[PATCH v6 3/5] ceph: add wait_list_lock for wait-list serialization

[Xiubo Li via B4 Relay <devnull+xiubo.li.clyso.com@kernel.org>]

From: Xiubo Li <xiubo.li@clyso.com>

The per-MDS session wait list and the global waiting-for-map list
are currently serialized by mdsc->mutex, even though the list
operations themselves don't need the mutex's broader protection.
Introduce a dedicated spinlock to guard these lists so that
waking and kicking waiters can run outside the mutex.

Reviewed-by: Viacheslav Dubeyko <slava@dubeyko.com>
Signed-off-by: Xiubo Li <xiubo.li@clyso.com>
---
 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 fdaf6f56ecd3..5983ae6e3085 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3689,7 +3689,9 @@ 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 &
@@ -3712,7 +3714,9 @@ 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;
 	}
 
@@ -3760,9 +3764,12 @@ 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;
 		}
 
@@ -3777,7 +3784,9 @@ 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;
 	}
 
@@ -3870,7 +3879,9 @@ 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,
@@ -3903,7 +3914,9 @@ 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);
 		}
@@ -6365,6 +6378,7 @@ 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;
@@ -6447,7 +6461,9 @@ 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 baba5dcf0def..0ea144ba4c7d 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -531,6 +531,9 @@ 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 */
 	u64                    oldest_tid;    /* oldest incomplete mds request,

-- 
2.53.0