Merge remote branch 'workqueues/for-next'

Conflicts:
	init/Kconfig
	kernel/sched.c

19 files changed, 795 insertions, 404 deletions

diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index ef3e7be29caf..a9e2b9c60d65 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	depends on HAVE_KVM && MODULES && EXPERIMENTAL
 	# for device assignment:
 	depends on PCI
-	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select KVM_APIC_ARCHITECTURE
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 07703f72330e..38818c08a33c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -18,7 +18,6 @@ if VIRTUALIZATION
 
 config KVM
 	bool
-	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 
 config KVM_BOOK3S_64_HANDLER
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 6ee55ae84ce2..f9b46b07a0a1 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -18,7 +18,6 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM && EXPERIMENTAL
-	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 565ebc65920e..ba43dfed353d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -687,7 +687,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
 	};
 
-	INIT_WORK(&c_idle.work, do_fork_idle);
+	INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle);
 
 	alternatives_smp_switch(1);
 
@@ -713,6 +713,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 
 	if (IS_ERR(c_idle.idle)) {
 		printk("failed fork for CPU %d\n", cpu);
+		destroy_work_on_stack(&c_idle.work);
 		return PTR_ERR(c_idle.idle);
 	}
 
@@ -831,6 +832,7 @@ do_rest:
 		smpboot_restore_warm_reset_vector();
 	}
 
+	destroy_work_on_stack(&c_idle.work);
 	return boot_error;
 }
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3c4d0109ad20..f5a136a65638 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	depends on HAVE_KVM
 	# for device assignment:
 	depends on PCI
-	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 02e8464e480f..93f664733d3f 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -191,36 +191,11 @@ acpi_status __init acpi_os_initialize(void)
 	return AE_OK;
 }
 
-static void bind_to_cpu0(struct work_struct *work)
-{
-	set_cpus_allowed_ptr(current, cpumask_of(0));
-	kfree(work);
-}
-
-static void bind_workqueue(struct workqueue_struct *wq)
-{
-	struct work_struct *work;
-
-	work = kzalloc(sizeof(struct work_struct), GFP_KERNEL);
-	INIT_WORK(work, bind_to_cpu0);
-	queue_work(wq, work);
-}
-
 acpi_status acpi_os_initialize1(void)
 {
-	/*
-	 * On some machines, a software-initiated SMI causes corruption unless
-	 * the SMI runs on CPU 0.  An SMI can be initiated by any AML, but
-	 * typically it's done in GPE-related methods that are run via
-	 * workqueues, so we can avoid the known corruption cases by binding
-	 * the workqueues to CPU 0.
-	 */
-	kacpid_wq = create_singlethread_workqueue("kacpid");
-	bind_workqueue(kacpid_wq);
-	kacpi_notify_wq = create_singlethread_workqueue("kacpi_notify");
-	bind_workqueue(kacpi_notify_wq);
-	kacpi_hotplug_wq = create_singlethread_workqueue("kacpi_hotplug");
-	bind_workqueue(kacpi_hotplug_wq);
+	kacpid_wq = create_workqueue("kacpid");
+	kacpi_notify_wq = create_workqueue("kacpi_notify");
+	kacpi_hotplug_wq = create_workqueue("kacpi_hotplug");
 	BUG_ON(!kacpid_wq);
 	BUG_ON(!kacpi_notify_wq);
 	BUG_ON(!kacpi_hotplug_wq);
@@ -759,7 +734,15 @@ static acpi_status __acpi_os_execute(acpi_execute_type type,
 		(type == OSL_NOTIFY_HANDLER ? kacpi_notify_wq : kacpid_wq);
 	dpc->wait = hp ? 1 : 0;
 	INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	ret = queue_work(queue, &dpc->work);
+
+	/*
+	 * On some machines, a software-initiated SMI causes corruption unless
+	 * the SMI runs on CPU 0.  An SMI can be initiated by any AML, but
+	 * typically it's done in GPE-related methods that are run via
+	 * workqueues, so we can avoid the known corruption cases by always
+	 * queueing on CPU 0.
+	 */
+	ret = queue_work_on(0, queue, &dpc->work);
 
 	if (!ret) {
 		printk(KERN_ERR PREFIX
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bd5a616d9373..45b631e9dc3b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -74,9 +74,7 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, struct kvm_io_bus *bus,
 
 struct kvm_vcpu {
 	struct kvm *kvm;
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-	struct preempt_notifier preempt_notifier;
-#endif
+	struct sched_notifier sched_notifier;
 	int vcpu_id;
 	struct mutex mutex;
 	int   cpu;
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 72b1a10a59b6..538c675b979d 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -93,47 +93,4 @@ do { \
 
 #endif
 
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-
-struct preempt_notifier;
-
-/**
- * preempt_ops - notifiers called when a task is preempted and rescheduled
- * @sched_in: we're about to be rescheduled:
- *    notifier: struct preempt_notifier for the task being scheduled
- *    cpu:  cpu we're scheduled on
- * @sched_out: we've just been preempted
- *    notifier: struct preempt_notifier for the task being preempted
- *    next: the task that's kicking us out
- */
-struct preempt_ops {
-	void (*sched_in)(struct preempt_notifier *notifier, int cpu);
-	void (*sched_out)(struct preempt_notifier *notifier,
-			  struct task_struct *next);
-};
-
-/**
- * preempt_notifier - key for installing preemption notifiers
- * @link: internal use
- * @ops: defines the notifier functions to be called
- *
- * Usually used in conjunction with container_of().
- */
-struct preempt_notifier {
-	struct hlist_node link;
-	struct preempt_ops *ops;
-};
-
-void preempt_notifier_register(struct preempt_notifier *notifier);
-void preempt_notifier_unregister(struct preempt_notifier *notifier);
-
-static inline void preempt_notifier_init(struct preempt_notifier *notifier,
-				     struct preempt_ops *ops)
-{
-	INIT_HLIST_NODE(&notifier->link);
-	notifier->ops = ops;
-}
-
-#endif
-
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1cddd4230868..e3c45ab0ad04 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1214,6 +1214,50 @@ struct sched_rt_entity {
 #endif
 };
 
+struct sched_notifier;
+
+/**
+ * sched_notifier_ops - notifiers called for scheduling events
+ * @wakeup: we're waking up
+ *    notifier: struct sched_notifier for the task being woken up
+ * @sleep: we're going to bed
+ *    notifier: struct sched_notifier for the task sleeping
+ * @in: we're now running on the cpu
+ *    notifier: struct sched_notifier for the task being scheduled in
+ *    prev: the task which ran before us
+ * @out: we're leaving the cpu
+ *    notifier: struct sched_notifier for the task being scheduled out
+ *    next: the task which will run after us
+ */
+struct sched_notifier_ops {
+	void (*wakeup)(struct sched_notifier *notifier);
+	void (*sleep)(struct sched_notifier *notifier);
+	void (*in)(struct sched_notifier *notifier, struct task_struct *prev);
+	void (*out)(struct sched_notifier *notifier, struct task_struct *next);
+};
+
+/**
+ * sched_notifier - key for installing scheduler notifiers
+ * @link: internal use
+ * @ops: defines the notifier functions to be called
+ *
+ * Usually used in conjunction with container_of().
+ */
+struct sched_notifier {
+	struct hlist_node link;
+	struct sched_notifier_ops *ops;
+};
+
+void sched_notifier_register(struct sched_notifier *notifier);
+void sched_notifier_unregister(struct sched_notifier *notifier);
+
+static inline void sched_notifier_init(struct sched_notifier *notifier,
+				       struct sched_notifier_ops *ops)
+{
+	INIT_HLIST_NODE(&notifier->link);
+	notifier->ops = ops;
+}
+
 struct rcu_node;
 
 struct task_struct {
@@ -1237,10 +1281,8 @@ struct task_struct {
 	struct sched_entity se;
 	struct sched_rt_entity rt;
 
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-	/* list of struct preempt_notifier: */
-	struct hlist_head preempt_notifiers;
-#endif
+	/* list of struct sched_notifier: */
+	struct hlist_head sched_notifiers;
 
 	/*
 	 * fpu_counter contains the number of consecutive context switches
@@ -1811,6 +1853,8 @@ static inline void rcu_copy_process(struct task_struct *p)
 #ifdef CONFIG_SMP
 extern int set_cpus_allowed_ptr(struct task_struct *p,
 				const struct cpumask *new_mask);
+extern int force_cpus_allowed(struct task_struct *p,
+				  const struct cpumask *new_mask);
 #else
 static inline int set_cpus_allowed_ptr(struct task_struct *p,
 				       const struct cpumask *new_mask)
@@ -1819,6 +1863,11 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 		return -EINVAL;
 	return 0;
 }
+static inline int force_cpus_allowed(struct task_struct *p,
+				     const struct cpumask *new_mask)
+{
+	return set_cpus_allowed_ptr(p, new_mask);
+}
 #endif
 
 #ifndef CONFIG_CPUMASK_OFFSTACK
@@ -2017,6 +2066,8 @@ extern void release_uids(struct user_namespace *ns);
 
 extern void do_timer(unsigned long ticks);
 
+extern bool try_to_wake_up_local(struct task_struct *p, unsigned int state,
+				 int wake_flags);
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk,
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index baba3a23a814..2d32e061bdc4 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -53,6 +53,11 @@ int stop_machine_create(void);
  */
 void stop_machine_destroy(void);
 
+/**
+ * init_stop_machine: initialize stop_machine during boot
+ */
+void init_stop_machine(void);
+
 #else
 
 static inline int stop_machine(int (*fn)(void *), void *data,
@@ -67,6 +72,7 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 
 static inline int stop_machine_create(void) { return 0; }
 static inline void stop_machine_destroy(void) { }
+static inline void init_stop_machine(void) { }
 
 #endif /* CONFIG_SMP */
 #endif /* _LINUX_STOP_MACHINE */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index cf24c20de9e4..8e689d1f91d8 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -22,11 +22,26 @@ 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_STATIC_BIT	= 1,	/* static initializer (debugobjects) */
+
+	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
+	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
+
+	/*
+	 * Reserve 3bits off of cwq pointer.  This is enough and
+	 * provides acceptable alignment on both 32 and 64bit
+	 * machines.
+	 */
+	WORK_STRUCT_FLAG_BITS	= 3,
+
+	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
+	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
+};
+
 struct work_struct {
 	atomic_long_t data;
-#define WORK_STRUCT_PENDING 0		/* T if work item pending execution */
-#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
@@ -35,6 +50,7 @@ struct work_struct {
 };
 
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT(0)
+#define WORK_DATA_STATIC_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_STATIC)
 
 struct delayed_work {
 	struct work_struct work;
@@ -63,7 +79,7 @@ struct execute_work {
 #endif
 
 #define __WORK_INITIALIZER(n, f) {				\
-	.data = WORK_DATA_INIT(),				\
+	.data = WORK_DATA_STATIC_INIT(),			\
 	.entry	= { &(n).entry, &(n).entry },			\
 	.func = (f),						\
 	__WORK_INIT_LOCKDEP_MAP(#n, &(n))			\
@@ -91,6 +107,19 @@ struct execute_work {
 #define PREPARE_DELAYED_WORK(_work, _func)			\
 	PREPARE_WORK(&(_work)->work, (_func))
 
+#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 bool work_static(struct work_struct *work)
+{
+	return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work));
+}
+#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 bool work_static(struct work_struct *work) { return false; }
+#endif
+
 /*
  * initialize all of a work item in one go
  *
@@ -99,24 +128,36 @@ struct execute_work {
  * to generate better code.
  */
 #ifdef CONFIG_LOCKDEP
-#define INIT_WORK(_work, _func)						\
+#define __INIT_WORK(_work, _func, _onstack)				\
 	do {								\
 		static struct lock_class_key __key;			\
 									\
+		__init_work((_work), _onstack);				\
 		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
 		lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0);\
 		INIT_LIST_HEAD(&(_work)->entry);			\
 		PREPARE_WORK((_work), (_func));				\
 	} while (0)
 #else
-#define INIT_WORK(_work, _func)						\
+#define __INIT_WORK(_work, _func, _onstack)				\
 	do {								\
+		__init_work((_work), _onstack);				\
 		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
 		INIT_LIST_HEAD(&(_work)->entry);			\
 		PREPARE_WORK((_work), (_func));				\
 	} while (0)
 #endif
 
+#define INIT_WORK(_work, _func)					\
+	do {							\
+		__INIT_WORK((_work), (_func), 0);		\
+	} while (0)
+
+#define INIT_WORK_ON_STACK(_work, _func)			\
+	do {							\
+		__INIT_WORK((_work), (_func), 1);		\
+	} while (0)
+
 #define INIT_DELAYED_WORK(_work, _func)				\
 	do {							\
 		INIT_WORK(&(_work)->work, (_func));		\
@@ -125,28 +166,22 @@ struct execute_work {
 
 #define INIT_DELAYED_WORK_ON_STACK(_work, _func)		\
 	do {							\
-		INIT_WORK(&(_work)->work, (_func));		\
+		INIT_WORK_ON_STACK(&(_work)->work, (_func));	\
 		init_timer_on_stack(&(_work)->timer);		\
 	} while (0)
 
-#define INIT_DELAYED_WORK_DEFERRABLE(_work, _func)			\
+#define INIT_DELAYED_WORK_DEFERRABLE(_work, _func)		\
 	do {							\
 		INIT_WORK(&(_work)->work, (_func));		\
 		init_timer_deferrable(&(_work)->timer);		\
 	} while (0)
 
-#define INIT_DELAYED_WORK_ON_STACK(_work, _func)		\
-	do {							\
-		INIT_WORK(&(_work)->work, (_func));		\
-		init_timer_on_stack(&(_work)->timer);		\
-	} while (0)
-
 /**
  * work_pending - Find out whether a work item is currently pending
  * @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
@@ -161,16 +196,19 @@ struct execute_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_FREEZEABLE		= 1 << 0, /* freeze during suspend */
+	WQ_SINGLE_THREAD	= 1 << 1, /* no per-cpu worker */
+};
 
 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);
+__create_workqueue_key(const char *name, unsigned int flags,
+		       struct lock_class_key *key, const char *lock_name);
 
 #ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
+#define __create_workqueue(name, flags)				\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\
@@ -180,20 +218,20 @@ __create_workqueue_key(const char *name, int singlethread,
 	else							\
 		__lock_name = #name;				\
 								\
-	__create_workqueue_key((name), (singlethread),		\
-			       (freezeable), (rt), &__key,	\
+	__create_workqueue_key((name), (flags), &__key,		\
 			       __lock_name);			\
 })
 #else
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
-	__create_workqueue_key((name), (singlethread), (freezeable), (rt), \
-			       NULL, NULL)
+#define __create_workqueue(name, flags)				\
+	__create_workqueue_key((name), (flags), 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)					\
+	__create_workqueue((name), 0)
+#define create_freezeable_workqueue(name)			\
+	__create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD)
+#define create_singlethread_workqueue(name)			\
+	__create_workqueue((name), WQ_SINGLE_THREAD)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/init/Kconfig b/init/Kconfig
index 94a8e10d6290..1b532005aede 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1235,7 +1235,4 @@ config STOP_MACHINE
 
 source "block/Kconfig"
 
-config PREEMPT_NOTIFIERS
-	bool
-
 source "kernel/Kconfig.locks"
diff --git a/init/main.c b/init/main.c
index 698066ff8762..43807f7dcf5f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -34,6 +34,7 @@
 #include <linux/security.h>
 #include <linux/smp.h>
 #include <linux/workqueue.h>
+#include <linux/stop_machine.h>
 #include <linux/profile.h>
 #include <linux/rcupdate.h>
 #include <linux/moduleparam.h>
@@ -779,6 +780,7 @@ static void __init do_initcalls(void)
 static void __init do_basic_setup(void)
 {
 	init_workqueues();
+	init_stop_machine();
 	cpuset_init_smp();
 	usermodehelper_init();
 	init_tmpfs();
diff --git a/kernel/sched.c b/kernel/sched.c
index dba459d08916..be7592902610 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1389,6 +1389,16 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
+#define fire_sched_notifier(p, callback, args...) do {			\
+	struct task_struct *__p = (p);					\
+	struct sched_notifier *__sn;					\
+	struct hlist_node *__pos;					\
+									\
+	hlist_for_each_entry(__sn, __pos, &__p->sched_notifiers, link)	\
+		if (__sn->ops->callback)				\
+			__sn->ops->callback(__sn , ##args);		\
+} while (0)
+
 static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
 
 /*
@@ -2097,6 +2107,7 @@ struct migration_req {
 
 	struct task_struct *task;
 	int dest_cpu;
+	bool force;
 
 	struct completion done;
 };
@@ -2105,8 +2116,8 @@ struct migration_req {
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static int
-migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
+static int migrate_task(struct task_struct *p, int dest_cpu,
+			struct migration_req *req, bool force)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2123,6 +2134,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 	init_completion(&req->done);
 	req->task = p;
 	req->dest_cpu = dest_cpu;
+	req->force = force;
 	list_add(&req->list, &rq->migration_queue);
 
 	return 1;
@@ -2323,11 +2335,73 @@ void task_oncpu_function_call(struct task_struct *p,
 	preempt_enable();
 }
 
-/***
+static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
+				 bool is_sync, bool is_migrate, bool is_local)
+{
+	schedstat_inc(p, se.nr_wakeups);
+	if (is_sync)
+		schedstat_inc(p, se.nr_wakeups_sync);
+	if (is_migrate)
+		schedstat_inc(p, se.nr_wakeups_migrate);
+	if (is_local)
+		schedstat_inc(p, se.nr_wakeups_local);
+	else
+		schedstat_inc(p, se.nr_wakeups_remote);
+
+	activate_task(rq, p, 1);
+
+	/*
+	 * Only attribute actual wakeups done by this task.
+	 */
+	if (!in_interrupt()) {
+		struct sched_entity *se = &current->se;
+		u64 sample = se->sum_exec_runtime;
+
+		if (se->last_wakeup)
+			sample -= se->last_wakeup;
+		else
+			sample -= se->start_runtime;
+		update_avg(&se->avg_wakeup, sample);
+
+		se->last_wakeup = se->sum_exec_runtime;
+	}
+}
+
+static inline void ttwu_woken_up(struct task_struct *p, struct rq *rq,
+				 int wake_flags, bool success)
+{
+	trace_sched_wakeup(rq, p, success);
+	check_preempt_curr(rq, p, wake_flags);
+
+	p->state = TASK_RUNNING;
+#ifdef CONFIG_SMP
+	if (p->sched_class->task_wake_up)
+		p->sched_class->task_wake_up(rq, p);
+
+	if (unlikely(rq->idle_stamp)) {
+		u64 delta = rq->clock - rq->idle_stamp;
+		u64 max = 2*sysctl_sched_migration_cost;
+
+		if (delta > max)
+			rq->avg_idle = max;
+		else
+			update_avg(&rq->avg_idle, delta);
+		rq->idle_stamp = 0;
+	}
+#endif
+	/*
+	 * Wake up is complete, fire wake up notifier.  This allows
+	 * try_to_wake_up_local() to be called from wake up notifiers.
+	 */
+	if (success)
+		fire_sched_notifier(p, wakeup);
+}
+
+/**
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread
  * @state: the mask of task states that can be woken
- * @sync: do a synchronous wakeup?
+ * @wake_flags: wake modifier flags (WF_*)
  *
  * Put it on the run-queue if it's not already there. The "current"
  * thread is always on the run-queue (except when the actual
@@ -2335,7 +2409,8 @@ void task_oncpu_function_call(struct task_struct *p,
  * the simpler "current->state = TASK_RUNNING" to mark yourself
  * runnable without the overhead of this.
  *
- * returns failure only if the task is already active.
+ * Returns %true if @p was woken up, %false if it was already running
+ * or @state didn't match @p's state.
  */
 static int try_to_wake_up(struct task_struct *p, unsigned int state,
 			  int wake_flags)
@@ -2406,57 +2481,61 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-	schedstat_inc(p, se.nr_wakeups);
-	if (wake_flags & WF_SYNC)
-		schedstat_inc(p, se.nr_wakeups_sync);
-	if (orig_cpu != cpu)
-		schedstat_inc(p, se.nr_wakeups_migrate);
-	if (cpu == this_cpu)
-		schedstat_inc(p, se.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.nr_wakeups_remote);
-	activate_task(rq, p, 1);
+	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
+		      cpu == this_cpu);
 	success = 1;
+out_running:
+	ttwu_woken_up(p, rq, wake_flags, success);
+out:
+	task_rq_unlock(rq, &flags);
+	put_cpu();
 
-	/*
-	 * Only attribute actual wakeups done by this task.
-	 */
-	if (!in_interrupt()) {
-		struct sched_entity *se = &current->se;
-		u64 sample = se->sum_exec_runtime;
-
-		if (se->last_wakeup)
-			sample -= se->last_wakeup;
-		else
-			sample -= se->start_runtime;
-		update_avg(&se->avg_wakeup, sample);
+	return success;
+}
 
-		se->last_wakeup = se->sum_exec_runtime;
-	}
+/**
+ * try_to_wake_up_local - try to wake up a local task with rq lock held
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @wake_flags: wake modifier flags (WF_*)
+ *
+ * Put @p on the run-queue if it's not alredy there.  The caller must
+ * ensure that this_rq() is locked, @p is bound to this_rq() and @p is
+ * not the current task.  this_rq() stays locked over invocation.
+ *
+ * This function can be called from wakeup and sleep scheduler
+ * notifiers.  Be careful not to create deep recursion by chaining
+ * wakeup notifiers.
+ *
+ * Returns %true if @p was woken up, %false if it was already running
+ * or @state didn't match @p's state.
+ */
+bool try_to_wake_up_local(struct task_struct *p, unsigned int state,
+			  int wake_flags)
+{
+	struct rq *rq = task_rq(p);
+	bool success = false;
 
-out_running:
-	trace_sched_wakeup(rq, p, success);
-	check_preempt_curr(rq, p, wake_flags);
+	BUG_ON(rq != this_rq());
+	BUG_ON(p == current);
+	lockdep_assert_held(&rq->lock);
 
-	p->state = TASK_RUNNING;
-#ifdef CONFIG_SMP
-	if (p->sched_class->task_wake_up)
-		p->sched_class->task_wake_up(rq, p);
+	if (!sched_feat(SYNC_WAKEUPS))
+		wake_flags &= ~WF_SYNC;
 
-	if (unlikely(rq->idle_stamp)) {
-		u64 delta = rq->clock - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
+	if (!(p->state & state))
+		return false;
 
-		if (delta > max)
-			rq->avg_idle = max;
-		else
-			update_avg(&rq->avg_idle, delta);
-		rq->idle_stamp = 0;
+	if (!p->se.on_rq) {
+		if (likely(!task_running(rq, p))) {
+			schedstat_inc(rq, ttwu_count);
+			schedstat_inc(rq, ttwu_local);
+		}
+		ttwu_activate(p, rq, wake_flags & WF_SYNC, false, true);
+		success = true;
 	}
-#endif
-out:
-	task_rq_unlock(rq, &flags);
-	put_cpu();
+
+	ttwu_woken_up(p, rq, wake_flags, success);
 
 	return success;
 }
@@ -2538,10 +2617,7 @@ static void __sched_fork(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rt.run_list);
 	p->se.on_rq = 0;
 	INIT_LIST_HEAD(&p->se.group_node);
-
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-	INIT_HLIST_HEAD(&p->preempt_notifiers);
-#endif
+	INIT_HLIST_HEAD(&p->sched_notifiers);
 
 	/*
 	 * We mark the process as running here, but have not actually
@@ -2651,63 +2727,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	task_rq_unlock(rq, &flags);
 }
 
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-
 /**
- * preempt_notifier_register - tell me when current is being preempted & rescheduled
+ * sched_notifier_register - register scheduler notifier
  * @notifier: notifier struct to register
  */
-void preempt_notifier_register(struct preempt_notifier *notifier)
+void sched_notifier_register(struct sched_notifier *notifier)
 {
-	hlist_add_head(&notifier->link, &current->preempt_notifiers);
+	hlist_add_head(&notifier->link, &current->sched_notifiers);
 }
-EXPORT_SYMBOL_GPL(preempt_notifier_register);
+EXPORT_SYMBOL_GPL(sched_notifier_register);
 
 /**
- * preempt_notifier_unregister - no longer interested in preemption notifications
+ * sched_notifier_unregister - unregister scheduler notifier
  * @notifier: notifier struct to unregister
  *
- * This is safe to call from within a preemption notifier.
+ * This is safe to call from within a scheduler notifier.
  */
-void preempt_notifier_unregister(struct preempt_notifier *notifier)
+void sched_notifier_unregister(struct sched_notifier *notifier)
 {
 	hlist_del(&notifier->link);
 }
-EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
-
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-{
-	struct preempt_notifier *notifier;
-	struct hlist_node *node;
-
-	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
-		notifier->ops->sched_in(notifier, raw_smp_processor_id());
-}
-
-static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
-				 struct task_struct *next)
-{
-	struct preempt_notifier *notifier;
-	struct hlist_node *node;
-
-	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
-		notifier->ops->sched_out(notifier, next);
-}
-
-#else /* !CONFIG_PREEMPT_NOTIFIERS */
-
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-{
-}
-
-static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
-				 struct task_struct *next)
-{
-}
-
-#endif /* CONFIG_PREEMPT_NOTIFIERS */
+EXPORT_SYMBOL_GPL(sched_notifier_unregister);
 
 /**
  * prepare_task_switch - prepare to switch tasks
@@ -2726,7 +2766,7 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
-	fire_sched_out_preempt_notifiers(prev, next);
+	fire_sched_notifier(current, out, next);
 	prepare_lock_switch(rq, next);
 	prepare_arch_switch(next);
 }
@@ -2768,7 +2808,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	prev_state = prev->state;
 	finish_arch_switch(prev);
 	perf_event_task_sched_in(current, cpu_of(rq));
-	fire_sched_in_preempt_notifiers(current);
+	fire_sched_notifier(current, in, prev);
 	finish_lock_switch(rq, prev);
 
 	if (mm)
@@ -3133,7 +3173,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 		goto out;
 
 	/* force the process onto the specified CPU */
-	if (migrate_task(p, dest_cpu, &req)) {
+	if (migrate_task(p, dest_cpu, &req, false)) {
 		/* Need to wait for migration thread (might exit: take ref). */
 		struct task_struct *mt = rq->migration_thread;
 
@@ -5446,10 +5486,17 @@ need_resched_nonpreemptible:
 	clear_tsk_need_resched(prev);
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
-		if (unlikely(signal_pending_state(prev->state, prev)))
+		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
-		else
+		} else {
+			/*
+			 * Fire sleep notifier before changing any scheduler
+			 * state.  This allows try_to_wake_up_local() to be
+			 * called from sleep notifiers.
+			 */
+			fire_sched_notifier(prev, sleep);
 			deactivate_task(rq, prev, 1);
+		}
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7039,34 +7086,19 @@ static inline void sched_init_granularity(void)
  * 7) we wake up and the migration is done.
  */
 
-/*
- * Change a given task's CPU affinity. Migrate the thread to a
- * proper CPU and schedule it away if the CPU it's executing on
- * is removed from the allowed bitmask.
- *
- * NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely. The
- * call is not atomic; no spinlocks may be held.
- */
-int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+static inline int __set_cpus_allowed(struct task_struct *p,
+				     const struct cpumask *new_mask,
+				     struct rq *rq, unsigned long *flags,
+				     bool force)
 {
 	struct migration_req req;
-	unsigned long flags;
-	struct rq *rq;
 	int ret = 0;
 
-	rq = task_rq_lock(p, &flags);
 	if (!cpumask_intersects(new_mask, cpu_online_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
-		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	if (p->sched_class->set_cpus_allowed)
 		p->sched_class->set_cpus_allowed(p, new_mask);
 	else {
@@ -7078,12 +7110,13 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req,
+			 force)) {
 		/* Need help from migration thread: drop lock and wait. */
 		struct task_struct *mt = rq->migration_thread;
 
 		get_task_struct(mt);
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, flags);
 		wake_up_process(rq->migration_thread);
 		put_task_struct(mt);
 		wait_for_completion(&req.done);
@@ -7091,13 +7124,54 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		return 0;
 	}
 out:
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, flags);
 
 	return ret;
 }
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &flags);
+
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
+		task_rq_unlock(rq, &flags);
+		return -EINVAL;
+	}
+
+	return __set_cpus_allowed(p, new_mask, rq, &flags, false);
+}
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
 /*
+ * Similar to set_cpus_allowed_ptr() but bypasses PF_THREAD_BOUND
+ * check and ignores cpu_active() status as long as the cpu is online.
+ * The caller is responsible for guaranteeing that the destination
+ * cpus don't go down until this function finishes and in general
+ * ensuring things don't go bonkers.
+ */
+int force_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &flags);
+	return __set_cpus_allowed(p, new_mask, rq, &flags, true);
+}
+
+/*
  * Move (not current) task off this cpu, onto dest cpu. We're doing
  * this because either it can't run here any more (set_cpus_allowed()
  * away from this CPU, or CPU going down), or because we're
@@ -7108,12 +7182,13 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
  *
  * Returns non-zero if task was successfully migrated.
  */
-static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu,
+			  bool force)
 {
 	struct rq *rq_dest, *rq_src;
 	int ret = 0, on_rq;
 
-	if (unlikely(!cpu_active(dest_cpu)))
+	if (!force && unlikely(!cpu_active(dest_cpu)))
 		return ret;
 
 	rq_src = cpu_rq(src_cpu);
@@ -7192,7 +7267,8 @@ static int migration_thread(void *data)
 
 		if (req->task != NULL) {
 			spin_unlock(&rq->lock);
-			__migrate_task(req->task, cpu, req->dest_cpu);
+			__migrate_task(req->task, cpu, req->dest_cpu,
+				       req->force);
 		} else if (likely(cpu == (badcpu = smp_processor_id()))) {
 			req->dest_cpu = RCU_MIGRATION_GOT_QS;
 			spin_unlock(&rq->lock);
@@ -7217,7 +7293,7 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
 	int ret;
 
 	local_irq_disable();
-	ret = __migrate_task(p, src_cpu, dest_cpu);
+	ret = __migrate_task(p, src_cpu, dest_cpu, false);
 	local_irq_enable();
 	return ret;
 }
@@ -9569,9 +9645,7 @@ void __init sched_init(void)
 
 	set_load_weight(&init_task);
 
-#ifdef CONFIG_PREEMPT_NOTIFIERS
-	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
-#endif
+	INIT_HLIST_HEAD(&init_task.sched_notifiers);
 
 #ifdef CONFIG_SMP
 	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 912823e2a11b..671a4ac00fba 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -25,6 +25,8 @@ enum stopmachine_state {
 	STOPMACHINE_RUN,
 	/* Exit */
 	STOPMACHINE_EXIT,
+	/* Done */
+	STOPMACHINE_DONE,
 };
 static enum stopmachine_state state;
 
@@ -42,10 +44,9 @@ static DEFINE_MUTEX(lock);
 static DEFINE_MUTEX(setup_lock);
 /* Users of stop_machine. */
 static int refcount;
-static struct workqueue_struct *stop_machine_wq;
+static struct task_struct **stop_machine_threads;
 static struct stop_machine_data active, idle;
 static const struct cpumask *active_cpus;
-static void *stop_machine_work;
 
 static void set_state(enum stopmachine_state newstate)
 {
@@ -63,14 +64,31 @@ static void ack_state(void)
 }
 
 /* This is the actual function which stops the CPU. It runs
- * in the context of a dedicated stopmachine workqueue. */
-static void stop_cpu(struct work_struct *unused)
+ * on dedicated per-cpu kthreads. */
+static int stop_cpu(void *unused)
 {
 	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	struct stop_machine_data *smdata = &idle;
+	struct stop_machine_data *smdata;
 	int cpu = smp_processor_id();
 	int err;
 
+repeat:
+	/* Wait for __stop_machine() to initiate */
+	while (true) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		/* <- kthread_stop() and __stop_machine()::smp_wmb() */
+		if (kthread_should_stop()) {
+			__set_current_state(TASK_RUNNING);
+			return 0;
+		}
+		if (state == STOPMACHINE_PREPARE)
+			break;
+		schedule();
+	}
+	smp_rmb();	/* <- __stop_machine()::set_state() */
+
+	/* Okay, let's go */
+	smdata = &idle;
 	if (!active_cpus) {
 		if (cpu == cpumask_first(cpu_online_mask))
 			smdata = &active;
@@ -104,6 +122,7 @@ static void stop_cpu(struct work_struct *unused)
 	} while (curstate != STOPMACHINE_EXIT);
 
 	local_irq_enable();
+	goto repeat;
 }
 
 /* Callback for CPUs which aren't supposed to do anything. */
@@ -112,46 +131,122 @@ static int chill(void *unused)
 	return 0;
 }
 
+static int create_stop_machine_thread(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	struct task_struct **pp = per_cpu_ptr(stop_machine_threads, cpu);
+	struct task_struct *p;
+
+	if (*pp)
+		return -EBUSY;
+
+	p = kthread_create(stop_cpu, NULL, "kstop/%u", cpu);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
+	*pp = p;
+	return 0;
+}
+
+/* Should be called with cpu hotplug disabled and setup_lock held */
+static void kill_stop_machine_threads(void)
+{
+	unsigned int cpu;
+
+	if (!stop_machine_threads)
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct task_struct *p = *per_cpu_ptr(stop_machine_threads, cpu);
+		if (p)
+			kthread_stop(p);
+	}
+	free_percpu(stop_machine_threads);
+	stop_machine_threads = NULL;
+}
+
 int stop_machine_create(void)
 {
+	unsigned int cpu;
+
+	get_online_cpus();
 	mutex_lock(&setup_lock);
 	if (refcount)
 		goto done;
-	stop_machine_wq = create_rt_workqueue("kstop");
-	if (!stop_machine_wq)
-		goto err_out;
-	stop_machine_work = alloc_percpu(struct work_struct);
-	if (!stop_machine_work)
+
+	stop_machine_threads = alloc_percpu(struct task_struct *);
+	if (!stop_machine_threads)
 		goto err_out;
+
+	/*
+	 * cpu hotplug is disabled, create only for online cpus,
+	 * cpu_callback() will handle cpu hot [un]plugs.
+	 */
+	for_each_online_cpu(cpu) {
+		if (create_stop_machine_thread(cpu))
+			goto err_out;
+		kthread_bind(*per_cpu_ptr(stop_machine_threads, cpu), cpu);
+	}
 done:
 	refcount++;
 	mutex_unlock(&setup_lock);
+	put_online_cpus();
 	return 0;
 
 err_out:
-	if (stop_machine_wq)
-		destroy_workqueue(stop_machine_wq);
+	kill_stop_machine_threads();
 	mutex_unlock(&setup_lock);
+	put_online_cpus();
 	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(stop_machine_create);
 
 void stop_machine_destroy(void)
 {
+	get_online_cpus();
 	mutex_lock(&setup_lock);
-	refcount--;
-	if (refcount)
-		goto done;
-	destroy_workqueue(stop_machine_wq);
-	free_percpu(stop_machine_work);
-done:
+	if (!--refcount)
+		kill_stop_machine_threads();
 	mutex_unlock(&setup_lock);
+	put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(stop_machine_destroy);
 
+static int __cpuinit stop_machine_cpu_callback(struct notifier_block *nfb,
+					       unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	struct task_struct **pp = per_cpu_ptr(stop_machine_threads, cpu);
+
+	/* Hotplug exclusion is enough, no need to worry about setup_lock */
+	if (!stop_machine_threads)
+		return NOTIFY_OK;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		if (create_stop_machine_thread(cpu)) {
+			printk(KERN_ERR "failed to create stop machine "
+			       "thread for %u\n", cpu);
+			return NOTIFY_BAD;
+		}
+		break;
+
+	case CPU_ONLINE:
+		kthread_bind(*pp, cpu);
+		break;
+
+	case CPU_UP_CANCELED:
+	case CPU_POST_DEAD:
+		kthread_stop(*pp);
+		*pp = NULL;
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-	struct work_struct *sm_work;
 	int i, ret;
 
 	/* Set up initial state. */
@@ -164,19 +259,18 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	idle.fn = chill;
 	idle.data = NULL;
 
-	set_state(STOPMACHINE_PREPARE);
+	set_state(STOPMACHINE_PREPARE);	/* -> stop_cpu()::smp_rmb() */
+	smp_wmb();			/* -> stop_cpu()::set_current_state() */
 
 	/* Schedule the stop_cpu work on all cpus: hold this CPU so one
 	 * doesn't hit this CPU until we're ready. */
 	get_cpu();
-	for_each_online_cpu(i) {
-		sm_work = per_cpu_ptr(stop_machine_work, i);
-		INIT_WORK(sm_work, stop_cpu);
-		queue_work_on(i, stop_machine_wq, sm_work);
-	}
+	for_each_online_cpu(i)
+		wake_up_process(*per_cpu_ptr(stop_machine_threads, i));
 	/* This will release the thread on our CPU. */
 	put_cpu();
-	flush_workqueue(stop_machine_wq);
+	while (state < STOPMACHINE_DONE)
+		yield();
 	ret = active.fnret;
 	mutex_unlock(&lock);
 	return ret;
@@ -197,3 +291,8 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
+
+void __init init_stop_machine(void)
+{
+	hotcpu_notifier(stop_machine_cpu_callback, 0);
+}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d006554888dc..de0bfeb5e95f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -414,7 +414,9 @@ config KMEMTRACE
 	  If unsure, say N.
 
 config WORKQUEUE_TRACER
-	bool "Trace workqueues"
+# Temporarily disabled during workqueue reimplementation
+#	bool "Trace workqueues"
+	def_bool n
 	select GENERIC_TRACER
 	help
 	  The workqueue tracer provides some statistical informations
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 67e526b6ae81..5392939cb1e7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -33,12 +33,22 @@
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
+
+/*
+ * Structure fields follow one of the following exclusion rules.
+ *
+ * I: Set during initialization and read-only afterwards.
+ *
+ * L: cwq->lock protected.  Access with cwq->lock held.
+ *
+ * W: workqueue_lock protected.
+ */
 
 /*
  * The per-CPU workqueue (if single thread, we always use the first
- * possible cpu).
+ * possible cpu).  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 {
 
@@ -48,26 +58,134 @@ struct cpu_workqueue_struct {
 	wait_queue_head_t more_work;
 	struct work_struct *current_work;
 
-	struct workqueue_struct *wq;
-	struct task_struct *thread;
-} ____cacheline_aligned;
+	struct workqueue_struct *wq;		/* I: the owning workqueue */
+	struct task_struct	*thread;
+} __attribute__((aligned(1 << WORK_STRUCT_FLAG_BITS)));
 
 /*
  * 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 */
+	struct cpu_workqueue_struct *cpu_wq;	/* I: cwq's */
+	struct list_head	list;		/* W: list of all workqueues */
+	const char		*name;		/* I: workqueue name */
 #ifdef CONFIG_LOCKDEP
-	struct lockdep_map lockdep_map;
+	struct lockdep_map	lockdep_map;
 #endif
 };
 
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+
+static struct debug_obj_descr work_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int work_fixup_init(void *addr, enum debug_obj_state state)
+{
+	struct work_struct *work = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		cancel_work_sync(work);
+		debug_object_init(work, &work_debug_descr);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int work_fixup_activate(void *addr, enum debug_obj_state state)
+{
+	struct work_struct *work = addr;
+
+	switch (state) {
+
+	case ODEBUG_STATE_NOTAVAILABLE:
+		/*
+		 * This is not really a fixup. The work struct was
+		 * statically initialized. We just make sure that it
+		 * is tracked in the object tracker.
+		 */
+		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;
+		}
+		WARN_ON_ONCE(1);
+		return 0;
+
+	case ODEBUG_STATE_ACTIVE:
+		WARN_ON(1);
+
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int work_fixup_free(void *addr, enum debug_obj_state state)
+{
+	struct work_struct *work = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		cancel_work_sync(work);
+		debug_object_free(work, &work_debug_descr);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static struct debug_obj_descr work_debug_descr = {
+	.name		= "work_struct",
+	.fixup_init	= work_fixup_init,
+	.fixup_activate	= work_fixup_activate,
+	.fixup_free	= work_fixup_free,
+};
+
+static inline void debug_work_activate(struct work_struct *work)
+{
+	debug_object_activate(work, &work_debug_descr);
+}
+
+static inline void debug_work_deactivate(struct work_struct *work)
+{
+	debug_object_deactivate(work, &work_debug_descr);
+}
+
+void __init_work(struct work_struct *work, int onstack)
+{
+	if (onstack)
+		debug_object_init_on_stack(work, &work_debug_descr);
+	else
+		debug_object_init(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(__init_work);
+
+void destroy_work_on_stack(struct work_struct *work)
+{
+	debug_object_free(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+
+#else
+static inline void debug_work_activate(struct work_struct *work) { }
+static inline void debug_work_deactivate(struct work_struct *work) { }
+#endif
+
 /* Serializes the accesses to the list of workqueues. */
 static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
@@ -84,9 +202,9 @@ static const struct cpumask *cpu_singlethread_map __read_mostly;
 static cpumask_var_t cpu_populated_map __read_mostly;
 
 /* 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 inline bool is_wq_single_threaded(struct workqueue_struct *wq)
 {
-	return wq->singlethread;
+	return wq->flags & WQ_SINGLE_THREAD;
 }
 
 static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
@@ -95,8 +213,8 @@ static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
 		? cpu_singlethread_map : cpu_populated_map;
 }
 
-static
-struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
+static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
+					    struct workqueue_struct *wq)
 {
 	if (unlikely(is_wq_single_threaded(wq)))
 		cpu = singlethread_cpu;
@@ -108,45 +226,61 @@ struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
  * - Must *only* be called if the pending flag is set
  */
 static inline void set_wq_data(struct work_struct *work,
-				struct cpu_workqueue_struct *cwq)
+			       struct cpu_workqueue_struct *cwq,
+			       unsigned long extra_flags)
 {
-	unsigned long new;
-
 	BUG_ON(!work_pending(work));
 
-	new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
-	new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
-	atomic_long_set(&work->data, new);
+	atomic_long_set(&work->data, (unsigned long)cwq |
+			(work_static(work) ? WORK_STRUCT_STATIC : 0) |
+			WORK_STRUCT_PENDING | extra_flags);
 }
 
-static inline
-struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
+static inline struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 {
-	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
+	return (void *)(atomic_long_read(&work->data) &
+			WORK_STRUCT_WQ_DATA_MASK);
 }
 
+/**
+ * insert_work - insert a work into cwq
+ * @cwq: cwq @work belongs to
+ * @work: work to insert
+ * @head: insertion point
+ * @extra_flags: extra WORK_STRUCT_* flags to set
+ *
+ * Insert @work into @cwq after @head.
+ *
+ * CONTEXT:
+ * spin_lock_irq(cwq->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);
+	/* we own @work, set data and link */
+	set_wq_data(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);
 }
 
-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 cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 	unsigned long flags;
 
+	debug_work_activate(work);
 	spin_lock_irqsave(&cwq->lock, flags);
-	insert_work(cwq, work, &cwq->worklist);
+	BUG_ON(!list_empty(&work->entry));
+	insert_work(cwq, work, &cwq->worklist, 0);
 	spin_unlock_irqrestore(&cwq->lock, flags);
 }
 
@@ -187,9 +321,8 @@ 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;
@@ -200,9 +333,8 @@ 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;
 
-	__queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work);
+	__queue_work(smp_processor_id(), cwq->wq, &dwork->work);
 }
 
 /**
@@ -239,14 +371,14 @@ 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))) {
 		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()));
+		set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0);
 		timer->expires = jiffies + delay;
 		timer->data = (unsigned long)dwork;
 		timer->function = delayed_work_timer_fn;
@@ -261,60 +393,88 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
+/**
+ * process_one_work - process single work
+ * @cwq: cwq to process work for
+ * @work: work to process
+ *
+ * Process @work.  This function contains all the logics necessary to
+ * process a single work including synchronization against and
+ * interaction with other workers on the same cpu, queueing and
+ * flushing.  As long as context requirement is met, any worker can
+ * call this function to process a work.
+ *
+ * CONTEXT:
+ * spin_lock_irq(cwq->lock) which is released and regrabbed.
+ */
+static void process_one_work(struct cpu_workqueue_struct *cwq,
+			     struct work_struct *work)
+{
+	work_func_t f = work->func;
+#ifdef CONFIG_LOCKDEP
+	/*
+	 * It is permissible to free the struct work_struct from
+	 * inside the function that is called from it, this we need to
+	 * take into account for lockdep too.  To avoid bogus "held
+	 * lock freed" warnings as well as problems when looking into
+	 * work->lockdep_map, make a copy and use that here.
+	 */
+	struct lockdep_map lockdep_map = work->lockdep_map;
+#endif
+	/* claim and process */
+	debug_work_deactivate(work);
+	cwq->current_work = work;
+	list_del_init(&work->entry);
+
+	spin_unlock_irq(&cwq->lock);
+
+	BUG_ON(get_wq_data(work) != cwq);
+	work_clear_pending(work);
+	lock_map_acquire(&cwq->wq->lockdep_map);
+	lock_map_acquire(&lockdep_map);
+	f(work);
+	lock_map_release(&lockdep_map);
+	lock_map_release(&cwq->wq->lockdep_map);
+
+	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
+		printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
+		       "%s/0x%08x/%d\n",
+		       current->comm, preempt_count(), task_pid_nr(current));
+		printk(KERN_ERR "    last function: ");
+		print_symbol("%s\n", (unsigned long)f);
+		debug_show_held_locks(current);
+		dump_stack();
+	}
+
+	spin_lock_irq(&cwq->lock);
+
+	/* we're done with it, release */
+	cwq->current_work = NULL;
+}
+
 static void run_workqueue(struct cpu_workqueue_struct *cwq)
 {
 	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
-		/*
-		 * It is permissible to free the struct work_struct
-		 * from inside the function that is called from it,
-		 * this we need to take into account for lockdep too.
-		 * To avoid bogus "held lock freed" warnings as well
-		 * as problems when looking into work->lockdep_map,
-		 * make a copy and use that here.
-		 */
-		struct lockdep_map lockdep_map = work->lockdep_map;
-#endif
-		trace_workqueue_execution(cwq->thread, work);
-		cwq->current_work = work;
-		list_del_init(cwq->worklist.next);
-		spin_unlock_irq(&cwq->lock);
-
-		BUG_ON(get_wq_data(work) != cwq);
-		work_clear_pending(work);
-		lock_map_acquire(&cwq->wq->lockdep_map);
-		lock_map_acquire(&lockdep_map);
-		f(work);
-		lock_map_release(&lockdep_map);
-		lock_map_release(&cwq->wq->lockdep_map);
-
-		if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
-			printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
-					"%s/0x%08x/%d\n",
-					current->comm, preempt_count(),
-				       	task_pid_nr(current));
-			printk(KERN_ERR "    last function: ");
-			print_symbol("%s\n", (unsigned long)f);
-			debug_show_held_locks(current);
-			dump_stack();
-		}
-
-		spin_lock_irq(&cwq->lock);
-		cwq->current_work = NULL;
+		process_one_work(cwq, work);
 	}
 	spin_unlock_irq(&cwq->lock);
 }
 
+/**
+ * worker_thread - the worker thread function
+ * @__cwq: cwq to serve
+ *
+ * The cwq worker thread function.
+ */
 static int worker_thread(void *__cwq)
 {
 	struct cpu_workqueue_struct *cwq = __cwq;
 	DEFINE_WAIT(wait);
 
-	if (cwq->wq->freezeable)
+	if (cwq->wq->flags & WQ_FREEZEABLE)
 		set_freezable();
 
 	for (;;) {
@@ -347,15 +507,32 @@ static void wq_barrier_func(struct work_struct *work)
 	complete(&barr->done);
 }
 
+/**
+ * insert_wq_barrier - insert a barrier work
+ * @cwq: cwq to insert barrier into
+ * @barr: wq_barrier to insert
+ * @head: insertion point
+ *
+ * Insert barrier @barr into @cwq before @head.
+ *
+ * CONTEXT:
+ * spin_lock_irq(cwq->lock).
+ */
 static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 			struct wq_barrier *barr, struct list_head *head)
 {
-	INIT_WORK(&barr->work, wq_barrier_func);
-	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
-
+	/*
+	 * debugobject calls are safe here even with cwq->lock locked
+	 * as we know for sure that this will not trigger any of the
+	 * checks and call back into the fixup functions where we
+	 * might deadlock.
+	 */
+	INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
+	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
 	init_completion(&barr->done);
 
-	insert_work(cwq, &barr->work, head);
+	debug_work_activate(&barr->work);
+	insert_work(cwq, &barr->work, head, 0);
 }
 
 static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
@@ -372,8 +549,10 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
 	}
 	spin_unlock_irq(&cwq->lock);
 
-	if (active)
+	if (active) {
 		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+	}
 
 	return active;
 }
@@ -387,9 +566,6 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
  *
  * We sleep until all works which were queued on entry have been handled,
  * but we are not livelocked by new incoming ones.
- *
- * This function used to run the workqueues itself.  Now we just wait for the
- * helper threads to do it.
  */
 void flush_workqueue(struct workqueue_struct *wq)
 {
@@ -428,7 +604,6 @@ int flush_work(struct work_struct *work)
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
 
-	prev = NULL;
 	spin_lock_irq(&cwq->lock);
 	if (!list_empty(&work->entry)) {
 		/*
@@ -437,21 +612,22 @@ int flush_work(struct work_struct *work)
 		 */
 		smp_rmb();
 		if (unlikely(cwq != get_wq_data(work)))
-			goto out;
+			goto already_gone;
 		prev = &work->entry;
 	} else {
 		if (cwq->current_work != work)
-			goto out;
+			goto already_gone;
 		prev = &cwq->worklist;
 	}
 	insert_wq_barrier(cwq, &barr, prev->next);
-out:
-	spin_unlock_irq(&cwq->lock);
-	if (!prev)
-		return 0;
 
+	spin_unlock_irq(&cwq->lock);
 	wait_for_completion(&barr.done);
+	destroy_work_on_stack(&barr.work);
 	return 1;
+already_gone:
+	spin_unlock_irq(&cwq->lock);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -464,7 +640,7 @@ static int try_to_grab_pending(struct work_struct *work)
 	struct cpu_workqueue_struct *cwq;
 	int ret = -1;
 
-	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)))
 		return 0;
 
 	/*
@@ -485,6 +661,7 @@ static int try_to_grab_pending(struct work_struct *work)
 		 */
 		smp_rmb();
 		if (cwq == get_wq_data(work)) {
+			debug_work_deactivate(work);
 			list_del_init(&work->entry);
 			ret = 1;
 		}
@@ -507,8 +684,10 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 	}
 	spin_unlock_irq(&cwq->lock);
 
-	if (unlikely(running))
+	if (unlikely(running)) {
 		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+	}
 }
 
 static void wait_on_work(struct work_struct *work)
@@ -531,7 +710,7 @@ static void wait_on_work(struct work_struct *work)
 	cpu_map = wq_cpu_map(wq);
 
 	for_each_cpu(cpu, cpu_map)
-		wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
+		wait_on_cpu_work(get_cwq(cpu, wq), work);
 }
 
 static int __cancel_work_timer(struct work_struct *work,
@@ -648,9 +827,7 @@ EXPORT_SYMBOL(schedule_delayed_work);
 void flush_delayed_work(struct delayed_work *dwork)
 {
 	if (del_timer_sync(&dwork->timer)) {
-		struct cpu_workqueue_struct *cwq;
-		cwq = wq_per_cpu(keventd_wq, get_cpu());
-		__queue_work(cwq, &dwork->work);
+		__queue_work(get_cpu(), keventd_wq, &dwork->work);
 		put_cpu();
 	}
 	flush_work(&dwork->work);
@@ -788,7 +965,6 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
 
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 	struct workqueue_struct *wq = cwq->wq;
 	const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
 	struct task_struct *p;
@@ -804,12 +980,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 	 */
 	if (IS_ERR(p))
 		return PTR_ERR(p);
-	if (cwq->wq->rt)
-		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
 	cwq->thread = p;
 
-	trace_workqueue_creation(cwq->thread, cpu);
-
 	return 0;
 }
 
@@ -825,9 +997,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 }
 
 struct workqueue_struct *__create_workqueue_key(const char *name,
-						int singlethread,
-						int freezeable,
-						int rt,
+						unsigned int flags,
 						struct lock_class_key *key,
 						const char *lock_name)
 {
@@ -837,22 +1007,18 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
 	if (!wq)
-		return NULL;
+		goto err;
 
 	wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
-	if (!wq->cpu_wq) {
-		kfree(wq);
-		return NULL;
-	}
+	if (!wq->cpu_wq)
+		goto err;
 
+	wq->flags = flags;
 	wq->name = name;
 	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
-	wq->singlethread = singlethread;
-	wq->freezeable = freezeable;
-	wq->rt = rt;
 	INIT_LIST_HEAD(&wq->list);
 
-	if (singlethread) {
+	if (flags & WQ_SINGLE_THREAD) {
 		cwq = init_cpu_workqueue(wq, singlethread_cpu);
 		err = create_workqueue_thread(cwq, singlethread_cpu);
 		start_workqueue_thread(cwq, -1);
@@ -888,6 +1054,12 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 		wq = NULL;
 	}
 	return wq;
+err:
+	if (wq) {
+		free_percpu(wq->cpu_wq);
+		kfree(wq);
+	}
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(__create_workqueue_key);
 
@@ -914,7 +1086,6 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 	 * checks list_empty(), and a "normal" queue_work() can't use
 	 * a dead CPU.
 	 */
-	trace_workqueue_destruction(cwq->thread);
 	kthread_stop(cwq->thread);
 	cwq->thread = NULL;
 }
@@ -1043,6 +1214,15 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 
 void __init init_workqueues(void)
 {
+	/*
+	 * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
+	 * Make sure that the alignment isn't lower than that of
+	 * unsigned long long in case this code survives for longer
+	 * than twenty years.  :-P
+	 */
+	BUILD_BUG_ON(__alignof__(struct cpu_workqueue_struct) <
+		     __alignof__(unsigned long long));
+
 	alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
 
 	cpumask_copy(cpu_populated_map, cpu_online_mask);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a24efcc3e6f0..62a33f3a2b49 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -298,6 +298,14 @@ config DEBUG_OBJECTS_TIMERS
 	  timer routines to track the life time of timer objects and
 	  validate the timer operations.
 
+config DEBUG_OBJECTS_WORK
+	bool "Debug work objects"
+	depends on DEBUG_OBJECTS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  work queue routines to track the life time of work objects and
+	  validate the work operations.
+
 config DEBUG_OBJECTS_ENABLE_DEFAULT
 	int "debug_objects bootup default value (0-1)"
         range 0 1
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e1f2bf8d7b1e..9ebb284403f9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -77,7 +77,7 @@ static atomic_t hardware_enable_failed;
 struct kmem_cache *kvm_vcpu_cache;
 EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
 
-static __read_mostly struct preempt_ops kvm_preempt_ops;
+static __read_mostly struct sched_notifier_ops kvm_sched_notifier_ops;
 
 struct dentry *kvm_debugfs_dir;
 
@@ -109,7 +109,7 @@ void vcpu_load(struct kvm_vcpu *vcpu)
 
 	mutex_lock(&vcpu->mutex);
 	cpu = get_cpu();
-	preempt_notifier_register(&vcpu->preempt_notifier);
+	sched_notifier_register(&vcpu->sched_notifier);
 	kvm_arch_vcpu_load(vcpu, cpu);
 	put_cpu();
 }
@@ -118,7 +118,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
-	preempt_notifier_unregister(&vcpu->preempt_notifier);
+	sched_notifier_unregister(&vcpu->sched_notifier);
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
 }
@@ -1192,7 +1192,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
 
-	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
+	sched_notifier_init(&vcpu->sched_notifier, &kvm_sched_notifier_ops);
 
 	r = kvm_arch_vcpu_setup(vcpu);
 	if (r)
@@ -2026,23 +2026,21 @@ static struct sys_device kvm_sysdev = {
 struct page *bad_page;
 pfn_t bad_pfn;
 
-static inline
-struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
+static inline struct kvm_vcpu *sched_notifier_to_vcpu(struct sched_notifier *sn)
 {
-	return container_of(pn, struct kvm_vcpu, preempt_notifier);
+	return container_of(sn, struct kvm_vcpu, sched_notifier);
 }
 
-static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
+static void kvm_sched_in(struct sched_notifier *sn, struct task_struct *prev)
 {
-	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+	struct kvm_vcpu *vcpu = sched_notifier_to_vcpu(sn);
 
-	kvm_arch_vcpu_load(vcpu, cpu);
+	kvm_arch_vcpu_load(vcpu, smp_processor_id());
 }
 
-static void kvm_sched_out(struct preempt_notifier *pn,
-			  struct task_struct *next)
+static void kvm_sched_out(struct sched_notifier *sn, struct task_struct *next)
 {
-	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+	struct kvm_vcpu *vcpu = sched_notifier_to_vcpu(sn);
 
 	kvm_arch_vcpu_put(vcpu);
 }
@@ -2115,8 +2113,8 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		goto out_free;
 	}
 
-	kvm_preempt_ops.sched_in = kvm_sched_in;
-	kvm_preempt_ops.sched_out = kvm_sched_out;
+	kvm_sched_notifier_ops.in = kvm_sched_in;
+	kvm_sched_notifier_ops.out = kvm_sched_out;
 
 	kvm_init_debug();