ll_rw_blk.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,525 行 · 第 1/5 页

 * @tag: The tag of the request
 *
 * Notes:
 *    Should be used when a device returns a tag and you want to match
 *    it with a request.
 *
 *    no locks need be held.
 **/
struct request *blk_queue_find_tag(request_queue_t *q, int tag)
{
	struct blk_queue_tag *bqt = q->queue_tags;

	if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
		return NULL;

	return bqt->tag_index[tag];
}

EXPORT_SYMBOL(blk_queue_find_tag);

/**
 * __blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *    blk_cleanup_queue() will take care of calling this function, if tagging
 *    has been used. So there's no need to call this directly.
 **/
static void __blk_queue_free_tags(request_queue_t *q)
{
	struct blk_queue_tag *bqt = q->queue_tags;

	if (!bqt)
		return;

	if (atomic_dec_and_test(&bqt->refcnt)) {
		BUG_ON(bqt->busy);
		BUG_ON(!list_empty(&bqt->busy_list));

		kfree(bqt->tag_index);
		bqt->tag_index = NULL;

		kfree(bqt->tag_map);
		bqt->tag_map = NULL;

		kfree(bqt);
	}

	q->queue_tags = NULL;
	q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
}

/**
 * blk_queue_free_tags - release tag maintenance info
 * @q:  the request queue for the device
 *
 *  Notes:
 *	This is used to disabled tagged queuing to a device, yet leave
 *	queue in function.
 **/
void blk_queue_free_tags(request_queue_t *q)
{
	clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
}

EXPORT_SYMBOL(blk_queue_free_tags);

static int
init_tag_map(request_queue_t *q, struct blk_queue_tag *tags, int depth)
{
	int bits, i;
	struct request **tag_index;
	unsigned long *tag_map;

	if (depth > q->nr_requests * 2) {
		depth = q->nr_requests * 2;
		printk(KERN_ERR "%s: adjusted depth to %d\n",
				__FUNCTION__, depth);
	}

	tag_index = kmalloc(depth * sizeof(struct request *), GFP_ATOMIC);
	if (!tag_index)
		goto fail;

	bits = (depth / BLK_TAGS_PER_LONG) + 1;
	tag_map = kmalloc(bits * sizeof(unsigned long), GFP_ATOMIC);
	if (!tag_map)
		goto fail;

	memset(tag_index, 0, depth * sizeof(struct request *));
	memset(tag_map, 0, bits * sizeof(unsigned long));
	tags->max_depth = depth;
	tags->real_max_depth = bits * BITS_PER_LONG;
	tags->tag_index = tag_index;
	tags->tag_map = tag_map;

	/*
	 * set the upper bits if the depth isn't a multiple of the word size
	 */
	for (i = depth; i < bits * BLK_TAGS_PER_LONG; i++)
		__set_bit(i, tag_map);

	return 0;
fail:
	kfree(tag_index);
	return -ENOMEM;
}

/**
 * blk_queue_init_tags - initialize the queue tag info
 * @q:  the request queue for the device
 * @depth:  the maximum queue depth supported
 **/
int blk_queue_init_tags(request_queue_t *q, int depth,
			struct blk_queue_tag *tags)
{
	int rc;

	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);

	if (!tags && !q->queue_tags) {
		tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
		if (!tags)
			goto fail;

		if (init_tag_map(q, tags, depth))
			goto fail;

		INIT_LIST_HEAD(&tags->busy_list);
		tags->busy = 0;
		atomic_set(&tags->refcnt, 1);
	} else if (q->queue_tags) {
		if ((rc = blk_queue_resize_tags(q, depth)))
			return rc;
		set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
		return 0;
	} else
		atomic_inc(&tags->refcnt);

	/*
	 * assign it, all done
	 */
	q->queue_tags = tags;
	q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
	return 0;
fail:
	kfree(tags);
	return -ENOMEM;
}

EXPORT_SYMBOL(blk_queue_init_tags);

/**
 * blk_queue_resize_tags - change the queueing depth
 * @q:  the request queue for the device
 * @new_depth: the new max command queueing depth
 *
 *  Notes:
 *    Must be called with the queue lock held.
 **/
int blk_queue_resize_tags(request_queue_t *q, int new_depth)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	struct request **tag_index;
	unsigned long *tag_map;
	int bits, max_depth;

	if (!bqt)
		return -ENXIO;

	/*
	 * don't bother sizing down
	 */
	if (new_depth <= bqt->real_max_depth) {
		bqt->max_depth = new_depth;
		return 0;
	}

	/*
	 * save the old state info, so we can copy it back
	 */
	tag_index = bqt->tag_index;
	tag_map = bqt->tag_map;
	max_depth = bqt->real_max_depth;

	if (init_tag_map(q, bqt, new_depth))
		return -ENOMEM;

	memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
	bits = max_depth / BLK_TAGS_PER_LONG;
	memcpy(bqt->tag_map, tag_map, bits * sizeof(unsigned long));

	kfree(tag_index);
	kfree(tag_map);
	return 0;
}

EXPORT_SYMBOL(blk_queue_resize_tags);

/**
 * blk_queue_end_tag - end tag operations for a request
 * @q:  the request queue for the device
 * @rq: the request that has completed
 *
 *  Description:
 *    Typically called when end_that_request_first() returns 0, meaning
 *    all transfers have been done for a request. It's important to call
 *    this function before end_that_request_last(), as that will put the
 *    request back on the free list thus corrupting the internal tag list.
 *
 *  Notes:
 *   queue lock must be held.
 **/
void blk_queue_end_tag(request_queue_t *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	int tag = rq->tag;

	BUG_ON(tag == -1);

	if (unlikely(tag >= bqt->real_max_depth))
		return;

	if (unlikely(!__test_and_clear_bit(tag, bqt->tag_map))) {
		printk("attempt to clear non-busy tag (%d)\n", tag);
		return;
	}

	list_del_init(&rq->queuelist);
	rq->flags &= ~REQ_QUEUED;
	rq->tag = -1;

	if (unlikely(bqt->tag_index[tag] == NULL))
		printk("tag %d is missing\n", tag);

	bqt->tag_index[tag] = NULL;
	bqt->busy--;
}

EXPORT_SYMBOL(blk_queue_end_tag);

/**
 * blk_queue_start_tag - find a free tag and assign it
 * @q:  the request queue for the device
 * @rq:  the block request that needs tagging
 *
 *  Description:
 *    This can either be used as a stand-alone helper, or possibly be
 *    assigned as the queue &prep_rq_fn (in which case &struct request
 *    automagically gets a tag assigned). Note that this function
 *    assumes that any type of request can be queued! if this is not
 *    true for your device, you must check the request type before
 *    calling this function.  The request will also be removed from
 *    the request queue, so it's the drivers responsibility to readd
 *    it if it should need to be restarted for some reason.
 *
 *  Notes:
 *   queue lock must be held.
 **/
int blk_queue_start_tag(request_queue_t *q, struct request *rq)
{
	struct blk_queue_tag *bqt = q->queue_tags;
	unsigned long *map = bqt->tag_map;
	int tag = 0;

	if (unlikely((rq->flags & REQ_QUEUED))) {
		printk(KERN_ERR 
		       "request %p for device [%s] already tagged %d",
		       rq, rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
		BUG();
	}

	for (map = bqt->tag_map; *map == -1UL; map++) {
		tag += BLK_TAGS_PER_LONG;

		if (tag >= bqt->max_depth)
			return 1;
	}

	tag += ffz(*map);
	__set_bit(tag, bqt->tag_map);

	rq->flags |= REQ_QUEUED;
	rq->tag = tag;
	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("bad tag found on list\n");
			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);
}


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;
}

EXPORT_SYMBOL(blk_phys_contig_segment);

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;
}

EXPORT_SYMBOL(blk_hw_contig_segment);

/*
 * 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
		 */