================ @@ -4052,3 +4193,192 @@ void AArch64FrameLowering::orderFrameObjects( dbgs() << "\n"; }); } + +/// Emit a loop to decrement SP until it is equal to TargetReg, with probes at +/// least every ProbeSize bytes. Returns an iterator of the first instruction +/// after the loop. The difference between SP and TargetReg must be an exact +/// multiple of ProbeSize. +MachineBasicBlock::iterator +AArch64FrameLowering::inlineStackProbeLoopExactMultiple( + MachineBasicBlock::iterator MBBI, int64_t ProbeSize, + Register TargetReg) const { + MachineBasicBlock &MBB = *MBBI->getParent(); + MachineFunction &MF = *MBB.getParent(); + const AArch64InstrInfo *TII = + MF.getSubtarget<AArch64Subtarget>().getInstrInfo(); + DebugLoc DL = MBB.findDebugLoc(MBBI); + + MachineFunction::iterator MBBInsertPoint = std::next(MBB.getIterator()); + MachineBasicBlock *LoopMBB = MF.CreateMachineBasicBlock(MBB.getBasicBlock()); + MF.insert(MBBInsertPoint, LoopMBB); + MachineBasicBlock *ExitMBB = MF.CreateMachineBasicBlock(MBB.getBasicBlock()); + MF.insert(MBBInsertPoint, ExitMBB); + + // SUB SP, SP, #ProbeSize (or equivalent if ProbeSize is not encodable + // in SUB). + emitFrameOffset(*LoopMBB, LoopMBB->end(), DL, AArch64::SP, AArch64::SP, + StackOffset::getFixed(-ProbeSize), TII, + MachineInstr::FrameSetup); + // STR XZR, [SP] + BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::STRXui)) + .addReg(AArch64::XZR) + .addReg(AArch64::SP) + .addImm(0) + .setMIFlags(MachineInstr::FrameSetup); + // CMP SP, TargetReg + BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::SUBSXrx64), + AArch64::XZR) + .addReg(AArch64::SP) + .addReg(TargetReg) + .addImm(AArch64_AM::getArithExtendImm(AArch64_AM::UXTX, 0)) + .setMIFlags(MachineInstr::FrameSetup); + // B.CC Loop + BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::Bcc)) + .addImm(AArch64CC::NE) + .addMBB(LoopMBB) + .setMIFlags(MachineInstr::FrameSetup); + + LoopMBB->addSuccessor(ExitMBB); + LoopMBB->addSuccessor(LoopMBB); + // Synthesize the exit MBB. + ExitMBB->splice(ExitMBB->end(), &MBB, MBBI, MBB.end()); + ExitMBB->transferSuccessorsAndUpdatePHIs(&MBB); + MBB.addSuccessor(LoopMBB); + // Update liveins. + recomputeLiveIns(*LoopMBB); + recomputeLiveIns(*ExitMBB); + + return ExitMBB->begin(); +} + +MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeFixed( + MachineBasicBlock::iterator MBBI, Register ScratchReg, int64_t FrameSize, + StackOffset CFAOffset) const { + MachineBasicBlock *MBB = MBBI->getParent(); + MachineFunction &MF = *MBB->getParent(); + const AArch64TargetLowering *TLI = + MF.getSubtarget<AArch64Subtarget>().getTargetLowering(); + const AArch64InstrInfo *TII = + MF.getSubtarget<AArch64Subtarget>().getInstrInfo(); + AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>(); + bool EmitAsyncCFI = AFI->needsAsyncDwarfUnwindInfo(MF); + bool HasFP = hasFP(MF); + + DebugLoc DL; + int64_t ProbeSize = TLI->getStackProbeSize(MF); + int64_t NumBlocks = FrameSize / ProbeSize; + int64_t ResidualSize = FrameSize % ProbeSize; + + LLVM_DEBUG(dbgs() << "Stack probing: total " << FrameSize << " bytes, " + << NumBlocks << " blocks of " << ProbeSize + << " bytes, plus " << ResidualSize << " bytes\n"); + + // Decrement SP by NumBlock * ProbeSize bytes, with either unrolled or + // ordinary loop. + if (NumBlocks <= AArch64::StackProbeMaxLoopUnroll) { + for (int i = 0; i < NumBlocks; ++i) { + // SUB SP, SP, #FrameSize (or equivalent if FrameSize is not ---------------- momchil-velikov wrote:
Wrong comment (code is OK): ProbeSize, not FrameSize. https://github.com/llvm/llvm-project/pull/66524 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits