ll_rw_blk.c

Linux块设备驱动源码

	while (!rq) {
		DEFINE_WAIT(wait);
		struct request_list *rl = &q->rq;

		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
				TASK_UNINTERRUPTIBLE);

		rq = get_request(q, rw, bio, GFP_NOIO);

		if (!rq) {
			struct io_context *ioc;

			__generic_unplug_device(q);
			spin_unlock_irq(q->queue_lock);
			io_schedule();

			/*
			 * After sleeping, we become a "batching" process and
			 * will be able to allocate at least one request, and
			 * up to a big batch of them for a small period time.
			 * See ioc_batching, ioc_set_batching
			 */
			ioc = current_io_context(GFP_NOIO);
			ioc_set_batching(q, ioc);

			spin_lock_irq(q->queue_lock);
		}
		finish_wait(&rl->wait[rw], &wait);
	}

	return rq;
}

struct request *blk_get_request(request_queue_t *q, int rw, int gfp_mask)
{
	struct request *rq;

	BUG_ON(rw != READ && rw != WRITE);

	spin_lock_irq(q->queue_lock);
	if (gfp_mask & __GFP_WAIT) {
		rq = get_request_wait(q, rw, NULL);
	} else {
		rq = get_request(q, rw, NULL, gfp_mask);
		if (!rq)
			spin_unlock_irq(q->queue_lock);
	}
	/* q->queue_lock is unlocked at this point */

	return rq;
}
EXPORT_SYMBOL(blk_get_request);

/**
 * blk_requeue_request - put a request back on queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 *
 * Description:
 *    Drivers often keep queueing requests until the hardware cannot accept
 *    more, when that condition happens we need to put the request back
 *    on the queue. Must be called with queue lock held.
 */
void blk_requeue_request(request_queue_t *q, struct request *rq)
{
	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	elv_requeue_request(q, rq);
}

EXPORT_SYMBOL(blk_requeue_request);

/**
 * blk_insert_request - insert a special request in to a request queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 * @at_head:	insert request at head or tail of queue
 * @data:	private data
 *
 * Description:
 *    Many block devices need to execute commands asynchronously, so they don't
 *    block the whole kernel from preemption during request execution.  This is
 *    accomplished normally by inserting aritficial requests tagged as
 *    REQ_SPECIAL in to the corresponding request queue, and letting them be
 *    scheduled for actual execution by the request queue.
 *
 *    We have the option of inserting the head or the tail of the queue.
 *    Typically we use the tail for new ioctls and so forth.  We use the head
 *    of the queue for things like a QUEUE_FULL message from a device, or a
 *    host that is unable to accept a particular command.
 */
void blk_insert_request(request_queue_t *q, struct request *rq,
			int at_head, void *data)
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
	unsigned long flags;

	/*
	 * tell I/O scheduler that this isn't a regular read/write (ie it
	 * must not attempt merges on this) and that it acts as a soft
	 * barrier
	 */
	rq->flags |= REQ_SPECIAL | REQ_SOFTBARRIER;

	rq->special = data;

	spin_lock_irqsave(q->queue_lock, flags);

	/*
	 * If command is tagged, release the tag
	 */
	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	drive_stat_acct(rq, rq->nr_sectors, 1);
	__elv_add_request(q, rq, where, 0);

	if (blk_queue_plugged(q))
		__generic_unplug_device(q);
	else
		q->request_fn(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

EXPORT_SYMBOL(blk_insert_request);

/**
 * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request structure to fill
 * @ubuf:	the user buffer
 * @len:	length of user data
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
		    unsigned int len)
{
	unsigned long uaddr;
	struct bio *bio;
	int reading;

	if (len > (q->max_sectors << 9))
		return -EINVAL;
	if (!len || !ubuf)
		return -EINVAL;

	reading = rq_data_dir(rq) == READ;

	/*
	 * if alignment requirement is satisfied, map in user pages for
	 * direct dma. else, set up kernel bounce buffers
	 */
	uaddr = (unsigned long) ubuf;
	if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
		bio = bio_map_user(q, NULL, uaddr, len, reading);
	else
		bio = bio_copy_user(q, uaddr, len, reading);

	if (!IS_ERR(bio)) {
		rq->bio = rq->biotail = bio;
		blk_rq_bio_prep(q, rq, bio);

		rq->buffer = rq->data = NULL;
		rq->data_len = len;
		return 0;
	}

	/*
	 * bio is the err-ptr
	 */
	return PTR_ERR(bio);
}

EXPORT_SYMBOL(blk_rq_map_user);

/**
 * blk_rq_map_user_iov - map user data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request to map data to
 * @iov:	pointer to the iovec
 * @iov_count:	number of elements in the iovec
 *
 * Description:
 *    Data will be mapped directly for zero copy io, if possible. Otherwise
 *    a kernel bounce buffer is used.
 *
 *    A matching blk_rq_unmap_user() must be issued at the end of io, while
 *    still in process context.
 *
 *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
 *    before being submitted to the device, as pages mapped may be out of
 *    reach. It's the callers responsibility to make sure this happens. The
 *    original bio must be passed back in to blk_rq_unmap_user() for proper
 *    unmapping.
 */
int blk_rq_map_user_iov(request_queue_t *q, struct request *rq,
			struct sg_iovec *iov, int iov_count)
{
	struct bio *bio;

	if (!iov || iov_count <= 0)
		return -EINVAL;

	/* we don't allow misaligned data like bio_map_user() does.  If the
	 * user is using sg, they're expected to know the alignment constraints
	 * and respect them accordingly */
	bio = bio_map_user_iov(q, NULL, iov, iov_count, rq_data_dir(rq)== READ);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	rq->bio = rq->biotail = bio;
	blk_rq_bio_prep(q, rq, bio);
	rq->buffer = rq->data = NULL;
	rq->data_len = bio->bi_size;
	return 0;
}

EXPORT_SYMBOL(blk_rq_map_user_iov);

/**
 * blk_rq_unmap_user - unmap a request with user data
 * @bio:	bio to be unmapped
 * @ulen:	length of user buffer
 *
 * Description:
 *    Unmap a bio previously mapped by blk_rq_map_user().
 */
int blk_rq_unmap_user(struct bio *bio, unsigned int ulen)
{
	int ret = 0;

	if (bio) {
		if (bio_flagged(bio, BIO_USER_MAPPED))
			bio_unmap_user(bio);
		else
			ret = bio_uncopy_user(bio);
	}

	return 0;
}

EXPORT_SYMBOL(blk_rq_unmap_user);

/**
 * blk_rq_map_kern - map kernel data to a request, for REQ_BLOCK_PC usage
 * @q:		request queue where request should be inserted
 * @rq:		request to fill
 * @kbuf:	the kernel buffer
 * @len:	length of user data
 * @gfp_mask:	memory allocation flags
 */
int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf,
		    unsigned int len, unsigned int gfp_mask)
{
	struct bio *bio;

	if (len > (q->max_sectors << 9))
		return -EINVAL;
	if (!len || !kbuf)
		return -EINVAL;

	bio = bio_map_kern(q, kbuf, len, gfp_mask);
	if (IS_ERR(bio))
		return PTR_ERR(bio);

	if (rq_data_dir(rq) == WRITE)
		bio->bi_rw |= (1 << BIO_RW);

	rq->bio = rq->biotail = bio;
	blk_rq_bio_prep(q, rq, bio);

	rq->buffer = rq->data = NULL;
	rq->data_len = len;
	return 0;
}

EXPORT_SYMBOL(blk_rq_map_kern);

/**
 * blk_execute_rq_nowait - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 * @done:	I/O completion handler
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution.  Don't wait for completion.
 */
void blk_execute_rq_nowait(request_queue_t *q, struct gendisk *bd_disk,
			   struct request *rq, int at_head,
			   void (*done)(struct request *))
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;

	rq->rq_disk = bd_disk;
	rq->flags |= REQ_NOMERGE;
	rq->end_io = done;
	elv_add_request(q, rq, where, 1);
	generic_unplug_device(q);
}

/**
 * blk_execute_rq - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 *
 * Description:
 *    Insert a fully prepared request at the back of the io scheduler queue
 *    for execution and wait for completion.
 */
int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk,
		   struct request *rq, int at_head)
{
	DECLARE_COMPLETION(wait);
	char sense[SCSI_SENSE_BUFFERSIZE];
	int err = 0;

	/*
	 * we need an extra reference to the request, so we can look at
	 * it after io completion
	 */
	rq->ref_count++;

	if (!rq->sense) {
		memset(sense, 0, sizeof(sense));
		rq->sense = sense;
		rq->sense_len = 0;
	}

	rq->waiting = &wait;
	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
	wait_for_completion(&wait);
	rq->waiting = NULL;

	if (rq->errors)
		err = -EIO;

	return err;
}

EXPORT_SYMBOL(blk_execute_rq);

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:	blockdev to issue flush for
 * @error_sector:	error sector
 *
 * Description:
 *    Issue a flush for the block device in question. Caller can supply
 *    room for storing the error offset in case of a flush error, if they
 *    wish to.  Caller must run wait_for_completion() on its own.
 */
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
	request_queue_t *q;

	if (bdev->bd_disk == NULL)
		return -ENXIO;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;
	if (!q->issue_flush_fn)
		return -EOPNOTSUPP;

	return q->issue_flush_fn(q, bdev->bd_disk, error_sector);
}

EXPORT_SYMBOL(blkdev_issue_flush);

static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io)
{
	int rw = rq_data_dir(rq);

	if (!blk_fs_request(rq) || !rq->rq_disk)
		return;

	if (rw == READ) {
		__disk_stat_add(rq->rq_disk, read_sectors, nr_sectors);
		if (!new_io)
			__disk_stat_inc(rq->rq_disk, read_merges);
	} else if (rw == WRITE) {
		__disk_stat_add(rq->rq_disk, write_sectors, nr_sectors);
		if (!new_io)
			__disk_stat_inc(rq->rq_disk, write_merges);
	}
	if (new_io) {
		disk_round_stats(rq->rq_disk);
		rq->rq_disk->in_flight++;
	}
}

/*
 * add-request adds a request to the linked list.
 * queue lock is held and interrupts disabled, as we muck with the
 * request queue list.
 */
static inline void add_request(request_queue_t * q, struct request * req)
{
	drive_stat_acct(req, req->nr_sectors, 1);

	if (q->activity_fn)
		q->activity_fn(q->activity_data, rq_data_dir(req));

	/*
	 * elevator indicated where it wants this request to be
	 * inserted at elevator_merge time
	 */
	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
}
 
/*
 * disk_round_stats()	- Round off the performance stats on a struct
 * disk_stats.
 *
 * The average IO queue length and utilisation statistics are maintained
 * by observing the current state of the queue length and the amount of
 * time it has been in this state for.
 *
 * Normally, that accounting is done on IO completion, but that can result
 * in more than a second's worth of IO being accounted for within any one
 * second, leading to >100% utilisation.  To deal with that, we call this
 * function to do a round-off before returning the results when reading
 * /proc/diskstats.  This accounts immediately for all queue usage up to
 * the current jiffies and restarts the counters again.
 */
void disk_round_stats(struct gendisk *disk)
{
	unsigned long now = jiffies;

	__disk_stat_add(disk, time_in_queue,
			disk->in_flight * (now - disk->stamp));
	disk->stamp = now;

	if (disk->in_flight)
		__disk_stat_add(disk, io_ticks, (now - disk->stamp_idle));
	disk->stamp_idle = now;
}

/*
 * queue lock must be held
 */
static void __blk_put_request(request_queue_t *q, struct request *req)
{
	struct request_list *rl = req->rl;

	if (unlikely(!q))
		return;
	if (unlikely(--req->ref_count))
		return;

	req->rq_status = RQ_INACTIVE;
	req->rl = NULL;

	/*
	 * Request may not have originated from ll_rw_blk. if not,
	 * it didn't come out of our reserved rq pools
	 */
	if (rl) {
		int rw = rq_data_dir(req);

		elv_completed_request(q, req);

		BUG_ON(!list_empty(&req->queuelist));

		blk_free_request(q, req);
		freed_request(q, rw);
	}
}

void blk_put_request(struct request *req)
{
	/*
	 * if req->rl isn't set, this request didnt originate from the
	 * block layer, so it's safe to just disregard it
	 */
	if (req->rl) {
		unsigned lo