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
  ...

25 files changed, 109 insertions, 224 deletions

diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 46c282fff104..dd73e1ff1759 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/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;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 422b7d84f686..ad80c85e0857 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/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);
 }
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index e774c50b6842..ffd1947500c6 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/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;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 64ab4951e9d6..f9ab74505e69 100644
--- a/drivers/block/brd.c
+++ b/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);
 
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 1318e3217cb0..b3868e7a1ffd 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/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:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 434c77dcc99e..e5e0f19ceda0 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/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
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index efd19c2da9c2..015c6e91b756 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/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);
 }
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a1518539b858..74d97f4bac34 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/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);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 74df8cfad414..e80cbefbc2b5 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/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);
 		}
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3907202fb9d9..211592682169 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/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;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d0fae55d871d..5578c1477ba6 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/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);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index a08cda955285..331363e7de0f 100644
--- a/drivers/block/floppy.c
+++ b/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);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f7a4c9d7f721..f9889b6bc02c 100644
--- a/drivers/block/loop.c
+++ b/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);
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 0e385d8e9b86..f169faf9838a 100644
--- a/drivers/block/nbd.c
+++ b/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;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 3177b245d2bd..17269a3b85f2 100644
--- a/drivers/block/null_blk.c
+++ b/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;
 	}
 
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 7920c2741b47..2f694d78da55 100644
--- a/drivers/block/nvme-core.c
+++ b/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;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4c20c228184c..7be2375db7f2 100644
--- a/drivers/block/pktcdvd.c
+++ b/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;
 }
 
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index b1612eb16172..d89fcac59515 100644
--- a/drivers/block/ps3vram.c
+++ b/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);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index bc67a93aa4f4..698f761037ce 100644
--- a/drivers/block/rbd.c
+++ b/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;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index ac8c62cb4875..3163e4cdc2cc 100644
--- a/drivers/block/rsxx/dev.c
+++ b/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 -------------------*/
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 1e46eb2305c0..586f9168ffa4 100644
--- a/drivers/block/skd_main.c
+++ b/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);
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 4cf81b5bf0f7..04d65790a886 100644
--- a/drivers/block/umem.c
+++ b/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;
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 954c0029fb3b..6a685aec6994 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/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);
 }
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 7a8a73f1fc04..5f6b3be0a93c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/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);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 763301c7828c..9c01f5bfa33f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/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