Fix input validation issues in llvm-as/llvm-dis

[sl]

Summary

1. llvm-as/llvm-dis tools do not check for input filename length.
2. llvm-dis does not verify the Streamer variable against nullptr properly, so the M variable could be uninitialized (e.g. if the input file does not exist) leading to null dref.

[samsonov]

tools/llvm-as/llvm-as.cpp

67 ↗

(On Diff #25254)

Can you use StringRef::endswith(".ll") instead?

[sl]

Can you use StringRef::endswith(".ll") instead?

Sure, done. It also may be useful to use llvm::StringRef::endswith_lower().

[samsonov]

LGTM with one comment.

tools/llvm-as/llvm-as.cpp

67 ↗

(On Diff #25330)

IFN.drop_back(3).str() (here and below)

[sl]

In D9584#169069, @samsonov wrote:

LGTM with one comment.

Alexey, could you please commit this? Thank you.

llvm/trunk/tools/llvm-as/llvm-as.cpp

static cl::opt<bool> PreserveBitcodeUseListOrder(
     cl::init(true), cl::Hidden);
 
 static void WriteOutputFile(const Module *M) {
   // Infer the output filename if needed.
   if (OutputFilename.empty()) {
     if (InputFilename == "-") {
       OutputFilename = "-";
     } else {
-      std::string IFN = InputFilename;
-      int Len = IFN.length();
-      if (IFN[Len-3] == '.' && IFN[Len-2] == 'l' && IFN[Len-1] == 'l') {
-        // Source ends in .ll
-        OutputFilename = std::string(IFN.begin(), IFN.end()-3);
-      } else {
-        OutputFilename = IFN;   // Append a .bc to it
-      }
+      StringRef IFN = InputFilename;
+      OutputFilename = (IFN.endswith(".ll") ? IFN.drop_back(3) : IFN).str();
       OutputFilename += ".bc";
     }
   }
 
   std::error_code EC;
   std::unique_ptr<tool_output_file> Out(
       new tool_output_file(OutputFilename, EC, sys::fs::F_None));
   if (EC) {

llvm/trunk/tools/llvm-dis/llvm-dis.cpp

void emitFunctionAnnot(const Function *F,
     OS << "; [#uses=" << F->getNumUses() << ']';  // Output # uses
     OS << '\n';
   }
   void printInfoComment(const Value &V, formatted_raw_ostream &OS) override {
     bool Padded = false;
     if (!V.getType()->isVoidTy()) {
       OS.PadToColumn(50);
       Padded = true;
-      OS << "; [#uses=" << V.getNumUses() << " type=" << *V.getType() << "]";  // Output # uses and type
+      // Output # uses and type
+      OS << "; [#uses=" << V.getNumUses() << " type=" << *V.getType() << "]";
     }
     if (const Instruction *I = dyn_cast<Instruction>(&V)) {
       if (const DebugLoc &DL = I->getDebugLoc()) {
         if (!Padded) {
           OS.PadToColumn(50);
           Padded = true;
           OS << ";";
         }
if (Streamer) {
     if (InputFilename == "-")
       DisplayFilename = "<stdin>";
     else
       DisplayFilename = InputFilename;
     ErrorOr<std::unique_ptr<Module>> MOrErr =
         getStreamedBitcodeModule(DisplayFilename, Streamer, Context);
     M = std::move(*MOrErr);
     M->materializeAllPermanently();
+  } else {
+    errs() << argv[0] << ": " << ErrorMessage << '\n';
+    return 1;
   }
 
   // Just use stdout.  We won't actually print anything on it.
   if (DontPrint)
     OutputFilename = "-";
 
   if (OutputFilename.empty()) { // Unspecified output, infer it.
     if (InputFilename == "-") {
       OutputFilename = "-";
     } else {
-      const std::string &IFN = InputFilename;
-      int Len = IFN.length();
-      // If the source ends in .bc, strip it off.
-      if (IFN[Len-3] == '.' && IFN[Len-2] == 'b' && IFN[Len-1] == 'c')
-        OutputFilename = std::string(IFN.begin(), IFN.end()-3)+".ll";
-      else
-        OutputFilename = IFN+".ll";
+      StringRef IFN = InputFilename;
+      OutputFilename = (IFN.endswith(".bc") ? IFN.drop_back(3) : IFN).str();
+      OutputFilename += ".ll";
     }
   }
 
   std::error_code EC;
   std::unique_ptr<tool_output_file> Out(
       new tool_output_file(OutputFilename, EC, sys::fs::F_None));
   if (EC) {
     errs() << EC.message() << '\n';