[llvm-debuginfo-analyzer] Add support for parsing DWARF / CodeView SourceLanguage #137223
+133
−22
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: Javier Lopez-Gomez (jalopezg-git) ChangesThis pull request adds support for parsing the source language in both DWARF and CodeView. Specifically,
FYI, @CarlosAlbertoEnciso. I believe this patch is ready too; feel free to start reviewing it. Full diff: https://github.com/llvm/llvm-project/pull/137223.diff 8 Files Affected:
diff --git a/llvm/include/llvm/DebugInfo/LogicalView/Core/LVElement.h b/llvm/include/llvm/DebugInfo/LogicalView/Core/LVElement.h
index 17fa04040ad77..22c24d0c0592c 100644
--- a/llvm/include/llvm/DebugInfo/LogicalView/Core/LVElement.h
+++ b/llvm/include/llvm/DebugInfo/LogicalView/Core/LVElement.h
@@ -14,10 +14,13 @@
#ifndef LLVM_DEBUGINFO_LOGICALVIEW_CORE_LVELEMENT_H
#define LLVM_DEBUGINFO_LOGICALVIEW_CORE_LVELEMENT_H
+#include "llvm/BinaryFormat/Dwarf.h"
+#include "llvm/DebugInfo/CodeView/CodeView.h"
#include "llvm/DebugInfo/LogicalView/Core/LVObject.h"
#include "llvm/Support/Casting.h"
#include <map>
#include <set>
+#include <variant>
#include <vector>
namespace llvm {
@@ -64,6 +67,22 @@ using LVElementKindSet = std::set<LVElementKind>;
using LVElementDispatch = std::map<LVElementKind, LVElementGetFunction>;
using LVElementRequest = std::vector<LVElementGetFunction>;
+/// A source language supported by any of the debug info representations.
+struct LVSourceLanguage {
+ LVSourceLanguage() = default;
+ LVSourceLanguage(llvm::dwarf::SourceLanguage SL) : Language(SL) {}
+ LVSourceLanguage(llvm::codeview::SourceLanguage SL) : Language(SL) {}
+
+ bool isValid() const { return Language.index() != 0; }
+ template <typename T> T getAs() { return std::get<T>(Language); }
+ StringRef getName() const;
+
+private:
+ std::variant<std::monostate, llvm::dwarf::SourceLanguage,
+ llvm::codeview::SourceLanguage>
+ Language;
+};
+
class LVElement : public LVObject {
enum class Property {
IsLine, // A logical line.
@@ -214,6 +233,9 @@ class LVElement : public LVObject {
virtual StringRef getProducer() const { return StringRef(); }
virtual void setProducer(StringRef ProducerName) {}
+ virtual LVSourceLanguage getSourceLanguage() const { return {}; }
+ virtual void setSourceLanguage(LVSourceLanguage SL) {}
+
virtual bool isCompileUnit() const { return false; }
virtual bool isRoot() const { return false; }
diff --git a/llvm/include/llvm/DebugInfo/LogicalView/Core/LVScope.h b/llvm/include/llvm/DebugInfo/LogicalView/Core/LVScope.h
index 1b3c377cd7dbb..378f249029730 100644
--- a/llvm/include/llvm/DebugInfo/LogicalView/Core/LVScope.h
+++ b/llvm/include/llvm/DebugInfo/LogicalView/Core/LVScope.h
@@ -407,6 +407,9 @@ class LVScopeCompileUnit final : public LVScope {
// Toolchain producer.
size_t ProducerIndex = 0;
+ // Source language.
+ LVSourceLanguage SourceLanguage{};
+
// Compilation directory name.
size_t CompilationDirectoryIndex = 0;
@@ -540,6 +543,9 @@ class LVScopeCompileUnit final : public LVScope {
ProducerIndex = getStringPool().getIndex(ProducerName);
}
+ LVSourceLanguage getSourceLanguage() const override { return SourceLanguage; }
+ void setSourceLanguage(LVSourceLanguage SL) override { SourceLanguage = SL; }
+
void setCPUType(codeview::CPUType Type) { CompilationCPUType = Type; }
codeview::CPUType getCPUType() { return CompilationCPUType; }
diff --git a/llvm/lib/DebugInfo/LogicalView/Core/LVElement.cpp b/llvm/lib/DebugInfo/LogicalView/Core/LVElement.cpp
index c6fb405baed1d..47aca07b7327e 100644
--- a/llvm/lib/DebugInfo/LogicalView/Core/LVElement.cpp
+++ b/llvm/lib/DebugInfo/LogicalView/Core/LVElement.cpp
@@ -11,6 +11,7 @@
//===----------------------------------------------------------------------===//
#include "llvm/DebugInfo/LogicalView/Core/LVElement.h"
+#include "llvm/DebugInfo/CodeView/EnumTables.h"
#include "llvm/DebugInfo/LogicalView/Core/LVReader.h"
#include "llvm/DebugInfo/LogicalView/Core/LVScope.h"
#include "llvm/DebugInfo/LogicalView/Core/LVType.h"
@@ -19,6 +20,21 @@ using namespace llvm;
using namespace llvm::codeview;
using namespace llvm::logicalview;
+StringRef LVSourceLanguage::getName() const {
+ if (!isValid())
+ return {};
+ switch (Language.index()) {
+ case 1: // DWARF
+ return llvm::dwarf::LanguageString(
+ std::get<llvm::dwarf::SourceLanguage>(Language));
+ case 2: // CodeView
+ static auto LangNames = llvm::codeview::getSourceLanguageNames();
+ return LangNames[std::get<llvm::codeview::SourceLanguage>(Language)].Name;
+ default:
+ llvm_unreachable("Unsupported language");
+ }
+}
+
#define DEBUG_TYPE "Element"
LVElementDispatch LVElement::Dispatch = {
diff --git a/llvm/lib/DebugInfo/LogicalView/Core/LVScope.cpp b/llvm/lib/DebugInfo/LogicalView/Core/LVScope.cpp
index 8bbaf93db0caa..ae585567c9de9 100644
--- a/llvm/lib/DebugInfo/LogicalView/Core/LVScope.cpp
+++ b/llvm/lib/DebugInfo/LogicalView/Core/LVScope.cpp
@@ -1707,11 +1707,17 @@ void LVScopeCompileUnit::print(raw_ostream &OS, bool Full) const {
void LVScopeCompileUnit::printExtra(raw_ostream &OS, bool Full) const {
OS << formattedKind(kind()) << " '" << getName() << "'\n";
- if (options().getPrintFormatting() && options().getAttributeProducer())
+ if (options().getPrintFormatting() && options().getAttributeProducer()) {
printAttributes(OS, Full, "{Producer} ",
const_cast<LVScopeCompileUnit *>(this), getProducer(),
/*UseQuotes=*/true,
/*PrintRef=*/false);
+ if (auto SL = getSourceLanguage(); SL.isValid())
+ printAttributes(OS, Full, "{Language} ",
+ const_cast<LVScopeCompileUnit *>(this), SL.getName(),
+ /*UseQuotes=*/true,
+ /*PrintRef=*/false);
+ }
// Reset file index, to allow its children to print the correct filename.
options().resetFilenameIndex();
diff --git a/llvm/lib/DebugInfo/LogicalView/Readers/LVCodeViewVisitor.cpp b/llvm/lib/DebugInfo/LogicalView/Readers/LVCodeViewVisitor.cpp
index 97214948d014a..3359cb8751923 100644
--- a/llvm/lib/DebugInfo/LogicalView/Readers/LVCodeViewVisitor.cpp
+++ b/llvm/lib/DebugInfo/LogicalView/Readers/LVCodeViewVisitor.cpp
@@ -947,8 +947,11 @@ Error LVSymbolVisitor::visitKnownRecord(CVSymbol &Record,
// The name of the CU, was extracted from the 'BuildInfo' subsection.
Reader->setCompileUnitCPUType(Compile2.Machine);
Scope->setName(CurrentObjectName);
- if (options().getAttributeProducer())
+ if (options().getAttributeProducer()) {
Scope->setProducer(Compile2.Version);
+ Scope->setSourceLanguage(LVSourceLanguage{
+ static_cast<llvm::codeview::SourceLanguage>(Compile2.getLanguage())});
+ }
getReader().isSystemEntry(Scope, CurrentObjectName);
// The line records in CodeView are recorded per Module ID. Update
@@ -992,8 +995,11 @@ Error LVSymbolVisitor::visitKnownRecord(CVSymbol &Record,
// The name of the CU, was extracted from the 'BuildInfo' subsection.
Reader->setCompileUnitCPUType(Compile3.Machine);
Scope->setName(CurrentObjectName);
- if (options().getAttributeProducer())
+ if (options().getAttributeProducer()) {
Scope->setProducer(Compile3.Version);
+ Scope->setSourceLanguage(LVSourceLanguage{
+ static_cast<llvm::codeview::SourceLanguage>(Compile3.getLanguage())});
+ }
getReader().isSystemEntry(Scope, CurrentObjectName);
// The line records in CodeView are recorded per Module ID. Update
diff --git a/llvm/lib/DebugInfo/LogicalView/Readers/LVDWARFReader.cpp b/llvm/lib/DebugInfo/LogicalView/Readers/LVDWARFReader.cpp
index 42da957233667..e5bdd1ba614d6 100644
--- a/llvm/lib/DebugInfo/LogicalView/Readers/LVDWARFReader.cpp
+++ b/llvm/lib/DebugInfo/LogicalView/Readers/LVDWARFReader.cpp
@@ -383,6 +383,11 @@ void LVDWARFReader::processOneAttribute(const DWARFDie &Die,
if (options().getAttributeProducer())
CurrentElement->setProducer(dwarf::toStringRef(FormValue));
break;
+ case dwarf::DW_AT_language:
+ if (options().getAttributeProducer())
+ CurrentElement->setSourceLanguage(LVSourceLanguage{
+ static_cast<llvm::dwarf::SourceLanguage>(GetAsUnsignedConstant())});
+ break;
case dwarf::DW_AT_upper_bound:
CurrentElement->setUpperBound(GetBoundValue(FormValue));
break;
diff --git a/llvm/unittests/DebugInfo/LogicalView/CodeViewReaderTest.cpp b/llvm/unittests/DebugInfo/LogicalView/CodeViewReaderTest.cpp
index c93a79094dce9..c6bdda782a17f 100644
--- a/llvm/unittests/DebugInfo/LogicalView/CodeViewReaderTest.cpp
+++ b/llvm/unittests/DebugInfo/LogicalView/CodeViewReaderTest.cpp
@@ -78,6 +78,11 @@ void checkElementPropertiesClangCodeview(LVReader *Reader) {
EXPECT_EQ(CompileUnit->getBaseAddress(), 0u);
EXPECT_TRUE(CompileUnit->getProducer().starts_with("clang"));
EXPECT_EQ(CompileUnit->getName(), "test.cpp");
+ LVSourceLanguage Language = CompileUnit->getSourceLanguage();
+ EXPECT_TRUE(Language.isValid());
+ ASSERT_EQ(Language.getAs<llvm::codeview::SourceLanguage>(),
+ llvm::codeview::SourceLanguage::Cpp);
+ ASSERT_EQ(Language.getName(), "Cpp");
EXPECT_EQ(Function->lineCount(), 16u);
EXPECT_EQ(Function->scopeCount(), 1u);
diff --git a/llvm/unittests/DebugInfo/LogicalView/DWARFReaderTest.cpp b/llvm/unittests/DebugInfo/LogicalView/DWARFReaderTest.cpp
index c062c15481da9..72d4bc1c7b7e5 100644
--- a/llvm/unittests/DebugInfo/LogicalView/DWARFReaderTest.cpp
+++ b/llvm/unittests/DebugInfo/LogicalView/DWARFReaderTest.cpp
@@ -72,6 +72,11 @@ void checkElementProperties(LVReader *Reader) {
EXPECT_EQ(CompileUnit->getBaseAddress(), 0u);
EXPECT_TRUE(CompileUnit->getProducer().starts_with("clang"));
EXPECT_EQ(CompileUnit->getName(), "test.cpp");
+ LVSourceLanguage Language = CompileUnit->getSourceLanguage();
+ EXPECT_TRUE(Language.isValid());
+ EXPECT_EQ(Language.getAs<llvm::dwarf::SourceLanguage>(),
+ llvm::dwarf::DW_LANG_C_plus_plus_14);
+ EXPECT_EQ(Language.getName(), "DW_LANG_C_plus_plus_14");
EXPECT_EQ(CompileUnit->lineCount(), 0u);
EXPECT_EQ(CompileUnit->scopeCount(), 1u);
|
jalopezg-git
force-pushed
the
jalopezg-logicalview-sourcelanguage
branch
from
af226a0 to
e75238a
Compare
jalopezg-git
force-pushed
the
jalopezg-logicalview-sourcelanguage
branch
3 times, most recently
from
5dfcb95 to
2e59c39
Compare
|
@jalopezg-git Thanks for doing this. What I would suggest is to include the command line option may be |
| llvm::codeview::SourceLanguage> | ||
| Language; | ||
| }; | ||
|
|
There was a problem hiding this comment.
May be explore the use of StringPool to store the Language string.
Basically, the setSourceLanguage function to use the logic from StringRef LVSourceLanguage::getName() to get the string and store it in the StringPool. And to get back the string in 'getSourceLanguage' query the StringPool.
There was a problem hiding this comment.
That sounds promising, and a bit simpler, given the existing infrastructure.
However, in the current state of this PR, we could write a switch statement on the returned value of getSourceLanguage.getAs<...>(); this particular use case would become a bit harder to support if using strings as the underlying representation.
Initially, I thought this could be supported by exposing the LanguageIndex data member (suggested below), but this is not reliable, as it depends on the interning order.
We could still go for StringPool + LanguageIndex at the cost of having to do string comparisons somewhere else (I would prefer to avoid this).
There was a problem hiding this comment.
I thought about this a bit and came to the conclusion that we could, either
- (1) Leave as-is, using
std::variant<Ts...>, perhaps with some additional improvement. - (2) Make
LVSourceLanguageessentially anenumwhich contains enumerators for every language supported by any of the readers. We could use the most-significant bits to store the format that defines such language (e.g. DWARF, CodeView, etc.). This may be simple, as we can do something similar to
static constexpr unsigned LVTagDwarf = (0x01 << 16);
static constexpr unsigned LVTagCodeView = (0x02 << 16);
enum LVSourceLanguage : uint32_t {
/* DWARF */
#define HANDLE_DW_LANG(ID, NAME, LOWER_BOUND, VERSION, VENDOR) \
DW_LANG_##NAME = LVTagDwarf | ID,
#include "llvm/BinaryFormat/Dwarf.def"
/* Codeview */
...
};Then, the SourceLanguage becomes just a uint32_t. Essentially, this tries to represent the same as above, but without using std::variant<Ts...>, and possibly being more space-efficient.
- (3) Relying on
StringPool, as you suggested. Then, it may be a bit uncomfortable fordebuginfologicalviewlibrary users to do something conditionally on the source language of a compile unit.
There was a problem hiding this comment.
BTW, I tend to like (2) more, so if you also agree, I could switch to this option for the next revision.
| @@ -407,6 +407,9 @@ class LVScopeCompileUnit final : public LVScope { | |||
| // Toolchain producer. | |||
| size_t ProducerIndex = 0; | |||
|
|
|||
| // Source language. | |||
| LVSourceLanguage SourceLanguage{}; | |||
|
|
|||
There was a problem hiding this comment.
May be just: size_t LanguageIndex = 0;
| @@ -540,6 +543,9 @@ class LVScopeCompileUnit final : public LVScope { | |||
| ProducerIndex = getStringPool().getIndex(ProducerName); | |||
| } | |||
|
|
|||
| LVSourceLanguage getSourceLanguage() const override { return SourceLanguage; } | |||
| void setSourceLanguage(LVSourceLanguage SL) override { SourceLanguage = SL; } | |||
|
|
|||
There was a problem hiding this comment.
Get/Set the language string from/into the StringPool.
| llvm_unreachable("Unsupported language"); | ||
| } | ||
| } | ||
|
|
There was a problem hiding this comment.
This logic can be used to store the language string in the StringPool.
|
Thanks for the review, @CarlosAlbertoEnciso 👍! See my concern above about going for |
jalopezg-git
force-pushed
the
jalopezg-logicalview-sourcelanguage
branch
2 times, most recently
from
5e54a5c to
b669e4f
Compare
Done too 👍; only missing discussion on whether to transition to |
|
✅ With the latest revision this PR passed the C/C++ code formatter. |
jalopezg-git
force-pushed
the
jalopezg-logicalview-sourcelanguage
branch
2 times, most recently
from
5ab70b8 to
ecbb30e
Compare
jalopezg-git
force-pushed
the
jalopezg-logicalview-sourcelanguage
branch
from
ecbb30e to
975eb58
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This pull request adds support for parsing the source language in both DWARF and CodeView. Specifically,
The
LVSourceLanguageclass is introduced to represent any supported language by any of the debug info representations.Update
LVDWARFReader.cppandLVCodeViewVisitor.cppto parse the source language where it applies. Similar to producing compiler,getAttributeProducer()currently controls whether this information is being filled-in / printed.An additional option could be registered for this, but I deemed it unneeded (at least for now).
FYI, @CarlosAlbertoEnciso. I believe this patch is ready too; feel free to start reviewing it.