Index: lld/ELF/Config.h
===================================================================
--- lld/ELF/Config.h
+++ lld/ELF/Config.h
@@ -191,6 +191,7 @@
   bool trace;
   bool thinLTOEmitImportsFiles;
   bool thinLTOIndexOnly;
+  bool timeTraceEnabled;
   bool tocOptimize;
   bool undefinedVersion;
   bool useAndroidRelrTags = false;
@@ -240,6 +241,7 @@
   unsigned ltoo;
   unsigned optimize;
   unsigned thinLTOJobs;
+  unsigned timeTraceGranularity;
   int32_t splitStackAdjustSize;
 
   // The following config options do not directly correspond to any
Index: lld/ELF/Driver.cpp
===================================================================
--- lld/ELF/Driver.cpp
+++ lld/ELF/Driver.cpp
@@ -56,6 +56,7 @@
 #include "llvm/Support/Path.h"
 #include "llvm/Support/TarWriter.h"
 #include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cstdlib>
 #include <utility>
@@ -500,6 +501,11 @@
   if (errorCount())
     return;
 
+  // Initialize time trace.
+  if (config->timeTraceEnabled)
+    llvm::timeTraceProfilerInitialize(config->timeTraceGranularity,
+                                      config->progName);
+
   // The Target instance handles target-specific stuff, such as applying
   // relocations or writing a PLT section. It also contains target-dependent
   // values such as a default image base address.
@@ -508,19 +514,34 @@
   switch (config->ekind) {
   case ELF32LEKind:
     link<ELF32LE>(args);
-    return;
+    break;
   case ELF32BEKind:
     link<ELF32BE>(args);
-    return;
+    break;
   case ELF64LEKind:
     link<ELF64LE>(args);
-    return;
+    break;
   case ELF64BEKind:
     link<ELF64BE>(args);
-    return;
+    break;
   default:
     llvm_unreachable("unknown Config->EKind");
   }
+
+  if (llvm::timeTraceProfilerEnabled()) {
+    SmallString<128> path(config->outputFile);
+    llvm::sys::path::replace_extension(path, "json");
+    if (!args.getLastArgValue(OPT_time_trace_eq).empty())
+      path = args.getLastArgValue(OPT_time_trace_eq);
+    std::error_code errorCode;
+    raw_fd_ostream profilerOS(path, errorCode, sys::fs::F_Text);
+    if (errorCode) {
+      error("cannot open " + path + ": " + errorCode.message());
+      return;
+    }
+    llvm::timeTraceProfilerWrite(profilerOS);
+    llvm::timeTraceProfilerCleanup();
+  }
 }
 
 static std::string getRpath(opt::InputArgList &args) {
@@ -952,6 +973,10 @@
       getOldNewOptions(args, OPT_thinlto_object_suffix_replace_eq);
   config->thinLTOPrefixReplace =
       getOldNewOptions(args, OPT_thinlto_prefix_replace_eq);
+  config->timeTraceEnabled =
+      args.hasArg(OPT_time_trace) || args.hasArg(OPT_time_trace_eq);
+  config->timeTraceGranularity =
+      args::getInteger(args, OPT_time_trace_granularity, 500u);
   config->trace = args.hasArg(OPT_trace);
   config->undefined = args::getStrings(args, OPT_undefined);
   config->undefinedVersion =
@@ -1596,6 +1621,7 @@
 // Because all bitcode files that the program consists of are passed to
 // the compiler at once, it can do a whole-program optimization.
 template <class ELFT> void LinkerDriver::compileBitcodeFiles() {
+  llvm::TimeTraceScope timeScope("LTO", StringRef(""));
   // Compile bitcode files and replace bitcode symbols.
   lto.reset(new BitcodeCompiler);
   for (BitcodeFile *file : bitcodeFiles)
@@ -1722,6 +1748,8 @@
 // Do actual linking. Note that when this function is called,
 // all linker scripts have already been parsed.
 template <class ELFT> void LinkerDriver::link(opt::InputArgList &args) {
+  llvm::TimeTraceScope timeScope("ExecuteLinker", StringRef(""));
+
   // If a -hash-style option was not given, set to a default value,
   // which varies depending on the target.
   if (!args.hasArg(OPT_hash_style)) {
@@ -1761,8 +1789,11 @@
   // symbols that we need to the symbol table. This process might
   // add files to the link, via autolinking, these files are always
   // appended to the Files vector.
-  for (size_t i = 0; i < files.size(); ++i)
-    parseFile(files[i]);
+  {
+    llvm::TimeTraceScope timeScope("Parse input files", StringRef(""));
+    for (size_t i = 0; i < files.size(); ++i)
+      parseFile(files[i]);
+  }
 
   // Now that we have every file, we can decide if we will need a
   // dynamic symbol table.
Index: lld/ELF/ICF.cpp
===================================================================
--- lld/ELF/ICF.cpp
+++ lld/ELF/ICF.cpp
@@ -84,6 +84,7 @@
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/Object/ELF.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/xxhash.h"
 #include <algorithm>
 #include <atomic>
@@ -445,6 +446,7 @@
 
 // The main function of ICF.
 template <class ELFT> void ICF<ELFT>::run() {
+  llvm::TimeTraceScope timeScope("ICF", StringRef(""));
   // Collect sections to merge.
   for (InputSectionBase *sec : inputSections) {
     auto *s = cast<InputSection>(sec);
Index: lld/ELF/LTO.cpp
===================================================================
--- lld/ELF/LTO.cpp
+++ lld/ELF/LTO.cpp
@@ -108,6 +108,9 @@
   c.DebugPassManager = config->ltoDebugPassManager;
   c.DwoDir = config->dwoDir;
 
+  c.TimeTraceEnabled = config->timeTraceEnabled;
+  c.TimeTraceGranularity = config->timeTraceGranularity;
+
   c.CSIRProfile = config->ltoCSProfileFile;
   c.RunCSIRInstr = config->ltoCSProfileGenerate;
 
Index: lld/ELF/MarkLive.cpp
===================================================================
--- lld/ELF/MarkLive.cpp
+++ lld/ELF/MarkLive.cpp
@@ -31,6 +31,7 @@
 #include "lld/Common/Strings.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Object/ELF.h"
+#include "llvm/Support/TimeProfiler.h"
 #include <functional>
 #include <vector>
 
@@ -323,6 +324,7 @@
 // input sections. This function make some or all of them on
 // so that they are emitted to the output file.
 template <class ELFT> void markLive() {
+  llvm::TimeTraceScope timeScope("GC", StringRef(""));
   // If -gc-sections is not given, no sections are removed.
   if (!config->gcSections) {
     for (InputSectionBase *sec : inputSections)
Index: lld/ELF/Options.td
===================================================================
--- lld/ELF/Options.td
+++ lld/ELF/Options.td
@@ -364,6 +364,12 @@
     "Run the linker multi-threaded (default)",
     "Do not run the linker multi-threaded">;
 
+def time_trace: F<"time-trace">, HelpText<"Record time trace">;
+def time_trace_eq: J<"time-trace=">, HelpText<"Record time trace to specified file">;
+
+defm time_trace_granularity: Eq<"time-trace-granularity",
+  "Minimum time granularity (in microseconds) traced by time profiler">;
+
 defm toc_optimize : B<"toc-optimize",
     "(PowerPC64) Enable TOC related optimizations (default)",
     "(PowerPC64) Disable TOC related optimizations">;
Index: lld/ELF/Writer.cpp
===================================================================
--- lld/ELF/Writer.cpp
+++ lld/ELF/Writer.cpp
@@ -27,6 +27,7 @@
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/Support/RandomNumberGenerator.h"
 #include "llvm/Support/SHA1.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/xxhash.h"
 #include <climits>
 
@@ -139,7 +140,10 @@
          script->needsInterpSection();
 }
 
-template <class ELFT> void writeResult() { Writer<ELFT>().run(); }
+template <class ELFT> void writeResult() {
+  llvm::TimeTraceScope timeScope("Write output file", StringRef(""));
+  Writer<ELFT>().run();
+}
 
 static void removeEmptyPTLoad(std::vector<PhdrEntry *> &phdrs) {
   llvm::erase_if(phdrs, [&](const PhdrEntry *p) {
Index: llvm/include/llvm/LTO/Config.h
===================================================================
--- llvm/include/llvm/LTO/Config.h
+++ llvm/include/llvm/LTO/Config.h
@@ -117,6 +117,12 @@
   /// Statistics output file path.
   std::string StatsFile;
 
+  /// Time trace enabled
+  bool TimeTraceEnabled = false;
+
+  /// Time trace granularity
+  unsigned TimeTraceGranularity = 500;
+
   bool ShouldDiscardValueNames = true;
   DiagnosticHandlerFunction DiagHandler;
 
Index: llvm/lib/LTO/LTO.cpp
===================================================================
--- llvm/lib/LTO/LTO.cpp
+++ llvm/lib/LTO/LTO.cpp
@@ -39,6 +39,7 @@
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/ThreadPool.h"
 #include "llvm/Support/Threading.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/VCSRevision.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
@@ -1133,6 +1134,9 @@
                 &ResolvedODR,
             const GVSummaryMapTy &DefinedGlobals,
             MapVector<StringRef, BitcodeModule> &ModuleMap) {
+          if (Conf.TimeTraceEnabled)
+            timeTraceProfilerInitialize(Conf.TimeTraceGranularity,
+                                        "thin backend");
           Error E = runThinLTOBackendThread(
               AddStream, Cache, Task, BM, CombinedIndex, ImportList, ExportList,
               ResolvedODR, DefinedGlobals, ModuleMap);
@@ -1143,6 +1147,8 @@
             else
               Err = std::move(E);
           }
+          if (timeTraceProfilerEnabled())
+            timeTraceProfilerFinishThread();
         },
         BM, std::ref(CombinedIndex), std::ref(ImportList), std::ref(ExportList),
         std::ref(ResolvedODR), std::ref(DefinedGlobals), std::ref(ModuleMap));