Fix z_xattr_lock/z_teardown_lock lock inversion

There exists a lock inversion between the z_xattr_lock and the
z_teardown_lock.  Detect this case and return EBUSY so zfs_resume_fs()
will mark the inode stale and it can be safely revalidated on next
access.

* process-1
zpl_xattr_get -> Takes zp->z_xattr_lock
  __zpl_xattr_get
    zfs_lookup -> Takes zsb->z_teardown_lock in ZFS_ENTER macro

* process-2
zfs_ioc_recv -> Takes zsb->z_teardown_lock in zfs_suspend_fs()
  zfs_resume_fs
    zfs_rezget -> Takes zp->z_xattr_lock

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chunwei Chen <david.chen@osnexus.com>
Closes #3969

diff --git a/module/zfs/zfs_znode.c b/module/zfs/zfs_znode.c
index bf360f1bc6359343268ab8b8995078b03c2a9e8c..6fda78e5f45166df34eab2f5dfbc8d5d04e19878 100644 (file)
--- a/module/zfs/zfs_znode.c
+++ b/module/zfs/zfs_znode.c
@@ -1012,7 +1012,16 @@ zfs_rezget(znode_t *zp)
        }
        mutex_exit(&zp->z_acl_lock);
 
-       rw_enter(&zp->z_xattr_lock, RW_WRITER);
+       /*
+        * Lock inversion with zpl_xattr_get->__zpl_xattr_get->zfs_lookup
+        * between z_xattr_lock and z_teardown_lock.  Detect this case and
+        * return EBUSY so zfs_resume_fs() will mark the inode stale and it
+        * will safely be revalidated on next access.
+        */
+       err = rw_tryenter(&zp->z_xattr_lock, RW_WRITER);
+       if (!err)
+               return (SET_ERROR(EBUSY));
+
        if (zp->z_xattr_cached) {
                nvlist_free(zp->z_xattr_cached);
                zp->z_xattr_cached = NULL;