Merge branch 'for-4.3/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
"This first core part of the block IO changes contains:

- Cleanup of the bio IO error signaling from Christoph. We used to
rely on the uptodate bit and passing around of an error, now we
store the error in the bio itself.

- Improvement of the above from myself, by shrinking the bio size
down again to fit in two cachelines on x86-64.

- Revert of the max_hw_sectors cap removal from a revision again,
from Jeff Moyer. This caused performance regressions in various
tests. Reinstate the limit, bump it to a more reasonable size
instead.

- Make /sys/block/<dev>/queue/discard_max_bytes writeable, by me.
Most devices have huge trim limits, which can cause nasty latencies
when deleting files. Enable the admin to configure the size down.
We will look into having a more sane default instead of UINT_MAX
sectors.

- Improvement of the SGP gaps logic from Keith Busch.

- Enable the block core to handle arbitrarily sized bios, which
enables a nice simplification of bio_add_page() (which is an IO hot
path). From Kent.

- Improvements to the partition io stats accounting, making it
faster. From Ming Lei.

- Also from Ming Lei, a basic fixup for overflow of the sysfs pending
file in blk-mq, as well as a fix for a blk-mq timeout race
condition.

- Ming Lin has been carrying Kents above mentioned patches forward
for a while, and testing them. Ming also did a few fixes around
that.

- Sasha Levin found and fixed a use-after-free problem introduced by
the bio->bi_error changes from Christoph.

- Small blk cgroup cleanup from Viresh Kumar"

* 'for-4.3/core' of git://git.kernel.dk/linux-block: (26 commits)
blk: Fix bio_io_vec index when checking bvec gaps
block: Replace SG_GAPS with new queue limits mask
block: bump BLK_DEF_MAX_SECTORS to 2560
Revert "block: remove artifical max_hw_sectors cap"
blk-mq: fix race between timeout and freeing request
blk-mq: fix buffer overflow when reading sysfs file of 'pending'
Documentation: update notes in biovecs about arbitrarily sized bios
block: remove bio_get_nr_vecs()
fs: use helper bio_add_page() instead of open coding on bi_io_vec
block: kill merge_bvec_fn() completely
md/raid5: get rid of bio_fits_rdev()
md/raid5: split bio for chunk_aligned_read
block: remove split code in blkdev_issue_{discard,write_same}
btrfs: remove bio splitting and merge_bvec_fn() calls
bcache: remove driver private bio splitting code
block: simplify bio_add_page()
block: make generic_make_request handle arbitrarily sized bios
blk-cgroup: Drop unlikely before IS_ERR(_OR_NULL)
block: don't access bio->bi_error after bio_put()
block: shrink struct bio down to 2 cache lines again
...

Documentation/block/biodoc.txt

···
 as specified.
 
 Now bh->b_end_io is replaced by bio->bi_end_io, but most of the time the
-right thing to use is bio_endio(bio, uptodate) instead.
+right thing to use is bio_endio(bio) instead.
 
 If the driver is dropping the io_request_lock from its request_fn strategy,
 then it just needs to replace that with q->queue_lock instead.

Documentation/block/biovecs.txt

···
 normal code doesn't have to deal with bi_bvec_done.
 
  * Driver code should no longer refer to biovecs directly; we now have
-   bio_iovec() and bio_iovec_iter() macros that return literal struct biovecs,
+   bio_iovec() and bio_iter_iovec() macros that return literal struct biovecs,
    constructed from the raw biovecs but taking into account bi_bvec_done and
    bi_size.
 
···
    over all the biovecs in the new bio - which is silly as it's not needed.
 
    So, don't use bi_vcnt anymore.
+
+ * The current interface allows the block layer to split bios as needed, so we
+   could eliminate a lot of complexity particularly in stacked drivers. Code
+   that creates bios can then create whatever size bios are convenient, and
+   more importantly stacked drivers don't have to deal with both their own bio
+   size limitations and the limitations of the underlying devices. Thus
+   there's no need to define ->merge_bvec_fn() callbacks for individual block
+   drivers.

Documentation/block/queue-sysfs.txt

···
 reported by the device. A value of '0' means device does not support
 the discard functionality.
 
-discard_max_bytes (RO)
+discard_max_hw_bytes (RO)
 ----------------------
 Devices that support discard functionality may have internal limits on
 the number of bytes that can be trimmed or unmapped in a single operation.
···
 number of bytes that can be discarded in a single operation. Discard
 requests issued to the device must not exceed this limit. A discard_max_bytes
 value of 0 means that the device does not support discard functionality.
+
+discard_max_bytes (RW)
+----------------------
+While discard_max_hw_bytes is the hardware limit for the device, this
+setting is the software limit. Some devices exhibit large latencies when
+large discards are issued, setting this value lower will make Linux issue
+smaller discards and potentially help reduce latencies induced by large
+discard operations.
 
 discard_zeroes_data (RO)
 ------------------------

arch/m68k/emu/nfblock.c

···
 				bvec_to_phys(&bvec));
 		sec += len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)

arch/powerpc/sysdev/axonram.c

···
 		phys_mem += vec.bv_len;
 		transfered += vec.bv_len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 /**

arch/xtensa/platforms/iss/simdisk.c

···
 	spin_unlock(&dev->lock);
 }
 
-static int simdisk_xfer_bio(struct simdisk *dev, struct bio *bio)
+static void simdisk_make_request(struct request_queue *q, struct bio *bio)
 {
+	struct simdisk *dev = q->queuedata;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	sector_t sector = bio->bi_iter.bi_sector;
···
 		sector += len;
 		__bio_kunmap_atomic(buffer);
 	}
-	return 0;
-}
 
-static void simdisk_make_request(struct request_queue *q, struct bio *bio)
-{
-	struct simdisk *dev = q->queuedata;
-	int status = simdisk_xfer_bio(dev, bio);
-	bio_endio(bio, status);
+	bio_endio(bio);
 }
-
 
 static int simdisk_open(struct block_device *bdev, fmode_t mode)
 {

block/bio-integrity.c

···
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	int error;
 
-	error = bio_integrity_process(bio, bi->verify_fn);
+	bio->bi_error = bio_integrity_process(bio, bi->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-	bio_endio(bio, error);
+	bio_endio(bio);
 }
 
 /**
···
  * in process context.	This function postpones completion
  * accordingly.
  */
-void bio_integrity_endio(struct bio *bio, int error)
+void bio_integrity_endio(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
···
 	 * integrity metadata.  Restore original bio end_io handler
 	 * and run it.
 	 */
-	if (error) {
+	if (bio->bi_error) {
 		bio->bi_end_io = bip->bip_end_io;
-		bio_endio(bio, error);
+		bio_endio(bio);
 
 		return;
 	}

block/bio.c

···
 void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
-	bio->bi_flags = 1 << BIO_UPTODATE;
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
 }
···
 	__bio_free(bio);
 
 	memset(bio, 0, BIO_RESET_BYTES);
-	bio->bi_flags = flags | (1 << BIO_UPTODATE);
+	bio->bi_flags = flags;
 	atomic_set(&bio->__bi_remaining, 1);
 }
 EXPORT_SYMBOL(bio_reset);
 
-static void bio_chain_endio(struct bio *bio, int error)
+static void bio_chain_endio(struct bio *bio)
 {
-	bio_endio(bio->bi_private, error);
+	struct bio *parent = bio->bi_private;
+
+	parent->bi_error = bio->bi_error;
+	bio_endio(parent);
 	bio_put(bio);
 }
 
···
  */
 static inline void bio_inc_remaining(struct bio *bio)
 {
-	bio->bi_flags |= (1 << BIO_CHAIN);
+	bio_set_flag(bio, BIO_CHAIN);
 	smp_mb__before_atomic();
 	atomic_inc(&bio->__bi_remaining);
 }
···
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio->bi_flags |= 1 << BIO_OWNS_VEC;
+		bio_set_flag(bio, BIO_OWNS_VEC);
 	} else if (nr_iovecs) {
 		bvl = bio->bi_inline_vecs;
 	}
···
 	 * so we don't set nor calculate new physical/hw segment counts here
 	 */
 	bio->bi_bdev = bio_src->bi_bdev;
-	bio->bi_flags |= 1 << BIO_CLONED;
+	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_rw = bio_src->bi_rw;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
···
 EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
- *	bio_get_nr_vecs		- return approx number of vecs
- *	@bdev:  I/O target
+ *	bio_add_pc_page	-	attempt to add page to bio
+ *	@q: the target queue
+ *	@bio: destination bio
+ *	@page: page to add
+ *	@len: vec entry length
+ *	@offset: vec entry offset
  *
- *	Return the approximate number of pages we can send to this target.
- *	There's no guarantee that you will be able to fit this number of pages
- *	into a bio, it does not account for dynamic restrictions that vary
- *	on offset.
+ *	Attempt to add a page to the bio_vec maplist. This can fail for a
+ *	number of reasons, such as the bio being full or target block device
+ *	limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *	so it is always possible to add a single page to an empty bio.
+ *
+ *	This should only be used by REQ_PC bios.
  */
-int bio_get_nr_vecs(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-	int nr_pages;
-
-	nr_pages = min_t(unsigned,
-		     queue_max_segments(q),
-		     queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
-
-	return min_t(unsigned, nr_pages, BIO_MAX_PAGES);
-
-}
-EXPORT_SYMBOL(bio_get_nr_vecs);
-
-static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
-			  *page, unsigned int len, unsigned int offset,
-			  unsigned int max_sectors)
+int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
+		    *page, unsigned int len, unsigned int offset)
 {
 	int retried_segments = 0;
 	struct bio_vec *bvec;
···
 	if (unlikely(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
+	if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
 		return 0;
 
 	/*
···
 
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
-			unsigned int prev_bv_len = prev->bv_len;
 			prev->bv_len += len;
-
-			if (q->merge_bvec_fn) {
-				struct bvec_merge_data bvm = {
-					/* prev_bvec is already charged in
-					   bi_size, discharge it in order to
-					   simulate merging updated prev_bvec
-					   as new bvec. */
-					.bi_bdev = bio->bi_bdev,
-					.bi_sector = bio->bi_iter.bi_sector,
-					.bi_size = bio->bi_iter.bi_size -
-						prev_bv_len,
-					.bi_rw = bio->bi_rw,
-				};
-
-				if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
-					prev->bv_len -= len;
-					return 0;
-				}
-			}
-
 			bio->bi_iter.bi_size += len;
 			goto done;
 		}
···
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
-		if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
-		    bvec_gap_to_prev(prev, offset))
+		if (bvec_gap_to_prev(q, prev, offset))
 			return 0;
 	}
 
···
 		blk_recount_segments(q, bio);
 	}
 
-	/*
-	 * if queue has other restrictions (eg varying max sector size
-	 * depending on offset), it can specify a merge_bvec_fn in the
-	 * queue to get further control
-	 */
-	if (q->merge_bvec_fn) {
-		struct bvec_merge_data bvm = {
-			.bi_bdev = bio->bi_bdev,
-			.bi_sector = bio->bi_iter.bi_sector,
-			.bi_size = bio->bi_iter.bi_size - len,
-			.bi_rw = bio->bi_rw,
-		};
-
-		/*
-		 * merge_bvec_fn() returns number of bytes it can accept
-		 * at this offset
-		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
-			goto failed;
-	}
-
 	/* If we may be able to merge these biovecs, force a recount */
 	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
-		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
+		bio_clear_flag(bio, BIO_SEG_VALID);
 
  done:
 	return len;
···
 	blk_recount_segments(q, bio);
 	return 0;
 }
-
-/**
- *	bio_add_pc_page	-	attempt to add page to bio
- *	@q: the target queue
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
- *
- *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block device
- *	limitations. The target block device must allow bio's up to PAGE_SIZE,
- *	so it is always possible to add a single page to an empty bio.
- *
- *	This should only be used by REQ_PC bios.
- */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
-		    unsigned int len, unsigned int offset)
-{
-	return __bio_add_page(q, bio, page, len, offset,
-			      queue_max_hw_sectors(q));
-}
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
···
  *	@len: vec entry length
  *	@offset: vec entry offset
  *
- *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block device
- *	limitations. The target block device must allow bio's up to PAGE_SIZE,
- *	so it is always possible to add a single page to an empty bio.
+ *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
  */
-int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
-		 unsigned int offset)
+int bio_add_page(struct bio *bio, struct page *page,
+		 unsigned int len, unsigned int offset)
 {
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int max_sectors;
+	struct bio_vec *bv;
 
-	max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
-	if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
-		max_sectors = len >> 9;
+	/*
+	 * cloned bio must not modify vec list
+	 */
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return 0;
 
-	return __bio_add_page(q, bio, page, len, offset, max_sectors);
+	/*
+	 * For filesystems with a blocksize smaller than the pagesize
+	 * we will often be called with the same page as last time and
+	 * a consecutive offset.  Optimize this special case.
+	 */
+	if (bio->bi_vcnt > 0) {
+		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (page == bv->bv_page &&
+		    offset == bv->bv_offset + bv->bv_len) {
+			bv->bv_len += len;
+			goto done;
+		}
+	}
+
+	if (bio->bi_vcnt >= bio->bi_max_vecs)
+		return 0;
+
+	bv		= &bio->bi_io_vec[bio->bi_vcnt];
+	bv->bv_page	= page;
+	bv->bv_len	= len;
+	bv->bv_offset	= offset;
+
+	bio->bi_vcnt++;
+done:
+	bio->bi_iter.bi_size += len;
+	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
 
···
 	int error;
 };
 
-static void submit_bio_wait_endio(struct bio *bio, int error)
+static void submit_bio_wait_endio(struct bio *bio)
 {
 	struct submit_bio_ret *ret = bio->bi_private;
 
-	ret->error = error;
+	ret->error = bio->bi_error;
 	complete(&ret->event);
 }
 
···
 	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
-	bio->bi_flags |= (1 << BIO_USER_MAPPED);
+	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
 	 * subtle -- if __bio_map_user() ended up bouncing a bio,
···
 }
 EXPORT_SYMBOL(bio_unmap_user);
 
-static void bio_map_kern_endio(struct bio *bio, int err)
+static void bio_map_kern_endio(struct bio *bio)
 {
 	bio_put(bio);
 }
···
 }
 EXPORT_SYMBOL(bio_map_kern);
 
-static void bio_copy_kern_endio(struct bio *bio, int err)
+static void bio_copy_kern_endio(struct bio *bio)
 {
 	bio_free_pages(bio);
 	bio_put(bio);
 }
 
-static void bio_copy_kern_endio_read(struct bio *bio, int err)
+static void bio_copy_kern_endio_read(struct bio *bio)
 {
 	char *p = bio->bi_private;
 	struct bio_vec *bvec;
···
 		p += bvec->bv_len;
 	}
 
-	bio_copy_kern_endio(bio, err);
+	bio_copy_kern_endio(bio);
 }
 
 /**
···
 	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
 
 	if (atomic_dec_and_test(&bio->__bi_remaining)) {
-		clear_bit(BIO_CHAIN, &bio->bi_flags);
+		bio_clear_flag(bio, BIO_CHAIN);
 		return true;
 	}
 
···
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
- * @error:	error, if any
  *
  * Description:
- *   bio_endio() will end I/O on the whole bio. bio_endio() is the
- *   preferred way to end I/O on a bio, it takes care of clearing
- *   BIO_UPTODATE on error. @error is 0 on success, and and one of the
- *   established -Exxxx (-EIO, for instance) error values in case
- *   something went wrong. No one should call bi_end_io() directly on a
- *   bio unless they own it and thus know that it has an end_io
- *   function.
+ *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
+ *   way to end I/O on a bio. No one should call bi_end_io() directly on a
+ *   bio unless they own it and thus know that it has an end_io function.
  **/
-void bio_endio(struct bio *bio, int error)
+void bio_endio(struct bio *bio)
 {
 	while (bio) {
-		if (error)
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
-		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-			error = -EIO;
-
 		if (unlikely(!bio_remaining_done(bio)))
 			break;
 
···
 		 */
 		if (bio->bi_end_io == bio_chain_endio) {
 			struct bio *parent = bio->bi_private;
+			parent->bi_error = bio->bi_error;
 			bio_put(bio);
 			bio = parent;
 		} else {
 			if (bio->bi_end_io)
-				bio->bi_end_io(bio, error);
+				bio->bi_end_io(bio);
 			bio = NULL;
 		}
 	}
···
 	if (offset == 0 && size == bio->bi_iter.bi_size)
 		return;
 
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	bio_advance(bio, offset << 9);
 

block/blk-core.c

···
 			  unsigned int nbytes, int error)
 {
 	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
+		bio->bi_error = error;
 
 	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
+		bio_set_flag(bio, BIO_QUIET);
 
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
+		bio_endio(bio);
 }
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
···
 	if (q->id < 0)
 		goto fail_q;
 
+	q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!q->bio_split)
+		goto fail_id;
+
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
···
 
 	err = bdi_init(&q->backing_dev_info);
 	if (err)
-		goto fail_id;
+		goto fail_split;
 
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
···
 
 fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
+fail_split:
+	bioset_free(q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
···
 	struct request *req;
 	unsigned int request_count = 0;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
···
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio->bi_error = -EIO;
+		bio_endio(bio);
 		return;
 	}
 
···
 	 */
 	req = get_request(q, rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
-		bio_endio(bio, PTR_ERR(req));	/* @q is dead */
+		bio->bi_error = PTR_ERR(req);
+		bio_endio(bio);
 		goto out_unlock;
 	}
 
···
 		goto end_io;
 	}
 
-	if (likely(bio_is_rw(bio) &&
-		   nr_sectors > queue_max_hw_sectors(q))) {
-		printk(KERN_ERR "bio too big device %s (%u > %u)\n",
-		       bdevname(bio->bi_bdev, b),
-		       bio_sectors(bio),
-		       queue_max_hw_sectors(q));
-		goto end_io;
-	}
-
 	part = bio->bi_bdev->bd_part;
 	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
···
 	return true;
 
 end_io:
-	bio_endio(bio, err);
+	bio->bi_error = err;
+	bio_endio(bio);
 	return false;
 }
 

block/blk-flush.c

···
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-tag.h"
 
 /* FLUSH/FUA sequences */
 enum {
···
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 
 	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+
+		/* release the tag's ownership to the req cloned from */
 		spin_lock_irqsave(&fq->mq_flush_lock, flags);
+		hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
 		flush_rq->tag = -1;
 	}
 
···
 
 	/*
 	 * Borrow tag from the first request since they can't
-	 * be in flight at the same time.
+	 * be in flight at the same time. And acquire the tag's
+	 * ownership for flush req.
 	 */
 	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+
 		flush_rq->mq_ctx = first_rq->mq_ctx;
 		flush_rq->tag = first_rq->tag;
+		fq->orig_rq = first_rq;
+
+		hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;

block/blk-lib.c

···
 
 struct bio_batch {
 	atomic_t		done;
-	unsigned long		flags;
+	int			error;
 	struct completion	*wait;
 };
 
-static void bio_batch_end_io(struct bio *bio, int err)
+static void bio_batch_end_io(struct bio *bio)
 {
 	struct bio_batch *bb = bio->bi_private;
 
-	if (err && (err != -EOPNOTSUPP))
-		clear_bit(BIO_UPTODATE, &bb->flags);
+	if (bio->bi_error && bio->bi_error != -EOPNOTSUPP)
+		bb->error = bio->bi_error;
 	if (atomic_dec_and_test(&bb->done))
 		complete(bb->wait);
 	bio_put(bio);
 }
+
+/*
+ * Ensure that max discard sectors doesn't overflow bi_size and hopefully
+ * it is of the proper granularity as long as the granularity is a power
+ * of two.
+ */
+#define MAX_BIO_SECTORS ((1U << 31) >> 9)
 
 /**
  * blkdev_issue_discard - queue a discard
···
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
 	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
···
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	/*
-	 * Ensure that max_discard_sectors is of the proper
-	 * granularity, so that requests stay aligned after a split.
-	 */
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors)) {
-		/* Avoid infinite loop below. Being cautious never hurts. */
-		return -EOPNOTSUPP;
-	}
-
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
···
 	}
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	blk_start_plug(&plug);
 	while (nr_sects) {
 		unsigned int req_sects;
-		sector_t end_sect, tmp;
+		sector_t end_sect;
 
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
···
 			break;
 		}
 
-		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
-
-		/*
-		 * If splitting a request, and the next starting sector would be
-		 * misaligned, stop the discard at the previous aligned sector.
-		 */
+		req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS);
 		end_sect = sector + req_sects;
-		tmp = end_sect;
-		if (req_sects < nr_sects &&
-		    sector_div(tmp, granularity) != alignment) {
-			end_sect = end_sect - alignment;
-			sector_div(end_sect, granularity);
-			end_sect = end_sect * granularity + alignment;
-			req_sects = end_sect - sector;
-		}
 
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
···
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		ret = -EIO;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
···
 	if (!q)
 		return -ENXIO;
 
-	max_write_same_sectors = q->limits.max_write_same_sectors;
-
-	if (max_write_same_sectors == 0)
-		return -EOPNOTSUPP;
+	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
+	max_write_same_sectors = UINT_MAX >> 9;
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	while (nr_sects) {
···
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		ret = -ENOTSUPP;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
···
 	DECLARE_COMPLETION_ONSTACK(wait);
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	ret = 0;
···
 	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion_io(&wait);
 
-	if (!test_bit(BIO_UPTODATE, &bb.flags))
-		/* One of bios in the batch was completed with error.*/
-		ret = -EIO;
-
+	if (bb.error)
+		return bb.error;
 	return ret;
 }
 

block/blk-map.c

···
 		return PTR_ERR(bio);
 
 	if (map_data && map_data->null_mapped)
-		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
+		bio_set_flag(bio, BIO_NULL_MAPPED);
 
 	if (bio->bi_iter.bi_size != iter->count) {
 		/*
···
 		 * normal IO completion path
 		 */
 		bio_get(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		__blk_rq_unmap_user(bio);
 		return -EINVAL;
 	}

block/blk-merge.c

···
 
 #include "blk.h"
 
+static struct bio *blk_bio_discard_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	unsigned int max_discard_sectors, granularity;
+	int alignment;
+	sector_t tmp;
+	unsigned split_sectors;
+
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+
+	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors -= max_discard_sectors % granularity;
+
+	if (unlikely(!max_discard_sectors)) {
+		/* XXX: warn */
+		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.
+	 */
+	alignment = (q->limits.discard_alignment >> 9) % granularity;
+
+	tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
+	tmp = sector_div(tmp, granularity);
+
+	if (split_sectors > tmp)
+		split_sectors -= tmp;
+
+	return bio_split(bio, split_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_write_same_split(struct request_queue *q,
+					    struct bio *bio,
+					    struct bio_set *bs)
+{
+	if (!q->limits.max_write_same_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
+		return NULL;
+
+	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_segment_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	struct bio *split;
+	struct bio_vec bv, bvprv;
+	struct bvec_iter iter;
+	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	int prev = 0;
+
+	bio_for_each_segment(bv, bio, iter) {
+		sectors += bv.bv_len >> 9;
+
+		if (sectors > queue_max_sectors(q))
+			goto split;
+
+		/*
+		 * If the queue doesn't support SG gaps and adding this
+		 * offset would create a gap, disallow it.
+		 */
+		if (prev && bvec_gap_to_prev(q, &bvprv, bv.bv_offset))
+			goto split;
+
+		if (prev && blk_queue_cluster(q)) {
+			if (seg_size + bv.bv_len > queue_max_segment_size(q))
+				goto new_segment;
+			if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
+				goto new_segment;
+			if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
+				goto new_segment;
+
+			seg_size += bv.bv_len;
+			bvprv = bv;
+			prev = 1;
+			continue;
+		}
+new_segment:
+		if (nsegs == queue_max_segments(q))
+			goto split;
+
+		nsegs++;
+		bvprv = bv;
+		prev = 1;
+		seg_size = bv.bv_len;
+	}
+
+	return NULL;
+split:
+	split = bio_clone_bioset(bio, GFP_NOIO, bs);
+
+	split->bi_iter.bi_size -= iter.bi_size;
+	bio->bi_iter = iter;
+
+	if (bio_integrity(bio)) {
+		bio_integrity_advance(bio, split->bi_iter.bi_size);
+		bio_integrity_trim(split, 0, bio_sectors(split));
+	}
+
+	return split;
+}
+
+void blk_queue_split(struct request_queue *q, struct bio **bio,
+		     struct bio_set *bs)
+{
+	struct bio *split;
+
+	if ((*bio)->bi_rw & REQ_DISCARD)
+		split = blk_bio_discard_split(q, *bio, bs);
+	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+		split = blk_bio_write_same_split(q, *bio, bs);
+	else
+		split = blk_bio_segment_split(q, *bio, q->bio_split);
+
+	if (split) {
+		bio_chain(split, *bio);
+		generic_make_request(*bio);
+		*bio = split;
+	}
+}
+EXPORT_SYMBOL(blk_queue_split);
+
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio,
 					     bool no_sg_merge)
 {
 	struct bio_vec bv, bvprv = { NULL };
-	int cluster, high, highprv = 1;
+	int cluster, prev = 0;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
···
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
-	high = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, iter) {
 			/*
···
 			if (no_sg_merge)
 				goto new_segment;
 
-			/*
-			 * the trick here is making sure that a high page is
-			 * never considered part of another segment, since
-			 * that might change with the bounce page.
-			 */
-			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
-			if (!high && !highprv && cluster) {
+			if (prev && cluster) {
 				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
 					goto new_segment;
···
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
···
 		bio->bi_next = nxt;
 	}
 
-	bio->bi_flags |= (1 << BIO_SEG_VALID);
+	bio_set_flag(bio, BIO_SEG_VALID);
 }
 EXPORT_SYMBOL(blk_recount_segments);
 
···
 	return !q->mq_ops && req->special;
 }
 
-static int req_gap_to_prev(struct request *req, struct request *next)
+static int req_gap_to_prev(struct request *req, struct bio *next)
 {
 	struct bio *prev = req->biotail;
 
-	return bvec_gap_to_prev(&prev->bi_io_vec[prev->bi_vcnt - 1],
-				next->bio->bi_io_vec[0].bv_offset);
+	return bvec_gap_to_prev(req->q, &prev->bi_io_vec[prev->bi_vcnt - 1],
+			next->bi_io_vec[0].bv_offset);
 }
 
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
···
 	if (req_no_special_merge(req) || req_no_special_merge(next))
 		return 0;
 
-	if (test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags) &&
-	    req_gap_to_prev(req, next))
+	if (req_gap_to_prev(req, next->bio))
 		return 0;
 
 	/*
···
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 {
-	struct request_queue *q = rq->q;
-
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
···
 		return false;
 
 	/* Only check gaps if the bio carries data */
-	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && bio_has_data(bio)) {
-		struct bio_vec *bprev;
-
-		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
-		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
-			return false;
-	}
+	if (bio_has_data(bio) && req_gap_to_prev(rq, bio))
+		return false;
 
 	return true;
 }

block/blk-mq-sysfs.c

···
 
 static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
 {
-	char *start_page = page;
 	struct request *rq;
+	int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);
 
-	page += sprintf(page, "%s:\n", msg);
+	list_for_each_entry(rq, list, queuelist) {
+		const int rq_len = 2 * sizeof(rq) + 2;
 
-	list_for_each_entry(rq, list, queuelist)
-		page += sprintf(page, "\t%p\n", rq);
+		/* if the output will be truncated */
+		if (PAGE_SIZE - 1 < len + rq_len) {
+			/* backspacing if it can't hold '\t...\n' */
+			if (PAGE_SIZE - 1 < len + 5)
+				len -= rq_len;
+			len += snprintf(page + len, PAGE_SIZE - 1 - len,
+					"\t...\n");
+			break;
+		}
+		len += snprintf(page + len, PAGE_SIZE - 1 - len,
+				"\t%p\n", rq);
+	}
 
-	return page - start_page;
+	return len;
 }
 
 static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)

block/blk-mq-tag.c

···
 		for (bit = find_first_bit(&bm->word, bm->depth);
 		     bit < bm->depth;
 		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
-		     	rq = blk_mq_tag_to_rq(hctx->tags, off + bit);
+			rq = hctx->tags->rqs[off + bit];
 			if (rq->q == hctx->queue)
 				fn(hctx, rq, data, reserved);
 		}
···
 		for (bit = find_first_bit(&bm->word, bm->depth);
 		     bit < bm->depth;
 		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
-			rq = blk_mq_tag_to_rq(tags, off + bit);
+			rq = tags->rqs[off + bit];
 			fn(rq, data, reserved);
 		}
 

block/blk-mq-tag.h

···
 	__blk_mq_tag_idle(hctx);
 }
 
+/*
+ * This helper should only be used for flush request to share tag
+ * with the request cloned from, and both the two requests can't be
+ * in flight at the same time. The caller has to make sure the tag
+ * can't be freed.
+ */
+static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
+		unsigned int tag, struct request *rq)
+{
+	hctx->tags->rqs[tag] = rq;
+}
+
 #endif

block/blk-mq.c

···
 }
 EXPORT_SYMBOL(blk_mq_abort_requeue_list);
 
-static inline bool is_flush_request(struct request *rq,
-		struct blk_flush_queue *fq, unsigned int tag)
-{
-	return ((rq->cmd_flags & REQ_FLUSH_SEQ) &&
-			fq->flush_rq->tag == tag);
-}
-
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
-	struct request *rq = tags->rqs[tag];
-	/* mq_ctx of flush rq is always cloned from the corresponding req */
-	struct blk_flush_queue *fq = blk_get_flush_queue(rq->q, rq->mq_ctx);
-
-	if (!is_flush_request(rq, fq, tag))
-		return rq;
-
-	return fq->flush_rq;
+	return tags->rqs[tag];
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
···
 	struct blk_mq_alloc_data alloc_data;
 
 	if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return NULL;
 	}
 
···
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return;
 	}
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
···
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return;
 	}
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, NULL))

block/blk-settings.c

···
 }
 EXPORT_SYMBOL(blk_queue_unprep_rq);
 
-/**
- * blk_queue_merge_bvec - set a merge_bvec function for queue
- * @q:		queue
- * @mbfn:	merge_bvec_fn
- *
- * Usually queues have static limitations on the max sectors or segments that
- * we can put in a request. Stacking drivers may have some settings that
- * are dynamic, and thus we have to query the queue whether it is ok to
- * add a new bio_vec to a bio at a given offset or not. If the block device
- * has such limitations, it needs to register a merge_bvec_fn to control
- * the size of bio's sent to it. Note that a block device *must* allow a
- * single page to be added to an empty bio. The block device driver may want
- * to use the bio_split() function to deal with these bio's. By default
- * no merge_bvec_fn is defined for a queue, and only the fixed limits are
- * honored.
- */
-void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
-{
-	q->merge_bvec_fn = mbfn;
-}
-EXPORT_SYMBOL(blk_queue_merge_bvec);
-
 void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
 {
 	q->softirq_done_fn = fn;
···
 	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
+	lim->max_hw_discard_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
···
 		       __func__, max_hw_sectors);
 	}
 
-	limits->max_sectors = limits->max_hw_sectors = max_hw_sectors;
+	limits->max_hw_sectors = max_hw_sectors;
+	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
+				    BLK_DEF_MAX_SECTORS);
 }
 EXPORT_SYMBOL(blk_limits_max_hw_sectors);
 
···
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
 {
+	q->limits.max_hw_discard_sectors = max_discard_sectors;
 	q->limits.max_discard_sectors = max_discard_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
···
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
+	t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
+					    b->virt_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
 	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
···
 
 		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
 						      b->max_discard_sectors);
+		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
+							 b->max_hw_discard_sectors);
 		t->discard_granularity = max(t->discard_granularity,
 					     b->discard_granularity);
 		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
···
 	q->limits.seg_boundary_mask = mask;
 }
 EXPORT_SYMBOL(blk_queue_segment_boundary);
+
+/**
+ * blk_queue_virt_boundary - set boundary rules for bio merging
+ * @q:  the request queue for the device
+ * @mask:  the memory boundary mask
+ **/
+void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
+{
+	q->limits.virt_boundary_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_virt_boundary);
 
 /**
  * blk_queue_dma_alignment - set dma length and memory alignment

block/blk-sysfs.c

···
 	return queue_var_show(q->limits.discard_granularity, page);
 }
 
+static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
+{
+	unsigned long long val;
+
+	val = q->limits.max_hw_discard_sectors << 9;
+	return sprintf(page, "%llu\n", val);
+}
+
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
 	return sprintf(page, "%llu\n",
 		       (unsigned long long)q->limits.max_discard_sectors << 9);
+}
+
+static ssize_t queue_discard_max_store(struct request_queue *q,
+				       const char *page, size_t count)
+{
+	unsigned long max_discard;
+	ssize_t ret = queue_var_store(&max_discard, page, count);
+
+	if (ret < 0)
+		return ret;
+
+	if (max_discard & (q->limits.discard_granularity - 1))
+		return -EINVAL;
+
+	max_discard >>= 9;
+	if (max_discard > UINT_MAX)
+		return -EINVAL;
+
+	if (max_discard > q->limits.max_hw_discard_sectors)
+		max_discard = q->limits.max_hw_discard_sectors;
+
+	q->limits.max_discard_sectors = max_discard;
+	return ret;
 }
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
···
 	.show = queue_discard_granularity_show,
 };
 
+static struct queue_sysfs_entry queue_discard_max_hw_entry = {
+	.attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+	.show = queue_discard_max_hw_show,
+};
+
 static struct queue_sysfs_entry queue_discard_max_entry = {
-	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_discard_max_show,
+	.store = queue_discard_max_store,
 };
 
 static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
···
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
 	&queue_discard_max_entry.attr,
+	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
 	&queue_write_same_max_entry.attr,
 	&queue_nonrot_entry.attr,
···
 		blk_mq_release(q);
 
 	blk_trace_shutdown(q);
+
+	if (q->bio_split)
+		bioset_free(q->bio_split);
 
 	ida_simple_remove(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);

block/blk.h

···
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
 	struct request		*flush_rq;
+
+	/*
+	 * flush_rq shares tag with this rq, both can't be active
+	 * at the same time
+	 */
+	struct request		*orig_rq;
 	spinlock_t		mq_flush_lock;
 };
 

block/bounce.c

···
 	}
 }
 
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+static void bounce_end_io(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 	struct bio_vec *bvec, *org_vec;
···
 		mempool_free(bvec->bv_page, pool);
 	}
 
-	bio_endio(bio_orig, err);
+	bio_orig->bi_error = bio->bi_error;
+	bio_endio(bio_orig);
 	bio_put(bio);
 }
 
-static void bounce_end_io_write(struct bio *bio, int err)
+static void bounce_end_io_write(struct bio *bio)
 {
-	bounce_end_io(bio, page_pool, err);
+	bounce_end_io(bio, page_pool);
 }
 
-static void bounce_end_io_write_isa(struct bio *bio, int err)
+static void bounce_end_io_write_isa(struct bio *bio)
 {
 
-	bounce_end_io(bio, isa_page_pool, err);
+	bounce_end_io(bio, isa_page_pool);
 }
 
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		copy_to_high_bio_irq(bio_orig, bio);
 
-	bounce_end_io(bio, pool, err);
+	bounce_end_io(bio, pool);
 }
 
-static void bounce_end_io_read(struct bio *bio, int err)
+static void bounce_end_io_read(struct bio *bio)
 {
-	__bounce_end_io_read(bio, page_pool, err);
+	__bounce_end_io_read(bio, page_pool);
 }
 
-static void bounce_end_io_read_isa(struct bio *bio, int err)
+static void bounce_end_io_read_isa(struct bio *bio)
 {
-	__bounce_end_io_read(bio, isa_page_pool, err);
+	__bounce_end_io_read(bio, isa_page_pool);
 }
 
 #ifdef CONFIG_NEED_BOUNCE_POOL
···
 	if (!bdi_cap_stable_pages_required(&q->backing_dev_info))
 		return 0;
 
-	return test_bit(BIO_SNAP_STABLE, &bio->bi_flags);
+	return bio_flagged(bio, BIO_SNAP_STABLE);
 }
 #else
 static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)

block/genhd.c

···
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
-	free_part_stats(&disk->part0);
-	free_part_info(&disk->part0);
+	hd_free_part(&disk->part0);
 	if (disk->queue)
 		blk_put_queue(disk->queue);
 	kfree(disk);
···
 		 * converted to make use of bd_mutex and sequence counters.
 		 */
 		seqcount_init(&disk->part0.nr_sects_seq);
-		hd_ref_init(&disk->part0);
+		if (hd_ref_init(&disk->part0)) {
+			hd_free_part(&disk->part0);
+			kfree(disk);
+			return NULL;
+		}
 
 		disk->minors = minors;
 		rand_initialize_disk(disk);

block/partition-generic.c

···
 {
 	struct hd_struct *p = dev_to_part(dev);
 	blk_free_devt(dev->devt);
-	free_part_stats(p);
-	free_part_info(p);
+	hd_free_part(p);
 	kfree(p);
 }
 
···
 	put_device(part_to_dev(part));
 }
 
-void __delete_partition(struct hd_struct *part)
+void __delete_partition(struct percpu_ref *ref)
 {
+	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
 	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
···
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
-	hd_struct_put(part);
+	hd_struct_kill(part);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
···
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
-	hd_ref_init(p);
-	return p;
+	if (!hd_ref_init(p))
+		return p;
 
 out_free_info:
 	free_part_info(p);

drivers/block/aoe/aoeblk.c

···
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	blk_queue_max_hw_sectors(q, 1024);
+	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
 	q->backing_dev_info.name = "aoe";
 	q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_CACHE_SIZE;
 	d->bufpool = mp;

drivers/block/aoe/aoecmd.c

···
 		d->ip.rq = NULL;
 	do {
 		bio = rq->bio;
-		bok = !fastfail && test_bit(BIO_UPTODATE, &bio->bi_flags);
+		bok = !fastfail && !bio->bi_error;
 	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
 
 	/* cf. http://lkml.org/lkml/2006/10/31/28 */
···
 			ahout->cmdstat, ahin->cmdstat,
 			d->aoemajor, d->aoeminor);
 noskb:		if (buf)
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 		goto out;
 	}
 
···
 				"aoe: runt data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 			       skb->len, n);
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 			break;
 		}
 		if (n > f->iter.bi_size) {
···
 				"aoe: too-large data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 				n, f->iter.bi_size);
-			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			buf->bio->bi_error = -EIO;
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
···
 	if (buf == NULL)
 		return;
 	buf->iter.bi_size = 0;
-	clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+	buf->bio->bi_error = -EIO;
 	if (buf->nframesout == 0)
 		aoe_end_buf(d, buf);
 }

drivers/block/aoe/aoedev.c

···
 	if (rq == NULL)
 		return;
 	while ((bio = d->ip.nxbio)) {
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 		d->ip.nxbio = bio->bi_next;
 		n = (unsigned long) rq->special;
 		rq->special = (void *) --n;

drivers/block/brd.c

···
 	struct bio_vec bvec;
 	sector_t sector;
 	struct bvec_iter iter;
-	int err = -EIO;
 
 	sector = bio->bi_iter.bi_sector;
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
-		goto out;
+		goto io_error;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
-		err = 0;
 		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
 		goto out;
 	}
···
 
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
+		int err;
+
 		err = brd_do_bvec(brd, bvec.bv_page, len,
 					bvec.bv_offset, rw, sector);
 		if (err)
-			break;
+			goto io_error;
 		sector += len >> SECTOR_SHIFT;
 	}
 
 out:
-	bio_endio(bio, err);
+	bio_endio(bio);
+	return;
+io_error:
+	bio_io_error(bio);
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
···
 	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
 
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
-	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
+	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 

drivers/block/drbd/drbd_actlog.c

···
 	atomic_inc(&device->md_io.in_use); /* drbd_md_put_buffer() is in the completion handler */
 	device->md_io.submit_jif = jiffies;
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		submit_bio(rw, bio);
 	wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
-	if (bio_flagged(bio, BIO_UPTODATE))
+	if (!bio->bi_error)
 		err = device->md_io.error;
 
  out:

drivers/block/drbd/drbd_bitmap.c

···
 }
 
 /* bv_page may be a copy, or may be the original */
-static void drbd_bm_endio(struct bio *bio, int error)
+static void drbd_bm_endio(struct bio *bio)
 {
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
 	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-
-	/* strange behavior of some lower level drivers...
-	 * fail the request by clearing the uptodate flag,
-	 * but do not return any error?!
-	 * do we want to WARN() on this? */
-	if (!error && !uptodate)
-		error = -EIO;
 
 	if ((ctx->flags & BM_AIO_COPY_PAGES) == 0 &&
 	    !bm_test_page_unchanged(b->bm_pages[idx]))
 		drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx);
 
-	if (error) {
+	if (bio->bi_error) {
 		/* ctx error will hold the completed-last non-zero error code,
 		 * in case error codes differ. */
-		ctx->error = error;
+		ctx->error = bio->bi_error;
 		bm_set_page_io_err(b->bm_pages[idx]);
 		/* Not identical to on disk version of it.
 		 * Is BM_PAGE_IO_ERROR enough? */
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_err(device, "IO ERROR %d on bitmap page idx %u\n",
-					error, idx);
+					bio->bi_error, idx);
 	} else {
 		bm_clear_page_io_err(b->bm_pages[idx]);
 		dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx);
···
 
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio->bi_rw |= rw;
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	} else {
 		submit_bio(rw, bio);
 		/* this should not count as user activity and cause the

drivers/block/drbd/drbd_int.h

···
 extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long);
 extern void drbd_make_request(struct request_queue *q, struct bio *bio);
 extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
-extern int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *bvec);
 extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
···
 
 /* drbd_worker.c */
 /* bi_end_io handlers */
-extern void drbd_md_endio(struct bio *bio, int error);
-extern void drbd_peer_request_endio(struct bio *bio, int error);
-extern void drbd_request_endio(struct bio *bio, int error);
+extern void drbd_md_endio(struct bio *bio);
+extern void drbd_peer_request_endio(struct bio *bio);
+extern void drbd_request_endio(struct bio *bio);
 extern int drbd_worker(struct drbd_thread *thi);
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor);
 void drbd_resync_after_changed(struct drbd_device *device);
···
 	__release(local);
 	if (!bio->bi_bdev) {
 		drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n");
-		bio_endio(bio, -ENODEV);
+		bio->bi_error = -ENODEV;
+		bio_endio(bio);
 		return;
 	}
 
 	if (drbd_insert_fault(device, fault_type))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		generic_make_request(bio);
 }

drivers/block/drbd/drbd_main.c

···
 	   This triggers a max_bio_size message upon first attach or connect */
 	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
 	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
-	blk_queue_merge_bvec(q, drbd_merge_bvec);
 	q->queue_lock = &resource->req_lock;
 
 	device->md_io.page = alloc_page(GFP_KERNEL);

drivers/block/drbd/drbd_nl.c

···
 			/* For now, don't allow more than one activity log extent worth of data
 			 * to be discarded in one go. We may need to rework drbd_al_begin_io()
 			 * to allow for even larger discard ranges */
-			q->limits.max_discard_sectors = DRBD_MAX_DISCARD_SECTORS;
+			blk_queue_max_discard_sectors(q, DRBD_MAX_DISCARD_SECTORS);
 
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 			/* REALLY? Is stacking secdiscard "legal"? */
 			if (blk_queue_secdiscard(b))
 				queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
 		} else {
-			q->limits.max_discard_sectors = 0;
+			blk_queue_max_discard_sectors(q, 0);
 			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 			queue_flag_clear_unlocked(QUEUE_FLAG_SECDISCARD, q);
 		}

drivers/block/drbd/drbd_req.c

···
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	bio_endio(m->bio, m->error);
+	m->bio->bi_error = m->error;
+	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
 
···
 				      rw == WRITE ? DRBD_FAULT_DT_WR
 				    : rw == READ  ? DRBD_FAULT_DT_RD
 				    :               DRBD_FAULT_DT_RA))
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 		else
 			generic_make_request(bio);
 		put_ldev(device);
 	} else
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 }
 
 static void drbd_queue_write(struct drbd_device *device, struct drbd_request *req)
···
 		/* only pass the error to the upper layers.
 		 * if user cannot handle io errors, that's not our business. */
 		drbd_err(device, "could not kmalloc() req\n");
-		bio_endio(bio, -ENOMEM);
+		bio->bi_error = -ENOMEM;
+		bio_endio(bio);
 		return ERR_PTR(-ENOMEM);
 	}
 	req->start_jif = start_jif;
···
 	struct drbd_device *device = (struct drbd_device *) q->queuedata;
 	unsigned long start_jif;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	start_jif = jiffies;
 
 	/*
···
 
 	inc_ap_bio(device);
 	__drbd_make_request(device, bio, start_jif);
-}
-
-/* This is called by bio_add_page().
- *
- * q->max_hw_sectors and other global limits are already enforced there.
- *
- * We need to call down to our lower level device,
- * in case it has special restrictions.
- *
- * We also may need to enforce configured max-bio-bvecs limits.
- *
- * As long as the BIO is empty we have to allow at least one bvec,
- * regardless of size and offset, so no need to ask lower levels.
- */
-int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *bvec)
-{
-	struct drbd_device *device = (struct drbd_device *) q->queuedata;
-	unsigned int bio_size = bvm->bi_size;
-	int limit = DRBD_MAX_BIO_SIZE;
-	int backing_limit;
-
-	if (bio_size && get_ldev(device)) {
-		unsigned int max_hw_sectors = queue_max_hw_sectors(q);
-		struct request_queue * const b =
-			device->ldev->backing_bdev->bd_disk->queue;
-		if (b->merge_bvec_fn) {
-			bvm->bi_bdev = device->ldev->backing_bdev;
-			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
-			limit = min(limit, backing_limit);
-		}
-		put_ldev(device);
-		if ((limit >> 9) > max_hw_sectors)
-			limit = max_hw_sectors << 9;
-	}
-	return limit;
 }
 
 void request_timer_fn(unsigned long data)

drivers/block/drbd/drbd_worker.c

···
 /* used for synchronous meta data and bitmap IO
  * submitted by drbd_md_sync_page_io()
  */
-void drbd_md_endio(struct bio *bio, int error)
+void drbd_md_endio(struct bio *bio)
 {
 	struct drbd_device *device;
 
 	device = bio->bi_private;
-	device->md_io.error = error;
+	device->md_io.error = bio->bi_error;
 
 	/* We grabbed an extra reference in _drbd_md_sync_page_io() to be able
 	 * to timeout on the lower level device, and eventually detach from it.
···
 /* writes on behalf of the partner, or resync writes,
  * "submitted" by the receiver.
  */
-void drbd_peer_request_endio(struct bio *bio, int error)
+void drbd_peer_request_endio(struct bio *bio)
 {
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 	int is_write = bio_data_dir(bio) == WRITE;
 	int is_discard = !!(bio->bi_rw & REQ_DISCARD);
 
-	if (error && __ratelimit(&drbd_ratelimit_state))
+	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
 				is_write ? (is_discard ? "discard" : "write")
-					: "read", error,
+					: "read", bio->bi_error,
 				(unsigned long long)peer_req->i.sector);
-	if (!error && !uptodate) {
-		if (__ratelimit(&drbd_ratelimit_state))
-			drbd_warn(device, "%s: setting error to -EIO s=%llus\n",
-					is_write ? "write" : "read",
-					(unsigned long long)peer_req->i.sector);
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
 
-	if (error)
+	if (bio->bi_error)
 		set_bit(__EE_WAS_ERROR, &peer_req->flags);
 
 	bio_put(bio); /* no need for the bio anymore */
···
 
 /* read, readA or write requests on R_PRIMARY coming from drbd_make_request
  */
-void drbd_request_endio(struct bio *bio, int error)
+void drbd_request_endio(struct bio *bio)
 {
 	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_device *device = req->device;
 	struct bio_and_error m;
 	enum drbd_req_event what;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-	if (!error && !uptodate) {
-		drbd_warn(device, "p %s: setting error to -EIO\n",
-			 bio_data_dir(bio) == WRITE ? "write" : "read");
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
-
 
 	/* If this request was aborted locally before,
 	 * but now was completed "successfully",
···
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
 
-		if (!error)
+		if (!bio->bi_error)
 			panic("possible random memory corruption caused by delayed completion of aborted local request\n");
 	}
 
 	/* to avoid recursion in __req_mod */
-	if (unlikely(error)) {
+	if (unlikely(bio->bi_error)) {
 		if (bio->bi_rw & REQ_DISCARD)
-			what = (error == -EOPNOTSUPP)
+			what = (bio->bi_error == -EOPNOTSUPP)
 				? DISCARD_COMPLETED_NOTSUPP
 				: DISCARD_COMPLETED_WITH_ERROR;
 		else
···
 		what = COMPLETED_OK;
 
 	bio_put(req->private_bio);
-	req->private_bio = ERR_PTR(error);
+	req->private_bio = ERR_PTR(bio->bi_error);
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);

drivers/block/floppy.c

···
 	struct completion complete;
 };
 
-static void floppy_rb0_cb(struct bio *bio, int err)
+static void floppy_rb0_cb(struct bio *bio)
 {
 	struct rb0_cbdata *cbdata = (struct rb0_cbdata *)bio->bi_private;
 	int drive = cbdata->drive;
 
-	if (err) {
-		pr_info("floppy: error %d while reading block 0\n", err);
+	if (bio->bi_error) {
+		pr_info("floppy: error %d while reading block 0\n",
+			bio->bi_error);
 		set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
 	}
 	complete(&cbdata->complete);

drivers/block/loop.c

···
 	    lo->lo_encrypt_key_size) {
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
-		q->limits.max_discard_sectors = 0;
+		blk_queue_max_discard_sectors(q, 0);
 		q->limits.discard_zeroes_data = 0;
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
···
 
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
-	q->limits.max_discard_sectors = UINT_MAX >> 9;
+	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
 	q->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }

drivers/block/nbd.c

···
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
 		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 		disk->queue->limits.discard_granularity = 512;
-		disk->queue->limits.max_discard_sectors = UINT_MAX;
+		blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
 		disk->queue->limits.discard_zeroes_data = 0;
 		blk_queue_max_hw_sectors(disk->queue, 65536);
 		disk->queue->limits.max_sectors = 256;

drivers/block/null_blk.c

···
 		blk_end_request_all(cmd->rq, 0);
 		break;
 	case NULL_Q_BIO:
-		bio_endio(cmd->bio, 0);
+		bio_endio(cmd->bio);
 		break;
 	}
 

drivers/block/nvme-core.c

···
 	ns->queue->limits.discard_zeroes_data = 0;
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
-	ns->queue->limits.max_discard_sectors = 0xffffffff;
+	blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
···
 		goto out_free_ns;
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
-	queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, ns->queue);
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
 
···
 		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
 	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
 		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
+	blk_queue_virt_boundary(ns->queue, dev->page_size - 1);
 
 	disk->major = nvme_major;
 	disk->first_minor = 0;

drivers/block/pktcdvd.c

···
 	}
 }
 
-static void pkt_end_io_read(struct bio *bio, int err)
+static void pkt_end_io_read(struct bio *bio)
 {
 	struct packet_data *pkt = bio->bi_private;
 	struct pktcdvd_device *pd = pkt->pd;
···
 
 	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
 		bio, (unsigned long long)pkt->sector,
-		(unsigned long long)bio->bi_iter.bi_sector, err);
+		(unsigned long long)bio->bi_iter.bi_sector, bio->bi_error);
 
-	if (err)
+	if (bio->bi_error)
 		atomic_inc(&pkt->io_errors);
 	if (atomic_dec_and_test(&pkt->io_wait)) {
 		atomic_inc(&pkt->run_sm);
···
 	pkt_bio_finished(pd);
 }
 
-static void pkt_end_io_packet_write(struct bio *bio, int err)
+static void pkt_end_io_packet_write(struct bio *bio)
 {
 	struct packet_data *pkt = bio->bi_private;
 	struct pktcdvd_device *pd = pkt->pd;
 	BUG_ON(!pd);
 
-	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, err);
+	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_error);
 
 	pd->stats.pkt_ended++;
 
···
 	pkt_queue_bio(pd, pkt->w_bio);
 }
 
-static void pkt_finish_packet(struct packet_data *pkt, int uptodate)
+static void pkt_finish_packet(struct packet_data *pkt, int error)
 {
 	struct bio *bio;
 
-	if (!uptodate)
+	if (error)
 		pkt->cache_valid = 0;
 
 	/* Finish all bios corresponding to this packet */
-	while ((bio = bio_list_pop(&pkt->orig_bios)))
-		bio_endio(bio, uptodate ? 0 : -EIO);
+	while ((bio = bio_list_pop(&pkt->orig_bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 
 static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
 {
-	int uptodate;
-
 	pkt_dbg(2, pd, "pkt %d\n", pkt->id);
 
 	for (;;) {
···
 			if (atomic_read(&pkt->io_wait) > 0)
 				return;
 
-			if (test_bit(BIO_UPTODATE, &pkt->w_bio->bi_flags)) {
+			if (!pkt->w_bio->bi_error) {
 				pkt_set_state(pkt, PACKET_FINISHED_STATE);
 			} else {
 				pkt_set_state(pkt, PACKET_RECOVERY_STATE);
···
 			break;
 
 		case PACKET_FINISHED_STATE:
-			uptodate = test_bit(BIO_UPTODATE, &pkt->w_bio->bi_flags);
-			pkt_finish_packet(pkt, uptodate);
+			pkt_finish_packet(pkt, pkt->w_bio->bi_error);
 			return;
 
 		default:
···
 }
 
 
-static void pkt_end_io_read_cloned(struct bio *bio, int err)
+static void pkt_end_io_read_cloned(struct bio *bio)
 {
 	struct packet_stacked_data *psd = bio->bi_private;
 	struct pktcdvd_device *pd = psd->pd;
 
+	psd->bio->bi_error = bio->bi_error;
 	bio_put(bio);
-	bio_endio(psd->bio, err);
+	bio_endio(psd->bio);
 	mempool_free(psd, psd_pool);
 	pkt_bio_finished(pd);
 }
···
 	char b[BDEVNAME_SIZE];
 	struct bio *split;
 
+	blk_queue_bounce(q, &bio);
+
+	blk_queue_split(q, &bio, q->bio_split);
+
 	pd = q->queuedata;
 	if (!pd) {
 		pr_err("%s incorrect request queue\n",
···
 		goto end_io;
 	}
 
-	blk_queue_bounce(q, &bio);
-
 	do {
 		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
 		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
···
 
 
 
-static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
-			  struct bio_vec *bvec)
-{
-	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = get_zone(bmd->bi_sector, pd);
-	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
-	int remaining = (pd->settings.size << 9) - used;
-	int remaining2;
-
-	/*
-	 * A bio <= PAGE_SIZE must be allowed. If it crosses a packet
-	 * boundary, pkt_make_request() will split the bio.
-	 */
-	remaining2 = PAGE_SIZE - bmd->bi_size;
-	remaining = max(remaining, remaining2);
-
-	BUG_ON(remaining < 0);
-	return remaining;
-}
-
 static void pkt_init_queue(struct pktcdvd_device *pd)
 {
 	struct request_queue *q = pd->disk->queue;
···
 	blk_queue_make_request(q, pkt_make_request);
 	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
-	blk_queue_merge_bvec(q, pkt_merge_bvec);
 	q->queuedata = pd;
 }
 

drivers/block/ps3vram.c

···
 	next = bio_list_peek(&priv->list);
 	spin_unlock_irq(&priv->lock);
 
-	bio_endio(bio, error);
+	bio->bi_error = error;
+	bio_endio(bio);
 	return next;
 }
 
···
 	int busy;
 
 	dev_dbg(&dev->core, "%s\n", __func__);
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	spin_lock_irq(&priv->lock);
 	busy = !bio_list_empty(&priv->list);

drivers/block/rbd.c

···
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
-/*
- * a queue callback. Makes sure that we don't create a bio that spans across
- * multiple osd objects. One exception would be with a single page bios,
- * which we handle later at bio_chain_clone_range()
- */
-static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
-			  struct bio_vec *bvec)
-{
-	struct rbd_device *rbd_dev = q->queuedata;
-	sector_t sector_offset;
-	sector_t sectors_per_obj;
-	sector_t obj_sector_offset;
-	int ret;
-
-	/*
-	 * Find how far into its rbd object the partition-relative
-	 * bio start sector is to offset relative to the enclosing
-	 * device.
-	 */
-	sector_offset = get_start_sect(bmd->bi_bdev) + bmd->bi_sector;
-	sectors_per_obj = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT);
-	obj_sector_offset = sector_offset & (sectors_per_obj - 1);
-
-	/*
-	 * Compute the number of bytes from that offset to the end
-	 * of the object.  Account for what's already used by the bio.
-	 */
-	ret = (int) (sectors_per_obj - obj_sector_offset) << SECTOR_SHIFT;
-	if (ret > bmd->bi_size)
-		ret -= bmd->bi_size;
-	else
-		ret = 0;
-
-	/*
-	 * Don't send back more than was asked for.  And if the bio
-	 * was empty, let the whole thing through because:  "Note
-	 * that a block device *must* allow a single page to be
-	 * added to an empty bio."
-	 */
-	rbd_assert(bvec->bv_len <= PAGE_SIZE);
-	if (ret > (int) bvec->bv_len || !bmd->bi_size)
-		ret = (int) bvec->bv_len;
-
-	return ret;
-}
-
 static void rbd_free_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk = rbd_dev->disk;
···
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	q->limits.discard_granularity = segment_size;
 	q->limits.discard_alignment = segment_size;
-	q->limits.max_discard_sectors = segment_size / SECTOR_SIZE;
+	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
 	q->limits.discard_zeroes_data = 1;
 
-	blk_queue_merge_bvec(q, rbd_merge_bvec);
 	disk->queue = q;
 
 	q->queuedata = rbd_dev;

drivers/block/rsxx/dev.c

···
 		if (!card->eeh_state && card->gendisk)
 			disk_stats_complete(card, meta->bio, meta->start_time);
 
-		bio_endio(meta->bio, atomic_read(&meta->error) ? -EIO : 0);
+		if (atomic_read(&meta->error))
+			bio_io_error(meta->bio);
+		else
+			bio_endio(meta->bio);
 		kmem_cache_free(bio_meta_pool, meta);
 	}
 }
···
 	struct rsxx_cardinfo *card = q->queuedata;
 	struct rsxx_bio_meta *bio_meta;
 	int st = -EINVAL;
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	might_sleep();
 
···
 queue_err:
 	kmem_cache_free(bio_meta_pool, bio_meta);
 req_err:
-	bio_endio(bio, st);
+	if (st)
+		bio->bi_error = st;
+	bio_endio(bio);
 }
 
 /*----------------- Device Setup -------------------*/

drivers/block/skd_main.c

···
 	/* DISCARD Flag initialization. */
 	q->limits.discard_granularity = 8192;
 	q->limits.discard_alignment = 0;
-	q->limits.max_discard_sectors = UINT_MAX >> 9;
+	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
 	q->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);

drivers/block/umem.c

···
 				PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
 		if (control & DMASCR_HARD_ERROR) {
 			/* error */
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			dev_printk(KERN_WARNING, &card->dev->dev,
 				"I/O error on sector %d/%d\n",
 				le32_to_cpu(desc->local_addr)>>9,
···
 
 		return_bio = bio->bi_next;
 		bio->bi_next = NULL;
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	}
 }
 
···
 	pr_debug("mm_make_request %llu %u\n",
 		 (unsigned long long)bio->bi_iter.bi_sector,
 		 bio->bi_iter.bi_size);
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;

drivers/block/xen-blkback/blkback.c

···
 /*
  * bio callback.
  */
-static void end_block_io_op(struct bio *bio, int error)
+static void end_block_io_op(struct bio *bio)
 {
-	__end_block_io_op(bio->bi_private, error);
+	__end_block_io_op(bio->bi_private, bio->bi_error);
 	bio_put(bio);
 }
 

drivers/block/xen-blkfront.c

···
 struct split_bio {
 	struct bio *bio;
 	atomic_t pending;
-	int err;
 };
 
 static DEFINE_MUTEX(blkfront_mutex);
···
 	return 0;
 }
 
-static void split_bio_end(struct bio *bio, int error)
+static void split_bio_end(struct bio *bio)
 {
 	struct split_bio *split_bio = bio->bi_private;
 
-	if (error)
-		split_bio->err = error;
-
 	if (atomic_dec_and_test(&split_bio->pending)) {
 		split_bio->bio->bi_phys_segments = 0;
-		bio_endio(split_bio->bio, split_bio->err);
+		split_bio->bio->bi_error = bio->bi_error;
+		bio_endio(split_bio->bio);
 		kfree(split_bio);
 	}
 	bio_put(bio);

drivers/block/zram/zram_drv.c

···
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		zram_bio_discard(zram, index, offset, bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
···
 		update_position(&index, &offset, &bvec);
 	}
 
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 
 out:
···
 
 	if (unlikely(!zram_meta_get(zram)))
 		goto error;
+
+	blk_queue_split(queue, &bio, queue->bio_split);
 
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
···
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
 	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
-	zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
+	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
 	 * size is identical with physical block size(PAGE_SIZE). But if it is

drivers/md/bcache/bcache.h

···
 	DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
 };
 
-struct bio_split_pool {
-	struct bio_set		*bio_split;
-	mempool_t		*bio_split_hook;
-};
-
-struct bio_split_hook {
-	struct closure		cl;
-	struct bio_split_pool	*p;
-	struct bio		*bio;
-	bio_end_io_t		*bi_end_io;
-	void			*bi_private;
-};
-
 struct bcache_device {
 	struct closure		cl;
 
···
 	int (*cache_miss)(struct btree *, struct search *,
 			  struct bio *, unsigned);
 	int (*ioctl) (struct bcache_device *, fmode_t, unsigned, unsigned long);
-
-	struct bio_split_pool	bio_split_hook;
 };
 
 struct io {
···
 	atomic_long_t		meta_sectors_written;
 	atomic_long_t		btree_sectors_written;
 	atomic_long_t		sectors_written;
-
-	struct bio_split_pool	bio_split_hook;
 };
 
 struct gc_stat {
···
 void bch_bbio_free(struct bio *, struct cache_set *);
 struct bio *bch_bbio_alloc(struct cache_set *);
 
-void bch_generic_make_request(struct bio *, struct bio_split_pool *);
 void __bch_submit_bbio(struct bio *, struct cache_set *);
 void bch_submit_bbio(struct bio *, struct cache_set *, struct bkey *, unsigned);
 

drivers/md/bcache/btree.c

···
 	goto out;
 }
 
-static void btree_node_read_endio(struct bio *bio, int error)
+static void btree_node_read_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	closure_put(cl);
···
 	bch_submit_bbio(bio, b->c, &b->key, 0);
 	closure_sync(&cl);
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (bio->bi_error)
 		set_btree_node_io_error(b);
 
 	bch_bbio_free(bio, b->c);
···
 	__btree_node_write_done(cl);
 }
 
-static void btree_node_write_endio(struct bio *bio, int error)
+static void btree_node_write_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct btree *b = container_of(cl, struct btree, io);
 
-	if (error)
+	if (bio->bi_error)
 		set_btree_node_io_error(b);
 
-	bch_bbio_count_io_errors(b->c, bio, error, "writing btree");
+	bch_bbio_count_io_errors(b->c, bio, bio->bi_error, "writing btree");
 	closure_put(cl);
 }
 

drivers/md/bcache/closure.h

···
  * they are running owned by the thread that is running them. Otherwise, suppose
  * you submit some bios and wish to have a function run when they all complete:
  *
- * foo_endio(struct bio *bio, int error)
+ * foo_endio(struct bio *bio)
  * {
  *	closure_put(cl);
  * }

drivers/md/bcache/io.c

···
 
 #include <linux/blkdev.h>
 
-static unsigned bch_bio_max_sectors(struct bio *bio)
-{
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct bio_vec bv;
-	struct bvec_iter iter;
-	unsigned ret = 0, seg = 0;
-
-	if (bio->bi_rw & REQ_DISCARD)
-		return min(bio_sectors(bio), q->limits.max_discard_sectors);
-
-	bio_for_each_segment(bv, bio, iter) {
-		struct bvec_merge_data bvm = {
-			.bi_bdev	= bio->bi_bdev,
-			.bi_sector	= bio->bi_iter.bi_sector,
-			.bi_size	= ret << 9,
-			.bi_rw		= bio->bi_rw,
-		};
-
-		if (seg == min_t(unsigned, BIO_MAX_PAGES,
-				 queue_max_segments(q)))
-			break;
-
-		if (q->merge_bvec_fn &&
-		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
-			break;
-
-		seg++;
-		ret += bv.bv_len >> 9;
-	}
-
-	ret = min(ret, queue_max_sectors(q));
-
-	WARN_ON(!ret);
-	ret = max_t(int, ret, bio_iovec(bio).bv_len >> 9);
-
-	return ret;
-}
-
-static void bch_bio_submit_split_done(struct closure *cl)
-{
-	struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
-
-	s->bio->bi_end_io = s->bi_end_io;
-	s->bio->bi_private = s->bi_private;
-	bio_endio(s->bio, 0);
-
-	closure_debug_destroy(&s->cl);
-	mempool_free(s, s->p->bio_split_hook);
-}
-
-static void bch_bio_submit_split_endio(struct bio *bio, int error)
-{
-	struct closure *cl = bio->bi_private;
-	struct bio_split_hook *s = container_of(cl, struct bio_split_hook, cl);
-
-	if (error)
-		clear_bit(BIO_UPTODATE, &s->bio->bi_flags);
-
-	bio_put(bio);
-	closure_put(cl);
-}
-
-void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
-{
-	struct bio_split_hook *s;
-	struct bio *n;
-
-	if (!bio_has_data(bio) && !(bio->bi_rw & REQ_DISCARD))
-		goto submit;
-
-	if (bio_sectors(bio) <= bch_bio_max_sectors(bio))
-		goto submit;
-
-	s = mempool_alloc(p->bio_split_hook, GFP_NOIO);
-	closure_init(&s->cl, NULL);
-
-	s->bio		= bio;
-	s->p		= p;
-	s->bi_end_io	= bio->bi_end_io;
-	s->bi_private	= bio->bi_private;
-	bio_get(bio);
-
-	do {
-		n = bio_next_split(bio, bch_bio_max_sectors(bio),
-				   GFP_NOIO, s->p->bio_split);
-
-		n->bi_end_io	= bch_bio_submit_split_endio;
-		n->bi_private	= &s->cl;
-
-		closure_get(&s->cl);
-		generic_make_request(n);
-	} while (n != bio);
-
-	continue_at(&s->cl, bch_bio_submit_split_done, NULL);
-	return;
-submit:
-	generic_make_request(bio);
-}
-
 /* Bios with headers */
 
 void bch_bbio_free(struct bio *bio, struct cache_set *c)
···
 	bio->bi_bdev		= PTR_CACHE(c, &b->key, 0)->bdev;
 
 	b->submit_time_us = local_clock_us();
-	closure_bio_submit(bio, bio->bi_private, PTR_CACHE(c, &b->key, 0));
+	closure_bio_submit(bio, bio->bi_private);
 }
 
 void bch_submit_bbio(struct bio *bio, struct cache_set *c,

drivers/md/bcache/journal.c

···
  * bit.
  */
 
-static void journal_read_endio(struct bio *bio, int error)
+static void journal_read_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	closure_put(cl);
···
 		bio->bi_private = &cl;
 		bch_bio_map(bio, data);
 
-		closure_bio_submit(bio, &cl, ca);
+		closure_bio_submit(bio, &cl);
 		closure_sync(&cl);
 
 		/* This function could be simpler now since we no longer write
···
 
 #define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)
 
-static void journal_discard_endio(struct bio *bio, int error)
+static void journal_discard_endio(struct bio *bio)
 {
 	struct journal_device *ja =
 		container_of(bio, struct journal_device, discard_bio);
···
 		pr_debug("journal_pin full (%zu)", fifo_used(&j->pin));
 }
 
-static void journal_write_endio(struct bio *bio, int error)
+static void journal_write_endio(struct bio *bio)
 {
 	struct journal_write *w = bio->bi_private;
 
-	cache_set_err_on(error, w->c, "journal io error");
+	cache_set_err_on(bio->bi_error, w->c, "journal io error");
 	closure_put(&w->c->journal.io);
 }
 
···
 	spin_unlock(&c->journal.lock);
 
 	while ((bio = bio_list_pop(&list)))
-		closure_bio_submit(bio, cl, c->cache[0]);
+		closure_bio_submit(bio, cl);
 
 	continue_at(cl, journal_write_done, NULL);
 }

drivers/md/bcache/movinggc.c

···
 	closure_return_with_destructor(cl, moving_io_destructor);
 }
 
-static void read_moving_endio(struct bio *bio, int error)
+static void read_moving_endio(struct bio *bio)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct moving_io *io = container_of(bio->bi_private,
 					    struct moving_io, cl);
 
-	if (error)
-		io->op.error = error;
+	if (bio->bi_error)
+		io->op.error = bio->bi_error;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(io->op.c, &b->key, 0)) {
 		io->op.error = -EINTR;
 	}
 
-	bch_bbio_endio(io->op.c, bio, error, "reading data to move");
+	bch_bbio_endio(io->op.c, bio, bio->bi_error, "reading data to move");
 }
 
 static void moving_init(struct moving_io *io)

drivers/md/bcache/request.c

···
 	bch_data_insert_keys(cl);
 }
 
-static void bch_data_insert_endio(struct bio *bio, int error)
+static void bch_data_insert_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	if (error) {
+	if (bio->bi_error) {
 		/* TODO: We could try to recover from this. */
 		if (op->writeback)
-			op->error = error;
+			op->error = bio->bi_error;
 		else if (!op->replace)
 			set_closure_fn(cl, bch_data_insert_error, op->wq);
 		else
 			set_closure_fn(cl, NULL, NULL);
 	}
 
-	bch_bbio_endio(op->c, bio, error, "writing data to cache");
+	bch_bbio_endio(op->c, bio, bio->bi_error, "writing data to cache");
 }
 
 static void bch_data_insert_start(struct closure *cl)
···
 	struct data_insert_op	iop;
 };
 
-static void bch_cache_read_endio(struct bio *bio, int error)
+static void bch_cache_read_endio(struct bio *bio)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct closure *cl = bio->bi_private;
···
 	 * from the backing device.
 	 */
 
-	if (error)
-		s->iop.error = error;
+	if (bio->bi_error)
+		s->iop.error = bio->bi_error;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(s->iop.c, &b->key, 0)) {
 		atomic_long_inc(&s->iop.c->cache_read_races);
 		s->iop.error = -EINTR;
 	}
 
-	bch_bbio_endio(s->iop.c, bio, error, "reading from cache");
+	bch_bbio_endio(s->iop.c, bio, bio->bi_error, "reading from cache");
 }
 
 /*
···
 
 /* Common code for the make_request functions */
 
-static void request_endio(struct bio *bio, int error)
+static void request_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 
-	if (error) {
+	if (bio->bi_error) {
 		struct search *s = container_of(cl, struct search, cl);
-		s->iop.error = error;
+		s->iop.error = bio->bi_error;
 		/* Only cache read errors are recoverable */
 		s->recoverable = false;
 	}
···
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
-		bio_endio(s->orig_bio, s->iop.error);
+		s->orig_bio->bi_error = s->iop.error;
+		bio_endio(s->orig_bio);
 		s->orig_bio = NULL;
 	}
 }
···
 
 		/* XXX: invalidate cache */
 
-		closure_bio_submit(bio, cl, s->d);
+		closure_bio_submit(bio, cl);
 	}
 
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
···
 	s->cache_miss	= miss;
 	s->iop.bio	= cache_bio;
 	bio_get(cache_bio);
-	closure_bio_submit(cache_bio, &s->cl, s->d);
+	closure_bio_submit(cache_bio, &s->cl);
 
 	return ret;
 out_put:
···
 out_submit:
 	miss->bi_end_io		= request_endio;
 	miss->bi_private	= &s->cl;
-	closure_bio_submit(miss, &s->cl, s->d);
+	closure_bio_submit(miss, &s->cl);
 	return ret;
 }
 
···
 
 		if (!(bio->bi_rw & REQ_DISCARD) ||
 		    blk_queue_discard(bdev_get_queue(dc->bdev)))
-			closure_bio_submit(bio, cl, s->d);
+			closure_bio_submit(bio, cl);
 	} else if (s->iop.writeback) {
 		bch_writeback_add(dc);
 		s->iop.bio = bio;
···
 			flush->bi_end_io = request_endio;
 			flush->bi_private = cl;
 
-			closure_bio_submit(flush, cl, s->d);
+			closure_bio_submit(flush, cl);
 		}
 	} else {
 		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
 
-		closure_bio_submit(bio, cl, s->d);
+		closure_bio_submit(bio, cl);
 	}
 
 	closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
···
 		bch_journal_meta(s->iop.c, cl);
 
 	/* If it's a flush, we send the flush to the backing device too */
-	closure_bio_submit(bio, cl, s->d);
+	closure_bio_submit(bio, cl);
 
 	continue_at(cl, cached_dev_bio_complete, NULL);
 }
···
 	} else {
 		if ((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
-			bch_generic_make_request(bio, &d->bio_split_hook);
+			generic_make_request(bio);
 	}
 }
 

drivers/md/bcache/super.c

···
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
 
-static void bio_split_pool_free(struct bio_split_pool *p)
-{
-	if (p->bio_split_hook)
-		mempool_destroy(p->bio_split_hook);
-
-	if (p->bio_split)
-		bioset_free(p->bio_split);
-}
-
-static int bio_split_pool_init(struct bio_split_pool *p)
-{
-	p->bio_split = bioset_create(4, 0);
-	if (!p->bio_split)
-		return -ENOMEM;
-
-	p->bio_split_hook = mempool_create_kmalloc_pool(4,
-				sizeof(struct bio_split_hook));
-	if (!p->bio_split_hook)
-		return -ENOMEM;
-
-	return 0;
-}
-
 /* Superblock */
 
 static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
···
 	return err;
 }
 
-static void write_bdev_super_endio(struct bio *bio, int error)
+static void write_bdev_super_endio(struct bio *bio)
 {
 	struct cached_dev *dc = bio->bi_private;
 	/* XXX: error checking */
···
 	closure_return_with_destructor(cl, bch_write_bdev_super_unlock);
 }
 
-static void write_super_endio(struct bio *bio, int error)
+static void write_super_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	bch_count_io_errors(ca, error, "writing superblock");
+	bch_count_io_errors(ca, bio->bi_error, "writing superblock");
 	closure_put(&ca->set->sb_write);
 }
 
···
 
 /* UUID io */
 
-static void uuid_endio(struct bio *bio, int error)
+static void uuid_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
 
-	cache_set_err_on(error, c, "accessing uuids");
+	cache_set_err_on(bio->bi_error, c, "accessing uuids");
 	bch_bbio_free(bio, c);
 	closure_put(cl);
 }
···
  * disk.
  */
 
-static void prio_endio(struct bio *bio, int error)
+static void prio_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	cache_set_err_on(error, ca->set, "accessing priorities");
+	cache_set_err_on(bio->bi_error, ca->set, "accessing priorities");
 	bch_bbio_free(bio, ca->set);
 	closure_put(&ca->prio);
 }
···
 	bio->bi_private = ca;
 	bch_bio_map(bio, ca->disk_buckets);
 
-	closure_bio_submit(bio, &ca->prio, ca);
+	closure_bio_submit(bio, &ca->prio);
 	closure_sync(cl);
 }
 
···
 		put_disk(d->disk);
 	}
 
-	bio_split_pool_free(&d->bio_split_hook);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
 	kvfree(d->full_dirty_stripes);
···
 		return minor;
 
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
-	    bio_split_pool_init(&d->bio_split_hook) ||
 	    !(d->disk = alloc_disk(1))) {
 		ida_simple_remove(&bcache_minor, minor);
 		return -ENOMEM;
···
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
 	q->limits.max_segments		= BIO_MAX_PAGES;
-	q->limits.max_discard_sectors	= UINT_MAX;
+	blk_queue_max_discard_sectors(q, UINT_MAX);
 	q->limits.discard_granularity	= 512;
 	q->limits.io_min		= block_size;
 	q->limits.logical_block_size	= block_size;
···
 		ca->set->cache[ca->sb.nr_this_dev] = NULL;
 	}
 
-	bio_split_pool_free(&ca->bio_split_hook);
-
 	free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca)));
 	kfree(ca->prio_buckets);
 	vfree(ca->buckets);
···
 					  ca->sb.nbuckets)) ||
 	    !(ca->prio_buckets	= kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
 					  2, GFP_KERNEL)) ||
-	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)) ||
-	    bio_split_pool_init(&ca->bio_split_hook))
+	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)))
 		return -ENOMEM;
 
 	ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);

drivers/md/bcache/util.h

···
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/llist.h>
 #include <linux/ratelimit.h>
···
 	return bdev->bd_inode->i_size >> 9;
 }
 
-#define closure_bio_submit(bio, cl, dev)				\
+#define closure_bio_submit(bio, cl)					\
 do {									\
 	closure_get(cl);						\
-	bch_generic_make_request(bio, &(dev)->bio_split_hook);		\
+	generic_make_request(bio);					\
 } while (0)
 
 uint64_t bch_crc64_update(uint64_t, const void *, size_t);

drivers/md/bcache/writeback.c

···
 	closure_return_with_destructor(cl, dirty_io_destructor);
 }
 
-static void dirty_endio(struct bio *bio, int error)
+static void dirty_endio(struct bio *bio)
 {
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
-	if (error)
+	if (bio->bi_error)
 		SET_KEY_DIRTY(&w->key, false);
 
 	closure_put(&io->cl);
···
 	io->bio.bi_bdev		= io->dc->bdev;
 	io->bio.bi_end_io	= dirty_endio;
 
-	closure_bio_submit(&io->bio, cl, &io->dc->disk);
+	closure_bio_submit(&io->bio, cl);
 
 	continue_at(cl, write_dirty_finish, system_wq);
 }
 
-static void read_dirty_endio(struct bio *bio, int error)
+static void read_dirty_endio(struct bio *bio)
 {
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
 	bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
-			    error, "reading dirty data from cache");
+			    bio->bi_error, "reading dirty data from cache");
 
-	dirty_endio(bio, error);
+	dirty_endio(bio);
 }
 
 static void read_dirty_submit(struct closure *cl)
 {
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 
-	closure_bio_submit(&io->bio, cl, &io->dc->disk);
+	closure_bio_submit(&io->bio, cl);
 
 	continue_at(cl, write_dirty, system_wq);
 }

drivers/md/dm-bio-prison.c

···
 	bio_list_init(&bios);
 	dm_cell_release(prison, cell, &bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		bio_endio(bio, error);
+	while ((bio = bio_list_pop(&bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 EXPORT_SYMBOL_GPL(dm_cell_error);
 

drivers/md/dm-bufio.c

···
 {
 	struct dm_buffer *b = context;
 
-	b->bio.bi_end_io(&b->bio, error ? -EIO : 0);
+	b->bio.bi_error = error ? -EIO : 0;
+	b->bio.bi_end_io(&b->bio);
 }
 
 static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
···
 	b->bio.bi_end_io = end_io;
 
 	r = dm_io(&io_req, 1, &region, NULL);
-	if (r)
-		end_io(&b->bio, r);
+	if (r) {
+		b->bio.bi_error = r;
+		end_io(&b->bio);
+	}
 }
 
-static void inline_endio(struct bio *bio, int error)
+static void inline_endio(struct bio *bio)
 {
 	bio_end_io_t *end_fn = bio->bi_private;
+	int error = bio->bi_error;
 
 	/*
 	 * Reset the bio to free any attached resources
···
 	 */
 	bio_reset(bio);
 
-	end_fn(bio, error);
+	bio->bi_error = error;
+	end_fn(bio);
 }
 
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
···
  * Set the error, clear B_WRITING bit and wake anyone who was waiting on
  * it.
  */
-static void write_endio(struct bio *bio, int error)
+static void write_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->write_error = error;
-	if (unlikely(error)) {
+	b->write_error = bio->bi_error;
+	if (unlikely(bio->bi_error)) {
 		struct dm_bufio_client *c = b->c;
+		int error = bio->bi_error;
 		(void)cmpxchg(&c->async_write_error, 0, error);
 	}
 
···
  * The endio routine for reading: set the error, clear the bit and wake up
  * anyone waiting on the buffer.
  */
-static void read_endio(struct bio *bio, int error)
+static void read_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->read_error = error;
+	b->read_error = bio->bi_error;
 
 	BUG_ON(!test_bit(B_READING, &b->state));
 

drivers/md/dm-cache-target.c

···
 	wake_worker(cache);
 }
 
-static void writethrough_endio(struct bio *bio, int err)
+static void writethrough_endio(struct bio *bio)
 {
 	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (err) {
-		bio_endio(bio, err);
+	if (bio->bi_error) {
+		bio_endio(bio);
 		return;
 	}
 
···
 			 * The block was promoted via an overwrite, so it's dirty.
 			 */
 			set_dirty(cache, mg->new_oblock, mg->cblock);
-			bio_endio(mg->new_ocell->holder, 0);
+			bio_endio(mg->new_ocell->holder);
 			cell_defer(cache, mg->new_ocell, false);
 		}
 		free_io_migration(mg);
···
 	}
 }
 
-static void overwrite_endio(struct bio *bio, int err)
+static void overwrite_endio(struct bio *bio)
 {
 	struct dm_cache_migration *mg = bio->bi_private;
 	struct cache *cache = mg->cache;
···
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (err)
+	if (bio->bi_error)
 		mg->err = true;
 
 	mg->requeue_holder = false;
···
 		b = to_dblock(from_dblock(b) + 1);
 	}
 
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	cell_defer(mg->cache, mg->new_ocell, false);
 	free_migration(mg);
 }
···
 
 	calc_discard_block_range(cache, bio, &b, &e);
 	if (b == e) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
···
 	bio_list_merge(&bios, &cache->deferred_bios);
 	bio_list_init(&cache->deferred_bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		bio_endio(bio, DM_ENDIO_REQUEUE);
+	while ((bio = bio_list_pop(&bios))) {
+		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio_endio(bio);
+	}
 }
 
 static int more_work(struct cache *cache)
···
 			 * This is a duplicate writethrough io that is no
 			 * longer needed because the block has been demoted.
 			 */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 			// FIXME: remap everything as a miss
 			cell_defer(cache, cell, false);
 			r = DM_MAPIO_SUBMITTED;
···
 	return r;
 }
 
-/*
- * We assume I/O is going to the origin (which is the volume
- * more likely to have restrictions e.g. by being striped).
- * (Looking up the exact location of the data would be expensive
- * and could always be out of date by the time the bio is submitted.)
- */
-static int cache_bvec_merge(struct dm_target *ti,
-			    struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size)
-{
-	struct cache *cache = ti->private;
-	struct request_queue *q = bdev_get_queue(cache->origin_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = cache->origin_dev->bdev;
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 {
 	/*
···
 	.status = cache_status,
 	.message = cache_message,
 	.iterate_devices = cache_iterate_devices,
-	.merge = cache_bvec_merge,
 	.io_hints = cache_io_hints,
 };
 

drivers/md/dm-crypt.c

···
 	if (io->ctx.req)
 		crypt_free_req(cc, io->ctx.req, base_bio);
 
-	bio_endio(base_bio, error);
+	base_bio->bi_error = error;
+	bio_endio(base_bio);
 }
 
 /*
···
  * The work is done per CPU global for all dm-crypt instances.
  * They should not depend on each other and do not block.
  */
-static void crypt_endio(struct bio *clone, int error)
+static void crypt_endio(struct bio *clone)
 {
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned rw = bio_data_dir(clone);
-
-	if (unlikely(!bio_flagged(clone, BIO_UPTODATE) && !error))
-		error = -EIO;
+	int error;
 
 	/*
 	 * free the processed pages
···
 	if (rw == WRITE)
 		crypt_free_buffer_pages(cc, clone);
 
+	error = clone->bi_error;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
···
 	return -EINVAL;
 }
 
-static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		       struct bio_vec *biovec, int max_size)
-{
-	struct crypt_config *cc = ti->private;
-	struct request_queue *q = bdev_get_queue(cc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = cc->dev->bdev;
-	bvm->bi_sector = cc->start + dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int crypt_iterate_devices(struct dm_target *ti,
 				 iterate_devices_callout_fn fn, void *data)
 {
···
 	.preresume = crypt_preresume,
 	.resume = crypt_resume,
 	.message = crypt_message,
-	.merge  = crypt_merge,
 	.iterate_devices = crypt_iterate_devices,
 };
 

drivers/md/dm-era-target.c

···
 	return fn(ti, era->origin_dev, 0, get_dev_size(era->origin_dev), data);
 }
 
-static int era_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		     struct bio_vec *biovec, int max_size)
-{
-	struct era *era = ti->private;
-	struct request_queue *q = bdev_get_queue(era->origin_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = era->origin_dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void era_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct era *era = ti->private;
···
 	.status = era_status,
 	.message = era_message,
 	.iterate_devices = era_iterate_devices,
-	.merge = era_merge,
 	.io_hints = era_io_hints
 };
 

drivers/md/dm-flakey.c

···
 		 * Drop writes?
 		 */
 		if (test_bit(DROP_WRITES, &fc->flags)) {
-			bio_endio(bio, 0);
+			bio_endio(bio);
 			return DM_MAPIO_SUBMITTED;
 		}
 
···
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int flakey_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct flakey_c *fc = ti->private;
-	struct request_queue *q = bdev_get_queue(fc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = fc->dev->bdev;
-	bvm->bi_sector = flakey_map_sector(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
 {
 	struct flakey_c *fc = ti->private;
···
 	.end_io = flakey_end_io,
 	.status = flakey_status,
 	.ioctl	= flakey_ioctl,
-	.merge	= flakey_merge,
 	.iterate_devices = flakey_iterate_devices,
 };
 

drivers/md/dm-io.c

···
 		complete_io(io);
 }
 
-static void endio(struct bio *bio, int error)
+static void endio(struct bio *bio)
 {
 	struct io *io;
 	unsigned region;
+	int error;
 
-	if (error && bio_data_dir(bio) == READ)
+	if (bio->bi_error && bio_data_dir(bio) == READ)
 		zero_fill_bio(bio);
 
 	/*
···
 	 */
 	retrieve_io_and_region_from_bio(bio, &io, &region);
 
+	error = bio->bi_error;
 	bio_put(bio);
 
 	dec_count(io, region, error);
···
 		if ((rw & REQ_DISCARD) || (rw & REQ_WRITE_SAME))
 			num_bvecs = 1;
 		else
-			num_bvecs = min_t(int, bio_get_nr_vecs(where->bdev),
+			num_bvecs = min_t(int, BIO_MAX_PAGES,
 					  dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
 
 		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);

drivers/md/dm-linear.c

···
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct linear_c *lc = ti->private;
-	struct request_queue *q = bdev_get_queue(lc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = lc->dev->bdev;
-	bvm->bi_sector = linear_map_sector(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int linear_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
···
 	.map    = linear_map,
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
-	.merge  = linear_merge,
 	.iterate_devices = linear_iterate_devices,
 };
 

drivers/md/dm-log-writes.c

···
 	}
 }
 
-static void log_end_io(struct bio *bio, int err)
+static void log_end_io(struct bio *bio)
 {
 	struct log_writes_c *lc = bio->bi_private;
 	struct bio_vec *bvec;
 	int i;
 
-	if (err) {
+	if (bio->bi_error) {
 		unsigned long flags;
 
-		DMERR("Error writing log block, error=%d", err);
+		DMERR("Error writing log block, error=%d", bio->bi_error);
 		spin_lock_irqsave(&lc->blocks_lock, flags);
 		lc->logging_enabled = false;
 		spin_unlock_irqrestore(&lc->blocks_lock, flags);
···
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page) {
···
 	bio->bi_bdev = lc->logdev->bdev;
 	bio->bi_end_io = log_end_io;
 	bio->bi_private = lc;
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 	for (i = 0; i < block->vec_cnt; i++) {
 		/*
···
 			bio->bi_bdev = lc->logdev->bdev;
 			bio->bi_end_io = log_end_io;
 			bio->bi_private = lc;
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 			ret = bio_add_page(bio, block->vecs[i].bv_page,
 					   block->vecs[i].bv_len, 0);
···
 		WARN_ON(flush_bio || fua_bio);
 		if (lc->device_supports_discard)
 			goto map_bio;
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 
···
 	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
-static int log_writes_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size)
-{
-	struct log_writes_c *lc = ti->private;
-	struct request_queue *q = bdev_get_queue(lc->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = lc->dev->bdev;
-	bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int log_writes_iterate_devices(struct dm_target *ti,
 				      iterate_devices_callout_fn fn,
 				      void *data)
···
 	.end_io = normal_end_io,
 	.status = log_writes_status,
 	.ioctl	= log_writes_ioctl,
-	.merge	= log_writes_merge,
 	.message = log_writes_message,
 	.iterate_devices = log_writes_iterate_devices,
 	.io_hints = log_writes_io_hints,

drivers/md/dm-raid.c

···
 	mddev_resume(&rs->md);
 }
 
-static int raid_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct raid_set *rs = ti->private;
-	struct md_personality *pers = rs->md.pers;
-
-	if (pers && pers->mergeable_bvec)
-		return min(max_size, pers->mergeable_bvec(&rs->md, bvm, biovec));
-
-	/*
-	 * In case we can't request the personality because
-	 * the raid set is not running yet
-	 *
-	 * -> return safe minimum
-	 */
-	return rs->md.chunk_sectors;
-}
-
 static struct target_type raid_target = {
 	.name = "raid",
 	.version = {1, 7, 0},
···
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
-	.merge = raid_merge,
 };
 
 static int __init dm_raid_init(void)

drivers/md/dm-raid1.c

···
 		 * If device is suspended, complete the bio.
 		 */
 		if (dm_noflush_suspending(ms->ti))
-			bio_endio(bio, DM_ENDIO_REQUEUE);
+			bio->bi_error = DM_ENDIO_REQUEUE;
 		else
-			bio_endio(bio, -EIO);
+			bio->bi_error = -EIO;
+
+		bio_endio(bio);
 		return;
 	}
 
···
 	bio_set_m(bio, NULL);
 
 	if (likely(!error)) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
···
 
 	DMERR_LIMIT("Read failure on mirror device %s.  Failing I/O.",
 		    m->dev->name);
-	bio_endio(bio, -EIO);
+	bio_io_error(bio);
 }
 
 /* Asynchronous read. */
···
 		if (likely(m))
 			read_async_bio(m, bio);
 		else
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 	}
 }
 
···
 
 static void write_callback(unsigned long error, void *context)
 {
-	unsigned i, ret = 0;
+	unsigned i;
 	struct bio *bio = (struct bio *) context;
 	struct mirror_set *ms;
 	int should_wake = 0;
···
 	 * regions with the same code.
 	 */
 	if (likely(!error)) {
-		bio_endio(bio, ret);
+		bio_endio(bio);
 		return;
 	}
 
···
 	 * degrade the array.
 	 */
 	if (bio->bi_rw & REQ_DISCARD) {
-		bio_endio(bio, -EOPNOTSUPP);
+		bio->bi_error = -EOPNOTSUPP;
+		bio_endio(bio);
 		return;
 	}
 
···
 		 * be wrong if the failed leg returned after reboot and
 		 * got replicated back to the good legs.)
 		 */
-
 		if (unlikely(!get_valid_mirror(ms) || (keep_log(ms) && ms->log_failure)))
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 		else if (errors_handled(ms) && !keep_log(ms))
 			hold_bio(ms, bio);
 		else
-			bio_endio(bio, 0);
+			bio_endio(bio);
 	}
 }
 

drivers/md/dm-snap.c

···
 		error_bios(snapshot_bios);
 	} else {
 		if (full_bio)
-			bio_endio(full_bio, 0);
+			bio_endio(full_bio);
 		flush_bios(snapshot_bios);
 	}
 
···
 	dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe);
 }
 
-static void full_bio_end_io(struct bio *bio, int error)
+static void full_bio_end_io(struct bio *bio)
 {
 	void *callback_data = bio->bi_private;
 
-	dm_kcopyd_do_callback(callback_data, 0, error ? 1 : 0);
+	dm_kcopyd_do_callback(callback_data, 0, bio->bi_error ? 1 : 0);
 }
 
 static void start_full_bio(struct dm_snap_pending_exception *pe,
···
 	}
 }
 
-static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct dm_origin *o = ti->private;
-	struct request_queue *q = bdev_get_queue(o->dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = o->dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int origin_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
···
 	.resume  = origin_resume,
 	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
-	.merge	 = origin_merge,
 	.iterate_devices = origin_iterate_devices,
 };
 

drivers/md/dm-stripe.c

···
 		return DM_MAPIO_REMAPPED;
 	} else {
 		/* The range doesn't map to the target stripe */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 }
···
 	blk_limits_io_opt(limits, chunk_size * sc->stripes);
 }
 
-static int stripe_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct stripe_c *sc = ti->private;
-	sector_t bvm_sector = bvm->bi_sector;
-	uint32_t stripe;
-	struct request_queue *q;
-
-	stripe_map_sector(sc, bvm_sector, &stripe, &bvm_sector);
-
-	q = bdev_get_queue(sc->stripe[stripe].dev->bdev);
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = sc->stripe[stripe].dev->bdev;
-	bvm->bi_sector = sc->stripe[stripe].physical_start + bvm_sector;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static struct target_type stripe_target = {
 	.name   = "striped",
 	.version = {1, 5, 1},
···
 	.status = stripe_status,
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
-	.merge  = stripe_merge,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm-table.c

···
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
 
-	/*
-	 * Check if merge fn is supported.
-	 * If not we'll force DM to use PAGE_SIZE or
-	 * smaller I/O, just to be safe.
-	 */
-	if (dm_queue_merge_is_compulsory(q) && !ti->type->merge)
-		blk_limits_max_hw_sectors(limits,
-					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
 
···
 	return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
 }
 
-static int queue_supports_sg_gaps(struct dm_target *ti, struct dm_dev *dev,
-				  sector_t start, sector_t len, void *data)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return q && !test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags);
-}
-
 static bool dm_table_all_devices_attribute(struct dm_table *t,
 					   iterate_devices_callout_fn func)
 {
···
 		queue_flag_clear_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
 	else
 		queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
-
-	if (dm_table_all_devices_attribute(t, queue_supports_sg_gaps))
-		queue_flag_clear_unlocked(QUEUE_FLAG_SG_GAPS, q);
-	else
-		queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, q);
 
 	dm_table_set_integrity(t);
 

drivers/md/dm-thin.c

···
 {
 	struct bio *bio;
 
-	while ((bio = bio_list_pop(bios)))
-		bio_endio(bio, error);
+	while ((bio = bio_list_pop(bios))) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	}
 }
 
 static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, int error)
···
 	complete_mapping_preparation(m);
 }
 
-static void overwrite_endio(struct bio *bio, int err)
+static void overwrite_endio(struct bio *bio)
 {
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct dm_thin_new_mapping *m = h->overwrite_mapping;
 
 	bio->bi_end_io = m->saved_bi_end_io;
 
-	m->err = err;
+	m->err = bio->bi_error;
 	complete_mapping_preparation(m);
 }
 
···
 	 */
 	if (bio) {
 		inc_remap_and_issue_cell(tc, m->cell, m->data_block);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	} else {
 		inc_all_io_entry(tc->pool, m->cell->holder);
 		remap_and_issue(tc, m->cell->holder, m->data_block);
···
 
 static void process_prepared_discard_success(struct dm_thin_new_mapping *m)
 {
-	bio_endio(m->bio, 0);
+	bio_endio(m->bio);
 	free_discard_mapping(m);
 }
 
···
 		metadata_operation_failed(tc->pool, "dm_thin_remove_range", r);
 		bio_io_error(m->bio);
 	} else
-		bio_endio(m->bio, 0);
+		bio_endio(m->bio);
 
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, tc->pool->mapping_pool);
···
 	 * Even if r is set, there could be sub discards in flight that we
 	 * need to wait for.
 	 */
-	bio_endio(m->bio, r);
+	m->bio->bi_error = r;
+	bio_endio(m->bio);
 	cell_defer_no_holder(tc, m->cell);
 	mempool_free(m, pool->mapping_pool);
 }
···
 {
 	int error = should_error_unserviceable_bio(pool);
 
-	if (error)
-		bio_endio(bio, error);
-	else
+	if (error) {
+		bio->bi_error = error;
+		bio_endio(bio);
+	} else
 		retry_on_resume(bio);
 }
 
···
 	 * will prevent completion until the sub range discards have
 	 * completed.
 	 */
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_discard_bio(struct thin_c *tc, struct bio *bio)
···
 		/*
 		 * The discard covers less than a block.
 		 */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
···
 	if (bio_data_dir(bio) == READ) {
 		zero_fill_bio(bio);
 		cell_defer_no_holder(tc, cell);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
···
 
 			} else {
 				zero_fill_bio(bio);
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			}
 		} else
 			provision_block(tc, bio, block, cell);
···
 		}
 
 		zero_fill_bio(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		break;
 
 	default:
···
 
 static void process_bio_success(struct thin_c *tc, struct bio *bio)
 {
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static void process_bio_fail(struct thin_c *tc, struct bio *bio)
···
 	thin_hook_bio(tc, bio);
 
 	if (tc->requeue_mode) {
-		bio_endio(bio, DM_ENDIO_REQUEUE);
+		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
 	}
 
···
 	return fn(ti, pt->data_dev, 0, ti->len, data);
 }
 
-static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct pool_c *pt = ti->private;
-	struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = pt->data_dev->bdev;
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct pool_c *pt = ti->private;
···
 	.resume = pool_resume,
 	.message = pool_message,
 	.status = pool_status,
-	.merge = pool_merge,
 	.iterate_devices = pool_iterate_devices,
 	.io_hints = pool_io_hints,
 };
···
 	DMEMIT("Error");
 }
 
-static int thin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-		      struct bio_vec *biovec, int max_size)
-{
-	struct thin_c *tc = ti->private;
-	struct request_queue *q = bdev_get_queue(tc->pool_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = tc->pool_dev->bdev;
-	bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
-}
-
 static int thin_iterate_devices(struct dm_target *ti,
 				iterate_devices_callout_fn fn, void *data)
 {
···
 	.presuspend = thin_presuspend,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
-	.merge = thin_merge,
 	.iterate_devices = thin_iterate_devices,
 	.io_hints = thin_io_hints,
 };

drivers/md/dm-verity.c

···
 
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_private = io->orig_bi_private;
+	bio->bi_error = error;
 
-	bio_endio(bio, error);
+	bio_endio(bio);
 }
 
 static void verity_work(struct work_struct *w)
···
 	verity_finish_io(io, verity_verify_io(io));
 }
 
-static void verity_end_io(struct bio *bio, int error)
+static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
 
-	if (error) {
-		verity_finish_io(io, error);
+	if (bio->bi_error) {
+		verity_finish_io(io, bio->bi_error);
 		return;
 	}
 
···
 
 	return r ? : __blkdev_driver_ioctl(v->data_dev->bdev, v->data_dev->mode,
 				     cmd, arg);
-}
-
-static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
-			struct bio_vec *biovec, int max_size)
-{
-	struct dm_verity *v = ti->private;
-	struct request_queue *q = bdev_get_queue(v->data_dev->bdev);
-
-	if (!q->merge_bvec_fn)
-		return max_size;
-
-	bvm->bi_bdev = v->data_dev->bdev;
-	bvm->bi_sector = verity_map_sector(v, bvm->bi_sector);
-
-	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
 static int verity_iterate_devices(struct dm_target *ti,
···
 	.map		= verity_map,
 	.status		= verity_status,
 	.ioctl		= verity_ioctl,
-	.merge		= verity_merge,
 	.iterate_devices = verity_iterate_devices,
 	.io_hints	= verity_io_hints,
 };

drivers/md/dm-zero.c

···
 		break;
 	}
 
-	bio_endio(bio, 0);
+	bio_endio(bio);
 
 	/* accepted bio, don't make new request */
 	return DM_MAPIO_SUBMITTED;

drivers/md/dm.c

···
 #define DMF_FREEING 3
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_MERGE_IS_OPTIONAL 6
-#define DMF_DEFERRED_REMOVE 7
-#define DMF_SUSPENDED_INTERNALLY 8
+#define DMF_DEFERRED_REMOVE 6
+#define DMF_SUSPENDED_INTERNALLY 7
 
 /*
  * A dummy definition to make RCU happy.
···
 		} else {
 			/* done with normal IO or empty flush */
 			trace_block_bio_complete(md->queue, bio, io_error);
-			bio_endio(bio, io_error);
+			bio->bi_error = io_error;
+			bio_endio(bio);
 		}
 	}
 }
···
 	limits->max_write_same_sectors = 0;
 }
 
-static void clone_endio(struct bio *bio, int error)
+static void clone_endio(struct bio *bio)
 {
+	int error = bio->bi_error;
 	int r = error;
 	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
-
-	if (!bio_flagged(bio, BIO_UPTODATE) && !error)
-		error = -EIO;
 
 	if (endio) {
 		r = endio(tio->ti, bio, error);
···
 /*
  * Partial completion handling for request-based dm
  */
-static void end_clone_bio(struct bio *clone, int error)
+static void end_clone_bio(struct bio *clone)
 {
 	struct dm_rq_clone_bio_info *info =
 		container_of(clone, struct dm_rq_clone_bio_info, clone);
···
 		 * the remainder.
 		 */
 		return;
-	else if (error) {
+	else if (bio->bi_error) {
 		/*
 		 * Don't notice the error to the upper layer yet.
 		 * The error handling decision is made by the target driver,
 		 * when the request is completed.
 		 */
-		tio->error = error;
+		tio->error = bio->bi_error;
 		return;
 	}
 
···
  * CRUD END
  *---------------------------------------------------------------*/
 
-static int dm_merge_bvec(struct request_queue *q,
-			 struct bvec_merge_data *bvm,
-			 struct bio_vec *biovec)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_table *map = dm_get_live_table_fast(md);
-	struct dm_target *ti;
-	sector_t max_sectors;
-	int max_size = 0;
-
-	if (unlikely(!map))
-		goto out;
-
-	ti = dm_table_find_target(map, bvm->bi_sector);
-	if (!dm_target_is_valid(ti))
-		goto out;
-
-	/*
-	 * Find maximum amount of I/O that won't need splitting
-	 */
-	max_sectors = min(max_io_len(bvm->bi_sector, ti),
-			  (sector_t) BIO_MAX_SECTORS);
-	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-	if (max_size < 0)
-		max_size = 0;
-
-	/*
-	 * merge_bvec_fn() returns number of bytes
-	 * it can accept at this offset
-	 * max is precomputed maximal io size
-	 */
-	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, max_size);
-	/*
-	 * If the target doesn't support merge method and some of the devices
-	 * provided their merge_bvec method (we know this by looking at
-	 * queue_max_hw_sectors), then we can't allow bios with multiple vector
-	 * entries.  So always set max_size to 0, and the code below allows
-	 * just one page.
-	 */
-	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
-		max_size = 0;
-
-out:
-	dm_put_live_table_fast(md);
-	/*
-	 * Always allow an entire first page
-	 */
-	if (max_size <= biovec->bv_len && !(bvm->bi_size >> SECTOR_SHIFT))
-		max_size = biovec->bv_len;
-
-	return max_size;
-}
-
 /*
  * The request function that just remaps the bio built up by
  * dm_merge_bvec.
···
 	struct dm_table *map;
 
 	map = dm_get_live_table(md, &srcu_idx);
+
+	blk_queue_split(q, &bio, q->bio_split);
 
 	generic_start_io_acct(rw, bio_sectors(bio), &dm_disk(md)->part0);
 
···
 }
 
 /*
- * Return 1 if the queue has a compulsory merge_bvec_fn function.
- *
- * If this function returns 0, then the device is either a non-dm
- * device without a merge_bvec_fn, or it is a dm device that is
- * able to split any bios it receives that are too big.
- */
-int dm_queue_merge_is_compulsory(struct request_queue *q)
-{
-	struct mapped_device *dev_md;
-
-	if (!q->merge_bvec_fn)
-		return 0;
-
-	if (q->make_request_fn == dm_make_request) {
-		dev_md = q->queuedata;
-		if (test_bit(DMF_MERGE_IS_OPTIONAL, &dev_md->flags))
-			return 0;
-	}
-
-	return 1;
-}
-
-static int dm_device_merge_is_compulsory(struct dm_target *ti,
-					 struct dm_dev *dev, sector_t start,
-					 sector_t len, void *data)
-{
-	struct block_device *bdev = dev->bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return dm_queue_merge_is_compulsory(q);
-}
-
-/*
- * Return 1 if it is acceptable to ignore merge_bvec_fn based
- * on the properties of the underlying devices.
- */
-static int dm_table_merge_is_optional(struct dm_table *table)
-{
-	unsigned i = 0;
-	struct dm_target *ti;
-
-	while (i < dm_table_get_num_targets(table)) {
-		ti = dm_table_get_target(table, i++);
-
-		if (ti->type->iterate_devices &&
-		    ti->type->iterate_devices(ti, dm_device_merge_is_compulsory, NULL))
-			return 0;
-	}
-
-	return 1;
-}
-
-/*
  * Returns old map, which caller must destroy.
  */
 static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
···
 	struct dm_table *old_map;
 	struct request_queue *q = md->queue;
 	sector_t size;
-	int merge_is_optional;
 
 	size = dm_table_get_size(t);
 
···
 
 	__bind_mempools(md, t);
 
-	merge_is_optional = dm_table_merge_is_optional(t);
-
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, t);
 	md->immutable_target_type = dm_table_get_immutable_target_type(t);
 
 	dm_table_set_restrictions(t, q, limits);
-	if (merge_is_optional)
-		set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
-	else
-		clear_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
 	if (old_map)
 		dm_sync_table(md);
 
···
 	case DM_TYPE_BIO_BASED:
 		dm_init_old_md_queue(md);
 		blk_queue_make_request(md->queue, dm_make_request);
-		blk_queue_merge_bvec(md->queue, dm_merge_bvec);
 		break;
 	}
 

drivers/md/dm.h

···
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
 
-int dm_queue_merge_is_compulsory(struct request_queue *q);
-
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
 void dm_set_md_type(struct mapped_device *md, unsigned type);

drivers/md/faulty.c

···
 #include <linux/seq_file.h>
 
 
-static void faulty_fail(struct bio *bio, int error)
+static void faulty_fail(struct bio *bio)
 {
 	struct bio *b = bio->bi_private;
 
···
 			/* special case - don't decrement, don't generic_make_request,
 			 * just fail immediately
 			 */
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 			return;
 		}
 

drivers/md/linear.c

···
 	return conf->disks + lo;
 }
 
-/**
- *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
- *	@q: request queue
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can take at this offset
- */
-static int linear_mergeable_bvec(struct mddev *mddev,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct dev_info *dev0;
-	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int maxbytes = biovec->bv_len;
-	struct request_queue *subq;
-
-	dev0 = which_dev(mddev, sector);
-	maxsectors = dev0->end_sector - sector;
-	subq = bdev_get_queue(dev0->rdev->bdev);
-	if (subq->merge_bvec_fn) {
-		bvm->bi_bdev = dev0->rdev->bdev;
-		bvm->bi_sector -= dev0->end_sector - dev0->rdev->sectors;
-		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
-							     biovec));
-	}
-
-	if (maxsectors < bio_sectors)
-		maxsectors = 0;
-	else
-		maxsectors -= bio_sectors;
-
-	if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
-		return maxbytes;
-
-	if (maxsectors > (maxbytes >> 9))
-		return maxbytes;
-	else
-		return maxsectors << 9;
-}
-
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
···
 		if (unlikely((split->bi_rw & REQ_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
-			bio_endio(split, 0);
+			bio_endio(split);
 		} else
 			generic_make_request(split);
 	} while (split != bio);
···
 	.size		= linear_size,
 	.quiesce	= linear_quiesce,
 	.congested	= linear_congested,
-	.mergeable_bvec	= linear_mergeable_bvec,
 };
 
 static int __init linear_init (void)

drivers/md/md.c

···
 	unsigned int sectors;
 	int cpu;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (mddev == NULL || mddev->pers == NULL
 	    || !mddev->ready) {
 		bio_io_error(bio);
 		return;
 	}
 	if (mddev->ro == 1 && unlikely(rw == WRITE)) {
-		bio_endio(bio, bio_sectors(bio) == 0 ? 0 : -EROFS);
+		if (bio_sectors(bio) != 0)
+			bio->bi_error = -EROFS;
+		bio_endio(bio);
 		return;
 	}
 	smp_rmb(); /* Ensure implications of  'active' are visible */
···
 	return mddev_congested(mddev, bits);
 }
 
-static int md_mergeable_bvec(struct request_queue *q,
-			     struct bvec_merge_data *bvm,
-			     struct bio_vec *biovec)
-{
-	struct mddev *mddev = q->queuedata;
-	int ret;
-	rcu_read_lock();
-	if (mddev->suspended) {
-		/* Must always allow one vec */
-		if (bvm->bi_size == 0)
-			ret = biovec->bv_len;
-		else
-			ret = 0;
-	} else {
-		struct md_personality *pers = mddev->pers;
-		if (pers && pers->mergeable_bvec)
-			ret = pers->mergeable_bvec(mddev, bvm, biovec);
-		else
-			ret = biovec->bv_len;
-	}
-	rcu_read_unlock();
-	return ret;
-}
 /*
  * Generic flush handling for md
  */
 
-static void md_end_flush(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
···
 
 	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	else {
 		bio->bi_rw &= ~REQ_FLUSH;
 		mddev->pers->make_request(mddev, bio);
···
 }
 EXPORT_SYMBOL_GPL(md_rdev_clear);
 
-static void super_written(struct bio *bio, int error)
+static void super_written(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
 
-	if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
-		printk("md: super_written gets error=%d, uptodate=%d\n",
-		       error, test_bit(BIO_UPTODATE, &bio->bi_flags));
-		WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
+	if (bio->bi_error) {
+		printk("md: super_written gets error=%d\n", bio->bi_error);
 		md_error(mddev, rdev);
 	}
 
···
 	bio_add_page(bio, page, size, 0);
 	submit_bio_wait(rw, bio);
 
-	ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	ret = !bio->bi_error;
 	bio_put(bio);
 	return ret;
 }
···
 	if (mddev->queue) {
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = md_congested;
-		blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
···
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->private = NULL;
-	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.default_space = 0;
···
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */

drivers/md/md.h

···
 	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
 				 * bitmap-based recovery to get fully in sync
 				 */
-	Unmerged,		/* device is being added to array and should
-				 * be considerred for bvec_merge_fn but not
-				 * yet for actual IO
-				 */
 	WriteMostly,		/* Avoid reading if at all possible */
 	AutoDetected,		/* added by auto-detect */
 	Blocked,		/* An error occurred but has not yet
···
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
-	int				merge_check_needed; /* at least one
-							     * member device
-							     * has a
-							     * merge_bvec_fn */
 
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
···
 	/* congested implements bdi.congested_fn().
 	 * Will not be called while array is 'suspended' */
 	int (*congested)(struct mddev *mddev, int bits);
-	/* mergeable_bvec is use to implement ->merge_bvec_fn */
-	int (*mergeable_bvec)(struct mddev *mddev,
-			      struct bvec_merge_data *bvm,
-			      struct bio_vec *biovec);
 };
 
 struct md_sysfs_entry {

drivers/md/multipath.c

···
 	struct bio *bio = mp_bh->master_bio;
 	struct mpconf *conf = mp_bh->mddev->private;
 
-	bio_endio(bio, err);
+	bio->bi_error = err;
+	bio_endio(bio);
 	mempool_free(mp_bh, conf->pool);
 }
 
-static void multipath_end_request(struct bio *bio, int error)
+static void multipath_end_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct multipath_bh *mp_bh = bio->bi_private;
 	struct mpconf *conf = mp_bh->mddev->private;
 	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
 
-	if (uptodate)
+	if (!bio->bi_error)
 		multipath_end_bh_io(mp_bh, 0);
 	else if (!(bio->bi_rw & REQ_RAHEAD)) {
 		/*
···
 		       (unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
-		multipath_end_bh_io(mp_bh, error);
+		multipath_end_bh_io(mp_bh, bio->bi_error);
 	rdev_dec_pending(rdev, conf->mddev);
 }
 
···
 
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		mempool_free(mp_bh, conf->pool);
 		return;
 	}
···
 			q = rdev->bdev->bd_disk->queue;
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
-
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit ->max_segments to one, lying
-		 * within a single page.
-		 * (Note: it is very unlikely that a device with
-		 * merge_bvec_fn will be involved in multipath.)
-		 */
-			if (q->merge_bvec_fn) {
-				blk_queue_max_segments(mddev->queue, 1);
-				blk_queue_segment_boundary(mddev->queue,
-							   PAGE_CACHE_SIZE - 1);
-			}
 
 			spin_lock_irq(&conf->device_lock);
 			mddev->degraded--;
···
 		disk->rdev = rdev;
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
-
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, not that we ever expect a device with
-		 * a merge_bvec_fn to be involved in multipath */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
 
 		if (!test_bit(Faulty, &rdev->flags))
 			working_disks++;

drivers/md/raid0.c

···
 			disk_stack_limits(mddev->gendisk, rdev1->bdev,
 					  rdev1->data_offset << 9);
 
-		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
-			conf->has_merge_bvec = 1;
-
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
···
 			     + sector_div(sector, zone->nb_dev)];
 }
 
-/**
- *	raid0_mergeable_bvec -- tell bio layer if two requests can be merged
- *	@mddev: the md device
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- */
-static int raid0_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	struct r0conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	sector_t sector_offset = sector;
-	int max;
-	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct strip_zone *zone;
-	struct md_rdev *rdev;
-	struct request_queue *subq;
-
-	if (is_power_of_2(chunk_sectors))
-		max =  (chunk_sectors - ((sector & (chunk_sectors-1))
-						+ bio_sectors)) << 9;
-	else
-		max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
-						+ bio_sectors)) << 9;
-	if (max < 0)
-		max = 0; /* bio_add cannot handle a negative return */
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	if (max < biovec->bv_len)
-		/* too small already, no need to check further */
-		return max;
-	if (!conf->has_merge_bvec)
-		return max;
-
-	/* May need to check subordinate device */
-	sector = sector_offset;
-	zone = find_zone(mddev->private, &sector_offset);
-	rdev = map_sector(mddev, zone, sector, &sector_offset);
-	subq = bdev_get_queue(rdev->bdev);
-	if (subq->merge_bvec_fn) {
-		bvm->bi_bdev = rdev->bdev;
-		bvm->bi_sector = sector_offset + zone->dev_start +
-			rdev->data_offset;
-		return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
-	} else
-		return max;
-}
-
 static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
 	sector_t array_sectors = 0;
···
 		if (unlikely((split->bi_rw & REQ_DISCARD) &&
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
-			bio_endio(split, 0);
+			bio_endio(split);
 		} else
 			generic_make_request(split);
 	} while (split != bio);
···
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
 	.congested	= raid0_congested,
-	.mergeable_bvec	= raid0_mergeable_bvec,
 };
 
 static int __init raid0_init (void)

drivers/md/raid0.h

···
 	struct md_rdev		**devlist; /* lists of rdevs, pointed to
 					    * by strip_zone->dev */
 	int			nr_strip_zones;
-	int			has_merge_bvec;	/* at least one member has
-						 * a merge_bvec_fn */
 };
 
 #endif

drivers/md/raid1.c

···
 		done = 1;
 
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
+
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
···
 	return mirror;
 }
 
-static void raid1_end_read_request(struct bio *bio, int error)
+static void raid1_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror;
 	struct r1conf *conf = r1_bio->mddev->private;
···
 	}
 }
 
-static void raid1_end_write_request(struct bio *bio, int error)
+static void raid1_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	struct r1conf *conf = r1_bio->mddev->private;
···
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		set_bit(WriteErrorSeen,
 			&conf->mirrors[mirror].rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
···
 		rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (r1_bio->bios[disk] == IO_BLOCKED
 		    || rdev == NULL
-		    || test_bit(Unmerged, &rdev->flags)
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
···
 	return best_disk;
 }
 
-static int raid1_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	struct r1conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		int disk;
-		rcu_read_lock();
-		for (disk = 0; disk < conf->raid_disks * 2; disk++) {
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = sector +
-						rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-
-}
-
 static int raid1_congested(struct mddev *mddev, int bits)
 {
 	struct r1conf *conf = mddev->private;
···
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
···
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
···
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
···
 			break;
 		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)
-		    || test_bit(Unmerged, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
 				set_bit(R1BIO_Degraded, &r1_bio->state);
 			continue;
···
 	struct raid1_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
-
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
 
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
···
 			rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
 			break;
 		}
-	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
 	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
···
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r1bio *r1_bio = bio->bi_private;
 
···
 	 * or re-read if the read failed.
 	 * We don't do much here, just schedule handling by raid1d
 	 */
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 	if (atomic_dec_and_test(&r1_bio->remaining))
 		reschedule_retry(r1_bio);
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
···
 		idx ++;
 	}
 	set_bit(R1BIO_Uptodate, &r1_bio->state);
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio->bi_error = 0;
 	return 1;
 }
 
···
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		int size;
-		int uptodate;
+		int error;
 		struct bio *b = r1_bio->bios[i];
 		if (b->bi_end_io != end_sync_read)
 			continue;
-		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
-		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+		/* fixup the bio for reuse, but preserve errno */
+		error = b->bi_error;
 		bio_reset(b);
-		if (!uptodate)
-			clear_bit(BIO_UPTODATE, &b->bi_flags);
+		b->bi_error = error;
 		b->bi_vcnt = vcnt;
 		b->bi_iter.bi_size = r1_bio->sectors << 9;
 		b->bi_iter.bi_sector = r1_bio->sector +
···
 	}
 	for (primary = 0; primary < conf->raid_disks * 2; primary++)
 		if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
-		    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+		    !r1_bio->bios[primary]->bi_error) {
 			r1_bio->bios[primary]->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
 			break;
···
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
-		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
+		int error = sbio->bi_error;
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
-		/* Now we can 'fixup' the BIO_UPTODATE flag */
-		set_bit(BIO_UPTODATE, &sbio->bi_flags);
+		/* Now we can 'fixup' the error value */
+		sbio->bi_error = 0;
 
-		if (uptodate) {
+		if (!error) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
···
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && uptodate)) {
+			      && !error)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
···
 		struct bio *bio = r1_bio->bios[m];
 		if (bio->bi_end_io == NULL)
 			continue;
-		if (test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (!bio->bi_error &&
 		    test_bit(R1BIO_MadeGood, &r1_bio->state)) {
 			rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
 		}
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (bio->bi_error &&
 		    test_bit(R1BIO_WriteError, &r1_bio->state)) {
 			if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
 				md_error(conf->mddev, rdev);
···
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_iter.bi_size -= len;
-						__clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+						bio_clear_flag(bio, BIO_SEG_VALID);
 					}
 					goto bio_full;
 				}
···
 			goto abort;
 		disk->rdev = rdev;
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 
 		disk->head_position = 0;
 		disk->seq_start = MaxSector;
···
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
 	.congested	= raid1_congested,
-	.mergeable_bvec	= raid1_mergeable_bvec,
 };
 
 static int __init raid_init(void)

drivers/md/raid10.c

···
 static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 				int *skipped);
 static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
-static void end_reshape_write(struct bio *bio, int error);
+static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
···
 	} else
 		done = 1;
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
···
 	return r10_bio->devs[slot].devnum;
 }
 
-static void raid10_end_read_request(struct bio *bio, int error)
+static void raid10_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r10bio *r10_bio = bio->bi_private;
 	int slot, dev;
 	struct md_rdev *rdev;
···
 	}
 }
 
-static void raid10_end_write_request(struct bio *bio, int error)
+static void raid10_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	int dev;
 	int dec_rdev = 1;
···
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
···
 	return (vchunk << geo->chunk_shift) + offset;
 }
 
-/**
- *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- *	@mddev: the md device
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- *	This requires checking for end-of-chunk if near_copies != raid_disks,
- *	and for subordinate merge_bvec_fns if merge_check_needed.
- */
-static int raid10_mergeable_bvec(struct mddev *mddev,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct r10conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct geom *geo = &conf->geo;
-
-	chunk_sectors = (conf->geo.chunk_mask & conf->prev.chunk_mask) + 1;
-	if (conf->reshape_progress != MaxSector &&
-	    ((sector >= conf->reshape_progress) !=
-	     conf->mddev->reshape_backwards))
-		geo = &conf->prev;
-
-	if (geo->near_copies < geo->raid_disks) {
-		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
-					+ bio_sectors)) << 9;
-		if (max < 0)
-			/* bio_add cannot handle a negative return */
-			max = 0;
-		if (max <= biovec->bv_len && bio_sectors == 0)
-			return biovec->bv_len;
-	} else
-		max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		struct {
-			struct r10bio r10_bio;
-			struct r10dev devs[conf->copies];
-		} on_stack;
-		struct r10bio *r10_bio = &on_stack.r10_bio;
-		int s;
-		if (conf->reshape_progress != MaxSector) {
-			/* Cannot give any guidance during reshape */
-			if (max <= biovec->bv_len && bio_sectors == 0)
-				return biovec->bv_len;
-			return 0;
-		}
-		r10_bio->sector = sector;
-		raid10_find_phys(conf, r10_bio);
-		rcu_read_lock();
-		for (s = 0; s < conf->copies; s++) {
-			int disk = r10_bio->devs[s].devnum;
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-			rdev = rcu_dereference(conf->mirrors[disk].replacement);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-}
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
···
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (rdev == NULL ||
-		    test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags))
+		    test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
···
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
···
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
···
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
···
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rdev && (test_bit(Faulty, &rdev->flags)
-			     || test_bit(Unmerged, &rdev->flags)))
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
-		if (rrdev && (test_bit(Faulty, &rrdev->flags)
-			      || test_bit(Unmerged, &rrdev->flags)))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
···
 	int mirror;
 	int first = 0;
 	int last = conf->geo.raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
···
 
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
-
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
 
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
···
 			conf->fullsync = 1;
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
-	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
 	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
···
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r10bio *r10_bio = bio->bi_private;
 	struct r10conf *conf = r10_bio->mddev->private;
···
 	} else
 		d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 	else
 		/* The write handler will notice the lack of
···
 	}
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
···
 	else
 		rdev = conf->mirrors[d].rdev;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			md_error(mddev, rdev);
 		else {
···
 
 	/* find the first device with a block */
 	for (i=0; i<conf->copies; i++)
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
+		if (!r10_bio->devs[i].bio->bi_error)
 			break;
 
 	if (i == conf->copies)
···
 			continue;
 		if (i == first)
 			continue;
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
+		if (!r10_bio->devs[i].bio->bi_error) {
 			/* We know that the bi_io_vec layout is the same for
 			 * both 'first' and 'i', so we just compare them.
 			 * All vec entries are PAGE_SIZE;
···
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
-			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
···
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
-			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
···
 			rdev = conf->mirrors[dev].rdev;
 			if (r10_bio->devs[m].bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].bio->bi_flags)) {
+			if (!r10_bio->devs[m].bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
···
 			rdev = conf->mirrors[dev].replacement;
 			if (r10_bio->devs[m].repl_bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].repl_bio->bi_flags)) {
+
+			if (!r10_bio->devs[m].repl_bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
···
 					r10_bio->devs[m].addr,
 					r10_bio->sectors, 0);
 				rdev_dec_pending(rdev, conf->mddev);
-			} else if (bio != NULL &&
-				   !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+			} else if (bio != NULL && bio->bi_error) {
 				if (!narrow_write_error(r10_bio, m)) {
 					md_error(conf->mddev, rdev);
 					set_bit(R10BIO_Degraded,
···
 
 			bio = r10_bio->devs[i].bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
 				continue;
···
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
 			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
···
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
···
 
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct(bio->bi_bdev, nr_sectors);
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = 0;
 			generic_make_request(bio);
 		}
 	}
···
 			disk->rdev = rdev;
 		}
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 		diff = (rdev->new_data_offset - rdev->data_offset);
 		if (!mddev->reshape_backwards)
 			diff = -diff;
···
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	__set_bit(BIO_UPTODATE, &read_bio->bi_flags);
+	read_bio->bi_error = 0;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
···
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
···
 	return 0;
 }
 
-static void end_reshape_write(struct bio *bio, int error)
+static void end_reshape_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
···
 		rdev = conf->mirrors[d].rdev;
 	}
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		/* FIXME should record badblock */
 		md_error(mddev, rdev);
 	}
···
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
 	.congested	= raid10_congested,
-	.mergeable_bvec	= raid10_mergeable_bvec,
 };
 
 static int __init raid_init(void)

drivers/md/raid5.c

···
 		bi->bi_iter.bi_size = 0;
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 		bi = return_bi;
 	}
 }
···
 }
 
 static void
-raid5_end_read_request(struct bio *bi, int error);
+raid5_end_read_request(struct bio *bi);
 static void
-raid5_end_write_request(struct bio *bi, int error);
+raid5_end_write_request(struct bio *bi);
 
 static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 {
···
 	conf->slab_cache = NULL;
 }
 
-static void raid5_end_read_request(struct bio * bi, int error)
+static void raid5_end_read_request(struct bio * bi)
 {
 	struct stripe_head *sh = bi->bi_private;
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev = NULL;
 	sector_t s;
···
 		if (bi == &sh->dev[i].req)
 			break;
 
-	pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n",
+	pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		uptodate);
+		bi->bi_error);
 	if (i == disks) {
 		BUG();
 		return;
···
 		s = sh->sector + rdev->new_data_offset;
 	else
 		s = sh->sector + rdev->data_offset;
-	if (uptodate) {
+	if (!bi->bi_error) {
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			/* Note that this cannot happen on a
···
 	release_stripe(sh);
 }
 
-static void raid5_end_write_request(struct bio *bi, int error)
+static void raid5_end_write_request(struct bio *bi)
 {
 	struct stripe_head *sh = bi->bi_private;
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *uninitialized_var(rdev);
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	sector_t first_bad;
 	int bad_sectors;
 	int replacement = 0;
···
 			break;
 		}
 	}
-	pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n",
+	pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		uptodate);
+		bi->bi_error);
 	if (i == disks) {
 		BUG();
 		return;
 	}
 
 	if (replacement) {
-		if (!uptodate)
+		if (bi->bi_error)
 			md_error(conf->mddev, rdev);
 		else if (is_badblock(rdev, sh->sector,
 				     STRIPE_SECTORS,
 				     &first_bad, &bad_sectors))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
-		if (!uptodate) {
+		if (bi->bi_error) {
 			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
···
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (sh->batch_head && !uptodate && !replacement)
+	if (sh->batch_head && bi->bi_error && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
···
 		while (bi && bi->bi_iter.bi_sector <
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+			bi->bi_error = -EIO;
 			if (!raid5_dec_bi_active_stripes(bi)) {
 				md_write_end(conf->mddev);
 				bi->bi_next = *return_bi;
···
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+			bi->bi_error = -EIO;
 			if (!raid5_dec_bi_active_stripes(bi)) {
 				md_write_end(conf->mddev);
 				bi->bi_next = *return_bi;
···
 			       sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
-				clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+				bi->bi_error = -EIO;
 				if (!raid5_dec_bi_active_stripes(bi)) {
 					bi->bi_next = *return_bi;
 					*return_bi = bi;
···
 	return 0;
 }
 
-/* We want read requests to align with chunks where possible,
- * but write requests don't need to.
- */
-static int raid5_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-
-	/*
-	 * always allow writes to be mergeable, read as well if array
-	 * is degraded as we'll go through stripe cache anyway.
-	 */
-	if ((bvm->bi_rw & 1) == WRITE || mddev->degraded)
-		return biovec->bv_len;
-
-	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
-		chunk_sectors = mddev->new_chunk_sectors;
-	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
-	if (max < 0) max = 0;
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	else
-		return max;
-}
-
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
···
  *  first).
  *  If the read failed..
  */
-static void raid5_align_endio(struct bio *bi, int error)
+static void raid5_align_endio(struct bio *bi)
 {
 	struct bio* raid_bi  = bi->bi_private;
 	struct mddev *mddev;
 	struct r5conf *conf;
-	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 	struct md_rdev *rdev;
+	int error = bi->bi_error;
 
 	bio_put(bi);
 
···
 
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (!error && uptodate) {
+	if (!error) {
 		trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
 					 raid_bi, 0);
-		bio_endio(raid_bi, 0);
+		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
 		return;
···
 	add_bio_to_retry(raid_bi, conf);
 }
 
-static int bio_fits_rdev(struct bio *bi)
-{
-	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
-
-	if (bio_sectors(bi) > queue_max_sectors(q))
-		return 0;
-	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > queue_max_segments(q))
-		return 0;
-
-	if (q->merge_bvec_fn)
-		/* it's too hard to apply the merge_bvec_fn at this stage,
-		 * just just give up
-		 */
-		return 0;
-
-	return 1;
-}
-
-static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
+static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct r5conf *conf = mddev->private;
 	int dd_idx;
···
 	sector_t end_sector;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
-		pr_debug("chunk_aligned_read : non aligned\n");
+		pr_debug("%s: non aligned\n", __func__);
 		return 0;
 	}
 	/*
···
 		rcu_read_unlock();
 		raid_bio->bi_next = (void*)rdev;
 		align_bi->bi_bdev =  rdev->bdev;
-		__clear_bit(BIO_SEG_VALID, &align_bi->bi_flags);
+		bio_clear_flag(align_bi, BIO_SEG_VALID);
 
-		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_iter.bi_sector,
+		if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
 				bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
-			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
 			rdev_dec_pending(rdev, mddev);
 			return 0;
···
 		bio_put(align_bi);
 		return 0;
 	}
+}
+
+static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
+{
+	struct bio *split;
+
+	do {
+		sector_t sector = raid_bio->bi_iter.bi_sector;
+		unsigned chunk_sects = mddev->chunk_sectors;
+		unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+
+		if (sectors < bio_sectors(raid_bio)) {
+			split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
+			bio_chain(split, raid_bio);
+		} else
+			split = raid_bio;
+
+		if (!raid5_read_one_chunk(mddev, split)) {
+			if (split != raid_bio)
+				generic_make_request(raid_bio);
+			return split;
+		}
+	} while (split != raid_bio);
+
+	return NULL;
 }
 
 /* __get_priority_stripe - get the next stripe to process
···
 	remaining = raid5_dec_bi_active_stripes(bi);
 	if (remaining == 0) {
 		md_write_end(mddev);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
···
 	 * data on failed drives.
 	 */
 	if (rw == READ && mddev->degraded == 0 &&
-	     mddev->reshape_position == MaxSector &&
-	     chunk_aligned_read(mddev,bi))
-		return;
+	    mddev->reshape_position == MaxSector) {
+		bi = chunk_aligned_read(mddev, bi);
+		if (!bi)
+			return;
+	}
 
 	if (unlikely(bi->bi_rw & REQ_DISCARD)) {
 		make_discard_request(mddev, bi);
···
 			release_stripe_plug(mddev, sh);
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
-			clear_bit(BIO_UPTODATE, &bi->bi_flags);
+			bi->bi_error = -EIO;
 			break;
 		}
 	}
···
 
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
···
 	if (remaining == 0) {
 		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
 					 raid_bio, 0);
-		bio_endio(raid_bio, 0);
+		bio_endio(raid_bio);
 	}
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_quiescent);
···
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 static struct md_personality raid5_personality =
 {
···
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static struct md_personality raid4_personality =
···
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static int __init raid5_init(void)

drivers/mmc/card/queue.c

···
 		return;
 
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
-	q->limits.max_discard_sectors = max_discard;
+	blk_queue_max_discard_sectors(q, max_discard);
 	if (card->erased_byte == 0 && !mmc_can_discard(card))
 		q->limits.discard_zeroes_data = 1;
 	q->limits.discard_granularity = card->pref_erase << 9;

drivers/mtd/mtd_blkdevs.c

···
 
 	if (tr->discard) {
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, new->rq);
-		new->rq->limits.max_discard_sectors = UINT_MAX;
+		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
 	}
 
 	gd->queue = new->rq;

drivers/nvdimm/blk.c

···
 	 * another kernel subsystem, and we just pass it through.
 	 */
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		err = -EIO;
+		bio->bi_error = -EIO;
 		goto out;
 	}
 
···
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
+			bio->bi_error = err;
 			break;
 		}
 	}
···
 		nd_iostat_end(bio, start);
 
  out:
-	bio_endio(bio, err);
+	bio_endio(bio);
 }
 
 static int nd_blk_rw_bytes(struct nd_namespace_common *ndns,

drivers/nvdimm/btt.c

···
 	 * another kernel subsystem, and we just pass it through.
 	 */
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		err = -EIO;
+		bio->bi_error = -EIO;
 		goto out;
 	}
 
···
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
+			bio->bi_error = err;
 			break;
 		}
 	}
···
 		nd_iostat_end(bio, start);
 
 out:
-	bio_endio(bio, err);
+	bio_endio(bio);
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,

drivers/nvdimm/pmem.c

···
 	if (bio_data_dir(bio))
 		wmb_pmem();
 
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,

drivers/s390/block/dcssblk.c

···
 	unsigned long source_addr;
 	unsigned long bytes_done;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	bytes_done = 0;
 	dev_info = bio->bi_bdev->bd_disk->private_data;
 	if (dev_info == NULL)
···
 		}
 		bytes_done += bvec.bv_len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 fail:
 	bio_io_error(bio);

drivers/s390/block/xpram.c

···
 	unsigned long page_addr;
 	unsigned long bytes;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if ((bio->bi_iter.bi_sector & 7) != 0 ||
 	    (bio->bi_iter.bi_size & 4095) != 0)
 		/* Request is not page-aligned. */
···
 			index++;
 		}
 	}
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 fail:
 	bio_io_error(bio);

drivers/scsi/sd.c

···
 	switch (mode) {
 
 	case SD_LBP_DISABLE:
-		q->limits.max_discard_sectors = 0;
+		blk_queue_max_discard_sectors(q, 0);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
 
···
 		break;
 	}
 
-	q->limits.max_discard_sectors = max_blocks * (logical_block_size >> 9);
+	blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9));
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 

drivers/staging/lustre/lustre/llite/lloop.c

···
 	int rw = bio_rw(old_bio);
 	int inactive;
 
+	blk_queue_split(q, &old_bio, q->bio_split);
+
 	if (!lo)
 		goto err;
 
···
 	while (bio) {
 		struct bio *tmp = bio->bi_next;
 		bio->bi_next = NULL;
-		bio_endio(bio, ret);
+		bio->bi_error = ret;
+		bio_endio(bio);
 		bio = tmp;
 	}
 }

drivers/target/target_core_iblock.c

···
 	kfree(ibr);
 }
 
-static void iblock_bio_done(struct bio *bio, int err)
+static void iblock_bio_done(struct bio *bio)
 {
 	struct se_cmd *cmd = bio->bi_private;
 	struct iblock_req *ibr = cmd->priv;
 
-	/*
-	 * Set -EIO if !BIO_UPTODATE and the passed is still err=0
-	 */
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags) && !err)
-		err = -EIO;
-
-	if (err != 0) {
-		pr_err("test_bit(BIO_UPTODATE) failed for bio: %p,"
-			" err: %d\n", bio, err);
+	if (bio->bi_error) {
+		pr_err("bio error: %p,  err: %d\n", bio, bio->bi_error);
 		/*
 		 * Bump the ib_bio_err_cnt and release bio.
 		 */
···
 	blk_finish_plug(&plug);
 }
 
-static void iblock_end_io_flush(struct bio *bio, int err)
+static void iblock_end_io_flush(struct bio *bio)
 {
 	struct se_cmd *cmd = bio->bi_private;
 
-	if (err)
-		pr_err("IBLOCK: cache flush failed: %d\n", err);
+	if (bio->bi_error)
+		pr_err("IBLOCK: cache flush failed: %d\n", bio->bi_error);
 
 	if (cmd) {
-		if (err)
+		if (bio->bi_error)
 			target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION);
 		else
 			target_complete_cmd(cmd, SAM_STAT_GOOD);

drivers/target/target_core_pscsi.c

···
 	return bl;
 }
 
-static void pscsi_bi_endio(struct bio *bio, int error)
+static void pscsi_bi_endio(struct bio *bio)
 {
 	bio_put(bio);
 }
···
 	while (*hbio) {
 		bio = *hbio;
 		*hbio = (*hbio)->bi_next;
-		bio_endio(bio, 0);	/* XXX: should be error */
+		bio_endio(bio);
 	}
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
···
 	while (hbio) {
 		struct bio *bio = hbio;
 		hbio = hbio->bi_next;
-		bio_endio(bio, 0);	/* XXX: should be error */
+		bio_endio(bio);
 	}
 	ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 fail:

fs/btrfs/check-integrity.c

···
 		struct btrfsic_state *state,
 		struct btrfsic_block *const block,
 		struct btrfs_super_block *const super_hdr);
-static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status);
+static void btrfsic_bio_end_io(struct bio *bp);
 static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate);
 static int btrfsic_is_block_ref_by_superblock(const struct btrfsic_state *state,
 					      const struct btrfsic_block *block,
···
 	goto again;
 }
 
-static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status)
+static void btrfsic_bio_end_io(struct bio *bp)
 {
 	struct btrfsic_block *block = (struct btrfsic_block *)bp->bi_private;
 	int iodone_w_error;
···
 	/* mutex is not held! This is not save if IO is not yet completed
 	 * on umount */
 	iodone_w_error = 0;
-	if (bio_error_status)
+	if (bp->bi_error)
 		iodone_w_error = 1;
 
 	BUG_ON(NULL == block);
···
 		     BTRFSIC_PRINT_MASK_END_IO_BIO_BH))
 			printk(KERN_INFO
 			       "bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n",
-			       bio_error_status,
+			       bp->bi_error,
 			       btrfsic_get_block_type(dev_state->state, block),
 			       block->logical_bytenr, dev_state->name,
 			       block->dev_bytenr, block->mirror_num);
···
 		block = next_block;
 	} while (NULL != block);
 
-	bp->bi_end_io(bp, bio_error_status);
+	bp->bi_end_io(bp);
 }
 
 static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate)

fs/btrfs/compression.c

···
 static struct bio *compressed_bio_alloc(struct block_device *bdev,
 					u64 first_byte, gfp_t gfp_flags)
 {
-	int nr_vecs;
-
-	nr_vecs = bio_get_nr_vecs(bdev);
-	return btrfs_bio_alloc(bdev, first_byte >> 9, nr_vecs, gfp_flags);
+	return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags);
 }
 
 static int check_compressed_csum(struct inode *inode,
···
  * The compressed pages are freed here, and it must be run
  * in process context
  */
-static void end_compressed_bio_read(struct bio *bio, int err)
+static void end_compressed_bio_read(struct bio *bio)
 {
 	struct compressed_bio *cb = bio->bi_private;
 	struct inode *inode;
···
 	unsigned long index;
 	int ret;
 
-	if (err)
+	if (bio->bi_error)
 		cb->errors = 1;
 
 	/* if there are more bios still pending for this compressed
···
 		bio_for_each_segment_all(bvec, cb->orig_bio, i)
 			SetPageChecked(bvec->bv_page);
 
-		bio_endio(cb->orig_bio, 0);
+		bio_endio(cb->orig_bio);
 	}
 
 	/* finally free the cb struct */
···
  * This also calls the writeback end hooks for the file pages so that
  * metadata and checksums can be updated in the file.
  */
-static void end_compressed_bio_write(struct bio *bio, int err)
+static void end_compressed_bio_write(struct bio *bio)
 {
 	struct extent_io_tree *tree;
 	struct compressed_bio *cb = bio->bi_private;
···
 	struct page *page;
 	unsigned long index;
 
-	if (err)
+	if (bio->bi_error)
 		cb->errors = 1;
 
 	/* if there are more bios still pending for this compressed
···
 					 cb->start,
 					 cb->start + cb->len - 1,
 					 NULL,
-					 err ? 0 : 1);
+					 bio->bi_error ? 0 : 1);
 	cb->compressed_pages[0]->mapping = NULL;
 
 	end_compressed_writeback(inode, cb);
···
 
 			ret = btrfs_map_bio(root, READ, comp_bio,
 					    mirror_num, 0);
-			if (ret)
-				bio_endio(comp_bio, ret);
+			if (ret) {
+				bio->bi_error = ret;
+				bio_endio(comp_bio);
+			}
 
 			bio_put(comp_bio);
 
···
 	}
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
-	if (ret)
-		bio_endio(comp_bio, ret);
+	if (ret) {
+		bio->bi_error = ret;
+		bio_endio(comp_bio);
+	}
 
 	bio_put(comp_bio);
 	return 0;

fs/btrfs/disk-io.c

···
 	return -EIO;	/* we fixed nothing */
 }
 
-static void end_workqueue_bio(struct bio *bio, int err)
+static void end_workqueue_bio(struct bio *bio)
 {
 	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
···
 	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
-	end_io_wq->error = err;
+	end_io_wq->error = bio->bi_error;
 
 	if (bio->bi_rw & REQ_WRITE) {
 		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
···
 
 	/* If an error occured we just want to clean up the bio and move on */
 	if (async->error) {
-		bio_endio(async->bio, async->error);
+		async->bio->bi_error = async->error;
+		bio_endio(async->bio);
 		return;
 	}
 
···
 	 * submission context.  Just jump into btrfs_map_bio
 	 */
 	ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
-	if (ret)
-		bio_endio(bio, ret);
+	if (ret) {
+		bio->bi_error = ret;
+		bio_endio(bio);
+	}
 	return ret;
 }
 
···
 					  __btree_submit_bio_done);
 	}
 
-	if (ret) {
+	if (ret)
+		goto out_w_error;
+	return 0;
+
 out_w_error:
-		bio_endio(bio, ret);
-	}
+	bio->bi_error = ret;
+	bio_endio(bio);
 	return ret;
 }
 
···
 {
 	struct bio *bio;
 	struct btrfs_end_io_wq *end_io_wq;
-	int error;
 
 	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
 	bio = end_io_wq->bio;
 
-	error = end_io_wq->error;
+	bio->bi_error = end_io_wq->error;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
 	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
-	bio_endio(bio, error);
+	bio_endio(bio);
 }
 
 static int cleaner_kthread(void *arg)
···
  * endio for the write_dev_flush, this will wake anyone waiting
  * for the barrier when it is done
  */
-static void btrfs_end_empty_barrier(struct bio *bio, int err)
+static void btrfs_end_empty_barrier(struct bio *bio)
 {
-	if (err)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	if (bio->bi_private)
 		complete(bio->bi_private);
 	bio_put(bio);
···
 
 		wait_for_completion(&device->flush_wait);
 
-		if (!bio_flagged(bio, BIO_UPTODATE)) {
-			ret = -EIO;
+		if (bio->bi_error) {
+			ret = bio->bi_error;
 			btrfs_dev_stat_inc_and_print(device,
 				BTRFS_DEV_STAT_FLUSH_ERRS);
 		}

fs/btrfs/extent_io.c

···
  * Scheduling is not allowed, so the extent state tree is expected
  * to have one and only one object corresponding to this IO.
  */
-static void end_bio_extent_writepage(struct bio *bio, int err)
+static void end_bio_extent_writepage(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	u64 start;
···
 		start = page_offset(page);
 		end = start + bvec->bv_offset + bvec->bv_len - 1;
 
-		if (end_extent_writepage(page, err, start, end))
+		if (end_extent_writepage(page, bio->bi_error, start, end))
 			continue;
 
 		end_page_writeback(page);
···
  * Scheduling is not allowed, so the extent state tree is expected
  * to have one and only one object corresponding to this IO.
  */
-static void end_bio_extent_readpage(struct bio *bio, int err)
+static void end_bio_extent_readpage(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	struct extent_io_tree *tree;
 	u64 offset = 0;
···
 	int ret;
 	int i;
 
-	if (err)
-		uptodate = 0;
-
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
 
 		pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
-			 "mirror=%u\n", (u64)bio->bi_iter.bi_sector, err,
-			 io_bio->mirror_num);
+			 "mirror=%u\n", (u64)bio->bi_iter.bi_sector,
+			 bio->bi_error, io_bio->mirror_num);
 		tree = &BTRFS_I(inode)->io_tree;
 
 		/* We always issue full-page reads, but if some block
···
 
 		if (tree->ops && tree->ops->readpage_io_failed_hook) {
 			ret = tree->ops->readpage_io_failed_hook(page, mirror);
-			if (!ret && !err &&
-			    test_bit(BIO_UPTODATE, &bio->bi_flags))
+			if (!ret && !bio->bi_error)
 				uptodate = 1;
 		} else {
 			/*
···
 			ret = bio_readpage_error(bio, offset, page, start, end,
 						 mirror);
 			if (ret == 0) {
-				uptodate =
-					test_bit(BIO_UPTODATE, &bio->bi_flags);
-				if (err)
-					uptodate = 0;
+				uptodate = !bio->bi_error;
 				offset += len;
 				continue;
 			}
···
 		endio_readpage_release_extent(tree, extent_start, extent_len,
 					      uptodate);
 	if (io_bio->end_io)
-		io_bio->end_io(io_bio, err);
+		io_bio->end_io(io_bio, bio->bi_error);
 	bio_put(bio);
 }
 
···
 {
 	int ret = 0;
 	struct bio *bio;
-	int nr;
 	int contig = 0;
-	int this_compressed = bio_flags & EXTENT_BIO_COMPRESSED;
 	int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
 	size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE);
 
···
 			return 0;
 		}
 	}
-	if (this_compressed)
-		nr = BIO_MAX_PAGES;
-	else
-		nr = bio_get_nr_vecs(bdev);
 
-	bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+	bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES,
+			GFP_NOFS | __GFP_HIGH);
 	if (!bio)
 		return -ENOMEM;
 
···
 	}
 }
 
-static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
+static void end_bio_extent_buffer_writepage(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	struct extent_buffer *eb;
···
 		BUG_ON(!eb);
 		done = atomic_dec_and_test(&eb->io_pages);
 
-		if (err || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
+		if (bio->bi_error ||
+		    test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
 			ClearPageUptodate(page);
 			set_btree_ioerr(page);
 		}

fs/btrfs/inode.c

···
 	int ret;
 
 	ret = btrfs_map_bio(root, rw, bio, mirror_num, 1);
-	if (ret)
-		bio_endio(bio, ret);
+	if (ret) {
+		bio->bi_error = ret;
+		bio_endio(bio);
+	}
 	return ret;
 }
 
···
 	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
 
 out:
-	if (ret < 0)
-		bio_endio(bio, ret);
+	if (ret < 0) {
+		bio->bi_error = ret;
+		bio_endio(bio);
+	}
 	return ret;
 }
 
···
 	int uptodate;
 };
 
-static void btrfs_retry_endio_nocsum(struct bio *bio, int err)
+static void btrfs_retry_endio_nocsum(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct bio_vec *bvec;
 	int i;
 
-	if (err)
+	if (bio->bi_error)
 		goto end;
 
 	done->uptodate = 1;
···
 	return 0;
 }
 
-static void btrfs_retry_endio(struct bio *bio, int err)
+static void btrfs_retry_endio(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
···
 	int ret;
 	int i;
 
-	if (err)
+	if (bio->bi_error)
 		goto end;
 
 	uptodate = 1;
···
 	}
 }
 
-static void btrfs_endio_direct_read(struct bio *bio, int err)
+static void btrfs_endio_direct_read(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
 	struct inode *inode = dip->inode;
 	struct bio *dio_bio;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	int err = bio->bi_error;
 
 	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
 		err = btrfs_subio_endio_read(inode, io_bio, err);
···
 
 	kfree(dip);
 
-	/* If we had a csum failure make sure to clear the uptodate flag */
-	if (err)
-		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
-	dio_end_io(dio_bio, err);
+	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
 		io_bio->end_io(io_bio, err);
 	bio_put(bio);
 }
 
-static void btrfs_endio_direct_write(struct bio *bio, int err)
+static void btrfs_endio_direct_write(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
 	struct inode *inode = dip->inode;
···
 again:
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
-						   ordered_bytes, !err);
+						   ordered_bytes,
+						   !bio->bi_error);
 	if (!ret)
 		goto out_test;
 
···
 
 	kfree(dip);
 
-	/* If we had an error make sure to clear the uptodate flag */
-	if (err)
-		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
-	dio_end_io(dio_bio, err);
+	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
 
···
 	return 0;
 }
 
-static void btrfs_end_dio_bio(struct bio *bio, int err)
+static void btrfs_end_dio_bio(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
+	int err = bio->bi_error;
 
 	if (err)
 		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
···
 	if (dip->errors) {
 		bio_io_error(dip->orig_bio);
 	} else {
-		set_bit(BIO_UPTODATE, &dip->dio_bio->bi_flags);
-		bio_endio(dip->orig_bio, 0);
+		dip->dio_bio->bi_error = 0;
+		bio_endio(dip->orig_bio);
 	}
 out:
 	bio_put(bio);
···
 static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 				       u64 first_sector, gfp_t gfp_flags)
 {
-	int nr_vecs = bio_get_nr_vecs(bdev);
-	return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
+	return btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
 }
 
 static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
···
 	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
 	if (io_bio && dip) {
-		bio_endio(io_bio, ret);
+		io_bio->bi_error = -EIO;
+		bio_endio(io_bio);
 		/*
 		 * The end io callbacks free our dip, do the final put on io_bio
 		 * and all the cleanup and final put for dio_bio (through
···
 			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
 			      file_offset + dio_bio->bi_iter.bi_size - 1);
 		}
-		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
+		dio_bio->bi_error = -EIO;
 		/*
 		 * Releases and cleans up our dio_bio, no need to bio_put()
 		 * nor bio_endio()/bio_io_error() against dio_bio.

fs/btrfs/raid56.c

···
  * this frees the rbio and runs through all the bios in the
  * bio_list and calls end_io on them
  */
-static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate)
+static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err)
 {
 	struct bio *cur = bio_list_get(&rbio->bio_list);
 	struct bio *next;
···
 	while (cur) {
 		next = cur->bi_next;
 		cur->bi_next = NULL;
-		if (uptodate)
-			set_bit(BIO_UPTODATE, &cur->bi_flags);
-		bio_endio(cur, err);
+		cur->bi_error = err;
+		bio_endio(cur);
 		cur = next;
 	}
 }
···
  * end io function used by finish_rmw.  When we finally
  * get here, we've written a full stripe
  */
-static void raid_write_end_io(struct bio *bio, int err)
+static void raid_write_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
+	int err = bio->bi_error;
 
 	if (err)
 		fail_bio_stripe(rbio, bio);
···
 	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
 		err = -EIO;
 
-	rbio_orig_end_io(rbio, err, 0);
+	rbio_orig_end_io(rbio, err);
 	return;
 }
 
···
 		 * devices or if they are not contiguous
 		 */
 		if (last_end == disk_start && stripe->dev->bdev &&
-		    test_bit(BIO_UPTODATE, &last->bi_flags) &&
+		    !last->bi_error &&
 		    last->bi_bdev == stripe->dev->bdev) {
 			ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0);
 			if (ret == PAGE_CACHE_SIZE)
···
 	bio->bi_iter.bi_size = 0;
 	bio->bi_bdev = stripe->dev->bdev;
 	bio->bi_iter.bi_sector = disk_start >> 9;
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
 
 	bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
 	bio_list_add(bio_list, bio);
···
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
 		submit_bio(WRITE, bio);
 	}
 	return;
 
 cleanup:
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 }
 
 /*
···
  * This will usually kick off finish_rmw once all the bios are read in, but it
  * may trigger parity reconstruction if we had any errors along the way
  */
-static void raid_rmw_end_io(struct bio *bio, int err)
+static void raid_rmw_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 
-	if (err)
+	if (bio->bi_error)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
···
 	if (!atomic_dec_and_test(&rbio->stripes_pending))
 		return;
 
-	err = 0;
 	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
 		goto cleanup;
 
···
 
 cleanup:
 
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 }
 
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
···
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
 		submit_bio(READ, bio);
 	}
 	/* the actual write will happen once the reads are done */
 	return 0;
 
 cleanup:
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 	return -EIO;
 
 finish:
···
 		else
 			clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
 
-		rbio_orig_end_io(rbio, err, err == 0);
+		rbio_orig_end_io(rbio, err);
 	} else if (err == 0) {
 		rbio->faila = -1;
 		rbio->failb = -1;
···
 		else
 			BUG();
 	} else {
-		rbio_orig_end_io(rbio, err, 0);
+		rbio_orig_end_io(rbio, err);
 	}
 }
 
···
  * This is called only for stripes we've read from disk to
  * reconstruct the parity.
  */
-static void raid_recover_end_io(struct bio *bio, int err)
+static void raid_recover_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 
···
 	 * we only read stripe pages off the disk, set them
 	 * up to date if there were no errors
 	 */
-	if (err)
+	if (bio->bi_error)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
···
 		return;
 
 	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
-		rbio_orig_end_io(rbio, -EIO, 0);
+		rbio_orig_end_io(rbio, -EIO);
 	else
 		__raid_recover_end_io(rbio);
 }
···
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
 		submit_bio(READ, bio);
 	}
 out:
···
 
 cleanup:
 	if (rbio->operation == BTRFS_RBIO_READ_REBUILD)
-		rbio_orig_end_io(rbio, -EIO, 0);
+		rbio_orig_end_io(rbio, -EIO);
 	return -EIO;
 }
 
···
  * end io function used by finish_rmw.  When we finally
  * get here, we've written a full stripe
  */
-static void raid_write_parity_end_io(struct bio *bio, int err)
+static void raid_write_parity_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
+	int err = bio->bi_error;
 
-	if (err)
+	if (bio->bi_error)
 		fail_bio_stripe(rbio, bio);
 
 	bio_put(bio);
···
 	if (atomic_read(&rbio->error))
 		err = -EIO;
 
-	rbio_orig_end_io(rbio, err, 0);
+	rbio_orig_end_io(rbio, err);
 }
 
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
···
 	nr_data = bio_list_size(&bio_list);
 	if (!nr_data) {
 		/* Every parity is right */
-		rbio_orig_end_io(rbio, 0, 0);
+		rbio_orig_end_io(rbio, 0);
 		return;
 	}
 
···
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_parity_end_io;
-		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
 		submit_bio(WRITE, bio);
 	}
 	return;
 
 cleanup:
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 }
 
 static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe)
···
 	return;
 
 cleanup:
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 }
 
 /*
···
  * This will usually kick off finish_rmw once all the bios are read in, but it
  * may trigger parity reconstruction if we had any errors along the way
  */
-static void raid56_parity_scrub_end_io(struct bio *bio, int err)
+static void raid56_parity_scrub_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 
-	if (err)
+	if (bio->bi_error)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
···
 		btrfs_bio_wq_end_io(rbio->fs_info, bio,
 				    BTRFS_WQ_ENDIO_RAID56);
 
-		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
 		submit_bio(READ, bio);
 	}
 	/* the actual write will happen once the reads are done */
 	return;
 
 cleanup:
-	rbio_orig_end_io(rbio, -EIO, 0);
+	rbio_orig_end_io(rbio, -EIO);
 	return;
 
 finish:

fs/btrfs/scrub.c

···
 		       u64 physical, struct btrfs_device *dev, u64 flags,
 		       u64 gen, int mirror_num, u8 *csum, int force,
 		       u64 physical_for_dev_replace);
-static void scrub_bio_end_io(struct bio *bio, int err);
+static void scrub_bio_end_io(struct bio *bio);
 static void scrub_bio_end_io_worker(struct btrfs_work *work);
 static void scrub_block_complete(struct scrub_block *sblock);
 static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
···
 static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 				    struct scrub_page *spage);
 static void scrub_wr_submit(struct scrub_ctx *sctx);
-static void scrub_wr_bio_end_io(struct bio *bio, int err);
+static void scrub_wr_bio_end_io(struct bio *bio);
 static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
 static int write_page_nocow(struct scrub_ctx *sctx,
 			    u64 physical_for_dev_replace, struct page *page);
···
 	struct scrub_ctx *sctx;
 	int		i;
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
-	int pages_per_rd_bio;
 	int ret;
 
-	/*
-	 * the setting of pages_per_rd_bio is correct for scrub but might
-	 * be wrong for the dev_replace code where we might read from
-	 * different devices in the initial huge bios. However, that
-	 * code is able to correctly handle the case when adding a page
-	 * to a bio fails.
-	 */
-	if (dev->bdev)
-		pages_per_rd_bio = min_t(int, SCRUB_PAGES_PER_RD_BIO,
-					 bio_get_nr_vecs(dev->bdev));
-	else
-		pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
 	sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
 	if (!sctx)
 		goto nomem;
 	atomic_set(&sctx->refs, 1);
 	sctx->is_dev_replace = is_dev_replace;
-	sctx->pages_per_rd_bio = pages_per_rd_bio;
+	sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
 	sctx->curr = -1;
 	sctx->dev_root = dev->dev_root;
 	for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
···
 	int error;
 };
 
-static void scrub_bio_wait_endio(struct bio *bio, int error)
+static void scrub_bio_wait_endio(struct bio *bio)
 {
 	struct scrub_bio_ret *ret = bio->bi_private;
 
-	ret->error = error;
+	ret->error = bio->bi_error;
 	complete(&ret->event);
 }
 
···
 	btrfsic_submit_bio(WRITE, sbio->bio);
 }
 
-static void scrub_wr_bio_end_io(struct bio *bio, int err)
+static void scrub_wr_bio_end_io(struct bio *bio)
 {
 	struct scrub_bio *sbio = bio->bi_private;
 	struct btrfs_fs_info *fs_info = sbio->dev->dev_root->fs_info;
 
-	sbio->err = err;
+	sbio->err = bio->bi_error;
 	sbio->bio = bio;
 
 	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
···
 		 */
 		printk_ratelimited(KERN_WARNING
 			"BTRFS: scrub_submit(bio bdev == NULL) is unexpected!\n");
-		bio_endio(sbio->bio, -EIO);
+		bio_io_error(sbio->bio);
 	} else {
 		btrfsic_submit_bio(READ, sbio->bio);
 	}
···
 	return 0;
 }
 
-static void scrub_bio_end_io(struct bio *bio, int err)
+static void scrub_bio_end_io(struct bio *bio)
 {
 	struct scrub_bio *sbio = bio->bi_private;
 	struct btrfs_fs_info *fs_info = sbio->dev->dev_root->fs_info;
 
-	sbio->err = err;
+	sbio->err = bio->bi_error;
 	sbio->bio = bio;
 
 	btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
···
 	scrub_pending_bio_dec(sctx);
 }
 
-static void scrub_parity_bio_endio(struct bio *bio, int error)
+static void scrub_parity_bio_endio(struct bio *bio)
 {
 	struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private;
 
-	if (error)
+	if (bio->bi_error)
 		bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 			  sparity->nsectors);
 
···
 		return 0;
 
 	WARN_ON(!dev->bdev);
-	wr_ctx->pages_per_wr_bio = min_t(int, SCRUB_PAGES_PER_WR_BIO,
-					 bio_get_nr_vecs(dev->bdev));
+	wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
 	wr_ctx->tgtdev = dev;
 	atomic_set(&wr_ctx->flush_all_writes, 0);
 	return 0;

fs/btrfs/volumes.c

···
 	return 0;
 }
 
-static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
+static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio)
 {
 	bio->bi_private = bbio->private;
 	bio->bi_end_io = bbio->end_io;
-	bio_endio(bio, err);
+	bio_endio(bio);
 
 	btrfs_put_bbio(bbio);
 }
 
-static void btrfs_end_bio(struct bio *bio, int err)
+static void btrfs_end_bio(struct bio *bio)
 {
 	struct btrfs_bio *bbio = bio->bi_private;
 	int is_orig_bio = 0;
 
-	if (err) {
+	if (bio->bi_error) {
 		atomic_inc(&bbio->error);
-		if (err == -EIO || err == -EREMOTEIO) {
+		if (bio->bi_error == -EIO || bio->bi_error == -EREMOTEIO) {
 			unsigned int stripe_index =
 				btrfs_io_bio(bio)->stripe_index;
 			struct btrfs_device *dev;
···
 		 * beyond the tolerance of the btrfs bio
 		 */
 		if (atomic_read(&bbio->error) > bbio->max_errors) {
-			err = -EIO;
+			bio->bi_error = -EIO;
 		} else {
 			/*
 			 * this bio is actually up to date, we didn't
 			 * go over the max number of errors
 			 */
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
-			err = 0;
+			bio->bi_error = 0;
 		}
 
-		btrfs_end_bbio(bbio, bio, err);
+		btrfs_end_bbio(bbio, bio);
 	} else if (!is_orig_bio) {
 		bio_put(bio);
 	}
···
 	struct btrfs_pending_bios *pending_bios;
 
 	if (device->missing || !device->bdev) {
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 		return;
 	}
 
···
 				 &device->work);
 }
 
-static int bio_size_ok(struct block_device *bdev, struct bio *bio,
-		       sector_t sector)
-{
-	struct bio_vec *prev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int max_sectors = queue_max_sectors(q);
-	struct bvec_merge_data bvm = {
-		.bi_bdev = bdev,
-		.bi_sector = sector,
-		.bi_rw = bio->bi_rw,
-	};
-
-	if (WARN_ON(bio->bi_vcnt == 0))
-		return 1;
-
-	prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
-	if (bio_sectors(bio) > max_sectors)
-		return 0;
-
-	if (!q->merge_bvec_fn)
-		return 1;
-
-	bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len;
-	if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
-		return 0;
-	return 1;
-}
-
 static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 			      struct bio *bio, u64 physical, int dev_nr,
 			      int rw, int async)
···
 		btrfsic_submit_bio(rw, bio);
 }
 
-static int breakup_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
-			      struct bio *first_bio, struct btrfs_device *dev,
-			      int dev_nr, int rw, int async)
-{
-	struct bio_vec *bvec = first_bio->bi_io_vec;
-	struct bio *bio;
-	int nr_vecs = bio_get_nr_vecs(dev->bdev);
-	u64 physical = bbio->stripes[dev_nr].physical;
-
-again:
-	bio = btrfs_bio_alloc(dev->bdev, physical >> 9, nr_vecs, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-
-	while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
-		if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len) {
-			u64 len = bio->bi_iter.bi_size;
-
-			atomic_inc(&bbio->stripes_pending);
-			submit_stripe_bio(root, bbio, bio, physical, dev_nr,
-					  rw, async);
-			physical += len;
-			goto again;
-		}
-		bvec++;
-	}
-
-	submit_stripe_bio(root, bbio, bio, physical, dev_nr, rw, async);
-	return 0;
-}
-
 static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 {
 	atomic_inc(&bbio->error);
···
 
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
-
-		btrfs_end_bbio(bbio, bio, -EIO);
+		bio->bi_error = -EIO;
+		btrfs_end_bbio(bbio, bio);
 	}
 }
 
···
 		dev = bbio->stripes[dev_nr].dev;
 		if (!dev || !dev->bdev || (rw & WRITE && !dev->writeable)) {
 			bbio_error(bbio, first_bio, logical);
-			continue;
-		}
-
-		/*
-		 * Check and see if we're ok with this bio based on it's size
-		 * and offset with the given device.
-		 */
-		if (!bio_size_ok(dev->bdev, first_bio,
-				 bbio->stripes[dev_nr].physical >> 9)) {
-			ret = breakup_stripe_bio(root, bbio, first_bio, dev,
-						 dev_nr, rw, async_submit);
-			BUG_ON(ret);
 			continue;
 		}
 

fs/buffer.c

···
 }
 EXPORT_SYMBOL(generic_block_bmap);
 
-static void end_bio_bh_io_sync(struct bio *bio, int err)
+static void end_bio_bh_io_sync(struct bio *bio)
 {
 	struct buffer_head *bh = bio->bi_private;
 
-	if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
+	if (unlikely(bio_flagged(bio, BIO_QUIET)))
 		set_bit(BH_Quiet, &bh->b_state);
 
-	bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
+	bh->b_end_io(bh, !bio->bi_error);
 	bio_put(bio);
 }
 
···
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
-	bio->bi_io_vec[0].bv_page = bh->b_page;
-	bio->bi_io_vec[0].bv_len = bh->b_size;
-	bio->bi_io_vec[0].bv_offset = bh_offset(bh);
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = bh->b_size;
+	bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	BUG_ON(bio->bi_iter.bi_size != bh->b_size);
 
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;

fs/direct-io.c

···
 /*
  * Asynchronous IO callback. 
  */
-static void dio_bio_end_aio(struct bio *bio, int error)
+static void dio_bio_end_aio(struct bio *bio)
 {
 	struct dio *dio = bio->bi_private;
 	unsigned long remaining;
···
  * During I/O bi_private points at the dio.  After I/O, bi_private is used to
  * implement a singly-linked list of completed BIOs, at dio->bio_list.
  */
-static void dio_bio_end_io(struct bio *bio, int error)
+static void dio_bio_end_io(struct bio *bio)
 {
 	struct dio *dio = bio->bi_private;
 	unsigned long flags;
···
 	struct dio *dio = bio->bi_private;
 
 	if (dio->is_async)
-		dio_bio_end_aio(bio, error);
+		dio_bio_end_aio(bio);
 	else
-		dio_bio_end_io(bio, error);
+		dio_bio_end_io(bio);
 }
 EXPORT_SYMBOL_GPL(dio_end_io);
 
···
  */
 static int dio_bio_complete(struct dio *dio, struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec;
 	unsigned i;
+	int err;
 
-	if (!uptodate)
+	if (bio->bi_error)
 		dio->io_error = -EIO;
 
 	if (dio->is_async && dio->rw == READ) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
+		err = bio->bi_error;
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
···
 				set_page_dirty_lock(page);
 			page_cache_release(page);
 		}
+		err = bio->bi_error;
 		bio_put(bio);
 	}
-	return uptodate ? 0 : -EIO;
+	return err;
 }
 
 /*
···
 	if (ret)
 		goto out;
 	sector = start_sector << (sdio->blkbits - 9);
-	nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev));
+	nr_pages = min(sdio->pages_in_io, BIO_MAX_PAGES);
 	BUG_ON(nr_pages <= 0);
 	dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages);
 	sdio->boundary = 0;

fs/ext4/page-io.c

···
 static void ext4_finish_bio(struct bio *bio)
 {
 	int i;
-	int error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec;
 
 	bio_for_each_segment_all(bvec, bio, i) {
···
 		}
 #endif
 
-		if (error) {
+		if (bio->bi_error) {
 			SetPageError(page);
 			set_bit(AS_EIO, &page->mapping->flags);
 		}
···
 				continue;
 			}
 			clear_buffer_async_write(bh);
-			if (error)
+			if (bio->bi_error)
 				buffer_io_error(bh);
 		} while ((bh = bh->b_this_page) != head);
 		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
···
 }
 
 /* BIO completion function for page writeback */
-static void ext4_end_bio(struct bio *bio, int error)
+static void ext4_end_bio(struct bio *bio)
 {
 	ext4_io_end_t *io_end = bio->bi_private;
 	sector_t bi_sector = bio->bi_iter.bi_sector;
 
 	BUG_ON(!io_end);
 	bio->bi_end_io = NULL;
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = 0;
 
-	if (error) {
+	if (bio->bi_error) {
 		struct inode *inode = io_end->inode;
 
 		ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
 			     "(offset %llu size %ld starting block %llu)",
-			     error, inode->i_ino,
+			     bio->bi_error, inode->i_ino,
 			     (unsigned long long) io_end->offset,
 			     (long) io_end->size,
 			     (unsigned long long)
 			     bi_sector >> (inode->i_blkbits - 9));
-		mapping_set_error(inode->i_mapping, error);
+		mapping_set_error(inode->i_mapping, bio->bi_error);
 	}
 
 	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
···
 static int io_submit_init_bio(struct ext4_io_submit *io,
 			      struct buffer_head *bh)
 {
-	int nvecs = bio_get_nr_vecs(bh->b_bdev);
 	struct bio *bio;
 
-	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
+	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 	if (!bio)
 		return -ENOMEM;
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);

fs/ext4/readpage.c

···
  * status of that page is hard.  See end_buffer_async_read() for the details.
  * There is no point in duplicating all that complexity.
  */
-static void mpage_end_io(struct bio *bio, int err)
+static void mpage_end_io(struct bio *bio)
 {
 	struct bio_vec *bv;
 	int i;
···
 	if (ext4_bio_encrypted(bio)) {
 		struct ext4_crypto_ctx *ctx = bio->bi_private;
 
-		if (err) {
+		if (bio->bi_error) {
 			ext4_release_crypto_ctx(ctx);
 		} else {
 			INIT_WORK(&ctx->r.work, completion_pages);
···
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
 
-		if (!err) {
+		if (!bio->bi_error) {
 			SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
···
 					goto set_error_page;
 			}
 			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
 					ext4_release_crypto_ctx(ctx);

fs/f2fs/data.c

···
 static struct kmem_cache *extent_tree_slab;
 static struct kmem_cache *extent_node_slab;
 
-static void f2fs_read_end_io(struct bio *bio, int err)
+static void f2fs_read_end_io(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	int i;
 
 	if (f2fs_bio_encrypted(bio)) {
-		if (err) {
+		if (bio->bi_error) {
 			f2fs_release_crypto_ctx(bio->bi_private);
 		} else {
 			f2fs_end_io_crypto_work(bio->bi_private, bio);
···
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
-		if (!err) {
+		if (!bio->bi_error) {
 			SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
···
 	bio_put(bio);
 }
 
-static void f2fs_write_end_io(struct bio *bio, int err)
+static void f2fs_write_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi = bio->bi_private;
 	struct bio_vec *bvec;
···
 
 		f2fs_restore_and_release_control_page(&page);
 
-		if (unlikely(err)) {
+		if (unlikely(bio->bi_error)) {
 			set_page_dirty(page);
 			set_bit(AS_EIO, &page->mapping->flags);
 			f2fs_stop_checkpoint(sbi);
···
 			}
 
 			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
 					f2fs_release_crypto_ctx(ctx);

fs/gfs2/lops.c

···
  *
  */
 
-static void gfs2_end_log_write(struct bio *bio, int error)
+static void gfs2_end_log_write(struct bio *bio)
 {
 	struct gfs2_sbd *sdp = bio->bi_private;
 	struct bio_vec *bvec;
 	struct page *page;
 	int i;
 
-	if (error) {
-		sdp->sd_log_error = error;
-		fs_err(sdp, "Error %d writing to log\n", error);
+	if (bio->bi_error) {
+		sdp->sd_log_error = bio->bi_error;
+		fs_err(sdp, "Error %d writing to log\n", bio->bi_error);
 	}
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		page = bvec->bv_page;
 		if (page_has_buffers(page))
-			gfs2_end_log_write_bh(sdp, bvec, error);
+			gfs2_end_log_write_bh(sdp, bvec, bio->bi_error);
 		else
 			mempool_free(page, gfs2_page_pool);
 	}
···
 static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
 {
 	struct super_block *sb = sdp->sd_vfs;
-	unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
 	struct bio *bio;
 
 	BUG_ON(sdp->sd_log_bio);
 
-	while (1) {
-		bio = bio_alloc(GFP_NOIO, nrvecs);
-		if (likely(bio))
-			break;
-		nrvecs = max(nrvecs/2, 1U);
-	}
-
+	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
 	bio->bi_bdev = sb->s_bdev;
 	bio->bi_end_io = gfs2_end_log_write;

fs/gfs2/ops_fstype.c

···
 	return -EINVAL;
 }
 
-static void end_bio_io_page(struct bio *bio, int error)
+static void end_bio_io_page(struct bio *bio)
 {
 	struct page *page = bio->bi_private;
 
-	if (!error)
+	if (!bio->bi_error)
 		SetPageUptodate(page);
 	else
-		pr_warn("error %d reading superblock\n", error);
+		pr_warn("error %d reading superblock\n", bio->bi_error);
 	unlock_page(page);
 }
 

fs/jfs/jfs_logmgr.c

···
 
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	bio->bi_bdev = log->bdev;
-	bio->bi_io_vec[0].bv_page = bp->l_page;
-	bio->bi_io_vec[0].bv_len = LOGPSIZE;
-	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = LOGPSIZE;
+	bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
 	/*check if journaling to disk has been disabled*/
 	if (log->no_integrity) {
 		bio->bi_iter.bi_size = 0;
-		lbmIODone(bio, 0);
+		lbmIODone(bio);
 	} else {
 		submit_bio(READ_SYNC, bio);
 	}
···
 	bio = bio_alloc(GFP_NOFS, 1);
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	bio->bi_bdev = log->bdev;
-	bio->bi_io_vec[0].bv_page = bp->l_page;
-	bio->bi_io_vec[0].bv_len = LOGPSIZE;
-	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = LOGPSIZE;
+	bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
···
 	/* check if journaling to disk has been disabled */
 	if (log->no_integrity) {
 		bio->bi_iter.bi_size = 0;
-		lbmIODone(bio, 0);
+		lbmIODone(bio);
 	} else {
 		submit_bio(WRITE_SYNC, bio);
 		INCREMENT(lmStat.submitted);
···
  *
  * executed at INTIODONE level
  */
-static void lbmIODone(struct bio *bio, int error)
+static void lbmIODone(struct bio *bio)
 {
 	struct lbuf *bp = bio->bi_private;
 	struct lbuf *nextbp, *tail;
···
 
 	bp->l_flag |= lbmDONE;
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+	if (bio->bi_error) {
 		bp->l_flag |= lbmERROR;
 
 		jfs_err("lbmIODone: I/O error in JFS log");

fs/jfs/jfs_metapage.c

···
 	unlock_page(page);
 }
 
-static void metapage_read_end_io(struct bio *bio, int err)
+static void metapage_read_end_io(struct bio *bio)
 {
 	struct page *page = bio->bi_private;
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+	if (bio->bi_error) {
 		printk(KERN_ERR "metapage_read_end_io: I/O error\n");
 		SetPageError(page);
 	}
···
 	end_page_writeback(page);
 }
 
-static void metapage_write_end_io(struct bio *bio, int err)
+static void metapage_write_end_io(struct bio *bio)
 {
 	struct page *page = bio->bi_private;
 
 	BUG_ON(!PagePrivate(page));
 
-	if (! test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+	if (bio->bi_error) {
 		printk(KERN_ERR "metapage_write_end_io: I/O error\n");
 		SetPageError(page);
 	}

fs/logfs/dev_bdev.c

···
 
 static DECLARE_WAIT_QUEUE_HEAD(wq);
 
-static void writeseg_end_io(struct bio *bio, int err)
+static void writeseg_end_io(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec;
 	int i;
 	struct super_block *sb = bio->bi_private;
 	struct logfs_super *super = logfs_super(sb);
 
-	BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */
-	BUG_ON(err);
+	BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		end_page_writeback(bvec->bv_page);
···
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
+	max_pages = min(nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);
···
 }
 
 
-static void erase_end_io(struct bio *bio, int err) 
+static void erase_end_io(struct bio *bio)
 { 
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); 
 	struct super_block *sb = bio->bi_private; 
 	struct logfs_super *super = logfs_super(sb); 
 
-	BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */ 
-	BUG_ON(err); 
+	BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */ 
 	BUG_ON(bio->bi_vcnt == 0); 
 	bio_put(bio); 
 	if (atomic_dec_and_test(&super->s_pending_writes))
···
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
+	max_pages = min(nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);

fs/mpage.c

···
  * status of that page is hard.  See end_buffer_async_read() for the details.
  * There is no point in duplicating all that complexity.
  */
-static void mpage_end_io(struct bio *bio, int err)
+static void mpage_end_io(struct bio *bio)
 {
 	struct bio_vec *bv;
 	int i;
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, bio_data_dir(bio), err);
+		page_endio(page, bio_data_dir(bio), bio->bi_error);
 	}
 
 	bio_put(bio);
···
 				goto out;
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-			  	min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
+				min_t(int, nr_pages, BIO_MAX_PAGES),
 				GFP_KERNEL);
 		if (bio == NULL)
 			goto confused;
···
 			}
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-				bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
+				BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
 		if (bio == NULL)
 			goto confused;
 

fs/nfs/blocklayout/blocklayout.c

···
 
 static struct bio *
 bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
-		void (*end_io)(struct bio *, int err), struct parallel_io *par)
+		bio_end_io_t end_io, struct parallel_io *par)
 {
 	struct bio *bio;
 
···
 static struct bio *
 do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
 		struct page *page, struct pnfs_block_dev_map *map,
-		struct pnfs_block_extent *be,
-		void (*end_io)(struct bio *, int err),
+		struct pnfs_block_extent *be, bio_end_io_t end_io,
 		struct parallel_io *par, unsigned int offset, int *len)
 {
 	struct pnfs_block_dev *dev =
···
 	return bio;
 }
 
-static void bl_end_io_read(struct bio *bio, int err)
+static void bl_end_io_read(struct bio *bio)
 {
 	struct parallel_io *par = bio->bi_private;
 
-	if (err) {
+	if (bio->bi_error) {
 		struct nfs_pgio_header *header = par->data;
 
 		if (!header->pnfs_error)
···
 	return PNFS_ATTEMPTED;
 }
 
-static void bl_end_io_write(struct bio *bio, int err)
+static void bl_end_io_write(struct bio *bio)
 {
 	struct parallel_io *par = bio->bi_private;
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct nfs_pgio_header *header = par->data;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
 		pnfs_set_lo_fail(header->lseg);

fs/nilfs2/segbuf.c

···
 /*
  * BIO operations
  */
-static void nilfs_end_bio_write(struct bio *bio, int err)
+static void nilfs_end_bio_write(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct nilfs_segment_buffer *segbuf = bio->bi_private;
 
-	if (!uptodate)
+	if (bio->bi_error)
 		atomic_inc(&segbuf->sb_err);
 
 	bio_put(bio);
···
 {
 	wi->bio = NULL;
 	wi->rest_blocks = segbuf->sb_sum.nblocks;
-	wi->max_pages = bio_get_nr_vecs(wi->nilfs->ns_bdev);
+	wi->max_pages = BIO_MAX_PAGES;
 	wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
 	wi->start = wi->end = 0;
 	wi->blocknr = segbuf->sb_pseg_start;

fs/ocfs2/cluster/heartbeat.c

···
 	wait_for_completion(&wc->wc_io_complete);
 }
 
-static void o2hb_bio_end_io(struct bio *bio,
-			   int error)
+static void o2hb_bio_end_io(struct bio *bio)
 {
 	struct o2hb_bio_wait_ctxt *wc = bio->bi_private;
 
-	if (error) {
-		mlog(ML_ERROR, "IO Error %d\n", error);
-		wc->wc_error = error;
+	if (bio->bi_error) {
+		mlog(ML_ERROR, "IO Error %d\n", bio->bi_error);
+		wc->wc_error = bio->bi_error;
 	}
 
 	o2hb_bio_wait_dec(wc, 1);

fs/xfs/xfs_aops.c

···
  */
 STATIC void
 xfs_end_bio(
-	struct bio		*bio,
-	int			error)
+	struct bio		*bio)
 {
 	xfs_ioend_t		*ioend = bio->bi_private;
 
-	ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error;
+	ioend->io_error = bio->bi_error;
 
 	/* Toss bio and pass work off to an xfsdatad thread */
 	bio->bi_private = NULL;
···
 xfs_alloc_ioend_bio(
 	struct buffer_head	*bh)
 {
-	int			nvecs = bio_get_nr_vecs(bh->b_bdev);
-	struct bio		*bio = bio_alloc(GFP_NOIO, nvecs);
+	struct bio		*bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 
 	ASSERT(bio->bi_private == NULL);
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);

fs/xfs/xfs_buf.c

···
 
 STATIC void
 xfs_buf_bio_end_io(
-	struct bio		*bio,
-	int			error)
+	struct bio		*bio)
 {
 	xfs_buf_t		*bp = (xfs_buf_t *)bio->bi_private;
 
···
 	 * don't overwrite existing errors - otherwise we can lose errors on
 	 * buffers that require multiple bios to complete.
 	 */
-	if (error) {
+	if (bio->bi_error) {
 		spin_lock(&bp->b_lock);
 		if (!bp->b_io_error)
-			bp->b_io_error = error;
+			bp->b_io_error = bio->bi_error;
 		spin_unlock(&bp->b_lock);
 	}
 

include/linux/bio.h

···
 	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 
 /*
- * 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 bio_vec *bprv, unsigned int offset)
-{
-	return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1));
-}
-
-#define bio_io_error(bio) bio_endio((bio), -EIO)
-
-/*
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
···
 		smp_mb__before_atomic();
 	}
 	atomic_set(&bio->__bi_cnt, count);
+}
+
+static inline bool bio_flagged(struct bio *bio, unsigned int bit)
+{
+	return (bio->bi_flags & (1U << bit)) != 0;
+}
+
+static inline void bio_set_flag(struct bio *bio, unsigned int bit)
+{
+	bio->bi_flags |= (1U << bit);
+}
+
+static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
+{
+	bio->bi_flags &= ~(1U << bit);
 }
 
 enum bip_flags {
···
 
 }
 
-extern void bio_endio(struct bio *, int);
+extern void bio_endio(struct bio *);
+
+static inline void bio_io_error(struct bio *bio)
+{
+	bio->bi_error = -EIO;
+	bio_endio(bio);
+}
+
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
···
 extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
-extern int bio_get_nr_vecs(struct block_device *);
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    const struct iov_iter *, gfp_t);
···
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_enabled(struct bio *bio);
 extern int bio_integrity_prep(struct bio *);
-extern void bio_integrity_endio(struct bio *, int);
+extern void bio_integrity_endio(struct bio *);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
 extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);

include/linux/blk-cgroup.h

···
 	 * root_rl in such cases.
 	 */
 	blkg = blkg_lookup_create(blkcg, q);
-	if (unlikely(IS_ERR(blkg)))
+	if (IS_ERR(blkg))
 		goto root_rl;
 
 	blkg_get(blkg);

include/linux/blk_types.h

···
 struct block_device;
 struct io_context;
 struct cgroup_subsys_state;
-typedef void (bio_end_io_t) (struct bio *, int);
+typedef void (bio_end_io_t) (struct bio *);
 typedef void (bio_destructor_t) (struct bio *);
 
 /*
···
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	unsigned long		bi_flags;	/* status, command, etc */
+	unsigned int		bi_flags;	/* status, command, etc */
+	int			bi_error;
 	unsigned long		bi_rw;		/* bottom bits READ/WRITE,
 						 * top bits priority
 						 */
···
 /*
  * bio flags
  */
-#define BIO_UPTODATE	0	/* ok after I/O completion */
 #define BIO_SEG_VALID	1	/* bi_phys_segments valid */
 #define BIO_CLONED	2	/* doesn't own data */
 #define BIO_BOUNCED	3	/* bio is a bounce bio */
···
 #define BIO_RESET_BITS	13
 #define BIO_OWNS_VEC	13	/* bio_free() should free bvec */
 
-#define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
-
 /*
  * top 4 bits of bio flags indicate the pool this bio came from
  */
 #define BIO_POOL_BITS		(4)
 #define BIO_POOL_NONE		((1UL << BIO_POOL_BITS) - 1)
-#define BIO_POOL_OFFSET		(BITS_PER_LONG - BIO_POOL_BITS)
+#define BIO_POOL_OFFSET		(32 - BIO_POOL_BITS)
 #define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
 #define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)
 

include/linux/blkdev.h

···
 typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
 
 struct bio_vec;
-struct bvec_merge_data {
-	struct block_device *bi_bdev;
-	sector_t bi_sector;
-	unsigned bi_size;
-	unsigned long bi_rw;
-};
-typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
-			     struct bio_vec *);
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
···
 struct queue_limits {
 	unsigned long		bounce_pfn;
 	unsigned long		seg_boundary_mask;
+	unsigned long		virt_boundary_mask;
 
 	unsigned int		max_hw_sectors;
 	unsigned int		chunk_sectors;
···
 	unsigned int		io_min;
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
+	unsigned int		max_hw_discard_sectors;
 	unsigned int		max_write_same_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
···
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unprep_rq_fn		*unprep_rq_fn;
-	merge_bvec_fn		*merge_bvec_fn;
 	softirq_done_fn		*softirq_done_fn;
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
···
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
+	struct bio_set		*bio_split;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
···
 #define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
 #define QUEUE_FLAG_NO_SG_MERGE 21	/* don't attempt to merge SG segments*/
-#define QUEUE_FLAG_SG_GAPS     22	/* queue doesn't support SG gaps */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
···
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
+extern void blk_queue_split(struct request_queue *, struct bio **,
+			    struct bio_set *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
···
 			       void *buf, unsigned int size);
 extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
+extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
 extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn);
-extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
···
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
+	BLK_DEF_MAX_SECTORS	= 2560,
 	BLK_MAX_SEGMENT_SIZE	= 65536,
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
···
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
+}
+
+static inline unsigned long queue_virt_boundary(struct request_queue *q)
+{
+	return q->limits.virt_boundary_mask;
 }
 
 static inline unsigned int queue_max_sectors(struct request_queue *q)
···
 static inline void put_dev_sector(Sector p)
 {
 	page_cache_release(p.v);
+}
+
+/*
+ * 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,
+				struct bio_vec *bprv, unsigned int offset)
+{
+	if (!queue_virt_boundary(q))
+		return false;
+	return offset ||
+		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
 }
 
 struct work_struct;

include/linux/device-mapper.h

···
 typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 			    unsigned long arg);
 
-typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size);
-
 /*
  * These iteration functions are typically used to check (and combine)
  * properties of underlying devices.
···
 	dm_status_fn status;
 	dm_message_fn message;
 	dm_ioctl_fn ioctl;
-	dm_merge_fn merge;
 	dm_busy_fn busy;
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;

include/linux/genhd.h

···
 #include <linux/kdev_t.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/percpu-refcount.h>
 
 #ifdef CONFIG_BLOCK
 
···
 #else
 	struct disk_stats dkstats;
 #endif
-	atomic_t ref;
+	struct percpu_ref ref;
 	struct rcu_head rcu_head;
 };
 
···
 						     sector_t len, int flags,
 						     struct partition_meta_info
 						       *info);
-extern void __delete_partition(struct hd_struct *);
+extern void __delete_partition(struct percpu_ref *);
 extern void delete_partition(struct gendisk *, int);
 extern void printk_all_partitions(void);
 
···
 			       const char *buf, size_t count);
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
-static inline void hd_ref_init(struct hd_struct *part)
+static inline int hd_ref_init(struct hd_struct *part)
 {
-	atomic_set(&part->ref, 1);
-	smp_mb();
+	if (percpu_ref_init(&part->ref, __delete_partition, 0,
+				GFP_KERNEL))
+		return -ENOMEM;
+	return 0;
 }
 
 static inline void hd_struct_get(struct hd_struct *part)
 {
-	atomic_inc(&part->ref);
-	smp_mb__after_atomic();
+	percpu_ref_get(&part->ref);
 }
 
 static inline int hd_struct_try_get(struct hd_struct *part)
 {
-	return atomic_inc_not_zero(&part->ref);
+	return percpu_ref_tryget_live(&part->ref);
 }
 
 static inline void hd_struct_put(struct hd_struct *part)
 {
-	if (atomic_dec_and_test(&part->ref))
-		__delete_partition(part);
+	percpu_ref_put(&part->ref);
+}
+
+static inline void hd_struct_kill(struct hd_struct *part)
+{
+	percpu_ref_kill(&part->ref);
+}
+
+static inline void hd_free_part(struct hd_struct *part)
+{
+	free_part_stats(part);
+	free_part_info(part);
+	percpu_ref_exit(&part->ref);
 }
 
 /*

include/linux/swap.h

···
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
-extern void end_swap_bio_write(struct bio *bio, int err);
+extern void end_swap_bio_write(struct bio *bio);
 extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
-	void (*end_write_func)(struct bio *, int));
+	bio_end_io_t end_write_func);
 extern int swap_set_page_dirty(struct page *page);
 
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,

kernel/power/swap.c

···
 	hb->error = 0;
 }
 
-static void hib_end_io(struct bio *bio, int error)
+static void hib_end_io(struct bio *bio)
 {
 	struct hib_bio_batch *hb = bio->bi_private;
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (!uptodate || error) {
+	if (bio->bi_error) {
 		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
 				imajor(bio->bi_bdev->bd_inode),
 				iminor(bio->bi_bdev->bd_inode),
 				(unsigned long long)bio->bi_iter.bi_sector);
-
-		if (!error)
-			error = -EIO;
 	}
 
 	if (bio_data_dir(bio) == WRITE)
 		put_page(page);
 
-	if (error && !hb->error)
-		hb->error = error;
+	if (bio->bi_error && !hb->error)
+		hb->error = bio->bi_error;
 	if (atomic_dec_and_test(&hb->count))
 		wake_up(&hb->wait);
 

kernel/trace/blktrace.c

···
 	if (likely(!bt))
 		return;
 
-	if (!error && !bio_flagged(bio, BIO_UPTODATE))
-		error = EIO;
-
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
 			bio->bi_rw, what, error, 0, NULL);
 }
···
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
-				!bio_flagged(bio, BIO_UPTODATE),
-				sizeof(rpdu), &rpdu);
+				bio->bi_error, sizeof(rpdu), &rpdu);
 	}
 }
 
···
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio->bi_rw, BLK_TA_REMAP,
-			!bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+			bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
+			sizeof(r), &r);
 }
 
 /**

mm/page_io.c

···
 	if (bio) {
 		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
 		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
-		bio->bi_io_vec[0].bv_page = page;
-		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
-		bio->bi_io_vec[0].bv_offset = 0;
-		bio->bi_vcnt = 1;
-		bio->bi_iter.bi_size = PAGE_SIZE;
 		bio->bi_end_io = end_io;
+
+		bio_add_page(bio, page, PAGE_SIZE, 0);
+		BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE);
 	}
 	return bio;
 }
 
-void end_swap_bio_write(struct bio *bio, int err)
+void end_swap_bio_write(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		SetPageError(page);
 		/*
 		 * We failed to write the page out to swap-space.
···
 	bio_put(bio);
 }
 
-static void end_swap_bio_read(struct bio *bio, int err)
+static void end_swap_bio_read(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		SetPageError(page);
 		ClearPageUptodate(page);
 		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
···
 }
 
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
-	void (*end_write_func)(struct bio *, int))
+		bio_end_io_t end_write_func)
 {
 	struct bio *bio;
 	int ret, rw = WRITE;