PR42301: Abort cleanly if we encounter a huge source file rather than

crashing.

Ideally we wouldn't care about the size of a file so long as it fits in
memory, but in practice we have lots of hardocded assumptions that
unsigned can be used to index files, string literals, and so on.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@364103 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Basic/DiagnosticCommonKinds.td b/include/clang/Basic/DiagnosticCommonKinds.td
index 52ab4b8ad3d9adab6073725fb93f7c37a4eef96d..776d16bd544b6b660acd94797ddc1b27c09a3c58 100644 (file)
--- a/include/clang/Basic/DiagnosticCommonKinds.td
+++ b/include/clang/Basic/DiagnosticCommonKinds.td
@@ -268,6 +268,8 @@ def err_opt_not_valid_on_target : Error<
 def err_cannot_open_file : Error<"cannot open file '%0': %1">, DefaultFatal;
 def err_file_modified : Error<
   "file '%0' modified since it was first processed">, DefaultFatal;
+def err_file_too_large : Error<
+  "sorry, unsupported: file '%0' is too large for Clang to process">;
 def err_unsupported_bom : Error<"%0 byte order mark detected in '%1', but "
   "encoding is not supported">, DefaultFatal;
 def err_unable_to_rename_temp : Error<

diff --git a/lib/Basic/SourceManager.cpp b/lib/Basic/SourceManager.cpp
index e62cef7ec5596c543ef481214f8325177b22d320..8d56b19b106cbb3804f8c94596bd29da34d1709c 100644 (file)
--- a/lib/Basic/SourceManager.cpp
+++ b/lib/Basic/SourceManager.cpp
@@ -108,6 +108,31 @@ const llvm::MemoryBuffer *ContentCache::getBuffer(DiagnosticsEngine &Diag,
     return Buffer.getPointer();
   }
 
+  // Check that the file's size fits in an 'unsigned' (with room for a
+  // past-the-end value). This is deeply regrettable, but various parts of
+  // Clang (including elsewhere in this file!) use 'unsigned' to represent file
+  // offsets, line numbers, string literal lengths, and so on, and fail
+  // miserably on large source files.
+  if (ContentsEntry->getSize() >= std::numeric_limits<unsigned>::max()) {
+    // We can't make a memory buffer of the required size, so just make a small
+    // one. We should never hit a situation where we've already parsed to a
+    // later offset of the file, so it shouldn't matter that the buffer is
+    // smaller than the file.
+    Buffer.setPointer(
+        llvm::MemoryBuffer::getMemBuffer("", ContentsEntry->getName())
+            .release());
+    if (Diag.isDiagnosticInFlight())
+      Diag.SetDelayedDiagnostic(diag::err_file_too_large,
+                                ContentsEntry->getName());
+    else
+      Diag.Report(Loc, diag::err_file_too_large)
+        << ContentsEntry->getName();
+
+    Buffer.setInt(Buffer.getInt() | InvalidFlag);
+    if (Invalid) *Invalid = true;
+    return Buffer.getPointer();
+  }
+
   bool isVolatile = SM.userFilesAreVolatile() && !IsSystemFile;
   auto BufferOrError =
       SM.getFileManager().getBufferForFile(ContentsEntry, isVolatile);