https://github.com/Michael137 updated https://github.com/llvm/llvm-project/pull/149827
>From b8f31ec8f556169a45370938cf28bd8582134a5c Mon Sep 17 00:00:00 2001 From: Michael Buch <michaelbuc...@gmail.com> Date: Sun, 3 Aug 2025 11:38:07 +0100 Subject: [PATCH 1/3] [clang][Attr] Remove 'literal label' form of AsmLabelAttr This was added purely for the needs of LLDB. However, starting with https://github.com/llvm/llvm-project/pull/151355 and https://github.com/llvm/llvm-project/pull/148877 we no longer create literal AsmLabels in LLDB either. So this is unused and we can get rid of it. In the near future LLDB will want to add special support for mangling `AsmLabel`s, and the "literal label" codepath in the mangler made this more cumbersome. (cherry picked from commit 342f0d5cd722ae7ec3f48f136472923ce38f9981) --- clang/include/clang/Basic/Attr.td | 17 ++++------------- clang/lib/AST/Mangle.cpp | 4 ++-- clang/lib/Sema/SemaDecl.cpp | 13 +++++-------- clang/unittests/AST/DeclTest.cpp | 9 +-------- .../TypeSystem/Clang/TypeSystemClang.cpp | 7 +++---- 5 files changed, 15 insertions(+), 35 deletions(-) diff --git a/clang/include/clang/Basic/Attr.td b/clang/include/clang/Basic/Attr.td index b3ff45b3e90a3..a0efb21218312 100644 --- a/clang/include/clang/Basic/Attr.td +++ b/clang/include/clang/Basic/Attr.td @@ -1059,22 +1059,13 @@ def AVRSignal : InheritableAttr, TargetSpecificAttr<TargetAVR> { def AsmLabel : InheritableAttr { let Spellings = [CustomKeyword<"asm">, CustomKeyword<"__asm__">]; let Args = [ - // Label specifies the mangled name for the decl. - StringArgument<"Label">, - - // IsLiteralLabel specifies whether the label is literal (i.e. suppresses - // the global C symbol prefix) or not. If not, the mangle-suppression prefix - // ('\01') is omitted from the decl name at the LLVM IR level. - // - // Non-literal labels are used by some external AST sources like LLDB. - BoolArgument<"IsLiteralLabel", /*optional=*/0, /*fake=*/1> - ]; + // Label specifies the mangled name for the decl. + StringArgument<"Label">, ]; let SemaHandler = 0; let Documentation = [AsmLabelDocs]; - let AdditionalMembers = -[{ + let AdditionalMembers = [{ bool isEquivalent(AsmLabelAttr *Other) const { - return getLabel() == Other->getLabel() && getIsLiteralLabel() == Other->getIsLiteralLabel(); + return getLabel() == Other->getLabel(); } }]; } diff --git a/clang/lib/AST/Mangle.cpp b/clang/lib/AST/Mangle.cpp index 9652fdbc4e125..0bfb51c11f0a5 100644 --- a/clang/lib/AST/Mangle.cpp +++ b/clang/lib/AST/Mangle.cpp @@ -161,9 +161,9 @@ void MangleContext::mangleName(GlobalDecl GD, raw_ostream &Out) { if (const AsmLabelAttr *ALA = D->getAttr<AsmLabelAttr>()) { // If we have an asm name, then we use it as the mangling. - // If the label isn't literal, or if this is an alias for an LLVM intrinsic, + // If the label is an alias for an LLVM intrinsic, // do not add a "\01" prefix. - if (!ALA->getIsLiteralLabel() || ALA->getLabel().starts_with("llvm.")) { + if (ALA->getLabel().starts_with("llvm.")) { Out << ALA->getLabel(); return; } diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp index e2ac648320c0f..885d04b9ab926 100644 --- a/clang/lib/Sema/SemaDecl.cpp +++ b/clang/lib/Sema/SemaDecl.cpp @@ -8113,9 +8113,7 @@ NamedDecl *Sema::ActOnVariableDeclarator( } } - NewVD->addAttr(AsmLabelAttr::Create(Context, Label, - /*IsLiteralLabel=*/true, - SE->getStrTokenLoc(0))); + NewVD->addAttr(AsmLabelAttr::Create(Context, Label, SE->getStrTokenLoc(0))); } else if (!ExtnameUndeclaredIdentifiers.empty()) { llvm::DenseMap<IdentifierInfo*,AsmLabelAttr*>::iterator I = ExtnameUndeclaredIdentifiers.find(NewVD->getIdentifier()); @@ -10345,9 +10343,8 @@ Sema::ActOnFunctionDeclarator(Scope *S, Declarator &D, DeclContext *DC, if (Expr *E = D.getAsmLabel()) { // The parser guarantees this is a string. StringLiteral *SE = cast<StringLiteral>(E); - NewFD->addAttr(AsmLabelAttr::Create(Context, SE->getString(), - /*IsLiteralLabel=*/true, - SE->getStrTokenLoc(0))); + NewFD->addAttr( + AsmLabelAttr::Create(Context, SE->getString(), SE->getStrTokenLoc(0))); } else if (!ExtnameUndeclaredIdentifiers.empty()) { llvm::DenseMap<IdentifierInfo*,AsmLabelAttr*>::iterator I = ExtnameUndeclaredIdentifiers.find(NewFD->getIdentifier()); @@ -20598,8 +20595,8 @@ void Sema::ActOnPragmaRedefineExtname(IdentifierInfo* Name, LookupOrdinaryName); AttributeCommonInfo Info(AliasName, SourceRange(AliasNameLoc), AttributeCommonInfo::Form::Pragma()); - AsmLabelAttr *Attr = AsmLabelAttr::CreateImplicit( - Context, AliasName->getName(), /*IsLiteralLabel=*/true, Info); + AsmLabelAttr *Attr = + AsmLabelAttr::CreateImplicit(Context, AliasName->getName(), Info); // If a declaration that: // 1) declares a function or a variable diff --git a/clang/unittests/AST/DeclTest.cpp b/clang/unittests/AST/DeclTest.cpp index ed635da683aab..afaf413493299 100644 --- a/clang/unittests/AST/DeclTest.cpp +++ b/clang/unittests/AST/DeclTest.cpp @@ -74,7 +74,6 @@ TEST(Decl, AsmLabelAttr) { StringRef Code = R"( struct S { void f() {} - void g() {} }; )"; auto AST = @@ -87,11 +86,8 @@ TEST(Decl, AsmLabelAttr) { const auto *DeclS = selectFirst<CXXRecordDecl>("d", match(cxxRecordDecl().bind("d"), Ctx)); NamedDecl *DeclF = *DeclS->method_begin(); - NamedDecl *DeclG = *(++DeclS->method_begin()); - // Attach asm labels to the decls: one literal, and one not. - DeclF->addAttr(AsmLabelAttr::Create(Ctx, "foo", /*LiteralLabel=*/true)); - DeclG->addAttr(AsmLabelAttr::Create(Ctx, "goo", /*LiteralLabel=*/false)); + DeclF->addAttr(AsmLabelAttr::Create(Ctx, "foo")); // Mangle the decl names. std::string MangleF, MangleG; @@ -99,14 +95,11 @@ TEST(Decl, AsmLabelAttr) { ItaniumMangleContext::create(Ctx, Diags)); { llvm::raw_string_ostream OS_F(MangleF); - llvm::raw_string_ostream OS_G(MangleG); MC->mangleName(DeclF, OS_F); - MC->mangleName(DeclG, OS_G); } ASSERT_EQ(MangleF, "\x01" "foo"); - ASSERT_EQ(MangleG, "goo"); } TEST(Decl, MangleDependentSizedArray) { diff --git a/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp b/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp index 8dd6aa08ba2aa..4af900a174e4f 100644 --- a/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp +++ b/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp @@ -2183,8 +2183,7 @@ FunctionDecl *TypeSystemClang::CreateFunctionDeclaration( // This is done separately for member functions in // AddMethodToCXXRecordType. if (!asm_label.empty()) - func_decl->addAttr(clang::AsmLabelAttr::CreateImplicit(ast, asm_label, - /*literal=*/true)); + func_decl->addAttr(clang::AsmLabelAttr::CreateImplicit(ast, asm_label)); SetOwningModule(func_decl, owning_module); decl_ctx->addDecl(func_decl); @@ -7823,8 +7822,8 @@ clang::CXXMethodDecl *TypeSystemClang::AddMethodToCXXRecordType( cxx_method_decl->addAttr(clang::UsedAttr::CreateImplicit(getASTContext())); if (!asm_label.empty()) - cxx_method_decl->addAttr(clang::AsmLabelAttr::CreateImplicit( - getASTContext(), asm_label, /*literal=*/true)); + cxx_method_decl->addAttr( + clang::AsmLabelAttr::CreateImplicit(getASTContext(), asm_label)); // Parameters on member function declarations in DWARF generally don't // have names, so we omit them when creating the ParmVarDecls. >From aac54f11b33455e6c5feca7da646b97edbb607d4 Mon Sep 17 00:00:00 2001 From: Michael Buch <michaelbuc...@gmail.com> Date: Mon, 4 Aug 2025 07:49:40 +0100 Subject: [PATCH 2/3] [ItaniumDemangle] Add getter for constructor/destructor variants This patch adds a way to retrieve the constructor/destructor variant from the Itanium demangle tree. This will be used by LLDB. --- libcxxabi/src/demangle/ItaniumDemangle.h | 2 ++ llvm/include/llvm/Demangle/Demangle.h | 3 +++ llvm/include/llvm/Demangle/ItaniumDemangle.h | 2 ++ llvm/lib/Demangle/ItaniumDemangle.cpp | 10 +++++++--- 4 files changed, 14 insertions(+), 3 deletions(-) diff --git a/libcxxabi/src/demangle/ItaniumDemangle.h b/libcxxabi/src/demangle/ItaniumDemangle.h index 6f27da7b9cadf..7b3983bc89367 100644 --- a/libcxxabi/src/demangle/ItaniumDemangle.h +++ b/libcxxabi/src/demangle/ItaniumDemangle.h @@ -1766,6 +1766,8 @@ class CtorDtorName final : public Node { template<typename Fn> void match(Fn F) const { F(Basename, IsDtor, Variant); } + int getVariant() const { return Variant; } + void printLeft(OutputBuffer &OB) const override { if (IsDtor) OB += "~"; diff --git a/llvm/include/llvm/Demangle/Demangle.h b/llvm/include/llvm/Demangle/Demangle.h index d9b08b2d856dc..6af8fad9ceb86 100644 --- a/llvm/include/llvm/Demangle/Demangle.h +++ b/llvm/include/llvm/Demangle/Demangle.h @@ -127,6 +127,9 @@ struct ItaniumPartialDemangler { /// If this symbol describes a constructor or destructor. DEMANGLE_ABI bool isCtorOrDtor() const; + /// If this symbol describes a constructor or destructor. + std::optional<int> getCtorOrDtorVariant() const; + /// If this symbol describes a function. DEMANGLE_ABI bool isFunction() const; diff --git a/llvm/include/llvm/Demangle/ItaniumDemangle.h b/llvm/include/llvm/Demangle/ItaniumDemangle.h index 62d427c3966bb..c0db02f8e7fef 100644 --- a/llvm/include/llvm/Demangle/ItaniumDemangle.h +++ b/llvm/include/llvm/Demangle/ItaniumDemangle.h @@ -1766,6 +1766,8 @@ class CtorDtorName final : public Node { template<typename Fn> void match(Fn F) const { F(Basename, IsDtor, Variant); } + int getVariant() const { return Variant; } + void printLeft(OutputBuffer &OB) const override { if (IsDtor) OB += "~"; diff --git a/llvm/lib/Demangle/ItaniumDemangle.cpp b/llvm/lib/Demangle/ItaniumDemangle.cpp index 1009cc91ca12a..a5d7a5576fccf 100644 --- a/llvm/lib/Demangle/ItaniumDemangle.cpp +++ b/llvm/lib/Demangle/ItaniumDemangle.cpp @@ -560,13 +560,17 @@ bool ItaniumPartialDemangler::hasFunctionQualifiers() const { } bool ItaniumPartialDemangler::isCtorOrDtor() const { + return getCtorOrDtorVariant().has_value(); +} + +std::optional<int> ItaniumPartialDemangler::getCtorOrDtorVariant() const { const Node *N = static_cast<const Node *>(RootNode); while (N) { switch (N->getKind()) { default: - return false; + return std::nullopt; case Node::KCtorDtorName: - return true; + return static_cast<const CtorDtorName *>(N)->getVariant(); case Node::KAbiTagAttr: N = static_cast<const AbiTagAttr *>(N)->Base; @@ -588,7 +592,7 @@ bool ItaniumPartialDemangler::isCtorOrDtor() const { break; } } - return false; + return std::nullopt; } bool ItaniumPartialDemangler::isFunction() const { >From 82075a2da654dde182b29c1d71469a4cc5c3029d Mon Sep 17 00:00:00 2001 From: Michael Buch <michaelbuc...@gmail.com> Date: Mon, 4 Aug 2025 07:49:47 +0100 Subject: [PATCH 3/3] [lldb][Expression] Encode structor variant into FunctionCallLabel This patch is an implementation of [this discussion](https://discourse.llvm.org/t/rfc-lldb-handling-abi-tagged-constructors-destructors-in-expression-evaluator/82816/7) about handling ABI-tagged structors during expression evaluation. **Motivation** LLDB encodes the mangled name of a `DW_TAG_subprogram` into `AsmLabel`s on function and method Clang AST nodes. This means that when calls to these functions get lowered into IR (when running JITted expressions), the address resolver can locate the appropriate symbol by mangled name (and it's guaranteed to find the symbol because we got the mangled name from debug-info, instead of letting Clang mangle it based on AST structure). However, we don't do this for `CXXConstructorDecl`s/`CXXDestructorDecl`s because these structor declarations in DWARF don't have a linkage name. This is because there can be multiple variants of a structor, each with a distinct mangling in the Itanium ABI. Each structor variant has its own definition `DW_TAG_subprogram`. So LLDB doesn't know which mangled name to put into the `AsmLabel`. Currently this means using an ABI-tagged constructor in LLDB expressions won't work (see [this RFC](https://discourse.llvm.org/t/rfc-lldb-handling-abi-tagged-constructors-destructors-in-expression-evaluator/82816) for concrete examples). **Proposed Solution** The `FunctionCallLabel` encoding that we put into `AsmLabel`s already supports stuffing more info about a DIE into it. So this patch extends the `FunctionCallLabel` to contain an optional discriminator (a sequence of bytes) which the `SymbolFileDWARF` plugin interprets as the constructor/destructor variant of that DIE. There's a few subtleties here: 1. At the point at which LLDB first constructs the label, it has no way of knowing (just by looking the debug-info declaration), which structor variant the expression evaluator is supposed to call. That's something that gets decided when compiling the expression. So we let the Clang mangler inject the correct structor variant into the `AsmLabel` during JITing. I adjusted the `AsmLabelAttr` mangling for this. An option would've been to create a new Clang attribute which behaved like an `AsmLabel` but with these special semantics for LLDB. My main concern there is that we'd have to adjust all the `AsmLabelAttr` checks around Clang to also now account for this new attribute. 2. The compiler is free to omit the `C1` variant of a constructor if the `C2` variant is sufficient. In that case it may alias `C1` to `C2`, leaving us with only the `C2` `DW_TAG_subprogram` in the object file. Linux is one of the platforms where this occurs. For those cases there's heuristic in `SymbolFileDWARF` where we pick `C2` if we asked for `C1` but it doesn't exist. This may not always be correct (if for some reason the compiler decided to drop `C1` for other reasons). --- clang/lib/AST/Mangle.cpp | 20 ++- lldb/include/lldb/Expression/Expression.h | 8 +- lldb/source/Expression/Expression.cpp | 29 ++-- .../SymbolFile/DWARF/DWARFASTParserClang.cpp | 47 +++++- .../SymbolFile/DWARF/SymbolFileDWARF.cpp | 149 +++++++++++++++--- .../SymbolFile/DWARF/SymbolFileDWARF.h | 4 + lldb/unittests/Expression/ExpressionTest.cpp | 37 +++-- lldb/unittests/Symbol/TestTypeSystemClang.cpp | 14 +- 8 files changed, 251 insertions(+), 57 deletions(-) diff --git a/clang/lib/AST/Mangle.cpp b/clang/lib/AST/Mangle.cpp index 0bfb51c11f0a5..58029476572c5 100644 --- a/clang/lib/AST/Mangle.cpp +++ b/clang/lib/AST/Mangle.cpp @@ -152,6 +152,20 @@ bool MangleContext::shouldMangleDeclName(const NamedDecl *D) { return shouldMangleCXXName(D); } +static llvm::StringRef g_lldb_func_call_label_prefix = "$__lldb_func"; + +static void emitLLDBAsmLabel(llvm::StringRef label, GlobalDecl GD, + llvm::raw_ostream &Out) { + Out << g_lldb_func_call_label_prefix << ":"; + + if (llvm::isa<clang::CXXConstructorDecl>(GD.getDecl())) + Out << "C" << GD.getCtorType(); + else if (llvm::isa<clang::CXXDestructorDecl>(GD.getDecl())) + Out << "D" << GD.getDtorType(); + + Out << label.substr(g_lldb_func_call_label_prefix.size() + 1); +} + void MangleContext::mangleName(GlobalDecl GD, raw_ostream &Out) { const ASTContext &ASTContext = getASTContext(); const NamedDecl *D = cast<NamedDecl>(GD.getDecl()); @@ -185,7 +199,11 @@ void MangleContext::mangleName(GlobalDecl GD, raw_ostream &Out) { if (!UserLabelPrefix.empty()) Out << '\01'; // LLVM IR Marker for __asm("foo") - Out << ALA->getLabel(); + if (ALA->getLabel().starts_with(g_lldb_func_call_label_prefix)) + emitLLDBAsmLabel(ALA->getLabel(), GD, Out); + else + Out << ALA->getLabel(); + return; } diff --git a/lldb/include/lldb/Expression/Expression.h b/lldb/include/lldb/Expression/Expression.h index 20067f469895b..847226167d584 100644 --- a/lldb/include/lldb/Expression/Expression.h +++ b/lldb/include/lldb/Expression/Expression.h @@ -103,11 +103,15 @@ class Expression { /// /// The format being: /// -/// <prefix>:<module uid>:<symbol uid>:<name> +/// <prefix>:<discriminator>:<module uid>:<symbol uid>:<name> /// /// The label string needs to stay valid for the entire lifetime /// of this object. struct FunctionCallLabel { + /// Arbitrary string which language plugins can interpret for their + /// own needs. + llvm::StringRef discriminator; + /// Unique identifier of the lldb_private::Module /// which contains the symbol identified by \c symbol_id. lldb::user_id_t module_id; @@ -133,7 +137,7 @@ struct FunctionCallLabel { /// /// The representation roundtrips through \c fromString: /// \code{.cpp} - /// llvm::StringRef encoded = "$__lldb_func:0x0:0x0:_Z3foov"; + /// llvm::StringRef encoded = "$__lldb_func:blah:0x0:0x0:_Z3foov"; /// FunctionCallLabel label = *fromString(label); /// /// assert (label.toString() == encoded); diff --git a/lldb/source/Expression/Expression.cpp b/lldb/source/Expression/Expression.cpp index 796851ff15ca3..16ecb1d7deef8 100644 --- a/lldb/source/Expression/Expression.cpp +++ b/lldb/source/Expression/Expression.cpp @@ -34,10 +34,10 @@ Expression::Expression(ExecutionContextScope &exe_scope) llvm::Expected<FunctionCallLabel> lldb_private::FunctionCallLabel::fromString(llvm::StringRef label) { - llvm::SmallVector<llvm::StringRef, 4> components; - label.split(components, ":", /*MaxSplit=*/3); + llvm::SmallVector<llvm::StringRef, 5> components; + label.split(components, ":", /*MaxSplit=*/4); - if (components.size() != 4) + if (components.size() != 5) return llvm::createStringError("malformed function call label."); if (components[0] != FunctionCallLabelPrefix) @@ -45,8 +45,10 @@ lldb_private::FunctionCallLabel::fromString(llvm::StringRef label) { "expected function call label prefix '{0}' but found '{1}' instead.", FunctionCallLabelPrefix, components[0])); - llvm::StringRef module_label = components[1]; - llvm::StringRef die_label = components[2]; + llvm::StringRef discriminator = components[1]; + llvm::StringRef module_label = components[2]; + llvm::StringRef die_label = components[3]; + llvm::StringRef lookup_name = components[4]; lldb::user_id_t module_id = 0; if (!llvm::to_integer(module_label, module_id)) @@ -58,20 +60,23 @@ lldb_private::FunctionCallLabel::fromString(llvm::StringRef label) { return llvm::createStringError( llvm::formatv("failed to parse symbol ID from '{0}'.", die_label)); - return FunctionCallLabel{/*.module_id=*/module_id, + return FunctionCallLabel{/*.discriminator=*/discriminator, + /*.module_id=*/module_id, /*.symbol_id=*/die_id, - /*.lookup_name=*/components[3]}; + /*.lookup_name=*/lookup_name}; } std::string lldb_private::FunctionCallLabel::toString() const { - return llvm::formatv("{0}:{1:x}:{2:x}:{3}", FunctionCallLabelPrefix, - module_id, symbol_id, lookup_name) + return llvm::formatv("{0}:{1}:{2:x}:{3:x}:{4}", FunctionCallLabelPrefix, + discriminator, module_id, symbol_id, lookup_name) .str(); } void llvm::format_provider<FunctionCallLabel>::format( const FunctionCallLabel &label, raw_ostream &OS, StringRef Style) { - OS << llvm::formatv("FunctionCallLabel{ module_id: {0:x}, symbol_id: {1:x}, " - "lookup_name: {2} }", - label.module_id, label.symbol_id, label.lookup_name); + OS << llvm::formatv("FunctionCallLabel{ discriminator: {0}, module_id: " + "{1:x}, symbol_id: {2:x}, " + "lookup_name: {3} }", + label.discriminator, label.module_id, label.symbol_id, + label.lookup_name); } diff --git a/lldb/source/Plugins/SymbolFile/DWARF/DWARFASTParserClang.cpp b/lldb/source/Plugins/SymbolFile/DWARF/DWARFASTParserClang.cpp index 781c1c6c5745d..5c674308160e5 100644 --- a/lldb/source/Plugins/SymbolFile/DWARF/DWARFASTParserClang.cpp +++ b/lldb/source/Plugins/SymbolFile/DWARF/DWARFASTParserClang.cpp @@ -250,11 +250,52 @@ static unsigned GetCXXMethodCVQuals(const DWARFDIE &subprogram, return cv_quals; } +static const char *GetMangledOrStructorName(const DWARFDIE &die) { + const char *name = die.GetMangledName(/*substitute_name_allowed*/ false); + if (name) + return name; + + name = die.GetName(); + if (!name) + return nullptr; + + DWARFDIE parent = die.GetParent(); + if (!parent.IsStructUnionOrClass()) + return nullptr; + + const char *parent_name = parent.GetName(); + if (!parent_name) + return nullptr; + + // Constructor. + if (::strcmp(parent_name, name) == 0) + return name; + + // Destructor. + if (name[0] == '~' && ::strcmp(parent_name, name + 1)) + return name; + + return nullptr; +} + static std::string MakeLLDBFuncAsmLabel(const DWARFDIE &die) { - char const *name = die.GetMangledName(/*substitute_name_allowed*/ false); + char const *name = GetMangledOrStructorName(die); if (!name) return {}; + auto *cu = die.GetCU(); + if (!cu) + return {}; + + // FIXME: When resolving function call labels, we check that + // that the definition's DW_AT_specification points to the + // declaration that we encoded into the label here. But if the + // declaration came from a type-unit (and the definition from + // .debug_info), that check won't work. So for now, don't use + // function call labels for declaration DIEs from type-units. + if (cu->IsTypeUnit()) + return {}; + SymbolFileDWARF *dwarf = die.GetDWARF(); if (!dwarf) return {}; @@ -285,7 +326,9 @@ static std::string MakeLLDBFuncAsmLabel(const DWARFDIE &die) { if (die_id == LLDB_INVALID_UID) return {}; - return FunctionCallLabel{/*module_id=*/module_id, + // Note, discriminator is added by Clang during mangling. + return FunctionCallLabel{/*discriminator=*/{}, + /*module_id=*/module_id, /*symbol_id=*/die_id, /*.lookup_name=*/name} .toString(); diff --git a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp index 42a66ce75d6d6..911ce5930ca4c 100644 --- a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp +++ b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp @@ -7,7 +7,9 @@ //===----------------------------------------------------------------------===// #include "SymbolFileDWARF.h" +#include "clang/Basic/ABI.h" #include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" #include "llvm/DebugInfo/DWARF/DWARFAddressRange.h" #include "llvm/DebugInfo/DWARF/DWARFDebugLoc.h" #include "llvm/Support/Casting.h" @@ -78,6 +80,7 @@ #include "llvm/DebugInfo/DWARF/DWARFContext.h" #include "llvm/DebugInfo/DWARF/DWARFDebugAbbrev.h" +#include "llvm/Demangle/Demangle.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/FormatVariadic.h" @@ -2482,6 +2485,133 @@ bool SymbolFileDWARF::ResolveFunction(const DWARFDIE &orig_die, return false; } +static int ClangToItaniumCtorKind(clang::CXXCtorType kind) { + switch (kind) { + case clang::CXXCtorType::Ctor_Complete: + return 1; + case clang::CXXCtorType::Ctor_Base: + return 2; + case clang::CXXCtorType::Ctor_CopyingClosure: + case clang::CXXCtorType::Ctor_DefaultClosure: + case clang::CXXCtorType::Ctor_Comdat: + llvm_unreachable("Unexpected constructor kind."); + } +} + +static int ClangToItaniumDtorKind(clang::CXXDtorType kind) { + switch (kind) { + case clang::CXXDtorType::Dtor_Deleting: + return 0; + case clang::CXXDtorType::Dtor_Complete: + return 1; + case clang::CXXDtorType::Dtor_Base: + return 2; + case clang::CXXDtorType::Dtor_Comdat: + llvm_unreachable("Unexpected destructor kind."); + } +} + +static std::optional<int> +GetItaniumCtorDtorVariant(llvm::StringRef discriminator) { + const bool is_ctor = discriminator.consume_front("C"); + if (!is_ctor && !discriminator.consume_front("D")) + return std::nullopt; + + uint64_t structor_kind; + if (!llvm::to_integer(discriminator, structor_kind)) + return std::nullopt; + + if (is_ctor) { + if (structor_kind > clang::CXXCtorType::Ctor_DefaultClosure) + return std::nullopt; + + return ClangToItaniumCtorKind( + static_cast<clang::CXXCtorType>(structor_kind)); + } + + if (structor_kind > clang::CXXDtorType::Dtor_Deleting) + return std::nullopt; + + return ClangToItaniumDtorKind(static_cast<clang::CXXDtorType>(structor_kind)); +} + +DWARFDIE SymbolFileDWARF::FindFunctionDefinition(const FunctionCallLabel &label, + const DWARFDIE &declaration) { + DWARFDIE definition; + llvm::DenseMap<int, DWARFDIE> structor_variant_to_die; + + // eFunctionNameTypeFull for mangled name lookup. + // eFunctionNameTypeMethod is required for structor lookups (since we look + // those up by DW_AT_name). + Module::LookupInfo info(ConstString(label.lookup_name), + lldb::eFunctionNameTypeFull | + lldb::eFunctionNameTypeMethod, + lldb::eLanguageTypeUnknown); + + m_index->GetFunctions(info, *this, {}, [&](DWARFDIE entry) { + if (entry.GetAttributeValueAsUnsigned(llvm::dwarf::DW_AT_declaration, 0)) + return IterationAction::Continue; + + auto spec = entry.GetAttributeValueAsReferenceDIE(DW_AT_specification); + if (!spec) + return IterationAction::Continue; + + if (spec != declaration) + return IterationAction::Continue; + + // We're not picking a specific structor variant DIE, so we're done here. + if (label.discriminator.empty()) { + definition = entry; + return IterationAction::Stop; + } + + const char *mangled = + entry.GetMangledName(/*substitute_name_allowed=*/false); + if (!mangled) + return IterationAction::Continue; + + llvm::ItaniumPartialDemangler D; + if (D.partialDemangle(mangled)) + return IterationAction::Continue; + + auto structor_variant = D.getCtorOrDtorVariant(); + if (!structor_variant) + return IterationAction::Continue; + + auto [_, inserted] = structor_variant_to_die.try_emplace(*structor_variant, + std::move(entry)); + assert(inserted); + + // The compiler may choose to alias the constructor variants + // (notably this happens on Linux), so we might not have a definition + // DIE for some structor variants. Hence we iterate over all variants + // and pick the most appropriate one out of those. + return IterationAction::Continue; + }); + + if (definition) + return definition; + + auto label_variant = GetItaniumCtorDtorVariant(label.discriminator); + if (!label_variant) + return {}; + + auto it = structor_variant_to_die.find(*label_variant); + + // Found the exact variant. + if (it != structor_variant_to_die.end()) + return it->getSecond(); + + // C1 was aliased to C2 + if (!label.lookup_name.starts_with("~") && label_variant == 1) { + if (auto it = structor_variant_to_die.find(2); + it != structor_variant_to_die.end()) + return it->getSecond(); + } + + return {}; +} + llvm::Expected<SymbolContext> SymbolFileDWARF::ResolveFunctionCallLabel(const FunctionCallLabel &label) { std::lock_guard<std::recursive_mutex> guard(GetModuleMutex()); @@ -2494,24 +2624,7 @@ SymbolFileDWARF::ResolveFunctionCallLabel(const FunctionCallLabel &label) { // Label was created using a declaration DIE. Need to fetch the definition // to resolve the function call. if (die.GetAttributeValueAsUnsigned(llvm::dwarf::DW_AT_declaration, 0)) { - Module::LookupInfo info(ConstString(label.lookup_name), - lldb::eFunctionNameTypeFull, - lldb::eLanguageTypeUnknown); - - m_index->GetFunctions(info, *this, {}, [&](DWARFDIE entry) { - if (entry.GetAttributeValueAsUnsigned(llvm::dwarf::DW_AT_declaration, 0)) - return IterationAction::Continue; - - // We don't check whether the specification DIE for this function - // corresponds to the declaration DIE because the declaration might be in - // a type-unit but the definition in the compile-unit (and it's - // specifcation would point to the declaration in the compile-unit). We - // rely on the mangled name within the module to be enough to find us the - // unique definition. - die = entry; - return IterationAction::Stop; - }); - + die = FindFunctionDefinition(label, die); if (die.GetAttributeValueAsUnsigned(llvm::dwarf::DW_AT_declaration, 0)) return llvm::createStringError( llvm::formatv("failed to find definition DIE for {0}", label)); diff --git a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.h b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.h index 3ec538da8cf77..843346619db37 100644 --- a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.h +++ b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.h @@ -372,6 +372,10 @@ class SymbolFileDWARF : public SymbolFileCommon { /// Returns the DWARFIndex for this symbol, if it exists. DWARFIndex *getIndex() { return m_index.get(); } +private: + DWARFDIE FindFunctionDefinition(const FunctionCallLabel &label, + const DWARFDIE &declaration); + protected: SymbolFileDWARF(const SymbolFileDWARF &) = delete; const SymbolFileDWARF &operator=(const SymbolFileDWARF &) = delete; diff --git a/lldb/unittests/Expression/ExpressionTest.cpp b/lldb/unittests/Expression/ExpressionTest.cpp index 12f6dd515fd11..ceb567c28ab99 100644 --- a/lldb/unittests/Expression/ExpressionTest.cpp +++ b/lldb/unittests/Expression/ExpressionTest.cpp @@ -23,15 +23,15 @@ struct LabelTestCase { static LabelTestCase g_label_test_cases[] = { // Failure modes - {"bar:0x0:0x0:_Z3foov", + {"bar:blah:0x0:0x0:_Z3foov", {}, {"expected function call label prefix '$__lldb_func' but found 'bar' " "instead."}}, - {"$__lldb_func :0x0:0x0:_Z3foov", + {"$__lldb_func :blah:0x0:0x0:_Z3foov", {}, {"expected function call label prefix '$__lldb_func' but found " "'$__lldb_func ' instead."}}, - {"$__lldb_funcc:0x0:0x0:_Z3foov", + {"$__lldb_funcc:blah:0x0:0x0:_Z3foov", {}, {"expected function call label prefix '$__lldb_func' but found " "'$__lldb_funcc' instead."}}, @@ -39,47 +39,52 @@ static LabelTestCase g_label_test_cases[] = { {"foo", {}, {"malformed function call label."}}, {"$__lldb_func", {}, {"malformed function call label."}}, {"$__lldb_func:", {}, {"malformed function call label."}}, - {"$__lldb_func:0x0:0x0", {}, {"malformed function call label."}}, - {"$__lldb_func:abc:0x0:_Z3foov", + {"$__lldb_func:blah", {}, {"malformed function call label."}}, + {"$__lldb_func:blah:0x0", {}, {"malformed function call label."}}, + {"$__lldb_func:111:0x0:0x0", {}, {"malformed function call label."}}, + {"$__lldb_func:111:abc:0x0:_Z3foov", {}, {"failed to parse module ID from 'abc'."}}, - {"$__lldb_func:-1:0x0:_Z3foov", + {"$__lldb_func:111:-1:0x0:_Z3foov", {}, {"failed to parse module ID from '-1'."}}, - {"$__lldb_func:0x0invalid:0x0:_Z3foov", + {"$__lldb_func:111:0x0invalid:0x0:_Z3foov", {}, {"failed to parse module ID from '0x0invalid'."}}, - {"$__lldb_func:0x0 :0x0:_Z3foov", + {"$__lldb_func:111:0x0 :0x0:_Z3foov", {}, {"failed to parse module ID from '0x0 '."}}, - {"$__lldb_func:0x0:abc:_Z3foov", + {"$__lldb_func:blah:0x0:abc:_Z3foov", {}, {"failed to parse symbol ID from 'abc'."}}, - {"$__lldb_func:0x5:-1:_Z3foov", + {"$__lldb_func:blah:0x5:-1:_Z3foov", {}, {"failed to parse symbol ID from '-1'."}}, - {"$__lldb_func:0x5:0x0invalid:_Z3foov", + {"$__lldb_func:blah:0x5:0x0invalid:_Z3foov", {}, {"failed to parse symbol ID from '0x0invalid'."}}, - {"$__lldb_func:0x5:0x0 :_Z3foov", + {"$__lldb_func:blah:0x5:0x0 :_Z3foov", {}, {"failed to parse symbol ID from '0x0 '."}}, - {"$__lldb_func:0x0:0x0:_Z3foov", + {"$__lldb_func:blah:0x0:0x0:_Z3foov", { + /*.discriminator=*/"blah", /*.module_id=*/0x0, /*.symbol_id=*/0x0, /*.lookup_name=*/"_Z3foov", }, {}}, - {"$__lldb_func:0x0:0x0:abc:def:::a", + {"$__lldb_func::0x0:0x0:abc:def:::a", { + /*.discriminator=*/"", /*.module_id=*/0x0, /*.symbol_id=*/0x0, /*.lookup_name=*/"abc:def:::a", }, {}}, - {"$__lldb_func:0xd2:0xf0:$__lldb_func", + {"$__lldb_func:0x45:0xd2:0xf0:$__lldb_func", { + /*.discriminator=*/"0x45", /*.module_id=*/0xd2, /*.symbol_id=*/0xf0, /*.lookup_name=*/"$__lldb_func", @@ -106,6 +111,7 @@ TEST_P(ExpressionTestFixture, FunctionCallLabel) { EXPECT_EQ(decoded_or_err->toString(), encoded); EXPECT_EQ(label_str, encoded); + EXPECT_EQ(decoded_or_err->discriminator, label.discriminator); EXPECT_EQ(decoded_or_err->module_id, label.module_id); EXPECT_EQ(decoded_or_err->symbol_id, label.symbol_id); EXPECT_EQ(decoded_or_err->lookup_name, label.lookup_name); @@ -113,6 +119,7 @@ TEST_P(ExpressionTestFixture, FunctionCallLabel) { auto roundtrip_or_err = FunctionCallLabel::fromString(label_str); EXPECT_THAT_EXPECTED(roundtrip_or_err, llvm::Succeeded()); + EXPECT_EQ(roundtrip_or_err->discriminator, label.discriminator); EXPECT_EQ(roundtrip_or_err->module_id, label.module_id); EXPECT_EQ(roundtrip_or_err->symbol_id, label.symbol_id); EXPECT_EQ(roundtrip_or_err->lookup_name, label.lookup_name); diff --git a/lldb/unittests/Symbol/TestTypeSystemClang.cpp b/lldb/unittests/Symbol/TestTypeSystemClang.cpp index b993b82612497..f673cceae00dd 100644 --- a/lldb/unittests/Symbol/TestTypeSystemClang.cpp +++ b/lldb/unittests/Symbol/TestTypeSystemClang.cpp @@ -1150,12 +1150,12 @@ TEST_F(TestTypeSystemClang, AsmLabel_CtorDtor) { is_explicit, is_attr_used, is_artificial); auto *ctor = m_ast->AddMethodToCXXRecordType( - t.GetOpaqueQualType(), "S", /*asm_label=*/"$__lldb_func:0x0:0x0:S", + t.GetOpaqueQualType(), "S", /*asm_label=*/"$__lldb_func::0x0:0x0:S", function_type, lldb::AccessType::eAccessPublic, is_virtual, is_static, is_inline, is_explicit, is_attr_used, is_artificial); auto *dtor = m_ast->AddMethodToCXXRecordType( - t.GetOpaqueQualType(), "~S", /*asm_label=*/"$__lldb_func:0x0:0x0:~S", + t.GetOpaqueQualType(), "~S", /*asm_label=*/"$__lldb_func::0x0:0x0:~S", function_type, lldb::AccessType::eAccessPublic, is_virtual, is_static, is_inline, is_explicit, is_attr_used, is_artificial); @@ -1181,11 +1181,11 @@ TEST_F(TestTypeSystemClang, AsmLabel_CtorDtor) { EXPECT_STREQ(llvm::GlobalValue::dropLLVMManglingEscape( m_ast->DeclGetMangledName(ctor).GetStringRef()) .data(), - "$__lldb_func:0x0:0x0:S"); + "$__lldb_func:C0:0x0:0x0:S"); EXPECT_STREQ(llvm::GlobalValue::dropLLVMManglingEscape( m_ast->DeclGetMangledName(dtor).GetStringRef()) .data(), - "$__lldb_func:0x0:0x0:~S"); + "$__lldb_func:D1:0x0:0x0:~S"); } struct AsmLabelTestCase { @@ -1215,10 +1215,10 @@ class TestTypeSystemClangAsmLabel }; static AsmLabelTestCase g_asm_label_test_cases[] = { - {/*mangled=*/"$__lldb_func:0x0:0x0:_Z3foov", + {/*mangled=*/"$__lldb_func::0x0:0x0:_Z3foov", /*expected=*/"_Z3foov"}, - {/*mangled=*/"$__lldb_func:0x0:0x0:foo", - /*expected=*/"$__lldb_func:0x0:0x0:foo"}, + {/*mangled=*/"$__lldb_func::0x0:0x0:foo", + /*expected=*/"$__lldb_func::0x0:0x0:foo"}, {/*mangled=*/"foo", /*expected=*/"foo"}, {/*mangled=*/"_Z3foov", _______________________________________________ lldb-commits mailing list lldb-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits
