From mboxrd@z Thu Jan 1 00:00:00 1970 From: sagi@grimberg.me (Sagi Grimberg) Date: Fri, 29 Jul 2016 22:57:20 +0300 Subject: [PATCH 3/5] nvme-rdma: Make sure to shutdown the controller if we can In-Reply-To: <1469822242-3477-1-git-send-email-sagi@grimberg.me> References: <1469822242-3477-1-git-send-email-sagi@grimberg.me> Message-ID: <1469822242-3477-4-git-send-email-sagi@grimberg.me> Relying on ctrl state in nvme_rdma_shutdown_ctrl is wrong because it will never be NVME_CTRL_LIVE (delete_ctrl or reset_ctrl invoked it). Instead, check that the admin queue is connected. Note that it is safe because we can never see a copmeting thread trying to destroy the admin queue (reset or delete controller). Signed-off-by: Sagi Grimberg --- drivers/nvme/host/rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index a70eb3cbf656..641ab7f91899 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1644,7 +1644,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_free_io_queues(ctrl); } - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags)) nvme_shutdown_ctrl(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); -- 1.9.1