[PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

The way the block layer is currently written, it goes to great lengths
to avoid having to split bios; upper layer code (such as bio_add_page())
checks what the underlying device can handle and tries to always create
bios that don't need to be split.

But this approach becomes unwieldy and eventually breaks down with
stacked devices and devices with dynamic limits, and it adds a lot of
complexity. If the block layer could split bios as needed, we could
eliminate a lot of complexity elsewhere - 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
(potentially multiple) devices underneath them.  In the future this will
let us delete merge_bvec_fn and a bunch of other code.

We do this by adding calls to blk_queue_split() to the various
make_request functions that need it - a few can already handle arbitrary
size bios. Note that we add the call _after_ any call to
blk_queue_bounce(); this means that blk_queue_split() and
blk_recalc_rq_segments() don't need to be concerned with bouncing
affecting segment merging.

Some make_request_fn() callbacks were simple enough to audit and verify
they don't need blk_queue_split() calls. The skipped ones are:

 * nfhd_make_request (arch/m68k/emu/nfblock.c)
 * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
 * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
 * brd_make_request (ramdisk - drivers/block/brd.c)
 * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
 * loop_make_request
 * null_queue_bio
 * bcache's make_request fns

Some others are almost certainly safe to remove now, but will be left
for future patches.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Ming Lei <ming.lei@canonical.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Jim Paris <jim@jtan.com>
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-core.c                            |  19 ++--
 block/blk-merge.c                           | 159 ++++++++++++++++++++++++++--
 block/blk-mq.c                              |   4 +
 block/blk-sysfs.c                           |   3 +
 drivers/block/drbd/drbd_req.c               |   2 +
 drivers/block/pktcdvd.c                     |   6 +-
 drivers/block/ps3vram.c                     |   2 +
 drivers/block/rsxx/dev.c                    |   2 +
 drivers/block/umem.c                        |   2 +
 drivers/block/zram/zram_drv.c               |   2 +
 drivers/md/dm.c                             |   2 +
 drivers/md/md.c                             |   2 +
 drivers/s390/block/dcssblk.c                |   2 +
 drivers/s390/block/xpram.c                  |   2 +
 drivers/staging/lustre/lustre/llite/lloop.c |   2 +
 include/linux/blkdev.h                      |   3 +
 16 files changed, 192 insertions(+), 22 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 82819e6..cecf80c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -645,6 +645,10 @@ 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 +657,7 @@ 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 +699,8 @@ 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 +1618,8 @@ 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
@@ -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,
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 30a0d9f..3707f30 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,12 +9,158 @@
 
 #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;
+	int prev = 0;
+
+	struct bvec_merge_data bvm = {
+		.bi_bdev	= bio->bi_bdev,
+		.bi_sector	= bio->bi_iter.bi_sector,
+		.bi_size	= 0,
+		.bi_rw		= bio->bi_rw,
+	};
+
+	bio_for_each_segment(bv, bio, iter) {
+		if (q->merge_bvec_fn &&
+		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
+			goto split;
+
+		bvm.bi_size += bv.bv_len;
+
+		if (bvm.bi_size >> 9 > 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 (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
+		    prev && bvec_gap_to_prev(&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 +182,6 @@ 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 +191,7 @@ 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 +211,8 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f537796..40d08e3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,6 +1291,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
@@ -1376,6 +1378,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6264b38..9a25db3 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -523,6 +523,9 @@ 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);
 }
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3907202..a6265bc 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1497,6 +1497,8 @@ 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;
 
 	/*
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4c20c22..05a81ae 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -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);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index b1612eb..748c63c 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -605,6 +605,8 @@ 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/rsxx/dev.c b/drivers/block/rsxx/dev.c
index ac8c62c..50ef199 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -148,6 +148,8 @@ 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)
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 4cf81b5..13d577c 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -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/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fb655e8..44e3b89 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -901,6 +901,8 @@ 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);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f331d88..530fc9a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1800,6 +1800,8 @@ 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 */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d429c30..10bf6d4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -257,6 +257,8 @@ 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);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index da21281..267ca3a 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/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)
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 7d4e939..1305ed3 100644
--- a/drivers/s390/block/xpram.c
+++ b/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. */
diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c
index cc00fd1..1e33d54 100644
--- a/drivers/staging/lustre/lustre/llite/lloop.c
+++ b/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;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4068c1..dc89cc8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -462,6 +462,7 @@ struct request_queue {
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
+	struct bio_set		*bio_split;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -782,6 +783,8 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
+extern void blk_queue_split(struct request_queue *, struct bio **,
+			    struct bio_set *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
-- 
1.9.1

[PATCH v5 02/11] block: simplify bio_add_page()

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

Since generic_make_request() can now handle arbitrary size bios, all we
have to do is make sure the bvec array doesn't overflow.
__bio_add_page() doesn't need to call ->merge_bvec_fn(), where
we can get rid of unnecessary code paths.

Removing the call to ->merge_bvec_fn() is also fine, as no driver that
implements support for BLOCK_PC commands even has a ->merge_bvec_fn()
method.

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: rebase and resolve merge conflicts, change a couple of comments,
 make bio_add_page() warn once upon a cloned bio.]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/bio.c | 135 +++++++++++++++++++++++++-----------------------------------
 1 file changed, 55 insertions(+), 80 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 2a00d34..da15e9a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -714,9 +714,23 @@ int bio_get_nr_vecs(struct block_device *bdev)
 }
 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)
+/**
+ *	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)
 {
 	int retried_segments = 0;
 	struct bio_vec *bvec;
@@ -727,7 +741,7 @@ 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 +754,7 @@ 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;
 		}
@@ -804,27 +797,6 @@ 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);
@@ -841,28 +813,6 @@ 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 +822,47 @@ 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;
 
-	max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
-	if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
-		max_sectors = len >> 9;
+	/*
+	 * cloned bio must not modify vec list
+	 */
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return 0;
 
-	return __bio_add_page(q, bio, page, len, offset, max_sectors);
+	/*
+	 * For filesystems with a blocksize smaller than the pagesize
+	 * we will often be called with the same page as last time and
+	 * a consecutive offset.  Optimize this special case.
+	 */
+	if (bio->bi_vcnt > 0) {
+		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (page == bv->bv_page &&
+		    offset == bv->bv_offset + bv->bv_len) {
+			bv->bv_len += len;
+			goto done;
+		}
+	}
+
+	if (bio->bi_vcnt >= bio->bi_max_vecs)
+		return 0;
+
+	bv		= &bio->bi_io_vec[bio->bi_vcnt];
+	bv->bv_page	= page;
+	bv->bv_len	= len;
+	bv->bv_offset	= offset;
+
+	bio->bi_vcnt++;
+done:
+	bio->bi_iter.bi_size += len;
+	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
 
-- 
1.9.1

[PATCH v5 03/11] bcache: remove driver private bio splitting code

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

The bcache driver has always accepted arbitrarily large bios and split
them internally.  Now that every driver must accept arbitrarily large
bios this code isn't nessecary anymore.

Cc: linux-bcache@vger.kernel.org
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 drivers/md/bcache/bcache.h    |  18 --------
 drivers/md/bcache/io.c        | 100 +-----------------------------------------
 drivers/md/bcache/journal.c   |   4 +-
 drivers/md/bcache/request.c   |  16 +++----
 drivers/md/bcache/super.c     |  32 +-------------
 drivers/md/bcache/util.h      |   5 ++-
 drivers/md/bcache/writeback.c |   4 +-
 7 files changed, 18 insertions(+), 161 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 04f7bc2..6b420a5 100644
--- a/drivers/md/bcache/bcache.h
+++ b/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);
 
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index cb64e64a..86a0bb8 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -11,104 +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);
-submit:
-	generic_make_request(bio);
-}
-
 /* Bios with headers */
 
 void bch_bbio_free(struct bio *bio, struct cache_set *c)
@@ -138,7 +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,
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index ce64fc8..54c02da 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -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
@@ -646,7 +646,7 @@ 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);
 }
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 4afb2d2..41e06da 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -711,7 +711,7 @@ 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);
@@ -834,7 +834,7 @@ 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:
@@ -842,7 +842,7 @@ 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;
 }
 
@@ -907,7 +907,7 @@ 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;
@@ -922,12 +922,12 @@ 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);
@@ -943,7 +943,7 @@ 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);
 }
@@ -987,7 +987,7 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
 			bio_endio(bio, 0);
 		else
-			bch_generic_make_request(bio, &d->bio_split_hook);
+			generic_make_request(bio);
 	}
 }
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 94980bf..db70c9e 100644
--- a/drivers/md/bcache/super.c
+++ b/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,
@@ -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;
@@ -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);
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 1d04c48..cf2cbc2 100644
--- a/drivers/md/bcache/util.h
+++ b/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);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index f1986bc..ca38362 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -188,7 +188,7 @@ 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);
 }
@@ -208,7 +208,7 @@ 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);
 }
-- 
1.9.1

[PATCH v5 04/11] btrfs: remove bio splitting and merge_bvec_fn() calls

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

Btrfs has been doing bio splitting from btrfs_map_bio(), by checking
device limits as well as calling ->merge_bvec_fn() etc. That is not
necessary any more, because generic_make_request() is now able to
handle arbitrarily sized bios. So clean up unnecessary code paths.

Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <jbacik@fb.com>
Cc: linux-btrfs@vger.kernel.org
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 fs/btrfs/volumes.c | 72 ------------------------------------------------------
 1 file changed, 72 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4b438b4..fd25b81 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5833,34 +5833,6 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 				 &device->work);
 }
 
-static int bio_size_ok(struct block_device *bdev, struct bio *bio,
-		       sector_t sector)
-{
-	struct bio_vec *prev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int max_sectors = queue_max_sectors(q);
-	struct bvec_merge_data bvm = {
-		.bi_bdev = bdev,
-		.bi_sector = sector,
-		.bi_rw = bio->bi_rw,
-	};
-
-	if (WARN_ON(bio->bi_vcnt == 0))
-		return 1;
-
-	prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
-	if (bio_sectors(bio) > max_sectors)
-		return 0;
-
-	if (!q->merge_bvec_fn)
-		return 1;
-
-	bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len;
-	if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
-		return 0;
-	return 1;
-}
-
 static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 			      struct bio *bio, u64 physical, int dev_nr,
 			      int rw, int async)
@@ -5894,38 +5866,6 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 		btrfsic_submit_bio(rw, bio);
 }
 
-static int breakup_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
-			      struct bio *first_bio, struct btrfs_device *dev,
-			      int dev_nr, int rw, int async)
-{
-	struct bio_vec *bvec = first_bio->bi_io_vec;
-	struct bio *bio;
-	int nr_vecs = bio_get_nr_vecs(dev->bdev);
-	u64 physical = bbio->stripes[dev_nr].physical;
-
-again:
-	bio = btrfs_bio_alloc(dev->bdev, physical >> 9, nr_vecs, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-
-	while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
-		if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len) {
-			u64 len = bio->bi_iter.bi_size;
-
-			atomic_inc(&bbio->stripes_pending);
-			submit_stripe_bio(root, bbio, bio, physical, dev_nr,
-					  rw, async);
-			physical += len;
-			goto again;
-		}
-		bvec++;
-	}
-
-	submit_stripe_bio(root, bbio, bio, physical, dev_nr, rw, async);
-	return 0;
-}
-
 static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 {
 	atomic_inc(&bbio->error);
@@ -5998,18 +5938,6 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 			continue;
 		}
 
-		/*
-		 * Check and see if we're ok with this bio based on it's size
-		 * and offset with the given device.
-		 */
-		if (!bio_size_ok(dev->bdev, first_bio,
-				 bbio->stripes[dev_nr].physical >> 9)) {
-			ret = breakup_stripe_bio(root, bbio, first_bio, dev,
-						 dev_nr, rw, async_submit);
-			BUG_ON(ret);
-			continue;
-		}
-
 		if (dev_nr < total_devs - 1) {
 			bio = btrfs_bio_clone(first_bio, GFP_NOFS);
 			BUG_ON(!bio); /* -ENOMEM */
-- 
1.9.1

[PATCH v5 05/11] block: remove split code in blkdev_issue_discard

[Ming Lin]

From: Ming Lin <ming.l@ssi.samsung.com>

The split code in blkdev_issue_discard() can go away now
that any driver that cares does the split.

Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-lib.c | 73 +++++++++++----------------------------------------------
 1 file changed, 14 insertions(+), 59 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3..3bf3c4a 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -43,34 +43,17 @@ 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;
 	struct blk_plug plug;
 
-	if (!q)
+	if (!q || !nr_sects)
 		return -ENXIO;
 
 	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;
@@ -82,52 +65,24 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	bb.wait = &wait;
 
 	blk_start_plug(&plug);
-	while (nr_sects) {
-		unsigned int req_sects;
-		sector_t end_sect, tmp;
 
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
+	bio = bio_alloc(gfp_mask, 1);
+	if (!bio) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
-		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.
-		 */
-		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;
+	bio->bi_bdev = bdev;
+	bio->bi_private = &bb;
 
-		bio->bi_iter.bi_sector = sector;
-		bio->bi_end_io = bio_batch_end_io;
-		bio->bi_bdev = bdev;
-		bio->bi_private = &bb;
+	bio->bi_iter.bi_size = nr_sects << 9;
 
-		bio->bi_iter.bi_size = req_sects << 9;
-		nr_sects -= req_sects;
-		sector = end_sect;
+	atomic_inc(&bb.done);
+	submit_bio(type, bio);
 
-		atomic_inc(&bb.done);
-		submit_bio(type, bio);
-
-		/*
-		 * We can loop for a long time in here, if someone does
-		 * full device discards (like mkfs). Be nice and allow
-		 * us to schedule out to avoid softlocking if preempt
-		 * is disabled.
-		 */
-		cond_resched();
-	}
+out:
 	blk_finish_plug(&plug);
 
 	/* Wait for bios in-flight */
-- 
1.9.1

[PATCH v5 06/11] md/raid5: split bio for chunk_aligned_read

[Ming Lin]

From: Ming Lin <ming.l@ssi.samsung.com>

If a read request fits entirely in a chunk, it will be passed directly to the
underlying device (providing it hasn't failed of course).  If it doesn't fit,
the slightly less efficient path that uses the stripe_cache is used.
Requests that get to the stripe cache are always completely split up as
necessary.

So with RAID5, ripping out the merge_bvec_fn doesn't cause it to stop work,
but could cause it to take the less efficient path more often.

All that is needed to manage this is for 'chunk_aligned_read' do some bio
splitting, much like the RAID0 code does.

Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Acked-by: NeilBrown <neilb@suse.de>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 drivers/md/raid5.c | 37 ++++++++++++++++++++++++++++++++-----
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 59e44e9..8377e72 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4799,7 +4799,7 @@ static int bio_fits_rdev(struct bio *bi)
 	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;
@@ -4808,7 +4808,7 @@ 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;
 	}
 	/*
@@ -4885,6 +4885,31 @@ 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
@@ -5162,9 +5187,11 @@ 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);
-- 
1.9.1

[PATCH v5 07/11] md/raid5: get rid of bio_fits_rdev()

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

Remove bio_fits_rdev() as sufficient merge_bvec_fn() handling is now
performed by blk_queue_split() in md_make_request().

Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Acked-by: NeilBrown <neilb@suse.de>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 drivers/md/raid5.c | 23 +----------------------
 1 file changed, 1 insertion(+), 22 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8377e72..8bdf81a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4780,25 +4780,6 @@ 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 raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct r5conf *conf = mddev->private;
@@ -4852,11 +4833,9 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		align_bi->bi_bdev =  rdev->bdev;
 		__clear_bit(BIO_SEG_VALID, &align_bi->bi_flags);
 
-		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;
-- 
1.9.1

[PATCH v5 08/11] block: kill merge_bvec_fn() completely

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

As generic_make_request() is now able to handle arbitrarily sized bios,
it's no longer necessary for each individual block driver to define its
own ->merge_bvec_fn() callback. Remove every invocation completely.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@kernel.org>
Cc: ceph-devel@vger.kernel.org
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: NeilBrown <neilb@suse.de> (for the 'md' bits)
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: also remove ->merge_bvec_fn() in dm-thin as well as
 dm-era-target, and resolve merge conflicts]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-merge.c              |  17 +-----
 block/blk-settings.c           |  22 -------
 drivers/block/drbd/drbd_int.h  |   1 -
 drivers/block/drbd/drbd_main.c |   1 -
 drivers/block/drbd/drbd_req.c  |  35 ------------
 drivers/block/pktcdvd.c        |  21 -------
 drivers/block/rbd.c            |  47 ---------------
 drivers/md/dm-cache-target.c   |  21 -------
 drivers/md/dm-crypt.c          |  16 ------
 drivers/md/dm-era-target.c     |  15 -----
 drivers/md/dm-flakey.c         |  16 ------
 drivers/md/dm-linear.c         |  16 ------
 drivers/md/dm-log-writes.c     |  16 ------
 drivers/md/dm-raid.c           |  19 ------
 drivers/md/dm-snap.c           |  15 -----
 drivers/md/dm-stripe.c         |  21 -------
 drivers/md/dm-table.c          |   8 ---
 drivers/md/dm-thin.c           |  31 ----------
 drivers/md/dm-verity.c         |  16 ------
 drivers/md/dm.c                | 127 +----------------------------------------
 drivers/md/dm.h                |   2 -
 drivers/md/linear.c            |  43 --------------
 drivers/md/md.c                |  26 ---------
 drivers/md/md.h                |  12 ----
 drivers/md/multipath.c         |  21 -------
 drivers/md/raid0.c             |  56 ------------------
 drivers/md/raid0.h             |   2 -
 drivers/md/raid1.c             |  58 +------------------
 drivers/md/raid10.c            | 121 +--------------------------------------
 drivers/md/raid5.c             |  32 -----------
 include/linux/blkdev.h         |  10 ----
 include/linux/device-mapper.h  |   4 --
 32 files changed, 9 insertions(+), 859 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3707f30..1f5dfa0 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -69,24 +69,13 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio *split;
 	struct bio_vec bv, bvprv;
 	struct bvec_iter iter;
-	unsigned seg_size = 0, nsegs = 0;
+	unsigned seg_size = 0, nsegs = 0, sectors = 0;
 	int prev = 0;
 
-	struct bvec_merge_data bvm = {
-		.bi_bdev	= bio->bi_bdev,
-		.bi_sector	= bio->bi_iter.bi_sector,
-		.bi_size	= 0,
-		.bi_rw		= bio->bi_rw,
-	};
-
 	bio_for_each_segment(bv, bio, iter) {
-		if (q->merge_bvec_fn &&
-		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
-			goto split;
-
-		bvm.bi_size += bv.bv_len;
+		sectors += bv.bv_len >> 9;
 
-		if (bvm.bi_size >> 9 > queue_max_sectors(q))
+		if (sectors > queue_max_sectors(q))
 			goto split;
 
 		/*
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 12600bf..e90d477 100644
--- a/block/blk-settings.c
+++ b/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;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index efd19c2..7ac66f3 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);
 
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a151853..74d97f4 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_req.c b/drivers/block/drbd/drbd_req.c
index a6265bc..7523f00 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1510,41 +1510,6 @@ 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/pktcdvd.c b/drivers/block/pktcdvd.c
index 05a81ae..190d7d7 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2506,26 +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;
@@ -2533,7 +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/rbd.c b/drivers/block/rbd.c
index d94529d..055f9fa 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3462,52 +3462,6 @@ 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;
@@ -3806,7 +3760,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.max_discard_sectors = 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/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1b4e175..256e54c 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -3769,26 +3769,6 @@ 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)
 {
 	/*
@@ -3832,7 +3812,6 @@ 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,
 };
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 0f48fed..a1f1d09 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -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,
 };
 
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index ad913cd..0119ebf 100644
--- a/drivers/md/dm-era-target.c
+++ b/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
 };
 
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index b257e46..d955b3e 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -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,
 };
 
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 53e848c..7dd5fc8 100644
--- a/drivers/md/dm-linear.c
+++ b/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,
 };
 
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index ad1b049..883595c 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -728,21 +728,6 @@ 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 +781,6 @@ 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,
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 2daa677..97e1651 100644
--- a/drivers/md/dm-raid.c
+++ b/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)
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 7c82d3c..eabc805 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -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,
 };
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a672a15..c7c8ced 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -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)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 16ba55a..afb4ad3 100644
--- a/drivers/md/dm-table.c
+++ b/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;
 }
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index c33f61a..37ef8b8 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3840,20 +3840,6 @@ 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;
@@ -3930,7 +3916,6 @@ 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,
 };
@@ -4257,21 +4242,6 @@ 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)
 {
@@ -4315,7 +4285,6 @@ 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,
 };
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index bb9c6a0..4f2cdd9 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -648,21 +648,6 @@ 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 +980,6 @@ 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,
 };
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 530fc9a..c5d0d19 100644
--- a/drivers/md/dm.c
+++ b/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.
@@ -1726,67 +1725,6 @@ 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, 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) queue_max_sectors(q));
-	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-
-	/*
-	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
-	 * to the targets' merge function since it holds sectors not bytes).
-	 * Just doing this as an interim fix for stable@ because the more
-	 * comprehensive cleanup of switching to sector_t will impact every
-	 * DM target that implements a ->merge hook.
-	 */
-	if (max_size > INT_MAX)
-		max_size = INT_MAX;
-
-	/*
-	 * 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, (int) 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 for the
-	 * max_hw_sectors that dm_set_device_limits may set), 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.
@@ -2509,59 +2447,6 @@ static void __set_size(struct mapped_device *md, sector_t size)
 }
 
 /*
- * Return 1 if the queue has a compulsory merge_bvec_fn function.
- *
- * If this function returns 0, then the device is either a non-dm
- * device without a merge_bvec_fn, or it is a dm device that is
- * able to split any bios it receives that are too big.
- */
-int dm_queue_merge_is_compulsory(struct request_queue *q)
-{
-	struct mapped_device *dev_md;
-
-	if (!q->merge_bvec_fn)
-		return 0;
-
-	if (q->make_request_fn == dm_make_request) {
-		dev_md = q->queuedata;
-		if (test_bit(DMF_MERGE_IS_OPTIONAL, &dev_md->flags))
-			return 0;
-	}
-
-	return 1;
-}
-
-static int dm_device_merge_is_compulsory(struct dm_target *ti,
-					 struct dm_dev *dev, sector_t start,
-					 sector_t len, void *data)
-{
-	struct block_device *bdev = dev->bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return dm_queue_merge_is_compulsory(q);
-}
-
-/*
- * Return 1 if it is acceptable to ignore merge_bvec_fn based
- * on the properties of the underlying devices.
- */
-static int dm_table_merge_is_optional(struct dm_table *table)
-{
-	unsigned i = 0;
-	struct dm_target *ti;
-
-	while (i < dm_table_get_num_targets(table)) {
-		ti = dm_table_get_target(table, i++);
-
-		if (ti->type->iterate_devices &&
-		    ti->type->iterate_devices(ti, dm_device_merge_is_compulsory, NULL))
-			return 0;
-	}
-
-	return 1;
-}
-
-/*
  * Returns old map, which caller must destroy.
  */
 static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
@@ -2570,7 +2455,6 @@ 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);
 
@@ -2596,17 +2480,11 @@ 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);
 
@@ -2887,7 +2765,6 @@ 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;
 	}
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 4e98499..7edcf97 100644
--- a/drivers/md/dm.h
+++ b/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);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index fa7d577..8721ef9 100644
--- a/drivers/md/linear.c
+++ b/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;
@@ -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)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 10bf6d4..a4aa6e5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -352,29 +352,6 @@ 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
  */
@@ -5188,7 +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 &&
@@ -5317,7 +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 +5489,6 @@ 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' */
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7da6e9c..ab33957 100644
--- a/drivers/md/md.h
+++ b/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 {
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index ac3ede2..7ee27fb 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -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++;
 	}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index efb654e..c853331 100644
--- a/drivers/md/raid0.c
+++ b/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;
@@ -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)
diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
index 05539d9..7127a62 100644
--- a/drivers/md/raid0.h
+++ b/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
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f80f1af..bb90edb 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -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;
@@ -1268,8 +1235,7 @@ 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;
@@ -1614,7 +1580,6 @@ 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;
@@ -1622,11 +1587,6 @@ 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) {
@@ -1658,19 +1618,6 @@ 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);
@@ -2807,8 +2754,6 @@ 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;
@@ -3173,7 +3118,6 @@ 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)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 940f2f3..84cb6bc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -672,93 +672,6 @@ 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 +734,10 @@ 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)
@@ -1326,11 +1237,9 @@ 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 +1686,6 @@ 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 +1698,6 @@ 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 +1736,6 @@ 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);
@@ -2394,7 +2284,6 @@ 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 +2337,6 @@ 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;
 
@@ -3642,8 +3530,6 @@ 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;
@@ -4697,7 +4583,6 @@ 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)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8bdf81a..5f938c0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4662,35 +4662,6 @@ 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);
@@ -7763,7 +7734,6 @@ 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 =
 {
@@ -7787,7 +7757,6 @@ 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 =
@@ -7812,7 +7781,6 @@ 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)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index dc89cc8..56cf082 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -213,14 +213,6 @@ typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
 
 struct bio_vec;
-struct bvec_merge_data {
-	struct block_device *bi_bdev;
-	sector_t bi_sector;
-	unsigned bi_size;
-	unsigned long bi_rw;
-};
-typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
-			     struct bio_vec *);
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
@@ -305,7 +297,6 @@ struct request_queue {
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unprep_rq_fn		*unprep_rq_fn;
-	merge_bvec_fn		*merge_bvec_fn;
 	softirq_done_fn		*softirq_done_fn;
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
@@ -991,7 +982,6 @@ extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
 extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn);
-extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 51cc1de..76d23fa 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -82,9 +82,6 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
 typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 			    unsigned long arg);
 
-typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
-			    struct bio_vec *biovec, int max_size);
-
 /*
  * These iteration functions are typically used to check (and combine)
  * properties of underlying devices.
@@ -160,7 +157,6 @@ struct target_type {
 	dm_status_fn status;
 	dm_message_fn message;
 	dm_ioctl_fn ioctl;
-	dm_merge_fn merge;
 	dm_busy_fn busy;
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
-- 
1.9.1

[PATCH v5 09/11] fs: use helper bio_add_page() instead of open coding on bi_io_vec

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

Call pre-defined helper bio_add_page() instead of open coding for
iterating through bi_io_vec[]. Doing that, it's possible to make some
parts in filesystems and mm/page_io.c simpler than before.

Acked-by: Dave Kleikamp <shaggy@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: add more description in commit message]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 fs/buffer.c         |  7 ++-----
 fs/jfs/jfs_logmgr.c | 14 ++++----------
 mm/page_io.c        |  8 +++-----
 3 files changed, 9 insertions(+), 20 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 1cf7a53..95996ba 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3046,12 +3046,9 @@ static int submit_bh_wbc(int rw, struct buffer_head *bh,
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
-	bio->bi_io_vec[0].bv_page = bh->b_page;
-	bio->bi_io_vec[0].bv_len = bh->b_size;
-	bio->bi_io_vec[0].bv_offset = bh_offset(bh);
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = bh->b_size;
+	bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	BUG_ON(bio->bi_iter.bi_size != bh->b_size);
 
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index bc462dc..46fae06 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1999,12 +1999,9 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
 
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	bio->bi_bdev = log->bdev;
-	bio->bi_io_vec[0].bv_page = bp->l_page;
-	bio->bi_io_vec[0].bv_len = LOGPSIZE;
-	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = LOGPSIZE;
+	bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
@@ -2145,12 +2142,9 @@ static void lbmStartIO(struct lbuf * bp)
 	bio = bio_alloc(GFP_NOFS, 1);
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	bio->bi_bdev = log->bdev;
-	bio->bi_io_vec[0].bv_page = bp->l_page;
-	bio->bi_io_vec[0].bv_len = LOGPSIZE;
-	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
-	bio->bi_vcnt = 1;
-	bio->bi_iter.bi_size = LOGPSIZE;
+	bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
 
 	bio->bi_end_io = lbmIODone;
 	bio->bi_private = bp;
diff --git a/mm/page_io.c b/mm/page_io.c
index 520baa4..194081b 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -33,12 +33,10 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
 	if (bio) {
 		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
 		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
-		bio->bi_io_vec[0].bv_page = page;
-		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
-		bio->bi_io_vec[0].bv_offset = 0;
-		bio->bi_vcnt = 1;
-		bio->bi_iter.bi_size = PAGE_SIZE;
 		bio->bi_end_io = end_io;
+
+		bio_add_page(bio, page, PAGE_SIZE, 0);
+		BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE);
 	}
 	return bio;
 }
-- 
1.9.1

[PATCH v5 10/11] block: remove bio_get_nr_vecs()

[Ming Lin]

From: Kent Overstreet <kent.overstreet@gmail.com>

We can always fill up the bio now, no need to estimate the possible
size based on queue parameters.

Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[hch: rebased and wrote a changelog]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/bio.c            | 23 -----------------------
 drivers/md/dm-io.c     |  2 +-
 fs/btrfs/compression.c |  5 +----
 fs/btrfs/extent_io.c   |  9 ++-------
 fs/btrfs/inode.c       |  3 +--
 fs/btrfs/scrub.c       | 18 ++----------------
 fs/direct-io.c         |  2 +-
 fs/ext4/page-io.c      |  3 +--
 fs/ext4/readpage.c     |  2 +-
 fs/f2fs/data.c         |  2 +-
 fs/gfs2/lops.c         |  9 +--------
 fs/logfs/dev_bdev.c    |  4 ++--
 fs/mpage.c             |  4 ++--
 fs/nilfs2/segbuf.c     |  2 +-
 fs/xfs/xfs_aops.c      |  3 +--
 include/linux/bio.h    |  1 -
 16 files changed, 18 insertions(+), 74 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index da15e9a..f28ca16 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -692,29 +692,6 @@ integrity_clone:
 EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
- *	bio_get_nr_vecs		- return approx number of vecs
- *	@bdev:  I/O target
- *
- *	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.
- */
-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);
-
-/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 74adcd2..7d64272 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -314,7 +314,7 @@ 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);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ce62324..449c752 100644
--- a/fs/btrfs/compression.c
+++ b/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,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 02d0581..ba89efd 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2802,9 +2802,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 {
 	int ret = 0;
 	struct bio *bio;
-	int nr;
 	int contig = 0;
-	int this_compressed = bio_flags & EXTENT_BIO_COMPRESSED;
 	int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
 	size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE);
 
@@ -2829,12 +2827,9 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			return 0;
 		}
 	}
-	if (this_compressed)
-		nr = BIO_MAX_PAGES;
-	else
-		nr = bio_get_nr_vecs(bdev);
 
-	bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+	bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES,
+			GFP_NOFS | __GFP_HIGH);
 	if (!bio)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 855935f..d66b9a3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7959,8 +7959,7 @@ out:
 static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 				       u64 first_sector, gfp_t gfp_flags)
 {
-	int nr_vecs = bio_get_nr_vecs(bdev);
-	return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
+	return btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
 }
 
 static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9f2feab..aab0b9a 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -454,27 +454,14 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	struct scrub_ctx *sctx;
 	int		i;
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
-	int pages_per_rd_bio;
 	int ret;
 
-	/*
-	 * the setting of pages_per_rd_bio is correct for scrub but might
-	 * be wrong for the dev_replace code where we might read from
-	 * different devices in the initial huge bios. However, that
-	 * code is able to correctly handle the case when adding a page
-	 * to a bio fails.
-	 */
-	if (dev->bdev)
-		pages_per_rd_bio = min_t(int, SCRUB_PAGES_PER_RD_BIO,
-					 bio_get_nr_vecs(dev->bdev));
-	else
-		pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
 	sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
 	if (!sctx)
 		goto nomem;
 	atomic_set(&sctx->refs, 1);
 	sctx->is_dev_replace = is_dev_replace;
-	sctx->pages_per_rd_bio = pages_per_rd_bio;
+	sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
 	sctx->curr = -1;
 	sctx->dev_root = dev->dev_root;
 	for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
@@ -3895,8 +3882,7 @@ static int scrub_setup_wr_ctx(struct scrub_ctx *sctx,
 		return 0;
 
 	WARN_ON(!dev->bdev);
-	wr_ctx->pages_per_wr_bio = min_t(int, SCRUB_PAGES_PER_WR_BIO,
-					 bio_get_nr_vecs(dev->bdev));
+	wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
 	wr_ctx->tgtdev = dev;
 	atomic_set(&wr_ctx->flush_all_writes, 0);
 	return 0;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 745d234..89baebe 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -653,7 +653,7 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio,
 	if (ret)
 		goto out;
 	sector = start_sector << (sdio->blkbits - 9);
-	nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev));
+	nr_pages = min(sdio->pages_in_io, BIO_MAX_PAGES);
 	BUG_ON(nr_pages <= 0);
 	dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages);
 	sdio->boundary = 0;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 5602450..e678ad3 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -375,10 +375,9 @@ void ext4_io_submit_init(struct ext4_io_submit *io,
 static int io_submit_init_bio(struct ext4_io_submit *io,
 			      struct buffer_head *bh)
 {
-	int nvecs = bio_get_nr_vecs(bh->b_bdev);
 	struct bio *bio;
 
-	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
+	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 	if (!bio)
 		return -ENOMEM;
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index ec3ef93..37c886c 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -284,7 +284,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 					goto set_error_page;
 			}
 			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
 					ext4_release_crypto_ctx(ctx);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9bedfa8..53866ce 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1552,7 +1552,7 @@ submit_and_realloc:
 			}
 
 			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
 					f2fs_release_crypto_ctx(ctx);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 2c1ae86..64d3116 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -261,18 +261,11 @@ void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
 static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
 {
 	struct super_block *sb = sdp->sd_vfs;
-	unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
 	struct bio *bio;
 
 	BUG_ON(sdp->sd_log_bio);
 
-	while (1) {
-		bio = bio_alloc(GFP_NOIO, nrvecs);
-		if (likely(bio))
-			break;
-		nrvecs = max(nrvecs/2, 1U);
-	}
-
+	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
 	bio->bi_bdev = sb->s_bdev;
 	bio->bi_end_io = gfs2_end_log_write;
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 76279e1..fbb5f95 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -83,7 +83,7 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
+	max_pages = min(nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);
@@ -175,7 +175,7 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
+	max_pages = min(nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);
diff --git a/fs/mpage.c b/fs/mpage.c
index ca0244b..4b92133 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -277,7 +277,7 @@ alloc_new:
 				goto out;
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-			  	min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
+				min_t(int, nr_pages, BIO_MAX_PAGES),
 				GFP_KERNEL);
 		if (bio == NULL)
 			goto confused;
@@ -602,7 +602,7 @@ alloc_new:
 			}
 		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-				bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
+				BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
 		if (bio == NULL)
 			goto confused;
 
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 42468e5..4b59031 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -415,7 +415,7 @@ static void nilfs_segbuf_prepare_write(struct nilfs_segment_buffer *segbuf,
 {
 	wi->bio = NULL;
 	wi->rest_blocks = segbuf->sb_sum.nblocks;
-	wi->max_pages = bio_get_nr_vecs(wi->nilfs->ns_bdev);
+	wi->max_pages = BIO_MAX_PAGES;
 	wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
 	wi->start = wi->end = 0;
 	wi->blocknr = segbuf->sb_pseg_start;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3859f5e..89a8c15 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -382,8 +382,7 @@ STATIC struct bio *
 xfs_alloc_ioend_bio(
 	struct buffer_head	*bh)
 {
-	int			nvecs = bio_get_nr_vecs(bh->b_bdev);
-	struct bio		*bio = bio_alloc(GFP_NOIO, nvecs);
+	struct bio		*bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 
 	ASSERT(bio->bi_private == NULL);
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5e963a6..1608b89 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -440,7 +440,6 @@ void bio_chain(struct bio *, struct bio *);
 extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
-extern int bio_get_nr_vecs(struct block_device *);
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    const struct iov_iter *, gfp_t);
-- 
1.9.1

[PATCH v5 11/11] Documentation: update notes in biovecs about arbitrarily sized bios

[Ming Lin]

From: Dongsu Park <dpark@posteo.net>

Update block/biovecs.txt so that it includes a note on what kind of
effects arbitrarily sized bios would bring to the block layer.
Also fix a trivial typo, bio_iter_iovec.

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-doc@vger.kernel.org
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 Documentation/block/biovecs.txt | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/block/biovecs.txt b/Documentation/block/biovecs.txt
index 74a32ad..2568958 100644
--- a/Documentation/block/biovecs.txt
+++ b/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.
-- 
1.9.1

Re: [PATCH v5 10/11] block: remove bio_get_nr_vecs()

[Steven Whitehouse]

Hi,


On 06/07/15 08:44, Ming Lin wrote:
> From: Kent Overstreet <kent.overstreet@gmail.com>
>
> We can always fill up the bio now, no need to estimate the possible
> size based on queue parameters.
[snip]
> diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
> index 2c1ae86..64d3116 100644
> --- a/fs/gfs2/lops.c
> +++ b/fs/gfs2/lops.c
> @@ -261,18 +261,11 @@ void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
>   static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
>   {
>   	struct super_block *sb = sdp->sd_vfs;
> -	unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
>   	struct bio *bio;
>   
>   	BUG_ON(sdp->sd_log_bio);
>   
> -	while (1) {
> -		bio = bio_alloc(GFP_NOIO, nrvecs);
> -		if (likely(bio))
> -			break;
> -		nrvecs = max(nrvecs/2, 1U);
> -	}
> -
> +	bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
>   	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
>   	bio->bi_bdev = sb->s_bdev;
>   	bio->bi_end_io = gfs2_end_log_write;

When I wrote this loop I understood that bio_alloc(GFP_NOIO, x) was only 
guaranteed to be successful in the case x = 1, and that for x > 1, it 
might return NULL. Does this now mean that for x = BIO_MAX_PAGES it will 
be guaranteed to never return NULL in this case?

Steve.

Re: [PATCH v5 10/11] block: remove bio_get_nr_vecs()

[Ming Lin]

On Mon, Jul 6, 2015 at 3:58 AM, Steven Whitehouse <swhiteho@redhat.com> wrote:
>
> Hi,
>
>
> On 06/07/15 08:44, Ming Lin wrote:
>>
>> From: Kent Overstreet <kent.overstreet@gmail.com>
>>
>> We can always fill up the bio now, no need to estimate the possible
>> size based on queue parameters.
>
> [snip]
>>
>> diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
>> index 2c1ae86..64d3116 100644
>> --- a/fs/gfs2/lops.c
>> +++ b/fs/gfs2/lops.c
>> @@ -261,18 +261,11 @@ void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
>>   static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
>>   {
>>         struct super_block *sb = sdp->sd_vfs;
>> -       unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
>>         struct bio *bio;
>>         BUG_ON(sdp->sd_log_bio);
>>   -     while (1) {
>> -               bio = bio_alloc(GFP_NOIO, nrvecs);
>> -               if (likely(bio))
>> -                       break;
>> -               nrvecs = max(nrvecs/2, 1U);
>> -       }
>> -
>> +       bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
>>         bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
>>         bio->bi_bdev = sb->s_bdev;
>>         bio->bi_end_io = gfs2_end_log_write;
>
>
> When I wrote this loop I understood that bio_alloc(GFP_NOIO, x) was only guaranteed to be successful in the case x = 1, and that for x > 1, it might return NULL. Does this now mean that for x = BIO_MAX_PAGES it will be guaranteed to never return NULL in this case?

Yes, it's guaranteed.

https://lkml.org/lkml/2013/11/26/47

commit df2cb6daa4cbc

Re: [PATCH v5 10/11] block: remove bio_get_nr_vecs()

[Steven Whitehouse]

Hi,

On 06/07/15 18:21, Ming Lin wrote:
> On Mon, Jul 6, 2015 at 3:58 AM, Steven Whitehouse <swhiteho@redhat.com> wrote:
>> Hi,
>>
>>
>> On 06/07/15 08:44, Ming Lin wrote:
>>> From: Kent Overstreet <kent.overstreet@gmail.com>
>>>
>>> We can always fill up the bio now, no need to estimate the possible
>>> size based on queue parameters.
>> [snip]
>>> diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
>>> index 2c1ae86..64d3116 100644
>>> --- a/fs/gfs2/lops.c
>>> +++ b/fs/gfs2/lops.c
>>> @@ -261,18 +261,11 @@ void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
>>>    static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
>>>    {
>>>          struct super_block *sb = sdp->sd_vfs;
>>> -       unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
>>>          struct bio *bio;
>>>          BUG_ON(sdp->sd_log_bio);
>>>    -     while (1) {
>>> -               bio = bio_alloc(GFP_NOIO, nrvecs);
>>> -               if (likely(bio))
>>> -                       break;
>>> -               nrvecs = max(nrvecs/2, 1U);
>>> -       }
>>> -
>>> +       bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
>>>          bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
>>>          bio->bi_bdev = sb->s_bdev;
>>>          bio->bi_end_io = gfs2_end_log_write;
>>
>> When I wrote this loop I understood that bio_alloc(GFP_NOIO, x) was only guaranteed to be successful in the case x = 1, and that for x > 1, it might return NULL. Does this now mean that for x = BIO_MAX_PAGES it will be guaranteed to never return NULL in this case?
> Yes, it's guaranteed.
>
> https://lkml.org/lkml/2013/11/26/47
>
> commit df2cb6daa4cbc

Ok. Feel free to add:
Acked-by: Steven Whitehouse <swhiteho@redhat.com>

Steve.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Mon, Jul 06 2015 at  3:44P -0400,
Ming Lin <mlin@kernel.org> wrote:

> From: Kent Overstreet <kent.overstreet@gmail.com>
> 
> The way the block layer is currently written, it goes to great lengths
> to avoid having to split bios; upper layer code (such as bio_add_page())
> checks what the underlying device can handle and tries to always create
> bios that don't need to be split.
> 
> But this approach becomes unwieldy and eventually breaks down with
> stacked devices and devices with dynamic limits, and it adds a lot of
> complexity. If the block layer could split bios as needed, we could
> eliminate a lot of complexity elsewhere - 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
> (potentially multiple) devices underneath them.  In the future this will
> let us delete merge_bvec_fn and a bunch of other code.
> 
> We do this by adding calls to blk_queue_split() to the various
> make_request functions that need it - a few can already handle arbitrary
> size bios. Note that we add the call _after_ any call to
> blk_queue_bounce(); this means that blk_queue_split() and
> blk_recalc_rq_segments() don't need to be concerned with bouncing
> affecting segment merging.
> 
> Some make_request_fn() callbacks were simple enough to audit and verify
> they don't need blk_queue_split() calls. The skipped ones are:
> 
>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
>  * brd_make_request (ramdisk - drivers/block/brd.c)
>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
>  * loop_make_request
>  * null_queue_bio
>  * bcache's make_request fns
> 
> Some others are almost certainly safe to remove now, but will be left
> for future patches.
> 
> Cc: Jens Axboe <axboe@kernel.dk>
> Cc: Christoph Hellwig <hch@infradead.org>
> Cc: Al Viro <viro@zeniv.linux.org.uk>
> Cc: Ming Lei <ming.lei@canonical.com>
> Cc: Neil Brown <neilb@suse.de>
> Cc: Alasdair Kergon <agk@redhat.com>
> Cc: Mike Snitzer <snitzer@redhat.com>
> Cc: dm-devel@redhat.com
> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
> Cc: drbd-user@lists.linbit.com
> Cc: Jiri Kosina <jkosina@suse.cz>
> Cc: Geoff Levand <geoff@infradead.org>
> Cc: Jim Paris <jim@jtan.com>
> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
> Cc: Minchan Kim <minchan@kernel.org>
> Cc: Nitin Gupta <ngupta@vflare.org>
> Cc: Oleg Drokin <oleg.drokin@intel.com>
> Cc: Andreas Dilger <andreas.dilger@intel.com>
> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
> Signed-off-by: Dongsu Park <dpark@posteo.net>
> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
...
> diff --git a/block/blk-merge.c b/block/blk-merge.c
> index 30a0d9f..3707f30 100644
> --- a/block/blk-merge.c
> +++ b/block/blk-merge.c
> @@ -9,12 +9,158 @@
>  
>  #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);
> +}

This code to stop the discard at the previous aligned sector could be
the reason why I have 2 device-mapper-test-suite tests in the
'thin-provisioning' testsuite failing due to this patchset:

  4) Failure:
test_discard_a_fragmented_device(DiscardQuickTests)
    [/root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:49:in `block in assert_no_mappings'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `call'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `block in with_dev_md'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `each'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `with_dev_md'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:48:in `assert_no_mappings'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:263:in `test_discard_a_fragmented_device']:
<0> expected but was
<131072>.

  5) Failure:
test_discard_fully_provisioned_device_benchmark(DiscardQuickTests)
    [/root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:49:in `block in assert_no_mappings'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `call'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `block in with_dev_md'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `each'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `with_dev_md'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:48:in `assert_no_mappings'
     /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:225:in `test_discard_fully_provisioned_device_benchmark']:
<0> expected but was
<262144>.

But I haven't yet figured out where the blk_bio_discard_split code, or
elsewhere, is going wrong.

Mike

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, Jul 31, 2015 at 12:23 PM, Mike Snitzer <snitzer@redhat.com> wrote:
> On Mon, Jul 06 2015 at  3:44P -0400,
> Ming Lin <mlin@kernel.org> wrote:
>
>> From: Kent Overstreet <kent.overstreet@gmail.com>
>>
>> The way the block layer is currently written, it goes to great lengths
>> to avoid having to split bios; upper layer code (such as bio_add_page())
>> checks what the underlying device can handle and tries to always create
>> bios that don't need to be split.
>>
>> But this approach becomes unwieldy and eventually breaks down with
>> stacked devices and devices with dynamic limits, and it adds a lot of
>> complexity. If the block layer could split bios as needed, we could
>> eliminate a lot of complexity elsewhere - 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
>> (potentially multiple) devices underneath them.  In the future this will
>> let us delete merge_bvec_fn and a bunch of other code.
>>
>> We do this by adding calls to blk_queue_split() to the various
>> make_request functions that need it - a few can already handle arbitrary
>> size bios. Note that we add the call _after_ any call to
>> blk_queue_bounce(); this means that blk_queue_split() and
>> blk_recalc_rq_segments() don't need to be concerned with bouncing
>> affecting segment merging.
>>
>> Some make_request_fn() callbacks were simple enough to audit and verify
>> they don't need blk_queue_split() calls. The skipped ones are:
>>
>>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
>>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
>>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
>>  * brd_make_request (ramdisk - drivers/block/brd.c)
>>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
>>  * loop_make_request
>>  * null_queue_bio
>>  * bcache's make_request fns
>>
>> Some others are almost certainly safe to remove now, but will be left
>> for future patches.
>>
>> Cc: Jens Axboe <axboe@kernel.dk>
>> Cc: Christoph Hellwig <hch@infradead.org>
>> Cc: Al Viro <viro@zeniv.linux.org.uk>
>> Cc: Ming Lei <ming.lei@canonical.com>
>> Cc: Neil Brown <neilb@suse.de>
>> Cc: Alasdair Kergon <agk@redhat.com>
>> Cc: Mike Snitzer <snitzer@redhat.com>
>> Cc: dm-devel@redhat.com
>> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
>> Cc: drbd-user@lists.linbit.com
>> Cc: Jiri Kosina <jkosina@suse.cz>
>> Cc: Geoff Levand <geoff@infradead.org>
>> Cc: Jim Paris <jim@jtan.com>
>> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
>> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
>> Cc: Minchan Kim <minchan@kernel.org>
>> Cc: Nitin Gupta <ngupta@vflare.org>
>> Cc: Oleg Drokin <oleg.drokin@intel.com>
>> Cc: Andreas Dilger <andreas.dilger@intel.com>
>> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
>> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
>> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
>> Signed-off-by: Dongsu Park <dpark@posteo.net>
>> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
> ...
>> diff --git a/block/blk-merge.c b/block/blk-merge.c
>> index 30a0d9f..3707f30 100644
>> --- a/block/blk-merge.c
>> +++ b/block/blk-merge.c
>> @@ -9,12 +9,158 @@
>>
>>  #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);
>> +}
>
> This code to stop the discard at the previous aligned sector could be
> the reason why I have 2 device-mapper-test-suite tests in the
> 'thin-provisioning' testsuite failing due to this patchset:

I'm setting up the testsuite to debug.

Ming

>
>   4) Failure:
> test_discard_a_fragmented_device(DiscardQuickTests)
>     [/root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:49:in `block in assert_no_mappings'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `call'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `block in with_dev_md'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `each'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `with_dev_md'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:48:in `assert_no_mappings'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:263:in `test_discard_a_fragmented_device']:
> <0> expected but was
> <131072>.
>
>   5) Failure:
> test_discard_fully_provisioned_device_benchmark(DiscardQuickTests)
>     [/root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:49:in `block in assert_no_mappings'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `call'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:43:in `block in with_dev_md'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `each'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:40:in `with_dev_md'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:48:in `assert_no_mappings'
>      /root/snitm/git/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:225:in `test_discard_fully_provisioned_device_benchmark']:
> <0> expected but was
> <262144>.
>
> But I haven't yet figured out where the blk_bio_discard_split code, or
> elsewhere, is going wrong.
>
> Mike

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Fri, Jul 31 2015 at  5:19pm -0400,
Ming Lin <mlin@kernel.org> wrote:

> On Fri, Jul 31, 2015 at 12:23 PM, Mike Snitzer <snitzer@redhat.com> wrote:
> > On Mon, Jul 06 2015 at  3:44P -0400,
> > Ming Lin <mlin@kernel.org> wrote:
> >
> >> From: Kent Overstreet <kent.overstreet@gmail.com>
> >>
> >> The way the block layer is currently written, it goes to great lengths
> >> to avoid having to split bios; upper layer code (such as bio_add_page())
> >> checks what the underlying device can handle and tries to always create
> >> bios that don't need to be split.
> >>
> >> But this approach becomes unwieldy and eventually breaks down with
> >> stacked devices and devices with dynamic limits, and it adds a lot of
> >> complexity. If the block layer could split bios as needed, we could
> >> eliminate a lot of complexity elsewhere - 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
> >> (potentially multiple) devices underneath them.  In the future this will
> >> let us delete merge_bvec_fn and a bunch of other code.
> >>
> >> We do this by adding calls to blk_queue_split() to the various
> >> make_request functions that need it - a few can already handle arbitrary
> >> size bios. Note that we add the call _after_ any call to
> >> blk_queue_bounce(); this means that blk_queue_split() and
> >> blk_recalc_rq_segments() don't need to be concerned with bouncing
> >> affecting segment merging.
> >>
> >> Some make_request_fn() callbacks were simple enough to audit and verify
> >> they don't need blk_queue_split() calls. The skipped ones are:
> >>
> >>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
> >>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
> >>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
> >>  * brd_make_request (ramdisk - drivers/block/brd.c)
> >>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
> >>  * loop_make_request
> >>  * null_queue_bio
> >>  * bcache's make_request fns
> >>
> >> Some others are almost certainly safe to remove now, but will be left
> >> for future patches.
> >>
> >> Cc: Jens Axboe <axboe@kernel.dk>
> >> Cc: Christoph Hellwig <hch@infradead.org>
> >> Cc: Al Viro <viro@zeniv.linux.org.uk>
> >> Cc: Ming Lei <ming.lei@canonical.com>
> >> Cc: Neil Brown <neilb@suse.de>
> >> Cc: Alasdair Kergon <agk@redhat.com>
> >> Cc: Mike Snitzer <snitzer@redhat.com>
> >> Cc: dm-devel@redhat.com
> >> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
> >> Cc: drbd-user@lists.linbit.com
> >> Cc: Jiri Kosina <jkosina@suse.cz>
> >> Cc: Geoff Levand <geoff@infradead.org>
> >> Cc: Jim Paris <jim@jtan.com>
> >> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
> >> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
> >> Cc: Minchan Kim <minchan@kernel.org>
> >> Cc: Nitin Gupta <ngupta@vflare.org>
> >> Cc: Oleg Drokin <oleg.drokin@intel.com>
> >> Cc: Andreas Dilger <andreas.dilger@intel.com>
> >> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
> >> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
> >> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
> >> Signed-off-by: Dongsu Park <dpark@posteo.net>
> >> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
> > ...
> >> diff --git a/block/blk-merge.c b/block/blk-merge.c
> >> index 30a0d9f..3707f30 100644
> >> --- a/block/blk-merge.c
> >> +++ b/block/blk-merge.c
> >> @@ -9,12 +9,158 @@
> >>
> >>  #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);
> >> +}
> >
> > This code to stop the discard at the previous aligned sector could be
> > the reason why I have 2 device-mapper-test-suite tests in the
> > 'thin-provisioning' testsuite failing due to this patchset:
> 
> I'm setting up the testsuite to debug.

OK, once setup, to run the 2 tests in question directly you'd do
something like:

dmtest run --suite thin-provisioning -n discard_a_fragmented_device

dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark

Again, these tests pass without this patchset.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, 2015-07-31 at 17:38 -0400, Mike Snitzer wrote:
> On Fri, Jul 31 2015 at  5:19pm -0400,
> Ming Lin <mlin@kernel.org> wrote:
> 
> > On Fri, Jul 31, 2015 at 12:23 PM, Mike Snitzer <snitzer@redhat.com> wrote:
> > > On Mon, Jul 06 2015 at  3:44P -0400,
> > > Ming Lin <mlin@kernel.org> wrote:
> > >
> > >> From: Kent Overstreet <kent.overstreet@gmail.com>
> > >>
> > >> The way the block layer is currently written, it goes to great lengths
> > >> to avoid having to split bios; upper layer code (such as bio_add_page())
> > >> checks what the underlying device can handle and tries to always create
> > >> bios that don't need to be split.
> > >>
> > >> But this approach becomes unwieldy and eventually breaks down with
> > >> stacked devices and devices with dynamic limits, and it adds a lot of
> > >> complexity. If the block layer could split bios as needed, we could
> > >> eliminate a lot of complexity elsewhere - 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
> > >> (potentially multiple) devices underneath them.  In the future this will
> > >> let us delete merge_bvec_fn and a bunch of other code.
> > >>
> > >> We do this by adding calls to blk_queue_split() to the various
> > >> make_request functions that need it - a few can already handle arbitrary
> > >> size bios. Note that we add the call _after_ any call to
> > >> blk_queue_bounce(); this means that blk_queue_split() and
> > >> blk_recalc_rq_segments() don't need to be concerned with bouncing
> > >> affecting segment merging.
> > >>
> > >> Some make_request_fn() callbacks were simple enough to audit and verify
> > >> they don't need blk_queue_split() calls. The skipped ones are:
> > >>
> > >>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
> > >>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
> > >>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
> > >>  * brd_make_request (ramdisk - drivers/block/brd.c)
> > >>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
> > >>  * loop_make_request
> > >>  * null_queue_bio
> > >>  * bcache's make_request fns
> > >>
> > >> Some others are almost certainly safe to remove now, but will be left
> > >> for future patches.
> > >>
> > >> Cc: Jens Axboe <axboe@kernel.dk>
> > >> Cc: Christoph Hellwig <hch@infradead.org>
> > >> Cc: Al Viro <viro@zeniv.linux.org.uk>
> > >> Cc: Ming Lei <ming.lei@canonical.com>
> > >> Cc: Neil Brown <neilb@suse.de>
> > >> Cc: Alasdair Kergon <agk@redhat.com>
> > >> Cc: Mike Snitzer <snitzer@redhat.com>
> > >> Cc: dm-devel@redhat.com
> > >> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
> > >> Cc: drbd-user@lists.linbit.com
> > >> Cc: Jiri Kosina <jkosina@suse.cz>
> > >> Cc: Geoff Levand <geoff@infradead.org>
> > >> Cc: Jim Paris <jim@jtan.com>
> > >> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
> > >> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
> > >> Cc: Minchan Kim <minchan@kernel.org>
> > >> Cc: Nitin Gupta <ngupta@vflare.org>
> > >> Cc: Oleg Drokin <oleg.drokin@intel.com>
> > >> Cc: Andreas Dilger <andreas.dilger@intel.com>
> > >> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
> > >> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
> > >> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
> > >> Signed-off-by: Dongsu Park <dpark@posteo.net>
> > >> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
> > > ...
> > >> diff --git a/block/blk-merge.c b/block/blk-merge.c
> > >> index 30a0d9f..3707f30 100644
> > >> --- a/block/blk-merge.c
> > >> +++ b/block/blk-merge.c
> > >> @@ -9,12 +9,158 @@
> > >>
> > >>  #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);
> > >> +}
> > >
> > > This code to stop the discard at the previous aligned sector could be
> > > the reason why I have 2 device-mapper-test-suite tests in the
> > > 'thin-provisioning' testsuite failing due to this patchset:
> > 
> > I'm setting up the testsuite to debug.
> 
> OK, once setup, to run the 2 tests in question directly you'd do
> something like:
> 
> dmtest run --suite thin-provisioning -n discard_a_fragmented_device
> 
> dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark
> 
> Again, these tests pass without this patchset.

(trim CC list)

I followed
https://github.com/jthornber/device-mapper-test-suite
https://github.com/jthornber/thin-provisioning-tools

to setup.

$ grep CONFIG_DM_ .config
CONFIG_DM_MQ_DEFAULT=y
CONFIG_DM_DEBUG=y
CONFIG_DM_BUFIO=y
CONFIG_DM_BIO_PRISON=y
CONFIG_DM_PERSISTENT_DATA=y
# CONFIG_DM_DEBUG_BLOCK_STACK_TRACING is not set
CONFIG_DM_CRYPT=y
CONFIG_DM_SNAPSHOT=y
CONFIG_DM_THIN_PROVISIONING=y
CONFIG_DM_CACHE=y
CONFIG_DM_CACHE_MQ=y
CONFIG_DM_CACHE_SMQ=y
CONFIG_DM_CACHE_CLEANER=y
CONFIG_DM_ERA=y
CONFIG_DM_MIRROR=y
CONFIG_DM_LOG_USERSPACE=y
CONFIG_DM_RAID=y
CONFIG_DM_ZERO=y
CONFIG_DM_MULTIPATH=y
CONFIG_DM_MULTIPATH_QL=y
CONFIG_DM_MULTIPATH_ST=y
CONFIG_DM_DELAY=y
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=y
CONFIG_DM_VERITY=y
CONFIG_DM_SWITCH=y
CONFIG_DM_LOG_WRITES=y


# cat .dmtest/config 
 profile :ssd do
   metadata_dev '/dev/vda'
   data_dev '/dev/vdb'
 end
#
# profile :spindle do
#   metadata_dev '/dev/vdd'
#   data_dev '/dev/vde'
# end
#
# profile :mix do
#   metadata_dev '/dev/vdb'
#   data_dev '/dev/vde'
# end
#
# default_profile :ssd
# default_test_scale :normal


root@bee:~/device-mapper-test-suite# dmtest run --suite thin-provisioning -n discard_a_fragmented_device
Loaded suite thin-provisioning
Started
DiscardQuickTests
  discard_a_fragmented_device...restored metadata
FAIL

Finished in 1.958143844 seconds.

  1) Error:
test_discard_a_fragmented_device(DiscardQuickTests):
ProcessControl::ExitError: command failed: dmsetup load test-dev-307057 /tmp/dm-table20150731-3386-1rncpsb
    /root/device-mapper-test-suite/lib/dmtest/process.rb:96:in `wait'
    /root/device-mapper-test-suite/lib/dmtest/process.rb:111:in `really_run'
    /root/device-mapper-test-suite/lib/dmtest/process.rb:116:in `run_'
    /root/device-mapper-test-suite/lib/dmtest/process.rb:138:in `run'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/interface.rb:16:in `block in load'
    /root/device-mapper-test-suite/lib/dmtest/utils.rb:94:in `with_temp_file'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/interface.rb:12:in `load'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/dev.rb:19:in `load'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/lexical_operators.rb:53:in `block in create'
    /root/device-mapper-test-suite/lib/dmtest/prelude.rb:39:in `protect_'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/lexical_operators.rb:47:in `create'
    /root/device-mapper-test-suite/lib/dmtest/device-mapper/lexical_operators.rb:10:in `with_dev'
    /root/device-mapper-test-suite/lib/dmtest/thinp-mixin.rb:147:in `with_fake_discard'
    /root/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:109:in `with_discardable_pool'
    /root/device-mapper-test-suite/lib/dmtest/tests/thin-provisioning/discard_tests.rb:253:in `test_discard_a_fragmented_device'

1 tests, 0 assertions, 0 failures, 1 errors
Tests failed

root@bee:~/device-mapper-test-suite# dmesg 
[   83.824523] device-mapper: table: 249:0: fake-discard: unknown target type
[   83.827539] device-mapper: ioctl: error adding target to table


Seems my setup has problem. Could you help to take a look?

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, Jul 31, 2015 at 3:02 PM, Ming Lin <mlin@kernel.org> wrote:
> On Fri, 2015-07-31 at 17:38 -0400, Mike Snitzer wrote:
>> On Fri, Jul 31 2015 at  5:19pm -0400,
>> Ming Lin <mlin@kernel.org> wrote:
>>
>> > On Fri, Jul 31, 2015 at 12:23 PM, Mike Snitzer <snitzer@redhat.com> wrote:
>> > > On Mon, Jul 06 2015 at  3:44P -0400,
>> > > Ming Lin <mlin@kernel.org> wrote:
>> > >
>> > >> From: Kent Overstreet <kent.overstreet@gmail.com>
>> > >>
>> > >> The way the block layer is currently written, it goes to great lengths
>> > >> to avoid having to split bios; upper layer code (such as bio_add_page())
>> > >> checks what the underlying device can handle and tries to always create
>> > >> bios that don't need to be split.
>> > >>
>> > >> But this approach becomes unwieldy and eventually breaks down with
>> > >> stacked devices and devices with dynamic limits, and it adds a lot of
>> > >> complexity. If the block layer could split bios as needed, we could
>> > >> eliminate a lot of complexity elsewhere - 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
>> > >> (potentially multiple) devices underneath them.  In the future this will
>> > >> let us delete merge_bvec_fn and a bunch of other code.
>> > >>
>> > >> We do this by adding calls to blk_queue_split() to the various
>> > >> make_request functions that need it - a few can already handle arbitrary
>> > >> size bios. Note that we add the call _after_ any call to
>> > >> blk_queue_bounce(); this means that blk_queue_split() and
>> > >> blk_recalc_rq_segments() don't need to be concerned with bouncing
>> > >> affecting segment merging.
>> > >>
>> > >> Some make_request_fn() callbacks were simple enough to audit and verify
>> > >> they don't need blk_queue_split() calls. The skipped ones are:
>> > >>
>> > >>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
>> > >>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
>> > >>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
>> > >>  * brd_make_request (ramdisk - drivers/block/brd.c)
>> > >>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
>> > >>  * loop_make_request
>> > >>  * null_queue_bio
>> > >>  * bcache's make_request fns
>> > >>
>> > >> Some others are almost certainly safe to remove now, but will be left
>> > >> for future patches.
>> > >>
>> > >> Cc: Jens Axboe <axboe@kernel.dk>
>> > >> Cc: Christoph Hellwig <hch@infradead.org>
>> > >> Cc: Al Viro <viro@zeniv.linux.org.uk>
>> > >> Cc: Ming Lei <ming.lei@canonical.com>
>> > >> Cc: Neil Brown <neilb@suse.de>
>> > >> Cc: Alasdair Kergon <agk@redhat.com>
>> > >> Cc: Mike Snitzer <snitzer@redhat.com>
>> > >> Cc: dm-devel@redhat.com
>> > >> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
>> > >> Cc: drbd-user@lists.linbit.com
>> > >> Cc: Jiri Kosina <jkosina@suse.cz>
>> > >> Cc: Geoff Levand <geoff@infradead.org>
>> > >> Cc: Jim Paris <jim@jtan.com>
>> > >> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
>> > >> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
>> > >> Cc: Minchan Kim <minchan@kernel.org>
>> > >> Cc: Nitin Gupta <ngupta@vflare.org>
>> > >> Cc: Oleg Drokin <oleg.drokin@intel.com>
>> > >> Cc: Andreas Dilger <andreas.dilger@intel.com>
>> > >> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
>> > >> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
>> > >> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
>> > >> Signed-off-by: Dongsu Park <dpark@posteo.net>
>> > >> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
>> > > ...
>> > >> diff --git a/block/blk-merge.c b/block/blk-merge.c
>> > >> index 30a0d9f..3707f30 100644
>> > >> --- a/block/blk-merge.c
>> > >> +++ b/block/blk-merge.c
>> > >> @@ -9,12 +9,158 @@
>> > >>
>> > >>  #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);
>> > >> +}
>> > >
>> > > This code to stop the discard at the previous aligned sector could be
>> > > the reason why I have 2 device-mapper-test-suite tests in the
>> > > 'thin-provisioning' testsuite failing due to this patchset:
>> >
>> > I'm setting up the testsuite to debug.
>>
>> OK, once setup, to run the 2 tests in question directly you'd do
>> something like:
>>
>> dmtest run --suite thin-provisioning -n discard_a_fragmented_device
>>
>> dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark
>>
>> Again, these tests pass without this patchset.
>
> (trim CC list)
>
> I followed
> https://github.com/jthornber/device-mapper-test-suite
> https://github.com/jthornber/thin-provisioning-tools
>
> to setup.
>
> $ grep CONFIG_DM_ .config
> CONFIG_DM_MQ_DEFAULT=y
> CONFIG_DM_DEBUG=y
> CONFIG_DM_BUFIO=y
> CONFIG_DM_BIO_PRISON=y
> CONFIG_DM_PERSISTENT_DATA=y
> # CONFIG_DM_DEBUG_BLOCK_STACK_TRACING is not set
> CONFIG_DM_CRYPT=y
> CONFIG_DM_SNAPSHOT=y
> CONFIG_DM_THIN_PROVISIONING=y
> CONFIG_DM_CACHE=y
> CONFIG_DM_CACHE_MQ=y
> CONFIG_DM_CACHE_SMQ=y
> CONFIG_DM_CACHE_CLEANER=y
> CONFIG_DM_ERA=y
> CONFIG_DM_MIRROR=y
> CONFIG_DM_LOG_USERSPACE=y
> CONFIG_DM_RAID=y
> CONFIG_DM_ZERO=y
> CONFIG_DM_MULTIPATH=y
> CONFIG_DM_MULTIPATH_QL=y
> CONFIG_DM_MULTIPATH_ST=y
> CONFIG_DM_DELAY=y
> CONFIG_DM_UEVENT=y
> CONFIG_DM_FLAKEY=y
> CONFIG_DM_VERITY=y
> CONFIG_DM_SWITCH=y
> CONFIG_DM_LOG_WRITES=y
>
>
> # cat .dmtest/config
>  profile :ssd do
>    metadata_dev '/dev/vda'
>    data_dev '/dev/vdb'
>  end

OK, virtio-blk doesn't support discard.
I could reproduce it with virtio-scsi.

Now debugging ...

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, 2015-07-31 at 17:38 -0400, Mike Snitzer wrote:
> On Fri, Jul 31 2015 at  5:19pm -0400,
> Ming Lin <mlin@kernel.org> wrote:
> 
> > On Fri, Jul 31, 2015 at 12:23 PM, Mike Snitzer <snitzer@redhat.com> wrote:
> > > On Mon, Jul 06 2015 at  3:44P -0400,
> > > Ming Lin <mlin@kernel.org> wrote:
> > >
> > >> From: Kent Overstreet <kent.overstreet@gmail.com>
> > >>
> > >> The way the block layer is currently written, it goes to great lengths
> > >> to avoid having to split bios; upper layer code (such as bio_add_page())
> > >> checks what the underlying device can handle and tries to always create
> > >> bios that don't need to be split.
> > >>
> > >> But this approach becomes unwieldy and eventually breaks down with
> > >> stacked devices and devices with dynamic limits, and it adds a lot of
> > >> complexity. If the block layer could split bios as needed, we could
> > >> eliminate a lot of complexity elsewhere - 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
> > >> (potentially multiple) devices underneath them.  In the future this will
> > >> let us delete merge_bvec_fn and a bunch of other code.
> > >>
> > >> We do this by adding calls to blk_queue_split() to the various
> > >> make_request functions that need it - a few can already handle arbitrary
> > >> size bios. Note that we add the call _after_ any call to
> > >> blk_queue_bounce(); this means that blk_queue_split() and
> > >> blk_recalc_rq_segments() don't need to be concerned with bouncing
> > >> affecting segment merging.
> > >>
> > >> Some make_request_fn() callbacks were simple enough to audit and verify
> > >> they don't need blk_queue_split() calls. The skipped ones are:
> > >>
> > >>  * nfhd_make_request (arch/m68k/emu/nfblock.c)
> > >>  * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
> > >>  * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
> > >>  * brd_make_request (ramdisk - drivers/block/brd.c)
> > >>  * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
> > >>  * loop_make_request
> > >>  * null_queue_bio
> > >>  * bcache's make_request fns
> > >>
> > >> Some others are almost certainly safe to remove now, but will be left
> > >> for future patches.
> > >>
> > >> Cc: Jens Axboe <axboe@kernel.dk>
> > >> Cc: Christoph Hellwig <hch@infradead.org>
> > >> Cc: Al Viro <viro@zeniv.linux.org.uk>
> > >> Cc: Ming Lei <ming.lei@canonical.com>
> > >> Cc: Neil Brown <neilb@suse.de>
> > >> Cc: Alasdair Kergon <agk@redhat.com>
> > >> Cc: Mike Snitzer <snitzer@redhat.com>
> > >> Cc: dm-devel@redhat.com
> > >> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
> > >> Cc: drbd-user@lists.linbit.com
> > >> Cc: Jiri Kosina <jkosina@suse.cz>
> > >> Cc: Geoff Levand <geoff@infradead.org>
> > >> Cc: Jim Paris <jim@jtan.com>
> > >> Cc: Joshua Morris <josh.h.morris@us.ibm.com>
> > >> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
> > >> Cc: Minchan Kim <minchan@kernel.org>
> > >> Cc: Nitin Gupta <ngupta@vflare.org>
> > >> Cc: Oleg Drokin <oleg.drokin@intel.com>
> > >> Cc: Andreas Dilger <andreas.dilger@intel.com>
> > >> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
> > >> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
> > >> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
> > >> Signed-off-by: Dongsu Park <dpark@posteo.net>
> > >> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
> > > ...
> > >> diff --git a/block/blk-merge.c b/block/blk-merge.c
> > >> index 30a0d9f..3707f30 100644
> > >> --- a/block/blk-merge.c
> > >> +++ b/block/blk-merge.c
> > >> @@ -9,12 +9,158 @@
> > >>
> > >>  #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);
> > >> +}
> > >
> > > This code to stop the discard at the previous aligned sector could be
> > > the reason why I have 2 device-mapper-test-suite tests in the
> > > 'thin-provisioning' testsuite failing due to this patchset:
> > 
> > I'm setting up the testsuite to debug.
> 
> OK, once setup, to run the 2 tests in question directly you'd do
> something like:
> 
> dmtest run --suite thin-provisioning -n discard_a_fragmented_device
> 
> dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark
> 
> Again, these tests pass without this patchset.

It's caused by patch 4.
When discard size >=4G, the bio->bi_iter.bi_size overflows.
Below is the new patch.

Christoph,
Could you also help to review it?

Now we still do "misaligned" check in blkdev_issue_discard().
So the same code in blk_bio_discard_split() was removed.
Please see
https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/commit/?h=block-generic-req&id=dcc5d9c41

I have updated both patch 1 & 4 on my tree.

commit 9607f737de9c4ca1a81655c320a61c287bf77bf5
Author: Ming Lin <ming.l@ssi.samsung.com>
Date:   Fri May 22 00:46:56 2015 -0700

    block: remove split code in blkdev_issue_discard
    
    The split code in blkdev_issue_discard() can go away now
    that any driver that cares does the split, all we have
    to do is make sure bio size doesn't overflow.
    
    Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-lib.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3..b9e2fca 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -43,7 +43,7 @@ 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;
+	unsigned int granularity;
 	int alignment;
 	struct bio_batch bb;
 	struct bio *bio;
@@ -60,17 +60,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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;
@@ -92,7 +81,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
+		/* Make sure bi_size doesn't overflow */
+		req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
 
 		/*
 		 * If splitting a request, and the next starting sector would be

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Sat, Aug 01 2015 at  2:58am -0400,
Ming Lin <mlin@kernel.org> wrote:

> On Fri, 2015-07-31 at 17:38 -0400, Mike Snitzer wrote:
> > 
> > OK, once setup, to run the 2 tests in question directly you'd do
> > something like:
> > 
> > dmtest run --suite thin-provisioning -n discard_a_fragmented_device
> > 
> > dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark
> > 
> > Again, these tests pass without this patchset.
> 
> It's caused by patch 4.
> When discard size >=4G, the bio->bi_iter.bi_size overflows.

Thanks for tracking this down!

> Below is the new patch.
> 
> Christoph,
> Could you also help to review it?
> 
> Now we still do "misaligned" check in blkdev_issue_discard().
> So the same code in blk_bio_discard_split() was removed.

But I don't agree with this approach.  One of the most meaningful
benefits of late bio splitting is the upper layers shouldn't _need_ to
depend on the intermediate devices' queue_limits being stacked properly.
Your solution to mix discard granularity/alignment checks at the upper
layer(s) but then split based on max_discard_sectors at the lower layer
defeats that benefit for discards.

This will translate to all intermediate layers that might split
discards needing to worry about granularity/alignment
too (e.g. how dm-thinp will have to care because it must generate
discard mappings with associated bios based on how blocks were mapped to
thinp).

Also, it is unfortunate that IO that doesn't have a payload is being
artificially split simply because bio->bi_iter.bi_size is 32bits.

Mike

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Sat, 2015-08-01 at 12:33 -0400, Mike Snitzer wrote:
> On Sat, Aug 01 2015 at  2:58am -0400,
> Ming Lin <mlin@kernel.org> wrote:
> 
> > On Fri, 2015-07-31 at 17:38 -0400, Mike Snitzer wrote:
> > > 
> > > OK, once setup, to run the 2 tests in question directly you'd do
> > > something like:
> > > 
> > > dmtest run --suite thin-provisioning -n discard_a_fragmented_device
> > > 
> > > dmtest run --suite thin-provisioning -n discard_fully_provisioned_device_benchmark
> > > 
> > > Again, these tests pass without this patchset.
> > 
> > It's caused by patch 4.

Typo. I mean patch 5.

> > When discard size >=4G, the bio->bi_iter.bi_size overflows.
> 
> Thanks for tracking this down!

blkdev_issue_write_same() has same problem.

> 
> > Below is the new patch.
> > 
> > Christoph,
> > Could you also help to review it?
> > 
> > Now we still do "misaligned" check in blkdev_issue_discard().
> > So the same code in blk_bio_discard_split() was removed.
> 
> But I don't agree with this approach.  One of the most meaningful
> benefits of late bio splitting is the upper layers shouldn't _need_ to
> depend on the intermediate devices' queue_limits being stacked properly.
> Your solution to mix discard granularity/alignment checks at the upper
> layer(s) but then split based on max_discard_sectors at the lower layer
> defeats that benefit for discards.
> 
> This will translate to all intermediate layers that might split
> discards needing to worry about granularity/alignment
> too (e.g. how dm-thinp will have to care because it must generate
> discard mappings with associated bios based on how blocks were mapped to
> thinp).

I think the important thing is the late splitting for regular bio.
For discard/write_same bio, how about just don't do late splitting?

That is:
1. remove "PATCH 5: block: remove split code in blkdev_issue_discard"
2. Add below changes to PATCH 1

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 1f5dfa0..90b085e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,59 +9,6 @@
 
 #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)
@@ -129,10 +76,8 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 {
 	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);
+	if ((*bio)->bi_rw & REQ_DISCARD || (*bio)->bi_rw & REQ_WRITE_SAME)
+		split = NULL;
 	else
 		split = blk_bio_segment_split(q, *bio, q->bio_split);
 

> 
> Also, it is unfortunate that IO that doesn't have a payload is being
> artificially split simply because bio->bi_iter.bi_size is 32bits.

Indeed.
Will it be possible to make it 64bits? I guess no.

> 
> Mike

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

On Sun, Aug 02, 2015 at 10:58:22PM -0700, Ming Lin wrote:
> I think the important thing is the late splitting for regular bio.
> For discard/write_same bio, how about just don't do late splitting?

I'd hate having to special case them even more.  Especially as the
discard splitting is nasty and we really don't want to send giant
discards by default anyway (see Jens' patches to limit discard size
by default).

So I'd recommend to keep everything as-is, just make sure we don't
overflow bi_size.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Tue, 2015-08-04 at 13:36 +0200, Christoph Hellwig wrote:
> On Sun, Aug 02, 2015 at 10:58:22PM -0700, Ming Lin wrote:
> > I think the important thing is the late splitting for regular bio.
> > For discard/write_same bio, how about just don't do late splitting?
> 
> I'd hate having to special case them even more.  Especially as the
> discard splitting is nasty and we really don't want to send giant
> discards by default anyway (see Jens' patches to limit discard size
> by default).
> 
> So I'd recommend to keep everything as-is, just make sure we don't
> overflow bi_size.

Did you mean to remove "PATCH 4 block: remove split code in
blkdev_issue_discard" or to keep it?

Which of below 2 solutions you prefer?

- Solution 1

remove splits in blkdev_issue_{discard,write_same} and keep
blk_bio_{discard,write_same}_split

But for blkdev_issue_discard(), it's not enough if only make sure
bi_size not overflow, for example, discard 4G

4G bytes = 8388608 sectors
UINT_MAX = 8388607 sectors

So blkdev_issue_discard() will send 2 discard bios.
First bio: sector 0 .. 8388606
Second bio: sector 8388607 .. 8388607

In this case, the 2 discard tests in device-mapper-test-suite still
fail, probably because the second bio start sector is not aligned with
discard_granularity.

So I have to take into account discard_granularity(assume 32 sectors),
then blkdev_issue_discard() will send 2 discard bios, as

First bio: sector 0 .. 8388575
Second bio: sector 8388576 .. 8388607

In this case, both discard tests passed.

- Solution 2

special case discard/write_same bios(You said you hate it).

That is to keep splits in blkdev_issue_{discard,write_same} and remove
blk_bio_{discard,write_same}_split

I think this is more clean way because blkdev_issue_{discard,write_same}
already make sure we don't overflow bi_size.

And blk_bio_{discard,write_same}_split are actually duplicated with the
splits in blkdev_issue_{discard,write_same}. It's OK to remove it.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Kent Overstreet]

On Tue, Aug 04, 2015 at 01:36:26PM +0200, Christoph Hellwig wrote:
> On Sun, Aug 02, 2015 at 10:58:22PM -0700, Ming Lin wrote:
> > I think the important thing is the late splitting for regular bio.
> > For discard/write_same bio, how about just don't do late splitting?
> 
> I'd hate having to special case them even more.  Especially as the
> discard splitting is nasty and we really don't want to send giant
> discards by default anyway (see Jens' patches to limit discard size
> by default).

Why is it that we don't want to send giant discards? Is it a latency issue?

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

I'm for solution 3:

 - keep blk_bio_{discard,write_same}_split, but ensure we never built
   a > 4GB bio in blkdev_issue_{discard,write_same}.

Note that this isn't special casing, we can't build > 4GB bios for
data either, it's just implemented as a side effect right now instead
of checked explicitly.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

On Thu, Aug 06, 2015 at 05:00:04PM -0700, Kent Overstreet wrote:
> Why is it that we don't want to send giant discards? Is it a latency issue?

Yes.  Take a look at the "Configurable max discard size" thread(s).

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, 2015-08-07 at 09:30 +0200, Christoph Hellwig wrote:
> I'm for solution 3:
> 
>  - keep blk_bio_{discard,write_same}_split, but ensure we never built
>    a > 4GB bio in blkdev_issue_{discard,write_same}.

This has problem as I mentioned in solution 1.
We need to also make sure max discard size is of proper granularity.
See below example.

      4G: 8388608 sectors
UINT_MAX: 8388607 sectors

dm-thinp block size = default discard granularity = 128 sectors

blkdev_issue_discard(sector=0, nr_sectors=8388608)

1. Only ensure bi_size not overflow

It doesn't work.

[start_sector, end_sector]
[0, 8388607]
    [0, 8388606], then dm-thinp splits it to 2 bios
        [0, 8388479]
        [8388480, 8388606] ---> this has problem in process_discard_bio(),
                                because the discard size(7 sectors) covers less than a block(128 sectors)
    [8388607, 8388607] ---> same problem 

2. Ensure bi_size not overflow and max discard size is of proper granularity

It works.

[start_sector, end_sector]
[0, 8388607]
    [0, 8388479]
    [8388480, 8388607]


So how about below patch?

commit 1ca2ad977255efb3c339f4ca16fb798ed5ec54f7
Author: Ming Lin <ming.l@ssi.samsung.com>
Date:   Fri Aug 7 15:07:07 2015 -0700

    block: remove split code in blkdev_issue_{discard,write_same}
    
    The split code in blkdev_issue_{discard,write_same} can go away
    now that any driver that cares does the split. We have to make
    sure bio size doesn't overflow.
    
    For discard, we ensure max_discard_sectors is of the proper
    granularity. So if discard size > 4G, blkdev_issue_discard() always
    send multiple granularity requests to lower level, except that the
    last one may be not multiple granularity.
    
    Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-lib.c | 37 +++++++++----------------------------
 1 file changed, 9 insertions(+), 28 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3..e178a07 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -44,7 +44,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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;
@@ -58,18 +57,15 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	/* 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);
+	 * Ensure that max_discard_sectors doesn't overflow bi_size and is of
+	 * the proper granularity. So if discard size > 4G, blkdev_issue_discard()
+	 * always split and send multiple granularity requests to lower level,
+	 * except that the last one may be not multiple granularity.
+         */
+	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))
@@ -84,7 +80,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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) {
@@ -93,20 +89,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		}
 
 		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.
-		 */
 		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;
@@ -166,10 +149,8 @@ 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;


> 
> Note that this isn't special casing, we can't build > 4GB bios for
> data either, it's just implemented as a side effect right now instead
> of checked explicitly.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Kent Overstreet]

On Fri, Aug 07, 2015 at 04:40:06PM -0700, Ming Lin wrote:
> 
> On Fri, 2015-08-07 at 09:30 +0200, Christoph Hellwig wrote:
> > I'm for solution 3:
> > 
> >  - keep blk_bio_{discard,write_same}_split, but ensure we never built
> >    a > 4GB bio in blkdev_issue_{discard,write_same}.
> 
> This has problem as I mentioned in solution 1.
> We need to also make sure max discard size is of proper granularity.
> See below example.
> 
>       4G: 8388608 sectors
> UINT_MAX: 8388607 sectors
> 
> dm-thinp block size = default discard granularity = 128 sectors
> 
> blkdev_issue_discard(sector=0, nr_sectors=8388608)
> 
> 1. Only ensure bi_size not overflow
> 
> It doesn't work.
> 
> [start_sector, end_sector]
> [0, 8388607]
>     [0, 8388606], then dm-thinp splits it to 2 bios
>         [0, 8388479]
>         [8388480, 8388606] ---> this has problem in process_discard_bio(),
>                                 because the discard size(7 sectors) covers less than a block(128 sectors)
>     [8388607, 8388607] ---> same problem 
> 
> 2. Ensure bi_size not overflow and max discard size is of proper granularity

Ideally we'd get upper layers out of the business of knowing about the queue
limits at all - that was the point of the patch series, after all.

Instead of using UINT_MAX, would it work to just make the max 1 << 31 sectors?

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Fri, Aug 7, 2015 at 5:30 PM, Kent Overstreet
<kent.overstreet@gmail.com> wrote:
> On Fri, Aug 07, 2015 at 04:40:06PM -0700, Ming Lin wrote:
>>
>> On Fri, 2015-08-07 at 09:30 +0200, Christoph Hellwig wrote:
>> > I'm for solution 3:
>> >
>> >  - keep blk_bio_{discard,write_same}_split, but ensure we never built
>> >    a > 4GB bio in blkdev_issue_{discard,write_same}.
>>
>> This has problem as I mentioned in solution 1.
>> We need to also make sure max discard size is of proper granularity.
>> See below example.
>>
>>       4G: 8388608 sectors
>> UINT_MAX: 8388607 sectors
>>
>> dm-thinp block size = default discard granularity = 128 sectors
>>
>> blkdev_issue_discard(sector=0, nr_sectors=8388608)
>>
>> 1. Only ensure bi_size not overflow
>>
>> It doesn't work.
>>
>> [start_sector, end_sector]
>> [0, 8388607]
>>     [0, 8388606], then dm-thinp splits it to 2 bios
>>         [0, 8388479]
>>         [8388480, 8388606] ---> this has problem in process_discard_bio(),
>>                                 because the discard size(7 sectors) covers less than a block(128 sectors)
>>     [8388607, 8388607] ---> same problem
>>
>> 2. Ensure bi_size not overflow and max discard size is of proper granularity
>
> Ideally we'd get upper layers out of the business of knowing about the queue
> limits at all - that was the point of the patch series, after all.
>
> Instead of using UINT_MAX, would it work to just make the max 1 << 31 sectors?'

1 << 31 = 2G bytes = 0x400000 sectors.

Yes, that works as long as it's multiple of granularity.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Kent Overstreet]

On Fri, Aug 07, 2015 at 10:17:43PM -0700, Ming Lin wrote:
> On Fri, Aug 7, 2015 at 5:30 PM, Kent Overstreet
> > Ideally we'd get upper layers out of the business of knowing about the queue
> > limits at all - that was the point of the patch series, after all.
> >
> > Instead of using UINT_MAX, would it work to just make the max 1 << 31 sectors?'
> 
> 1 << 31 = 2G bytes = 0x400000 sectors.
> 
> Yes, that works as long as it's multiple of granularity.

Is granularity required to be a power of two? One would hope, but looking at the
code that doesn't appear to be a requirement... ugh, that's terrible...

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Hannes Reinecke]

On 08/08/2015 01:40 AM, Ming Lin wrote:
> 
> On Fri, 2015-08-07 at 09:30 +0200, Christoph Hellwig wrote:
>> I'm for solution 3:
>>
>>  - keep blk_bio_{discard,write_same}_split, but ensure we never built
>>    a > 4GB bio in blkdev_issue_{discard,write_same}.
> 
> This has problem as I mentioned in solution 1.
> We need to also make sure max discard size is of proper granularity.
> See below example.
> 
>       4G: 8388608 sectors
> UINT_MAX: 8388607 sectors
> 
> dm-thinp block size = default discard granularity = 128 sectors
> 
> blkdev_issue_discard(sector=0, nr_sectors=8388608)
> 
> 1. Only ensure bi_size not overflow
> 
> It doesn't work.
> 
> [start_sector, end_sector]
> [0, 8388607]
>     [0, 8388606], then dm-thinp splits it to 2 bios
>         [0, 8388479]
>         [8388480, 8388606] ---> this has problem in process_discard_bio(),
>                                 because the discard size(7 sectors) covers less than a block(128 sectors)
>     [8388607, 8388607] ---> same problem 
> 
> 2. Ensure bi_size not overflow and max discard size is of proper granularity
> 
> It works.
> 
> [start_sector, end_sector]
> [0, 8388607]
>     [0, 8388479]
>     [8388480, 8388607]
> 
> 
> So how about below patch?
> 
> commit 1ca2ad977255efb3c339f4ca16fb798ed5ec54f7
> Author: Ming Lin <ming.l@ssi.samsung.com>
> Date:   Fri Aug 7 15:07:07 2015 -0700
> 
>     block: remove split code in blkdev_issue_{discard,write_same}
>     
>     The split code in blkdev_issue_{discard,write_same} can go away
>     now that any driver that cares does the split. We have to make
>     sure bio size doesn't overflow.
>     
>     For discard, we ensure max_discard_sectors is of the proper
>     granularity. So if discard size > 4G, blkdev_issue_discard() always
>     send multiple granularity requests to lower level, except that the
>     last one may be not multiple granularity.
>     
>     Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
> ---
>  block/blk-lib.c | 37 +++++++++----------------------------
>  1 file changed, 9 insertions(+), 28 deletions(-)
> 
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index 7688ee3..e178a07 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -44,7 +44,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  	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;
> @@ -58,18 +57,15 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  
>  	/* 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);
> +	 * Ensure that max_discard_sectors doesn't overflow bi_size and is of
> +	 * the proper granularity. So if discard size > 4G, blkdev_issue_discard()
> +	 * always split and send multiple granularity requests to lower level,
> +	 * except that the last one may be not multiple granularity.
> +         */
> +	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))
> @@ -84,7 +80,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  	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) {
> @@ -93,20 +89,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  		}
>  
>  		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.
> -		 */
>  		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;
> @@ -166,10 +149,8 @@ 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;
> 
Wouldn't it be easier to move both max_write_same_sectors and
max_discard sectors to 64 bit (ie to type sector_t) and be done with the
overflow?
Seems to me this is far too much coding around self-imposed restrictions...

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		      zSeries & Storage
hare@suse.de			      +49 911 74053 688
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: J. Hawn, J. Guild, F. Imendörffer, HRB 16746 (AG Nürnberg)

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Kent Overstreet]

On Sat, Aug 08, 2015 at 10:52:24AM +0200, Hannes Reinecke wrote:
> Wouldn't it be easier to move both max_write_same_sectors and
> max_discard sectors to 64 bit (ie to type sector_t) and be done with the
> overflow?
> Seems to me this is far too much coding around self-imposed restrictions...

It's bio->bi_iter.bi_size that would have to be increased to 64 bits. Which I
suppose wouldn't actually increase the size of struct bio (when sector_t is 64
bits), since struct bvec_iter has padding right now...

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

On Fri, Aug 07, 2015 at 09:22:26PM -0800, Kent Overstreet wrote:
> Is granularity required to be a power of two? One would hope, but looking at the
> code that doesn't appear to be a requirement... ugh, that's terrible...

If devices have an odd granularity we'll just have to split more than
nessecary.  Let's hope no major hardware does that.

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:

Mike> This will translate to all intermediate layers that might split
Mike> discards needing to worry about granularity/alignment too
Mike> (e.g. how dm-thinp will have to care because it must generate
Mike> discard mappings with associated bios based on how blocks were
Mike> mapped to thinp).

The fundamental issue here is that alignment and granularity should
never, ever have been enforced at the top of the stack. Horrendous idea
from the very beginning.

For the < handful of braindead devices that get confused when you do
partial or misaligned blocks we should have had a quirk that did any
range adjusting at the bottom in sd_setup_discard_cmnd().

There's a reason I turned discard_zeroes_data off for UNMAP!

Wrt. the range size I don't have a problem with capping at the 32-bit
bi_size limit. We probably don't want to send commands much bigger than
that anyway.

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Sat, 2015-08-08 at 12:19 -0400, Martin K. Petersen wrote:
> >>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:
> 
> Mike> This will translate to all intermediate layers that might split
> Mike> discards needing to worry about granularity/alignment too
> Mike> (e.g. how dm-thinp will have to care because it must generate
> Mike> discard mappings with associated bios based on how blocks were
> Mike> mapped to thinp).
> 
> The fundamental issue here is that alignment and granularity should
> never, ever have been enforced at the top of the stack. Horrendous idea
> from the very beginning.
> 
> For the < handful of braindead devices that get confused when you do
> partial or misaligned blocks we should have had a quirk that did any
> range adjusting at the bottom in sd_setup_discard_cmnd().
> 
> There's a reason I turned discard_zeroes_data off for UNMAP!
> 
> Wrt. the range size I don't have a problem with capping at the 32-bit
> bi_size limit. We probably don't want to send commands much bigger than
> that anyway.

How about below?

commit b8ca440bd77653d4d2bac90b7fd1599e9e0e150a
Author: Ming Lin <ming.l@ssi.samsung.com>
Date:   Fri Aug 7 15:07:07 2015 -0700

    block: remove split code in blkdev_issue_{discard,write_same}
    
    The split code in blkdev_issue_{discard,write_same} can go away
    now that any driver that cares does the split. We have to make
    sure bio size doesn't overflow.
    
    For discard, we set max discard sectors to (1<<31)>>9 to ensure
    it doesn't overflow bi_size and hopefully it is of the proper
    granularity as long as the granularity is a power of two.
    
    Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-lib.c | 47 +++++++++++------------------------------------
 1 file changed, 11 insertions(+), 36 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3..4859e4b 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -26,6 +26,13 @@ static void bio_batch_end_io(struct bio *bio, int err)
 	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_DISCARD_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;
@@ -84,7 +74,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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_DISCARD_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;
@@ -166,10 +143,8 @@ 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;

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

On Sat, Aug 08, 2015 at 10:59:50PM -0700, Ming Lin wrote:
> +/*
> + * 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_DISCARD_SECTORS ((1U << 31) >> 9)

Thisn't isn't MAX_DISCARD_SECTORS, it's MAX_BIO_SECTORS.  If we ever
to something like Kent's multipage biovecs we'll actually need it for
regular read/write bios in addition to discard and write same.

Except for that the patch looks reasonable to me.

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Sat, 2015-08-08 at 23:41 -0700, Christoph Hellwig wrote:
> On Sat, Aug 08, 2015 at 10:59:50PM -0700, Ming Lin wrote:
> > +/*
> > + * 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_DISCARD_SECTORS ((1U << 31) >> 9)
> 
> Thisn't isn't MAX_DISCARD_SECTORS, it's MAX_BIO_SECTORS.  If we ever
> to something like Kent's multipage biovecs we'll actually need it for
> regular read/write bios in addition to discard and write same.
> 
> Except for that the patch looks reasonable to me.

Will change it to MAX_BIO_SECTORS.
May I add your ACK?

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Christoph Hellwig]

On Sat, Aug 08, 2015 at 11:55:47PM -0700, Ming Lin wrote:
> Will change it to MAX_BIO_SECTORS.
> May I add your ACK?

Yes, please go ahead.

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Sun, 2015-08-09 at 00:01 -0700, Christoph Hellwig wrote:
> On Sat, Aug 08, 2015 at 11:55:47PM -0700, Ming Lin wrote:
> > Will change it to MAX_BIO_SECTORS.
> > May I add your ACK?
> 
> Yes, please go ahead.

Thanks. I'll send a new version of the series once device-mapper guy
acks.

Hi Mike,

I have updated my tree. Could you pull and re-test?
https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/log/?h=block-generic-req

The 2 thin-provisioning tests passed.
Hope I can have your ACK soon.

Thanks.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Sun, Aug 09 2015 at  3:18am -0400,
Ming Lin <mlin@kernel.org> wrote:

> On Sun, 2015-08-09 at 00:01 -0700, Christoph Hellwig wrote:
> > On Sat, Aug 08, 2015 at 11:55:47PM -0700, Ming Lin wrote:
> > > Will change it to MAX_BIO_SECTORS.
> > > May I add your ACK?
> > 
> > Yes, please go ahead.
> 
> Thanks. I'll send a new version of the series once device-mapper guy
> acks.
> 
> Hi Mike,
> 
> I have updated my tree. Could you pull and re-test?
> https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/log/?h=block-generic-req
> 
> The 2 thin-provisioning tests passed.

I've merged your latest branch with my dm-4.3 branch, I had one conflict
in the merge due to the dm_merge_bvec() change from 4.2-rc6 (no
surprise).  I've published the result here:
http://git.kernel.org/cgit/linux/kernel/git/snitzer/linux.git/log/?h=block-late-bio-splitting

It passes the device-mapper-test-suite's 'thin-provisioning' tests.

> Hope I can have your ACK soon.

Shouldn't we also be using MAX_BIO_SECTORS in blkdev_issue_write_same
(instead of UINT_MAX >> 9)?

Aside from that, I'm in favor of seeing this late bio splitting patchset
finally land upstream (hopefully in time for the 4.3 merge, Jens?):

Acked-by: Mike Snitzer <snitzer@redhat.com>

p.s. I'll be working with Joe Thornber on optimizing DM (particularly
dm-thinp and dm-cache) once this patchset is included upstream.  You'll
see I've already added a couple WIP dm-thinp patches ontop.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Mon, 2015-08-10 at 11:02 -0400, Mike Snitzer wrote:
> On Sun, Aug 09 2015 at  3:18am -0400,
> Ming Lin <mlin@kernel.org> wrote:
> 
> > On Sun, 2015-08-09 at 00:01 -0700, Christoph Hellwig wrote:
> > > On Sat, Aug 08, 2015 at 11:55:47PM -0700, Ming Lin wrote:
> > > > Will change it to MAX_BIO_SECTORS.
> > > > May I add your ACK?
> > > 
> > > Yes, please go ahead.
> > 
> > Thanks. I'll send a new version of the series once device-mapper guy
> > acks.
> > 
> > Hi Mike,
> > 
> > I have updated my tree. Could you pull and re-test?
> > https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/log/?h=block-generic-req
> > 
> > The 2 thin-provisioning tests passed.
> 
> I've merged your latest branch with my dm-4.3 branch, I had one conflict
> in the merge due to the dm_merge_bvec() change from 4.2-rc6 (no
> surprise).  I've published the result here:
> http://git.kernel.org/cgit/linux/kernel/git/snitzer/linux.git/log/?h=block-late-bio-splitting
> 
> It passes the device-mapper-test-suite's 'thin-provisioning' tests.
> 
> > Hope I can have your ACK soon.
> 
> Shouldn't we also be using MAX_BIO_SECTORS in blkdev_issue_write_same
> (instead of UINT_MAX >> 9)?

I also prefer using MAX_BIO_SECTORS.
Otherwise, we may have non page size aligned splits.

Say, write_same 8G.

Using UINT_MAX >> 9, we'll have 2 sector aligned splits in
blkdev_issue_write_same():
0 - (4G - 512 - 1)
(4G - 512, 8G -1)

This looks weired.

Using MAX_BIO_SECTORS, we'll have 4 page size aligned splits:
0 - (2G -1)
2G - (4G - 1)
4G - (6G - 1)
6G - (8G - 1)

I'll use MAX_BIO_SECTORS in blkdev_issue_write_same() if no objection.

> 
> Aside from that, I'm in favor of seeing this late bio splitting patchset
> finally land upstream (hopefully in time for the 4.3 merge, Jens?):
> 
> Acked-by: Mike Snitzer <snitzer@redhat.com>

Thanks!

May I add your Ack to "PATCH: block: kill merge_bvec_fn() completely"
also?

> 
> p.s. I'll be working with Joe Thornber on optimizing DM (particularly
> dm-thinp and dm-cache) once this patchset is included upstream.  You'll
> see I've already added a couple WIP dm-thinp patches ontop.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Mon, 2015-08-10 at 09:14 -0700, Ming Lin wrote:
> On Mon, 2015-08-10 at 11:02 -0400, Mike Snitzer wrote:
> > On Sun, Aug 09 2015 at  3:18am -0400,
> > Ming Lin <mlin@kernel.org> wrote:
> > 
> > > On Sun, 2015-08-09 at 00:01 -0700, Christoph Hellwig wrote:
> > > > On Sat, Aug 08, 2015 at 11:55:47PM -0700, Ming Lin wrote:
> > > > > Will change it to MAX_BIO_SECTORS.
> > > > > May I add your ACK?
> > > > 
> > > > Yes, please go ahead.
> > > 
> > > Thanks. I'll send a new version of the series once device-mapper guy
> > > acks.
> > > 
> > > Hi Mike,
> > > 
> > > I have updated my tree. Could you pull and re-test?
> > > https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/log/?h=block-generic-req
> > > 
> > > The 2 thin-provisioning tests passed.
> > 
> > I've merged your latest branch with my dm-4.3 branch, I had one conflict
> > in the merge due to the dm_merge_bvec() change from 4.2-rc6 (no
> > surprise).  I've published the result here:
> > http://git.kernel.org/cgit/linux/kernel/git/snitzer/linux.git/log/?h=block-late-bio-splitting
> > 
> > It passes the device-mapper-test-suite's 'thin-provisioning' tests.
> > 
> > > Hope I can have your ACK soon.
> > 
> > Shouldn't we also be using MAX_BIO_SECTORS in blkdev_issue_write_same
> > (instead of UINT_MAX >> 9)?
> 
> I also prefer using MAX_BIO_SECTORS.
> Otherwise, we may have non page size aligned splits.
> 
> Say, write_same 8G.
> 
> Using UINT_MAX >> 9, we'll have 2 sector aligned splits in
> blkdev_issue_write_same():
> 0 - (4G - 512 - 1)
> (4G - 512, 8G -1)

Actually, 3 sector aligned splits.

0 - (4G-512-1)
(4G-512), (8G-512-1)
(8G-512), (8G-1)

> 
> This looks weired.
> 
> Using MAX_BIO_SECTORS, we'll have 4 page size aligned splits:
> 0 - (2G -1)
> 2G - (4G - 1)
> 4G - (6G - 1)
> 6G - (8G - 1)
> 
> I'll use MAX_BIO_SECTORS in blkdev_issue_write_same() if no objection.
> 
> > 
> > Aside from that, I'm in favor of seeing this late bio splitting patchset
> > finally land upstream (hopefully in time for the 4.3 merge, Jens?):
> > 
> > Acked-by: Mike Snitzer <snitzer@redhat.com>
> 
> Thanks!
> 
> May I add your Ack to "PATCH: block: kill merge_bvec_fn() completely"
> also?
> 
> > 
> > p.s. I'll be working with Joe Thornber on optimizing DM (particularly
> > dm-thinp and dm-cache) once this patchset is included upstream.  You'll
> > see I've already added a couple WIP dm-thinp patches ontop.
> 

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:

Mike> Shouldn't we also be using MAX_BIO_SECTORS in
Mike> blkdev_issue_write_same (instead of UINT_MAX >> 9)?

The granularity of WRITE SAME is always 1 logical block and there is no
reason to round it down to the next power of two.

+/*
+ * 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_DISCARD_SECTORS ((1U << 31) >> 9)
+

That's fine for SATA since we're already capping at 2TB minus change.
But it means we'll be capping unnecessarily on SCSI. And larger range
counts are impending in SATA as well.

So this goes back to my original comment: The only place there can be a
discard granularity is for SCSI UNMAP. And consequently, we should only
enforce alignment and granularity when that code path is taken in sd.c.

I'm OK with Ming's patch series in general. Let's leave the discard cap
at UINT_MAX and I'll twiddle the rest in SCSI.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:

Ming,

Ming> I also prefer using MAX_BIO_SECTORS.  Otherwise, we may have non
Ming> page size aligned splits.

This does not matter for write same and discard since there is only a
single logical block of payload. Also, given limitations in SATA we're
always issuing 2GB-32KB sized discards. Rounding those down to an even
1GB would impact performance.

I am sympathetic to wanting to issue I/Os that are aligned to powers of
two. But for most devices this matters little since the additional cost
is limited to misaligned head and tail blocks.

One thing that may be worth considering is switching bi_size from bytes
to blocks for REQ_FS. That would give us some headroom without
increasing bi_size beyond 32 bits. But I'm not entirely sure it's worth
the pain.

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Mon, Aug 10 2015 at 12:14pm -0400,
Ming Lin <mlin@kernel.org> wrote:

> On Mon, 2015-08-10 at 11:02 -0400, Mike Snitzer wrote:
> > 
> > Aside from that, I'm in favor of seeing this late bio splitting patchset
> > finally land upstream (hopefully in time for the 4.3 merge, Jens?):
> > 
> > Acked-by: Mike Snitzer <snitzer@redhat.com>
> 
> Thanks!
> 
> May I add your Ack to "PATCH: block: kill merge_bvec_fn() completely"
> also?

Sure, but please fold in the removal of dm.c comments I made in this
merge commit:

http://git.kernel.org/cgit/linux/kernel/git/snitzer/linux.git/commit/?h=block-late-bio-splitting&id=d6df875bb65ef1ee10c91cf09cb58d009286321f

thanks.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Mon, 2015-08-10 at 12:22 -0400, Martin K. Petersen wrote:
> >>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:
> 
> Mike> Shouldn't we also be using MAX_BIO_SECTORS in
> Mike> blkdev_issue_write_same (instead of UINT_MAX >> 9)?
> 
> The granularity of WRITE SAME is always 1 logical block and there is no
> reason to round it down to the next power of two.
> 
> +/*
> + * 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_DISCARD_SECTORS ((1U << 31) >> 9)
> +
> 
> That's fine for SATA since we're already capping at 2TB minus change.
> But it means we'll be capping unnecessarily on SCSI. And larger range
> counts are impending in SATA as well.
> 
> So this goes back to my original comment: The only place there can be a
> discard granularity is for SCSI UNMAP. And consequently, we should only
> enforce alignment and granularity when that code path is taken in sd.c.
> 
> I'm OK with Ming's patch series in general. Let's leave the discard cap
> at UINT_MAX and I'll twiddle the rest in SCSI.

Just to make sure I didn't misunderstand it.

Did you mean still use (UINT_MAX >> 9) in blkdev_issue_discard()?

	req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
instead of:
	req_sects = min_t(sector_t, nr_sects, MAX_DISCARD_SECTORS);

But that doesn't work for dm-thinp. See Kent's suggestion to use 1<<31.
https://www.redhat.com/archives/dm-devel/2015-August/msg00053.html

> 
> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
> 

Thanks!

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Mon, Aug 10, 2015 at 11:13 AM, Mike Snitzer <snitzer@redhat.com> wrote:
> On Mon, Aug 10 2015 at 12:14pm -0400,
> Ming Lin <mlin@kernel.org> wrote:
>
>> On Mon, 2015-08-10 at 11:02 -0400, Mike Snitzer wrote:
>> >
>> > Aside from that, I'm in favor of seeing this late bio splitting patchset
>> > finally land upstream (hopefully in time for the 4.3 merge, Jens?):
>> >
>> > Acked-by: Mike Snitzer <snitzer@redhat.com>
>>
>> Thanks!
>>
>> May I add your Ack to "PATCH: block: kill merge_bvec_fn() completely"
>> also?
>
> Sure, but please fold in the removal of dm.c comments I made in this
> merge commit:
>
> http://git.kernel.org/cgit/linux/kernel/git/snitzer/linux.git/commit/?h=block-late-bio-splitting&id=d6df875bb65ef1ee10c91cf09cb58d009286321f

Rebased on top of latest Linus tree(4.2-rc6+).

https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/diff/drivers/md/dm.c?h=block-generic-req&id=3dd8509a3f05152cca83bc41c37a8ba3e9119736

>
> thanks.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:

Ming> Did you mean still use (UINT_MAX >> 9) in blkdev_issue_discard()?

Ming> But that doesn't work for dm-thinp. See Kent's suggestion to use
Ming> 1<<31.

I'm not sure why things are not working for dm-thinp. Presumably Kent's
code would split the discard at a granularity boundary so why would that
cause problems for dm?

In looking at this I just found out that we'll corrupt data on certain
SCSI configs with the granularity enforcement in place. I'll have to
conjure up a fix for that...

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Mon, Aug 10 2015 at 10:00pm -0400,
Martin K. Petersen <martin.petersen@oracle.com> wrote:

> >>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:
> 
> Ming> Did you mean still use (UINT_MAX >> 9) in blkdev_issue_discard()?
> 
> Ming> But that doesn't work for dm-thinp. See Kent's suggestion to use
> Ming> 1<<31.
> 
> I'm not sure why things are not working for dm-thinp. Presumably Kent's
> code would split the discard at a granularity boundary so why would that
> cause problems for dm?

DM-thinp processes discards internally before it passes them down (if
configured to do so).  If a discard is smaller than the granularity of a
thinp block (whose size is configurable) or if the start and end of the
discard's extent is misaligned (relative to the thinp blocks mapped to
the logical extent) then the discard won't actually discard partial
thinp blocks.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Kent Overstreet]

On Mon, Aug 10, 2015 at 10:41:55PM -0400, Mike Snitzer wrote:
> On Mon, Aug 10 2015 at 10:00pm -0400,
> Martin K. Petersen <martin.petersen@oracle.com> wrote:
> 
> > >>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:
> > 
> > Ming> Did you mean still use (UINT_MAX >> 9) in blkdev_issue_discard()?
> > 
> > Ming> But that doesn't work for dm-thinp. See Kent's suggestion to use
> > Ming> 1<<31.
> > 
> > I'm not sure why things are not working for dm-thinp. Presumably Kent's
> > code would split the discard at a granularity boundary so why would that
> > cause problems for dm?
> 
> DM-thinp processes discards internally before it passes them down (if
> configured to do so).  If a discard is smaller than the granularity of a
> thinp block (whose size is configurable) or if the start and end of the
> discard's extent is misaligned (relative to the thinp blocks mapped to
> the logical extent) then the discard won't actually discard partial
> thinp blocks.

This kind of logic really doesn't belong in dm - if it's needed, it really
belongs in bio_split() (which is supposed to work correctly for discards - so if
it is needed, then bio_split() needs fixing...)

IMO though it belongs in the driver - if a discard needs to be dropped because
it's too small and the hardware can't do it, that should be the driver's
responsibility.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Mon, Aug 10 2015 at 11:38pm -0400,
Kent Overstreet <kent.overstreet@gmail.com> wrote:

> On Mon, Aug 10, 2015 at 10:41:55PM -0400, Mike Snitzer wrote:
> > On Mon, Aug 10 2015 at 10:00pm -0400,
> > Martin K. Petersen <martin.petersen@oracle.com> wrote:
> > 
> > > >>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:
> > > 
> > > Ming> Did you mean still use (UINT_MAX >> 9) in blkdev_issue_discard()?
> > > 
> > > Ming> But that doesn't work for dm-thinp. See Kent's suggestion to use
> > > Ming> 1<<31.
> > > 
> > > I'm not sure why things are not working for dm-thinp. Presumably Kent's
> > > code would split the discard at a granularity boundary so why would that
> > > cause problems for dm?
> > 
> > DM-thinp processes discards internally before it passes them down (if
> > configured to do so).  If a discard is smaller than the granularity of a
> > thinp block (whose size is configurable) or if the start and end of the
> > discard's extent is misaligned (relative to the thinp blocks mapped to
> > the logical extent) then the discard won't actually discard partial
> > thinp blocks.
> 
> This kind of logic really doesn't belong in dm - if it's needed, it really
> belongs in bio_split() (which is supposed to work correctly for discards - so if
> it is needed, then bio_split() needs fixing...)

DM thinp does advertise discard_granularity that reflects the thinp blocksize.
blk_queue_split() does look like it'd do the right thing.  But the
splitting that DM thinp is doing is a long standing implementation (in
DM core) that will need to be carefully reviewed/rewritten.  We can
tackle it after all this late splitting code lands.

> IMO though it belongs in the driver - if a discard needs to be dropped because
> it's too small and the hardware can't do it, that should be the driver's
> responsibility.

This isn't about the hardware's limits.  This is about the intermediate
remapping/stacking driver's own space management hooking off of the
discard bio too.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:

Mike> DM-thinp processes discards internally before it passes them down
Mike> (if configured to do so).  If a discard is smaller than the
Mike> granularity of a thinp block (whose size is configurable) or if
Mike> the start and end of the discard's extent is misaligned (relative
Mike> to the thinp blocks mapped to the logical extent) then the discard
Mike> won't actually discard partial thinp blocks.

That's fine. You can throw away anything you don't like as long as
discard_zeroes_data=0.

But I don't understand why having an artificial cap at 2GB fixes
things. Other than making it less likely for you to receive a runt by
virtue of being aligned to a power of two.

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Mike Snitzer]

On Tue, Aug 11 2015 at  1:36pm -0400,
Martin K. Petersen <martin.petersen@oracle.com> wrote:

> >>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:
> 
> Mike> DM-thinp processes discards internally before it passes them down
> Mike> (if configured to do so).  If a discard is smaller than the
> Mike> granularity of a thinp block (whose size is configurable) or if
> Mike> the start and end of the discard's extent is misaligned (relative
> Mike> to the thinp blocks mapped to the logical extent) then the discard
> Mike> won't actually discard partial thinp blocks.
> 
> That's fine. You can throw away anything you don't like as long as
> discard_zeroes_data=0.

Correct, dm-thinp sets discard_zeroes_data=0

> But I don't understand why having an artificial cap at 2GB fixes
> things. Other than making it less likely for you to receive a runt by
> virtue of being aligned to a power of two.

That is the benefit.  And when coupled with the new default max_discard
of 64K (pending change from Jens for 4.3) this 2GB upper limit really
isn't such a big deal.  Unless I'm missing something...

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Kent" == Kent Overstreet <kent.overstreet@gmail.com> writes:

Kent> This kind of logic really doesn't belong in dm

Well it does in this case since the thinp personality actually
provisions and unprovisions space.

But there is a difference between what dm thinp acts on for its own
internal provisioning purposes and what it passes down the stack. I am
really against dropping information anywhere along the path. We don't
round off read/write requests either.

The queue limits were meant as hints to mkfs.* so that on-disk data
structures could be laid out in an aligned and storage friendly way. I
never intended for the hints to affect runtime behavior.

Kent> IMO though it belongs in the driver - if a discard needs to be
Kent> dropped because it's too small and the hardware can't do it, that
Kent> should be the driver's responsibility.

I agree except I really don't want to lop off anything unless the device
locks up if we send it partial blocks. There was an array that had
problems a while back but I believe they have been fixed.

The fundamental premise should be that we pass as comprehensive
information as we can. And the device can then decide to ignore all or
parts of the request. That's fundamentally how things work at the
protocol level in both SCSI and SATA. I don't see any reason why the
Linux I/O stack should behave in a different manner.

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:

Mike> That is the benefit.  And when coupled with the new default
Mike> max_discard of 64K (pending change from Jens for 4.3) this 2GB
Mike> upper limit really isn't such a big deal.  Unless I'm missing
Mike> something...

2GB is fine for current SATA due to the stupid range descriptors. But
there are some changes in the pipeline to support descriptors with
bigger ranges so that will change.

However, we currently do 4GB discards on SCSI so the proposed cap will
cut that in half. I'm OK with that as an interim solution. though.

But I'm a bit concerned about what might be lurking in dm thinp if you
trip over partial blocks like in Ming's example...

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Martin" == Martin K Petersen <martin.petersen@oracle.com> writes:

Martin> I agree except I really don't want to lop off anything unless
Martin> the device locks up if we send it partial blocks. There was an
Martin> array that had problems a while back but I believe they have
Martin> been fixed.

Oh, and there are several arrays out there that have allocation units
that are not powers of two. *sigh*

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Tue, 2015-08-11 at 14:05 -0400, Martin K. Petersen wrote:
> >>>>> "Martin" == Martin K Petersen <martin.petersen@oracle.com> writes:
> 
> Martin> I agree except I really don't want to lop off anything unless
> Martin> the device locks up if we send it partial blocks. There was an
> Martin> array that had problems a while back but I believe they have
> Martin> been fixed.
> 
> Oh, and there are several arrays out there that have allocation units
> that are not powers of two. *sigh*

Do you still agree we cap discard to 2G as an interim solution?
https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/commit/?h=block-generic-req&id=39d2f5f

If OK, I'll send out new version asking Jens to apply.

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Martin K. Petersen]

>>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:

Ming> Do you still agree we cap discard to 2G as an interim solution?

I can live with the 2G cap for 4.3 but would like to see it fixed
properly in 4.4.

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Ming Lin]

On Tue, 2015-08-11 at 20:24 -0400, Martin K. Petersen wrote:
> >>>>> "Ming" == Ming Lin <mlin@kernel.org> writes:
> 
> Ming> Do you still agree we cap discard to 2G as an interim solution?
> 
> I can live with the 2G cap for 4.3 but would like to see it fixed
> properly in 4.4.

Sure. I'd like to work on the fix.

Re: [dm-devel] [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[Hannes Reinecke]

On 08/08/2015 11:02 AM, Kent Overstreet wrote:
> On Sat, Aug 08, 2015 at 10:52:24AM +0200, Hannes Reinecke wrote:
>> Wouldn't it be easier to move both max_write_same_sectors and
>> max_discard sectors to 64 bit (ie to type sector_t) and be done with the
>> overflow?
>> Seems to me this is far too much coding around self-imposed restrictions...
> 
> It's bio->bi_iter.bi_size that would have to be increased to 64 bits. Which I
> suppose wouldn't actually increase the size of struct bio (when sector_t is 64
> bits), since struct bvec_iter has padding right now...
> 
Which I guess we should be doing anyway.
Devices are getting larger and larger, so in the long run in need to
be moved to 64 bits.

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		               zSeries & Storage
hare@suse.de			               +49 911 74053 688
SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: F. Imendörffer, J. Smithard, J. Guild, D. Upmanyu, G. Norton
HRB 21284 (AG Nürnberg)

[PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios

[mlin]

From: Kent Overstreet <kent.overstreet@gmail.com>

The way the block layer is currently written, it goes to great lengths
to avoid having to split bios; upper layer code (such as bio_add_page())
checks what the underlying device can handle and tries to always create
bios that don't need to be split.

But this approach becomes unwieldy and eventually breaks down with
stacked devices and devices with dynamic limits, and it adds a lot of
complexity. If the block layer could split bios as needed, we could
eliminate a lot of complexity elsewhere - 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
(potentially multiple) devices underneath them.  In the future this will
let us delete merge_bvec_fn and a bunch of other code.

We do this by adding calls to blk_queue_split() to the various
make_request functions that need it - a few can already handle arbitrary
size bios. Note that we add the call _after_ any call to
blk_queue_bounce(); this means that blk_queue_split() and
blk_recalc_rq_segments() don't need to be concerned with bouncing
affecting segment merging.

Some make_request_fn() callbacks were simple enough to audit and verify
they don't need blk_queue_split() calls. The skipped ones are:

 * nfhd_make_request (arch/m68k/emu/nfblock.c)
 * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
 * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
 * brd_make_request (ramdisk - drivers/block/brd.c)
 * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c)
 * loop_make_request
 * null_queue_bio
 * bcache's make_request fns

Some others are almost certainly safe to remove now, but will be left
for future patches.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Ming Lei <ming.lei@canonical.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Jim Paris <jim@jtan.com>
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits)
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: skip more mq-based drivers, resolve merge conflicts, etc.]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
---
 block/blk-core.c                            |  19 ++--
 block/blk-merge.c                           | 159 ++++++++++++++++++++++++++--
 block/blk-mq.c                              |   4 +
 block/blk-sysfs.c                           |   3 +
 drivers/block/drbd/drbd_req.c               |   2 +
 drivers/block/pktcdvd.c                     |   6 +-
 drivers/block/ps3vram.c                     |   2 +
 drivers/block/rsxx/dev.c                    |   2 +
 drivers/block/umem.c                        |   2 +
 drivers/block/zram/zram_drv.c               |   2 +
 drivers/md/dm.c                             |   2 +
 drivers/md/md.c                             |   2 +
 drivers/s390/block/dcssblk.c                |   2 +
 drivers/s390/block/xpram.c                  |   2 +
 drivers/staging/lustre/lustre/llite/lloop.c |   2 +
 include/linux/blkdev.h                      |   3 +
 16 files changed, 192 insertions(+), 22 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 82819e6..cecf80c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -645,6 +645,10 @@ 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 +657,7 @@ 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 +699,8 @@ 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 +1618,8 @@ 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
@@ -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,
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 30a0d9f..3707f30 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,12 +9,158 @@
 
 #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;
+	int prev = 0;
+
+	struct bvec_merge_data bvm = {
+		.bi_bdev	= bio->bi_bdev,
+		.bi_sector	= bio->bi_iter.bi_sector,
+		.bi_size	= 0,
+		.bi_rw		= bio->bi_rw,
+	};
+
+	bio_for_each_segment(bv, bio, iter) {
+		if (q->merge_bvec_fn &&
+		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
+			goto split;
+
+		bvm.bi_size += bv.bv_len;
+
+		if (bvm.bi_size >> 9 > 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 (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
+		    prev && bvec_gap_to_prev(&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 +182,6 @@ 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 +191,7 @@ 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 +211,8 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f537796..40d08e3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,6 +1291,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
@@ -1376,6 +1378,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6264b38..9a25db3 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -523,6 +523,9 @@ 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);
 }
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3907202..a6265bc 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1497,6 +1497,8 @@ 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;
 
 	/*
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4c20c22..05a81ae 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -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);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index b1612eb..748c63c 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -605,6 +605,8 @@ 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/rsxx/dev.c b/drivers/block/rsxx/dev.c
index ac8c62c..50ef199 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -148,6 +148,8 @@ 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)
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 4cf81b5..13d577c 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -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/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fb655e8..44e3b89 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -901,6 +901,8 @@ 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);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f331d88..530fc9a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1800,6 +1800,8 @@ 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 */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d429c30..10bf6d4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -257,6 +257,8 @@ 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);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index da21281..267ca3a 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/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)
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 7d4e939..1305ed3 100644
--- a/drivers/s390/block/xpram.c
+++ b/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. */
diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c
index cc00fd1..1e33d54 100644
--- a/drivers/staging/lustre/lustre/llite/lloop.c
+++ b/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;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4068c1..dc89cc8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -462,6 +462,7 @@ struct request_queue {
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
+	struct bio_set		*bio_split;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -782,6 +783,8 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
+extern void blk_queue_split(struct request_queue *, struct bio **,
+			    struct bio_set *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
-- 
1.9.1