Add a checkSymbolTable() method to the MachOObjectFile class.

The philosophy of the error checking in libObject for Mach-O files
is that the constructor will check the load commands so for their
tables the offsets and sizes are properly contained in the file.
But there is no checking of the entries of any of the tables.

For the contents of the tables themselves the methods accessing
the contents of the entries return errors as needed.  In some
cases this however makes it difficult or cumbersome to produce
a good error message which would include the tool name, file name,
archive member, and name of the architecture of a slice of a universal file
the error occurred in.

So idea is that there will be a method to check a table which can
be called up front before using it allowing a good error message
to be produced before a table is used.  And if only verification of
the Mach-O file and its tables are wanted a new possible method
checkAllTables() could be added to call all of the methods to
check all the tables at some time when such methods exist.

The checkSymbolTable() is the first of such methods to check
one of the Mach-O file tables.  This method initially will used in
llvm-objdump’s DisassembleMachO() routine before it gets the
section and symbol information.  As if there are problems with
the symbol table currently the error is first encountered by the
bool operator() in the SymbolSorter() struct which passed to
std::sort().  In this case there is no context as to the file name
the symbol which results a poor error message:

LLVM ERROR: truncated or malformed object (bad string index: 22 for symbol at index 1)

with the added call to the checkSymbolTable() method the
error message includes the tool name and file name:

llvm-objdump: 'macho-invalid-symbol-strx': truncated or malformed object (bad string table index: 22 past the end of string table, for symbol at index 1)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286887 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Object/MachO.h

@@ -203,6 +203,8 @@ class MachOObjectFile : public ObjectFile {
   Expected<StringRef> getSymbolName(DataRefImpl Symb) const override;
 
   // MachO specific.
+  Error checkSymbolTable() const;
+
   std::error_code getIndirectName(DataRefImpl Symb, StringRef &Res) const;
   unsigned getSectionType(SectionRef Sec) const;
 

lib/Object/MachOObjectFile.cpp

@@ -1501,6 +1501,74 @@ MachOObjectFile::MachOObjectFile(MemoryBufferRef Object, bool IsLittleEndian,
   Err = Error::success();
 }
 
+Error MachOObjectFile::checkSymbolTable() const {
+  uint32_t Flags = 0;
+  if (is64Bit()) {
+    MachO::mach_header_64 H_64 = MachOObjectFile::getHeader64();
+    Flags = H_64.flags;
+  } else {
+    MachO::mach_header H = MachOObjectFile::getHeader();
+    Flags = H.flags;
+  }
+  uint8_t NType = 0;
+  uint8_t NSect = 0;
+  uint16_t NDesc = 0;
+  uint32_t NStrx = 0;
+  uint64_t NValue = 0;
+  uint32_t SymbolIndex = 0;
+  MachO::symtab_command S = getSymtabLoadCommand();
+  for (const SymbolRef &Symbol : symbols()) {
+    DataRefImpl SymDRI = Symbol.getRawDataRefImpl();
+    if (is64Bit()) {
+      MachO::nlist_64 STE_64 = getSymbol64TableEntry(SymDRI);
+      NType = STE_64.n_type;
+      NSect = STE_64.n_sect;
+      NDesc = STE_64.n_desc;
+      NStrx = STE_64.n_strx;
+      NValue = STE_64.n_value;
+    } else {
+      MachO::nlist STE = getSymbolTableEntry(SymDRI);
+      NType = STE.n_type;
+      NType = STE.n_type;
+      NSect = STE.n_sect;
+      NDesc = STE.n_desc;
+      NStrx = STE.n_strx;
+      NValue = STE.n_value;
+    }
+    if ((NType & MachO::N_STAB) == 0 &&
+        (NType & MachO::N_TYPE) == MachO::N_SECT) {
+      if (NSect == 0 || NSect > Sections.size())
+        return malformedError("bad section index: " + Twine((int)NSect) +
+                              " for symbol at index " + Twine(SymbolIndex));
+    }
+    if ((NType & MachO::N_STAB) == 0 &&
+        (NType & MachO::N_TYPE) == MachO::N_INDR) {
+      if (NValue >= S.strsize)
+        return malformedError("bad n_value: " + Twine((int)NValue) + " past "
+                              "the end of string table, for N_INDR symbol at "
+                              "index " + Twine(SymbolIndex));
+    }
+    if ((Flags & MachO::MH_TWOLEVEL) == MachO::MH_TWOLEVEL &&
+        (((NType & MachO::N_TYPE) == MachO::N_UNDF && NValue == 0) ||
+         (NType & MachO::N_TYPE) == MachO::N_PBUD)) {
+      uint32_t LibraryOrdinal = MachO::GET_LIBRARY_ORDINAL(NDesc);
+      if (LibraryOrdinal != 0 &&
+          LibraryOrdinal != MachO::EXECUTABLE_ORDINAL &&
+          LibraryOrdinal != MachO::DYNAMIC_LOOKUP_ORDINAL &&
+          LibraryOrdinal - 1 >= Libraries.size() ) {
+        return malformedError("bad library ordinal: " + Twine(LibraryOrdinal) +
+                            " for symbol at index " + Twine(SymbolIndex));
+      }
+    }
+    if (NStrx >= S.strsize)
+      return malformedError("bad string table index: " + Twine((int)NStrx) +
+                            " past the end of string table, for symbol at "
+                            "index " + Twine(SymbolIndex));
+    SymbolIndex++;
+  }
+  return Error::success();
+}
+
 void MachOObjectFile::moveSymbolNext(DataRefImpl &Symb) const {
   unsigned SymbolTableEntrySize = is64Bit() ?
     sizeof(MachO::nlist_64) :

test/tools/llvm-objdump/X86/malformed-machos.test

@@ -39,3 +39,15 @@
 # RUN:   | FileCheck -check-prefix=m0337 %s 
 
 # m0337: mem-crup-0337.macho': truncated or malformed object (section relocation entries at offset 0 with a size of 512, overlaps Mach-O headers at offset 0 with a size of 2048)
+
+RUN: not llvm-objdump -macho -disassemble %p/Inputs/macho-invalid-symbol-nsect 2>&1 | FileCheck -check-prefix INVALID-SYMBOL-NSECT %s
+INVALID-SYMBOL-NSECT: macho-invalid-symbol-nsect': truncated or malformed object (bad section index: 97 for symbol at index 1)
+
+RUN: not llvm-objdump -macho -disassemble %p/Inputs/macho-invalid-symbol-indr 2>&1 | FileCheck -check-prefix INVALID-SYMBOL-INDR %s
+INVALID-SYMBOL-INDR: macho-invalid-symbol-indr': truncated or malformed object (bad n_value: 22 past the end of string table, for N_INDR symbol at index 1)
+
+RUN: not llvm-objdump -macho -disassemble %p/Inputs/macho-invalid-symbol-strx 2>&1 | FileCheck -check-prefix INVALID-SYMBOL-STRX %s
+INVALID-SYMBOL-STRX: macho-invalid-symbol-strx': truncated or malformed object (bad string table index: 22 past the end of string table, for symbol at index 1)
+
+RUN: not llvm-objdump -macho -disassemble %p/Inputs/macho-invalid-symbol-lib_ordinal 2>&1 | FileCheck -check-prefix INVALID-SYMBOL-LIB_ORDINAL %s
+INVALID-SYMBOL-LIB_ORDINAL: macho-invalid-symbol-lib_ordinal': truncated or malformed object (bad library ordinal: 7 for symbol at index 2)

tools/llvm-objdump/MachODump.cpp

@@ -6523,6 +6523,9 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF,
   SmallVector<uint64_t, 8> FoundFns;
   uint64_t BaseSegmentAddress;
 
+  if (Error Err = MachOOF->checkSymbolTable())
+    report_error(Filename, std::move(Err));
+
   getSectionsAndSymbols(MachOOF, Sections, Symbols, FoundFns,
                         BaseSegmentAddress);