[PATCH] nvmet: move percpu handling into nvmet_ns_{enable,disable}

[hare at kernel.org]

From: Hannes Reinecke <hare at kernel.org>

The namespace percpu counter protects pending I/O, and we can
only safely diable the namespace once the counter drop to zero.
So we need to init the percpu counter in nvmet_ns_enable(), and
wait for it to drop to zero in nvmet_ns_disable() to avoid having
I/O pending after the namespace has been disabled.

Fixes: 74d16965d7ac ("nvmet-loop: avoid using mutex in IO hotpath")

Signed-off-by: Hannes Reinecke <hare at kernel.org>
---
 drivers/nvme/target/core.c | 44 +++++++++++++++++---------------------
 1 file changed, 20 insertions(+), 24 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 5f7b5d1f78c0..cdf8e16c1c6d 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -611,6 +611,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 			goto out_dev_put;
 	}
 
+	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
+		goto out_pr_exit;
+
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
 	xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED);
@@ -618,6 +621,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
+out_pr_exit:
+	if (ns->pr.enable)
+		nvmet_pr_exit_ns(ns);
 out_dev_put:
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
 		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
@@ -643,6 +649,19 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 
 	mutex_unlock(&subsys->lock);
 
+	/*
+	 * Now that we removed the namespaces from the lookup list, we
+	 * can kill the per_cpu ref and wait for any remaining references
+	 * to be dropped, as well as a RCU grace period for anyone only
+	 * using the namepace under rcu_read_lock().  Note that we can't
+	 * use call_rcu here as we need to ensure the namespaces have
+	 * been fully destroyed before unloading the module.
+	 */
+	percpu_ref_kill(&ns->ref);
+	synchronize_rcu();
+	wait_for_completion(&ns->disable_done);
+	percpu_ref_exit(&ns->ref);
+
 	if (ns->pr.enable)
 		nvmet_pr_exit_ns(ns);
 
@@ -660,25 +679,7 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 	nvmet_ns_disable(ns);
 
 	mutex_lock(&subsys->lock);
-
 	xa_erase(&subsys->namespaces, ns->nsid);
-
-	mutex_unlock(&subsys->lock);
-
-	/*
-	 * Now that we removed the namespaces from the lookup list, we
-	 * can kill the per_cpu ref and wait for any remaining references
-	 * to be dropped, as well as a RCU grace period for anyone only
-	 * using the namepace under rcu_read_lock().  Note that we can't
-	 * use call_rcu here as we need to ensure the namespaces have
-	 * been fully destroyed before unloading the module.
-	 */
-	percpu_ref_kill(&ns->ref);
-	synchronize_rcu();
-	wait_for_completion(&ns->disable_done);
-	percpu_ref_exit(&ns->ref);
-
-	mutex_lock(&subsys->lock);
 	subsys->nr_namespaces--;
 	mutex_unlock(&subsys->lock);
 
@@ -708,11 +709,8 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	ns->nsid = nsid;
 	ns->subsys = subsys;
 
-	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
-		goto out_free;
-
 	if (xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL))
-		goto out_exit;
+		goto out_free;
 
 	subsys->nr_namespaces++;
 
@@ -728,8 +726,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	ns->csi = NVME_CSI_NVM;
 
 	return ns;
-out_exit:
-	percpu_ref_exit(&ns->ref);
 out_free:
 	kfree(ns);
 out_unlock:
-- 
2.35.3