[LLD][COFF] Add more `--time-trace` tags for ThinLTO linking (#156471)

In order to better see what's going on during ThinLTO linking, this PR
adds more profile tags when using `--time-trace` on a `lld-link.exe`
invocation.

After PR, linking `clang.exe`:

<img width="3839" height="2026" alt="Capture d’écran 2025-09-02 082021"
src="https://github.com/user-attachments/assets/bf0c85ba-2f85-4bbf-a5c1-800039b56910"
/>

Linking a custom (Unreal Engine game) binary gives a completly
different picture, probably because of using Unity files, and the sheer
amount of input files (here, providing over 60 GB of .OBJs/.LIBs).

<img width="1940" height="1008" alt="Capture d’écran 2025-09-02 102048"
src="https://github.com/user-attachments/assets/60b28630-7995-45ce-9e8c-13f3cb5312e0"
/>

1 files changed, 13 insertions, 4 deletions

diff --git a/llvm/lib/LTO/LTOBackend.cpp b/llvm/lib/LTO/LTOBackend.cpp
index 5e8cd12..ce42fc5 100644
--- a/llvm/lib/LTO/LTOBackend.cpp
+++ b/llvm/lib/LTO/LTOBackend.cpp
@@ -366,6 +366,7 @@ bool lto::opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
               bool IsThinLTO, ModuleSummaryIndex *ExportSummary,
               const ModuleSummaryIndex *ImportSummary,
               const std::vector<uint8_t> &CmdArgs) {
+  llvm::TimeTraceScope timeScope("opt");
   if (EmbedBitcode == LTOBitcodeEmbedding::EmbedPostMergePreOptimized) {
     // FIXME: the motivation for capturing post-merge bitcode and command line
     // is replicating the compilation environment from bitcode, without needing
@@ -399,6 +400,7 @@ bool lto::opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
 static void codegen(const Config &Conf, TargetMachine *TM,
                     AddStreamFn AddStream, unsigned Task, Module &Mod,
                     const ModuleSummaryIndex &CombinedIndex) {
+  llvm::TimeTraceScope timeScope("codegen");
   if (Conf.PreCodeGenModuleHook && !Conf.PreCodeGenModuleHook(Task, Mod))
     return;
 
@@ -552,6 +554,7 @@ Error lto::finalizeOptimizationRemarks(
 Error lto::backend(const Config &C, AddStreamFn AddStream,
                    unsigned ParallelCodeGenParallelismLevel, Module &Mod,
                    ModuleSummaryIndex &CombinedIndex) {
+  llvm::TimeTraceScope timeScope("LTO backend");
   Expected<const Target *> TOrErr = initAndLookupTarget(C, Mod);
   if (!TOrErr)
     return TOrErr.takeError();
@@ -577,6 +580,7 @@ Error lto::backend(const Config &C, AddStreamFn AddStream,
 
 static void dropDeadSymbols(Module &Mod, const GVSummaryMapTy &DefinedGlobals,
                             const ModuleSummaryIndex &Index) {
+  llvm::TimeTraceScope timeScope("Drop dead symbols");
   std::vector<GlobalValue*> DeadGVs;
   for (auto &GV : Mod.global_values())
     if (GlobalValueSummary *GVS = DefinedGlobals.lookup(GV.getGUID()))
@@ -603,6 +607,7 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
                        MapVector<StringRef, BitcodeModule> *ModuleMap,
                        bool CodeGenOnly, AddStreamFn IRAddStream,
                        const std::vector<uint8_t> &CmdArgs) {
+  llvm::TimeTraceScope timeScope("Thin backend", Mod.getModuleIdentifier());
   Expected<const Target *> TOrErr = initAndLookupTarget(Conf, Mod);
   if (!TOrErr)
     return TOrErr.takeError();
@@ -679,6 +684,7 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
     return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
 
   auto ModuleLoader = [&](StringRef Identifier) {
+    llvm::TimeTraceScope moduleLoaderScope("Module loader", Identifier);
     assert(Mod.getContext().isODRUniquingDebugTypes() &&
            "ODR Type uniquing should be enabled on the context");
     if (ModuleMap) {
@@ -712,10 +718,13 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
     return MOrErr;
   };
 
-  FunctionImporter Importer(CombinedIndex, ModuleLoader,
-                            ClearDSOLocalOnDeclarations);
-  if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
-    return Err;
+  {
+    llvm::TimeTraceScope importScope("Import functions");
+    FunctionImporter Importer(CombinedIndex, ModuleLoader,
+                              ClearDSOLocalOnDeclarations);
+    if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
+      return Err;
+  }
 
   // Do this after any importing so that imported code is updated.
   updateMemProfAttributes(Mod, CombinedIndex);