Revert "workqueue: allow work_on_cpu() to be called recursively"

This reverts commit c2fda509667b0fda4372a237f5a59ea4570b1627.

c2fda509667b removed lockdep annotation from work_on_cpu() to work around
the PCI path that calls work_on_cpu() from within a work_on_cpu() work item
(PF driver .probe() method -> pci_enable_sriov() -> add VFs -> VF driver
.probe method).

961da7fb6b22 ("PCI: Avoid unnecessary CPU switch when calling driver
.probe() method) avoids that recursive work_on_cpu() use in a different
way, so this revert restores the work_on_cpu() lockdep annotation.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 987293d..5690b8e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2840,19 +2840,6 @@
 	return false;
 }
 
-static bool __flush_work(struct work_struct *work)
-{
-	struct wq_barrier barr;
-
-	if (start_flush_work(work, &barr)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-		return true;
-	} else {
-		return false;
-	}
-}
-
 /**
  * flush_work - wait for a work to finish executing the last queueing instance
  * @work: the work to flush
@@ -2866,10 +2853,18 @@
  */
 bool flush_work(struct work_struct *work)
 {
+	struct wq_barrier barr;
+
 	lock_map_acquire(&work->lockdep_map);
 	lock_map_release(&work->lockdep_map);
 
-	return __flush_work(work);
+	if (start_flush_work(work, &barr)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else {
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -4814,14 +4809,7 @@
 
 	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
 	schedule_work_on(cpu, &wfc.work);
-
-	/*
-	 * The work item is on-stack and can't lead to deadlock through
-	 * flushing.  Use __flush_work() to avoid spurious lockdep warnings
-	 * when work_on_cpu()s are nested.
-	 */
-	__flush_work(&wfc.work);
-
+	flush_work(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);