Kernel/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2025-01-03 19:55:31 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Two patches to improve RBD exclusive lock interaction with

Browse Source 
osd_request_timeout option and another fix to reduce the potential for
 erroneous blocklisting -- this time in CephFS.  All going to stable.
 -----BEGIN PGP SIGNATURE-----
 
 iQFHBAABCAAxFiEEydHwtzie9C7TfviiSn/eOAIR84sFAmTNFFUTHGlkcnlvbW92
 QGdtYWlsLmNvbQAKCRBKf944AhHzi5I8B/9a8C5ed0XfTadHcHX5VQsY3b//4rgp
 0VYkQbjYnSCwrYRIPsvnL8LeLHzbcPGLpFAQXg7uUlmJ5dpaOz303hKmKt5GdyOR
 qvWka3K4zeG177b6yc1srqs0cEsCLpQrn+krnvOl5v87QdFsCP/bsJMOrJ9mlhdM
 9GjkjDRn6jvNyOLGbn3kIvwCRF9NH6/nHzjBcTUzvS8fBUye02o9C1H6ZQ7sYjKH
 sJnmQCNCFHEqdaVjDZ7mw/doIrAbmTV6sgusuPjiF5bHILzX4oWG4UJmRpHFV//S
 JPQgMp2DNjP8tW9aCVLVVVV5t5AKBr84etF59DaFNflk27U3COJWkE0a
 =gw7n
 -----END PGP SIGNATURE-----

Merge tag 'ceph-for-6.5-rc5' of https://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "Two patches to improve RBD exclusive lock interaction with
  osd_request_timeout option and another fix to reduce the potential for
  erroneous blocklisting -- this time in CephFS. All going to stable"

* tag 'ceph-for-6.5-rc5' of https://github.com/ceph/ceph-client:
  libceph: fix potential hang in ceph_osdc_notify()
  rbd: prevent busy loop when requesting exclusive lock
  ceph: defer stopping mdsc delayed_work
This commit is contained in:
Linus Torvalds 2023-08-04 11:29:38 -07:00
commit 4593f3c2c6
5 changed files with 46 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
drivers/block/rbd.c
View File

@ -3675,7 +3675,7 @@ static int rbd_lock(struct rbd_device *rbd_dev)
ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
RBD_LOCK_NAME, CEPH_CLS_LOCK_EXCLUSIVE, cookie,
RBD_LOCK_TAG, "", 0);
if (ret)
if (ret && ret != -EEXIST)
return ret;
__rbd_lock(rbd_dev, cookie);
@ -3878,7 +3878,7 @@ static struct ceph_locker *get_lock_owner_info(struct rbd_device *rbd_dev)
&rbd_dev->header_oloc, RBD_LOCK_NAME,
&lock_type, &lock_tag, &lockers, &num_lockers);
if (ret) {
rbd_warn(rbd_dev, "failed to retrieve lockers: %d", ret);
rbd_warn(rbd_dev, "failed to get header lockers: %d", ret);
return ERR_PTR(ret);
}
@ -3940,8 +3940,10 @@ static int find_watcher(struct rbd_device *rbd_dev,
ret = ceph_osdc_list_watchers(osdc, &rbd_dev->header_oid,
&rbd_dev->header_oloc, &watchers,
&num_watchers);
if (ret)
if (ret) {
rbd_warn(rbd_dev, "failed to get watchers: %d", ret);
return ret;
}
sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie);
for (i = 0; i < num_watchers; i++) {
@ -3985,8 +3987,12 @@ static int rbd_try_lock(struct rbd_device *rbd_dev)
locker = refreshed_locker = NULL;
ret = rbd_lock(rbd_dev);
if (ret != -EBUSY)
if (!ret)
goto out;
if (ret != -EBUSY) {
rbd_warn(rbd_dev, "failed to lock header: %d", ret);
goto out;
}
/* determine if the current lock holder is still alive */
locker = get_lock_owner_info(rbd_dev);
@ -4089,11 +4095,8 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev)
ret = rbd_try_lock(rbd_dev);
if (ret < 0) {
rbd_warn(rbd_dev, "failed to lock header: %d", ret);
if (ret == -EBLOCKLISTED)
goto out;
ret = 1; /* request lock anyway */
rbd_warn(rbd_dev, "failed to acquire lock: %d", ret);
goto out;
}
if (ret > 0) {
up_write(&rbd_dev->lock_rwsem);
@ -6627,12 +6630,11 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
cancel_delayed_work_sync(&rbd_dev->lock_dwork);
if (!ret)
ret = -ETIMEDOUT;
}
if (ret) {
rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret);
return ret;
rbd_warn(rbd_dev, "failed to acquire lock: %ld", ret);
}
if (ret)
return ret;
/*
* The lock may have been released by now, unless automatic lock

4
fs/ceph/mds_client.c
View File

@ -4764,7 +4764,7 @@ static void delayed_work(struct work_struct *work)
dout("mdsc delayed_work\n");
if (mdsc->stopping)
if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED)
return;
mutex_lock(&mdsc->mutex);
@ -4943,7 +4943,7 @@ void send_flush_mdlog(struct ceph_mds_session *s)
void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
{
dout("pre_umount\n");
mdsc->stopping = 1;
mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN;
ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true);
ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false);

5
fs/ceph/mds_client.h
View File

@ -380,6 +380,11 @@ struct cap_wait {
int want;
};
enum {
CEPH_MDSC_STOPPING_BEGIN = 1,
CEPH_MDSC_STOPPING_FLUSHED = 2,
};
/*
* mds client state
*/

10
fs/ceph/super.c
View File

@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s)
ceph_mdsc_pre_umount(fsc->mdsc);
flush_fs_workqueues(fsc);
/*
* Though the kill_anon_super() will finally trigger the
* sync_filesystem() anyway, we still need to do it here
* and then bump the stage of shutdown to stop the work
* queue as earlier as possible.
*/
sync_filesystem(s);
fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
kill_anon_super(s);
fsc->client->extra_mon_dispatch = NULL;

20
net/ceph/osd_client.c
View File

@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq)
int ret;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
ret = wait_for_completion_killable(&lreq->reg_commit_wait);
return ret ?: lreq->reg_commit_error;
}
static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq,
unsigned long timeout)
{
int ret;
long left;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
return ret ?: lreq->notify_finish_error;
left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait,
ceph_timeout_jiffies(timeout));
if (left <= 0)
left = left ?: -ETIMEDOUT;
else
left = lreq->notify_finish_error; /* completed */
return left;
}
/*
@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
linger_submit(lreq);
ret = linger_reg_commit_wait(lreq);
if (!ret)
ret = linger_notify_finish_wait(lreq);
ret = linger_notify_finish_wait(lreq,
msecs_to_jiffies(2 * timeout * MSEC_PER_SEC));
else
dout("lreq %p failed to initiate notify %d\n", lreq, ret);