[lldb] Extend FindTypes to optionally search by mangled type name

[augusto2112]

Swift types have mangled type names. This adds functionality to look up those types through the FindTypes API by searching for the mangled type name instead of the regular name.

[augusto2112]

This depends on https://github.com/llvm/llvm-project/pull/113006

[llvmbot]

@llvm/pr-subscribers-lldb

Author: Augusto Noronha (augusto2112)

Changes

Swift types have mangled type names. This adds functionality to look up those types through the FindTypes API by searching for the mangled type name instead of the regular name.

---

Full diff: https://github.com/llvm/llvm-project/pull/113007.diff

7 Files Affected:

• (modified) lldb/include/lldb/Symbol/Type.h (+8)
• (modified) lldb/source/Plugins/SymbolFile/CTF/SymbolFileCTF.cpp (+10-4)
• (modified) lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.cpp (+28-7)
• (modified) lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.h (+3-2)
• (modified) lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp (+1-1)
• (modified) lldb/source/Plugins/SymbolFile/NativePDB/SymbolFileNativePDB.cpp (+4-1)
• (modified) lldb/source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp (+4-1)

diff --git a/lldb/include/lldb/Symbol/Type.h b/lldb/include/lldb/Symbol/Type.h
index 03d9f927997476..b90cfc44e907b9 100644
--- a/lldb/include/lldb/Symbol/Type.h
+++ b/lldb/include/lldb/Symbol/Type.h
@@ -84,6 +84,8 @@ FLAGS_ENUM(TypeQueryOptions){
     /// matching type is found. When false, the type query should find all
     /// matching types.
     e_find_one = (1u << 4),
+    // If set, treat TypeQuery::m_name as a mangled name that should be searched.
+    e_search_by_mangled_name = (1u << 5),
 };
 LLDB_MARK_AS_BITMASK_ENUM(TypeQueryOptions)
 
@@ -300,6 +302,12 @@ class TypeQuery {
       m_options &= ~e_find_one;
   }
 
+  /// Returns true if the type query is supposed to treat the name to be searched
+  /// as a mangled name.
+  bool GetSearchByMangledName() const {
+    return (m_options & e_search_by_mangled_name) != 0;
+  }
+
   /// Access the internal compiler context array.
   ///
   /// Clients can use this to populate the context manually.
diff --git a/lldb/source/Plugins/SymbolFile/CTF/SymbolFileCTF.cpp b/lldb/source/Plugins/SymbolFile/CTF/SymbolFileCTF.cpp
index bb738c3dcc54a0..ee63c21663128a 100644
--- a/lldb/source/Plugins/SymbolFile/CTF/SymbolFileCTF.cpp
+++ b/lldb/source/Plugins/SymbolFile/CTF/SymbolFileCTF.cpp
@@ -1032,10 +1032,16 @@ void SymbolFileCTF::FindTypes(const lldb_private::TypeQuery &match,
 
   ConstString name = match.GetTypeBasename();
   for (TypeSP type_sp : GetTypeList().Types()) {
-    if (type_sp && type_sp->GetName() == name) {
-      results.InsertUnique(type_sp);
-      if (results.Done(match))
-        return;
+    if (type_sp) {
+      auto type_name =
+          match.GetSearchByMangledName()
+              ? type_sp->GetForwardCompilerType().GetMangledTypeName()
+              : type_sp->GetName();
+      if (type_name == name) {
+        results.InsertUnique(type_sp);
+        if (results.Done(match))
+          return;
+      }
     }
   }
 }
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.cpp b/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.cpp
index d83740f8e2113b..d4604d72b3a3b6 100644
--- a/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.cpp
+++ b/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.cpp
@@ -14,6 +14,7 @@
 #include "DWARFDeclContext.h"
 #include "DWARFUnit.h"
 #include "lldb/Symbol/Type.h"
+#include "lldb/lldb-private-enumerations.h"
 
 #include "llvm/ADT/iterator.h"
 #include "llvm/BinaryFormat/Dwarf.h"
@@ -368,7 +369,7 @@ lldb_private::Type *DWARFDIE::ResolveTypeUID(const DWARFDIE &die) const {
   return nullptr;
 }
 
-static void GetDeclContextImpl(DWARFDIE die,
+static void GetDeclContextImpl(DWARFDIE die, bool use_mangled_name,
                                llvm::SmallSet<lldb::user_id_t, 4> &seen,
                                std::vector<CompilerContext> &context) {
   // Stop if we hit a cycle.
@@ -383,6 +384,13 @@ static void GetDeclContextImpl(DWARFDIE die,
     auto push_ctx = [&](CompilerContextKind kind, llvm::StringRef name) {
       context.push_back({kind, ConstString(name)});
     };
+
+    // Since mangled names are unique there's no need to build an entire context.
+    if (use_mangled_name) {
+      push_ctx(CompilerContextKind::AnyType, die.GetMangledName());
+      return;
+    }
+
     switch (die.Tag()) {
     case DW_TAG_module:
       push_ctx(CompilerContextKind::Module, die.GetName());
@@ -417,15 +425,15 @@ static void GetDeclContextImpl(DWARFDIE die,
   }
 }
 
-std::vector<CompilerContext> DWARFDIE::GetDeclContext() const {
+std::vector<CompilerContext> DWARFDIE::GetDeclContext(bool use_mangled_name) const {
   llvm::SmallSet<lldb::user_id_t, 4> seen;
   std::vector<CompilerContext> context;
-  GetDeclContextImpl(*this, seen, context);
+  GetDeclContextImpl(*this, use_mangled_name, seen, context);
   std::reverse(context.begin(), context.end());
   return context;
 }
 
-static void GetTypeLookupContextImpl(DWARFDIE die,
+static void GetTypeLookupContextImpl(DWARFDIE die, bool use_mangled_name,
                                      llvm::SmallSet<lldb::user_id_t, 4> &seen,
                                      std::vector<CompilerContext> &context) {
   // Stop if we hit a cycle.
@@ -434,6 +442,19 @@ static void GetTypeLookupContextImpl(DWARFDIE die,
     auto push_ctx = [&](CompilerContextKind kind, llvm::StringRef name) {
       context.push_back({kind, ConstString(name)});
     };
+
+    // Since mangled names are unique there's no need to build an entire context.
+    if (use_mangled_name) {
+      push_ctx(CompilerContextKind::AnyType, die.GetMangledName());
+      return;
+    }
+
+    // If there is no name, then there is no need to look anything up for this
+    // DIE.
+       const char *name = die.GetName();
+    if (!name || !name[0])
+      return;
+
     switch (die.Tag()) {
     case DW_TAG_namespace:
       push_ctx(CompilerContextKind::Namespace, die.GetName());
@@ -453,7 +474,7 @@ static void GetTypeLookupContextImpl(DWARFDIE die,
       break;
     case DW_TAG_typedef:
       push_ctx(CompilerContextKind::Typedef, die.GetName());
-      break;
+   break;
     case DW_TAG_base_type:
       push_ctx(CompilerContextKind::Builtin, die.GetName());
       break;
@@ -477,10 +498,10 @@ static void GetTypeLookupContextImpl(DWARFDIE die,
   }
 }
 
-std::vector<CompilerContext> DWARFDIE::GetTypeLookupContext() const {
+std::vector<CompilerContext> DWARFDIE::GetTypeLookupContext(bool use_mangled_name) const {
   llvm::SmallSet<lldb::user_id_t, 4> seen;
   std::vector<CompilerContext> context;
-  GetTypeLookupContextImpl(*this, seen, context);
+  GetTypeLookupContextImpl(*this, use_mangled_name, seen, context);
   std::reverse(context.begin(), context.end());
   return context;
 }
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.h b/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.h
index e1318953a384cd..109070bdcb6e95 100644
--- a/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.h
+++ b/lldb/source/Plugins/SymbolFile/DWARF/DWARFDIE.h
@@ -72,7 +72,7 @@ class DWARFDIE : public DWARFBaseDIE {
   /// Return this DIE's decl context as it is needed to look up types
   /// in Clang modules. This context will include any modules or functions that
   /// the type is declared in so an exact module match can be efficiently made.
-  std::vector<CompilerContext> GetDeclContext() const;
+  std::vector<CompilerContext> GetDeclContext(bool use_mangled_name = false) const;
 
   /// Get a context to a type so it can be looked up.
   ///
@@ -84,7 +84,8 @@ class DWARFDIE : public DWARFBaseDIE {
   /// appropriate time, like either the translation unit or at a function
   /// context. This is designed to allow users to efficiently look for types
   /// using a full or partial CompilerContext array.
-  std::vector<CompilerContext> GetTypeLookupContext() const;
+  std::vector<CompilerContext>
+  GetTypeLookupContext(bool use_mangled_name = false) const;
 
   DWARFDeclContext GetDWARFDeclContext() const;
 
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp
index 9287d4baf19e9c..f1956f006de84d 100644
--- a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp
+++ b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp
@@ -2762,7 +2762,7 @@ void SymbolFileDWARF::FindTypes(const TypeQuery &query, TypeResults &results) {
     if (query.GetModuleSearch())
       die_context = die.GetDeclContext();
     else
-      die_context = die.GetTypeLookupContext();
+      die_context = die.GetTypeLookupContext(query.GetSearchByMangledName());
     assert(!die_context.empty());
     if (!query.ContextMatches(die_context))
       return true; // Keep iterating over index types, context mismatch.
diff --git a/lldb/source/Plugins/SymbolFile/NativePDB/SymbolFileNativePDB.cpp b/lldb/source/Plugins/SymbolFile/NativePDB/SymbolFileNativePDB.cpp
index 7fded6a31a3af5..b55518a136c997 100644
--- a/lldb/source/Plugins/SymbolFile/NativePDB/SymbolFileNativePDB.cpp
+++ b/lldb/source/Plugins/SymbolFile/NativePDB/SymbolFileNativePDB.cpp
@@ -1735,7 +1735,10 @@ void SymbolFileNativePDB::FindTypes(const lldb_private::TypeQuery &query,
       continue;
 
     // We resolved a type. Get the fully qualified name to ensure it matches.
-    ConstString name = type_sp->GetQualifiedName();
+    ConstString name =
+        query.GetSearchByMangledName()
+            ? type_sp->GetForwardCompilerType().GetMangledTypeName()
+            : type_sp->GetQualifiedName();
     TypeQuery type_match(name.GetStringRef(), TypeQueryOptions::e_exact_match);
     if (query.ContextMatches(type_match.GetContextRef())) {
       results.InsertUnique(type_sp);
diff --git a/lldb/source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp b/lldb/source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
index 584c2115459c66..0179c52df9e563 100644
--- a/lldb/source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
+++ b/lldb/source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
@@ -1562,7 +1562,10 @@ void SymbolFilePDB::FindTypes(const lldb_private::TypeQuery &query,
     if (iter == m_types.end())
       continue;
     // We resolved a type. Get the fully qualified name to ensure it matches.
-    ConstString name = iter->second->GetQualifiedName();
+    ConstString name =
+        query.GetSearchByMangledName()
+            ? iter->second->GetForwardCompilerType().GetMangledTypeName()
+            : iter->second->GetQualifiedName();
     TypeQuery type_match(name.GetStringRef(), TypeQueryOptions::e_exact_match);
     if (query.ContextMatches(type_match.GetContextRef())) {
       type_results.InsertUnique(iter->second);

[github-actions[bot]]

:white_check_mark: With the latest revision this PR passed the C/C++ code formatter.

[Michael137]

Yea using the new TypeQuery option in lldb-test seems doable. Whether obj2yaml/yaml2obj supports .debug_names, i'm not sure, haven't tried

[augusto2112]

@Michael137 I wasn't able to run yaml2obj to convert back an object file that contains debug info, I'm not sure if the issue is that yaml2obj doesn't support something that's encoded in the debug info, or some bug with MachO.

This is the error:

error: wrote too much data somewhere, section offsets in section __debug_str_offs__DWARF for segment __DWARF don't line up: [cursor=0x41d1e0], [fileStart=0x41ccdc], [sectionOffset=0x4f2]

[Michael137]

@Michael137 I wasn't able to run yaml2obj to convert back an object file that contains debug info, I'm not sure if the issue is that yaml2obj doesn't support something that's encoded in the debug info, or some bug with MachO.

This is the error:

error: wrote too much data somewhere, section offsets in section __debug_str_offs__DWARF for segment __DWARF don't line up: [cursor=0x41d1e0], [fileStart=0x41ccdc], [sectionOffset=0x4f2]

Hmm yea I wouldn't be surprised if yaml2obj doesn't properly handle this. Could give it a shot using ELF (I think that has better support). But if that doesn't work either I wouldn't bother

[augusto2112]

Ok, I was able to add a test