[PATCH] dwarf2out: Emit DWARF 6 DW_AT_language_{name,version}

Jakub Jelinek via Gdb <[email protected]>
Newsgroups gmane.comp.gdb.devel,gmane.comp.gcc.patches
Message-ID <Z31+98CZmv7BROyx@tucnak> 
Hi!

DWARF has voted in yesterday https://dwarfstd.org/issues/241209.1.html ,
which is basically just a guarantee that the DWARF 6 draft
DW_AT_language_{name,version} attribute codes and content of
https://dwarfstd.org/languages-v6.html can be used as an extension
in DWARF 5 and won't be changed.

So, this patch is an alternative to the
https://gcc.gnu.org/pipermail/gcc-patches/2024-November/669671.html
patch, which had the major problem that it required changing all the
DWARF consumers to be able to debug C17 or later or C++17 or later
sources.
This patch uses still DWARF 5 DW_LANG_C11 or DW_LANG_C_plus_plus_14,
the latest code in DWARF 5 proper, so all DWARF 5 capable consumers
should be able to deal with that, but additionally emits the
DWARF 6 attributes so that newer DWARF consumers can see it isn't
just C++14 but say C++23 or C11 but C23.  Consumers which don't know
those DWARF 6 attributes would just ignore them.  This is like any other
-gno-strict-dwarf extension, except that normally we emit say DWARF 5
codes where possible only after DWARF 5 is released, while in this case
there is a guarantee it can be used before DWARF 6 is released.

Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?

2025-01-07  Jakub Jelinek  <[email protected]>

include/
	* dwarf2.h (enum dwarf_source_language): Fix comment pasto.
	(enum dwarf_source_language_name): New type.
	* dwarf2.def (DW_AT_language_name, DW_AT_language_version): New
	DWARF 6 codes.
gcc/
	* dwarf2out.cc (break_out_comdat_types): Copy over
	DW_AT_language_{name,version} if present.
	(output_skeleton_debug_sections): Remove also
	DW_AT_language_{name,version}.
	(gen_compile_unit_die): For C17, C23, C2Y, C++17, C++20, C++23
	and C++26 emit for -gdwarf-5 -gno-strict-dwarf also
	DW_AT_language_{name,version} attributes.
gcc/testsuite/
	* g++.dg/debug/dwarf2/lang-cpp17.C: Add -gno-strict-dwarf to
	dg-options.  Check also for DW_AT_language_{name,version} values.
	* g++.dg/debug/dwarf2/lang-cpp20.C: Likewise.
	* g++.dg/debug/dwarf2/lang-cpp23.C: New test.

--- include/dwarf2.h.jj	2025-01-02 11:47:47.431981968 +0100
+++ include/dwarf2.h	2025-01-06 18:55:59.802378204 +0100
@@ -411,7 +411,7 @@ enum dwarf_source_language
     DW_LANG_Hylo = 0x0042,
 
     DW_LANG_lo_user = 0x8000,	/* Implementation-defined range start.  */
-    DW_LANG_hi_user = 0xffff,	/* Implementation-defined range start.  */
+    DW_LANG_hi_user = 0xffff,	/* Implementation-defined range end.  */
 
     /* MIPS.  */
     DW_LANG_Mips_Assembler = 0x8001,
@@ -428,6 +428,59 @@ enum dwarf_source_language
     DW_LANG_Rust_old = 0x9000
   };
 
+/* DWARF 6 source language names and codes.  */
+enum dwarf_source_language_name
+  {
+    /* https://dwarfstd.org/languages-v6.html */
+    DW_LNAME_Ada = 0x0001,
+    DW_LNAME_BLISS = 0x0002,
+    DW_LNAME_C = 0x0003,
+    DW_LNAME_C_plus_plus = 0x0004,
+    DW_LNAME_Cobol = 0x0005,
+    DW_LNAME_Crystal = 0x0006,
+    DW_LNAME_D = 0x0007,
+    DW_LNAME_Dylan = 0x0008,
+    DW_LNAME_Fortran = 0x0009,
+    DW_LNAME_Go = 0x000a,
+    DW_LNAME_Haskell = 0x000b,
+    DW_LNAME_Java = 0x000c,
+    DW_LNAME_Julia = 0x000d,
+    DW_LNAME_Kotlin = 0x000e,
+    DW_LNAME_Modula2 = 0x000f,
+    DW_LNAME_Modula3 = 0x0010,
+    DW_LNAME_ObjC = 0x0011,
+    DW_LNAME_ObjC_plus_plus = 0x0012,
+    DW_LNAME_OCaml = 0x0013,
+    DW_LNAME_OpenCL_C = 0x0014,
+    DW_LNAME_Pascal = 0x0015,
+    DW_LNAME_PLI = 0x0016,
+    DW_LNAME_Python = 0x0017,
+    DW_LNAME_RenderScript = 0x0018,
+    DW_LNAME_Rust = 0x0019,
+    DW_LNAME_Swift = 0x001a,
+    DW_LNAME_UPC = 0x001b,
+    DW_LNAME_Zig = 0x001c,
+    DW_LNAME_Assembly = 0x001d,
+    DW_LNAME_C_sharp = 0x001e,
+    DW_LNAME_Mojo = 0x001f,
+    DW_LNAME_GLSL = 0x0020,
+    DW_LNAME_GLSL_ES = 0x0021,
+    DW_LNAME_HLSL = 0x0022,
+    DW_LNAME_OpenCL_CPP = 0x0023,
+    DW_LNAME_CPP_for_OpenCL = 0x0024,
+    DW_LNAME_SYCL = 0x0025,
+    DW_LNAME_Ruby = 0x0026,
+    DW_LNAME_Move = 0x0027,
+    DW_LNAME_Hylo = 0x0028,
+    DW_LNAME_HIP = 0x0029,
+    DW_LNAME_Odin = 0x002a,
+    DW_LNAME_P4 = 0x002b,
+    DW_LNAME_Metal = 0x002c,
+
+    DW_LNAME_lo_user = 0x8000,	/* Implementation-defined range start.  */
+    DW_LNAME_hi_user = 0xffff	/* Implementation-defined range end.  */
+  };
+
 /* Names and codes for macro information.  */
 enum dwarf_macinfo_record_type
   {
--- include/dwarf2.def.jj	2025-01-02 11:47:47.191985318 +0100
+++ include/dwarf2.def	2025-01-06 18:39:02.642383150 +0100
@@ -364,6 +364,9 @@ DW_AT (DW_AT_export_symbols, 0x89)
 DW_AT (DW_AT_deleted, 0x8a)
 DW_AT (DW_AT_defaulted, 0x8b)
 DW_AT (DW_AT_loclists_base, 0x8c)
+/* DWARF 6.  */
+DW_AT (DW_AT_language_name, 0x90)
+DW_AT (DW_AT_language_version, 0x91)
 
 DW_AT_DUP (DW_AT_lo_user, 0x2000) /* Implementation-defined range start.  */
 DW_AT_DUP (DW_AT_hi_user, 0x3fff) /* Implementation-defined range end.  */
--- gcc/dwarf2out.cc.jj	2025-01-02 11:23:35.541251268 +0100
+++ gcc/dwarf2out.cc	2025-01-07 10:09:16.866866563 +0100
@@ -8755,6 +8755,14 @@ break_out_comdat_types (dw_die_ref die)
         unit = new_die (DW_TAG_type_unit, NULL, NULL);
         add_AT_unsigned (unit, DW_AT_language,
                          get_AT_unsigned (comp_unit_die (), DW_AT_language));
+	if (unsigned lname = get_AT_unsigned (comp_unit_die (),
+					      DW_AT_language_name))
+	  {
+	    add_AT_unsigned (unit, DW_AT_language_name, lname);
+	    add_AT_unsigned (unit, DW_AT_language_version,
+			     get_AT_unsigned (comp_unit_die (),
+					      DW_AT_language_version));
+	  }
 
 	/* Add the new unit's type DIE into the comdat type list.  */
         type_node = ggc_cleared_alloc<comdat_type_node> ();
@@ -11404,6 +11412,8 @@ output_skeleton_debug_sections (dw_die_r
   /* These attributes will be found in the full debug_info section.  */
   remove_AT (comp_unit, DW_AT_producer);
   remove_AT (comp_unit, DW_AT_language);
+  remove_AT (comp_unit, DW_AT_language_name);
+  remove_AT (comp_unit, DW_AT_language_version);
 
   switch_to_section (debug_skeleton_info_section);
   ASM_OUTPUT_LABEL (asm_out_file, debug_skeleton_info_section_label);
@@ -25318,7 +25328,7 @@ gen_compile_unit_die (const char *filena
 {
   dw_die_ref die;
   const char *language_string = lang_hooks.name;
-  int language;
+  int language, lname, lversion;
 
   die = new_die (DW_TAG_compile_unit, NULL, NULL);
 
@@ -25366,6 +25376,8 @@ gen_compile_unit_die (const char *filena
     }
 
   language = DW_LANG_C;
+  lname = 0;
+  lversion = 0;
   if (startswith (language_string, "GNU C")
       && ISDIGIT (language_string[5]))
     {
@@ -25376,11 +25388,28 @@ gen_compile_unit_die (const char *filena
 	    language = DW_LANG_C99;
 
 	  if (dwarf_version >= 5 /* || !dwarf_strict */)
-	    if (strcmp (language_string, "GNU C11") == 0
-		|| strcmp (language_string, "GNU C17") == 0
-		|| strcmp (language_string, "GNU C23") == 0
-		|| strcmp (language_string, "GNU C2Y") == 0)
-	      language = DW_LANG_C11;
+	    {
+	      if (strcmp (language_string, "GNU C11") == 0)
+		language = DW_LANG_C11;
+	      else if (strcmp (language_string, "GNU C17") == 0)
+		{
+		  language = DW_LANG_C11;
+		  lname = DW_LNAME_C;
+		  lversion = 201710;
+		}
+	      else if (strcmp (language_string, "GNU C23") == 0)
+		{
+		  language = DW_LANG_C11;
+		  lname = DW_LNAME_C;
+		  lversion = 202311;
+		}
+	      else if (strcmp (language_string, "GNU C2Y") == 0)
+		{
+		  language = DW_LANG_C11;
+		  lname = DW_LNAME_C;
+		  lversion = 202500;
+		}
+	    }
 	}
     }
   else if (startswith (language_string, "GNU C++"))
@@ -25392,12 +25421,30 @@ gen_compile_unit_die (const char *filena
 	    language = DW_LANG_C_plus_plus_11;
 	  else if (strcmp (language_string, "GNU C++14") == 0)
 	    language = DW_LANG_C_plus_plus_14;
-	  else if (strcmp (language_string, "GNU C++17") == 0
-		   || strcmp (language_string, "GNU C++20") == 0
-		   || strcmp (language_string, "GNU C++23") == 0
-		   || strcmp (language_string, "GNU C++26") == 0)
-	    /* For now.  */
-	    language = DW_LANG_C_plus_plus_14;
+	  else if (strcmp (language_string, "GNU C++17") == 0)
+	    {
+	      language = DW_LANG_C_plus_plus_14;
+	      lname = DW_LNAME_C_plus_plus;
+	      lversion = 201703;
+	    }
+	  else if (strcmp (language_string, "GNU C++20") == 0)
+	    {
+	      language = DW_LANG_C_plus_plus_14;
+	      lname = DW_LNAME_C_plus_plus;
+	      lversion = 202002;
+	    }
+	  else if (strcmp (language_string, "GNU C++23") == 0)
+	    {
+	      language = DW_LANG_C_plus_plus_14;
+	      lname = DW_LNAME_C_plus_plus;
+	      lversion = 202302;
+	    }
+	  else if (strcmp (language_string, "GNU C++26") == 0)
+	    {
+	      language = DW_LANG_C_plus_plus_14;
+	      lname = DW_LNAME_C_plus_plus;
+	      lversion = 202400;
+	    }
 	}
     }
   else if (strcmp (language_string, "GNU F77") == 0)
@@ -25441,6 +25488,11 @@ gen_compile_unit_die (const char *filena
     language = DW_LANG_Ada83;
 
   add_AT_unsigned (die, DW_AT_language, language);
+  if (lname && dwarf_version >= 5 && !dwarf_strict)
+    {
+      add_AT_unsigned (die, DW_AT_language_name, lname);
+      add_AT_unsigned (die, DW_AT_language_version, lversion);
+    }
 
   switch (language)
     {
--- gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp17.C.jj	2021-01-18 07:18:14.929659650 +0100
+++ gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp17.C	2025-01-07 10:07:46.473125326 +0100
@@ -1,8 +1,10 @@
 // { dg-do compile }
-// { dg-options "-O -std=c++17 -gdwarf-5 -dA" }
+// { dg-options "-O -std=c++17 -gdwarf-5 -dA -gno-strict-dwarf" }
 // { dg-skip-if "AIX DWARF5" { powerpc-ibm-aix* } }
-// For -gdwarf-6 hopefully DW_LANG_C_plus_plus_17
 // DW_LANG_C_plus_plus_14 = 0x0021
+// DW_LNAME_C_plus_plus = 0x0004 201703
 // { dg-final { scan-assembler "0x21\[^\n\r]* DW_AT_language" } } */
+// { dg-final { scan-assembler "0x4\[^\n\r]* DW_AT_language_name" } } */
+// { dg-final { scan-assembler "0x313e7\[^\n\r]* DW_AT_language_version" } } */
 
 int version;
--- gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp20.C.jj	2021-01-18 14:52:42.946040137 +0100
+++ gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp20.C	2025-01-07 10:08:28.982533366 +0100
@@ -1,8 +1,10 @@
 // { dg-do compile }
-// { dg-options "-O -std=c++20 -gdwarf-5 -dA" }
+// { dg-options "-O -std=c++20 -gdwarf-5 -dA -gno-strict-dwarf" }
 // { dg-skip-if "AIX DWARF5" { powerpc-ibm-aix* } }
-// For -gdwarf-6 hopefully DW_LANG_C_plus_plus_20
 // DW_LANG_C_plus_plus_14 = 0x0021
+// DW_LNAME_C_plus_plus = 0x0004 202002
 // { dg-final { scan-assembler "0x21\[^\n\r]* DW_AT_language" } } */
+// { dg-final { scan-assembler "0x4\[^\n\r]* DW_AT_language_name" } } */
+// { dg-final { scan-assembler "0x31512\[^\n\r]* DW_AT_language_version" } } */
 
 int version;
--- gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp23.C.jj	2025-01-07 10:07:54.926007612 +0100
+++ gcc/testsuite/g++.dg/debug/dwarf2/lang-cpp23.C	2025-01-07 10:08:19.206669497 +0100
@@ -0,0 +1,10 @@
+// { dg-do compile }
+// { dg-options "-O -std=c++23 -gdwarf-5 -dA -gno-strict-dwarf" }
+// { dg-skip-if "AIX DWARF5" { powerpc-ibm-aix* } }
+// DW_LANG_C_plus_plus_14 = 0x0021
+// DW_LNAME_C_plus_plus = 0x0004 202302
+// { dg-final { scan-assembler "0x21\[^\n\r]* DW_AT_language" } } */
+// { dg-final { scan-assembler "0x4\[^\n\r]* DW_AT_language_name" } } */
+// { dg-final { scan-assembler "0x3163e\[^\n\r]* DW_AT_language_version" } } */
+
+int version;

	Jakub
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.