[MachO] Fixing ub in MachO BinaryFormat

This isn't encountered anywhere inside LLVM, so I wrote a test case to expose the issue and verify that it is fixed.

The basic problem is that the macho_load_command union contains all load comamnd structs. Load command structs in 32-bit macho files can be 32-bit aligned instead of 64-bit aligned.

There are some strange circumstances in which this can be exposed in a 64-bit macho if the load commands are invalid or if a 32-bit aligned load command is used. In the past we've worked around this type of problem with changes like r264232.

llvm-svn: 333797

1 files changed, 43 insertions, 0 deletions

diff --git a/llvm/unittests/BinaryFormat/MachOTest.cpp b/llvm/unittests/BinaryFormat/MachOTest.cpp
new file mode 100644
index 00000000000..d55440a61b3
--- /dev/null
+++ b/llvm/unittests/BinaryFormat/MachOTest.cpp
@@ -0,0 +1,43 @@
+//===- unittest/BinaryFormat/MachOTest.cpp - MachO support tests ----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/BinaryFormat/MachO.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+using namespace llvm::MachO;
+
+TEST(MachOTest, UnalignedLC) {
+  const unsigned char Valid32BitMachO[] = {
+      0xCE, 0xFA, 0xED, 0xFE, 0x07, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00,
+      0x02, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x70, 0x00, 0x00, 0x00,
+      0x85, 0x80, 0x21, 0x01, 0x01, 0x00, 0x00, 0x00, 0x38, 0x00, 0x00, 0x00,
+      0x5F, 0x5F, 0x50, 0x41, 0x47, 0x45, 0x5A, 0x45, 0x52, 0x4F, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x01, 0x00, 0x00, 0x00, 0x38, 0x00, 0x00, 0x00, 0x5F, 0x5F, 0x4C, 0x49,
+      0x4E, 0x4B, 0x45, 0x44, 0x49, 0x54, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x40, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, 0x30, 0x00, 0x00,
+      0x8C, 0x0B, 0x00, 0x00, 0x07, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
+
+  const mach_header *Header =
+      reinterpret_cast<const mach_header *>(Valid32BitMachO);
+  ASSERT_EQ(Header->magic, MH_MAGIC);
+  const unsigned char *Current = Valid32BitMachO + sizeof(mach_header);
+  const unsigned char *BufferEnd =
+      Valid32BitMachO + sizeof(mach_header) + Header->sizeofcmds;
+  while (Current < BufferEnd) {
+    const macho_load_command *LC =
+        reinterpret_cast<const macho_load_command *>(Current);
+    ASSERT_EQ(LC->load_command_data.cmd, LC_SEGMENT);
+    Current += LC->load_command_data.cmdsize;
+  }
+}