[lldb][debuginfod] Fix the DebugInfoD PR that caused issues when working with stripped binaries (#99362)

@walter-erquinigo found the the [PR with testing and a fix for
DebugInfoD](#98344) caused an
issue when working with stripped binaries.

The issue is that when you're working with split-dwarf, there are *3*
possible files: The stripped binary the user is debugging, the
"only-keep-debug" *or* unstripped binary, plus the `.dwp` file. The
debuginfod plugin should provide the unstripped/OKD binary. However, if
the debuginfod plugin fails, the default symbol locator plugin will just
return the stripped binary, which doesn't help. So, to address that, the
SymbolVendorELF code checks to see if the SymbolLocator's
ExecutableObjectFile request returned the same file, and bails if that's
the case. You can see the specific diff as the second commit in the PR.

I'm investigating adding a test: I can't quite get a simple repro, and
I'm unwilling to make any additional changes to Makefile.rules to this
diff, for Pavlovian reasons.

Author: Kevin Frei

lldb/include/lldb/Host/Config.h.cmake

@@ -33,6 +33,8 @@
 
 #cmakedefine01 LLDB_ENABLE_LZMA
 
+#cmakedefine01 LLVM_ENABLE_CURL
+
 #cmakedefine01 LLDB_ENABLE_CURSES
 
 #cmakedefine01 CURSES_HAVE_NCURSES_CURSES_H

lldb/packages/Python/lldbsuite/test/decorators.py

@@ -1053,6 +1053,10 @@ def _get_bool_config_skip_if_decorator(key):
     return unittest.skipIf(not have, "requires " + key)
 
 
+def skipIfCurlSupportMissing(func):
+    return _get_bool_config_skip_if_decorator("curl")(func)
+
+
 def skipIfCursesSupportMissing(func):
     return _get_bool_config_skip_if_decorator("curses")(func)
 

lldb/packages/Python/lldbsuite/test/make/Makefile.rules

@@ -202,6 +202,12 @@ else
 	ifeq "$(SPLIT_DEBUG_SYMBOLS)" "YES"
 		DSYM = $(EXE).debug
 	endif
+
+	ifeq "$(MAKE_DWP)" "YES"
+		MAKE_DWO := YES
+		DWP_NAME = $(EXE).dwp
+		DYLIB_DWP_NAME = $(DYLIB_NAME).dwp
+	endif
 endif
 
 LIMIT_DEBUG_INFO_FLAGS =
@@ -347,6 +353,17 @@ ifneq "$(OS)" "Darwin"
 
 	OBJCOPY ?= $(call replace_cc_with,objcopy)
 	ARCHIVER ?= $(call replace_cc_with,ar)
+	# Look for llvm-dwp or gnu dwp
+	DWP ?= $(call replace_cc_with,llvm-dwp)
+	ifeq ($(wildcard $(DWP)),)
+		DWP = $(call replace_cc_with,dwp)
+		ifeq ($(wildcard $(DWP)),)
+			DWP = $(shell command -v llvm-dwp 2> /dev/null)
+			ifeq ($(wildcard $(DWP)),)
+				DWP = $(shell command -v dwp 2> /dev/null)
+			endif
+		endif
+	endif
 	override AR = $(ARCHIVER)
 endif
 
@@ -526,6 +543,10 @@ ifneq "$(CXX)" ""
 	endif
 endif
 
+ifeq "$(GEN_GNU_BUILD_ID)" "YES"
+	LDFLAGS += -Wl,--build-id
+endif
+
 #----------------------------------------------------------------------
 # DYLIB_ONLY variable can be used to skip the building of a.out.
 # See the sections below regarding dSYM file as well as the building of
@@ -564,11 +585,18 @@ else
 endif
 else
 ifeq "$(SPLIT_DEBUG_SYMBOLS)" "YES"
+ifeq "$(SAVE_FULL_DEBUG_BINARY)" "YES"
+	cp "$(EXE)" "$(EXE).unstripped"
+endif
 	$(OBJCOPY) --only-keep-debug "$(EXE)" "$(DSYM)"
 	$(OBJCOPY) --strip-debug --add-gnu-debuglink="$(DSYM)" "$(EXE)" "$(EXE)"
 endif
+ifeq "$(MAKE_DWP)" "YES"
+	$(DWP) -o "$(DWP_NAME)" $(DWOS)
+endif
 endif
 
+
 #----------------------------------------------------------------------
 # Make the dylib
 #----------------------------------------------------------------------
@@ -609,9 +637,15 @@ endif
 else
 	$(LD) $(DYLIB_OBJECTS) $(LDFLAGS) -shared -o "$(DYLIB_FILENAME)"
 ifeq "$(SPLIT_DEBUG_SYMBOLS)" "YES"
+ifeq "$(SAVE_FULL_DEBUG_BINARY)" "YES"
+	cp "$(DYLIB_FILENAME)" "$(DYLIB_FILENAME).unstripped"
+endif
 	$(OBJCOPY) --only-keep-debug "$(DYLIB_FILENAME)" "$(DYLIB_FILENAME).debug"
 	$(OBJCOPY) --strip-debug --add-gnu-debuglink="$(DYLIB_FILENAME).debug" "$(DYLIB_FILENAME)" "$(DYLIB_FILENAME)"
 endif
+ifeq "$(MAKE_DWP)" "YES"
+	$(DWP) -o $(DYLIB_DWP_FILE) $(DYLIB_DWOS)
+endif
 endif
 
 #----------------------------------------------------------------------

lldb/source/API/SBDebugger.cpp

@@ -775,6 +775,9 @@ SBStructuredData SBDebugger::GetBuildConfiguration() {
   AddBoolConfigEntry(
       *config_up, "xml", XMLDocument::XMLEnabled(),
       "A boolean value that indicates if XML support is enabled in LLDB");
+  AddBoolConfigEntry(
+      *config_up, "curl", LLVM_ENABLE_CURL,
+      "A boolean value that indicates if CURL support is enabled in LLDB");
   AddBoolConfigEntry(
       *config_up, "curses", LLDB_ENABLE_CURSES,
       "A boolean value that indicates if curses support is enabled in LLDB");
@@ -1724,20 +1727,20 @@ SBDebugger::LoadTraceFromFile(SBError &error,
 
 void SBDebugger::RequestInterrupt() {
   LLDB_INSTRUMENT_VA(this);
-  
+
   if (m_opaque_sp)
-    m_opaque_sp->RequestInterrupt();  
+    m_opaque_sp->RequestInterrupt();
 }
 void SBDebugger::CancelInterruptRequest()  {
   LLDB_INSTRUMENT_VA(this);
-  
+
   if (m_opaque_sp)
-    m_opaque_sp->CancelInterruptRequest();  
+    m_opaque_sp->CancelInterruptRequest();
 }
 
 bool SBDebugger::InterruptRequested()   {
   LLDB_INSTRUMENT_VA(this);
-  
+
   if (m_opaque_sp)
     return m_opaque_sp->InterruptRequested();
   return false;

lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp

@@ -4331,26 +4331,38 @@ const std::shared_ptr<SymbolFileDWARFDwo> &SymbolFileDWARF::GetDwpSymbolFile() {
     FileSpecList search_paths = Target::GetDefaultDebugFileSearchPaths();
     ModuleSpec module_spec;
     module_spec.GetFileSpec() = m_objfile_sp->GetFileSpec();
+    FileSpec dwp_filespec;
     for (const auto &symfile : symfiles.files()) {
       module_spec.GetSymbolFileSpec() =
           FileSpec(symfile.GetPath() + ".dwp", symfile.GetPathStyle());
       LLDB_LOG(log, "Searching for DWP using: \"{0}\"",
                module_spec.GetSymbolFileSpec());
-      FileSpec dwp_filespec =
+      dwp_filespec =
           PluginManager::LocateExecutableSymbolFile(module_spec, search_paths);
       if (FileSystem::Instance().Exists(dwp_filespec)) {
-        LLDB_LOG(log, "Found DWP file: \"{0}\"", dwp_filespec);
-        DataBufferSP dwp_file_data_sp;
-        lldb::offset_t dwp_file_data_offset = 0;
-        ObjectFileSP dwp_obj_file = ObjectFile::FindPlugin(
-            GetObjectFile()->GetModule(), &dwp_filespec, 0,
-            FileSystem::Instance().GetByteSize(dwp_filespec), dwp_file_data_sp,
-            dwp_file_data_offset);
-        if (dwp_obj_file) {
-          m_dwp_symfile = std::make_shared<SymbolFileDWARFDwo>(
-              *this, dwp_obj_file, DIERef::k_file_index_mask);
-          break;
-        }
+        break;
+      }
+    }
+    if (!FileSystem::Instance().Exists(dwp_filespec)) {
+      LLDB_LOG(log, "No DWP file found locally");
+      // Fill in the UUID for the module we're trying to match for, so we can
+      // find the correct DWP file, as the Debuginfod plugin uses *only* this
+      // data to correctly match the DWP file with the binary.
+      module_spec.GetUUID() = m_objfile_sp->GetUUID();
+      dwp_filespec =
+          PluginManager::LocateExecutableSymbolFile(module_spec, search_paths);
+    }
+    if (FileSystem::Instance().Exists(dwp_filespec)) {
+      LLDB_LOG(log, "Found DWP file: \"{0}\"", dwp_filespec);
+      DataBufferSP dwp_file_data_sp;
+      lldb::offset_t dwp_file_data_offset = 0;
+      ObjectFileSP dwp_obj_file = ObjectFile::FindPlugin(
+          GetObjectFile()->GetModule(), &dwp_filespec, 0,
+          FileSystem::Instance().GetByteSize(dwp_filespec), dwp_file_data_sp,
+          dwp_file_data_offset);
+      if (dwp_obj_file) {
+        m_dwp_symfile = std::make_shared<SymbolFileDWARFDwo>(
+            *this, dwp_obj_file, DIERef::k_file_index_mask);
       }
     }
     if (!m_dwp_symfile) {

lldb/source/Plugins/SymbolLocator/CMakeLists.txt

@@ -1,5 +1,10 @@
+# Order matters here: the first symbol locator prevents further searching.
+# For DWARF binaries that are both stripped and split, the Default plugin
+# will return the stripped binary when asked for the ObjectFile, which then
+# prevents an unstripped binary from being requested from the Debuginfod
+# provider.
+add_subdirectory(Debuginfod)
 add_subdirectory(Default)
 if (CMAKE_SYSTEM_NAME MATCHES "Darwin")
   add_subdirectory(DebugSymbols)
 endif()
-add_subdirectory(Debuginfod)

lldb/source/Plugins/SymbolVendor/ELF/SymbolVendorELF.cpp

@@ -44,6 +44,24 @@ llvm::StringRef SymbolVendorELF::GetPluginDescriptionStatic() {
          "executables.";
 }
 
+// If this is needed elsewhere, it can be exported/moved.
+static bool IsDwpSymbolFile(const lldb::ModuleSP &module_sp,
+                            const FileSpec &file_spec) {
+  DataBufferSP dwp_file_data_sp;
+  lldb::offset_t dwp_file_data_offset = 0;
+  // Try to create an ObjectFile from the file_spec.
+  ObjectFileSP dwp_obj_file = ObjectFile::FindPlugin(
+      module_sp, &file_spec, 0, FileSystem::Instance().GetByteSize(file_spec),
+      dwp_file_data_sp, dwp_file_data_offset);
+  // The presence of a debug_cu_index section is the key identifying feature of
+  // a DWP file. Make sure we don't fill in the section list on dwp_obj_file
+  // (by calling GetSectionList(false)) as this function could be called before
+  // we may have all the symbol files collected and available.
+  return dwp_obj_file && ObjectFileELF::classof(dwp_obj_file.get()) &&
+         dwp_obj_file->GetSectionList(false)->FindSectionByType(
+             eSectionTypeDWARFDebugCuIndex, false);
+}
+
 // CreateInstance
 //
 // Platforms can register a callback to use when creating symbol vendors to
@@ -87,8 +105,20 @@ SymbolVendorELF::CreateInstance(const lldb::ModuleSP &module_sp,
   FileSpecList search_paths = Target::GetDefaultDebugFileSearchPaths();
   FileSpec dsym_fspec =
       PluginManager::LocateExecutableSymbolFile(module_spec, search_paths);
-  if (!dsym_fspec)
-    return nullptr;
+  if (!dsym_fspec || IsDwpSymbolFile(module_sp, dsym_fspec)) {
+    // If we have a stripped binary or if we have a DWP file, SymbolLocator
+    // plugins may be able to give us an unstripped binary or an
+    // 'only-keep-debug' stripped file.
+    ModuleSpec unstripped_spec =
+        PluginManager::LocateExecutableObjectFile(module_spec);
+    if (!unstripped_spec)
+      return nullptr;
+    // The default SymbolLocator plugin returns the original binary if no other
+    // plugin finds something better.
+    if (unstripped_spec.GetFileSpec() == module_spec.GetFileSpec())
+      return nullptr;
+    dsym_fspec = unstripped_spec.GetFileSpec();
+  }
 
   DataBufferSP dsym_file_data_sp;
   lldb::offset_t dsym_file_data_offset = 0;

lldb/test/API/debuginfod/Normal/Makefile

@@ -0,0 +1,19 @@
+C_SOURCES := main.c
+
+# For normal (non DWP) Debuginfod tests, we need:
+
+# * The full binary: a.out.unstripped
+#   Produced by Makefile.rules with SAVE_FULL_DEBUG_BINARY set to YES and
+#   SPLIT_DEBUG_SYMBOLS set to YES
+
+# * The stripped binary (a.out)
+#   Produced by Makefile.rules with SPLIT_DEBUG_SYMBOLS set to YES
+
+# * The 'only-keep-debug' binary (a.out.debug)
+#   Produced below
+
+SPLIT_DEBUG_SYMBOLS := YES
+SAVE_FULL_DEBUG_BINARY := YES
+GEN_GNU_BUILD_ID := YES
+
+include Makefile.rules