Merge branch 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue changes from Tejun Heo:
 "There are three major changes.

   - WQ_HIGHPRI has been reimplemented so that high priority work items
     are served by worker threads with -20 nice value from dedicated
     highpri worker pools.

   - CPU hotplug support has been reimplemented such that idle workers
     are kept across CPU hotplug events.  This makes CPU hotplug cheaper
     (for PM) and makes the code simpler.

   - flush_kthread_work() has been reimplemented so that a work item can
     be freed while executing.  This removes an annoying behavior
     difference between kthread_worker and workqueue."

* 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: fix spurious CPU locality WARN from process_one_work()
  kthread_worker: reimplement flush_kthread_work() to allow freeing the work item being executed
  kthread_worker: reorganize to prepare for flush_kthread_work() reimplementation
  workqueue: simplify CPU hotplug code
  workqueue: remove CPU offline trustee
  workqueue: don't butcher idle workers on an offline CPU
  workqueue: reimplement CPU online rebinding to handle idle workers
  workqueue: drop @bind from create_worker()
  workqueue: use mutex for global_cwq manager exclusion
  workqueue: ROGUE workers are UNBOUND workers
  workqueue: drop CPU_DYING notifier operation
  workqueue: perform cpu down operations from low priority cpu_notifier()
  workqueue: reimplement WQ_HIGHPRI using a separate worker_pool
  workqueue: introduce NR_WORKER_POOLS and for_each_worker_pool()
  workqueue: separate out worker_pool flags
  workqueue: use @pool instead of @gcwq or @cpu where applicable
  workqueue: factor out worker_pool from global_cwq
  workqueue: don't use WQ_HIGHPRI for unbound workqueues

Documentation/workqueue.txt

@@ -89,25 +89,28 @@ called thread-pools.
 
 The cmwq design differentiates between the user-facing workqueues that
 subsystems and drivers queue work items on and the backend mechanism
-which manages thread-pool and processes the queued work items.
+which manages thread-pools and processes the queued work items.
 
 The backend is called gcwq.  There is one gcwq for each possible CPU
-and one gcwq to serve work items queued on unbound workqueues.
+and one gcwq to serve work items queued on unbound workqueues.  Each
+gcwq has two thread-pools - one for normal work items and the other
+for high priority ones.
 
 Subsystems and drivers can create and queue work items through special
 workqueue API functions as they see fit. They can influence some
 aspects of the way the work items are executed by setting flags on the
 workqueue they are putting the work item on. These flags include
-things like CPU locality, reentrancy, concurrency limits and more. To
-get a detailed overview refer to the API description of
+things like CPU locality, reentrancy, concurrency limits, priority and
+more.  To get a detailed overview refer to the API description of
 alloc_workqueue() below.
 
-When a work item is queued to a workqueue, the target gcwq is
-determined according to the queue parameters and workqueue attributes
-and appended on the shared worklist of the gcwq.  For example, unless
-specifically overridden, a work item of a bound workqueue will be
-queued on the worklist of exactly that gcwq that is associated to the
-CPU the issuer is running on.
+When a work item is queued to a workqueue, the target gcwq and
+thread-pool is determined according to the queue parameters and
+workqueue attributes and appended on the shared worklist of the
+thread-pool.  For example, unless specifically overridden, a work item
+of a bound workqueue will be queued on the worklist of either normal
+or highpri thread-pool of the gcwq that is associated to the CPU the
+issuer is running on.
 
 For any worker pool implementation, managing the concurrency level
 (how many execution contexts are active) is an important issue.  cmwq
@@ -115,26 +118,26 @@ tries to keep the concurrency at a minimal but sufficient level.
 Minimal to save resources and sufficient in that the system is used at
 its full capacity.
 
-Each gcwq bound to an actual CPU implements concurrency management by
-hooking into the scheduler.  The gcwq is notified whenever an active
-worker wakes up or sleeps and keeps track of the number of the
-currently runnable workers.  Generally, work items are not expected to
-hog a CPU and consume many cycles.  That means maintaining just enough
-concurrency to prevent work processing from stalling should be
-optimal.  As long as there are one or more runnable workers on the
-CPU, the gcwq doesn't start execution of a new work, but, when the
-last running worker goes to sleep, it immediately schedules a new
-worker so that the CPU doesn't sit idle while there are pending work
-items.  This allows using a minimal number of workers without losing
-execution bandwidth.
+Each thread-pool bound to an actual CPU implements concurrency
+management by hooking into the scheduler.  The thread-pool is notified
+whenever an active worker wakes up or sleeps and keeps track of the
+number of the currently runnable workers.  Generally, work items are
+not expected to hog a CPU and consume many cycles.  That means
+maintaining just enough concurrency to prevent work processing from
+stalling should be optimal.  As long as there are one or more runnable
+workers on the CPU, the thread-pool doesn't start execution of a new
+work, but, when the last running worker goes to sleep, it immediately
+schedules a new worker so that the CPU doesn't sit idle while there
+are pending work items.  This allows using a minimal number of workers
+without losing execution bandwidth.
 
 Keeping idle workers around doesn't cost other than the memory space
 for kthreads, so cmwq holds onto idle ones for a while before killing
 them.
 
 For an unbound wq, the above concurrency management doesn't apply and
-the gcwq for the pseudo unbound CPU tries to start executing all work
-items as soon as possible.  The responsibility of regulating
+the thread-pools for the pseudo unbound CPU try to start executing all
+work items as soon as possible.  The responsibility of regulating
 concurrency level is on the users.  There is also a flag to mark a
 bound wq to ignore the concurrency management.  Please refer to the
 API section for details.
@@ -205,31 +208,22 @@ resources, scheduled and executed.
 
   WQ_HIGHPRI
 
-	Work items of a highpri wq are queued at the head of the
-	worklist of the target gcwq and start execution regardless of
-	the current concurrency level.  In other words, highpri work
-	items will always start execution as soon as execution
-	resource is available.
+	Work items of a highpri wq are queued to the highpri
+	thread-pool of the target gcwq.  Highpri thread-pools are
+	served by worker threads with elevated nice level.
 
-	Ordering among highpri work items is preserved - a highpri
-	work item queued after another highpri work item will start
-	execution after the earlier highpri work item starts.
-
-	Although highpri work items are not held back by other
-	runnable work items, they still contribute to the concurrency
-	level.  Highpri work items in runnable state will prevent
-	non-highpri work items from starting execution.
-
-	This flag is meaningless for unbound wq.
+	Note that normal and highpri thread-pools don't interact with
+	each other.  Each maintain its separate pool of workers and
+	implements concurrency management among its workers.
 
   WQ_CPU_INTENSIVE
 
 	Work items of a CPU intensive wq do not contribute to the
 	concurrency level.  In other words, runnable CPU intensive
-	work items will not prevent other work items from starting
-	execution.  This is useful for bound work items which are
-	expected to hog CPU cycles so that their execution is
-	regulated by the system scheduler.
+	work items will not prevent other work items in the same
+	thread-pool from starting execution.  This is useful for bound
+	work items which are expected to hog CPU cycles so that their
+	execution is regulated by the system scheduler.
 
 	Although CPU intensive work items don't contribute to the
 	concurrency level, start of their executions is still
@@ -239,14 +233,6 @@ resources, scheduled and executed.
 
 	This flag is meaningless for unbound wq.
 
-  WQ_HIGHPRI | WQ_CPU_INTENSIVE
-
-	This combination makes the wq avoid interaction with
-	concurrency management completely and behave as a simple
-	per-CPU execution context provider.  Work items queued on a
-	highpri CPU-intensive wq start execution as soon as resources
-	are available and don't affect execution of other work items.
-
 @max_active:
 
 @max_active determines the maximum number of execution contexts per
@@ -328,20 +314,7 @@ If @max_active == 2,
  35		w2 wakes up and finishes
 
 Now, let's assume w1 and w2 are queued to a different wq q1 which has
-WQ_HIGHPRI set,
-
- TIME IN MSECS	EVENT
- 0		w1 and w2 start and burn CPU
- 5		w1 sleeps
- 10		w2 sleeps
- 10		w0 starts and burns CPU
- 15		w0 sleeps
- 15		w1 wakes up and finishes
- 20		w2 wakes up and finishes
- 25		w0 wakes up and burns CPU
- 30		w0 finishes
-
-If q1 has WQ_CPU_INTENSIVE set,
+WQ_CPU_INTENSIVE set,
 
  TIME IN MSECS	EVENT
  0		w0 starts and burns CPU

include/linux/cpu.h

@@ -73,8 +73,9 @@ enum {
 	/* migration should happen before other stuff but after perf */
 	CPU_PRI_PERF		= 20,
 	CPU_PRI_MIGRATION	= 10,
-	/* prepare workqueues for other notifiers */
-	CPU_PRI_WORKQUEUE	= 5,
+	/* bring up workqueues before normal notifiers and down after */
+	CPU_PRI_WORKQUEUE_UP	= 5,
+	CPU_PRI_WORKQUEUE_DOWN	= -5,
 };
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */

include/linux/kthread.h

@@ -49,8 +49,6 @@ extern int tsk_fork_get_node(struct task_struct *tsk);
  * can be queued and flushed using queue/flush_kthread_work()
  * respectively.  Queued kthread_works are processed by a kthread
  * running kthread_worker_fn().
- *
- * A kthread_work can't be freed while it is executing.
  */
 struct kthread_work;
 typedef void (*kthread_work_func_t)(struct kthread_work *work);
@@ -59,15 +57,14 @@ struct kthread_worker {
 	spinlock_t		lock;
 	struct list_head	work_list;
 	struct task_struct	*task;
+	struct kthread_work	*current_work;
 };
 
 struct kthread_work {
 	struct list_head	node;
 	kthread_work_func_t	func;
 	wait_queue_head_t	done;
-	atomic_t		flushing;
-	int			queue_seq;
-	int			done_seq;
+	struct kthread_worker	*worker;
 };
 
 #define KTHREAD_WORKER_INIT(worker)	{				\
@@ -79,7 +76,6 @@ struct kthread_work {
 	.node = LIST_HEAD_INIT((work).node),				\
 	.func = (fn),							\
 	.done = __WAIT_QUEUE_HEAD_INITIALIZER((work).done),		\
-	.flushing = ATOMIC_INIT(0),					\
 	}
 
 #define DEFINE_KTHREAD_WORKER(worker)					\

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",

kernel/kthread.c

@@ -360,16 +360,12 @@ repeat:
 					struct kthread_work, node);
 		list_del_init(&work->node);
 	}
+	worker->current_work = work;
 	spin_unlock_irq(&worker->lock);
 
 	if (work) {
 		__set_current_state(TASK_RUNNING);
 		work->func(work);
-		smp_wmb();	/* wmb worker-b0 paired with flush-b1 */
-		work->done_seq = work->queue_seq;
-		smp_mb();	/* mb worker-b1 paired with flush-b0 */
-		if (atomic_read(&work->flushing))
-			wake_up_all(&work->done);
 	} else if (!freezing(current))
 		schedule();
 
@@ -378,6 +374,19 @@ repeat:
 }
 EXPORT_SYMBOL_GPL(kthread_worker_fn);
 
+/* insert @work before @pos in @worker */
+static void insert_kthread_work(struct kthread_worker *worker,
+			       struct kthread_work *work,
+			       struct list_head *pos)
+{
+	lockdep_assert_held(&worker->lock);
+
+	list_add_tail(&work->node, pos);
+	work->worker = worker;
+	if (likely(worker->task))
+		wake_up_process(worker->task);
+}
+
 /**
  * queue_kthread_work - queue a kthread_work
  * @worker: target kthread_worker
@@ -395,10 +404,7 @@ bool queue_kthread_work(struct kthread_worker *worker,
 
 	spin_lock_irqsave(&worker->lock, flags);
 	if (list_empty(&work->node)) {
-		list_add_tail(&work->node, &worker->work_list);
-		work->queue_seq++;
-		if (likely(worker->task))
-			wake_up_process(worker->task);
+		insert_kthread_work(worker, work, &worker->work_list);
 		ret = true;
 	}
 	spin_unlock_irqrestore(&worker->lock, flags);
@@ -406,6 +412,18 @@ bool queue_kthread_work(struct kthread_worker *worker,
 }
 EXPORT_SYMBOL_GPL(queue_kthread_work);
 
+struct kthread_flush_work {
+	struct kthread_work	work;
+	struct completion	done;
+};
+
+static void kthread_flush_work_fn(struct kthread_work *work)
+{
+	struct kthread_flush_work *fwork =
+		container_of(work, struct kthread_flush_work, work);
+	complete(&fwork->done);
+}
+
 /**
  * flush_kthread_work - flush a kthread_work
  * @work: work to flush
@@ -414,39 +432,37 @@ EXPORT_SYMBOL_GPL(queue_kthread_work);
  */
 void flush_kthread_work(struct kthread_work *work)
 {
-	int seq = work->queue_seq;
-
-	atomic_inc(&work->flushing);
+	struct kthread_flush_work fwork = {
+		KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
+		COMPLETION_INITIALIZER_ONSTACK(fwork.done),
+	};
+	struct kthread_worker *worker;
+	bool noop = false;
 
-	/*
-	 * mb flush-b0 paired with worker-b1, to make sure either
-	 * worker sees the above increment or we see done_seq update.
-	 */
-	smp_mb__after_atomic_inc();
+retry:
+	worker = work->worker;
+	if (!worker)
+		return;
 
-	/* A - B <= 0 tests whether B is in front of A regardless of overflow */
-	wait_event(work->done, seq - work->done_seq <= 0);
-	atomic_dec(&work->flushing);
+	spin_lock_irq(&worker->lock);
+	if (work->worker != worker) {
+		spin_unlock_irq(&worker->lock);
+		goto retry;
+	}
 
-	/*
-	 * rmb flush-b1 paired with worker-b0, to make sure our caller
-	 * sees every change made by work->func().
-	 */
-	smp_mb__after_atomic_dec();
-}
-EXPORT_SYMBOL_GPL(flush_kthread_work);
+	if (!list_empty(&work->node))
+		insert_kthread_work(worker, &fwork.work, work->node.next);
+	else if (worker->current_work == work)
+		insert_kthread_work(worker, &fwork.work, worker->work_list.next);
+	else
+		noop = true;
 
-struct kthread_flush_work {
-	struct kthread_work	work;
-	struct completion	done;
-};
+	spin_unlock_irq(&worker->lock);
 
-static void kthread_flush_work_fn(struct kthread_work *work)
-{
-	struct kthread_flush_work *fwork =
-		container_of(work, struct kthread_flush_work, work);
-	complete(&fwork->done);
+	if (!noop)
+		wait_for_completion(&fwork.done);
 }
+EXPORT_SYMBOL_GPL(flush_kthread_work);
 
 /**
  * flush_kthread_worker - flush all current works on a kthread_worker