workqueue: perform non-reentrancy test when queueing to unbound workqueues too

Because per-cpu workqueues have multiple pwqs (pool_workqueues) to
serve the CPUs, to guarantee that a single work item isn't queued on
one pwq while still executing another, __queue_work() takes a look at
the previous pool the target work item was on and if it's still
executing there, queue the work item on that pool.

To support changing workqueue_attrs on the fly, unbound workqueues too
will have multiple pwqs and thus need non-reentrancy test when
queueing.  This patch modifies __queue_work() such that the reentrancy
test is performed regardless of the workqueue type.

per_cpu_ptr(wq->cpu_pwqs, cpu) used to be used to determine the
matching pwq for the last pool.  This can't be used for unbound
workqueues and is replaced with worker->current_pwq which also happens
to be simpler.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>

kernel/workqueue.c

@@ -1209,6 +1209,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
 	struct pool_workqueue *pwq;
+	struct worker_pool *last_pool;
 	struct list_head *worklist;
 	unsigned int work_flags;
 	unsigned int req_cpu = cpu;
@@ -1228,22 +1229,21 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
 
-	/* determine the pwq to use */
+	/* pwq which will be used unless @work is executing elsewhere */
 	if (!(wq->flags & WQ_UNBOUND)) {
-		struct worker_pool *last_pool;
-
 		if (cpu == WORK_CPU_UNBOUND)
 			cpu = raw_smp_processor_id();
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	} else {
+		pwq = first_pwq(wq);
+	}
 
 	/*
-		 * It's multi cpu.  If @work was previously on a different
-		 * cpu, it might still be running there, in which case the
-		 * work needs to be queued on that cpu to guarantee
-		 * non-reentrancy.
+	 * If @work was previously on a different pool, it might still be
+	 * running there, in which case the work needs to be queued on that
+	 * pool to guarantee non-reentrancy.
 	 */
-		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
 	last_pool = get_work_pool(work);
-
 	if (last_pool && last_pool != pwq->pool) {
 		struct worker *worker;
 
@@ -1252,7 +1252,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		worker = find_worker_executing_work(last_pool, work);
 
 		if (worker && worker->current_pwq->wq == wq) {
-				pwq = per_cpu_ptr(wq->cpu_pwqs, last_pool->cpu);
+			pwq = worker->current_pwq;
 		} else {
 			/* meh... not running there, queue here */
 			spin_unlock(&last_pool->lock);
@@ -1261,10 +1261,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	} else {
 		spin_lock(&pwq->pool->lock);
 	}
-	} else {
-		pwq = first_pwq(wq);
-		spin_lock(&pwq->pool->lock);
-	}
 
 	/* pwq determined, queue */
 	trace_workqueue_queue_work(req_cpu, pwq, work);