From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga07.intel.com ([134.134.136.100]:56291 "EHLO mga07.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752724AbeBIVfV (ORCPT ); Fri, 9 Feb 2018 16:35:21 -0500 From: Keith Busch To: Linux NVMe , Greg Kroah-Hartman Cc: Keith Busch , stable@vger.kernel.org Subject: [PATCH 4.4.y] nvme: Fix managing degraded controllers Date: Fri, 9 Feb 2018 14:39:22 -0700 Message-Id: <20180209213922.12644-1-keith.busch@intel.com> Sender: stable-owner@vger.kernel.org List-ID: commit 3e1e21c7bfcf upstream Upstream is a near rewrite of the async nvme probe that ultimately didn't even cleanly merge in 4.5. This patch is a much smaller change targeted to the regression introduced in 4.4. If a controller is in a degraded mode that needs admin assistence to recover, we need to leave the controller running. We just want to disable namespace access without shuting the controller down. Fixes: 3cf519b5a8d4("nvme: merge nvme_dev_start, nvme_dev_resume and nvme_async_probe") Cc: # 4.4.x Signed-off-by: Keith Busch --- drivers/nvme/host/pci.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d6ceb8b91cd6..1c8aedf21370 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2976,10 +2976,16 @@ static void nvme_dev_shutdown(struct nvme_dev *dev) mutex_unlock(&dev->shutdown_lock); } -static void nvme_dev_remove(struct nvme_dev *dev) +static void nvme_remove_namespaces(struct nvme_dev *dev) { struct nvme_ns *ns, *next; + list_for_each_entry_safe(ns, next, &dev->namespaces, list) + nvme_ns_remove(ns); +} + +static void nvme_dev_remove(struct nvme_dev *dev) +{ if (nvme_io_incapable(dev)) { /* * If the device is not capable of IO (surprise hot-removal, @@ -2989,8 +2995,7 @@ static void nvme_dev_remove(struct nvme_dev *dev) */ nvme_dev_shutdown(dev); } - list_for_each_entry_safe(ns, next, &dev->namespaces, list) - nvme_ns_remove(ns); + nvme_remove_namespaces(dev); } static int nvme_setup_prp_pools(struct nvme_dev *dev) @@ -3174,7 +3179,7 @@ static void nvme_probe_work(struct work_struct *work) */ if (dev->online_queues < 2) { dev_warn(dev->dev, "IO queues not created\n"); - nvme_dev_remove(dev); + nvme_remove_namespaces(dev); } else { nvme_unfreeze_queues(dev); nvme_dev_add(dev); -- 2.13.6