Some BPF JIT backends would want to optimize memcpy in their own architecture specific way. However, at the moment, there is no way for JIT backends to see memcpy semantics in a reliable way. This is due to LLVM BPF backend is expanding memcpy into load/store sequences and could possibly schedule them apart from each other further. So, BPF JIT backends inside kernel can't reliably recognize memcpy semantics by peephole BPF sequence. This patch introduce new intrinsic expand infrastructure to memcpy. To get stable in-order load/store sequence from memcpy, we first lower memcpy into BPF::MEMCPY node which then expanded into in-order load/store sequences in expandPostRAPseudo pass which will happen after instruction scheduling. By this way, kernel JIT backends could reliably recognize memcpy through scanning BPF sequence. This new memcpy expand infrastructure is gated by a new option: -bpf-expand-memcpy-in-order Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Jiong Wang <jiong.wang@netronome.com> Signed-off-by: Yonghong Song <yhs@fb.com> llvm-svn: 337977
67 lines
2.4 KiB
C++
67 lines
2.4 KiB
C++
//===-- BPFInstrInfo.h - BPF Instruction Information ------------*- C++ -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains the BPF implementation of the TargetInstrInfo class.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_BPF_BPFINSTRINFO_H
|
|
#define LLVM_LIB_TARGET_BPF_BPFINSTRINFO_H
|
|
|
|
#include "BPFRegisterInfo.h"
|
|
#include "llvm/CodeGen/TargetInstrInfo.h"
|
|
|
|
#define GET_INSTRINFO_HEADER
|
|
#include "BPFGenInstrInfo.inc"
|
|
|
|
namespace llvm {
|
|
|
|
class BPFInstrInfo : public BPFGenInstrInfo {
|
|
const BPFRegisterInfo RI;
|
|
|
|
public:
|
|
BPFInstrInfo();
|
|
|
|
const BPFRegisterInfo &getRegisterInfo() const { return RI; }
|
|
|
|
void copyPhysReg(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
|
|
const DebugLoc &DL, unsigned DestReg, unsigned SrcReg,
|
|
bool KillSrc) const override;
|
|
|
|
bool expandPostRAPseudo(MachineInstr &MI) const override;
|
|
|
|
void storeRegToStackSlot(MachineBasicBlock &MBB,
|
|
MachineBasicBlock::iterator MBBI, unsigned SrcReg,
|
|
bool isKill, int FrameIndex,
|
|
const TargetRegisterClass *RC,
|
|
const TargetRegisterInfo *TRI) const override;
|
|
|
|
void loadRegFromStackSlot(MachineBasicBlock &MBB,
|
|
MachineBasicBlock::iterator MBBI, unsigned DestReg,
|
|
int FrameIndex, const TargetRegisterClass *RC,
|
|
const TargetRegisterInfo *TRI) const override;
|
|
bool analyzeBranch(MachineBasicBlock &MBB, MachineBasicBlock *&TBB,
|
|
MachineBasicBlock *&FBB,
|
|
SmallVectorImpl<MachineOperand> &Cond,
|
|
bool AllowModify) const override;
|
|
|
|
unsigned removeBranch(MachineBasicBlock &MBB,
|
|
int *BytesRemoved = nullptr) const override;
|
|
unsigned insertBranch(MachineBasicBlock &MBB, MachineBasicBlock *TBB,
|
|
MachineBasicBlock *FBB, ArrayRef<MachineOperand> Cond,
|
|
const DebugLoc &DL,
|
|
int *BytesAdded = nullptr) const override;
|
|
private:
|
|
void expandMEMCPY(MachineBasicBlock::iterator) const;
|
|
|
|
};
|
|
}
|
|
|
|
#endif
|