ty(C), true)); - F.setPersonalityFn(PersFn); - } - LandingPadInst *LPad = - LandingPadInst::Create(ExnTy, 1, "cleanup.lpad", CleanupBB); - LPad->setCleanup(true); - ResumeInst *RI = ResumeInst::Create(LPad, CleanupBB); - - // Transform the 'call' instructions into 'invoke's branching to the - // cleanup block. Go in reverse order to make prettier BB names. - SmallVector Args; - for (unsigned I = Calls.size(); I != 0;) { - CallInst *CI = cast(Calls[--I]); - - // Split the basic block containing the function call. - BasicBlock *CallBB = CI->getParent(); - BasicBlock *NewBB = CallBB->splitBasicBlock( - CI->getIterator(), CallBB->getName() + ".cont"); - - // Remove the unconditional branch inserted at the end of CallBB. - CallBB->getInstList().pop_back(); - NewBB->getInstList().remove(CI); - - // Create a new invoke instruction. - Args.clear(); - CallSite CS(CI); - Args.append(CS.arg_begin(), CS.arg_end()); - - InvokeInst *II = - InvokeInst::Create(CI->getCalledValue(), NewBB, CleanupBB, Args, - CI->getName(), CallBB); - II->setCallingConv(CI->getCallingConv()); - II->setAttributes(CI->getAttributes()); - CI->replaceAllUsesWith(II); - delete CI; - } - - Builder.SetInsertPoint(RI); - return &Builder; - } - } -}; -} - - Constant *ShadowStackGCLowering::GetFrameMap(Function &F) { // doInitialization creates the abstract type of this value. Type *VoidPtr = Type::getInt8PtrTy(F.getContext()); diff --git a/lib/Transforms/Instrumentation/ThreadSanitizer.cpp b/lib/Transforms/Instrumentation/ThreadSanitizer.cpp index 2c8728945c3..d9659694da4 100644 --- a/lib/Transforms/Instrumentation/ThreadSanitizer.cpp +++ b/lib/Transforms/Instrumentation/ThreadSanitizer.cpp @@ -43,6 +43,7 @@ #include "llvm/Support/MathExtras.h" #include "llvm/Support/raw_ostream.h" #include "llvm/Transforms/Utils/BasicBlockUtils.h" +#include "llvm/Transforms/Utils/EscapeEnumerator.h" #include "llvm/Transforms/Utils/Local.h" #include "llvm/Transforms/Utils/ModuleUtils.h" @@ -56,6 +57,10 @@ static cl::opt ClInstrumentMemoryAccesses( static cl::opt ClInstrumentFuncEntryExit( "tsan-instrument-func-entry-exit", cl::init(true), cl::desc("Instrument function entry and exit"), cl::Hidden); +static cl::opt ClHandleCxxExceptions( + "tsan-handle-cxx-exceptions", cl::init(true), + cl::desc("Handle C++ exceptions (insert cleanup blocks for unwinding)"), + cl::Hidden); static cl::opt ClInstrumentAtomics( "tsan-instrument-atomics", cl::init(true), cl::desc("Instrument atomics"), cl::Hidden); @@ -99,7 +104,7 @@ struct ThreadSanitizer : public FunctionPass { const DataLayout &DL); bool addrPointsToConstantData(Value *Addr); int getMemoryAccessFuncIndex(Value *Addr, const DataLayout &DL); - void InsertRuntimeIgnores(Function &F, SmallVector &RetVec); + void InsertRuntimeIgnores(Function &F); Type *IntptrTy; IntegerType *OrdTy; @@ -150,15 +155,17 @@ FunctionPass *llvm::createThreadSanitizerPass() { void ThreadSanitizer::initializeCallbacks(Module &M) { IRBuilder<> IRB(M.getContext()); + AttributeSet Attr; + Attr = Attr.addAttribute(M.getContext(), AttributeSet::FunctionIndex, Attribute::NoUnwind); // Initialize the callbacks. TsanFuncEntry = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_func_entry", IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + "__tsan_func_entry", Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); TsanFuncExit = checkSanitizerInterfaceFunction( - M.getOrInsertFunction("__tsan_func_exit", IRB.getVoidTy(), nullptr)); + M.getOrInsertFunction("__tsan_func_exit", Attr, IRB.getVoidTy(), nullptr)); TsanIgnoreBegin = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_ignore_thread_begin", IRB.getVoidTy(), nullptr)); + "__tsan_ignore_thread_begin", Attr, IRB.getVoidTy(), nullptr)); TsanIgnoreEnd = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_ignore_thread_end", IRB.getVoidTy(), nullptr)); + "__tsan_ignore_thread_end", Attr, IRB.getVoidTy(), nullptr)); OrdTy = IRB.getInt32Ty(); for (size_t i = 0; i < kNumberOfAccessSizes; ++i) { const unsigned ByteSize = 1U << i; @@ -167,31 +174,31 @@ void ThreadSanitizer::initializeCallbacks(Module &M) { std::string BitSizeStr = utostr(BitSize); SmallString<32> ReadName("__tsan_read" + ByteSizeStr); TsanRead[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - ReadName, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + ReadName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); SmallString<32> WriteName("__tsan_write" + ByteSizeStr); TsanWrite[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - WriteName, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + WriteName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); SmallString<64> UnalignedReadName("__tsan_unaligned_read" + ByteSizeStr); TsanUnalignedRead[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - UnalignedReadName, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + UnalignedReadName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); SmallString<64> UnalignedWriteName("__tsan_unaligned_write" + ByteSizeStr); TsanUnalignedWrite[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - UnalignedWriteName, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + UnalignedWriteName, Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); Type *Ty = Type::getIntNTy(M.getContext(), BitSize); Type *PtrTy = Ty->getPointerTo(); SmallString<32> AtomicLoadName("__tsan_atomic" + BitSizeStr + "_load"); TsanAtomicLoad[i] = checkSanitizerInterfaceFunction( - M.getOrInsertFunction(AtomicLoadName, Ty, PtrTy, OrdTy, nullptr)); + M.getOrInsertFunction(AtomicLoadName, Attr, Ty, PtrTy, OrdTy, nullptr)); SmallString<32> AtomicStoreName("__tsan_atomic" + BitSizeStr + "_store"); TsanAtomicStore[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - AtomicStoreName, IRB.getVoidTy(), PtrTy, Ty, OrdTy, nullptr)); + AtomicStoreName, Attr, IRB.getVoidTy(), PtrTy, Ty, OrdTy, nullptr)); for (int op = AtomicRMWInst::FIRST_BINOP; op <= AtomicRMWInst::LAST_BINOP; ++op) { @@ -215,32 +222,32 @@ void ThreadSanitizer::initializeCallbacks(Module &M) { continue; SmallString<32> RMWName("__tsan_atomic" + itostr(BitSize) + NamePart); TsanAtomicRMW[op][i] = checkSanitizerInterfaceFunction( - M.getOrInsertFunction(RMWName, Ty, PtrTy, Ty, OrdTy, nullptr)); + M.getOrInsertFunction(RMWName, Attr, Ty, PtrTy, Ty, OrdTy, nullptr)); } SmallString<32> AtomicCASName("__tsan_atomic" + BitSizeStr + "_compare_exchange_val"); TsanAtomicCAS[i] = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - AtomicCASName, Ty, PtrTy, Ty, Ty, OrdTy, OrdTy, nullptr)); + AtomicCASName, Attr, Ty, PtrTy, Ty, Ty, OrdTy, OrdTy, nullptr)); } TsanVptrUpdate = checkSanitizerInterfaceFunction( - M.getOrInsertFunction("__tsan_vptr_update", IRB.getVoidTy(), + M.getOrInsertFunction("__tsan_vptr_update", Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), nullptr)); TsanVptrLoad = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_vptr_read", IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); + "__tsan_vptr_read", Attr, IRB.getVoidTy(), IRB.getInt8PtrTy(), nullptr)); TsanAtomicThreadFence = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_atomic_thread_fence", IRB.getVoidTy(), OrdTy, nullptr)); + "__tsan_atomic_thread_fence", Attr, IRB.getVoidTy(), OrdTy, nullptr)); TsanAtomicSignalFence = checkSanitizerInterfaceFunction(M.getOrInsertFunction( - "__tsan_atomic_signal_fence", IRB.getVoidTy(), OrdTy, nullptr)); + "__tsan_atomic_signal_fence", Attr, IRB.getVoidTy(), OrdTy, nullptr)); MemmoveFn = checkSanitizerInterfaceFunction( - M.getOrInsertFunction("memmove", IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), + M.getOrInsertFunction("memmove", Attr, IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IntptrTy, nullptr)); MemcpyFn = checkSanitizerInterfaceFunction( - M.getOrInsertFunction("memcpy", IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), + M.getOrInsertFunction("memcpy", Attr, IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IntptrTy, nullptr)); MemsetFn = checkSanitizerInterfaceFunction( - M.getOrInsertFunction("memset", IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), + M.getOrInsertFunction("memset", Attr, IRB.getInt8PtrTy(), IRB.getInt8PtrTy(), IRB.getInt32Ty(), IntptrTy, nullptr)); } @@ -383,13 +390,12 @@ static bool isAtomic(Instruction *I) { return false; } -void ThreadSanitizer::InsertRuntimeIgnores(Function &F, - SmallVector &RetVec) { +void ThreadSanitizer::InsertRuntimeIgnores(Function &F) { IRBuilder<> IRB(F.getEntryBlock().getFirstNonPHI()); IRB.CreateCall(TsanIgnoreBegin); - for (auto RetInst : RetVec) { - IRBuilder<> IRB(RetInst); - IRB.CreateCall(TsanIgnoreEnd); + EscapeEnumerator EE(F, "tsan_ignore_cleanup", ClHandleCxxExceptions); + while (IRBuilder<> *AtExit = EE.Next()) { + AtExit->CreateCall(TsanIgnoreEnd); } } @@ -399,7 +405,6 @@ bool ThreadSanitizer::runOnFunction(Function &F) { if (&F == TsanCtorFunction) return false; initializeCallbacks(*F.getParent()); - SmallVector RetVec; SmallVector AllLoadsAndStores; SmallVector LocalLoadsAndStores; SmallVector AtomicAccesses; @@ -418,8 +423,6 @@ bool ThreadSanitizer::runOnFunction(Function &F) { AtomicAccesses.push_back(&Inst); else if (isa(Inst) || isa(Inst)) LocalLoadsAndStores.push_back(&Inst); - else if (isa(Inst)) - RetVec.push_back(&Inst); else if (isa(Inst) || isa(Inst)) { if (CallInst *CI = dyn_cast(&Inst)) maybeMarkSanitizerLibraryCallNoBuiltin(CI, TLI); @@ -458,7 +461,7 @@ bool ThreadSanitizer::runOnFunction(Function &F) { if (F.hasFnAttribute("sanitize_thread_no_checking_at_run_time")) { assert(!F.hasFnAttribute(Attribute::SanitizeThread)); if (HasCalls) - InsertRuntimeIgnores(F, RetVec); + InsertRuntimeIgnores(F); } // Instrument function entry/exit points if there were instrumented accesses. @@ -468,9 +471,10 @@ bool ThreadSanitizer::runOnFunction(Function &F) { Intrinsic::getDeclaration(F.getParent(), Intrinsic::returnaddress), IRB.getInt32(0)); IRB.CreateCall(TsanFuncEntry, ReturnAddress); - for (auto RetInst : RetVec) { - IRBuilder<> IRBRet(RetInst); - IRBRet.CreateCall(TsanFuncExit, {}); + + EscapeEnumerator EE(F, "tsan_cleanup", ClHandleCxxExceptions); + while (IRBuilder<> *AtExit = EE.Next()) { + AtExit->CreateCall(TsanFuncExit, {}); } Res = true; } diff --git a/lib/Transforms/Utils/CMakeLists.txt b/lib/Transforms/Utils/CMakeLists.txt index a66c096508a..b4982de419d 100644 --- a/lib/Transforms/Utils/CMakeLists.txt +++ b/lib/Transforms/Utils/CMakeLists.txt @@ -11,6 +11,7 @@ add_llvm_library(LLVMTransformUtils CodeExtractor.cpp CtorUtils.cpp DemoteRegToStack.cpp + EscapeEnumerator.cpp Evaluator.cpp FlattenCFG.cpp FunctionComparator.cpp diff --git a/lib/Transforms/Utils/EscapeEnumerator.cpp b/lib/Transforms/Utils/EscapeEnumerator.cpp new file mode 100644 index 00000000000..8c2386554da --- /dev/null +++ b/lib/Transforms/Utils/EscapeEnumerator.cpp @@ -0,0 +1,96 @@ +//===- EscapeEnumerator.cpp -----------------------------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// Defines a helper class that enumerates all possible exits from a function, +// including exception handling. +// +//===----------------------------------------------------------------------===// + +#include "llvm/Transforms/Utils/EscapeEnumerator.h" +#include "llvm/Analysis/EHPersonalities.h" +#include "llvm/IR/CallSite.h" +#include "llvm/IR/Module.h" +#include "llvm/Transforms/Utils/Local.h" +using namespace llvm; + +static Constant *getDefaultPersonalityFn(Module *M) { + LLVMContext &C = M->getContext(); + Triple T(M->getTargetTriple()); + EHPersonality Pers = getDefaultEHPersonality(T); + return M->getOrInsertFunction(getEHPersonalityName(Pers), + FunctionType::get(Type::getInt32Ty(C), true)); +} + +IRBuilder<> *EscapeEnumerator::Next() { + if (Done) + return nullptr; + + // Find all 'return', 'resume', and 'unwind' instructions. + while (StateBB != StateE) { + BasicBlock *CurBB = &*StateBB++; + + // Branches and invokes do not escape, only unwind, resume, and return + // do. + TerminatorInst *TI = CurBB->getTerminator(); + if (!isa(TI) && !isa(TI)) + continue; + + Builder.SetInsertPoint(TI); + return &Builder; + } + + Done = true; + + if (!HandleExceptions) + return nullptr; + + if (F.doesNotThrow()) + return nullptr; + + // Find all 'call' instructions that may throw. + SmallVector Calls; + for (BasicBlock &BB : F) + for (Instruction &II : BB) + if (CallInst *CI = dyn_cast(&II)) + if (!CI->doesNotThrow()) + Calls.push_back(CI); + + if (Calls.empty()) + return nullptr; + + // Create a cleanup block. + LLVMContext &C = F.getContext(); + BasicBlock *CleanupBB = BasicBlock::Create(C, CleanupBBName, &F); + Type *ExnTy = + StructType::get(Type::getInt8PtrTy(C), Type::getInt32Ty(C), nullptr); + if (!F.hasPersonalityFn()) { + Constant *PersFn = getDefaultPersonalityFn(F.getParent()); + F.setPersonalityFn(PersFn); + } + + if (isFuncletEHPersonality(classifyEHPersonality(F.getPersonalityFn()))) { + report_fatal_error("Funclet EH not supported"); + } + + LandingPadInst *LPad = + LandingPadInst::Create(ExnTy, 1, "cleanup.lpad", CleanupBB); + LPad->setCleanup(true); + ResumeInst *RI = ResumeInst::Create(LPad, CleanupBB); + + // Transform the 'call' instructions into 'invoke's branching to the + // cleanup block. Go in reverse order to make prettier BB names. + SmallVector Args; + for (unsigned I = Calls.size(); I != 0;) { + CallInst *CI = cast(Calls[--I]); + changeToInvokeAndSplitBasicBlock(CI, CleanupBB); + } + + Builder.SetInsertPoint(RI); + return &Builder; +} diff --git a/lib/Transforms/Utils/InlineFunction.cpp b/lib/Transforms/Utils/InlineFunction.cpp index 383010f0f9d..6c02094df29 100644 --- a/lib/Transforms/Utils/InlineFunction.cpp +++ b/lib/Transforms/Utils/InlineFunction.cpp @@ -535,37 +535,7 @@ static BasicBlock *HandleCallsInBlockInlinedThroughInvoke( #endif // NDEBUG } - // Convert this function call into an invoke instruction. First, split the - // basic block. - BasicBlock *Split = - BB->splitBasicBlock(CI->getIterator(), CI->getName() + ".noexc"); - - // Delete the unconditional branch inserted by splitBasicBlock - BB->getInstList().pop_back(); - - // Create the new invoke instruction. - SmallVector InvokeArgs(CI->arg_begin(), CI->arg_end()); - SmallVector OpBundles; - - CI->getOperandBundlesAsDefs(OpBundles); - - // Note: we're round tripping operand bundles through memory here, and that - // can potentially be avoided with a cleverer API design that we do not have - // as of this time. - - InvokeInst *II = - InvokeInst::Create(CI->getCalledValue(), Split, UnwindEdge, InvokeArgs, - OpBundles, CI->getName(), BB); - II->setDebugLoc(CI->getDebugLoc()); - II->setCallingConv(CI->getCallingConv()); - II->setAttributes(CI->getAttributes()); - - // Make sure that anything using the call now uses the invoke! This also - // updates the CallGraph if present, because it uses a WeakVH. - CI->replaceAllUsesWith(II); - - // Delete the original call - Split->getInstList().pop_front(); + changeToInvokeAndSplitBasicBlock(CI, UnwindEdge); return BB; } return nullptr; diff --git a/lib/Transforms/Utils/Local.cpp b/lib/Transforms/Utils/Local.cpp index e52d87a7a51..0483c1e65a8 100644 --- a/lib/Transforms/Utils/Local.cpp +++ b/lib/Transforms/Utils/Local.cpp @@ -1408,6 +1408,43 @@ static void changeToCall(InvokeInst *II) { II->eraseFromParent(); } +BasicBlock *llvm::changeToInvokeAndSplitBasicBlock(CallInst *CI, + BasicBlock *UnwindEdge) { + BasicBlock *BB = CI->getParent(); + + // Convert this function call into an invoke instruction. First, split the + // basic block. + BasicBlock *Split = + BB->splitBasicBlock(CI->getIterator(), CI->getName() + ".noexc"); + + // Delete the unconditional branch inserted by splitBasicBlock + BB->getInstList().pop_back(); + + // Create the new invoke instruction. + SmallVector InvokeArgs(CI->arg_begin(), CI->arg_end()); + SmallVector OpBundles; + + CI->getOperandBundlesAsDefs(OpBundles); + + // Note: we're round tripping operand bundles through memory here, and that + // can potentially be avoided with a cleverer API design that we do not have + // as of this time. + + InvokeInst *II = InvokeInst::Create(CI->getCalledValue(), Split, UnwindEdge, + InvokeArgs, OpBundles, CI->getName(), BB); + II->setDebugLoc(CI->getDebugLoc()); + II->setCallingConv(CI->getCallingConv()); + II->setAttributes(CI->getAttributes()); + + // Make sure that anything using the call now uses the invoke! This also + // updates the CallGraph if present, because it uses a WeakVH. + CI->replaceAllUsesWith(II); + + // Delete the original call + Split->getInstList().pop_front(); + return Split; +} + static bool markAliveBlocks(Function &F, SmallPtrSetImpl &Reachable) { diff --git a/test/Instrumentation/ThreadSanitizer/eh.ll b/test/Instrumentation/ThreadSanitizer/eh.ll new file mode 100644 index 00000000000..a9a54b6cae2 --- /dev/null +++ b/test/Instrumentation/ThreadSanitizer/eh.ll @@ -0,0 +1,57 @@ +; RUN: opt < %s -tsan -S | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-EXC +; RUN: opt < %s -tsan -S -tsan-handle-cxx-exceptions=0 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-NOEXC + +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" + +declare void @can_throw() +declare void @cannot_throw() nounwind + +define i32 @func1() sanitize_thread { + call void @can_throw() + ret i32 0 + ; CHECK-EXC: define i32 @func1() + ; CHECK-EXC: call void @__tsan_func_entry + ; CHECK-EXC: invoke void @can_throw() + ; CHECK-EXC: .noexc: + ; CHECK-EXC: call void @__tsan_func_exit() + ; CHECK-EXC: ret i32 0 + ; CHECK-EXC: tsan_cleanup: + ; CHECK-EXC: call void @__tsan_func_exit() + ; CHECK-EXC: resume + ; CHECK-NOEXC: define i32 @func1() + ; CHECK-NOEXC: call void @__tsan_func_entry + ; CHECK-NOEXC: call void @can_throw() + ; CHECK-NOEXC: call void @__tsan_func_exit() + ; CHECK-NOEXC: ret i32 0 +} + +define i32 @func2() sanitize_thread { + call void @cannot_throw() + ret i32 0 + ; CHECK: define i32 @func2() + ; CHECK: call void @__tsan_func_entry + ; CHECK: call void @cannot_throw() + ; CHECK: call void @__tsan_func_exit() + ; CHECK: ret i32 0 +} + +define i32 @func3(i32* %p) sanitize_thread { + %a = load i32, i32* %p + ret i32 %a + ; CHECK: define i32 @func3(i32* %p) + ; CHECK: call void @__tsan_func_entry + ; CHECK: call void @__tsan_read4 + ; CHECK: %a = load i32, i32* %p + ; CHECK: call void @__tsan_func_exit() + ; CHECK: ret i32 %a +} + +define i32 @func4() sanitize_thread nounwind { + call void @can_throw() + ret i32 0 + ; CHECK: define i32 @func4() + ; CHECK: call void @__tsan_func_entry + ; CHECK: call void @can_throw() + ; CHECK: call void @__tsan_func_exit() + ; CHECK: ret i32 0 +} diff --git a/test/Instrumentation/ThreadSanitizer/no_sanitize_thread.ll b/test/Instrumentation/ThreadSanitizer/no_sanitize_thread.ll index a90a56064a0..70154251d14 100644 --- a/test/Instrumentation/ThreadSanitizer/no_sanitize_thread.ll +++ b/test/Instrumentation/ThreadSanitizer/no_sanitize_thread.ll @@ -32,5 +32,5 @@ entry: ; CHECK-NEXT: call void @__tsan_func_exit() ; CHECK-NEXT: ret i32 %tmp1 -declare void @foo() +declare void @foo() nounwind diff --git a/test/Instrumentation/ThreadSanitizer/sanitize-thread-no-checking.ll b/test/Instrumentation/ThreadSanitizer/sanitize-thread-no-checking.ll index 1bb3291f484..8bd45031f1d 100644 --- a/test/Instrumentation/ThreadSanitizer/sanitize-thread-no-checking.ll +++ b/test/Instrumentation/ThreadSanitizer/sanitize-thread-no-checking.ll @@ -14,7 +14,7 @@ entry: ; CHECK-NEXT: %tmp1 = load i32, i32* %a, align 4 ; CHECK-NEXT: ret i32 %tmp1 -declare void @"foo"() +declare void @"foo"() nounwind define i32 @"\01-[WithCalls dealloc]"(i32* %a) "sanitize_thread_no_checking_at_run_time" { entry: diff --git a/test/Instrumentation/ThreadSanitizer/str-nobuiltin.ll b/test/Instrumentation/ThreadSanitizer/str-nobuiltin.ll index 452d7becaaa..7f9383de404 100644 --- a/test/Instrumentation/ThreadSanitizer/str-nobuiltin.ll +++ b/test/Instrumentation/ThreadSanitizer/str-nobuiltin.ll @@ -4,13 +4,13 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" target triple = "x86_64-unknown-linux-gnu" -declare i8* @memchr(i8* %a, i32 %b, i64 %c) -declare i32 @memcmp(i8* %a, i8* %b, i64 %c) -declare i32 @strcmp(i8* %a, i8* %b) -declare i8* @strcpy(i8* %a, i8* %b) -declare i8* @stpcpy(i8* %a, i8* %b) -declare i64 @strlen(i8* %a) -declare i64 @strnlen(i8* %a, i64 %b) +declare i8* @memchr(i8* %a, i32 %b, i64 %c) nounwind +declare i32 @memcmp(i8* %a, i8* %b, i64 %c) nounwind +declare i32 @strcmp(i8* %a, i8* %b) nounwind +declare i8* @strcpy(i8* %a, i8* %b) nounwind +declare i8* @stpcpy(i8* %a, i8* %b) nounwind +declare i64 @strlen(i8* %a) nounwind +declare i64 @strnlen(i8* %a, i64 %b) nounwind ; CHECK: call{{.*}}@memchr{{.*}} #[[ATTR:[0-9]+]] ; CHECK: call{{.*}}@memcmp{{.*}} #[[ATTR]]