Log recovered from a user's cluster:

    <7>[ 5413.970692] ceph:  get_cap_refs 00000000958c114b ret 1 got Fr
    <7>[ 5413.970695] ceph:  start_read 00000000958c114b, no cache cap
    ...
    <7>[ 5473.934609] ceph:   my wanted = Fr, used = Fr, dirty -
    <7>[ 5473.934616] ceph:  revocation: pAsLsXsFr -> pAsLsXs (revoking Fr)
    <7>[ 5473.934632] ceph:  __ceph_caps_issued 00000000958c114b cap 00000000f7784259 issued pAsLsXs
    <7>[ 5473.934638] ceph:  check_caps 10000000e68.fffffffffffffffe file_want - used Fr dirty - flushing - issued pAsLsXs revoking Fr retain pAsLsXsFsr  AUTHONLY NOINVAL FLUSH_FORCE

The MDS subsequently complains that the kernel client is late releasing
caps.

Approximately, a series of changes to this code by commits 49870056
("ceph: convert ceph_readpages to ceph_readahead"), 2de16041
("netfs: Change ->init_request() to return an error code") and
a5c9dc44 ("ceph: Make ceph_init_request() check caps on readahead")
resulted in subtle resource cleanup to be missed. The main culprit is
the change in error handling in 2de16041 which meant that a failure
in init_request() would no longer cause cleanup to be called. That
would prevent the ceph_put_cap_refs() call which would cleanup the
leaked cap ref.

Cc: stable@vger.kernel.org
Fixes: a5c9dc44 ("ceph: Make ceph_init_request() check caps on readahead")
Link: https://tracker.ceph.com/issues/67008Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>