11 files changed, 170 insertions, 82 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2ea490b9d370..1492c8552255 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -168,14 +168,14 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 {
 	const char *err;
 	struct cache_sb_disk *s;
-	struct page *page;
+	struct folio *folio;
 	unsigned int i;
 
-	page = read_cache_page_gfp(bdev->bd_mapping,
-				   SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
-	if (IS_ERR(page))
+	folio = mapping_read_folio_gfp(bdev->bd_mapping,
+			SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
+	if (IS_ERR(folio))
 		return "IO error";
-	s = page_address(page) + offset_in_page(SB_OFFSET);
+	s = folio_address(folio) + offset_in_folio(folio, SB_OFFSET);
 
 	sb->offset		= le64_to_cpu(s->offset);
 	sb->version		= le64_to_cpu(s->version);
@@ -272,7 +272,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	*res = s;
 	return NULL;
 err:
-	put_page(page);
+	folio_put(folio);
 	return err;
 }
 
@@ -1366,7 +1366,7 @@ static CLOSURE_CALLBACK(cached_dev_free)
 	mutex_unlock(&bch_register_lock);
 
 	if (dc->sb_disk)
-		put_page(virt_to_page(dc->sb_disk));
+		folio_put(virt_to_folio(dc->sb_disk));
 
 	if (dc->bdev_file)
 		fput(dc->bdev_file);
@@ -2216,7 +2216,7 @@ void bch_cache_release(struct kobject *kobj)
 		free_fifo(&ca->free[i]);
 
 	if (ca->sb_disk)
-		put_page(virt_to_page(ca->sb_disk));
+		folio_put(virt_to_folio(ca->sb_disk));
 
 	if (ca->bdev_file)
 		fput(ca->bdev_file);
@@ -2593,7 +2593,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!holder) {
 		ret = -ENOMEM;
 		err = "cannot allocate memory";
-		goto out_put_sb_page;
+		goto out_put_sb_folio;
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
@@ -2667,8 +2667,8 @@ async_done:
 
 out_free_holder:
 	kfree(holder);
-out_put_sb_page:
-	put_page(virt_to_page(sb_disk));
+out_put_sb_folio:
+	folio_put(virt_to_folio(sb_disk));
 out_blkdev_put:
 	if (bdev_file)
 		fput(bdev_file);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 17157c4216a5..5ef43231fe77 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -253,17 +253,35 @@ MODULE_PARM_DESC(max_read_size, "Maximum size of a read request");
 static unsigned int max_write_size = 0;
 module_param(max_write_size, uint, 0644);
 MODULE_PARM_DESC(max_write_size, "Maximum size of a write request");
-static unsigned get_max_request_size(struct crypt_config *cc, bool wrt)
+
+static unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio)
 {
+	struct crypt_config *cc = ti->private;
 	unsigned val, sector_align;
-	val = !wrt ? READ_ONCE(max_read_size) : READ_ONCE(max_write_size);
-	if (likely(!val))
-		val = !wrt ? DM_CRYPT_DEFAULT_MAX_READ_SIZE : DM_CRYPT_DEFAULT_MAX_WRITE_SIZE;
-	if (wrt || cc->used_tag_size) {
-		if (unlikely(val > BIO_MAX_VECS << PAGE_SHIFT))
-			val = BIO_MAX_VECS << PAGE_SHIFT;
-	}
-	sector_align = max(bdev_logical_block_size(cc->dev->bdev), (unsigned)cc->sector_size);
+	bool wrt = op_is_write(bio_op(bio));
+
+	if (wrt) {
+		/*
+		 * For zoned devices, splitting write operations creates the
+		 * risk of deadlocking queue freeze operations with zone write
+		 * plugging BIO work when the reminder of a split BIO is
+		 * issued. So always allow the entire BIO to proceed.
+		 */
+		if (ti->emulate_zone_append)
+			return bio_sectors(bio);
+
+		val = min_not_zero(READ_ONCE(max_write_size),
+				   DM_CRYPT_DEFAULT_MAX_WRITE_SIZE);
+	} else {
+		val = min_not_zero(READ_ONCE(max_read_size),
+				   DM_CRYPT_DEFAULT_MAX_READ_SIZE);
+	}
+
+	if (wrt || cc->used_tag_size)
+		val = min(val, BIO_MAX_VECS << PAGE_SHIFT);
+
+	sector_align = max(bdev_logical_block_size(cc->dev->bdev),
+			   (unsigned)cc->sector_size);
 	val = round_down(val, sector_align);
 	if (unlikely(!val))
 		val = sector_align;
@@ -1192,11 +1210,11 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 		return -EINVAL;
 	}
 
-	if (bi->tuple_size < cc->used_tag_size) {
+	if (bi->metadata_size < cc->used_tag_size) {
 		ti->error = "Integrity profile tag size mismatch.";
 		return -EINVAL;
 	}
-	cc->tuple_size = bi->tuple_size;
+	cc->tuple_size = bi->metadata_size;
 	if (1 << bi->interval_exp != cc->sector_size) {
 		ti->error = "Integrity profile sector size mismatch.";
 		return -EINVAL;
@@ -3496,7 +3514,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	/*
 	 * Check if bio is too large, split as needed.
 	 */
-	max_sectors = get_max_request_size(cc, bio_data_dir(bio) == WRITE);
+	max_sectors = get_max_request_sectors(ti, bio);
 	if (unlikely(bio_sectors(bio) > max_sectors))
 		dm_accept_partial_bio(bio, max_sectors);
 
@@ -3733,6 +3751,17 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 		max_t(unsigned int, limits->physical_block_size, cc->sector_size);
 	limits->io_min = max_t(unsigned int, limits->io_min, cc->sector_size);
 	limits->dma_alignment = limits->logical_block_size - 1;
+
+	/*
+	 * For zoned dm-crypt targets, there will be no internal splitting of
+	 * write BIOs to avoid exceeding BIO_MAX_VECS vectors per BIO. But
+	 * without respecting this limit, crypt_alloc_buffer() will trigger a
+	 * BUG(). Avoid this by forcing DM core to split write BIOs to this
+	 * limit.
+	 */
+	if (ti->emulate_zone_append)
+		limits->max_hw_sectors = min(limits->max_hw_sectors,
+					     BIO_MAX_VECS << PAGE_SECTORS_SHIFT);
 }
 
 static struct target_type crypt_target = {
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 4395657fa583..efeee0a873c0 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3906,8 +3906,8 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		struct blk_integrity *bi = &limits->integrity;
 
 		memset(bi, 0, sizeof(*bi));
-		bi->tuple_size = ic->tag_size;
-		bi->tag_size = bi->tuple_size;
+		bi->metadata_size = ic->tag_size;
+		bi->tag_size = bi->metadata_size;
 		bi->interval_exp =
 			ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
 	}
@@ -4746,18 +4746,18 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 			ti->error = "Integrity profile not supported";
 			goto bad;
 		}
-		/*printk("tag_size: %u, tuple_size: %u\n", bi->tag_size, bi->tuple_size);*/
-		if (bi->tuple_size < ic->tag_size) {
+		/*printk("tag_size: %u, metadata_size: %u\n", bi->tag_size, bi->metadata_size);*/
+		if (bi->metadata_size < ic->tag_size) {
 			r = -EINVAL;
 			ti->error = "The integrity profile is smaller than tag size";
 			goto bad;
 		}
-		if ((unsigned long)bi->tuple_size > PAGE_SIZE / 2) {
+		if ((unsigned long)bi->metadata_size > PAGE_SIZE / 2) {
 			r = -EINVAL;
 			ti->error = "Too big tuple size";
 			goto bad;
 		}
-		ic->tuple_size = bi->tuple_size;
+		ic->tuple_size = bi->metadata_size;
 		if (1 << bi->interval_exp != ic->sectors_per_block << SECTOR_SHIFT) {
 			r = -EINVAL;
 			ti->error = "Integrity profile sector size mismatch";
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a7dc04bd55e5..5bbbdf8fc1bd 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -458,6 +458,7 @@ static void stripe_io_hints(struct dm_target *ti,
 	struct stripe_c *sc = ti->private;
 	unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT;
 
+	limits->chunk_sectors = sc->chunk_size;
 	limits->io_min = chunk_size;
 	limits->io_opt = chunk_size * sc->stripes;
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 24a857ff6d0b..d9d5e6aa5707 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -2065,8 +2065,10 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		limits->discard_alignment = 0;
 	}
 
-	if (!dm_table_supports_write_zeroes(t))
+	if (!dm_table_supports_write_zeroes(t)) {
 		limits->max_write_zeroes_sectors = 0;
+		limits->max_hw_wzeroes_unmap_sectors = 0;
+	}
 
 	if (!dm_table_supports_secure_erase(t))
 		limits->max_secure_erase_sectors = 0;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1726f0f828cc..abfe0392b5a4 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1293,8 +1293,9 @@ out:
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management
- * operations, REQ_OP_ZONE_APPEND (zone append writes) and any bio serviced by
- * __send_duplicate_bios().
+ * operations, zone append writes (native with REQ_OP_ZONE_APPEND or emulated
+ * with write BIOs flagged with BIO_EMULATES_ZONE_APPEND) and any bio serviced
+ * by __send_duplicate_bios().
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1327,11 +1328,19 @@ void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors)
 	unsigned int bio_sectors = bio_sectors(bio);
 
 	BUG_ON(dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO));
-	BUG_ON(op_is_zone_mgmt(bio_op(bio)));
-	BUG_ON(bio_op(bio) == REQ_OP_ZONE_APPEND);
 	BUG_ON(bio_sectors > *tio->len_ptr);
 	BUG_ON(n_sectors > bio_sectors);
 
+	if (static_branch_unlikely(&zoned_enabled) &&
+	    unlikely(bdev_is_zoned(bio->bi_bdev))) {
+		enum req_op op = bio_op(bio);
+
+		BUG_ON(op_is_zone_mgmt(op));
+		BUG_ON(op == REQ_OP_WRITE);
+		BUG_ON(op == REQ_OP_WRITE_ZEROES);
+		BUG_ON(op == REQ_OP_ZONE_APPEND);
+	}
+
 	*tio->len_ptr -= bio_sectors - n_sectors;
 	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;
 
@@ -1776,19 +1785,35 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	/*
-	 * For mapped device that need zone append emulation, we must
-	 * split any large BIO that straddles zone boundaries.
+	 * Special case the zone operations that cannot or should not be split.
 	 */
-	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
-		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+	switch (bio_op(bio)) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return false;
+	default:
+		break;
+	}
+
+	/*
+	 * When mapped devices use the block layer zone write plugging, we must
+	 * split any large BIO to the mapped device limits to not submit BIOs
+	 * that span zone boundaries and to avoid potential deadlocks with
+	 * queue freeze operations.
+	 */
+	return bio_needs_zone_write_plugging(bio) || bio_straddles_zones(bio);
 }
+
 static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
-	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+	if (!bio_needs_zone_write_plugging(bio))
+		return false;
+	return blk_zone_plug_bio(bio, 0);
 }
 
 static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
@@ -1904,8 +1929,7 @@ static blk_status_t __send_zone_reset_all(struct clone_info *ci)
 }
 
 #else
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	return false;
 }
@@ -1932,9 +1956,7 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 
 	is_abnormal = is_abnormal_io(bio);
 	if (static_branch_unlikely(&zoned_enabled)) {
-		/* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */
-		need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) &&
-			(is_abnormal || dm_zone_bio_needs_split(md, bio));
+		need_split = is_abnormal || dm_zone_bio_needs_split(bio);
 	} else {
 		need_split = is_abnormal;
 	}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0f03b21e66e4..046fe85c76fe 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -636,9 +636,6 @@ static void __mddev_put(struct mddev *mddev)
 	    mddev->ctime || mddev->hold_active)
 		return;
 
-	/* Array is not configured at all, and not held active, so destroy it */
-	set_bit(MD_DELETED, &mddev->flags);
-
 	/*
 	 * Call queue_work inside the spinlock so that flush_workqueue() after
 	 * mddev_find will succeed in waiting for the work to be done.
@@ -873,6 +870,16 @@ void mddev_unlock(struct mddev *mddev)
 		kobject_del(&rdev->kobj);
 		export_rdev(rdev, mddev);
 	}
+
+	/* Call del_gendisk after release reconfig_mutex to avoid
+	 * deadlock (e.g. call del_gendisk under the lock and an
+	 * access to sysfs files waits the lock)
+	 * And MD_DELETED is only used for md raid which is set in
+	 * do_md_stop. dm raid only uses md_stop to stop. So dm raid
+	 * doesn't need to check MD_DELETED when getting reconfig lock
+	 */
+	if (test_bit(MD_DELETED, &mddev->flags))
+		del_gendisk(mddev->gendisk);
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
 
@@ -5774,19 +5781,30 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
 	struct mddev *mddev = container_of(kobj, struct mddev, kobj);
 	ssize_t rv;
+	struct kernfs_node *kn = NULL;
 
 	if (!entry->store)
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+
+	if (entry->store == array_state_store && cmd_match(page, "clear"))
+		kn = sysfs_break_active_protection(kobj, attr);
+
 	spin_lock(&all_mddevs_lock);
 	if (!mddev_get(mddev)) {
 		spin_unlock(&all_mddevs_lock);
+		if (kn)
+			sysfs_unbreak_active_protection(kn);
 		return -EBUSY;
 	}
 	spin_unlock(&all_mddevs_lock);
 	rv = entry->store(mddev, page, length);
 	mddev_put(mddev);
+
+	if (kn)
+		sysfs_unbreak_active_protection(kn);
+
 	return rv;
 }
 
@@ -5794,12 +5812,6 @@ static void md_kobj_release(struct kobject *ko)
 {
 	struct mddev *mddev = container_of(ko, struct mddev, kobj);
 
-	if (mddev->sysfs_state)
-		sysfs_put(mddev->sysfs_state);
-	if (mddev->sysfs_level)
-		sysfs_put(mddev->sysfs_level);
-
-	del_gendisk(mddev->gendisk);
 	put_disk(mddev->gendisk);
 }
 
@@ -6413,15 +6425,10 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	/*
-	 * Don't clear MD_CLOSING, or mddev can be opened again.
-	 * 'hold_active != 0' means mddev is still in the creation
-	 * process and will be used later.
-	 */
-	if (mddev->hold_active)
-		mddev->flags = 0;
-	else
-		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
+	/* if UNTIL_STOP is set, it's cleared here */
+	mddev->hold_active = 0;
+	/* Don't clear MD_CLOSING, or mddev can be opened again. */
+	mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6516,8 +6523,6 @@ static void __md_stop(struct mddev *mddev)
 	if (mddev->private)
 		pers->free(mddev, mddev->private);
 	mddev->private = NULL;
-	if (pers->sync_request && mddev->to_remove == NULL)
-		mddev->to_remove = &md_redundancy_group;
 	put_pers(pers);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
@@ -6646,10 +6651,8 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		mddev->bitmap_info.offset = 0;
 
 		export_array(mddev);
-
 		md_clean(mddev);
-		if (mddev->hold_active == UNTIL_STOP)
-			mddev->hold_active = 0;
+		set_bit(MD_DELETED, &mddev->flags);
 	}
 	md_new_event();
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -9456,17 +9459,11 @@ static bool md_spares_need_change(struct mddev *mddev)
 	return false;
 }
 
-static int remove_and_add_spares(struct mddev *mddev,
-				 struct md_rdev *this)
+static int remove_spares(struct mddev *mddev, struct md_rdev *this)
 {
 	struct md_rdev *rdev;
-	int spares = 0;
 	int removed = 0;
 
-	if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		/* Mustn't remove devices when resync thread is running */
-		return 0;
-
 	rdev_for_each(rdev, mddev) {
 		if ((this == NULL || rdev == this) && rdev_removeable(rdev) &&
 		    !mddev->pers->hot_remove_disk(mddev, rdev)) {
@@ -9480,6 +9477,21 @@ static int remove_and_add_spares(struct mddev *mddev,
 	if (removed && mddev->kobj.sd)
 		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 
+	return removed;
+}
+
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this)
+{
+	struct md_rdev *rdev;
+	int spares = 0;
+	int removed = 0;
+
+	if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		/* Mustn't remove devices when resync thread is running */
+		return 0;
+
+	removed = remove_spares(mddev, this);
 	if (this && removed)
 		goto no_add;
 
@@ -9522,6 +9534,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
 
 	/* Check if resync is in progress. */
 	if (mddev->recovery_cp < MaxSector) {
+		remove_spares(mddev, NULL);
 		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		return true;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index d45a9e6ead80..67b365621507 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -700,11 +700,26 @@ static inline bool reshape_interrupted(struct mddev *mddev)
 
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
-	return mutex_lock_interruptible(&mddev->reconfig_mutex);
+	int ret;
+
+	ret = mutex_lock_interruptible(&mddev->reconfig_mutex);
+
+	/* MD_DELETED is set in do_md_stop with reconfig_mutex.
+	 * So check it here.
+	 */
+	if (!ret && test_bit(MD_DELETED, &mddev->flags)) {
+		ret = -ENODEV;
+		mutex_unlock(&mddev->reconfig_mutex);
+	}
+
+	return ret;
 }
 
 /* Sometimes we need to take the lock in a situation where
  * failure due to interrupts is not acceptable.
+ * It doesn't need to check MD_DELETED here, the owner which
+ * holds the lock here can't be stopped. And all paths can't
+ * call this function after do_md_stop.
  */
 static inline void mddev_lock_nointr(struct mddev *mddev)
 {
@@ -713,7 +728,14 @@ static inline void mddev_lock_nointr(struct mddev *mddev)
 
 static inline int mddev_trylock(struct mddev *mddev)
 {
-	return mutex_trylock(&mddev->reconfig_mutex);
+	int ret;
+
+	ret = mutex_trylock(&mddev->reconfig_mutex);
+	if (!ret && test_bit(MD_DELETED, &mddev->flags)) {
+		ret = -ENODEV;
+		mutex_unlock(&mddev->reconfig_mutex);
+	}
+	return ret;
 }
 extern void mddev_unlock(struct mddev *mddev);
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index d8f639f4ae12..cbe2a9054cb9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -384,6 +384,7 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
+	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c9bd2005bfd0..95dc354a86a0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2446,15 +2446,12 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	 * that are active
 	 */
 	for (i = 0; i < conf->copies; i++) {
-		int d;
-
 		tbio = r10_bio->devs[i].repl_bio;
 		if (!tbio || !tbio->bi_end_io)
 			continue;
 		if (r10_bio->devs[i].bio->bi_end_io != end_sync_write
 		    && r10_bio->devs[i].bio != fbio)
 			bio_copy_data(tbio, fbio);
-		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
 		submit_bio_noacct(tbio);
 	}
@@ -4012,6 +4009,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
+	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ca5b0e8ba707..7ec61ee7b218 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -9040,7 +9040,7 @@ static int __init raid5_init(void)
 	int ret;
 
 	raid5_wq = alloc_workqueue("raid5wq",
-		WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0);
+		WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_SYSFS, 0);
 	if (!raid5_wq)
 		return -ENOMEM;