X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fworkqueue.c;h=2f445833ae371a58d35c56907e2eeb638e75a453;hb=1092307d582a7566d23779c304cf86f3075ac5f0;hp=25cee1afe6fb9cf64e26bd79b90045ce2d503cae;hpb=5de18d169739293e27e0cf9acfc75a2d2f4aa572;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 25cee1a..2f44583 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -9,11 +9,11 @@ * Derived from the taskqueue/keventd code by: * * David Woodhouse - * Andrew Morton + * Andrew Morton * Kai Petzke * Theodore Ts'o * - * Made to use alloc_percpu by Christoph Lameter . + * Made to use alloc_percpu by Christoph Lameter. */ #include @@ -32,6 +32,7 @@ #include #include #include +#include /* * The per-CPU workqueue (if single thread, we always use the first @@ -47,7 +48,6 @@ struct cpu_workqueue_struct { struct workqueue_struct *wq; struct task_struct *thread; - int should_stop; int run_depth; /* Detect run_workqueue() recursion depth */ } ____cacheline_aligned; @@ -62,34 +62,43 @@ 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 }; -/* All the per-cpu workqueues on the system, for hotplug cpu to add/remove - threads to each one as cpus come/go. */ -static DEFINE_MUTEX(workqueue_mutex); +/* Serializes the accesses to the list of workqueues. */ +static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); static int singlethread_cpu __read_mostly; -static cpumask_t cpu_singlethread_map __read_mostly; -/* optimization, we could use cpu_possible_map */ -static cpumask_t cpu_populated_map __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 int is_single_threaded(struct workqueue_struct *wq) +static inline int is_wq_single_threaded(struct workqueue_struct *wq) { return wq->singlethread; } -static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq) +static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq) { - return is_single_threaded(wq) - ? &cpu_singlethread_map : &cpu_populated_map; + return is_wq_single_threaded(wq) + ? cpu_singlethread_map : cpu_populated_map; } static struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu) { - if (unlikely(is_single_threaded(wq))) + if (unlikely(is_wq_single_threaded(wq))) cpu = singlethread_cpu; return per_cpu_ptr(wq->cpu_wq, cpu); } @@ -117,24 +126,25 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) } static void insert_work(struct cpu_workqueue_struct *cwq, - struct work_struct *work, int tail) + struct work_struct *work, struct list_head *head) { set_wq_data(work, cwq); - if (tail) - list_add_tail(&work->entry, &cwq->worklist); - else - list_add(&work->entry, &cwq->worklist); + /* + * 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); } -/* Preempt must be disabled. */ static void __queue_work(struct cpu_workqueue_struct *cwq, struct work_struct *work) { unsigned long flags; spin_lock_irqsave(&cwq->lock, flags); - insert_work(cwq, work, 1); + insert_work(cwq, work, &cwq->worklist); spin_unlock_irqrestore(&cwq->lock, flags); } @@ -145,24 +155,46 @@ static void __queue_work(struct cpu_workqueue_struct *cwq, * * Returns 0 if @work was already on a queue, non-zero otherwise. * - * We queue the work to the CPU it was submitted, but there is no - * guarantee that it will be processed by that CPU. + * We queue the work to the CPU on which it was submitted, but if the CPU dies + * it can be processed by another CPU. */ -int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work) +int queue_work(struct workqueue_struct *wq, struct work_struct *work) +{ + int ret; + + ret = queue_work_on(get_cpu(), wq, work); + put_cpu(); + + return ret; +} +EXPORT_SYMBOL_GPL(queue_work); + +/** + * queue_work_on - queue work on specific cpu + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @work: work to queue + * + * Returns 0 if @work was already on a queue, non-zero otherwise. + * + * We queue the work to a specific CPU, the caller must ensure it + * can't go away. + */ +int +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, get_cpu()), work); - put_cpu(); + __queue_work(wq_per_cpu(wq, cpu), work); ret = 1; } return ret; } -EXPORT_SYMBOL_GPL(queue_work); +EXPORT_SYMBOL_GPL(queue_work_on); -void delayed_work_timer_fn(unsigned long __data) +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); @@ -179,10 +211,9 @@ void delayed_work_timer_fn(unsigned long __data) * * Returns 0 if @work was already on a queue, non-zero otherwise. */ -int fastcall queue_delayed_work(struct workqueue_struct *wq, +int queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { - timer_stats_timer_set_start_info(&dwork->timer); if (delay == 0) return queue_work(wq, &dwork->work); @@ -210,6 +241,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, 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())); timer->expires = jiffies + delay; @@ -233,13 +266,24 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) if (cwq->run_depth > 3) { /* morton gets to eat his hat */ printk("%s: recursion depth exceeded: %d\n", - __FUNCTION__, cwq->run_depth); + __func__, cwq->run_depth); dump_stack(); } 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 cwq->current_work = work; list_del_init(cwq->worklist.next); @@ -247,13 +291,17 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) 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(), - current->pid); + task_pid_nr(current)); printk(KERN_ERR " last function: "); print_symbol("%s\n", (unsigned long)f); debug_show_held_locks(current); @@ -267,44 +315,27 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) spin_unlock_irq(&cwq->lock); } -/* - * NOTE: the caller must not touch *cwq if this func returns true - */ -static int cwq_should_stop(struct cpu_workqueue_struct *cwq) -{ - int should_stop = cwq->should_stop; - - if (unlikely(should_stop)) { - spin_lock_irq(&cwq->lock); - should_stop = cwq->should_stop && list_empty(&cwq->worklist); - if (should_stop) - cwq->thread = NULL; - spin_unlock_irq(&cwq->lock); - } - - return should_stop; -} - static int worker_thread(void *__cwq) { struct cpu_workqueue_struct *cwq = __cwq; DEFINE_WAIT(wait); - if (!cwq->wq->freezeable) - current->flags |= PF_NOFREEZE; + if (cwq->wq->freezeable) + set_freezable(); set_user_nice(current, -5); for (;;) { prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE); - if (!freezing(current) && !cwq->should_stop - && list_empty(&cwq->worklist)) + if (!freezing(current) && + !kthread_should_stop() && + list_empty(&cwq->worklist)) schedule(); finish_wait(&cwq->more_work, &wait); try_to_freeze(); - if (cwq_should_stop(cwq)) + if (kthread_should_stop()) break; run_workqueue(cwq); @@ -325,31 +356,34 @@ static void wq_barrier_func(struct work_struct *work) } static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, - struct wq_barrier *barr, int tail) + 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)); init_completion(&barr->done); - insert_work(cwq, &barr->work, tail); + insert_work(cwq, &barr->work, head); } -static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) +static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) { + int active; + if (cwq->thread == current) { /* * Probably keventd trying to flush its own queue. So simply run * it by hand rather than deadlocking. */ run_workqueue(cwq); + active = 1; } else { struct wq_barrier barr; - int active = 0; + active = 0; spin_lock_irq(&cwq->lock); if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { - insert_wq_barrier(cwq, &barr, 1); + insert_wq_barrier(cwq, &barr, &cwq->worklist); active = 1; } spin_unlock_irq(&cwq->lock); @@ -357,6 +391,8 @@ static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) if (active) wait_for_completion(&barr.done); } + + return active; } /** @@ -372,18 +408,110 @@ static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) * This function used to run the workqueues itself. Now we just wait for the * helper threads to do it. */ -void fastcall flush_workqueue(struct workqueue_struct *wq) +void flush_workqueue(struct workqueue_struct *wq) { - const cpumask_t *cpu_map = wq_cpu_map(wq); + const struct cpumask *cpu_map = wq_cpu_map(wq); int cpu; might_sleep(); - for_each_cpu_mask(cpu, *cpu_map) + lock_map_acquire(&wq->lockdep_map); + lock_map_release(&wq->lockdep_map); + for_each_cpu_mask_nr(cpu, *cpu_map) flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu)); } EXPORT_SYMBOL_GPL(flush_workqueue); -static void wait_on_work(struct cpu_workqueue_struct *cwq, +/** + * flush_work - block until a work_struct's callback has terminated + * @work: the work which is to be flushed + * + * Returns false if @work has already terminated. + * + * It is expected that, prior to calling flush_work(), the caller has + * arranged for the work to not be requeued, otherwise it doesn't make + * sense to use this function. + */ +int flush_work(struct work_struct *work) +{ + struct cpu_workqueue_struct *cwq; + struct list_head *prev; + struct wq_barrier barr; + + might_sleep(); + cwq = get_wq_data(work); + if (!cwq) + return 0; + + 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)) { + /* + * See the comment near try_to_grab_pending()->smp_rmb(). + * If it was re-queued under us we are not going to wait. + */ + smp_rmb(); + if (unlikely(cwq != get_wq_data(work))) + goto out; + prev = &work->entry; + } else { + if (cwq->current_work != work) + goto out; + prev = &cwq->worklist; + } + insert_wq_barrier(cwq, &barr, prev->next); +out: + spin_unlock_irq(&cwq->lock); + if (!prev) + return 0; + + wait_for_completion(&barr.done); + return 1; +} +EXPORT_SYMBOL_GPL(flush_work); + +/* + * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, + * so this work can't be re-armed in any way. + */ +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))) + return 0; + + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. + */ + + cwq = get_wq_data(work); + if (!cwq) + return ret; + + spin_lock_irq(&cwq->lock); + if (!list_empty(&work->entry)) { + /* + * This work is queued, but perhaps we locked the wrong cwq. + * In that case we must see the new value after rmb(), see + * insert_work()->wmb(). + */ + smp_rmb(); + if (cwq == get_wq_data(work)) { + list_del_init(&work->entry); + ret = 1; + } + } + spin_unlock_irq(&cwq->lock); + + return ret; +} + +static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq, struct work_struct *work) { struct wq_barrier barr; @@ -391,7 +519,7 @@ static void wait_on_work(struct cpu_workqueue_struct *cwq, spin_lock_irq(&cwq->lock); if (unlikely(cwq->current_work == work)) { - insert_wq_barrier(cwq, &barr, 0); + insert_wq_barrier(cwq, &barr, cwq->worklist.next); running = 1; } spin_unlock_irq(&cwq->lock); @@ -400,52 +528,88 @@ static void wait_on_work(struct cpu_workqueue_struct *cwq, wait_for_completion(&barr.done); } -/** - * cancel_work_sync - block until a work_struct's callback has terminated - * @work: the work which is to be flushed - * - * cancel_work_sync() will attempt to cancel the work if it is queued. If the - * work's callback appears to be running, cancel_work_sync() will block until - * it has completed. - * - * cancel_work_sync() is designed to be used when the caller is tearing down - * data structures which the callback function operates upon. It is expected - * that, prior to calling cancel_work_sync(), the caller has arranged for the - * work to not be requeued. - */ -void cancel_work_sync(struct work_struct *work) +static void wait_on_work(struct work_struct *work) { struct cpu_workqueue_struct *cwq; struct workqueue_struct *wq; - const cpumask_t *cpu_map; + const struct cpumask *cpu_map; int cpu; might_sleep(); + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + cwq = get_wq_data(work); - /* Was it ever queued ? */ if (!cwq) return; - /* - * This work can't be re-queued, no need to re-check that - * get_wq_data() is still the same when we take cwq->lock. - */ - spin_lock_irq(&cwq->lock); - list_del_init(&work->entry); - work_clear_pending(work); - spin_unlock_irq(&cwq->lock); - wq = cwq->wq; cpu_map = wq_cpu_map(wq); - for_each_cpu_mask(cpu, *cpu_map) - wait_on_work(per_cpu_ptr(wq->cpu_wq, cpu), work); + for_each_cpu_mask_nr(cpu, *cpu_map) + wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work); +} + +static int __cancel_work_timer(struct work_struct *work, + struct timer_list* timer) +{ + int ret; + + do { + ret = (timer && likely(del_timer(timer))); + if (!ret) + ret = try_to_grab_pending(work); + wait_on_work(work); + } while (unlikely(ret < 0)); + + work_clear_pending(work); + return ret; +} + +/** + * cancel_work_sync - block until a work_struct's callback has terminated + * @work: the work which is to be flushed + * + * Returns true if @work was pending. + * + * cancel_work_sync() will cancel the work if it is queued. If the work's + * callback appears to be running, cancel_work_sync() will block until it + * has completed. + * + * It is possible to use this function if the work re-queues itself. It can + * cancel the work even if it migrates to another workqueue, however in that + * case it only guarantees that work->func() has completed on the last queued + * workqueue. + * + * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not + * pending, otherwise it goes into a busy-wait loop until the timer expires. + * + * The caller must ensure that workqueue_struct on which this work was last + * queued can't be destroyed before this function returns. + */ +int cancel_work_sync(struct work_struct *work) +{ + return __cancel_work_timer(work, NULL); } EXPORT_SYMBOL_GPL(cancel_work_sync); +/** + * cancel_delayed_work_sync - reliably kill off a delayed work. + * @dwork: the delayed work struct + * + * Returns true if @dwork was pending. + * + * It is possible to use this function if @dwork rearms itself via queue_work() + * or queue_delayed_work(). See also the comment for cancel_work_sync(). + */ +int cancel_delayed_work_sync(struct delayed_work *dwork) +{ + return __cancel_work_timer(&dwork->work, &dwork->timer); +} +EXPORT_SYMBOL(cancel_delayed_work_sync); -static struct workqueue_struct *keventd_wq; +static struct workqueue_struct *keventd_wq __read_mostly; /** * schedule_work - put work task in global workqueue @@ -453,12 +617,25 @@ static struct workqueue_struct *keventd_wq; * * This puts a job in the kernel-global workqueue. */ -int fastcall schedule_work(struct work_struct *work) +int schedule_work(struct work_struct *work) { return queue_work(keventd_wq, work); } EXPORT_SYMBOL(schedule_work); +/* + * schedule_work_on - put work task on a specific cpu + * @cpu: cpu to put the work task on + * @work: job to be done + * + * This puts a job on a specific cpu + */ +int schedule_work_on(int cpu, struct work_struct *work) +{ + return queue_work_on(cpu, keventd_wq, work); +} +EXPORT_SYMBOL(schedule_work_on); + /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done @@ -467,10 +644,9 @@ EXPORT_SYMBOL(schedule_work); * After waiting for a given time this puts a job in the kernel-global * workqueue. */ -int fastcall schedule_delayed_work(struct delayed_work *dwork, +int schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { - timer_stats_timer_set_start_info(&dwork->timer); return queue_delayed_work(keventd_wq, dwork, delay); } EXPORT_SYMBOL(schedule_delayed_work); @@ -498,8 +674,6 @@ EXPORT_SYMBOL(schedule_delayed_work_on); * Returns zero on success. * Returns -ve errno on failure. * - * Appears to be racy against CPU hotplug. - * * schedule_on_each_cpu() is very slow. */ int schedule_on_each_cpu(work_func_t func) @@ -511,16 +685,16 @@ int schedule_on_each_cpu(work_func_t func) if (!works) return -ENOMEM; - preempt_disable(); /* CPU hotplug */ + get_online_cpus(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); - set_bit(WORK_STRUCT_PENDING, work_data_bits(work)); - __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), work); + schedule_work_on(cpu, work); } - preempt_enable(); - flush_workqueue(keventd_wq); + for_each_online_cpu(cpu) + flush_work(per_cpu_ptr(works, cpu)); + put_online_cpus(); free_percpu(works); return 0; } @@ -532,28 +706,6 @@ void flush_scheduled_work(void) EXPORT_SYMBOL(flush_scheduled_work); /** - * cancel_rearming_delayed_work - kill off a delayed work whose handler rearms the delayed work. - * @dwork: the delayed work struct - * - * Note that the work callback function may still be running on return from - * cancel_delayed_work(). Run flush_workqueue() or cancel_work_sync() to wait - * on it. - */ -void cancel_rearming_delayed_work(struct delayed_work *dwork) -{ - struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work); - - /* Was it ever queued ? */ - if (cwq != NULL) { - struct workqueue_struct *wq = cwq->wq; - - while (!cancel_delayed_work(dwork)) - flush_workqueue(wq); - } -} -EXPORT_SYMBOL(cancel_rearming_delayed_work); - -/** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must @@ -587,7 +739,7 @@ int keventd_up(void) int current_is_keventd(void) { struct cpu_workqueue_struct *cwq; - int cpu = smp_processor_id(); /* preempt-safe: keventd is per-cpu */ + int cpu = raw_smp_processor_id(); /* preempt-safe: keventd is per-cpu */ int ret = 0; BUG_ON(!keventd_wq); @@ -615,8 +767,9 @@ 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_single_threaded(wq) ? "%s" : "%s/%d"; + 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); @@ -630,9 +783,9 @@ 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, ¶m); cwq->thread = p; - cwq->should_stop = 0; return 0; } @@ -648,8 +801,12 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) } } -struct workqueue_struct *__create_workqueue(const char *name, - int singlethread, int freezeable) +struct workqueue_struct *__create_workqueue_key(const char *name, + int singlethread, + int freezeable, + int rt, + struct lock_class_key *key, + const char *lock_name) { struct workqueue_struct *wq; struct cpu_workqueue_struct *cwq; @@ -666,8 +823,10 @@ struct workqueue_struct *__create_workqueue(const char *name, } 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) { @@ -675,9 +834,22 @@ struct workqueue_struct *__create_workqueue(const char *name, err = create_workqueue_thread(cwq, singlethread_cpu); start_workqueue_thread(cwq, -1); } else { - mutex_lock(&workqueue_mutex); + 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)) @@ -685,7 +857,7 @@ struct workqueue_struct *__create_workqueue(const char *name, err = create_workqueue_thread(cwq, cpu); start_workqueue_thread(cwq, cpu); } - mutex_unlock(&workqueue_mutex); + cpu_maps_update_done(); } if (err) { @@ -694,33 +866,33 @@ struct workqueue_struct *__create_workqueue(const char *name, } return wq; } -EXPORT_SYMBOL_GPL(__create_workqueue); +EXPORT_SYMBOL_GPL(__create_workqueue_key); -static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) +static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) { - struct wq_barrier barr; - int alive = 0; - - spin_lock_irq(&cwq->lock); - if (cwq->thread != NULL) { - insert_wq_barrier(cwq, &barr, 1); - cwq->should_stop = 1; - alive = 1; - } - spin_unlock_irq(&cwq->lock); + /* + * Our caller is either destroy_workqueue() or CPU_POST_DEAD, + * cpu_add_remove_lock protects cwq->thread. + */ + if (cwq->thread == NULL) + return; - if (alive) { - wait_for_completion(&barr.done); + lock_map_acquire(&cwq->wq->lockdep_map); + lock_map_release(&cwq->wq->lockdep_map); - while (unlikely(cwq->thread != NULL)) - cpu_relax(); - /* - * Wait until cwq->thread unlocks cwq->lock, - * it won't touch *cwq after that. - */ - smp_rmb(); - spin_unlock_wait(&cwq->lock); - } + flush_cpu_workqueue(cwq); + /* + * If the caller is CPU_POST_DEAD and cwq->worklist was not empty, + * a concurrent flush_workqueue() can insert a barrier after us. + * However, in that case run_workqueue() won't return and check + * kthread_should_stop() until it flushes all work_struct's. + * When ->worklist becomes empty it is safe to exit because no + * more work_structs can be queued on this cwq: flush_workqueue + * checks list_empty(), and a "normal" queue_work() can't use + * a dead CPU. + */ + kthread_stop(cwq->thread); + cwq->thread = NULL; } /** @@ -731,18 +903,17 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) */ void destroy_workqueue(struct workqueue_struct *wq) { - const cpumask_t *cpu_map = wq_cpu_map(wq); - struct cpu_workqueue_struct *cwq; + const struct cpumask *cpu_map = wq_cpu_map(wq); int cpu; - mutex_lock(&workqueue_mutex); + cpu_maps_update_begin(); + spin_lock(&workqueue_lock); list_del(&wq->list); - mutex_unlock(&workqueue_mutex); + spin_unlock(&workqueue_lock); - for_each_cpu_mask(cpu, *cpu_map) { - cwq = per_cpu_ptr(wq->cpu_wq, cpu); - cleanup_workqueue_thread(cwq, cpu); - } + for_each_cpu_mask_nr(cpu, *cpu_map) + cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu)); + cpu_maps_update_done(); free_percpu(wq->cpu_wq); kfree(wq); @@ -756,20 +927,15 @@ 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; - switch (action) { - case CPU_LOCK_ACQUIRE: - mutex_lock(&workqueue_mutex); - return NOTIFY_OK; - - case CPU_LOCK_RELEASE: - mutex_unlock(&workqueue_mutex); - return NOTIFY_OK; + action &= ~CPU_TASKS_FROZEN; + switch (action) { case CPU_UP_PREPARE: - cpu_set(cpu, cpu_populated_map); + cpumask_set_cpu(cpu, cpu_populated_map); } - +undo: list_for_each_entry(wq, &workqueues, list) { cwq = per_cpu_ptr(wq->cpu_wq, cpu); @@ -777,8 +943,11 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, case CPU_UP_PREPARE: if (!create_workqueue_thread(cwq, cpu)) break; - printk(KERN_ERR "workqueue for %i failed\n", cpu); - return NOTIFY_BAD; + printk(KERN_ERR "workqueue [%s] for %i failed\n", + wq->name, cpu); + action = CPU_UP_CANCELED; + ret = NOTIFY_BAD; + goto undo; case CPU_ONLINE: start_workqueue_thread(cwq, cpu); @@ -786,20 +955,73 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, case CPU_UP_CANCELED: start_workqueue_thread(cwq, -1); - case CPU_DEAD: - cleanup_workqueue_thread(cwq, cpu); + case CPU_POST_DEAD: + cleanup_workqueue_thread(cwq); break; } } - return NOTIFY_OK; + switch (action) { + case CPU_UP_CANCELED: + case CPU_POST_DEAD: + cpumask_clear_cpu(cpu, cpu_populated_map); + } + + return ret; +} + +#ifdef CONFIG_SMP +struct work_for_cpu { + struct work_struct work; + long (*fn)(void *); + void *arg; + long ret; +}; + +static void do_work_for_cpu(struct work_struct *w) +{ + struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work); + + wfc->ret = wfc->fn(wfc->arg); +} + +/** + * work_on_cpu - run a function in user context on a particular cpu + * @cpu: the cpu to run on + * @fn: the function to run + * @arg: the function arg + * + * This will return -EINVAL in the cpu is not online, or the return value + * of @fn otherwise. + */ +long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +{ + struct work_for_cpu wfc; + + INIT_WORK(&wfc.work, do_work_for_cpu); + wfc.fn = fn; + wfc.arg = arg; + get_online_cpus(); + if (unlikely(!cpu_online(cpu))) + wfc.ret = -EINVAL; + else { + schedule_work_on(cpu, &wfc.work); + flush_work(&wfc.work); + } + put_online_cpus(); + + return wfc.ret; } +EXPORT_SYMBOL_GPL(work_on_cpu); +#endif /* CONFIG_SMP */ void __init init_workqueues(void) { - cpu_populated_map = cpu_online_map; - singlethread_cpu = first_cpu(cpu_possible_map); - cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu); + 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);