Destroy ib state early during shutdown. Otherwise we can get callbacks
after the QP isn't really able to handle them.

Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchand...@oracle.com>
Signed-off-by: Santosh Shilimkar <ssant...@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilim...@oracle.com>
---
 net/rds/ib_cm.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 0da2a45..8b40d3c 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -639,6 +639,16 @@ void rds_ib_conn_shutdown(struct rds_connection *conn)
                           (atomic_read(&ic->i_signaled_sends) == 0));
                tasklet_kill(&ic->i_recv_tasklet);
 
+               /* first destroy the ib state that generates callbacks */
+               if (ic->i_cm_id->qp)
+                       rdma_destroy_qp(ic->i_cm_id);
+               if (ic->i_send_cq)
+                       ib_destroy_cq(ic->i_send_cq);
+               if (ic->i_recv_cq)
+                       ib_destroy_cq(ic->i_recv_cq);
+               rdma_destroy_id(ic->i_cm_id);
+
+               /* then free the resources that ib callbacks use */
                if (ic->i_send_hdrs)
                        ib_dma_free_coherent(dev,
                                           ic->i_send_ring.w_nr *
@@ -662,14 +672,6 @@ void rds_ib_conn_shutdown(struct rds_connection *conn)
                if (ic->i_recvs)
                        rds_ib_recv_clear_ring(ic);
 
-               if (ic->i_cm_id->qp)
-                       rdma_destroy_qp(ic->i_cm_id);
-               if (ic->i_send_cq)
-                       ib_destroy_cq(ic->i_send_cq);
-               if (ic->i_recv_cq)
-                       ib_destroy_cq(ic->i_recv_cq);
-               rdma_destroy_id(ic->i_cm_id);
-
                /*
                 * Move connection back to the nodev list.
                 */
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to