[BPF] Return fail if disassembled insn registers out of range

[yonghong-song]

Summary

Daniel reported a llvm-objdump segfault like below:

$ llvm-objdump -D bpf_xdp.o
...
0000000000000000 <.strtab>:
     0:       00 63 69 6c 69 75 6d 5f <unknown>
     1:       6c 62 36 5f 61 66 66 69 w2 <<= w6
...
(llvm-objdump: lib/Target/BPF/BPFGenAsmWriter.inc:1087: static const char*
 llvm::BPFInstPrinter::getRegisterName(unsigned int): Assertion
 `RegNo && RegNo < 25 && "Invalid register number!"' failed.
 Stack dump:
 0.      Program arguments: llvm-objdump -D bpf_xdp.o
  ...
  abort
  ...
  llvm::BPFInstPrinter::getRegisterName(unsigned int)
  llvm::BPFInstPrinter::printMemOperand(llvm::MCInst const*,
                        int, llvm::raw_ostream&, char const*)
  llvm::BPFInstPrinter::printInstruction(llvm::MCInst const*,
                        unsigned long, llvm::raw_ostream&)
  llvm::BPFInstPrinter::printInst(llvm::MCInst const*,
                        unsigned long, llvm::StringRef, llvm::MCSubtargetInfo const&,
                        llvm::raw_ostream&)
 ...

Basically, since -D enables disassembly for all sections, .strtab is also disassembled,
but some strings are decoded as legal instructions but with illegal register numbers.
When llvm-objdump tries to print register name for these illegal register numbers,
assertion and segfault happens.

The patch fixed the issue by returning fail for a disassembled insn if
that insn contain a reg operand with illegal reg number.
The insn will be printed as "<unknown>" instead of causing an assertion.

llvm/lib/Target/BPF/Disassembler/BPFDisassembler.cpp

if ((InstClass == BPF_LDX || InstClass == BPF_STX) &&
     Result = decodeInstruction(DecoderTableBPFALU3264, Instr, Insn, Address,
                                this, STI);
   else
     Result = decodeInstruction(DecoderTableBPF64, Instr, Insn, Address, this,
                                STI);
 
   if (Result == MCDisassembler::Fail) return MCDisassembler::Fail;
 
+  /* to ensure registers in range */
+  for (unsigned i = 0, e = Instr.getNumOperands(); i != e; ++i) {
+    const MCOperand &MO = Instr.getOperand(i);
+    if (MO.isReg() &&
+        (MO.getReg() <= BPF::NoRegister || MO.getReg() >= BPF::NUM_TARGET_REGS))
+      return MCDisassembler::Fail;
+  }
+
   switch (Instr.getOpcode()) {
   case BPF::LD_imm64:
   case BPF::LD_pseudo: {
     if (Bytes.size() < 16) {
       Size = 0;
       return MCDisassembler::Fail;
     }
     Size = 16;

llvm/test/CodeGen/BPF/objdump_dis_all.ll

+; RUN: llc -march=bpfel -filetype=obj -o - %s | llvm-objdump -D - | FileCheck %s
+;
+; Source:
+;   /* *(u64 *)(r10 - 16) = r1 */
+;   unsigned long long g = 0x00000000fff01a7bULL;
+;   /* *(u64 *)(r15 - 16) = r1 */
+;   unsigned long long h = 0x00000000fff01f7bULL;
+;   int test() {
+;     return 0;
+;   }
+; Compilation flag:
+;  clang -target bpf -O2 -S -emit-llvm t.c
+
+@g = dso_local local_unnamed_addr global i64 4293925499, align 8
+@h = dso_local local_unnamed_addr global i64 4293926779, align 8
+
+; Function Attrs: norecurse nounwind readnone
+define dso_local i32 @test() local_unnamed_addr {
+entry:
+  ret i32 0
+}
+; CHECK-LABEL: section .data
+; CHECK-LABEL: g
+; CHECK:       *(u64 *)(r10 - 16) = r1
+; CHECK-LABEL: h
+; CHECK:       <unknown>