[llvm-dwarfdump] Support for DW_AT_language_name and DW_AT_language_version #162449
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
|
@llvm/pr-subscribers-llvm-binary-utilities @llvm/pr-subscribers-debuginfo Author: Michael Buch (Michael137) ChangesDepends on:
Makes sure we dump the attributes in a user-friendly way. More info on the attributes here: https://dwarfstd.org/languages-v6.html Full diff: https://github.com/llvm/llvm-project/pull/162449.diff 7 Files Affected:
diff --git a/llvm/include/llvm/BinaryFormat/Dwarf.def b/llvm/include/llvm/BinaryFormat/Dwarf.def
index 2c9a3c0f6fb04..fbf22cc6f760b 100644
--- a/llvm/include/llvm/BinaryFormat/Dwarf.def
+++ b/llvm/include/llvm/BinaryFormat/Dwarf.def
@@ -424,6 +424,9 @@ HANDLE_DW_AT(0x89, export_symbols, 5, DWARF)
HANDLE_DW_AT(0x8a, deleted, 5, DWARF)
HANDLE_DW_AT(0x8b, defaulted, 5, DWARF)
HANDLE_DW_AT(0x8c, loclists_base, 5, DWARF)
+// New in Dwarf v6:
+HANDLE_DW_AT(0x90, language_name, 6, DWARF)
+HANDLE_DW_AT(0x91, language_version, 6, DWARF)
// Vendor extensions:
HANDLE_DW_AT(0x806, GHS_namespace_alias, 0, GHS)
diff --git a/llvm/include/llvm/BinaryFormat/Dwarf.h b/llvm/include/llvm/BinaryFormat/Dwarf.h
index 2c5012510a5c3..ba74ab9515a75 100644
--- a/llvm/include/llvm/BinaryFormat/Dwarf.h
+++ b/llvm/include/llvm/BinaryFormat/Dwarf.h
@@ -997,6 +997,7 @@ LLVM_ABI StringRef VisibilityString(unsigned Visibility);
LLVM_ABI StringRef VirtualityString(unsigned Virtuality);
LLVM_ABI StringRef EnumKindString(unsigned EnumKind);
LLVM_ABI StringRef LanguageString(unsigned Language);
+LLVM_ABI StringRef SourceLanguageNameString(SourceLanguageName Lang);
LLVM_ABI StringRef CaseString(unsigned Case);
LLVM_ABI StringRef ConventionString(unsigned Convention);
LLVM_ABI StringRef InlineCodeString(unsigned Code);
@@ -1038,6 +1039,7 @@ LLVM_ABI unsigned getSubOperationEncoding(unsigned OpEncoding,
LLVM_ABI unsigned getVirtuality(StringRef VirtualityString);
LLVM_ABI unsigned getEnumKind(StringRef EnumKindString);
LLVM_ABI unsigned getLanguage(StringRef LanguageString);
+LLVM_ABI unsigned getSourceLanguageName(StringRef SourceLanguageNameString);
LLVM_ABI unsigned getCallingConvention(StringRef LanguageString);
LLVM_ABI unsigned getAttributeEncoding(StringRef EncodingString);
LLVM_ABI unsigned getMacinfo(StringRef MacinfoString);
diff --git a/llvm/lib/BinaryFormat/Dwarf.cpp b/llvm/lib/BinaryFormat/Dwarf.cpp
index 8b24044e19e50..033c6a44be638 100644
--- a/llvm/lib/BinaryFormat/Dwarf.cpp
+++ b/llvm/lib/BinaryFormat/Dwarf.cpp
@@ -472,6 +472,26 @@ StringRef llvm::dwarf::LanguageDescription(dwarf::SourceLanguageName lname) {
return "Unknown";
}
+llvm::StringRef llvm::dwarf::SourceLanguageNameString(SourceLanguageName Lang) {
+ switch (Lang) {
+#define HANDLE_DW_LNAME(ID, NAME, DESC, LOWER_BOUND) \
+ case DW_LNAME_##NAME: \
+ return "DW_LNAME_" #NAME;
+#include "llvm/BinaryFormat/Dwarf.def"
+ }
+
+ return {};
+}
+
+unsigned
+llvm::dwarf::getSourceLanguageName(StringRef SourceLanguageNameString) {
+ return StringSwitch<unsigned>(SourceLanguageNameString)
+#define HANDLE_DW_LNAME(ID, NAME, DESC, LOWER_BOUND) \
+ .Case("DW_LNAME_" #NAME, DW_LNAME_##NAME)
+#include "llvm/BinaryFormat/Dwarf.def"
+ .Default(0);
+}
+
StringRef llvm::dwarf::CaseString(unsigned Case) {
switch (Case) {
case DW_ID_case_sensitive:
@@ -762,6 +782,8 @@ StringRef llvm::dwarf::AttributeValueString(uint16_t Attr, unsigned Val) {
return DefaultedMemberString(Val);
case DW_AT_APPLE_enum_kind:
return EnumKindString(Val);
+ case DW_AT_language_name:
+ return SourceLanguageNameString(static_cast<SourceLanguageName>(Val));
}
return StringRef();
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
index edc69a36cdff2..212a0c039298b 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
@@ -149,7 +149,8 @@ static void dumpAttribute(raw_ostream &OS, const DWARFDie &Die,
if (!Name.empty())
WithColor(OS, Color) << Name;
else if (Attr == DW_AT_decl_line || Attr == DW_AT_decl_column ||
- Attr == DW_AT_call_line || Attr == DW_AT_call_column) {
+ Attr == DW_AT_call_line || Attr == DW_AT_call_column ||
+ Attr == DW_AT_language_version) {
if (std::optional<uint64_t> Val = FormValue.getAsUnsignedConstant())
OS << *Val;
else
diff --git a/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_name.s b/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_name.s
new file mode 100644
index 0000000000000..af581753be56a
--- /dev/null
+++ b/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_name.s
@@ -0,0 +1,35 @@
+# Demonstrate dumping DW_AT_language_name.
+# RUN: llvm-mc -triple=x86_64--linux -filetype=obj < %s | \
+# RUN: llvm-dwarfdump -v - | FileCheck %s
+
+# CHECK: .debug_abbrev contents:
+# CHECK: DW_AT_language_name DW_FORM_data2
+# CHECK: DW_AT_language_name DW_FORM_data2
+# CHECK: .debug_info contents:
+# CHECK: DW_AT_language_name [DW_FORM_data2] (DW_LNAME_C)
+# CHECK: DW_AT_language_name [DW_FORM_data2] (0x0000)
+
+ .section .debug_abbrev,"",@progbits
+ .byte 1 # Abbreviation Code
+ .byte 17 # DW_TAG_compile_unit
+ .byte 1 # DW_CHILDREN_no
+ .ascii "\220\001" # DW_AT_language_name
+ .byte 5 # DW_FORM_data2
+ .ascii "\220\001" # DW_AT_language_name
+ .byte 5 # DW_FORM_data2
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 0 # EOM(3)
+
+ .section .debug_info,"",@progbits
+ .long .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+ .short 5 # DWARF version number
+ .byte 1 # Unit type
+ .byte 8 # Address Size (in bytes)
+ .long .debug_abbrev # Offset Into Abbrev. Section
+ .byte 1 # Abbrev [1] DW_TAG_compile_unit
+ .short 3 # DW_AT_language_name
+ .short 0 # DW_AT_language_name
+ .byte 0
+.Ldebug_info_end0:
diff --git a/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_version.s b/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_version.s
new file mode 100644
index 0000000000000..f1be8fdf6cd3e
--- /dev/null
+++ b/llvm/test/tools/llvm-dwarfdump/X86/DW_AT_language_version.s
@@ -0,0 +1,35 @@
+# Demonstrate dumping DW_AT_language_version.
+# RUN: llvm-mc -triple=x86_64--linux -filetype=obj < %s | \
+# RUN: llvm-dwarfdump -v - | FileCheck %s
+
+# CHECK: .debug_abbrev contents:
+# CHECK: DW_AT_language_version DW_FORM_data4
+# CHECK: DW_AT_language_version DW_FORM_data2
+# CHECK: .debug_info contents:
+# CHECK: DW_AT_language_version [DW_FORM_data4] (201402)
+# CHECK: DW_AT_language_version [DW_FORM_data2] (0)
+
+ .section .debug_abbrev,"",@progbits
+ .byte 1 # Abbreviation Code
+ .byte 17 # DW_TAG_compile_unit
+ .byte 1 # DW_CHILDREN_no
+ .ascii "\221\001" # DW_AT_language_version
+ .byte 6 # DW_FORM_data4
+ .ascii "\221\001" # DW_AT_language_version
+ .byte 5 # DW_FORM_data2
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 0 # EOM(3)
+
+ .section .debug_info,"",@progbits
+ .long .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+ .short 5 # DWARF version number
+ .byte 1 # Unit type
+ .byte 8 # Address Size (in bytes)
+ .long .debug_abbrev # Offset Into Abbrev. Section
+ .byte 1 # Abbrev [1] DW_TAG_compile_unit
+ .long 201402 # DW_AT_language_version
+ .short 0 # DW_AT_language_version
+ .byte 0
+.Ldebug_info_end0:
diff --git a/llvm/unittests/BinaryFormat/DwarfTest.cpp b/llvm/unittests/BinaryFormat/DwarfTest.cpp
index 684e59fa2785c..1162eb709aa83 100644
--- a/llvm/unittests/BinaryFormat/DwarfTest.cpp
+++ b/llvm/unittests/BinaryFormat/DwarfTest.cpp
@@ -219,4 +219,39 @@ TEST(DwarfTest, lname) {
EXPECT_EQ(roundtrip(DW_LANG_##NAME), DW_LANG_##NAME);
#include "llvm/BinaryFormat/Dwarf.def"
}
+
+TEST(DwarfTest, lname_getSourceLanguageName) {
+ // Some basics.
+ EXPECT_EQ(getSourceLanguageName("DW_LNAME_Ada"), DW_LNAME_Ada);
+ EXPECT_EQ(getSourceLanguageName("DW_LNAME_Metal"), DW_LNAME_Metal);
+
+ // Test invalid input.
+ EXPECT_EQ(getSourceLanguageName(""), 0U);
+ EXPECT_EQ(getSourceLanguageName("blah"), 0U);
+ EXPECT_EQ(getSourceLanguageName("DW_LNAME__something_unlikely"), 0U);
+ EXPECT_EQ(getSourceLanguageName("DW_LANG_C"), 0U);
+
+ // Test that we cover all DW_LNAME_ names.
+#define xstr(X) #X
+#define HANDLE_DW_LNAME(ID, NAME, DESC, LOWER_BOUND) \
+ EXPECT_EQ(getSourceLanguageName(xstr(DW_LNAME_##NAME)), DW_LNAME_##NAME);
+#include "llvm/BinaryFormat/Dwarf.def"
+}
+
+TEST(DwarfTest, lname_SourceLanguageNameString) {
+ // Some basics.
+ EXPECT_EQ(SourceLanguageNameString(DW_LNAME_C_plus_plus),
+ "DW_LNAME_C_plus_plus");
+ EXPECT_EQ(SourceLanguageNameString(DW_LNAME_CPP_for_OpenCL),
+ "DW_LNAME_CPP_for_OpenCL");
+
+ // Test invalid input.
+ EXPECT_EQ(SourceLanguageNameString(static_cast<SourceLanguageName>(0)), "");
+
+ // Test that we cover all DW_LNAME_ names.
+#define xstr(X) #X
+#define HANDLE_DW_LNAME(ID, NAME, DESC, LOWER_BOUND) \
+ EXPECT_EQ(SourceLanguageNameString(DW_LNAME_##NAME), xstr(DW_LNAME_##NAME));
+#include "llvm/BinaryFormat/Dwarf.def"
+}
} // end namespace
|
…ersion Makes sure we dump the attributes in a user-friendly way.
Michael137
force-pushed
the
llvm/dwarf-language-attrs-2-part-3
branch
from
754ef1f to
e03b759
Compare
adrian-prantl
approved these changes
Oct 9, 2025
| # CHECK: DW_AT_language_version DW_FORM_data4 | ||
| # CHECK: DW_AT_language_version DW_FORM_data2 | ||
| # CHECK: .debug_info contents: | ||
| # CHECK: DW_AT_language_version [DW_FORM_data4] (201402) |
There was a problem hiding this comment.
Should dwarfdump also translate this into the human-readable version?
i.e.:
dwarfdump: DW_AT_language_version (C++17)
dwarfdump -v: DW_AT_language_version (201402)
There was a problem hiding this comment.
That would be a neat addition. We'd have to detect the fact that there is a DW_AT_language_name present (I don't think the standard mandates that both attributes be present). Although it would be weird to have a version without a name. Might be worth asking the committee to clarify.
Either way, I'll do it as a follow-up. For now I wanted to just get the minimal dwarfdump support for testing these attributes
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/162/builds/32928 Here is the relevant piece of the build log for the reference |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/169/builds/15824 Here is the relevant piece of the build log for the reference |
Michael137
added a commit
that referenced
this pull request
Oct 10, 2025
llvm-sync bot
pushed a commit
to arm/arm-toolchain
that referenced
this pull request
Oct 10, 2025
…name (#162621) Depends on: * llvm/llvm-project#162445 * llvm/llvm-project#162449 Emit `DW_AT_language_name` (new in DWARFv6) if `DICompileUnit` has a `sourceLanguageName` field. Emit a `DW_AT_language` otherwise.
DharuniRAcharya
pushed a commit
to DharuniRAcharya/llvm-project
that referenced
this pull request
Oct 13, 2025
…ersion (llvm#162449) Depends on: * llvm#162434 * llvm#162446 Makes sure we dump the attributes in a user-friendly way. More info on the attributes here: https://dwarfstd.org/languages-v6.html
DharuniRAcharya
pushed a commit
to DharuniRAcharya/llvm-project
that referenced
this pull request
Oct 13, 2025
…162621) Depends on: * llvm#162445 * llvm#162449 Emit `DW_AT_language_name` (new in DWARFv6) if `DICompileUnit` has a `sourceLanguageName` field. Emit a `DW_AT_language` otherwise.
akadutta
pushed a commit
to akadutta/llvm-project
that referenced
this pull request
Oct 14, 2025
…ersion (llvm#162449) Depends on: * llvm#162434 * llvm#162446 Makes sure we dump the attributes in a user-friendly way. More info on the attributes here: https://dwarfstd.org/languages-v6.html
akadutta
pushed a commit
to akadutta/llvm-project
that referenced
this pull request
Oct 14, 2025
…162621) Depends on: * llvm#162445 * llvm#162449 Emit `DW_AT_language_name` (new in DWARFv6) if `DICompileUnit` has a `sourceLanguageName` field. Emit a `DW_AT_language` otherwise.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Depends on:
Makes sure we dump the attributes in a user-friendly way.
More info on the attributes here: https://dwarfstd.org/languages-v6.html