[9.0] Backport 115546 FLS initialization fix to 9.

src/coreclr/vm/ceemain.cpp

@@ -862,36 +862,19 @@ void EEStartupHelper()
 
 #ifdef PROFILING_SUPPORTED
         // Initialize the profiling services.
+        // This must happen before Thread::HasStarted() that fires profiler notifications is called on the finalizer thread.
         hr = ProfilingAPIUtility::InitializeProfiling();
 
         _ASSERTE(SUCCEEDED(hr));
         IfFailGo(hr);
 #endif // PROFILING_SUPPORTED
 
-        InitializeExceptionHandling();
-
-        //
-        // Install our global exception filter
-        //
-        if (!InstallUnhandledExceptionFilter())
-        {
-            IfFailGo(E_FAIL);
-        }
-
-        // throws on error
-        SetupThread();
-
-#ifdef DEBUGGING_SUPPORTED
-        // Notify debugger once the first thread is created to finish initialization.
-        if (g_pDebugInterface != NULL)
-        {
-            g_pDebugInterface->StartupPhase2(GetThread());
-        }
-#endif
-
-        // This isn't done as part of InitializeGarbageCollector() above because
-        // debugger must be initialized before creating EE thread objects 
+#ifdef TARGET_WINDOWS
+        // Create the finalizer thread on windows earlier, as we will need to wait for
+        // the completion of its initialization part that initializes COM as that has to be done
+        // before the first Thread is attached. Thus we want to give the thread a bit more time.
         FinalizerThread::FinalizerThreadCreate();
+#endif
 
         InitPreStubManager();
 
@@ -906,8 +889,6 @@ void EEStartupHelper()
         InitJITHelpers1();
         InitJITHelpers2();
 
-        SyncBlockCache::Attach();
-
         // Set up the sync block
         SyncBlockCache::Start();
 
@@ -922,6 +903,48 @@ void EEStartupHelper()
 
         IfFailGo(hr);
 
+        InitializeExceptionHandling();
+
+        //
+        // Install our global exception filter
+        //
+        if (!InstallUnhandledExceptionFilter())
+        {
+            IfFailGo(E_FAIL);
+        }
+
+#ifdef TARGET_WINDOWS
+        // g_pGCHeap->Initialize() above could take nontrivial time, so by now the finalizer thread
+        // should have initialized FLS slot for thread cleanup notifications.
+        // And ensured that COM is initialized (must happen before allocating FLS slot).
+        // Make sure that this was done before we start creating Thread objects
+        // Ex: The call to SetupThread below will create and attach a Thread object.
+        //     Event pipe might also do that.
+        FinalizerThread::WaitForFinalizerThreadStart();
+#endif
+
+        // throws on error
+        _ASSERTE(GetThreadNULLOk() == NULL);
+        SetupThread();
+
+#ifdef DEBUGGING_SUPPORTED
+        // Notify debugger once the first thread is created to finish initialization.
+        if (g_pDebugInterface != NULL)
+        {
+            g_pDebugInterface->StartupPhase2(GetThread());
+        }
+#endif
+
+#ifndef TARGET_WINDOWS
+        // This isn't done as part of InitializeGarbageCollector() above because
+        // debugger must be initialized before creating EE thread objects
+        FinalizerThread::FinalizerThreadCreate();
+#else
+        // On windows the finalizer thread is already partially created and is waiting
+        // right before doing HasStarted(). We will release it now.
+        FinalizerThread::EnableFinalization();
+#endif
+
 #ifdef FEATURE_PERFTRACING
         // Finish setting up rest of EventPipe - specifically enable SampleProfiler if it was requested at startup.
         // SampleProfiler needs to cooperate with the GC which hasn't fully finished setting up in the first part of the
@@ -982,12 +1005,6 @@ void EEStartupHelper()
                                                 g_MiniMetaDataBuffMaxSize, MEM_COMMIT, PAGE_READWRITE);
 #endif // FEATURE_MINIMETADATA_IN_TRIAGEDUMPS
 
-#ifdef TARGET_WINDOWS
-        // By now finalizer thread should have initialized FLS slot for thread cleanup notifications.
-        // And ensured that COM is initialized (must happen before allocating FLS slot).
-        // Make sure that this was done.
-        FinalizerThread::WaitForFinalizerThreadStart();
-#endif
         g_fEEStarted = TRUE;
         g_EEStartupStatus = S_OK;
         hr = S_OK;
@@ -1794,6 +1811,8 @@ void InitFlsSlot()
 //  thread        - thread to attach
 static void OsAttachThread(void* thread)
 {
+    _ASSERTE(g_flsIndex != FLS_OUT_OF_INDEXES);
+
     if (t_flsState == FLS_STATE_INVOKED)
     {
         _ASSERTE_ALL_BUILDS(!"Attempt to execute managed code after the .NET runtime thread state has been destroyed.");

src/coreclr/vm/finalizerthread.cpp

@@ -445,6 +445,7 @@ DWORD WINAPI FinalizerThread::FinalizerThreadStart(void *args)
 
     // handshake with EE initialization, as now we can attach Thread objects to native threads.
     hEventFinalizerDone->Set();
+    WaitForFinalizerEvent (hEventFinalizer);
 #endif
 
     s_FinalizerThreadOK = GetFinalizerThread()->HasStarted();

src/coreclr/vm/syncblk.cpp

@@ -625,13 +625,6 @@ void SyncBlockCache::CleanupSyncBlocks()
     } EE_END_FINALLY;
 }
 
-// create the sync block cache
-/* static */
-void SyncBlockCache::Attach()
-{
-    LIMITED_METHOD_CONTRACT;
-}
-
 // create the sync block cache
 /* static */
 void SyncBlockCache::Start()