/// Lower a single value incoming to a statepoint node. This value can be
/// either a deopt value or a gc value, the handling is the same. We special
/// case constants and allocas, then fall back to spilling if required.
static void lowerIncomingStatepointValue(SDValue Incoming, bool LiveInOnly,
SmallVectorImpl<SDValue> &Ops,
SelectionDAGBuilder &Builder) {
SDValue Chain = Builder.getRoot();
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Incoming)) {
// If the original value was a constant, make sure it gets recorded as
// such in the stackmap. This is required so that the consumer can
// parse any internal format to the deopt state. It also handles null
// pointers and other constant pointers in GC states. Note the constant
// vectors do not appear to actually hit this path and that anything larger
// than an i64 value (not type!) will fail asserts here.
pushStackMapConstant(Ops, Builder, C->getSExtValue());
} else if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Incoming)) {
// This handles allocas as arguments to the statepoint (this is only
// really meaningful for a deopt value. For GC, we'd be trying to
// relocate the address of the alloca itself?)
assert(Incoming.getValueType() == Builder.getFrameIndexTy() &&
"Incoming value is a frame index!");
Ops.push_back(Builder.DAG.getTargetFrameIndex(FI->getIndex(),
Builder.getFrameIndexTy()));
} else if (LiveInOnly) {
// If this value is live in (not live-on-return, or live-through), we can
// treat it the same way patchpoint treats it's "live in" values. We'll
// end up folding some of these into stack references, but they'll be
// handled by the register allocator. Note that we do not have the notion
// of a late use so these values might be placed in registers which are
// clobbered by the call. This is fine for live-in.
Ops.push_back(Incoming);
} else {
// Otherwise, locate a spill slot and explicitly spill it so it
// can be found by the runtime later. We currently do not support
// tracking values through callee saved registers to their eventual
// spill location. This would be a useful optimization, but would
// need to be optional since it requires a lot of complexity on the
// runtime side which not all would support.
auto Res = spillIncomingStatepointValue(Incoming, Chain, Builder);
Ops.push_back(Res.first);
Chain = Res.second;
}
Builder.DAG.setRoot(Chain);
}
/// Try to find existing copies of the incoming values in stack slots used for
/// statepoint spilling. If we can find a spill slot for the incoming value,
/// mark that slot as allocated, and reuse the same slot for this safepoint.
/// This helps to avoid series of loads and stores that only serve to reshuffle
/// values on the stack between calls.
static void reservePreviousStackSlotForValue(const Value *IncomingValue,
SelectionDAGBuilder &Builder) {
SDValue Incoming = Builder.getValue(IncomingValue);
if (isa<ConstantSDNode>(Incoming) || isa<FrameIndexSDNode>(Incoming)) {
// We won't need to spill this, so no need to check for previously
// allocated stack slots
return;
}
SDValue OldLocation = Builder.StatepointLowering.getLocation(Incoming);
if (OldLocation.getNode())
// Duplicates in input
return;
const int LookUpDepth = 6;
Optional<int> Index =
findPreviousSpillSlot(IncomingValue, Builder, LookUpDepth);
if (!Index.hasValue())
return;
const auto &StatepointSlots = Builder.FuncInfo.StatepointStackSlots;
auto SlotIt = find(StatepointSlots, *Index);
assert(SlotIt != StatepointSlots.end() &&
"Value spilled to the unknown stack slot");
// This is one of our dedicated lowering slots
const int Offset = std::distance(StatepointSlots.begin(), SlotIt);
if (Builder.StatepointLowering.isStackSlotAllocated(Offset)) {
// stack slot already assigned to someone else, can't use it!
// TODO: currently we reserve space for gc arguments after doing
// normal allocation for deopt arguments. We should reserve for
// _all_ deopt and gc arguments, then start allocating. This
// will prevent some moves being inserted when vm state changes,
// but gc state doesn't between two calls.
return;
}
// Reserve this stack slot
Builder.StatepointLowering.reserveStackSlot(Offset);
// Cache this slot so we find it when going through the normal
// assignment loop.
SDValue Loc =
Builder.DAG.getTargetFrameIndex(*Index, Builder.getFrameIndexTy());
Builder.StatepointLowering.setLocation(Incoming, Loc);
}
/// Spill a value incoming to the statepoint. It might be either part of
/// vmstate
/// or gcstate. In both cases unconditionally spill it on the stack unless it
/// is a null constant. Return pair with first element being frame index
/// containing saved value and second element with outgoing chain from the
/// emitted store
static std::pair<SDValue, SDValue>
spillIncomingStatepointValue(SDValue Incoming, SDValue Chain,
SelectionDAGBuilder &Builder) {
SDValue Loc = Builder.StatepointLowering.getLocation(Incoming);
// Emit new store if we didn't do it for this ptr before
if (!Loc.getNode()) {
Loc = Builder.StatepointLowering.allocateStackSlot(Incoming.getValueType(),
Builder);
int Index = cast<FrameIndexSDNode>(Loc)->getIndex();
// We use TargetFrameIndex so that isel will not select it into LEA
Loc = Builder.DAG.getTargetFrameIndex(Index, Builder.getFrameIndexTy());
// TODO: We can create TokenFactor node instead of
// chaining stores one after another, this may allow
// a bit more optimal scheduling for them
#ifndef NDEBUG
// Right now we always allocate spill slots that are of the same
// size as the value we're about to spill (the size of spillee can
// vary since we spill vectors of pointers too). At some point we
// can consider allowing spills of smaller values to larger slots
// (i.e. change the '==' in the assert below to a '>=').
MachineFrameInfo &MFI = Builder.DAG.getMachineFunction().getFrameInfo();
assert((MFI.getObjectSize(Index) * 8) == Incoming.getValueSizeInBits() &&
"Bad spill: stack slot does not match!");
#endif
Chain = Builder.DAG.getStore(Chain, Builder.getCurSDLoc(), Incoming, Loc,
MachinePointerInfo::getFixedStack(
Builder.DAG.getMachineFunction(), Index));
Builder.StatepointLowering.setLocation(Incoming, Loc);
}
assert(Loc.getNode());
return std::make_pair(Loc, Chain);
}
/// Lower deopt state and gc pointer arguments of the statepoint. The actual
/// lowering is described in lowerIncomingStatepointValue. This function is
/// responsible for lowering everything in the right position and playing some
/// tricks to avoid redundant stack manipulation where possible. On
/// completion, 'Ops' will contain ready to use operands for machine code
/// statepoint. The chain nodes will have already been created and the DAG root
/// will be set to the last value spilled (if any were).
static void
lowerStatepointMetaArgs(SmallVectorImpl<SDValue> &Ops,
SelectionDAGBuilder::StatepointLoweringInfo &SI,
SelectionDAGBuilder &Builder) {
// Lower the deopt and gc arguments for this statepoint. Layout will be:
// deopt argument length, deopt arguments.., gc arguments...
#ifndef NDEBUG
if (auto *GFI = Builder.GFI) {
// Check that each of the gc pointer and bases we've gotten out of the
// safepoint is something the strategy thinks might be a pointer (or vector
// of pointers) into the GC heap. This is basically just here to help catch
// errors during statepoint insertion. TODO: This should actually be in the
// Verifier, but we can't get to the GCStrategy from there (yet).
GCStrategy &S = GFI->getStrategy();
for (const Value *V : SI.Bases) {
auto Opt = S.isGCManagedPointer(V->getType()->getScalarType());
if (Opt.hasValue()) {
assert(Opt.getValue() &&
"non gc managed base pointer found in statepoint");
}
}
for (const Value *V : SI.Ptrs) {
auto Opt = S.isGCManagedPointer(V->getType()->getScalarType());
if (Opt.hasValue()) {
assert(Opt.getValue() &&
"non gc managed derived pointer found in statepoint");
}
}
assert(SI.Bases.size() == SI.Ptrs.size() && "Pointer without base!");
} else {
assert(SI.Bases.empty() && "No gc specified, so cannot relocate pointers!");
assert(SI.Ptrs.empty() && "No gc specified, so cannot relocate pointers!");
}
#endif
// Figure out what lowering strategy we're going to use for each part
// Note: Is is conservatively correct to lower both "live-in" and "live-out"
// as "live-through". A "live-through" variable is one which is "live-in",
// "live-out", and live throughout the lifetime of the call (i.e. we can find
// it from any PC within the transitive callee of the statepoint). In
// particular, if the callee spills callee preserved registers we may not
// be able to find a value placed in that register during the call. This is
// fine for live-out, but not for live-through. If we were willing to make
// assumptions about the code generator producing the callee, we could
// potentially allow live-through values in callee saved registers.
const bool LiveInDeopt =
SI.StatepointFlags & (uint64_t)StatepointFlags::DeoptLiveIn;
auto isGCValue =[&](const Value *V) {
return is_contained(SI.Ptrs, V) || is_contained(SI.Bases, V);
};
// Before we actually start lowering (and allocating spill slots for values),
// reserve any stack slots which we judge to be profitable to reuse for a
// particular value. This is purely an optimization over the code below and
// doesn't change semantics at all. It is important for performance that we
// reserve slots for both deopt and gc values before lowering either.
for (const Value *V : SI.DeoptState) {
if (!LiveInDeopt || isGCValue(V))
reservePreviousStackSlotForValue(V, Builder);
}
for (unsigned i = 0; i < SI.Bases.size(); ++i) {
reservePreviousStackSlotForValue(SI.Bases[i], Builder);
reservePreviousStackSlotForValue(SI.Ptrs[i], Builder);
}
// First, prefix the list with the number of unique values to be
// lowered. Note that this is the number of *Values* not the
// number of SDValues required to lower them.
const int NumVMSArgs = SI.DeoptState.size();
pushStackMapConstant(Ops, Builder, NumVMSArgs);
// The vm state arguments are lowered in an opaque manner. We do not know
// what type of values are contained within.
for (const Value *V : SI.DeoptState) {
SDValue Incoming = Builder.getValue(V);
const bool LiveInValue = LiveInDeopt && !isGCValue(V);
lowerIncomingStatepointValue(Incoming, LiveInValue, Ops, Builder);
}
// Finally, go ahead and lower all the gc arguments. There's no prefixed
// length for this one. After lowering, we'll have the base and pointer
// arrays interwoven with each (lowered) base pointer immediately followed by
// it's (lowered) derived pointer. i.e
// (base[0], ptr[0], base[1], ptr[1], ...)
for (unsigned i = 0; i < SI.Bases.size(); ++i) {
const Value *Base = SI.Bases[i];
lowerIncomingStatepointValue(Builder.getValue(Base), /*LiveInOnly*/ false,
Ops, Builder);
const Value *Ptr = SI.Ptrs[i];
lowerIncomingStatepointValue(Builder.getValue(Ptr), /*LiveInOnly*/ false,
Ops, Builder);
}
// If there are any explicit spill slots passed to the statepoint, record
// them, but otherwise do not do anything special. These are user provided
// allocas and give control over placement to the consumer. In this case,
// it is the contents of the slot which may get updated, not the pointer to
// the alloca
for (Value *V : SI.GCArgs) {
SDValue Incoming = Builder.getValue(V);
if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Incoming)) {
// This handles allocas as arguments to the statepoint
assert(Incoming.getValueType() == Builder.getFrameIndexTy() &&
"Incoming value is a frame index!");
Ops.push_back(Builder.DAG.getTargetFrameIndex(FI->getIndex(),
Builder.getFrameIndexTy()));
}
}
// Record computed locations for all lowered values.
// This can not be embedded in lowering loops as we need to record *all*
// values, while previous loops account only values with unique SDValues.
const Instruction *StatepointInstr = SI.StatepointInstr;
auto &SpillMap = Builder.FuncInfo.StatepointSpillMaps[StatepointInstr];
for (const GCRelocateInst *Relocate : SI.GCRelocates) {
const Value *V = Relocate->getDerivedPtr();
SDValue SDV = Builder.getValue(V);
SDValue Loc = Builder.StatepointLowering.getLocation(SDV);
if (Loc.getNode()) {
SpillMap.SlotMap[V] = cast<FrameIndexSDNode>(Loc)->getIndex();
} else {
// Record value as visited, but not spilled. This is case for allocas
// and constants. For this values we can avoid emitting spill load while
// visiting corresponding gc_relocate.
// Actually we do not need to record them in this map at all.
// We do this only to check that we are not relocating any unvisited
// value.
SpillMap.SlotMap[V] = None;
// Default llvm mechanisms for exporting values which are used in
// different basic blocks does not work for gc relocates.
// Note that it would be incorrect to teach llvm that all relocates are
// uses of the corresponding values so that it would automatically
// export them. Relocates of the spilled values does not use original
// value.
if (Relocate->getParent() != StatepointInstr->getParent())
Builder.ExportFromCurrentBlock(V);
}
}
}
