4 files changed, 68 insertions, 36 deletions

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/raid10.c b/drivers/md/raid10.c
index 97065bb26f43..0757be2f5f04 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2438,15 +2438,12 @@ 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);
 	}
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;