[llvm-readobj/elf] - Report "bitcode files are not supported" warning for bitcode files.

[grimar]

Summary

Fixes https://bugs.llvm.org/show_bug.cgi?id=43543

Currently we report "The file was not recognized as a valid object file" for BC files.
Also, we terminate dumping.

Instead we could report a better warning and try to continue dumping other files.
This is what this patch implements.

[jhenderson]

llvm/test/tools/llvm-readobj/basic.test

24

27

I'm guessing the problem is related to the third and fourth bytes being greater than 0x7f and therefore potentially signed?

33–34

Did you mean to repeat this check twice? Doesn't seem to be much point in that... I'm guessing you meant to do them the other way around.

llvm/tools/llvm-readobj/llvm-readobj.cpp

659

Error messages generally don't end in a full stop.

[grimar]

llvm/test/tools/llvm-readobj/basic.test

33–34

It is correct: the first tests the llvm-readelf, and the second calls llvm-readobj.

[jhenderson]

llvm/test/tools/llvm-readobj/basic.test

33–34

Oops, thanks!

[grimar]

• Addressed review comments.

llvm/test/tools/llvm-readobj/basic.test

27

I'm guessing the problem is related to the third and fourth bytes being greater than 0x7f and therefore potentially signed?

Hmm, looks like that!

The output of echo -e -n "\x7e\x7f\x80\x81" is 7e 7f c2 80 c2 81

[jhenderson]

LGTM.

llvm/test/tools/llvm-readobj/basic.test

27

llvm/test/tools/llvm-readobj/basic.test

 EMPTY: '{{.*}}.empty': The file was not recognized as a valid object file
 
 # Test that unrecognised files in archives are ignored.
 RUN: rm -f %t.a
 RUN: llvm-ar rc %t.a %t.empty
 RUN: llvm-readobj --all %t.a 2>&1 | FileCheck --check-prefix=NO-OUTPUT --allow-empty %s
 NO-OUTPUT-NOT: {{.}}
 
+## Test we report a meaningful warning for bitcode files.
+## Check we try to continue dumping other files.
+
+## Note: 'echo -e -n "\x42\x43\xc0\xde" > %t.bc.1' simply doesn't work properly on windows.
+## It has an issue with writing of 2 last bytes and emits different data instead.
+## echo.exe from GnuWin32 works properly though, but using of python is a more stable way.
+RUN: %python -c "import os; open(r'%t.bc.1', 'wb').write(b'\x42\x43\xC0\xDE')"
+RUN: %python -c "import os; open(r'%t.bc.2', 'wb').write(b'\xDE\xC0\x17\x0B')"
+RUN: llvm-readelf %t.bc.1 %t.bc.2 2>&1 | \
+RUN:   FileCheck --check-prefix=BITCODE -DFILE1=%t.bc.1 -DFILE2=%t.bc.2 %s
+RUN: llvm-readobj %t.bc.1 %t.bc.2 2>&1 | \
+RUN:   FileCheck --check-prefix=BITCODE -DFILE1=%t.bc.1 -DFILE2=%t.bc.2 %s
+
+# BITCODE: warning: '[[FILE1]]': bitcode files are not supported{{$}}
+# BITCODE: warning: '[[FILE2]]': bitcode files are not supported{{$}}
+
 # Test case where switch it not recognised.
 RUN: not llvm-readobj --unknown-switch 2>&1 | FileCheck --check-prefix=UNKNOWN %s
 UNKNOWN: Unknown command line argument '--unknown-switch'
 
 # Test version switch.
 RUN: llvm-readobj --version | FileCheck %s --check-prefix=VERSION
 RUN: llvm-readelf --version | FileCheck %s --check-prefix=VERSION
 # In default configuration we could match "LLVM version", but the "LLVM" part

llvm/tools/llvm-readobj/llvm-readobj.cpp

static void dumpWindowsResourceFile(WindowsResource *WinRes,
   WindowsRes::Dumper Dumper(WinRes, Printer);
   if (auto Err = Dumper.printData())
     reportError(std::move(Err), WinRes->getFileName());
 }
 
 
 /// Opens \a File and dumps it.
 static void dumpInput(StringRef File, ScopedPrinter &Writer) {
-  // Attempt to open the binary.
-  Expected<OwningBinary<Binary>> BinaryOrErr =
-      createBinary(File, /*Context=*/nullptr, /*InitContent=*/false);
+  ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
+      MemoryBuffer::getFileOrSTDIN(File, /*FileSize=*/-1,
+                                   /*RequiresNullTerminator=*/false);
+  if (std::error_code EC = FileOrErr.getError())
+    return reportError(errorCodeToError(EC), File);
+
+  std::unique_ptr<MemoryBuffer> &Buffer = FileOrErr.get();
+  file_magic Type = identify_magic(Buffer->getBuffer());
+  if (Type == file_magic::bitcode) {
+    reportWarning(createStringError(errc::invalid_argument,
+                                    "bitcode files are not supported"),
+                  File);
+    return;
+  }
+
+  Expected<std::unique_ptr<Binary>> BinaryOrErr = createBinary(
+      Buffer->getMemBufferRef(), /*Context=*/nullptr, /*InitContent=*/false);
   if (!BinaryOrErr)
     reportError(BinaryOrErr.takeError(), File);
-  Binary &Binary = *BinaryOrErr.get().getBinary();
 
-  if (Archive *Arc = dyn_cast<Archive>(&Binary))
+  std::unique_ptr<Binary> Bin = std::move(*BinaryOrErr);
+  if (Archive *Arc = dyn_cast<Archive>(Bin.get()))
     dumpArchive(Arc, Writer);
   else if (MachOUniversalBinary *UBinary =
-               dyn_cast<MachOUniversalBinary>(&Binary))
+               dyn_cast<MachOUniversalBinary>(Bin.get()))
     dumpMachOUniversalBinary(UBinary, Writer);
-  else if (ObjectFile *Obj = dyn_cast<ObjectFile>(&Binary))
+  else if (ObjectFile *Obj = dyn_cast<ObjectFile>(Bin.get()))
     dumpObject(*Obj, Writer);
-  else if (COFFImportFile *Import = dyn_cast<COFFImportFile>(&Binary))
+  else if (COFFImportFile *Import = dyn_cast<COFFImportFile>(Bin.get()))
     dumpCOFFImportFile(Import, Writer);
-  else if (WindowsResource *WinRes = dyn_cast<WindowsResource>(&Binary))
+  else if (WindowsResource *WinRes = dyn_cast<WindowsResource>(Bin.get()))
     dumpWindowsResourceFile(WinRes, Writer);
   else
     llvm_unreachable("unrecognized file type");
 
-  CVTypes.Binaries.push_back(std::move(*BinaryOrErr));
+  CVTypes.Binaries.push_back(
+      OwningBinary<Binary>(std::move(Bin), std::move(Buffer)));
 }
 
 /// Registers aliases that should only be allowed by readobj.
 static void registerReadobjAliases() {
   // -s has meant --sections for a very long time in llvm-readobj despite
   // meaning --symbols in readelf.
   static cl::alias SectionsShort("s", cl::desc("Alias for --section-headers"),
                                  cl::aliasopt(opts::SectionHeaders),