[PATCH 3/5] ceph: add wait_list_lock for wait-list serialization
From: Xiubo Li via B4 Relay
Date: Mon Jul 13 2026 - 05:51:23 EST
From: Xiubo Li <xiubo.li@xxxxxxxxx>
Add a dedicated spinlock to protect the waiting_for_map and
s_waiting lists, which are currently serialized by mdsc->mutex.
This is a preparatory step for removing mdsc->mutex from the
kick_requests() path: xa_for_each() is internally locked and the
per-request filter checks are lockless, so only list_del_init()
needs external protection.
Signed-off-by: Xiubo Li <xiubo.li@xxxxxxxxx>
---
fs/ceph/mds_client.c | 18 +++++++++++++++++-
fs/ceph/mds_client.h | 3 +++
2 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 909f909b64ed..6f9049148721 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3609,7 +3609,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
doutc(cl, "no mdsmap, waiting for map\n");
trace_ceph_mdsc_suspend_request(mdsc, session, req,
ceph_mdsc_suspend_reason_no_mdsmap);
+ spin_lock(&mdsc->wait_list_lock);
list_add(&req->r_wait, &mdsc->waiting_for_map);
+ spin_unlock(&mdsc->wait_list_lock);
return;
}
if (!(mdsc->fsc->mount_options->flags &
@@ -3632,7 +3634,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
doutc(cl, "no mds or not active, waiting for map\n");
trace_ceph_mdsc_suspend_request(mdsc, session, req,
ceph_mdsc_suspend_reason_no_active_mds);
+ spin_lock(&mdsc->wait_list_lock);
list_add(&req->r_wait, &mdsc->waiting_for_map);
+ spin_unlock(&mdsc->wait_list_lock);
return;
}
@@ -3680,9 +3684,12 @@ static void __do_request(struct ceph_mds_client *mdsc,
if (ceph_test_mount_opt(mdsc->fsc, CLEANRECOVER)) {
trace_ceph_mdsc_suspend_request(mdsc, session, req,
ceph_mdsc_suspend_reason_rejected);
+ spin_lock(&mdsc->wait_list_lock);
list_add(&req->r_wait, &mdsc->waiting_for_map);
- } else
+ spin_unlock(&mdsc->wait_list_lock);
+ } else {
err = -EACCES;
+ }
goto out_session;
}
@@ -3697,7 +3704,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
}
trace_ceph_mdsc_suspend_request(mdsc, session, req,
ceph_mdsc_suspend_reason_session);
+ spin_lock(&mdsc->wait_list_lock);
list_add(&req->r_wait, &session->s_waiting);
+ spin_unlock(&mdsc->wait_list_lock);
goto out_session;
}
@@ -3790,7 +3799,9 @@ static void __wake_requests(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req;
LIST_HEAD(tmp_list);
+ spin_lock(&mdsc->wait_list_lock);
list_splice_init(head, &tmp_list);
+ spin_unlock(&mdsc->wait_list_lock);
while (!list_empty(&tmp_list)) {
req = list_entry(tmp_list.next,
@@ -3823,7 +3834,9 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
if (req->r_session &&
req->r_session->s_mds == mds) {
doutc(cl, " kicking tid %llu\n", req->r_tid);
+ spin_lock(&mdsc->wait_list_lock);
list_del_init(&req->r_wait);
+ spin_unlock(&mdsc->wait_list_lock);
trace_ceph_mdsc_resume_request(mdsc, req);
__do_request(mdsc, req);
}
@@ -6258,6 +6271,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
mdsc->snap_realms = RB_ROOT;
INIT_LIST_HEAD(&mdsc->snap_empty);
spin_lock_init(&mdsc->snap_empty_lock);
+ spin_lock_init(&mdsc->wait_list_lock);
xa_init(&mdsc->request_tree);
INIT_DELAYED_WORK(&mdsc->delayed_work, delayed_work);
mdsc->last_renew_caps = jiffies;
@@ -6340,7 +6354,9 @@ static void wait_requests(struct ceph_mds_client *mdsc)
mutex_lock(&mdsc->mutex);
while ((req = __get_oldest_req(mdsc))) {
doutc(cl, "timed out on tid %llu\n", req->r_tid);
+ spin_lock(&mdsc->wait_list_lock);
list_del_init(&req->r_wait);
+ spin_unlock(&mdsc->wait_list_lock);
__unregister_request(mdsc, req);
}
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 00ca993ed583..cd5dacfb42bd 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -529,6 +529,9 @@ struct ceph_mds_client {
struct list_head snap_empty;
int num_snap_realms;
spinlock_t snap_empty_lock; /* protect snap_empty */
+ spinlock_t wait_list_lock; /* protect waiting_for_map
+ * and s_waiting lists
+ */
u64 last_tid; /* most recent mds request */
atomic64_t oldest_tid; /* oldest incomplete mds request,
--
2.53.0