In [1], a few new insns are proposed to expand BPF ISA to
. fixing the limitation of existing insn (e.g., 16bit jmp offset)
. adding new insns which may improve code quality
(sign_ext_ld, sign_ext_mov, st)
. feature complete (sdiv, smod)
. better user experience (bswap)
This patch implemented insn encoding for
. sign-extended load
. sign-extended mov
. sdiv/smod
. bswap insns
. unconditional jump with 32bit offset
The new bswap insns are generated under cpu=v4 for __builtin_bswap.
For cpu=v3 or earlier, for __builtin_bswap, be or le insns are generated
which is not intuitive for the user.
To support 32-bit branch offset, a 32-bit ja (JMPL) insn is implemented.
For conditional branch which is beyond 16-bit offset, llvm will do
some transformation 'cond_jmp' -> 'cond_jmp + jmpl' to simulate 32bit
conditional jmp. See BPFMIPeephole.cpp for details. The algorithm is
hueristic based. I have tested bpf selftest pyperf600 with unroll account
600 which can indeed generate 32-bit jump insn, e.g.,
13: 06 00 00 00 9b cd 00 00 gotol +0xcd9b <LBB0_6619>
Eduard is working on to add 'st' insn to cpu=v4.
A list of llc flags:
disable-ldsx, disable-movsx, disable-bswap,
disable-sdiv-smod, disable-gotol
can be used to disable a particular insn for cpu v4.
For example, user can do:
llc -march=bpf -mcpu=v4 -disable-movsx t.ll
to enable cpu v4 without movsx insns.
References:
[1] https://lore.kernel.org/bpf/4bfe98be-5333-1c7e-2f6d-42486c8ec039@meta.com/
Differential Revision: https://reviews.llvm.org/D144829
173 lines
6.2 KiB
C++
173 lines
6.2 KiB
C++
//===-- BPFMCCodeEmitter.cpp - Convert BPF code to machine code -----------===//
|
|
//
|
|
// 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 implements the BPFMCCodeEmitter class.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "MCTargetDesc/BPFMCFixups.h"
|
|
#include "MCTargetDesc/BPFMCTargetDesc.h"
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/MC/MCCodeEmitter.h"
|
|
#include "llvm/MC/MCExpr.h"
|
|
#include "llvm/MC/MCFixup.h"
|
|
#include "llvm/MC/MCInst.h"
|
|
#include "llvm/MC/MCInstrInfo.h"
|
|
#include "llvm/MC/MCRegisterInfo.h"
|
|
#include "llvm/MC/MCSubtargetInfo.h"
|
|
#include "llvm/Support/Endian.h"
|
|
#include "llvm/Support/EndianStream.h"
|
|
#include <cassert>
|
|
#include <cstdint>
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "mccodeemitter"
|
|
|
|
namespace {
|
|
|
|
class BPFMCCodeEmitter : public MCCodeEmitter {
|
|
const MCRegisterInfo &MRI;
|
|
bool IsLittleEndian;
|
|
|
|
public:
|
|
BPFMCCodeEmitter(const MCInstrInfo &, const MCRegisterInfo &mri,
|
|
bool IsLittleEndian)
|
|
: MRI(mri), IsLittleEndian(IsLittleEndian) { }
|
|
BPFMCCodeEmitter(const BPFMCCodeEmitter &) = delete;
|
|
void operator=(const BPFMCCodeEmitter &) = delete;
|
|
~BPFMCCodeEmitter() override = default;
|
|
|
|
// getBinaryCodeForInstr - TableGen'erated function for getting the
|
|
// binary encoding for an instruction.
|
|
uint64_t getBinaryCodeForInstr(const MCInst &MI,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const;
|
|
|
|
// getMachineOpValue - Return binary encoding of operand. If the machin
|
|
// operand requires relocation, record the relocation and return zero.
|
|
unsigned getMachineOpValue(const MCInst &MI, const MCOperand &MO,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const;
|
|
|
|
uint64_t getMemoryOpValue(const MCInst &MI, unsigned Op,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const;
|
|
|
|
void encodeInstruction(const MCInst &MI, SmallVectorImpl<char> &CB,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const override;
|
|
};
|
|
|
|
} // end anonymous namespace
|
|
|
|
MCCodeEmitter *llvm::createBPFMCCodeEmitter(const MCInstrInfo &MCII,
|
|
MCContext &Ctx) {
|
|
return new BPFMCCodeEmitter(MCII, *Ctx.getRegisterInfo(), true);
|
|
}
|
|
|
|
MCCodeEmitter *llvm::createBPFbeMCCodeEmitter(const MCInstrInfo &MCII,
|
|
MCContext &Ctx) {
|
|
return new BPFMCCodeEmitter(MCII, *Ctx.getRegisterInfo(), false);
|
|
}
|
|
|
|
unsigned BPFMCCodeEmitter::getMachineOpValue(const MCInst &MI,
|
|
const MCOperand &MO,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const {
|
|
if (MO.isReg())
|
|
return MRI.getEncodingValue(MO.getReg());
|
|
if (MO.isImm())
|
|
return static_cast<unsigned>(MO.getImm());
|
|
|
|
assert(MO.isExpr());
|
|
|
|
const MCExpr *Expr = MO.getExpr();
|
|
|
|
assert(Expr->getKind() == MCExpr::SymbolRef);
|
|
|
|
if (MI.getOpcode() == BPF::JAL)
|
|
// func call name
|
|
Fixups.push_back(MCFixup::create(0, Expr, FK_PCRel_4));
|
|
else if (MI.getOpcode() == BPF::LD_imm64)
|
|
Fixups.push_back(MCFixup::create(0, Expr, FK_SecRel_8));
|
|
else if (MI.getOpcode() == BPF::JMPL)
|
|
Fixups.push_back(MCFixup::create(0, Expr, (MCFixupKind)BPF::FK_BPF_PCRel_4));
|
|
else
|
|
// bb label
|
|
Fixups.push_back(MCFixup::create(0, Expr, FK_PCRel_2));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static uint8_t SwapBits(uint8_t Val)
|
|
{
|
|
return (Val & 0x0F) << 4 | (Val & 0xF0) >> 4;
|
|
}
|
|
|
|
void BPFMCCodeEmitter::encodeInstruction(const MCInst &MI,
|
|
SmallVectorImpl<char> &CB,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const {
|
|
unsigned Opcode = MI.getOpcode();
|
|
raw_svector_ostream OS(CB);
|
|
support::endian::Writer OSE(OS,
|
|
IsLittleEndian ? support::little : support::big);
|
|
|
|
if (Opcode == BPF::LD_imm64 || Opcode == BPF::LD_pseudo) {
|
|
uint64_t Value = getBinaryCodeForInstr(MI, Fixups, STI);
|
|
CB.push_back(Value >> 56);
|
|
if (IsLittleEndian)
|
|
CB.push_back((Value >> 48) & 0xff);
|
|
else
|
|
CB.push_back(SwapBits((Value >> 48) & 0xff));
|
|
OSE.write<uint16_t>(0);
|
|
OSE.write<uint32_t>(Value & 0xffffFFFF);
|
|
|
|
const MCOperand &MO = MI.getOperand(1);
|
|
uint64_t Imm = MO.isImm() ? MO.getImm() : 0;
|
|
OSE.write<uint8_t>(0);
|
|
OSE.write<uint8_t>(0);
|
|
OSE.write<uint16_t>(0);
|
|
OSE.write<uint32_t>(Imm >> 32);
|
|
} else {
|
|
// Get instruction encoding and emit it
|
|
uint64_t Value = getBinaryCodeForInstr(MI, Fixups, STI);
|
|
CB.push_back(Value >> 56);
|
|
if (IsLittleEndian)
|
|
CB.push_back(char((Value >> 48) & 0xff));
|
|
else
|
|
CB.push_back(SwapBits((Value >> 48) & 0xff));
|
|
OSE.write<uint16_t>((Value >> 32) & 0xffff);
|
|
OSE.write<uint32_t>(Value & 0xffffFFFF);
|
|
}
|
|
}
|
|
|
|
// Encode BPF Memory Operand
|
|
uint64_t BPFMCCodeEmitter::getMemoryOpValue(const MCInst &MI, unsigned Op,
|
|
SmallVectorImpl<MCFixup> &Fixups,
|
|
const MCSubtargetInfo &STI) const {
|
|
// For CMPXCHG instructions, output is implicitly in R0/W0,
|
|
// so memory operand starts from operand 0.
|
|
int MemOpStartIndex = 1, Opcode = MI.getOpcode();
|
|
if (Opcode == BPF::CMPXCHGW32 || Opcode == BPF::CMPXCHGD)
|
|
MemOpStartIndex = 0;
|
|
|
|
uint64_t Encoding;
|
|
const MCOperand Op1 = MI.getOperand(MemOpStartIndex);
|
|
assert(Op1.isReg() && "First operand is not register.");
|
|
Encoding = MRI.getEncodingValue(Op1.getReg());
|
|
Encoding <<= 16;
|
|
MCOperand Op2 = MI.getOperand(MemOpStartIndex + 1);
|
|
assert(Op2.isImm() && "Second operand is not immediate.");
|
|
Encoding |= Op2.getImm() & 0xffff;
|
|
return Encoding;
|
|
}
|
|
|
|
#include "BPFGenMCCodeEmitter.inc"
|