Reapply "DebugInfo: Add/support new DW_LANG codes for recent C and C++ versions""

This may be a breaking change for consumers if they're trying to detect
if code is C or C++, since it'll start using new codes that they may not
be ready to recognize, in which case they may fall back to non-C
handling.

This caused regressions due to PS4 having a different default for C
language version than other targets. Those tests were adapted to be
relaxed about which C version is used.

This reapplies commit 3c312e4
Which was reverted by commit 6ab6085.

Differential Revision: https://reviews.llvm.org/D138597

Author: dwblaikie

clang/lib/CodeGen/CGDebugInfo.cpp

@@ -526,7 +526,8 @@ void CGDebugInfo::CreateCompileUnit() {
 
   // Get absolute path name.
   SourceManager &SM = CGM.getContext().getSourceManager();
-  std::string MainFileName = CGM.getCodeGenOpts().MainFileName;
+  auto &CGO = CGM.getCodeGenOpts();
+  std::string MainFileName = CGO.MainFileName;
   if (MainFileName.empty())
     MainFileName = "<stdin>";
 
@@ -562,11 +563,11 @@ void CGDebugInfo::CreateCompileUnit() {
   if (LO.CPlusPlus) {
     if (LO.ObjC)
       LangTag = llvm::dwarf::DW_LANG_ObjC_plus_plus;
-    else if (LO.CPlusPlus14 && (!CGM.getCodeGenOpts().DebugStrictDwarf ||
-                                CGM.getCodeGenOpts().DwarfVersion >= 5))
+    else if (CGO.DebugStrictDwarf && CGO.DwarfVersion < 5)
+      LangTag = llvm::dwarf::DW_LANG_C_plus_plus;
+    else if (LO.CPlusPlus14)
       LangTag = llvm::dwarf::DW_LANG_C_plus_plus_14;
-    else if (LO.CPlusPlus11 && (!CGM.getCodeGenOpts().DebugStrictDwarf ||
-                                CGM.getCodeGenOpts().DwarfVersion >= 5))
+    else if (LO.CPlusPlus11)
       LangTag = llvm::dwarf::DW_LANG_C_plus_plus_11;
     else
       LangTag = llvm::dwarf::DW_LANG_C_plus_plus;
@@ -577,6 +578,8 @@ void CGDebugInfo::CreateCompileUnit() {
     LangTag = llvm::dwarf::DW_LANG_OpenCL;
   } else if (LO.RenderScript) {
     LangTag = llvm::dwarf::DW_LANG_GOOGLE_RenderScript;
+  } else if (LO.C11) {
+    LangTag = llvm::dwarf::DW_LANG_C11;
   } else if (LO.C99) {
     LangTag = llvm::dwarf::DW_LANG_C99;
   } else {

clang/test/CodeGen/debug-info-preprocessed-file.i

@@ -7,5 +7,5 @@
 # 1 "preprocessed-input.c" 2
 
 // RUN: %clang -g -c -S -emit-llvm -o - %s | FileCheck %s
-// CHECK: !DICompileUnit(language: DW_LANG_C99, file: ![[FILE:[0-9]+]] 
+// CHECK: !DICompileUnit(language: DW_LANG_C{{.*}}, file: ![[FILE:[0-9]+]]
 // CHECK: ![[FILE]] = !DIFile(filename: "/foo/bar/preprocessed-input.c"

clang/test/CodeGen/debug-info-programming-language.c

@@ -0,0 +1,15 @@
+// RUN: %clang_cc1 -dwarf-version=3 -emit-llvm -triple %itanium_abi_triple %s -o - \
+// RUN:   -x c -std=c11 -O0 -disable-llvm-passes -debug-info-kind=limited \
+// RUN:   | FileCheck --check-prefix=CHECK-C11 %s
+// RUN: %clang_cc1 -dwarf-version=3 -emit-llvm -triple %itanium_abi_triple %s -o - \
+// RUN:   -x c -std=c17 -O0 -disable-llvm-passes -debug-info-kind=limited \
+// RUN:   | FileCheck --check-prefix=CHECK-C17 %s
+
+// CHECK-C11: !DICompileUnit(language: DW_LANG_C11
+// Update this check once support for DW_LANG_C17 is broadly supported/known in
+// consumers. Maybe we'll skip this and go to the DWARFv6 language+version
+// encoding that avoids the risk of regression when describing a language
+// version newer than what the consumer is aware of.
+// CHECK-C17: !DICompileUnit(language: DW_LANG_C11
+
+void f1(void) { }

clang/test/CodeGenCXX/debug-info-programming-language.cpp

@@ -4,6 +4,12 @@
 // RUN: %clang_cc1 -dwarf-version=3 -emit-llvm -triple %itanium_abi_triple %s -o - \
 // RUN:   -x c++ -std=c++14 -O0 -disable-llvm-passes -debug-info-kind=limited \
 // RUN:   | FileCheck --check-prefix=CHECK-CPP14 %s
+// RUN: %clang_cc1 -dwarf-version=3 -emit-llvm -triple %itanium_abi_triple %s -o - \
+// RUN:   -x c++ -std=c++17 -O0 -disable-llvm-passes -debug-info-kind=limited \
+// RUN:   | FileCheck --check-prefix=CHECK-CPP17 %s
+// RUN: %clang_cc1 -dwarf-version=3 -emit-llvm -triple %itanium_abi_triple %s -o - \
+// RUN:   -x c++ -std=c++20 -O0 -disable-llvm-passes -debug-info-kind=limited \
+// RUN:   | FileCheck --check-prefix=CHECK-CPP20 %s
 // RUN: %clang_cc1 -dwarf-version=3 -gstrict-dwarf -emit-llvm -triple %itanium_abi_triple %s -o - \
 // RUN:   -x c++ -std=c++14 -O0 -disable-llvm-passes -debug-info-kind=limited | FileCheck %s
 // RUN: %clang_cc1 -dwarf-version=5 -gstrict-dwarf -emit-llvm -triple %itanium_abi_triple %s -o - \
@@ -14,5 +20,15 @@ int main() {
   return 0;
 }
 
+// Update these tests once support for DW_LANG_C_plus_plus_17/20 is added - it's
+// a complicated tradeoff. The language codes are already published/blessed by
+// the DWARF committee, but haven't been released in a published standard yet,
+// so consumers might not be ready for these codes & could regress functionality
+// (because they wouldn't be able to identify that the language was C++). The
+// DWARFv6 language encoding, separating language from language version, would
+// remove this problem/not require new codes for new language versions and make
+// it possible to identify the base language irrespective of the version.
 // CHECK-CPP14: distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14,
+// CHECK-CPP17: distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14,
+// CHECK-CPP20: distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14,
 // CHECK: distinct !DICompileUnit(language: DW_LANG_C_plus_plus,

clang/test/PCH/debug-info-pch-container-path.c

@@ -14,7 +14,7 @@
 // RUN: cat %t-container.ll | FileCheck %s
 
 // CHECK: distinct !DICompileUnit(
-// CHECK-SAME:                    language: DW_LANG_C99,
+// CHECK-SAME:                    language: DW_LANG_C{{[^,]*}},
 // CHECK-SAME:                    file: ![[FILE:[0-9]+]],
 // CHECK: ![[FILE]] = !DIFile(
 // CHECK-SAME:                filename: "SOURCE/debug-info-limited-struct.h",