kernel/linux.git/drivers/block/rbd.c, branch v6.1.87

rbd: don't move requests to the running list on errors

2024-02-01T00:17:07+00:00

commit ded080c86b3f99683774af0441a58fc2e3d60cae upstream. The running list is supposed to contain requests that are pinning the exclusive lock, i.e. those that must be flushed before exclusive lock is released. When wake_lock_waiters() is called to handle an error, requests on the acquiring list are failed with that error and no flushing takes place. Briefly moving them to the running list is not only pointless but also harmful: if exclusive lock gets acquired before all of their state machines are scheduled and go through rbd_lock_del_request(), we trigger rbd_assert(list_empty(&rbd_dev->running_list)); in rbd_try_acquire_lock(). Cc: stable@vger.kernel.org Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code") Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman

rbd: take header_rwsem in rbd_dev_refresh() only when updating

2023-10-10T20:00:37+00:00

commit 0b207d02bd9ab8dcc31b262ca9f60dbc1822500d upstream. rbd_dev_refresh() has been holding header_rwsem across header and parent info read-in unnecessarily for ages. With commit 870611e4877e ("rbd: get snapshot context after exclusive lock is ensured to be held"), the potential for deadlocks became much more real owning to a) header_rwsem now nesting inside lock_rwsem and b) rw_semaphores not allowing new readers after a writer is registered. For example, assuming that I/O request 1, I/O request 2 and header read-in request all target the same OSD: 1. I/O request 1 comes in and gets submitted 2. watch error occurs 3. rbd_watch_errcb() takes lock_rwsem for write, clears owner_cid and releases lock_rwsem 4. after reestablishing the watch, rbd_reregister_watch() calls rbd_dev_refresh() which takes header_rwsem for write and submits a header read-in request 5. I/O request 2 comes in: after taking lock_rwsem for read in __rbd_img_handle_request(), it blocks trying to take header_rwsem for read in rbd_img_object_requests() 6. another watch error occurs 7. rbd_watch_errcb() blocks trying to take lock_rwsem for write 8. I/O request 1 completion is received by the messenger but can't be processed because lock_rwsem won't be granted anymore 9. header read-in request completion can't be received, let alone processed, because the messenger is stranded Change rbd_dev_refresh() to take header_rwsem only for actually updating rbd_dev->header. Header and parent info read-in don't need any locking. Cc: stable@vger.kernel.org # 0b035401c570: rbd: move rbd_dev_refresh() definition Cc: stable@vger.kernel.org # 510a7330c82a: rbd: decouple header read-in from updating rbd_dev->header Cc: stable@vger.kernel.org # c10311776f0a: rbd: decouple parent info read-in from updating rbd_dev Cc: stable@vger.kernel.org Fixes: 870611e4877e ("rbd: get snapshot context after exclusive lock is ensured to be held") Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin

rbd: decouple parent info read-in from updating rbd_dev

2023-10-10T20:00:37+00:00

commit c10311776f0a8ddea2276df96e255625b07045a8 upstream. Unlike header read-in, parent info read-in is already decoupled in get_parent_info(), but it's buried in rbd_dev_v2_parent_info() along with the processing logic. Separate the initial read-in and update read-in logic into rbd_dev_setup_parent() and rbd_dev_update_parent() respectively and have rbd_dev_v2_parent_info() just populate struct parent_image_info (i.e. what get_parent_info() did). Some existing QoI issues, like flatten of a standalone clone being disregarded on refresh, remain. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin

rbd: decouple header read-in from updating rbd_dev->header

2023-10-10T20:00:37+00:00

commit 510a7330c82a7754d5df0117a8589e8a539067c7 upstream. Make rbd_dev_header_info() populate a passed struct rbd_image_header instead of rbd_dev->header and introduce rbd_dev_update_header() for updating mutable fields in rbd_dev->header upon refresh. The initial read-in of both mutable and immutable fields in rbd_dev_image_probe() passes in rbd_dev->header so no update step is required there. rbd_init_layout() is now called directly from rbd_dev_image_probe() instead of individually in format 1 and format 2 implementations. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin

rbd: move rbd_dev_refresh() definition

2023-10-10T20:00:37+00:00

commit 0b035401c57021fc6c300272cbb1c5a889d4fe45 upstream. Move rbd_dev_refresh() definition further down to avoid having to move struct parent_image_info definition in the next commit. This spares some forward declarations too. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang [idryomov@gmail.com: backport to 5.10-6.1: context] Signed-off-by: Sasha Levin

rbd: prevent busy loop when requesting exclusive lock

2023-08-11T10:08:21+00:00

commit 9d01e07fd1bfb4daae156ab528aa196f5ac2b2bc upstream. Due to rbd_try_acquire_lock() effectively swallowing all but EBLOCKLISTED error from rbd_try_lock() ("request lock anyway") and rbd_request_lock() returning ETIMEDOUT error not only for an actual notify timeout but also when the lock owner doesn't respond, a busy loop inside of rbd_acquire_lock() between rbd_try_acquire_lock() and rbd_request_lock() is possible. Requesting the lock on EBUSY error (returned by get_lock_owner_info() if an incompatible lock or invalid lock owner is detected) makes very little sense. The same goes for ETIMEDOUT error (might pop up pretty much anywhere if osd_request_timeout option is set) and many others. Just fail I/O requests on rbd_dev->acquiring_list immediately on any error from rbd_try_lock(). Cc: stable@vger.kernel.org # 588159009d5b: rbd: retrieve and check lock owner twice before blocklisting Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman

rbd: retrieve and check lock owner twice before blocklisting

2023-08-03T08:24:17+00:00

commit 588159009d5b7a09c3e5904cffddbe4a4e170301 upstream. An attempt to acquire exclusive lock can race with the current lock owner closing the image: 1. lock is held by client123, rbd_lock() returns -EBUSY 2. get_lock_owner_info() returns client123 instance details 3. client123 closes the image, lock is released 4. find_watcher() returns 0 as there is no matching watcher anymore 5. client123 instance gets erroneously blocklisted Particularly impacted is mirror snapshot scheduler in snapshot-based mirroring since it happens to open and close images a lot (images are opened only for as long as it takes to take the next mirror snapshot, the same client instance is used for all images). To reduce the potential for erroneous blocklisting, retrieve the lock owner again after find_watcher() returns 0. If it's still there, make sure it matches the previously detected lock owner. Cc: stable@vger.kernel.org # f38cb9d9c204: rbd: make get_lock_owner_info() return a single locker or NULL Cc: stable@vger.kernel.org # 8ff2c64c9765: rbd: harden get_lock_owner_info() a bit Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman

rbd: harden get_lock_owner_info() a bit

2023-08-03T08:24:17+00:00

commit 8ff2c64c9765446c3cef804fb99da04916603e27 upstream. - we want the exclusive lock type, so test for it directly - use sscanf() to actually parse the lock cookie and avoid admitting invalid handles - bail if locker has a blank address Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman

rbd: make get_lock_owner_info() return a single locker or NULL

2023-08-03T08:24:17+00:00

commit f38cb9d9c2045dad16eead4a2e1aedfddd94603b upstream. Make the "num_lockers can be only 0 or 1" assumption explicit and simplify the API by getting rid of output parameters in preparation for calling get_lock_owner_info() twice before blocklisting. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman

rbd: get snapshot context after exclusive lock is ensured to be held

2023-06-14T09:15:28+00:00

commit 870611e4877eff1e8413c3fb92a585e45d5291f6 upstream. Move capturing the snapshot context into the image request state machine, after exclusive lock is ensured to be held for the duration of dealing with the image request. This is needed to ensure correctness of fast-diff states (OBJECT_EXISTS vs OBJECT_EXISTS_CLEAN) and object deltas computed based off of them. Otherwise the object map that is forked for the snapshot isn't guaranteed to accurately reflect the contents of the snapshot when the snapshot is taken under I/O. This breaks differential backup and snapshot-based mirroring use cases with fast-diff enabled: since some object deltas may be incomplete, the destination image may get corrupted. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61472 Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman