work_on_cpu(): rewrite it to create a kernel thread on demand

Impact: circular locking bugfix

The various implemetnations and proposed implemetnations of work_on_cpu()
are vulnerable to various deadlocks because they all used queues of some
form.

Unrelated pieces of kernel code thus gained dependencies wherein if one
work_on_cpu() caller holds a lock which some other work_on_cpu() callback
also takes, the kernel could rarely deadlock.

Fix this by creating a short-lived kernel thread for each work_on_cpu()
invokation.

This is not terribly fast, but the only current caller of work_on_cpu() is
pci_call_probe().

It would be nice to find some other way of doing the node-local
allocations in the PCI probe code so that we can zap work_on_cpu()
altogether.  The code there is rather nasty.  I can't think of anything
simple at this time...

Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

kernel/workqueue.c

@@ -966,20 +966,20 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 }
 
 #ifdef CONFIG_SMP
-static struct workqueue_struct *work_on_cpu_wq __read_mostly;
 
 struct work_for_cpu {
-	struct work_struct work;
+	struct completion completion;
 	long (*fn)(void *);
 	void *arg;
 	long ret;
 };
 
-static void do_work_for_cpu(struct work_struct *w)
+static int do_work_for_cpu(void *_wfc)
 {
-	struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
-
+	struct work_for_cpu *wfc = _wfc;
 	wfc->ret = wfc->fn(wfc->arg);
+	complete(&wfc->completion);
+	return 0;
 }
 
 /**
@@ -990,17 +990,23 @@ static void do_work_for_cpu(struct work_struct *w)
  *
  * This will return the value @fn returns.
  * It is up to the caller to ensure that the cpu doesn't go offline.
+ * The caller must not hold any locks which would prevent @fn from completing.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
-	struct work_for_cpu wfc;
-
-	INIT_WORK(&wfc.work, do_work_for_cpu);
-	wfc.fn = fn;
-	wfc.arg = arg;
-	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
-	flush_work(&wfc.work);
-
+	struct task_struct *sub_thread;
+	struct work_for_cpu wfc = {
+		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
+		.fn = fn,
+		.arg = arg,
+	};
+
+	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
+	if (IS_ERR(sub_thread))
+		return PTR_ERR(sub_thread);
+	kthread_bind(sub_thread, cpu);
+	wake_up_process(sub_thread);
+	wait_for_completion(&wfc.completion);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);
@@ -1016,8 +1022,4 @@ void __init init_workqueues(void)
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
-#ifdef CONFIG_SMP
-	work_on_cpu_wq = create_workqueue("work_on_cpu");
-	BUG_ON(!work_on_cpu_wq);
-#endif
 }