[BitcodeReader] Use tighter upper bound to validate forward references.

At the moment, bitcode files with invalid forward reference can easily
cause the bitcode reader to run out of memory, by creating a forward
reference with a very high index.

We can use the size of the bitcode file as an upper bound, because a
valid bitcode file can never contain more records. This should be
sufficient to fail early in most cases. The only exception is large
files with invalid forward references close to the file size.

There are a couple of clusterfuzz runs that fail with out-of-memory
because of very high forward references and they should be fixed by this
patch.

A concrete example for this is D64507, which causes out-of-memory on
systems with low memory, like the hexagon upstream bots.

Reviewers: t.p.northover, thegameg, jfb, efriedma, hfinkel

Reviewed By: jfb

Differential Revision: https://reviews.llvm.org/D64577

llvm-svn: 366017

llvm/lib/Bitcode/Reader/MetadataLoader.cpp

@@ -130,8 +130,15 @@ class BitcodeReaderMetadataList {
 
   LLVMContext &Context;
 
+  /// Maximum number of valid references. Forward references exceeding the
+  /// maximum must be invalid.
+  unsigned RefsUpperBound;
+
 public:
-  BitcodeReaderMetadataList(LLVMContext &C) : Context(C) {}
+  BitcodeReaderMetadataList(LLVMContext &C, size_t RefsUpperBound)
+      : Context(C),
+        RefsUpperBound(std::min((size_t)std::numeric_limits<unsigned>::max(),
+                                RefsUpperBound)) {}
 
   // vector compatibility methods
   unsigned size() const { return MetadataPtrs.size(); }
@@ -218,6 +225,10 @@ void BitcodeReaderMetadataList::assignValue(Metadata *MD, unsigned Idx) {
 }
 
 Metadata *BitcodeReaderMetadataList::getMetadataFwdRef(unsigned Idx) {
+  // Bail out for a clearly invalid value.
+  if (Idx >= RefsUpperBound)
+    return nullptr;
+
   if (Idx >= size())
     resize(Idx + 1);
 
@@ -625,9 +636,10 @@ public:
                      BitcodeReaderValueList &ValueList,
                      std::function<Type *(unsigned)> getTypeByID,
                      bool IsImporting)
-      : MetadataList(TheModule.getContext()), ValueList(ValueList),
-        Stream(Stream), Context(TheModule.getContext()), TheModule(TheModule),
-        getTypeByID(std::move(getTypeByID)), IsImporting(IsImporting) {}
+      : MetadataList(TheModule.getContext(), Stream.SizeInBytes()),
+        ValueList(ValueList), Stream(Stream), Context(TheModule.getContext()),
+        TheModule(TheModule), getTypeByID(std::move(getTypeByID)),
+        IsImporting(IsImporting) {}
 
   Error parseMetadata(bool ModuleLevel);