workqueue: Remove the cacheline_aligned for nr_running

nr_running is never modified remotely after the schedule callback in
wakeup path is removed.

Rather nr_running is often accessed with other fields in the pool
together, so the cacheline_aligned for nr_running isn't needed.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/workqueue.c

@@ -154,6 +154,9 @@ struct worker_pool {
 
 	unsigned long		watchdog_ts;	/* L: watchdog timestamp */
 
+	/* The current concurrency level. */
+	atomic_t		nr_running;
+
 	struct list_head	worklist;	/* L: list of pending works */
 
 	int			nr_workers;	/* L: total number of workers */
@@ -177,19 +180,12 @@ struct worker_pool {
 	struct hlist_node	hash_node;	/* PL: unbound_pool_hash node */
 	int			refcnt;		/* PL: refcnt for unbound pools */
 
-	/*
-	 * The current concurrency level.  As it's likely to be accessed
-	 * from other CPUs during try_to_wake_up(), put it in a separate
-	 * cacheline.
-	 */
-	atomic_t		nr_running ____cacheline_aligned_in_smp;
-
 	/*
 	 * Destruction of pool is RCU protected to allow dereferences
 	 * from get_work_pool().
 	 */
 	struct rcu_head		rcu;
-} ____cacheline_aligned_in_smp;
+};
 
 /*
  * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS