Fix tsd cleanup regressions.

Fix tsd cleanup regressions that were introduced in
5460aa6f66 (Convert all tsd variables to
reside in a single tsd structure.).  These regressions were twofold:

1) tsd_tryget() should never (and need never) return NULL.  Rename it to
   tsd_fetch() and simplify all callers.
2) tsd_*_set() must only be called when tsd is in the nominal state,
   because cleanup happens during the nominal-->purgatory transition,
   and re-initialization must not happen while in the purgatory state.
   Add tsd_nominal() and use it as needed.  Note that tsd_*{p,}_get()
   can still be used as long as no re-initialization that would require
   cleanup occurs.  This means that e.g. the thread_allocated counter
   can be updated unconditionally.

test/unit/tsd.c

@@ -6,17 +6,46 @@ typedef unsigned int data_t;
 
 static bool data_cleanup_executed;
 
+malloc_tsd_protos(, data_, data_t)
+
 void
 data_cleanup(void *arg)
 {
 	data_t *data = (data_t *)arg;
 
-	assert_x_eq(*data, THREAD_DATA,
-	    "Argument passed into cleanup function should match tsd value");
+	if (!data_cleanup_executed) {
+		assert_x_eq(*data, THREAD_DATA,
+		    "Argument passed into cleanup function should match tsd "
+		    "value");
+	}
 	data_cleanup_executed = true;
+
+	/*
+	 * Allocate during cleanup for two rounds, in order to assure that
+	 * jemalloc's internal tsd reinitialization happens.
+	 */
+	switch (*data) {
+	case THREAD_DATA:
+		*data = 1;
+		data_tsd_set(data);
+		break;
+	case 1:
+		*data = 2;
+		data_tsd_set(data);
+		break;
+	case 2:
+		return;
+	default:
+		not_reached();
+	}
+
+	{
+		void *p = mallocx(1, 0);
+		assert_ptr_not_null(p, "Unexpeced mallocx() failure");
+		dallocx(p, 0);
+	}
 }
 
-malloc_tsd_protos(, data_, data_t)
 malloc_tsd_externs(data_, data_t)
 #define	DATA_INIT 0x12345678
 malloc_tsd_data(, data_, data_t, DATA_INIT)