diff options
Diffstat (limited to 'contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp')
| -rw-r--r-- | contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp | 579 |
1 files changed, 363 insertions, 216 deletions
diff --git a/contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp b/contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp index 33c20d3..8bbfa01 100644 --- a/contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp +++ b/contrib/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp @@ -17,6 +17,7 @@ #include "llvm/ADT/SmallSet.h" #include "llvm/ADT/Statistic.h" #include "llvm/CodeGen/FunctionLoweringInfo.h" +#include "llvm/CodeGen/GCMetadata.h" #include "llvm/CodeGen/GCStrategy.h" #include "llvm/CodeGen/SelectionDAG.h" #include "llvm/CodeGen/StackMaps.h" @@ -37,13 +38,19 @@ STATISTIC(NumOfStatepoints, "Number of statepoint nodes encountered"); STATISTIC(StatepointMaxSlotsRequired, "Maximum number of stack slots required for a singe statepoint"); -void -StatepointLoweringState::startNewStatepoint(SelectionDAGBuilder &Builder) { +static void pushStackMapConstant(SmallVectorImpl<SDValue>& 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 @@ StatepointLoweringState::startNewStatepoint(SelectionDAGBuilder &Builder) { AllocatedStackSlots[i] = false; } } + void StatepointLoweringState::clear() { Locations.clear(); - RelocLocations.clear(); AllocatedStackSlots.clear(); assert(PendingGCRelocateCalls.empty() && "cleared before statepoint sequence completed"); @@ -222,75 +229,83 @@ static void removeDuplicatesGCPtrs(SmallVectorImpl<const Value *> &Bases, /// Extract call from statepoint, lower it and return pointer to the /// call node. Also update NodeMap so that getValue(statepoint) will /// reference lowered call result -static SDNode *lowerCallFromStatepoint(const CallInst &CI, - SelectionDAGBuilder &Builder) { +static SDNode * +lowerCallFromStatepoint(ImmutableStatepoint ISP, MachineBasicBlock *LandingPad, + SelectionDAGBuilder &Builder, + SmallVectorImpl<SDValue> &PendingExports) { - assert(Intrinsic::experimental_gc_statepoint == - dyn_cast<IntrinsicInst>(&CI)->getIntrinsicID() && - "function called must be the statepoint function"); + ImmutableCallSite CS(ISP.getCallSite()); + + SDValue ActualCallee = Builder.getValue(ISP.getActualCallee()); + + assert(CS.getCallingConv() != CallingConv::AnyReg && + "anyregcc is not supported on statepoints!"); + + Type *DefTy = ISP.getActualReturnType(); + bool HasDef = !DefTy->isVoidTy(); + + SDValue ReturnValue, CallEndVal; + std::tie(ReturnValue, CallEndVal) = Builder.lowerCallOperands( + ISP.getCallSite(), ImmutableStatepoint::CallArgsBeginPos, + ISP.getNumCallArgs(), ActualCallee, DefTy, LandingPad, + false /* IsPatchPoint */); + + SDNode *CallEnd = CallEndVal.getNode(); + + // Get a call instruction from the call sequence chain. Tail calls are not + // allowed. The following code is essentially reverse engineering X86's + // LowerCallTo. + // + // We are expecting DAG to have the following form: + // + // ch = eh_label (only in case of invoke statepoint) + // ch, glue = callseq_start ch + // ch, glue = X86::Call ch, glue + // ch, glue = callseq_end ch, glue + // get_return_value ch, glue + // + // get_return_value can either be a CopyFromReg to grab the return value from + // %RAX, or it can be a LOAD to load a value returned by reference via a stack + // slot. + + if (HasDef && (CallEnd->getOpcode() == ISD::CopyFromReg || + CallEnd->getOpcode() == ISD::LOAD)) + CallEnd = CallEnd->getOperand(0).getNode(); + + assert(CallEnd->getOpcode() == ISD::CALLSEQ_END && "expected!"); - ImmutableStatepoint StatepointOperands(&CI); - - // Lower the actual call itself - This is a bit of a hack, but we want to - // avoid modifying the actual lowering code. This is similiar in intent to - // the LowerCallOperands mechanism used by PATCHPOINT, but is structured - // differently. Hopefully, this is slightly more robust w.r.t. calling - // convention, return values, and other function attributes. - Value *ActualCallee = const_cast<Value *>(StatepointOperands.actualCallee()); - - std::vector<Value *> Args; - CallInst::const_op_iterator arg_begin = StatepointOperands.call_args_begin(); - CallInst::const_op_iterator arg_end = StatepointOperands.call_args_end(); - Args.insert(Args.end(), arg_begin, arg_end); - // TODO: remove the creation of a new instruction! We should not be - // modifying the IR (even temporarily) at this point. - CallInst *Tmp = CallInst::Create(ActualCallee, Args); - Tmp->setTailCall(CI.isTailCall()); - Tmp->setCallingConv(CI.getCallingConv()); - Tmp->setAttributes(CI.getAttributes()); - Builder.LowerCallTo(Tmp, Builder.getValue(ActualCallee), false); - - // Handle the return value of the call iff any. - const bool HasDef = !Tmp->getType()->isVoidTy(); if (HasDef) { - // The value of the statepoint itself will be the value of call itself. - // We'll replace the actually call node shortly. gc_result will grab - // this value. - Builder.setValue(&CI, Builder.getValue(Tmp)); + if (CS.isInvoke()) { + // Result value will be used in different basic block for invokes + // so we need to export it now. But statepoint call has a different type + // than the actuall call. It means that standart exporting mechanism will + // create register of the wrong type. So instead we need to create + // 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.getActualReturnType()); + RegsForValue RFV(*Builder.DAG.getContext(), + Builder.DAG.getTargetLoweringInfo(), Reg, + ISP.getActualReturnType()); + SDValue Chain = Builder.DAG.getEntryNode(); + + RFV.getCopyToRegs(ReturnValue, Builder.DAG, Builder.getCurSDLoc(), Chain, + nullptr); + PendingExports.push_back(Chain); + Builder.FuncInfo.ValueMap[CS.getInstruction()] = Reg; + } else { + // The value of the statepoint itself will be the value of call itself. + // We'll replace the actually call node shortly. gc_result will grab + // this value. + Builder.setValue(CS.getInstruction(), ReturnValue); + } } else { // The token value is never used from here on, just generate a poison value - Builder.setValue(&CI, Builder.DAG.getIntPtrConstant(-1)); + Builder.setValue(CS.getInstruction(), + Builder.DAG.getIntPtrConstant(-1, Builder.getCurSDLoc())); } - // Remove the fake entry we created so we don't have a hanging reference - // after we delete this node. - Builder.removeValue(Tmp); - delete Tmp; - Tmp = nullptr; - - // Search for the call node - // The following code is essentially reverse engineering X86's - // LowerCallTo. - SDNode *CallNode = nullptr; - - // We just emitted a call, so it should be last thing generated - SDValue Chain = Builder.DAG.getRoot(); - - // Find closest CALLSEQ_END walking back through lowered nodes if needed - SDNode *CallEnd = Chain.getNode(); - int Sanity = 0; - while (CallEnd->getOpcode() != ISD::CALLSEQ_END) { - CallEnd = CallEnd->getGluedNode(); - assert(CallEnd && "Can not find call node"); - assert(Sanity < 20 && "should have found call end already"); - Sanity++; - } - assert(CallEnd->getOpcode() == ISD::CALLSEQ_END && - "Expected a callseq node."); - assert(CallEnd->getGluedNode()); - // Step back inside the CALLSEQ - CallNode = CallEnd->getGluedNode(); - return CallNode; + return CallEnd->getOperand(0).getNode(); } /// Callect all gc pointers coming into statepoint intrinsic, clean them up, @@ -300,24 +315,15 @@ static SDNode *lowerCallFromStatepoint(const CallInst &CI, /// Relocs - the gc_relocate corresponding to each base/ptr pair /// Elements of this arrays should be in one-to-one correspondence with each /// other i.e Bases[i], Ptrs[i] are from the same gcrelocate call -static void -getIncomingStatepointGCValues(SmallVectorImpl<const Value *> &Bases, - SmallVectorImpl<const Value *> &Ptrs, - SmallVectorImpl<const Value *> &Relocs, - ImmutableCallSite Statepoint, - SelectionDAGBuilder &Builder) { - // Search for relocated pointers. Note that working backwards from the - // gc_relocates ensures that we only get pairs which are actually relocated - // and used after the statepoint. - // TODO: This logic should probably become a utility function in Statepoint.h - for (const User *U : cast<CallInst>(Statepoint.getInstruction())->users()) { - if (!isGCRelocate(U)) { - continue; - } - GCRelocateOperands relocateOpers(U); - Relocs.push_back(cast<Value>(U)); - Bases.push_back(relocateOpers.basePtr()); - Ptrs.push_back(relocateOpers.derivedPtr()); +static void getIncomingStatepointGCValues( + SmallVectorImpl<const Value *> &Bases, SmallVectorImpl<const Value *> &Ptrs, + SmallVectorImpl<const Value *> &Relocs, ImmutableStatepoint StatepointSite, + SelectionDAGBuilder &Builder) { + for (GCRelocateOperands relocateOpers : + StatepointSite.getRelocates(StatepointSite)) { + Relocs.push_back(relocateOpers.getUnderlyingCallSite().getInstruction()); + Bases.push_back(relocateOpers.getBasePtr()); + Ptrs.push_back(relocateOpers.getDerivedPtr()); } // Remove any redundant llvm::Values which map to the same SDValue as another @@ -376,14 +382,13 @@ 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, MVT::i64)); - Ops.push_back(Builder.DAG.getTargetConstant(C->getSExtValue(), MVT::i64)); + pushStackMapConstant(Ops, Builder, C->getSExtValue()); } else if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Incoming)) { - // This handles allocas as arguments to the statepoint - const TargetLowering &TLI = Builder.DAG.getTargetLoweringInfo(); - Ops.push_back( - Builder.DAG.getTargetFrameIndex(FI->getIndex(), TLI.getPointerTy())); + // 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?) + Ops.push_back(Builder.DAG.getTargetFrameIndex(FI->getIndex(), + Incoming.getValueType())); } else { // Otherwise, locate a spill slot and explicitly spill it so it // can be found by the runtime later. We currently do not support @@ -408,15 +413,15 @@ static void lowerIncomingStatepointValue(SDValue Incoming, /// 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, - ImmutableStatepoint Statepoint, + ImmutableStatepoint StatepointSite, SelectionDAGBuilder &Builder) { // Lower the deopt and gc arguments for this statepoint. Layout will // be: deopt argument length, deopt arguments.., gc arguments... SmallVector<const Value *, 64> Bases, Ptrs, Relocations; - getIncomingStatepointGCValues(Bases, Ptrs, Relocations, - Statepoint.getCallSite(), Builder); + getIncomingStatepointGCValues(Bases, Ptrs, Relocations, StatepointSite, + Builder); #ifndef NDEBUG // Check that each of the gc pointer and bases we've gotten out of the @@ -424,61 +429,54 @@ static void lowerStatepointMetaArgs(SmallVectorImpl<SDValue> &Ops, // 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). - if (Builder.GFI) { - GCStrategy &S = Builder.GFI->getStrategy(); - for (const Value *V : Bases) { - auto Opt = S.isGCManagedPointer(V); - if (Opt.hasValue()) { - assert(Opt.getValue() && - "non gc managed base pointer found in statepoint"); - } + GCStrategy &S = Builder.GFI->getStrategy(); + for (const Value *V : Bases) { + auto Opt = S.isGCManagedPointer(V); + if (Opt.hasValue()) { + assert(Opt.getValue() && + "non gc managed base pointer found in statepoint"); } - for (const Value *V : Ptrs) { - auto Opt = S.isGCManagedPointer(V); - if (Opt.hasValue()) { - assert(Opt.getValue() && - "non gc managed derived pointer found in statepoint"); - } + } + for (const Value *V : Ptrs) { + auto Opt = S.isGCManagedPointer(V); + if (Opt.hasValue()) { + assert(Opt.getValue() && + "non gc managed derived pointer found in statepoint"); } - for (const Value *V : Relocations) { - auto Opt = S.isGCManagedPointer(V); - if (Opt.hasValue()) { - assert(Opt.getValue() && "non gc managed pointer relocated"); - } + } + for (const Value *V : Relocations) { + auto Opt = S.isGCManagedPointer(V); + if (Opt.hasValue()) { + assert(Opt.getValue() && "non gc managed pointer relocated"); } } #endif - - // 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 (auto I = Statepoint.vm_state_begin() + 1, E = Statepoint.vm_state_end(); - I != E; ++I) { - Value *V = *I; + for (const Value *V : StatepointSite.vm_state_args()) { SDValue Incoming = Builder.getValue(V); reservePreviousStackSlotForValue(Incoming, 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) { + const Value *Base = Bases[i]; + reservePreviousStackSlotForValue(Builder.getValue(Base), Builder); + + const Value *Ptr = Ptrs[i]; + reservePreviousStackSlotForValue(Builder.getValue(Ptr), 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 = Statepoint.numTotalVMSArgs(); - Ops.push_back( - Builder.DAG.getTargetConstant(StackMaps::ConstantOp, MVT::i64)); - Ops.push_back(Builder.DAG.getTargetConstant(NumVMSArgs, MVT::i64)); + const int NumVMSArgs = StatepointSite.getNumTotalVMSArgs(); + pushStackMapConstant(Ops, Builder, NumVMSArgs); - assert(NumVMSArgs + 1 == std::distance(Statepoint.vm_state_begin(), - Statepoint.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 @@ -486,9 +484,7 @@ static void lowerStatepointMetaArgs(SmallVectorImpl<SDValue> &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 = Statepoint.vm_state_begin() + 1, E = Statepoint.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); } @@ -498,35 +494,96 @@ static void lowerStatepointMetaArgs(SmallVectorImpl<SDValue> &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]; + 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 + // 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 : StatepointSite.gc_args()) { SDValue Incoming = Builder.getValue(V); - lowerIncomingStatepointValue(Incoming, Ops, Builder); + if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Incoming)) { + // This handles allocas as arguments to the statepoint + Ops.push_back(Builder.DAG.getTargetFrameIndex(FI->getIndex(), + 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(StatepointSite)) { + const Value *V = RelocateOpers.getDerivedPtr(); + SDValue SDV = Builder.getValue(V); + SDValue Loc = Builder.StatepointLowering.getLocation(SDV); + + if (Loc.getNode()) { + SpillMap[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 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) { + // Check some preconditions for sanity + assert(isStatepoint(&CI) && + "function called must be the statepoint function"); + + LowerStatepoint(ImmutableStatepoint(&CI)); +} + +void SelectionDAGBuilder::LowerStatepoint( + ImmutableStatepoint ISP, MachineBasicBlock *LandingPad /*=nullptr*/) { // The basic scheme here is that information about both the original call and // the safepoint is encoded in the CallInst. We create a temporary call and // lower it, then reverse engineer the calling sequence. - // Check some preconditions for sanity - assert(isStatepoint(&CI) && - "function called must be the statepoint function"); NumOfStatepoints++; // Clear state StatepointLowering.startNewStatepoint(*this); + ImmutableCallSite CS(ISP.getCallSite()); + #ifndef NDEBUG - // Consistency check - for (const User *U : CI.users()) { - const CallInst *Call = cast<CallInst>(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<CallInst>(U); + if (isGCRelocate(Call)) + StatepointLowering.scheduleRelocCall(*Call); + } } #endif - ImmutableStatepoint ISP(&CI); #ifndef NDEBUG // If this is a malformed statepoint, report it early to simplify debugging. // This should catch any IR level mistake that's made when constructing or @@ -534,42 +591,82 @@ void SelectionDAGBuilder::visitStatepoint(const CallInst &CI) { 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). - if (GFI) { - assert(GFI->getStrategy().useStatepoints() && - "GCStrategy does not expect to encounter statepoints"); - } + assert(GFI->getStrategy().useStatepoints() && + "GCStrategy does not expect to encounter statepoints"); #endif - // Lower statepoint vmstate and gcstate arguments - SmallVector<SDValue, 10> LoweredArgs; - lowerStatepointMetaArgs(LoweredArgs, ISP, *this); + SmallVector<SDValue, 10> LoweredMetaArgs; + lowerStatepointMetaArgs(LoweredMetaArgs, ISP, *this); // Get call node, we will replace it later with statepoint - SDNode *CallNode = lowerCallFromStatepoint(CI, *this); + SDNode *CallNode = + lowerCallFromStatepoint(ISP, LandingPad, *this, PendingExports); + + // 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<SDValue, 8> 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)); + } - // Construct the actual STATEPOINT node with all the appropriate arguments - // and return values. + // 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<SDValue, 40> Ops; + // Add the <id> and <numBytes> 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); - Ops.push_back(DAG.getTargetConstant(NumCallRegArgs, MVT::i32)); + CallNode->getNumOperands() - (CallHasIncomingGlue ? 4 : 3); + Ops.push_back(DAG.getTargetConstant(NumCallRegArgs, getCurSDLoc(), MVT::i32)); // Add call target SDValue CallTarget = SDValue(CallNode->getOperand(1).getNode(), 0); @@ -578,47 +675,74 @@ void SelectionDAGBuilder::visitStatepoint(const CallInst &CI) { // 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 = CI.getCallingConv(); - int Flags = dyn_cast<ConstantInt>(CI.getArgOperand(2))->getZExtValue(); - assert(Flags == 0 && "not expected to be used"); - Ops.push_back(DAG.getTargetConstant(StackMaps::ConstantOp, MVT::i64)); - Ops.push_back( - DAG.getTargetConstant(Flags | ((unsigned)CallConv << 1), 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(), LoweredArgs.begin(), LoweredArgs.end()); + Ops.insert(Ops.end(), LoweredMetaArgs.begin(), LoweredMetaArgs.end()); // Add register mask from call node 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()) Ops.push_back(Glue); - // Compute return values - SmallVector<EVT, 21> ValueVTs; - ValueVTs.push_back(MVT::Other); - ValueVTs.push_back(MVT::Glue); // provide a glue output since we consume one - // as input. This allows someone else to chain - // off us as needed. - SDVTList NodeTys = DAG.getVTList(ValueVTs); + // Compute return values. Provide a glue output since we consume one as + // input. This allows someone else to chain off us as needed. + SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue); + + 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<SDValue, 8> TEOps; + + // Add chain + TEOps.push_back(SDValue(StatepointMCNode, 0)); - SDNode *StatepointMCNode = DAG.getMachineNode(TargetOpcode::STATEPOINT, - getCurSDLoc(), NodeTys, Ops); + // 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); @@ -636,49 +760,72 @@ void SelectionDAGBuilder::visitGCResult(const CallInst &CI) { // The result value of the gc_result is simply the result of the actual // call. We've already emitted this, so just grab the value. Instruction *I = cast<Instruction>(CI.getArgOperand(0)); - assert(isStatepoint(I) && - "first argument must be a statepoint token"); - - setValue(&CI, getValue(I)); + assert(isStatepoint(I) && "first argument must be a statepoint token"); + + if (isa<InvokeInst>(I)) { + // For invokes we should have stored call result in a virtual register. + // We can not use default getValue() functionality to copy value from this + // 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<PointerType>(ImmutableStatepoint(I).getActualCallee()->getType()); + Type *RetTy = + cast<FunctionType>(CalleeType->getElementType())->getReturnType(); + SDValue CopyFromReg = getCopyFromRegs(I, RetTy); + + assert(CopyFromReg.getNode()); + setValue(&CI, CopyFromReg); + } else { + setValue(&CI, getValue(I)); + } } 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<ConstantSDNode>(SD) || isa<FrameIndexSDNode>(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<int> 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<FrameIndexSDNode>(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); } |
