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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (55 commits)
  workqueue: mark init_workqueues() as early_initcall()
  workqueue: explain for_each_*cwq_cpu() iterators
  fscache: fix build on !CONFIG_SYSCTL
  slow-work: kill it
  gfs2: use workqueue instead of slow-work
  drm: use workqueue instead of slow-work
  cifs: use workqueue instead of slow-work
  fscache: drop references to slow-work
  fscache: convert operation to use workqueue instead of slow-work
  fscache: convert object to use workqueue instead of slow-work
  workqueue: fix how cpu number is stored in work->data
  workqueue: fix mayday_mask handling on UP
  workqueue: fix build problem on !CONFIG_SMP
  workqueue: fix locking in retry path of maybe_create_worker()
  async: use workqueue for worker pool
  workqueue: remove WQ_SINGLE_CPU and use WQ_UNBOUND instead
  workqueue: implement unbound workqueue
  workqueue: prepare for WQ_UNBOUND implementation
  libata: take advantage of cmwq and remove concurrency limitations
  workqueue: fix worker management invocation without pending works
  ...

Fixed up conflicts in fs/cifs/* as per Tejun. Other trivial conflicts in
include/linux/workqueue.h, kernel/trace/Kconfig and kernel/workqueue.c

8 files changed, 215 insertions, 312 deletions

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 93a1a31b9c2..c707270bff5 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -31,7 +31,6 @@
 #include <linux/idr.h>
 
 #include <linux/fb.h>
-#include <linux/slow-work.h>
 
 struct drm_device;
 struct drm_mode_set;
@@ -595,7 +594,7 @@ struct drm_mode_config {
 
 	/* output poll support */
 	bool poll_enabled;
-	struct delayed_slow_work output_poll_slow_work;
+	struct delayed_work output_poll_work;
 
 	/* pointers to standard properties */
 	struct list_head property_blob_list;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index de6b1722cdc..4823af64e9d 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -71,6 +71,8 @@ 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,
 };
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index c57db27ac86..b8581c09d19 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -20,7 +20,7 @@
 
 #include <linux/fscache.h>
 #include <linux/sched.h>
-#include <linux/slow-work.h>
+#include <linux/workqueue.h>
 
 #define NR_MAXCACHES BITS_PER_LONG
 
@@ -76,18 +76,14 @@ typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
 typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
 
 struct fscache_operation {
-	union {
-		struct work_struct fast_work;	/* record for fast ops */
-		struct slow_work slow_work;	/* record for (very) slow ops */
-	};
+	struct work_struct	work;		/* record for async ops */
 	struct list_head	pend_link;	/* link in object->pending_ops */
 	struct fscache_object	*object;	/* object to be operated upon */
 
 	unsigned long		flags;
 #define FSCACHE_OP_TYPE		0x000f	/* operation type */
-#define FSCACHE_OP_FAST		0x0001	/* - fast op, processor may not sleep for disk */
-#define FSCACHE_OP_SLOW		0x0002	/* - (very) slow op, processor may sleep for disk */
-#define FSCACHE_OP_MYTHREAD	0x0003	/* - processing is done be issuing thread, not pool */
+#define FSCACHE_OP_ASYNC	0x0001	/* - async op, processor may sleep for disk */
+#define FSCACHE_OP_MYTHREAD	0x0002	/* - processing is done be issuing thread, not pool */
 #define FSCACHE_OP_WAITING	4	/* cleared when op is woken */
 #define FSCACHE_OP_EXCLUSIVE	5	/* exclusive op, other ops must wait */
 #define FSCACHE_OP_DEAD		6	/* op is now dead */
@@ -105,7 +101,8 @@ struct fscache_operation {
 	/* operation releaser */
 	fscache_operation_release_t release;
 
-#ifdef CONFIG_SLOW_WORK_DEBUG
+#ifdef CONFIG_WORKQUEUE_DEBUGFS
+	struct work_struct put_work;	/* work to delay operation put */
 	const char *name;		/* operation name */
 	const char *state;		/* operation state */
 #define fscache_set_op_name(OP, N)	do { (OP)->name  = (N); } while(0)
@@ -117,7 +114,7 @@ struct fscache_operation {
 };
 
 extern atomic_t fscache_op_debug_id;
-extern const struct slow_work_ops fscache_op_slow_work_ops;
+extern void fscache_op_work_func(struct work_struct *work);
 
 extern void fscache_enqueue_operation(struct fscache_operation *);
 extern void fscache_put_operation(struct fscache_operation *);
@@ -128,33 +125,21 @@ extern void fscache_put_operation(struct fscache_operation *);
  * @release: The release function to assign
  *
  * Do basic initialisation of an operation.  The caller must still set flags,
- * object, either fast_work or slow_work if necessary, and processor if needed.
+ * object and processor if needed.
  */
 static inline void fscache_operation_init(struct fscache_operation *op,
-					  fscache_operation_release_t release)
+					fscache_operation_processor_t processor,
+					fscache_operation_release_t release)
 {
+	INIT_WORK(&op->work, fscache_op_work_func);
 	atomic_set(&op->usage, 1);
 	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->processor = processor;
 	op->release = release;
 	INIT_LIST_HEAD(&op->pend_link);
 	fscache_set_op_state(op, "Init");
 }
 
-/**
- * fscache_operation_init_slow - Do additional initialisation of a slow op
- * @op: The operation to initialise
- * @processor: The processor function to assign
- *
- * Do additional initialisation of an operation as required for slow work.
- */
-static inline
-void fscache_operation_init_slow(struct fscache_operation *op,
-				 fscache_operation_processor_t processor)
-{
-	op->processor = processor;
-	slow_work_init(&op->slow_work, &fscache_op_slow_work_ops);
-}
-
 /*
  * data read operation
  */
@@ -389,7 +374,7 @@ struct fscache_object {
 	struct fscache_cache	*cache;		/* cache that supplied this object */
 	struct fscache_cookie	*cookie;	/* netfs's file/index object */
 	struct fscache_object	*parent;	/* parent object */
-	struct slow_work	work;		/* attention scheduling record */
+	struct work_struct	work;		/* attention scheduling record */
 	struct list_head	dependents;	/* FIFO of dependent objects */
 	struct list_head	dep_link;	/* link in parent's dependents list */
 	struct list_head	pending_ops;	/* unstarted operations on this object */
@@ -411,7 +396,7 @@ extern const char *fscache_object_states[];
 	(test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) &&	\
 	 (obj)->state >= FSCACHE_OBJECT_DYING)
 
-extern const struct slow_work_ops fscache_object_slow_work_ops;
+extern void fscache_object_work_func(struct work_struct *work);
 
 /**
  * fscache_object_init - Initialise a cache object description
@@ -433,7 +418,7 @@ void fscache_object_init(struct fscache_object *object,
 	spin_lock_init(&object->lock);
 	INIT_LIST_HEAD(&object->cache_link);
 	INIT_HLIST_NODE(&object->cookie_link);
-	vslow_work_init(&object->work, &fscache_object_slow_work_ops);
+	INIT_WORK(&object->work, fscache_object_work_func);
 	INIT_LIST_HEAD(&object->dependents);
 	INIT_LIST_HEAD(&object->dep_link);
 	INIT_LIST_HEAD(&object->pending_ops);
@@ -534,6 +519,8 @@ extern void fscache_io_error(struct fscache_cache *cache);
 extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
 				      struct pagevec *pagevec);
 
+extern bool fscache_object_sleep_till_congested(signed long *timeoutp);
+
 extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
 					       const void *data,
 					       uint16_t datalen);
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index aabc8a13ba7..685ea65eb80 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -30,8 +30,73 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 int kthread_stop(struct task_struct *k);
 int kthread_should_stop(void);
+void *kthread_data(struct task_struct *k);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
 
+/*
+ * Simple work processor based on kthread.
+ *
+ * This provides easier way to make use of kthreads.  A kthread_work
+ * 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);
+
+struct kthread_worker {
+	spinlock_t		lock;
+	struct list_head	work_list;
+	struct task_struct	*task;
+};
+
+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;
+};
+
+#define KTHREAD_WORKER_INIT(worker)	{				\
+	.lock = SPIN_LOCK_UNLOCKED,					\
+	.work_list = LIST_HEAD_INIT((worker).work_list),		\
+	}
+
+#define KTHREAD_WORK_INIT(work, fn)	{				\
+	.node = LIST_HEAD_INIT((work).node),				\
+	.func = (fn),							\
+	.done = __WAIT_QUEUE_HEAD_INITIALIZER((work).done),		\
+	.flushing = ATOMIC_INIT(0),					\
+	}
+
+#define DEFINE_KTHREAD_WORKER(worker)					\
+	struct kthread_worker worker = KTHREAD_WORKER_INIT(worker)
+
+#define DEFINE_KTHREAD_WORK(work, fn)					\
+	struct kthread_work work = KTHREAD_WORK_INIT(work, fn)
+
+static inline void init_kthread_worker(struct kthread_worker *worker)
+{
+	*worker = (struct kthread_worker)KTHREAD_WORKER_INIT(*worker);
+}
+
+static inline void init_kthread_work(struct kthread_work *work,
+				     kthread_work_func_t fn)
+{
+	*work = (struct kthread_work)KTHREAD_WORK_INIT(*work, fn);
+}
+
+int kthread_worker_fn(void *worker_ptr);
+
+bool queue_kthread_work(struct kthread_worker *worker,
+			struct kthread_work *work);
+void flush_kthread_work(struct kthread_work *work);
+void flush_kthread_worker(struct kthread_worker *worker);
+
 #endif /* _LINUX_KTHREAD_H */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index b85f3ff34d7..f010f18a0f8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -751,6 +751,7 @@ struct ata_port {
 	struct ata_host		*host;
 	struct device 		*dev;
 
+	struct mutex		scsi_scan_mutex;
 	struct delayed_work	hotplug_task;
 	struct work_struct	scsi_rescan_task;
 
diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h
deleted file mode 100644
index 13337bf6c3f..00000000000
--- a/include/linux/slow-work.h
+++ /dev/null
@@ -1,163 +0,0 @@
-/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- *
- * See Documentation/slow-work.txt
- */
-
-#ifndef _LINUX_SLOW_WORK_H
-#define _LINUX_SLOW_WORK_H
-
-#ifdef CONFIG_SLOW_WORK
-
-#include <linux/sysctl.h>
-#include <linux/timer.h>
-
-struct slow_work;
-#ifdef CONFIG_SLOW_WORK_DEBUG
-struct seq_file;
-#endif
-
-/*
- * The operations used to support slow work items
- */
-struct slow_work_ops {
-	/* owner */
-	struct module *owner;
-
-	/* get a ref on a work item
-	 * - return 0 if successful, -ve if not
-	 */
-	int (*get_ref)(struct slow_work *work);
-
-	/* discard a ref to a work item */
-	void (*put_ref)(struct slow_work *work);
-
-	/* execute a work item */
-	void (*execute)(struct slow_work *work);
-
-#ifdef CONFIG_SLOW_WORK_DEBUG
-	/* describe a work item for debugfs */
-	void (*desc)(struct slow_work *work, struct seq_file *m);
-#endif
-};
-
-/*
- * A slow work item
- * - A reference is held on the parent object by the thread pool when it is
- *   queued
- */
-struct slow_work {
-	struct module		*owner;	/* the owning module */
-	unsigned long		flags;
-#define SLOW_WORK_PENDING	0	/* item pending (further) execution */
-#define SLOW_WORK_EXECUTING	1	/* item currently executing */
-#define SLOW_WORK_ENQ_DEFERRED	2	/* item enqueue deferred */
-#define SLOW_WORK_VERY_SLOW	3	/* item is very slow */
-#define SLOW_WORK_CANCELLING	4	/* item is being cancelled, don't enqueue */
-#define SLOW_WORK_DELAYED	5	/* item is struct delayed_slow_work with active timer */
-	const struct slow_work_ops *ops; /* operations table for this item */
-	struct list_head	link;	/* link in queue */
-#ifdef CONFIG_SLOW_WORK_DEBUG
-	struct timespec		mark;	/* jiffies at which queued or exec begun */
-#endif
-};
-
-struct delayed_slow_work {
-	struct slow_work	work;
-	struct timer_list	timer;
-};
-
-/**
- * slow_work_init - Initialise a slow work item
- * @work: The work item to initialise
- * @ops: The operations to use to handle the slow work item
- *
- * Initialise a slow work item.
- */
-static inline void slow_work_init(struct slow_work *work,
-				  const struct slow_work_ops *ops)
-{
-	work->flags = 0;
-	work->ops = ops;
-	INIT_LIST_HEAD(&work->link);
-}
-
-/**
- * slow_work_init - Initialise a delayed slow work item
- * @work: The work item to initialise
- * @ops: The operations to use to handle the slow work item
- *
- * Initialise a delayed slow work item.
- */
-static inline void delayed_slow_work_init(struct delayed_slow_work *dwork,
-					  const struct slow_work_ops *ops)
-{
-	init_timer(&dwork->timer);
-	slow_work_init(&dwork->work, ops);
-}
-
-/**
- * vslow_work_init - Initialise a very slow work item
- * @work: The work item to initialise
- * @ops: The operations to use to handle the slow work item
- *
- * Initialise a very slow work item.  This item will be restricted such that
- * only a certain number of the pool threads will be able to execute items of
- * this type.
- */
-static inline void vslow_work_init(struct slow_work *work,
-				   const struct slow_work_ops *ops)
-{
-	work->flags = 1 << SLOW_WORK_VERY_SLOW;
-	work->ops = ops;
-	INIT_LIST_HEAD(&work->link);
-}
-
-/**
- * slow_work_is_queued - Determine if a slow work item is on the work queue
- * work: The work item to test
- *
- * Determine if the specified slow-work item is on the work queue.  This
- * returns true if it is actually on the queue.
- *
- * If the item is executing and has been marked for requeue when execution
- * finishes, then false will be returned.
- *
- * Anyone wishing to wait for completion of execution can wait on the
- * SLOW_WORK_EXECUTING bit.
- */
-static inline bool slow_work_is_queued(struct slow_work *work)
-{
-	unsigned long flags = work->flags;
-	return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING);
-}
-
-extern int slow_work_enqueue(struct slow_work *work);
-extern void slow_work_cancel(struct slow_work *work);
-extern int slow_work_register_user(struct module *owner);
-extern void slow_work_unregister_user(struct module *owner);
-
-extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
-				     unsigned long delay);
-
-static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork)
-{
-	slow_work_cancel(&dwork->work);
-}
-
-extern bool slow_work_sleep_till_thread_needed(struct slow_work *work,
-					       signed long *_timeout);
-
-#ifdef CONFIG_SYSCTL
-extern ctl_table slow_work_sysctls[];
-#endif
-
-#endif /* CONFIG_SLOW_WORK */
-#endif /* _LINUX_SLOW_WORK_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index d0f7c817849..4f9d277bcd9 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -9,6 +9,7 @@
 #include <linux/linkage.h>
 #include <linux/bitops.h>
 #include <linux/lockdep.h>
+#include <linux/threads.h>
 #include <asm/atomic.h>
 
 struct workqueue_struct;
@@ -22,12 +23,59 @@ typedef void (*work_func_t)(struct work_struct *work);
  */
 #define work_data_bits(work) ((unsigned long *)(&(work)->data))
 
+enum {
+	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
+	WORK_STRUCT_CWQ_BIT	= 1,	/* data points to cwq */
+	WORK_STRUCT_LINKED_BIT	= 2,	/* next work is linked to this one */
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+	WORK_STRUCT_STATIC_BIT	= 3,	/* static initializer (debugobjects) */
+	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
+#else
+	WORK_STRUCT_COLOR_SHIFT	= 3,	/* color for workqueue flushing */
+#endif
+
+	WORK_STRUCT_COLOR_BITS	= 4,
+
+	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
+	WORK_STRUCT_CWQ		= 1 << WORK_STRUCT_CWQ_BIT,
+	WORK_STRUCT_LINKED	= 1 << WORK_STRUCT_LINKED_BIT,
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
+#else
+	WORK_STRUCT_STATIC	= 0,
+#endif
+
+	/*
+	 * The last color is no color used for works which don't
+	 * participate in workqueue flushing.
+	 */
+	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS) - 1,
+	WORK_NO_COLOR		= WORK_NR_COLORS,
+
+	/* special cpu IDs */
+	WORK_CPU_UNBOUND	= NR_CPUS,
+	WORK_CPU_NONE		= NR_CPUS + 1,
+	WORK_CPU_LAST		= WORK_CPU_NONE,
+
+	/*
+	 * Reserve 7 bits off of cwq pointer w/ debugobjects turned
+	 * off.  This makes cwqs aligned to 128 bytes which isn't too
+	 * excessive while allowing 15 workqueue flush colors.
+	 */
+	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
+				  WORK_STRUCT_COLOR_BITS,
+
+	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
+	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
+	WORK_STRUCT_NO_CPU	= WORK_CPU_NONE << WORK_STRUCT_FLAG_BITS,
+
+	/* bit mask for work_busy() return values */
+	WORK_BUSY_PENDING	= 1 << 0,
+	WORK_BUSY_RUNNING	= 1 << 1,
+};
+
 struct work_struct {
 	atomic_long_t data;
-#define WORK_STRUCT_PENDING 0		/* T if work item pending execution */
-#define WORK_STRUCT_STATIC  1		/* static initializer (debugobjects) */
-#define WORK_STRUCT_FLAG_MASK (3UL)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
 	struct list_head entry;
 	work_func_t func;
 #ifdef CONFIG_LOCKDEP
@@ -35,8 +83,9 @@ struct work_struct {
 #endif
 };
 
-#define WORK_DATA_INIT()	ATOMIC_LONG_INIT(0)
-#define WORK_DATA_STATIC_INIT()	ATOMIC_LONG_INIT(2)
+#define WORK_DATA_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU)
+#define WORK_DATA_STATIC_INIT()	\
+	ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC)
 
 struct delayed_work {
 	struct work_struct work;
@@ -96,9 +145,14 @@ struct execute_work {
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 extern void __init_work(struct work_struct *work, int onstack);
 extern void destroy_work_on_stack(struct work_struct *work);
+static inline unsigned int work_static(struct work_struct *work)
+{
+	return *work_data_bits(work) & WORK_STRUCT_STATIC;
+}
 #else
 static inline void __init_work(struct work_struct *work, int onstack) { }
 static inline void destroy_work_on_stack(struct work_struct *work) { }
+static inline unsigned int work_static(struct work_struct *work) { return 0; }
 #endif
 
 /*
@@ -162,7 +216,7 @@ static inline void destroy_work_on_stack(struct work_struct *work) { }
  * @work: The work item in question
  */
 #define work_pending(work) \
-	test_bit(WORK_STRUCT_PENDING, work_data_bits(work))
+	test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
 
 /**
  * delayed_work_pending - Find out whether a delayable work item is currently
@@ -177,16 +231,56 @@ static inline void destroy_work_on_stack(struct work_struct *work) { }
  * @work: The work item in question
  */
 #define work_clear_pending(work) \
-	clear_bit(WORK_STRUCT_PENDING, work_data_bits(work))
+	clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
+
+enum {
+	WQ_NON_REENTRANT	= 1 << 0, /* guarantee non-reentrance */
+	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
+	WQ_FREEZEABLE		= 1 << 2, /* freeze during suspend */
+	WQ_RESCUER		= 1 << 3, /* has an rescue worker */
+	WQ_HIGHPRI		= 1 << 4, /* high priority */
+	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
+
+	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
+	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
+	WQ_DFL_ACTIVE		= WQ_MAX_ACTIVE / 2,
+};
+
+/* unbound wq's aren't per-cpu, scale max_active according to #cpus */
+#define WQ_UNBOUND_MAX_ACTIVE	\
+	max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU)
 
+/*
+ * System-wide workqueues which are always present.
+ *
+ * system_wq is the one used by schedule[_delayed]_work[_on]().
+ * Multi-CPU multi-threaded.  There are users which expect relatively
+ * short queue flush time.  Don't queue works which can run for too
+ * long.
+ *
+ * system_long_wq is similar to system_wq but may host long running
+ * works.  Queue flushing might take relatively long.
+ *
+ * system_nrt_wq is non-reentrant and guarantees that any given work
+ * item is never executed in parallel by multiple CPUs.  Queue
+ * flushing might take relatively long.
+ *
+ * system_unbound_wq is unbound workqueue.  Workers are not bound to
+ * any specific CPU, not concurrency managed, and all queued works are
+ * executed immediately as long as max_active limit is not reached and
+ * resources are available.
+ */
+extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_long_wq;
+extern struct workqueue_struct *system_nrt_wq;
+extern struct workqueue_struct *system_unbound_wq;
 
 extern struct workqueue_struct *
-__create_workqueue_key(const char *name, int singlethread,
-		       int freezeable, int rt, struct lock_class_key *key,
-		       const char *lock_name);
+__alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
+		      struct lock_class_key *key, const char *lock_name);
 
 #ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
+#define alloc_workqueue(name, flags, max_active)		\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\
@@ -196,20 +290,20 @@ __create_workqueue_key(const char *name, int singlethread,
 	else							\
 		__lock_name = #name;				\
 								\
-	__create_workqueue_key((name), (singlethread),		\
-			       (freezeable), (rt), &__key,	\
-			       __lock_name);			\
+	__alloc_workqueue_key((name), (flags), (max_active),	\
+			      &__key, __lock_name);		\
 })
 #else
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
-	__create_workqueue_key((name), (singlethread), (freezeable), (rt), \
-			       NULL, NULL)
+#define alloc_workqueue(name, flags, max_active)		\
+	__alloc_workqueue_key((name), (flags), (max_active), NULL, NULL)
 #endif
 
-#define create_workqueue(name) __create_workqueue((name), 0, 0, 0)
-#define create_rt_workqueue(name) __create_workqueue((name), 0, 0, 1)
-#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1, 0)
-#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0, 0)
+#define create_workqueue(name)					\
+	alloc_workqueue((name), WQ_RESCUER, 1)
+#define create_freezeable_workqueue(name)			\
+	alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1)
+#define create_singlethread_workqueue(name)			\
+	alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
@@ -231,16 +325,19 @@ extern int schedule_delayed_work(struct delayed_work *work, unsigned long delay)
 extern int schedule_delayed_work_on(int cpu, struct delayed_work *work,
 					unsigned long delay);
 extern int schedule_on_each_cpu(work_func_t func);
-extern int current_is_keventd(void);
 extern int keventd_up(void);
 
-extern void init_workqueues(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 void workqueue_set_max_active(struct workqueue_struct *wq,
+				     int max_active);
+extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq);
+extern unsigned int work_cpu(struct work_struct *work);
+extern unsigned int work_busy(struct work_struct *work);
+
 /*
  * Kill off a pending schedule_delayed_work().  Note that the work callback
  * function may still be running on return from cancel_delayed_work(), unless
@@ -298,7 +395,14 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_FREEZER
+extern void freeze_workqueues_begin(void);
+extern bool freeze_workqueues_busy(void);
+extern void thaw_workqueues(void);
+#endif /* CONFIG_FREEZER */
+
 #ifdef CONFIG_LOCKDEP
 int in_workqueue_context(struct workqueue_struct *wq);
 #endif
+
 #endif
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
deleted file mode 100644
index d6c974474e7..00000000000
--- a/include/trace/events/workqueue.h
+++ /dev/null
@@ -1,92 +0,0 @@
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM workqueue
-
-#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_WORKQUEUE_H
-
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-DECLARE_EVENT_CLASS(workqueue,
-
-	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-
-	TP_ARGS(wq_thread, work),
-
-	TP_STRUCT__entry(
-		__array(char,		thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,		thread_pid)
-		__field(work_func_t,	func)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-		__entry->func		= work->func;
-	),
-
-	TP_printk("thread=%s:%d func=%pf", __entry->thread_comm,
-		__entry->thread_pid, __entry->func)
-);
-
-DEFINE_EVENT(workqueue, workqueue_insertion,
-
-	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-
-	TP_ARGS(wq_thread, work)
-);
-
-DEFINE_EVENT(workqueue, workqueue_execution,
-
-	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-
-	TP_ARGS(wq_thread, work)
-);
-
-/* Trace the creation of one workqueue thread on a cpu */
-TRACE_EVENT(workqueue_creation,
-
-	TP_PROTO(struct task_struct *wq_thread, int cpu),
-
-	TP_ARGS(wq_thread, cpu),
-
-	TP_STRUCT__entry(
-		__array(char,	thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,	thread_pid)
-		__field(int,	cpu)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-		__entry->cpu		= cpu;
-	),
-
-	TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
-		__entry->thread_pid, __entry->cpu)
-);
-
-TRACE_EVENT(workqueue_destruction,
-
-	TP_PROTO(struct task_struct *wq_thread),
-
-	TP_ARGS(wq_thread),
-
-	TP_STRUCT__entry(
-		__array(char,	thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,	thread_pid)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-	),
-
-	TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
-);
-
-#endif /* _TRACE_WORKQUEUE_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>