llvm-project/llvm/lib/Target/BPF/BPFSubtarget.h
Peilin Ye 17bfc00f7c
[BPF] Add load-acquire and store-release instructions under -mcpu=v4 (#108636)
As discussed in [1], introduce BPF instructions with load-acquire and
store-release semantics under -mcpu=v4.  Define 2 new flags:

  BPF_LOAD_ACQ    0x100
  BPF_STORE_REL   0x110

A "load-acquire" is a BPF_STX | BPF_ATOMIC instruction with the 'imm'
field set to BPF_LOAD_ACQ (0x100).

Similarly, a "store-release" is a BPF_STX | BPF_ATOMIC instruction with
the 'imm' field set to BPF_STORE_REL (0x110).

Unlike existing atomic read-modify-write operations that only support
BPF_W (32-bit) and BPF_DW (64-bit) size modifiers, load-acquires and
store-releases also support BPF_B (8-bit) and BPF_H (16-bit).  An 8- or
16-bit load-acquire zero-extends the value before writing it to a 32-bit
register, just like ARM64 instruction LDAPRH and friends.

As an example (assuming little-endian):

  long foo(long *ptr) {
      return __atomic_load_n(ptr, __ATOMIC_ACQUIRE);
  }

foo() can be compiled to:

  db 10 00 00 00 01 00 00  r0 = load_acquire((u64 *)(r1 + 0x0))
  95 00 00 00 00 00 00 00  exit

  opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
  imm (0x00000100): BPF_LOAD_ACQ

Similarly:

  void bar(short *ptr, short val) {
      __atomic_store_n(ptr, val, __ATOMIC_RELEASE);
  }

bar() can be compiled to:

  cb 21 00 00 10 01 00 00  store_release((u16 *)(r1 + 0x0), w2)
  95 00 00 00 00 00 00 00  exit

  opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
  imm (0x00000110): BPF_STORE_REL

Inline assembly is also supported.

Add a pre-defined macro, __BPF_FEATURE_LOAD_ACQ_STORE_REL, to let
developers detect this new feature.  It can also be disabled using a new
llc option, -disable-load-acq-store-rel.

Using __ATOMIC_RELAXED for __atomic_store{,_n}() will generate a "plain"
store (BPF_MEM | BPF_STX) instruction:

  void foo(short *ptr, short val) {
      __atomic_store_n(ptr, val, __ATOMIC_RELAXED);
  }

  6b 21 00 00 00 00 00 00  *(u16 *)(r1 + 0x0) = w2
  95 00 00 00 00 00 00 00  exit

Similarly, using __ATOMIC_RELAXED for __atomic_load{,_n}() will generate
a zero-extending, "plain" load (BPF_MEM | BPF_LDX) instruction:

  int foo(char *ptr) {
      return __atomic_load_n(ptr, __ATOMIC_RELAXED);
  }

  71 11 00 00 00 00 00 00  w1 = *(u8 *)(r1 + 0x0)
  bc 10 08 00 00 00 00 00  w0 = (s8)w1
  95 00 00 00 00 00 00 00  exit

Currently __ATOMIC_CONSUME is an alias for __ATOMIC_ACQUIRE.  Using
__ATOMIC_SEQ_CST ("sequentially consistent") is not supported yet and
will cause an error:

  $ clang --target=bpf -mcpu=v4 -c bar.c > /dev/null
bar.c:1:5: error: sequentially consistent (seq_cst) atomic load/store is
not supported
1 | int foo(int *ptr) { return __atomic_load_n(ptr, __ATOMIC_SEQ_CST); }
      |     ^
  ...

Finally, rename those isST*() and isLD*() helper functions in
BPFMISimplifyPatchable.cpp based on what the instructions actually do,
rather than their instruction class.

[1]
https://lore.kernel.org/all/20240729183246.4110549-1-yepeilin@google.com/
2025-03-04 09:19:39 -08:00

122 lines
4.0 KiB
C++

//===-- BPFSubtarget.h - Define Subtarget for the BPF -----------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file declares the BPF specific subclass of TargetSubtargetInfo.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_BPF_BPFSUBTARGET_H
#define LLVM_LIB_TARGET_BPF_BPFSUBTARGET_H
#include "BPFFrameLowering.h"
#include "BPFISelLowering.h"
#include "BPFInstrInfo.h"
#include "BPFRegisterInfo.h"
#include "BPFSelectionDAGInfo.h"
#include "llvm/CodeGen/GlobalISel/CallLowering.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
#include "llvm/CodeGen/RegisterBankInfo.h"
#include "llvm/CodeGen/SelectionDAGTargetInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/Target/TargetMachine.h"
#define GET_SUBTARGETINFO_HEADER
#include "BPFGenSubtargetInfo.inc"
namespace llvm {
class StringRef;
class BPFSubtarget : public BPFGenSubtargetInfo {
virtual void anchor();
BPFInstrInfo InstrInfo;
BPFFrameLowering FrameLowering;
BPFTargetLowering TLInfo;
BPFSelectionDAGInfo TSInfo;
private:
void initializeEnvironment();
void initSubtargetFeatures(StringRef CPU, StringRef FS);
protected:
// unused
bool isDummyMode;
bool IsLittleEndian;
// whether the cpu supports jmp ext
bool HasJmpExt;
// whether the cpu supports jmp32 ext.
// NOTE: jmp32 is not enabled when alu32 enabled.
bool HasJmp32;
// whether the cpu supports alu32 instructions.
bool HasAlu32;
// whether we should enable MCAsmInfo DwarfUsesRelocationsAcrossSections
bool UseDwarfRIS;
// whether cpu v4 insns are enabled.
bool HasLdsx, HasMovsx, HasBswap, HasSdivSmod, HasGotol, HasStoreImm,
HasLoadAcqStoreRel;
std::unique_ptr<CallLowering> CallLoweringInfo;
std::unique_ptr<InstructionSelector> InstSelector;
std::unique_ptr<LegalizerInfo> Legalizer;
std::unique_ptr<RegisterBankInfo> RegBankInfo;
public:
// This constructor initializes the data members to match that
// of the specified triple.
BPFSubtarget(const Triple &TT, const std::string &CPU, const std::string &FS,
const TargetMachine &TM);
BPFSubtarget &initializeSubtargetDependencies(StringRef CPU, StringRef FS);
// ParseSubtargetFeatures - Parses features string setting specified
// subtarget options. Definition of function is auto generated by tblgen.
void ParseSubtargetFeatures(StringRef CPU, StringRef TuneCPU, StringRef FS);
bool getHasJmpExt() const { return HasJmpExt; }
bool getHasJmp32() const { return HasJmp32; }
bool getHasAlu32() const { return HasAlu32; }
bool getUseDwarfRIS() const { return UseDwarfRIS; }
bool hasLdsx() const { return HasLdsx; }
bool hasMovsx() const { return HasMovsx; }
bool hasBswap() const { return HasBswap; }
bool hasSdivSmod() const { return HasSdivSmod; }
bool hasGotol() const { return HasGotol; }
bool hasStoreImm() const { return HasStoreImm; }
bool hasLoadAcqStoreRel() const { return HasLoadAcqStoreRel; }
bool isLittleEndian() const { return IsLittleEndian; }
const BPFInstrInfo *getInstrInfo() const override { return &InstrInfo; }
const BPFFrameLowering *getFrameLowering() const override {
return &FrameLowering;
}
const BPFTargetLowering *getTargetLowering() const override {
return &TLInfo;
}
const BPFSelectionDAGInfo *getSelectionDAGInfo() const override {
return &TSInfo;
}
const BPFRegisterInfo *getRegisterInfo() const override {
return &InstrInfo.getRegisterInfo();
}
const CallLowering *getCallLowering() const override;
InstructionSelector *getInstructionSelector() const override;
const LegalizerInfo *getLegalizerInfo() const override;
const RegisterBankInfo *getRegBankInfo() const override;
};
} // End llvm namespace
#endif