Yan, Zheng 85784f9395 ceph: only dirty ITER_IOVEC pages for direct read
If a page is already locked, attempting to dirty it leads to a deadlock
in lock_page().  This is what currently happens to ITER_BVEC pages when
a dio-enabled loop device is backed by ceph:

  $ losetup --direct-io /dev/loop0 /mnt/cephfs/img
  $ xfs_io -c 'pread 0 4k' /dev/loop0

Follow other file systems and only dirty ITER_IOVEC pages.

Cc: stable@kernel.org
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2018-03-30 11:17:48 +02:00
..
2018-02-06 14:43:37 +00:00
2018-03-16 13:37:42 -07:00
2018-02-07 14:25:22 -08:00
2018-02-07 14:25:22 -08:00
2017-11-16 11:41:22 -08:00
2018-01-24 17:33:57 -05:00
2018-02-06 18:32:45 -08:00
2018-01-01 10:09:33 -05:00
2018-03-07 11:47:15 +01:00
2018-02-07 14:25:22 -08:00
2017-09-04 19:05:15 -04:00
2018-02-06 18:32:45 -08:00
2018-01-03 10:13:36 -08:00
2017-12-07 14:23:30 -05:00
2018-01-29 07:27:24 -08:00
2018-02-06 10:41:33 -08:00
2018-02-08 15:18:32 -08:00
2017-12-09 20:16:33 -05:00