From: Hannes Reinecke <hare@suse.de>
Date: Fri, 16 Jul 2021 13:30:35 +0200
Subject: nvme: fix refcounting imbalance when all paths are down
Patch-mainline: v5.14-rc3
Git-commit: 5396fdac56d87d04e75e5068c0c92d33625f51e7
References: bsc#1188067

When the last path to a ns_head drops the current code
removes the ns_head from the subsystem list, but will only
delete the disk itself if the last reference to the ns_head
drops. This is causing an refcounting imbalance eg when
applications have a reference to the disk, as then they'll
never get notified that the disk is in fact dead.
This patch moves the call 'del_gendisk' into nvme_mpath_check_last_path(),
ensuring that the disk can be properly removed and applications get the
appropriate notifications.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/core.c      |   14 +++++++++++---
 drivers/nvme/host/multipath.c |    9 ++++++++-
 drivers/nvme/host/nvme.h      |   10 ++--------
 3 files changed, 21 insertions(+), 12 deletions(-)

--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3760,6 +3760,8 @@ static void nvme_alloc_ns(struct nvme_ct
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
+	bool last_path = false;
+
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
@@ -3767,8 +3769,6 @@ static void nvme_ns_remove(struct nvme_n
 
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
-	if (list_empty(&ns->head->list))
-		list_del_init(&ns->head->entry);
 	mutex_unlock(&ns->ctrl->subsys->lock);
 
 	synchronize_rcu(); /* guarantee not available in head->list */
@@ -3786,7 +3786,15 @@ static void nvme_ns_remove(struct nvme_n
 	list_del_init(&ns->list);
 	up_write(&ns->ctrl->namespaces_rwsem);
 
-	nvme_mpath_check_last_path(ns);
+	/* Synchronize with nvme_init_ns_head() */
+	mutex_lock(&ns->head->subsys->lock);
+	if (list_empty(&ns->head->list)) {
+		list_del_init(&ns->head->entry);
+		last_path = true;
+	}
+	mutex_unlock(&ns->head->subsys->lock);
+	if (last_path)
+		nvme_mpath_shutdown_disk(ns->head);
 	nvme_put_ns(ns);
 }
 
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -716,12 +716,19 @@ void nvme_mpath_add_disk(struct nvme_ns
 	}
 }
 
-void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
+	kblockd_schedule_work(&head->requeue_work);
 	if (head->disk->flags & GENHD_FL_UP)
 		del_gendisk(head->disk);
+}
+
+void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+{
+	if (!head->disk)
+		return;
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -608,13 +608,7 @@ bool nvme_mpath_clear_current_path(struc
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
-{
-	struct nvme_ns_head *head = ns->head;
-
-	if (head->disk && list_empty(&head->list))
-		kblockd_schedule_work(&head->requeue_work);
-}
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
 
 static inline void nvme_trace_bio_complete(struct request *req,
         blk_status_t status)
@@ -681,7 +675,7 @@ static inline bool nvme_mpath_clear_curr
 static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 }
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
+static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 }
 static inline void nvme_trace_bio_complete(struct request *req,