Add jump table (switch statement and computed goto) support for BPF
backend.
A `gotox <reg>` insn is implemented and the `<reg>` holds the target
insn where the gotox will go.
For a switch statement like
```
...
switch (ctx->x) {
case 1: ret_user = 18; break;
case 20: ret_user = 6; break;
case 16: ret_user = 9; break;
case 6: ret_user = 16; break;
case 8: ret_user = 14; break;
case 30: ret_user = 2; break;
default: ret_user = 1; break;
}
...
```
and the final binary
```
The final binary:
4: 67 01 00 00 03 00 00 00 r1 <<= 0x3
5: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0x0 ll
0000000000000028: R_BPF_64_64 BPF.JT.0.0
7: 0f 12 00 00 00 00 00 00 r2 += r1
...
Symbol table:
4: 0000000000000000 240 OBJECT GLOBAL DEFAULT 4 BPF.JT.0.0
5: 0000000000000000 4 OBJECT GLOBAL DEFAULT 6 ret_user
6: 0000000000000000 0 NOTYPE GLOBAL DEFAULT UND bar
7: 00000000000000f0 256 OBJECT GLOBAL DEFAULT 4 BPF.JT.0.1
and
[ 4] .jumptables PROGBITS 0000000000000000 0001c8 0001f0 00 0 0 1
```
Note that for the above example, `-mllvm -bpf-min-jump-table-entries=5`
should be in compilation flags as the current default
bpf-min-jump-table-entries is 13. For example.
```
clang --target=bpf -mcpu=v4 -O2 -mllvm -bpf-min-jump-table-entries=5 -S -g test.c
```
For computed goto like
```
int foo(int a, int b) {
__label__ l1, l2, l3, l4;
void *jt1[] = {[0]=&&l1, [1]=&&l2};
void *jt2[] = {[0]=&&l3, [1]=&&l4};
int ret = 0;
goto *jt1[a % 2];
l1: ret += 1;
l2: ret += 3;
goto *jt2[b % 2];
l3: ret += 5;
l4: ret += 7;
return ret;
}
```
The final binary:
```
12: bf 23 20 00 00 00 00 00 r3 = (s32)r2
13: 67 03 00 00 03 00 00 00 r3 <<= 0x3
14: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0x0 ll
0000000000000070: R_BPF_64_64 BPF.JT.0.0
16: 0f 32 00 00 00 00 00 00 r2 += r3
17: bf 11 20 00 00 00 00 00 r1 = (s32)r1
18: 67 01 00 00 03 00 00 00 r1 <<= 0x3
19: 18 03 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r3 = 0x0 ll
0000000000000098: R_BPF_64_64 BPF.JT.0.1
21: 0f 13 00 00 00 00 00 00 r3 += r1
[ 4] .jumptables PROGBITS 0000000000000000 000160 000020 00 0 0 1
4: 0000000000000000 16 OBJECT GLOBAL DEFAULT 4 BPF.JT.0.0
5: 0000000000000010 16 OBJECT GLOBAL DEFAULT 4 BPF.JT.0.1
```
A more complicated test with both switch-statement triggered jump table
and compute gotos:
```
$ cat test3.c
struct simple_ctx {
int x;
int y;
int z;
};
int ret_user, ret_user2;
void bar(void);
int foo(struct simple_ctx *ctx, struct simple_ctx *ctx2, int a, int b)
{
__label__ l1, l2, l3, l4;
void *jt1[] = {[0]=&&l1, [1]=&&l2};
void *jt2[] = {[0]=&&l3, [1]=&&l4};
int ret = 0;
goto *jt1[a % 2];
l1: ret += 1;
l2: ret += 3;
goto *jt2[b % 2];
l3: ret += 5;
l4: ret += 7;
bar();
switch (ctx->x) {
case 1: ret_user = 18; break;
case 20: ret_user = 6; break;
case 16: ret_user = 9; break;
case 6: ret_user = 16; break;
case 8: ret_user = 14; break;
case 30: ret_user = 2; break;
default: ret_user = 1; break;
}
return ret;
}
```
Compile with
```
clang --target=bpf -mcpu=v4 -O2 -S test3.c
clang --target=bpf -mcpu=v4 -O2 -c test3.c
```
The binary:
```
/* For computed goto */
13: bf 42 20 00 00 00 00 00 r2 = (s32)r4
14: 67 02 00 00 03 00 00 00 r2 <<= 0x3
15: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0x0 ll
0000000000000078: R_BPF_64_64 BPF.JT.0.1
17: 0f 21 00 00 00 00 00 00 r1 += r2
18: bf 32 20 00 00 00 00 00 r2 = (s32)r3
19: 67 02 00 00 03 00 00 00 r2 <<= 0x3
20: 18 03 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r3 = 0x0 ll
00000000000000a0: R_BPF_64_64 BPF.JT.0.2
22: 0f 23 00 00 00 00 00 00 r3 += r2
/* For switch statement */
39: 67 01 00 00 03 00 00 00 r1 <<= 0x3
40: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0x0 ll
0000000000000140: R_BPF_64_64 BPF.JT.0.0
42: 0f 12 00 00 00 00 00 00 r2 += r1
```
You can see jump table symbols are all different.
212 lines
7.2 KiB
C++
212 lines
7.2 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 "BPFTargetLoweringObjectFile.h"
|
|
#include "BPFTargetTransformInfo.h"
|
|
#include "MCTargetDesc/BPFMCAsmInfo.h"
|
|
#include "TargetInfo/BPFTargetInfo.h"
|
|
#include "llvm/CodeGen/GlobalISel/IRTranslator.h"
|
|
#include "llvm/CodeGen/GlobalISel/InstructionSelect.h"
|
|
#include "llvm/CodeGen/GlobalISel/Legalizer.h"
|
|
#include "llvm/CodeGen/GlobalISel/RegBankSelect.h"
|
|
#include "llvm/CodeGen/Passes.h"
|
|
#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
|
|
#include "llvm/CodeGen/TargetPassConfig.h"
|
|
#include "llvm/IR/PassManager.h"
|
|
#include "llvm/InitializePasses.h"
|
|
#include "llvm/MC/TargetRegistry.h"
|
|
#include "llvm/Passes/PassBuilder.h"
|
|
#include "llvm/Support/Compiler.h"
|
|
#include "llvm/Target/TargetOptions.h"
|
|
#include "llvm/Transforms/Scalar.h"
|
|
#include "llvm/Transforms/Scalar/SimplifyCFG.h"
|
|
#include "llvm/Transforms/Utils/SimplifyCFGOptions.h"
|
|
#include <optional>
|
|
using namespace llvm;
|
|
|
|
static cl::
|
|
opt<bool> DisableMIPeephole("disable-bpf-peephole", cl::Hidden,
|
|
cl::desc("Disable machine peepholes for BPF"));
|
|
|
|
static cl::opt<bool>
|
|
DisableCheckUnreachable("bpf-disable-trap-unreachable", cl::Hidden,
|
|
cl::desc("Disable Trap Unreachable for BPF"));
|
|
|
|
extern "C" LLVM_ABI LLVM_EXTERNAL_VISIBILITY void LLVMInitializeBPFTarget() {
|
|
// Register the target.
|
|
RegisterTargetMachine<BPFTargetMachine> X(getTheBPFleTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Y(getTheBPFbeTarget());
|
|
RegisterTargetMachine<BPFTargetMachine> Z(getTheBPFTarget());
|
|
|
|
PassRegistry &PR = *PassRegistry::getPassRegistry();
|
|
initializeGlobalISel(PR);
|
|
initializeBPFAsmPrinterPass(PR);
|
|
initializeBPFCheckAndAdjustIRPass(PR);
|
|
initializeBPFMIPeepholePass(PR);
|
|
initializeBPFMIPreEmitPeepholePass(PR);
|
|
initializeBPFDAGToDAGISelLegacyPass(PR);
|
|
initializeBPFMISimplifyPatchablePass(PR);
|
|
initializeBPFMIPreEmitCheckingPass(PR);
|
|
}
|
|
|
|
static Reloc::Model getEffectiveRelocModel(std::optional<Reloc::Model> RM) {
|
|
return RM.value_or(Reloc::PIC_);
|
|
}
|
|
|
|
BPFTargetMachine::BPFTargetMachine(const Target &T, const Triple &TT,
|
|
StringRef CPU, StringRef FS,
|
|
const TargetOptions &Options,
|
|
std::optional<Reloc::Model> RM,
|
|
std::optional<CodeModel::Model> CM,
|
|
CodeGenOptLevel OL, bool JIT)
|
|
: CodeGenTargetMachineImpl(T, TT.computeDataLayout(), TT, CPU, FS, Options,
|
|
getEffectiveRelocModel(RM),
|
|
getEffectiveCodeModel(CM, CodeModel::Small), OL),
|
|
TLOF(std::make_unique<BPFTargetLoweringObjectFileELF>()),
|
|
Subtarget(TT, std::string(CPU), std::string(FS), *this) {
|
|
if (!DisableCheckUnreachable) {
|
|
this->Options.TrapUnreachable = true;
|
|
this->Options.NoTrapAfterNoreturn = true;
|
|
}
|
|
|
|
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;
|
|
|
|
bool addIRTranslator() override;
|
|
bool addLegalizeMachineIR() override;
|
|
bool addRegBankSelect() override;
|
|
bool addGlobalInstructionSelect() override;
|
|
};
|
|
}
|
|
|
|
TargetPassConfig *BPFTargetMachine::createPassConfig(PassManagerBase &PM) {
|
|
return new BPFPassConfig(*this, PM);
|
|
}
|
|
|
|
static Expected<bool> parseBPFPreserveStaticOffsetOptions(StringRef Params) {
|
|
return PassBuilder::parseSinglePassOption(Params, "allow-partial",
|
|
"BPFPreserveStaticOffsetPass");
|
|
}
|
|
|
|
void BPFTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) {
|
|
#define GET_PASS_REGISTRY "BPFPassRegistry.def"
|
|
#include "llvm/Passes/TargetPassRegistry.inc"
|
|
|
|
PB.registerPipelineStartEPCallback(
|
|
[=](ModulePassManager &MPM, OptimizationLevel) {
|
|
FunctionPassManager FPM;
|
|
FPM.addPass(BPFPreserveStaticOffsetPass(true));
|
|
FPM.addPass(BPFAbstractMemberAccessPass(this));
|
|
FPM.addPass(BPFPreserveDITypePass());
|
|
FPM.addPass(BPFIRPeepholePass());
|
|
MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
|
|
});
|
|
PB.registerPeepholeEPCallback([=](FunctionPassManager &FPM,
|
|
OptimizationLevel Level) {
|
|
FPM.addPass(SimplifyCFGPass(SimplifyCFGOptions().hoistCommonInsts(true)));
|
|
FPM.addPass(BPFASpaceCastSimplifyPass());
|
|
});
|
|
PB.registerScalarOptimizerLateEPCallback(
|
|
[=](FunctionPassManager &FPM, OptimizationLevel Level) {
|
|
// Run this after loop unrolling but before
|
|
// SimplifyCFGPass(... .sinkCommonInsts(true))
|
|
FPM.addPass(BPFPreserveStaticOffsetPass(false));
|
|
});
|
|
PB.registerPipelineEarlySimplificationEPCallback(
|
|
[=](ModulePassManager &MPM, OptimizationLevel, ThinOrFullLTOPhase) {
|
|
MPM.addPass(BPFAdjustOptPass());
|
|
});
|
|
}
|
|
|
|
void BPFPassConfig::addIRPasses() {
|
|
addPass(createAtomicExpandLegacyPass());
|
|
addPass(createBPFCheckAndAdjustIR());
|
|
|
|
TargetPassConfig::addIRPasses();
|
|
}
|
|
|
|
TargetTransformInfo
|
|
BPFTargetMachine::getTargetTransformInfo(const Function &F) const {
|
|
return TargetTransformInfo(std::make_unique<BPFTTIImpl>(this, F));
|
|
}
|
|
|
|
// 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());
|
|
}
|
|
}
|
|
|
|
void BPFPassConfig::addPreEmitPass() {
|
|
addPass(createBPFMIPreEmitCheckingPass());
|
|
if (getOptLevel() != CodeGenOptLevel::None)
|
|
if (!DisableMIPeephole)
|
|
addPass(createBPFMIPreEmitPeepholePass());
|
|
}
|
|
|
|
bool BPFPassConfig::addIRTranslator() {
|
|
addPass(new IRTranslator());
|
|
return false;
|
|
}
|
|
|
|
bool BPFPassConfig::addLegalizeMachineIR() {
|
|
addPass(new Legalizer());
|
|
return false;
|
|
}
|
|
|
|
bool BPFPassConfig::addRegBankSelect() {
|
|
addPass(new RegBankSelect());
|
|
return false;
|
|
}
|
|
|
|
bool BPFPassConfig::addGlobalInstructionSelect() {
|
|
addPass(new InstructionSelect(getOptLevel()));
|
|
return false;
|
|
}
|