nvme-rdma: destroy nvme queue rdma resources on connect failure
authorSteve Wise <swise@opengridcomputing.com>
Fri, 2 Sep 2016 16:01:27 +0000 (09:01 -0700)
committerSagi Grimberg <sagi@grimberg.me>
Sun, 4 Sep 2016 07:00:54 +0000 (10:00 +0300)
commitf361e5a01ed35c0f9a00816d76a910d8a5cb4547
treee5365a13f3c2f56b18d1727d6adc72c29834d0e9
parentcdbecc8d24b642b67ae79a0acc2ff18d3d0e677e
nvme-rdma: destroy nvme queue rdma resources on connect failure

After address resolution, the nvme_rdma_queue rdma resources are
allocated.  If rdma route resolution or the connect fails, or the
controller reconnect times out and gives up, then the rdma resources
need to be freed.  Otherwise, rdma resources are leaked.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimbrg.me>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
drivers/nvme/host/rdma.c