NVMe: Fix namespace removal deadlock

This patch makes nvme namespace removal lockless. It is up to the caller
to ensure no active namespace scanning is occuring. To ensure no scan
work occurs, the nvme pci driver adds a removing state to the controller
device to avoid queueing scan work during removal. The work is flushed
after setting the state, so no new scan work can be queued.

The lockless removal allows the driver to cleanup a namespace
request_queue if the controller fails during removal. Previously this
could deadlock trying to acquire the namespace mutex in order to handle
such events.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 7 insertions, 5 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 6c39dbf0290f..8c2ddd5025ab 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1186,11 +1186,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
-	bool kill = nvme_io_incapable(ns->ctrl) &&
-			!blk_queue_dying(ns->queue);
+	bool kill;
 
-	lockdep_assert_held(&ns->ctrl->namespaces_mutex);
+	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
+		return;
 
+	kill = nvme_io_incapable(ns->ctrl) &&
+			!blk_queue_dying(ns->queue);
 	if (kill) {
 		blk_set_queue_dying(ns->queue);
 
@@ -1213,7 +1215,9 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
+	mutex_lock(&ns->ctrl->namespaces_mutex);
 	list_del_init(&ns->list);
+	mutex_unlock(&ns->ctrl->namespaces_mutex);
 	nvme_put_ns(ns);
 }
 
@@ -1307,10 +1311,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns, *next;
 
-	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
 		nvme_ns_remove(ns);
-	mutex_unlock(&ctrl->namespaces_mutex);
 }
 
 static DEFINE_IDA(nvme_instance_ida);