r333311 - [DebugInfo] Don't bother with MD5 checksums of preprocessed files.

[Paul Robinson via cfe-commits]

Author: probinson
Date: Fri May 25 13:59:29 2018
New Revision: 333311

URL: http://llvm.org/viewvc/llvm-project?rev=333311&view=rev
Log:
[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

Added:
    cfe/trunk/test/CodeGen/md5-checksum-crash.c
Modified:
    cfe/trunk/lib/CodeGen/CGDebugInfo.cpp
    cfe/trunk/lib/CodeGen/CGDebugInfo.h

Modified: cfe/trunk/lib/CodeGen/CGDebugInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/CodeGen/CGDebugInfo.cpp?rev=333311&r1=333310&r2=333311&view=diff
==============================================================================
--- cfe/trunk/lib/CodeGen/CGDebugInfo.cpp (original)
+++ cfe/trunk/lib/CodeGen/CGDebugInfo.cpp Fri May 25 13:59:29 2018
@@ -67,6 +67,8 @@ CGDebugInfo::CGDebugInfo(CodeGenModule &
       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;

Modified: cfe/trunk/lib/CodeGen/CGDebugInfo.h
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/CodeGen/CGDebugInfo.h?rev=333311&r1=333310&r2=333311&view=diff
==============================================================================
--- cfe/trunk/lib/CodeGen/CGDebugInfo.h (original)
+++ cfe/trunk/lib/CodeGen/CGDebugInfo.h Fri May 25 13:59:29 2018
@@ -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;

Added: cfe/trunk/test/CodeGen/md5-checksum-crash.c
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGen/md5-checksum-crash.c?rev=333311&view=auto
==============================================================================
--- cfe/trunk/test/CodeGen/md5-checksum-crash.c (added)
+++ cfe/trunk/test/CodeGen/md5-checksum-crash.c Fri May 25 13:59:29 2018
@@ -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: "{{[^"]*}}")