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

@@ -1109,7 +1109,7 @@ it will loop and handle as many sectors (on a bio-segment granularity)
 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

@@ -24,7 +24,7 @@ particular, presenting the illusion of partially completed biovecs so that
 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.
 
@@ -109,3 +109,11 @@ Other implications:
    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

@@ -20,7 +20,7 @@ This shows the size of internal allocation of the device in bytes, if
 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.
@@ -29,6 +29,14 @@ 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)
 ------------------------
 When read, this file will show if the discarded block are zeroed by the

arch/m68k/emu/nfblock.c

@@ -76,7 +76,7 @@ static void nfhd_make_request(struct request_queue *queue, struct bio *bio)
 				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

@@ -132,7 +132,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
 		phys_mem += vec.bv_len;
 		transfered += vec.bv_len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 }
 
 /**

arch/xtensa/platforms/iss/simdisk.c

@@ -101,8 +101,9 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	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;
@@ -116,17 +117,10 @@ static int simdisk_xfer_bio(struct simdisk *dev, struct bio *bio)
 		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)
 {
 	struct simdisk *dev = bdev->bd_disk->private_data;

block/bio-integrity.c

@@ -355,13 +355,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 		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);
 }
 
 /**
@@ -376,7 +375,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  * 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);
 
@@ -386,9 +385,9 @@ void bio_integrity_endio(struct bio *bio, int error)
 	 * 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

@@ -269,7 +269,6 @@ static void bio_free(struct bio *bio)
 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);
 }
@@ -292,14 +291,17 @@ void bio_reset(struct bio *bio)
 	__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);
 }
 
@@ -309,7 +311,7 @@ static void bio_chain_endio(struct bio *bio, int error)
  */
 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);
 }
@@ -493,7 +495,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		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;
 	}
@@ -578,7 +580,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	 * 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;
@@ -692,31 +694,22 @@ integrity_clone:
 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;
@@ -727,7 +720,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	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;
 
 	/*
@@ -740,28 +733,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 
 		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;
 		}
@@ -770,8 +742,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		 * 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;
 	}
 
@@ -804,30 +775,9 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		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;
@@ -841,28 +791,6 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	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);
 
 /**
@@ -872,22 +800,47 @@ 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;
+
+	/*
+	 * cloned bio must not modify vec list
+	 */
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return 0;
 
-	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;
+	/*
+	 * 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];
 
-	return __bio_add_page(q, bio, page, len, offset, max_sectors);
+		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);
 
@@ -896,11 +849,11 @@ struct submit_bio_ret {
 	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);
 }
 
@@ -1388,7 +1341,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	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,
@@ -1445,7 +1398,7 @@ void bio_unmap_user(struct bio *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);
 }
@@ -1501,13 +1454,13 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 }
 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;
@@ -1518,7 +1471,7 @@ static void bio_copy_kern_endio_read(struct bio *bio, int err)
 		p += bvec->bv_len;
 	}
 
-	bio_copy_kern_endio(bio, err);
+	bio_copy_kern_endio(bio);
 }
 
 /**
@@ -1768,7 +1721,7 @@ static inline bool bio_remaining_done(struct bio *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;
 	}
 
@@ -1778,25 +1731,15 @@ static inline bool bio_remaining_done(struct bio *bio)
 /**
  * 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;
 
@@ -1810,11 +1753,12 @@ void bio_endio(struct bio *bio, int error)
 		 */
 		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;
 		}
 	}
@@ -1882,7 +1826,7 @@ void bio_trim(struct bio *bio, int offset, int size)
 	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

@@ -143,18 +143,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 			  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)
@@ -645,6 +643,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	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;
@@ -653,7 +655,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	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);
@@ -695,6 +697,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 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:
@@ -1612,6 +1616,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	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
@@ -1620,7 +1626,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	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;
 	}
 
@@ -1673,7 +1680,8 @@ get_rq:
 	 */
 	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;
 	}
 
@@ -1832,15 +1840,6 @@ generic_make_request_checks(struct bio *bio)
 		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,
@@ -1896,7 +1895,8 @@ generic_make_request_checks(struct bio *bio)
 	return true;
 
 end_io:
-	bio_endio(bio, err);
+	bio->bi_error = err;
+	bio_endio(bio);
 	return false;
 }
 

block/blk-flush.c

@@ -73,6 +73,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-tag.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -226,7 +227,12 @@ static void flush_end_io(struct request *flush_rq, int error)
 	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;
 	}
 
@@ -308,11 +314,18 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 
 	/*
 	 * 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

@@ -11,21 +11,28 @@
 
 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
  * @bdev:	blockdev to issue discard for
@@ -43,8 +50,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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;
@@ -56,21 +61,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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;
@@ -78,13 +68,13 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	}
 
 	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) {
@@ -92,21 +82,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			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;
@@ -134,9 +111,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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);
@@ -166,13 +142,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	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) {
@@ -208,9 +182,8 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	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);
@@ -236,7 +209,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	DECLARE_COMPLETION_ONSTACK(wait);
 
 	atomic_set(&bb.done, 1);
-	bb.flags = 1 << BIO_UPTODATE;
+	bb.error = 0;
 	bb.wait = &wait;
 
 	ret = 0;
@@ -270,10 +243,8 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	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

@@ -94,7 +94,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		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) {
 		/*
@@ -103,7 +103,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		 * 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

@@ -9,12 +9,146 @@
 
 #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;
@@ -36,7 +170,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	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) {
 			/*
@@ -46,13 +179,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			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;
@@ -72,8 +199,8 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
@@ -116,7 +243,7 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
 		bio->bi_next = nxt;
 	}
 
-	bio->bi_flags |= (1 << BIO_SEG_VALID);
+	bio_set_flag(bio, BIO_SEG_VALID);
 }
 EXPORT_SYMBOL(blk_recount_segments);
 
@@ -356,12 +483,12 @@ static bool req_no_special_merge(struct request *req)
 	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,
@@ -378,8 +505,7 @@ 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;
 
 	/*
@@ -564,8 +690,6 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 
 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;
 
@@ -590,13 +714,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		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

@@ -141,15 +141,26 @@ static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
 
 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);
+
+	list_for_each_entry(rq, list, queuelist) {
+		const int rq_len = 2 * sizeof(rq) + 2;
+
+		/* 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);
+	}
 
-	page += sprintf(page, "%s:\n", msg);
-
-	list_for_each_entry(rq, list, queuelist)
-		page += sprintf(page, "\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

@@ -429,7 +429,7 @@ static void bt_for_each(struct blk_mq_hw_ctx *hctx,
 		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);
 		}
@@ -453,7 +453,7 @@ static void bt_tags_for_each(struct blk_mq_tags *tags,
 		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

@@ -89,4 +89,16 @@ static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 	__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

@@ -559,23 +559,9 @@ void blk_mq_abort_requeue_list(struct request_queue *q)
 }
 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);
 
@@ -1199,7 +1185,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	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;
 	}
 
@@ -1283,10 +1269,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	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))
 		return;
@@ -1368,10 +1356,12 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	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))
 		return;

block/blk-settings.c

@@ -53,28 +53,6 @@ void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
 }
 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;
@@ -111,11 +89,13 @@ void blk_set_default_limits(struct queue_limits *lim)
 	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;
@@ -257,7 +237,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
 		       __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);
 
@@ -303,6 +285,7 @@ EXPORT_SYMBOL(blk_queue_chunk_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);
@@ -550,6 +533,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	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,
@@ -641,6 +626,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 		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) %
@@ -787,6 +774,17 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long 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
  * @q:     the request queue for the device

block/blk-sysfs.c

@@ -145,12 +145,43 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 	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)
 {
 	return queue_var_show(queue_discard_zeroes_data(q), page);
@@ -360,9 +391,15 @@ static struct queue_sysfs_entry queue_discard_granularity_entry = {
 	.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 = {
@@ -421,6 +458,7 @@ static struct attribute *default_attrs[] = {
 	&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,
@@ -523,6 +561,9 @@ static void blk_release_queue(struct kobject *kobj)
 
 	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

@@ -22,6 +22,12 @@ struct blk_flush_queue {
 	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

@@ -123,7 +123,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 	}
 }
 
-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;
@@ -141,39 +141,40 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 		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
@@ -185,7 +186,7 @@ static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
 	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

@@ -1110,8 +1110,7 @@ static void disk_release(struct device *dev)
 	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);
@@ -1285,7 +1284,11 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 		 * 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

@@ -212,8 +212,7 @@ static void part_release(struct device *dev)
 {
 	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);
 }
 
@@ -233,8 +232,9 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
 	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);
 }
 
@@ -255,7 +255,7 @@ void delete_partition(struct gendisk *disk, int partno)
 	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,
@@ -356,8 +356,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	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

@@ -395,7 +395,7 @@ aoeblk_gdalloc(void *vp)
 	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

@@ -1110,7 +1110,7 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 		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 */
@@ -1172,7 +1172,7 @@ ktiocomplete(struct frame *f)
 			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;
 	}
 
@@ -1185,7 +1185,7 @@ noskb:		if (buf)
 				"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) {
@@ -1193,7 +1193,7 @@ noskb:		if (buf)
 				"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);
@@ -1695,7 +1695,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf)
 	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

@@ -170,7 +170,7 @@ aoe_failip(struct aoedev *d)
 	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

@@ -331,14 +331,12 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 	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;
 	}
@@ -349,15 +347,20 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 
 	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,
@@ -500,7 +503,7 @@ static struct brd_device *brd_alloc(int i)
 	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

@@ -175,11 +175,11 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	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

@@ -941,36 +941,27 @@ static void drbd_bm_aio_ctx_destroy(struct kref *kref)
 }
 
 /* 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);
@@ -1031,7 +1022,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 
 	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

@@ -1450,7 +1450,6 @@ extern void do_submit(struct work_struct *ws);
 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);
 
 
@@ -1481,9 +1480,9 @@ extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* 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);
@@ -1604,12 +1603,13 @@ static inline void drbd_generic_make_request(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

@@ -2774,7 +2774,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	   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

@@ -1156,14 +1156,14 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 			/* 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

@@ -201,7 +201,8 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 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);
 }
 
@@ -1153,12 +1154,12 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 				      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)
@@ -1191,7 +1192,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 		/* 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;
@@ -1497,6 +1499,8 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	struct drbd_device *device = (struct drbd_device *) q->queuedata;
 	unsigned long start_jif;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	start_jif = jiffies;
 
 	/*
@@ -1508,41 +1512,6 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	__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)
 {
 	struct drbd_device *device = (struct drbd_device *) data;

drivers/block/drbd/drbd_worker.c

@@ -65,12 +65,12 @@ rwlock_t global_state_lock;
 /* 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.
@@ -170,31 +170,20 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 /* 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 */
@@ -208,24 +197,13 @@ void drbd_peer_request_endio(struct bio *bio, int error)
 
 /* 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",
@@ -259,14 +237,14 @@ void drbd_request_endio(struct bio *bio, int error)
 		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
@@ -279,7 +257,7 @@ void drbd_request_endio(struct bio *bio, int error)
 		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

@@ -3771,13 +3771,14 @@ struct rb0_cbdata {
 	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

@@ -675,7 +675,7 @@ static void loop_config_discard(struct loop_device *lo)
 	    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;
@@ -683,7 +683,7 @@ static void loop_config_discard(struct loop_device *lo)
 
 	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

@@ -822,7 +822,7 @@ static int __init nbd_init(void)
 		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

@@ -222,7 +222,7 @@ static void end_cmd(struct nullb_cmd *cmd)
 		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

@@ -1935,7 +1935,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	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);
 }
 
@@ -2067,7 +2067,6 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 		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;
 
@@ -2087,6 +2086,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 		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

@@ -977,7 +977,7 @@ static void pkt_make_local_copy(struct packet_data *pkt, struct bio_vec *bvec)
 	}
 }
 
-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;
@@ -985,9 +985,9 @@ static void pkt_end_io_read(struct bio *bio, int err)
 
 	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);
@@ -996,13 +996,13 @@ static void pkt_end_io_read(struct bio *bio, int err)
 	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++;
 
@@ -1340,22 +1340,22 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	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 (;;) {
@@ -1384,7 +1384,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			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);
@@ -1401,8 +1401,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			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:
@@ -2332,13 +2331,14 @@ static void pkt_close(struct gendisk *disk, fmode_t mode)
 }
 
 
-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);
 }
@@ -2447,6 +2447,10 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 	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",
@@ -2477,8 +2481,6 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 		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);
@@ -2504,26 +2506,6 @@ end_io:
 
 
 
-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;
@@ -2531,7 +2513,6 @@ static void pkt_init_queue(struct pktcdvd_device *pd)
 	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

@@ -593,7 +593,8 @@ out:
 	next = bio_list_peek(&priv->list);
 	spin_unlock_irq(&priv->lock);
 
-	bio_endio(bio, error);
+	bio->bi_error = error;
+	bio_endio(bio);
 	return next;
 }
 
@@ -605,6 +606,8 @@ static void ps3vram_make_request(struct request_queue *q, struct bio *bio)
 
 	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);
 	bio_list_add(&priv->list, bio);

drivers/block/rbd.c

@@ -3474,52 +3474,6 @@ static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	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;
@@ -3815,10 +3769,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	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

@@ -137,7 +137,10 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
 		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);
 	}
 }
@@ -148,6 +151,8 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 	struct rsxx_bio_meta *bio_meta;
 	int st = -EINVAL;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	might_sleep();
 
 	if (!card)
@@ -199,7 +204,9 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 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

@@ -4422,7 +4422,7 @@ static int skd_cons_disk(struct skd_device *skdev)
 	/* 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

@@ -456,7 +456,7 @@ static void process_page(unsigned long data)
 				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,
@@ -505,7 +505,7 @@ static void process_page(unsigned long data)
 
 		return_bio = bio->bi_next;
 		bio->bi_next = NULL;
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	}
 }
 
@@ -531,6 +531,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
 		 (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;
 	bio->bi_next = NULL;

drivers/block/xen-blkback/blkback.c

@@ -1078,9 +1078,9 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 /*
  * 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

@@ -82,7 +82,6 @@ struct blk_shadow {
 struct split_bio {
 	struct bio *bio;
 	atomic_t pending;
-	int err;
 };
 
 static DEFINE_MUTEX(blkfront_mutex);
@@ -1481,16 +1480,14 @@ static int blkfront_probe(struct xenbus_device *dev,
 	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

@@ -848,7 +848,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		zram_bio_discard(zram, index, offset, bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -881,8 +881,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		update_position(&index, &offset, &bvec);
 	}
 
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 
 out:
@@ -899,6 +898,8 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 	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)) {
 		atomic64_inc(&zram->stats.invalid_io);
@@ -1242,7 +1243,7 @@ static int zram_add(void)
 	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

@@ -243,19 +243,6 @@ struct keybuf {
 	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;
 
@@ -288,8 +275,6 @@ struct bcache_device {
 	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 {
@@ -454,8 +439,6 @@ struct cache {
 	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 {
@@ -873,7 +856,6 @@ void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *);
 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

@@ -278,7 +278,7 @@ err:
 	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);
@@ -305,7 +305,7 @@ static void bch_btree_node_read(struct btree *b)
 	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);
@@ -371,15 +371,15 @@ static void btree_node_write_done(struct closure *cl)
 	__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

@@ -38,7 +38,7 @@
  * 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

@@ -11,105 +11,6 @@
 
 #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)
@@ -139,7 +40,7 @@ void __bch_submit_bbio(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

@@ -24,7 +24,7 @@
  * 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);
@@ -61,7 +61,7 @@ reread:		left = ca->sb.bucket_size - offset;
 		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
@@ -401,7 +401,7 @@ retry:
 
 #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);
@@ -547,11 +547,11 @@ void bch_journal_next(struct journal *j)
 		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);
 }
 
@@ -648,7 +648,7 @@ static void journal_write_unlocked(struct closure *cl)
 	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

@@ -60,20 +60,20 @@ static void write_moving_finish(struct closure *cl)
 	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

@@ -173,22 +173,22 @@ static void bch_data_insert_error(struct closure *cl)
 	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)
@@ -477,7 +477,7 @@ struct search {
 	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;
@@ -490,15 +490,15 @@ static void bch_cache_read_endio(struct bio *bio, int error)
 	 * 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");
 }
 
 /*
@@ -591,13 +591,13 @@ static void cache_lookup(struct closure *cl)
 
 /* 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;
 	}
@@ -613,7 +613,8 @@ static void bio_complete(struct search *s)
 				    &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;
 	}
 }
@@ -718,7 +719,7 @@ static void cached_dev_read_error(struct closure *cl)
 
 		/* XXX: invalidate cache */
 
-		closure_bio_submit(bio, cl, s->d);
+		closure_bio_submit(bio, cl);
 	}
 
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
@@ -841,7 +842,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	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:
@@ -849,7 +850,7 @@ 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;
 }
 
@@ -914,7 +915,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 
 		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;
@@ -929,12 +930,12 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			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);
@@ -950,7 +951,7 @@ static void cached_dev_nodata(struct closure *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);
 }
@@ -992,9 +993,9 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 	} 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

@@ -59,29 +59,6 @@ struct workqueue_struct *bcache_wq;
 
 #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,
@@ -221,7 +198,7 @@ err:
 	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 */
@@ -290,11 +267,11 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent)
 	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);
 }
 
@@ -339,12 +316,12 @@ void bcache_write_super(struct cache_set *c)
 
 /* 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);
 }
@@ -512,11 +489,11 @@ static struct uuid_entry *uuid_find_empty(struct cache_set *c)
  * 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);
 }
@@ -537,7 +514,7 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
 	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);
 }
 
@@ -757,7 +734,6 @@ static void bcache_device_free(struct bcache_device *d)
 		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);
@@ -804,7 +780,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		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;
@@ -830,7 +805,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	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;
@@ -1793,8 +1768,6 @@ void bch_cache_release(struct kobject *kobj)
 		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);
@@ -1839,8 +1812,7 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 					  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

@@ -4,6 +4,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/llist.h>
 #include <linux/ratelimit.h>
@@ -570,10 +571,10 @@ static inline sector_t bdev_sectors(struct block_device *bdev)
 	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

@@ -166,12 +166,12 @@ static void write_dirty_finish(struct closure *cl)
 	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);
@@ -188,27 +188,27 @@ static void write_dirty(struct closure *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

@@ -236,8 +236,10 @@ void dm_cell_error(struct dm_bio_prison *prison,
 	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

@@ -545,7 +545,8 @@ static void dmio_complete(unsigned long error, void *context)
 {
 	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,
@@ -575,13 +576,16 @@ 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
@@ -589,7 +593,8 @@ static void inline_endio(struct bio *bio, int error)
 	 */
 	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,
@@ -661,13 +666,14 @@ static void submit_io(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);
 	}
 
@@ -1026,11 +1032,11 @@ found_buffer:
  * 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

@@ -919,14 +919,14 @@ static void defer_writethrough_bio(struct cache *cache, struct bio *bio)
 	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;
 	}
 
@@ -1231,7 +1231,7 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 			 * 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);
@@ -1284,7 +1284,7 @@ static void issue_copy(struct dm_cache_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;
@@ -1294,7 +1294,7 @@ static void overwrite_endio(struct bio *bio, int err)
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (err)
+	if (bio->bi_error)
 		mg->err = true;
 
 	mg->requeue_holder = false;
@@ -1358,7 +1358,7 @@ static void issue_discard(struct dm_cache_migration *mg)
 		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);
 }
@@ -1631,7 +1631,7 @@ static void process_discard_bio(struct cache *cache, struct prealloc *structs,
 
 	calc_discard_block_range(cache, bio, &b, &e);
 	if (b == e) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -2217,8 +2217,10 @@ static void requeue_deferred_bios(struct cache *cache)
 	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)
@@ -3123,7 +3125,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 			 * 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;
@@ -3778,26 +3780,6 @@ static int cache_iterate_devices(struct dm_target *ti,
 	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)
 {
 	/*
@@ -3841,7 +3823,6 @@ static struct target_type cache_target = {
 	.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

@@ -1076,7 +1076,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	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);
 }
 
 /*
@@ -1096,14 +1097,12 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
  * 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
@@ -1111,6 +1110,7 @@ static void crypt_endio(struct bio *clone, int error)
 	if (rw == WRITE)
 		crypt_free_buffer_pages(cc, clone);
 
+	error = clone->bi_error;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -2035,21 +2035,6 @@ 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)
 {
@@ -2070,7 +2055,6 @@ static struct target_type crypt_target = {
 	.preresume = crypt_preresume,
 	.resume = crypt_resume,
 	.message = crypt_message,
-	.merge  = crypt_merge,
 	.iterate_devices = crypt_iterate_devices,
 };
 

drivers/md/dm-era-target.c

@@ -1673,20 +1673,6 @@ static int era_iterate_devices(struct dm_target *ti,
 	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;
@@ -1717,7 +1703,6 @@ static struct target_type era_target = {
 	.status = era_status,
 	.message = era_message,
 	.iterate_devices = era_iterate_devices,
-	.merge = era_merge,
 	.io_hints = era_io_hints
 };
 

drivers/md/dm-flakey.c

@@ -296,7 +296,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		 * Drop writes?
 		 */
 		if (test_bit(DROP_WRITES, &fc->flags)) {
-			bio_endio(bio, 0);
+			bio_endio(bio);
 			return DM_MAPIO_SUBMITTED;
 		}
 
@@ -387,21 +387,6 @@ static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long ar
 	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;
@@ -419,7 +404,6 @@ static struct target_type flakey_target = {
 	.end_io = flakey_end_io,
 	.status = flakey_status,
 	.ioctl	= flakey_ioctl,
-	.merge	= flakey_merge,
 	.iterate_devices = flakey_iterate_devices,
 };
 

drivers/md/dm-io.c

@@ -134,12 +134,13 @@ static void dec_count(struct io *io, unsigned int region, int error)
 		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);
 
 	/*
@@ -147,6 +148,7 @@ static void endio(struct bio *bio, int error)
 	 */
 	retrieve_io_and_region_from_bio(bio, &io, &region);
 
+	error = bio->bi_error;
 	bio_put(bio);
 
 	dec_count(io, region, error);
@@ -314,7 +316,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		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

@@ -130,21 +130,6 @@ static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
 	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)
 {
@@ -162,7 +147,6 @@ static struct target_type linear_target = {
 	.map    = linear_map,
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
-	.merge  = linear_merge,
 	.iterate_devices = linear_iterate_devices,
 };
 

drivers/md/dm-log-writes.c

@@ -146,16 +146,16 @@ static void put_io_block(struct log_writes_c *lc)
 	}
 }
 
-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);
@@ -205,7 +205,6 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
 	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) {
@@ -270,7 +269,6 @@ static int log_one_block(struct log_writes_c *lc,
 	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++) {
 		/*
@@ -292,7 +290,6 @@ static int log_one_block(struct log_writes_c *lc,
 			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);
@@ -606,7 +603,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 		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;
 	}
 
@@ -728,21 +725,6 @@ static int log_writes_ioctl(struct dm_target *ti, unsigned int cmd,
 	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)
@@ -796,7 +778,6 @@ static struct target_type log_writes_target = {
 	.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

@@ -1717,24 +1717,6 @@ static void raid_resume(struct dm_target *ti)
 	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},
@@ -1749,7 +1731,6 @@ static struct target_type raid_target = {
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
-	.merge = raid_merge,
 };
 
 static int __init dm_raid_init(void)

drivers/md/dm-raid1.c

@@ -490,9 +490,11 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio)
 		 * 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;
 	}
 
@@ -515,7 +517,7 @@ static void read_callback(unsigned long error, void *context)
 	bio_set_m(bio, NULL);
 
 	if (likely(!error)) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -531,7 +533,7 @@ static void read_callback(unsigned long error, void *context)
 
 	DMERR_LIMIT("Read failure on mirror device %s.  Failing I/O.",
 		    m->dev->name);
-	bio_endio(bio, -EIO);
+	bio_io_error(bio);
 }
 
 /* Asynchronous read. */
@@ -580,7 +582,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 		if (likely(m))
 			read_async_bio(m, bio);
 		else
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 	}
 }
 
@@ -598,7 +600,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 
 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;
@@ -614,7 +616,7 @@ static void write_callback(unsigned long error, void *context)
 	 * regions with the same code.
 	 */
 	if (likely(!error)) {
-		bio_endio(bio, ret);
+		bio_endio(bio);
 		return;
 	}
 
@@ -623,7 +625,8 @@ static void write_callback(unsigned long error, void *context)
 	 * degrade the array.
 	 */
 	if (bio->bi_rw & REQ_DISCARD) {
-		bio_endio(bio, -EOPNOTSUPP);
+		bio->bi_error = -EOPNOTSUPP;
+		bio_endio(bio);
 		return;
 	}
 
@@ -828,13 +831,12 @@ static void do_failures(struct mirror_set *ms, struct bio_list *failures)
 		 * 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

@@ -1490,7 +1490,7 @@ out:
 		error_bios(snapshot_bios);
 	} else {
 		if (full_bio)
-			bio_endio(full_bio, 0);
+			bio_endio(full_bio);
 		flush_bios(snapshot_bios);
 	}
 
@@ -1580,11 +1580,11 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 	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,
@@ -2330,20 +2330,6 @@ static void origin_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-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)
 {
@@ -2362,7 +2348,6 @@ static struct target_type origin_target = {
 	.resume  = origin_resume,
 	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
-	.merge	 = origin_merge,
 	.iterate_devices = origin_iterate_devices,
 };
 

drivers/md/dm-stripe.c

@@ -273,7 +273,7 @@ static int stripe_map_range(struct stripe_c *sc, struct bio *bio,
 		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;
 	}
 }
@@ -412,26 +412,6 @@ static void stripe_io_hints(struct dm_target *ti,
 	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},
@@ -443,7 +423,6 @@ static struct target_type stripe_target = {
 	.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

@@ -440,14 +440,6 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       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;
 }
 
@@ -1388,14 +1380,6 @@ static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev,
 	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)
 {
@@ -1516,11 +1500,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *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

@@ -615,8 +615,10 @@ static void error_bio_list(struct bio_list *bios, int error)
 {
 	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)
@@ -870,14 +872,14 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
 	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);
 }
 
@@ -1002,7 +1004,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *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);
@@ -1032,7 +1034,7 @@ static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
 
 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);
 }
 
@@ -1046,7 +1048,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_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);
@@ -1117,7 +1119,8 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	 * 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);
 }
@@ -1493,9 +1496,10 @@ static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
 	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);
 }
 
@@ -1631,7 +1635,7 @@ static void process_discard_cell_passdown(struct thin_c *tc, struct dm_bio_priso
 	 * 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)
@@ -1645,7 +1649,7 @@ 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;
 	}
 
@@ -1790,7 +1794,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	if (bio_data_dir(bio) == READ) {
 		zero_fill_bio(bio);
 		cell_defer_no_holder(tc, cell);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		return;
 	}
 
@@ -1855,7 +1859,7 @@ static void process_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 
 			} else {
 				zero_fill_bio(bio);
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			}
 		} else
 			provision_block(tc, bio, block, cell);
@@ -1926,7 +1930,7 @@ static void __process_bio_read_only(struct thin_c *tc, struct bio *bio,
 		}
 
 		zero_fill_bio(bio);
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		break;
 
 	default:
@@ -1951,7 +1955,7 @@ static void process_cell_read_only(struct thin_c *tc, struct dm_bio_prison_cell
 
 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)
@@ -2600,7 +2604,8 @@ static int thin_bio_map(struct dm_target *ti, 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;
 	}
 
@@ -3875,20 +3880,6 @@ static int pool_iterate_devices(struct dm_target *ti,
 	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;
@@ -3965,7 +3956,6 @@ static struct target_type pool_target = {
 	.resume = pool_resume,
 	.message = pool_message,
 	.status = pool_status,
-	.merge = pool_merge,
 	.iterate_devices = pool_iterate_devices,
 	.io_hints = pool_io_hints,
 };
@@ -4292,21 +4282,6 @@ err:
 	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)
 {
@@ -4350,7 +4325,6 @@ static struct target_type thin_target = {
 	.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

@@ -458,8 +458,9 @@ static void verity_finish_io(struct dm_verity_io *io, int error)
 
 	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)
@@ -469,12 +470,12 @@ 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;
 	}
 
@@ -648,21 +649,6 @@ static int verity_ioctl(struct dm_target *ti, unsigned cmd,
 				     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,
 				  iterate_devices_callout_fn fn, void *data)
 {
@@ -995,7 +981,6 @@ static struct target_type verity_target = {
 	.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

@@ -47,7 +47,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
 		break;
 	}
 
-	bio_endio(bio, 0);
+	bio_endio(bio);
 
 	/* accepted bio, don't make new request */
 	return DM_MAPIO_SUBMITTED;

drivers/md/dm.c

@@ -124,9 +124,8 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #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.
@@ -944,7 +943,8 @@ static void dec_pending(struct dm_io *io, int error)
 		} 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);
 		}
 	}
 }
@@ -957,17 +957,15 @@ static void disable_write_same(struct mapped_device *md)
 	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);
 		if (r < 0 || r == DM_ENDIO_REQUEUE)
@@ -996,7 +994,7 @@ static void clone_endio(struct bio *bio, int 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);
@@ -1013,13 +1011,13 @@ static void end_clone_bio(struct bio *clone, int error)
 		 * 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;
 	}
 
@@ -1722,60 +1720,6 @@ static void __split_and_process_bio(struct mapped_device *md,
  * 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.
@@ -1789,6 +1733,8 @@ static void dm_make_request(struct request_queue *q, struct bio *bio)
 
 	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);
 
 	/* if we're suspended, we have to queue this io for later */
@@ -2495,59 +2441,6 @@ static void __set_size(struct mapped_device *md, sector_t size)
 	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
 }
 
-/*
- * 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.
  */
@@ -2557,7 +2450,6 @@ 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);
 
@@ -2583,17 +2475,11 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *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);
 
@@ -2874,7 +2760,6 @@ int dm_setup_md_queue(struct mapped_device *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

@@ -78,8 +78,6 @@ bool dm_table_mq_request_based(struct dm_table *t);
 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

@@ -70,7 +70,7 @@
 #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;
 
@@ -181,7 +181,7 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 			/* 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

@@ -52,48 +52,6 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	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;
@@ -297,7 +255,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 		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);
@@ -338,7 +296,6 @@ static struct md_personality linear_personality =
 	.size		= linear_size,
 	.quiesce	= linear_quiesce,
 	.congested	= linear_congested,
-	.mergeable_bvec	= linear_mergeable_bvec,
 };
 
 static int __init linear_init (void)

drivers/md/md.c

@@ -257,13 +257,17 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 	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 */
@@ -350,34 +354,11 @@ static int md_congested(void *data, int bits)
 	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;
@@ -433,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 
 	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);
@@ -728,15 +709,13 @@ void md_rdev_clear(struct md_rdev *rdev)
 }
 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);
 	}
 
@@ -791,7 +770,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 	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;
 }
@@ -5186,7 +5165,6 @@ int md_run(struct mddev *mddev)
 	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 &&
@@ -5315,7 +5293,6 @@ static void md_clean(struct mddev *mddev)
 	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;
@@ -5514,7 +5491,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__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

@@ -134,10 +134,6 @@ enum flag_bits {
 	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
@@ -374,10 +370,6 @@ struct mddev {
 	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;
@@ -532,10 +524,6 @@ struct md_personality
 	/* 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

@@ -77,18 +77,18 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 	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)) {
 		/*
@@ -101,7 +101,7 @@ static void multipath_end_request(struct bio *bio, int error)
 		       (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);
 }
 
@@ -123,7 +123,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 
 	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;
 	}
@@ -257,18 +257,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_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, 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--;
 			rdev->raid_disk = path;
@@ -432,15 +420,6 @@ static int multipath_run (struct mddev *mddev)
 		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

@@ -192,9 +192,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			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++;
@@ -351,58 +348,6 @@ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
 			     + 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;
@@ -543,7 +488,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 		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);
@@ -727,7 +672,6 @@ static struct md_personality raid0_personality=
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
 	.congested	= raid0_congested,
-	.mergeable_bvec	= raid0_mergeable_bvec,
 };
 
 static int __init raid0_init (void)

drivers/md/raid0.h

@@ -12,8 +12,6 @@ struct r0conf {
 	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

@@ -255,9 +255,10 @@ static void call_bio_endio(struct r1bio *r1_bio)
 		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.
@@ -312,9 +313,9 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
 	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;
@@ -397,9 +398,8 @@ static void r1_bio_write_done(struct r1bio *r1_bio)
 	}
 }
 
-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;
@@ -410,7 +410,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
 	/*
 	 * '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,
@@ -557,7 +557,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		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) &&
@@ -708,38 +707,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	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;
@@ -793,7 +760,7 @@ static void flush_pending_writes(struct r1conf *conf)
 			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;
@@ -1068,7 +1035,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		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;
@@ -1158,7 +1125,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	 * 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) {
 		/*
@@ -1269,8 +1236,7 @@ read_again:
 			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;
@@ -1617,7 +1583,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	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;
@@ -1625,11 +1590,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	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;
 		if (!p->rdev) {
@@ -1661,19 +1621,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_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)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1737,7 +1684,7 @@ abort:
 	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;
 
@@ -1748,16 +1695,16 @@ static void end_sync_read(struct bio *bio, int error)
 	 * 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;
@@ -1944,7 +1891,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 		idx ++;
 	}
 	set_bit(R1BIO_Uptodate, &r1_bio->state);
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio->bi_error = 0;
 	return 1;
 }
 
@@ -1968,15 +1915,14 @@ static void process_checks(struct r1bio *r1_bio)
 	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 +
@@ -1999,7 +1945,7 @@ static void process_checks(struct r1bio *r1_bio)
 	}
 	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;
@@ -2009,14 +1955,14 @@ static void process_checks(struct r1bio *r1_bio)
 		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;
@@ -2031,7 +1977,7 @@ static void process_checks(struct r1bio *r1_bio)
 		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);
@@ -2272,11 +2218,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
 		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);
@@ -2715,7 +2661,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 						/* 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;
 				}
@@ -2810,8 +2756,6 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 			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;
@@ -3176,7 +3120,6 @@ static struct md_personality raid1_personality =
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
 	.congested	= raid1_congested,
-	.mergeable_bvec	= raid1_mergeable_bvec,
 };
 
 static int __init raid_init(void)

drivers/md/raid10.c

@@ -101,7 +101,7 @@ static int _enough(struct r10conf *conf, int previous, int ignore);
 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)
@@ -307,9 +307,9 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
 	} 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.
@@ -358,9 +358,9 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	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;
@@ -438,9 +438,8 @@ static void one_write_done(struct r10bio *r10_bio)
 	}
 }
 
-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;
@@ -460,7 +459,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
 	/*
 	 * 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.
@@ -672,93 +671,6 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 	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
@@ -821,12 +733,10 @@ retry:
 		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)
@@ -957,7 +867,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			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;
@@ -1133,7 +1043,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		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;
@@ -1217,7 +1127,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	 * 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) {
 		/*
@@ -1326,11 +1236,9 @@ retry_write:
 			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;
@@ -1777,7 +1685,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	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
@@ -1790,11 +1697,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	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)
 		mirror = rdev->saved_raid_disk;
@@ -1833,19 +1735,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		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)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1916,7 +1805,7 @@ abort:
 	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;
@@ -1928,7 +1817,7 @@ static void end_sync_read(struct bio *bio, int error)
 	} 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
@@ -1977,9 +1866,8 @@ static void end_sync_request(struct r10bio *r10_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);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -1996,7 +1884,7 @@ static void end_sync_write(struct bio *bio, int error)
 	else
 		rdev = conf->mirrors[d].rdev;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			md_error(mddev, rdev);
 		else {
@@ -2044,7 +1932,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 	/* 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)
@@ -2064,7 +1952,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			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;
@@ -2394,7 +2282,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			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) {
@@ -2448,7 +2335,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			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;
 
@@ -2706,8 +2592,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			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,
@@ -2722,8 +2607,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			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,
@@ -2748,8 +2633,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 					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,
@@ -3263,7 +3147,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			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;
@@ -3300,7 +3184,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			/* 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);
@@ -3357,7 +3241,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* 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;
 		}
@@ -3377,7 +3261,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		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);
 		}
 	}
@@ -3643,8 +3527,6 @@ static int run(struct mddev *mddev)
 			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;
@@ -4382,7 +4264,7 @@ read_more:
 	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;
@@ -4439,7 +4321,7 @@ read_more:
 				/* 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;
 		}
@@ -4604,9 +4486,8 @@ static int handle_reshape_read_error(struct mddev *mddev,
 	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;
@@ -4623,7 +4504,7 @@ static void end_reshape_write(struct bio *bio, int error)
 		rdev = conf->mirrors[d].rdev;
 	}
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		/* FIXME should record badblock */
 		md_error(mddev, rdev);
 	}
@@ -4700,7 +4581,6 @@ static struct md_personality raid10_personality =
 	.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

@@ -233,7 +233,7 @@ static void return_io(struct bio *return_bi)
 		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;
 	}
 }
@@ -887,9 +887,9 @@ static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
 }
 
 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)
 {
@@ -2282,12 +2282,11 @@ static void shrink_stripes(struct r5conf *conf)
 	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;
@@ -2296,9 +2295,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		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;
@@ -2317,7 +2316,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		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
@@ -2405,13 +2404,12 @@ static void raid5_end_read_request(struct bio * bi, int error)
 	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;
@@ -2434,23 +2432,23 @@ static void raid5_end_write_request(struct bio *bi, int error)
 			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);
@@ -2471,7 +2469,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
 	}
 	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))
@@ -3112,7 +3110,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		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;
@@ -3136,7 +3135,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		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;
@@ -3161,7 +3161,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			       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;
@@ -4669,35 +4670,6 @@ static int raid5_congested(struct mddev *mddev, int bits)
 	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);
@@ -4756,13 +4728,13 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
  *  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);
 
@@ -4773,10 +4745,10 @@ static void raid5_align_endio(struct bio *bi, int error)
 
 	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;
@@ -4787,26 +4759,7 @@ static void raid5_align_endio(struct bio *bi, int error)
 	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;
@@ -4815,7 +4768,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	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;
 	}
 	/*
@@ -4857,13 +4810,11 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		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;
@@ -4892,6 +4843,31 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	}
 }
 
+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
  *
  * Full stripe writes are allowed to pass preread active stripes up until
@@ -5140,7 +5116,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	remaining = raid5_dec_bi_active_stripes(bi);
 	if (remaining == 0) {
 		md_write_end(mddev);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
@@ -5169,9 +5145,11 @@ static void make_request(struct mddev *mddev, struct bio * 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);
@@ -5304,7 +5282,7 @@ static void make_request(struct mddev *mddev, struct bio * 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;
 		}
 	}
@@ -5318,7 +5296,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
-		bio_endio(bi, 0);
+		bio_endio(bi);
 	}
 }
 
@@ -5714,7 +5692,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	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);
@@ -7779,7 +7757,6 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.congested	= raid5_congested,
-	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 static struct md_personality raid5_personality =
 {
@@ -7803,7 +7780,6 @@ 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 =
@@ -7828,7 +7804,6 @@ 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

@@ -165,7 +165,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 		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

@@ -419,7 +419,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 
 	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

@@ -180,7 +180,7 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	 * 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;
 	}
 
@@ -199,6 +199,7 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 					"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;
 		}
 	}
@@ -206,7 +207,7 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 		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

@@ -1189,7 +1189,7 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 	 * 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;
 	}
 
@@ -1211,6 +1211,7 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 					"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;
 		}
 	}
@@ -1218,7 +1219,7 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 		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

@@ -77,7 +77,7 @@ static void pmem_make_request(struct request_queue *q, struct bio *bio)
 	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

@@ -826,6 +826,8 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 	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)
@@ -871,7 +873,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 		}
 		bytes_done += bvec.bv_len;
 	}
-	bio_endio(bio, 0);
+	bio_endio(bio);
 	return;
 fail:
 	bio_io_error(bio);

drivers/s390/block/xpram.c

@@ -190,6 +190,8 @@ static void xpram_make_request(struct request_queue *q, struct bio *bio)
 	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. */
@@ -220,8 +222,7 @@ static void xpram_make_request(struct request_queue *q, struct bio *bio)
 			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

@@ -647,7 +647,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	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;
 
@@ -675,7 +675,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 		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

@@ -340,6 +340,8 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 	int rw = bio_rw(old_bio);
 	int inactive;
 
+	blk_queue_split(q, &old_bio, q->bio_split);
+
 	if (!lo)
 		goto err;
 
@@ -376,7 +378,8 @@ static inline void loop_handle_bio(struct lloop_device *lo, struct bio *bio)
 	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

@@ -306,20 +306,13 @@ static void iblock_complete_cmd(struct se_cmd *cmd)
 	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.
 		 */
@@ -370,15 +363,15 @@ static void iblock_submit_bios(struct bio_list *list, int rw)
 	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

@@ -852,7 +852,7 @@ static ssize_t pscsi_show_configfs_dev_params(struct se_device *dev, char *b)
 	return bl;
 }
 
-static void pscsi_bi_endio(struct bio *bio, int error)
+static void pscsi_bi_endio(struct bio *bio)
 {
 	bio_put(bio);
 }
@@ -973,7 +973,7 @@ fail:
 	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;
 }
@@ -1061,7 +1061,7 @@ fail_free_bio:
 	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

@@ -343,7 +343,7 @@ static int btrfsic_process_written_superblock(
 		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,
@@ -2207,7 +2207,7 @@ continue_loop:
 	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;
@@ -2215,7 +2215,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status)
 	/* 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);
@@ -2230,7 +2230,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status)
 		     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);
@@ -2252,7 +2252,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status)
 		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

@@ -97,10 +97,7 @@ static inline int compressed_bio_size(struct btrfs_root *root,
 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,
@@ -152,7 +149,7 @@ fail:
  * 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;
@@ -160,7 +157,7 @@ static void end_compressed_bio_read(struct bio *bio, int err)
 	unsigned long index;
 	int ret;
 
-	if (err)
+	if (bio->bi_error)
 		cb->errors = 1;
 
 	/* if there are more bios still pending for this compressed
@@ -210,7 +207,7 @@ csum_failed:
 		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 */
@@ -266,7 +263,7 @@ static noinline void end_compressed_writeback(struct inode *inode,
  * 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;
@@ -274,7 +271,7 @@ static void end_compressed_bio_write(struct bio *bio, int err)
 	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
@@ -293,7 +290,7 @@ static void end_compressed_bio_write(struct bio *bio, int err)
 					 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);
@@ -697,8 +694,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *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);
 
@@ -724,8 +723,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *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;