[DebugInfo] Don't bother with MD5 checksums of preprocessed files.

The checksum will not reflect the real source, so there's no clear
reason to include them in the debug info.  Also this was causing a
crash on the DWARF side.

Differential Revision: https://reviews.llvm.org/D47260

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@333311 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGDebugInfo.cpp b/lib/CodeGen/CGDebugInfo.cpp
index 9e99a646b0bff2ca89580f77b923e8dcef20c23b..8cf37f48a27ef701040024b94c662801f78106d4 100644 (file)
--- a/lib/CodeGen/CGDebugInfo.cpp
+++ b/lib/CodeGen/CGDebugInfo.cpp
@@ -67,6 +67,8 @@ CGDebugInfo::CGDebugInfo(CodeGenModule &CGM)
       DBuilder(CGM.getModule()) {
   for (const auto &KV : CGM.getCodeGenOpts().DebugPrefixMap)
     DebugPrefixMap[KV.first] = KV.second;
+  EmitFileChecksums = CGM.getCodeGenOpts().EmitCodeView ||
+                      CGM.getCodeGenOpts().DwarfVersion >= 5;
   CreateCompileUnit();
 }
 
@@ -365,15 +367,21 @@ Optional<llvm::DIFile::ChecksumKind>
 CGDebugInfo::computeChecksum(FileID FID, SmallString<32> &Checksum) const {
   Checksum.clear();
 
-  if (!CGM.getCodeGenOpts().EmitCodeView &&
-      CGM.getCodeGenOpts().DwarfVersion < 5)
+  if (!EmitFileChecksums)
     return None;
 
   SourceManager &SM = CGM.getContext().getSourceManager();
   bool Invalid;
-  llvm::MemoryBuffer *MemBuffer = SM.getBuffer(FID, &Invalid);
-  if (Invalid)
+  const SrcMgr::SLocEntry &Entry = SM.getSLocEntry(FID, &Invalid);
+  if (Invalid || !Entry.isFile())
     return None;
+  if (Entry.getFile().hasLineDirectives()) {
+    // This must be a preprocessed file; its content won't match the original
+    // source; therefore checksumming the text we have is pointless or wrong.
+    EmitFileChecksums = false;
+    return None;
+  }
+  llvm::MemoryBuffer *MemBuffer = SM.getBuffer(FID);
 
   llvm::MD5 Hash;
   llvm::MD5::MD5Result Result;

diff --git a/lib/CodeGen/CGDebugInfo.h b/lib/CodeGen/CGDebugInfo.h
index a692babef5369e436466610c5b0abc57ccdeb301..ec7b046c8f30aa47cb13bbf0fc50ea0c2ad6db95 100644 (file)
--- a/lib/CodeGen/CGDebugInfo.h
+++ b/lib/CodeGen/CGDebugInfo.h
@@ -57,6 +57,7 @@ class CGDebugInfo {
   CodeGenModule &CGM;
   const codegenoptions::DebugInfoKind DebugKind;
   bool DebugTypeExtRefs;
+  mutable bool EmitFileChecksums;
   llvm::DIBuilder DBuilder;
   llvm::DICompileUnit *TheCU = nullptr;
   ModuleMap *ClangModuleMap = nullptr;

diff --git a/test/CodeGen/md5-checksum-crash.c b/test/CodeGen/md5-checksum-crash.c
new file mode 100644 (file)
index 0000000..7a4d487
--- /dev/null
+++ b/test/CodeGen/md5-checksum-crash.c
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -triple %itanium_abi_triple -debug-info-kind=limited -dwarf-version=5 %s -emit-llvm -o- | FileCheck %s
+// RUN: %clang_cc1 -triple %ms_abi_triple -gcodeview -debug-info-kind=limited %s -emit-llvm -o- | FileCheck %s
+
+// This had been crashing, no MD5 checksum for string.h.
+// Now if there are #line directives, don't bother with checksums
+// as a preprocessed file won't properly reflect the original source.
+#define __NTH fct
+void fn1() {}
+# 7 "/usr/include/string.h"
+void __NTH() {}
+// Verify no checksum attributes on these files.
+// CHECK-DAG: DIFile(filename: "{{.*}}.c", directory: "{{[^"]*}}")
+// CHECK-DAG: DIFile(filename: "{{.*}}string.h", directory: "{{[^"]*}}")