Merge tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Improvements to the queue_rqs() support, and adding null_blk support
   for that as well (Chengming)

 - Series improving badblocks support (Coly)

 - Key store support for sed-opal (Greg)

 - IBM partition string handling improvements (Jan)

 - Make number of ublk devices supported configurable (Mike)

 - Cancelation improvements for ublk (Ming)

 - MD pull requests via Song:
     - Handle timeout in md-cluster, by Denis Plotnikov
     - Cleanup pers->prepare_suspend, by Yu Kuai
     - Rewrite mddev_suspend(), by Yu Kuai
     - Simplify md_seq_ops, by Yu Kuai
     - Reduce unnecessary locking array_state_store(), by Mariusz
       Tkaczyk
     - Make rdev add/remove independent from daemon thread, by Yu Kuai
     - Refactor code around quiesce() and mddev_suspend(), by Yu Kuai

 - NVMe pull request via Keith:
     - nvme-auth updates (Mark)
     - nvme-tcp tls (Hannes)
     - nvme-fc annotaions (Kees)

 - Misc cleanups and improvements (Jiapeng, Joel)

* tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux: (95 commits)
  block: ublk_drv: Remove unused function
  md: cleanup pers->prepare_suspend()
  nvme-auth: allow mixing of secret and hash lengths
  nvme-auth: use transformed key size to create resp
  nvme-auth: alloc nvme_dhchap_key as single buffer
  nvmet-tcp: use 'spin_lock_bh' for state_lock()
  powerpc/pseries: PLPKS SED Opal keystore support
  block: sed-opal: keystore access for SED Opal keys
  block:sed-opal: SED Opal keystore
  ublk: simplify aborting request
  ublk: replace monitor with cancelable uring_cmd
  ublk: quiesce request queue when aborting queue
  ublk: rename mm_lock as lock
  ublk: move ublk_cancel_dev() out of ub->mutex
  ublk: make sure io cmd handled in submitter task context
  ublk: don't get ublk device reference in ublk_abort_queue()
  ublk: Make ublks_max configurable
  ublk: Limit dev_id/ub_number values
  md-cluster: check for timeout while a new disk adding
  nvme: rework NVME_AUTH Kconfig selection
  ...

1 files changed, 465 insertions, 357 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 839e79e567ee..411121a72df9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -91,6 +91,18 @@ 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);
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -206,8 +218,7 @@ static int rdev_need_serial(struct md_rdev *rdev)
  * 1. rdev is the first device which return true from rdev_enable_serial.
  * 2. rdev is NULL, means we want to enable serialization for all rdevs.
  */
-void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-			      bool is_suspend)
+void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 {
 	int ret = 0;
 
@@ -215,15 +226,12 @@ void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 	    !test_bit(CollisionCheck, &rdev->flags))
 		return;
 
-	if (!is_suspend)
-		mddev_suspend(mddev);
-
 	if (!rdev)
 		ret = rdevs_init_serial(mddev);
 	else
 		ret = rdev_init_serial(rdev);
 	if (ret)
-		goto abort;
+		return;
 
 	if (mddev->serial_info_pool == NULL) {
 		/*
@@ -238,10 +246,6 @@ void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 			pr_err("can't alloc memory pool for serialization\n");
 		}
 	}
-
-abort:
-	if (!is_suspend)
-		mddev_resume(mddev);
 }
 
 /*
@@ -250,8 +254,7 @@ abort:
  * 2. when bitmap is destroyed while policy is not enabled.
  * 3. for disable policy, the pool is destroyed only when no rdev needs it.
  */
-void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-			       bool is_suspend)
+void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 {
 	if (rdev && !test_bit(CollisionCheck, &rdev->flags))
 		return;
@@ -260,8 +263,6 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 		struct md_rdev *temp;
 		int num = 0; /* used to track if other rdevs need the pool */
 
-		if (!is_suspend)
-			mddev_suspend(mddev);
 		rdev_for_each(temp, mddev) {
 			if (!rdev) {
 				if (!mddev->serialize_policy ||
@@ -283,8 +284,6 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 			mempool_destroy(mddev->serial_info_pool);
 			mddev->serial_info_pool = NULL;
 		}
-		if (!is_suspend)
-			mddev_resume(mddev);
 	}
 }
 
@@ -346,6 +345,10 @@ EXPORT_SYMBOL_GPL(md_new_event);
 static LIST_HEAD(all_mddevs);
 static DEFINE_SPINLOCK(all_mddevs_lock);
 
+static bool is_md_suspended(struct mddev *mddev)
+{
+	return percpu_ref_is_dying(&mddev->active_io);
+}
 /* Rather than calling directly into the personality make_request function,
  * IO requests come here first so that we can check if the device is
  * being suspended pending a reconfiguration.
@@ -359,11 +362,11 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 		return true;
 	if (bio_data_dir(bio) != WRITE)
 		return false;
-	if (mddev->suspend_lo >= mddev->suspend_hi)
+	if (READ_ONCE(mddev->suspend_lo) >= READ_ONCE(mddev->suspend_hi))
 		return false;
-	if (bio->bi_iter.bi_sector >= mddev->suspend_hi)
+	if (bio->bi_iter.bi_sector >= READ_ONCE(mddev->suspend_hi))
 		return false;
-	if (bio_end_sector(bio) < mddev->suspend_lo)
+	if (bio_end_sector(bio) < READ_ONCE(mddev->suspend_lo))
 		return false;
 	return true;
 }
@@ -431,42 +434,73 @@ static void md_submit_bio(struct bio *bio)
 	md_handle_request(mddev, bio);
 }
 
-/* mddev_suspend makes sure no new requests are submitted
- * to the device, and that any requests that have been submitted
- * are completely handled.
- * Once mddev_detach() is called and completes, the module will be
- * completely unused.
+/*
+ * Make sure no new requests are submitted to the device, and any requests that
+ * have been submitted are completely handled.
  */
-void mddev_suspend(struct mddev *mddev)
+int mddev_suspend(struct mddev *mddev, bool interruptible)
 {
-	struct md_thread *thread = rcu_dereference_protected(mddev->thread,
-			lockdep_is_held(&mddev->reconfig_mutex));
+	int err = 0;
 
-	WARN_ON_ONCE(thread && current == thread->tsk);
-	if (mddev->suspended++)
-		return;
-	wake_up(&mddev->sb_wait);
-	set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags);
-	percpu_ref_kill(&mddev->active_io);
+	/*
+	 * hold reconfig_mutex to wait for normal io will deadlock, because
+	 * other context can't update super_block, and normal io can rely on
+	 * updating super_block.
+	 */
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
 
-	if (mddev->pers->prepare_suspend)
-		mddev->pers->prepare_suspend(mddev);
+	if (interruptible)
+		err = mutex_lock_interruptible(&mddev->suspend_mutex);
+	else
+		mutex_lock(&mddev->suspend_mutex);
+	if (err)
+		return err;
 
-	wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io));
-	clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags);
-	wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags));
+	if (mddev->suspended) {
+		WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
+		mutex_unlock(&mddev->suspend_mutex);
+		return 0;
+	}
+
+	percpu_ref_kill(&mddev->active_io);
+	if (interruptible)
+		err = wait_event_interruptible(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	else
+		wait_event(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	if (err) {
+		percpu_ref_resurrect(&mddev->active_io);
+		mutex_unlock(&mddev->suspend_mutex);
+		return err;
+	}
+
+	/*
+	 * For raid456, io might be waiting for reshape to make progress,
+	 * allow new reshape to start while waiting for io to be done to
+	 * prevent deadlock.
+	 */
+	WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
 
 	del_timer_sync(&mddev->safemode_timer);
 	/* restrict memory reclaim I/O during raid array is suspend */
 	mddev->noio_flag = memalloc_noio_save();
+
+	mutex_unlock(&mddev->suspend_mutex);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
 void mddev_resume(struct mddev *mddev)
 {
-	lockdep_assert_held(&mddev->reconfig_mutex);
-	if (--mddev->suspended)
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
+
+	mutex_lock(&mddev->suspend_mutex);
+	WRITE_ONCE(mddev->suspended, mddev->suspended - 1);
+	if (mddev->suspended) {
+		mutex_unlock(&mddev->suspend_mutex);
 		return;
+	}
 
 	/* entred the memalloc scope from mddev_suspend() */
 	memalloc_noio_restore(mddev->noio_flag);
@@ -477,6 +511,8 @@ void mddev_resume(struct mddev *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
+	mutex_unlock(&mddev->suspend_mutex);
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
@@ -616,34 +652,63 @@ static inline struct mddev *mddev_get(struct mddev *mddev)
 
 static void mddev_delayed_delete(struct work_struct *ws);
 
+static void __mddev_put(struct mddev *mddev)
+{
+	if (mddev->raid_disks || !list_empty(&mddev->disks) ||
+	    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.
+	 */
+	queue_work(md_misc_wq, &mddev->del_work);
+}
+
 void mddev_put(struct mddev *mddev)
 {
 	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
 		return;
-	if (!mddev->raid_disks && list_empty(&mddev->disks) &&
-	    mddev->ctime == 0 && !mddev->hold_active) {
-		/* 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.
-		 */
-		INIT_WORK(&mddev->del_work, mddev_delayed_delete);
-		queue_work(md_misc_wq, &mddev->del_work);
-	}
+	__mddev_put(mddev);
 	spin_unlock(&all_mddevs_lock);
 }
 
 static void md_safemode_timeout(struct timer_list *t);
+static void md_start_sync(struct work_struct *ws);
+
+static void active_io_release(struct percpu_ref *ref)
+{
+	struct mddev *mddev = container_of(ref, struct mddev, active_io);
+
+	wake_up(&mddev->sb_wait);
+}
+
+static void no_op(struct percpu_ref *r) {}
 
-void mddev_init(struct mddev *mddev)
+int mddev_init(struct mddev *mddev)
 {
+
+	if (percpu_ref_init(&mddev->active_io, active_io_release,
+			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (percpu_ref_init(&mddev->writes_pending, no_op,
+			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+		percpu_ref_exit(&mddev->active_io);
+		return -ENOMEM;
+	}
+
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
+
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
 	mutex_init(&mddev->sync_mutex);
+	mutex_init(&mddev->suspend_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
@@ -662,9 +727,21 @@ void mddev_init(struct mddev *mddev)
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
+
+	INIT_WORK(&mddev->sync_work, md_start_sync);
+	INIT_WORK(&mddev->del_work, mddev_delayed_delete);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
+void mddev_destroy(struct mddev *mddev)
+{
+	percpu_ref_exit(&mddev->active_io);
+	percpu_ref_exit(&mddev->writes_pending);
+}
+EXPORT_SYMBOL_GPL(mddev_destroy);
+
 static struct mddev *mddev_find_locked(dev_t unit)
 {
 	struct mddev *mddev;
@@ -708,13 +785,16 @@ static struct mddev *mddev_alloc(dev_t unit)
 	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return ERR_PTR(-ENOMEM);
-	mddev_init(new);
+
+	error = mddev_init(new);
+	if (error)
+		goto out_free_new;
 
 	spin_lock(&all_mddevs_lock);
 	if (unit) {
 		error = -EEXIST;
 		if (mddev_find_locked(unit))
-			goto out_free_new;
+			goto out_destroy_new;
 		new->unit = unit;
 		if (MAJOR(unit) == MD_MAJOR)
 			new->md_minor = MINOR(unit);
@@ -725,7 +805,7 @@ static struct mddev *mddev_alloc(dev_t unit)
 		error = -ENODEV;
 		new->unit = mddev_alloc_unit();
 		if (!new->unit)
-			goto out_free_new;
+			goto out_destroy_new;
 		new->md_minor = MINOR(new->unit);
 		new->hold_active = UNTIL_STOP;
 	}
@@ -733,8 +813,11 @@ static struct mddev *mddev_alloc(dev_t unit)
 	list_add(&new->all_mddevs, &all_mddevs);
 	spin_unlock(&all_mddevs_lock);
 	return new;
-out_free_new:
+
+out_destroy_new:
 	spin_unlock(&all_mddevs_lock);
+	mddev_destroy(new);
+out_free_new:
 	kfree(new);
 	return ERR_PTR(error);
 }
@@ -745,6 +828,7 @@ static void mddev_free(struct mddev *mddev)
 	list_del(&mddev->all_mddevs);
 	spin_unlock(&all_mddevs_lock);
 
+	mddev_destroy(mddev);
 	kfree(mddev);
 }
 
@@ -2412,7 +2496,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	pr_debug("md: bind<%s>\n", b);
 
 	if (mddev->raid_disks)
-		mddev_create_serial_pool(mddev, rdev, false);
+		mddev_create_serial_pool(mddev, rdev);
 
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
@@ -2464,7 +2548,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev)
 	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
 	list_del_rcu(&rdev->same_set);
 	pr_debug("md: unbind<%pg>\n", rdev->bdev);
-	mddev_destroy_serial_pool(rdev->mddev, rdev, false);
+	mddev_destroy_serial_pool(rdev->mddev, rdev);
 	rdev->mddev = NULL;
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
@@ -2794,11 +2878,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		 */
 		super_types[mddev->major_version].
 			validate_super(mddev, rdev);
-		if (add_journal)
-			mddev_suspend(mddev);
 		err = mddev->pers->hot_add_disk(mddev, rdev);
-		if (add_journal)
-			mddev_resume(mddev);
 		if (err) {
 			md_kick_rdev_from_array(rdev);
 			return err;
@@ -2935,11 +3015,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		}
 	} else if (cmd_match(buf, "writemostly")) {
 		set_bit(WriteMostly, &rdev->flags);
-		mddev_create_serial_pool(rdev->mddev, rdev, false);
+		mddev_create_serial_pool(rdev->mddev, rdev);
 		need_update_sb = true;
 		err = 0;
 	} else if (cmd_match(buf, "-writemostly")) {
-		mddev_destroy_serial_pool(rdev->mddev, rdev, false);
+		mddev_destroy_serial_pool(rdev->mddev, rdev);
 		clear_bit(WriteMostly, &rdev->flags);
 		need_update_sb = true;
 		err = 0;
@@ -3551,6 +3631,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
 	struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);
 	struct kernfs_node *kn = NULL;
+	bool suspend = false;
 	ssize_t rv;
 	struct mddev *mddev = rdev->mddev;
 
@@ -3558,17 +3639,25 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+	if (!mddev)
+		return -ENODEV;
 
-	if (entry->store == state_store && cmd_match(page, "remove"))
-		kn = sysfs_break_active_protection(kobj, attr);
+	if (entry->store == state_store) {
+		if (cmd_match(page, "remove"))
+			kn = sysfs_break_active_protection(kobj, attr);
+		if (cmd_match(page, "remove") || cmd_match(page, "re-add") ||
+		    cmd_match(page, "writemostly") ||
+		    cmd_match(page, "-writemostly"))
+			suspend = true;
+	}
 
-	rv = mddev ? mddev_lock(mddev) : -ENODEV;
+	rv = suspend ? mddev_suspend_and_lock(mddev) : mddev_lock(mddev);
 	if (!rv) {
 		if (rdev->mddev == NULL)
 			rv = -ENODEV;
 		else
 			rv = entry->store(rdev, page, length);
-		mddev_unlock(mddev);
+		suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
 	}
 
 	if (kn)
@@ -3867,12 +3956,12 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	if (slen == 0 || slen >= sizeof(clevel))
 		return -EINVAL;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
 
 	if (mddev->pers == NULL) {
-		strncpy(mddev->clevel, buf, slen);
+		memcpy(mddev->clevel, buf, slen);
 		if (mddev->clevel[slen-1] == '\n')
 			slen--;
 		mddev->clevel[slen] = 0;
@@ -3905,7 +3994,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 
 	/* Now find the new personality */
-	strncpy(clevel, buf, slen);
+	memcpy(clevel, buf, slen);
 	if (clevel[slen-1] == '\n')
 		slen--;
 	clevel[slen] = 0;
@@ -3960,7 +4049,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 
 	/* Looks like we have a winner */
-	mddev_suspend(mddev);
 	mddev_detach(mddev);
 
 	spin_lock(&mddev->lock);
@@ -4046,14 +4134,13 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	mddev_resume(mddev);
 	if (!mddev->thread)
 		md_update_sb(mddev, 1);
 	sysfs_notify_dirent_safe(mddev->sysfs_level);
 	md_new_event();
 	rv = len;
 out_unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return rv;
 }
 
@@ -4361,6 +4448,18 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	int err = 0;
 	enum array_state st = match_word(buf, array_states);
 
+	/* No lock dependent actions */
+	switch (st) {
+	case suspended:		/* not supported yet */
+	case write_pending:	/* cannot be set */
+	case active_idle:	/* cannot be set */
+	case broken:		/* cannot be set */
+	case bad_word:
+		return -EINVAL;
+	default:
+		break;
+	}
+
 	if (mddev->pers && (st == active || st == clean) &&
 	    mddev->ro != MD_RDONLY) {
 		/* don't take reconfig_mutex when toggling between
@@ -4385,23 +4484,16 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	err = mddev_lock(mddev);
 	if (err)
 		return err;
-	err = -EINVAL;
-	switch(st) {
-	case bad_word:
-		break;
-	case clear:
-		/* stopping an active array */
-		err = do_md_stop(mddev, 0, NULL);
-		break;
+
+	switch (st) {
 	case inactive:
-		/* stopping an active array */
+		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
 			err = do_md_stop(mddev, 2, NULL);
-		else
-			err = 0; /* already inactive */
 		break;
-	case suspended:
-		break; /* not supported yet */
+	case clear:
+		err = do_md_stop(mddev, 0, NULL);
+		break;
 	case readonly:
 		if (mddev->pers)
 			err = md_set_readonly(mddev, NULL);
@@ -4452,10 +4544,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 			err = do_md_run(mddev);
 		}
 		break;
-	case write_pending:
-	case active_idle:
-	case broken:
-		/* these cannot be set */
+	default:
+		err = -EINVAL;
 		break;
 	}
 
@@ -4528,7 +4618,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	    minor != MINOR(dev))
 		return -EOVERFLOW;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	if (mddev->persistent) {
@@ -4549,14 +4639,14 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 		rdev = md_import_device(dev, -1, -1);
 
 	if (IS_ERR(rdev)) {
-		mddev_unlock(mddev);
+		mddev_unlock_and_resume(mddev);
 		return PTR_ERR(rdev);
 	}
 	err = bind_rdev_to_array(rdev, mddev);
  out:
 	if (err)
 		export_rdev(rdev, mddev);
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	if (!err)
 		md_new_event();
 	return err ? err : len;
@@ -4691,7 +4781,7 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
 		size_t namelen = len-9;
 		if (namelen >= sizeof(mddev->metadata_type))
 			namelen = sizeof(mddev->metadata_type)-1;
-		strncpy(mddev->metadata_type, buf+9, namelen);
+		memcpy(mddev->metadata_type, buf+9, namelen);
 		mddev->metadata_type[namelen] = 0;
 		if (namelen && mddev->metadata_type[namelen-1] == '\n')
 			mddev->metadata_type[--namelen] = 0;
@@ -4865,6 +4955,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		/* A write to sync_action is enough to justify
 		 * canceling read-auto mode
 		 */
+		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		md_wakeup_thread(mddev->sync_thread);
 	}
@@ -5121,7 +5212,8 @@ __ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store);
 static ssize_t
 suspend_lo_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)READ_ONCE(mddev->suspend_lo));
 }
 
 static ssize_t
@@ -5136,21 +5228,14 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 	if (new != (sector_t)new)
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend(mddev, true);
 	if (err)
 		return err;
-	err = -EINVAL;
-	if (mddev->pers == NULL ||
-	    mddev->pers->quiesce == NULL)
-		goto unlock;
-	mddev_suspend(mddev);
-	mddev->suspend_lo = new;
+
+	WRITE_ONCE(mddev->suspend_lo, new);
 	mddev_resume(mddev);
 
-	err = 0;
-unlock:
-	mddev_unlock(mddev);
-	return err ?: len;
+	return len;
 }
 static struct md_sysfs_entry md_suspend_lo =
 __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
@@ -5158,7 +5243,8 @@ __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
 static ssize_t
 suspend_hi_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)READ_ONCE(mddev->suspend_hi));
 }
 
 static ssize_t
@@ -5173,21 +5259,14 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 	if (new != (sector_t)new)
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend(mddev, true);
 	if (err)
 		return err;
-	err = -EINVAL;
-	if (mddev->pers == NULL)
-		goto unlock;
 
-	mddev_suspend(mddev);
-	mddev->suspend_hi = new;
+	WRITE_ONCE(mddev->suspend_hi, new);
 	mddev_resume(mddev);
 
-	err = 0;
-unlock:
-	mddev_unlock(mddev);
-	return err ?: len;
+	return len;
 }
 static struct md_sysfs_entry md_suspend_hi =
 __ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
@@ -5434,7 +5513,7 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 	if (value == mddev->serialize_policy)
 		return len;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	if (mddev->pers == NULL || (mddev->pers->level != 1)) {
@@ -5443,15 +5522,13 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 		goto unlock;
 	}
 
-	mddev_suspend(mddev);
 	if (value)
-		mddev_create_serial_pool(mddev, NULL, true);
+		mddev_create_serial_pool(mddev, NULL);
 	else
-		mddev_destroy_serial_pool(mddev, NULL, true);
+		mddev_destroy_serial_pool(mddev, NULL);
 	mddev->serialize_policy = value;
-	mddev_resume(mddev);
 unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return err ?: len;
 }
 
@@ -5590,21 +5667,6 @@ static void mddev_delayed_delete(struct work_struct *ws)
 	kobject_put(&mddev->kobj);
 }
 
-static void no_op(struct percpu_ref *r) {}
-
-int mddev_init_writes_pending(struct mddev *mddev)
-{
-	if (mddev->writes_pending.percpu_count_ptr)
-		return 0;
-	if (percpu_ref_init(&mddev->writes_pending, no_op,
-			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL) < 0)
-		return -ENOMEM;
-	/* We want to start with the refcount at zero */
-	percpu_ref_put(&mddev->writes_pending);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
-
 struct mddev *md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5776,12 +5838,6 @@ static void md_safemode_timeout(struct timer_list *t)
 }
 
 static int start_dirty_degraded;
-static void active_io_release(struct percpu_ref *ref)
-{
-	struct mddev *mddev = container_of(ref, struct mddev, active_io);
-
-	wake_up(&mddev->sb_wait);
-}
 
 int md_run(struct mddev *mddev)
 {
@@ -5862,15 +5918,10 @@ int md_run(struct mddev *mddev)
 		nowait = nowait && bdev_nowait(rdev->bdev);
 	}
 
-	err = percpu_ref_init(&mddev->active_io, active_io_release,
-				PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
-	if (err)
-		return err;
-
 	if (!bioset_initialized(&mddev->bio_set)) {
 		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			goto exit_active_io;
+			return err;
 	}
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
@@ -6067,8 +6118,6 @@ exit_sync_set:
 	bioset_exit(&mddev->sync_set);
 exit_bio_set:
 	bioset_exit(&mddev->bio_set);
-exit_active_io:
-	percpu_ref_exit(&mddev->active_io);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6242,7 +6291,7 @@ static void __md_stop_writes(struct mddev *mddev)
 	}
 	/* disable policy to guarantee rdevs free resources for serialization */
 	mddev->serialize_policy = 0;
-	mddev_destroy_serial_pool(mddev, NULL, true);
+	mddev_destroy_serial_pool(mddev, NULL);
 }
 
 void md_stop_writes(struct mddev *mddev)
@@ -6284,7 +6333,6 @@ static void __md_stop(struct mddev *mddev)
 	module_put(pers->owner);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
-	percpu_ref_exit(&mddev->active_io);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
 	bioset_exit(&mddev->io_clone_set);
@@ -6299,7 +6347,6 @@ void md_stop(struct mddev *mddev)
 	 */
 	__md_stop_writes(mddev);
 	__md_stop(mddev);
-	percpu_ref_exit(&mddev->writes_pending);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -6536,13 +6583,13 @@ static void autorun_devices(int part)
 		if (IS_ERR(mddev))
 			break;
 
-		if (mddev_lock(mddev))
+		if (mddev_suspend_and_lock(mddev))
 			pr_warn("md: %s locked, cannot run\n", mdname(mddev));
 		else if (mddev->raid_disks || mddev->major_version
 			 || !list_empty(&mddev->disks)) {
 			pr_warn("md: %s already running, cannot run %pg\n",
 				mdname(mddev), rdev0->bdev);
-			mddev_unlock(mddev);
+			mddev_unlock_and_resume(mddev);
 		} else {
 			pr_debug("md: created %s\n", mdname(mddev));
 			mddev->persistent = 1;
@@ -6552,7 +6599,7 @@ static void autorun_devices(int part)
 					export_rdev(rdev, mddev);
 			}
 			autorun_array(mddev);
-			mddev_unlock(mddev);
+			mddev_unlock_and_resume(mddev);
 		}
 		/* on success, candidates will be empty, on error
 		 * it won't...
@@ -7102,7 +7149,6 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 			struct bitmap *bitmap;
 
 			bitmap = md_bitmap_create(mddev, -1);
-			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				err = md_bitmap_load(mddev);
@@ -7112,11 +7158,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 				md_bitmap_destroy(mddev);
 				fd = -1;
 			}
-			mddev_resume(mddev);
 		} else if (fd < 0) {
-			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 		}
 	}
 	if (fd < 0) {
@@ -7405,7 +7448,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 			mddev->bitmap_info.space =
 				mddev->bitmap_info.default_space;
 			bitmap = md_bitmap_create(mddev, -1);
-			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				rv = md_bitmap_load(mddev);
@@ -7413,7 +7455,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				rv = PTR_ERR(bitmap);
 			if (rv)
 				md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 		} else {
 			/* remove the bitmap */
 			if (!mddev->bitmap) {
@@ -7438,9 +7479,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				module_put(md_cluster_mod);
 				mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 			}
-			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 			mddev->bitmap_info.offset = 0;
 		}
 	}
@@ -7511,6 +7550,20 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	}
 }
 
+static bool md_ioctl_need_suspend(unsigned int cmd)
+{
+	switch (cmd) {
+	case ADD_NEW_DISK:
+	case HOT_ADD_DISK:
+	case HOT_REMOVE_DISK:
+	case SET_BITMAP_FILE:
+	case SET_ARRAY_INFO:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int __md_set_array_info(struct mddev *mddev, void __user *argp)
 {
 	mdu_array_info_t info;
@@ -7639,7 +7692,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
-	err = mddev_lock(mddev);
+
+	if (!md_is_rdwr(mddev))
+		flush_work(&mddev->sync_work);
+
+	err = md_ioctl_need_suspend(cmd) ? mddev_suspend_and_lock(mddev) :
+					   mddev_lock(mddev);
 	if (err) {
 		pr_debug("md: ioctl lock interrupted, reason %d, cmd %d\n",
 			 err, cmd);
@@ -7767,7 +7825,10 @@ unlock:
 	if (mddev->hold_active == UNTIL_IOCTL &&
 	    err != -EINVAL)
 		mddev->hold_active = 0;
-	mddev_unlock(mddev);
+
+	md_ioctl_need_suspend(cmd) ? mddev_unlock_and_resume(mddev) :
+				     mddev_unlock(mddev);
+
 out:
 	if(did_set_md_closing)
 		clear_bit(MD_CLOSING, &mddev->flags);
@@ -7879,7 +7940,6 @@ static void md_free_disk(struct gendisk *disk)
 {
 	struct mddev *mddev = disk->private_data;
 
-	percpu_ref_exit(&mddev->writes_pending);
 	mddev_free(mddev);
 }
 
@@ -8195,105 +8255,46 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 }
 
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(&all_mddevs_lock)
 {
-	struct list_head *tmp;
-	loff_t l = *pos;
-	struct mddev *mddev;
+	struct md_personality *pers;
 
-	if (l == 0x10000) {
-		++*pos;
-		return (void *)2;
-	}
-	if (l > 0x10000)
-		return NULL;
-	if (!l--)
-		/* header */
-		return (void*)1;
+	seq_puts(seq, "Personalities : ");
+	spin_lock(&pers_lock);
+	list_for_each_entry(pers, &pers_list, list)
+		seq_printf(seq, "[%s] ", pers->name);
+
+	spin_unlock(&pers_lock);
+	seq_puts(seq, "\n");
+	seq->poll_event = atomic_read(&md_event_count);
 
 	spin_lock(&all_mddevs_lock);
-	list_for_each(tmp,&all_mddevs)
-		if (!l--) {
-			mddev = list_entry(tmp, struct mddev, all_mddevs);
-			if (!mddev_get(mddev))
-				continue;
-			spin_unlock(&all_mddevs_lock);
-			return mddev;
-		}
-	spin_unlock(&all_mddevs_lock);
-	if (!l--)
-		return (void*)2;/* tail */
-	return NULL;
+
+	return seq_list_start(&all_mddevs, *pos);
 }
 
 static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct list_head *tmp;
-	struct mddev *next_mddev, *mddev = v;
-	struct mddev *to_put = NULL;
-
-	++*pos;
-	if (v == (void*)2)
-		return NULL;
-
-	spin_lock(&all_mddevs_lock);
-	if (v == (void*)1) {
-		tmp = all_mddevs.next;
-	} else {
-		to_put = mddev;
-		tmp = mddev->all_mddevs.next;
-	}
-
-	for (;;) {
-		if (tmp == &all_mddevs) {
-			next_mddev = (void*)2;
-			*pos = 0x10000;
-			break;
-		}
-		next_mddev = list_entry(tmp, struct mddev, all_mddevs);
-		if (mddev_get(next_mddev))
-			break;
-		mddev = next_mddev;
-		tmp = mddev->all_mddevs.next;
-	}
-	spin_unlock(&all_mddevs_lock);
-
-	if (to_put)
-		mddev_put(to_put);
-	return next_mddev;
-
+	return seq_list_next(v, &all_mddevs, pos);
 }
 
 static void md_seq_stop(struct seq_file *seq, void *v)
+	__releases(&all_mddevs_lock)
 {
-	struct mddev *mddev = v;
-
-	if (mddev && v != (void*)1 && v != (void*)2)
-		mddev_put(mddev);
+	status_unused(seq);
+	spin_unlock(&all_mddevs_lock);
 }
 
 static int md_seq_show(struct seq_file *seq, void *v)
 {
-	struct mddev *mddev = v;
+	struct mddev *mddev = list_entry(v, struct mddev, all_mddevs);
 	sector_t sectors;
 	struct md_rdev *rdev;
 
-	if (v == (void*)1) {
-		struct md_personality *pers;
-		seq_printf(seq, "Personalities : ");
-		spin_lock(&pers_lock);
-		list_for_each_entry(pers, &pers_list, list)
-			seq_printf(seq, "[%s] ", pers->name);
-
-		spin_unlock(&pers_lock);
-		seq_printf(seq, "\n");
-		seq->poll_event = atomic_read(&md_event_count);
+	if (!mddev_get(mddev))
 		return 0;
-	}
-	if (v == (void*)2) {
-		status_unused(seq);
-		return 0;
-	}
 
+	spin_unlock(&all_mddevs_lock);
 	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : %sactive", mdname(mddev),
@@ -8364,6 +8365,9 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	spin_unlock(&mddev->lock);
+	spin_lock(&all_mddevs_lock);
+	if (atomic_dec_and_test(&mddev->active))
+		__mddev_put(mddev);
 
 	return 0;
 }
@@ -8563,6 +8567,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
 	BUG_ON(mddev->ro == MD_RDONLY);
 	if (mddev->ro == MD_AUTO_READ) {
 		/* need to switch to read/write */
+		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -9148,12 +9153,90 @@ void md_do_sync(struct md_thread *thread)
 	spin_unlock(&mddev->lock);
 
 	wake_up(&resync_wait);
-	wake_up(&mddev->sb_wait);
 	md_wakeup_thread(mddev->thread);
 	return;
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
+static bool rdev_removeable(struct md_rdev *rdev)
+{
+	/* rdev is not used. */
+	if (rdev->raid_disk < 0)
+		return false;
+
+	/* There are still inflight io, don't remove this rdev. */
+	if (atomic_read(&rdev->nr_pending))
+		return false;
+
+	/*
+	 * An error occurred but has not yet been acknowledged by the metadata
+	 * handler, don't remove this rdev.
+	 */
+	if (test_bit(Blocked, &rdev->flags))
+		return false;
+
+	/* Fautly rdev is not used, it's safe to remove it. */
+	if (test_bit(Faulty, &rdev->flags))
+		return true;
+
+	/* Journal disk can only be removed if it's faulty. */
+	if (test_bit(Journal, &rdev->flags))
+		return false;
+
+	/*
+	 * 'In_sync' is cleared while 'raid_disk' is valid, which means
+	 * replacement has just become active from pers->spare_active(), and
+	 * then pers->hot_remove_disk() will replace this rdev with replacement.
+	 */
+	if (!test_bit(In_sync, &rdev->flags))
+		return true;
+
+	return false;
+}
+
+static bool rdev_is_spare(struct md_rdev *rdev)
+{
+	return !test_bit(Candidate, &rdev->flags) && rdev->raid_disk >= 0 &&
+	       !test_bit(In_sync, &rdev->flags) &&
+	       !test_bit(Journal, &rdev->flags) &&
+	       !test_bit(Faulty, &rdev->flags);
+}
+
+static bool rdev_addable(struct md_rdev *rdev)
+{
+	/* rdev is already used, don't add it again. */
+	if (test_bit(Candidate, &rdev->flags) || rdev->raid_disk >= 0 ||
+	    test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* Allow to add journal disk. */
+	if (test_bit(Journal, &rdev->flags))
+		return true;
+
+	/* Allow to add if array is read-write. */
+	if (md_is_rdwr(rdev->mddev))
+		return true;
+
+	/*
+	 * For read-only array, only allow to readd a rdev. And if bitmap is
+	 * used, don't allow to readd a rdev that is too old.
+	 */
+	if (rdev->saved_raid_disk >= 0 && !test_bit(Bitmap_sync, &rdev->flags))
+		return true;
+
+	return false;
+}
+
+static bool md_spares_need_change(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev)
+		if (rdev_removeable(rdev) || rdev_addable(rdev))
+			return true;
+	return false;
+}
+
 static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this)
 {
@@ -9186,12 +9269,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 		synchronize_rcu();
 	rdev_for_each(rdev, mddev) {
 		if ((this == NULL || rdev == this) &&
-		    rdev->raid_disk >= 0 &&
-		    !test_bit(Blocked, &rdev->flags) &&
-		    ((test_bit(RemoveSynchronized, &rdev->flags) ||
-		     (!test_bit(In_sync, &rdev->flags) &&
-		      !test_bit(Journal, &rdev->flags))) &&
-		    atomic_read(&rdev->nr_pending)==0)) {
+		    (test_bit(RemoveSynchronized, &rdev->flags) ||
+		     rdev_removeable(rdev))) {
 			if (mddev->pers->hot_remove_disk(
 				    mddev, rdev) == 0) {
 				sysfs_unlink_rdev(mddev, rdev);
@@ -9213,25 +9292,12 @@ static int remove_and_add_spares(struct mddev *mddev,
 	rdev_for_each(rdev, mddev) {
 		if (this && this != rdev)
 			continue;
-		if (test_bit(Candidate, &rdev->flags))
-			continue;
-		if (rdev->raid_disk >= 0 &&
-		    !test_bit(In_sync, &rdev->flags) &&
-		    !test_bit(Journal, &rdev->flags) &&
-		    !test_bit(Faulty, &rdev->flags))
+		if (rdev_is_spare(rdev))
 			spares++;
-		if (rdev->raid_disk >= 0)
-			continue;
-		if (test_bit(Faulty, &rdev->flags))
+		if (!rdev_addable(rdev))
 			continue;
-		if (!test_bit(Journal, &rdev->flags)) {
-			if (!md_is_rdwr(mddev) &&
-			    !(rdev->saved_raid_disk >= 0 &&
-			      !test_bit(Bitmap_sync, &rdev->flags)))
-				continue;
-
+		if (!test_bit(Journal, &rdev->flags))
 			rdev->recovery_offset = 0;
-		}
 		if (mddev->pers->hot_add_disk(mddev, rdev) == 0) {
 			/* failure here is OK */
 			sysfs_link_rdev(mddev, rdev);
@@ -9247,9 +9313,86 @@ no_add:
 	return spares;
 }
 
+static bool md_choose_sync_action(struct mddev *mddev, int *spares)
+{
+	/* Check if reshape is in progress first. */
+	if (mddev->reshape_position != MaxSector) {
+		if (mddev->pers->check_reshape == NULL ||
+		    mddev->pers->check_reshape(mddev) != 0)
+			return false;
+
+		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/*
+	 * Remove any failed drives, then add spares if possible. Spares are
+	 * also removed and re-added, to allow the personality to fail the
+	 * re-add.
+	 */
+	*spares = remove_and_add_spares(mddev, NULL);
+	if (*spares) {
+		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+
+		/* Start new recovery. */
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/* Check if recovery is in progress. */
+	if (mddev->recovery_cp < MaxSector) {
+		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/* Delay to choose resync/check/repair in md_do_sync(). */
+	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+		return true;
+
+	/* Nothing to be done */
+	return false;
+}
+
 static void md_start_sync(struct work_struct *ws)
 {
-	struct mddev *mddev = container_of(ws, struct mddev, del_work);
+	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
+	int spares = 0;
+	bool suspend = false;
+
+	if (md_spares_need_change(mddev))
+		suspend = true;
+
+	suspend ? mddev_suspend_and_lock_nointr(mddev) :
+		  mddev_lock_nointr(mddev);
+
+	if (!md_is_rdwr(mddev)) {
+		/*
+		 * On a read-only array we can:
+		 * - remove failed devices
+		 * - add already-in_sync devices if the array itself is in-sync.
+		 * As we only add devices that are already in-sync, we can
+		 * activate the spares immediately.
+		 */
+		remove_and_add_spares(mddev, NULL);
+		goto not_running;
+	}
+
+	if (!md_choose_sync_action(mddev, &spares))
+		goto not_running;
+
+	if (!mddev->pers->sync_request)
+		goto not_running;
+
+	/*
+	 * We are adding a device or devices to an array which has the bitmap
+	 * stored on all devices. So make sure all bitmap pages get written.
+	 */
+	if (spares)
+		md_bitmap_write_all(mddev->bitmap);
 
 	rcu_assign_pointer(mddev->sync_thread,
 			   md_register_thread(md_do_sync, mddev, "resync"));
@@ -9257,20 +9400,27 @@ static void md_start_sync(struct work_struct *ws)
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
 		/* leave the spares where they are, it shouldn't hurt */
-		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-		clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		wake_up(&resync_wait);
-		if (test_and_clear_bit(MD_RECOVERY_RECOVER,
-				       &mddev->recovery))
-			if (mddev->sysfs_action)
-				sysfs_notify_dirent_safe(mddev->sysfs_action);
-	} else
-		md_wakeup_thread(mddev->sync_thread);
+		goto not_running;
+	}
+
+	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event();
+	return;
+
+not_running:
+	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+
+	wake_up(&resync_wait);
+	if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
+	    mddev->sysfs_action)
+		sysfs_notify_dirent_safe(mddev->sysfs_action);
 }
 
 /*
@@ -9297,19 +9447,7 @@ static void md_start_sync(struct work_struct *ws)
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) {
-		/* Write superblock - thread that called mddev_suspend()
-		 * holds reconfig_mutex for us.
-		 */
-		set_bit(MD_UPDATING_SB, &mddev->flags);
-		smp_mb__after_atomic();
-		if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags))
-			md_update_sb(mddev, 0);
-		clear_bit_unlock(MD_UPDATING_SB, &mddev->flags);
-		wake_up(&mddev->sb_wait);
-	}
-
-	if (is_md_suspended(mddev))
+	if (READ_ONCE(mddev->suspended))
 		return;
 
 	if (mddev->bitmap)
@@ -9338,7 +9476,6 @@ void md_check_recovery(struct mddev *mddev)
 		return;
 
 	if (mddev_trylock(mddev)) {
-		int spares = 0;
 		bool try_set_sync = mddev->safemode != 0;
 
 		if (!mddev->external && mddev->safemode == 1)
@@ -9346,30 +9483,43 @@ void md_check_recovery(struct mddev *mddev)
 
 		if (!md_is_rdwr(mddev)) {
 			struct md_rdev *rdev;
+
+			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+				/* sync_work already queued. */
+				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				goto unlock;
+			}
+
 			if (!mddev->external && mddev->in_sync)
-				/* 'Blocked' flag not needed as failed devices
+				/*
+				 * 'Blocked' flag not needed as failed devices
 				 * will be recorded if array switched to read/write.
 				 * Leaving it set will prevent the device
 				 * from being removed.
 				 */
 				rdev_for_each(rdev, mddev)
 					clear_bit(Blocked, &rdev->flags);
-			/* On a read-only array we can:
-			 * - remove failed devices
-			 * - add already-in_sync devices if the array itself
-			 *   is in-sync.
-			 * As we only add devices that are already in-sync,
-			 * we can activate the spares immediately.
-			 */
-			remove_and_add_spares(mddev, NULL);
-			/* There is no thread, but we need to call
+
+			/*
+			 * There is no thread, but we need to call
 			 * ->spare_active and clear saved_raid_disk
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_reap_sync_thread(mddev);
+
+			/*
+			 * Let md_start_sync() to remove and add rdevs to the
+			 * array.
+			 */
+			if (md_spares_need_change(mddev)) {
+				set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+				queue_work(md_misc_wq, &mddev->sync_work);
+			}
+
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
+
 			goto unlock;
 		}
 
@@ -9425,56 +9575,14 @@ void md_check_recovery(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 
-		if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
-		    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
-			goto not_running;
-		/* no recovery is running.
-		 * remove any failed drives, then
-		 * add spares if possible.
-		 * Spares are also removed and re-added, to allow
-		 * the personality to fail the re-add.
-		 */
-
-		if (mddev->reshape_position != MaxSector) {
-			if (mddev->pers->check_reshape == NULL ||
-			    mddev->pers->check_reshape(mddev) != 0)
-				/* Cannot proceed */
-				goto not_running;
-			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if ((spares = remove_and_add_spares(mddev, NULL))) {
-			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-			clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if (mddev->recovery_cp < MaxSector) {
-			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-			/* nothing to be done ... */
-			goto not_running;
-
-		if (mddev->pers->sync_request) {
-			if (spares) {
-				/* We are adding a device or devices to an array
-				 * which has the bitmap stored on all devices.
-				 * So make sure all bitmap pages get written
-				 */
-				md_bitmap_write_all(mddev->bitmap);
-			}
-			INIT_WORK(&mddev->del_work, md_start_sync);
-			queue_work(md_misc_wq, &mddev->del_work);
-			goto unlock;
-		}
-	not_running:
-		if (!mddev->sync_thread) {
+		if (test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+		    !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
+			queue_work(md_misc_wq, &mddev->sync_work);
+		} else {
 			clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 			wake_up(&resync_wait);
-			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
-					       &mddev->recovery))
-				if (mddev->sysfs_action)
-					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
+
 	unlock:
 		wake_up(&mddev->sb_wait);
 		mddev_unlock(mddev);