as-iosched.c

Linux块设备驱动源码

	WARN_ON(arq->state != AS_RQ_DISPATCHED);
	WARN_ON(ON_RB(&arq->rb_node));
	if (arq->io_context && arq->io_context->aic) {
		aic = arq->io_context->aic;
		if (aic) {
			WARN_ON(!atomic_read(&aic->nr_dispatched));
			atomic_dec(&aic->nr_dispatched);
		}
	}
}

/*
 * as_remove_request is called when a driver has finished with a request.
 * This should be only called for dispatched requests, but for some reason
 * a POWER4 box running hwscan it does not.
 */
static void as_remove_request(request_queue_t *q, struct request *rq)
{
	struct as_rq *arq = RQ_DATA(rq);

	if (unlikely(arq->state == AS_RQ_NEW))
		goto out;

	if (ON_RB(&arq->rb_node)) {
		if (arq->state != AS_RQ_QUEUED) {
			printk("arq->state %d\n", arq->state);
			WARN_ON(1);
			goto out;
		}
		/*
		 * We'll lose the aliased request(s) here. I don't think this
		 * will ever happen, but if it does, hopefully someone will
		 * report it.
		 */
		WARN_ON(!list_empty(&rq->queuelist));
		as_remove_queued_request(q, rq);
	} else {
		if (arq->state != AS_RQ_DISPATCHED) {
			printk("arq->state %d\n", arq->state);
			WARN_ON(1);
			goto out;
		}
		as_remove_dispatched_request(q, rq);
	}
out:
	arq->state = AS_RQ_REMOVED;
}

/*
 * as_fifo_expired returns 0 if there are no expired reads on the fifo,
 * 1 otherwise.  It is ratelimited so that we only perform the check once per
 * `fifo_expire' interval.  Otherwise a large number of expired requests
 * would create a hopeless seekstorm.
 *
 * See as_antic_expired comment.
 */
static int as_fifo_expired(struct as_data *ad, int adir)
{
	struct as_rq *arq;
	long delta_jif;

	delta_jif = jiffies - ad->last_check_fifo[adir];
	if (unlikely(delta_jif < 0))
		delta_jif = -delta_jif;
	if (delta_jif < ad->fifo_expire[adir])
		return 0;

	ad->last_check_fifo[adir] = jiffies;

	if (list_empty(&ad->fifo_list[adir]))
		return 0;

	arq = list_entry_fifo(ad->fifo_list[adir].next);

	return time_after(jiffies, arq->expires);
}

/*
 * as_batch_expired returns true if the current batch has expired. A batch
 * is a set of reads or a set of writes.
 */
static inline int as_batch_expired(struct as_data *ad)
{
	if (ad->changed_batch || ad->new_batch)
		return 0;

	if (ad->batch_data_dir == REQ_SYNC)
		/* TODO! add a check so a complete fifo gets written? */
		return time_after(jiffies, ad->current_batch_expires);

	return time_after(jiffies, ad->current_batch_expires)
		|| ad->current_write_count == 0;
}

/*
 * move an entry to dispatch queue
 */
static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
{
	struct request *rq = arq->request;
	struct list_head *insert;
	const int data_dir = arq->is_sync;

	BUG_ON(!ON_RB(&arq->rb_node));

	as_antic_stop(ad);
	ad->antic_status = ANTIC_OFF;

	/*
	 * This has to be set in order to be correctly updated by
	 * as_find_next_arq
	 */
	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;

	if (data_dir == REQ_SYNC) {
		/* In case we have to anticipate after this */
		copy_io_context(&ad->io_context, &arq->io_context);
	} else {
		if (ad->io_context) {
			put_io_context(ad->io_context);
			ad->io_context = NULL;
		}

		if (ad->current_write_count != 0)
			ad->current_write_count--;
	}
	ad->ioc_finished = 0;

	ad->next_arq[data_dir] = as_find_next_arq(ad, arq);

	/*
	 * take it off the sort and fifo list, add to dispatch queue
	 */
	insert = ad->dispatch->prev;

	while (!list_empty(&rq->queuelist)) {
		struct request *__rq = list_entry_rq(rq->queuelist.next);
		struct as_rq *__arq = RQ_DATA(__rq);

		list_move_tail(&__rq->queuelist, ad->dispatch);

		if (__arq->io_context && __arq->io_context->aic)
			atomic_inc(&__arq->io_context->aic->nr_dispatched);

		WARN_ON(__arq->state != AS_RQ_QUEUED);
		__arq->state = AS_RQ_DISPATCHED;

		ad->nr_dispatched++;
	}

	as_remove_queued_request(ad->q, rq);
	WARN_ON(arq->state != AS_RQ_QUEUED);

	list_add(&rq->queuelist, insert);
	arq->state = AS_RQ_DISPATCHED;
	if (arq->io_context && arq->io_context->aic)
		atomic_inc(&arq->io_context->aic->nr_dispatched);
	ad->nr_dispatched++;
}

/*
 * as_dispatch_request selects the best request according to
 * read/write expire, batch expire, etc, and moves it to the dispatch
 * queue. Returns 1 if a request was found, 0 otherwise.
 */
static int as_dispatch_request(struct as_data *ad)
{
	struct as_rq *arq;
	const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
	const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);

	/* Signal that the write batch was uncontended, so we can't time it */
	if (ad->batch_data_dir == REQ_ASYNC && !reads) {
		if (ad->current_write_count == 0 || !writes)
			ad->write_batch_idled = 1;
	}

	if (!(reads || writes)
		|| ad->antic_status == ANTIC_WAIT_REQ
		|| ad->antic_status == ANTIC_WAIT_NEXT
		|| ad->changed_batch)
		return 0;

	if (!(reads && writes && as_batch_expired(ad)) ) {
		/*
		 * batch is still running or no reads or no writes
		 */
		arq = ad->next_arq[ad->batch_data_dir];

		if (ad->batch_data_dir == REQ_SYNC && ad->antic_expire) {
			if (as_fifo_expired(ad, REQ_SYNC))
				goto fifo_expired;

			if (as_can_anticipate(ad, arq)) {
				as_antic_waitreq(ad);
				return 0;
			}
		}

		if (arq) {
			/* we have a "next request" */
			if (reads && !writes)
				ad->current_batch_expires =
					jiffies + ad->batch_expire[REQ_SYNC];
			goto dispatch_request;
		}
	}

	/*
	 * at this point we are not running a batch. select the appropriate
	 * data direction (read / write)
	 */

	if (reads) {
		BUG_ON(RB_EMPTY(&ad->sort_list[REQ_SYNC]));

		if (writes && ad->batch_data_dir == REQ_SYNC)
			/*
			 * Last batch was a read, switch to writes
			 */
			goto dispatch_writes;

		if (ad->batch_data_dir == REQ_ASYNC) {
			WARN_ON(ad->new_batch);
			ad->changed_batch = 1;
		}
		ad->batch_data_dir = REQ_SYNC;
		arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
		ad->last_check_fifo[ad->batch_data_dir] = jiffies;
		goto dispatch_request;
	}

	/*
	 * the last batch was a read
	 */

	if (writes) {
dispatch_writes:
		BUG_ON(RB_EMPTY(&ad->sort_list[REQ_ASYNC]));

		if (ad->batch_data_dir == REQ_SYNC) {
			ad->changed_batch = 1;

			/*
			 * new_batch might be 1 when the queue runs out of
			 * reads. A subsequent submission of a write might
			 * cause a change of batch before the read is finished.
			 */
			ad->new_batch = 0;
		}
		ad->batch_data_dir = REQ_ASYNC;
		ad->current_write_count = ad->write_batch_count;
		ad->write_batch_idled = 0;
		arq = ad->next_arq[ad->batch_data_dir];
		goto dispatch_request;
	}

	BUG();
	return 0;

dispatch_request:
	/*
	 * If a request has expired, service it.
	 */

	if (as_fifo_expired(ad, ad->batch_data_dir)) {
fifo_expired:
		arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
		BUG_ON(arq == NULL);
	}

	if (ad->changed_batch) {
		WARN_ON(ad->new_batch);

		if (ad->nr_dispatched)
			return 0;

		if (ad->batch_data_dir == REQ_ASYNC)
			ad->current_batch_expires = jiffies +
					ad->batch_expire[REQ_ASYNC];
		else
			ad->new_batch = 1;

		ad->changed_batch = 0;
	}

	/*
	 * arq is the selected appropriate request.
	 */
	as_move_to_dispatch(ad, arq);

	return 1;
}

static struct request *as_next_request(request_queue_t *q)
{
	struct as_data *ad = q->elevator->elevator_data;
	struct request *rq = NULL;

	/*
	 * if there are still requests on the dispatch queue, grab the first
	 */
	if (!list_empty(ad->dispatch) || as_dispatch_request(ad))
		rq = list_entry_rq(ad->dispatch->next);

	return rq;
}

/*
 * Add arq to a list behind alias
 */
static inline void
as_add_aliased_request(struct as_data *ad, struct as_rq *arq, struct as_rq *alias)
{
	struct request  *req = arq->request;
	struct list_head *insert = alias->request->queuelist.prev;

	/*
	 * Transfer list of aliases
	 */
	while (!list_empty(&req->queuelist)) {
		struct request *__rq = list_entry_rq(req->queuelist.next);
		struct as_rq *__arq = RQ_DATA(__rq);

		list_move_tail(&__rq->queuelist, &alias->request->queuelist);

		WARN_ON(__arq->state != AS_RQ_QUEUED);
	}

	/*
	 * Another request with the same start sector on the rbtree.
	 * Link this request to that sector. They are untangled in
	 * as_move_to_dispatch
	 */
	list_add(&arq->request->queuelist, insert);

	/*
	 * Don't want to have to handle merges.
	 */
	as_remove_merge_hints(ad->q, arq);
}

/*
 * add arq to rbtree and fifo
 */
static void as_add_request(struct as_data *ad, struct as_rq *arq)
{
	struct as_rq *alias;
	int data_dir;

	if (rq_data_dir(arq->request) == READ
			|| current->flags&PF_SYNCWRITE)
		arq->is_sync = 1;
	else
		arq->is_sync = 0;
	data_dir = arq->is_sync;

	arq->io_context = as_get_io_context();

	if (arq->io_context) {
		as_update_iohist(ad, arq->io_context->aic, arq->request);
		atomic_inc(&arq->io_context->aic->nr_queued);
	}

	alias = as_add_arq_rb(ad, arq);
	if (!alias) {
		/*
		 * set expire time (only used for reads) and add to fifo list
		 */
		arq->expires = jiffies + ad->fifo_expire[data_dir];
		list_add_tail(&arq->fifo, &ad->fifo_list[data_dir]);

		if (rq_mergeable(arq->request)) {
			as_add_arq_hash(ad, arq);

			if (!ad->q->last_merge)
				ad->q->last_merge = arq->request;
		}
		as_update_arq(ad, arq); /* keep state machine up to date */

	} else {
		as_add_aliased_request(ad, arq, alias);

		/*
		 * have we been anticipating this request?
		 * or does it come from the same process as the one we are
		 * anticipating for?
		 */
		if (ad->antic_status == ANTIC_WAIT_REQ
				|| ad->antic_status == ANTIC_WAIT_NEXT) {
			if (as_can_break_anticipation(ad, arq))
				as_antic_stop(ad);
		}
	}

	arq->state = AS_RQ_QUEUED;
}

static void as_deactivate_request(request_queue_t *q, struct request *rq)
{
	struct as_data *ad = q->elevator->elevator_data;
	struct as_rq *arq = RQ_DATA(rq);

	if (arq) {
		if (arq->state == AS_RQ_REMOVED) {
			arq->state = AS_RQ_DISPATCHED;
			if (arq->io_context && arq->io_context->aic)
				atomic_inc(&arq->io_context->aic->nr_dispatched);
		}
	} else
		WARN_ON(blk_fs_request(rq)
			&& (!(rq->flags & (REQ_HARDBARRIER|REQ_SOFTBARRIER))) );

	/* Stop anticipating - let this request get through */
	as_antic_stop(ad);
}

/*
 * requeue the request. The request has not been completed, nor is it a
 * new request, so don't touch accounting.
 */
static void as_requeue_request(request_queue_t *q, struct request *rq)
{
	as_deactivate_request(q, rq);
	list_add(&rq->queuelist, &q->queue_head);
}

/*
 * Account a request that is inserted directly onto the dispatch queue.
 * arq->io_context->aic->nr_dispatched should not need to be incremented
 * because only new requests should come through here: requeues go through
 * our explicit requeue handler.
 */
static void as_account_queued_request(struct as_data *ad, struct request *rq)
{
	if (blk_fs_request(rq)) {
		struct as_rq *arq = RQ_DATA(rq);
		arq->state = AS_RQ_DISPATCHED;
		ad->nr_dispatched++;
	}
}

static void
as_insert_request(request_queue_t *q, struct request *rq, int where)
{
	struct as_data *ad = q->elevator->elevator_data;
	struct as_rq *arq = RQ_DATA(rq);

	if (arq) {
		if (arq->state != AS_RQ_PRESCHED) {
			printk("arq->state: %d\n", arq->state);
			WARN_ON(1);
		}
		arq->state = AS_RQ_NEW;
	}

	/* barriers must flush the reorder queue */
	if (unlikely(rq->flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)
			&& where == ELEVATOR_INSERT_SORT)) {
		WARN_ON(1);
		where = ELEVATOR_INSERT_BACK;
	}

	switch (where) {
		case ELEVATOR_INSERT_BACK:
			while (ad->next_arq[REQ_SYNC])
				as_move_to_dispatch(ad, ad->next_arq[REQ_SYNC]);

			while (ad->next_arq[REQ_ASYNC])
				as_move_to_dispatch(ad, ad->next_arq[REQ_ASYNC]);

			list_add_tail(&rq->queuelist, ad->dispatch);
			as_account_queued_request(ad, rq);
			as_antic_stop(ad);
			break;
		case ELEVATOR_INSERT_FRONT:
			list_add(&rq->queuelist, ad->dispatch);
			as_account_queued_request(ad, rq);
			as_antic_stop(ad);
			break;
		case ELEVATOR_INSERT_SORT:
			BUG_ON(!blk_fs_request(rq));
			as_add_request(ad, arq);
			break;
		default:
			BUG();
			return;
	}
}

/*
 * as_queue_empty tells us if there are requests left in the device. It may
 * not be the case that a driver can get the next request even if the queue
 * is not empty - it is used in the block layer to check for plugging and
 * merging opportunities
 */
static int as_queue_empty(request_queue_t *q)
{
	struct as_data *ad = q->elevator->elevator_data;

	if (!list_empty(&ad->fifo_list[REQ_ASYNC])
		|| !list_empty(&ad->fifo_list[REQ_SYNC])
		|| !list_empty(ad->dispatch))
			return 0;

	return 1;
}

static struct request *
as_former_request(request_queue_t *q, struct request *rq)
{
	struct as_rq *arq = RQ_DATA(rq);
	struct rb_node *rbprev = rb_prev(&arq->rb_node);
	struct request *ret = NULL;

	if (rbprev)
		ret = rb_entry_arq(rbprev)->request;

	return ret;
}

static struct request *
as_latter_request(request_queue_t *q, struct request *rq)
{
	struct as_rq *arq = RQ_DATA(rq);
	struct rb_node *rbnext = rb_next(&arq->rb_node);
	struct request *ret = NULL;

	if (rbnext)
		ret = rb_entry_arq(rbnext)->request;

	return ret;