workqueue.c

Kernel code of linux kernel

/*
 * linux/kernel/workqueue.c
 *
 * Generic mechanism for defining kernel helper threads for running
 * arbitrary tasks in process context.
 *
 * Started by Ingo Molnar, Copyright (C) 2002
 *
 * Derived from the taskqueue/keventd code by:
 *
 *   David Woodhouse <[e-mail]>
 *   Andrew Morton <[e-mail]>
 *   Kai Petzke <[e-mail]>
 *   Theodore Ts'o <[e-mail]>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>

/*
 * The per-CPU workqueue (if single thread, we always use the first
 * possible cpu).
 */
struct cpu_workqueue_struct {

	spinlock_t lock;

	struct list_head worklist;
	wait_queue_head_t more_work;
	struct work_struct *current_work;

	struct workqueue_struct *wq;
	struct task_struct *thread;

	int run_depth;		/* Detect run_workqueue() recursion depth */
} ____cacheline_aligned;

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	struct cpu_workqueue_struct *cpu_wq;
	struct list_head list;
	const char *name;
	int singlethread;
	int freezeable;		/* Freeze threads during suspend */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map lockdep_map;
#endif
};

/* 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;
/*
 * _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_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)
{
	return wq->singlethread;
}

static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
{
	return is_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)))
		cpu = singlethread_cpu;
	return per_cpu_ptr(wq->cpu_wq, cpu);
}

/*
 * Set the workqueue on which a work item is to be run
 * - Must *only* be called if the pending flag is set
 */
static inline void set_wq_data(struct work_struct *work,
				struct cpu_workqueue_struct *cwq)
{
	unsigned long new;

	BUG_ON(!work_pending(work));

	new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
	new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
	atomic_long_set(&work->data, new);
}

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);
}

static void insert_work(struct cpu_workqueue_struct *cwq,
			struct work_struct *work, struct list_head *head)
{
	set_wq_data(work, cwq);
	/*
	 * Ensure that we get the right work->data if we see the
	 * result of list_add() below, see try_to_grab_pending().
	 */
	smp_wmb();
	list_add_tail(&work->entry, head);
	wake_up(&cwq->more_work);
}

static void __queue_work(struct cpu_workqueue_struct *cwq,
			 struct work_struct *work)
{
	unsigned long flags;

	spin_lock_irqsave(&cwq->lock, flags);
	insert_work(cwq, work, &cwq->worklist);
	spin_unlock_irqrestore(&cwq->lock, flags);
}

/**
 * queue_work - queue work on a workqueue
 * @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 the CPU on which it was submitted, but if the CPU dies
 * it can be processed by another CPU.
 */
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, cpu), work);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_work_on);

static void delayed_work_timer_fn(unsigned long __data)
{
	struct delayed_work *dwork = (struct delayed_work *)__data;
	struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);
	struct workqueue_struct *wq = cwq->wq;

	__queue_work(wq_per_cpu(wq, smp_processor_id()), &dwork->work);
}

/**
 * queue_delayed_work - queue work on a workqueue after delay
 * @wq: workqueue to use
 * @dwork: delayable work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work(struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	if (delay == 0)
		return queue_work(wq, &dwork->work);

	return queue_delayed_work_on(-1, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);

/**
 * queue_delayed_work_on - queue work on specific CPU after delay
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	int ret = 0;
	struct timer_list *timer = &dwork->timer;
	struct work_struct *work = &dwork->work;

	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
		BUG_ON(timer_pending(timer));
		BUG_ON(!list_empty(&work->entry));

		timer_stats_timer_set_start_info(&dwork->timer);

		/* This stores cwq for the moment, for the timer_fn */
		set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
		timer->expires = jiffies + delay;
		timer->data = (unsigned long)dwork;
		timer->function = delayed_work_timer_fn;

		if (unlikely(cpu >= 0))
			add_timer_on(timer, cpu);
		else
			add_timer(timer);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);

static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
	spin_lock_irq(&cwq->lock);
	cwq->run_depth++;
	if (cwq->run_depth > 3) {
		/* morton gets to eat his hat */
		printk("%s: recursion depth exceeded: %d\n",
			__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);
		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;
	}
	cwq->run_depth--;
	spin_unlock_irq(&cwq->lock);
}

static int worker_thread(void *__cwq)
{
	struct cpu_workqueue_struct *cwq = __cwq;
	DEFINE_WAIT(wait);

	if (cwq->wq->freezeable)
		set_freezable();

	set_user_nice(current, -5);

	for (;;) {
		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
		if (!freezing(current) &&
		    !kthread_should_stop() &&
		    list_empty(&cwq->worklist))
			schedule();
		finish_wait(&cwq->more_work, &wait);

		try_to_freeze();

		if (kthread_should_stop())
			break;

		run_workqueue(cwq);
	}

	return 0;
}

struct wq_barrier {
	struct work_struct	work;
	struct completion	done;
};

static void wq_barrier_func(struct work_struct *work)
{
	struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
	complete(&barr->done);
}

static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
			struct wq_barrier *barr, struct list_head *head)
{
	INIT_WORK(&barr->work, wq_barrier_func);
	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));

	init_completion(&barr->done);

	insert_work(cwq, &barr->work, head);
}

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;

		active = 0;
		spin_lock_irq(&cwq->lock);
		if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
			insert_wq_barrier(cwq, &barr, &cwq->worklist);
			active = 1;
		}
		spin_unlock_irq(&cwq->lock);

		if (active)
			wait_for_completion(&barr.done);
	}

	return active;
}

/**
 * flush_workqueue - ensure that any scheduled work has run to completion.
 * @wq: workqueue to flush
 *
 * Forces execution of the workqueue and blocks until its completion.
 * This is typically used in driver shutdown handlers.
 *
 * We sleep until all works which were queued on entry have been handled,
 * but we are not livelocked by new incoming ones.
 *
 * This function used to run the workqueues itself.  Now we just wait for the
 * helper threads to do it.
 */
void flush_workqueue(struct workqueue_struct *wq)
{
	const cpumask_t *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_mask_nr(cpu, *cpu_map)
		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);

/**
 * 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.
	 */