diff --git a/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp b/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp --- a/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp +++ b/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp @@ -1343,8 +1343,8 @@ .addReg(DstReg) .addReg(ZERO_REGISTER); - // SREG is always implicitly killed - MIB->getOperand(2).setIsKill(); + MIB->getOperand(3).setIsDead(); // SREG is always dead + MIB->getOperand(4).setIsKill(); // SREG is always implicitly killed MI.eraseFromParent(); return true; diff --git a/llvm/lib/Target/AVR/AVRFrameLowering.cpp b/llvm/lib/Target/AVR/AVRFrameLowering.cpp --- a/llvm/lib/Target/AVR/AVRFrameLowering.cpp +++ b/llvm/lib/Target/AVR/AVRFrameLowering.cpp @@ -56,6 +56,7 @@ const AVRSubtarget &STI = MF.getSubtarget(); const AVRInstrInfo &TII = *STI.getInstrInfo(); const AVRMachineFunctionInfo *AFI = MF.getInfo(); + const MachineRegisterInfo &MRI = MF.getRegInfo(); bool HasFP = hasFP(MF); // Interrupt handlers re-enable interrupts in function entry. @@ -68,8 +69,8 @@ // Emit special prologue code to save R1, R0 and SREG in interrupt/signal // handlers before saving any other registers. if (AFI->isInterruptOrSignalHandler()) { - BuildMI(MBB, MBBI, DL, TII.get(AVR::PUSHWRr)) - .addReg(AVR::R1R0, RegState::Kill) + BuildMI(MBB, MBBI, DL, TII.get(AVR::PUSHRr)) + .addReg(AVR::R0, RegState::Kill) .setMIFlag(MachineInstr::FrameSetup); BuildMI(MBB, MBBI, DL, TII.get(AVR::INRdA), AVR::R0) @@ -78,11 +79,16 @@ BuildMI(MBB, MBBI, DL, TII.get(AVR::PUSHRr)) .addReg(AVR::R0, RegState::Kill) .setMIFlag(MachineInstr::FrameSetup); - BuildMI(MBB, MBBI, DL, TII.get(AVR::EORRdRr)) - .addReg(AVR::R1, RegState::Define) - .addReg(AVR::R1, RegState::Kill) - .addReg(AVR::R1, RegState::Kill) - .setMIFlag(MachineInstr::FrameSetup); + if (!MRI.reg_empty(AVR::R1)) { + BuildMI(MBB, MBBI, DL, TII.get(AVR::PUSHRr)) + .addReg(AVR::R1, RegState::Kill) + .setMIFlag(MachineInstr::FrameSetup); + BuildMI(MBB, MBBI, DL, TII.get(AVR::EORRdRr)) + .addReg(AVR::R1, RegState::Define) + .addReg(AVR::R1, RegState::Kill) + .addReg(AVR::R1, RegState::Kill) + .setMIFlag(MachineInstr::FrameSetup); + } } // Early exit if the frame pointer is not needed in this function. @@ -132,6 +138,7 @@ static void restoreStatusRegister(MachineFunction &MF, MachineBasicBlock &MBB) { const AVRMachineFunctionInfo *AFI = MF.getInfo(); + const MachineRegisterInfo &MRI = MF.getRegInfo(); MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr(); @@ -142,11 +149,14 @@ // Emit special epilogue code to restore R1, R0 and SREG in interrupt/signal // handlers at the very end of the function, just before reti. if (AFI->isInterruptOrSignalHandler()) { + if (!MRI.reg_empty(AVR::R1)) { + BuildMI(MBB, MBBI, DL, TII.get(AVR::POPRd), AVR::R1); + } BuildMI(MBB, MBBI, DL, TII.get(AVR::POPRd), AVR::R0); BuildMI(MBB, MBBI, DL, TII.get(AVR::OUTARr)) .addImm(0x3f) .addReg(AVR::R0, RegState::Kill); - BuildMI(MBB, MBBI, DL, TII.get(AVR::POPWRd), AVR::R1R0); + BuildMI(MBB, MBBI, DL, TII.get(AVR::POPRd), AVR::R0); } } diff --git a/llvm/lib/Target/AVR/AVRISelDAGToDAG.cpp b/llvm/lib/Target/AVR/AVRISelDAGToDAG.cpp --- a/llvm/lib/Target/AVR/AVRISelDAGToDAG.cpp +++ b/llvm/lib/Target/AVR/AVRISelDAGToDAG.cpp @@ -431,6 +431,10 @@ SmallVector Ops; Ops.push_back(CurDAG->getRegister(AVR::R31R30, MVT::i16)); + // The R1 register must be passed as an implicit register so that R1 is + // correctly zeroed in interrupts. + Ops.push_back(CurDAG->getRegister(AVR::R1, MVT::i8)); + // Map all operands into the new node. for (unsigned i = 2, e = LastOpNum + 1; i != e; ++i) { Ops.push_back(N->getOperand(i)); diff --git a/llvm/lib/Target/AVR/AVRISelLowering.cpp b/llvm/lib/Target/AVR/AVRISelLowering.cpp --- a/llvm/lib/Target/AVR/AVRISelLowering.cpp +++ b/llvm/lib/Target/AVR/AVRISelLowering.cpp @@ -56,6 +56,8 @@ setOperationAction(ISD::DYNAMIC_STACKALLOC, MVT::i8, Expand); setOperationAction(ISD::DYNAMIC_STACKALLOC, MVT::i16, Expand); + setOperationAction(ISD::INLINEASM, MVT::Other, Custom); + for (MVT VT : MVT::integer_valuetypes()) { for (auto N : {ISD::EXTLOAD, ISD::SEXTLOAD, ISD::ZEXTLOAD}) { setLoadExtAction(N, VT, MVT::i1, Promote); @@ -816,6 +818,52 @@ MachinePointerInfo(SV)); } +// Modify the existing ISD::INLINEASM node to add the implicit register r1. +SDValue AVRTargetLowering::LowerINLINEASM(SDValue Op, SelectionDAG &DAG) const { + SDValue R1Reg = DAG.getRegister(AVR::R1, MVT::i8); + if (Op.getOperand(Op.getNumOperands() - 1) == R1Reg || + Op.getOperand(Op.getNumOperands() - 2) == R1Reg) { + // R1 has already been added. Don't add it again. + // If this isn't handled, we get called over and over again. + return Op; + } + + // Get a list of operands to the new INLINEASM node. This is mostly a copy, + // with some edits. + // Add the following operands at the end (but before the glue node, if it's + // there): + // - The flags of the operand (input operand, one register). + // - The register itself. + SDLoc dl(Op); + SmallVector Ops; + SDNode *N = Op.getNode(); + SDValue Glue; + for (unsigned I = 0; I < N->getNumOperands(); I++) { + SDValue Operand = N->getOperand(I); + if (Operand.getValueType() == MVT::Glue) { + // The glue operand always needs to be at the end, so we need to treat it + // specially. + Glue = Operand; + continue; + } + Ops.push_back(Operand); + } + unsigned Flags = InlineAsm::getFlagWord(InlineAsm::Kind_RegUse, 1); + Ops.push_back(DAG.getTargetConstant(Flags, dl, MVT::i32)); + Ops.push_back(R1Reg); + if (Glue) { + Ops.push_back(Glue); + } + + // Replace the current INLINEASM node with a new one that has R1 as implicit + // parameter. + SDValue New = DAG.getNode(N->getOpcode(), dl, N->getVTList(), Ops); + DAG.ReplaceAllUsesOfValueWith(Op, New); + DAG.ReplaceAllUsesOfValueWith(Op.getValue(1), New.getValue(1)); + + return New; +} + SDValue AVRTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const { switch (Op.getOpcode()) { default: @@ -841,6 +889,8 @@ case ISD::SDIVREM: case ISD::UDIVREM: return LowerDivRem(Op, DAG); + case ISD::INLINEASM: + return LowerINLINEASM(Op, DAG); } return SDValue(); @@ -1399,6 +1449,10 @@ Ops.push_back(DAG.getRegister(Reg.first, Reg.second.getValueType())); } + // The R1 register must be passed as an implicit register so that R1 is + // correctly zeroed in interrupts. + Ops.push_back(DAG.getRegister(AVR::R1, MVT::i8)); + // Add a register mask operand representing the call-preserved registers. const TargetRegisterInfo *TRI = Subtarget.getRegisterInfo(); const uint32_t *Mask = @@ -1520,6 +1574,14 @@ const AVRMachineFunctionInfo *AFI = MF.getInfo(); + if (!AFI->isInterruptOrSignalHandler()) { + // The return instruction has an implicit R1 operand: it must contain zero + // on return. + // This is not needed in interrupts however, where R1 is handled specially + // (only pushed/popped when needed). + RetOps.push_back(DAG.getRegister(AVR::R1, MVT::i8)); + } + unsigned RetOpc = AFI->isInterruptOrSignalHandler() ? AVRISD::RETI_FLAG : AVRISD::RET_FLAG; diff --git a/llvm/lib/Target/AVR/AVRInstrInfo.td b/llvm/lib/Target/AVR/AVRInstrInfo.td --- a/llvm/lib/Target/AVR/AVRInstrInfo.td +++ b/llvm/lib/Target/AVR/AVRInstrInfo.td @@ -906,6 +906,7 @@ // neg Rd+1 // neg Rd // sbc Rd+1, r1 + let Uses = [R1] in def NEGWRd : Pseudo<(outs DREGS : $rd), (ins DREGS @@ -1980,6 +1981,7 @@ def ASRWLoRd : Pseudo<(outs DREGS:$rd), (ins DREGS:$src), "asrwlo\t$rd", [(set i16:$rd, (AVRasrlo i16:$src)), (implicit SREG)]>; + let Uses = [R1] in def ROLBRd : Pseudo<(outs GPR8 : $rd), (ins GPR8 diff --git a/llvm/test/CodeGen/AVR/interrupts.ll b/llvm/test/CodeGen/AVR/interrupts.ll --- a/llvm/test/CodeGen/AVR/interrupts.ll +++ b/llvm/test/CodeGen/AVR/interrupts.ll @@ -6,13 +6,10 @@ ; CHECK-LABEL: interrupt_handler: ; CHECK: sei ; CHECK-NEXT: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti ret void @@ -22,13 +19,10 @@ ; CHECK-LABEL: interrupt_handler_via_ir_attribute: ; CHECK: sei ; CHECK-NEXT: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti ret void @@ -38,13 +32,10 @@ ; CHECK-LABEL: signal_handler: ; CHECK-NOT: sei ; CHECK: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti ret void @@ -54,13 +45,10 @@ ; CHECK-LABEL: signal_handler_via_attribute: ; CHECK-NOT: sei ; CHECK: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti ret void @@ -70,10 +58,8 @@ ; CHECK-LABEL: interrupt_alloca: ; CHECK: sei ; CHECK-NEXT: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK: push r28 ; CHECK-NEXT: push r29 ; CHECK-NEXT: in r28, 61 @@ -94,7 +80,6 @@ ; CHECK-NEXT: pop r28 ; CHECK: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti alloca i8 @@ -104,10 +89,8 @@ define void @signal_handler_with_increment() #1 { ; CHECK-LABEL: signal_handler_with_increment: ; CHECK: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 -; CHECK-NEXT: clr r1 ; CHECK-NEXT: push r24 ; CHECK-NEXT: lds r24, count ; CHECK-NEXT: inc r24 @@ -115,7 +98,6 @@ ; CHECK-NEXT: pop r24 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti %old = load volatile i8, i8* @count @@ -124,6 +106,29 @@ ret void } +; Check that r1 is saved/restored and set to 0 when using inline assembly. +define void @signal_handler_with_asm() #1 { +; CHECK-LABEL: signal_handler_with_asm: +; CHECK: push r0 +; CHECK-NEXT: in r0, 63 +; CHECK-NEXT: push r0 +; CHECK-NEXT: push r1 +; CHECK-NEXT: clr r1 +; CHECK-NEXT: push r24 +; CHECK-NEXT: ldi +; ;APP +; CHECK: mov +; ;NO_APP +; CHECK: pop r24 +; CHECK-NEXT: pop r1 +; CHECK-NEXT: pop r0 +; CHECK-NEXT: out 63, r0 +; CHECK-NEXT: pop r0 +; CHECK-NEXT: reti + call i8 asm sideeffect "mov $0, $1", "=r,r"(i8 3) nounwind + ret void +} + declare void @foo() ; When a signal handler calls a function, it must push/pop all call clobbered @@ -131,9 +136,9 @@ define void @signal_handler_with_call() #1 { ; CHECK-LABEL: signal_handler_with_call: ; CHECK: push r0 -; CHECK-NEXT: push r1 ; CHECK-NEXT: in r0, 63 ; CHECK-NEXT: push r0 +; CHECK-NEXT: push r1 ; CHECK-NEXT: clr r1 ; CHECK-NEXT: push r18 ; CHECK-NEXT: push r19 @@ -160,9 +165,9 @@ ; CHECK-NEXT: pop r20 ; CHECK-NEXT: pop r19 ; CHECK-NEXT: pop r18 +; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: out 63, r0 -; CHECK-NEXT: pop r1 ; CHECK-NEXT: pop r0 ; CHECK-NEXT: reti call void @foo() diff --git a/llvm/test/CodeGen/AVR/pseudo/NEGWRd.mir b/llvm/test/CodeGen/AVR/pseudo/NEGWRd.mir --- a/llvm/test/CodeGen/AVR/pseudo/NEGWRd.mir +++ b/llvm/test/CodeGen/AVR/pseudo/NEGWRd.mir @@ -22,5 +22,5 @@ ; CHECK-NEXT: $r14 = NEGRd $r14 ; CHECK-NEXT: $r15 = SBCRdRr $r15, $r1, implicit-def $sreg, implicit killed $sreg - $r15r14 = NEGWRd $r15r14, implicit-def $sreg + $r15r14 = NEGWRd $r15r14, implicit-def $sreg, implicit $r1 ... diff --git a/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir b/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir @@ -0,0 +1,25 @@ +# RUN: llc -O0 -run-pass=avr-expand-pseudo %s -o - | FileCheck %s + +# This test checks the expansion of the 8-bit ROLB (rotate) pseudo instruction. + +--- | + target triple = "avr--" + define void @test_rolbrd() { + entry: + ret void + } +... + +--- +name: test_rolbrd +body: | + bb.0.entry: + liveins: $r14 + + ; CHECK-LABEL: test_rolbrd + + ; CHECK: $r14 = ADDRdRr $r14, $r14, implicit-def $sreg + ; CHECK-NEXT: $r14 = ADCRdRr $r14, $r1, implicit-def dead $sreg, implicit killed $sreg + + $r14 = ROLBRd $r14, implicit-def $sreg, implicit $r1 +... diff --git a/llvm/test/CodeGen/AVR/zeroreg.ll b/llvm/test/CodeGen/AVR/zeroreg.ll new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/AVR/zeroreg.ll @@ -0,0 +1,27 @@ +; RUN: llc -mattr=avr6,sram < %s -march=avr | FileCheck %s + +; This file tests whether the compiler correctly works with the r1 register, +; clearing it when needed. + +; Test regular use of r1 as a zero register. +; CHECK-LABEL: store8zero: +; CHECK: st {{[XYZ]}}, r1 +; CHECK-NEXT: mov r24, r1 +; CHECK-NEXT: ret +define i8 @store8zero(i8* %x) { + store i8 0, i8* %x + ret i8 0 +} + +; Test that mulitplication instructions (mul, muls, etc) clobber r1 and require +; a "clr r1" instruction. +; CHECK-LABEL: mul: +; CHECK: muls +; CHECK-NEXT: clr r1 +; CHECK-NEXT: st {{[XYZ]}}, r0 +; CHECK-NEXT: ret +define void @mul(i8* %ptr, i8 %n) { + %result = mul i8 %n, 3 + store i8 %result, i8* %ptr + ret void +}