From 8000d1fdb07e365e6565c2415aefdfed15413794 Mon Sep 17 00:00:00 2001 From: Nitzan Carmi Date: Wed, 17 Jan 2018 11:01:14 +0000 Subject: nvme-rdma: fix sysfs invoked reset_ctrl error flow When reset_controller that is invoked by sysfs fails, it enters an error flow which practically removes the nvme ctrl entirely (similar to delete_ctrl flow). It causes the system to hang, since a sysfs attribute cannot be unregistered by one of its own methods. This can be fixed by calling delete_ctrl as a work rather than sequential code. In addition, it should give the ctrl a chance to recover using reconnection mechanism (consistant with FC reset_ctrl error flow). Also, while we're here, return suitable errno in case the reset ended with non live ctrl. Signed-off-by: Nitzan Carmi Reviewed-by: Max Gurtovoy Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 6 +++++- drivers/nvme/host/rdma.c | 7 ++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 52b3626fb64e..0fe7ea35c221 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -120,8 +120,12 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) int ret; ret = nvme_reset_ctrl(ctrl); - if (!ret) + if (!ret) { flush_work(&ctrl->reset_work); + if (ctrl->state != NVME_CTRL_LIVE) + ret = -ENETRESET; + } + return ret; } EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5e2cc4f0d207..3a51ed50eff2 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1784,11 +1784,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) return; out_fail: - dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl, true); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + ++ctrl->ctrl.nr_reconnects; + nvme_rdma_reconnect_or_remove(ctrl); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { -- cgit v1.2.3-55-g7522