kernel/net/ceph/osd_client.c, branch linux-rolling-lts

libceph: make calc_target() set t->paused, not just clear it

2026-01-17T15:35:15Z

commit c0fe2994f9a9d0a2ec9e42441ea5ba74b6a16176 upstream. Currently calc_target() clears t->paused if the request shouldn't be paused anymore, but doesn't ever set t->paused even though it's able to determine when the request should be paused. Setting t->paused is left to __submit_request() which is fine for regular requests but doesn't work for linger requests -- since __submit_request() doesn't operate on linger requests, there is nowhere for lreq->t.paused to be set. One consequence of this is that watches don't get reestablished on paused -> unpaused transitions in cases where requests have been paused long enough for the (paused) unwatch request to time out and for the subsequent (re)watch request to enter the paused state. On top of the watch not getting reestablished, rbd_reregister_watch() gets stuck with rbd_dev->watch_mutex held: rbd_register_watch __rbd_register_watch ceph_osdc_watch linger_reg_commit_wait It's waiting for lreq->reg_commit_wait to be completed, but for that to happen the respective request needs to end up on need_resend_linger list and be kicked when requests are unpaused. There is no chance for that if the request in question is never marked paused in the first place. The fact that rbd_dev->watch_mutex remains taken out forever then prevents the image from getting unmapped -- "rbd unmap" would inevitably hang in D state on an attempt to grab the mutex. Cc: stable@vger.kernel.org Reported-by: Raphael Zimmer Signed-off-by: Ilya Dryomov Reviewed-by: Viacheslav Dubeyko Signed-off-by: Greg Kroah-Hartman

libceph: reset sparse-read state in osd_fault()

2026-01-17T15:35:15Z

commit 11194b416ef95012c2cfe5f546d71af07b639e93 upstream. When a fault occurs, the connection is abandoned, reestablished, and any pending operations are retried. The OSD client tracks the progress of a sparse-read reply using a separate state machine, largely independent of the messenger's state. If a connection is lost mid-payload or the sparse-read state machine returns an error, the sparse-read state is not reset. The OSD client will then interpret the beginning of a new reply as the continuation of the old one. If this makes the sparse-read machinery enter a failure state, it may never recover, producing loops like: libceph: [0] got 0 extents libceph: data len 142248331 != extent len 0 libceph: osd0 (1)...:6801 socket error on read libceph: data len 142248331 != extent len 0 libceph: osd0 (1)...:6801 socket error on read Therefore, reset the sparse-read state in osd_fault(), ensuring retries start from a clean state. Cc: stable@vger.kernel.org Fixes: f628d7999727 ("libceph: add sparse read support to OSD client") Signed-off-by: Sam Edwards Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman

ceph: Remove osd_client deadcode

2025-04-03T19:35:32Z

osd_req_op_extent_osd_data_pagelist() was added in 2013 as part of commit a4ce40a9a7c1 ("libceph: combine initializing and setting osd data") but never used. The last use of osd_req_op_cls_request_data_pagelist() was removed in 2017's commit ecd4a68a26a2 ("rbd: switch rbd_obj_method_sync() to ceph_osdc_call()") Remove them. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov

ceph: allocate sparse_ext map only for sparse reads

2024-12-16T22:25:44Z

If mounted with sparseread option, ceph_direct_read_write() ends up making an unnecessarily allocation for O_DIRECT writes. Fixes: 03bc06c7b0bd ("ceph: add new mount option to enable sparse reads") Signed-off-by: Ilya Dryomov Reviewed-by: Alex Markuze

libceph: Remove unused ceph_osdc_watch_check

2024-11-18T16:34:35Z

ceph_osdc_watch_check() has been unused since it was added in commit b07d3c4bd727 ("libceph: support for checking on status of watch") Remove it. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov

libceph: just wait for more data to be available on the socket

2024-02-07T13:43:29Z

A short read may occur while reading the message footer from the socket. Later, when the socket is ready for another read, the messenger invokes all read_partial_*() handlers, including read_partial_sparse_msg_data(). The expectation is that read_partial_sparse_msg_data() would bail, allowing the messenger to invoke read_partial() for the footer and pick up where it left off. However read_partial_sparse_msg_data() violates that and ends up calling into the state machine in the OSD client. The sparse-read state machine assumes that it's a new op and interprets some piece of the footer as the sparse-read header and returns bogus extents/data length, etc. To determine whether read_partial_sparse_msg_data() should bail, let's reuse cursor->total_resid. Because once it reaches to zero that means all the extents and data have been successfully received in last read, else it could break out when partially reading any of the extents and data. And then osd_sparse_read() could continue where it left off. [ idryomov: changelog ] Link: https://tracker.ceph.com/issues/63586 Fixes: d396f89db39a ("libceph: add sparse read support to msgr1") Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov

libceph: fail sparse-read if the data length doesn't match

2024-02-07T13:43:29Z

Once this happens that means there have bugs. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov

libceph: remove MAX_EXTENTS check for sparse reads

2024-01-15T14:40:50Z

There is no any limit for the extent array size and it's possible that when reading with a large size contents the total number of extents will exceed 4096. Then the messager will fail by reseting the connection and keeps resending the inflight IOs infinitely. [ idryomov: adjust error message ] Link: https://tracker.ceph.com/issues/62081 Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov

libceph: allow ceph_osdc_new_request to accept a multi-op read

2023-08-24T09:24:35Z

Currently we have some special-casing for multi-op writes, but in the case of a read, we can't really handle it. All of the current multi-op callers call it with CEPH_OSD_FLAG_WRITE set. Have ceph_osdc_new_request check for CEPH_OSD_FLAG_READ and if it's set, allocate multiple reply ops instead of multiple request ops. If neither flag is set, return -EINVAL. Signed-off-by: Jeff Layton Reviewed-by: Xiubo Li Reviewed-and-tested-by: Luís Henriques Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov

libceph: add CEPH_OSD_OP_ASSERT_VER support

2023-08-24T09:24:35Z

...and record the user_version in the reply in a new field in ceph_osd_request, so we can populate the assert_ver appropriately. Shuffle the fields a bit too so that the new field fits in an existing hole on x86_64. Signed-off-by: Jeff Layton Reviewed-by: Xiubo Li Reviewed-and-tested-by: Luís Henriques Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov