From 4cf7e2a3053a4527cba9e46539f353036999cab2 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 23 Jul 2024 18:07:59 +0200 Subject: [PATCH] rbd: don't assume RBD_LOCK_STATE_LOCKED for exclusive mappings commit 2237ceb71f89837ac47c5dce2aaa2c2b3a337a3c upstream. Every time a watch is reestablished after getting lost, we need to update the cookie which involves quiescing exclusive lock. For this, we transition from RBD_LOCK_STATE_LOCKED to RBD_LOCK_STATE_QUIESCING roughly for the duration of rbd_reacquire_lock() call. If the mapping is exclusive and I/O happens to arrive in this time window, it's failed with EROFS (later translated to EIO) based on the wrong assumption in rbd_img_exclusive_lock() -- "lock got released?" check there stopped making sense with commit a2b1da09793d ("rbd: lock should be quiesced on reacquire"). To make it worse, any such I/O is added to the acquiring list before EROFS is returned and this sets up for violating rbd_lock_del_request() precondition that the request is either on the running list or not on any list at all -- see commit ded080c86b3f ("rbd: don't move requests to the running list on errors"). rbd_lock_del_request() ends up processing these requests as if they were on the running list which screws up quiescing_wait completion counter and ultimately leads to rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); being triggered on the next watch error. Cc: stable@vger.kernel.org # 06ef84c4e9c4: rbd: rename RBD_LOCK_STATE_RELEASING and releasing_wait 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 --- drivers/block/rbd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index cbaa9ceb1dd1..f617fc3a1102 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3459,6 +3459,7 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req) lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); if (!list_empty(&img_req->lock_item)) { + rbd_assert(!list_empty(&rbd_dev->running_list)); list_del_init(&img_req->lock_item); need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING && list_empty(&rbd_dev->running_list)); @@ -3478,11 +3479,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) if (rbd_lock_add_request(img_req)) return 1; - if (rbd_dev->opts->exclusive) { - WARN_ON(1); /* lock got released? */ - return -EROFS; - } - /* * Note the use of mod_delayed_work() in rbd_acquire_lock() * and cancel_delayed_work() in wake_lock_waiters(). @@ -4603,6 +4599,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "failed to update lock cookie: %d", ret); + if (rbd_dev->opts->exclusive) + rbd_warn(rbd_dev, + "temporarily releasing lock on exclusive mapping"); + /* * Lock cookie cannot be updated on older OSDs, so do * a manual release and queue an acquire.