This is a note to let you know that I've just added the patch titled
rbd: don't move requests to the running list on errors
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rbd-don-t-move-requests-to-the-running-list-on-errors.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From ded080c86b3f99683774af0441a58fc2e3d60cae Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@xxxxxxxxx>
Date: Wed, 17 Jan 2024 18:59:44 +0100
Subject: rbd: don't move requests to the running list on errors
From: Ilya Dryomov <idryomov@xxxxxxxxx>
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@xxxxxxxxxxxxxxx
Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code")
Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxx>
Reviewed-by: Dongsheng Yang <dongsheng.yang@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/block/rbd.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3453,14 +3453,15 @@ static bool rbd_lock_add_request(struct
static void rbd_lock_del_request(struct rbd_img_request *img_req)
{
struct rbd_device *rbd_dev = img_req->rbd_dev;
- bool need_wakeup;
+ bool need_wakeup = false;
lockdep_assert_held(&rbd_dev->lock_rwsem);
spin_lock(&rbd_dev->lock_lists_lock);
- rbd_assert(!list_empty(&img_req->lock_item));
- list_del_init(&img_req->lock_item);
- need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
- list_empty(&rbd_dev->running_list));
+ if (!list_empty(&img_req->lock_item)) {
+ list_del_init(&img_req->lock_item);
+ need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+ list_empty(&rbd_dev->running_list));
+ }
spin_unlock(&rbd_dev->lock_lists_lock);
if (need_wakeup)
complete(&rbd_dev->releasing_wait);
@@ -3843,14 +3844,19 @@ static void wake_lock_waiters(struct rbd
return;
}
- list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+ while (!list_empty(&rbd_dev->acquiring_list)) {
+ img_req = list_first_entry(&rbd_dev->acquiring_list,
+ struct rbd_img_request, lock_item);
mutex_lock(&img_req->state_mutex);
rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+ if (!result)
+ list_move_tail(&img_req->lock_item,
+ &rbd_dev->running_list);
+ else
+ list_del_init(&img_req->lock_item);
rbd_img_schedule(img_req, result);
mutex_unlock(&img_req->state_mutex);
}
-
- list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
}
static bool locker_equal(const struct ceph_locker *lhs,
Patches currently in stable-queue which might be from idryomov@xxxxxxxxx are
queue-6.1/rbd-don-t-move-requests-to-the-running-list-on-errors.patch
