Contributors: 45
Author Tokens Token Proportion Commits Commit Proportion
Christoph Hellwig 1002 21.18% 37 19.17%
Jens Axboe 916 19.36% 35 18.13%
Ming Lei 733 15.49% 26 13.47%
Baolin Wang 580 12.26% 3 1.55%
Kent Overstreet 353 7.46% 6 3.11%
Tejun Heo 289 6.11% 8 4.15%
Bart Van Assche 134 2.83% 9 4.66%
Martin K. Petersen 99 2.09% 7 3.63%
Damien Le Moal 74 1.56% 4 2.07%
Asias He 51 1.08% 1 0.52%
Satya Tangirala 46 0.97% 1 0.52%
Keith Busch 45 0.95% 5 2.59%
Jianchao Wang 43 0.91% 1 0.52%
Linus Torvalds 43 0.91% 6 3.11%
Sagi Grimberg 36 0.76% 2 1.04%
David Jeffery 35 0.74% 1 0.52%
Jerome Marchand 31 0.66% 4 2.07%
Linus Torvalds (pre-git) 27 0.57% 7 3.63%
Michael Christie 23 0.49% 2 1.04%
Lei Ming 23 0.49% 1 0.52%
Konstantin Khlebnikov 16 0.34% 1 0.52%
Chaitanya Kulkarni 16 0.34% 1 0.52%
Ritesh Harjani 15 0.32% 1 0.52%
Adrian Hunter 14 0.30% 1 0.52%
Mike Krinkin 14 0.30% 1 0.52%
yu kuai 13 0.27% 1 0.52%
Jan Kara 8 0.17% 2 1.04%
Omar Sandoval 8 0.17% 1 0.52%
Eric Biggers 6 0.13% 2 1.04%
Arnaldo Carvalho de Melo 6 0.13% 1 0.52%
Boaz Harrosh 6 0.13% 1 0.52%
Song Muchun 5 0.11% 1 0.52%
Pavel Begunkov 3 0.06% 1 0.52%
Jeffle Xu 3 0.06% 1 0.52%
Andrew Morton 2 0.04% 1 0.52%
Dan J Williams 2 0.04% 1 0.52%
Martin Schwidefsky 2 0.04% 1 0.52%
Mikulas Patocka 2 0.04% 1 0.52%
Johannes Thumshirn 1 0.02% 1 0.52%
Josef Bacik 1 0.02% 1 0.52%
Greg Kroah-Hartman 1 0.02% 1 0.52%
John Garry 1 0.02% 1 0.52%
Adrian Bunk 1 0.02% 1 0.52%
FUJITA Tomonori 1 0.02% 1 0.52%
Brian King 1 0.02% 1 0.52%
Total 4731 193 


// SPDX-License-Identifier: GPL-2.0
/*
 * Functions related to segment and merge handling
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/scatterlist.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"

static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
{
	*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,
		struct request *prev_rq, struct bio *prev, struct bio *next)
{
	struct bio_vec pb, nb;

	if (!bio_has_data(prev) || !queue_virt_boundary(q))
		return false;

	/*
	 * Don't merge if the 1st bio starts with non-zero offset, otherwise it
	 * is quite difficult to respect the sg gap limit.  We work hard to
	 * merge a huge number of small single bios in case of mkfs.
	 */
	if (prev_rq)
		bio_get_first_bvec(prev_rq->bio, &pb);
	else
		bio_get_first_bvec(prev, &pb);
	if (pb.bv_offset & queue_virt_boundary(q))
		return true;

	/*
	 * We don't need to worry about the situation that the merged segment
	 * ends in unaligned virt boundary:
	 *
	 * - if 'pb' ends aligned, the merged segment ends aligned
	 * - if 'pb' ends unaligned, the next bio must include
	 *   one single bvec of 'nb', otherwise the 'nb' can't
	 *   merge with 'pb'
	 */
	bio_get_last_bvec(prev, &pb);
	bio_get_first_bvec(next, &nb);
	if (biovec_phys_mergeable(q, &pb, &nb))
		return false;
	return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset);
}

static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
{
	return bio_will_gap(req->q, req, req->biotail, bio);
}

static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
{
	return bio_will_gap(req->q, NULL, bio, req->bio);
}

/*
 * 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;
}

static struct bio *bio_split_discard(struct bio *bio,
				     const struct queue_limits *lim,
				     unsigned *nsegs, struct bio_set *bs)
{
	unsigned int max_discard_sectors, granularity;
	sector_t tmp;
	unsigned split_sectors;

	*nsegs = 1;

	granularity = max(lim->discard_granularity >> 9, 1U);

	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))
		return NULL;

	if (bio_sectors(bio) <= max_discard_sectors)
		return NULL;

	split_sectors = max_discard_sectors;

	/*
	 * If the next starting sector would be misaligned, stop the discard at
	 * the previous aligned sector.
	 */
	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);
}

static struct bio *bio_split_write_zeroes(struct bio *bio,
					  const struct queue_limits *lim,
					  unsigned *nsegs, struct bio_set *bs)
{
	*nsegs = 0;
	if (!lim->max_write_zeroes_sectors)
		return NULL;
	if (bio_sectors(bio) <= lim->max_write_zeroes_sectors)
		return NULL;
	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
}

/*
 * 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;
	unsigned max_sectors = lim->max_sectors, start, end;

	if (lim->chunk_sectors) {
		max_sectors = min(max_sectors,
			blk_chunk_sectors_left(bio->bi_iter.bi_sector,
					       lim->chunk_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);
}

/**
 * get_max_segment_size() - maximum number of bytes to add as a single segment
 * @lim: Request queue limits.
 * @start_page: See below.
 * @offset: Offset from @start_page where to add a segment.
 *
 * Returns the maximum number of bytes that can be added as a single segment.
 */
static inline unsigned get_max_segment_size(const struct queue_limits *lim,
		struct page *start_page, unsigned long offset)
{
	unsigned long mask = lim->seg_boundary_mask;

	offset = mask & (page_to_phys(start_page) + offset);

	/*
	 * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1
	 * after having calculated the minimum.
	 */
	return min(mask - offset, (unsigned long)lim->max_segment_size - 1) + 1;
}

/**
 * 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)
{
	unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
	unsigned len = min(bv->bv_len, max_len);
	unsigned total_len = 0;
	unsigned seg_size = 0;

	while (len && *nsegs < max_segs) {
		seg_size = get_max_segment_size(lim, bv->bv_page,
						bv->bv_offset + total_len);
		seg_size = min(seg_size, len);

		(*nsegs)++;
		total_len += seg_size;
		len -= seg_size;

		if ((bv->bv_offset + total_len) & lim->virt_boundary_mask)
			break;
	}

	*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;
}

/**
 * bio_split_rw - split a bio in two bios
 * @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
 * @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 @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
 * the original bio. It is the responsibility of the caller to ensure that the
 * original bio is not freed before the cloned bio. The caller is also
 * responsible for ensuring that @bs is only destroyed after processing of the
 * split bio has finished.
 */
struct bio *bio_split_rw(struct bio *bio, const 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;

	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(lim, bvprvp, bv.bv_offset))
			goto split;

		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(lim, &bv, &nsegs, &bytes,
					lim->max_segments, max_bytes))
				goto split;
		}

		bvprv = bv;
		bvprvp = &bvprv;
	}

	*segs = nsegs;
	return NULL;
split:
	/*
	 * 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) {
		bio->bi_status = BLK_STS_AGAIN;
		bio_endio(bio);
		return ERR_PTR(-EAGAIN);
	}

	*segs = nsegs;

	/*
	 * 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.
	 */
	bytes = ALIGN_DOWN(bytes, lim->logical_block_size);

	/*
	 * 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);
	return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs);
}
EXPORT_SYMBOL_GPL(bio_split_rw);

/**
 * __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.
 *
 * 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,
				  const struct queue_limits *lim,
				  unsigned int *nr_segs)
{
	struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split;
	struct bio *split;

	switch (bio_op(bio)) {
	case REQ_OP_DISCARD:
	case REQ_OP_SECURE_ERASE:
		split = bio_split_discard(bio, lim, nr_segs, bs);
		break;
	case REQ_OP_WRITE_ZEROES:
		split = bio_split_write_zeroes(bio, lim, nr_segs, bs);
		break;
	default:
		split = bio_split_rw(bio, lim, nr_segs, bs,
				get_max_io_size(bio, lim) << SECTOR_SHIFT);
		if (IS_ERR(split))
			return NULL;
		break;
	}

	if (split) {
		/* there isn't chance to merge the split bio */
		split->bi_opf |= REQ_NOMERGE;

		blkcg_bio_issue_init(split);
		bio_chain(split, bio);
		trace_block_split(split, bio->bi_iter.bi_sector);
		WARN_ON_ONCE(bio_zone_write_plugging(bio));
		submit_bio_noacct(bio);
		return split;
	}
	return bio;
}

/**
 * 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)
{
	const struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits;
	unsigned int nr_segs;

	if (bio_may_exceed_limits(bio, lim))
		return __bio_split_to_limits(bio, lim, &nr_segs);
	return bio;
}
EXPORT_SYMBOL(bio_split_to_limits);

unsigned int blk_recalc_rq_segments(struct request *rq)
{
	unsigned int nr_phys_segs = 0;
	unsigned int bytes = 0;
	struct req_iterator iter;
	struct bio_vec bv;

	if (!rq->bio)
		return 0;

	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;

			for_each_bio(bio)
				nr_phys_segs++;
			return nr_phys_segs;
		}
		return 1;
	case REQ_OP_WRITE_ZEROES:
		return 0;
	default:
		break;
	}

	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 inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
		struct scatterlist *sglist)
{
	if (!*sg)
		return sglist;

	/*
	 * 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);
	return sg_next(*sg);
}

static unsigned blk_bvec_map_sg(struct request_queue *q,
		struct bio_vec *bvec, struct scatterlist *sglist,
		struct scatterlist **sg)
{
	unsigned nbytes = bvec->bv_len;
	unsigned nsegs = 0, total = 0;

	while (nbytes > 0) {
		unsigned offset = bvec->bv_offset + total;
		unsigned len = min(get_max_segment_size(&q->limits,
				   bvec->bv_page, offset), nbytes);
		struct page *page = bvec->bv_page;

		/*
		 * Unfortunately a fair number of drivers barf on scatterlists
		 * that have an offset larger than PAGE_SIZE, despite other
		 * subsystems dealing with that invariant just fine.  For now
		 * stick to the legacy format where we never present those from
		 * the block layer, but the code below should be removed once
		 * these offenders (mostly MMC/SD drivers) are fixed.
		 */
		page += (offset >> PAGE_SHIFT);
		offset &= ~PAGE_MASK;

		*sg = blk_next_sg(sg, sglist);
		sg_set_page(*sg, page, len, offset);

		total += len;
		nbytes -= len;
		nsegs++;
	}

	return nsegs;
}

static inline int __blk_bvec_map_sg(struct bio_vec bv,
		struct scatterlist *sglist, struct scatterlist **sg)
{
	*sg = blk_next_sg(sg, sglist);
	sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
	return 1;
}

/* only try to merge bvecs into one sg if they are from two bios */
static inline bool
__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
			   struct bio_vec *bvprv, struct scatterlist **sg)
{

	int nbytes = bvec->bv_len;

	if (!*sg)
		return false;

	if ((*sg)->length + nbytes > queue_max_segment_size(q))
		return false;

	if (!biovec_phys_mergeable(q, bvprv, bvec))
		return false;

	(*sg)->length += nbytes;

	return true;
}

static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
			     struct scatterlist *sglist,
			     struct scatterlist **sg)
{
	struct bio_vec bvec, bvprv = { NULL };
	struct bvec_iter iter;
	int nsegs = 0;
	bool new_bio = false;

	for_each_bio(bio) {
		bio_for_each_bvec(bvec, bio, iter) {
			/*
			 * Only try to merge bvecs from two bios given we
			 * have done bio internal merge when adding pages
			 * to bio
			 */
			if (new_bio &&
			    __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
				goto next_bvec;

			if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
				nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
			else
				nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
 next_bvec:
			new_bio = false;
		}
		if (likely(bio->bi_iter.bi_size)) {
			bvprv = bvec;
			new_bio = true;
		}
	}

	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 **last_sg)
{
	int nsegs = 0;

	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
		nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg);
	else if (rq->bio)
		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg);

	if (*last_sg)
		sg_mark_end(*last_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;
}
EXPORT_SYMBOL(__blk_rq_map_sg);

static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
						  sector_t offset)
{
	struct request_queue *q = rq->q;
	unsigned int max_sectors;

	if (blk_rq_is_passthrough(rq))
		return q->limits.max_hw_sectors;

	max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
	if (!q->limits.chunk_sectors ||
	    req_op(rq) == REQ_OP_DISCARD ||
	    req_op(rq) == REQ_OP_SECURE_ERASE)
		return max_sectors;
	return min(max_sectors,
		   blk_chunk_sectors_left(offset, q->limits.chunk_sectors));
}

static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
		unsigned int nr_phys_segs)
{
	if (!blk_cgroup_mergeable(req, bio))
		goto no_merge;

	if (blk_integrity_merge_bio(req->q, req, bio) == false)
		goto no_merge;

	/* 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;

	/*
	 * This will form the start of a new hw segment.  Bump both
	 * counters.
	 */
	req->nr_phys_segments += nr_phys_segs;
	return 1;

no_merge:
	req_set_nomerge(req->q, req);
	return 0;
}

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(req->q, req);
		return 0;
	}

	return ll_new_hw_segment(req, bio, nr_segs);
}

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(req->q, req);
		return 0;
	}

	return ll_new_hw_segment(req, bio, nr_segs);
}

static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
		struct request *next)
{
	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(next->bio) >
	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
		goto no_merge;

	req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next);
	return true;
no_merge:
	req_set_nomerge(q, req);
	return false;
}

static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
				struct request *next)
{
	int total_phys_segments;

	if (req_gap_back_merge(req, next->bio))
		return 0;

	/*
	 * Will it become too large?
	 */
	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
		return 0;

	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
	if (total_phys_segments > blk_rq_get_max_segments(req))
		return 0;

	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;
	return 1;
}

/**
 * blk_rq_set_mixed_merge - mark a request as mixed merge
 * @rq: request to mark as mixed merge
 *
 * Description:
 *     @rq is about to be mixed merged.  Make sure the attributes
 *     which can be mixed are set in each bio and mark @rq as mixed
 *     merged.
 */
static void blk_rq_set_mixed_merge(struct request *rq)
{
	blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
	struct bio *bio;

	if (rq->rq_flags & RQF_MIXED_MERGE)
		return;

	/*
	 * @rq will no longer represent mixable attributes for all the
	 * contained bios.  It will just track those of the first one.
	 * Distributes the attributs to each bio.
	 */
	for (bio = rq->bio; bio; bio = bio->bi_next) {
		WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) &&
			     (bio->bi_opf & REQ_FAILFAST_MASK) != ff);
		bio->bi_opf |= ff;
	}
	rq->rq_flags |= RQF_MIXED_MERGE;
}

static inline blk_opf_t bio_failfast(const struct bio *bio)
{
	if (bio->bi_opf & REQ_RAHEAD)
		return REQ_FAILFAST_MASK;

	return bio->bi_opf & REQ_FAILFAST_MASK;
}

/*
 * 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;

		if (front_merge) {
			req->cmd_flags &= ~REQ_FAILFAST_MASK;
			req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK;
		}
	}
}

static void blk_account_io_merge_request(struct request *req)
{
	if (blk_do_io_stat(req)) {
		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,
					struct request *next)
{
	if (blk_discard_mergable(req))
		return ELEVATOR_DISCARD_MERGE;
	else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next))
		return ELEVATOR_BACK_MERGE;

	return ELEVATOR_NO_MERGE;
}

/*
 * 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.
 */
static struct request *attempt_merge(struct request_queue *q,
				     struct request *req, struct request *next)
{
	if (!rq_mergeable(req) || !rq_mergeable(next))
		return NULL;

	if (req_op(req) != req_op(next))
		return NULL;

	if (rq_data_dir(req) != rq_data_dir(next))
		return NULL;

	/* Don't merge requests with different write hints. */
	if (req->write_hint != next->write_hint)
		return NULL;

	if (req->ioprio != next->ioprio)
		return NULL;

	/*
	 * If we are allowed to merge, then append bio list
	 * from next to rq and release next. merge_requests_fn
	 * will have updated segment counts, update sector
	 * counts here. Handle DISCARDs separately, as they
	 * have separate settings.
	 */

	switch (blk_try_req_merge(req, next)) {
	case ELEVATOR_DISCARD_MERGE:
		if (!req_attempt_discard_merge(q, req, next))
			return NULL;
		break;
	case ELEVATOR_BACK_MERGE:
		if (!ll_merge_requests_fn(q, req, next))
			return NULL;
		break;
	default:
		return NULL;
	}

	/*
	 * If failfast settings disagree or any of the two is already
	 * a mixed merge, mark both as mixed before proceeding.  This
	 * makes sure that all involved bios have mixable attributes
	 * set properly.
	 */
	if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) ||
	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
		blk_rq_set_mixed_merge(req);
		blk_rq_set_mixed_merge(next);
	}

	/*
	 * At this point we have either done a back merge or front merge. We
	 * need the smaller start_time_ns of the merged requests to be the
	 * current request for accounting purposes.
	 */
	if (next->start_time_ns < req->start_time_ns)
		req->start_time_ns = next->start_time_ns;

	req->biotail->bi_next = next->bio;
	req->biotail = next->biotail;

	req->__data_len += blk_rq_bytes(next);

	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_request(next);

	trace_block_rq_merge(next);

	/*
	 * ownership of bio passed from next to req, return 'next' for
	 * the caller to free
	 */
	next->bio = NULL;
	return next;
}

static struct request *attempt_back_merge(struct request_queue *q,
		struct request *rq)
{
	struct request *next = elv_latter_request(q, rq);

	if (next)
		return attempt_merge(q, rq, next);

	return NULL;
}

static struct request *attempt_front_merge(struct request_queue *q,
		struct request *rq)
{
	struct request *prev = elv_former_request(q, rq);

	if (prev)
		return attempt_merge(q, prev, rq);

	return NULL;
}

/*
 * 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)
{
	return attempt_merge(q, rq, next);
}

bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
{
	if (!rq_mergeable(rq) || !bio_mergeable(bio))
		return false;

	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;

	/* don't merge across cgroup boundaries */
	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;

	/* Only merge if the crypt contexts are compatible */
	if (!bio_crypt_rq_ctx_compatible(rq, bio))
		return false;

	/* Don't merge requests with different write hints. */
	if (rq->write_hint != bio->bi_write_hint)
		return false;

	if (rq->ioprio != bio_prio(bio))
		return false;

	return true;
}

enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
{
	if (blk_discard_mergable(rq))
		return ELEVATOR_DISCARD_MERGE;
	else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
		return ELEVATOR_BACK_MERGE;
	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
		return ELEVATOR_FRONT_MERGE;
	return ELEVATOR_NO_MERGE;
}

static void blk_account_io_merge_bio(struct request *req)
{
	if (!blk_do_io_stat(req))
		return;

	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->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);

	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_list_for_each(&plug->mq_list, rq) {
		if (rq->q == q) {
			if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
			    BIO_MERGE_OK)
				return true;
			break;
		}

		/*
		 * Only keep iterating plug list for merges if we have multiple
		 * queues
		 */
		if (!plug->multiple_queues)
			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);