dm: fix add_disk() NULL pointer due to race with free_dev()

Commit c4db59d31e39 ("fs: don't reassign dirty inodes to
default_backing_dev_info") exposed DM to a latent race in free_dev() vs
add_disk() in relation to management of the device's minor number.

Fix this by refactoring free_dev() to match cleanup order of the
alloc_dev() error path.  Move cleanup of the gendisk, queue, and bdev
to _before_ the cleanup of the idr managed minor number.

Also, purely due to cleanup that fell out during the free_dev() audit:
- adjust dm_blk_close() to access the gendisk's private_data under
  the _minor_lock spinlock.
- move __dm_destroy()'s dm_get_live_table() call out from under the
  _minor_lock spinlock.

Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1202449

Reported-by: Zdenek Kabelac <zkabelac@redhat.com>
Reported-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9b641b38b857106000c6645035e7490c943f9233..8001fe9e3434734ad92c8109ef8fa860906238ce 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -433,7 +433,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
 
        dm_get(md);
        atomic_inc(&md->open_count);
-
 out:
        spin_unlock(&_minor_lock);
 
@@ -442,16 +441,20 @@ out:
 
 static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 {
-       struct mapped_device *md = disk->private_data;
+       struct mapped_device *md;
 
        spin_lock(&_minor_lock);
 
+       md = disk->private_data;
+       if (WARN_ON(!md))
+               goto out;
+
        if (atomic_dec_and_test(&md->open_count) &&
            (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
                queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
        dm_put(md);
-
+out:
        spin_unlock(&_minor_lock);
 }
 
@@ -2241,7 +2244,6 @@ static void free_dev(struct mapped_device *md)
        int minor = MINOR(disk_devt(md->disk));
 
        unlock_fs(md);
-       bdput(md->bdev);
        destroy_workqueue(md->wq);
 
        if (md->kworker_task)
@@ -2252,19 +2254,22 @@ static void free_dev(struct mapped_device *md)
                mempool_destroy(md->rq_pool);
        if (md->bs)
                bioset_free(md->bs);
-       blk_integrity_unregister(md->disk);
-       del_gendisk(md->disk);
+
        cleanup_srcu_struct(&md->io_barrier);
        free_table_devices(&md->table_devices);
-       free_minor(minor);
+       dm_stats_cleanup(&md->stats);
 
        spin_lock(&_minor_lock);
        md->disk->private_data = NULL;
        spin_unlock(&_minor_lock);
-
+       if (blk_get_integrity(md->disk))
+               blk_integrity_unregister(md->disk);
+       del_gendisk(md->disk);
        put_disk(md->disk);
        blk_cleanup_queue(md->queue);
-       dm_stats_cleanup(&md->stats);
+       bdput(md->bdev);
+       free_minor(minor);
+
        module_put(THIS_MODULE);
        kfree(md);
 }
@@ -2642,8 +2647,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 
        might_sleep();
 
-       spin_lock(&_minor_lock);
        map = dm_get_live_table(md, &srcu_idx);
+
+       spin_lock(&_minor_lock);
        idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
        set_bit(DMF_FREEING, &md->flags);
        spin_unlock(&_minor_lock);