summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
authorAnton Eidelman <anton@lightbitslabs.com>2019-06-20 08:48:10 +0200
committerChristoph Hellwig <hch@lst.de>2019-06-21 11:08:38 +0200
commit2181e455612a8db2761eabbf126640552a451e96 (patch)
tree3c3e8132083043b5a220b0ad6b96b4b50dfccc7b /drivers/nvme
parent4bea364f161810523032f37a8ae0b7d92cf28eea (diff)
nvme: fix possible io failures when removing multipathed ns
When a shared namespace is removed, we call blk_cleanup_queue() when the device can still be accessed as the current path and this can result in submission to a dying queue. Hence, direct_make_request() called by our mpath device may fail (propagating the failure to userspace). Instead, we want to failover this I/O to a different path if one exists. Thus, before we cleanup the request queue, we make sure that the device is cleared from the current path nor it can be selected again as such. Fix this by: - clear the ns from the head->list and synchronize rcu to make sure there is no concurrent path search that restores it as the current path - clear the mpath current path in order to trigger a subsequent path search and sync srcu to wait for any ongoing request submissions - safely continue to namespace removal and blk_cleanup_queue Signed-off-by: Anton Eidelman <anton@lightbitslabs.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c14
1 files changed, 8 insertions, 6 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 120fb593d1da..22c68e3b71d5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3344,6 +3344,14 @@ static void nvme_ns_remove(struct nvme_ns *ns)
return;
nvme_fault_inject_fini(ns);
+
+ mutex_lock(&ns->ctrl->subsys->lock);
+ list_del_rcu(&ns->siblings);
+ mutex_unlock(&ns->ctrl->subsys->lock);
+ synchronize_rcu(); /* guarantee not available in head->list */
+ nvme_mpath_clear_current_path(ns);
+ synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
+
if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
del_gendisk(ns->disk);
blk_cleanup_queue(ns->queue);
@@ -3351,16 +3359,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
blk_integrity_unregister(ns->disk);
}
- mutex_lock(&ns->ctrl->subsys->lock);
- list_del_rcu(&ns->siblings);
- nvme_mpath_clear_current_path(ns);
- mutex_unlock(&ns->ctrl->subsys->lock);
-
down_write(&ns->ctrl->namespaces_rwsem);
list_del_init(&ns->list);
up_write(&ns->ctrl->namespaces_rwsem);
- synchronize_srcu(&ns->head->srcu);
nvme_mpath_check_last_path(ns);
nvme_put_ns(ns);
}