nvme: avoid race in shutdown namespace removal

When we remove the siblings entry, we update ns->head->list, hence we
can't separate the removal and test for being empty. They have to be
in the same critical section to avoid a race.

To avoid breaking the refcounting imbalance again, add a list empty
check to nvme_find_ns_head.

Fixes: 5396fdac56d8 ("nvme: fix refcounting imbalance when all paths are down")
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7efb31b87f37aa756124d52606d270a76f905ad2..97f8211cf92c1a261ae6490382c0eebfa5fa5d56 100644 (file)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3524,7 +3524,9 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
        lockdep_assert_held(&subsys->lock);
 
        list_for_each_entry(h, &subsys->nsheads, entry) {
-               if (h->ns_id == nsid && nvme_tryget_ns_head(h))
+               if (h->ns_id != nsid)
+                       continue;
+               if (!list_empty(&h->list) && nvme_tryget_ns_head(h))
                        return h;
        }
 
@@ -3843,6 +3845,10 @@ 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);
+               last_path = true;
+       }
        mutex_unlock(&ns->ctrl->subsys->lock);
 
        /* guarantee not available in head->list */
@@ -3863,13 +3869,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
        list_del_init(&ns->list);
        up_write(&ns->ctrl->namespaces_rwsem);
 
-       /* 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);