[PATCH net-next v4 06/12] net/rds: wait for connections to be freed on transport unload

@@ -48,6 +48,8 @@
 /* converting this to RCU is a chore for another day.. */
 static DEFINE_SPINLOCK(rds_conn_lock);
 static unsigned long rds_conn_count;
+/* woken whenever a transport's t_conn_count drops to zero */
+static DECLARE_WAIT_QUEUE_HEAD(rds_conn_freed_waitq);
 static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
 static struct kmem_cache *rds_conn_slab;
 

@@ -341,6 +343,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 			parent->c_passive = conn;
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
+			atomic_inc(&conn->c_trans->t_conn_count);
 		}
 	} else {
 		/* Creating normal conn */

@@ -359,6 +362,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 			hlist_add_head_rcu(&conn->c_hash_node, head);
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
+			atomic_inc(&conn->c_trans->t_conn_count);
 		}
 	}
 	spin_unlock_irqrestore(&rds_conn_lock, flags);

@@ -584,6 +588,7 @@ static void rds_conn_destroy_fini(struct kref *kref)
 	struct rds_connection *conn = container_of(kref, struct rds_connection,
 						   c_refcount);
 	int npaths = (conn->c_trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
+	struct rds_transport *trans = conn->c_trans;
 	unsigned long flags;
 	int i;
 

@@ -596,7 +601,52 @@ static void rds_conn_destroy_fini(struct kref *kref)
 	spin_lock_irqsave(&rds_conn_lock, flags);
 	rds_conn_count--;
 	spin_unlock_irqrestore(&rds_conn_lock, flags);
+
+	/* only after everything the transport module owns has been
+	 * freed above may its unload proceed
+	 */
+	if (!atomic_dec_return(&trans->t_conn_count))
+		wake_up_all(&rds_conn_freed_waitq);
+}
+
+/* Wait for all of @trans's connections to be freed; the free runs
+ * asynchronously once rds_conn_destroy() has quiesced a connection.
+ * Called on transport module unload, after the transport has destroyed
+ * all of its connections.  A connection reference can be held for an
+ * application-controlled time - once incs hold one, an unread datagram
+ * pins the inc that carries it, and thus the connection - so the wait
+ * is unbounded: the
+ * frees that run after unload call into this module's text (conn_free,
+ * inc_free) and free into its slabs, so proceeding while any remain
+ * would be a use-after-free, not a leak.  Warn periodically so a stuck
+ * count is diagnosable, but never stop waiting.  This matches the
+ * historical RDS contract that teardown does not discard queued data.
+ */
+void rds_conn_wait_conns_freed(struct rds_transport *trans,
+			       void (*resweep)(void))
+{
+	unsigned long warn_interval =
+			msecs_to_jiffies(RDS_CONN_FREE_WARN_INTERVAL_MS);
+	unsigned long warn_at = jiffies + warn_interval;
+
+	while (!wait_event_timeout(rds_conn_freed_waitq,
+				   !atomic_read(&trans->t_conn_count),
+				   msecs_to_jiffies(RDS_CONN_FREE_POLL_MS))) {
+		/* A transport whose teardown is asynchronous (IB moves a
+		 * connection off its device from the shutdown work) gives
+		 * us a resweep to destroy what has arrived since.
+		 */
+		if (resweep)
+			resweep();
+		if (time_after_eq(jiffies, warn_at)) {
+			pr_warn("RDS/%s: still waiting for %d connection(s) to be freed before unload\n",
+				trans->t_name,
+				atomic_read(&trans->t_conn_count));
+			warn_at = jiffies + warn_interval;
+		}
+	}
 }
+EXPORT_SYMBOL_GPL(rds_conn_wait_conns_freed);
 
 void rds_conn_get(struct rds_connection *conn)
 {

@@ -537,7 +537,24 @@ void rds_ib_exit(void)
 	rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
 #endif
 	rds_ib_unregister_client();
+
+	/* rds_ib_dev_shutdown() only dropped the connections still
+	 * attached to a device; each moves itself to ib_nodev_conns
+	 * from its shutdown work.  Destroy what is there now and keep
+	 * sweeping the list while the wait sees connections outstanding,
+	 * so a late arrival is destroyed rather than waited on forever.
+	 */
 	rds_ib_destroy_nodev_conns();
+	rds_conn_wait_conns_freed(&rds_ib_transport,
+				  rds_ib_destroy_nodev_conns);
+
+	/* Tearing down the last connection may have dropped the final
+	 * reference on a device, deferring rds_ib_dev_free() to rds_wq.
+	 * Drain it before the module goes away; it queues nothing
+	 * further on rds_wq.
+	 */
+	flush_workqueue(rds_wq);
+
 	rds_ib_sysctl_exit();
 	rds_ib_recv_exit();
 	rds_trans_unregister(&rds_ib_transport);

@@ -165,7 +165,7 @@ void rds_ib_destroy_nodev_conns(void)
 
 	/* avoid calling conn_destroy with irqs off */
 	spin_lock_irq(&ib_nodev_conns_lock);
-	list_splice(&ib_nodev_conns, &tmp_list);
+	list_splice_init(&ib_nodev_conns, &tmp_list);
 	spin_unlock_irq(&ib_nodev_conns_lock);
 
 	list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node)

@@ -195,6 +195,8 @@ void rds_loop_exit(void)
 		WARN_ON(lc->conn->c_passive);
 		rds_conn_destroy(lc->conn);
 	}
+
+	rds_conn_wait_conns_freed(&rds_loop_transport, NULL);
 }
 
 static void rds_loop_kill_conns(struct net *net)

@@ -557,6 +557,12 @@ struct rds_transport {
 	unsigned int		t_prefer_loopback:1,
 				t_mp_capable:1;
 	unsigned int		t_type;
+	/* Connections of this transport not yet freed; freeing runs
+	 * asynchronously once rds_conn_destroy() has quiesced a
+	 * connection, so transport module unload has to wait for this
+	 * to reach zero (rds_conn_wait_conns_freed()).
+	 */
+	atomic_t		t_conn_count;
 
 	int (*laddr_check)(struct net *net, const struct in6_addr *addr,
 			   __u32 scope_id);

@@ -839,6 +845,14 @@ static inline bool rds_conn_get_unless_zero(struct rds_connection *conn)
 {
 	return kref_get_unless_zero(&conn->c_refcount);
 }
+
+/* transport unload waits for its connections to be freed, polling at
+ * the first interval and warning at the second
+ */
+#define RDS_CONN_FREE_POLL_MS		100
+#define RDS_CONN_FREE_WARN_INTERVAL_MS	10000
+void rds_conn_wait_conns_freed(struct rds_transport *trans,
+			       void (*resweep)(void));
 void rds_conn_drop(struct rds_connection *conn);
 void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy);
 void rds_conn_connect_if_down(struct rds_connection *conn);

@@ -805,6 +805,7 @@ static void rds_tcp_exit(void)
 #endif
 	unregister_pernet_device(&rds_tcp_net_ops);
 	rds_tcp_destroy_conns();
+	rds_conn_wait_conns_freed(&rds_tcp_transport, NULL);
 	rds_trans_unregister(&rds_tcp_transport);
 	rds_tcp_recv_exit();
 	kmem_cache_destroy(rds_tcp_conn_slab);