objdump: Better handling of Mach-O universal binaries

Summary:
With Mach-O, there is a flag requirement discrepancy between working with
universal binaries and thin binaries. Many flags that don't require the `-macho`
flag (for example `-private-headers` and `-disassemble`) fail to work on
universal binaries unless `-macho` is given. When this happens, the error
message is unhelpful, stating:

    The file was not recognized as a valid object file.

Which can lead to confusion.

This change allows generic flags to be used on universal binaries with and
without the `-macho` flag. This means flags that can be used for thin files can
be used consistently with fat files too.

To do this, the universal binary support within `ParseInputMachO()` is extracted
into a new function. This new function is called directly from `DumpInput()`
when the input binary is universal. Additionally the `-arch` flag validation in
`ParseInputMachO()` was extracted to be reused.

Reviewers: compnerd

Reviewed By: compnerd

Subscribers: keith, llvm-commits

Differential Revision: https://reviews.llvm.org/D48702

llvm-svn: 338792

test/tools/llvm-objdump/X86/macho-private-headers.test

@@ -19,6 +19,8 @@
 // RUN:     | FileCheck %s -check-prefix=THREAD
 // RUN: llvm-objdump -macho -p -arch i386 %p/Inputs/macho-universal.x86_64.i386 \
 // RUN:     | FileCheck %s -check-prefix=FATi386
+// RUN: llvm-objdump -p -arch i386 %p/Inputs/macho-universal.x86_64.i386 \
+// RUN:     | FileCheck %s -check-prefix=FATi386
 // RUN: llvm-objdump -p -non-verbose %p/Inputs/hello.obj.macho-x86_64 \
 // RUN:     | FileCheck %s -check-prefix=NON_VERBOSE
 // RUN: llvm-objdump -p %p/Inputs/codesig.macho-x86_64 \

test/tools/llvm-objdump/X86/macho-universal-x86_64.i386.test

@@ -1,5 +1,7 @@
 RUN: llvm-objdump %p/Inputs/macho-universal.x86_64.i386 -d -m -no-show-raw-insn -full-leading-addr -print-imm-hex -arch all \
 RUN: | FileCheck %s -check-prefix UEXE-all
+RUN: llvm-objdump %p/Inputs/macho-universal.x86_64.i386 -d -no-show-raw-insn -full-leading-addr -print-imm-hex -arch all \
+RUN: | FileCheck %s -check-prefix UEXE-all
 RUN: llvm-objdump %p/Inputs/macho-universal-archive.x86_64.i386 -d -m -no-show-raw-insn -full-leading-addr -print-imm-hex -arch i386 \
 RUN: | FileCheck %s -check-prefix UArchive-i386
 RUN: llvm-objdump %p/Inputs/macho-universal.x86_64.i386 -universal-headers -m \

tools/llvm-objdump/MachODump.cpp

@@ -1937,11 +1937,7 @@ static void printArchiveHeaders(StringRef Filename, Archive *A, bool verbose,
     report_error(StringRef(), Filename, std::move(Err), ArchitectureName);
 }
 
-// ParseInputMachO() parses the named Mach-O file in Filename and handles the
-// -arch flags selecting just those slices as specified by them and also parses
-// archive files.  Then for each individual Mach-O file ProcessMachO() is
-// called to process the file based on the command line options.
-void llvm::ParseInputMachO(StringRef Filename) {
+static bool ValidateArchFlags() {
   // Check for -arch all and verifiy the -arch flags are valid.
   for (unsigned i = 0; i < ArchFlags.size(); ++i) {
     if (ArchFlags[i] == "all") {
@@ -1950,10 +1946,20 @@ void llvm::ParseInputMachO(StringRef Filename) {
       if (!MachOObjectFile::isValidArch(ArchFlags[i])) {
         errs() << "llvm-objdump: Unknown architecture named '" + ArchFlags[i] +
                       "'for the -arch option\n";
+        return false;
+      }
+    }
+  }
+  return true;
+}
+
+// ParseInputMachO() parses the named Mach-O file in Filename and handles the
+// -arch flags selecting just those slices as specified by them and also parses
+// archive files.  Then for each individual Mach-O file ProcessMachO() is
+// called to process the file based on the command line options.
+void llvm::ParseInputMachO(StringRef Filename) {
+  if (!ValidateArchFlags())
     return;
-      }
-    }
-  }
 
   // Attempt to open the binary.
   Expected<OwningBinary<Binary>> BinaryOrErr = createBinary(Filename);
@@ -1989,11 +1995,32 @@ void llvm::ParseInputMachO(StringRef Filename) {
       report_error(Filename, std::move(Err));
     return;
   }
-  if (UniversalHeaders) {
-    if (MachOUniversalBinary *UB = dyn_cast<MachOUniversalBinary>(&Bin))
-      printMachOUniversalHeaders(UB, !NonVerbose);
-  }
   if (MachOUniversalBinary *UB = dyn_cast<MachOUniversalBinary>(&Bin)) {
+    ParseInputMachO(UB);
+    return;
+  }
+  if (ObjectFile *O = dyn_cast<ObjectFile>(&Bin)) {
+    if (!checkMachOAndArchFlags(O, Filename))
+      return;
+    if (MachOObjectFile *MachOOF = dyn_cast<MachOObjectFile>(&*O))
+      ProcessMachO(Filename, MachOOF);
+    else
+      errs() << "llvm-objdump: '" << Filename << "': "
+             << "Object is not a Mach-O file type.\n";
+    return;
+  }
+  llvm_unreachable("Input object can't be invalid at this point");
+}
+
+void llvm::ParseInputMachO(MachOUniversalBinary *UB) {
+  if (!ValidateArchFlags())
+    return;
+
+  auto Filename = UB->getFileName();
+
+  if (UniversalHeaders)
+    printMachOUniversalHeaders(UB, !NonVerbose);
+
   // If we have a list of architecture flags specified dump only those.
   if (!ArchAll && ArchFlags.size() != 0) {
     // Look for a slice in the universal binary that matches each ArchFlag.
@@ -2161,19 +2188,6 @@ void llvm::ParseInputMachO(StringRef Filename) {
             " is not a Mach-O file or an archive file");
     }
   }
-    return;
-  }
-  if (ObjectFile *O = dyn_cast<ObjectFile>(&Bin)) {
-    if (!checkMachOAndArchFlags(O, Filename))
-      return;
-    if (MachOObjectFile *MachOOF = dyn_cast<MachOObjectFile>(&*O)) {
-      ProcessMachO(Filename, MachOOF);
-    } else
-      errs() << "llvm-objdump: '" << Filename << "': "
-             << "Object is not a Mach-O file type.\n";
-    return;
-  }
-  llvm_unreachable("Input object can't be invalid at this point");
 }
 
 // The block of info used by the Symbolizer call backs.

tools/llvm-objdump/llvm-objdump.cpp

@@ -42,6 +42,7 @@
 #include "llvm/Object/COFFImportFile.h"
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/Object/MachO.h"
+#include "llvm/Object/MachOUniversal.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Object/Wasm.h"
 #include "llvm/Support/Casting.h"
@@ -2363,6 +2364,8 @@ static void DumpInput(StringRef file) {
     DumpArchive(a);
   else if (ObjectFile *o = dyn_cast<ObjectFile>(&Binary))
     DumpObject(o);
+  else if (MachOUniversalBinary *UB = dyn_cast<MachOUniversalBinary>(&Binary))
+    ParseInputMachO(UB);
   else
     report_error(file, object_error::invalid_file_type);
 }

tools/llvm-objdump/llvm-objdump.h

@@ -22,6 +22,7 @@ namespace object {
   class COFFObjectFile;
   class COFFImportFile;
   class MachOObjectFile;
+  class MachOUniversalBinary;
   class ObjectFile;
   class Archive;
   class RelocationRef;
@@ -71,6 +72,7 @@ extern cl::opt<DIDumpType> DwarfDumpType;
 void error(std::error_code ec);
 bool RelocAddressLess(object::RelocationRef a, object::RelocationRef b);
 void ParseInputMachO(StringRef Filename);
+void ParseInputMachO(object::MachOUniversalBinary *UB);
 void printCOFFUnwindInfo(const object::COFFObjectFile* o);
 void printMachOUnwindInfo(const object::MachOObjectFile* o);
 void printMachOExportsTrie(const object::MachOObjectFile* o);