block: fix deadlock between bd_link_disk_holder and partition scan

'open_mutex' of gendisk is used to protect open/close block devices. But
in bd_link_disk_holder(), it is used to protect the creation of symlink
between holding disk and slave bdev, which introduces some issues.

When bd_link_disk_holder() is called, the driver is usually in the process
of initialization/modification and may suspend submitting io. At this
time, any io hold 'open_mutex', such as scanning partitions, can cause
deadlocks. For example, in raid:

T1                              T2
bdev_open_by_dev
 lock open_mutex [1]
 ...
  efi_partition
  ...
   md_submit_bio
				md_ioctl mddev_syspend
				  -> suspend all io
				 md_add_new_disk
				  bind_rdev_to_array
				   bd_link_disk_holder
				    try lock open_mutex [2]
    md_handle_request
     -> wait mddev_resume

T1 scan partition, T2 add a new device to raid. T1 waits for T2 to resume
mddev, but T2 waits for open_mutex held by T1. Deadlock occurs.

Fix it by introducing a local mutex 'blk_holder_mutex' to replace
'open_mutex'.

Fixes: 1b0a2d950e ("md: use new apis to suspend array for ioctls involed array reconfiguration")
Reported-by: mgperkow@gmail.com
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218459
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240221090122.1281868-1-linan666@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Li Nan 2024-02-21 17:01:22 +08:00 committed by Jens Axboe
parent 522d73526f
commit 03f12122b2

View File

@ -8,6 +8,8 @@ struct bd_holder_disk {
int refcnt; int refcnt;
}; };
static DEFINE_MUTEX(blk_holder_mutex);
static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
struct gendisk *disk) struct gendisk *disk)
{ {
@ -80,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
kobject_get(bdev->bd_holder_dir); kobject_get(bdev->bd_holder_dir);
mutex_unlock(&bdev->bd_disk->open_mutex); mutex_unlock(&bdev->bd_disk->open_mutex);
mutex_lock(&disk->open_mutex); mutex_lock(&blk_holder_mutex);
WARN_ON_ONCE(!bdev->bd_holder); WARN_ON_ONCE(!bdev->bd_holder);
holder = bd_find_holder_disk(bdev, disk); holder = bd_find_holder_disk(bdev, disk);
@ -108,7 +110,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
goto out_del_symlink; goto out_del_symlink;
list_add(&holder->list, &disk->slave_bdevs); list_add(&holder->list, &disk->slave_bdevs);
mutex_unlock(&disk->open_mutex); mutex_unlock(&blk_holder_mutex);
return 0; return 0;
out_del_symlink: out_del_symlink:
@ -116,7 +118,7 @@ out_del_symlink:
out_free_holder: out_free_holder:
kfree(holder); kfree(holder);
out_unlock: out_unlock:
mutex_unlock(&disk->open_mutex); mutex_unlock(&blk_holder_mutex);
if (ret) if (ret)
kobject_put(bdev->bd_holder_dir); kobject_put(bdev->bd_holder_dir);
return ret; return ret;
@ -140,7 +142,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
if (WARN_ON_ONCE(!disk->slave_dir)) if (WARN_ON_ONCE(!disk->slave_dir))
return; return;
mutex_lock(&disk->open_mutex); mutex_lock(&blk_holder_mutex);
holder = bd_find_holder_disk(bdev, disk); holder = bd_find_holder_disk(bdev, disk);
if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
del_symlink(disk->slave_dir, bdev_kobj(bdev)); del_symlink(disk->slave_dir, bdev_kobj(bdev));
@ -149,6 +151,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
list_del_init(&holder->list); list_del_init(&holder->list);
kfree(holder); kfree(holder);
} }
mutex_unlock(&disk->open_mutex); mutex_unlock(&blk_holder_mutex);
} }
EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);