mirror of
https://github.com/RPCS3/llvm.git
synced 2026-01-31 01:25:19 +01:00
b41a9002cc
Currently, BPF backend is doing truncation elimination. If one truncation
is performed on a value defined by narrow loads, then it could be redundant
given BPF loads zero extend the destination register implicitly.
When the definition of the truncated value is a merging value (PHI node)
that could come from different code paths, then checks need to be done on
all possible code paths.
Above described optimization was introduced as r306685, however it doesn't
work when there is back-edge, for example when loop is used inside BPF
code.
For example for the following code, a zero-extended value should be stored
into b[i], but the "and reg, 0xffff" is wrongly eliminated which then
generates corrupted data.
void cal1(unsigned short *a, unsigned long *b, unsigned int k)
{
unsigned short e;
e = *a;
for (unsigned int i = 0; i < k; i++) {
b[i] = e;
e = ~e;
}
}
The reason is r306685 was trying to do the PHI node checks inside isel
DAG2DAG phase, and the checks are done on MachineInstr. This is actually
wrong, because MachineInstr is being built during isel phase and the
associated information is not completed yet. A quick search shows none
target other than BPF is access MachineInstr info during isel phase.
For an PHI node, when you reached it during isel phase, it may have all
predecessors linked, but not successors. It seems successors are linked to
PHI node only when doing SelectionDAGISel::FinishBasicBlock and this
happens later than PreprocessISelDAG hook.
Previously, BPF program doesn't allow loop, there is probably the reason
why this bug was not exposed.
This patch therefore fixes the bug by the following approach:
- The existing truncation elimination code and the associated
"load_to_vreg_" records are removed.
- Instead, implement truncation elimination using MachineSSA pass, this
is where all information are built, and keep the pass together with other
similar peephole optimizations inside BPFMIPeephole.cpp. Redundant move
elimination logic is updated accordingly.
- Unit testcase included + no compilation errors for kernel BPF selftest.
Patch Review
===
Patch was sent to and reviewed by BPF community at:
https://lore.kernel.org/bpf
Reported-by: David Beckett <david.beckett@netronome.com>
Reviewed-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@375007 91177308-0d34-0410-b5e6-96231b3b80d8
132 lines
4.3 KiB
C++
132 lines
4.3 KiB
C++
//===-- BPFTargetMachine.cpp - Define TargetMachine for BPF ---------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Implements the info about BPF target spec.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "BPFTargetMachine.h"
|
|
#include "BPF.h"
|
|
#include "MCTargetDesc/BPFMCAsmInfo.h"
|
|
#include "TargetInfo/BPFTargetInfo.h"
|
|
#include "llvm/CodeGen/Passes.h"
|
|
#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
|
|
#include "llvm/CodeGen/TargetPassConfig.h"
|
|
#include "llvm/IR/LegacyPassManager.h"
|
|
#include "llvm/Support/FormattedStream.h"
|
|
#include "llvm/Support/TargetRegistry.h"
|
|
#include "llvm/Target/TargetOptions.h"
|
|
using namespace llvm;
|
|
|
|
static cl::
|
|
opt<bool> DisableMIPeephole("disable-bpf-peephole", cl::Hidden,
|
|
cl::desc("Disable machine peepholes for BPF"));
|
|
|
|
extern "C" void LLVMInitializeBPFTarget() {
|
|
// Register the target.
|
|
RegisterTargetMachine<BPFTargetMachine> X(getTheBPFleTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Y(getTheBPFbeTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Z(getTheBPFTarget());
|
|
|
|
PassRegistry &PR = *PassRegistry::getPassRegistry();
|
|
initializeBPFAbstractMemberAccessPass(PR);
|
|
initializeBPFMIPeepholePass(PR);
|
|
initializeBPFMIPeepholeTruncElimPass(PR);
|
|
}
|
|
|
|
// DataLayout: little or big endian
|
|
static std::string computeDataLayout(const Triple &TT) {
|
|
if (TT.getArch() == Triple::bpfeb)
|
|
return "E-m:e-p:64:64-i64:64-n32:64-S128";
|
|
else
|
|
return "e-m:e-p:64:64-i64:64-n32:64-S128";
|
|
}
|
|
|
|
static Reloc::Model getEffectiveRelocModel(Optional<Reloc::Model> RM) {
|
|
if (!RM.hasValue())
|
|
return Reloc::PIC_;
|
|
return *RM;
|
|
}
|
|
|
|
BPFTargetMachine::BPFTargetMachine(const Target &T, const Triple &TT,
|
|
StringRef CPU, StringRef FS,
|
|
const TargetOptions &Options,
|
|
Optional<Reloc::Model> RM,
|
|
Optional<CodeModel::Model> CM,
|
|
CodeGenOpt::Level OL, bool JIT)
|
|
: LLVMTargetMachine(T, computeDataLayout(TT), TT, CPU, FS, Options,
|
|
getEffectiveRelocModel(RM),
|
|
getEffectiveCodeModel(CM, CodeModel::Small), OL),
|
|
TLOF(std::make_unique<TargetLoweringObjectFileELF>()),
|
|
Subtarget(TT, CPU, FS, *this) {
|
|
initAsmInfo();
|
|
|
|
BPFMCAsmInfo *MAI =
|
|
static_cast<BPFMCAsmInfo *>(const_cast<MCAsmInfo *>(AsmInfo.get()));
|
|
MAI->setDwarfUsesRelocationsAcrossSections(!Subtarget.getUseDwarfRIS());
|
|
}
|
|
|
|
namespace {
|
|
// BPF Code Generator Pass Configuration Options.
|
|
class BPFPassConfig : public TargetPassConfig {
|
|
public:
|
|
BPFPassConfig(BPFTargetMachine &TM, PassManagerBase &PM)
|
|
: TargetPassConfig(TM, PM) {}
|
|
|
|
BPFTargetMachine &getBPFTargetMachine() const {
|
|
return getTM<BPFTargetMachine>();
|
|
}
|
|
|
|
void addIRPasses() override;
|
|
bool addInstSelector() override;
|
|
void addMachineSSAOptimization() override;
|
|
void addPreEmitPass() override;
|
|
};
|
|
}
|
|
|
|
TargetPassConfig *BPFTargetMachine::createPassConfig(PassManagerBase &PM) {
|
|
return new BPFPassConfig(*this, PM);
|
|
}
|
|
|
|
void BPFPassConfig::addIRPasses() {
|
|
|
|
addPass(createBPFAbstractMemberAccess(&getBPFTargetMachine()));
|
|
|
|
TargetPassConfig::addIRPasses();
|
|
}
|
|
|
|
// Install an instruction selector pass using
|
|
// the ISelDag to gen BPF code.
|
|
bool BPFPassConfig::addInstSelector() {
|
|
addPass(createBPFISelDag(getBPFTargetMachine()));
|
|
|
|
return false;
|
|
}
|
|
|
|
void BPFPassConfig::addMachineSSAOptimization() {
|
|
addPass(createBPFMISimplifyPatchablePass());
|
|
|
|
// The default implementation must be called first as we want eBPF
|
|
// Peephole ran at last.
|
|
TargetPassConfig::addMachineSSAOptimization();
|
|
|
|
const BPFSubtarget *Subtarget = getBPFTargetMachine().getSubtargetImpl();
|
|
if (!DisableMIPeephole) {
|
|
if (Subtarget->getHasAlu32())
|
|
addPass(createBPFMIPeepholePass());
|
|
addPass(createBPFMIPeepholeTruncElimPass());
|
|
}
|
|
}
|
|
|
|
void BPFPassConfig::addPreEmitPass() {
|
|
addPass(createBPFMIPreEmitCheckingPass());
|
|
if (getOptLevel() != CodeGenOpt::None)
|
|
if (!DisableMIPeephole)
|
|
addPass(createBPFMIPreEmitPeepholePass());
|
|
}
|