block: move request based cloning helpers to blk-mq.c

Keep all the request based code together.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20211117061404.331732-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 174 insertions, 1 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index df28e5ef8c2d..812dac9ecb29 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2435,7 +2435,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	hctx_unlock(hctx, srcu_idx);
 }
 
-blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
+static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 {
 	blk_status_t ret;
 	int srcu_idx;
@@ -2824,6 +2824,179 @@ void blk_mq_submit_bio(struct bio *bio)
 	}
 }
 
+/**
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ *                              for the new queue limits
+ * @q:  the queue
+ * @rq: the request being checked
+ *
+ * Description:
+ *    @rq may have been made based on weaker limitations of upper-level queues
+ *    in request stacking drivers, and it may violate the limitation of @q.
+ *    Since the block layer and the underlying device driver trust @rq
+ *    after it is inserted to @q, it should be checked against @q before
+ *    the insertion using this generic function.
+ *
+ *    Request stacking drivers like request-based dm may change the queue
+ *    limits when retrying requests on other queues. Those requests need
+ *    to be checked against the new queue limits again during dispatch.
+ */
+static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q,
+				      struct request *rq)
+{
+	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+
+	if (blk_rq_sectors(rq) > max_sectors) {
+		/*
+		 * SCSI device does not have a good way to return if
+		 * Write Same/Zero is actually supported. If a device rejects
+		 * a non-read/write command (discard, write same,etc.) the
+		 * low-level device driver will set the relevant queue limit to
+		 * 0 to prevent blk-lib from issuing more of the offending
+		 * operations. Commands queued prior to the queue limit being
+		 * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O
+		 * errors being propagated to upper layers.
+		 */
+		if (max_sectors == 0)
+			return BLK_STS_NOTSUPP;
+
+		printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
+			__func__, blk_rq_sectors(rq), max_sectors);
+		return BLK_STS_IOERR;
+	}
+
+	/*
+	 * The queue settings related to segment counting may differ from the
+	 * original queue.
+	 */
+	rq->nr_phys_segments = blk_recalc_rq_segments(rq);
+	if (rq->nr_phys_segments > queue_max_segments(q)) {
+		printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
+			__func__, rq->nr_phys_segments, queue_max_segments(q));
+		return BLK_STS_IOERR;
+	}
+
+	return BLK_STS_OK;
+}
+
+/**
+ * blk_insert_cloned_request - Helper for stacking drivers to submit a request
+ * @q:  the queue to submit the request
+ * @rq: the request being queued
+ */
+blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
+{
+	blk_status_t ret;
+
+	ret = blk_cloned_rq_check_limits(q, rq);
+	if (ret != BLK_STS_OK)
+		return ret;
+
+	if (rq->rq_disk &&
+	    should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
+		return BLK_STS_IOERR;
+
+	if (blk_crypto_insert_cloned_request(rq))
+		return BLK_STS_IOERR;
+
+	blk_account_io_start(rq);
+
+	/*
+	 * Since we have a scheduler attached on the top device,
+	 * bypass a potential scheduler on the bottom device for
+	 * insert.
+	 */
+	return blk_mq_request_issue_directly(rq, true);
+}
+EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
+
+/**
+ * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
+ * @rq: the clone request to be cleaned up
+ *
+ * Description:
+ *     Free all bios in @rq for a cloned request.
+ */
+void blk_rq_unprep_clone(struct request *rq)
+{
+	struct bio *bio;
+
+	while ((bio = rq->bio) != NULL) {
+		rq->bio = bio->bi_next;
+
+		bio_put(bio);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
+
+/**
+ * blk_rq_prep_clone - Helper function to setup clone request
+ * @rq: the request to be setup
+ * @rq_src: original request to be cloned
+ * @bs: bio_set that bios for clone are allocated from
+ * @gfp_mask: memory allocation mask for bio
+ * @bio_ctr: setup function to be called for each clone bio.
+ *           Returns %0 for success, non %0 for failure.
+ * @data: private data to be passed to @bio_ctr
+ *
+ * Description:
+ *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
+ *     Also, pages which the original bios are pointing to are not copied
+ *     and the cloned bios just point same pages.
+ *     So cloned bios must be completed before original bios, which means
+ *     the caller must complete @rq before @rq_src.
+ */
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+		      struct bio_set *bs, gfp_t gfp_mask,
+		      int (*bio_ctr)(struct bio *, struct bio *, void *),
+		      void *data)
+{
+	struct bio *bio, *bio_src;
+
+	if (!bs)
+		bs = &fs_bio_set;
+
+	__rq_for_each_bio(bio_src, rq_src) {
+		bio = bio_clone_fast(bio_src, gfp_mask, bs);
+		if (!bio)
+			goto free_and_out;
+
+		if (bio_ctr && bio_ctr(bio, bio_src, data))
+			goto free_and_out;
+
+		if (rq->bio) {
+			rq->biotail->bi_next = bio;
+			rq->biotail = bio;
+		} else {
+			rq->bio = rq->biotail = bio;
+		}
+		bio = NULL;
+	}
+
+	/* Copy attributes of the original request to the clone request. */
+	rq->__sector = blk_rq_pos(rq_src);
+	rq->__data_len = blk_rq_bytes(rq_src);
+	if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+		rq->special_vec = rq_src->special_vec;
+	}
+	rq->nr_phys_segments = rq_src->nr_phys_segments;
+	rq->ioprio = rq_src->ioprio;
+
+	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
+		goto free_and_out;
+
+	return 0;
+
+free_and_out:
+	if (bio)
+		bio_put(bio);
+	blk_rq_unprep_clone(rq);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
+
 static size_t order_to_size(unsigned int order)
 {
 	return (size_t)PAGE_SIZE << order;