Switch to ceph_object_id and use ceph_oid_aprintf() instead of a bare
const char *. This reduces noise in rbd_dev_header_name().
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Currently ceph_object_id can hold object names of up to 100
(CEPH_MAX_OID_NAME_LEN) characters. This is enough for all use cases,
expect one - long rbd image names:
- a format 1 header is named "<imgname>.rbd"
- an object that points to a format 2 header is named "rbd_id.<imgname>"
We operate on these potentially long-named objects during rbd map, and,
for format 1 images, during header refresh. (A format 2 header name is
a small system-generated string.)
Lift this 100 character limit by making ceph_object_id be able to point
to an externally-allocated string. Apart from being able to work with
almost arbitrarily-long named objects, this allows us to reduce the
size of ceph_object_id from >100 bytes to 64 bytes.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
The size of ->r_request and ->r_reply messages depends on the size of
the object name (ceph_object_id), while the size of ceph_osd_request is
fixed. Move message allocation into a separate function that would
have to be called after ceph_object_id and ceph_object_locator (which
is also going to become variable in size with RADOS namespaces) have
been filled in:
req = ceph_osdc_alloc_request(...);
<fill in req->r_base_oid>
<fill in req->r_base_oloc>
ceph_osdc_alloc_messages(req);
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
By the time we get to checking for_each_obj_request_safe(img_request)
terminating condition, all obj_requests may be complete and img_request
ref, that rbd_img_request_submit() takes away from its caller, may be
put. Moving the next_obj_request cursor is then a use-after-free on
img_request.
It's totally benign, as the value that's read is never used, but
I think it's still worth fixing.
Cc: Alex Elder <elder@linaro.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
A while ago, commit 9875201e10 ("rbd: fix use-after free of
rbd_dev->disk") fixed rbd unmap vs notify race by introducing
an exported wrapper for flushing notifies and sticking it into
do_rbd_remove().
A similar problem exists on the rbd map path, though: the watch is
registered in rbd_dev_image_probe(), while the disk is set up quite
a few steps later, in rbd_dev_device_setup(). Nothing prevents
a notify from coming in and crashing on a NULL rbd_dev->disk:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000050
Call Trace:
[<ffffffffa0508344>] rbd_watch_cb+0x34/0x180 [rbd]
[<ffffffffa04bd290>] do_event_work+0x40/0xb0 [libceph]
[<ffffffff8109d5db>] process_one_work+0x17b/0x470
[<ffffffff8109e3ab>] worker_thread+0x11b/0x400
[<ffffffff8109e290>] ? rescuer_thread+0x400/0x400
[<ffffffff810a5acf>] kthread+0xcf/0xe0
[<ffffffff810b41b3>] ? finish_task_switch+0x53/0x170
[<ffffffff810a5a00>] ? kthread_create_on_node+0x140/0x140
[<ffffffff81645dd8>] ret_from_fork+0x58/0x90
[<ffffffff810a5a00>] ? kthread_create_on_node+0x140/0x140
RIP [<ffffffffa050828a>] rbd_dev_refresh+0xfa/0x180 [rbd]
If an error occurs during rbd map, we have to error out, potentially
tearing down a watch. Just like on rbd unmap, notifies have to be
flushed, otherwise rbd_watch_cb() may end up trying to read in the
image header after rbd_dev_image_release() has run:
Assertion failure in rbd_dev_header_info() at line 4722:
rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
Call Trace:
[<ffffffff81cccee0>] ? rbd_parent_request_create+0x150/0x150
[<ffffffff81cd4e59>] rbd_dev_refresh+0x59/0x390
[<ffffffff81cd5229>] rbd_watch_cb+0x69/0x290
[<ffffffff81fde9bf>] do_event_work+0x10f/0x1c0
[<ffffffff81107799>] process_one_work+0x689/0x1a80
[<ffffffff811076f7>] ? process_one_work+0x5e7/0x1a80
[<ffffffff81132065>] ? finish_task_switch+0x225/0x640
[<ffffffff81107110>] ? pwq_dec_nr_in_flight+0x2b0/0x2b0
[<ffffffff81108c69>] worker_thread+0xd9/0x1320
[<ffffffff81108b90>] ? process_one_work+0x1a80/0x1a80
[<ffffffff8111b02d>] kthread+0x21d/0x2e0
[<ffffffff8111ae10>] ? kthread_stop+0x550/0x550
[<ffffffff82022802>] ret_from_fork+0x22/0x40
[<ffffffff8111ae10>] ? kthread_stop+0x550/0x550
RIP [<ffffffff81ccd8f9>] rbd_dev_header_info+0xa19/0x1e30
To fix this, a) check if RBD_DEV_FLAG_EXISTS is set before calling
revalidate_disk(), b) move ceph_osdc_flush_notifies() call into
rbd_dev_header_unwatch_sync() to cover rbd map error paths and c) turn
header read-in into a critical section. The latter also happens to
take care of rbd map foo@bar vs rbd snap rm foo@bar race.
Fixes: http://tracker.ceph.com/issues/15490
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
As of 5a60e87603, RBD object request
allocations are made via rbd_obj_request_create() with GFP_NOIO.
However, subsequent OSD request allocations in rbd_osd_req_create*()
use GFP_ATOMIC.
With heavy page cache usage (e.g. OSDs running on same host as krbd
client), rbd_osd_req_create() order-1 GFP_ATOMIC allocations have been
observed to fail, where direct reclaim would have allowed GFP_NOIO
allocations to succeed.
Cc: stable@vger.kernel.org # 3.18+
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Suggested-by: Neil Brown <neilb@suse.com>
Signed-off-by: David Disseldorp <ddiss@suse.de>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Use KMEM_CACHE() instead of kmem_cache_create() to simplify the code.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Turn r_ops into a flexible array member to enable large, consisting of
up to 16 ops, OSD requests. The use case is scattered writeback in
cephfs and, as far as the kernel client is concerned, 16 is just a made
up number.
r_ops had size 3 for copyup+hint+write, but copyup is really a special
case - it can only happen once. ceph_osd_request_cache is therefore
stuffed with num_ops=2 requests, anything bigger than that is allocated
with kmalloc(). req_mempool is backed by ceph_osd_request_cache, which
means either num_ops=1 or num_ops=2 for use_mempool=true - all existing
users (ceph_writepages_start(), ceph_osdc_writepages()) are fine with
that.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This avoids defining large array of r_reply_op_{len,result} in
in struct ceph_osd_request.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
The rbd_dev_destroy() function tests whether its argument is NULL
and then returns immediately. Thus the test around the call is not needed.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Commit 4e752f0ab0 ("rbd: access snapshot context and mapping size
safely") moved ceph_get_snap_context() out of rbd_img_request_create()
and into rbd_queue_workfn(), adding a ceph_put_snap_context() to the
error path in rbd_queue_workfn(). However, rbd_img_request_create()
consumes a ref on snapc, so calling ceph_put_snap_context() after
a successful rbd_img_request_create() leads to an extra put. Fix it.
Cc: stable@vger.kernel.org # 3.18+
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Commit d1cf578845 ("rbd: set mapping info earlier") defined
rbd_dev_mapping_clear(), but, just a few days after, commit
f35a4dee14 ("rbd: set the mapping size and features later") moved
rbd_dev_mapping_set() calls and added another rbd_dev_mapping_clear()
call instead of moving the old one. Around the same time, another
duplicate was introduced in rbd_dev_device_release() - kill both.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
No point in providing an empty device_type::release callback and then
setting device::release for each rbd_dev dynamically.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
struct rbd_device has struct device embedded in it, which means it's
part of kobject universe and has an unpredictable life cycle. Freeing
its memory outside of the release callback is flawed, yet commits
200a6a8be5 ("rbd: don't destroy rbd_dev in device release function")
and 8ad42cd0c0 ("rbd: don't have device release destroy rbd_dev")
moved rbd_dev_destroy() out to rbd_dev_image_release().
This commit reverts most of that, the key points are:
- rbd_dev->dev is initialized in rbd_dev_create(), making it possible
to use rbd_dev_destroy() - which is just a put_device() - both before
we register with device core and after.
- rbd_dev_release() (the release callback) is the only place we
kfree(rbd_dev). It's also where we do module_put(), keeping the
module unload race window as small as possible.
- We pin the module in rbd_dev_create(), but only for mapping
rbd_dev-s. Moving image related stuff out of struct rbd_device into
another struct which isn't tied with sysfs and device core is long
overdue, but until that happens, this will keep rbd module refcount
(which users can observe with lsmod) sane.
Fixes: http://tracker.ceph.com/issues/12697
Cc: Alex Elder <elder@linaro.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Returning pool id (i.e. >= 0) from a sysfs ->store() callback makes
userspace think it needs to retry the write. Fix it - it's a leftover
from the times when the equivalent of rbd_dev_create() was the first
action in rbd_add().
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
rbd requires stable pages, as it performs a crc of the page data before
they are send to the OSDs.
But since kernel 3.9 (patch 1d1d1a7672
"mm: only enforce stable page writes if the backing device requires
it") it is not assumed anymore that block devices require stable pages.
This patch sets the necessary flag to get stable pages back for rbd.
In a ceph installation that provides multiple ext4 formatted rbd
devices "bad crc" messages appeared regularly (ca 1 message every 1-2
minutes on every OSD that provided the data for the rbd) in the
OSD-logs before this patch. After this patch this messages are pretty
much gone (only ca 1-2 / month / OSD).
Cc: stable@vger.kernel.org # 3.9+, needs backporting
Signed-off-by: Ronny Hegewald <Ronny.Hegewald@online.de>
[idryomov@gmail.com: require stable pages only in crc case, changelog]
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Mapping an image with a long parent chain (e.g. image foo, whose parent
is bar, whose parent is baz, etc) currently leads to a kernel stack
overflow, due to the following recursion in the reply path:
rbd_osd_req_callback()
rbd_obj_request_complete()
rbd_img_obj_callback()
rbd_img_parent_read_callback()
rbd_obj_request_complete()
...
Limit the parent chain to 16 images, which is ~5K worth of stack. When
the above recursion is eliminated, this limit can be lifted.
Fixes: http://tracker.ceph.com/issues/12538
Cc: stable@vger.kernel.org # 3.10+, needs backporting for < 4.2
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Currently we leak parent_spec and trigger a "parent reference
underflow" warning if rbd_dev_create() in rbd_dev_probe_parent() fails.
The problem is we take the !parent out_err branch and that only drops
refcounts; parent_spec that would've been freed had we called
rbd_dev_unparent() remains and triggers rbd_warn() in
rbd_dev_parent_put() - at that point we have parent_spec != NULL and
parent_ref == 0, so counter ends up being -1 after the decrement.
Redo rbd_dev_probe_parent() to fix this.
Cc: stable@vger.kernel.org # 3.10+, needs backporting for < 4.2
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
This covers only the simplest case - an object size sized write, but
it's still useful in tiering setups when EC is used for the base tier
as writefull op can be proxied, saving an object promotion.
Even though updating ceph_osdc_new_request() to allow writefull should
just be a matter of fixing an assert, I didn't do it because its only
user is cephfs. All other sites were updated.
Reflects ceph.git commit 7bfb7f9025a8ee0d2305f49bf0336d2424da5b5b.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Commit 30e2bc08b2 ("Revert "block: remove artifical max_hw_sectors
cap"") restored a clamp on max_sectors. It's now 2560 sectors instead
of 1024, but it's not good enough: we set max_hw_sectors to rbd object
size because we don't want object sized I/Os to be split, and the
default object size is 4M.
So, set max_sectors to max_hw_sectors in rbd at queue init time.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Pull Ceph update from Sage Weil:
"There are a few fixes for snapshot behavior with CephFS and support
for the new keepalive protocol from Zheng, a libceph fix that affects
both RBD and CephFS, a few bug fixes and cleanups for RBD from Ilya,
and several small fixes and cleanups from Jianpeng and others"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
ceph: improve readahead for file holes
ceph: get inode size for each append write
libceph: check data_len in ->alloc_msg()
libceph: use keepalive2 to verify the mon session is alive
rbd: plug rbd_dev->header.object_prefix memory leak
rbd: fix double free on rbd_dev->header_name
libceph: set 'exists' flag for newly up osd
ceph: cleanup use of ceph_msg_get
ceph: no need to get parent inode in ceph_open
ceph: remove the useless judgement
ceph: remove redundant test of head->safe and silence static analysis warnings
ceph: fix queuing inode to mdsdir's snaprealm
libceph: rename con_work() to ceph_con_workfn()
libceph: Avoid holding the zero page on ceph_msgr_slab_init errors
libceph: remove the unused macro AES_KEY_SIZE
ceph: invalidate dirty pages after forced umount
ceph: EIO all operations after forced umount
Need to free object_prefix when rbd_dev_v2_snap_context() fails, but
only if this is the first time we are reading in the header.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
If rbd_dev_image_probe() in rbd_dev_probe_parent() fails, header_name
is freed twice: once in rbd_dev_probe_parent() and then in its caller
rbd_dev_image_probe() (rbd_dev_image_probe() is called recursively to
handle parent images).
rbd_dev_probe_parent() is responsible for probing the parent, so it
shouldn't muck with clone's fields.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Pull core block updates from Jens Axboe:
"This first core part of the block IO changes contains:
- Cleanup of the bio IO error signaling from Christoph. We used to
rely on the uptodate bit and passing around of an error, now we
store the error in the bio itself.
- Improvement of the above from myself, by shrinking the bio size
down again to fit in two cachelines on x86-64.
- Revert of the max_hw_sectors cap removal from a revision again,
from Jeff Moyer. This caused performance regressions in various
tests. Reinstate the limit, bump it to a more reasonable size
instead.
- Make /sys/block/<dev>/queue/discard_max_bytes writeable, by me.
Most devices have huge trim limits, which can cause nasty latencies
when deleting files. Enable the admin to configure the size down.
We will look into having a more sane default instead of UINT_MAX
sectors.
- Improvement of the SGP gaps logic from Keith Busch.
- Enable the block core to handle arbitrarily sized bios, which
enables a nice simplification of bio_add_page() (which is an IO hot
path). From Kent.
- Improvements to the partition io stats accounting, making it
faster. From Ming Lei.
- Also from Ming Lei, a basic fixup for overflow of the sysfs pending
file in blk-mq, as well as a fix for a blk-mq timeout race
condition.
- Ming Lin has been carrying Kents above mentioned patches forward
for a while, and testing them. Ming also did a few fixes around
that.
- Sasha Levin found and fixed a use-after-free problem introduced by
the bio->bi_error changes from Christoph.
- Small blk cgroup cleanup from Viresh Kumar"
* 'for-4.3/core' of git://git.kernel.dk/linux-block: (26 commits)
blk: Fix bio_io_vec index when checking bvec gaps
block: Replace SG_GAPS with new queue limits mask
block: bump BLK_DEF_MAX_SECTORS to 2560
Revert "block: remove artifical max_hw_sectors cap"
blk-mq: fix race between timeout and freeing request
blk-mq: fix buffer overflow when reading sysfs file of 'pending'
Documentation: update notes in biovecs about arbitrarily sized bios
block: remove bio_get_nr_vecs()
fs: use helper bio_add_page() instead of open coding on bi_io_vec
block: kill merge_bvec_fn() completely
md/raid5: get rid of bio_fits_rdev()
md/raid5: split bio for chunk_aligned_read
block: remove split code in blkdev_issue_{discard,write_same}
btrfs: remove bio splitting and merge_bvec_fn() calls
bcache: remove driver private bio splitting code
block: simplify bio_add_page()
block: make generic_make_request handle arbitrarily sized bios
blk-cgroup: Drop unlikely before IS_ERR(_OR_NULL)
block: don't access bio->bi_error after bio_put()
block: shrink struct bio down to 2 cache lines again
...
As generic_make_request() is now able to handle arbitrarily sized bios,
it's no longer necessary for each individual block driver to define its
own ->merge_bvec_fn() callback. Remove every invocation completely.
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@kernel.org>
Cc: ceph-devel@vger.kernel.org
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: NeilBrown <neilb@suse.de> (for the 'md' bits)
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
[dpark: also remove ->merge_bvec_fn() in dm-thin as well as
dm-era-target, and resolve merge conflicts]
Signed-off-by: Dongsu Park <dpark@posteo.net>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
For write/discard obj_requests that involved a copyup method call, the
opcode of the first op is CEPH_OSD_OP_CALL and the ->callback is
rbd_img_obj_copyup_callback(). The latter frees copyup pages, sets
->xferred and delegates to rbd_img_obj_callback(), the "normal" image
object callback, for reporting to block layer and putting refs.
rbd_osd_req_callback() however treats CEPH_OSD_OP_CALL as a trivial op,
which means obj_request is marked done in rbd_osd_trivial_callback(),
*before* ->callback is invoked and rbd_img_obj_copyup_callback() has
a chance to run. Marking obj_request done essentially means giving
rbd_img_obj_callback() a license to end it at any moment, so if another
obj_request from the same img_request is being completed concurrently,
rbd_img_obj_end_request() may very well be called on such prematurally
marked done request:
<obj_request-1/2 reply>
handle_reply()
rbd_osd_req_callback()
rbd_osd_trivial_callback()
rbd_obj_request_complete()
rbd_img_obj_copyup_callback()
rbd_img_obj_callback()
<obj_request-2/2 reply>
handle_reply()
rbd_osd_req_callback()
rbd_osd_trivial_callback()
for_each_obj_request(obj_request->img_request) {
rbd_img_obj_end_request(obj_request-1/2)
rbd_img_obj_end_request(obj_request-2/2) <--
}
Calling rbd_img_obj_end_request() on such a request leads to trouble,
in particular because its ->xfferred is 0. We report 0 to the block
layer with blk_update_request(), get back 1 for "this request has more
data in flight" and then trip on
rbd_assert(more ^ (which == img_request->obj_request_count));
with rhs (which == ...) being 1 because rbd_img_obj_end_request() has
been called for both requests and lhs (more) being 1 because we haven't
got a chance to set ->xfferred in rbd_img_obj_copyup_callback() yet.
To fix this, leverage that rbd wants to call class methods in only two
cases: one is a generic method call wrapper (obj_request is standalone)
and the other is a copyup (obj_request is part of an img_request). So
make a dedicated handler for CEPH_OSD_OP_CALL and directly invoke
rbd_img_obj_copyup_callback() from it if obj_request is part of an
img_request, similar to how CEPH_OSD_OP_READ handler invokes
rbd_img_obj_request_read_callback().
Since rbd_img_obj_copyup_callback() is now being called from the OSD
request callback (only), it is renamed to rbd_osd_copyup_callback().
Cc: Alex Elder <elder@linaro.org>
Cc: stable@vger.kernel.org # 3.10+, needs backporting for < 3.18
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Some drivers use it now, others just set the limits field manually.
But in preparation for splitting this into a hard and soft limit,
ensure that they all call the proper function for setting the hw
limit for discards.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
rbd_obj_request_create() is called on the main I/O path, so we need to
use GFP_NOIO to make sure allocation doesn't blow back on us. Not all
callers need this, but I'm still hardcoding the flag inside rather than
making it a parameter because a) this is going to stable, and b) those
callers shouldn't really use rbd_obj_request_create() and will be fixed
in the future.
More memory allocation fixes will follow.
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
nr_requests (/sys/block/rbd<id>/queue/nr_requests) is pretty much
irrelevant in blk-mq case because each driver sets its own max depth
that it can handle and that's the number of tags that gets preallocated
on setup. Users can't increase queue depth beyond that value via
writing to nr_requests.
For rbd we are happy with the default BLKDEV_MAX_RQ (128) for most
cases but we want to give users the opportunity to increase it.
Introduce a new per-device queue_depth option to do just that:
$ sudo rbd map -o queue_depth=1024 ...
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
The default queue_limits::max_segments value (BLK_MAX_SEGMENTS = 128)
unnecessarily limits bio sizes to 512k (assuming 4k pages). rbd, being
a virtual block device, doesn't have any restrictions on the number of
physical segments, so bump max_segments to max_hw_sectors, in theory
allowing a sector per segment (although the only case this matters that
I can think of is some readv/writev style thing). In practice this is
going to give us 1M bios - the number of segments in a bio is limited
in bio_get_nr_vecs() by BIO_MAX_PAGES = 256.
Note that this doesn't result in any improvement on a typical direct
sequential test. This is because on a box with a not too badly
fragmented memory the default BLK_MAX_SEGMENTS is enough to see nice
rbd object size sized requests. The only difference is the size of
bios being merged - 512k vs 1M for something like
$ dd if=/dev/zero of=/dev/rbd0 oflag=direct bs=$RBD_OBJ_SIZE
$ dd if=/dev/rbd0 iflag=direct of=/dev/null bs=$RBD_OBJ_SIZE
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
As part of unmap sequence, kernel client has to talk to the OSDs to
teardown watch on the header object. If none of the OSDs are available
it would hang forever, until interrupted by a signal - when that
happens we follow through with the rest of unmap procedure (i.e.
unregister the device and put all the data structures) and the unmap is
still considired successful (rbd cli tool exits with 0). The watch on
the userspace side should eventually timeout so that's fine.
This isn't very nice, because various userspace tools (pacemaker rbd
resource agent, for example) then have to worry about setting up their
own timeouts. Timeout it with mount_timeout (60 seconds by default).
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Reviewed-by: Sage Weil <sage@redhat.com>
There are currently three libceph-level timeouts that the user can
specify on mount: mount_timeout, osd_idle_ttl and osdkeepalive. All of
these are in seconds and no checking is done on user input: negative
values are accepted, we multiply them all by HZ which may or may not
overflow, arbitrarily large jiffies then get added together, etc.
There is also a bug in the way mount_timeout=0 is handled. It's
supposed to mean "infinite timeout", but that's not how wait.h APIs
treat it and so __ceph_open_session() for example will busy loop
without much chance of being interrupted if none of ceph-mons are
there.
Fix all this by verifying user input, storing timeouts capped by
msecs_to_jiffies() in jiffies and using the new ceph_timeout_jiffies()
helper for all user-specified waits to handle infinite timeouts
correctly.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Elder <elder@linaro.org>
When we end I/O struct request with error, we need to pass
obj_request->length as @nr_bytes so that the entire obj_request worth
of bytes is completed. Otherwise block layer ends up confused and we
trip on
rbd_assert(more ^ (which == img_request->obj_request_count));
in rbd_img_obj_callback() due to more being true no matter what. We
already do it in most cases but we are missing some, in particular
those where we don't even get a chance to submit any obj_requests, due
to an early -ENOMEM for example.
A number of obj_request->xferred assignments seem to be redundant but
I haven't touched any of obj_request->xferred stuff to keep this small
and isolated.
Cc: Alex Elder <elder@linaro.org>
Cc: stable@vger.kernel.org # 3.10+
Reported-by: Shawn Edwards <lesser.evil@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Set QUEUE_FLAG_NONROT. Following commit b277da0a8a ("block: disable
entropy contributions for nonrot devices") we should also clear
QUEUE_FLAG_ADD_RANDOM, but it's off by default for blk-mq drivers, so
just note it in the comment.
Also remove physical block size assignment - no sense in repeating
defaults that are not going to change.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This converts the rbd driver to use the blk-mq infrastructure. Except
for switching to a per-request work item this is almost mechanical.
This was tested by Alexandre DERUMIER in November, and found to give
him 120000 iops, although the only comparism available was an old
3.10 kernel which gave 80000iops.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Alex Elder <elder@linaro.org>
[idryomov@gmail.com: context, blk_mq_init_queue() EH]
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
If the clone is resized down to 0, it becomes standalone. If such
resize is carried over while an image is mapped we would detect this
and call rbd_dev_parent_put() which means "let go of all parent state,
including the spec(s) of parent images(s)". This leads to a mismatch
between "rbd info" and sysfs parent fields, so a fix is in order.
# rbd create --image-format 2 --size 1 foo
# rbd snap create foo@snap
# rbd snap protect foo@snap
# rbd clone foo@snap bar
# DEV=$(rbd map bar)
# rbd resize --allow-shrink --size 0 bar
# rbd resize --size 1 bar
# rbd info bar | grep parent
parent: rbd/foo@snap
Before:
# cat /sys/bus/rbd/devices/0/parent
(no parent image)
After:
# cat /sys/bus/rbd/devices/0/parent
pool_id 0
pool_name rbd
image_id 10056b8b4567
image_name foo
snap_id 2
snap_name snap
overlap 0
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Alex Elder <elder@linaro.org>
header_rwsem should be released on errors. Also remove useless
rbd_dev->mapping.size != rbd_dev->header.image_size test.
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
It's been largely superseded by dup_token() and unused for over
2 years, identified by cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
[idryomov@redhat.com: changelog]
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
This effectively reverts the last hunk of 392a9dad7e ("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 <idryomov@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Alex Elder <elder@linaro.org>
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 <idryomov@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Alex Elder <elder@linaro.org>
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 <idryomov@redhat.com>
Reviewed-by: Alex Elder <elder@linaro.org>
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 <elfring@users.sourceforge.net>
[idryomov@redhat.com: squashed rbd.c hunk, changelog]
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
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 <yehuda@inktank.com>
CC: Sage Weil <sage@inktank.com>
CC: ceph-devel@vger.kernel.org
CC: stable@vger.kernel.org
Coverity-id: 1226882
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
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 <idryomov@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
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 <idryomov@redhat.com>
Tested-by: Micha Krause <micha@krausam.de>
Reviewed-by: Sage Weil <sage@redhat.com>
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 <josh.durgin@inktank.com>
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 <josh.durgin@inktank.com>
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 <josh.durgin@inktank.com>
Discard requests are a form of write, so they should go through the
same process as plain write requests and trigger copy-on-write for
layered images.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Discard may try to delete an object from a non-layered image that does not exist.
If this occurs, the image already has no data in that range, so change the
result to success.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Discards take a reference to the snapshot context of an image when
they are created. This reference needs to be cleaned up when the
request is done just as it is for regular writes.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
In rbd_img_request_fill() the image size is only checked to determine
whether we can truncate an object instead of zeroing it for discard
requests. Take rbd_dev->header_rwsem while reading the image size, and
move this read into the discard check, so that non-discard ops don't
need to take the semaphore in this function.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
This patch add the discard support for rbd driver.
There are three types operation in the driver:
1. The objects would be removed if they completely contained
within the discard range.
2. The objects would be truncated if they partly contained within
the discard range, and align with their boundary.
3. Others would be zeroed.
A discard request from blkdev_issue_discard() is defined which
REQ_WRITE and REQ_DISCARD both marked and no data, so we must
check the REQ_DISCARD first when getting the request type.
This resolve:
http://tracker.ceph.com/issues/190
[ Ilya Dryomov: This is incomplete and somewhat buggy, see follow up
commits by Josh Durgin for refinements and fixes which weren't
folded in to preserve authorship. ]
Signed-off-by: Guangliang Zhao <lucienchao@gmail.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
It could only handle the read and write operations now,
extend it for the coming discard support.
Signed-off-by: Guangliang Zhao <lucienchao@gmail.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
It need to copyup the parent's content when layered writing,
but an entire object write would overwrite it, so skip it.
Signed-off-by: Guangliang Zhao <lucienchao@gmail.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
These fields may both change while the image is mapped if a snapshot
is created or deleted or the image is resized. They are guarded by
rbd_dev->header_rwsem, so hold that while reading them, and store a
local copy to refer to outside of the critical section. The local copy
will stay consistent since the snapshot context is reference counted,
and the mapping size is just a u64. This prevents torn loads from
giving us inconsistent values.
Move reading header.snapc into the caller of rbd_img_request_create()
so that we only need to take the semaphore once. The read-only caller,
rbd_parent_request_create() can just pass NULL for snapc, since the
snapshot context is only relevant for writes.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Trying to map an image out of a pool for which we don't have an 'x'
permission bit fails with -ERANGE from ceph_extract_encoded_string()
due to an unsigned vs signed bug. Fix it and get rid of the -EINVAL
sink, thus propagating rbd::get_id cls method errors. (I've seen
a bunch of unexplained -ERANGE reports, I bet this is it).
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Fix to return -ENOMEM from the workqueue alloc error handling
case instead of 0, as done elsewhere in this function.
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
drivers/block/rbd.c: In function ‘rbd_dev_device_setup’:
drivers/block/rbd.c:5090:19: warning: format not a string literal and no format arguments [-Wformat-security]
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Now that rbd_img_request_create() is called from work functions, no
need to use GFP_ATOMIC.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
While it was never a good idea to sleep in request_fn(), commit
34c6bc2c91 ("locking/mutexes: Add extra reschedule point") made it
a *bad* idea. mutex_lock() since 3.15 may reschedule *before* putting
task on the mutex wait queue, which for tasks in !TASK_RUNNING state
means block forever. request_fn() may be called with !TASK_RUNNING on
the way to schedule() in io_schedule().
Offload request handling to a workqueue, one per rbd device, to avoid
calling blocking primitives from rbd_request_fn().
Fixes: http://tracker.ceph.com/issues/8818
Cc: stable@vger.kernel.org # 3.16, needs backporting for 3.15
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Tested-by: Eric Eastman <eric0e@aol.com>
Tested-by: Greg Wilson <greg.wilson@keepertech.com>
Reviewed-by: Alex Elder <elder@linaro.org>
If we are mapping a snapshot, we must read in the parent_overlap value
of that snapshot instead of that of the base image. Not doing so may
in particular result in us returning zeros instead of user data:
# cat overlap-snap.sh
#!/bin/bash
rbd create --size 10 --image-format 2 foo
FOO_DEV=$(rbd map foo)
dd if=/dev/urandom of=$FOO_DEV bs=1M &>/dev/null
echo "Base image"
dd if=$FOO_DEV bs=1 count=16 skip=$(((4 << 20) - 8)) 2>/dev/null | xxd
rbd snap create foo@snap
rbd snap protect foo@snap
rbd clone foo@snap bar
rbd snap create bar@snap
BAR_DEV=$(rbd map bar@snap)
echo "Snapshot"
dd if=$BAR_DEV bs=1 count=16 skip=$(((4 << 20) - 8)) 2>/dev/null | xxd
rbd resize --allow-shrink --size 4 bar
echo "Snapshot after base image resize"
dd if=$BAR_DEV bs=1 count=16 skip=$(((4 << 20) - 8)) 2>/dev/null | xxd
# ./overlap-snap.sh
Base image
0000000: e781 e33b d34b 2225 6034 2845 a2e3 36ed ...;.K"%`4(E..6.
Snapshot
0000000: e781 e33b d34b 2225 6034 2845 a2e3 36ed ...;.K"%`4(E..6.
Resizing image: 100% complete...done.
Snapshot after base image resize
0000000: e781 e33b d34b 2225 0000 0000 0000 0000 ...;.K"%........
Even though bar@snap is taken with the old bar parent_overlap (8M),
reads from bar@snap beyond the new bar parent_overlap (4M) return
zeroes. Fix it.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Currently rbd_dev_v2_header_info() reads in parent info before the snap
context is read in. This is wrong, because we may need to look at the
the parent_overlap value of the snapshot instead of that of the base
image, for example when mapping a snapshot - see next commit. (When
mapping a snapshot, all we got is its name and we need the snap context
to translate that name into an id to know which parent info to look
for.)
The approach taken here is to make sure rbd_dev_v2_parent_info() is
called after the snap context has been read in. The other approach
would be to add a parent_overlap field to struct rbd_mapping and
maintain it the same way rbd_mapping::size is maintained. The reason
I chose the first approach is that the value of keeping around both
base image values and the actual mapping values is unclear to me.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
There is no sense in trying to update the mapping size before it's even
been set.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Recently discovered watch/notify problems showed that we really can't
ignore errors in anything refresh related. Alas, currently there is
not much we can do in response to those errors, except print warnings.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
rbd_dev_spec_update() has two modes of operation, with nothing in
common between them. Split it into two functions, one for each mode
and make our expectations more clear.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
spec->image_id assert doesn't buy us much and image_format is asserted
in rbd_dev_header_name() and rbd_dev_header_info() anyway.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
A wrapper around rbd_dev_v{1,2}_header_info() to reduce duplication.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Make /sys/bus/rbd/devices/<id>/parent show the entire chain of parent
images. While at it, kernel sprintf() doesn't return negative values,
casting to unsigned long long is no longer necessary and there is no
good reason to split into multiple sprintf() calls.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Free memory allocated using kmem_cache_zalloc using kmem_cache_free
rather than kfree. The helper rbd_segment_name_free does the job here.
Its position is shifted above the calling function.
The Coccinelle semantic patch that detects this change is as follows:
// <smpl>
@@
expression x,E,c;
@@
x = \(kmem_cache_alloc\|kmem_cache_zalloc\|kmem_cache_alloc_node\)(c,...)
... when != x = E
when != &x
?-kfree(x)
+kmem_cache_free(c,x)
// </smpl>
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
image_id is leaked if the parent happens to have been recorded already.
Fix it.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Switch rbd_dev_header_{un,}watch_sync() to use the new helper and fix
rbd_dev_header_unwatch_sync() to destroy watch_request structures
before queuing watch-remove message while at it. This mistake slipped
into commit b30a01f2a3 ("rbd: fix osd_request memory leak in
__rbd_dev_header_watch_sync()") and could lead to "image still in use"
errors on image removal.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
In the past, rbd_dev_header_watch_sync() used to handle both watch and
unwatch requests and was entangled and leaky. Commit b30a01f2a3
("rbd: fix osd_request memory leak in __rbd_dev_header_watch_sync()")
split it into two separate functions. This commit cleanly abstracts
the common bits, relying on the fixed rbd_obj_request_wait().
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
rbd_obj_request_wait() should cancel the underlying OSD request if
interrupted. Otherwise libceph will hold onto it indefinitely, causing
assert failures or leaking the original object request.
This also adds an rbd wrapper around ceph_osdc_cancel_request() to
match rbd_obj_request_submit() and rbd_obj_request_wait().
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
The following check in rbd_img_obj_request_submit()
rbd_dev->parent_overlap <= obj_request->img_offset
allows the fall through to the non-layered write case even if both
parent_overlap and obj_request->img_offset belong to the same RADOS
object. This leads to data corruption, because the area to the left of
parent_overlap ends up unconditionally zero-filled instead of being
populated with parent data. Suppose we want to write 1M to offset 6M
of image bar, which is a clone of foo@snap; object_size is 4M,
parent_overlap is 5M:
rbd_data.<id>.0000000000000001
---------------------|----------------------|------------
| should be copyup'ed | should be zeroed out | write ...
---------------------|----------------------|------------
4M 5M 6M
parent_overlap obj_request->img_offset
4..5M should be copyup'ed from foo, yet it is zero-filled, just like
5..6M is.
Given that the only striping mode kernel client currently supports is
chunking (i.e. stripe_unit == object_size, stripe_count == 1), round
parent_overlap up to the next object boundary for the purposes of the
overlap check.
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
rbd_open(), called every time the device is opened, calls
set_device_ro(). There's no reason to set the device read-only or
read-write every time it is opened. Just do this once during device
setup, using set_disk_ro() instead because the struct block_device
isn't available to us there.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
get_user() and set_disk_ro() may allocate memory, leading to a
potential deadlock if theye are called while a spin lock is held.
Move the acquisition and release of rbd_dev->lock from rbd_ioctl()
into rbd_ioctl_set_ro(), so it can occur between get_user() and
set_disk_ro().
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
When running the following commands:
[root@ceph0 mnt]# blockdev --setro /dev/rbd1
[root@ceph0 mnt]# blockdev --getro /dev/rbd1
0
The block setro didn't take effect, it is because
the rbd doesn't support ioctl of block driver.
This resolves:
http://tracker.ceph.com/issues/6265
Signed-off-by: Guangliang Zhao <guangliang@unitedstack.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
ida_destroy() needs to be called on module exit to release ida caches.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Each image request contains a reference count, but to date it has
not actually been used. (I think this was just an oversight.) A
recent report involving rbd failing an assertion shed light on why
and where we need to use these reference counts.
Every OSD request associated with an object request uses
rbd_osd_req_callback() as its callback function. That function will
call a helper function (dependent on the type of OSD request) that
will set the object request's "done" flag if the object request if
appropriate. If that "done" flag is set, the object request is
passed to rbd_obj_request_complete().
In rbd_obj_request_complete(), requests are processed in sequential
order. So if an object request completes before one of its
predecessors in the image request, the completion is deferred.
Otherwise, if it's a completing object's "turn" to be completed, it
is passed to rbd_img_obj_end_request(), which records the result of
the operation, accumulates transferred bytes, and so on. Next, the
successor to this request is checked and if it is marked "done",
(deferred) completion processing is performed on that request, and
so on. If the last object request in an image request is completed,
rbd_img_request_complete() is called, which (typically) destroys
the image request.
There is a race here, however. The instant an object request is
marked "done" it can be provided (by a thread handling completion of
one of its predecessor operations) to rbd_img_obj_end_request(),
which (for the last request) can then lead to the image request
getting torn down. And this can happen *before* that object has
itself entered rbd_img_obj_end_request(). As a result, once it
*does* enter that function, the image request (and even the object
request itself) may have been freed and become invalid.
All that's necessary to avoid this is to properly count references
to the image requests. We tear down an image request's object
requests all at once--only when the entire image request has
completed. So there's no need for an image request to count
references for its object requests. However, we don't want an
image request to go away until the last of its object requests
has passed through rbd_img_obj_callback(). In other words,
we don't want rbd_img_request_complete() to necessarily
result in the image request being destroyed, because it may
get called before we've finished processing on all of its
object requests.
So the fix is to add a reference to an image request for
each of its object requests. The reference can be viewed
as representing an object request that has not yet finished
its call to rbd_img_obj_callback(). That is emphasized by
getting the reference right after assigning that as the image
object's callback function. The corresponding release of that
reference is done at the end of rbd_img_obj_callback(), which
every image object request passes through exactly once.
Cc: stable@vger.kernel.org
Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com>
osd_request, along with r_request and r_reply messages attached to it
are leaked in __rbd_dev_header_watch_sync() if the requested image
doesn't exist. This is because lingering requests are special and get
an extra ref in the reply path. Fix it by unregistering linger request
on the error path and split __rbd_dev_header_watch_sync() into two
functions to make it maintainable.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Given an existing idle mapping (img1), mapping an image (img2) in
a newly created pool (pool2) fails:
$ ceph osd pool create pool1 8 8
$ rbd create --size 1000 pool1/img1
$ sudo rbd map pool1/img1
$ ceph osd pool create pool2 8 8
$ rbd create --size 1000 pool2/img2
$ sudo rbd map pool2/img2
rbd: sysfs write failed
rbd: map failed: (2) No such file or directory
This is because client instances are shared by default and we don't
request an osdmap update when bumping a ref on an existing client. The
fix is to use the mon_get_version request to see if the osdmap we have
is the latest, and block until the requested update is received if it's
not.
Fixes: http://tracker.ceph.com/issues/8184
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
In an effort to reduce fragmentation, prefix every rbd write with
a CEPH_OSD_OP_SETALLOCHINT osd op with an expected_write_size value set
to the object size (1 << order). Backwards compatibility is taken care
of on the libceph/osd side.
"The CEPH_OSD_OP_SETALLOCHINT hint is durable, in that it's enough to
do it once. The reason every rbd write is prefixed is that rbd doesn't
explicitly create objects and relies on writes creating them
implicitly, so there is no place to stick a single hint op into. To
get around that we decided to prefix every rbd write with a hint (just
like write and setattr ops, hint op will create an object implicitly if
it doesn't exist)."
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
In preparation for prefixing rbd writes with an allocation hint
introduce a num_ops parameter for rbd_osd_req_create(). The rationale
is that not every write request is a write op that needs to be prefixed
(e.g. watch op), so the num_ops logic needs to be in the callers.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Our longest osd request now contains 3 ops: copyup+hint+write.
Also, CEPH_OSD_MAX_OP value in a BUG_ON in rbd_osd_req_callback() was
hard-coded to 2. Fix it, and switch to rbd_assert while at it.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Doing rbd_obj_request_put() in rbd_img_request_fill() error paths is
not only insufficient, but also triggers an rbd_assert() in
rbd_obj_request_destroy():
Assertion failure in rbd_obj_request_destroy() at line 1867:
rbd_assert(obj_request->img_request == NULL);
rbd_img_obj_request_add() adds obj_requests to the img_request, the
opposite is rbd_img_obj_request_del(). Use it.
Fixes: http://tracker.ceph.com/issues/7327
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Commit 03507db631 ("rbd: fix buffer size for writes to images with
snapshots") moved the call to rbd_img_obj_request_add() up, making the
out_partial label bogus. Remove it.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Olivier Bonvalet reported having repeated crashes due to a failed
assertion he was hitting in rbd_img_obj_callback():
Assertion failure in rbd_img_obj_callback() at line 2165:
rbd_assert(which >= img_request->next_completion);
With a lot of help from Olivier with reproducing the problem
we were able to determine the object and image requests had
already been completed (and often freed) at the point the
assertion failed.
There was a great deal of discussion on the ceph-devel mailing list
about this. The problem only arose when there were two (or more)
object requests in an image request, and the problem was always
seen when the second request was being completed.
The problem is due to a race in the window between setting the
"done" flag on an object request and checking the image request's
next completion value. When the first object request completes, it
checks to see if its successor request is marked "done", and if
so, that request is also completed. In the process, the image
request's next_completion value is updated to reflect that both
the first and second requests are completed. By the time the
second request is able to check the next_completion value, it
has been set to a value *greater* than its own "which" value,
which caused an assertion to fail.
Fix this problem by skipping over any completion processing
unless the completing object request is the next one expected.
Test only for inequality (not >=), and eliminate the bad
assertion.
Tested-by: Olivier Bonvalet <ob@daevel.fr>
Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Pull core block IO changes from Jens Axboe:
"The major piece in here is the immutable bio_ve series from Kent, the
rest is fairly minor. It was supposed to go in last round, but
various issues pushed it to this release instead. The pull request
contains:
- Various smaller blk-mq fixes from different folks. Nothing major
here, just minor fixes and cleanups.
- Fix for a memory leak in the error path in the block ioctl code
from Christian Engelmayer.
- Header export fix from CaiZhiyong.
- Finally the immutable biovec changes from Kent Overstreet. This
enables some nice future work on making arbitrarily sized bios
possible, and splitting more efficient. Related fixes to immutable
bio_vecs:
- dm-cache immutable fixup from Mike Snitzer.
- btrfs immutable fixup from Muthu Kumar.
- bio-integrity fix from Nic Bellinger, which is also going to stable"
* 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits)
xtensa: fixup simdisk driver to work with immutable bio_vecs
block/blk-mq-cpu.c: use hotcpu_notifier()
blk-mq: for_each_* macro correctness
block: Fix memory leak in rw_copy_check_uvector() handling
bio-integrity: Fix bio_integrity_verify segment start bug
block: remove unrelated header files and export symbol
blk-mq: uses page->list incorrectly
blk-mq: use __smp_call_function_single directly
btrfs: fix missing increment of bi_remaining
Revert "block: Warn and free bio if bi_end_io is not set"
block: Warn and free bio if bi_end_io is not set
blk-mq: fix initializing request's start time
block: blk-mq: don't export blk_mq_free_queue()
block: blk-mq: make blk_sync_queue support mq
block: blk-mq: support draining mq queue
dm cache: increment bi_remaining when bi_end_io is restored
block: fixup for generic bio chaining
block: Really silence spurious compiler warnings
block: Silence spurious compiler warnings
block: Kill bio_pair_split()
...
Rename ceph_osd_request::r_{oloc,oid} to r_base_{oloc,oid} before
introducing r_target_{oloc,oid} needed for redirects.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Ilya Dryomov