Index: llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp +++ llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp @@ -5147,10 +5147,30 @@ }; const unsigned NumGPRs = array_lengthof(GPR); - const unsigned NumFPRs = 13; + const unsigned NumFPRs = useSoftFloat() ? 0 : 13; const unsigned NumVRs = array_lengthof(VR); const unsigned NumQFPRs = NumFPRs; + // On ELFv2, we can avoid allocating the parameter area if all the arguments + // can be passed to the callee in registers. + // For the fast calling convention, there is another check below. + // Note: keep consistent with LowerFormalArguments_64SVR4() + bool HasParameterArea = !isELFv2ABI || isVarArg || CallConv == CallingConv::Fast; + if (!HasParameterArea) { + unsigned ParamAreaSize = NumGPRs * PtrByteSize; + unsigned AvailableFPRs = NumFPRs; + unsigned AvailableVRs = NumVRs; + unsigned NumBytesTmp = NumBytes; + for (unsigned i = 0; i != NumOps; ++i) { + if (Outs[i].Flags.isNest()) continue; + if (CalculateStackSlotUsed(Outs[i].VT, Outs[i].ArgVT, Outs[i].Flags, + PtrByteSize, LinkageSize, ParamAreaSize, + NumBytesTmp, AvailableFPRs, AvailableVRs, + Subtarget.hasQPX())) + HasParameterArea = true; + } + } + // When using the fast calling convention, we don't provide backing for // arguments that will be in registers. unsigned NumGPRsUsed = 0, NumFPRsUsed = 0, NumVRsUsed = 0; @@ -5218,13 +5238,18 @@ unsigned NumBytesActuallyUsed = NumBytes; - // The prolog code of the callee may store up to 8 GPR argument registers to + // In the old ELFv1 ABI, + // the prolog code of the callee may store up to 8 GPR argument registers to // the stack, allowing va_start to index over them in memory if its varargs. // Because we cannot tell if this is needed on the caller side, we have to // conservatively assume that it is needed. As such, make sure we have at // least enough stack space for the caller to store the 8 GPRs. - // FIXME: On ELFv2, it may be unnecessary to allocate the parameter area. - NumBytes = std::max(NumBytes, LinkageSize + 8 * PtrByteSize); + // In the ELFv2 ABI, we allocate the parameter area iff a callee + // really requires memory operands, e.g. a vararg function. + if (HasParameterArea) + NumBytes = std::max(NumBytes, LinkageSize + 8 * PtrByteSize); + else + NumBytes = LinkageSize; // Tail call needs the stack to be aligned. if (getTargetMachine().Options.GuaranteedTailCallOpt && @@ -5443,6 +5468,8 @@ if (CallConv == CallingConv::Fast) ComputePtrOff(); + assert(HasParameterArea && + "Parameter area must exist to pass an argument in memory."); LowerMemOpCallTo(DAG, MF, Chain, Arg, PtrOff, SPDiff, ArgOffset, true, isTailCall, false, MemOpChains, TailCallArguments, dl); @@ -5528,6 +5555,8 @@ PtrOff = DAG.getNode(ISD::ADD, dl, PtrVT, PtrOff, ConstFour); } + assert(HasParameterArea && + "Parameter area must exist to pass an argument in memory."); LowerMemOpCallTo(DAG, MF, Chain, Arg, PtrOff, SPDiff, ArgOffset, true, isTailCall, false, MemOpChains, TailCallArguments, dl); @@ -5562,6 +5591,8 @@ // GPRs when within range. For now, we always put the value in both // locations (or even all three). if (isVarArg) { + assert(HasParameterArea && + "Parameter area must exist if we have a varargs call."); // We could elide this store in the case where the object fits // entirely in R registers. Maybe later. SDValue Store = @@ -5594,6 +5625,8 @@ if (CallConv == CallingConv::Fast) ComputePtrOff(); + assert(HasParameterArea && + "Parameter area must exist to pass an argument in memory."); LowerMemOpCallTo(DAG, MF, Chain, Arg, PtrOff, SPDiff, ArgOffset, true, isTailCall, true, MemOpChains, TailCallArguments, dl); @@ -5614,6 +5647,8 @@ case MVT::v4i1: { bool IsF32 = Arg.getValueType().getSimpleVT().SimpleTy == MVT::v4f32; if (isVarArg) { + assert(HasParameterArea && + "Parameter area must exist if we have a varargs call."); // We could elide this store in the case where the object fits // entirely in R registers. Maybe later. SDValue Store = @@ -5646,6 +5681,8 @@ if (CallConv == CallingConv::Fast) ComputePtrOff(); + assert(HasParameterArea && + "Parameter area must exist to pass an argument in memory."); LowerMemOpCallTo(DAG, MF, Chain, Arg, PtrOff, SPDiff, ArgOffset, true, isTailCall, true, MemOpChains, TailCallArguments, dl); @@ -5660,7 +5697,8 @@ } } - assert(NumBytesActuallyUsed == ArgOffset); + assert((!HasParameterArea || NumBytesActuallyUsed == ArgOffset) && + "mismatch in size of parameter area"); (void)NumBytesActuallyUsed; if (!MemOpChains.empty()) Index: llvm/trunk/test/CodeGen/PowerPC/stacksize.ll =================================================================== --- llvm/trunk/test/CodeGen/PowerPC/stacksize.ll +++ llvm/trunk/test/CodeGen/PowerPC/stacksize.ll @@ -0,0 +1,86 @@ +; For ELFv2 ABI, we can avoid allocating the parameter area in the stack frame of the caller function +; if all the arguments can be passed to the callee in registers. +; For ELFv1 ABI, we always need to allocate the parameter area. + +; Tests for ELFv2 ABI +; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu -target-abi elfv2 < %s | FileCheck %s -check-prefix=PPC64-ELFV2 +; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu -target-abi elfv2 < %s | FileCheck %s -check-prefix=PPC64-ELFV2 + +; Tests for ELFv1 ABI +; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu -target-abi elfv1 < %s | FileCheck %s -check-prefix=PPC64-ELFV1 +; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu -target-abi elfv1 < %s | FileCheck %s -check-prefix=PPC64-ELFV1 + +; If the callee has at most eight integer args, parameter area can be ommited for ELFv2 ABI. + +; PPC64-ELFV2-LABEL: WithoutParamArea1: +; PPC64-ELFV2-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV2: stdu 1, -32(1) +; PPC64-ELFV2: addi 1, 1, 32 +; PPC64-ELFV2-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1-LABEL: WithoutParamArea1: +; PPC64-ELFV1-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1: stdu 1, -112(1) +; PPC64-ELFV1: addi 1, 1, 112 +; PPC64-ELFV1-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +define signext i32 @WithoutParamArea1(i32 signext %a) local_unnamed_addr #0 { +entry: + %call = tail call signext i32 @onearg(i32 signext %a) #2 + ret i32 %call +} + +; PPC64-ELFV2-LABEL: WithoutParamArea2: +; PPC64-ELFV2-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV2: stdu 1, -32(1) +; PPC64-ELFV2: addi 1, 1, 32 +; PPC64-ELFV2-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1-LABEL: WithoutParamArea2: +; PPC64-ELFV1-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1: stdu 1, -112(1) +; PPC64-ELFV1: addi 1, 1, 112 +; PPC64-ELFV1-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +define signext i32 @WithoutParamArea2(i32 signext %a) local_unnamed_addr #0 { +entry: + %call = tail call signext i32 @eightargs(i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a) #2 + ret i32 %call +} + +; If the callee has more than eight integer args or variable number of args, +; parameter area cannot be ommited even for ELFv2 ABI + +; PPC64-ELFV2-LABEL: WithParamArea1: +; PPC64-ELFV2-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV2: stdu 1, -96(1) +; PPC64-ELFV2: addi 1, 1, 96 +; PPC64-ELFV2-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1-LABEL: WithParamArea1: +; PPC64-ELFV1-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1: stdu 1, -112(1) +; PPC64-ELFV1: addi 1, 1, 112 +; PPC64-ELFV1-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +define signext i32 @WithParamArea1(i32 signext %a) local_unnamed_addr #0 { +entry: + %call = tail call signext i32 (i32, ...) @varargs(i32 signext %a, i32 signext %a) #2 + ret i32 %call +} + +; PPC64-ELFV2-LABEL: WithParamArea2: +; PPC64-ELFV2-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV2: stdu 1, -112(1) +; PPC64-ELFV2: addi 1, 1, 112 +; PPC64-ELFV2-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1-LABEL: WithParamArea2: +; PPC64-ELFV1-NOT: stw {{[0-9]+}}, -{{[0-9]+}}(1) +; PPC64-ELFV1: stdu 1, -128(1) +; PPC64-ELFV1: addi 1, 1, 128 +; PPC64-ELFV1-NOT: lwz {{[0-9]+}}, -{{[0-9]+}}(1) +define signext i32 @WithParamArea2(i32 signext %a) local_unnamed_addr #0 { +entry: + %call = tail call signext i32 @nineargs(i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a, i32 signext %a) #2 + ret i32 %call +} + +declare signext i32 @onearg(i32 signext) local_unnamed_addr #1 +declare signext i32 @eightargs(i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext) local_unnamed_addr #1 +declare signext i32 @nineargs(i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext) local_unnamed_addr #1 +declare signext i32 @varargs(i32 signext, ...) local_unnamed_addr #1 +