cfq-iosched.c

	struct request_queue *q = cfqd->queue;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_start_queueing(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

/*
 * Timer running if the active_queue is currently idling inside its time slice
 */
static void cfq_idle_slice_timer(unsigned long data)
{
	struct cfq_data *cfqd = (struct cfq_data *) data;
	struct cfq_queue *cfqq;
	unsigned long flags;
	int timed_out = 1;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	if ((cfqq = cfqd->active_queue) != NULL) {
		timed_out = 0;

		/*
		 * expired
		 */
		if (cfq_slice_used(cfqq))
			goto expire;

		/*
		 * only expire and reinvoke request handler, if there are
		 * other queues with pending requests
		 */
		if (!cfqd->busy_queues)
			goto out_cont;

		/*
		 * not expired and it has a request pending, let it dispatch
		 */
		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
			cfq_mark_cfqq_must_dispatch(cfqq);
			goto out_kick;
		}
	}
expire:
	cfq_slice_expired(cfqd, timed_out);
out_kick:
	cfq_schedule_dispatch(cfqd);
out_cont:
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
	del_timer_sync(&cfqd->idle_slice_timer);
	kblockd_flush_work(&cfqd->unplug_work);
}

static void cfq_put_async_queues(struct cfq_data *cfqd)
{
	int i;

	for (i = 0; i < IOPRIO_BE_NR; i++) {
		if (cfqd->async_cfqq[0][i])
			cfq_put_queue(cfqd->async_cfqq[0][i]);
		if (cfqd->async_cfqq[1][i])
			cfq_put_queue(cfqd->async_cfqq[1][i]);
	}

	if (cfqd->async_idle_cfqq)
		cfq_put_queue(cfqd->async_idle_cfqq);
}

static void cfq_exit_queue(elevator_t *e)
{
	struct cfq_data *cfqd = e->elevator_data;
	struct request_queue *q = cfqd->queue;

	cfq_shutdown_timer_wq(cfqd);

	spin_lock_irq(q->queue_lock);

	if (cfqd->active_queue)
		__cfq_slice_expired(cfqd, cfqd->active_queue, 0);

	while (!list_empty(&cfqd->cic_list)) {
		struct cfq_io_context *cic = list_entry(cfqd->cic_list.next,
							struct cfq_io_context,
							queue_list);

		__cfq_exit_single_io_context(cfqd, cic);
	}

	cfq_put_async_queues(cfqd);

	spin_unlock_irq(q->queue_lock);

	cfq_shutdown_timer_wq(cfqd);

	kfree(cfqd);
}

static void *cfq_init_queue(struct request_queue *q)
{
	struct cfq_data *cfqd;

	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
	if (!cfqd)
		return NULL;

	cfqd->service_tree = CFQ_RB_ROOT;
	INIT_LIST_HEAD(&cfqd->cic_list);

	cfqd->queue = q;

	init_timer(&cfqd->idle_slice_timer);
	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
	cfqd->idle_slice_timer.data = (unsigned long) cfqd;

	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);

	cfqd->last_end_request = jiffies;
	cfqd->cfq_quantum = cfq_quantum;
	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
	cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
	cfqd->cfq_back_max = cfq_back_max;
	cfqd->cfq_back_penalty = cfq_back_penalty;
	cfqd->cfq_slice[0] = cfq_slice_async;
	cfqd->cfq_slice[1] = cfq_slice_sync;
	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
	cfqd->cfq_slice_idle = cfq_slice_idle;

	return cfqd;
}

static void cfq_slab_kill(void)
{
	if (cfq_pool)
		kmem_cache_destroy(cfq_pool);
	if (cfq_ioc_pool)
		kmem_cache_destroy(cfq_ioc_pool);
}

static int __init cfq_slab_setup(void)
{
	cfq_pool = KMEM_CACHE(cfq_queue, 0);
	if (!cfq_pool)
		goto fail;

	cfq_ioc_pool = KMEM_CACHE(cfq_io_context, SLAB_DESTROY_BY_RCU);
	if (!cfq_ioc_pool)
		goto fail;

	return 0;
fail:
	cfq_slab_kill();
	return -ENOMEM;
}

/*
 * sysfs parts below -->
 */
static ssize_t
cfq_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%d\n", var);
}

static ssize_t
cfq_var_store(unsigned int *var, const char *page, size_t count)
{
	char *p = (char *) page;

	*var = simple_strtoul(p, &p, 10);
	return count;
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(elevator_t *e, char *page)			\
{									\
	struct cfq_data *cfqd = e->elevator_data;			\
	unsigned int __data = __VAR;					\
	if (__CONV)							\
		__data = jiffies_to_msecs(__data);			\
	return cfq_var_show(__data, (page));				\
}
SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
SHOW_FUNCTION(cfq_fifo_expire_sync_show, cfqd->cfq_fifo_expire[1], 1);
SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
#undef SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
{									\
	struct cfq_data *cfqd = e->elevator_data;			\
	unsigned int __data;						\
	int ret = cfq_var_store(&__data, (page), count);		\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	if (__CONV)							\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else								\
		*(__PTR) = __data;					\
	return ret;							\
}
STORE_FUNCTION(cfq_quantum_store, &cfqd->cfq_quantum, 1, UINT_MAX, 0);
STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0);
#undef STORE_FUNCTION

#define CFQ_ATTR(name) \
	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)

static struct elv_fs_entry cfq_attrs[] = {
	CFQ_ATTR(quantum),
	CFQ_ATTR(fifo_expire_sync),
	CFQ_ATTR(fifo_expire_async),
	CFQ_ATTR(back_seek_max),
	CFQ_ATTR(back_seek_penalty),
	CFQ_ATTR(slice_sync),
	CFQ_ATTR(slice_async),
	CFQ_ATTR(slice_async_rq),
	CFQ_ATTR(slice_idle),
	__ATTR_NULL
};

static struct elevator_type iosched_cfq = {
	.ops = {
		.elevator_merge_fn = 		cfq_merge,
		.elevator_merged_fn =		cfq_merged_request,
		.elevator_merge_req_fn =	cfq_merged_requests,
		.elevator_allow_merge_fn =	cfq_allow_merge,
		.elevator_dispatch_fn =		cfq_dispatch_requests,
		.elevator_add_req_fn =		cfq_insert_request,
		.elevator_activate_req_fn =	cfq_activate_request,
		.elevator_deactivate_req_fn =	cfq_deactivate_request,
		.elevator_queue_empty_fn =	cfq_queue_empty,
		.elevator_completed_req_fn =	cfq_completed_request,
		.elevator_former_req_fn =	elv_rb_former_request,
		.elevator_latter_req_fn =	elv_rb_latter_request,
		.elevator_set_req_fn =		cfq_set_request,
		.elevator_put_req_fn =		cfq_put_request,
		.elevator_may_queue_fn =	cfq_may_queue,
		.elevator_init_fn =		cfq_init_queue,
		.elevator_exit_fn =		cfq_exit_queue,
		.trim =				cfq_free_io_context,
	},
	.elevator_attrs =	cfq_attrs,
	.elevator_name =	"cfq",
	.elevator_owner =	THIS_MODULE,
};

static int __init cfq_init(void)
{
	/*
	 * could be 0 on HZ < 1000 setups
	 */
	if (!cfq_slice_async)
		cfq_slice_async = 1;
	if (!cfq_slice_idle)
		cfq_slice_idle = 1;

	if (cfq_slab_setup())
		return -ENOMEM;

	elv_register(&iosched_cfq);

	return 0;
}

static void __exit cfq_exit(void)
{
	DECLARE_COMPLETION_ONSTACK(all_gone);
	elv_unregister(&iosched_cfq);
	ioc_gone = &all_gone;
	/* ioc_gone's update must be visible before reading ioc_count */
	smp_wmb();
	if (elv_ioc_count_read(ioc_count))
		wait_for_completion(ioc_gone);
	synchronize_rcu();
	cfq_slab_kill();
}

module_init(cfq_init);
module_exit(cfq_exit);

MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Completely Fair Queueing IO scheduler");