[Object, MachO] Don't crash on parsing invalid MachO header.

[samsonov]

Summary

Instead, properly report this error from MachOObjectFile constructor.

[filcab]

LGTM

test/Object/macho-invalid.test

41

If you're expecting to add a lot of these, we might want to start putting the expected error next to the respective run line, instead of all the run lines and then all the errors.
(Both are ok with me, we can also wait until it gets unreadable and then change)

[samsonov]

test/Object/macho-invalid.test

41

Right, I'm addressing this in subsequent http://reviews.llvm.org/D10230

[samsonov]

Submitted in r239078.

lib/Object/MachOObjectFile.cpp

 
 namespace {
   struct section_base {
     char sectname[16];
     char segname[16];
   };
 }
 
+// FIXME: Replace all uses of this function with getStructOrErr.
 template <typename T>
 static T getStruct(const MachOObjectFile *O, const char *P) {
   // Don't read before the beginning or past the end of the file
   if (P < O->getData().begin() || P + sizeof(T) > O->getData().end())
     report_fatal_error("Malformed MachO file.");
 
   T Cmd;
   memcpy(&Cmd, P, sizeof(T));
   if (O->isLittleEndian() != sys::IsLittleEndianHost)
     MachO::swapStruct(Cmd);
   return Cmd;
 }
 
+template <typename T>
+static ErrorOr<T> getStructOrErr(const MachOObjectFile *O, const char *P) {
+  // Don't read before the beginning or past the end of the file
+  if (P < O->getData().begin() || P + sizeof(T) > O->getData().end())
+    return object_error::parse_failed;
+
+  T Cmd;
+  memcpy(&Cmd, P, sizeof(T));
+  if (O->isLittleEndian() != sys::IsLittleEndianHost)
+    MachO::swapStruct(Cmd);
+  return Cmd;
+}
+
 template <typename SegmentCmd>
 static uint32_t getSegmentLoadCommandNumSections(const SegmentCmd &S,
                                                  uint32_t Cmdsize) {
   const unsigned SectionSize = sizeof(SegmentCmd);
   if (S.nsects > std::numeric_limits<uint32_t>::max() / SectionSize ||
       S.nsects * SectionSize > Cmdsize - sizeof(S))
     report_fatal_error(
         "Number of sections too large for size of load command.");
static uint32_t getSectionFlags(const MachOObjectFile *O,
   if (O->is64Bit()) {
     MachO::section_64 Sect = O->getSection64(Sec);
     return Sect.flags;
   }
   MachO::section Sect = O->getSection(Sec);
   return Sect.flags;
 }
 
+template <typename T>
+static void parseHeader(const MachOObjectFile *Obj, T &Header,
+                        std::error_code &EC) {
+  auto HeaderOrErr = getStructOrErr<T>(Obj, getPtr(Obj, 0));
+  if (HeaderOrErr)
+    Header = HeaderOrErr.get();
+  else
+    EC = HeaderOrErr.getError();
+}
+
 MachOObjectFile::MachOObjectFile(MemoryBufferRef Object, bool IsLittleEndian,
                                  bool Is64bits, std::error_code &EC)
     : ObjectFile(getMachOType(IsLittleEndian, Is64bits), Object),
       Header(reinterpret_cast<MachO::mach_header*>(&this->Header64)),
       SymtabLoadCmd(nullptr), DysymtabLoadCmd(nullptr),
       DataInCodeLoadCmd(nullptr), LinkOptHintsLoadCmd(nullptr),
       DyldInfoLoadCmd(nullptr), UuidLoadCmd(nullptr),
       HasPageZeroSegment(false) {
   // Parse header.
   if (is64Bit())
-    Header64 = getStruct<MachO::mach_header_64>(this, getPtr(this, 0));
+    parseHeader(this, Header64, EC);
   else
-    *Header = getStruct<MachO::mach_header>(this, getPtr(this, 0));
+    parseHeader(this, *Header, EC);
+  if (EC)
+    return;
 
   uint32_t LoadCommandCount = Header->ncmds;
   if (LoadCommandCount == 0)
     return;
 
   MachO::LoadCommandType SegmentLoadType = is64Bit() ?
     MachO::LC_SEGMENT_64 : MachO::LC_SEGMENT;
 

test/Object/macho-invalid.test

 RUN:      | FileCheck -check-prefix BAD-SYMBOL %s
 
 RUN: not llvm-objdump -t %p/Inputs/macho-invalid-symbol-name-past-eof 2>&1 \
 RUN:      | FileCheck -check-prefix NAME-PAST-EOF %s
 
 RUN: not llvm-nm %p/Inputs/macho-invalid-section-index-getSectionRawName 2>&1 \
 RUN:      | FileCheck -check-prefix INVALID-SECTION-IDX-SYMBOL-SEC %s
 
+RUN: llvm-objdump -private-headers %p/Inputs/macho-invalid-header 2>&1 | FileCheck -check-prefix INVALID-HEADER %s
+
 SMALL-LOADC-SIZE: Load command with size < 8 bytes
 SMALL-SEGLOADC-SIZE: Segment load command size is too small
 INCOMPLETE-LOADC: Malformed MachO file
 TOO-MANY-SECTS: Number of sections too large for size of load command
 BAD-SYMBOL: Requested symbol index is out of range
 NAME-PAST-EOF: Symbol name entry points before beginning or past end of file
 
 INVALID-SECTION-IDX-SYMBOL-SEC: getSymbolSection: Invalid section index
+INVALID-HEADER: Invalid data was encountered while parsing the file.