Move worklist and all worker management fields from global_cwq into
the new struct worker_pool.  worker_pool points back to the containing
gcwq.  worker and cpu_workqueue_struct are updated to point to
worker_pool instead of gcwq too.

This change is mechanical and doesn't introduce any functional
difference other than rearranging of fields and an added level of
indirection in some places.  This is to prepare for multiple pools per
gcwq.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/trace/events/workqueue.h |    2 +-
 kernel/workqueue.c               |  216 ++++++++++++++++++++-----------------
 2 files changed, 118 insertions(+), 100 deletions(-)

diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 4018f50..f28d1b6 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h

@@ -54,7 +54,7 @@ TRACE_EVENT(workqueue_queue_work,
 		__entry->function	= work->func;
 		__entry->workqueue	= cwq->wq;
 		__entry->req_cpu	= req_cpu;
-		__entry->cpu		= cwq->gcwq->cpu;
+		__entry->cpu		= cwq->pool->gcwq->cpu;
 	),
 
 	TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u",

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 27637c2..bc43a0c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c

@@ -115,6 +115,7 @@ enum {
  */
 
 struct global_cwq;
+struct worker_pool;
 
 /*
  * The poor guys doing the actual heavy lifting.  All on-duty workers

@@ -131,7 +132,7 @@ struct worker {
 	struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */
 	struct list_head	scheduled;	/* L: scheduled works */
 	struct task_struct	*task;		/* I: worker task */
-	struct global_cwq	*gcwq;		/* I: the associated gcwq */
+	struct worker_pool	*pool;		/* I: the associated pool */
 	/* 64 bytes boundary on 64bit, 32 on 32bit */
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */

@@ -139,6 +140,21 @@ struct worker {
 	struct work_struct	rebind_work;	/* L: rebind worker to cpu */
 };
 
+struct worker_pool {
+	struct global_cwq	*gcwq;		/* I: the owning gcwq */
+
+	struct list_head	worklist;	/* L: list of pending works */
+	int			nr_workers;	/* L: total number of workers */
+	int			nr_idle;	/* L: currently idle ones */
+
+	struct list_head	idle_list;	/* X: list of idle workers */
+	struct timer_list	idle_timer;	/* L: worker idle timeout */
+	struct timer_list	mayday_timer;	/* L: SOS timer for dworkers */

+
+	struct ida		worker_ida;	/* L: for worker IDs */
+	struct worker		*first_idle;	/* L: first idle worker */
+};
+
 /*
  * Global per-cpu workqueue.  There's one and only one for each cpu
  * and all works are queued and processed here regardless of their

@@ -146,27 +162,18 @@ struct worker {
  */
 struct global_cwq {
 	spinlock_t		lock;		/* the gcwq lock */
-	struct list_head	worklist;	/* L: list of pending works */
 	unsigned int		cpu;		/* I: the associated cpu */
 	unsigned int		flags;		/* L: GCWQ_* flags */
 
-	int			nr_workers;	/* L: total number of workers */
-	int			nr_idle;	/* L: currently idle ones */
-
-	/* workers are chained either in the idle_list or busy_hash */
-	struct list_head	idle_list;	/* X: list of idle workers */
+	/* workers are chained either in busy_head or pool idle_list */