Merge tag 'for-5.20/block-2022-08-04' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - add support for In-Band authentication (Hannes Reinecke)
      - handle the persistent internal error AER (Michael Kelley)
      - use in-capsule data for TCP I/O queue connect (Caleb Sander)
      - remove timeout for getting RDMA-CM established event (Israel
        Rukshin)
      - misc cleanups (Joel Granados, Sagi Grimberg, Chaitanya Kulkarni,
        Guixin Liu, Xiang wangx)
      - use command_id instead of req->tag in trace_nvme_complete_rq()
        (Bean Huo)
      - various fixes for the new authentication code (Lukas Bulwahn,
        Dan Carpenter, Colin Ian King, Chaitanya Kulkarni, Hannes
        Reinecke)
      - small cleanups (Liu Song, Christoph Hellwig)
      - restore compat_ioctl support (Nick Bowler)
      - make a nvmet-tcp workqueue lockdep-safe (Sagi Grimberg)
      - enable generic interface (/dev/ngXnY) for unknown command sets
        (Joel Granados, Christoph Hellwig)
      - don't always build constants.o (Christoph Hellwig)
      - print the command name of aborted commands (Christoph Hellwig)

 - MD pull requests via Song:
      - Improve raid5 lock contention, by Logan Gunthorpe.
      - Misc fixes to raid5, by Logan Gunthorpe.
      - Fix race condition with md_reap_sync_thread(), by Guoqing Jiang.
      - Fix potential deadlock with raid5_quiesce and
        raid5_get_active_stripe, by Logan Gunthorpe.
      - Refactoring md_alloc(), by Christoph"
      - Fix md disk_name lifetime problems, by Christoph Hellwig
      - Convert prepare_to_wait() to wait_woken() api, by Logan
        Gunthorpe;
      - Fix sectors_to_do bitmap issue, by Logan Gunthorpe.

 - Work on unifying the null_blk module parameters and configfs API
   (Vincent)

 - drbd bitmap IO error fix (Lars)

 - Set of rnbd fixes (Guoqing, Md Haris)

 - Remove experimental marker on bcache async device registration (Coly)

 - Series from cleaning up the bio splitting (Christoph)

 - Removal of the sx8 block driver. This hardware never really
   widespread, and it didn't receive a lot of attention after the
   initial merge of it back in 2005 (Christoph)

 - A few fixes for s390 dasd (Eric, Jiang)

 - Followup set of fixes for ublk (Ming)

 - Support for UBLK_IO_NEED_GET_DATA for ublk (ZiyangZhang)

 - Fixes for the dio dma alignment (Keith)

 - Misc fixes and cleanups (Ming, Yu, Dan, Christophe

* tag 'for-5.20/block-2022-08-04' of git://git.kernel.dk/linux-block: (136 commits)
  s390/dasd: Establish DMA alignment
  s390/dasd: drop unexpected word 'for' in comments
  ublk_drv: add support for UBLK_IO_NEED_GET_DATA
  ublk_cmd.h: add one new ublk command: UBLK_IO_NEED_GET_DATA
  ublk_drv: cleanup ublksrv_ctrl_dev_info
  ublk_drv: add SET_PARAMS/GET_PARAMS control command
  ublk_drv: fix ublk device leak in case that add_disk fails
  ublk_drv: cancel device even though disk isn't up
  block: fix leaking page ref on truncated direct io
  block: ensure bio_iov_add_page can't fail
  block: ensure iov_iter advances for added pages
  drivers:md:fix a potential use-after-free bug
  md/raid5: Ensure batch_last is released before sleeping for quiesce
  md/raid5: Move stripe_request_ctx up
  md/raid5: Drop unnecessary call to r5c_check_stripe_cache_usage()
  md/raid5: Make is_inactive_blocked() helper
  md/raid5: Refactor raid5_get_active_stripe()
  block: pass struct queue_limits to the bio splitting helpers
  block: move bio_allowed_max_sectors to blk-merge.c
  block: move the call to get_max_io_size out of blk_bio_segment_split
  ...

9 files changed, 165 insertions, 171 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 32929c89ba8a..3f5685c00e36 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -134,7 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	iv = bip->bip_vec + bip->bip_vcnt;
 
 	if (bip->bip_vcnt &&
-	    bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev),
+	    bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits,
 			     &bip->bip_vec[bip->bip_vcnt - 1], offset))
 		return 0;
 
diff --git a/block/bio.c b/block/bio.c
index 6f9f883f9a65..d6eb90d9b20b 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -965,7 +965,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		 * would create a gap, disallow it.
 		 */
 		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-		if (bvec_gap_to_prev(q, bvec, offset))
+		if (bvec_gap_to_prev(&q->limits, bvec, offset))
 			return 0;
 	}
 
@@ -1151,22 +1151,12 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static void bio_put_pages(struct page **pages, size_t size, size_t off)
-{
-	size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
-
-	for (i = 0; i < nr; i++)
-		put_page(pages[i]);
-}
-
 static int bio_iov_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int offset)
 {
 	bool same_page = false;
 
 	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-		if (WARN_ON_ONCE(bio_full(bio, len)))
-			return -EINVAL;
 		__bio_add_page(bio, page, len, offset);
 		return 0;
 	}
@@ -1209,8 +1199,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
 	ssize_t size, left;
-	unsigned len, i;
+	unsigned len, i = 0;
 	size_t offset;
+	int ret = 0;
 
 	/*
 	 * Move page array up in the allocated memory for the bio vecs as far as
@@ -1227,32 +1218,40 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
-	if (size > 0)
+	size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size,
+				  nr_pages, &offset);
+	if (size > 0) {
+		nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
 		size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev));
-	if (unlikely(size <= 0))
-		return size ? size : -EFAULT;
+	} else
+		nr_pages = 0;
+
+	if (unlikely(size <= 0)) {
+		ret = size ? size : -EFAULT;
+		goto out;
+	}
 
 	for (left = size, i = 0; left > 0; left -= len, i++) {
 		struct page *page = pages[i];
-		int ret;
 
 		len = min_t(size_t, PAGE_SIZE - offset, left);
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			ret = bio_iov_add_zone_append_page(bio, page, len,
 					offset);
-		else
-			ret = bio_iov_add_page(bio, page, len, offset);
+			if (ret)
+				break;
+		} else
+			bio_iov_add_page(bio, page, len, offset);
 
-		if (ret) {
-			bio_put_pages(pages + i, left, offset);
-			return ret;
-		}
 		offset = 0;
 	}
 
-	iov_iter_advance(iter, size);
-	return 0;
+	iov_iter_advance(iter, size - left);
+out:
+	while (i < nr_pages)
+		put_page(pages[i++]);
+
+	return ret;
 }
 
 /**
diff --git a/block/blk-core.c b/block/blk-core.c
index 3d286a256d3d..a0d1104c5590 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -377,7 +377,6 @@ static void blk_timeout_work(struct work_struct *work)
 struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 {
 	struct request_queue *q;
-	int ret;
 
 	q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
 			GFP_KERNEL | __GFP_ZERO, node_id);
@@ -396,13 +395,9 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 	if (q->id < 0)
 		goto fail_srcu;
 
-	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0);
-	if (ret)
-		goto fail_id;
-
 	q->stats = blk_alloc_queue_stats();
 	if (!q->stats)
-		goto fail_split;
+		goto fail_id;
 
 	q->node = node_id;
 
@@ -439,8 +434,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 
 fail_stats:
 	blk_free_queue_stats(q->stats);
-fail_split:
-	bioset_exit(&q->bio_split);
 fail_id:
 	ida_free(&blk_queue_ida, q->id);
 fail_srcu:
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4c8a699754c9..ff04e9290715 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -82,7 +82,7 @@ static inline bool bio_will_gap(struct request_queue *q,
 	bio_get_first_bvec(next, &nb);
 	if (biovec_phys_mergeable(q, &pb, &nb))
 		return false;
-	return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+	return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset);
 }
 
 static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
@@ -95,23 +95,30 @@ static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
 	return bio_will_gap(req->q, NULL, bio, req->bio);
 }
 
-static struct bio *blk_bio_discard_split(struct request_queue *q,
-					 struct bio *bio,
-					 struct bio_set *bs,
-					 unsigned *nsegs)
+/*
+ * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
+ * is defined as 'unsigned int', meantime it has to be aligned to with the
+ * logical block size, which is the minimum accepted unit by hardware.
+ */
+static unsigned int bio_allowed_max_sectors(struct queue_limits *lim)
+{
+	return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT;
+}
+
+static struct bio *bio_split_discard(struct bio *bio, struct queue_limits *lim,
+		unsigned *nsegs, struct bio_set *bs)
 {
 	unsigned int max_discard_sectors, granularity;
-	int alignment;
 	sector_t tmp;
 	unsigned split_sectors;
 
 	*nsegs = 1;
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
+	granularity = max(lim->discard_granularity >> 9, 1U);
 
-	max_discard_sectors = min(q->limits.max_discard_sectors,
-			bio_allowed_max_sectors(q));
+	max_discard_sectors =
+		min(lim->max_discard_sectors, bio_allowed_max_sectors(lim));
 	max_discard_sectors -= max_discard_sectors % granularity;
 
 	if (unlikely(!max_discard_sectors)) {
@@ -128,9 +135,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	 * If the next starting sector would be misaligned, stop the discard at
 	 * the previous aligned sector.
 	 */
-	alignment = (q->limits.discard_alignment >> 9) % granularity;
-
-	tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
+	tmp = bio->bi_iter.bi_sector + split_sectors -
+		((lim->discard_alignment >> 9) % granularity);
 	tmp = sector_div(tmp, granularity);
 
 	if (split_sectors > tmp)
@@ -139,18 +145,15 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	return bio_split(bio, split_sectors, GFP_NOIO, bs);
 }
 
-static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
-		struct bio *bio, struct bio_set *bs, unsigned *nsegs)
+static struct bio *bio_split_write_zeroes(struct bio *bio,
+		struct queue_limits *lim, unsigned *nsegs, struct bio_set *bs)
 {
 	*nsegs = 0;
-
-	if (!q->limits.max_write_zeroes_sectors)
+	if (!lim->max_write_zeroes_sectors)
 		return NULL;
-
-	if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
+	if (bio_sectors(bio) <= lim->max_write_zeroes_sectors)
 		return NULL;
-
-	return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
 }
 
 /*
@@ -161,17 +164,17 @@ static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
  * requests that are submitted to a block device if the start of a bio is not
  * aligned to a physical block boundary.
  */
-static inline unsigned get_max_io_size(struct request_queue *q,
-				       struct bio *bio)
+static inline unsigned get_max_io_size(struct bio *bio,
+		struct queue_limits *lim)
 {
-	unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
-	unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
-	unsigned max_sectors = queue_max_sectors(q), start, end;
+	unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT;
+	unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT;
+	unsigned max_sectors = lim->max_sectors, start, end;
 
-	if (q->limits.chunk_sectors) {
+	if (lim->chunk_sectors) {
 		max_sectors = min(max_sectors,
 			blk_chunk_sectors_left(bio->bi_iter.bi_sector,
-					       q->limits.chunk_sectors));
+					       lim->chunk_sectors));
 	}
 
 	start = bio->bi_iter.bi_sector & (pbs - 1);
@@ -181,11 +184,10 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return max_sectors & ~(lbs - 1);
 }
 
-static inline unsigned get_max_segment_size(const struct request_queue *q,
-					    struct page *start_page,
-					    unsigned long offset)
+static inline unsigned get_max_segment_size(struct queue_limits *lim,
+		struct page *start_page, unsigned long offset)
 {
-	unsigned long mask = queue_segment_boundary(q);
+	unsigned long mask = lim->seg_boundary_mask;
 
 	offset = mask & (page_to_phys(start_page) + offset);
 
@@ -194,12 +196,12 @@ static inline unsigned get_max_segment_size(const struct request_queue *q,
 	 * on 32bit arch, use queue's max segment size when that happens.
 	 */
 	return min_not_zero(mask - offset + 1,
-			(unsigned long)queue_max_segment_size(q));
+			(unsigned long)lim->max_segment_size);
 }
 
 /**
  * bvec_split_segs - verify whether or not a bvec should be split in the middle
- * @q:        [in] request queue associated with the bio associated with @bv
+ * @lim:      [in] queue limits to split based on
  * @bv:       [in] bvec to examine
  * @nsegs:    [in,out] Number of segments in the bio being built. Incremented
  *            by the number of segments from @bv that may be appended to that
@@ -217,10 +219,9 @@ static inline unsigned get_max_segment_size(const struct request_queue *q,
  * *@nsegs segments and *@sectors sectors would make that bio unacceptable for
  * the block driver.
  */
-static bool bvec_split_segs(const struct request_queue *q,
-			    const struct bio_vec *bv, unsigned *nsegs,
-			    unsigned *bytes, unsigned max_segs,
-			    unsigned max_bytes)
+static bool bvec_split_segs(struct queue_limits *lim, const struct bio_vec *bv,
+		unsigned *nsegs, unsigned *bytes, unsigned max_segs,
+		unsigned max_bytes)
 {
 	unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
 	unsigned len = min(bv->bv_len, max_len);
@@ -228,7 +229,7 @@ static bool bvec_split_segs(const struct request_queue *q,
 	unsigned seg_size = 0;
 
 	while (len && *nsegs < max_segs) {
-		seg_size = get_max_segment_size(q, bv->bv_page,
+		seg_size = get_max_segment_size(lim, bv->bv_page,
 						bv->bv_offset + total_len);
 		seg_size = min(seg_size, len);
 
@@ -236,7 +237,7 @@ static bool bvec_split_segs(const struct request_queue *q,
 		total_len += seg_size;
 		len -= seg_size;
 
-		if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
+		if ((bv->bv_offset + total_len) & lim->virt_boundary_mask)
 			break;
 	}
 
@@ -247,16 +248,17 @@ static bool bvec_split_segs(const struct request_queue *q,
 }
 
 /**
- * blk_bio_segment_split - split a bio in two bios
- * @q:    [in] request queue pointer
+ * bio_split_rw - split a bio in two bios
  * @bio:  [in] bio to be split
- * @bs:	  [in] bio set to allocate the clone from
+ * @lim:  [in] queue limits to split based on
  * @segs: [out] number of segments in the bio with the first half of the sectors
+ * @bs:	  [in] bio set to allocate the clone from
+ * @max_bytes: [in] maximum number of bytes per bio
  *
  * Clone @bio, update the bi_iter of the clone to represent the first sectors
  * of @bio and update @bio->bi_iter to represent the remaining sectors. The
  * following is guaranteed for the cloned bio:
- * - That it has at most get_max_io_size(@q, @bio) sectors.
+ * - That it has at most @max_bytes worth of data
  * - That it has at most queue_max_segments(@q) segments.
  *
  * Except for discard requests the cloned bio will point at the bi_io_vec of
@@ -265,33 +267,30 @@ static bool bvec_split_segs(const struct request_queue *q,
  * responsible for ensuring that @bs is only destroyed after processing of the
  * split bio has finished.
  */
-static struct bio *blk_bio_segment_split(struct request_queue *q,
-					 struct bio *bio,
-					 struct bio_set *bs,
-					 unsigned *segs)
+static struct bio *bio_split_rw(struct bio *bio, struct queue_limits *lim,
+		unsigned *segs, struct bio_set *bs, unsigned max_bytes)
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned nsegs = 0, bytes = 0;
-	const unsigned max_bytes = get_max_io_size(q, bio) << 9;
-	const unsigned max_segs = queue_max_segments(q);
 
 	bio_for_each_bvec(bv, bio, iter) {
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
-		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
+		if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv.bv_offset))
 			goto split;
 
-		if (nsegs < max_segs &&
+		if (nsegs < lim->max_segments &&
 		    bytes + bv.bv_len <= max_bytes &&
 		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
 			nsegs++;
 			bytes += bv.bv_len;
-		} else if (bvec_split_segs(q, &bv, &nsegs, &bytes, max_segs,
-					   max_bytes)) {
-			goto split;
+		} else {
+			if (bvec_split_segs(lim, &bv, &nsegs, &bytes,
+					lim->max_segments, max_bytes))
+				goto split;
 		}
 
 		bvprv = bv;
@@ -308,7 +307,7 @@ split:
 	 * split size so that each bio is properly block size aligned, even if
 	 * we do not use the full hardware limits.
 	 */
-	bytes = ALIGN_DOWN(bytes, queue_logical_block_size(q));
+	bytes = ALIGN_DOWN(bytes, lim->logical_block_size);
 
 	/*
 	 * Bio splitting may cause subtle trouble such as hang when doing sync
@@ -320,34 +319,35 @@ split:
 }
 
 /**
- * __blk_queue_split - split a bio and submit the second half
- * @q:       [in] request_queue new bio is being queued at
- * @bio:     [in, out] bio to be split
- * @nr_segs: [out] number of segments in the first bio
+ * __bio_split_to_limits - split a bio to fit the queue limits
+ * @bio:     bio to be split
+ * @lim:     queue limits to split based on
+ * @nr_segs: returns the number of segments in the returned bio
+ *
+ * Check if @bio needs splitting based on the queue limits, and if so split off
+ * a bio fitting the limits from the beginning of @bio and return it.  @bio is
+ * shortened to the remainder and re-submitted.
  *
- * Split a bio into two bios, chain the two bios, submit the second half and
- * store a pointer to the first half in *@bio. If the second bio is still too
- * big it will be split by a recursive call to this function. Since this
- * function may allocate a new bio from q->bio_split, it is the responsibility
- * of the caller to ensure that q->bio_split is only released after processing
- * of the split bio has finished.
+ * The split bio is allocated from @q->bio_split, which is provided by the
+ * block layer.
  */
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
+struct bio *__bio_split_to_limits(struct bio *bio, struct queue_limits *lim,
 		       unsigned int *nr_segs)
 {
-	struct bio *split = NULL;
+	struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split;
+	struct bio *split;
 
-	switch (bio_op(*bio)) {
+	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
-		split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs);
+		split = bio_split_discard(bio, lim, nr_segs, bs);
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split,
-				nr_segs);
+		split = bio_split_write_zeroes(bio, lim, nr_segs, bs);
 		break;
 	default:
-		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
+		split = bio_split_rw(bio, lim, nr_segs, bs,
+				get_max_io_size(bio, lim) << SECTOR_SHIFT);
 		break;
 	}
 
@@ -356,32 +356,35 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		split->bi_opf |= REQ_NOMERGE;
 
 		blkcg_bio_issue_init(split);
-		bio_chain(split, *bio);
-		trace_block_split(split, (*bio)->bi_iter.bi_sector);
-		submit_bio_noacct(*bio);
-		*bio = split;
+		bio_chain(split, bio);
+		trace_block_split(split, bio->bi_iter.bi_sector);
+		submit_bio_noacct(bio);
+		return split;
 	}
+	return bio;
 }
 
 /**
- * blk_queue_split - split a bio and submit the second half
- * @bio: [in, out] bio to be split
+ * bio_split_to_limits - split a bio to fit the queue limits
+ * @bio:     bio to be split
+ *
+ * Check if @bio needs splitting based on the queue limits of @bio->bi_bdev, and
+ * if so split off a bio fitting the limits from the beginning of @bio and
+ * return it.  @bio is shortened to the remainder and re-submitted.
  *
- * Split a bio into two bios, chains the two bios, submit the second half and
- * store a pointer to the first half in *@bio. Since this function may allocate
- * a new bio from q->bio_split, it is the responsibility of the caller to ensure
- * that q->bio_split is only released after processing of the split bio has
- * finished.
+ * The split bio is allocated from @q->bio_split, which is provided by the
+ * block layer.
  */
-void blk_queue_split(struct bio **bio)
+struct bio *bio_split_to_limits(struct bio *bio)
 {
-	struct request_queue *q = bdev_get_queue((*bio)->bi_bdev);
+	struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits;
 	unsigned int nr_segs;
 
-	if (blk_may_split(q, *bio))
-		__blk_queue_split(q, bio, &nr_segs);
+	if (bio_may_exceed_limits(bio, lim))
+		return __bio_split_to_limits(bio, lim, &nr_segs);
+	return bio;
 }
-EXPORT_SYMBOL(blk_queue_split);
+EXPORT_SYMBOL(bio_split_to_limits);
 
 unsigned int blk_recalc_rq_segments(struct request *rq)
 {
@@ -411,7 +414,7 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
 	}
 
 	rq_for_each_bvec(bv, rq, iter)
-		bvec_split_segs(rq->q, &bv, &nr_phys_segs, &bytes,
+		bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes,
 				UINT_MAX, UINT_MAX);
 	return nr_phys_segs;
 }
@@ -442,8 +445,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
 
 	while (nbytes > 0) {
 		unsigned offset = bvec->bv_offset + total;
-		unsigned len = min(get_max_segment_size(q, bvec->bv_page,
-					offset), nbytes);
+		unsigned len = min(get_max_segment_size(&q->limits,
+				   bvec->bv_page, offset), nbytes);
 		struct page *page = bvec->bv_page;
 
 		/*
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 70177ee74295..5ee62b95f3e5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2815,9 +2815,9 @@ void blk_mq_submit_bio(struct bio *bio)
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
-	blk_queue_bounce(q, &bio);
-	if (blk_may_split(q, bio))
-		__blk_queue_split(q, &bio, &nr_segs);
+	bio = blk_queue_bounce(bio, q);
+	if (bio_may_exceed_limits(bio, &q->limits))
+		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
 		return;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index c0303026752d..e1f009aba6fd 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -779,8 +779,6 @@ static void blk_release_queue(struct kobject *kobj)
 	if (queue_is_mq(q))
 		blk_mq_release(q);
 
-	bioset_exit(&q->bio_split);
-
 	if (blk_queue_has_srcu(q))
 		cleanup_srcu_struct(q->srcu);
 
diff --git a/block/blk.h b/block/blk.h
index 1d83b1d41cd1..d7142c4d2fef 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -97,23 +97,23 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 	return true;
 }
 
-static inline bool __bvec_gap_to_prev(struct request_queue *q,
+static inline bool __bvec_gap_to_prev(struct queue_limits *lim,
 		struct bio_vec *bprv, unsigned int offset)
 {
-	return (offset & queue_virt_boundary(q)) ||
-		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
+	return (offset & lim->virt_boundary_mask) ||
+		((bprv->bv_offset + bprv->bv_len) & lim->virt_boundary_mask);
 }
 
 /*
  * Check if adding a bio_vec after bprv with offset would create a gap in
  * the SG list. Most drivers don't care about this, but some do.
  */
-static inline bool bvec_gap_to_prev(struct request_queue *q,
+static inline bool bvec_gap_to_prev(struct queue_limits *lim,
 		struct bio_vec *bprv, unsigned int offset)
 {
-	if (!queue_virt_boundary(q))
+	if (!lim->virt_boundary_mask)
 		return false;
-	return __bvec_gap_to_prev(q, bprv, offset);
+	return __bvec_gap_to_prev(lim, bprv, offset);
 }
 
 static inline bool rq_mergeable(struct request *rq)
@@ -189,7 +189,8 @@ static inline bool integrity_req_gap_back_merge(struct request *req,
 	struct bio_integrity_payload *bip = bio_integrity(req->bio);
 	struct bio_integrity_payload *bip_next = bio_integrity(next);
 
-	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
+	return bvec_gap_to_prev(&req->q->limits,
+				&bip->bip_vec[bip->bip_vcnt - 1],
 				bip_next->bip_vec[0].bv_offset);
 }
 
@@ -199,7 +200,8 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
 
-	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
+	return bvec_gap_to_prev(&req->q->limits,
+				&bip->bip_vec[bip->bip_vcnt - 1],
 				bip_next->bip_vec[0].bv_offset);
 }
 
@@ -288,7 +290,8 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
 
-static inline bool blk_may_split(struct request_queue *q, struct bio *bio)
+static inline bool bio_may_exceed_limits(struct bio *bio,
+		struct queue_limits *lim)
 {
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
@@ -307,12 +310,12 @@ static inline bool blk_may_split(struct request_queue *q, struct bio *bio)
 	 * to the performance impact of cloned bios themselves the loop below
 	 * doesn't matter anyway.
 	 */
-	return q->limits.chunk_sectors || bio->bi_vcnt != 1 ||
+	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
 		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
 }
 
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
-			unsigned int *nr_segs);
+struct bio *__bio_split_to_limits(struct bio *bio, struct queue_limits *lim,
+		       unsigned int *nr_segs);
 int ll_back_merge_fn(struct request *req, struct bio *bio,
 		unsigned int nr_segs);
 bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
@@ -345,16 +348,6 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 }
 
 /*
- * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
- * is defined as 'unsigned int', meantime it has to aligned to with logical
- * block size which is the minimum accepted unit by hardware.
- */
-static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
-{
-	return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
-}
-
-/*
  * Internal io_context interface
  */
 struct io_cq *ioc_find_get_icq(struct request_queue *q);
@@ -378,7 +371,7 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { }
 static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
 #endif
 
-void __blk_queue_bounce(struct request_queue *q, struct bio **bio);
+struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q);
 
 static inline bool blk_queue_may_bounce(struct request_queue *q)
 {
@@ -387,10 +380,12 @@ static inline bool blk_queue_may_bounce(struct request_queue *q)
 		max_low_pfn >= max_pfn;
 }
 
-static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
+static inline struct bio *blk_queue_bounce(struct bio *bio,
+		struct request_queue *q)
 {
-	if (unlikely(blk_queue_may_bounce(q) && bio_has_data(*bio)))
-		__blk_queue_bounce(q, bio);	
+	if (unlikely(blk_queue_may_bounce(q) && bio_has_data(bio)))
+		return __blk_queue_bounce(bio, q);
+	return bio;
 }
 
 #ifdef CONFIG_BLK_CGROUP_IOLATENCY
diff --git a/block/bounce.c b/block/bounce.c
index c8f487af7be3..7cfcb242f9a1 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -199,24 +199,24 @@ err_put:
 	return NULL;
 }
 
-void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
+struct bio *__blk_queue_bounce(struct bio *bio_orig, struct request_queue *q)
 {
 	struct bio *bio;
-	int rw = bio_data_dir(*bio_orig);
+	int rw = bio_data_dir(bio_orig);
 	struct bio_vec *to, from;
 	struct bvec_iter iter;
 	unsigned i = 0, bytes = 0;
 	bool bounce = false;
 	int sectors;
 
-	bio_for_each_segment(from, *bio_orig, iter) {
+	bio_for_each_segment(from, bio_orig, iter) {
 		if (i++ < BIO_MAX_VECS)
 			bytes += from.bv_len;
 		if (PageHighMem(from.bv_page))
 			bounce = true;
 	}
 	if (!bounce)
-		return;
+		return bio_orig;
 
 	/*
 	 * Individual bvecs might not be logical block aligned. Round down
@@ -225,13 +225,13 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 */
 	sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >>
 			SECTOR_SHIFT;
-	if (sectors < bio_sectors(*bio_orig)) {
-		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
-		bio_chain(bio, *bio_orig);
-		submit_bio_noacct(*bio_orig);
-		*bio_orig = bio;
+	if (sectors < bio_sectors(bio_orig)) {
+		bio = bio_split(bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
+		bio_chain(bio, bio_orig);
+		submit_bio_noacct(bio_orig);
+		bio_orig = bio;
 	}
-	bio = bounce_clone_bio(*bio_orig);
+	bio = bounce_clone_bio(bio_orig);
 
 	/*
 	 * Bvec table can't be updated by bio_for_each_segment_all(),
@@ -254,7 +254,7 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 		to->bv_page = bounce_page;
 	}
 
-	trace_block_bio_bounce(*bio_orig);
+	trace_block_bio_bounce(bio_orig);
 
 	bio->bi_flags |= (1 << BIO_BOUNCED);
 
@@ -263,6 +263,6 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	else
 		bio->bi_end_io = bounce_end_io_write;
 
-	bio->bi_private = *bio_orig;
-	*bio_orig = bio;
+	bio->bi_private = bio_orig;
+	return bio;
 }
diff --git a/block/genhd.c b/block/genhd.c
index e1d5b10ac193..b901fea1d55a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1151,6 +1151,7 @@ static void disk_release(struct device *dev)
 		blk_mq_exit_queue(disk->queue);
 
 	blkcg_exit_queue(disk->queue);
+	bioset_exit(&disk->bio_split);
 
 	disk_release_events(disk);
 	kfree(disk->random);
@@ -1342,9 +1343,12 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (!disk)
 		goto out_put_queue;
 
+	if (bioset_init(&disk->bio_split, BIO_POOL_SIZE, 0, 0))
+		goto out_free_disk;
+
 	disk->bdi = bdi_alloc(node_id);
 	if (!disk->bdi)
-		goto out_free_disk;
+		goto out_free_bioset;
 
 	/* bdev_alloc() might need the queue, set before the first call */
 	disk->queue = q;
@@ -1382,6 +1386,8 @@ out_destroy_part_tbl:
 	iput(disk->part0->bd_inode);
 out_free_bdi:
 	bdi_put(disk->bdi);
+out_free_bioset:
+	bioset_exit(&disk->bio_split);
 out_free_disk:
 	kfree(disk);
 out_put_queue: