Linux下的workqueue

先看workqueue的创建过程

kernel/workqueue.c

/**
 * alloc_ordered_workqueue - allocate an ordered workqueue
 * @fmt: printf format for the name of the workqueue
 * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
 * @args...: args for @fmt
 *
 * Allocate an ordered workqueue.  An ordered workqueue executes at
 * most one work item at any given time in the queued order.  They are
 * implemented as unbound workqueues with @max_active of one.
 *
 * RETURNS:
 * Pointer to the allocated workqueue on success, %NULL on failure.
 */
#define alloc_ordered_workqueue(fmt, flags, args...)                    \
        alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |                \
                        __WQ_ORDERED_EXPLICIT | (flags), 1, ##args)

#define create_workqueue(name)                                          \
        alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
#define create_freezable_workqueue(name)                                \
        alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
                        1, (name))
#define create_singlethread_workqueue(name)                             \
        alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)

/*
 * System-wide workqueues which are always present.
 *
 * system_wq is the one used by schedule[_delayed]_work[_on]().
 * Multi-CPU multi-threaded.  There are users which expect relatively
 * short queue flush time.  Don't queue works which can run for too
 * long.
 *
 * system_highpri_wq is similar to system_wq but for work items which
 * require WQ_HIGHPRI.
 *
 * system_long_wq is similar to system_wq but may host long running
 * works.  Queue flushing might take relatively long.
 *
 * system_unbound_wq is unbound workqueue.  Workers are not bound to
 * any specific CPU, not concurrency managed, and all queued works are
 * executed immediately as long as max_active limit is not reached and
 * resources are available.
 *
 * system_freezable_wq is equivalent to system_wq except that it's
 * freezable.
 *
 * *_power_efficient_wq are inclined towards saving power and converted
 * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
 * they are same as their non-power-efficient counterparts - e.g.
 * system_power_efficient_wq is identical to system_wq if
 * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
 */
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_highpri_wq;
extern struct workqueue_struct *system_long_wq;
extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *system_freezable_wq;
extern struct workqueue_struct *system_power_efficient_wq;
extern struct workqueue_struct *system_freezable_power_efficient_wq;
static int __init init_workqueues(void)
{
	system_wq = alloc_workqueue("events", 0, 0);
	system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
	system_long_wq = alloc_workqueue("events_long", 0, 0);
	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
					    WQ_UNBOUND_MAX_ACTIVE);
	system_freezable_wq = alloc_workqueue("events_freezable",
					      WQ_FREEZABLE, 0);
	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
					      WQ_POWER_EFFICIENT, 0);
	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
					      WQ_FREEZABLE | WQ_POWER_EFFICIENT,
					      0);
	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
	       !system_unbound_wq || !system_freezable_wq ||
	       !system_power_efficient_wq ||
	       !system_freezable_power_efficient_wq);
	return 0;
}

/**
 * alloc_workqueue - allocate a workqueue
 * @fmt: printf format for the name of the workqueue
 * @flags: WQ_* flags
 * @max_active: max in-flight work items, 0 for default
 * @args...: args for @fmt
 *
 * Allocate a workqueue with the specified parameters.  For detailed
 * information on WQ_* flags, please refer to Documentation/workqueue.txt.
 *
 * The __lock_name macro dance is to guarantee that single lock_class_key
 * doesn't end up with different namesm, which isn't allowed by lockdep.
 *
 * RETURNS:
 * Pointer to the allocated workqueue on success, %NULL on failure.
 */
#ifdef CONFIG_LOCKDEP
#define alloc_workqueue(fmt, flags, max_active, args...)                \
({                                                                      \
        static struct lock_class_key __key;                             \
        const char *__lock_name;                                        \
                                                                        \
        __lock_name = #fmt#args;                                        \
                                                                        \
        __alloc_workqueue_key((fmt), (flags), (max_active),             \
                              &__key, __lock_name, ##args);             \
})
#else
#define alloc_workqueue(fmt, flags, max_active, args...)                \
        __alloc_workqueue_key((fmt), (flags), (max_active),             \
                              NULL, NULL, ##args)
#endif

struct workqueue_struct *__alloc_workqueue_key(const char *fmt,unsigned int flags,int max_active,struct lock_class_key *key,const char *lock_name, ...)
{
	size_t tbl_size = 0;
	struct workqueue_struct *wq;
	struct pool_workqueue *pwq;
	wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL);	
	if (alloc_and_link_pwqs(wq) < 0)
		goto err_free_wq;	
}

对于BOUND类型的workqueue

static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
				     cpu_worker_pools);
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
	bool highpri = wq->flags & WQ_HIGHPRI;
	int cpu, ret;

	if (!(wq->flags & WQ_UNBOUND)) {
		wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);。
		for_each_possible_cpu(cpu) {
			struct pool_workqueue *pwq =per_cpu_ptr(wq->cpu_pwqs, cpu);
			struct worker_pool *cpu_pools =per_cpu(cpu_worker_pools, cpu);
			init_pwq(pwq, wq, &cpu_pools[highpri]);
		}
		return 0;
	} else if (wq->flags & __WQ_ORDERED) {
		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
		return ret;
	} else {
		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
	}
}

static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
		     struct worker_pool *pool)
{
	pwq->pool = pool;
	pwq->wq = wq;
}

struct worker_pool *cpu_pools在kernel启动时已赋值,如下

#define for_each_cpu_worker_pool(pool, cpu)				\
	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\
	     (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
	     (pool)++)
static int __init init_workqueues(void)
{
	int cpu;

	/* initialize CPU pools */
	for_each_possible_cpu(cpu) {
		struct worker_pool *pool;
		for_each_cpu_worker_pool(pool, cpu) {
			BUG_ON(init_worker_pool(pool));
		}
	}

	/* create the initial worker */
	for_each_online_cpu(cpu) {
		struct worker_pool *pool;
		for_each_cpu_worker_pool(pool, cpu) {
			BUG_ON(!create_worker(pool));
		}
	}
}

static struct worker *create_worker(struct worker_pool *pool)
{
	struct worker *worker = NULL;
	worker = alloc_worker(pool->node);
	worker->pool = pool;
	worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf);
	worker_enter_idle(worker);
	wake_up_process(worker->task);
}

上面是boud类型的workqueue,对于unboud类型的workqueue,workqueue创建过程如下

__alloc_workqueue_key
alloc_and_link_pwqs
apply_workqueue_attrs
apply_workqueue_attrs_locked
apply_wqattrs_prepare
	alloc_unbound_pwq  
		get_unbound_pool  create_worker
		init_pwq
apply_wqattrs_commit  ctx->pwq_tbl[0] = numa_pwq_tbl_install(ctx->wq, node, ctx->pwq_tbl[0]);

看下workstruct工作流程，以schedule_work为例

static inline bool schedule_work(struct work_struct *work)
{
	return queue_work(system_wq, work);
}

static inline bool queue_work(struct workqueue_struct *wq,
                              struct work_struct *work)
{
        return queue_work_on(WORK_CPU_UNBOUND, wq, work);
}

bool queue_work_on(int cpu, struct workqueue_struct *wq,
		   struct work_struct *work)
{

	unsigned long flags;
	local_irq_save(flags);
	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
		__queue_work(cpu, wq, work);
		ret = true;
	}
	local_irq_restore(flags);
}

static void __queue_work(int cpu, struct workqueue_struct *wq,
			 struct work_struct *work)
{
	struct pool_workqueue *pwq;
	struct list_head *worklist;
	unsigned int req_cpu = cpu;

	if (req_cpu == WORK_CPU_UNBOUND)
		cpu = raw_smp_processor_id();

	if (!(wq->flags & WQ_UNBOUND))
		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);//run here
	
	if (likely(pwq->nr_active < pwq->max_active)) {
		trace_workqueue_activate_work(work);
		pwq->nr_active++;
		worklist = &pwq->pool->worklist;
	} 
	insert_work(pwq, work, worklist, work_flags);
}

static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
			struct list_head *head, unsigned int extra_flags)
{
	struct worker_pool *pool = pwq->pool;
	set_work_pwq(work, pwq, extra_flags);
	if (__need_more_worker(pool))
		wake_up_worker(pool);
}
static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
			 unsigned long extra_flags)
{
	set_work_data(work, (unsigned long)pwq,
		      WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
}

static bool __need_more_worker(struct worker_pool *pool)
{
	return !atomic_read(&pool->nr_running);
}

static void wake_up_worker(struct worker_pool *pool)
{
	struct worker *worker = first_idle_worker(pool);

	if (likely(worker))
		wake_up_process(worker->task);
}

前面有worker->task被赋值如下

worker->task = kthread_create_on_node(worker_thread, worker, pool->node,"kworker/%s", id_buf);

/**
 * process_scheduled_works - process scheduled works
 * @worker: self
 *
 * Process all scheduled works.  Please note that the scheduled list
 * may change while processing a work, so this function repeatedly
 * fetches a work from the top and executes it.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.
 */
static void process_scheduled_works(struct worker *worker)
{
	while (!list_empty(&worker->scheduled)) {
		struct work_struct *work = list_first_entry(&worker->scheduled,
						struct work_struct, entry);
		process_one_work(worker, work);
	}
}

/**
 * worker_thread - the worker thread function
 * @__worker: self
 *
 * The worker thread function.  All workers belong to a worker_pool -
 * either a per-cpu one or dynamic unbound one.  These workers process all
 * work items regardless of their specific target workqueue.  The only
 * exception is work items which belong to workqueues with a rescuer which
 * will be explained in rescuer_thread().
 *
 * Return: 0
 */
static int worker_thread(void *__worker)
{
	struct worker *worker = __worker;
	struct worker_pool *pool = worker->pool;

	/* tell the scheduler that this is a workqueue worker */
	worker->task->flags |= PF_WQ_WORKER;
woke_up:
	spin_lock_irq(&pool->lock);

	/* am I supposed to die? */
	if (unlikely(worker->flags & WORKER_DIE)) {
		spin_unlock_irq(&pool->lock);
		WARN_ON_ONCE(!list_empty(&worker->entry));
		worker->task->flags &= ~PF_WQ_WORKER;

		set_task_comm(worker->task, "kworker/dying");
		ida_simple_remove(&pool->worker_ida, worker->id);
		worker_detach_from_pool(worker, pool);
		kfree(worker);
		return 0;
	}

	worker_leave_idle(worker);
recheck:
	/* no more worker necessary? */
	if (!need_more_worker(pool))
		goto sleep;

	/* do we need to manage? */
	if (unlikely(!may_start_working(pool)) && manage_workers(worker))
		goto recheck;

	/*
	 * ->scheduled list can only be filled while a worker is
	 * preparing to process a work or actually processing it.
	 * Make sure nobody diddled with it while I was sleeping.
	 */
	WARN_ON_ONCE(!list_empty(&worker->scheduled));

	/*
	 * Finish PREP stage.  We're guaranteed to have at least one idle
	 * worker or that someone else has already assumed the manager
	 * role.  This is where @worker starts participating in concurrency
	 * management if applicable and concurrency management is restored
	 * after being rebound.  See rebind_workers() for details.
	 */
	worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND);

	do {
		struct work_struct *work =
			list_first_entry(&pool->worklist,
					 struct work_struct, entry);

		if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
			/* optimization path, not strictly necessary */
			process_one_work(worker, work);
			if (unlikely(!list_empty(&worker->scheduled)))
				process_scheduled_works(worker);
		} else {
			move_linked_works(work, &worker->scheduled, NULL);
			process_scheduled_works(worker);
		}
	} while (keep_working(pool));

	worker_set_flags(worker, WORKER_PREP);
sleep:
	/*
	 * pool->lock is held and there's no work to process and no need to
	 * manage, sleep.  Workers are woken up only while holding
	 * pool->lock or from local cpu, so setting the current state
	 * before releasing pool->lock is enough to prevent losing any
	 * event.
	 */
	worker_enter_idle(worker);
	__set_current_state(TASK_INTERRUPTIBLE);
	spin_unlock_irq(&pool->lock);
	schedule();
	goto woke_up;
}

static void process_one_work(struct worker *worker, struct work_struct *work)
__releases(&pool->lock)
__acquires(&pool->lock)
{
	worker->current_func = work->func;
	worker->current_func(work);	
}