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

1 files changed, 2755 insertions, 405 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 59fef1531dd..9ca34cddaf6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -33,41 +33,272 @@
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
+#include <linux/idr.h>
+
+#include "workqueue_sched.h"
+
+enum {
+	/* global_cwq flags */
+	GCWQ_MANAGE_WORKERS	= 1 << 0,	/* need to manage workers */
+	GCWQ_MANAGING_WORKERS	= 1 << 1,	/* managing workers */
+	GCWQ_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
+	GCWQ_FREEZING		= 1 << 3,	/* freeze in progress */
+	GCWQ_HIGHPRI_PENDING	= 1 << 4,	/* highpri works on queue */
+
+	/* worker flags */
+	WORKER_STARTED		= 1 << 0,	/* started */
+	WORKER_DIE		= 1 << 1,	/* die die die */
+	WORKER_IDLE		= 1 << 2,	/* is idle */
+	WORKER_PREP		= 1 << 3,	/* preparing to run works */
+	WORKER_ROGUE		= 1 << 4,	/* not bound to any cpu */
+	WORKER_REBIND		= 1 << 5,	/* mom is home, come back */
+	WORKER_CPU_INTENSIVE	= 1 << 6,	/* cpu intensive */
+	WORKER_UNBOUND		= 1 << 7,	/* worker is unbound */
+
+	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_ROGUE | WORKER_REBIND |
+				  WORKER_CPU_INTENSIVE | WORKER_UNBOUND,
+
+	/* gcwq->trustee_state */
+	TRUSTEE_START		= 0,		/* start */
+	TRUSTEE_IN_CHARGE	= 1,		/* trustee in charge of gcwq */
+	TRUSTEE_BUTCHER		= 2,		/* butcher workers */
+	TRUSTEE_RELEASE		= 3,		/* release workers */
+	TRUSTEE_DONE		= 4,		/* trustee is done */
+
+	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */
+	BUSY_WORKER_HASH_SIZE	= 1 << BUSY_WORKER_HASH_ORDER,
+	BUSY_WORKER_HASH_MASK	= BUSY_WORKER_HASH_SIZE - 1,
+
+	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
+	IDLE_WORKER_TIMEOUT	= 300 * HZ,	/* keep idle ones for 5 mins */
+
+	MAYDAY_INITIAL_TIMEOUT	= HZ / 100,	/* call for help after 10ms */
+	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
+	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */
+	TRUSTEE_COOLDOWN	= HZ / 10,	/* for trustee draining */
+
+	/*
+	 * Rescue workers are used only on emergencies and shared by
+	 * all cpus.  Give -20.
+	 */
+	RESCUER_NICE_LEVEL	= -20,
+};
 
 /*
- * The per-CPU workqueue (if single thread, we always use the first
- * possible cpu).
+ * Structure fields follow one of the following exclusion rules.
+ *
+ * I: Set during initialization and read-only afterwards.
+ *
+ * P: Preemption protected.  Disabling preemption is enough and should
+ *    only be modified and accessed from the local cpu.
+ *
+ * L: gcwq->lock protected.  Access with gcwq->lock held.
+ *
+ * X: During normal operation, modification requires gcwq->lock and
+ *    should be done only from local cpu.  Either disabling preemption
+ *    on local cpu or grabbing gcwq->lock is enough for read access.
+ *    If GCWQ_DISASSOCIATED is set, it's identical to L.
+ *
+ * F: wq->flush_mutex protected.
+ *
+ * W: workqueue_lock protected.
  */
-struct cpu_workqueue_struct {
 
-	spinlock_t lock;
+struct global_cwq;
 
-	struct list_head worklist;
-	wait_queue_head_t more_work;
-	struct work_struct *current_work;
+/*
+ * The poor guys doing the actual heavy lifting.  All on-duty workers
+ * are either serving the manager role, on idle list or on busy hash.
+ */
+struct worker {
+	/* on idle list while idle, on busy hash table while busy */
+	union {
+		struct list_head	entry;	/* L: while idle */
+		struct hlist_node	hentry;	/* L: while busy */
+	};
 
-	struct workqueue_struct *wq;
-	struct task_struct *thread;
-} ____cacheline_aligned;
+	struct work_struct	*current_work;	/* L: work being processed */
+	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 */
+	/* 64 bytes boundary on 64bit, 32 on 32bit */
+	unsigned long		last_active;	/* L: last active timestamp */
+	unsigned int		flags;		/* X: flags */
+	int			id;		/* I: worker id */
+	struct work_struct	rebind_work;	/* L: rebind worker to cpu */
+};
+
+/*
+ * Global per-cpu workqueue.  There's one and only one for each cpu
+ * and all works are queued and processed here regardless of their
+ * target workqueues.
+ */
+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 */
+	struct hlist_head	busy_hash[BUSY_WORKER_HASH_SIZE];
+						/* L: hash of busy 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 task_struct	*trustee;	/* L: for gcwq shutdown */
+	unsigned int		trustee_state;	/* L: trustee state */
+	wait_queue_head_t	trustee_wait;	/* trustee wait */
+	struct worker		*first_idle;	/* L: first idle worker */
+} ____cacheline_aligned_in_smp;
+
+/*
+ * The per-CPU workqueue.  The lower WORK_STRUCT_FLAG_BITS of
+ * work_struct->data are used for flags and thus cwqs need to be
+ * aligned at two's power of the number of flag bits.
+ */
+struct cpu_workqueue_struct {
+	struct global_cwq	*gcwq;		/* I: the associated gcwq */
+	struct workqueue_struct *wq;		/* I: the owning workqueue */
+	int			work_color;	/* L: current color */
+	int			flush_color;	/* L: flushing color */
+	int			nr_in_flight[WORK_NR_COLORS];
+						/* L: nr of in_flight works */
+	int			nr_active;	/* L: nr of active works */
+	int			max_active;	/* L: max active works */
+	struct list_head	delayed_works;	/* L: delayed works */
+};
+
+/*
+ * Structure used to wait for workqueue flush.
+ */
+struct wq_flusher {
+	struct list_head	list;		/* F: list of flushers */
+	int			flush_color;	/* F: flush color waiting for */
+	struct completion	done;		/* flush completion */
+};
+
+/*
+ * All cpumasks are assumed to be always set on UP and thus can't be
+ * used to determine whether there's something to be done.
+ */
+#ifdef CONFIG_SMP
+typedef cpumask_var_t mayday_mask_t;
+#define mayday_test_and_set_cpu(cpu, mask)	\
+	cpumask_test_and_set_cpu((cpu), (mask))
+#define mayday_clear_cpu(cpu, mask)		cpumask_clear_cpu((cpu), (mask))
+#define for_each_mayday_cpu(cpu, mask)		for_each_cpu((cpu), (mask))
+#define alloc_mayday_mask(maskp, gfp)		alloc_cpumask_var((maskp), (gfp))
+#define free_mayday_mask(mask)			free_cpumask_var((mask))
+#else
+typedef unsigned long mayday_mask_t;
+#define mayday_test_and_set_cpu(cpu, mask)	test_and_set_bit(0, &(mask))
+#define mayday_clear_cpu(cpu, mask)		clear_bit(0, &(mask))
+#define for_each_mayday_cpu(cpu, mask)		if ((cpu) = 0, (mask))
+#define alloc_mayday_mask(maskp, gfp)		true
+#define free_mayday_mask(mask)			do { } while (0)
+#endif
 
 /*
  * The externally visible workqueue abstraction is an array of
  * per-CPU workqueues:
  */
 struct workqueue_struct {
-	struct cpu_workqueue_struct *cpu_wq;
-	struct list_head list;
-	const char *name;
-	int singlethread;
-	int freezeable;		/* Freeze threads during suspend */
-	int rt;
+	unsigned int		flags;		/* I: WQ_* flags */
+	union {
+		struct cpu_workqueue_struct __percpu	*pcpu;
+		struct cpu_workqueue_struct		*single;
+		unsigned long				v;
+	} cpu_wq;				/* I: cwq's */
+	struct list_head	list;		/* W: list of all workqueues */
+
+	struct mutex		flush_mutex;	/* protects wq flushing */
+	int			work_color;	/* F: current work color */
+	int			flush_color;	/* F: current flush color */
+	atomic_t		nr_cwqs_to_flush; /* flush in progress */
+	struct wq_flusher	*first_flusher;	/* F: first flusher */
+	struct list_head	flusher_queue;	/* F: flush waiters */
+	struct list_head	flusher_overflow; /* F: flush overflow list */
+
+	mayday_mask_t		mayday_mask;	/* cpus requesting rescue */
+	struct worker		*rescuer;	/* I: rescue worker */
+
+	int			saved_max_active; /* W: saved cwq max_active */
+	const char		*name;		/* I: workqueue name */
 #ifdef CONFIG_LOCKDEP
-	struct lockdep_map lockdep_map;
+	struct lockdep_map	lockdep_map;
 #endif
 };
 
+struct workqueue_struct *system_wq __read_mostly;
+struct workqueue_struct *system_long_wq __read_mostly;
+struct workqueue_struct *system_nrt_wq __read_mostly;
+struct workqueue_struct *system_unbound_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_wq);
+EXPORT_SYMBOL_GPL(system_long_wq);
+EXPORT_SYMBOL_GPL(system_nrt_wq);
+EXPORT_SYMBOL_GPL(system_unbound_wq);
+
+#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)
+
+static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask,
+				  unsigned int sw)
+{
+	if (cpu < nr_cpu_ids) {
+		if (sw & 1) {
+			cpu = cpumask_next(cpu, mask);
+			if (cpu < nr_cpu_ids)
+				return cpu;
+		}
+		if (sw & 2)
+			return WORK_CPU_UNBOUND;
+	}
+	return WORK_CPU_NONE;
+}
+
+static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
+				struct workqueue_struct *wq)
+{
+	return __next_gcwq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2);
+}
+
+/*
+ * CPU iterators
+ *
+ * An extra gcwq is defined for an invalid cpu number
+ * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any
+ * specific CPU.  The following iterators are similar to
+ * for_each_*_cpu() iterators but also considers the unbound gcwq.
+ *
+ * for_each_gcwq_cpu()		: possible CPUs + WORK_CPU_UNBOUND
+ * for_each_online_gcwq_cpu()	: online CPUs + WORK_CPU_UNBOUND
+ * for_each_cwq_cpu()		: possible CPUs for bound workqueues,
+ *				  WORK_CPU_UNBOUND for unbound workqueues
+ */
+#define for_each_gcwq_cpu(cpu)						\
+	for ((cpu) = __next_gcwq_cpu(-1, cpu_possible_mask, 3);		\
+	     (cpu) < WORK_CPU_NONE;					\
+	     (cpu) = __next_gcwq_cpu((cpu), cpu_possible_mask, 3))
+
+#define for_each_online_gcwq_cpu(cpu)					\
+	for ((cpu) = __next_gcwq_cpu(-1, cpu_online_mask, 3);		\
+	     (cpu) < WORK_CPU_NONE;					\
+	     (cpu) = __next_gcwq_cpu((cpu), cpu_online_mask, 3))
+
+#define for_each_cwq_cpu(cpu, wq)					\
+	for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, (wq));	\
+	     (cpu) < WORK_CPU_NONE;					\
+	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
+
 #ifdef CONFIG_LOCKDEP
 /**
  * in_workqueue_context() - in context of specified workqueue?
@@ -122,7 +353,7 @@ static int work_fixup_activate(void *addr, enum debug_obj_state state)
 		 * statically initialized. We just make sure that it
 		 * is tracked in the object tracker.
 		 */
-		if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
+		if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) {
 			debug_object_init(work, &work_debug_descr);
 			debug_object_activate(work, &work_debug_descr);
 			return 0;
@@ -196,94 +427,575 @@ static inline void debug_work_deactivate(struct work_struct *work) { }
 /* Serializes the accesses to the list of workqueues. */
 static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
+static bool workqueue_freezing;		/* W: have wqs started freezing? */
+
+/*
+ * The almighty global cpu workqueues.  nr_running is the only field
+ * which is expected to be used frequently by other cpus via
+ * try_to_wake_up().  Put it in a separate cacheline.
+ */
+static DEFINE_PER_CPU(struct global_cwq, global_cwq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, gcwq_nr_running);
+
+/*
+ * Global cpu workqueue and nr_running counter for unbound gcwq.  The
+ * gcwq is always online, has GCWQ_DISASSOCIATED set, and all its
+ * workers have WORKER_UNBOUND set.
+ */
+static struct global_cwq unbound_global_cwq;
+static atomic_t unbound_gcwq_nr_running = ATOMIC_INIT(0);	/* always 0 */
+
+static int worker_thread(void *__worker);
+
+static struct global_cwq *get_gcwq(unsigned int cpu)
+{
+	if (cpu != WORK_CPU_UNBOUND)
+		return &per_cpu(global_cwq, cpu);
+	else
+		return &unbound_global_cwq;
+}
+
+static atomic_t *get_gcwq_nr_running(unsigned int cpu)
+{
+	if (cpu != WORK_CPU_UNBOUND)
+		return &per_cpu(gcwq_nr_running, cpu);
+	else
+		return &unbound_gcwq_nr_running;
+}
+
+static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
+					    struct workqueue_struct *wq)
+{
+	if (!(wq->flags & WQ_UNBOUND)) {
+		if (likely(cpu < nr_cpu_ids)) {
+#ifdef CONFIG_SMP
+			return per_cpu_ptr(wq->cpu_wq.pcpu, cpu);
+#else
+			return wq->cpu_wq.single;
+#endif
+		}
+	} else if (likely(cpu == WORK_CPU_UNBOUND))
+		return wq->cpu_wq.single;
+	return NULL;
+}
+
+static unsigned int work_color_to_flags(int color)
+{
+	return color << WORK_STRUCT_COLOR_SHIFT;
+}
+
+static int get_work_color(struct work_struct *work)
+{
+	return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) &
+		((1 << WORK_STRUCT_COLOR_BITS) - 1);
+}
+
+static int work_next_color(int color)
+{
+	return (color + 1) % WORK_NR_COLORS;
+}
 
-static int singlethread_cpu __read_mostly;
-static const struct cpumask *cpu_singlethread_map __read_mostly;
 /*
- * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
- * flushes cwq->worklist. This means that flush_workqueue/wait_on_work
- * which comes in between can't use for_each_online_cpu(). We could
- * use cpu_possible_map, the cpumask below is more a documentation
- * than optimization.
+ * A work's data points to the cwq with WORK_STRUCT_CWQ set while the
+ * work is on queue.  Once execution starts, WORK_STRUCT_CWQ is
+ * cleared and the work data contains the cpu number it was last on.
+ *
+ * set_work_{cwq|cpu}() and clear_work_data() can be used to set the
+ * cwq, cpu or clear work->data.  These functions should only be
+ * called while the work is owned - ie. while the PENDING bit is set.
+ *
+ * get_work_[g]cwq() can be used to obtain the gcwq or cwq
+ * corresponding to a work.  gcwq is available once the work has been
+ * queued anywhere after initialization.  cwq is available only from
+ * queueing until execution starts.
  */
-static cpumask_var_t cpu_populated_map __read_mostly;
+static inline void set_work_data(struct work_struct *work, unsigned long data,
+				 unsigned long flags)
+{
+	BUG_ON(!work_pending(work));
+	atomic_long_set(&work->data, data | flags | work_static(work));
+}
 
-/* If it's single threaded, it isn't in the list of workqueues. */
-static inline int is_wq_single_threaded(struct workqueue_struct *wq)
+static void set_work_cwq(struct work_struct *work,
+			 struct cpu_workqueue_struct *cwq,
+			 unsigned long extra_flags)
 {
-	return wq->singlethread;
+	set_work_data(work, (unsigned long)cwq,
+		      WORK_STRUCT_PENDING | WORK_STRUCT_CWQ | extra_flags);
 }
 
-static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
+static void set_work_cpu(struct work_struct *work, unsigned int cpu)
 {
-	return is_wq_single_threaded(wq)
-		? cpu_singlethread_map : cpu_populated_map;
+	set_work_data(work, cpu << WORK_STRUCT_FLAG_BITS, WORK_STRUCT_PENDING);
 }
 
-static
-struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
+static void clear_work_data(struct work_struct *work)
 {
-	if (unlikely(is_wq_single_threaded(wq)))
-		cpu = singlethread_cpu;
-	return per_cpu_ptr(wq->cpu_wq, cpu);
+	set_work_data(work, WORK_STRUCT_NO_CPU, 0);
+}
+
+static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work)
+{
+	unsigned long data = atomic_long_read(&work->data);
+
+	if (data & WORK_STRUCT_CWQ)
+		return (void *)(data & WORK_STRUCT_WQ_DATA_MASK);
+	else
+		return NULL;
+}
+
+static struct global_cwq *get_work_gcwq(struct work_struct *work)
+{
+	unsigned long data = atomic_long_read(&work->data);
+	unsigned int cpu;
+
+	if (data & WORK_STRUCT_CWQ)
+		return ((struct cpu_workqueue_struct *)
+			(data & WORK_STRUCT_WQ_DATA_MASK))->gcwq;
+
+	cpu = data >> WORK_STRUCT_FLAG_BITS;
+	if (cpu == WORK_CPU_NONE)
+		return NULL;
+
+	BUG_ON(cpu >= nr_cpu_ids && cpu != WORK_CPU_UNBOUND);
+	return get_gcwq(cpu);
 }
 
 /*
- * Set the workqueue on which a work item is to be run
- * - Must *only* be called if the pending flag is set
+ * Policy functions.  These define the policies on how the global
+ * worker pool is managed.  Unless noted otherwise, these functions
+ * assume that they're being called with gcwq->lock held.
  */
-static inline void set_wq_data(struct work_struct *work,
-				struct cpu_workqueue_struct *cwq)
+
+static bool __need_more_worker(struct global_cwq *gcwq)
 {
-	unsigned long new;
+	return !atomic_read(get_gcwq_nr_running(gcwq->cpu)) ||
+		gcwq->flags & GCWQ_HIGHPRI_PENDING;
+}
 
-	BUG_ON(!work_pending(work));
+/*
+ * Need to wake up a worker?  Called from anything but currently
+ * running workers.
+ */
+static bool need_more_worker(struct global_cwq *gcwq)
+{
+	return !list_empty(&gcwq->worklist) && __need_more_worker(gcwq);
+}
+
+/* Can I start working?  Called from busy but !running workers. */
+static bool may_start_working(struct global_cwq *gcwq)
+{
+	return gcwq->nr_idle;
+}
+
+/* Do I need to keep working?  Called from currently running workers. */
+static bool keep_working(struct global_cwq *gcwq)
+{
+	atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
+
+	return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1;
+}
+
+/* Do we need a new worker?  Called from manager. */
+static bool need_to_create_worker(struct global_cwq *gcwq)
+{
+	return need_more_worker(gcwq) && !may_start_working(gcwq);
+}
 
-	new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
-	new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
-	atomic_long_set(&work->data, new);
+/* Do I need to be the manager? */
+static bool need_to_manage_workers(struct global_cwq *gcwq)
+{
+	return need_to_create_worker(gcwq) || gcwq->flags & GCWQ_MANAGE_WORKERS;
+}
+
+/* Do we have too many workers and should some go away? */
+static bool too_many_workers(struct global_cwq *gcwq)
+{
+	bool managing = gcwq->flags & GCWQ_MANAGING_WORKERS;
+	int nr_idle = gcwq->nr_idle + managing; /* manager is considered idle */
+	int nr_busy = gcwq->nr_workers - nr_idle;
+
+	return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
 }
 
 /*
- * Clear WORK_STRUCT_PENDING and the workqueue on which it was queued.
+ * Wake up functions.
+ */
+
+/* Return the first worker.  Safe with preemption disabled */
+static struct worker *first_worker(struct global_cwq *gcwq)
+{
+	if (unlikely(list_empty(&gcwq->idle_list)))
+		return NULL;
+
+	return list_first_entry(&gcwq->idle_list, struct worker, entry);
+}
+
+/**
+ * wake_up_worker - wake up an idle worker
+ * @gcwq: gcwq to wake worker for
+ *
+ * Wake up the first idle worker of @gcwq.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ */
+static void wake_up_worker(struct global_cwq *gcwq)
+{
+	struct worker *worker = first_worker(gcwq);
+
+	if (likely(worker))
+		wake_up_process(worker->task);
+}
+
+/**
+ * wq_worker_waking_up - a worker is waking up
+ * @task: task waking up
+ * @cpu: CPU @task is waking up to
+ *
+ * This function is called during try_to_wake_up() when a worker is
+ * being awoken.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ */
+void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
+{
+	struct worker *worker = kthread_data(task);
+
+	if (likely(!(worker->flags & WORKER_NOT_RUNNING)))
+		atomic_inc(get_gcwq_nr_running(cpu));
+}
+
+/**
+ * wq_worker_sleeping - a worker is going to sleep
+ * @task: task going to sleep
+ * @cpu: CPU in question, must be the current CPU number
+ *
+ * This function is called during schedule() when a busy worker is
+ * going to sleep.  Worker on the same cpu can be woken up by
+ * returning pointer to its task.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * RETURNS:
+ * Worker task on @cpu to wake up, %NULL if none.
+ */
+struct task_struct *wq_worker_sleeping(struct task_struct *task,
+				       unsigned int cpu)
+{
+	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+	struct global_cwq *gcwq = get_gcwq(cpu);
+	atomic_t *nr_running = get_gcwq_nr_running(cpu);
+
+	if (unlikely(worker->flags & WORKER_NOT_RUNNING))
+		return NULL;
+
+	/* this can only happen on the local cpu */
+	BUG_ON(cpu != raw_smp_processor_id());
+
+	/*
+	 * The counterpart of the following dec_and_test, implied mb,
+	 * worklist not empty test sequence is in insert_work().
+	 * Please read comment there.
+	 *
+	 * NOT_RUNNING is clear.  This means that trustee is not in
+	 * charge and we're running on the local cpu w/ rq lock held
+	 * and preemption disabled, which in turn means that none else
+	 * could be manipulating idle_list, so dereferencing idle_list
+	 * without gcwq lock is safe.
+	 */
+	if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist))
+		to_wakeup = first_worker(gcwq);
+	return to_wakeup ? to_wakeup->task : NULL;
+}
+
+/**
+ * worker_set_flags - set worker flags and adjust nr_running accordingly
+ * @worker: self
+ * @flags: flags to set
+ * @wakeup: wakeup an idle worker if necessary
+ *
+ * Set @flags in @worker->flags and adjust nr_running accordingly.  If
+ * nr_running becomes zero and @wakeup is %true, an idle worker is
+ * woken up.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock)
+ */
+static inline void worker_set_flags(struct worker *worker, unsigned int flags,
+				    bool wakeup)
+{
+	struct global_cwq *gcwq = worker->gcwq;
+
+	WARN_ON_ONCE(worker->task != current);
+
+	/*
+	 * If transitioning into NOT_RUNNING, adjust nr_running and
+	 * wake up an idle worker as necessary if requested by
+	 * @wakeup.
+	 */
+	if ((flags & WORKER_NOT_RUNNING) &&
+	    !(worker->flags & WORKER_NOT_RUNNING)) {
+		atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
+
+		if (wakeup) {
+			if (atomic_dec_and_test(nr_running) &&
+			    !list_empty(&gcwq->worklist))
+				wake_up_worker(gcwq);
+		} else
+			atomic_dec(nr_running);
+	}
+
+	worker->flags |= flags;
+}
+
+/**
+ * worker_clr_flags - clear worker flags and adjust nr_running accordingly
+ * @worker: self
+ * @flags: flags to clear
+ *
+ * Clear @flags in @worker->flags and adjust nr_running accordingly.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock)
+ */
+static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
+{
+	struct global_cwq *gcwq = worker->gcwq;
+	unsigned int oflags = worker->flags;
+
+	WARN_ON_ONCE(worker->task != current);
+
+	worker->flags &= ~flags;
+
+	/* if transitioning out of NOT_RUNNING, increment nr_running */
+	if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
+		if (!(worker->flags & WORKER_NOT_RUNNING))
+			atomic_inc(get_gcwq_nr_running(gcwq->cpu));
+}
+
+/**
+ * busy_worker_head - return the busy hash head for a work
+ * @gcwq: gcwq of interest
+ * @work: work to be hashed
+ *
+ * Return hash head of @gcwq for @work.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ *
+ * RETURNS:
+ * Pointer to the hash head.
+ */
+static struct hlist_head *busy_worker_head(struct global_cwq *gcwq,
+					   struct work_struct *work)
+{
+	const int base_shift = ilog2(sizeof(struct work_struct));
+	unsigned long v = (unsigned long)work;
+
+	/* simple shift and fold hash, do we need something better? */
+	v >>= base_shift;
+	v += v >> BUSY_WORKER_HASH_ORDER;
+	v &= BUSY_WORKER_HASH_MASK;
+
+	return &gcwq->busy_hash[v];
+}
+
+/**
+ * __find_worker_executing_work - find worker which is executing a work
+ * @gcwq: gcwq of interest
+ * @bwh: hash head as returned by busy_worker_head()
+ * @work: work to find worker for
+ *
+ * Find a worker which is executing @work on @gcwq.  @bwh should be
+ * the hash head obtained by calling busy_worker_head() with the same
+ * work.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ *
+ * RETURNS:
+ * Pointer to worker which is executing @work if found, NULL
+ * otherwise.
+ */
+static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
+						   struct hlist_head *bwh,
+						   struct work_struct *work)
+{
+	struct worker *worker;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry(worker, tmp, bwh, hentry)
+		if (worker->current_work == work)
+			return worker;
+	return NULL;
+}
+
+/**
+ * find_worker_executing_work - find worker which is executing a work
+ * @gcwq: gcwq of interest
+ * @work: work to find worker for
+ *
+ * Find a worker which is executing @work on @gcwq.  This function is
+ * identical to __find_worker_executing_work() except that this
+ * function calculates @bwh itself.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ *
+ * RETURNS:
+ * Pointer to worker which is executing @work if found, NULL
+ * otherwise.
  */
-static inline void clear_wq_data(struct work_struct *work)
+static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
+						 struct work_struct *work)
 {
-	unsigned long flags = *work_data_bits(work) &
-				(1UL << WORK_STRUCT_STATIC);
-	atomic_long_set(&work->data, flags);
+	return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work),
+					    work);
 }
 
-static inline
-struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
+/**
+ * gcwq_determine_ins_pos - find insertion position
+ * @gcwq: gcwq of interest
+ * @cwq: cwq a work is being queued for
+ *
+ * A work for @cwq is about to be queued on @gcwq, determine insertion
+ * position for the work.  If @cwq is for HIGHPRI wq, the work is
+ * queued at the head of the queue but in FIFO order with respect to
+ * other HIGHPRI works; otherwise, at the end of the queue.  This
+ * function also sets GCWQ_HIGHPRI_PENDING flag to hint @gcwq that
+ * there are HIGHPRI works pending.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ *
+ * RETURNS:
+ * Pointer to inserstion position.
+ */
+static inline struct list_head *gcwq_determine_ins_pos(struct global_cwq *gcwq,
+					       struct cpu_workqueue_struct *cwq)
 {
-	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
+	struct work_struct *twork;
+
+	if (likely(!(cwq->wq->flags & WQ_HIGHPRI)))
+		return &gcwq->worklist;
+
+	list_for_each_entry(twork, &gcwq->worklist, entry) {
+		struct cpu_workqueue_struct *tcwq = get_work_cwq(twork);
+
+		if (!(tcwq->wq->flags & WQ_HIGHPRI))
+			break;
+	}
+
+	gcwq->flags |= GCWQ_HIGHPRI_PENDING;
+	return &twork->entry;
 }
 
+/**
+ * insert_work - insert a work into gcwq
+ * @cwq: cwq @work belongs to
+ * @work: work to insert
+ * @head: insertion point
+ * @extra_flags: extra WORK_STRUCT_* flags to set
+ *
+ * Insert @work which belongs to @cwq into @gcwq after @head.
+ * @extra_flags is or'd to work_struct flags.
+ *
+ * CONTEXT:
+ * spin_lock_irq(gcwq->lock).
+ */
 static void insert_work(struct cpu_workqueue_struct *cwq,
-			struct work_struct *work, struct list_head *head)
+			struct work_struct *work, struct list_head *head,
+			unsigned int extra_flags)
 {
-	trace_workqueue_insertion(cwq->thread, work);
+	struct global_cwq *gcwq = cwq->gcwq;
+
+	/* we own @work, set data and link */
+	set_work_cwq(work, cwq, extra_flags);
 
-	set_wq_data(work, cwq);
 	/*
 	 * Ensure that we get the right work->data if we see the
 	 * result of list_add() below, see try_to_grab_pending().
 	 */
 	smp_wmb();
+
 	list_add_tail(&work->entry, head);
-	wake_up(&cwq->more_work);
+
+	/*
+	 * Ensure either worker_sched_deactivated() sees the above
+	 * list_add_tail() or we see zero nr_running to avoid workers
+	 * lying around lazily while there are works to be processed.
+	 */
+	smp_mb();
+
+	if (__need_more_worker(gcwq))
+		wake_up_worker(gcwq);
 }
 
-static void __queue_work(struct cpu_workqueue_struct *cwq,
+static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
+	struct global_cwq *gcwq;
+	struct cpu_workqueue_struct *cwq;
+	struct list_head *worklist;
 	unsigned long flags;
 
 	debug_work_activate(work);
-	spin_lock_irqsave(&cwq->lock, flags);
-	insert_work(cwq, work, &cwq->worklist);
-	spin_unlock_irqrestore(&cwq->lock, flags);
+
+	/* determine gcwq to use */
+	if (!(wq->flags & WQ_UNBOUND)) {
+		struct global_cwq *last_gcwq;
+
+		if (unlikely(cpu == WORK_CPU_UNBOUND))
+			cpu = raw_smp_processor_id();
+
+		/*
+		 * It's multi cpu.  If @wq is non-reentrant and @work
+		 * was previously on a different cpu, it might still
+		 * be running there, in which case the work needs to
+		 * be queued on that cpu to guarantee non-reentrance.
+		 */
+		gcwq = get_gcwq(cpu);
+		if (wq->flags & WQ_NON_REENTRANT &&
+		    (last_gcwq = get_work_gcwq(work)) && last_gcwq != gcwq) {
+			struct worker *worker;
+
+			spin_lock_irqsave(&last_gcwq->lock, flags);
+
+			worker = find_worker_executing_work(last_gcwq, work);
+
+			if (worker && worker->current_cwq->wq == wq)
+				gcwq = last_gcwq;
+			else {
+				/* meh... not running there, queue here */
+				spin_unlock_irqrestore(&last_gcwq->lock, flags);
+				spin_lock_irqsave(&gcwq->lock, flags);
+			}
+		} else
+			spin_lock_irqsave(&gcwq->lock, flags);
+	} else {
+		gcwq = get_gcwq(WORK_CPU_UNBOUND);
+		spin_lock_irqsave(&gcwq->lock, flags);
+	}
+
+	/* gcwq determined, get cwq and queue */
+	cwq = get_cwq(gcwq->cpu, wq);
+
+	BUG_ON(!list_empty(&work->entry));
+
+	cwq->nr_in_flight[cwq->work_color]++;
+
+	if (likely(cwq->nr_active < cwq->max_active)) {
+		cwq->nr_active++;
+		worklist = gcwq_determine_ins_pos(gcwq, cwq);
+	} else
+		worklist = &cwq->delayed_works;
+
+	insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color));
+
+	spin_unlock_irqrestore(&gcwq->lock, flags);
 }
 
 /**
@@ -323,9 +1035,8 @@ queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
 {
 	int ret = 0;
 
-	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
-		BUG_ON(!list_empty(&work->entry));
-		__queue_work(wq_per_cpu(wq, cpu), work);
+	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+		__queue_work(cpu, wq, work);
 		ret = 1;
 	}
 	return ret;
@@ -335,10 +1046,9 @@ EXPORT_SYMBOL_GPL(queue_work_on);
 static void delayed_work_timer_fn(unsigned long __data)
 {
 	struct delayed_work *dwork = (struct delayed_work *)__data;
-	struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);
-	struct workqueue_struct *wq = cwq->wq;
+	struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work);
 
-	__queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work);
+	__queue_work(smp_processor_id(), cwq->wq, &dwork->work);
 }
 
 /**
@@ -375,14 +1085,31 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 	struct timer_list *timer = &dwork->timer;
 	struct work_struct *work = &dwork->work;
 
-	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
+	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+		unsigned int lcpu;
+
 		BUG_ON(timer_pending(timer));
 		BUG_ON(!list_empty(&work->entry));
 
 		timer_stats_timer_set_start_info(&dwork->timer);
 
-		/* This stores cwq for the moment, for the timer_fn */
-		set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
+		/*
+		 * This stores cwq for the moment, for the timer_fn.
+		 * Note that the work's gcwq is preserved to allow
+		 * reentrance detection for delayed works.
+		 */
+		if (!(wq->flags & WQ_UNBOUND)) {
+			struct global_cwq *gcwq = get_work_gcwq(work);
+
+			if (gcwq && gcwq->cpu != WORK_CPU_UNBOUND)
+				lcpu = gcwq->cpu;
+			else
+				lcpu = raw_smp_processor_id();
+		} else
+			lcpu = WORK_CPU_UNBOUND;
+
+		set_work_cwq(work, get_cwq(lcpu, wq), 0);
+
 		timer->expires = jiffies + delay;
 		timer->data = (unsigned long)dwork;
 		timer->function = delayed_work_timer_fn;
@@ -397,80 +1124,872 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
-static void run_workqueue(struct cpu_workqueue_struct *cwq)
+/**
+ * worker_enter_idle - enter idle state
+ * @worker: worker which is entering idle state
+ *
+ * @worker is entering idle state.  Update stats and idle timer if
+ * necessary.
+ *
+ * LOCKING:
+ * spin_lock_irq(gcwq->lock).
+ */
+static void worker_enter_idle(struct worker *worker)
 {
-	spin_lock_irq(&cwq->lock);
-	while (!list_empty(&cwq->worklist)) {
-		struct work_struct *work = list_entry(cwq->worklist.next,
-						struct work_struct, entry);
-		work_func_t f = work->func;
-#ifdef CONFIG_LOCKDEP
+	struct global_cwq *gcwq = worker->gcwq;
+
+	BUG_ON(worker->flags & WORKER_IDLE);
+	BUG_ON(!list_empty(&worker->entry) &&
+	       (worker->hentry.next || worker->hentry.pprev));
+
+	/* can't use worker_set_flags(), also called from start_worker() */
+	worker->flags |= WORKER_IDLE;
+	gcwq->nr_idle++;
+	worker->last_active = jiffies;
+
+	/* idle_list is LIFO */
+	list_add(&worker->entry, &gcwq->idle_list);
+
+	if (likely(!(worker->flags & WORKER_ROGUE))) {
+		if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer))
+			mod_timer(&gcwq->idle_timer,
+				  jiffies + IDLE_WORKER_TIMEOUT);
+	} else
+		wake_up_all(&gcwq->trustee_wait);
+
+	/* sanity check nr_running */
+	WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle &&
+		     atomic_read(get_gcwq_nr_running(gcwq->cpu)));
+}
+
+/**
+ * worker_leave_idle - leave idle state
+ * @worker: worker which is leaving idle state
+ *
+ * @worker is leaving idle state.  Update stats.
+ *
+ * LOCKING:
+ * spin_lock_irq(gcwq->lock).
+ */
+static void worker_leave_id