5.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ilya Dryomov idryomov@gmail.com
[ Upstream commit 9d01e07fd1bfb4daae156ab528aa196f5ac2b2bc ]
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 idryomov@gmail.com Reviewed-by: Dongsheng Yang dongsheng.yang@easystack.cn Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/rbd.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 60d3a143ff450..95cbd5790ed60 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3740,7 +3740,7 @@ 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); @@ -3944,7 +3944,7 @@ 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); }
@@ -3996,8 +3996,10 @@ 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++) { @@ -4041,8 +4043,12 @@ 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); @@ -4145,11 +4151,8 @@ 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); @@ -6699,12 +6702,11 @@ 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