Merge tag 'md-6.19-20251111' of gitolite.kernel.org:pub/scm/linux/kernel/git/mdraid/linux into for-6.19/block

Pull MD changes from Yu:

"- Change maintainer's email address (Yu Kuai)
 - Data can be lost if array is created with different lbs devices, fix
   this problem and record lbs of the array in metadata (Li Nan)
 - Fix rcu protection for md_thread (Yun Zhou)
 - Fix mddev kobject lifetime regression (Xiao Ni)
 - Enable atomic writes for md-linear (John Garry)
 - Some cleanups (Chen Ni, Huiwen He, Wu Guanghao)"

* tag 'md-6.19-20251111' of gitolite.kernel.org:pub/scm/linux/kernel/git/mdraid/linux:
  md: allow configuring logical block size
  md: add check_new_feature module parameter
  md/raid0: Move queue limit setup before r0conf initialization
  md: init bioset in mddev_init
  md: delete md_redundancy_group when array is becoming inactive
  md: prevent adding disks with larger logical_block_size to active arrays
  md/raid5: remove redundant __GFP_NOWARN
  md: avoid repeated calls to del_gendisk
  md/md-llbitmap: Remove unneeded semicolon
  md/md-linear: Enable atomic writes
  Factor out code into md_should_do_recovery()
  md: fix rcu protection in md_wakeup_thread
  md: delete mddev kobj before deleting gendisk kobj
  MAINTAINERS: Update Yu Kuai's E-mail address

12 files changed, 225 insertions, 75 deletions

diff --git a/Documentation/admin-guide/md.rst b/Documentation/admin-guide/md.rst
index deed823eab01..dc7eab191caa 100644
--- a/Documentation/admin-guide/md.rst
+++ b/Documentation/admin-guide/md.rst
@@ -238,6 +238,16 @@ All md devices contain:
      the number of devices in a raid4/5/6, or to support external
      metadata formats which mandate such clipping.
 
+  logical_block_size
+     Configure the array's logical block size in bytes. This attribute
+     is only supported for 1.x meta. Write the value before starting
+     array. The final array LBS uses the maximum between this
+     configuration and LBS of all combined devices. Note that
+     LBS cannot exceed PAGE_SIZE before RAID supports folio.
+     WARNING: Arrays created on new kernel cannot be assembled at old
+     kernel due to padding check, Set module parameter 'check_new_feature'
+     to false to bypass, but data loss may occur.
+
   reshape_position
      This is either ``none`` or a sector number within the devices of
      the array where ``reshape`` is up to.  If this is set, the three
diff --git a/MAINTAINERS b/MAINTAINERS
index 545a4776795e..ce7f67e09910 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4300,7 +4300,7 @@ F:	Documentation/filesystems/befs.rst
 F:	fs/befs/
 
 BFQ I/O SCHEDULER
-M:	Yu Kuai <yukuai3@huawei.com>
+M:	Yu Kuai <yukuai@fnnas.com>
 L:	linux-block@vger.kernel.org
 S:	Odd Fixes
 F:	Documentation/block/bfq-iosched.rst
@@ -23842,7 +23842,7 @@ F:	include/linux/property.h
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Song Liu <song@kernel.org>
-M:	Yu Kuai <yukuai3@huawei.com>
+M:	Yu Kuai <yukuai@fnnas.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-raid/list/
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 7033d982d377..8d7b82c4a723 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -72,9 +72,11 @@ static int linear_set_limits(struct mddev *mddev)
 
 	md_init_stacking_limits(&lim);
 	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
 		return err;
diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c
index 1eb434306162..9c1ade19b774 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -378,7 +378,7 @@ static void llbitmap_infect_dirty_bits(struct llbitmap *llbitmap,
 		case BitClean:
 			pctl->state[pos] = BitDirty;
 			break;
-		};
+		}
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 41c476b40c7a..7b5c5967568f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -99,7 +99,7 @@ static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this);
 static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
-static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
+static void md_wakeup_thread_directly(struct md_thread __rcu **thread);
 
 /*
  * Default number of read corrections we'll attempt on an rdev
@@ -339,6 +339,7 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 static bool legacy_async_del_gendisk = true;
+static bool check_new_feature = true;
 
 /*
  * We have a system wide 'event count' that is incremented
@@ -730,6 +731,8 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev)
 
 int mddev_init(struct mddev *mddev)
 {
+	int err = 0;
+
 	if (!IS_ENABLED(CONFIG_MD_BITMAP))
 		mddev->bitmap_id = ID_BITMAP_NONE;
 	else
@@ -741,10 +744,23 @@ int mddev_init(struct mddev *mddev)
 
 	if (percpu_ref_init(&mddev->writes_pending, no_op,
 			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
-		percpu_ref_exit(&mddev->active_io);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto exit_acitve_io;
 	}
 
+	err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (err)
+		goto exit_writes_pending;
+
+	err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (err)
+		goto exit_bio_set;
+
+	err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
+			  offsetof(struct md_io_clone, bio_clone), 0);
+	if (err)
+		goto exit_sync_set;
+
 	/* We want to start with the refcount at zero */
 	percpu_ref_put(&mddev->writes_pending);
 
@@ -773,11 +789,24 @@ int mddev_init(struct mddev *mddev)
 	INIT_WORK(&mddev->del_work, mddev_delayed_delete);
 
 	return 0;
+
+exit_sync_set:
+	bioset_exit(&mddev->sync_set);
+exit_bio_set:
+	bioset_exit(&mddev->bio_set);
+exit_writes_pending:
+	percpu_ref_exit(&mddev->writes_pending);
+exit_acitve_io:
+	percpu_ref_exit(&mddev->active_io);
+	return err;
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
 void mddev_destroy(struct mddev *mddev)
 {
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
+	bioset_exit(&mddev->io_clone_set);
 	percpu_ref_exit(&mddev->active_io);
 	percpu_ref_exit(&mddev->writes_pending);
 }
@@ -941,8 +970,11 @@ void mddev_unlock(struct mddev *mddev)
 		 * 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))
+		if (test_bit(MD_DELETED, &mddev->flags) &&
+		    !test_and_set_bit(MD_DO_DELETE, &mddev->flags)) {
+			kobject_del(&mddev->kobj);
 			del_gendisk(mddev->gendisk);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
@@ -1820,9 +1852,13 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	}
 	if (sb->pad0 ||
 	    sb->pad3[0] ||
-	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1])))
-		/* Some padding is non-zero, might be a new feature */
-		return -EINVAL;
+	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1]))) {
+		pr_warn("Some padding is non-zero on %pg, might be a new feature\n",
+			rdev->bdev);
+		if (check_new_feature)
+			return -EINVAL;
+		pr_warn("check_new_feature is disabled, data corruption possible\n");
+	}
 
 	rdev->preferred_minor = 0xffff;
 	rdev->data_offset = le64_to_cpu(sb->data_offset);
@@ -1963,6 +1999,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
 		mddev->layout = le32_to_cpu(sb->layout);
 		mddev->raid_disks = le32_to_cpu(sb->raid_disks);
 		mddev->dev_sectors = le64_to_cpu(sb->size);
+		mddev->logical_block_size = le32_to_cpu(sb->logical_block_size);
 		mddev->events = ev1;
 		mddev->bitmap_info.offset = 0;
 		mddev->bitmap_info.space = 0;
@@ -2172,6 +2209,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
 	sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
 	sb->level = cpu_to_le32(mddev->level);
 	sb->layout = cpu_to_le32(mddev->layout);
+	sb->logical_block_size = cpu_to_le32(mddev->logical_block_size);
 	if (test_bit(FailFast, &rdev->flags))
 		sb->devflags |= FailFast1;
 	else
@@ -5134,7 +5172,7 @@ static void stop_sync_thread(struct mddev *mddev, bool locked)
 	 * Thread might be blocked waiting for metadata update which will now
 	 * never happen
 	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
+	md_wakeup_thread_directly(&mddev->sync_thread);
 	if (work_pending(&mddev->sync_work))
 		flush_work(&mddev->sync_work);
 
@@ -5900,6 +5938,68 @@ static struct md_sysfs_entry md_serialize_policy =
 __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show,
        serialize_policy_store);
 
+static int mddev_set_logical_block_size(struct mddev *mddev,
+				unsigned int lbs)
+{
+	int err = 0;
+	struct queue_limits lim;
+
+	if (queue_logical_block_size(mddev->gendisk->queue) >= lbs) {
+		pr_err("%s: Cannot set LBS smaller than mddev LBS %u\n",
+		       mdname(mddev), lbs);
+		return -EINVAL;
+	}
+
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.logical_block_size = lbs;
+	pr_info("%s: logical_block_size is changed, data may be lost\n",
+		mdname(mddev));
+	err = queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	if (err)
+		return err;
+
+	mddev->logical_block_size = lbs;
+	/* New lbs will be written to superblock after array is running */
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
+	return 0;
+}
+
+static ssize_t
+lbs_show(struct mddev *mddev, char *page)
+{
+	return sprintf(page, "%u\n", mddev->logical_block_size);
+}
+
+static ssize_t
+lbs_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	unsigned int lbs;
+	int err = -EBUSY;
+
+	/* Only 1.x meta supports configurable LBS */
+	if (mddev->major_version == 0)
+		return -EINVAL;
+
+	if (mddev->pers)
+		return -EBUSY;
+
+	err = kstrtouint(buf, 10, &lbs);
+	if (err < 0)
+		return -EINVAL;
+
+	err = mddev_lock(mddev);
+	if (err)
+		goto unlock;
+
+	err = mddev_set_logical_block_size(mddev, lbs);
+
+unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
+}
+
+static struct md_sysfs_entry md_logical_block_size =
+__ATTR(logical_block_size, 0644, lbs_show, lbs_store);
 
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
@@ -5922,6 +6022,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_consistency_policy.attr,
 	&md_fail_last_dev.attr,
 	&md_serialize_policy.attr,
+	&md_logical_block_size.attr,
 	NULL,
 };
 
@@ -6052,6 +6153,17 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
 			return -EINVAL;
 	}
 
+	/*
+	 * Before RAID adding folio support, the logical_block_size
+	 * should be smaller than the page size.
+	 */
+	if (lim->logical_block_size > PAGE_SIZE) {
+		pr_err("%s: logical_block_size must not larger than PAGE_SIZE\n",
+			mdname(mddev));
+		return -EINVAL;
+	}
+	mddev->logical_block_size = lim->logical_block_size;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
@@ -6064,6 +6176,13 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev_is_dm(mddev))
 		return 0;
 
+	if (queue_logical_block_size(rdev->bdev->bd_disk->queue) >
+	    queue_logical_block_size(mddev->gendisk->queue)) {
+		pr_err("%s: incompatible logical_block_size, can not add\n",
+		       mdname(mddev));
+		return -EINVAL;
+	}
+
 	lim = queue_limits_start_update(mddev->gendisk->queue);
 	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
 				mddev->gendisk->disk_name);
@@ -6384,29 +6503,9 @@ int md_run(struct mddev *mddev)
 		nowait = nowait && bdev_nowait(rdev->bdev);
 	}
 
-	if (!bioset_initialized(&mddev->bio_set)) {
-		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (err)
-			return err;
-	}
-	if (!bioset_initialized(&mddev->sync_set)) {
-		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (err)
-			goto exit_bio_set;
-	}
-
-	if (!bioset_initialized(&mddev->io_clone_set)) {
-		err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
-				  offsetof(struct md_io_clone, bio_clone), 0);
-		if (err)
-			goto exit_sync_set;
-	}
-
 	pers = get_pers(mddev->level, mddev->clevel);
-	if (!pers) {
-		err = -EINVAL;
-		goto abort;
-	}
+	if (!pers)
+		return -EINVAL;
 	if (mddev->level != pers->head.id) {
 		mddev->level = pers->head.id;
 		mddev->new_level = pers->head.id;
@@ -6417,8 +6516,7 @@ int md_run(struct mddev *mddev)
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
 		put_pers(pers);
-		err = -EINVAL;
-		goto abort;
+		return -EINVAL;
 	}
 
 	if (pers->sync_request) {
@@ -6545,12 +6643,6 @@ bitmap_abort:
 	mddev->private = NULL;
 	put_pers(pers);
 	md_bitmap_destroy(mddev);
-abort:
-	bioset_exit(&mddev->io_clone_set);
-exit_sync_set:
-	bioset_exit(&mddev->sync_set);
-exit_bio_set:
-	bioset_exit(&mddev->bio_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6683,6 +6775,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->chunk_sectors = 0;
 	mddev->ctime = mddev->utime = 0;
 	mddev->layout = 0;
+	mddev->logical_block_size = 0;
 	mddev->max_disks = 0;
 	mddev->events = 0;
 	mddev->can_decrease_events = 0;
@@ -6775,10 +6868,6 @@ static void __md_stop(struct mddev *mddev)
 	mddev->private = NULL;
 	put_pers(pers);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-
-	bioset_exit(&mddev->bio_set);
-	bioset_exit(&mddev->sync_set);
-	bioset_exit(&mddev->io_clone_set);
 }
 
 void md_stop(struct mddev *mddev)
@@ -6869,6 +6958,10 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		if (!md_is_rdwr(mddev))
 			set_disk_ro(disk, 0);
 
+		if (mode == 2 && mddev->pers->sync_request &&
+		    mddev->to_remove == NULL)
+			mddev->to_remove = &md_redundancy_group;
+
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
 
@@ -8373,22 +8466,21 @@ static int md_thread(void *arg)
 	return 0;
 }
 
-static void md_wakeup_thread_directly(struct md_thread __rcu *thread)
+static void md_wakeup_thread_directly(struct md_thread __rcu **thread)
 {
 	struct md_thread *t;
 
 	rcu_read_lock();
-	t = rcu_dereference(thread);
+	t = rcu_dereference(*thread);
 	if (t)
 		wake_up_process(t->tsk);
 	rcu_read_unlock();
 }
 
-void md_wakeup_thread(struct md_thread __rcu *thread)
+void __md_wakeup_thread(struct md_thread __rcu *thread)
 {
 	struct md_thread *t;
 
-	rcu_read_lock();
 	t = rcu_dereference(thread);
 	if (t) {
 		pr_debug("md: waking up MD thread %s.\n", t->tsk->comm);
@@ -8396,9 +8488,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread)
 		if (wq_has_sleeper(&t->wqueue))
 			wake_up(&t->wqueue);
 	}
-	rcu_read_unlock();
 }
-EXPORT_SYMBOL(md_wakeup_thread);
+EXPORT_SYMBOL(__md_wakeup_thread);
 
 struct md_thread *md_register_thread(void (*run) (struct md_thread *),
 		struct mddev *mddev, const char *name)
@@ -9978,6 +10069,52 @@ static void unregister_sync_thread(struct mddev *mddev)
 	md_reap_sync_thread(mddev);
 }
 
+static bool md_should_do_recovery(struct mddev *mddev)
+{
+	/*
+	 * As long as one of the following flags is set,
+	 * recovery needs to do or cleanup.
+	 */
+	if (test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+		return true;
+
+	/*
+	 * If no flags are set and it is in read-only status,
+	 * there is nothing to do.
+	 */
+	if (!md_is_rdwr(mddev))
+		return false;
+
+	/*
+	 * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to
+	 * active, and no action is needed for now.
+	 * All other MD_SB_* flags require to update the superblock.
+	 */
+	if (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING))
+		return true;
+
+	/*
+	 * If the array is not using external metadata and there has been no data
+	 * written for some time, then the array's status needs to be set to
+	 * in_sync.
+	 */
+	if (mddev->external == 0 && mddev->safemode == 1)
+		return true;
+
+	/*
+	 * When the system is about to restart or the process receives an signal,
+	 * the array needs to be synchronized as soon as possible.
+	 * Once the data synchronization is completed, need to change the array
+	 * status to in_sync.
+	 */
+	if (mddev->safemode == 2 && !mddev->in_sync &&
+	    mddev->resync_offset == MaxSector)
+		return true;
+
+	return false;
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -10014,18 +10151,7 @@ void md_check_recovery(struct mddev *mddev)
 		flush_signals(current);
 	}
 
-	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
-		return;
-	if ( ! (
-		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
-		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
-		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-		(mddev->external == 0 && mddev->safemode == 1) ||
-		(mddev->safemode == 2
-		 && !mddev->in_sync && mddev->resync_offset == MaxSector)
-		))
+	if (!md_should_do_recovery(mddev))
 		return;
 
 	if (mddev_trylock(mddev)) {
@@ -10697,6 +10823,7 @@ module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
 module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR);
 module_param(create_on_open, bool, S_IRUSR|S_IWUSR);
 module_param(legacy_async_del_gendisk, bool, 0600);
+module_param(check_new_feature, bool, 0600);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1979c2d4fe89..6985f2829bbd 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -354,6 +354,7 @@ enum mddev_flags {
 	MD_HAS_MULTIPLE_PPLS,
 	MD_NOT_READY,
 	MD_BROKEN,
+	MD_DO_DELETE,
 	MD_DELETED,
 };
 
@@ -432,6 +433,7 @@ struct mddev {
 	sector_t			array_sectors; /* exported array size */
 	int				external_size; /* size managed
 							* externally */
+	unsigned int			logical_block_size;
 	__u64				events;
 	/* If the last 'event' was simply a clean->dirty transition, and
 	 * we didn't write it to the spares, then it is safe and simple
@@ -882,6 +884,12 @@ struct md_io_clone {
 
 #define THREAD_WAKEUP  0
 
+#define md_wakeup_thread(thread) do {   \
+	rcu_read_lock();                    \
+	__md_wakeup_thread(thread);         \
+	rcu_read_unlock();                  \
+} while (0)
+
 static inline void safe_put_page(struct page *p)
 {
 	if (p) put_page(p);
@@ -895,7 +903,7 @@ extern struct md_thread *md_register_thread(
 	struct mddev *mddev,
 	const char *name);
 extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp);
-extern void md_wakeup_thread(struct md_thread __rcu *thread);
+extern void __md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
 extern enum sync_action md_sync_action(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e443e478645a..47aee1b1d4d1 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -68,7 +68,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	struct strip_zone *zone;
 	int cnt;
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	unsigned blksize = 512;
+	unsigned int blksize = queue_logical_block_size(mddev->gendisk->queue);
 
 	*private_conf = ERR_PTR(-ENOMEM);
 	if (!conf)
@@ -84,9 +84,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
-		blksize = max(blksize, queue_logical_block_size(
-				      rdev1->bdev->bd_disk->queue));
-
 		rdev_for_each(rdev2, mddev) {
 			pr_debug("md/raid0:%s:   comparing %pg(%llu)"
 				 " with %pg(%llu)\n",
@@ -383,6 +380,7 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.max_hw_sectors = mddev->chunk_sectors;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	lim.chunk_sectors = mddev->chunk_sectors;
@@ -405,6 +403,12 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			return ret;
+	}
+
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
@@ -413,11 +417,6 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (!mddev_is_dm(mddev)) {
-		ret = raid0_set_limits(mddev);
-		if (ret)
-			return ret;
-	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 592a40233004..57d50465eed1 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3213,6 +3213,7 @@ static int raid1_set_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.max_hw_wzeroes_unmap_sectors = 0;
+	lim.logical_block_size = mddev->logical_block_size;
 	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 14dcd5142eb4..84be4cc7e873 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4000,6 +4000,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.max_hw_wzeroes_unmap_sectors = 0;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index ba768ca7f422..e29e69335c69 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -3104,7 +3104,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 		goto out_mempool;
 
 	spin_lock_init(&log->tree_lock);
-	INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT | __GFP_NOWARN);
+	INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT);
 
 	thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev,
 				    "reclaim");
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 24b32a0c95b4..cdbc7eba5c54 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7745,6 +7745,7 @@ static int raid5_set_limits(struct mddev *mddev)
 	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
 
 	md_init_stacking_limits(&lim);
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
 	lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE;
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index ac74133a4768..310068bb2a1d 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -291,7 +291,8 @@ struct mdp_superblock_1 {
 	__le64	resync_offset;	/* data before this offset (from data_offset) known to be in sync */
 	__le32	sb_csum;	/* checksum up to devs[max_dev] */
 	__le32	max_dev;	/* size of devs[] array to consider */
-	__u8	pad3[64-32];	/* set to 0 when writing */
+	__le32  logical_block_size;	/* same as q->limits->logical_block_size */
+	__u8	pad3[64-36];	/* set to 0 when writing */
 
 	/* device state information. Indexed by dev_number.
 	 * 2 bytes per device