scsi: iscsi: Perform connection failure entirely in kernel space

Connection failure processing depends on a daemon being present to (at
least) stop the connection and start recovery.  This is a problem on a
multipath scenario, where if the daemon failed for whatever reason, the
SCSI path is never marked as down, multipath won't perform the failover and
IO to the device will be forever waiting for that connection to come back.

This patch performs the connection failure entirely inside the kernel.
This way, the failover can happen and pending IO can continue even if the
daemon is dead. Once the daemon comes alive again, it can execute recovery
procedures if applicable.

Cc: Mike Christie <mchristi@redhat.com>
Cc: Lee Duncan <LDuncan@suse.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20200125061925.191601-1-krisman@collabora.com
Co-developed-by: Dave Clausen <dclausen@google.com>
Co-developed-by: Nick Black <nlb@google.com>
Co-developed-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Co-developed-by: Anatol Pomazau <anatol@google.com>
Co-developed-by: Tahsin Erdogan <tahsin@google.com>
Co-developed-by: Frank Mayhar <fmayhar@google.com>
Co-developed-by: Junho Ryu <jayr@google.com>
Co-developed-by: Khazhismel Kumykov <khazhy@google.com>
Reviewed-by: Reviewed-by: Khazhismel Kumykov <khazhy@google.com>
Co-developed-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Bharath Ravi <rbharath@google.com>
Signed-off-by: Dave Clausen <dclausen@google.com>
Signed-off-by: Nick Black <nlb@google.com>
Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Anatol Pomazau <anatol@google.com>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Signed-off-by: Frank Mayhar <fmayhar@google.com>
Signed-off-by: Junho Ryu <jayr@google.com>
Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 68 insertions, 0 deletions

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index dfc726fa34e3..f3f0ecdb09a2 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -86,6 +86,12 @@ struct iscsi_internal {
 	struct transport_container session_cont;
 };
 
+/* Worker to perform connection failure on unresponsive connections
+ * completely in kernel space.
+ */
+static void stop_conn_work_fn(struct work_struct *work);
+static DECLARE_WORK(stop_conn_work, stop_conn_work_fn);
+
 static atomic_t iscsi_session_nr; /* sysfs session id for next new session */
 static struct workqueue_struct *iscsi_eh_timer_workq;
 
@@ -1611,6 +1617,7 @@ static DEFINE_MUTEX(rx_queue_mutex);
 static LIST_HEAD(sesslist);
 static DEFINE_SPINLOCK(sesslock);
 static LIST_HEAD(connlist);
+static LIST_HEAD(connlist_err);
 static DEFINE_SPINLOCK(connlock);
 
 static uint32_t iscsi_conn_get_sid(struct iscsi_cls_conn *conn)
@@ -2254,6 +2261,7 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid)
 
 	mutex_init(&conn->ep_mutex);
 	INIT_LIST_HEAD(&conn->conn_list);
+	INIT_LIST_HEAD(&conn->conn_list_err);
 	conn->transport = transport;
 	conn->cid = cid;
 
@@ -2307,6 +2315,7 @@ int iscsi_destroy_conn(struct iscsi_cls_conn *conn)
 
 	spin_lock_irqsave(&connlock, flags);
 	list_del(&conn->conn_list);
+	list_del(&conn->conn_list_err);
 	spin_unlock_irqrestore(&connlock, flags);
 
 	transport_unregister_device(&conn->dev);
@@ -2421,6 +2430,51 @@ int iscsi_offload_mesg(struct Scsi_Host *shost,
 }
 EXPORT_SYMBOL_GPL(iscsi_offload_mesg);
 
+static void stop_conn_work_fn(struct work_struct *work)
+{
+	struct iscsi_cls_conn *conn, *tmp;
+	unsigned long flags;
+	LIST_HEAD(recovery_list);
+
+	spin_lock_irqsave(&connlock, flags);
+	if (list_empty(&connlist_err)) {
+		spin_unlock_irqrestore(&connlock, flags);
+		return;
+	}
+	list_splice_init(&connlist_err, &recovery_list);
+	spin_unlock_irqrestore(&connlock, flags);
+
+	list_for_each_entry_safe(conn, tmp, &recovery_list, conn_list_err) {
+		uint32_t sid = iscsi_conn_get_sid(conn);
+		struct iscsi_cls_session *session;
+
+		mutex_lock(&rx_queue_mutex);
+
+		session = iscsi_session_lookup(sid);
+		if (session) {
+			if (system_state != SYSTEM_RUNNING) {
+				session->recovery_tmo = 0;
+				conn->transport->stop_conn(conn,
+							   STOP_CONN_TERM);
+			} else {
+				conn->transport->stop_conn(conn,
+							   STOP_CONN_RECOVER);
+			}
+		}
+
+		list_del_init(&conn->conn_list_err);
+
+		mutex_unlock(&rx_queue_mutex);
+
+		/* we don't want to hold rx_queue_mutex for too long,
+		 * for instance if many conns failed at the same time,
+		 * since this stall other iscsi maintenance operations.
+		 * Give other users a chance to proceed.
+		 */
+		cond_resched();
+	}
+}
+
 void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
 {
 	struct nlmsghdr	*nlh;
@@ -2428,6 +2482,12 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
 	struct iscsi_uevent *ev;
 	struct iscsi_internal *priv;
 	int len = nlmsg_total_size(sizeof(*ev));
+	unsigned long flags;
+
+	spin_lock_irqsave(&connlock, flags);
+	list_add(&conn->conn_list_err, &connlist_err);
+	spin_unlock_irqrestore(&connlock, flags);
+	queue_work(system_unbound_wq, &stop_conn_work);
 
 	priv = iscsi_if_transport_lookup(conn->transport);
 	if (!priv)
@@ -2757,11 +2817,19 @@ static int
 iscsi_if_destroy_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev)
 {
 	struct iscsi_cls_conn *conn;
+	unsigned long flags;
 
 	conn = iscsi_conn_lookup(ev->u.d_conn.sid, ev->u.d_conn.cid);
 	if (!conn)
 		return -EINVAL;
 
+	spin_lock_irqsave(&connlock, flags);
+	if (!list_empty(&conn->conn_list_err)) {
+		spin_unlock_irqrestore(&connlock, flags);
+		return -EAGAIN;
+	}
+	spin_unlock_irqrestore(&connlock, flags);
+
 	ISCSI_DBG_TRANS_CONN(conn, "Destroying transport conn\n");
 	if (transport->destroy_conn)
 		transport->destroy_conn(conn);