llvm-project/llvm/lib/Target/BPF/BPFAsmPrinter.cpp
yonghong-song c3fb2e1cee
[BPF] Support Jump Table (#149715)
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.
2025-09-16 09:27:08 -07:00

231 lines
7.3 KiB
C++

//===-- BPFAsmPrinter.cpp - BPF LLVM assembly writer ----------------------===//
//
// 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 contains a printer that converts from our internal representation
// of machine-dependent LLVM code to the BPF assembly language.
//
//===----------------------------------------------------------------------===//
#include "BPFAsmPrinter.h"
#include "BPF.h"
#include "BPFInstrInfo.h"
#include "BPFMCInstLower.h"
#include "BTFDebug.h"
#include "MCTargetDesc/BPFInstPrinter.h"
#include "TargetInfo/BPFTargetInfo.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineJumpTableInfo.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/IR/Module.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCExpr.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/MC/MCSymbolELF.h"
#include "llvm/MC/TargetRegistry.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
using namespace llvm;
#define DEBUG_TYPE "asm-printer"
bool BPFAsmPrinter::doInitialization(Module &M) {
AsmPrinter::doInitialization(M);
// Only emit BTF when debuginfo available.
if (MAI->doesSupportDebugInformation() && !M.debug_compile_units().empty()) {
BTF = new BTFDebug(this);
Handlers.push_back(std::unique_ptr<BTFDebug>(BTF));
}
return false;
}
const BPFTargetMachine &BPFAsmPrinter::getBTM() const {
return static_cast<const BPFTargetMachine &>(TM);
}
bool BPFAsmPrinter::doFinalization(Module &M) {
// Remove unused globals which are previously used for jump table.
const BPFSubtarget *Subtarget = getBTM().getSubtargetImpl();
if (Subtarget->hasGotox()) {
std::vector<GlobalVariable *> Targets;
for (GlobalVariable &Global : M.globals()) {
if (Global.getLinkage() != GlobalValue::PrivateLinkage)
continue;
if (!Global.isConstant() || !Global.hasInitializer())
continue;
Constant *CV = dyn_cast<Constant>(Global.getInitializer());
if (!CV)
continue;
ConstantArray *CA = dyn_cast<ConstantArray>(CV);
if (!CA)
continue;
for (unsigned i = 1, e = CA->getNumOperands(); i != e; ++i) {
if (!dyn_cast<BlockAddress>(CA->getOperand(i)))
continue;
}
Targets.push_back(&Global);
}
for (GlobalVariable *GV : Targets) {
GV->replaceAllUsesWith(PoisonValue::get(GV->getType()));
GV->dropAllReferences();
GV->eraseFromParent();
}
}
return AsmPrinter::doFinalization(M);
}
void BPFAsmPrinter::printOperand(const MachineInstr *MI, int OpNum,
raw_ostream &O) {
const MachineOperand &MO = MI->getOperand(OpNum);
switch (MO.getType()) {
case MachineOperand::MO_Register:
O << BPFInstPrinter::getRegisterName(MO.getReg());
break;
case MachineOperand::MO_Immediate:
O << MO.getImm();
break;
case MachineOperand::MO_MachineBasicBlock:
O << *MO.getMBB()->getSymbol();
break;
case MachineOperand::MO_GlobalAddress:
O << *getSymbol(MO.getGlobal());
break;
case MachineOperand::MO_BlockAddress: {
MCSymbol *BA = GetBlockAddressSymbol(MO.getBlockAddress());
O << BA->getName();
break;
}
case MachineOperand::MO_ExternalSymbol:
O << *GetExternalSymbolSymbol(MO.getSymbolName());
break;
case MachineOperand::MO_JumpTableIndex:
case MachineOperand::MO_ConstantPoolIndex:
default:
llvm_unreachable("<unknown operand type>");
}
}
bool BPFAsmPrinter::PrintAsmOperand(const MachineInstr *MI, unsigned OpNo,
const char *ExtraCode, raw_ostream &O) {
if (ExtraCode && ExtraCode[0])
return AsmPrinter::PrintAsmOperand(MI, OpNo, ExtraCode, O);
printOperand(MI, OpNo, O);
return false;
}
bool BPFAsmPrinter::PrintAsmMemoryOperand(const MachineInstr *MI,
unsigned OpNum, const char *ExtraCode,
raw_ostream &O) {
assert(OpNum + 1 < MI->getNumOperands() && "Insufficient operands");
const MachineOperand &BaseMO = MI->getOperand(OpNum);
const MachineOperand &OffsetMO = MI->getOperand(OpNum + 1);
assert(BaseMO.isReg() && "Unexpected base pointer for inline asm memory operand.");
assert(OffsetMO.isImm() && "Unexpected offset for inline asm memory operand.");
int Offset = OffsetMO.getImm();
if (ExtraCode)
return true; // Unknown modifier.
if (Offset < 0)
O << "(" << BPFInstPrinter::getRegisterName(BaseMO.getReg()) << " - " << -Offset << ")";
else
O << "(" << BPFInstPrinter::getRegisterName(BaseMO.getReg()) << " + " << Offset << ")";
return false;
}
void BPFAsmPrinter::emitInstruction(const MachineInstr *MI) {
BPF_MC::verifyInstructionPredicates(MI->getOpcode(),
getSubtargetInfo().getFeatureBits());
MCInst TmpInst;
if (!BTF || !BTF->InstLower(MI, TmpInst)) {
BPFMCInstLower MCInstLowering(OutContext, *this);
MCInstLowering.Lower(MI, TmpInst);
}
EmitToStreamer(*OutStreamer, TmpInst);
}
MCSymbol *BPFAsmPrinter::getJTPublicSymbol(unsigned JTI) {
SmallString<60> Name;
raw_svector_ostream(Name)
<< "BPF.JT." << MF->getFunctionNumber() << '.' << JTI;
MCSymbol *S = OutContext.getOrCreateSymbol(Name);
if (auto *ES = static_cast<MCSymbolELF *>(S)) {
ES->setBinding(ELF::STB_GLOBAL);
ES->setType(ELF::STT_OBJECT);
}
return S;
}
void BPFAsmPrinter::emitJumpTableInfo() {
const MachineJumpTableInfo *MJTI = MF->getJumpTableInfo();
if (!MJTI)
return;
const std::vector<MachineJumpTableEntry> &JT = MJTI->getJumpTables();
if (JT.empty())
return;
const TargetLoweringObjectFile &TLOF = getObjFileLowering();
const Function &F = MF->getFunction();
MCSection *JTS = TLOF.getSectionForJumpTable(F, TM);
assert(MJTI->getEntryKind() == MachineJumpTableInfo::EK_BlockAddress);
unsigned EntrySize = MJTI->getEntrySize(getDataLayout());
OutStreamer->switchSection(JTS);
for (unsigned JTI = 0; JTI < JT.size(); JTI++) {
ArrayRef<MachineBasicBlock *> JTBBs = JT[JTI].MBBs;
if (JTBBs.empty())
continue;
MCSymbol *JTStart = getJTPublicSymbol(JTI);
OutStreamer->emitLabel(JTStart);
for (const MachineBasicBlock *MBB : JTBBs) {
const MCExpr *LHS = MCSymbolRefExpr::create(MBB->getSymbol(), OutContext);
OutStreamer->emitValue(LHS, EntrySize);
}
const MCExpr *JTSize =
MCConstantExpr::create(JTBBs.size() * EntrySize, OutContext);
OutStreamer->emitELFSize(JTStart, JTSize);
}
}
char BPFAsmPrinter::ID = 0;
INITIALIZE_PASS(BPFAsmPrinter, "bpf-asm-printer", "BPF Assembly Printer", false,
false)
// Force static initialization.
extern "C" LLVM_ABI LLVM_EXTERNAL_VISIBILITY void
LLVMInitializeBPFAsmPrinter() {
RegisterAsmPrinter<BPFAsmPrinter> X(getTheBPFleTarget());
RegisterAsmPrinter<BPFAsmPrinter> Y(getTheBPFbeTarget());
RegisterAsmPrinter<BPFAsmPrinter> Z(getTheBPFTarget());
}