md: add legacy_async_del_gendisk mode

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 25db5f2
Author: Xiao Ni <xni@redhat.com>
Date:   Wed Aug 13 11:29:29 2025 +0800

    md: add legacy_async_del_gendisk mode

    commit 9e59d60 ("md: call del_gendisk in control path") changes the
    async way to sync way of calling del_gendisk. But it breaks mdadm
    --assemble command. The assemble command runs like this:
    1. create the array
    2. stop the array
    3. access the sysfs files after stopping

    The sync way calls del_gendisk in step 2, so all sysfs files are removed.
    Now to avoid breaking mdadm assemble command, this patch adds the parameter
    legacy_async_del_gendisk that can be used to choose which way. The default
    is async way. In future, we plan to change default to sync way in kernel
    7.0. Then users need to upgrade to mdadm 4.5+ which removes step 2.

    Fixes: 9e59d60 ("md: call del_gendisk in control path")
    Reported-by: Mikulas Patocka <mpatocka@redhat.com>
    Closes: https://lore.kernel.org/linux-raid/CAMw=ZnQ=ET2St-+hnhsuq34rRPnebqcXqP1QqaHW5Bh4aaaZ4g@mail.gmail.com/T/#t
    Suggested-and-reviewed-by: Yu Kuai <yukuai3@huawei.com>
    Signed-off-by: Xiao Ni <xni@redhat.com>
    Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
    Link: https://lore.kernel.org/linux-raid/20250813032929.54978-1-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

@@ -340,6 +340,7 @@ 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
@@ -878,15 +879,18 @@ void mddev_unlock(struct mddev *mddev)
 		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);
+	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);
 
@@ -5844,6 +5848,13 @@ static void md_kobj_release(struct kobject *ko)
 {
 	struct mddev *mddev = container_of(ko, struct mddev, kobj);
 
+	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);
 }
 
@@ -6047,6 +6058,9 @@ 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);
@@ -6457,10 +6471,22 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	/* 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);
+
+	/*
+	 * 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 (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;
@@ -6684,7 +6710,8 @@ static int do_md_stop(struct mddev *mddev, int mode)
 
 		export_array(mddev);
 		md_clean(mddev);
-		set_bit(MD_DELETED, &mddev->flags);
+		if (!legacy_async_del_gendisk)
+			set_bit(MD_DELETED, &mddev->flags);
 	}
 	md_new_event();
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -10418,6 +10445,7 @@ 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");