1 files changed, 735 insertions, 479 deletions

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 71e9ac03f621..d3115d7469df 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -6,27 +6,46 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/scatterlist.h>
+#include <linux/blk-integrity.h>
+#include <linux/part_stat.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
+#include "blk-throttle.h"
 
-/*
- * Check if the two bvecs from two bios can be merged to one segment.  If yes,
- * no need to check gap between the two bios since the 1st bio and the 1st bvec
- * in the 2nd bio can be handled in one segment.
- */
-static inline bool bios_segs_mergeable(struct request_queue *q,
-		struct bio *prev, struct bio_vec *prev_last_bv,
-		struct bio_vec *next_first_bv)
+static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
 {
-	if (!biovec_phys_mergeable(q, prev_last_bv, next_first_bv))
-		return false;
-	if (prev->bi_seg_back_size + next_first_bv->bv_len >
-			queue_max_segment_size(q))
-		return false;
-	return true;
+	*bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+}
+
+static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
+{
+	struct bvec_iter iter = bio->bi_iter;
+	int idx;
+
+	bio_get_first_bvec(bio, bv);
+	if (bv->bv_len == bio->bi_iter.bi_size)
+		return;		/* this bio only has a single bvec */
+
+	bio_advance_iter(bio, &iter, iter.bi_size);
+
+	if (!iter.bi_bvec_done)
+		idx = iter.bi_idx - 1;
+	else	/* in the middle of bvec */
+		idx = iter.bi_idx;
+
+	*bv = bio->bi_io_vec[idx];
+
+	/*
+	 * iter.bi_bvec_done records actual length of the last bvec
+	 * if this bio ends in the middle of one io vector
+	 */
+	if (iter.bi_bvec_done)
+		bv->bv_len = iter.bi_bvec_done;
 }
 
 static inline bool bio_will_gap(struct request_queue *q,
@@ -60,9 +79,9 @@ static inline bool bio_will_gap(struct request_queue *q,
 	 */
 	bio_get_last_bvec(prev, &pb);
 	bio_get_first_bvec(next, &nb);
-	if (bios_segs_mergeable(q, prev, &pb, &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)
@@ -75,32 +94,89 @@ 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(const struct queue_limits *lim)
+{
+	return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT;
+}
+
+/*
+ * bio_submit_split_bioset - Submit a bio, splitting it at a designated sector
+ * @bio:		the original bio to be submitted and split
+ * @split_sectors:	the sector count at which to split
+ * @bs:			the bio set used for allocating the new split bio
+ *
+ * The original bio is modified to contain the remaining sectors and submitted.
+ * The caller is responsible for submitting the returned bio.
+ *
+ * If succeed, the newly allocated bio representing the initial part will be
+ * returned, on failure NULL will be returned and original bio will fail.
+ */
+struct bio *bio_submit_split_bioset(struct bio *bio, unsigned int split_sectors,
+				    struct bio_set *bs)
+{
+	struct bio *split = bio_split(bio, split_sectors, GFP_NOIO, bs);
+
+	if (IS_ERR(split)) {
+		bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+		bio_endio(bio);
+		return NULL;
+	}
+
+	bio_chain(split, bio);
+	trace_block_split(split, bio->bi_iter.bi_sector);
+	WARN_ON_ONCE(bio_zone_write_plugging(bio));
+
+	if (should_fail_bio(bio))
+		bio_io_error(bio);
+	else if (!blk_throtl_bio(bio))
+		submit_bio_noacct_nocheck(bio, true);
+
+	return split;
+}
+EXPORT_SYMBOL_GPL(bio_submit_split_bioset);
+
+static struct bio *bio_submit_split(struct bio *bio, int split_sectors)
+{
+	if (unlikely(split_sectors < 0)) {
+		bio->bi_status = errno_to_blk_status(split_sectors);
+		bio_endio(bio);
+		return NULL;
+	}
+
+	if (split_sectors) {
+		bio = bio_submit_split_bioset(bio, split_sectors,
+				&bio->bi_bdev->bd_disk->bio_split);
+		if (bio)
+			bio->bi_opf |= REQ_NOMERGE;
+	}
+
+	return bio;
+}
+
+struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim,
+		unsigned *nsegs)
 {
 	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)) {
-		/* XXX: warn */
-		return NULL;
-	}
+	if (unlikely(!max_discard_sectors))
+		return bio;
 
 	if (bio_sectors(bio) <= max_discard_sectors)
-		return NULL;
+		return bio;
 
 	split_sectors = max_discard_sectors;
 
@@ -108,432 +184,357 @@ 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)
 		split_sectors -= tmp;
 
-	return bio_split(bio, split_sectors, GFP_NOIO, bs);
+	return bio_submit_split(bio, split_sectors);
 }
 
-static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
-		struct bio *bio, struct bio_set *bs, unsigned *nsegs)
+static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim,
+						bool is_atomic)
 {
-	*nsegs = 1;
+	/*
+	 * chunk_sectors must be a multiple of atomic_write_boundary_sectors if
+	 * both non-zero.
+	 */
+	if (is_atomic && lim->atomic_write_boundary_sectors)
+		return lim->atomic_write_boundary_sectors;
 
-	if (!q->limits.max_write_zeroes_sectors)
-		return NULL;
+	return lim->chunk_sectors;
+}
 
-	if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
-		return NULL;
+/*
+ * Return the maximum number of sectors from the start of a bio that may be
+ * submitted as a single request to a block device. If enough sectors remain,
+ * align the end to the physical block size. Otherwise align the end to the
+ * logical block size. This approach minimizes the number of non-aligned
+ * 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 bio *bio,
+				       const struct queue_limits *lim)
+{
+	unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT;
+	unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT;
+	bool is_atomic = bio->bi_opf & REQ_ATOMIC;
+	unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic);
+	unsigned max_sectors, start, end;
+
+	/*
+	 * We ignore lim->max_sectors for atomic writes because it may less
+	 * than the actual bio size, which we cannot tolerate.
+	 */
+	if (bio_op(bio) == REQ_OP_WRITE_ZEROES)
+		max_sectors = lim->max_write_zeroes_sectors;
+	else if (is_atomic)
+		max_sectors = lim->atomic_write_max_sectors;
+	else
+		max_sectors = lim->max_sectors;
 
-	return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+	if (boundary_sectors) {
+		max_sectors = min(max_sectors,
+			blk_boundary_sectors_left(bio->bi_iter.bi_sector,
+					      boundary_sectors));
+	}
+
+	start = bio->bi_iter.bi_sector & (pbs - 1);
+	end = (start + max_sectors) & ~(pbs - 1);
+	if (end > start)
+		return end - start;
+	return max_sectors & ~(lbs - 1);
 }
 
-static struct bio *blk_bio_write_same_split(struct request_queue *q,
-					    struct bio *bio,
-					    struct bio_set *bs,
-					    unsigned *nsegs)
+/**
+ * bvec_split_segs - verify whether or not a bvec should be split in the middle
+ * @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
+ *            bio without exceeding @max_segs
+ * @bytes:    [in,out] Number of bytes in the bio being built. Incremented
+ *            by the number of bytes from @bv that may be appended to that
+ *            bio without exceeding @max_bytes
+ * @max_segs: [in] upper bound for *@nsegs
+ * @max_bytes: [in] upper bound for *@bytes
+ *
+ * When splitting a bio, it can happen that a bvec is encountered that is too
+ * big to fit in a single segment and hence that it has to be split in the
+ * middle. This function verifies whether or not that should happen. The value
+ * %true is returned if and only if appending the entire @bv to a bio with
+ * *@nsegs segments and *@sectors sectors would make that bio unacceptable for
+ * the block driver.
+ */
+static bool bvec_split_segs(const struct queue_limits *lim,
+		const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes,
+		unsigned max_segs, unsigned max_bytes)
 {
-	*nsegs = 1;
+	unsigned max_len = max_bytes - *bytes;
+	unsigned len = min(bv->bv_len, max_len);
+	unsigned total_len = 0;
+	unsigned seg_size = 0;
 
-	if (!q->limits.max_write_same_sectors)
-		return NULL;
+	while (len && *nsegs < max_segs) {
+		seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len);
 
-	if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
-		return NULL;
+		(*nsegs)++;
+		total_len += seg_size;
+		len -= seg_size;
+
+		if ((bv->bv_offset + total_len) & lim->virt_boundary_mask)
+			break;
+	}
 
-	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+	*bytes += total_len;
+
+	/* tell the caller to split the bvec if it is too big to fit */
+	return len > 0 || bv->bv_len > max_len;
 }
 
-static inline unsigned get_max_io_size(struct request_queue *q,
-				       struct bio *bio)
+static unsigned int bio_split_alignment(struct bio *bio,
+		const struct queue_limits *lim)
 {
-	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
-	unsigned mask = queue_logical_block_size(q) - 1;
-
-	/* aligned to logical block size */
-	sectors &= ~(mask >> 9);
+	if (op_is_write(bio_op(bio)) && lim->zone_write_granularity)
+		return lim->zone_write_granularity;
+	return lim->logical_block_size;
+}
 
-	return sectors;
+static inline unsigned int bvec_seg_gap(struct bio_vec *bvprv,
+					struct bio_vec *bv)
+{
+	return bv->bv_offset | (bvprv->bv_offset + bvprv->bv_len);
 }
 
-static struct bio *blk_bio_segment_split(struct request_queue *q,
-					 struct bio *bio,
-					 struct bio_set *bs,
-					 unsigned *segs)
+/**
+ * bio_split_io_at - check if and where to split a bio
+ * @bio:  [in] bio to be split
+ * @lim:  [in] queue limits to split based on
+ * @segs: [out] number of segments in the bio with the first half of the sectors
+ * @max_bytes: [in] maximum number of bytes per bio
+ * @len_align_mask: [in] length alignment mask for each vector
+ *
+ * Find out if @bio needs to be split to fit the queue limits in @lim and a
+ * maximum size of @max_bytes.  Returns a negative error number if @bio can't be
+ * split, 0 if the bio doesn't have to be split, or a positive sector offset if
+ * @bio needs to be split.
+ */
+int bio_split_io_at(struct bio *bio, const struct queue_limits *lim,
+		unsigned *segs, unsigned max_bytes, unsigned len_align_mask)
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
+	unsigned nsegs = 0, bytes = 0, gaps = 0;
 	struct bvec_iter iter;
-	unsigned seg_size = 0, nsegs = 0, sectors = 0;
-	unsigned front_seg_size = bio->bi_seg_front_size;
-	bool do_split = true;
-	struct bio *new = NULL;
-	const unsigned max_sectors = get_max_io_size(q, bio);
 
-	bio_for_each_segment(bv, bio, iter) {
+	bio_for_each_bvec(bv, bio, iter) {
+		if (bv.bv_offset & lim->dma_alignment ||
+		    bv.bv_len & len_align_mask)
+			return -EINVAL;
+
 		/*
 		 * 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))
-			goto split;
-
-		if (sectors + (bv.bv_len >> 9) > max_sectors) {
-			/*
-			 * Consider this a new segment if we're splitting in
-			 * the middle of this vector.
-			 */
-			if (nsegs < queue_max_segments(q) &&
-			    sectors < max_sectors) {
-				nsegs++;
-				sectors = max_sectors;
-			}
-			goto split;
-		}
-
 		if (bvprvp) {
-			if (seg_size + bv.bv_len > queue_max_segment_size(q))
-				goto new_segment;
-			if (!biovec_phys_mergeable(q, bvprvp, &bv))
-				goto new_segment;
-
-			seg_size += bv.bv_len;
-			bvprv = bv;
-			bvprvp = &bvprv;
-			sectors += bv.bv_len >> 9;
-
-			continue;
+			if (bvec_gap_to_prev(lim, bvprvp, bv.bv_offset))
+				goto split;
+			gaps |= bvec_seg_gap(bvprvp, &bv);
 		}
-new_segment:
-		if (nsegs == queue_max_segments(q))
-			goto split;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
+		if (nsegs < lim->max_segments &&
+		    bytes + bv.bv_len <= max_bytes &&
+		    bv.bv_offset + bv.bv_len <= lim->max_fast_segment_size) {
+			nsegs++;
+			bytes += bv.bv_len;
+		} else {
+			if (bvec_split_segs(lim, &bv, &nsegs, &bytes,
+					lim->max_segments, max_bytes))
+				goto split;
+		}
 
-		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
-		seg_size = bv.bv_len;
-		sectors += bv.bv_len >> 9;
-
 	}
 
-	do_split = false;
-split:
 	*segs = nsegs;
+	bio->bi_bvec_gap_bit = ffs(gaps);
+	return 0;
+split:
+	if (bio->bi_opf & REQ_ATOMIC)
+		return -EINVAL;
 
-	if (do_split) {
-		new = bio_split(bio, sectors, GFP_NOIO, bs);
-		if (new)
-			bio = new;
-	}
-
-	if (nsegs == 1 && seg_size > front_seg_size)
-		front_seg_size = seg_size;
-	bio->bi_seg_front_size = front_seg_size;
-	if (seg_size > bio->bi_seg_back_size)
-		bio->bi_seg_back_size = seg_size;
-
-	return do_split ? new : NULL;
-}
-
-void blk_queue_split(struct request_queue *q, struct bio **bio)
-{
-	struct bio *split, *res;
-	unsigned nsegs;
-
-	switch (bio_op(*bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-		split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs);
-		break;
-	case REQ_OP_WRITE_ZEROES:
-		split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs);
-		break;
-	case REQ_OP_WRITE_SAME:
-		split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs);
-		break;
-	default:
-		split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs);
-		break;
-	}
-
-	/* physical segments can be figured out during splitting */
-	res = split ? split : *bio;
-	res->bi_phys_segments = nsegs;
-	bio_set_flag(res, BIO_SEG_VALID);
+	/*
+	 * We can't sanely support splitting for a REQ_NOWAIT bio. End it
+	 * with EAGAIN if splitting is required and return an error pointer.
+	 */
+	if (bio->bi_opf & REQ_NOWAIT)
+		return -EAGAIN;
 
-	if (split) {
-		/* there isn't chance to merge the splitted bio */
-		split->bi_opf |= REQ_NOMERGE;
+	*segs = nsegs;
 
-		/*
-		 * Since we're recursing into make_request here, ensure
-		 * that we mark this bio as already having entered the queue.
-		 * If not, and the queue is going away, we can get stuck
-		 * forever on waiting for the queue reference to drop. But
-		 * that will never happen, as we're already holding a
-		 * reference to it.
-		 */
-		bio_set_flag(*bio, BIO_QUEUE_ENTERED);
+	/*
+	 * Individual bvecs might not be logical block aligned. Round down the
+	 * split size so that each bio is properly block size aligned, even if
+	 * we do not use the full hardware limits.
+	 *
+	 * It is possible to submit a bio that can't be split into a valid io:
+	 * there may either be too many discontiguous vectors for the max
+	 * segments limit, or contain virtual boundary gaps without having a
+	 * valid block sized split. A zero byte result means one of those
+	 * conditions occured.
+	 */
+	bytes = ALIGN_DOWN(bytes, bio_split_alignment(bio, lim));
+	if (!bytes)
+		return -EINVAL;
 
-		bio_chain(split, *bio);
-		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
-		generic_make_request(*bio);
-		*bio = split;
-	}
+	/*
+	 * Bio splitting may cause subtle trouble such as hang when doing sync
+	 * iopoll in direct IO routine. Given performance gain of iopoll for
+	 * big IO can be trival, disable iopoll when split needed.
+	 */
+	bio_clear_polled(bio);
+	bio->bi_bvec_gap_bit = ffs(gaps);
+	return bytes >> SECTOR_SHIFT;
 }
-EXPORT_SYMBOL(blk_queue_split);
+EXPORT_SYMBOL_GPL(bio_split_io_at);
 
-static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
-					     struct bio *bio,
-					     bool no_sg_merge)
+struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
+		unsigned *nr_segs)
 {
-	struct bio_vec bv, bvprv = { NULL };
-	int prev = 0;
-	unsigned int seg_size, nr_phys_segs;
-	struct bio *fbio, *bbio;
-	struct bvec_iter iter;
-
-	if (!bio)
-		return 0;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_ZEROES:
-		return 0;
-	case REQ_OP_WRITE_SAME:
-		return 1;
-	}
-
-	fbio = bio;
-	seg_size = 0;
-	nr_phys_segs = 0;
-	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, iter) {
-			/*
-			 * If SG merging is disabled, each bio vector is
-			 * a segment
-			 */
-			if (no_sg_merge)
-				goto new_segment;
-
-			if (prev) {
-				if (seg_size + bv.bv_len
-				    > queue_max_segment_size(q))
-					goto new_segment;
-				if (!biovec_phys_mergeable(q, &bvprv, &bv))
-					goto new_segment;
-
-				seg_size += bv.bv_len;
-				bvprv = bv;
-				continue;
-			}
-new_segment:
-			if (nr_phys_segs == 1 && seg_size >
-			    fbio->bi_seg_front_size)
-				fbio->bi_seg_front_size = seg_size;
-
-			nr_phys_segs++;
-			bvprv = bv;
-			prev = 1;
-			seg_size = bv.bv_len;
-		}
-		bbio = bio;
-	}
-
-	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
-		fbio->bi_seg_front_size = seg_size;
-	if (seg_size > bbio->bi_seg_back_size)
-		bbio->bi_seg_back_size = seg_size;
-
-	return nr_phys_segs;
+	return bio_submit_split(bio,
+		bio_split_rw_at(bio, lim, nr_segs,
+			get_max_io_size(bio, lim) << SECTOR_SHIFT));
 }
 
-void blk_recalc_rq_segments(struct request *rq)
+/*
+ * REQ_OP_ZONE_APPEND bios must never be split by the block layer.
+ *
+ * But we want the nr_segs calculation provided by bio_split_rw_at, and having
+ * a good sanity check that the submitter built the bio correctly is nice to
+ * have as well.
+ */
+struct bio *bio_split_zone_append(struct bio *bio,
+		const struct queue_limits *lim, unsigned *nr_segs)
 {
-	bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
-			&rq->q->queue_flags);
+	int split_sectors;
 
-	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio,
-			no_sg_merge);
+	split_sectors = bio_split_rw_at(bio, lim, nr_segs,
+			lim->max_zone_append_sectors << SECTOR_SHIFT);
+	if (WARN_ON_ONCE(split_sectors > 0))
+		split_sectors = -EINVAL;
+	return bio_submit_split(bio, split_sectors);
 }
 
-void blk_recount_segments(struct request_queue *q, struct bio *bio)
+struct bio *bio_split_write_zeroes(struct bio *bio,
+		const struct queue_limits *lim, unsigned *nsegs)
 {
-	unsigned short seg_cnt;
+	unsigned int max_sectors = get_max_io_size(bio, lim);
 
-	/* estimate segment number by bi_vcnt for non-cloned bio */
-	if (bio_flagged(bio, BIO_CLONED))
-		seg_cnt = bio_segments(bio);
-	else
-		seg_cnt = bio->bi_vcnt;
+	*nsegs = 0;
 
-	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
-			(seg_cnt < queue_max_segments(q)))
-		bio->bi_phys_segments = seg_cnt;
-	else {
-		struct bio *nxt = bio->bi_next;
+	/*
+	 * An unset limit should normally not happen, as bio submission is keyed
+	 * off having a non-zero limit.  But SCSI can clear the limit in the
+	 * I/O completion handler, and we can race and see this.  Splitting to a
+	 * zero limit obviously doesn't make sense, so band-aid it here.
+	 */
+	if (!max_sectors)
+		return bio;
+	if (bio_sectors(bio) <= max_sectors)
+		return bio;
+	return bio_submit_split(bio, max_sectors);
+}
 
-		bio->bi_next = NULL;
-		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
-		bio->bi_next = nxt;
-	}
+/**
+ * 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.
+ *
+ * The split bio is allocated from @q->bio_split, which is provided by the
+ * block layer.
+ */
+struct bio *bio_split_to_limits(struct bio *bio)
+{
+	unsigned int nr_segs;
 
-	bio_set_flag(bio, BIO_SEG_VALID);
+	return __bio_split_to_limits(bio, bdev_limits(bio->bi_bdev), &nr_segs);
 }
+EXPORT_SYMBOL(bio_split_to_limits);
 
-static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
-				   struct bio *nxt)
+unsigned int blk_recalc_rq_segments(struct request *rq)
 {
-	struct bio_vec end_bv = { NULL }, nxt_bv;
+	unsigned int nr_phys_segs = 0;
+	unsigned int bytes = 0;
+	struct req_iterator iter;
+	struct bio_vec bv;
 
-	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    queue_max_segment_size(q))
+	if (!rq->bio)
 		return 0;
 
-	if (!bio_has_data(bio))
-		return 1;
+	switch (bio_op(rq->bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		if (queue_max_discard_segments(rq->q) > 1) {
+			struct bio *bio = rq->bio;
 
-	bio_get_last_bvec(bio, &end_bv);
-	bio_get_first_bvec(nxt, &nxt_bv);
-
-	return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
-}
-
-static inline void
-__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
-		     struct scatterlist *sglist, struct bio_vec *bvprv,
-		     struct scatterlist **sg, int *nsegs)
-{
-
-	int nbytes = bvec->bv_len;
-
-	if (*sg) {
-		if ((*sg)->length + nbytes > queue_max_segment_size(q))
-			goto new_segment;
-		if (!biovec_phys_mergeable(q, bvprv, bvec))
-			goto new_segment;
-
-		(*sg)->length += nbytes;
-	} else {
-new_segment:
-		if (!*sg)
-			*sg = sglist;
-		else {
-			/*
-			 * If the driver previously mapped a shorter
-			 * list, we could see a termination bit
-			 * prematurely unless it fully inits the sg
-			 * table on each mapping. We KNOW that there
-			 * must be more entries here or the driver
-			 * would be buggy, so force clear the
-			 * termination bit to avoid doing a full
-			 * sg_init_table() in drivers for each command.
-			 */
-			sg_unmark_end(*sg);
-			*sg = sg_next(*sg);
+			for_each_bio(bio)
+				nr_phys_segs++;
+			return nr_phys_segs;
 		}
-
-		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
-		(*nsegs)++;
+		return 1;
+	case REQ_OP_WRITE_ZEROES:
+		return 0;
+	default:
+		break;
 	}
-	*bvprv = *bvec;
-}
 
-static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv,
-		struct scatterlist *sglist, struct scatterlist **sg)
-{
-	*sg = sglist;
-	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
-	return 1;
+	rq_for_each_bvec(bv, rq, iter)
+		bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes,
+				UINT_MAX, UINT_MAX);
+	return nr_phys_segs;
 }
 
-static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
-			     struct scatterlist *sglist,
-			     struct scatterlist **sg)
+static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
+						  sector_t offset)
 {
-	struct bio_vec bvec, bvprv = { NULL };
-	struct bvec_iter iter;
-	int nsegs = 0;
-
-	for_each_bio(bio)
-		bio_for_each_segment(bvec, bio, iter)
-			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
-					     &nsegs);
-
-	return nsegs;
-}
-
-/*
- * 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(struct request_queue *q, struct request *rq,
-		  struct scatterlist *sglist)
-{
-	struct scatterlist *sg = NULL;
-	int nsegs = 0;
-
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg);
-	else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
-		nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg);
-	else if (rq->bio)
-		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
-
-	if (unlikely(rq->rq_flags & RQF_COPY_USER) &&
-	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
-		unsigned int pad_len =
-			(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
-
-		sg->length += pad_len;
-		rq->extra_len += pad_len;
-	}
-
-	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (op_is_write(req_op(rq)))
-			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
-
-		sg_unmark_end(sg);
-		sg = sg_next(sg);
-		sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
-			    q->dma_drain_size,
-			    ((unsigned long)q->dma_drain_buffer) &
-			    (PAGE_SIZE - 1));
-		nsegs++;
-		rq->extra_len += q->dma_drain_size;
-	}
-
-	if (sg)
-		sg_mark_end(sg);
-
-	/*
-	 * Something must have been wrong if the figured number of
-	 * segment is bigger than number of req's physical segments
-	 */
-	WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
-
-	return nsegs;
+	struct request_queue *q = rq->q;
+	struct queue_limits *lim = &q->limits;
+	unsigned int max_sectors, boundary_sectors;
+	bool is_atomic = rq->cmd_flags & REQ_ATOMIC;
+
+	if (blk_rq_is_passthrough(rq))
+		return q->limits.max_hw_sectors;
+
+	boundary_sectors = blk_boundary_sectors(lim, is_atomic);
+	max_sectors = blk_queue_get_max_sectors(rq);
+
+	if (!boundary_sectors ||
+	    req_op(rq) == REQ_OP_DISCARD ||
+	    req_op(rq) == REQ_OP_SECURE_ERASE)
+		return max_sectors;
+	return min(max_sectors,
+		   blk_boundary_sectors_left(offset, boundary_sectors));
 }
-EXPORT_SYMBOL(blk_rq_map_sg);
 
-static inline int ll_new_hw_segment(struct request_queue *q,
-				    struct request *req,
-				    struct bio *bio)
+static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
+		unsigned int nr_phys_segs)
 {
-	int nr_phys_segs = bio_phys_segments(q, bio);
+	if (!blk_cgroup_mergeable(req, bio))
+		goto no_merge;
 
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
+	if (blk_integrity_merge_bio(req->q, req, bio) == false)
 		goto no_merge;
 
-	if (blk_integrity_merge_bio(q, req, bio) == false)
+	/* discard request merge won't add new segment */
+	if (req_op(req) == REQ_OP_DISCARD)
+		return 1;
+
+	if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
 		goto no_merge;
 
 	/*
@@ -541,54 +542,51 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 	 * counters.
 	 */
 	req->nr_phys_segments += nr_phys_segs;
+	if (bio_integrity(bio))
+		req->nr_integrity_segments += blk_rq_count_integrity_sg(req->q,
+									bio);
 	return 1;
 
 no_merge:
-	req_set_nomerge(q, req);
+	req_set_nomerge(req->q, req);
 	return 0;
 }
 
-int ll_back_merge_fn(struct request_queue *q, struct request *req,
-		     struct bio *bio)
+int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
 {
 	if (req_gap_back_merge(req, bio))
 		return 0;
 	if (blk_integrity_rq(req) &&
 	    integrity_req_gap_back_merge(req, bio))
 		return 0;
+	if (!bio_crypt_ctx_back_mergeable(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
-		req_set_nomerge(q, req);
+		req_set_nomerge(req->q, req);
 		return 0;
 	}
-	if (!bio_flagged(req->biotail, BIO_SEG_VALID))
-		blk_recount_segments(q, req->biotail);
-	if (!bio_flagged(bio, BIO_SEG_VALID))
-		blk_recount_segments(q, bio);
 
-	return ll_new_hw_segment(q, req, bio);
+	return ll_new_hw_segment(req, bio, nr_segs);
 }
 
-int ll_front_merge_fn(struct request_queue *q, struct request *req,
-		      struct bio *bio)
+static int ll_front_merge_fn(struct request *req, struct bio *bio,
+		unsigned int nr_segs)
 {
-
 	if (req_gap_front_merge(req, bio))
 		return 0;
 	if (blk_integrity_rq(req) &&
 	    integrity_req_gap_front_merge(req, bio))
 		return 0;
+	if (!bio_crypt_ctx_front_mergeable(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
-		req_set_nomerge(q, req);
+		req_set_nomerge(req->q, req);
 		return 0;
 	}
-	if (!bio_flagged(bio, BIO_SEG_VALID))
-		blk_recount_segments(q, bio);
-	if (!bio_flagged(req->bio, BIO_SEG_VALID))
-		blk_recount_segments(q, req->bio);
 
-	return ll_new_hw_segment(q, req, bio);
+	return ll_new_hw_segment(req, bio, nr_segs);
 }
 
 static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
@@ -613,8 +611,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
 	int total_phys_segments;
-	unsigned int seg_size =
-		req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
 
 	if (req_gap_back_merge(req, next->bio))
 		return 0;
@@ -627,22 +623,21 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
-		if (req->nr_phys_segments == 1)
-			req->bio->bi_seg_front_size = seg_size;
-		if (next->nr_phys_segments == 1)
-			next->biotail->bi_seg_back_size = seg_size;
-		total_phys_segments--;
-	}
+	if (total_phys_segments > blk_rq_get_max_segments(req))
+		return 0;
 
-	if (total_phys_segments > queue_max_segments(q))
+	if (!blk_cgroup_mergeable(req, next->bio))
 		return 0;
 
 	if (blk_integrity_merge_rq(q, req, next) == false)
 		return 0;
 
+	if (!bio_crypt_ctx_merge_rq(req, next))
+		return 0;
+
 	/* Merge is OK... */
 	req->nr_phys_segments = total_phys_segments;
+	req->nr_integrity_segments += next->nr_integrity_segments;
 	return 1;
 }
 
@@ -655,9 +650,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
  *     which can be mixed are set in each bio and mark @rq as mixed
  *     merged.
  */
-void blk_rq_set_mixed_merge(struct request *rq)
+static void blk_rq_set_mixed_merge(struct request *rq)
 {
-	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
 	struct bio *bio;
 
 	if (rq->rq_flags & RQF_MIXED_MERGE)
@@ -676,34 +671,42 @@ void blk_rq_set_mixed_merge(struct request *rq)
 	rq->rq_flags |= RQF_MIXED_MERGE;
 }
 
-static void blk_account_io_merge(struct request *req)
+static inline blk_opf_t bio_failfast(const struct bio *bio)
 {
-	if (blk_do_io_stat(req)) {
-		struct hd_struct *part;
+	if (bio->bi_opf & REQ_RAHEAD)
+		return REQ_FAILFAST_MASK;
 
-		part_stat_lock();
-		part = req->part;
+	return bio->bi_opf & REQ_FAILFAST_MASK;
+}
 
-		part_dec_in_flight(req->q, part, rq_data_dir(req));
+/*
+ * After we are marked as MIXED_MERGE, any new RA bio has to be updated
+ * as failfast, and request's failfast has to be updated in case of
+ * front merge.
+ */
+static inline void blk_update_mixed_merge(struct request *req,
+		struct bio *bio, bool front_merge)
+{
+	if (req->rq_flags & RQF_MIXED_MERGE) {
+		if (bio->bi_opf & REQ_RAHEAD)
+			bio->bi_opf |= REQ_FAILFAST_MASK;
 
-		hd_struct_put(part);
-		part_stat_unlock();
+		if (front_merge) {
+			req->cmd_flags &= ~REQ_FAILFAST_MASK;
+			req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK;
+		}
 	}
 }
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
+
+static void blk_account_io_merge_request(struct request *req)
 {
-	if (req_op(req) == REQ_OP_DISCARD &&
-	    queue_max_discard_segments(req->q) > 1)
-		return true;
-	return false;
+	if (req->rq_flags & RQF_IO_STAT) {
+		part_stat_lock();
+		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
+		part_stat_unlock();
+	}
 }
 
 static enum elv_merge blk_try_req_merge(struct request *req,
@@ -717,6 +720,36 @@ static enum elv_merge blk_try_req_merge(struct request *req,
 	return ELEVATOR_NO_MERGE;
 }
 
+static bool blk_atomic_write_mergeable_rq_bio(struct request *rq,
+					      struct bio *bio)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC);
+}
+
+static bool blk_atomic_write_mergeable_rqs(struct request *rq,
+					   struct request *next)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC);
+}
+
+u8 bio_seg_gap(struct request_queue *q, struct bio *prev, struct bio *next,
+	       u8 gaps_bit)
+{
+	struct bio_vec pb, nb;
+
+	if (!bio_has_data(prev))
+		return 0;
+
+	gaps_bit = min_not_zero(gaps_bit, prev->bi_bvec_gap_bit);
+	gaps_bit = min_not_zero(gaps_bit, next->bi_bvec_gap_bit);
+
+	bio_get_last_bvec(prev, &pb);
+	bio_get_first_bvec(next, &nb);
+	if (!biovec_phys_mergeable(q, &pb, &nb))
+		gaps_bit = min_not_zero(gaps_bit, ffs(bvec_seg_gap(&pb, &nb)));
+	return gaps_bit;
+}
+
 /*
  * For non-mq, this has to be called with the request spinlock acquired.
  * For mq with scheduling, the appropriate queue wide lock should be held.
@@ -730,22 +763,13 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (req_op(req) != req_op(next))
 		return NULL;
 
-	if (rq_data_dir(req) != rq_data_dir(next)
-	    || req->rq_disk != next->rq_disk)
+	if (req->bio->bi_write_hint != next->bio->bi_write_hint)
 		return NULL;
-
-	if (req_op(req) == REQ_OP_WRITE_SAME &&
-	    !blk_write_same_mergeable(req->bio, next->bio))
+	if (req->bio->bi_write_stream != next->bio->bi_write_stream)
 		return NULL;
-
-	/*
-	 * Don't allow merge of different write hints, or for a hint with
-	 * non-hint IO.
-	 */
-	if (req->write_hint != next->write_hint)
+	if (req->bio->bi_ioprio != next->bio->bi_ioprio)
 		return NULL;
-
-	if (req->ioprio != next->ioprio)
+	if (!blk_atomic_write_mergeable_rqs(req, next))
 		return NULL;
 
 	/*
@@ -790,6 +814,9 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (next->start_time_ns < req->start_time_ns)
 		req->start_time_ns = next->start_time_ns;
 
+	req->phys_gap_bit = bio_seg_gap(req->q, req->biotail, next->bio,
+					min_not_zero(next->phys_gap_bit,
+						     req->phys_gap_bit));
 	req->biotail->bi_next = next->bio;
 	req->biotail = next->biotail;
 
@@ -798,10 +825,14 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (!blk_discard_mergable(req))
 		elv_merge_requests(q, req, next);
 
+	blk_crypto_rq_put_keyslot(next);
+
 	/*
 	 * 'next' is going away, so update stats accordingly
 	 */
-	blk_account_io_merge(next);
+	blk_account_io_merge_request(next);
+
+	trace_block_rq_merge(next);
 
 	/*
 	 * ownership of bio passed from next to req, return 'next' for
@@ -811,7 +842,8 @@ static struct request *attempt_merge(struct request_queue *q,
 	return next;
 }
 
-struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
+static struct request *attempt_back_merge(struct request_queue *q,
+		struct request *rq)
 {
 	struct request *next = elv_latter_request(q, rq);
 
@@ -821,7 +853,8 @@ struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
 	return NULL;
 }
 
-struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
+static struct request *attempt_front_merge(struct request_queue *q,
+		struct request *rq)
 {
 	struct request *prev = elv_former_request(q, rq);
 
@@ -831,18 +864,15 @@ struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
 	return NULL;
 }
 
-int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
-			  struct request *next)
+/*
+ * Try to merge 'next' into 'rq'. Return true if the merge happened, false
+ * otherwise. The caller is responsible for freeing 'next' if the merge
+ * happened.
+ */
+bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+			   struct request *next)
 {
-	struct request *free;
-
-	free = attempt_merge(q, rq, next);
-	if (free) {
-		blk_put_request(free);
-		return 1;
-	}
-
-	return 0;
+	return attempt_merge(q, rq, next);
 }
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
@@ -853,31 +883,19 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (req_op(rq) != bio_op(bio))
 		return false;
 
-	/* different data direction or already started, don't merge */
-	if (bio_data_dir(bio) != rq_data_dir(rq))
-		return false;
-
-	/* must be same device */
-	if (rq->rq_disk != bio->bi_disk)
+	if (!blk_cgroup_mergeable(rq, bio))
 		return false;
-
-	/* only merge integrity protected bio into ditto rq */
 	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
-
-	/* must be using the same buffer */
-	if (req_op(rq) == REQ_OP_WRITE_SAME &&
-	    !blk_write_same_mergeable(rq->bio, bio))
+	if (!bio_crypt_rq_ctx_compatible(rq, bio))
 		return false;
-
-	/*
-	 * Don't allow merge of different write hints, or for a hint with
-	 * non-hint IO.
-	 */
-	if (rq->write_hint != bio->bi_write_hint)
+	if (rq->bio->bi_write_hint != bio->bi_write_hint)
 		return false;
-
-	if (rq->ioprio != bio_prio(bio))
+	if (rq->bio->bi_write_stream != bio->bi_write_stream)
+		return false;
+	if (rq->bio->bi_ioprio != bio->bi_ioprio)
+		return false;
+	if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false)
 		return false;
 
 	return true;
@@ -893,3 +911,241 @@ enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 		return ELEVATOR_FRONT_MERGE;
 	return ELEVATOR_NO_MERGE;
 }
+
+static void blk_account_io_merge_bio(struct request *req)
+{
+	if (req->rq_flags & RQF_IO_STAT) {
+		part_stat_lock();
+		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_unlock();
+	}
+}
+
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs)
+{
+	const blk_opf_t ff = bio_failfast(bio);
+
+	if (!ll_back_merge_fn(req, bio, nr_segs))
+		return BIO_MERGE_FAILED;
+
+	trace_block_bio_backmerge(bio);
+	rq_qos_merge(req->q, req, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	blk_update_mixed_merge(req, bio, false);
+
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		blk_zone_write_plug_bio_merged(bio);
+
+	req->phys_gap_bit = bio_seg_gap(req->q, req->biotail, bio,
+					req->phys_gap_bit);
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	bio_crypt_free_ctx(bio);
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+}
+
+static enum bio_merge_status bio_attempt_front_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs)
+{
+	const blk_opf_t ff = bio_failfast(bio);
+
+	/*
+	 * A front merge for writes to sequential zones of a zoned block device
+	 * can happen only if the user submitted writes out of order. Do not
+	 * merge such write to let it fail.
+	 */
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		return BIO_MERGE_FAILED;
+
+	if (!ll_front_merge_fn(req, bio, nr_segs))
+		return BIO_MERGE_FAILED;
+
+	trace_block_bio_frontmerge(bio);
+	rq_qos_merge(req->q, req, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	blk_update_mixed_merge(req, bio, true);
+
+	req->phys_gap_bit = bio_seg_gap(req->q, bio, req->bio,
+					req->phys_gap_bit);
+	bio->bi_next = req->bio;
+	req->bio = bio;
+
+	req->__sector = bio->bi_iter.bi_sector;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	bio_crypt_do_front_merge(req, bio);
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+}
+
+static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q,
+		struct request *req, struct bio *bio)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+
+	if (segments >= queue_max_discard_segments(q))
+		goto no_merge;
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
+		goto no_merge;
+
+	rq_qos_merge(q, req, bio);
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+	req->nr_phys_segments = segments + 1;
+
+	blk_account_io_merge_bio(req);
+	return BIO_MERGE_OK;
+no_merge:
+	req_set_nomerge(q, req);
+	return BIO_MERGE_FAILED;
+}
+
+static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
+						   struct request *rq,
+						   struct bio *bio,
+						   unsigned int nr_segs,
+						   bool sched_allow_merge)
+{
+	if (!blk_rq_merge_ok(rq, bio))
+		return BIO_MERGE_NONE;
+
+	switch (blk_try_merge(rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
+			return bio_attempt_back_merge(rq, bio, nr_segs);
+		break;
+	case ELEVATOR_FRONT_MERGE:
+		if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
+			return bio_attempt_front_merge(rq, bio, nr_segs);
+		break;
+	case ELEVATOR_DISCARD_MERGE:
+		return bio_attempt_discard_merge(q, rq, bio);
+	default:
+		return BIO_MERGE_NONE;
+	}
+
+	return BIO_MERGE_FAILED;
+}
+
+/**
+ * blk_attempt_plug_merge - try to merge with %current's plugged list
+ * @q: request_queue new bio is being queued at
+ * @bio: new bio being queued
+ * @nr_segs: number of segments in @bio
+ * from the passed in @q already in the plug list
+ *
+ * Determine whether @bio being queued on @q can be merged with the previous
+ * request on %current's plugged list.  Returns %true if merge was successful,
+ * otherwise %false.
+ *
+ * Plugging coalesces IOs from the same issuer for the same purpose without
+ * going through @q->queue_lock.  As such it's more of an issuing mechanism
+ * than scheduling, and the request, while may have elvpriv data, is not
+ * added on the elevator at this point.  In addition, we don't have
+ * reliable access to the elevator outside queue lock.  Only check basic
+ * merging parameters without querying the elevator.
+ *
+ * Caller must ensure !blk_queue_nomerges(q) beforehand.
+ */
+bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+		unsigned int nr_segs)
+{
+	struct blk_plug *plug = current->plug;
+	struct request *rq;
+
+	if (!plug || rq_list_empty(&plug->mq_list))
+		return false;
+
+	rq = plug->mq_list.tail;
+	if (rq->q == q)
+		return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+			BIO_MERGE_OK;
+	else if (!plug->multiple_queues)
+		return false;
+
+	rq_list_for_each(&plug->mq_list, rq) {
+		if (rq->q != q)
+			continue;
+		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+		    BIO_MERGE_OK)
+			return true;
+		break;
+	}
+	return false;
+}
+
+/*
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
+ */
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs)
+{
+	struct request *rq;
+	int checked = 8;
+
+	list_for_each_entry_reverse(rq, list, queuelist) {
+		if (!checked--)
+			break;
+
+		switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) {
+		case BIO_MERGE_NONE:
+			continue;
+		case BIO_MERGE_OK:
+			return true;
+		case BIO_MERGE_FAILED:
+			return false;
+		}
+
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(blk_bio_list_merge);
+
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+		unsigned int nr_segs, struct request **merged_request)
+{
+	struct request *rq;
+
+	switch (elv_merge(q, &rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
+			return false;
+		*merged_request = attempt_back_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
+		return true;
+	case ELEVATOR_FRONT_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
+			return false;
+		*merged_request = attempt_front_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
+		return true;
+	case ELEVATOR_DISCARD_MERGE:
+		return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);