Report fatal errors instead of segfaulting/asserting on a few invalid accesses while reading MachO files.

Summary:
Shift an older “invalid file” test to get a consistent naming for these tests.

Bugs found by afl-fuzz

Reviewers: rafael

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D6945

llvm-svn: 226219

17 files changed, 97 insertions, 17 deletions

diff --git a/llvm/lib/Object/MachOObjectFile.cpp b/llvm/lib/Object/MachOObjectFile.cpp
index 978988c2569..a367a49f6bc 100644
--- a/llvm/lib/Object/MachOObjectFile.cpp
+++ b/llvm/lib/Object/MachOObjectFile.cpp
@@ -38,8 +38,12 @@ namespace {
   };
 }
 
-template<typename T>
+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)
@@ -47,15 +51,26 @@ static T getStruct(const MachOObjectFile *O, const char *P) {
   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.");
+  return S.nsects;
+}
+
 static uint32_t
 getSegmentLoadCommandNumSections(const MachOObjectFile *O,
                                  const MachOObjectFile::LoadCommandInfo &L) {
-  if (O->is64Bit()) {
-    MachO::segment_command_64 S = O->getSegment64LoadCommand(L);
-    return S.nsects;
-  }
-  MachO::segment_command S = O->getSegmentLoadCommand(L);
-  return S.nsects;
+  if (O->is64Bit())
+    return getSegmentLoadCommandNumSections(O->getSegment64LoadCommand(L),
+                                            L.C.cmdsize);
+
+  return getSegmentLoadCommandNumSections(O->getSegmentLoadCommand(L),
+                                          L.C.cmdsize);
 }
 
 static bool isPageZeroSegment(const MachOObjectFile *O,
@@ -281,6 +296,12 @@ MachOObjectFile::MachOObjectFile(MemoryBufferRef Object, bool IsLittleEndian,
       }
       UuidLoadCmd = Load.Ptr;
     } else if (Load.C.cmd == SegmentLoadType) {
+      const unsigned SegmentLoadSize = this->is64Bit()
+                                           ? sizeof(MachO::segment_command_64)
+                                           : sizeof(MachO::segment_command);
+      if (Load.C.cmdsize < SegmentLoadSize)
+        report_fatal_error("Segment load command size is too small.");
+
       uint32_t NumSections = getSegmentLoadCommandNumSections(this, Load);
       for (unsigned J = 0; J < NumSections; ++J) {
         const char *Sec = getSectionPtr(this, Load, J);
@@ -315,6 +336,8 @@ std::error_code MachOObjectFile::getSymbolName(DataRefImpl Symb,
   StringRef StringTable = getStringTableData();
   MachO::nlist_base Entry = getSymbolTableEntryBase(this, Symb);
   const char *Start = &StringTable.data()[Entry.n_strx];
+  if (Start >= getData().end())
+    report_fatal_error("Symbol name entry points past end of file.");
   Res = StringRef(Start);
   return object_error::success;
 }
@@ -1204,7 +1227,8 @@ basic_symbol_iterator MachOObjectFile::getSymbolByIndex(unsigned Index) const {
     return basic_symbol_iterator(SymbolRef(DRI, this));
 
   MachO::symtab_command Symtab = getSymtabLoadCommand();
-  assert(Index < Symtab.nsyms && "Requested symbol index is out of range.");
+  if (Index >= Symtab.nsyms)
+    report_fatal_error("Requested symbol index is out of range.");
   unsigned SymbolTableEntrySize =
     is64Bit() ? sizeof(MachO::nlist_64) : sizeof(MachO::nlist);
   DRI.p = reinterpret_cast<uintptr_t>(getPtr(this, Symtab.symoff));
@@ -2108,6 +2132,8 @@ MachOObjectFile::getSectionFinalSegmentName(DataRefImpl Sec) const {
 
 ArrayRef<char>
 MachOObjectFile::getSectionRawName(DataRefImpl Sec) const {
+  if (Sec.d.a >= Sections.size())
+    report_fatal_error("getSectionRawName: Invalid section index");
   const section_base *Base =
     reinterpret_cast<const section_base *>(Sections[Sec.d.a]);
   return makeArrayRef(Base->sectname);
@@ -2115,6 +2141,8 @@ MachOObjectFile::getSectionRawName(DataRefImpl Sec) const {
 
 ArrayRef<char>
 MachOObjectFile::getSectionRawFinalSegmentName(DataRefImpl Sec) const {
+  if (Sec.d.a >= Sections.size())
+    report_fatal_error("getSectionRawFinalSegmentName: Invalid section index");
   const section_base *Base =
     reinterpret_cast<const section_base *>(Sections[Sec.d.a]);
   return makeArrayRef(Base->segname);
@@ -2205,6 +2233,8 @@ MachOObjectFile::getFirstLoadCommandInfo() const {
                                     sizeof(MachO::mach_header);
   Load.Ptr = getPtr(this, HeaderSize);
   Load.C = getStruct<MachO::load_command>(this, Load.Ptr);
+  if (Load.C.cmdsize < 8)
+    report_fatal_error("Load command with size < 8 bytes.");
   return Load;
 }
 
@@ -2213,14 +2243,22 @@ MachOObjectFile::getNextLoadCommandInfo(const LoadCommandInfo &L) const {
   MachOObjectFile::LoadCommandInfo Next;
   Next.Ptr = L.Ptr + L.C.cmdsize;
   Next.C = getStruct<MachO::load_command>(this, Next.Ptr);
+  if (Next.C.cmdsize < 8)
+    report_fatal_error("Load command with size < 8 bytes.");
   return Next;
 }
 
 MachO::section MachOObjectFile::getSection(DataRefImpl DRI) const {
+  // TODO: What if Sections.size() == 0?
+  if (DRI.d.a >= Sections.size())
+    report_fatal_error("getSection: Invalid section index.");
   return getStruct<MachO::section>(this, Sections[DRI.d.a]);
 }
 
 MachO::section_64 MachOObjectFile::getSection64(DataRefImpl DRI) const {
+  // TODO: What if Sections.size() == 0?
+  if (DRI.d.a >= Sections.size())
+    report_fatal_error("getSection64: Invalid section index.");
   return getStruct<MachO::section_64>(this, Sections[DRI.d.a]);
 }
 
diff --git a/llvm/test/Object/Inputs/macho-invalid-bad-symbol-index b/llvm/test/Object/Inputs/macho-invalid-bad-symbol-index
new file mode 100644
index 00000000000..294bbde3ddf
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-bad-symbol-index
diff --git a/llvm/test/Object/Inputs/macho-invalid-getsection-index b/llvm/test/Object/Inputs/macho-invalid-getsection-index
new file mode 100644
index 00000000000..b7e4b95bc9b
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-getsection-index
diff --git a/llvm/test/Object/Inputs/macho-invalid-no-size-for-sections b/llvm/test/Object/Inputs/macho-invalid-no-size-for-sections
new file mode 100644
index 00000000000..89fa95acbcf
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-no-size-for-sections
diff --git a/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawFinalSegmentName b/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawFinalSegmentName
new file mode 100644
index 00000000000..e3f65865922
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawFinalSegmentName
diff --git a/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawName b/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawName
new file mode 100644
index 00000000000..9cd3e1cace8
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-section-index-getSectionRawName
diff --git a/llvm/test/Object/Inputs/macho-invalid-symbol-name-past-eof b/llvm/test/Object/Inputs/macho-invalid-symbol-name-past-eof
new file mode 100644
index 00000000000..87478840787
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-symbol-name-past-eof
diff --git a/llvm/test/Object/Inputs/macho-invalid-too-small-load-command b/llvm/test/Object/Inputs/macho-invalid-too-small-load-command
new file mode 100644
index 00000000000..36021692ee5
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-too-small-load-command
diff --git a/llvm/test/Object/Inputs/macho-invalid-too-small-segment-load-command b/llvm/test/Object/Inputs/macho-invalid-too-small-segment-load-command
new file mode 100644
index 00000000000..8cbfbf96578
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho-invalid-too-small-segment-load-command
diff --git a/llvm/test/Object/Inputs/macho-zero-ncmds b/llvm/test/Object/Inputs/macho-invalid-zero-ncmds
index 0505419195e..0505419195e 100644
--- a/llvm/test/Object/Inputs/macho-zero-ncmds
+++ b/llvm/test/Object/Inputs/macho-invalid-zero-ncmds
diff --git a/llvm/test/Object/Inputs/macho64-invalid-getsection-index b/llvm/test/Object/Inputs/macho64-invalid-getsection-index
new file mode 100644
index 00000000000..a2a7bc10c4f
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho64-invalid-getsection-index
diff --git a/llvm/test/Object/Inputs/macho64-invalid-incomplete-load-command b/llvm/test/Object/Inputs/macho64-invalid-incomplete-load-command
new file mode 100644
index 00000000000..a569c9e14b3
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho64-invalid-incomplete-load-command
diff --git a/llvm/test/Object/Inputs/macho64-invalid-no-size-for-sections b/llvm/test/Object/Inputs/macho64-invalid-no-size-for-sections
new file mode 100644
index 00000000000..5aae5ffed3a
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho64-invalid-no-size-for-sections
diff --git a/llvm/test/Object/Inputs/macho64-invalid-too-small-load-command b/llvm/test/Object/Inputs/macho64-invalid-too-small-load-command
new file mode 100644
index 00000000000..0028451d190
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho64-invalid-too-small-load-command
diff --git a/llvm/test/Object/Inputs/macho64-invalid-too-small-segment-load-command b/llvm/test/Object/Inputs/macho64-invalid-too-small-segment-load-command
new file mode 100644
index 00000000000..ce6a20134a9
--- /dev/null
+++ b/llvm/test/Object/Inputs/macho64-invalid-too-small-segment-load-command
diff --git a/llvm/test/Object/macho-invalid.test b/llvm/test/Object/macho-invalid.test
new file mode 100644
index 00000000000..138d8eb1f3d
--- /dev/null
+++ b/llvm/test/Object/macho-invalid.test
@@ -0,0 +1,51 @@
+// No crash, might not be totally invalid
+RUN: llvm-objdump -private-headers %p/Inputs/macho-invalid-zero-ncmds
+
+RUN: not llvm-objdump -private-headers %p/Inputs/macho64-invalid-incomplete-load-command 2>&1 \
+RUN:      | FileCheck -check-prefix INCOMPLETE-LOADC %s
+
+RUN: not llvm-objdump -private-headers %p/Inputs/macho-invalid-too-small-load-command 2>&1 \
+RUN:      | FileCheck -check-prefix SMALL-LOADC-SIZE %s
+RUN: not llvm-objdump -private-headers %p/Inputs/macho64-invalid-too-small-load-command 2>&1 \
+RUN:      | FileCheck -check-prefix SMALL-LOADC-SIZE %s
+
+RUN: not llvm-objdump -private-headers %p/Inputs/macho-invalid-too-small-segment-load-command 2>&1 \
+RUN:      | FileCheck -check-prefix SMALL-SEGLOADC-SIZE %s
+RUN: not llvm-objdump -private-headers %p/Inputs/macho64-invalid-too-small-segment-load-command 2>&1 \
+RUN:      | FileCheck -check-prefix SMALL-SEGLOADC-SIZE %s
+
+RUN: not llvm-objdump -private-headers %p/Inputs/macho-invalid-no-size-for-sections 2>&1 \
+RUN:      | FileCheck -check-prefix TOO-MANY-SECTS %s
+RUN: not llvm-objdump -private-headers %p/Inputs/macho64-invalid-no-size-for-sections 2>&1 \
+RUN:      | FileCheck -check-prefix TOO-MANY-SECTS %s
+
+RUN: not llvm-objdump -t %p/Inputs/macho-invalid-bad-symbol-index 2>&1 \
+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-objdump -t %p/Inputs/macho-invalid-section-index-getSectionRawFinalSegmentName 2>&1 \
+RUN:      | FileCheck -check-prefix INVALID-SECTION-IDX-SEG-NAME %s
+
+RUN: not llvm-nm %p/Inputs/macho-invalid-section-index-getSectionRawName 2>&1 \
+RUN:      | FileCheck -check-prefix INVALID-SECTION-IDX-SECT-NAME %s
+
+RUN: not llvm-objdump -t %p/Inputs/macho-invalid-getsection-index 2>&1 \
+RUN:      | FileCheck -check-prefix INVALID-SECTION-IDX-GETSECT %s
+
+RUN: not llvm-objdump -t %p/Inputs/macho64-invalid-getsection-index 2>&1 \
+RUN:      | FileCheck -check-prefix INVALID-SECTION-IDX-GETSECT64 %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 past end of file
+
+INVALID-SECTION-IDX-SEG-NAME: getSectionRawFinalSegmentName: Invalid section index
+INVALID-SECTION-IDX-SECT-NAME: getSectionRawName: Invalid section index
+INVALID-SECTION-IDX-GETSECT: getSection: Invalid section index
+INVALID-SECTION-IDX-GETSECT64: getSection64: Invalid section index
diff --git a/llvm/test/Object/objdump-macho-quirks.test b/llvm/test/Object/objdump-macho-quirks.test
deleted file mode 100644
index eeee1537def..00000000000
--- a/llvm/test/Object/objdump-macho-quirks.test
+++ /dev/null
@@ -1,9 +0,0 @@
-RUN: llvm-objdump -private-headers %p/Inputs/macho-zero-ncmds \
-RUN:         | FileCheck %s -check-prefix A
-
-// Check that we don't get an infinite loop if ncmds = 0
-A: file format Mach-O 64-bit unknown
-A: Mach header
-A:      magic cputype cpusubtype  caps    filetype ncmds sizeofcmds      flags
-A: MH_MAGIC_64  0x00      OBJECT     0          0 0x00000000
-