X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FCodeGen%2FSelectionDAG%2FStatepointLowering.cpp;h=34688df4765b688fc52295778b2835ac6adfdb9a;hb=8770f7af5f46c0d34a79cf0beeeef80b1a2ab690;hp=9193f316a615befdf572cf5f459fefa744c9d915;hpb=d77522093ed310ff76a2c9e6a3e1e15567ac734a;p=oota-llvm.git diff --git a/lib/CodeGen/SelectionDAG/StatepointLowering.cpp b/lib/CodeGen/SelectionDAG/StatepointLowering.cpp index 9193f316a61..34688df4765 100644 --- a/lib/CodeGen/SelectionDAG/StatepointLowering.cpp +++ b/lib/CodeGen/SelectionDAG/StatepointLowering.cpp @@ -38,12 +38,19 @@ STATISTIC(NumOfStatepoints, "Number of statepoint nodes encountered"); STATISTIC(StatepointMaxSlotsRequired, "Maximum number of stack slots required for a singe statepoint"); +static void pushStackMapConstant(SmallVectorImpl& Ops, + SelectionDAGBuilder &Builder, uint64_t Value) { + SDLoc L = Builder.getCurSDLoc(); + Ops.push_back(Builder.DAG.getTargetConstant(StackMaps::ConstantOp, L, + MVT::i64)); + Ops.push_back(Builder.DAG.getTargetConstant(Value, L, MVT::i64)); +} + void StatepointLoweringState::startNewStatepoint(SelectionDAGBuilder &Builder) { // Consistency check assert(PendingGCRelocateCalls.empty() && "Trying to visit statepoint before finished processing previous one"); Locations.clear(); - RelocLocations.clear(); NextSlotToAllocate = 0; // Need to resize this on each safepoint - we need the two to stay in // sync and the clear patterns of a SelectionDAGBuilder have no relation @@ -53,9 +60,9 @@ void StatepointLoweringState::startNewStatepoint(SelectionDAGBuilder &Builder) { AllocatedStackSlots[i] = false; } } + void StatepointLoweringState::clear() { Locations.clear(); - RelocLocations.clear(); AllocatedStackSlots.clear(); assert(PendingGCRelocateCalls.empty() && "cleared before statepoint sequence completed"); @@ -106,84 +113,137 @@ StatepointLoweringState::allocateStackSlot(EVT ValueType, llvm_unreachable("infinite loop?"); } +/// Utility function for reservePreviousStackSlotForValue. Tries to find +/// stack slot index to which we have spilled value for previous statepoints. +/// LookUpDepth specifies maximum DFS depth this function is allowed to look. +static Optional findPreviousSpillSlot(const Value *Val, + SelectionDAGBuilder &Builder, + int LookUpDepth) { + // Can not look any futher - give up now + if (LookUpDepth <= 0) + return Optional(); + + // Spill location is known for gc relocates + if (isGCRelocate(Val)) { + GCRelocateOperands RelocOps(cast(Val)); + + FunctionLoweringInfo::StatepointSpilledValueMapTy &SpillMap = + Builder.FuncInfo.StatepointRelocatedValues[RelocOps.getStatepoint()]; + + auto It = SpillMap.find(RelocOps.getDerivedPtr()); + if (It == SpillMap.end()) + return Optional(); + + return It->second; + } + + // Look through bitcast instructions. + if (const BitCastInst *Cast = dyn_cast(Val)) { + return findPreviousSpillSlot(Cast->getOperand(0), Builder, LookUpDepth - 1); + } + + // Look through phi nodes + // All incoming values should have same known stack slot, otherwise result + // is unknown. + if (const PHINode *Phi = dyn_cast(Val)) { + Optional MergedResult = None; + + for (auto &IncomingValue : Phi->incoming_values()) { + Optional SpillSlot = + findPreviousSpillSlot(IncomingValue, Builder, LookUpDepth - 1); + if (!SpillSlot.hasValue()) + return Optional(); + + if (MergedResult.hasValue() && *MergedResult != *SpillSlot) + return Optional(); + + MergedResult = SpillSlot; + } + return MergedResult; + } + + // TODO: We can do better for PHI nodes. In cases like this: + // ptr = phi(relocated_pointer, not_relocated_pointer) + // statepoint(ptr) + // We will return that stack slot for ptr is unknown. And later we might + // assign different stack slots for ptr and relocated_pointer. This limits + // llvm's ability to remove redundant stores. + // Unfortunately it's hard to accomplish in current infrastructure. + // We use this function to eliminate spill store completely, while + // in example we still need to emit store, but instead of any location + // we need to use special "preferred" location. + + // TODO: handle simple updates. If a value is modified and the original + // value is no longer live, it would be nice to put the modified value in the + // same slot. This allows folding of the memory accesses for some + // instructions types (like an increment). + // statepoint (i) + // i1 = i+1 + // statepoint (i1) + // However we need to be careful for cases like this: + // statepoint(i) + // i1 = i+1 + // statepoint(i, i1) + // Here we want to reserve spill slot for 'i', but not for 'i+1'. If we just + // put handling of simple modifications in this function like it's done + // for bitcasts we might end up reserving i's slot for 'i+1' because order in + // which we visit values is unspecified. + + // Don't know any information about this instruction + return Optional(); +} + /// 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 resuffle /// values on the stack between calls. -static void reservePreviousStackSlotForValue(SDValue Incoming, +static void reservePreviousStackSlotForValue(const Value *IncomingValue, SelectionDAGBuilder &Builder) { + SDValue Incoming = Builder.getValue(IncomingValue); + if (isa(Incoming) || isa(Incoming)) { // We won't need to spill this, so no need to check for previously // allocated stack slots return; } - SDValue Loc = Builder.StatepointLowering.getLocation(Incoming); - if (Loc.getNode()) { + SDValue OldLocation = Builder.StatepointLowering.getLocation(Incoming); + if (OldLocation.getNode()) // duplicates in input return; - } - - // Search back for the load from a stack slot pattern to find the original - // slot we allocated for this value. We could extend this to deal with - // simple modification patterns, but simple dealing with trivial load/store - // sequences helps a lot already. - if (LoadSDNode *Load = dyn_cast(Incoming)) { - if (auto *FI = dyn_cast(Load->getBasePtr())) { - const int Index = FI->getIndex(); - auto Itr = std::find(Builder.FuncInfo.StatepointStackSlots.begin(), - Builder.FuncInfo.StatepointStackSlots.end(), Index); - if (Itr == Builder.FuncInfo.StatepointStackSlots.end()) { - // not one of the lowering stack slots, can't reuse! - // TODO: Actually, we probably could reuse the stack slot if the value - // hasn't changed at all, but we'd need to look for intervening writes - return; - } else { - // This is one of our dedicated lowering slots - const int Offset = - std::distance(Builder.FuncInfo.StatepointStackSlots.begin(), Itr); - 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, Incoming.getValueType()); + const int LookUpDepth = 6; + Optional Index = + findPreviousSpillSlot(IncomingValue, Builder, LookUpDepth); + if (!Index.hasValue()) + return; - Builder.StatepointLowering.setLocation(Incoming, Loc); - } + auto Itr = std::find(Builder.FuncInfo.StatepointStackSlots.begin(), + Builder.FuncInfo.StatepointStackSlots.end(), *Index); + assert(Itr != Builder.FuncInfo.StatepointStackSlots.end() && + "value spilled to the unknown stack slot"); + + // This is one of our dedicated lowering slots + const int Offset = + std::distance(Builder.FuncInfo.StatepointStackSlots.begin(), Itr); + 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); - // TODO: handle case where a reloaded value flows through a phi to - // another safepoint. e.g. - // bb1: - // a' = relocated... - // bb2: % pred: bb1, bb3, bb4, etc. - // a_phi = phi(a', ...) - // statepoint ... a_phi - // NOTE: This will require reasoning about cross basic block values. This is - // decidedly non trivial and this might not be the right place to do it. We - // don't really have the information we need here... - - // TODO: handle simple updates. If a value is modified and the original - // value is no longer live, it would be nice to put the modified value in the - // same slot. This allows folding of the memory accesses for some - // instructions types (like an increment). - // statepoint (i) - // i1 = i+1 - // statepoint (i1) + // Cache this slot so we find it when going through the normal + // assignment loop. + SDValue Loc = Builder.DAG.getTargetFrameIndex(*Index, Incoming.getValueType()); + Builder.StatepointLowering.setLocation(Incoming, Loc); } /// Remove any duplicate (as SDValues) from the derived pointer pairs. This @@ -229,29 +289,19 @@ lowerCallFromStatepoint(ImmutableStatepoint ISP, MachineBasicBlock *LandingPad, ImmutableCallSite CS(ISP.getCallSite()); - SDValue ActualCallee = Builder.getValue(ISP.actualCallee()); - - // Handle immediate and symbolic callees. - if (auto *ConstCallee = dyn_cast(ActualCallee.getNode())) - ActualCallee = Builder.DAG.getIntPtrConstant(ConstCallee->getZExtValue(), - Builder.getCurSDLoc(), - /*isTarget=*/true); - else if (auto *SymbolicCallee = - dyn_cast(ActualCallee.getNode())) - ActualCallee = Builder.DAG.getTargetGlobalAddress( - SymbolicCallee->getGlobal(), SDLoc(SymbolicCallee), - SymbolicCallee->getValueType(0)); + SDValue ActualCallee = Builder.getValue(ISP.getCalledValue()); assert(CS.getCallingConv() != CallingConv::AnyReg && "anyregcc is not supported on statepoints!"); - Type *DefTy = ISP.actualReturnType(); + Type *DefTy = ISP.getActualReturnType(); bool HasDef = !DefTy->isVoidTy(); SDValue ReturnValue, CallEndVal; std::tie(ReturnValue, CallEndVal) = Builder.lowerCallOperands( - ISP.getCallSite(), ISP.callArgsBeginOffset(), ISP.numCallArgs(), - ActualCallee, DefTy, LandingPad, false /* IsPatchPoint */); + ISP.getCallSite(), ImmutableStatepoint::CallArgsBeginPos, + ISP.getNumCallArgs(), ActualCallee, DefTy, LandingPad, + false /* IsPatchPoint */); SDNode *CallEnd = CallEndVal.getNode(); @@ -286,10 +336,10 @@ lowerCallFromStatepoint(ImmutableStatepoint ISP, MachineBasicBlock *LandingPad, // register with correct type and save value into it manually. // TODO: To eliminate this problem we can remove gc.result intrinsics // completelly and make statepoint call to return a tuple. - unsigned Reg = Builder.FuncInfo.CreateRegs(ISP.actualReturnType()); - RegsForValue RFV(*Builder.DAG.getContext(), - Builder.DAG.getTargetLoweringInfo(), Reg, - ISP.actualReturnType()); + unsigned Reg = Builder.FuncInfo.CreateRegs(ISP.getActualReturnType()); + RegsForValue RFV( + *Builder.DAG.getContext(), Builder.DAG.getTargetLoweringInfo(), + Builder.DAG.getDataLayout(), Reg, ISP.getActualReturnType()); SDValue Chain = Builder.DAG.getEntryNode(); RFV.getCopyToRegs(ReturnValue, Builder.DAG, Builder.getCurSDLoc(), Chain, @@ -322,11 +372,10 @@ static void getIncomingStatepointGCValues( SmallVectorImpl &Bases, SmallVectorImpl &Ptrs, SmallVectorImpl &Relocs, ImmutableStatepoint StatepointSite, SelectionDAGBuilder &Builder) { - for (GCRelocateOperands relocateOpers : - StatepointSite.getRelocates(StatepointSite)) { + for (GCRelocateOperands relocateOpers : StatepointSite.getRelocates()) { Relocs.push_back(relocateOpers.getUnderlyingCallSite().getInstruction()); - Bases.push_back(relocateOpers.basePtr()); - Ptrs.push_back(relocateOpers.derivedPtr()); + Bases.push_back(relocateOpers.getBasePtr()); + Ptrs.push_back(relocateOpers.getDerivedPtr()); } // Remove any redundant llvm::Values which map to the same SDValue as another @@ -385,12 +434,7 @@ static void lowerIncomingStatepointValue(SDValue Incoming, // 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 - Ops.push_back(Builder.DAG.getTargetConstant(StackMaps::ConstantOp, - Builder.getCurSDLoc(), - MVT::i64)); - Ops.push_back(Builder.DAG.getTargetConstant(C->getSExtValue(), - Builder.getCurSDLoc(), - MVT::i64)); + pushStackMapConstant(Ops, Builder, C->getSExtValue()); } else if (FrameIndexSDNode *FI = dyn_cast(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 @@ -465,32 +509,22 @@ static void lowerStatepointMetaArgs(SmallVectorImpl &Ops, // 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 (auto I = StatepointSite.vm_state_begin() + 1, - E = StatepointSite.vm_state_end(); - I != E; ++I) { - Value *V = *I; - SDValue Incoming = Builder.getValue(V); - reservePreviousStackSlotForValue(Incoming, Builder); + for (const Value *V : StatepointSite.vm_state_args()) { + reservePreviousStackSlotForValue(V, Builder); } - for (unsigned i = 0; i < Bases.size() * 2; ++i) { - // Even elements will contain base, odd elements - derived ptr - const Value *V = i % 2 ? Bases[i / 2] : Ptrs[i / 2]; - SDValue Incoming = Builder.getValue(V); - reservePreviousStackSlotForValue(Incoming, Builder); + for (unsigned i = 0; i < Bases.size(); ++i) { + reservePreviousStackSlotForValue(Bases[i], Builder); + reservePreviousStackSlotForValue(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 = StatepointSite.numTotalVMSArgs(); - Ops.push_back( Builder.DAG.getTargetConstant(StackMaps::ConstantOp, - Builder.getCurSDLoc(), - MVT::i64)); - Ops.push_back(Builder.DAG.getTargetConstant(NumVMSArgs, Builder.getCurSDLoc(), - MVT::i64)); + const int NumVMSArgs = StatepointSite.getNumTotalVMSArgs(); + pushStackMapConstant(Ops, Builder, NumVMSArgs); - assert(NumVMSArgs + 1 == std::distance(StatepointSite.vm_state_begin(), - StatepointSite.vm_state_end())); + assert(NumVMSArgs == std::distance(StatepointSite.vm_state_begin(), + StatepointSite.vm_state_end())); // The vm state arguments are lowered in an opaque manner. We do // not know what type of values are contained within. We skip the @@ -498,10 +532,7 @@ static void lowerStatepointMetaArgs(SmallVectorImpl &Ops, // explicitly just above. We could have left it in the loop and // not done it explicitly, but it's far easier to understand this // way. - for (auto I = StatepointSite.vm_state_begin() + 1, - E = StatepointSite.vm_state_end(); - I != E; ++I) { - const Value *V = *I; + for (const Value *V : StatepointSite.vm_state_args()) { SDValue Incoming = Builder.getValue(V); lowerIncomingStatepointValue(Incoming, Ops, Builder); } @@ -511,11 +542,12 @@ static void lowerStatepointMetaArgs(SmallVectorImpl &Ops, // 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 < Bases.size() * 2; ++i) { - // Even elements will contain base, odd elements - derived ptr - const Value *V = i % 2 ? Bases[i / 2] : Ptrs[i / 2]; - SDValue Incoming = Builder.getValue(V); - lowerIncomingStatepointValue(Incoming, Ops, Builder); + for (unsigned i = 0; i < Bases.size(); ++i) { + const Value *Base = Bases[i]; + lowerIncomingStatepointValue(Builder.getValue(Base), Ops, Builder); + + const Value *Ptr = Ptrs[i]; + lowerIncomingStatepointValue(Builder.getValue(Ptr), Ops, Builder); } // If there are any explicit spill slots passed to the statepoint, record @@ -531,6 +563,40 @@ static void lowerStatepointMetaArgs(SmallVectorImpl &Ops, Incoming.getValueType())); } } + + // 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 = + StatepointSite.getCallSite().getInstruction(); + FunctionLoweringInfo::StatepointSpilledValueMapTy &SpillMap = + Builder.FuncInfo.StatepointRelocatedValues[StatepointInstr]; + + for (GCRelocateOperands RelocateOpers : StatepointSite.getRelocates()) { + const Value *V = RelocateOpers.getDerivedPtr(); + SDValue SDV = Builder.getValue(V); + SDValue Loc = Builder.StatepointLowering.getLocation(SDV); + + if (Loc.getNode()) { + SpillMap[V] = cast(Loc)->getIndex(); + } else { + // Record value as visited, but not spilled. This is case for allocas + // and constants. For this values we can avoid emiting 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[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 corresponging values so that it would automatically + // export them. Relocates of the spilled values does not use original + // value. + if (StatepointSite.getCallSite().isInvoke()) + Builder.ExportFromCurrentBlock(V); + } + } } void SelectionDAGBuilder::visitStatepoint(const CallInst &CI) { @@ -554,11 +620,14 @@ void SelectionDAGBuilder::LowerStatepoint( ImmutableCallSite CS(ISP.getCallSite()); #ifndef NDEBUG - // Consistency check - for (const User *U : CS->users()) { - const CallInst *Call = cast(U); - if (isGCRelocate(Call)) - StatepointLowering.scheduleRelocCall(*Call); + // Consistency check. Don't do this for invokes. It would be too + // expensive to preserve this information across different basic blocks + if (!CS.isInvoke()) { + for (const User *U : CS->users()) { + const CallInst *Call = cast(U); + if (isGCRelocate(Call)) + StatepointLowering.scheduleRelocCall(*Call); + } } #endif @@ -569,9 +638,6 @@ void SelectionDAGBuilder::LowerStatepoint( ISP.verify(); // Check that the associated GCStrategy expects to encounter statepoints. - // TODO: This if should become an assert. For now, we allow the GCStrategy - // to be optional for backwards compatibility. This will only last a short - // period (i.e. a couple of weeks). assert(GFI->getStrategy().useStatepoints() && "GCStrategy does not expect to encounter statepoints"); #endif @@ -584,24 +650,69 @@ void SelectionDAGBuilder::LowerStatepoint( SDNode *CallNode = lowerCallFromStatepoint(ISP, LandingPad, *this, PendingExports); - // Construct the actual STATEPOINT node with all the appropriate arguments - // and return values. + // Construct the actual GC_TRANSITION_START, STATEPOINT, and GC_TRANSITION_END + // nodes with all the appropriate arguments and return values. + + // Call Node: Chain, Target, {Args}, RegMask, [Glue] + SDValue Chain = CallNode->getOperand(0); + + SDValue Glue; + bool CallHasIncomingGlue = CallNode->getGluedNode(); + if (CallHasIncomingGlue) { + // Glue is always last operand + Glue = CallNode->getOperand(CallNode->getNumOperands() - 1); + } + + // Build the GC_TRANSITION_START node if necessary. + // + // The operands to the GC_TRANSITION_{START,END} nodes are laid out in the + // order in which they appear in the call to the statepoint intrinsic. If + // any of the operands is a pointer-typed, that operand is immediately + // followed by a SRCVALUE for the pointer that may be used during lowering + // (e.g. to form MachinePointerInfo values for loads/stores). + const bool IsGCTransition = + (ISP.getFlags() & (uint64_t)StatepointFlags::GCTransition) == + (uint64_t)StatepointFlags::GCTransition; + if (IsGCTransition) { + SmallVector TSOps; + + // Add chain + TSOps.push_back(Chain); + + // Add GC transition arguments + for (const Value *V : ISP.gc_transition_args()) { + TSOps.push_back(getValue(V)); + if (V->getType()->isPointerTy()) + TSOps.push_back(DAG.getSrcValue(V)); + } + + // Add glue if necessary + if (CallHasIncomingGlue) + TSOps.push_back(Glue); + + SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue); + + SDValue GCTransitionStart = + DAG.getNode(ISD::GC_TRANSITION_START, getCurSDLoc(), NodeTys, TSOps); + + Chain = GCTransitionStart.getValue(0); + Glue = GCTransitionStart.getValue(1); + } // TODO: Currently, all of these operands are being marked as read/write in // PrologEpilougeInserter.cpp, we should special case the VMState arguments // and flags to be read-only. SmallVector Ops; + // Add the and constants. + Ops.push_back(DAG.getTargetConstant(ISP.getID(), getCurSDLoc(), MVT::i64)); + Ops.push_back( + DAG.getTargetConstant(ISP.getNumPatchBytes(), getCurSDLoc(), MVT::i32)); + // Calculate and push starting position of vmstate arguments - // Call Node: Chain, Target, {Args}, RegMask, [Glue] - SDValue Glue; - if (CallNode->getGluedNode()) { - // Glue is always last operand - Glue = CallNode->getOperand(CallNode->getNumOperands() - 1); - } // Get number of arguments incoming directly into call node unsigned NumCallRegArgs = - CallNode->getNumOperands() - (Glue.getNode() ? 4 : 3); + CallNode->getNumOperands() - (CallHasIncomingGlue ? 4 : 3); Ops.push_back(DAG.getTargetConstant(NumCallRegArgs, getCurSDLoc(), MVT::i32)); // Add call target @@ -611,21 +722,21 @@ void SelectionDAGBuilder::LowerStatepoint( // Add call arguments // Get position of register mask in the call SDNode::op_iterator RegMaskIt; - if (Glue.getNode()) + if (CallHasIncomingGlue) RegMaskIt = CallNode->op_end() - 2; else RegMaskIt = CallNode->op_end() - 1; Ops.insert(Ops.end(), CallNode->op_begin() + 2, RegMaskIt); - // Add a leading constant argument with the Flags and the calling convention - // masked together - CallingConv::ID CallConv = CS.getCallingConv(); - int Flags = cast(CS.getArgument(2))->getZExtValue(); - assert(Flags == 0 && "not expected to be used"); - Ops.push_back(DAG.getTargetConstant(StackMaps::ConstantOp, getCurSDLoc(), - MVT::i64)); - Ops.push_back(DAG.getTargetConstant(Flags | ((unsigned)CallConv << 1), - getCurSDLoc(), MVT::i64)); + // Add a constant argument for the calling convention + pushStackMapConstant(Ops, *this, CS.getCallingConv()); + + // Add a constant argument for the flags + uint64_t Flags = ISP.getFlags(); + assert( + ((Flags & ~(uint64_t)StatepointFlags::MaskAll) == 0) + && "unknown flag used"); + pushStackMapConstant(Ops, *this, Flags); // Insert all vmstate and gcstate arguments Ops.insert(Ops.end(), LoweredMetaArgs.begin(), LoweredMetaArgs.end()); @@ -634,7 +745,7 @@ void SelectionDAGBuilder::LowerStatepoint( Ops.push_back(*RegMaskIt); // Add chain - Ops.push_back(CallNode->getOperand(0)); + Ops.push_back(Chain); // Same for the glue, but we add it only if original call had it if (Glue.getNode()) @@ -647,8 +758,38 @@ void SelectionDAGBuilder::LowerStatepoint( SDNode *StatepointMCNode = DAG.getMachineNode(TargetOpcode::STATEPOINT, getCurSDLoc(), NodeTys, Ops); + SDNode *SinkNode = StatepointMCNode; + + // Build the GC_TRANSITION_END node if necessary. + // + // See the comment above regarding GC_TRANSITION_START for the layout of + // the operands to the GC_TRANSITION_END node. + if (IsGCTransition) { + SmallVector TEOps; + + // Add chain + TEOps.push_back(SDValue(StatepointMCNode, 0)); + + // Add GC transition arguments + for (const Value *V : ISP.gc_transition_args()) { + TEOps.push_back(getValue(V)); + if (V->getType()->isPointerTy()) + TEOps.push_back(DAG.getSrcValue(V)); + } + + // Add glue + TEOps.push_back(SDValue(StatepointMCNode, 1)); + + SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue); + + SDValue GCTransitionStart = + DAG.getNode(ISD::GC_TRANSITION_END, getCurSDLoc(), NodeTys, TEOps); + + SinkNode = GCTransitionStart.getNode(); + } + // Replace original call - DAG.ReplaceAllUsesWith(CallNode, StatepointMCNode); // This may update Root + DAG.ReplaceAllUsesWith(CallNode, SinkNode); // This may update Root // Remove originall call node DAG.DeleteNode(CallNode); @@ -674,8 +815,8 @@ void SelectionDAGBuilder::visitGCResult(const CallInst &CI) { // register because statepoint and actuall call return types can be // different, and getValue() will use CopyFromReg of the wrong type, // which is always i32 in our case. - PointerType *CalleeType = - cast(ImmutableStatepoint(I).actualCallee()->getType()); + PointerType *CalleeType = cast( + ImmutableStatepoint(I).getCalledValue()->getType()); Type *RetTy = cast(CalleeType->getElementType())->getReturnType(); SDValue CopyFromReg = getCopyFromRegs(I, RetTy); @@ -688,42 +829,50 @@ void SelectionDAGBuilder::visitGCResult(const CallInst &CI) { } void SelectionDAGBuilder::visitGCRelocate(const CallInst &CI) { + GCRelocateOperands RelocateOpers(&CI); + #ifndef NDEBUG // Consistency check - StatepointLowering.relocCallVisited(CI); + // We skip this check for invoke statepoints. It would be too expensive to + // preserve validation info through different basic blocks. + if (!RelocateOpers.isTiedToInvoke()) { + StatepointLowering.relocCallVisited(CI); + } #endif - GCRelocateOperands relocateOpers(&CI); - SDValue SD = getValue(relocateOpers.derivedPtr()); + const Value *DerivedPtr = RelocateOpers.getDerivedPtr(); + SDValue SD = getValue(DerivedPtr); + + FunctionLoweringInfo::StatepointSpilledValueMapTy &SpillMap = + FuncInfo.StatepointRelocatedValues[RelocateOpers.getStatepoint()]; - if (isa(SD) || isa(SD)) { - // We didn't need to spill these special cases (constants and allocas). - // See the handling in spillIncomingValueForStatepoint for detail. + // We should have recorded location for this pointer + assert(SpillMap.count(DerivedPtr) && "Relocating not lowered gc value"); + Optional DerivedPtrLocation = SpillMap[DerivedPtr]; + + // We didn't need to spill these special cases (constants and allocas). + // See the handling in spillIncomingValueForStatepoint for detail. + if (!DerivedPtrLocation) { setValue(&CI, SD); return; } - SDValue Loc = StatepointLowering.getRelocLocation(SD); - // Emit new load if we did not emit it before - if (!Loc.getNode()) { - SDValue SpillSlot = StatepointLowering.getLocation(SD); - int FI = cast(SpillSlot)->getIndex(); + SDValue SpillSlot = DAG.getTargetFrameIndex(*DerivedPtrLocation, + SD.getValueType()); - // Be conservative: flush all pending loads - // TODO: Probably we can be less restrictive on this, - // it may allow more scheduling opprtunities - SDValue Chain = getRoot(); + // Be conservative: flush all pending loads + // TODO: Probably we can be less restrictive on this, + // it may allow more scheduling opprtunities + SDValue Chain = getRoot(); - Loc = DAG.getLoad(SpillSlot.getValueType(), getCurSDLoc(), Chain, SpillSlot, - MachinePointerInfo::getFixedStack(FI), false, false, - false, 0); + SDValue SpillLoad = + DAG.getLoad(SpillSlot.getValueType(), getCurSDLoc(), Chain, SpillSlot, + MachinePointerInfo::getFixedStack(*DerivedPtrLocation), + false, false, false, 0); - StatepointLowering.setRelocLocation(SD, Loc); + // Again, be conservative, don't emit pending loads + DAG.setRoot(SpillLoad.getValue(1)); - // Again, be conservative, don't emit pending loads - DAG.setRoot(Loc.getValue(1)); - } - - assert(Loc.getNode()); - setValue(&CI, Loc); + assert(SpillLoad.getNode()); + setValue(&CI, SpillLoad); }