ceph: fix use-after-free bug for inodes when flushing capsnaps

There is a race between capsnaps flush and removing the inode from
'mdsc->snap_flush_list' list:

   == Thread A ==                     == Thread B ==
ceph_queue_cap_snap()
 -> allocate 'capsnapA'
 ->ihold('&ci->vfs_inode')
 ->add 'capsnapA' to 'ci->i_cap_snaps'
 ->add 'ci' to 'mdsc->snap_flush_list'
    ...
   == Thread C ==
ceph_flush_snaps()
 ->__ceph_flush_snaps()
  ->__send_flush_snap()
                                handle_cap_flushsnap_ack()
                                 ->iput('&ci->vfs_inode')
                                   this also will release 'ci'
                                    ...
				      == Thread D ==
                                ceph_handle_snap()
                                 ->flush_snaps()
                                  ->iterate 'mdsc->snap_flush_list'
                                   ->get the stale 'ci'
 ->remove 'ci' from                ->ihold(&ci->vfs_inode) this
   'mdsc->snap_flush_list'           will WARNING

To fix this we will increase the inode's i_count ref when adding 'ci'
to the 'mdsc->snap_flush_list' list.

[ idryomov: need_put int -> bool ]

Cc: stable@vger.kernel.org
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2209299
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 789be30..2321e5d 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1627,6 +1627,7 @@ void ceph_flush_snaps(struct ceph_inode_info *ci,
        struct inode *inode = &ci->netfs.inode;
        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
        struct ceph_mds_session *session = NULL;
+       bool need_put = false;
        int mds;
 
        dout("ceph_flush_snaps %p\n", inode);
@@ -1671,8 +1672,13 @@ out:
                ceph_put_mds_session(session);
        /* we flushed them all; remove this inode from the queue */
        spin_lock(&mdsc->snap_flush_lock);
+       if (!list_empty(&ci->i_snap_flush_item))
+               need_put = true;
        list_del_init(&ci->i_snap_flush_item);
        spin_unlock(&mdsc->snap_flush_lock);
+
+       if (need_put)
+               iput(inode);
 }
 
 /*

diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 0b236eb..2e73ba6 100644 (file)
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -693,8 +693,10 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
             capsnap->size);
 
        spin_lock(&mdsc->snap_flush_lock);
-       if (list_empty(&ci->i_snap_flush_item))
+       if (list_empty(&ci->i_snap_flush_item)) {
+               ihold(inode);
                list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
+       }
        spin_unlock(&mdsc->snap_flush_lock);
        return 1;  /* caller may want to ceph_flush_snaps */
 }