[llvm][Dwarf] Create re-usable constants for C-language DWARFv6 language codes #163199
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…age codes Instead of hardcoding these in several places lets make these part of the `LLVMConstants` enum.
|
@llvm/pr-subscribers-debuginfo @llvm/pr-subscribers-llvm-binary-utilities Author: Michael Buch (Michael137) ChangesInstead of hardcoding these in several places lets make these part of the There's no official C++03 language version code so I left it out (though we have some support for it when converting between Full diff: https://github.com/llvm/llvm-project/pull/163199.diff 3 Files Affected:
diff --git a/llvm/include/llvm/BinaryFormat/Dwarf.h b/llvm/include/llvm/BinaryFormat/Dwarf.h
index 5039a3fe7ecc7..7a0fda1d041f5 100644
--- a/llvm/include/llvm/BinaryFormat/Dwarf.h
+++ b/llvm/include/llvm/BinaryFormat/Dwarf.h
@@ -66,6 +66,22 @@ enum LLVMConstants : uint32_t {
DW_ARANGES_VERSION = 2, ///< Section version number for .debug_aranges.
/// \}
+ /// DWARFv6 DW_AT_language_version constants:
+ /// https://dwarfstd.org/languages-v6.html
+ /// \{
+ DW_LANG_VERSION_C89 = 198912,
+ DW_LANG_VERSION_C99 = 199901,
+ DW_LANG_VERSION_C11 = 201112,
+ DW_LANG_VERSION_C17 = 201710,
+ DW_LANG_VERSION_C23 = 202311,
+ DW_LANG_VERSION_C_plus_plus_98 = 199711,
+ DW_LANG_VERSION_C_plus_plus_11 = 201103,
+ DW_LANG_VERSION_C_plus_plus_14 = 201402,
+ DW_LANG_VERSION_C_plus_plus_17 = 201703,
+ DW_LANG_VERSION_C_plus_plus_20 = 202002,
+ DW_LANG_VERSION_C_plus_plus_23 = 202302,
+ /// \}
+
/// Identifiers we use to distinguish vendor extensions.
/// \{
DWARF_VENDOR_DWARF = 0, ///< Defined in v2 or later of the DWARF standard.
@@ -246,29 +262,29 @@ inline std::optional<SourceLanguage> toDW_LANG(SourceLanguageName name,
case DW_LNAME_C: // YYYYMM, K&R 000000
if (version == 0)
return DW_LANG_C;
- if (version <= 198912)
+ if (version <= DW_LANG_VERSION_C89)
return DW_LANG_C89;
- if (version <= 199901)
+ if (version <= DW_LANG_VERSION_C99)
return DW_LANG_C99;
- if (version <= 201112)
+ if (version <= DW_LANG_VERSION_C11)
return DW_LANG_C11;
- if (version <= 201710)
+ if (version <= DW_LANG_VERSION_C17)
return DW_LANG_C17;
return {};
case DW_LNAME_C_plus_plus: // YYYYMM
if (version == 0)
return DW_LANG_C_plus_plus;
- if (version <= 199711)
+ if (version <= DW_LANG_VERSION_C_plus_plus_98)
return DW_LANG_C_plus_plus;
if (version <= 200310)
return DW_LANG_C_plus_plus_03;
- if (version <= 201103)
+ if (version <= DW_LANG_VERSION_C_plus_plus_11)
return DW_LANG_C_plus_plus_11;
- if (version <= 201402)
+ if (version <= DW_LANG_VERSION_C_plus_plus_14)
return DW_LANG_C_plus_plus_14;
- if (version <= 201703)
+ if (version <= DW_LANG_VERSION_C_plus_plus_17)
return DW_LANG_C_plus_plus_17;
- if (version <= 202002)
+ if (version <= DW_LANG_VERSION_C_plus_plus_20)
return DW_LANG_C_plus_plus_20;
return {};
case DW_LNAME_Cobol: // YYYY
@@ -384,25 +400,25 @@ toDW_LNAME(SourceLanguage language) {
case DW_LANG_C:
return {{DW_LNAME_C, 0}};
case DW_LANG_C89:
- return {{DW_LNAME_C, 198912}};
+ return {{DW_LNAME_C, DW_LANG_VERSION_C89}};
case DW_LANG_C99:
- return {{DW_LNAME_C, 199901}};
+ return {{DW_LNAME_C, DW_LANG_VERSION_C99}};
case DW_LANG_C11:
- return {{DW_LNAME_C, 201112}};
+ return {{DW_LNAME_C, DW_LANG_VERSION_C11}};
case DW_LANG_C17:
- return {{DW_LNAME_C, 201710}};
+ return {{DW_LNAME_C, DW_LANG_VERSION_C17}};
case DW_LANG_C_plus_plus:
return {{DW_LNAME_C_plus_plus, 0}};
case DW_LANG_C_plus_plus_03:
return {{DW_LNAME_C_plus_plus, 200310}};
case DW_LANG_C_plus_plus_11:
- return {{DW_LNAME_C_plus_plus, 201103}};
+ return {{DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_11}};
case DW_LANG_C_plus_plus_14:
- return {{DW_LNAME_C_plus_plus, 201402}};
+ return {{DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_14}};
case DW_LANG_C_plus_plus_17:
- return {{DW_LNAME_C_plus_plus, 201703}};
+ return {{DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_17}};
case DW_LANG_C_plus_plus_20:
- return {{DW_LNAME_C_plus_plus, 202002}};
+ return {{DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_20}};
case DW_LANG_Cobol74:
return {{DW_LNAME_Cobol, 1974}};
case DW_LANG_Cobol85:
diff --git a/llvm/lib/BinaryFormat/Dwarf.cpp b/llvm/lib/BinaryFormat/Dwarf.cpp
index 55fa2df632bfa..9c0dabd0e746f 100644
--- a/llvm/lib/BinaryFormat/Dwarf.cpp
+++ b/llvm/lib/BinaryFormat/Dwarf.cpp
@@ -513,30 +513,30 @@ StringRef llvm::dwarf::LanguageDescription(dwarf::SourceLanguageName Name,
case DW_LNAME_C: {
if (Version == 0)
break;
- if (Version <= 198912)
+ if (Version <= DW_LANG_VERSION_C89)
return "C89";
- if (Version <= 199901)
+ if (Version <= DW_LANG_VERSION_C99)
return "C99";
- if (Version <= 201112)
+ if (Version <= DW_LANG_VERSION_C11)
return "C11";
- if (Version <= 201710)
+ if (Version <= DW_LANG_VERSION_C17)
return "C17";
} break;
case DW_LNAME_C_plus_plus: {
if (Version == 0)
break;
- if (Version <= 199711)
+ if (Version <= DW_LANG_VERSION_C_plus_plus_98)
return "C++98";
if (Version <= 200310)
return "C++03";
- if (Version <= 201103)
+ if (Version <= DW_LANG_VERSION_C_plus_plus_11)
return "C++11";
- if (Version <= 201402)
+ if (Version <= DW_LANG_VERSION_C_plus_plus_14)
return "C++14";
- if (Version <= 201703)
+ if (Version <= DW_LANG_VERSION_C_plus_plus_17)
return "C++17";
- if (Version <= 202002)
+ if (Version <= DW_LANG_VERSION_C_plus_plus_20)
return "C++20";
} break;
diff --git a/llvm/unittests/BinaryFormat/DwarfTest.cpp b/llvm/unittests/BinaryFormat/DwarfTest.cpp
index ba7d59182ea53..a219a1ab51376 100644
--- a/llvm/unittests/BinaryFormat/DwarfTest.cpp
+++ b/llvm/unittests/BinaryFormat/DwarfTest.cpp
@@ -296,32 +296,32 @@ LanguageDescriptionTestCase LanguageDescriptionTestCases[] = {
{DW_LNAME_Fortran, 2019, "ISO Fortran"},
{DW_LNAME_C, 0, "C (K&R and ISO)"},
{DW_LNAME_C, 198911, "C89"},
- {DW_LNAME_C, 198912, "C89"},
- {DW_LNAME_C, 199901, "C99"},
+ {DW_LNAME_C, DW_LANG_VERSION_C89, "C89"},
+ {DW_LNAME_C, DW_LANG_VERSION_C99, "C99"},
{DW_LNAME_C, 199902, "C11"},
{DW_LNAME_C, 201111, "C11"},
- {DW_LNAME_C, 201112, "C11"},
+ {DW_LNAME_C, DW_LANG_VERSION_C11, "C11"},
{DW_LNAME_C, 201201, "C17"},
{DW_LNAME_C, 201709, "C17"},
- {DW_LNAME_C, 201710, "C17"},
+ {DW_LNAME_C, DW_LANG_VERSION_C17, "C17"},
{DW_LNAME_C, 201711, "C (K&R and ISO)"},
{DW_LNAME_C_plus_plus, 0, "ISO C++"},
{DW_LNAME_C_plus_plus, 199710, "C++98"},
- {DW_LNAME_C_plus_plus, 199711, "C++98"},
+ {DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_98, "C++98"},
{DW_LNAME_C_plus_plus, 199712, "C++03"},
{DW_LNAME_C_plus_plus, 200310, "C++03"},
{DW_LNAME_C_plus_plus, 200311, "C++11"},
{DW_LNAME_C_plus_plus, 201102, "C++11"},
- {DW_LNAME_C_plus_plus, 201103, "C++11"},
+ {DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_11, "C++11"},
{DW_LNAME_C_plus_plus, 201104, "C++14"},
{DW_LNAME_C_plus_plus, 201401, "C++14"},
- {DW_LNAME_C_plus_plus, 201402, "C++14"},
+ {DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_14, "C++14"},
{DW_LNAME_C_plus_plus, 201403, "C++17"},
{DW_LNAME_C_plus_plus, 201702, "C++17"},
- {DW_LNAME_C_plus_plus, 201703, "C++17"},
+ {DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_17, "C++17"},
{DW_LNAME_C_plus_plus, 201704, "C++20"},
{DW_LNAME_C_plus_plus, 202001, "C++20"},
- {DW_LNAME_C_plus_plus, 202002, "C++20"},
+ {DW_LNAME_C_plus_plus, DW_LANG_VERSION_C_plus_plus_20, "C++20"},
{DW_LNAME_C_plus_plus, 202003, "ISO C++"},
{DW_LNAME_ObjC_plus_plus, 0, LanguageDescription(DW_LNAME_ObjC_plus_plus)},
{DW_LNAME_ObjC_plus_plus, 1, LanguageDescription(DW_LNAME_ObjC_plus_plus)},
|
Michael137
commented
Oct 13, 2025
| /// DWARFv6 DW_AT_language_version constants: | ||
| /// https://dwarfstd.org/languages-v6.html | ||
| /// \{ | ||
| DW_LANG_VERSION_C89 = 198912, |
There was a problem hiding this comment.
Not sure what the best naming convention here would be. The DW_LANG_ prefix might get confused with the DW_LANG_ language codes.
| if (version == 0) | ||
| return DW_LANG_C; | ||
| if (version <= 198912) | ||
| if (version <= DW_LANG_VERSION_C89) |
There was a problem hiding this comment.
What do you think about adding a table to Dwarf.def that ties these together, such as:
HANDLE_DW_LANG_VERSION(DW_LANG_C99, "C99", 199901)
?
There was a problem hiding this comment.
Hmm how would we be able to re-use it in this function though? Because we're enumerating DW_LNAME_, not DW_LANG_. And DW_LNAME_ doesn't encode versions
There was a problem hiding this comment.
Right, we would either need one macro per language or a real lookup table. And wether the table lives in code or data doesn't make a huge difference.
adrian-prantl
approved these changes
Oct 14, 2025
| if (version == 0) | ||
| return DW_LANG_C; | ||
| if (version <= 198912) | ||
| if (version <= DW_LANG_VERSION_C89) |
There was a problem hiding this comment.
Right, we would either need one macro per language or a real lookup table. And wether the table lives in code or data doesn't make a huge difference.
|
Closing in favour of #163348 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Instead of hardcoding these in several places lets make these part of the
LLVMConstantsenum.There's no official C++03 language version code so I left it out (though we have some support for it when converting between
DW_LNAME_andDW_LANG_C_plus_plus_03).