[PATCHv8] nvme: fix refcounting imbalance when all paths are down

[Hannes Reinecke]

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 at suse.de>
Reviewed-by: Keith Busch <kbusch at kernel.org>
---
Changes to v8:
- Rebase to 5.14
- Rename nvme_mpath_check_last_path() to nvme_mpath_shutdown_disk()
Changes to v7:
- Move the list_del() call outside of nvme_mpath_check_last_path()
Changes to v6:
- Move the list_del() into nvme_mpath_check_last_path()
- Drop the tests for GENHD_FL_UP
Changes to v5:
- Synchronize between nvme_init_ns_head() and nvme_mpath_check_last_path()
- Check for removed gendisk in nvme_ns_head_submit_bio()
Changes to v4:
- Call del_gendisk() in nvme_mpath_check_last_path() to avoid deadlock
Changes to v3:
- Simplify if() clause to detect duplicate namespaces
Changes to v2:
- Drop memcpy() statement
Changes to v1:
- Always check NSIDs after reattach

 drivers/nvme/host/core.c      | 14 +++++++++++---
 drivers/nvme/host/multipath.c |  9 ++++++++-
 drivers/nvme/host/nvme.h      | 11 ++---------
 3 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 11779be42186..17c05a4595f0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3807,6 +3807,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
+	bool last_path = false;
+
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
@@ -3815,8 +3817,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	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 */
@@ -3836,7 +3836,15 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	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);
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0ea5298469c3..3f32c5e86bfc 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -760,14 +760,21 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 #endif
 }
 
-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) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		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);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 18ef8dd03a90..5cd1fa3b8464 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -716,14 +716,7 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-
-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)
 {
@@ -772,7 +765,7 @@ static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
 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)
-- 
2.29.2