From 6ce4c55a7217ab58c0df1259371a1c44d7e2cfa0 Mon Sep 17 00:00:00 2001
From: Paul Robinson <paul.robinson@sony.com>
Date: Fri, 25 May 2018 20:59:29 +0000
Subject: [PATCH] [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
---
 lib/CodeGen/CGDebugInfo.cpp       | 16 ++++++++++++----
 lib/CodeGen/CGDebugInfo.h         |  1 +
 test/CodeGen/md5-checksum-crash.c | 13 +++++++++++++
 3 files changed, 26 insertions(+), 4 deletions(-)
 create mode 100644 test/CodeGen/md5-checksum-crash.c

diff --git a/lib/CodeGen/CGDebugInfo.cpp b/lib/CodeGen/CGDebugInfo.cpp
index 9e99a646b0..8cf37f48a2 100644
--- 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 a692babef5..ec7b046c8f 100644
--- 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
index 0000000000..7a4d48757c
--- /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: "{{[^"]*}}")
-- 
2.50.1