Re: [PATCH 4.4.y] nvme: Fix managing degraded controllers

[Keith Busch <keith.busch@intel.com>]

commit 5bae7f73d378a986 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: <stable@vger.kernel.org> # 4.4.x
Signed-off-by: Keith Busch <keith.busch@intel.com>
---
 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