ASTReader: Copy input file offset data to avoid unaligned accesses

We interpret Blob as an array of uint64_t here, but there's no reason
to think that it has suitable alignment. Instead, read the data in in
an alignment-safe way and store it in a std::vector.

This fixes 225 test failures when clang is built with ubsan.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@240228 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Serialization/Module.h b/include/clang/Serialization/Module.h
index 5571d91a541141a2fcd61d94c06a0bc14f6b23b7..48715e30156552618884f9f471c8ef3995b4adc8 100644 (file)
--- a/include/clang/Serialization/Module.h
+++ b/include/clang/Serialization/Module.h
@@ -206,7 +206,7 @@ public:
   llvm::BitstreamCursor InputFilesCursor;
 
   /// \brief Offsets for all of the input file entries in the AST file.
-  const uint64_t *InputFileOffsets;
+  std::vector<uint64_t> InputFileOffsets;
 
   /// \brief The input files that have been loaded from this AST file.
   std::vector<InputFile> InputFilesLoaded;

diff --git a/lib/Serialization/ASTReader.cpp b/lib/Serialization/ASTReader.cpp
index d75b5eb73d51b38209270df2f61b542483655839..af6f92a5115700abb5f2379582cb42afcdde79df 100644 (file)
--- a/lib/Serialization/ASTReader.cpp
+++ b/lib/Serialization/ASTReader.cpp
@@ -2304,13 +2304,21 @@ ASTReader::ReadControlBlock(ModuleFile &F,
         return Result;
       break;
 
-    case INPUT_FILE_OFFSETS:
+    case INPUT_FILE_OFFSETS: {
       NumInputs = Record[0];
       NumUserInputs = Record[1];
-      F.InputFileOffsets = (const uint64_t *)Blob.data();
+      F.InputFileOffsets.clear();
+      F.InputFileOffsets.reserve(NumInputs);
+      using namespace llvm::support;
+      const char *Buf = Blob.data();
+      for (unsigned int I = 0; I < NumInputs; ++I)
+        F.InputFileOffsets.push_back(
+            endian::readNext<uint64_t, native, unaligned>(Buf));
+
       F.InputFilesLoaded.resize(NumInputs);
       break;
     }
+    }
   }
 }