/// RemoveDeadArgumentsFromCallers - Checks if the given function has any
/// arguments that are unused, and changes the caller parameters to be undefined
/// instead.
bool DAE::RemoveDeadArgumentsFromCallers(Function &Fn)
{
if (Fn.isDeclaration() || Fn.mayBeOverridden())
return false;
// Functions with local linkage should already have been handled, except the
// fragile (variadic) ones which we can improve here.
if (Fn.hasLocalLinkage() && !Fn.getFunctionType()->isVarArg())
return false;
// If a function seen at compile time is not necessarily the one linked to
// the binary being built, it is illegal to change the actual arguments
// passed to it. These functions can be captured by isWeakForLinker().
// *NOTE* that mayBeOverridden() is insufficient for this purpose as it
// doesn't include linkage types like AvailableExternallyLinkage and
// LinkOnceODRLinkage. Take link_odr* as an example, it indicates a set of
// *EQUIVALENT* globals that can be merged at link-time. However, the
// semantic of *EQUIVALENT*-functions includes parameters. Changing
// parameters breaks this assumption.
//
if (Fn.isWeakForLinker())
return false;
if (Fn.use_empty())
return false;
SmallVector<unsigned, 8> UnusedArgs;
for (Function::arg_iterator I = Fn.arg_begin(), E = Fn.arg_end();
I != E; ++I) {
Argument *Arg = I;
if (Arg->use_empty() && !Arg->hasByValOrInAllocaAttr())
UnusedArgs.push_back(Arg->getArgNo());
}
if (UnusedArgs.empty())
return false;
bool Changed = false;
for (Use &U : Fn.uses()) {
CallSite CS(U.getUser());
if (!CS || !CS.isCallee(&U))
continue;
// Now go through all unused args and replace them with "undef".
for (unsigned I = 0, E = UnusedArgs.size(); I != E; ++I) {
unsigned ArgNo = UnusedArgs[I];
Value *Arg = CS.getArgument(ArgNo);
CS.setArgument(ArgNo, UndefValue::get(Arg->getType()));
++NumArgumentsReplacedWithUndef;
Changed = true;
}
}
return Changed;
}
/// RemoveDeadArgumentsFromCallers - Checks if the given function has any
/// arguments that are unused, and changes the caller parameters to be undefined
/// instead.
bool DAE::RemoveDeadArgumentsFromCallers(Function &Fn)
{
if (Fn.isDeclaration() || Fn.mayBeOverridden())
return false;
// Functions with local linkage should already have been handled, except the
// fragile (variadic) ones which we can improve here.
if (Fn.hasLocalLinkage() && !Fn.getFunctionType()->isVarArg())
return false;
if (Fn.use_empty())
return false;
SmallVector<unsigned, 8> UnusedArgs;
for (Function::arg_iterator I = Fn.arg_begin(), E = Fn.arg_end();
I != E; ++I) {
Argument *Arg = I;
if (Arg->use_empty() && !Arg->hasByValAttr())
UnusedArgs.push_back(Arg->getArgNo());
}
if (UnusedArgs.empty())
return false;
bool Changed = false;
for (Function::use_iterator I = Fn.use_begin(), E = Fn.use_end();
I != E; ++I) {
CallSite CS(*I);
if (!CS || !CS.isCallee(I))
continue;
// Now go through all unused args and replace them with "undef".
for (unsigned I = 0, E = UnusedArgs.size(); I != E; ++I) {
unsigned ArgNo = UnusedArgs[I];
Value *Arg = CS.getArgument(ArgNo);
CS.setArgument(ArgNo, UndefValue::get(Arg->getType()));
++NumArgumentsReplacedWithUndef;
Changed = true;
}
}
return Changed;
}
/// PromoteArguments - This method checks the specified function to see if there
/// are any promotable arguments and if it is safe to promote the function (for
/// example, all callers are direct). If safe to promote some arguments, it
/// calls the DoPromotion method.
///
CallGraphNode *ArgPromotion::PromoteArguments(CallGraphNode *CGN) {
Function *F = CGN->getFunction();
// Make sure that it is local to this module.
if (!F || !F->hasLocalLinkage()) return nullptr;
// Don't promote arguments for variadic functions. Adding, removing, or
// changing non-pack parameters can change the classification of pack
// parameters. Frontends encode that classification at the call site in the
// IR, while in the callee the classification is determined dynamically based
// on the number of registers consumed so far.
if (F->isVarArg()) return nullptr;
// First check: see if there are any pointer arguments! If not, quick exit.
SmallVector<Argument*, 16> PointerArgs;
for (Argument &I : F->args())
if (I.getType()->isPointerTy())
PointerArgs.push_back(&I);
if (PointerArgs.empty()) return nullptr;
// Second check: make sure that all callers are direct callers. We can't
// transform functions that have indirect callers. Also see if the function
// is self-recursive.
bool isSelfRecursive = false;
for (Use &U : F->uses()) {
CallSite CS(U.getUser());
// Must be a direct call.
if (CS.getInstruction() == nullptr || !CS.isCallee(&U)) return nullptr;
if (CS.getInstruction()->getParent()->getParent() == F)
isSelfRecursive = true;
}
const DataLayout &DL = F->getParent()->getDataLayout();
// We need to manually construct BasicAA directly in order to disable its use
// of other function analyses.
BasicAAResult BAR(createLegacyPMBasicAAResult(*this, *F));
// Construct our own AA results for this function. We do this manually to
// work around the limitations of the legacy pass manager.
AAResults AAR(createLegacyPMAAResults(*this, *F, BAR));
// Check to see which arguments are promotable. If an argument is promotable,
// add it to ArgsToPromote.
SmallPtrSet<Argument*, 8> ArgsToPromote;
SmallPtrSet<Argument*, 8> ByValArgsToTransform;
for (unsigned i = 0, e = PointerArgs.size(); i != e; ++i) {
Argument *PtrArg = PointerArgs[i];
Type *AgTy = cast<PointerType>(PtrArg->getType())->getElementType();
// Replace sret attribute with noalias. This reduces register pressure by
// avoiding a register copy.
if (PtrArg->hasStructRetAttr()) {
unsigned ArgNo = PtrArg->getArgNo();
F->setAttributes(
F->getAttributes()
.removeAttribute(F->getContext(), ArgNo + 1, Attribute::StructRet)
.addAttribute(F->getContext(), ArgNo + 1, Attribute::NoAlias));
for (Use &U : F->uses()) {
CallSite CS(U.getUser());
CS.setAttributes(
CS.getAttributes()
.removeAttribute(F->getContext(), ArgNo + 1,
Attribute::StructRet)
.addAttribute(F->getContext(), ArgNo + 1, Attribute::NoAlias));
}
}
// If this is a byval argument, and if the aggregate type is small, just
// pass the elements, which is always safe, if the passed value is densely
// packed or if we can prove the padding bytes are never accessed. This does
// not apply to inalloca.
bool isSafeToPromote =
PtrArg->hasByValAttr() &&
(isDenselyPacked(AgTy, DL) || !canPaddingBeAccessed(PtrArg));
if (isSafeToPromote) {
if (StructType *STy = dyn_cast<StructType>(AgTy)) {
if (maxElements > 0 && STy->getNumElements() > maxElements) {
DEBUG(dbgs() << "argpromotion disable promoting argument '"
<< PtrArg->getName() << "' because it would require adding more"
<< " than " << maxElements << " arguments to the function.\n");
continue;
}
// If all the elements are single-value types, we can promote it.
bool AllSimple = true;
for (const auto *EltTy : STy->elements()) {
if (!EltTy->isSingleValueType()) {
AllSimple = false;
break;
}
}
// Safe to transform, don't even bother trying to "promote" it.
// Passing the elements as a scalar will allow sroa to hack on
// the new alloca we introduce.
if (AllSimple) {
ByValArgsToTransform.insert(PtrArg);
continue;
}
}
}
// If the argument is a recursive type and we're in a recursive
// function, we could end up infinitely peeling the function argument.
if (isSelfRecursive) {
if (StructType *STy = dyn_cast<StructType>(AgTy)) {
bool RecursiveType = false;
for (const auto *EltTy : STy->elements()) {
if (EltTy == PtrArg->getType()) {
RecursiveType = true;
break;
}
}
if (RecursiveType)
continue;
}
}
// Otherwise, see if we can promote the pointer to its value.
if (isSafeToPromoteArgument(PtrArg, PtrArg->hasByValOrInAllocaAttr(), AAR))
ArgsToPromote.insert(PtrArg);
}
// No promotable pointer arguments.
if (ArgsToPromote.empty() && ByValArgsToTransform.empty())
return nullptr;
return DoPromotion(F, ArgsToPromote, ByValArgsToTransform);
}
/// Deduce nocapture attributes for the SCC.
static bool addArgumentAttrs(const SCCNodeSet &SCCNodes) {
bool Changed = false;
ArgumentGraph AG;
AttrBuilder B;
B.addAttribute(Attribute::NoCapture);
// Check each function in turn, determining which pointer arguments are not
// captured.
for (Function *F : SCCNodes) {
// 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(AttributeSet::get(F->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
}
continue;
}
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end(); A != E;
++A) {
if (!A->getType()->isPointerTy())
continue;
bool HasNonLocalUses = false;
if (!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(
AttributeSet::get(F->getContext(), A->getArgNo() + 1, B));
++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]);
if (*UI != A)
HasNonLocalUses = true;
}
}
}
// Otherwise, it's captured. Don't bother doing SCC analysis on it.
}
if (!HasNonLocalUses && !A->onlyReadsMemory()) {
// Can we determine that it's readonly/readnone without doing an SCC?
// Note that we don't allow any calls at all here, or else our result
// will be dependent on the iteration order through the functions in the
// SCC.
SmallPtrSet<Argument *, 8> Self;
Self.insert(&*A);
Attribute::AttrKind R = determinePointerReadAttrs(&*A, Self);
if (R != Attribute::None) {
AttrBuilder B;
B.addAttribute(R);
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
Changed = true;
R == Attribute::ReadOnly ? ++NumReadOnlyArg : ++NumReadNoneArg;
}
}
}
}
// 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); !I.isAtEnd(); ++I) {
const 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]) {
Argument *A = ArgumentSCC[0]->Definition;
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
continue;
}
bool SCCCaptured = false;
for (auto 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 (auto I = ArgumentSCC.begin(), E = ArgumentSCC.end(); I != E; ++I) {
ArgumentSCCNodes.insert((*I)->Definition);
}
for (auto 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(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
// We also want to compute readonly/readnone. With a small number of false
// negatives, we can assume that any pointer which is captured isn't going
// to be provably readonly or readnone, since by definition we can't
// analyze all uses of a captured pointer.
//
// The false negatives happen when the pointer is captured by a function
// that promises readonly/readnone behaviour on the pointer, then the
// pointer's lifetime ends before anything that writes to arbitrary memory.
// Also, a readonly/readnone pointer may be returned, but returning a
// pointer is capturing it.
Attribute::AttrKind ReadAttr = Attribute::ReadNone;
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
Attribute::AttrKind K = determinePointerReadAttrs(A, ArgumentSCCNodes);
if (K == Attribute::ReadNone)
continue;
if (K == Attribute::ReadOnly) {
ReadAttr = Attribute::ReadOnly;
continue;
}
ReadAttr = K;
break;
}
if (ReadAttr != Attribute::None) {
AttrBuilder B, R;
B.addAttribute(ReadAttr);
R.addAttribute(Attribute::ReadOnly).addAttribute(Attribute::ReadNone);
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
// Clear out existing readonly/readnone attributes
A->removeAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, R));
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
ReadAttr == Attribute::ReadOnly ? ++NumReadOnlyArg : ++NumReadNoneArg;
Changed = true;
}
}
}
return Changed;
}
