linux-stable.git/drivers/block/rbd.c, branch linux-3.19.y

rbd: drop parent_ref in rbd_dev_unprobe() unconditionally

2015-01-28T13:12:02+00:00

This effectively reverts the last hunk of 392a9dad7e77 ("rbd: detect
when clone image is flattened").

The problem with parent_overlap != 0 condition is that it's possible
and completely valid to have an image with parent_overlap == 0 whose
parent state needs to be cleaned up on unmap.  The next commit, which
drops the "clone image now standalone" logic, opens up another window
of opportunity to hit this, but even without it

    # cat parent-ref.sh
    #!/bin/bash
    rbd create --image-format 2 --size 1 foo
    rbd snap create foo@snap
    rbd snap protect foo@snap
    rbd clone foo@snap bar
    rbd resize --allow-shrink --size 0 bar
    rbd resize --size 1 bar
    DEV=$(rbd map bar)
    rbd unmap $DEV

leaves rbd_device/rbd_spec/etc and rbd_client along with ceph_client
hanging around.

My thinking behind calling rbd_dev_parent_put() unconditionally is that
there shouldn't be any requests in flight at that point in time as we
are deep into unmap sequence.  Hence, even if rbd_dev_unparent() caused
by flatten is delayed by in-flight requests, it will have finished by
the time we reach rbd_dev_unprobe() caused by unmap, thus turning
unconditional rbd_dev_parent_put() into a no-op.

Fixes: http://tracker.ceph.com/issues/10352

Cc: stable@vger.kernel.org # 3.11+
Signed-off-by: Ilya Dryomov 
Reviewed-by: Josh Durgin 
Reviewed-by: Alex Elder

rbd: fix rbd_dev_parent_get() when parent_overlap == 0

2015-01-28T13:11:51+00:00

The comment for rbd_dev_parent_get() said

    * We must get the reference before checking for the overlap to
    * coordinate properly with zeroing the parent overlap in
    * rbd_dev_v2_parent_info() when an image gets flattened.  We
    * drop it again if there is no overlap.

but the "drop it again if there is no overlap" part was missing from
the implementation.  This lead to absurd parent_ref values for images
with parent_overlap == 0, as parent_ref was incremented for each
img_request and virtually never decremented.

Fix this by leveraging the fact that refresh path calls
rbd_dev_v2_parent_info() under header_rwsem and use it for read in
rbd_dev_parent_get(), instead of messing around with atomics.  Get rid
of barriers in rbd_dev_v2_parent_info() while at it - I don't see what
they'd pair with now and I suspect we are in a pretty miserable
situation as far as proper locking goes regardless.

Cc: stable@vger.kernel.org # 3.11+
Signed-off-by: Ilya Dryomov 
Reviewed-by: Josh Durgin 
Reviewed-by: Alex Elder

rbd: don't treat CEPH_OSD_OP_DELETE as extent op

2014-12-17T17:09:51+00:00

CEPH_OSD_OP_DELETE is not an extent op, stop treating it as such.  This
sneaked in with discard patches - it's one of the three osd ops (the
other two are CEPH_OSD_OP_TRUNCATE and CEPH_OSD_OP_ZERO) that discard
is implemented with.

Signed-off-by: Ilya Dryomov 
Reviewed-by: Alex Elder

ceph, rbd: delete unnecessary checks before two function calls

2014-12-17T17:09:50+00:00

The functions ceph_put_snap_context() and iput() test whether their
argument is NULL and then return immediately. Thus the test around the
call is not needed.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring 
[idryomov@redhat.com: squashed rbd.c hunk, changelog]
Signed-off-by: Ilya Dryomov

rbd: Fix error recovery in rbd_obj_read_sync()

2014-10-30T10:11:51+00:00

When we fail to allocate page vector in rbd_obj_read_sync() we just
basically ignore the problem and continue which will result in an oops
later. Fix the problem by returning proper error.

CC: Yehuda Sadeh 
CC: Sage Weil 
CC: ceph-devel@vger.kernel.org
CC: stable@vger.kernel.org
Coverity-id: 1226882
Signed-off-by: Jan Kara 
Signed-off-by: Ilya Dryomov

rbd: use a single workqueue for all devices

2014-10-30T10:11:25+00:00

Using one queue per device doesn't make much sense given that our
workfn processes "devices" and not "requests".  Switch to a single
workqueue for all devices.

Signed-off-by: Ilya Dryomov 
Reviewed-by: Sage Weil

rbd: rbd workqueues need a resque worker

2014-10-14T19:57:05+00:00

Need to use WQ_MEM_RECLAIM for our workqueues to prevent I/O lockups
under memory pressure - we sit on the memory reclaim path.

Cc: stable@vger.kernel.org # 3.17, needs backporting for 3.16
Signed-off-by: Ilya Dryomov 
Tested-by: Micha Krause 
Reviewed-by: Sage Weil

rbd: set the remaining discard properties to enable support

2014-10-14T17:03:37+00:00

max_discard_sectors must be set for the queue to support discard.
Operations implementing discard for rbd zero data, so report that.

Signed-off-by: Josh Durgin

rbd: use helpers to handle discard for layered images correctly

2014-10-14T17:03:36+00:00

Only allocate two osd ops for discard requests, since the
preallocation hint is only added for regular writes.  Use
rbd_img_obj_request_fill() to recreate the original write or discard
osd operations, isolating that logic to one place, and change the
assert in rbd_osd_req_create_copyup() to accept discard requests as
well.

Signed-off-by: Josh Durgin

rbd: extract a method for adding object operations

2014-10-14T17:03:35+00:00

rbd_img_request_fill() creates a ceph_osd_request and has logic for
adding the appropriate osd ops to it based on the request type and
image properties.

For layered images, the original rbd_obj_request is resent with a
copyup operation in front, using a new ceph_osd_request. The logic for
adding the original operations should be the same as when first
sending them, so move it to a helper function.

op_type only needs to be checked once, so create a helper for that as
well and call it outside the loop in rbd_img_request_fill().

Signed-off-by: Josh Durgin