ll_rw_blk.c

Linux块设备驱动源码

	bqt->tag_index[tag] = rq;
	blkdev_dequeue_request(rq);
	list_add(&rq->queuelist, &bqt->busy_list);
	bqt->busy++;
	return 0;
}

EXPORT_SYMBOL(blk_queue_start_tag);

/**
 * blk_queue_invalidate_tags - invalidate all pending tags
 * @q:  the request queue for the device
 *
 *  Description:
 *   Hardware conditions may dictate a need to stop all pending requests.
 *   In this case, we will safely clear the block side of the tag queue and
 *   readd all requests to the request queue in the right order.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_invalidate_tags(request_queue_t *q)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	struct list_head *tmp, *n;
	struct request *rq;

	list_for_each_safe(tmp, n, &bqt->busy_list) {
		rq = list_entry_rq(tmp);

		if (rq->tag == -1) {
			printk(KERN_ERR
			       "%s: bad tag found on list\n", __FUNCTION__);
			list_del_init(&rq->queuelist);
			rq->flags &= ~REQ_QUEUED;
		} else
			blk_queue_end_tag(q, rq);

		rq->flags &= ~REQ_STARTED;
		__elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
	}
}

EXPORT_SYMBOL(blk_queue_invalidate_tags);

static char *rq_flags[] = {
	"REQ_RW",
	"REQ_FAILFAST",
	"REQ_SOFTBARRIER",
	"REQ_HARDBARRIER",
	"REQ_CMD",
	"REQ_NOMERGE",
	"REQ_STARTED",
	"REQ_DONTPREP",
	"REQ_QUEUED",
	"REQ_PC",
	"REQ_BLOCK_PC",
	"REQ_SENSE",
	"REQ_FAILED",
	"REQ_QUIET",
	"REQ_SPECIAL",
	"REQ_DRIVE_CMD",
	"REQ_DRIVE_TASK",
	"REQ_DRIVE_TASKFILE",
	"REQ_PREEMPT",
	"REQ_PM_SUSPEND",
	"REQ_PM_RESUME",
	"REQ_PM_SHUTDOWN",
};

void blk_dump_rq_flags(struct request *rq, char *msg)
{
	int bit;

	printk("%s: dev %s: flags = ", msg,
		rq->rq_disk ? rq->rq_disk->disk_name : "?");
	bit = 0;
	do {
		if (rq->flags & (1 << bit))
			printk("%s ", rq_flags[bit]);
		bit++;
	} while (bit < __REQ_NR_BITS);

	printk("\nsector %llu, nr/cnr %lu/%u\n", (unsigned long long)rq->sector,
						       rq->nr_sectors,
						       rq->current_nr_sectors);
	printk("bio %p, biotail %p, buffer %p, data %p, len %u\n", rq->bio, rq->biotail, rq->buffer, rq->data, rq->data_len);

	if (rq->flags & (REQ_BLOCK_PC | REQ_PC)) {
		printk("cdb: ");
		for (bit = 0; bit < sizeof(rq->cmd); bit++)
			printk("%02x ", rq->cmd[bit]);
		printk("\n");
	}
}

EXPORT_SYMBOL(blk_dump_rq_flags);

void blk_recount_segments(request_queue_t *q, struct bio *bio)
{
	struct bio_vec *bv, *bvprv = NULL;
	int i, nr_phys_segs, nr_hw_segs, seg_size, hw_seg_size, cluster;
	int high, highprv = 1;

	if (unlikely(!bio->bi_io_vec))
		return;

	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
	hw_seg_size = seg_size = nr_phys_segs = nr_hw_segs = 0;
	bio_for_each_segment(bv, bio, i) {
		/*
		 * the trick here is making sure that a high page is never
		 * considered part of another segment, since that might
		 * change with the bounce page.
		 */
		high = page_to_pfn(bv->bv_page) >= q->bounce_pfn;
		if (high || highprv)
			goto new_hw_segment;
		if (cluster) {
			if (seg_size + bv->bv_len > q->max_segment_size)
				goto new_segment;
			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
				goto new_segment;
			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
				goto new_segment;
			if (BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
				goto new_hw_segment;

			seg_size += bv->bv_len;
			hw_seg_size += bv->bv_len;
			bvprv = bv;
			continue;
		}
new_segment:
		if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
		    !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len)) {
			hw_seg_size += bv->bv_len;
		} else {
new_hw_segment:
			if (hw_seg_size > bio->bi_hw_front_size)
				bio->bi_hw_front_size = hw_seg_size;
			hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
			nr_hw_segs++;
		}

		nr_phys_segs++;
		bvprv = bv;
		seg_size = bv->bv_len;
		highprv = high;
	}
	if (hw_seg_size > bio->bi_hw_back_size)
		bio->bi_hw_back_size = hw_seg_size;
	if (nr_hw_segs == 1 && hw_seg_size > bio->bi_hw_front_size)
		bio->bi_hw_front_size = hw_seg_size;
	bio->bi_phys_segments = nr_phys_segs;
	bio->bi_hw_segments = nr_hw_segs;
	bio->bi_flags |= (1 << BIO_SEG_VALID);
}


static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
				   struct bio *nxt)
{
	if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
		return 0;

	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
		return 0;
	if (bio->bi_size + nxt->bi_size > q->max_segment_size)
		return 0;

	/*
	 * bio and nxt are contigous in memory, check if the queue allows
	 * these two to be merged into one
	 */
	if (BIO_SEG_BOUNDARY(q, bio, nxt))
		return 1;

	return 0;
}

static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio,
				 struct bio *nxt)
{
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
		blk_recount_segments(q, nxt);
	if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
	    BIOVEC_VIRT_OVERSIZE(bio->bi_hw_front_size + bio->bi_hw_back_size))
		return 0;
	if (bio->bi_size + nxt->bi_size > q->max_segment_size)
		return 0;

	return 1;
}

/*
 * map a request to scatterlist, return number of sg entries setup. Caller
 * must make sure sg can hold rq->nr_phys_segments entries
 */
int blk_rq_map_sg(request_queue_t *q, struct request *rq, struct scatterlist *sg)
{
	struct bio_vec *bvec, *bvprv;
	struct bio *bio;
	int nsegs, i, cluster;

	nsegs = 0;
	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);

	/*
	 * for each bio in rq
	 */
	bvprv = NULL;
	rq_for_each_bio(bio, rq) {
		/*
		 * for each segment in bio
		 */
		bio_for_each_segment(bvec, bio, i) {
			int nbytes = bvec->bv_len;

			if (bvprv && cluster) {
				if (sg[nsegs - 1].length + nbytes > q->max_segment_size)
					goto new_segment;

				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
					goto new_segment;
				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
					goto new_segment;

				sg[nsegs - 1].length += nbytes;
			} else {
new_segment:
				memset(&sg[nsegs],0,sizeof(struct scatterlist));
				sg[nsegs].page = bvec->bv_page;
				sg[nsegs].length = nbytes;
				sg[nsegs].offset = bvec->bv_offset;

				nsegs++;
			}
			bvprv = bvec;
		} /* segments in bio */
	} /* bios in rq */

	return nsegs;
}

EXPORT_SYMBOL(blk_rq_map_sg);

/*
 * the standard queue merge functions, can be overridden with device
 * specific ones if so desired
 */

static inline int ll_new_mergeable(request_queue_t *q,
				   struct request *req,
				   struct bio *bio)
{
	int nr_phys_segs = bio_phys_segments(q, bio);

	if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
		req->flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}

	/*
	 * A hw segment is just getting larger, bump just the phys
	 * counter.
	 */
	req->nr_phys_segments += nr_phys_segs;
	return 1;
}

static inline int ll_new_hw_segment(request_queue_t *q,
				    struct request *req,
				    struct bio *bio)
{
	int nr_hw_segs = bio_hw_segments(q, bio);
	int nr_phys_segs = bio_phys_segments(q, bio);

	if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
		req->flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}

	/*
	 * This will form the start of a new hw segment.  Bump both
	 * counters.
	 */
	req->nr_hw_segments += nr_hw_segs;
	req->nr_phys_segments += nr_phys_segs;
	return 1;
}

static int ll_back_merge_fn(request_queue_t *q, struct request *req, 
			    struct bio *bio)
{
	int len;

	if (req->nr_sectors + bio_sectors(bio) > q->max_sectors) {
		req->flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}
	if (unlikely(!bio_flagged(req->biotail, BIO_SEG_VALID)))
		blk_recount_segments(q, req->biotail);
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	len = req->biotail->bi_hw_back_size + bio->bi_hw_front_size;
	if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(req->biotail), __BVEC_START(bio)) &&
	    !BIOVEC_VIRT_OVERSIZE(len)) {
		int mergeable =  ll_new_mergeable(q, req, bio);

		if (mergeable) {
			if (req->nr_hw_segments == 1)
				req->bio->bi_hw_front_size = len;
			if (bio->bi_hw_segments == 1)
				bio->bi_hw_back_size = len;
		}
		return mergeable;
	}

	return ll_new_hw_segment(q, req, bio);
}

static int ll_front_merge_fn(request_queue_t *q, struct request *req, 
			     struct bio *bio)
{
	int len;

	if (req->nr_sectors + bio_sectors(bio) > q->max_sectors) {
		req->flags |= REQ_NOMERGE;
		if (req == q->last_merge)
			q->last_merge = NULL;
		return 0;
	}
	len = bio->bi_hw_back_size + req->bio->bi_hw_front_size;
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);
	if (unlikely(!bio_flagged(req->bio, BIO_SEG_VALID)))
		blk_recount_segments(q, req->bio);
	if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(req->bio)) &&
	    !BIOVEC_VIRT_OVERSIZE(len)) {
		int mergeable =  ll_new_mergeable(q, req, bio);

		if (mergeable) {
			if (bio->bi_hw_segments == 1)
				bio->bi_hw_front_size = len;
			if (req->nr_hw_segments == 1)
				req->biotail->bi_hw_back_size = len;
		}
		return mergeable;
	}

	return ll_new_hw_segment(q, req, bio);
}

static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
				struct request *next)
{
	int total_phys_segments;
	int total_hw_segments;

	/*
	 * First check if the either of the requests are re-queued
	 * requests.  Can't merge them if they are.
	 */
	if (req->special || next->special)
		return 0;

	/*
	 * Will it become too large?
	 */
	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
		return 0;

	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
	if (blk_phys_contig_segment(q, req->biotail, next->bio))
		total_phys_segments--;

	if (total_phys_segments > q->max_phys_segments)
		return 0;

	total_hw_segments = req->nr_hw_segments + next->nr_hw_segments;
	if (blk_hw_contig_segment(q, req->biotail, next->bio)) {
		int len = req->biotail->bi_hw_back_size + next->bio->bi_hw_front_size;
		/*
		 * propagate the combined length to the end of the requests
		 */
		if (req->nr_hw_segments == 1)
			req->bio->bi_hw_front_size = len;
		if (next->nr_hw_segments == 1)
			next->biotail->bi_hw_back_size = len;
		total_hw_segments--;
	}

	if (total_hw_segments > q->max_hw_segments)
		return 0;

	/* Merge is OK... */
	req->nr_phys_segments = total_phys_segments;
	req->nr_hw_segments = total_hw_segments;
	return 1;
}

/*
 * "plug" the device if there are no outstanding requests: this will
 * force the transfer to start only after we have put all the requests
 * on the list.
 *
 * This is called with interrupts off and no requests on the queue and
 * with the queue lock held.
 */
void blk_plug_device(request_queue_t *q)
{
	WARN_ON(!irqs_disabled());

	/*
	 * don't plug a stopped queue, it must be paired with blk_start_queue()
	 * which will restart the queueing
	 */
	if (test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags))
		return;

	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
}

EXPORT_SYMBOL(blk_plug_device);

/*
 * remove the queue from the plugged list, if present. called with
 * queue lock held and interrupts disabled.
 */
int blk_remove_plug(request_queue_t *q)
{
	WARN_ON(!irqs_disabled());

	if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
		return 0;

	del_timer(&q->unplug_timer);
	return 1;
}

EXPORT_SYMBOL(blk_remove_plug);

/*
 * remove the plug and let it rip..
 */
void __generic_unplug_device(request_queue_t *q)
{
	if (unlikely(test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags)))
		return;

	if (!blk_remove_plug(q))
		return;

	q->request_fn(q);
}
EXPORT_SYMBOL(__generic_unplug_device);

/**
 * generic_unplug_device - fire a request queue
 * @q:    The &request_queue_t in question
 *
 * Description:
 *   Linux uses plugging to build bigger requests queues before letting
 *   the device have at them. If a queue is plugged, the I/O scheduler
 *   is still adding and merging requests on the queue. Once the queue
 *   gets unplugged, the request_fn defined for the queue is invoked and
 *   transfers started.
 **/
void generic_unplug_device(request_queue_t *q)
{
	spin_lock_irq(q->queue_lock);
	__generic_unplug_device(q);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL(generic_unplug_device);

static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
				   struct page *page)
{
	request_queue_t *q = bdi->unplug_io_data;

	/*
	 * devices don't necessarily have an ->unplug_fn defined
	 */
	if (q->unplug_fn)
		q->unplug_fn(q);