static bool addNoRecurseAttrs(const CallGraphSCC &SCC) {
// Try and identify functions that do not recurse.
// If the SCC contains multiple nodes we know for sure there is recursion.
if (!SCC.isSingular())
return false;
const CallGraphNode *CGN = *SCC.begin();
Function *F = CGN->getFunction();
if (!F || F->isDeclaration() || F->doesNotRecurse())
return false;
// If all of the calls in F are identifiable and are to norecurse functions, F
// is norecurse. This check also detects self-recursion as F is not currently
// marked norecurse, so any called from F to F will not be marked norecurse.
if (std::all_of(CGN->begin(), CGN->end(),
[](const CallGraphNode::CallRecord &CR) {
Function *F = CR.second->getFunction();
return F && F->doesNotRecurse();
}))
// Function calls a potentially recursive function.
return setDoesNotRecurse(*F);
// Nothing else we can deduce usefully during the postorder traversal.
return false;
}
static bool addNoRecurseAttrs(const CallGraphSCC &SCC,
SmallVectorImpl<WeakVH> &Revisit) {
// Try and identify functions that do not recurse.
// If the SCC contains multiple nodes we know for sure there is recursion.
if (!SCC.isSingular())
return false;
const CallGraphNode *CGN = *SCC.begin();
Function *F = CGN->getFunction();
if (!F || F->isDeclaration() || F->doesNotRecurse())
return false;
// If all of the calls in F are identifiable and are to norecurse functions, F
// is norecurse. This check also detects self-recursion as F is not currently
// marked norecurse, so any called from F to F will not be marked norecurse.
if (std::all_of(CGN->begin(), CGN->end(),
[](const CallGraphNode::CallRecord &CR) {
Function *F = CR.second->getFunction();
return F && F->doesNotRecurse();
}))
// Function calls a potentially recursive function.
return setDoesNotRecurse(*F);
// We know that F is not obviously recursive, but we haven't been able to
// prove that it doesn't actually recurse. Add it to the Revisit list to try
// again top-down later.
Revisit.push_back(F);
return false;
}
/// AddNoCaptureAttrs - Deduce nocapture attributes for the SCC.
bool FunctionAttrs::AddNoCaptureAttrs(const CallGraphSCC &SCC) {
bool Changed = false;
// Check each function in turn, determining which pointer arguments are not
// captured.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0)
// External node - skip it;
continue;
// Definitions with weak linkage may be overridden at linktime with
// something that writes memory, so treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
continue;
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end(); A!=E; ++A)
if (A->getType()->isPointerTy() && !A->hasNoCaptureAttr() &&
!PointerMayBeCaptured(A, true, /*StoreCaptures=*/false)) {
A->addAttr(Attribute::NoCapture);
++NumNoCapture;
Changed = true;
}
}
return Changed;
}
bool AnalysisEngine::runOnSCC(CallGraphSCC &scc) {
for (CallGraphSCC::iterator i = scc.begin(),
e = scc.end(); i != e; ++i) {
CallGraphNode *cgnode = *i;
Function *f = cgnode->getFunction();
FunctionSimulator fsimulator(f);
fsimulator.simulate();
}
}
/// RefreshCallGraph - Scan the functions in the specified CFG and resync the
/// callgraph with the call sites found in it. This is used after
/// FunctionPasses have potentially munged the callgraph, and can be used after
/// CallGraphSCC passes to verify that they correctly updated the callgraph.
///
/// This function returns true if it devirtualized an existing function call,
/// meaning it turned an indirect call into a direct call. This happens when
/// a function pass like GVN optimizes away stuff feeding the indirect call.
/// This never happens in checking mode.
///
bool CGPassManager::RefreshCallGraph(CallGraphSCC &CurSCC,
CallGraph &CG, bool CheckingMode) {
DenseMap<Value*, CallGraphNode*> CallSites;
DEBUG(dbgs() << "CGSCCPASSMGR: Refreshing SCC with " << CurSCC.size()
<< " nodes:\n";
for (CallGraphSCC::iterator I = CurSCC.begin(), E = CurSCC.end();
I != E; ++I)
(*I)->dump();
);
bool CGPassManager::RunPassOnSCC(Pass *P, CallGraphSCC &CurSCC,
CallGraph &CG, bool &CallGraphUpToDate,
bool &DevirtualizedCall) {
bool Changed = false;
PMDataManager *PM = P->getAsPMDataManager();
if (!PM) {
CallGraphSCCPass *CGSP = (CallGraphSCCPass*)P;
if (!CallGraphUpToDate) {
DevirtualizedCall |= RefreshCallGraph(CurSCC, CG, false);
CallGraphUpToDate = true;
}
{
TimeRegion PassTimer(getPassTimer(CGSP));
Changed = CGSP->runOnSCC(CurSCC);
}
// After the CGSCCPass is done, when assertions are enabled, use
// RefreshCallGraph to verify that the callgraph was correctly updated.
#ifndef NDEBUG
if (Changed)
RefreshCallGraph(CurSCC, CG, true);
#endif
return Changed;
}
assert(PM->getPassManagerType() == PMT_FunctionPassManager &&
"Invalid CGPassManager member");
FPPassManager *FPP = (FPPassManager*)P;
// Run pass P on all functions in the current SCC.
for (CallGraphSCC::iterator I = CurSCC.begin(), E = CurSCC.end();
I != E; ++I) {
if (Function *F = (*I)->getFunction()) {
dumpPassInfo(P, EXECUTION_MSG, ON_FUNCTION_MSG, F->getName());
{
TimeRegion PassTimer(getPassTimer(FPP));
Changed |= FPP->runOnFunction(*F);
}
F->getContext().yield();
}
}
// The function pass(es) modified the IR, they may have clobbered the
// callgraph.
if (Changed && CallGraphUpToDate) {
DEBUG(dbgs() << "CGSCCPASSMGR: Pass Dirtied SCC: "
<< P->getPassName() << '\n');
CallGraphUpToDate = false;
}
return Changed;
}
bool SRETPromotion::runOnSCC(CallGraphSCC &SCC) {
bool Changed = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
if (CallGraphNode *NewNode = PromoteReturn(*I)) {
SCC.ReplaceNode(*I, NewNode);
Changed = true;
}
return Changed;
}
bool BottomUpPass::runOnSCC(CallGraphSCC &SCC)
{
// NumCalls =0;
// CallGraph CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
//DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
//const DataLayout *DL = DLP ? &DLP->getDataLayout() : nullptr;
//const TargetLibraryInfo *TLI = getAnalysisIfAvailable<TargetLibraryInfo>();
SmallPtrSet<Function*, 8> SCCFunctions;
DEBUG(dbgs() << "\nInliner visiting SCC:");
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F) {SCCFunctions.insert(F); NumFuncitons++; }
DEBUG(dbgs() << " " << (F ? F->getName() : "INDIRECTNODE"));
}
// NumCalls = SCCFunctions.size();
DEBUG(dbgs() << "\nSizeof the SCC: "<<SCC.size());
//Collect all the call sites.
SmallVector<std::pair<CallSite, int>, 16> CallSites;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F)
{
//Check waht kind of call it is:
// errs()<<"\nCallGRaph node dump -- ";
// (*I)->dump();
continue;
}
for (Function::iterator BB = F->begin(), E = F->end(); BB != E; ++BB)
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
CallSite CS(cast<Value>(I));
// If this isn't a call, or it is a call to an intrinsic, it can
// never be inlined.
if (!CS || isa<IntrinsicInst>(I))
continue;
// If this is a direct call to an external function, we can never inline
// it. If it is an indirect call, inlining may resolve it to be a
// direct call, so we keep it.
if (CS.getCalledFunction() && CS.getCalledFunction()->isDeclaration())
continue;
CallSites.push_back(std::make_pair(CS, -1));
}
}
DEBUG(dbgs() << ": " << CallSites.size() << " call sites.\n");
NumCalls +=CallSites.size();
}
bool CverPruneStack::PruneWithSCCCallGraph(CallGraphSCC &SCC) {
CVER_DEBUG("-----------------------------------\n");
bool mayCallCast = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F)
continue;
CVER_DEBUG(" F : " << F->getName() << "\n");
// Check if this function may call __cver_handle_stack_enter
for (Function::iterator BB = F->begin(), E = F->end(); BB != E; ++BB) {
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
if (CallInst *CI = dyn_cast<CallInst>(I)) {
Function *Callee = CI->getCalledFunction();
if (!Callee) {
CVER_DEBUG("\t mayCallCast due to indirect calls\n");
// Indirect call, and we lost the control.
mayCallCast = true;
break;
} else if (Callee->getName() == sCast) {
CVER_DEBUG("\t mayCallCast due to explicit __cver_handle_cast\n");
mayCallCast = true;
break;
}
}
} // End of I loop.
if (mayCallCast)
break;
} // End of BB loop.
}
bool isModified = false;
SmallVector<Instruction *, 16> InstToDelete;
// If there must not exist __stack_handle_cast, we prune all
// __cver_handle_stack_enter and __cver_handle_stack_exit in SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F)
continue;
if (!mayCallCast)
isModified = CollectStackInvokeInstructions(F, InstToDelete);
}
for (Instruction *inst : InstToDelete) {
CVER_DEBUG( "(prunning) : " << *inst << "\n");
inst->eraseFromParent();
}
return isModified;
}
bool CverPruneStack::PruneWithDepthFirstSearch(CallGraphSCC &SCC) {
bool isModified = false;
SmallPtrSet<CallGraphNode *, 8> SCCNodes;
CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
SmallVector<Instruction *, 16> InstToDelete;
CVER_DEBUG("-----------------------------------\n");
// First, check each function whether it has static_cast.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F)
continue;
CVER_DEBUG("[*] F : " << F->getName() << "\n");
// This function does not invoke stack_enter or stack_exit, so not our
// interests.
if (!IsInvokeStack(F, CG)) {
CVER_DEBUG("\t Skip " << F->getName() << "as there's no stack funcs\n");
NumNonPrunned++;
continue;
}
SmallSet<Function *, 32> Visited;
bool mayCast = IsAnyCallesInvokeCast(F, CG, Visited, 0);
CVER_DEBUG("\t mayCast : " << mayCast << "\n");
if (!mayCast) {
// Implies all of callees of this function never invoke
// __cver_handle_cast.
CollectStackInvokeInstructions(F, InstToDelete);
NumPrunned++;
isModified = true;
} else {
NumNonPrunned++;
}
}
for (Instruction *inst : InstToDelete) {
CVER_DEBUG( "(prunning) : " << *inst << "\n");
inst->eraseFromParent();
}
return isModified;
}
bool PostOrderFunctionAttrsLegacyPass::runOnSCC(CallGraphSCC &SCC) {
TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
bool Changed = false;
// We compute dedicated AA results for each function in the SCC as needed. We
// use a lambda referencing external objects so that they live long enough to
// be queried, but we re-use them each time.
Optional<BasicAAResult> BAR;
Optional<AAResults> AAR;
auto AARGetter = [&](Function &F) -> AAResults & {
BAR.emplace(createLegacyPMBasicAAResult(*this, F));
AAR.emplace(createLegacyPMAAResults(*this, F, *BAR));
return *AAR;
};
// Fill SCCNodes with the elements of the SCC. Used for quickly looking up
// whether a given CallGraphNode is in this SCC. Also track whether there are
// any external or opt-none nodes that will prevent us from optimizing any
// part of the SCC.
SCCNodeSet SCCNodes;
bool ExternalNode = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F || F->hasFnAttribute(Attribute::OptimizeNone)) {
// External node or function we're trying not to optimize - we both avoid
// transform them and avoid leveraging information they provide.
ExternalNode = true;
continue;
}
SCCNodes.insert(F);
}
Changed |= addReadAttrs(SCCNodes, AARGetter);
Changed |= addArgumentAttrs(SCCNodes);
// If we have no external nodes participating in the SCC, we can deduce some
// more precise attributes as well.
if (!ExternalNode) {
Changed |= addNoAliasAttrs(SCCNodes);
Changed |= addNonNullAttrs(SCCNodes, *TLI);
Changed |= removeConvergentAttrs(SCCNodes);
Changed |= addNoRecurseAttrs(SCCNodes);
}
return Changed;
}
/// Scan the functions in the specified CFG and resync the
/// callgraph with the call sites found in it. This is used after
/// FunctionPasses have potentially munged the callgraph, and can be used after
/// CallGraphSCC passes to verify that they correctly updated the callgraph.
///
/// This function returns true if it devirtualized an existing function call,
/// meaning it turned an indirect call into a direct call. This happens when
/// a function pass like GVN optimizes away stuff feeding the indirect call.
/// This never happens in checking mode.
bool CGPassManager::RefreshCallGraph(const CallGraphSCC &CurSCC, CallGraph &CG,
bool CheckingMode) {
DenseMap<Value*, CallGraphNode*> CallSites;
LLVM_DEBUG(dbgs() << "CGSCCPASSMGR: Refreshing SCC with " << CurSCC.size()
<< " nodes:\n";
for (CallGraphNode *CGN
: CurSCC) CGN->dump(););
bool ArgPromotion::runOnSCC(CallGraphSCC &SCC) {
bool Changed = false, LocalChange;
do { // Iterate until we stop promoting from this SCC.
LocalChange = false;
// Attempt to promote arguments from all functions in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
if (CallGraphNode *CGN = PromoteArguments(*I)) {
LocalChange = true;
SCC.ReplaceNode(*I, CGN);
}
}
Changed |= LocalChange; // Remember that we changed something.
} while (LocalChange);
return Changed;
}
// Rebuild CGN after we extracted parts of the code from ParentFunc into
// NewFuncs. Builds CGNs for the NewFuncs and adds them to the current SCC.
void coro::updateCallGraph(Function &ParentFunc, ArrayRef<Function *> NewFuncs,
CallGraph &CG, CallGraphSCC &SCC) {
// Rebuild CGN from scratch for the ParentFunc
auto *ParentNode = CG[&ParentFunc];
ParentNode->removeAllCalledFunctions();
buildCGN(CG, ParentNode);
SmallVector<CallGraphNode *, 8> Nodes(SCC.begin(), SCC.end());
for (Function *F : NewFuncs) {
CallGraphNode *Callee = CG.getOrInsertFunction(F);
Nodes.push_back(Callee);
buildCGN(CG, Callee);
}
SCC.initialize(Nodes);
}
bool ArgPromotion::runOnSCC(CallGraphSCC &SCC) {
bool Changed = false, LocalChange;
DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
DL = DLP ? &DLP->getDataLayout() : nullptr;
do { // Iterate until we stop promoting from this SCC.
LocalChange = false;
// Attempt to promote arguments from all functions in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
if (CallGraphNode *CGN = PromoteArguments(*I)) {
LocalChange = true;
SCC.ReplaceNode(*I, CGN);
}
}
Changed |= LocalChange; // Remember that we changed something.
} while (LocalChange);
return Changed;
}
// Make sure that there is a devirtualization trigger function that CoroSplit
// pass uses the force restart CGSCC pipeline. If devirt trigger function is not
// found, we will create one and add it to the current SCC.
static void createDevirtTriggerFunc(CallGraph &CG, CallGraphSCC &SCC) {
Module &M = CG.getModule();
if (M.getFunction(CORO_DEVIRT_TRIGGER_FN))
return;
LLVMContext &C = M.getContext();
auto *FnTy = FunctionType::get(Type::getVoidTy(C), Type::getInt8PtrTy(C),
/*IsVarArgs=*/false);
Function *DevirtFn =
Function::Create(FnTy, GlobalValue::LinkageTypes::PrivateLinkage,
CORO_DEVIRT_TRIGGER_FN, &M);
DevirtFn->addFnAttr(Attribute::AlwaysInline);
auto *Entry = BasicBlock::Create(C, "entry", DevirtFn);
ReturnInst::Create(C, Entry);
auto *Node = CG.getOrInsertFunction(DevirtFn);
SmallVector<CallGraphNode *, 8> Nodes(SCC.begin(), SCC.end());
Nodes.push_back(Node);
SCC.initialize(Nodes);
}
bool ArgPromotion::runOnSCC(CallGraphSCC &SCC) {
if (skipSCC(SCC))
return false;
// Get the callgraph information that we need to update to reflect our
// changes.
CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
LegacyAARGetter AARGetter(*this);
bool Changed = false, LocalChange;
// Iterate until we stop promoting from this SCC.
do {
LocalChange = false;
// Attempt to promote arguments from all functions in this SCC.
for (CallGraphNode *OldNode : SCC) {
Function *OldF = OldNode->getFunction();
if (!OldF)
continue;
auto ReplaceCallSite = [&](CallSite OldCS, CallSite NewCS) {
Function *Caller = OldCS.getInstruction()->getParent()->getParent();
CallGraphNode *NewCalleeNode =
CG.getOrInsertFunction(NewCS.getCalledFunction());
CallGraphNode *CallerNode = CG[Caller];
CallerNode->replaceCallEdge(OldCS, NewCS, NewCalleeNode);
};
if (Function *NewF = promoteArguments(OldF, AARGetter, MaxElements,
{ReplaceCallSite})) {
LocalChange = true;
// Update the call graph for the newly promoted function.
CallGraphNode *NewNode = CG.getOrInsertFunction(NewF);
NewNode->stealCalledFunctionsFrom(OldNode);
if (OldNode->getNumReferences() == 0)
delete CG.removeFunctionFromModule(OldNode);
else
OldF->setLinkage(Function::ExternalLinkage);
// And updat ethe SCC we're iterating as well.
SCC.ReplaceNode(OldNode, NewNode);
}
}
// Remember that we changed something.
Changed |= LocalChange;
} while (LocalChange);
return Changed;
}
static bool runImpl(CallGraphSCC &SCC, CallGraph &CG,
function_ref<AAResults &(Function &F)> AARGetter,
unsigned MaxElements) {
bool Changed = false, LocalChange;
do { // Iterate until we stop promoting from this SCC.
LocalChange = false;
// Attempt to promote arguments from all functions in this SCC.
for (CallGraphNode *OldNode : SCC) {
if (CallGraphNode *NewNode =
PromoteArguments(OldNode, CG, AARGetter, MaxElements)) {
LocalChange = true;
SCC.ReplaceNode(OldNode, NewNode);
}
}
Changed |= LocalChange; // Remember that we changed something.
} while (LocalChange);
return Changed;
}
/// AddNoAliasAttrs - Deduce noalias attributes for the SCC.
bool FunctionAttrs::AddNoAliasAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function*, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
// Check each function in turn, determining which functions return noalias
// pointers.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0)
// External node - skip it;
return false;
// Already noalias.
if (F->doesNotAlias(0))
continue;
// Definitions with weak linkage may be overridden at linktime, so
// treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
return false;
// We annotate noalias return values, which are only applicable to
// pointer types.
if (!F->getReturnType()->isPointerTy())
continue;
if (!IsFunctionMallocLike(F, SCCNodes))
return false;
}
bool MadeChange = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->doesNotAlias(0) || !F->getReturnType()->isPointerTy())
continue;
F->setDoesNotAlias(0);
++NumNoAlias;
MadeChange = true;
}
return MadeChange;
}
static bool runImpl(CallGraphSCC &SCC, CallGraph &CG) {
SmallPtrSet<CallGraphNode *, 8> SCCNodes;
bool MadeChange = false;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphNode *I : SCC)
SCCNodes.insert(I);
// First pass, scan all of the functions in the SCC, simplifying them
// according to what we know.
for (CallGraphNode *I : SCC)
if (Function *F = I->getFunction())
MadeChange |= SimplifyFunction(F, CG);
// Next, check to see if any callees might throw or if there are any external
// functions in this SCC: if so, we cannot prune any functions in this SCC.
// Definitions that are weak and not declared non-throwing might be
// overridden at linktime with something that throws, so assume that.
// If this SCC includes the unwind instruction, we KNOW it throws, so
// obviously the SCC might throw.
//
bool SCCMightUnwind = false, SCCMightReturn = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end();
(!SCCMightUnwind || !SCCMightReturn) && I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F) {
SCCMightUnwind = true;
SCCMightReturn = true;
} else if (F->isDeclaration() || F->isInterposable()) {
// Note: isInterposable (as opposed to hasExactDefinition) is fine above,
// since we're not inferring new attributes here, but only using existing,
// assumed to be correct, function attributes.
SCCMightUnwind |= !F->doesNotThrow();
SCCMightReturn |= !F->doesNotReturn();
} else {
bool CheckUnwind = !SCCMightUnwind && !F->doesNotThrow();
bool CheckReturn = !SCCMightReturn && !F->doesNotReturn();
// Determine if we should scan for InlineAsm in a naked function as it
// is the only way to return without a ReturnInst. Only do this for
// no-inline functions as functions which may be inlined cannot
// meaningfully return via assembly.
bool CheckReturnViaAsm = CheckReturn &&
F->hasFnAttribute(Attribute::Naked) &&
F->hasFnAttribute(Attribute::NoInline);
if (!CheckUnwind && !CheckReturn)
continue;
for (const BasicBlock &BB : *F) {
const TerminatorInst *TI = BB.getTerminator();
if (CheckUnwind && TI->mayThrow()) {
SCCMightUnwind = true;
} else if (CheckReturn && isa<ReturnInst>(TI)) {
SCCMightReturn = true;
}
for (const Instruction &I : BB) {
if ((!CheckUnwind || SCCMightUnwind) &&
(!CheckReturnViaAsm || SCCMightReturn))
break;
// Check to see if this function performs an unwind or calls an
// unwinding function.
if (CheckUnwind && !SCCMightUnwind && I.mayThrow()) {
bool InstMightUnwind = true;
if (const auto *CI = dyn_cast<CallInst>(&I)) {
if (Function *Callee = CI->getCalledFunction()) {
CallGraphNode *CalleeNode = CG[Callee];
// If the callee is outside our current SCC then we may throw
// because it might. If it is inside, do nothing.
if (SCCNodes.count(CalleeNode) > 0)
InstMightUnwind = false;
}
}
SCCMightUnwind |= InstMightUnwind;
}
if (CheckReturnViaAsm && !SCCMightReturn)
if (auto ICS = ImmutableCallSite(&I))
if (const auto *IA = dyn_cast<InlineAsm>(ICS.getCalledValue()))
if (IA->hasSideEffects())
SCCMightReturn = true;
}
if (SCCMightUnwind && SCCMightReturn)
break;
}
}
}
// If the SCC doesn't unwind or doesn't throw, note this fact.
if (!SCCMightUnwind || !SCCMightReturn)
for (CallGraphNode *I : SCC) {
Function *F = I->getFunction();
if (!SCCMightUnwind && !F->hasFnAttribute(Attribute::NoUnwind)) {
F->addFnAttr(Attribute::NoUnwind);
MadeChange = true;
}
if (!SCCMightReturn && !F->hasFnAttribute(Attribute::NoReturn)) {
F->addFnAttr(Attribute::NoReturn);
MadeChange = true;
}
}
for (CallGraphNode *I : SCC) {
// Convert any invoke instructions to non-throwing functions in this node
// into call instructions with a branch. This makes the exception blocks
// dead.
if (Function *F = I->getFunction())
MadeChange |= SimplifyFunction(F, CG);
}
return MadeChange;
}
bool PruneEH::runOnSCC(CallGraphSCC &SCC) {
SmallPtrSet<CallGraphNode *, 8> SCCNodes;
CallGraph &CG = getAnalysis<CallGraph>();
bool MadeChange = false;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert(*I);
// First pass, scan all of the functions in the SCC, simplifying them
// according to what we know.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
if (Function *F = (*I)->getFunction())
MadeChange |= SimplifyFunction(F);
// Next, check to see if any callees might throw or if there are any external
// functions in this SCC: if so, we cannot prune any functions in this SCC.
// Definitions that are weak and not declared non-throwing might be
// overridden at linktime with something that throws, so assume that.
// If this SCC includes the unwind instruction, we KNOW it throws, so
// obviously the SCC might throw.
//
bool SCCMightUnwind = false, SCCMightReturn = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end();
(!SCCMightUnwind || !SCCMightReturn) && I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0) {
SCCMightUnwind = true;
SCCMightReturn = true;
} else if (F->isDeclaration() || F->mayBeOverridden()) {
SCCMightUnwind |= !F->doesNotThrow();
SCCMightReturn |= !F->doesNotReturn();
} else {
bool CheckUnwind = !SCCMightUnwind && !F->doesNotThrow();
bool CheckReturn = !SCCMightReturn && !F->doesNotReturn();
if (!CheckUnwind && !CheckReturn)
continue;
// Check to see if this function performs an unwind or calls an
// unwinding function.
for (Function::iterator BB = F->begin(), E = F->end(); BB != E; ++BB) {
if (CheckUnwind && isa<ResumeInst>(BB->getTerminator())) {
// Uses unwind / resume!
SCCMightUnwind = true;
} else if (CheckReturn && isa<ReturnInst>(BB->getTerminator())) {
SCCMightReturn = true;
}
// Invoke instructions don't allow unwinding to continue, so we are
// only interested in call instructions.
if (CheckUnwind && !SCCMightUnwind)
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I)
if (CallInst *CI = dyn_cast<CallInst>(I)) {
if (CI->doesNotThrow()) {
// This call cannot throw.
} else if (Function *Callee = CI->getCalledFunction()) {
CallGraphNode *CalleeNode = CG[Callee];
// If the callee is outside our current SCC then we may
// throw because it might.
if (!SCCNodes.count(CalleeNode)) {
SCCMightUnwind = true;
break;
}
} else {
// Indirect call, it might throw.
SCCMightUnwind = true;
break;
}
}
if (SCCMightUnwind && SCCMightReturn) break;
}
}
}
// If the SCC doesn't unwind or doesn't throw, note this fact.
if (!SCCMightUnwind || !SCCMightReturn)
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
AttrBuilder NewAttributes;
if (!SCCMightUnwind)
NewAttributes.addAttribute(Attributes::NoUnwind);
if (!SCCMightReturn)
NewAttributes.addAttribute(Attributes::NoReturn);
Function *F = (*I)->getFunction();
const AttributeSet &PAL = F->getAttributes();
const AttributeSet &NPAL = PAL.addAttr(F->getContext(), ~0,
Attributes::get(F->getContext(),
NewAttributes));
if (PAL != NPAL) {
MadeChange = true;
F->setAttributes(NPAL);
}
}
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
// Convert any invoke instructions to non-throwing functions in this node
// into call instructions with a branch. This makes the exception blocks
// dead.
if (Function *F = (*I)->getFunction())
MadeChange |= SimplifyFunction(F);
}
return MadeChange;
}
bool Inliner::runOnSCC(CallGraphSCC &SCC) {
CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
AssumptionCacheTracker *ACT = &getAnalysis<AssumptionCacheTracker>();
auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
const TargetLibraryInfo *TLI = TLIP ? &TLIP->getTLI() : nullptr;
AliasAnalysis *AA = &getAnalysis<AliasAnalysis>();
SmallPtrSet<Function*, 8> SCCFunctions;
DEBUG(dbgs() << "Inliner visiting SCC:");
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F) SCCFunctions.insert(F);
DEBUG(dbgs() << " " << (F ? F->getName() : "INDIRECTNODE"));
}
// Scan through and identify all call sites ahead of time so that we only
// inline call sites in the original functions, not call sites that result
// from inlining other functions.
SmallVector<std::pair<CallSite, int>, 16> CallSites;
// When inlining a callee produces new call sites, we want to keep track of
// the fact that they were inlined from the callee. This allows us to avoid
// infinite inlining in some obscure cases. To represent this, we use an
// index into the InlineHistory vector.
SmallVector<std::pair<Function*, int>, 8> InlineHistory;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F) continue;
for (Function::iterator BB = F->begin(), E = F->end(); BB != E; ++BB)
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
CallSite CS(cast<Value>(I));
// If this isn't a call, or it is a call to an intrinsic, it can
// never be inlined.
if (!CS || isa<IntrinsicInst>(I))
continue;
// If this is a direct call to an external function, we can never inline
// it. If it is an indirect call, inlining may resolve it to be a
// direct call, so we keep it.
if (CS.getCalledFunction() && CS.getCalledFunction()->isDeclaration())
continue;
CallSites.push_back(std::make_pair(CS, -1));
}
}
DEBUG(dbgs() << ": " << CallSites.size() << " call sites.\n");
// If there are no calls in this function, exit early.
if (CallSites.empty())
return false;
// Now that we have all of the call sites, move the ones to functions in the
// current SCC to the end of the list.
unsigned FirstCallInSCC = CallSites.size();
for (unsigned i = 0; i < FirstCallInSCC; ++i)
if (Function *F = CallSites[i].first.getCalledFunction())
if (SCCFunctions.count(F))
std::swap(CallSites[i--], CallSites[--FirstCallInSCC]);
InlinedArrayAllocasTy InlinedArrayAllocas;
InlineFunctionInfo InlineInfo(&CG, AA, ACT);
// Now that we have all of the call sites, loop over them and inline them if
// it looks profitable to do so.
bool Changed = false;
bool LocalChange;
do {
LocalChange = false;
// Iterate over the outer loop because inlining functions can cause indirect
// calls to become direct calls.
for (unsigned CSi = 0; CSi != CallSites.size(); ++CSi) {
CallSite CS = CallSites[CSi].first;
Function *Caller = CS.getCaller();
Function *Callee = CS.getCalledFunction();
// If this call site is dead and it is to a readonly function, we should
// just delete the call instead of trying to inline it, regardless of
// size. This happens because IPSCCP propagates the result out of the
// call and then we're left with the dead call.
if (isInstructionTriviallyDead(CS.getInstruction(), TLI)) {
DEBUG(dbgs() << " -> Deleting dead call: "
<< *CS.getInstruction() << "\n");
// Update the call graph by deleting the edge from Callee to Caller.
CG[Caller]->removeCallEdgeFor(CS);
CS.getInstruction()->eraseFromParent();
++NumCallsDeleted;
} else {
// We can only inline direct calls to non-declarations.
if (!Callee || Callee->isDeclaration()) continue;
// If this call site was obtained by inlining another function, verify
// that the include path for the function did not include the callee
// itself. If so, we'd be recursively inlining the same function,
// which would provide the same callsites, which would cause us to
// infinitely inline.
int InlineHistoryID = CallSites[CSi].second;
if (InlineHistoryID != -1 &&
InlineHistoryIncludes(Callee, InlineHistoryID, InlineHistory))
continue;
LLVMContext &CallerCtx = Caller->getContext();
// Get DebugLoc to report. CS will be invalid after Inliner.
DebugLoc DLoc = CS.getInstruction()->getDebugLoc();
// If the policy determines that we should inline this function,
// try to do so.
if (!shouldInline(CS)) {
emitOptimizationRemarkMissed(CallerCtx, DEBUG_TYPE, *Caller, DLoc,
Twine(Callee->getName() +
" will not be inlined into " +
Caller->getName()));
continue;
}
// Attempt to inline the function.
if (!InlineCallIfPossible(CS, InlineInfo, InlinedArrayAllocas,
InlineHistoryID, InsertLifetime)) {
emitOptimizationRemarkMissed(CallerCtx, DEBUG_TYPE, *Caller, DLoc,
Twine(Callee->getName() +
" will not be inlined into " +
Caller->getName()));
continue;
}
++NumInlined;
// Report the inline decision.
emitOptimizationRemark(
CallerCtx, DEBUG_TYPE, *Caller, DLoc,
Twine(Callee->getName() + " inlined into " + Caller->getName()));
// If inlining this function gave us any new call sites, throw them
// onto our worklist to process. They are useful inline candidates.
if (!InlineInfo.InlinedCalls.empty()) {
// Create a new inline history entry for this, so that we remember
// that these new callsites came about due to inlining Callee.
int NewHistoryID = InlineHistory.size();
InlineHistory.push_back(std::make_pair(Callee, InlineHistoryID));
for (unsigned i = 0, e = InlineInfo.InlinedCalls.size();
i != e; ++i) {
Value *Ptr = InlineInfo.InlinedCalls[i];
CallSites.push_back(std::make_pair(CallSite(Ptr), NewHistoryID));
}
}
}
// If we inlined or deleted the last possible call site to the function,
// delete the function body now.
if (Callee && Callee->use_empty() && Callee->hasLocalLinkage() &&
// TODO: Can remove if in SCC now.
!SCCFunctions.count(Callee) &&
// The function may be apparently dead, but if there are indirect
// callgraph references to the node, we cannot delete it yet, this
// could invalidate the CGSCC iterator.
CG[Callee]->getNumReferences() == 0) {
DEBUG(dbgs() << " -> Deleting dead function: "
<< Callee->getName() << "\n");
CallGraphNode *CalleeNode = CG[Callee];
// Remove any call graph edges from the callee to its callees.
CalleeNode->removeAllCalledFunctions();
// Removing the node for callee from the call graph and delete it.
delete CG.removeFunctionFromModule(CalleeNode);
++NumDeleted;
}
// Remove this call site from the list. If possible, use
// swap/pop_back for efficiency, but do not use it if doing so would
// move a call site to a function in this SCC before the
// 'FirstCallInSCC' barrier.
if (SCC.isSingular()) {
CallSites[CSi] = CallSites.back();
CallSites.pop_back();
} else {
CallSites.erase(CallSites.begin()+CSi);
}
--CSi;
Changed = true;
LocalChange = true;
}
} while (LocalChange);
return Changed;
}
/// AddReadAttrs - Deduce readonly/readnone attributes for the SCC.
bool FunctionAttrs::AddReadAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function*, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
// Check if any of the functions in the SCC read or write memory. If they
// write memory then they can't be marked readnone or readonly.
bool ReadsMemory = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0)
// External node - may write memory. Just give up.
return false;
if (F->doesNotAccessMemory())
// Already perfect!
continue;
// Definitions with weak linkage may be overridden at linktime with
// something that writes memory, so treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden()) {
if (!F->onlyReadsMemory())
// May write memory. Just give up.
return false;
ReadsMemory = true;
continue;
}
// Scan the function body for instructions that may read or write memory.
for (inst_iterator II = inst_begin(F), E = inst_end(F); II != E; ++II) {
Instruction *I = &*II;
// Some instructions can be ignored even if they read or write memory.
// Detect these now, skipping to the next instruction if one is found.
CallSite CS = CallSite::get(I);
if (CS.getInstruction() && CS.getCalledFunction()) {
// Ignore calls to functions in the same SCC.
if (SCCNodes.count(CS.getCalledFunction()))
continue;
// Ignore intrinsics that only access local memory.
if (unsigned id = CS.getCalledFunction()->getIntrinsicID())
if (AliasAnalysis::getModRefBehavior(id) ==
AliasAnalysis::AccessesArguments) {
// Check that all pointer arguments point to local memory.
for (CallSite::arg_iterator CI = CS.arg_begin(), CE = CS.arg_end();
CI != CE; ++CI) {
Value *Arg = *CI;
if (Arg->getType()->isPointerTy() && !PointsToLocalMemory(Arg))
// Writes memory. Just give up.
return false;
}
// Only reads and writes local memory.
continue;
}
} else if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
// Ignore loads from local memory.
if (PointsToLocalMemory(LI->getPointerOperand()))
continue;
} else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
// Ignore stores to local memory.
if (PointsToLocalMemory(SI->getPointerOperand()))
continue;
}
// Any remaining instructions need to be taken seriously! Check if they
// read or write memory.
if (I->mayWriteToMemory())
// Writes memory. Just give up.
return false;
if (isMalloc(I))
// malloc claims not to write memory! PR3754.
return false;
// If this instruction may read memory, remember that.
ReadsMemory |= I->mayReadFromMemory();
}
}
// Success! Functions in this SCC do not access memory, or only read memory.
// Give them the appropriate attribute.
bool MadeChange = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->doesNotAccessMemory())
// Already perfect!
continue;
if (F->onlyReadsMemory() && ReadsMemory)
// No change.
continue;
MadeChange = true;
// Clear out any existing attributes.
F->removeAttribute(~0, Attribute::ReadOnly | Attribute::ReadNone);
// Add in the new attribute.
F->addAttribute(~0, ReadsMemory? Attribute::ReadOnly : Attribute::ReadNone);
if (ReadsMemory)
++NumReadOnly;
else
++NumReadNone;
}
return MadeChange;
}
static bool
inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
std::function<AssumptionCache &(Function &)> GetAssumptionCache,
ProfileSummaryInfo *PSI, TargetLibraryInfo &TLI,
bool InsertLifetime,
function_ref<InlineCost(CallSite CS)> GetInlineCost,
function_ref<AAResults &(Function &)> AARGetter,
ImportedFunctionsInliningStatistics &ImportedFunctionsStats) {
SmallPtrSet<Function *, 8> SCCFunctions;
LLVM_DEBUG(dbgs() << "Inliner visiting SCC:");
for (CallGraphNode *Node : SCC) {
Function *F = Node->getFunction();
if (F)
SCCFunctions.insert(F);
LLVM_DEBUG(dbgs() << " " << (F ? F->getName() : "INDIRECTNODE"));
}
// Scan through and identify all call sites ahead of time so that we only
// inline call sites in the original functions, not call sites that result
// from inlining other functions.
SmallVector<std::pair<CallSite, int>, 16> CallSites;
// When inlining a callee produces new call sites, we want to keep track of
// the fact that they were inlined from the callee. This allows us to avoid
// infinite inlining in some obscure cases. To represent this, we use an
// index into the InlineHistory vector.
SmallVector<std::pair<Function *, int>, 8> InlineHistory;
for (CallGraphNode *Node : SCC) {
Function *F = Node->getFunction();
if (!F || F->isDeclaration())
continue;
OptimizationRemarkEmitter ORE(F);
for (BasicBlock &BB : *F)
for (Instruction &I : BB) {
CallSite CS(cast<Value>(&I));
// If this isn't a call, or it is a call to an intrinsic, it can
// never be inlined.
if (!CS || isa<IntrinsicInst>(I))
continue;
// If this is a direct call to an external function, we can never inline
// it. If it is an indirect call, inlining may resolve it to be a
// direct call, so we keep it.
if (Function *Callee = CS.getCalledFunction())
if (Callee->isDeclaration()) {
using namespace ore;
ORE.emit([&]() {
return OptimizationRemarkMissed(DEBUG_TYPE, "NoDefinition", &I)
<< NV("Callee", Callee) << " will not be inlined into "
<< NV("Caller", CS.getCaller())
<< " because its definition is unavailable"
<< setIsVerbose();
});
continue;
}
CallSites.push_back(std::make_pair(CS, -1));
}
}
LLVM_DEBUG(dbgs() << ": " << CallSites.size() << " call sites.\n");
// If there are no calls in this function, exit early.
if (CallSites.empty())
return false;
// Now that we have all of the call sites, move the ones to functions in the
// current SCC to the end of the list.
unsigned FirstCallInSCC = CallSites.size();
for (unsigned i = 0; i < FirstCallInSCC; ++i)
if (Function *F = CallSites[i].first.getCalledFunction())
if (SCCFunctions.count(F))
std::swap(CallSites[i--], CallSites[--FirstCallInSCC]);
InlinedArrayAllocasTy InlinedArrayAllocas;
InlineFunctionInfo InlineInfo(&CG, &GetAssumptionCache, PSI);
// Now that we have all of the call sites, loop over them and inline them if
// it looks profitable to do so.
bool Changed = false;
bool LocalChange;
do {
LocalChange = false;
// Iterate over the outer loop because inlining functions can cause indirect
// calls to become direct calls.
// CallSites may be modified inside so ranged for loop can not be used.
for (unsigned CSi = 0; CSi != CallSites.size(); ++CSi) {
CallSite CS = CallSites[CSi].first;
Function *Caller = CS.getCaller();
Function *Callee = CS.getCalledFunction();
// We can only inline direct calls to non-declarations.
if (!Callee || Callee->isDeclaration())
continue;
Instruction *Instr = CS.getInstruction();
bool IsTriviallyDead = isInstructionTriviallyDead(Instr, &TLI);
int InlineHistoryID;
if (!IsTriviallyDead) {
// If this call site was obtained by inlining another function, verify
// that the include path for the function did not include the callee
// itself. If so, we'd be recursively inlining the same function,
// which would provide the same callsites, which would cause us to
// infinitely inline.
InlineHistoryID = CallSites[CSi].second;
if (InlineHistoryID != -1 &&
InlineHistoryIncludes(Callee, InlineHistoryID, InlineHistory))
continue;
}
// FIXME for new PM: because of the old PM we currently generate ORE and
// in turn BFI on demand. With the new PM, the ORE dependency should
// just become a regular analysis dependency.
OptimizationRemarkEmitter ORE(Caller);
Optional<InlineCost> OIC = shouldInline(CS, GetInlineCost, ORE);
// If the policy determines that we should inline this function,
// delete the call instead.
if (!OIC)
continue;
// If this call site is dead and it is to a readonly function, we should
// just delete the call instead of trying to inline it, regardless of
// size. This happens because IPSCCP propagates the result out of the
// call and then we're left with the dead call.
if (IsTriviallyDead) {
LLVM_DEBUG(dbgs() << " -> Deleting dead call: " << *Instr << "\n");
// Update the call graph by deleting the edge from Callee to Caller.
CG[Caller]->removeCallEdgeFor(CS);
Instr->eraseFromParent();
++NumCallsDeleted;
} else {
// Get DebugLoc to report. CS will be invalid after Inliner.
DebugLoc DLoc = CS->getDebugLoc();
BasicBlock *Block = CS.getParent();
// Attempt to inline the function.
using namespace ore;
if (!InlineCallIfPossible(CS, InlineInfo, InlinedArrayAllocas,
InlineHistoryID, InsertLifetime, AARGetter,
ImportedFunctionsStats)) {
ORE.emit([&]() {
return OptimizationRemarkMissed(DEBUG_TYPE, "NotInlined", DLoc,
Block)
<< NV("Callee", Callee) << " will not be inlined into "
<< NV("Caller", Caller);
});
continue;
}
++NumInlined;
ORE.emit([&]() {
bool AlwaysInline = OIC->isAlways();
StringRef RemarkName = AlwaysInline ? "AlwaysInline" : "Inlined";
OptimizationRemark R(DEBUG_TYPE, RemarkName, DLoc, Block);
R << NV("Callee", Callee) << " inlined into ";
R << NV("Caller", Caller);
if (AlwaysInline)
R << " with cost=always";
else {
R << " with cost=" << NV("Cost", OIC->getCost());
R << " (threshold=" << NV("Threshold", OIC->getThreshold());
R << ")";
}
return R;
});
// If inlining this function gave us any new call sites, throw them
// onto our worklist to process. They are useful inline candidates.
if (!InlineInfo.InlinedCalls.empty()) {
// Create a new inline history entry for this, so that we remember
// that these new callsites came about due to inlining Callee.
int NewHistoryID = InlineHistory.size();
InlineHistory.push_back(std::make_pair(Callee, InlineHistoryID));
for (Value *Ptr : InlineInfo.InlinedCalls)
CallSites.push_back(std::make_pair(CallSite(Ptr), NewHistoryID));
}
}
// If we inlined or deleted the last possible call site to the function,
// delete the function body now.
if (Callee && Callee->use_empty() && Callee->hasLocalLinkage() &&
// TODO: Can remove if in SCC now.
!SCCFunctions.count(Callee) &&
// The function may be apparently dead, but if there are indirect
// callgraph references to the node, we cannot delete it yet, this
// could invalidate the CGSCC iterator.
CG[Callee]->getNumReferences() == 0) {
LLVM_DEBUG(dbgs() << " -> Deleting dead function: "
<< Callee->getName() << "\n");
CallGraphNode *CalleeNode = CG[Callee];
// Remove any call graph edges from the callee to its callees.
CalleeNode->removeAllCalledFunctions();
// Removing the node for callee from the call graph and delete it.
delete CG.removeFunctionFromModule(CalleeNode);
++NumDeleted;
}
// Remove this call site from the list. If possible, use
// swap/pop_back for efficiency, but do not use it if doing so would
// move a call site to a function in this SCC before the
// 'FirstCallInSCC' barrier.
if (SCC.isSingular()) {
CallSites[CSi] = CallSites.back();
CallSites.pop_back();
} else {
CallSites.erase(CallSites.begin() + CSi);
}
--CSi;
Changed = true;
LocalChange = true;
}
} while (LocalChange);
return Changed;
}
/// AddNoCaptureAttrs - Deduce nocapture attributes for the SCC.
bool FunctionAttrs::AddNoCaptureAttrs(const CallGraphSCC &SCC) {
bool Changed = false;
SmallPtrSet<Function*, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F && !F->isDeclaration() && !F->mayBeOverridden())
SCCNodes.insert(F);
}
ArgumentGraph AG;
// Check each function in turn, determining which pointer arguments are not
// captured.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0)
// External node - only a problem for arguments that we pass to it.
continue;
// Definitions with weak linkage may be overridden at linktime with
// something that captures pointers, so treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
continue;
// Functions that are readonly (or readnone) and nounwind and don't return
// a value can't capture arguments. Don't analyze them.
if (F->onlyReadsMemory() && F->doesNotThrow() &&
F->getReturnType()->isVoidTy()) {
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end();
A != E; ++A) {
if (A->getType()->isPointerTy() && !A->hasNoCaptureAttr()) {
A->addAttr(Attribute::NoCapture);
++NumNoCapture;
Changed = true;
}
}
continue;
}
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end(); A!=E; ++A)
if (A->getType()->isPointerTy() && !A->hasNoCaptureAttr()) {
ArgumentUsesTracker Tracker(SCCNodes);
PointerMayBeCaptured(A, &Tracker);
if (!Tracker.Captured) {
if (Tracker.Uses.empty()) {
// If it's trivially not captured, mark it nocapture now.
A->addAttr(Attribute::NoCapture);
++NumNoCapture;
Changed = true;
} else {
// If it's not trivially captured and not trivially not captured,
// then it must be calling into another function in our SCC. Save
// its particulars for Argument-SCC analysis later.
ArgumentGraphNode *Node = AG[A];
for (SmallVectorImpl<Argument*>::iterator UI = Tracker.Uses.begin(),
UE = Tracker.Uses.end(); UI != UE; ++UI)
Node->Uses.push_back(AG[*UI]);
}
}
// Otherwise, it's captured. Don't bother doing SCC analysis on it.
}
}
// The graph we've collected is partial because we stopped scanning for
// argument uses once we solved the argument trivially. These partial nodes
// show up as ArgumentGraphNode objects with an empty Uses list, and for
// these nodes the final decision about whether they capture has already been
// made. If the definition doesn't have a 'nocapture' attribute by now, it
// captures.
for (scc_iterator<ArgumentGraph*> I = scc_begin(&AG), E = scc_end(&AG);
I != E; ++I) {
std::vector<ArgumentGraphNode*> &ArgumentSCC = *I;
if (ArgumentSCC.size() == 1) {
if (!ArgumentSCC[0]->Definition) continue; // synthetic root node
// eg. "void f(int* x) { if (...) f(x); }"
if (ArgumentSCC[0]->Uses.size() == 1 &&
ArgumentSCC[0]->Uses[0] == ArgumentSCC[0]) {
ArgumentSCC[0]->Definition->addAttr(Attribute::NoCapture);
++NumNoCapture;
Changed = true;
}
continue;
}
bool SCCCaptured = false;
for (std::vector<ArgumentGraphNode*>::iterator I = ArgumentSCC.begin(),
E = ArgumentSCC.end(); I != E && !SCCCaptured; ++I) {
ArgumentGraphNode *Node = *I;
if (Node->Uses.empty()) {
if (!Node->Definition->hasNoCaptureAttr())
SCCCaptured = true;
}
}
if (SCCCaptured) continue;
SmallPtrSet<Argument*, 8> ArgumentSCCNodes;
// Fill ArgumentSCCNodes with the elements of the ArgumentSCC. Used for
// quickly looking up whether a given Argument is in this ArgumentSCC.
for (std::vector<ArgumentGraphNode*>::iterator I = ArgumentSCC.begin(),
E = ArgumentSCC.end(); I != E; ++I) {
ArgumentSCCNodes.insert((*I)->Definition);
}
for (std::vector<ArgumentGraphNode*>::iterator I = ArgumentSCC.begin(),
E = ArgumentSCC.end(); I != E && !SCCCaptured; ++I) {
ArgumentGraphNode *N = *I;
for (SmallVectorImpl<ArgumentGraphNode*>::iterator UI = N->Uses.begin(),
UE = N->Uses.end(); UI != UE; ++UI) {
Argument *A = (*UI)->Definition;
if (A->hasNoCaptureAttr() || ArgumentSCCNodes.count(A))
continue;
SCCCaptured = true;
break;
}
}
if (SCCCaptured) continue;
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
A->addAttr(Attribute::NoCapture);
++NumNoCapture;
Changed = true;
}
}
return Changed;
}
/// AddReadAttrs - Deduce readonly/readnone attributes for the SCC.
bool FunctionAttrs::AddReadAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function*, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
// Check if any of the functions in the SCC read or write memory. If they
// write memory then they can't be marked readnone or readonly.
bool ReadsMemory = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F == 0)
// External node - may write memory. Just give up.
return false;
AliasAnalysis::ModRefBehavior MRB = AA->getModRefBehavior(F);
if (MRB == AliasAnalysis::DoesNotAccessMemory)
// Already perfect!
continue;
// Definitions with weak linkage may be overridden at linktime with
// something that writes memory, so treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden()) {
if (!AliasAnalysis::onlyReadsMemory(MRB))
// May write memory. Just give up.
return false;
ReadsMemory = true;
continue;
}
// Scan the function body for instructions that may read or write memory.
for (inst_iterator II = inst_begin(F), E = inst_end(F); II != E; ++II) {
Instruction *I = &*II;
// Some instructions can be ignored even if they read or write memory.
// Detect these now, skipping to the next instruction if one is found.
CallSite CS(cast<Value>(I));
if (CS) {
// Ignore calls to functions in the same SCC.
if (CS.getCalledFunction() && SCCNodes.count(CS.getCalledFunction()))
continue;
AliasAnalysis::ModRefBehavior MRB = AA->getModRefBehavior(CS);
// If the call doesn't access arbitrary memory, we may be able to
// figure out something.
if (AliasAnalysis::onlyAccessesArgPointees(MRB)) {
// If the call does access argument pointees, check each argument.
if (AliasAnalysis::doesAccessArgPointees(MRB))
// Check whether all pointer arguments point to local memory, and
// ignore calls that only access local memory.
for (CallSite::arg_iterator CI = CS.arg_begin(), CE = CS.arg_end();
CI != CE; ++CI) {
Value *Arg = *CI;
if (Arg->getType()->isPointerTy()) {
AliasAnalysis::Location Loc(Arg,
AliasAnalysis::UnknownSize,
I->getMetadata(LLVMContext::MD_tbaa));
if (!AA->pointsToConstantMemory(Loc, /*OrLocal=*/true)) {
if (MRB & AliasAnalysis::Mod)
// Writes non-local memory. Give up.
return false;
if (MRB & AliasAnalysis::Ref)
// Ok, it reads non-local memory.
ReadsMemory = true;
}
}
}
continue;
}
// The call could access any memory. If that includes writes, give up.
if (MRB & AliasAnalysis::Mod)
return false;
// If it reads, note it.
if (MRB & AliasAnalysis::Ref)
ReadsMemory = true;
continue;
} else if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
// Ignore non-volatile loads from local memory. (Atomic is okay here.)
if (!LI->isVolatile()) {
AliasAnalysis::Location Loc = AA->getLocation(LI);
if (AA->pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
} else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
// Ignore non-volatile stores to local memory. (Atomic is okay here.)
if (!SI->isVolatile()) {
AliasAnalysis::Location Loc = AA->getLocation(SI);
if (AA->pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
} else if (VAArgInst *VI = dyn_cast<VAArgInst>(I)) {
// Ignore vaargs on local memory.
AliasAnalysis::Location Loc = AA->getLocation(VI);
if (AA->pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
// Any remaining instructions need to be taken seriously! Check if they
// read or write memory.
if (I->mayWriteToMemory())
// Writes memory. Just give up.
return false;
// If this instruction may read memory, remember that.
ReadsMemory |= I->mayReadFromMemory();
}
}
// Success! Functions in this SCC do not access memory, or only read memory.
// Give them the appropriate attribute.
bool MadeChange = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->doesNotAccessMemory())
// Already perfect!
continue;
if (F->onlyReadsMemory() && ReadsMemory)
// No change.
continue;
MadeChange = true;
// Clear out any existing attributes.
F->removeAttribute(~0, Attribute::ReadOnly | Attribute::ReadNone);
// Add in the new attribute.
F->addAttribute(~0, ReadsMemory? Attribute::ReadOnly : Attribute::ReadNone);
if (ReadsMemory)
++NumReadOnly;
else
++NumReadNone;
}
return MadeChange;
}
