concurrency managed workqueue, take#3

index c535cc4..09d97e3 100644
@@ -2288,12 +2288,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
 
 	/* Look for allowed, online CPU in same node. */
-	for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+	for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
 		if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 			return dest_cpu;
 
 	/* Any allowed, online CPU? */
-	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
+	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
 	if (dest_cpu < nr_cpu_ids)
 		return dest_cpu;
 

@@ -2302,6 +2302,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		rcu_read_lock();
 		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
 		rcu_read_unlock();
+		/* breaking affinity, consider active mask instead */
 		dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
 
 		/*

index bd5a616..8079759 100644
@@ -74,8 +74,8 @@ 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;
+#ifdef CONFIG_SCHED_NOTIFIERS
+	struct sched_notifier sched_notifier;
 #endif
 	int vcpu_id;
 	struct mutex mutex;

52 lines not on this page · raw message

65 lines not on this page · raw message

144 lines not on this page · raw message

index a944be3..557d5f9 100644
@@ -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);
 }

@@ -1195,7 +1195,7 @@ 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)

@@ -2029,23 +2029,21 @@ 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, int cpu)
 {
-	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+	struct kvm_vcpu *vcpu = sched_notifier_to_vcpu(sn);
 
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
 
-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);
 }

@@ -2118,8 +2116,8 @@ 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();
 

index 768d313..7633915 100644
@@ -2391,11 +2391,67 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 }
 #endif
 
-/***
+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_post_activation(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_woken)
+		p->sched_class->task_woken(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
+}
+
+/**
  * try_to_wake_up - wake up a thread
- * @p: the to-be-woken-up thread
+ * @p: the thread to be awakened
  * @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

@@ -2403,7 +2459,8 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
  * 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)

@@ -2475,54 +2532,11 @@ 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;
-
-	/*
-	 * 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;
-	}
-
 out_running:
-	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_woken)
-		p->sched_class->task_woken(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
+	ttwu_post_activation(p, rq, wake_flags, success);
 out:
 	task_rq_unlock(rq, &flags);
 	put_cpu();

index b65c23b..803c6a8 100644
@@ -1871,11 +1871,11 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
-extern int set_cpus_allowed_ptr(struct task_struct *p,
-				const struct cpumask *new_mask);
+extern int __set_cpus_allowed(struct task_struct *p,
+			      const struct cpumask *new_mask, bool force);
 #else
-static inline 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, bool force)
 {
 	if (!cpumask_test_cpu(0, new_mask))
 		return -EINVAL;

@@ -1883,6 +1883,12 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 }
 #endif
 
+static inline int set_cpus_allowed_ptr(struct task_struct *p,
+				       const struct cpumask *new_mask)
+{
+	return __set_cpus_allowed(p, new_mask, false);
+}
+
 #ifndef CONFIG_CPUMASK_OFFSTACK
 static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 {

132 lines not on this page · raw message

index 8079759..45b631e 100644
@@ -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_SCHED_NOTIFIERS
 	struct sched_notifier sched_notifier;
-#endif
 	int vcpu_id;
 	struct mutex mutex;
 	int   cpu;

index 803c6a8..9fc537a 100644
@@ -1218,8 +1218,6 @@ struct sched_rt_entity {
 #endif
 };
 
-#ifdef CONFIG_SCHED_NOTIFIERS
-
 struct sched_notifier;
 
 /**

@@ -1263,8 +1261,6 @@ static inline void sched_notifier_init(struct sched_notifier *notifier,
 	notifier->ops = ops;
 }
 
-#endif	/* CONFIG_SCHED_NOTIFIERS */
-
 struct rcu_node;
 
 struct task_struct {

@@ -1288,10 +1284,8 @@ struct task_struct {
 	struct sched_entity se;
 	struct sched_rt_entity rt;
 
-#ifdef CONFIG_SCHED_NOTIFIERS
 	/* list of struct sched_notifier: */
 	struct hlist_head sched_notifiers;
-#endif
 
 	/*
 	 * fpu_counter contains the number of consecutive context switches

index 63fcada..30b7ea8 100644
@@ -1434,8 +1434,6 @@ static inline void cpuacct_update_stats(struct task_struct *tsk,
 		enum cpuacct_stat_index idx, cputime_t val) {}
 #endif
 
-#ifdef CONFIG_SCHED_NOTIFIERS
-
 #define fire_sched_notifiers(p, callback, args...) do {			\
 	struct sched_notifier *__sn;					\
 	struct hlist_node *__pos;					\

@@ -1466,12 +1464,6 @@ void sched_notifier_unregister(struct sched_notifier *notifier)
 }
 EXPORT_SYMBOL_GPL(sched_notifier_unregister);
 
-#else	/* !CONFIG_SCHED_NOTIFIERS */
-
-#define fire_sched_notifiers(p, callback, args...)	do { } while (0)
-
-#endif	/* CONFIG_SCHED_NOTIFIERS */
-
 static inline void inc_cpu_load(struct rq *rq, unsigned long load)
 {
 	update_load_add(&rq->load, load);

@@ -2621,10 +2613,7 @@ 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_SCHED_NOTIFIERS
 	INIT_HLIST_HEAD(&p->sched_notifiers);
-#endif
 }
 
 /*

@@ -9648,9 +9637,7 @@ void __init sched_init(void)
 
 	set_load_weight(&init_task);
 
-#ifdef CONFIG_SCHED_NOTIFIERS
 	INIT_HLIST_HEAD(&init_task.sched_notifiers);
-#endif
 
 #ifdef CONFIG_SMP
 	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);

index 9fc537a..a6b4e9c 100644
@@ -1222,6 +1222,10 @@ 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 about to be rescheduled:
  *    notifier: struct sched_notifier for the task being scheduled
  *    cpu:  cpu we're scheduled on

@@ -1235,6 +1239,8 @@ struct sched_notifier;
  * and depended upon by its users.
  */
 struct sched_notifier_ops {
+	void (*wakeup)(struct sched_notifier *notifier);
+	void (*sleep)(struct sched_notifier *notifier);
 	void (*in)(struct sched_notifier *notifier, int cpu);
 	void (*out)(struct sched_notifier *notifier, struct task_struct *next);
 };

index 30b7ea8..eae624f 100644
@@ -1439,7 +1439,8 @@ static inline void cpuacct_update_stats(struct task_struct *tsk,
 	struct hlist_node *__pos;					\
 									\
 	hlist_for_each_entry(__sn, __pos, &(p)->sched_notifiers, link)	\
-		__sn->ops->callback(__sn , ##args);			\
+		if (__sn->ops->callback)				\
+			__sn->ops->callback(__sn , ##args);		\
 } while (0)
 
 /**

@@ -2439,6 +2440,8 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
 		rq->idle_stamp = 0;
 	}
 #endif
+	if (success)
+		fire_sched_notifiers(p, wakeup);
 }
 
 /**

@@ -5481,10 +5484,12 @@ 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_sched_notifiers(prev, sleep);
 			deactivate_task(rq, prev, 1);
+		}
 		switch_count = &prev->nvcsw;
 	}
 

index a6b4e9c..d7db574 100644
@@ -2094,6 +2094,8 @@ 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,

74 lines not on this page · raw message

index 02e8464..93f6647 100644
@@ -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

index baba3a2..2d32e06 100644
@@ -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 */

index 9466e86..0697946 100644
@@ -181,12 +181,11 @@ static inline void destroy_work_on_stack(struct work_struct *work) { }
 
 
 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, int singlethread, int freezeable,
+		       struct lock_class_key *key, const char *lock_name);
 
 #ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
+#define __create_workqueue(name, singlethread, freezeable)	\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\

@@ -197,19 +196,18 @@ __create_workqueue_key(const char *name, int singlethread,
 		__lock_name = #name;				\
 								\
 	__create_workqueue_key((name), (singlethread),		\
-			       (freezeable), (rt), &__key,	\
+			       (freezeable), &__key,		\
 			       __lock_name);			\
 })
 #else
-#define __create_workqueue(name, singlethread, freezeable, rt)	\
-	__create_workqueue_key((name), (singlethread), (freezeable), (rt), \
+#define __create_workqueue(name, singlethread, freezeable)	\
+	__create_workqueue_key((name), (singlethread), (freezeable), \
 			       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, 0)
+#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1)
+#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 

index dac44a9..adb09f8 100644
@@ -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>

@@ -769,6 +770,7 @@ 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();

229 lines not on this page · raw message

index dee4865..3dccec6 100644
@@ -62,7 +62,6 @@ struct workqueue_struct {
 	const char *name;
 	int singlethread;
 	int freezeable;		/* Freeze threads during suspend */
-	int rt;
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map lockdep_map;
 #endif

@@ -913,7 +912,6 @@ 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;

@@ -929,8 +927,6 @@ 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);

@@ -952,7 +948,6 @@ 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,
 						struct lock_class_key *key,
 						const char *lock_name)
 {

@@ -974,7 +969,6 @@ struct workqueue_struct *__create_workqueue_key(const char *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) {

index 0697946..ac06c55 100644
@@ -96,9 +96,14 @@ struct execute_work {
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 extern void __init_work(struct work_struct *work, int onstack);
 extern void destroy_work_on_stack(struct work_struct *work);
+static inline bool work_static(struct work_struct *work)
+{
+	return test_bit(WORK_STRUCT_STATIC, 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
 
 /*

282 lines not on this page · raw message

index ac06c55..495572a 100644
@@ -184,13 +184,17 @@ static inline bool work_static(struct work_struct *work) { return false; }
 #define work_clear_pending(work) \
 	clear_bit(WORK_STRUCT_PENDING, 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,
+__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)	\
+#define __create_workqueue(name, flags)				\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\

@@ -200,19 +204,20 @@ __create_workqueue_key(const char *name, int singlethread, int freezeable,
 	else							\
 		__lock_name = #name;				\
 								\
-	__create_workqueue_key((name), (singlethread),		\
-			       (freezeable), &__key,		\
+	__create_workqueue_key((name), (flags), &__key,		\
 			       __lock_name);			\
 })
 #else
-#define __create_workqueue(name, singlethread, freezeable)	\
-	__create_workqueue_key((name), (singlethread), (freezeable), \
-			       NULL, NULL)
+#define __create_workqueue(name, flags)				\
+	__create_workqueue_key((name), (flags), NULL, NULL)
 #endif
 
-#define create_workqueue(name) __create_workqueue((name), 0, 0)
-#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1)
-#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 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);
 

index e16c457..579041f 100644
@@ -67,11 +67,10 @@ struct cpu_workqueue_struct {
  * per-CPU workqueues:
  */
 struct workqueue_struct {
+	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 */
-	int singlethread;
-	int freezeable;		/* Freeze threads during suspend */
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map	lockdep_map;
 #endif

@@ -203,9 +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)

@@ -456,7 +455,7 @@ 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 (;;) {

@@ -981,8 +980,7 @@ 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,
+						unsigned int flags,
 						struct lock_class_key *key,
 						const char *lock_name)
 {

@@ -998,13 +996,12 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 	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;
 	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);

index 495572a..e51b5dc 100644
@@ -22,12 +22,19 @@ 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,
+
+	WORK_STRUCT_FLAG_MASK	= 3UL,
+	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_STATIC  1		/* static initializer (debugobjects) */
-#define WORK_STRUCT_FLAG_MASK (3UL)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
 	struct list_head entry;
 	work_func_t func;
 #ifdef CONFIG_LOCKDEP

@@ -36,7 +43,7 @@ struct work_struct {
 };
 
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT(0)
-#define WORK_DATA_STATIC_INIT()	ATOMIC_LONG_INIT(2)
+#define WORK_DATA_STATIC_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_STATIC)
 
 struct delayed_work {
 	struct work_struct work;

@@ -98,7 +105,7 @@ 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, work_data_bits(work));
+	return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work));
 }
 #else
 static inline void __init_work(struct work_struct *work, int onstack) { }

@@ -167,7 +174,7 @@ static inline bool work_static(struct work_struct *work) { return false; }
  * @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

@@ -182,7 +189,7 @@ static inline bool work_static(struct work_struct *work) { return false; }
  * @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 */

index 579041f..f8e4d67 100644
@@ -115,7 +115,7 @@ 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;

@@ -232,8 +232,8 @@ static inline void set_wq_data(struct work_struct *work,
 	BUG_ON(!work_pending(work));
 
 	atomic_long_set(&work->data, (unsigned long)cwq |
-			(work_static(work) ? (1UL << WORK_STRUCT_STATIC) : 0) |
-			(1UL << WORK_STRUCT_PENDING) | extra_flags);
+			(work_static(work) ? WORK_STRUCT_STATIC : 0) |
+			WORK_STRUCT_PENDING | extra_flags);
 }
 
 static inline

@@ -323,7 +323,7 @@ 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))) {
+	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		__queue_work(cpu, wq, work);
 		ret = 1;
 	}

@@ -373,7 +373,7 @@ 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));
 

@@ -509,7 +509,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 	 * might deadlock.
 	 */
 	INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
-	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
+	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
 	init_completion(&barr->done);
 
 	debug_work_activate(&barr->work);

@@ -621,7 +621,7 @@ 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;
 
 	/*

index f8e4d67..aa1d680 100644
@@ -395,51 +395,73 @@ 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 */
+	trace_workqueue_execution(cwq->thread, work);
+	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);
-		debug_work_deactivate(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);
 }

index aa1d680..a48a9b8 100644
@@ -33,8 +33,6 @@
 #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.

@@ -236,10 +234,10 @@ static inline void set_wq_data(struct work_struct *work,
 			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);
 }
 
 /**

@@ -258,8 +256,6 @@ static void insert_work(struct cpu_workqueue_struct *cwq,
 			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);
 

@@ -424,7 +420,6 @@ static void process_one_work(struct cpu_workqueue_struct *cwq,
 	struct lockdep_map lockdep_map = work->lockdep_map;
 #endif
 	/* claim and process */
-	trace_workqueue_execution(cwq->thread, work);
 	debug_work_deactivate(work);
 	cwq->current_work = work;
 	list_del_init(&work->entry);

@@ -985,8 +980,6 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 		return PTR_ERR(p);
 	cwq->thread = p;
 
-	trace_workqueue_creation(cwq->thread, cpu);
-
 	return 0;
 }
 

@@ -1091,7 +1084,6 @@ 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;
 }

index a48a9b8..d29e069 100644
@@ -189,34 +189,19 @@ static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
 
 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.
- */
-static cpumask_var_t cpu_populated_map __read_mostly;
-
-/* If it's single threaded, it isn't in the list of workqueues. */
-static inline bool is_wq_single_threaded(struct workqueue_struct *wq)
-{
-	return wq->flags & WQ_SINGLE_THREAD;
-}
 
-static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
+static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
+					    struct workqueue_struct *wq)
 {
-	return is_wq_single_threaded(wq)
-		? cpu_singlethread_map : cpu_populated_map;
+	return per_cpu_ptr(wq->cpu_wq, cpu);
 }
 
-static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
-					    struct workqueue_struct *wq)
+static struct cpu_workqueue_struct *target_cwq(unsigned int cpu,
+					       struct workqueue_struct *wq)
 {
-	if (unlikely(is_wq_single_threaded(wq)))
+	if (unlikely(wq->flags & WQ_SINGLE_THREAD))
 		cpu = singlethread_cpu;
-	return per_cpu_ptr(wq->cpu_wq, cpu);
+	return get_cwq(cpu, wq);
 }
 
 /*

@@ -272,7 +257,7 @@ static void insert_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);
+	struct cpu_workqueue_struct *cwq = target_cwq(cpu, wq);
 	unsigned long flags;
 
 	debug_work_activate(work);

@@ -376,7 +361,7 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 		timer_stats_timer_set_start_info(&dwork->timer);
 
 		/* This stores cwq for the moment, for the timer_fn */
-		set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0);
+		set_wq_data(work, target_cwq(raw_smp_processor_id(), wq), 0);
 		timer->expires = jiffies + delay;
 		timer->data = (unsigned long)dwork;
 		timer->function = delayed_work_timer_fn;

@@ -567,14 +552,13 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
  */
 void flush_workqueue(struct workqueue_struct *wq)
 {
-	const struct cpumask *cpu_map = wq_cpu_map(wq);
 	int cpu;
 
 	might_sleep();
 	lock_map_acquire(&wq->lockdep_map);
 	lock_map_release(&wq->lockdep_map);
-	for_each_cpu(cpu, cpu_map)
-		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
+	for_each_possible_cpu(cpu)
+		flush_cpu_workqueue(get_cwq(cpu, wq));
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 

@@ -692,7 +676,6 @@ static void wait_on_work(struct work_struct *work)
 {
 	struct cpu_workqueue_struct *cwq;
 	struct workqueue_struct *wq;
-	const struct cpumask *cpu_map;
 	int cpu;
 
 	might_sleep();

@@ -705,9 +688,8 @@ static void wait_on_work(struct work_struct *work)
 		return;
 
 	wq = cwq->wq;
-	cpu_map = wq_cpu_map(wq);
 
-	for_each_cpu(cpu, cpu_map)
+	for_each_possible_cpu(cpu)
 		wait_on_cpu_work(get_cwq(cpu, wq), work);
 }
 

@@ -940,7 +922,7 @@ int current_is_keventd(void)
 
 	BUG_ON(!keventd_wq);
 
-	cwq = per_cpu_ptr(keventd_wq->cpu_wq, cpu);
+	cwq = get_cwq(cpu, keventd_wq);
 	if (current == cwq->thread)
 		ret = 1;
 

@@ -948,26 +930,12 @@ int current_is_keventd(void)
 
 }
 
-static struct cpu_workqueue_struct *
-init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
-{
-	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
-
-	cwq->wq = wq;
-	spin_lock_init(&cwq->lock);
-	INIT_LIST_HEAD(&cwq->worklist);
-	init_waitqueue_head(&cwq->more_work);
-
-	return cwq;
-}
-
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
 	struct workqueue_struct *wq = cwq->wq;
-	const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
 	struct task_struct *p;
 
-	p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
+	p = kthread_create(worker_thread, cwq, "%s/%d", wq->name, cpu);
 	/*
 	 * Nobody can add the work_struct to this cwq,
 	 *	if (caller is __create_workqueue)

@@ -999,8 +967,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 						struct lock_class_key *key,
 						const char *lock_name)
 {
+	bool singlethread = flags & WQ_SINGLE_THREAD;
 	struct workqueue_struct *wq;
-	struct cpu_workqueue_struct *cwq;
 	int err = 0, cpu;
 
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);

@@ -1016,41 +984,40 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
 	INIT_LIST_HEAD(&wq->list);
 
-	if (flags & WQ_SINGLE_THREAD) {
-		cwq = init_cpu_workqueue(wq, singlethread_cpu);
-		err = create_workqueue_thread(cwq, singlethread_cpu);
-		start_workqueue_thread(cwq, -1);
-	} else {
-		cpu_maps_update_begin();
-		/*
-		 * We must place this wq on list even if the code below fails.
-		 * cpu_down(cpu) can remove cpu from cpu_populated_map before
-		 * destroy_workqueue() takes the lock, in that case we leak
-		 * cwq[cpu]->thread.
-		 */
-		spin_lock(&workqueue_lock);
-		list_add(&wq->list, &workqueues);
-		spin_unlock(&workqueue_lock);
-		/*
-		 * We must initialize cwqs for each possible cpu even if we
-		 * are going to call destroy_workqueue() finally. Otherwise
-		 * cpu_up() can hit the uninitialized cwq once we drop the
-		 * lock.
-		 */
-		for_each_possible_cpu(cpu) {
-			cwq = init_cpu_workqueue(wq, cpu);
-			if (err || !cpu_online(cpu))
-				continue;
-			err = create_workqueue_thread(cwq, cpu);
+	cpu_maps_update_begin();
+	/*
+	 * We must initialize cwqs for each possible cpu even if we
+	 * are going to call destroy_workqueue() finally. Otherwise
+	 * cpu_up() can hit the uninitialized cwq once we drop the
+	 * lock.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+
+		cwq->wq = wq;
+		spin_lock_init(&cwq->lock);
+		INIT_LIST_HEAD(&cwq->worklist);
+		init_waitqueue_head(&cwq->more_work);
+
+		if (err)
+			continue;
+		err = create_workqueue_thread(cwq, cpu);
+		if (cpu_online(cpu) && !singlethread)
 			start_workqueue_thread(cwq, cpu);
-		}
-		cpu_maps_update_done();
+		else
+			start_workqueue_thread(cwq, -1);
 	}
+	cpu_maps_update_done();
 
 	if (err) {
 		destroy_workqueue(wq);
 		wq = NULL;
 	}
+
+	spin_lock(&workqueue_lock);
+	list_add(&wq->list, &workqueues);
+	spin_unlock(&workqueue_lock);
+
 	return wq;
 err:
 	if (wq) {

@@ -1096,17 +1063,14 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
  */
 void destroy_workqueue(struct workqueue_struct *wq)
 {
-	const struct cpumask *cpu_map = wq_cpu_map(wq);
 	int cpu;
 
-	cpu_maps_update_begin();
 	spin_lock(&workqueue_lock);
 	list_del(&wq->list);
 	spin_unlock(&workqueue_lock);
 
-	for_each_cpu(cpu, cpu_map)
-		cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
- 	cpu_maps_update_done();
+	for_each_possible_cpu(cpu)
+		cleanup_workqueue_thread(get_cwq(cpu, wq));
 
 	free_percpu(wq->cpu_wq);
 	kfree(wq);

@@ -1120,47 +1084,30 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 	unsigned int cpu = (unsigned long)hcpu;
 	struct cpu_workqueue_struct *cwq;
 	struct workqueue_struct *wq;
-	int ret = NOTIFY_OK;
 
 	action &= ~CPU_TASKS_FROZEN;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		cpumask_set_cpu(cpu, cpu_populated_map);
-	}
-undo:
 	list_for_each_entry(wq, &workqueues, list) {
-		cwq = per_cpu_ptr(wq->cpu_wq, cpu);
+		if (wq->flags & WQ_SINGLE_THREAD)
+			continue;
 
-		switch (action) {
-		case CPU_UP_PREPARE:
-			if (!create_workqueue_thread(cwq, cpu))
-				break;
-			printk(KERN_ERR "workqueue [%s] for %i failed\n",
-				wq->name, cpu);
-			action = CPU_UP_CANCELED;
-			ret = NOTIFY_BAD;
-			goto undo;
+		cwq = get_cwq(cpu, wq);
 
+		switch (action) {
 		case CPU_ONLINE:
-			start_workqueue_thread(cwq, cpu);
+			__set_cpus_allowed(cwq->thread, get_cpu_mask(cpu),
+					   true);
 			break;
 
-		case CPU_UP_CANCELED:
-			start_workqueue_thread(cwq, -1);
 		case CPU_POST_DEAD:
-			cleanup_workqueue_thread(cwq);
+			lock_map_acquire(&cwq->wq->lockdep_map);
+			lock_map_release(&cwq->wq->lockdep_map);
+			flush_cpu_workqueue(cwq);
 			break;
 		}
 	}
 
-	switch (action) {
-	case CPU_UP_CANCELED:
-	case CPU_POST_DEAD:
-		cpumask_clear_cpu(cpu, cpu_populated_map);
-	}
-
-	return ret;
+	return NOTIFY_OK;
 }
 
 #ifdef CONFIG_SMP

@@ -1212,11 +1159,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 
 void __init init_workqueues(void)
 {
-	alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
-
-	cpumask_copy(cpu_populated_map, cpu_online_mask);
 	singlethread_cpu = cpumask_first(cpu_possible_mask);
-	cpu_singlethread_map = cpumask_of(singlethread_cpu);
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);

index e51b5dc..011738a 100644
@@ -29,7 +29,9 @@ enum {
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
 
-	WORK_STRUCT_FLAG_MASK	= 3UL,
+	WORK_STRUCT_FLAG_BITS	= 2,
+
+	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
 	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
 };
 

107 lines not on this page · raw message

index 011738a..316cc48 100644
@@ -29,7 +29,22 @@ enum {
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
 
-	WORK_STRUCT_FLAG_BITS	= 2,
+	WORK_STRUCT_COLOR_SHIFT	= 3,	/* color for workqueue flushing */
+	WORK_STRUCT_COLOR_BITS	= 4,
+
+	/*
+	 * The last color is no color used for works which don't
+	 * participate in workqueue flushing.
+	 */
+	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS) - 1,
+	WORK_NO_COLOR		= WORK_NR_COLORS,
+
+	/*
+	 * Reserve 7 bits off of cwq pointer.  This makes cwqs aligned
+	 * to 128 bytes which isn't too excessive while allowing 15
+	 * workqueue flush colors.
+	 */
+	WORK_STRUCT_FLAG_BITS	= 7,
 
 	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
 	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,

468 lines not on this page · raw message

index 9e55c80..17d270b 100644
@@ -33,6 +33,7 @@
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
+#include <linux/idr.h>
 
 /*
  * Structure fields follow one of the following exclusion rules.

@@ -46,6 +47,15 @@
  * W: workqueue_lock protected.
  */
 
+struct cpu_workqueue_struct;
+
+struct worker {
+	struct work_struct	*current_work;	/* L: work being processed */
+	struct task_struct	*task;		/* I: worker task */
+	struct cpu_workqueue_struct *cwq;	/* I: the associated cwq */
+	int			id;		/* I: worker id */
+};
+
 /*
  * The per-CPU workqueue (if single thread, we always use the first
  * possible cpu).  The lower WORK_STRUCT_FLAG_BITS of

@@ -58,14 +68,14 @@ struct cpu_workqueue_struct {
 
 	struct list_head worklist;
 	wait_queue_head_t more_work;
-	struct work_struct *current_work;
+	unsigned int		cpu;
+	struct worker		*worker;
 
 	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 */
-	struct task_struct	*thread;
 };
 
 /*

@@ -213,6 +223,9 @@ 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 DEFINE_PER_CPU(struct ida, worker_ida);
+
+static int worker_thread(void *__worker);
 
 static int singlethread_cpu __read_mostly;
 

@@ -420,6 +433,105 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
+static struct worker *alloc_worker(void)
+{
+	struct worker *worker;
+
+	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
+	return worker;
+}
+
+/**
+ * create_worker - create a new workqueue worker
+ * @cwq: cwq the new worker will belong to
+ * @bind: whether to set affinity to @cpu or not
+ *
+ * Create a new worker which is bound to @cwq.  The returned worker
+ * can be started by calling start_worker() or destroyed using
+ * destroy_worker().
+ *
+ * CONTEXT:
+ * Might sleep.  Does GFP_KERNEL allocations.
+ *
+ * RETURNS:
+ * Pointer to the newly created worker.
+ */
+static struct worker *create_worker(struct cpu_workqueue_struct *cwq, bool bind)
+{
+	int id = -1;
+	struct worker *worker = NULL;
+
+	spin_lock(&workqueue_lock);
+	while (ida_get_new(&per_cpu(worker_ida, cwq->cpu), &id)) {
+		spin_unlock(&workqueue_lock);
+		if (!ida_pre_get(&per_cpu(worker_ida, cwq->cpu), GFP_KERNEL))
+			goto fail;
+		spin_lock(&workqueue_lock);
+	}
+	spin_unlock(&workqueue_lock);
+
+	worker = alloc_worker();
+	if (!worker)
+		goto fail;
+
+	worker->cwq = cwq;
+	worker->id = id;
+
+	worker->task = kthread_create(worker_thread, worker, "kworker/%u:%d",
+				      cwq->cpu, id);
+	if (IS_ERR(worker->task))
+		goto fail;
+
+	if (bind)
+		kthread_bind(worker->task, cwq->cpu);
+
+	return worker;
+fail:
+	if (id >= 0) {
+		spin_lock(&workqueue_lock);
+		ida_remove(&per_cpu(worker_ida, cwq->cpu), id);
+		spin_unlock(&workqueue_lock);
+	}
+	kfree(worker);
+	return NULL;
+}
+
+/**
+ * start_worker - start a newly created worker
+ * @worker: worker to start
+ *
+ * Start @worker.
+ *
+ * CONTEXT:
+ * spin_lock_irq(cwq->lock).
+ */
+static void start_worker(struct worker *worker)
+{
+	wake_up_process(worker->task);
+}
+
+/**
+ * destroy_worker - destroy a workqueue worker
+ * @worker: worker to be destroyed
+ *
+ * Destroy @worker.
+ */
+static void destroy_worker(struct worker *worker)
+{
+	int cpu = worker->cwq->cpu;
+	int id = worker->id;
+
+	/* sanity check frenzy */
+	BUG_ON(worker->current_work);
+
+	kthread_stop(worker->task);
+	kfree(worker);
+
+	spin_lock(&workqueue_lock);
+	ida_remove(&per_cpu(worker_ida, cpu), id);
+	spin_unlock(&workqueue_lock);
+}
+
 /**
  * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
  * @cwq: cwq of interest

@@ -460,7 +572,7 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
 
 /**
  * process_one_work - process single work
- * @cwq: cwq to process work for
+ * @worker: self
  * @work: work to process
  *
  * Process @work.  This function contains all the logics necessary to

@@ -472,9 +584,9 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
  * 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)
+static void process_one_work(struct worker *worker, struct work_struct *work)
 {
+	struct cpu_workqueue_struct *cwq = worker->cwq;
 	work_func_t f = work->func;
 	int work_color;
 #ifdef CONFIG_LOCKDEP

@@ -489,7 +601,7 @@ static void process_one_work(struct cpu_workqueue_struct *cwq,
 #endif
 	/* claim and process */
 	debug_work_deactivate(work);
-	cwq->current_work = work;
+	worker->current_work = work;
 	work_color = work_flags_to_color(*work_data_bits(work));
 	list_del_init(&work->entry);
 

@@ -516,30 +628,33 @@ static void process_one_work(struct cpu_workqueue_struct *cwq,
 	spin_lock_irq(&cwq->lock);
 
 	/* we're done with it, release */
-	cwq->current_work = NULL;
+	worker->current_work = NULL;
 	cwq_dec_nr_in_flight(cwq, work_color);
 }
 
-static void run_workqueue(struct cpu_workqueue_struct *cwq)
+static void run_workqueue(struct worker *worker)
 {
+	struct cpu_workqueue_struct *cwq = worker->cwq;
+
 	spin_lock_irq(&cwq->lock);
 	while (!list_empty(&cwq->worklist)) {
 		struct work_struct *work = list_entry(cwq->worklist.next,
 						struct work_struct, entry);
-		process_one_work(cwq, work);
+		process_one_work(worker, work);
 	}
 	spin_unlock_irq(&cwq->lock);
 }
 
 /**
  * worker_thread - the worker thread function
- * @__cwq: cwq to serve
+ * @__worker: self
  *
  * The cwq worker thread function.
  */
-static int worker_thread(void *__cwq)
+static int worker_thread(void *__worker)
 {
-	struct cpu_workqueue_struct *cwq = __cwq;
+	struct worker *worker = __worker;
+	struct cpu_workqueue_struct *cwq = worker->cwq;
 	DEFINE_WAIT(wait);
 
 	if (cwq->wq->flags & WQ_FREEZEABLE)

@@ -558,7 +673,7 @@ static int worker_thread(void *__cwq)
 		if (kthread_should_stop())
 			break;
 
-		run_workqueue(cwq);
+		run_workqueue(worker);
 	}
 
 	return 0;

@@ -856,7 +971,7 @@ int flush_work(struct work_struct *work)
 			goto already_gone;
 		prev = &work->entry;
 	} else {
-		if (cwq->current_work != work)
+		if (!cwq->worker || cwq->worker->current_work != work)
 			goto already_gone;
 		prev = &cwq->worklist;
 	}

@@ -921,7 +1036,7 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 	int running = 0;
 
 	spin_lock_irq(&cwq->lock);
-	if (unlikely(cwq->current_work == work)) {
+	if (unlikely(cwq->worker && cwq->worker->current_work == work)) {
 		insert_wq_barrier(cwq, &barr, cwq->worklist.next);
 		running = 1;
 	}

@@ -1184,7 +1299,7 @@ int current_is_keventd(void)
 	BUG_ON(!keventd_wq);
 
 	cwq = get_cwq(cpu, keventd_wq);
-	if (current == cwq->thread)
+	if (current == cwq->worker->task)
 		ret = 1;
 
 	return ret;

@@ -1229,38 +1344,6 @@ static void free_cwqs(struct cpu_workqueue_struct *cwqs)
 #endif
 }
 
-static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
-{
-	struct workqueue_struct *wq = cwq->wq;
-	struct task_struct *p;
-
-	p = kthread_create(worker_thread, cwq, "%s/%d", wq->name, cpu);
-	/*
-	 * Nobody can add the work_struct to this cwq,
-	 *	if (caller is __create_workqueue)
-	 *		nobody should see this wq
-	 *	else // caller is CPU_UP_PREPARE
-	 *		cpu is not on cpu_online_map
-	 * so we can abort safely.
-	 */
-	if (IS_ERR(p))
-		return PTR_ERR(p);
-	cwq->thread = p;
-
-	return 0;
-}
-
-static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
-{
-	struct task_struct *p = cwq->thread;
-
-	if (p != NULL) {
-		if (cpu >= 0)
-			kthread_bind(p, cpu);
-		wake_up_process(p);
-	}
-}
-
 struct workqueue_struct *__create_workqueue_key(const char *name,
 						unsigned int flags,
 						struct lock_class_key *key,

@@ -1268,7 +1351,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 {
 	bool singlethread = flags & WQ_SINGLE_THREAD;
 	struct workqueue_struct *wq;
-	int err = 0, cpu;
+	bool failed = false;
+	unsigned int cpu;
 
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
 	if (!wq)

@@ -1298,23 +1382,25 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
 		BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK);
+		cwq->cpu = cpu;
 		cwq->wq = wq;
 		cwq->flush_color = -1;
 		spin_lock_init(&cwq->lock);
 		INIT_LIST_HEAD(&cwq->worklist);
 		init_waitqueue_head(&cwq->more_work);
 
-		if (err)
+		if (failed)
 			continue;
-		err = create_workqueue_thread(cwq, cpu);
-		if (cpu_online(cpu) && !singlethread)
-			start_workqueue_thread(cwq, cpu);
+		cwq->worker = create_worker(cwq,
+					    cpu_online(cpu) && !singlethread);
+		if (cwq->worker)
+			start_worker(cwq->worker);
 		else
-			start_workqueue_thread(cwq, -1);
+			failed = true;
 	}
 	cpu_maps_update_done();
 
-	if (err) {
+	if (failed) {
 		destroy_workqueue(wq);
 		wq = NULL;
 	}

@@ -1353,9 +1439,9 @@ void destroy_workqueue(struct workqueue_struct *wq)
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 		int i;
 
-		if (cwq->thread) {
-			kthread_stop(cwq->thread);
-			cwq->thread = NULL;
+		if (cwq->worker) {
+			destroy_worker(cwq->worker);
+			cwq->worker = NULL;
 		}
 
 		for (i = 0; i < WORK_NR_COLORS; i++)

@@ -1385,8 +1471,8 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
 		switch (action) {
 		case CPU_ONLINE:
-			__set_cpus_allowed(cwq->thread, get_cpu_mask(cpu),
-					   true);
+			__set_cpus_allowed(cwq->worker->task,
+					   get_cpu_mask(cpu), true);
 			break;
 
 		case CPU_POST_DEAD:

@@ -1447,6 +1533,8 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 
 void __init init_workqueues(void)
 {
+	unsigned int cpu;
+
 	/*
 	 * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
 	 * Make sure that the alignment isn't lower than that of

@@ -1455,6 +1543,9 @@ void __init init_workqueues(void)
 	BUILD_BUG_ON(__alignof__(struct cpu_workqueue_struct) <
 		     __alignof__(unsigned long long));
 
+	for_each_possible_cpu(cpu)
+		ida_init(&per_cpu(worker_ida, cpu));
+
 	singlethread_cpu = cpumask_first(cpu_possible_mask);
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");

index 316cc48..a6650f1 100644
@@ -25,9 +25,11 @@ typedef void (*work_func_t)(struct work_struct *work);
 enum {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
 	WORK_STRUCT_STATIC_BIT	= 1,	/* static initializer (debugobjects) */
+	WORK_STRUCT_LINKED_BIT	= 2,	/* next work is linked to this one */
 
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
+	WORK_STRUCT_LINKED	= 1 << WORK_STRUCT_LINKED_BIT,
 
 	WORK_STRUCT_COLOR_SHIFT	= 3,	/* color for workqueue flushing */
 	WORK_STRUCT_COLOR_BITS	= 4,

241 lines not on this page · raw message

index a6650f1..974a232 100644
@@ -216,11 +216,11 @@ enum {
 };
 
 extern struct workqueue_struct *
-__create_workqueue_key(const char *name, unsigned int flags,
+__create_workqueue_key(const char *name, unsigned int flags, int max_active,
 		       struct lock_class_key *key, const char *lock_name);
 
 #ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, flags)				\
+#define __create_workqueue(name, flags, max_active)		\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\

@@ -230,20 +230,20 @@ __create_workqueue_key(const char *name, unsigned int flags,
 	else							\
 		__lock_name = #name;				\
 								\
-	__create_workqueue_key((name), (flags), &__key,		\
-			       __lock_name);			\
+	__create_workqueue_key((name), (flags), (max_active),	\
+				&__key, __lock_name);		\
 })
 #else
-#define __create_workqueue(name, flags)				\
-	__create_workqueue_key((name), (flags), NULL, NULL)
+#define __create_workqueue(name, flags, max_active)		\
+	__create_workqueue_key((name), (flags), (max_active), NULL, NULL)
 #endif
 
 #define create_workqueue(name)					\
-	__create_workqueue((name), 0)
+	__create_workqueue((name), 0, 1)
 #define create_freezeable_workqueue(name)			\
-	__create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD)
+	__create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD, 1)
 #define create_singlethread_workqueue(name)			\
-	__create_workqueue((name), WQ_SINGLE_THREAD)
+	__create_workqueue((name), WQ_SINGLE_THREAD, 1)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 

index 2ac1624..0c9c01d 100644
@@ -77,6 +77,9 @@ struct cpu_workqueue_struct {
 	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;	/* I: max active works */
+	struct list_head	delayed_works;	/* L: delayed works */
 };
 
 /*

@@ -314,14 +317,24 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
 	struct cpu_workqueue_struct *cwq = target_cwq(cpu, wq);
+	struct list_head *worklist;
 	unsigned long flags;
 
 	debug_work_activate(work);
+
 	spin_lock_irqsave(&cwq->lock, flags);
 	BUG_ON(!list_empty(&work->entry));
+
 	cwq->nr_in_flight[cwq->work_color]++;
-	insert_work(cwq, work, &cwq->worklist,
-		    work_color_to_flags(cwq->work_color));
+
+	if (likely(cwq->nr_active < cwq->max_active)) {
+		cwq->nr_active++;
+		worklist = &cwq->worklist;
+	} else
+		worklist = &cwq->delayed_works;
+
+	insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color));
+
 	spin_unlock_irqrestore(&cwq->lock, flags);
 }
 

@@ -578,6 +591,15 @@ static void move_linked_works(struct work_struct *work, struct list_head *head,
 		*nextp = n;
 }
 
+static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
+{
+	struct work_struct *work = list_first_entry(&cwq->delayed_works,
+						    struct work_struct, entry);
+
+	move_linked_works(work, &cwq->worklist, NULL);
+	cwq->nr_active++;
+}
+
 /**
  * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight
  * @cwq: cwq of interest

@@ -596,6 +618,12 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
 		return;
 
 	cwq->nr_in_flight[color]--;
+	cwq->nr_active--;
+
+	/* one down, submit a delayed one */
+	if (!list_empty(&cwq->delayed_works) &&
+	    cwq->nr_active < cwq->max_active)
+		cwq_activate_first_delayed(cwq);
 
 	/* is flush in progress and are we at the flushing tip? */
 	if (likely(cwq->flush_color != color))

@@ -1456,6 +1484,7 @@ static void free_cwqs(struct cpu_workqueue_struct *cwqs)
 
 struct workqueue_struct *__create_workqueue_key(const char *name,
 						unsigned int flags,
+						int max_active,
 						struct lock_class_key *key,
 						const char *lock_name)
 {

@@ -1464,6 +1493,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 	bool failed = false;
 	unsigned int cpu;
 
+	max_active = clamp_val(max_active, 1, INT_MAX);
+
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
 	if (!wq)
 		goto err;

@@ -1495,8 +1526,10 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 		cwq->cpu = cpu;
 		cwq->wq = wq;
 		cwq->flush_color = -1;
+		cwq->max_active = max_active;
 		spin_lock_init(&cwq->lock);
 		INIT_LIST_HEAD(&cwq->worklist);
+		INIT_LIST_HEAD(&cwq->delayed_works);
 		init_waitqueue_head(&cwq->more_work);
 
 		if (failed)

@@ -1556,6 +1589,8 @@ void destroy_workqueue(struct workqueue_struct *wq)
 
 		for (i = 0; i < WORK_NR_COLORS; i++)
 			BUG_ON(cwq->nr_in_flight[i]);
+		BUG_ON(cwq->nr_active);
+		BUG_ON(!list_empty(&cwq->delayed_works));
 	}
 
 	free_cwqs(wq->cpu_wq);

index 974a232..7a260df 100644
@@ -331,4 +331,11 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 #else
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_FREEZER
+extern void freeze_workqueues_begin(void);
+extern bool freeze_workqueues_busy(void);
+extern void thaw_workqueues(void);
+#endif /* CONFIG_FREEZER */
+
 #endif

index 5ade1bd..6f89afd 100644
@@ -15,6 +15,7 @@
 #include <linux/syscalls.h>
 #include <linux/freezer.h>
 #include <linux/delay.h>
+#include <linux/workqueue.h>
 
 /* 
  * Timeout for stopping processes

@@ -35,6 +36,7 @@ static int try_to_freeze_tasks(bool sig_only)
 	struct task_struct *g, *p;
 	unsigned long end_time;
 	unsigned int todo;
+	bool wq_busy = false;
 	struct timeval start, end;
 	u64 elapsed_csecs64;
 	unsigned int elapsed_csecs;

@@ -42,6 +44,10 @@ static int try_to_freeze_tasks(bool sig_only)
 	do_gettimeofday(&start);
 
 	end_time = jiffies + TIMEOUT;
+
+	if (!sig_only)
+		freeze_workqueues_begin();
+
 	while (true) {
 		todo = 0;
 		read_lock(&tasklist_lock);

@@ -63,6 +69,12 @@ static int try_to_freeze_tasks(bool sig_only)
 				todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
+
+		if (!sig_only) {
+			wq_busy = freeze_workqueues_busy();
+			todo += wq_busy;
+		}
+
 		if (!todo || time_after(jiffies, end_time))
 			break;
 

@@ -86,9 +98,13 @@ static int try_to_freeze_tasks(bool sig_only)
 		 */
 		printk("\n");
 		printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
-				"(%d tasks refusing to freeze):\n",
-				elapsed_csecs / 100, elapsed_csecs % 100, todo);
+		       "(%d tasks refusing to freeze, wq_busy=%d):\n",
+		       elapsed_csecs / 100, elapsed_csecs % 100,
+		       todo - wq_busy, wq_busy);
 		show_state();
+
+		thaw_workqueues();
+
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
 			task_lock(p);

@@ -158,6 +174,7 @@ void thaw_processes(void)
 	oom_killer_enable();
 
 	printk("Restarting tasks ... ");
+	thaw_workqueues();
 	thaw_tasks(true);
 	thaw_tasks(false);
 	schedule();

223 lines not on this page · raw message

index eca3925..91c924c 100644
@@ -40,38 +40,45 @@
  *
  * I: Set during initialization and read-only afterwards.
  *
- * L: cwq->lock protected.  Access with cwq->lock held.
+ * L: gcwq->lock protected.  Access with gcwq->lock held.
  *
  * F: wq->flush_mutex protected.
  *
  * W: workqueue_lock protected.
  */
 
+struct global_cwq;
 struct cpu_workqueue_struct;
 
 struct worker {
 	struct work_struct	*current_work;	/* L: work being processed */
 	struct list_head	scheduled;	/* L: scheduled works */
 	struct task_struct	*task;		/* I: worker task */
+	struct global_cwq	*gcwq;		/* I: the associated gcwq */
 	struct cpu_workqueue_struct *cwq;	/* I: the associated cwq */
 	int			id;		/* I: worker id */
 };
 
 /*
+ * Global per-cpu workqueue.
+ */
+struct global_cwq {
+	spinlock_t		lock;		/* the gcwq lock */
+	unsigned int		cpu;		/* I: the associated cpu */
+	struct ida		worker_ida;	/* L: for worker IDs */
+} ____cacheline_aligned_in_smp;
+
+/*
  * The per-CPU workqueue (if single thread, we always use the first
  * 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 {
-
-	spinlock_t lock;
-
+	struct global_cwq	*gcwq;		/* I: the associated gcwq */
 	struct list_head worklist;
 	wait_queue_head_t more_work;
-	unsigned int		cpu;
 	struct worker		*worker;
-
 	struct workqueue_struct *wq;		/* I: the owning workqueue */
 	int			work_color;	/* L: current color */
 	int			flush_color;	/* L: flushing color */

@@ -228,13 +235,19 @@ 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 DEFINE_PER_CPU(struct ida, worker_ida);
 static bool workqueue_freezing;		/* W: have wqs started freezing? */
 
+static DEFINE_PER_CPU(struct global_cwq, global_cwq);
+
 static int worker_thread(void *__worker);
 
 static int singlethread_cpu __read_mostly;
 
+static struct global_cwq *get_gcwq(unsigned int cpu)
+{
+	return &per_cpu(global_cwq, cpu);
+}
+
 static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
 					    struct workqueue_struct *wq)
 {

@@ -296,7 +309,7 @@ static inline struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
  * Insert @work into @cwq after @head.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock).
+ * spin_lock_irq(gcwq->lock).
  */
 static void insert_work(struct cpu_workqueue_struct *cwq,
 			struct work_struct *work, struct list_head *head,

@@ -319,12 +332,13 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
 	struct cpu_workqueue_struct *cwq = target_cwq(cpu, wq);
+	struct global_cwq *gcwq = cwq->gcwq;
 	struct list_head *worklist;
 	unsigned long flags;
 
 	debug_work_activate(work);
 
-	spin_lock_irqsave(&cwq->lock, flags);
+	spin_lock_irqsave(&gcwq->lock, flags);
 	BUG_ON(!list_empty(&work->entry));
 
 	cwq->nr_in_flight[cwq->work_color]++;

@@ -337,7 +351,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 
 	insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color));
 
-	spin_unlock_irqrestore(&cwq->lock, flags);
+	spin_unlock_irqrestore(&gcwq->lock, flags);
 }
 
 /**

@@ -476,39 +490,41 @@ static struct worker *alloc_worker(void)
  */
 static struct worker *create_worker(struct cpu_workqueue_struct *cwq, bool bind)
 {
+	struct global_cwq *gcwq = cwq->gcwq;
 	int id = -1;
 	struct worker *worker = NULL;
 
-	spin_lock(&workqueue_lock);
-	while (ida_get_new(&per_cpu(worker_ida, cwq->cpu), &id)) {
-		spin_unlock(&workqueue_lock);
-		if (!ida_pre_get(&per_cpu(worker_ida, cwq->cpu), GFP_KERNEL))
+	spin_lock_irq(&gcwq->lock);
+	while (ida_get_new(&gcwq->worker_ida, &id)) {
+		spin_unlock_irq(&gcwq->lock);
+		if (!ida_pre_get(&gcwq->worker_ida, GFP_KERNEL))
 			goto fail;
-		spin_lock(&workqueue_lock);
+		spin_lock_irq(&gcwq->lock);
 	}
-	spin_unlock(&workqueue_lock);
+	spin_unlock_irq(&gcwq->lock);
 
 	worker = alloc_worker();
 	if (!worker)
 		goto fail;
 
+	worker->gcwq = gcwq;
 	worker->cwq = cwq;
 	worker->id = id;
 
 	worker->task = kthread_create(worker_thread, worker, "kworker/%u:%d",
-				      cwq->cpu, id);
+				      gcwq->cpu, id);
 	if (IS_ERR(worker->task))
 		goto fail;
 
 	if (bind)
-		kthread_bind(worker->task, cwq->cpu);
+		kthread_bind(worker->task, gcwq->cpu);
 
 	return worker;
 fail:
 	if (id >= 0) {
-		spin_lock(&workqueue_lock);
-		ida_remove(&per_cpu(worker_ida, cwq->cpu), id);
-		spin_unlock(&workqueue_lock);
+		spin_lock_irq(&gcwq->lock);
+		ida_remove(&gcwq->worker_ida, id);
+		spin_unlock_irq(&gcwq->lock);
 	}
 	kfree(worker);
 	return NULL;

@@ -521,7 +537,7 @@ fail:
  * Start @worker.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock).
+ * spin_lock_irq(gcwq->lock).
  */
 static void start_worker(struct worker *worker)
 {

@@ -536,7 +552,7 @@ static void start_worker(struct worker *worker)
  */
 static void destroy_worker(struct worker *worker)
 {
-	int cpu = worker->cwq->cpu;
+	struct global_cwq *gcwq = worker->gcwq;
 	int id = worker->id;
 
 	/* sanity check frenzy */

@@ -546,9 +562,9 @@ static void destroy_worker(struct worker *worker)
 	kthread_stop(worker->task);
 	kfree(worker);
 
-	spin_lock(&workqueue_lock);
-	ida_remove(&per_cpu(worker_ida, cpu), id);
-	spin_unlock(&workqueue_lock);
+	spin_lock_irq(&gcwq->lock);
+	ida_remove(&gcwq->worker_ida, id);
+	spin_unlock_irq(&gcwq->lock);
 }
 
 /**

@@ -566,7 +582,7 @@ static void destroy_worker(struct worker *worker)
  * nested inside outer list_for_each_entry_safe().
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock).
+ * spin_lock_irq(gcwq->lock).
  */
 static void move_linked_works(struct work_struct *work, struct list_head *head,
 			      struct work_struct **nextp)

@@ -611,7 +627,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
  * decrement nr_in_flight of its cwq and handle workqueue flushing.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock).
+ * spin_lock_irq(gcwq->lock).
  */
 static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
 {

@@ -658,11 +674,12 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color)
  * call this function to process a work.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock) which is released and regrabbed.
+ * spin_lock_irq(gcwq->lock) which is released and regrabbed.
  */
 static void process_one_work(struct worker *worker, struct work_struct *work)
 {
 	struct cpu_workqueue_struct *cwq = worker->cwq;
+	struct global_cwq *gcwq = cwq->gcwq;
 	work_func_t f = work->func;
 	int work_color;
 #ifdef CONFIG_LOCKDEP

@@ -681,7 +698,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
 	work_color = work_flags_to_color(*work_data_bits(work));
 	list_del_init(&work->entry);
 
-	spin_unlock_irq(&cwq->lock);
+	spin_unlock_irq(&gcwq->lock);
 
 	BUG_ON(get_wq_data(work) != cwq);
 	work_clear_pending(work);

@@ -701,7 +718,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
 		dump_stack();
 	}
 
-	spin_lock_irq(&cwq->lock);
+	spin_lock_irq(&gcwq->lock);
 
 	/* we're done with it, release */
 	worker->current_work = NULL;

@@ -717,7 +734,7 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
  * fetches a work from the top and executes it.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock) which may be released and regrabbed
+ * spin_lock_irq(gcwq->lock) which may be released and regrabbed
  * multiple times.
  */
 static void process_scheduled_works(struct worker *worker)

@@ -738,6 +755,7 @@ static void process_scheduled_works(struct worker *worker)
 static int worker_thread(void *__worker)
 {
 	struct worker *worker = __worker;
+	struct global_cwq *gcwq = worker->gcwq;
 	struct cpu_workqueue_struct *cwq = worker->cwq;
 	DEFINE_WAIT(wait);
 

@@ -751,7 +769,7 @@ static int worker_thread(void *__worker)
 		if (kthread_should_stop())
 			break;
 
-		spin_lock_irq(&cwq->lock);
+		spin_lock_irq(&gcwq->lock);
 
 		while (!list_empty(&cwq->worklist)) {
 			struct work_struct *work =

@@ -771,7 +789,7 @@ static int worker_thread(void *__worker)
 			}
 		}
 
-		spin_unlock_irq(&cwq->lock);
+		spin_unlock_irq(&gcwq->lock);
 	}
 
 	return 0;

@@ -810,7 +828,7 @@ static void wq_barrier_func(struct work_struct *work)
  * underneath us, so we can't reliably determine cwq from @target.
  *
  * CONTEXT:
- * spin_lock_irq(cwq->lock).
+ * spin_lock_irq(gcwq->lock).
  */
 static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 			      struct wq_barrier *barr,

@@ -820,7 +838,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 	unsigned int linked = 0;
 
 	/*
-	 * debugobject calls are safe here even with cwq->lock locked
+	 * debugobject calls are safe here even with gcwq->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.

@@ -890,8 +908,9 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq,
 
 	for_each_possible_cpu(cpu) {
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+		struct global_cwq *gcwq = cwq->gcwq;
 
-		spin_lock_irq(&cwq->lock);
+		spin_lock_irq(&gcwq->lock);
 
 		if (flush_color >= 0) {
 			BUG_ON(cwq->flush_color != -1);

@@ -908,7 +927,7 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq,
 			cwq->work_color = work_color;
 		}
 
-		spin_unlock_irq(&cwq->lock);
+		spin_unlock_irq(&gcwq->lock);
 	}
 
 	return wait;

@@ -1081,17 +1100,19 @@ int flush_work(struct work_struct *work)
 {
 	struct worker *worker = NULL;
 	struct cpu_workqueue_struct *cwq;
+	struct global_cwq *gcwq;
 	struct wq_barrier barr;
 
 	might_sleep();
 	cwq = get_wq_data(work);
 	if (!cwq)
 		return 0;
+	gcwq = cwq->gcwq;
 
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
 
-	spin_lock_irq(&cwq->lock);
+	spin_lock_irq(&gcwq->lock);
 	if (!list_empty(&work->entry)) {
 		/*
 		 * See the comment near try_to_grab_pending()->smp_rmb().

@@ -1108,12 +1129,12 @@ int flush_work(struct work_struct *work)
 	}
 
 	insert_wq_barrier(cwq, &barr, work, worker);
-	spin_unlock_irq(&cwq->lock);
+	spin_unlock_irq(&gcwq->lock);
 	wait_for_completion(&barr.done);
 	destroy_work_on_stack(&barr.work);
 	return 1;
 already_gone:
-	spin_unlock_irq(&cwq->lock);
+	spin_unlock_irq(&gcwq->lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(flush_work);

@@ -1124,6 +1145,7 @@ EXPORT_SYMBOL_GPL(flush_work);
  */
 static int try_to_grab_pending(struct work_struct *work)
 {
+	struct global_cwq *gcwq;
 	struct cpu_workqueue_struct *cwq;
 	int ret = -1;
 

@@ -1138,8 +1160,9 @@ static int try_to_grab_pending(struct work_struct *work)
 	cwq = get_wq_data(work);
 	if (!cwq)
 		return ret;
+	gcwq = cwq->gcwq;
 
-	spin_lock_irq(&cwq->lock);
+	spin_lock_irq(&gcwq->lock);
 	if (!list_empty(&work->entry)) {
 		/*
 		 * This work is queued, but perhaps we locked the wrong cwq.

@@ -1155,7 +1178,7 @@ static int try_to_grab_pending(struct work_struct *work)
 			ret = 1;
 		}
 	}
-	spin_unlock_irq(&cwq->lock);
+	spin_unlock_irq(&gcwq->lock);
 
 	return ret;
 }

@@ -1163,10 +1186,11 @@ static int try_to_grab_pending(struct work_struct *work)
 static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 				struct work_struct *work)
 {
+	struct global_cwq *gcwq = cwq->gcwq;
 	struct wq_barrier barr;
 	struct worker *worker;
 
-	spin_lock_irq(&cwq->lock);
+	spin_lock_irq(&gcwq->lock);
 
 	worker = NULL;
 	if (unlikely(cwq->worker && cwq->worker->current_work == work)) {

@@ -1174,7 +1198,7 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 		insert_wq_barrier(cwq, &barr, work, worker);
 	}
 
-	spin_unlock_irq(&cwq->lock);
+	spin_unlock_irq(&gcwq->lock);
 
 	if (unlikely(worker)) {
 		wait_for_completion(&barr.done);

@@ -1518,13 +1542,13 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 	 */
 	for_each_possible_cpu(cpu) {
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+		struct global_cwq *gcwq = get_gcwq(cpu);
 
 		BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK);
-		cwq->cpu = cpu;
+		cwq->gcwq = gcwq;
 		cwq->wq = wq;
 		cwq->flush_color = -1;
 		cwq->max_active = max_active;
-		spin_lock_init(&cwq->lock);
 		INIT_LIST_HEAD(&cwq->worklist);
 		INIT_LIST_HEAD(&cwq->delayed_works);
 		init_waitqueue_head(&cwq->more_work);

@@ -1698,7 +1722,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
  * list instead of the cwq ones.
  *
  * CONTEXT:
- * Grabs and releases workqueue_lock and cwq->lock's.
+ * Grabs and releases workqueue_lock and gcwq->lock's.
  */
 void freeze_workqueues_begin(void)
 {

@@ -1711,16 +1735,18 @@ void freeze_workqueues_begin(void)
 	workqueue_freezing = true;
 
 	for_each_possible_cpu(cpu) {
+		struct global_cwq *gcwq = get_gcwq(cpu);
+
+		spin_lock_irq(&gcwq->lock);
+
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			spin_lock_irq(&cwq->lock);
-
 			if (wq->flags & WQ_FREEZEABLE)
 				cwq->max_active = 0;
-
-			spin_unlock_irq(&cwq->lock);
 		}
+
+		spin_unlock_irq(&gcwq->lock);
 	}
 
 	spin_unlock(&workqueue_lock);

@@ -1779,7 +1805,7 @@ out_unlock:
  * frozen works are transferred to their respective cwq worklists.
  *
  * CONTEXT:
- * Grabs and releases workqueue_lock and cwq->lock's.
+ * Grabs and releases workqueue_lock and gcwq->lock's.
  */
 void thaw_workqueues(void)
 {

@@ -1792,14 +1818,16 @@ void thaw_workqueues(void)
 		goto out_unlock;
 
 	for_each_possible_cpu(cpu) {
+		struct global_cwq *gcwq = get_gcwq(cpu);
+
+		spin_lock_irq(&gcwq->lock);
+
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
 			if (!(wq->flags & WQ_FREEZEABLE))
 				continue;
 
-			spin_lock_irq(&cwq->lock);
-
 			/* restore max_active and repopulate worklist */
 			cwq->max_active = wq->saved_max_active;
 

@@ -1808,9 +1836,9 @@ void thaw_workqueues(void)
 				cwq_activate_first_delayed(cwq);
 
 			wake_up(&cwq->more_work);
-
-			spin_unlock_irq(&cwq->lock);
 		}
+
+		spin_unlock_irq(&gcwq->lock);
 	}
 
 	workqueue_freezing = false;

@@ -1831,11 +1859,19 @@ void __init init_workqueues(void)
 	BUILD_BUG_ON(__alignof__(struct cpu_workqueue_struct) <
 		     __alignof__(unsigned long long));
 
-	for_each_possible_cpu(cpu)
-		ida_init(&per_cpu(worker_ida, cpu));
-
 	singlethread_cpu = cpumask_first(cpu_possible_mask);
 	hotcpu_notifier(workqueue_cpu_callback, 0);
+
+	/* initialize gcwqs */
+	for_each_possible_cpu(cpu) {
+		struct global_cwq *gcwq = get_gcwq(cpu);
+
+		spin_lock_init(&gcwq->lock);
+		gcwq->cpu = cpu;
+
+		ida_init(&gcwq->worker_ida);
+	}
+
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
 }

index 91c924c..104f72f 100644
@@ -35,6 +35,17 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
+enum {
+	/* worker flags */
+	WORKER_STARTED		= 1 << 0,	/* started */
+	WORKER_DIE		= 1 << 1,	/* die die die */
+	WORKER_IDLE		= 1 << 2,	/* is idle */
+
+	BUSY_WORKER_HASH_ORDER	= 5,		/* 32 pointers */
+	BUSY_WORKER_HASH_SIZE	= 1 << BUSY_WORKER_HASH_ORDER,
+	BUSY_WORKER_HASH_MASK	= BUSY_WORKER_HASH_SIZE - 1,
+};
+
 /*
  * Structure fields follow one of the following exclusion rules.
  *

@@ -51,11 +62,18 @@ struct global_cwq;
 struct cpu_workqueue_struct;
 
 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 work_struct	*current_work;	/* L: work being processed */
 	struct list_head	scheduled;	/* L: scheduled works */
 	struct task_struct	*task;		/* I: worker task */
 	struct global_cwq	*gcwq;		/* I: the associated gcwq */
 	struct cpu_workqueue_struct *cwq;	/* I: the associated cwq */
+	unsigned int		flags;		/* L: flags */
 	int			id;		/* I: worker id */
 };