Move abstractMemberAccess and PreserveDIType passes as early as
possible, right after clang code generation.
Currently, compiler may transform the above code
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
a = llvm.bpf.builtin.preserve_field_info(p2, EXIST);
if (a) {
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
bpf_probe_read(buf, buf_size, p2);
}
to
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
a = llvm.bpf.builtin.preserve_field_info(p2, EXIST);
if (a) {
bpf_probe_read(buf, buf_size, p2);
}
and eventually assembly code looks like
reloc_exist = 1;
reloc_member_offset = 10; //calculate member offset from base
p2 = base + reloc_member_offset;
if (reloc_exist) {
bpf_probe_read(bpf, buf_size, p2);
}
if during libbpf relocation resolution, reloc_exist is actually
resolved to 0 (not exist), reloc_member_offset relocation cannot
be resolved and will be patched with illegal instruction.
This will cause verifier failure.
This patch attempts to address this issue by do chaining
analysis and replace chains with special globals right
after clang code gen. This will remove the cse possibility
described in the above. The IR typically looks like
%6 = load @llvm.sk_buff:0:50$0:0:0:2:0
%7 = bitcast %struct.sk_buff* %2 to i8*
%8 = getelementptr i8, i8* %7, %6
for a particular address computation relocation.
But this transformation has another consequence, code sinking
may happen like below:
PHI = <possibly different @preserve_*_access_globals>
%7 = bitcast %struct.sk_buff* %2 to i8*
%8 = getelementptr i8, i8* %7, %6
For such cases, we will not able to generate relocations since
multiple relocations are merged into one.
This patch introduced a passthrough builtin
to prevent such optimization. Looks like inline assembly has more
impact for optimizaiton, e.g., inlining. Using passthrough has
less impact on optimizations.
A new IR pass is introduced at the beginning of target-dependent
IR optimization, which does:
- report fatal error if any reloc global in PHI nodes
- remove all bpf passthrough builtin functions
Changes for existing CORE tests:
- for clang tests, add "-Xclang -disable-llvm-passes" flags to
avoid builtin->reloc_global transformation so the test is still
able to check correctness for clang generated IR.
- for llvm CodeGen/BPF tests, add "opt -O2 <ir_file> | llvm-dis" command
before "llc" command since "opt" is needed to call newly-placed
builtin->reloc_global transformation. Add target triple in the IR
file since "opt" requires it.
- Since target triple is added in IR file, if a test may produce
different results for different endianness, two tests will be
created, one for bpfeb and another for bpfel, e.g., some tests
for relocation of lshift/rshift of bitfields.
- field-reloc-bitfield-1.ll has different relocations compared to
old codes. This is because for the structure in the test,
new code returns struct layout alignment 4 while old code
is 8. Align 8 is more precise and permits double load. With align 4,
the new mechanism uses 4-byte load, so generating different
relocations.
- test intrinsic-transforms.ll is removed. This is used to test
cse on intrinsics so we do not lose metadata. Now metadata is attached
to global and not instruction, it won't get lost with cse.
Differential Revision: https://reviews.llvm.org/D87153
151 lines
5.1 KiB
C++
151 lines
5.1 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"
|
|
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
|
|
#include "llvm/Transforms/Scalar.h"
|
|
#include "llvm/Transforms/Utils/SimplifyCFGOptions.h"
|
|
using namespace llvm;
|
|
|
|
static cl::
|
|
opt<bool> DisableMIPeephole("disable-bpf-peephole", cl::Hidden,
|
|
cl::desc("Disable machine peepholes for BPF"));
|
|
|
|
extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeBPFTarget() {
|
|
// Register the target.
|
|
RegisterTargetMachine<BPFTargetMachine> X(getTheBPFleTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Y(getTheBPFbeTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Z(getTheBPFTarget());
|
|
|
|
PassRegistry &PR = *PassRegistry::getPassRegistry();
|
|
initializeBPFAbstractMemberAccessPass(PR);
|
|
initializeBPFPreserveDITypePass(PR);
|
|
initializeBPFCheckAndAdjustIRPass(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-i128:128-n32:64-S128";
|
|
else
|
|
return "e-m:e-p:64:64-i64:64-i128:128-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, std::string(CPU), std::string(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 BPFTargetMachine::adjustPassManager(PassManagerBuilder &Builder) {
|
|
Builder.addExtension(
|
|
PassManagerBuilder::EP_EarlyAsPossible,
|
|
[&](const PassManagerBuilder &, legacy::PassManagerBase &PM) {
|
|
PM.add(createBPFAbstractMemberAccess(this));
|
|
PM.add(createBPFPreserveDIType());
|
|
});
|
|
|
|
Builder.addExtension(
|
|
PassManagerBuilder::EP_Peephole,
|
|
[&](const PassManagerBuilder &, legacy::PassManagerBase &PM) {
|
|
PM.add(createCFGSimplificationPass(
|
|
SimplifyCFGOptions().hoistCommonInsts(true)));
|
|
});
|
|
}
|
|
|
|
void BPFPassConfig::addIRPasses() {
|
|
addPass(createBPFCheckAndAdjustIR());
|
|
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());
|
|
}
|