md: call del_gendisk in control path

JIRA: https://issues.redhat.com/browse/RHEL-94433
JIRA: https://issues.redhat.com/browse/RHEL-20191
JIRA: https://issues.redhat.com/browse/RHEL-9656

commit 9e59d60
Author: Xiao Ni <xni@redhat.com>
Date:   Wed Jun 11 15:31:06 2025 +0800

    md: call del_gendisk in control path

    Now del_gendisk and put_disk are called asynchronously in workqueue work.
    The asynchronous way has a problem that the device node can still exist
    after mdadm --stop command returns in a short window. So udev rule can
    open this device node and create the struct mddev in kernel again. So put
    del_gendisk in control path and still leave put_disk in md_kobj_release
    to avoid uaf of gendisk.

    Function del_gendisk can't be called with reconfig_mutex. If it's called
    with reconfig mutex, a deadlock can happen. del_gendisk waits all sysfs
    files access to finish and sysfs file access waits reconfig mutex. So
    put del_gendisk after releasing reconfig mutex.

    But there is still a window that sysfs can be accessed between mddev_unlock
    and del_gendisk. So some actions (add disk, change level, .e.g) can happen
    which lead unexpected results. MD_DELETED is used to resolve this problem.
    MD_DELETED is set before releasing reconfig mutex and it should be checked
    for these sysfs access which need reconfig mutex. For sysfs access which
    don't need reconfig mutex, del_gendisk will wait them to finish.

    But it doesn't need to do this in function mddev_lock_nointr. There are
    ten places that call it.
    * Five of them are in dm raid which we don't need to care. MD_DELETED is
    only used for md raid.
    * stop_sync_thread, md_do_sync and md_start_sync are related sync request,
    and it needs to wait sync thread to finish before stopping an array.
    * md_ioctl: md_open is called before md_ioctl, so ->openers is added. It
    will fail to stop the array. So it doesn't need to check MD_DELETED here
    * md_set_readonly:
    It needs to call mddev_set_closing_and_sync_blockdev when setting readonly
    or read_auto. So it will fail to stop the array too because MD_CLOSING is
    already set.

    Reviewed-by: Yu Kuai <yukuai3@huawei.com>
    Signed-off-by: Xiao Ni <xni@redhat.com>
    Link: https://lore.kernel.org/linux-raid/20250611073108.25463-2-xni@redhat.com
    Signed-off-by: Yu Kuai <yukuai3@huawei.com>

Signed-off-by: Nigel Croxon <ncroxon@redhat.com>

Author: ncroxon

drivers/md/md.c

@@ -637,9 +637,6 @@ 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.
@@ -874,6 +871,16 @@ 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);
 
@@ -5800,32 +5807,37 @@ 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;
 }
 
 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);
 }
 
@@ -6672,8 +6684,9 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		mddev->bitmap_info.offset = 0;
 
 		export_array(mddev);
-
 		md_clean(mddev);
+		set_bit(MD_DELETED, &mddev->flags);
+
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
 	}

drivers/md/md.h

@@ -702,11 +702,26 @@ 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)
 {
@@ -715,7 +730,14 @@ 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);