1 files changed, 56 insertions, 19 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0f41573fa9f5..4e033c26fdd4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -339,6 +339,7 @@ static int start_readonly;
  * so all the races disappear.
  */
 static bool create_on_open = true;
+static bool legacy_async_del_gendisk = true;
 
 /*
  * We have a system wide 'event count' that is incremented
@@ -636,9 +637,12 @@ 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 */
+	/*
+	 * If array is freed by stopping array, MD_DELETED is set by
+	 * do_md_stop(), MD_DELETED is still set here in case mddev is freed
+	 * directly by closing a mddev that is created by create_on_open.
+	 */
 	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 +877,19 @@ void mddev_unlock(struct mddev *mddev)
 		kobject_del(&rdev->kobj);
 		export_rdev(rdev, mddev);
 	}
+
+	if (!legacy_async_del_gendisk) {
+		/*
+		 * 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);
 
@@ -5816,19 +5833,30 @@ 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;
 }
 
@@ -5836,12 +5864,13 @@ 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);
+	if (legacy_async_del_gendisk) {
+		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);
 }
 
@@ -6045,6 +6074,9 @@ static int md_alloc_and_put(dev_t dev, char *name)
 {
 	struct mddev *mddev = md_alloc(dev, name);
 
+	if (legacy_async_del_gendisk)
+		pr_warn("md: async del_gendisk mode will be removed in future, please upgrade to mdadm-4.5+\n");
+
 	if (IS_ERR(mddev))
 		return PTR_ERR(mddev);
 	mddev_put(mddev);
@@ -6455,15 +6487,22 @@ 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.
+	 * For legacy_async_del_gendisk mode, it can stop the array in the
+	 * middle of assembling it, then it still can access the array. So
+	 * it needs to clear MD_CLOSING. If not legacy_async_del_gendisk,
+	 * it can't open the array again after stopping it. So it doesn't
+	 * clear MD_CLOSING.
 	 */
-	if (mddev->hold_active)
-		mddev->flags = 0;
-	else
+	if (legacy_async_del_gendisk && mddev->hold_active) {
+		clear_bit(MD_CLOSING, &mddev->flags);
+	} else {
+		/* 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;
@@ -6558,8 +6597,6 @@ 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);
 
@@ -6688,10 +6725,9 @@ 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;
+		if (!legacy_async_del_gendisk)
+			set_bit(MD_DELETED, &mddev->flags);
 	}
 	md_new_event();
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -10422,6 +10458,7 @@ module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
 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_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");