[PATCH 1/2] infiniband: force disconnect if DREP and DREQ fail

[Ammar Ratnani]

When we call `rdma_disconnect`, it's possible that we fail to send both
a DREQ and a DREP. In that case, we currently either do nothing or move
into the `IB_CM_TIMEWAIT` state. Either way, we remain in the
`RDMA_CM_CONNECT` state. Anyone waiting for us to disconnect hangs.

Instead, while we're connected, when we call `rdma_disconnect`, and fail
to send both a DREQ and a DREP, mark the connection as disconnected.
Call the upper layer's handler for the disconnect, and destroy the
connection if instructed.

Cc: Leon Romanovsky <leon@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Namjae Jeon <linkinjeon@xxxxxxxxxx>
Cc: Paulo Alcantara <pc@xxxxxxxxxxxxx>
Cc: Stefan Metzmacher <metze@xxxxxxxxx>
Cc: Tom Talpey <tom@xxxxxxxxxx>
Cc: linux-rdma@xxxxxxxxxxxxxxx
Cc: linux-cifs@xxxxxxxxxxxxxxx
Cc: samba-technical@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Ammar Ratnani <ammrat13@xxxxxxxxx>
---
 drivers/infiniband/core/cma.c | 39 +++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 73170b15fc3d..1f1a8b4e160a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4823,6 +4823,34 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 }
 EXPORT_SYMBOL(rdma_reject);
 
+/*
+ * Called from rdma_disconnect() when we know we're not receiving a callback.
+ * Emulate what that callback (in cma_ib_handler()) would have done.
+ *
+ * NOTE: Despite the name, this function will only actually disconnect when
+ * we're in the RDMA_CM_CONNECT state. Else, it does nothing.
+ */
+static int cma_force_disconnect(struct rdma_id_private *id_priv)
+{
+	struct cma_work *work;
+
+	work = kzalloc_obj(*work);
+	if (!work)
+		return -ENOMEM;
+
+	INIT_WORK(&work->work, cma_work_handler);
+	work->old_state = RDMA_CM_CONNECT;
+	work->new_state = RDMA_CM_DISCONNECT;
+	work->event.event = RDMA_CM_EVENT_DISCONNECTED;
+	work->event.status = -ECONNABORTED;
+
+	cma_id_get(id_priv);
+	work->id = id_priv;
+
+	queue_work(cma_wq, &work->work);
+	return 0;
+}
+
 int rdma_disconnect(struct rdma_cm_id *id)
 {
 	struct rdma_id_private *id_priv;
@@ -4838,12 +4866,15 @@ int rdma_disconnect(struct rdma_cm_id *id)
 			goto out;
 		/* Initiate or respond to a disconnect. */
 		trace_cm_disconnect(id_priv);
-		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) {
-			if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0))
-				trace_cm_sent_drep(id_priv);
-		} else {
+		if (!ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) {
 			trace_cm_sent_dreq(id_priv);
+			goto out;
+		}
+		if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) {
+			trace_cm_sent_drep(id_priv);
+			goto out;
 		}
+		ret = cma_force_disconnect(id_priv);
 	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
 	} else
-- 
2.55.0