Merge remote branch 'workqueues/for-next'

3 files changed, 275 insertions, 114 deletions

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 25e02c941bac..e33ff4a91703 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -306,6 +306,24 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
 	__alloc_workqueue_key((name), (flags), (max_active), NULL, NULL)
 #endif
 
+/**
+ * alloc_ordered_workqueue - allocate an ordered workqueue
+ * @name: name of the workqueue
+ * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful)
+ *
+ * Allocate an ordered workqueue.  An ordered workqueue executes at
+ * most one work item at any given time in the queued order.  They are
+ * implemented as unbound workqueues with @max_active of one.
+ *
+ * RETURNS:
+ * Pointer to the allocated workqueue on success, %NULL on failure.
+ */
+static inline struct workqueue_struct *
+alloc_ordered_workqueue(const char *name, unsigned int flags)
+{
+	return alloc_workqueue(name, WQ_UNBOUND | flags, 1);
+}
+
 #define create_workqueue(name)					\
 	alloc_workqueue((name), WQ_RESCUER, 1)
 #define create_freezeable_workqueue(name)			\
@@ -325,7 +343,6 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 
 extern void flush_workqueue(struct workqueue_struct *wq);
 extern void flush_scheduled_work(void);
-extern void flush_delayed_work(struct delayed_work *work);
 
 extern int schedule_work(struct work_struct *work);
 extern int schedule_work_on(int cpu, struct work_struct *work);
@@ -337,8 +354,13 @@ extern int keventd_up(void);
 
 int execute_in_process_context(work_func_t fn, struct execute_work *);
 
-extern int flush_work(struct work_struct *work);
-extern int cancel_work_sync(struct work_struct *work);
+extern bool flush_work(struct work_struct *work);
+extern bool flush_work_sync(struct work_struct *work);
+extern bool cancel_work_sync(struct work_struct *work);
+
+extern bool flush_delayed_work(struct delayed_work *dwork);
+extern bool flush_delayed_work_sync(struct delayed_work *work);
+extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
@@ -352,9 +374,9 @@ extern unsigned int work_busy(struct work_struct *work);
  * it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or
  * cancel_work_sync() to wait on it.
  */
-static inline int cancel_delayed_work(struct delayed_work *work)
+static inline bool cancel_delayed_work(struct delayed_work *work)
 {
-	int ret;
+	bool ret;
 
 	ret = del_timer_sync(&work->timer);
 	if (ret)
@@ -367,9 +389,9 @@ static inline int cancel_delayed_work(struct delayed_work *work)
  * if it returns 0 the timer function may be running and the queueing is in
  * progress.
  */
-static inline int __cancel_delayed_work(struct delayed_work *work)
+static inline bool __cancel_delayed_work(struct delayed_work *work)
 {
-	int ret;
+	bool ret;
 
 	ret = del_timer(&work->timer);
 	if (ret)
@@ -377,8 +399,6 @@ static inline int __cancel_delayed_work(struct delayed_work *work)
 	return ret;
 }
 
-extern int cancel_delayed_work_sync(struct delayed_work *work);
-
 /* Obsolete. use cancel_delayed_work_sync() */
 static inline
 void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq,
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 49682d7e9d60..7d497291c85d 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -7,38 +7,83 @@
 #include <linux/tracepoint.h>
 #include <linux/workqueue.h>
 
+DECLARE_EVENT_CLASS(workqueue_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+	),
+
+	TP_printk("work struct %p", __entry->work)
+);
+
 /**
- * workqueue_execute_start - called immediately before the workqueue callback
+ * workqueue_queue_work - called when a work gets queued
+ * @req_cpu:	the requested cpu
+ * @cwq:	pointer to struct cpu_workqueue_struct
  * @work:	pointer to struct work_struct
  *
- * Allows to track workqueue execution.
+ * This event occurs when a work is queued immediately or once a
+ * delayed work is actually queued on a workqueue (ie: once the delay
+ * has been reached).
  */
-TRACE_EVENT(workqueue_execute_start,
+TRACE_EVENT(workqueue_queue_work,
 
-	TP_PROTO(struct work_struct *work),
+	TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq,
+		 struct work_struct *work),
 
-	TP_ARGS(work),
+	TP_ARGS(req_cpu, cwq, work),
 
 	TP_STRUCT__entry(
 		__field( void *,	work	)
 		__field( void *,	function)
+		__field( void *,	workqueue)
+		__field( unsigned int,	req_cpu	)
+		__field( unsigned int,	cpu	)
 	),
 
 	TP_fast_assign(
 		__entry->work		= work;
 		__entry->function	= work->func;
+		__entry->workqueue	= cwq->wq;
+		__entry->req_cpu	= req_cpu;
+		__entry->cpu		= cwq->gcwq->cpu;
 	),
 
-	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
+	TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u",
+		  __entry->work, __entry->function, __entry->workqueue,
+		  __entry->req_cpu, __entry->cpu)
 );
 
 /**
- * workqueue_execute_end - called immediately before the workqueue callback
+ * workqueue_activate_work - called when a work gets activated
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a queued work is put on the active queue,
+ * which happens immediately after queueing unless @max_active limit
+ * is reached.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_activate_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
+);
+
+/**
+ * workqueue_execute_start - called immediately before the workqueue callback
  * @work:	pointer to struct work_struct
  *
  * Allows to track workqueue execution.
  */
-TRACE_EVENT(workqueue_execute_end,
+TRACE_EVENT(workqueue_execute_start,
 
 	TP_PROTO(struct work_struct *work),
 
@@ -46,15 +91,29 @@ TRACE_EVENT(workqueue_execute_end,
 
 	TP_STRUCT__entry(
 		__field( void *,	work	)
+		__field( void *,	function)
 	),
 
 	TP_fast_assign(
 		__entry->work		= work;
+		__entry->function	= work->func;
 	),
 
-	TP_printk("work struct %p", __entry->work)
+	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
 );
 
+/**
+ * workqueue_execute_end - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_execute_end,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
+);
 
 #endif /*  _TRACE_WORKQUEUE_H */
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f77afd939229..cb2ccfbed0c6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -42,9 +42,6 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
-
 #include "workqueue_sched.h"
 
 enum {
@@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #define for_each_busy_worker(worker, i, pos, gcwq)			\
 	for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)			\
 		hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
@@ -997,6 +997,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 
 	/* gcwq determined, get cwq and queue */
 	cwq = get_cwq(gcwq->cpu, wq);
+	trace_workqueue_queue_work(cpu, cwq, work);
 
 	BUG_ON(!list_empty(&work->entry));
 
@@ -1004,6 +1005,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 	work_flags = work_color_to_flags(cwq->work_color);
 
 	if (likely(cwq->nr_active < cwq->max_active)) {
+		trace_workqueue_activate_work(work);
 		cwq->nr_active++;
 		worklist = gcwq_determine_ins_pos(gcwq, cwq);
 	} else {
@@ -1679,6 +1681,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
 						    struct work_struct, entry);
 	struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
 
+	trace_workqueue_activate_work(work);
 	move_linked_works(work, pos, NULL);
 	__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
 	cwq->nr_active++;
@@ -2326,27 +2329,17 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
-/**
- * flush_work - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns false if @work has already terminated.
- *
- * It is expected that, prior to calling flush_work(), the caller has
- * arranged for the work to not be requeued, otherwise it doesn't make
- * sense to use this function.
- */
-int flush_work(struct work_struct *work)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+			     bool wait_executing)
 {
 	struct worker *worker = NULL;
 	struct global_cwq *gcwq;
 	struct cpu_workqueue_struct *cwq;
-	struct wq_barrier barr;
 
 	might_sleep();
 	gcwq = get_work_gcwq(work);
 	if (!gcwq)
-		return 0;
+		return false;
 
 	spin_lock_irq(&gcwq->lock);
 	if (!list_empty(&work->entry)) {
@@ -2359,28 +2352,127 @@ int flush_work(struct work_struct *work)
 		cwq = get_work_cwq(work);
 		if (unlikely(!cwq || gcwq != cwq->gcwq))
 			goto already_gone;
-	} else {
+	} else if (wait_executing) {
 		worker = find_worker_executing_work(gcwq, work);
 		if (!worker)
 			goto already_gone;
 		cwq = worker->current_cwq;
-	}
+	} else
+		goto already_gone;
 
-	insert_wq_barrier(cwq, &barr, work, worker);
+	insert_wq_barrier(cwq, barr, work, worker);
 	spin_unlock_irq(&gcwq->lock);
 
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
-
-	wait_for_completion(&barr.done);
-	destroy_work_on_stack(&barr.work);
-	return 1;
+	return true;
 already_gone:
 	spin_unlock_irq(&gcwq->lock);
-	return 0;
+	return false;
+}
+
+/**
+ * flush_work - wait for a work to finish executing the last queueing instance
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  This function considers
+ * only the last queueing instance of @work.  If @work has been
+ * enqueued across different CPUs on a non-reentrant workqueue or on
+ * multiple workqueues, @work might still be executing on return on
+ * some of the CPUs from earlier queueing.
+ *
+ * If @work was queued only on a non-reentrant, ordered or unbound
+ * workqueue, @work is guaranteed to be idle on return if it hasn't
+ * been requeued since flush started.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work(struct work_struct *work)
+{
+	struct wq_barrier barr;
+
+	if (start_flush_work(work, &barr, true)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else
+		return false;
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
+static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
+{
+	struct wq_barrier barr;
+	struct worker *worker;
+
+	spin_lock_irq(&gcwq->lock);
+
+	worker = find_worker_executing_work(gcwq, work);
+	if (unlikely(worker))
+		insert_wq_barrier(worker->current_cwq, &barr, work, worker);
+
+	spin_unlock_irq(&gcwq->lock);
+
+	if (unlikely(worker)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else
+		return false;
+}
+
+static bool wait_on_work(struct work_struct *work)
+{
+	bool ret = false;
+	int cpu;
+
+	might_sleep();
+
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
+
+	for_each_gcwq_cpu(cpu)
+		ret |= wait_on_cpu_work(get_gcwq(cpu), work);
+	return ret;
+}
+
+/**
+ * flush_work_sync - wait until a work has finished execution
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  On return, it's
+ * guaranteed that all queueing instances of @work which happened
+ * before this function is called are finished.  In other words, if
+ * @work hasn't been requeued since this function was called, @work is
+ * guaranteed to be idle on return.
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work_sync(struct work_struct *work)
+{
+	struct wq_barrier barr;
+	bool pending, waited;
+
+	/* we'll wait for executions separately, queue barr only if pending */
+	pending = start_flush_work(work, &barr, false);
+
+	/* wait for executions to finish */
+	waited = wait_on_work(work);
+
+	/* wait for the pending one */
+	if (pending) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+	}
+
+	return pending || waited;
+}
+EXPORT_SYMBOL_GPL(flush_work_sync);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.
@@ -2423,39 +2515,7 @@ static int try_to_grab_pending(struct work_struct *work)
 	return ret;
 }
 
-static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
-{
-	struct wq_barrier barr;
-	struct worker *worker;
-
-	spin_lock_irq(&gcwq->lock);
-
-	worker = find_worker_executing_work(gcwq, work);
-	if (unlikely(worker))
-		insert_wq_barrier(worker->current_cwq, &barr, work, worker);
-
-	spin_unlock_irq(&gcwq->lock);
-
-	if (unlikely(worker)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-	}
-}
-
-static void wait_on_work(struct work_struct *work)
-{
-	int cpu;
-
-	might_sleep();
-
-	lock_map_acquire(&work->lockdep_map);
-	lock_map_release(&work->lockdep_map);
-
-	for_each_gcwq_cpu(cpu)
-		wait_on_cpu_work(get_gcwq(cpu), work);
-}
-
-static int __cancel_work_timer(struct work_struct *work,
+static bool __cancel_work_timer(struct work_struct *work,
 				struct timer_list* timer)
 {
 	int ret;
@@ -2472,42 +2532,81 @@ static int __cancel_work_timer(struct work_struct *work,
 }
 
 /**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
  *
- * Returns true if @work was pending.
+ * Cancel @work and wait for its execution to finish.  This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue.  On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
  *
- * cancel_work_sync() will cancel the work if it is queued. If the work's
- * callback appears to be running, cancel_work_sync() will block until it
- * has completed.
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's.  Use cancel_delayed_work_sync() instead.
  *
- * It is possible to use this function if the work re-queues itself. It can
- * cancel the work even if it migrates to another workqueue, however in that
- * case it only guarantees that work->func() has completed on the last queued
- * workqueue.
- *
- * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
- * pending, otherwise it goes into a busy-wait loop until the timer expires.
- *
- * The caller must ensure that workqueue_struct on which this work was last
+ * The caller must ensure that the workqueue on which @work was last
  * queued can't be destroyed before this function returns.
+ *
+ * RETURNS:
+ * %true if @work was pending, %false otherwise.
  */
-int cancel_work_sync(struct work_struct *work)
+bool cancel_work_sync(struct work_struct *work)
 {
 	return __cancel_work_timer(work, NULL);
 }
 EXPORT_SYMBOL_GPL(cancel_work_sync);
 
 /**
- * cancel_delayed_work_sync - reliably kill off a delayed work.
- * @dwork: the delayed work struct
+ * flush_delayed_work - wait for a dwork to finish executing the last queueing
+ * @dwork: the delayed work to flush
  *
- * Returns true if @dwork was pending.
+ * Delayed timer is cancelled and the pending work is queued for
+ * immediate execution.  Like flush_work(), this function only
+ * considers the last queueing instance of @dwork.
  *
- * It is possible to use this function if @dwork rearms itself via queue_work()
- * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
  */
-int cancel_delayed_work_sync(struct delayed_work *dwork)
+bool flush_delayed_work(struct delayed_work *dwork)
+{
+	if (del_timer_sync(&dwork->timer))
+		__queue_work(raw_smp_processor_id(),
+			     get_work_cwq(&dwork->work)->wq, &dwork->work);
+	return flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
+ * flush_delayed_work_sync - wait for a dwork to finish
+ * @dwork: the delayed work to flush
+ *
+ * Delayed timer is cancelled and the pending work is queued for
+ * execution immediately.  Other than timer handling, its behavior
+ * is identical to flush_work_sync().
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_delayed_work_sync(struct delayed_work *dwork)
+{
+	if (del_timer_sync(&dwork->timer))
+		__queue_work(raw_smp_processor_id(),
+			     get_work_cwq(&dwork->work)->wq, &dwork->work);
+	return flush_work_sync(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work_sync);
+
+/**
+ * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
+ * @dwork: the delayed work cancel
+ *
+ * This is cancel_work_sync() for delayed works.
+ *
+ * RETURNS:
+ * %true if @dwork was pending, %false otherwise.
+ */
+bool cancel_delayed_work_sync(struct delayed_work *dwork)
 {
 	return __cancel_work_timer(&dwork->work, &dwork->timer);
 }
@@ -2559,23 +2658,6 @@ int schedule_delayed_work(struct delayed_work *dwork,
 EXPORT_SYMBOL(schedule_delayed_work);
 
 /**
- * flush_delayed_work - block until a dwork_struct's callback has terminated
- * @dwork: the delayed work which is to be flushed
- *
- * Any timeout is cancelled, and any pending work is run immediately.
- */
-void flush_delayed_work(struct delayed_work *dwork)
-{
-	if (del_timer_sync(&dwork->timer)) {
-		__queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
-			     &dwork->work);
-		put_cpu();
-	}
-	flush_work(&dwork->work);
-}
-EXPORT_SYMBOL(flush_delayed_work);
-
-/**
  * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
  * @cpu: cpu to use
  * @dwork: job to be done