[lldb] Load embedded type summary section (#7859)

Add support for type summaries embedded into the binary.

These embedded summaries will typically be generated by macros, but can be generated by 
any other means.

rdar://115184658

Author: kastiglione

lldb/include/lldb/lldb-enumerations.h

@@ -770,6 +770,7 @@ enum SectionType {
   eSectionTypeDWARFDebugLocListsDwo,
   eSectionTypeDWARFDebugTuIndex,
   eSectionTypeCTF,
+  eSectionTypeLLDBTypeSummaries,
 };
 
 FLAGS_ENUM(EmulateInstructionOptions){

lldb/source/Core/Section.cpp

@@ -149,6 +149,8 @@ const char *Section::GetTypeAsCString() const {
     return "dwarf-gnu-debugaltlink";
   case eSectionTypeCTF:
     return "ctf";
+  case eSectionTypeLLDBTypeSummaries:
+    return "lldb-type-summaries";
   case eSectionTypeOther:
     return "regular";
 
@@ -465,6 +467,7 @@ bool Section::ContainsOnlyDebugInfo() const {
   case eSectionTypeDWARFAppleObjC:
   case eSectionTypeDWARFGNUDebugAltLink:
   case eSectionTypeCTF:
+  case eSectionTypeLLDBTypeSummaries:
     return true;
   }
   return false;

lldb/source/Plugins/ObjectFile/ELF/ObjectFileELF.cpp

@@ -1685,7 +1685,7 @@ static SectionType GetSectionTypeFromName(llvm::StringRef Name) {
       .Case(".text", eSectionTypeCode)
       // Swift support:
       .Case(".swift_ast", eSectionTypeSwiftModules)
-      //
+      .Case(".lldbsummaries", lldb::eSectionTypeLLDBTypeSummaries)
       .Default(eSectionTypeOther);
 }
 

lldb/source/Plugins/ObjectFile/Mach-O/ObjectFileMachO.cpp

@@ -1208,6 +1208,7 @@ AddressClass ObjectFileMachO::GetAddressClass(lldb::addr_t file_addr) {
         case eSectionTypeSwiftModules:
         case eSectionTypeDWARFGNUDebugAltLink:
         case eSectionTypeCTF:
+        case eSectionTypeLLDBTypeSummaries:
           return AddressClass::eDebug;
 
         case eSectionTypeEHFrame:
@@ -1485,6 +1486,7 @@ static lldb::SectionType GetSectionType(uint32_t flags,
   static ConstString g_sect_name_swift_ast("__swift_ast");
   static ConstString g_sect_name_go_symtab("__gosymtab");
   static ConstString g_sect_name_ctf("__ctf");
+  static ConstString g_sect_name_lldb_summaries("__lldbsummaries");
 
   if (section_name == g_sect_name_dwarf_debug_abbrev)
     return eSectionTypeDWARFDebugAbbrev;
@@ -1573,6 +1575,9 @@ static lldb::SectionType GetSectionType(uint32_t flags,
       section_name == g_sect_name_objc_classlist) {
     return eSectionTypeDataPointers;
   }
+  if (section_name == g_sect_name_lldb_summaries) {
+    return lldb::eSectionTypeLLDBTypeSummaries;
+  }
 
   switch (mach_sect_type) {
   // TODO: categorize sections by other flags for regular sections

lldb/source/Plugins/ObjectFile/PECOFF/ObjectFilePECOFF.cpp

@@ -1015,6 +1015,7 @@ SectionType ObjectFilePECOFF::GetSectionType(llvm::StringRef sect_name,
           .Cases(".eh_frame", ".eh_fram", eSectionTypeEHFrame)
           .Case(".gosymtab", eSectionTypeGoSymtab)
           .Case("swiftast", eSectionTypeSwiftModules) // downstream change
+          .Case(".lldbsummaries", lldb::eSectionTypeLLDBTypeSummaries)
           .Default(eSectionTypeInvalid);
   if (section_type != eSectionTypeInvalid)
     return section_type;

lldb/source/Symbol/ObjectFile.cpp

@@ -358,6 +358,7 @@ AddressClass ObjectFile::GetAddressClass(addr_t file_addr) {
           case eSectionTypeSwiftModules:
           case eSectionTypeDWARFGNUDebugAltLink:
           case eSectionTypeCTF:
+          case eSectionTypeLLDBTypeSummaries:
             return AddressClass::eDebug;
           case eSectionTypeEHFrame:
           case eSectionTypeARMexidx:

lldb/source/Target/Target.cpp

@@ -27,6 +27,7 @@
 #include "lldb/Core/StructuredDataImpl.h"
 #include "lldb/Core/ValueObject.h"
 #include "lldb/Core/ValueObjectConstResult.h"
+#include "lldb/DataFormatters/DataVisualization.h"
 #include "lldb/Expression/DiagnosticManager.h"
 #include "lldb/Expression/ExpressionVariable.h"
 #include "lldb/Expression/REPL.h"
@@ -1438,6 +1439,76 @@ static void LoadScriptingResourceForModule(const ModuleSP &module_sp,
                                                   feedback_stream.GetData());
 }
 
+// Load type summaries embedded in the binary. These are type summaries provided
+// by the authors of the code.
+static void LoadTypeSummariesForModule(ModuleSP module_sp) {
+  auto *sections = module_sp->GetSectionList();
+  if (!sections)
+    return;
+
+  auto summaries_sp =
+      sections->FindSectionByType(eSectionTypeLLDBTypeSummaries, true);
+  if (!summaries_sp)
+    return;
+
+  Log *log = GetLog(LLDBLog::DataFormatters);
+  const char *module_name = module_sp->GetObjectName().GetCString();
+
+  TypeCategoryImplSP category;
+  DataVisualization::Categories::GetCategory(ConstString("default"), category);
+
+  // The type summary record is serialized as follows.
+  //
+  // Each record contains, in order:
+  //   * Version number of the record format
+  //   * The remaining size of the record
+  //   * The size of the type identifier
+  //   * The type identifier, either a type name, or a regex
+  //   * The size of the summary string
+  //   * The summary string
+  //
+  // Integers are encoded using ULEB.
+  //
+  // Strings are encoded with first a length (ULEB), then the string contents,
+  // and lastly a null terminator. The length includes the null.
+
+  DataExtractor extractor;
+  auto section_size = summaries_sp->GetSectionData(extractor);
+  lldb::offset_t offset = 0;
+  while (offset < section_size) {
+    uint64_t version = extractor.GetULEB128(&offset);
+    uint64_t record_size = extractor.GetULEB128(&offset);
+    if (version == 1) {
+      uint64_t type_size = extractor.GetULEB128(&offset);
+      llvm::StringRef type_name = extractor.GetCStr(&offset, type_size);
+      uint64_t summary_size = extractor.GetULEB128(&offset);
+      llvm::StringRef summary_string = extractor.GetCStr(&offset, summary_size);
+      if (!type_name.empty() && !summary_string.empty()) {
+        TypeSummaryImpl::Flags flags;
+        auto summary_sp =
+            std::make_shared<StringSummaryFormat>(flags, summary_string.data());
+        FormatterMatchType match_type = eFormatterMatchExact;
+        if (summary_string.front() == '^' && summary_string.back() == '$')
+          match_type = eFormatterMatchRegex;
+        category->AddTypeSummary(type_name, match_type, summary_sp);
+        LLDB_LOGF(log, "Loaded embedded type summary for '%s' from %s.",
+                  type_name.data(), module_name);
+      } else {
+        if (type_name.empty())
+          LLDB_LOGF(log, "Missing string(s) in embedded type summary in %s.",
+                    module_name);
+      }
+    } else {
+      // Skip unsupported record.
+      offset += record_size;
+      LLDB_LOGF(
+          log,
+          "Skipping unsupported embedded type summary of version %llu in %s.",
+          version, module_name);
+    }
+  }
+}
+
 void Target::ClearModules(bool delete_locations) {
   ModulesDidUnload(m_images, delete_locations);
   m_section_load_history.Clear();
@@ -1682,6 +1753,7 @@ void Target::ModulesDidLoad(ModuleList &module_list) {
     for (size_t idx = 0; idx < num_images; ++idx) {
       ModuleSP module_sp(module_list.GetModuleAtIndex(idx));
       LoadScriptingResourceForModule(module_sp, this);
+      LoadTypeSummariesForModule(module_sp);
     }
     m_breakpoint_list.UpdateBreakpoints(module_list, true, false);
     m_internal_breakpoint_list.UpdateBreakpoints(module_list, true, false);

lldb/test/API/functionalities/data-formatter/embedded-summary/Makefile

@@ -0,0 +1,2 @@
+C_SOURCES := main.c
+include Makefile.rules

lldb/test/API/functionalities/data-formatter/embedded-summary/TestEmbeddedTypeSummary.py

@@ -0,0 +1,12 @@
+import lldb
+from lldbsuite.test.decorators import *
+from lldbsuite.test.lldbtest import *
+from lldbsuite.test import lldbutil
+
+
+class TestCase(TestBase):
+    @skipUnlessDarwin
+    def test(self):
+        self.build()
+        lldbutil.run_to_source_breakpoint(self, "break here", lldb.SBFileSpec("main.c"))
+        self.expect("v player", substrs=['"Dirk" (41)'])

lldb/test/API/functionalities/data-formatter/embedded-summary/main.c

@@ -0,0 +1,22 @@
+#include <stdio.h>
+
+struct Player {
+  char *name;
+  int number;
+};
+
+__attribute__((used, section("__DATA_CONST,__lldbsummaries"))) unsigned char
+    _Player_type_summary[] = "\x01"     // version
+                             "\x25"     // record size
+                             "\x07"     // type name size
+                             "Player\0" // type name
+                             "\x1c"     // summary string size
+                             "${var.name} (${var.number})"; // summary string
+
+int main() {
+  struct Player player;
+  player.name = "Dirk";
+  player.number = 41;
+  puts("break here");
+  return 0;
+}